diff options
| author | Jani Nikula <jani.nikula@intel.com> | 2023-01-02 10:31:03 +0100 |
|---|---|---|
| committer | Jani Nikula <jani.nikula@intel.com> | 2023-01-02 10:31:03 +0100 |
| commit | 0d8eae7b124e2ddaee00f186fe922450faad0ed7 (patch) | |
| tree | 5acf7a7a4300665c26b128d9afd1843b402e8b8e /drivers/gpu/drm | |
| parent | drm/i915/mtl: Add support of Tile4 to MTL (diff) | |
| parent | Linux 6.2-rc1 (diff) | |
| download | linux-0d8eae7b124e2ddaee00f186fe922450faad0ed7.tar.xz linux-0d8eae7b124e2ddaee00f186fe922450faad0ed7.zip | |
Merge drm/drm-next into drm-intel-next
Sync up with v6.2-rc1.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Diffstat (limited to 'drivers/gpu/drm')
614 files changed, 13435 insertions, 5540 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 34f5a092c99e..315cbdf61979 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -8,7 +8,6 @@ menuconfig DRM tristate "Direct Rendering Manager (XFree86 4.1.0 and higher DRI support)" depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && HAS_DMA - select DRM_NOMODESET select DRM_PANEL_ORIENTATION_QUIRKS select HDMI select FB_CMDLINE @@ -19,6 +18,7 @@ menuconfig DRM # gallium uses SYS_kcmp for os_same_file_description() to de-duplicate # device and dmabuf fd. Let's make sure that is available for our userspace. select KCMP + select VIDEO_NOMODESET help Kernel-level support for the Direct Rendering Infrastructure (DRI) introduced in XFree86 4.0. If you say Y here, you need to select @@ -233,64 +233,8 @@ source "drivers/gpu/drm/i2c/Kconfig" source "drivers/gpu/drm/arm/Kconfig" -config DRM_RADEON - tristate "ATI Radeon" - depends on DRM && PCI && MMU - depends on AGP || !AGP - select FW_LOADER - select DRM_DISPLAY_DP_HELPER - select DRM_DISPLAY_HELPER - select DRM_KMS_HELPER - select DRM_TTM - select DRM_TTM_HELPER - select POWER_SUPPLY - select HWMON - select BACKLIGHT_CLASS_DEVICE - select INTERVAL_TREE - # radeon depends on ACPI_VIDEO when ACPI is enabled, for select to work - # ACPI_VIDEO's dependencies must also be selected. - select INPUT if ACPI - select ACPI_VIDEO if ACPI - # On x86 ACPI_VIDEO also needs ACPI_WMI - select X86_PLATFORM_DEVICES if ACPI && X86 - select ACPI_WMI if ACPI && X86 - help - Choose this option if you have an ATI Radeon graphics card. There - are both PCI and AGP versions. You don't need to choose this to - run the Radeon in plain VGA mode. - - If M is selected, the module will be called radeon. - source "drivers/gpu/drm/radeon/Kconfig" -config DRM_AMDGPU - tristate "AMD GPU" - depends on DRM && PCI && MMU - select FW_LOADER - select DRM_DISPLAY_DP_HELPER - select DRM_DISPLAY_HDMI_HELPER - select DRM_DISPLAY_HELPER - select DRM_KMS_HELPER - select DRM_SCHED - select DRM_TTM - select DRM_TTM_HELPER - select POWER_SUPPLY - select HWMON - select BACKLIGHT_CLASS_DEVICE - select INTERVAL_TREE - select DRM_BUDDY - # amdgpu depends on ACPI_VIDEO when ACPI is enabled, for select to work - # ACPI_VIDEO's dependencies must also be selected. - select INPUT if ACPI - select ACPI_VIDEO if ACPI - # On x86 ACPI_VIDEO also needs ACPI_WMI - select X86_PLATFORM_DEVICES if ACPI && X86 - select ACPI_WMI if ACPI && X86 - help - Choose this option if you have a recent AMD Radeon graphics card. - - If M is selected, the module will be called amdgpu. - source "drivers/gpu/drm/amd/amdgpu/Kconfig" source "drivers/gpu/drm/nouveau/Kconfig" @@ -514,11 +458,6 @@ config DRM_EXPORT_FOR_TESTS config DRM_PANEL_ORIENTATION_QUIRKS tristate -# Separate option because nomodeset parameter is global and expected built-in -config DRM_NOMODESET - bool - default n - config DRM_LIB_RANDOM bool default n diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 6e55c47288e4..cc637343d87b 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -70,9 +70,9 @@ drm-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o drm-$(CONFIG_DRM_PRIVACY_SCREEN) += \ drm_privacy_screen.o \ drm_privacy_screen_x86.o +drm-$(CONFIG_DRM_ACCEL) += ../../accel/drm_accel.o obj-$(CONFIG_DRM) += drm.o -obj-$(CONFIG_DRM_NOMODESET) += drm_nomodeset.o obj-$(CONFIG_DRM_PANEL_ORIENTATION_QUIRKS) += drm_panel_orientation_quirks.o # @@ -117,7 +117,9 @@ drm_kms_helper-y := \ drm_self_refresh_helper.o \ drm_simple_kms_helper.o drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o -drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o +drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += \ + drm_fbdev_generic.o \ + drm_fb_helper.o obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o # diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig index 7777d55275de..5fcd510f1abb 100644 --- a/drivers/gpu/drm/amd/amdgpu/Kconfig +++ b/drivers/gpu/drm/amd/amdgpu/Kconfig @@ -1,4 +1,33 @@ # SPDX-License-Identifier: MIT + +config DRM_AMDGPU + tristate "AMD GPU" + depends on DRM && PCI && MMU + select FW_LOADER + select DRM_DISPLAY_DP_HELPER + select DRM_DISPLAY_HDMI_HELPER + select DRM_DISPLAY_HELPER + select DRM_KMS_HELPER + select DRM_SCHED + select DRM_TTM + select DRM_TTM_HELPER + select POWER_SUPPLY + select HWMON + select BACKLIGHT_CLASS_DEVICE + select INTERVAL_TREE + select DRM_BUDDY + # amdgpu depends on ACPI_VIDEO when ACPI is enabled, for select to work + # ACPI_VIDEO's dependencies must also be selected. + select INPUT if ACPI + select ACPI_VIDEO if ACPI + # On x86 ACPI_VIDEO also needs ACPI_WMI + select X86_PLATFORM_DEVICES if ACPI && X86 + select ACPI_WMI if ACPI && X86 + help + Choose this option if you have a recent AMD Radeon graphics card. + + If M is selected, the module will be called amdgpu. + config DRM_AMDGPU_SI bool "Enable amdgpu support for SI parts" depends on DRM_AMDGPU diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 6ad39cf71bdd..798d0e9a60b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -58,7 +58,8 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \ amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o amdgpu_nbio.o \ amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \ amdgpu_fw_attestation.o amdgpu_securedisplay.o \ - amdgpu_eeprom.o amdgpu_mca.o amdgpu_psp_ta.o amdgpu_lsdma.o + amdgpu_eeprom.o amdgpu_mca.o amdgpu_psp_ta.o amdgpu_lsdma.o \ + amdgpu_ring_mux.o amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o @@ -250,7 +251,7 @@ endif amdgpu-$(CONFIG_COMPAT) += amdgpu_ioc32.o amdgpu-$(CONFIG_VGA_SWITCHEROO) += amdgpu_atpx_handler.o amdgpu-$(CONFIG_ACPI) += amdgpu_acpi.o -amdgpu-$(CONFIG_HMM_MIRROR) += amdgpu_mn.o +amdgpu-$(CONFIG_HMM_MIRROR) += amdgpu_hmm.o include $(FULL_AMD_PATH)/pm/Makefile diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 9999c18e7d8e..6b74df446694 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -82,7 +82,6 @@ #include "amdgpu_vce.h" #include "amdgpu_vcn.h" #include "amdgpu_jpeg.h" -#include "amdgpu_mn.h" #include "amdgpu_gmc.h" #include "amdgpu_gfx.h" #include "amdgpu_sdma.h" @@ -1065,6 +1064,7 @@ struct amdgpu_device { struct work_struct reset_work; bool job_hang; + bool dc_enabled; }; static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev) @@ -1122,6 +1122,8 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev, bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type); bool amdgpu_device_has_dc_support(struct amdgpu_device *adev); +void amdgpu_device_set_sriov_virtual_display(struct amdgpu_device *adev); + int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, struct amdgpu_reset_context *reset_context); @@ -1295,6 +1297,7 @@ void amdgpu_device_pcie_port_wreg(struct amdgpu_device *adev, u32 reg, u32 v); struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev, struct dma_fence *gang); +bool amdgpu_device_has_display_hardware(struct amdgpu_device *adev); /* atpx handler */ #if defined(CONFIG_VGA_SWITCHEROO) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index b14800ac179e..57b5e11446c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -847,7 +847,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev) struct amdgpu_atif *atif = &amdgpu_acpi_priv.atif; if (atif->notifications.brightness_change) { - if (amdgpu_device_has_dc_support(adev)) { + if (adev->dc_enabled) { #if defined(CONFIG_DRM_AMD_DC) struct amdgpu_display_manager *dm = &adev->dm; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 8816853e50c0..f99d4873bf22 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -673,7 +673,7 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev, goto err; } - ret = amdgpu_job_alloc(adev, 1, &job, NULL); + ret = amdgpu_job_alloc(adev, NULL, NULL, NULL, 1, &job); if (ret) goto err; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index f50e3ba4d7a5..0040deaf8a83 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -29,6 +29,7 @@ #include <linux/mm.h> #include <linux/kthread.h> #include <linux/workqueue.h> +#include <linux/mmu_notifier.h> #include <kgd_kfd_interface.h> #include <drm/ttm/ttm_execbuf_util.h> #include "amdgpu_sync.h" @@ -65,6 +66,7 @@ struct kgd_mem { struct mutex lock; struct amdgpu_bo *bo; struct dma_buf *dmabuf; + struct hmm_range *range; struct list_head attachments; /* protected by amdkfd_process_info.lock */ struct ttm_validate_buffer validate_list; @@ -75,7 +77,7 @@ struct kgd_mem { uint32_t alloc_flags; - atomic_t invalid; + uint32_t invalid; struct amdkfd_process_info *process_info; struct amdgpu_sync sync; @@ -131,7 +133,8 @@ struct amdkfd_process_info { struct amdgpu_amdkfd_fence *eviction_fence; /* MMU-notifier related fields */ - atomic_t evicted_bos; + struct mutex notifier_lock; + uint32_t evicted_bos; struct delayed_work restore_userptr_work; struct pid *pid; bool block_mmu_notifications; @@ -180,7 +183,8 @@ int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data); bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm); struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f); int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo); -int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm); +int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni, + unsigned long cur_seq, struct kgd_mem *mem); #else static inline bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm) @@ -201,7 +205,8 @@ int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo) } static inline -int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm) +int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni, + unsigned long cur_seq, struct kgd_mem *mem) { return 0; } @@ -265,8 +270,10 @@ int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_ (&((struct amdgpu_fpriv *) \ ((struct drm_file *)(drm_priv))->driver_priv)->vm) +int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev, + struct file *filp, u32 pasid); int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, - struct file *filp, u32 pasid, + struct file *filp, void **process_info, struct dma_fence **ef); void amdgpu_amdkfd_gpuvm_release_process_vm(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c index c8935d718207..4485bb29bec9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c @@ -41,5 +41,6 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = { .get_atc_vmid_pasid_mapping_info = kgd_gfx_v9_get_atc_vmid_pasid_mapping_info, .set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base, + .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index ba72a910d0d5..b15091d8310d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -29,6 +29,7 @@ #include "amdgpu_object.h" #include "amdgpu_gem.h" #include "amdgpu_vm.h" +#include "amdgpu_hmm.h" #include "amdgpu_amdkfd.h" #include "amdgpu_dma_buf.h" #include <uapi/linux/kfd_ioctl.h> @@ -171,9 +172,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > kfd_mem_limit.max_ttm_mem_limit) || (adev && adev->kfd.vram_used + vram_needed > - adev->gmc.real_vram_size - - atomic64_read(&adev->vram_pin_size) - - reserved_for_pt)) { + adev->gmc.real_vram_size - reserved_for_pt)) { ret = -ENOMEM; goto release; } @@ -405,63 +404,15 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync) static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem) { - struct amdgpu_device *bo_adev = amdgpu_ttm_adev(mem->bo->tbo.bdev); - bool coherent = mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_COHERENT; - bool uncached = mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED; - uint32_t mapping_flags; - uint64_t pte_flags; - bool snoop = false; + uint32_t mapping_flags = AMDGPU_VM_PAGE_READABLE | + AMDGPU_VM_MTYPE_DEFAULT; - mapping_flags = AMDGPU_VM_PAGE_READABLE; if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE) mapping_flags |= AMDGPU_VM_PAGE_WRITEABLE; if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE) mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE; - switch (adev->ip_versions[GC_HWIP][0]) { - case IP_VERSION(9, 4, 1): - case IP_VERSION(9, 4, 2): - if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { - if (bo_adev == adev) { - if (uncached) - mapping_flags |= AMDGPU_VM_MTYPE_UC; - else if (coherent) - mapping_flags |= AMDGPU_VM_MTYPE_CC; - else - mapping_flags |= AMDGPU_VM_MTYPE_RW; - if ((adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2)) && - adev->gmc.xgmi.connected_to_cpu) - snoop = true; - } else { - if (uncached || coherent) - mapping_flags |= AMDGPU_VM_MTYPE_UC; - else - mapping_flags |= AMDGPU_VM_MTYPE_NC; - if (amdgpu_xgmi_same_hive(adev, bo_adev)) - snoop = true; - } - } else { - if (uncached || coherent) - mapping_flags |= AMDGPU_VM_MTYPE_UC; - else - mapping_flags |= AMDGPU_VM_MTYPE_NC; - snoop = true; - } - break; - default: - if (uncached || coherent) - mapping_flags |= AMDGPU_VM_MTYPE_UC; - else - mapping_flags |= AMDGPU_VM_MTYPE_NC; - - if (!(mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)) - snoop = true; - } - - pte_flags = amdgpu_gem_va_map_flags(adev, mapping_flags); - pte_flags |= snoop ? AMDGPU_PTE_SNOOPED : 0; - - return pte_flags; + return amdgpu_gem_va_map_flags(adev, mapping_flags); } /** @@ -988,6 +939,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, struct amdkfd_process_info *process_info = mem->process_info; struct amdgpu_bo *bo = mem->bo; struct ttm_operation_ctx ctx = { true, false }; + struct hmm_range *range; int ret = 0; mutex_lock(&process_info->lock); @@ -998,7 +950,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, goto out; } - ret = amdgpu_mn_register(bo, user_addr); + ret = amdgpu_hmm_register(bo, user_addr); if (ret) { pr_err("%s: Failed to register MMU notifier: %d\n", __func__, ret); @@ -1012,12 +964,14 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, * later stage when it is scheduled by another ioctl called by * CRIU master process for the target pid for restore. */ - atomic_inc(&mem->invalid); + mutex_lock(&process_info->notifier_lock); + mem->invalid++; + mutex_unlock(&process_info->notifier_lock); mutex_unlock(&process_info->lock); return 0; } - ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, &range); if (ret) { pr_err("%s: Failed to get user pages: %d\n", __func__, ret); goto unregister_out; @@ -1035,10 +989,10 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, amdgpu_bo_unreserve(bo); release_out: - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range); unregister_out: if (ret) - amdgpu_mn_unregister(bo); + amdgpu_hmm_unregister(bo); out: mutex_unlock(&process_info->lock); return ret; @@ -1349,6 +1303,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, return -ENOMEM; mutex_init(&info->lock); + mutex_init(&info->notifier_lock); INIT_LIST_HEAD(&info->vm_list_head); INIT_LIST_HEAD(&info->kfd_bo_list); INIT_LIST_HEAD(&info->userptr_valid_list); @@ -1365,7 +1320,6 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, } info->pid = get_task_pid(current->group_leader, PIDTYPE_PID); - atomic_set(&info->evicted_bos, 0); INIT_DELAYED_WORK(&info->restore_userptr_work, amdgpu_amdkfd_restore_userptr_worker); @@ -1420,6 +1374,7 @@ reserve_pd_fail: put_pid(info->pid); create_evict_fence_fail: mutex_destroy(&info->lock); + mutex_destroy(&info->notifier_lock); kfree(info); } return ret; @@ -1474,10 +1429,9 @@ static void amdgpu_amdkfd_gpuvm_unpin_bo(struct amdgpu_bo *bo) amdgpu_bo_unreserve(bo); } -int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, - struct file *filp, u32 pasid, - void **process_info, - struct dma_fence **ef) +int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev, + struct file *filp, u32 pasid) + { struct amdgpu_fpriv *drv_priv; struct amdgpu_vm *avm; @@ -1488,10 +1442,6 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, return ret; avm = &drv_priv->vm; - /* Already a compute VM? */ - if (avm->process_info) - return -EINVAL; - /* Free the original amdgpu allocated pasid, * will be replaced with kfd allocated pasid. */ @@ -1500,14 +1450,36 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, amdgpu_vm_set_pasid(adev, avm, 0); } - /* Convert VM into a compute VM */ - ret = amdgpu_vm_make_compute(adev, avm); + ret = amdgpu_vm_set_pasid(adev, avm, pasid); if (ret) return ret; - ret = amdgpu_vm_set_pasid(adev, avm, pasid); + return 0; +} + +int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, + struct file *filp, + void **process_info, + struct dma_fence **ef) +{ + struct amdgpu_fpriv *drv_priv; + struct amdgpu_vm *avm; + int ret; + + ret = amdgpu_file_to_fpriv(filp, &drv_priv); if (ret) return ret; + avm = &drv_priv->vm; + + /* Already a compute VM? */ + if (avm->process_info) + return -EINVAL; + + /* Convert VM into a compute VM */ + ret = amdgpu_vm_make_compute(adev, avm); + if (ret) + return ret; + /* Initialize KFD part of the VM and process info */ ret = init_kfd_vm(avm, process_info, ef); if (ret) @@ -1544,6 +1516,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, cancel_delayed_work_sync(&process_info->restore_userptr_work); put_pid(process_info->pid); mutex_destroy(&process_info->lock); + mutex_destroy(&process_info->notifier_lock); kfree(process_info); } } @@ -1596,7 +1569,9 @@ int amdgpu_amdkfd_criu_resume(void *p) mutex_lock(&pinfo->lock); pr_debug("scheduling work\n"); - atomic_inc(&pinfo->evicted_bos); + mutex_lock(&pinfo->notifier_lock); + pinfo->evicted_bos++; + mutex_unlock(&pinfo->notifier_lock); if (!READ_ONCE(pinfo->block_mmu_notifications)) { ret = -EINVAL; goto out_unlock; @@ -1673,6 +1648,11 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( } } + if (flags & KFD_IOC_ALLOC_MEM_FLAGS_COHERENT) + alloc_flags |= AMDGPU_GEM_CREATE_COHERENT; + if (flags & KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED) + alloc_flags |= AMDGPU_GEM_CREATE_UNCACHED; + *mem = kzalloc(sizeof(struct kgd_mem), GFP_KERNEL); if (!*mem) { ret = -ENOMEM; @@ -1816,8 +1796,13 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( list_del(&bo_list_entry->head); mutex_unlock(&process_info->lock); - /* No more MMU notifiers */ - amdgpu_mn_unregister(mem->bo); + /* Cleanup user pages and MMU notifiers */ + if (amdgpu_ttm_tt_get_usermm(mem->bo->tbo.ttm)) { + amdgpu_hmm_unregister(mem->bo); + mutex_lock(&process_info->notifier_lock); + amdgpu_ttm_tt_discard_user_pages(mem->bo->tbo.ttm, mem->range); + mutex_unlock(&process_info->notifier_lock); + } ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx); if (unlikely(ret)) @@ -1907,6 +1892,16 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( */ mutex_lock(&mem->process_info->lock); + /* Lock notifier lock. If we find an invalid userptr BO, we can be + * sure that the MMU notifier is no longer running + * concurrently and the queues are actually stopped + */ + if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) { + mutex_lock(&mem->process_info->notifier_lock); + is_invalid_userptr = !!mem->invalid; + mutex_unlock(&mem->process_info->notifier_lock); + } + mutex_lock(&mem->lock); domain = mem->domain; @@ -2247,7 +2242,7 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev, ret = drm_vma_node_allow(&obj->vma_node, drm_priv); if (ret) { - kfree(mem); + kfree(*mem); return ret; } @@ -2284,34 +2279,38 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev, * * Runs in MMU notifier, may be in RECLAIM_FS context. This means it * cannot do any memory allocations, and cannot take any locks that - * are held elsewhere while allocating memory. Therefore this is as - * simple as possible, using atomic counters. + * are held elsewhere while allocating memory. * * It doesn't do anything to the BO itself. The real work happens in * restore, where we get updated page addresses. This function only * ensures that GPU access to the BO is stopped. */ -int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, - struct mm_struct *mm) +int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni, + unsigned long cur_seq, struct kgd_mem *mem) { struct amdkfd_process_info *process_info = mem->process_info; - int evicted_bos; int r = 0; - /* Do not process MMU notifications until stage-4 IOCTL is received */ + /* Do not process MMU notifications during CRIU restore until + * KFD_CRIU_OP_RESUME IOCTL is received + */ if (READ_ONCE(process_info->block_mmu_notifications)) return 0; - atomic_inc(&mem->invalid); - evicted_bos = atomic_inc_return(&process_info->evicted_bos); - if (evicted_bos == 1) { + mutex_lock(&process_info->notifier_lock); + mmu_interval_set_seq(mni, cur_seq); + + mem->invalid++; + if (++process_info->evicted_bos == 1) { /* First eviction, stop the queues */ - r = kgd2kfd_quiesce_mm(mm, KFD_QUEUE_EVICTION_TRIGGER_USERPTR); + r = kgd2kfd_quiesce_mm(mni->mm, + KFD_QUEUE_EVICTION_TRIGGER_USERPTR); if (r) pr_err("Failed to quiesce KFD\n"); schedule_delayed_work(&process_info->restore_userptr_work, msecs_to_jiffies(AMDGPU_USERPTR_RESTORE_DELAY_MS)); } + mutex_unlock(&process_info->notifier_lock); return r; } @@ -2328,51 +2327,58 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, struct kgd_mem *mem, *tmp_mem; struct amdgpu_bo *bo; struct ttm_operation_ctx ctx = { false, false }; - int invalid, ret; + uint32_t invalid; + int ret = 0; - /* Move all invalidated BOs to the userptr_inval_list and - * release their user pages by migration to the CPU domain - */ + mutex_lock(&process_info->notifier_lock); + + /* Move all invalidated BOs to the userptr_inval_list */ list_for_each_entry_safe(mem, tmp_mem, &process_info->userptr_valid_list, - validate_list.head) { - if (!atomic_read(&mem->invalid)) - continue; /* BO is still valid */ - - bo = mem->bo; - - if (amdgpu_bo_reserve(bo, true)) - return -EAGAIN; - amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU); - ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - amdgpu_bo_unreserve(bo); - if (ret) { - pr_err("%s: Failed to invalidate userptr BO\n", - __func__); - return -EAGAIN; - } - - list_move_tail(&mem->validate_list.head, - &process_info->userptr_inval_list); - } - - if (list_empty(&process_info->userptr_inval_list)) - return 0; /* All evicted userptr BOs were freed */ + validate_list.head) + if (mem->invalid) + list_move_tail(&mem->validate_list.head, + &process_info->userptr_inval_list); /* Go through userptr_inval_list and update any invalid user_pages */ list_for_each_entry(mem, &process_info->userptr_inval_list, validate_list.head) { - invalid = atomic_read(&mem->invalid); + invalid = mem->invalid; if (!invalid) /* BO hasn't been invalidated since the last - * revalidation attempt. Keep its BO list. + * revalidation attempt. Keep its page list. */ continue; bo = mem->bo; + amdgpu_ttm_tt_discard_user_pages(bo->tbo.ttm, mem->range); + mem->range = NULL; + + /* BO reservations and getting user pages (hmm_range_fault) + * must happen outside the notifier lock + */ + mutex_unlock(&process_info->notifier_lock); + + /* Move the BO to system (CPU) domain if necessary to unmap + * and free the SG table + */ + if (bo->tbo.resource->mem_type != TTM_PL_SYSTEM) { + if (amdgpu_bo_reserve(bo, true)) + return -EAGAIN; + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU); + ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + amdgpu_bo_unreserve(bo); + if (ret) { + pr_err("%s: Failed to invalidate userptr BO\n", + __func__); + return -EAGAIN; + } + } + /* Get updated user pages */ - ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, + &mem->range); if (ret) { pr_debug("Failed %d to get user pages\n", ret); @@ -2385,30 +2391,32 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, */ if (ret != -EFAULT) return ret; - } else { - /* - * FIXME: Cannot ignore the return code, must hold - * notifier_lock - */ - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + ret = 0; } + mutex_lock(&process_info->notifier_lock); + /* Mark the BO as valid unless it was invalidated * again concurrently. */ - if (atomic_cmpxchg(&mem->invalid, invalid, 0) != invalid) - return -EAGAIN; + if (mem->invalid != invalid) { + ret = -EAGAIN; + goto unlock_out; + } + mem->invalid = 0; } - return 0; +unlock_out: + mutex_unlock(&process_info->notifier_lock); + + return ret; } /* Validate invalid userptr BOs * - * Validates BOs on the userptr_inval_list, and moves them back to the - * userptr_valid_list. Also updates GPUVM page tables with new page - * addresses and waits for the page table updates to complete. + * Validates BOs on the userptr_inval_list. Also updates GPUVM page tables + * with new page addresses and waits for the page table updates to complete. */ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) { @@ -2479,9 +2487,6 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) } } - list_move_tail(&mem->validate_list.head, - &process_info->userptr_valid_list); - /* Update mapping. If the BO was not validated * (because we couldn't get user pages), this will * clear the page table entries, which will result in @@ -2497,7 +2502,9 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) if (ret) { pr_err("%s: update PTE failed\n", __func__); /* make sure this gets validated again */ - atomic_inc(&mem->invalid); + mutex_lock(&process_info->notifier_lock); + mem->invalid++; + mutex_unlock(&process_info->notifier_lock); goto unreserve_out; } } @@ -2517,6 +2524,36 @@ out_no_mem: return ret; } +/* Confirm that all user pages are valid while holding the notifier lock + * + * Moves valid BOs from the userptr_inval_list back to userptr_val_list. + */ +static int confirm_valid_user_pages_locked(struct amdkfd_process_info *process_info) +{ + struct kgd_mem *mem, *tmp_mem; + int ret = 0; + + list_for_each_entry_safe(mem, tmp_mem, + &process_info->userptr_inval_list, + validate_list.head) { + bool valid = amdgpu_ttm_tt_get_user_pages_done( + mem->bo->tbo.ttm, mem->range); + + mem->range = NULL; + if (!valid) { + WARN(!mem->invalid, "Invalid BO not marked invalid"); + ret = -EAGAIN; + continue; + } + WARN(mem->invalid, "Valid BO is marked invalid"); + + list_move_tail(&mem->validate_list.head, + &process_info->userptr_valid_list); + } + + return ret; +} + /* Worker callback to restore evicted userptr BOs * * Tries to update and validate all userptr BOs. If successful and no @@ -2531,9 +2568,11 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) restore_userptr_work); struct task_struct *usertask; struct mm_struct *mm; - int evicted_bos; + uint32_t evicted_bos; - evicted_bos = atomic_read(&process_info->evicted_bos); + mutex_lock(&process_info->notifier_lock); + evicted_bos = process_info->evicted_bos; + mutex_unlock(&process_info->notifier_lock); if (!evicted_bos) return; @@ -2556,9 +2595,6 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) * and we can just restart the queues. */ if (!list_empty(&process_info->userptr_inval_list)) { - if (atomic_read(&process_info->evicted_bos) != evicted_bos) - goto unlock_out; /* Concurrent eviction, try again */ - if (validate_invalid_user_pages(process_info)) goto unlock_out; } @@ -2567,10 +2603,17 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) * be a first eviction that calls quiesce_mm. The eviction * reference counting inside KFD will handle this case. */ - if (atomic_cmpxchg(&process_info->evicted_bos, evicted_bos, 0) != - evicted_bos) - goto unlock_out; - evicted_bos = 0; + mutex_lock(&process_info->notifier_lock); + if (process_info->evicted_bos != evicted_bos) + goto unlock_notifier_out; + + if (confirm_valid_user_pages_locked(process_info)) { + WARN(1, "User pages unexpectedly invalid"); + goto unlock_notifier_out; + } + + process_info->evicted_bos = evicted_bos = 0; + if (kgd2kfd_resume_mm(mm)) { pr_err("%s: Failed to resume KFD\n", __func__); /* No recovery from this failure. Probably the CP is @@ -2578,6 +2621,8 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work) */ } +unlock_notifier_out: + mutex_unlock(&process_info->notifier_lock); unlock_out: mutex_unlock(&process_info->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index b81b77a9efa6..ac6fe0ae4609 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -101,39 +101,101 @@ void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev) } } +static int amdgpu_atomfirmware_allocate_fb_v2_1(struct amdgpu_device *adev, + struct vram_usagebyfirmware_v2_1 *fw_usage, int *usage_bytes) +{ + u32 start_addr, fw_size, drv_size; + + start_addr = le32_to_cpu(fw_usage->start_address_in_kb); + fw_size = le16_to_cpu(fw_usage->used_by_firmware_in_kb); + drv_size = le16_to_cpu(fw_usage->used_by_driver_in_kb); + + DRM_DEBUG("atom firmware v2_1 requested %08x %dkb fw %dkb drv\n", + start_addr, + fw_size, + drv_size); + + if ((start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) == + (u32)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION << + ATOM_VRAM_OPERATION_FLAGS_SHIFT)) { + /* Firmware request VRAM reservation for SR-IOV */ + adev->mman.fw_vram_usage_start_offset = (start_addr & + (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; + adev->mman.fw_vram_usage_size = fw_size << 10; + /* Use the default scratch size */ + *usage_bytes = 0; + } else { + *usage_bytes = drv_size << 10; + } + return 0; +} + +static int amdgpu_atomfirmware_allocate_fb_v2_2(struct amdgpu_device *adev, + struct vram_usagebyfirmware_v2_2 *fw_usage, int *usage_bytes) +{ + u32 fw_start_addr, fw_size, drv_start_addr, drv_size; + + fw_start_addr = le32_to_cpu(fw_usage->fw_region_start_address_in_kb); + fw_size = le16_to_cpu(fw_usage->used_by_firmware_in_kb); + + drv_start_addr = le32_to_cpu(fw_usage->driver_region0_start_address_in_kb); + drv_size = le32_to_cpu(fw_usage->used_by_driver_region0_in_kb); + + DRM_DEBUG("atom requested fw start at %08x %dkb and drv start at %08x %dkb\n", + fw_start_addr, + fw_size, + drv_start_addr, + drv_size); + + if (amdgpu_sriov_vf(adev) && + ((fw_start_addr & (ATOM_VRAM_BLOCK_NEEDS_NO_RESERVATION << + ATOM_VRAM_OPERATION_FLAGS_SHIFT)) == 0)) { + /* Firmware request VRAM reservation for SR-IOV */ + adev->mman.fw_vram_usage_start_offset = (fw_start_addr & + (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; + adev->mman.fw_vram_usage_size = fw_size << 10; + } + + if (amdgpu_sriov_vf(adev) && + ((drv_start_addr & (ATOM_VRAM_BLOCK_NEEDS_NO_RESERVATION << + ATOM_VRAM_OPERATION_FLAGS_SHIFT)) == 0)) { + /* driver request VRAM reservation for SR-IOV */ + adev->mman.drv_vram_usage_start_offset = (drv_start_addr & + (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; + adev->mman.drv_vram_usage_size = drv_size << 10; + } + + *usage_bytes = 0; + return 0; +} + int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev) { struct atom_context *ctx = adev->mode_info.atom_context; int index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, vram_usagebyfirmware); - struct vram_usagebyfirmware_v2_1 *firmware_usage; - uint32_t start_addr, size; - uint16_t data_offset; + struct vram_usagebyfirmware_v2_1 *fw_usage_v2_1; + struct vram_usagebyfirmware_v2_2 *fw_usage_v2_2; + u16 data_offset; + u8 frev, crev; int usage_bytes = 0; - if (amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) { - firmware_usage = (struct vram_usagebyfirmware_v2_1 *)(ctx->bios + data_offset); - DRM_DEBUG("atom firmware requested %08x %dkb fw %dkb drv\n", - le32_to_cpu(firmware_usage->start_address_in_kb), - le16_to_cpu(firmware_usage->used_by_firmware_in_kb), - le16_to_cpu(firmware_usage->used_by_driver_in_kb)); - - start_addr = le32_to_cpu(firmware_usage->start_address_in_kb); - size = le16_to_cpu(firmware_usage->used_by_firmware_in_kb); - - if ((uint32_t)(start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) == - (uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION << - ATOM_VRAM_OPERATION_FLAGS_SHIFT)) { - /* Firmware request VRAM reservation for SR-IOV */ - adev->mman.fw_vram_usage_start_offset = (start_addr & - (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; - adev->mman.fw_vram_usage_size = size << 10; - /* Use the default scratch size */ - usage_bytes = 0; - } else { - usage_bytes = le16_to_cpu(firmware_usage->used_by_driver_in_kb) << 10; + if (amdgpu_atom_parse_data_header(ctx, index, NULL, &frev, &crev, &data_offset)) { + if (frev == 2 && crev == 1) { + fw_usage_v2_1 = + (struct vram_usagebyfirmware_v2_1 *)(ctx->bios + data_offset); + amdgpu_atomfirmware_allocate_fb_v2_1(adev, + fw_usage_v2_1, + &usage_bytes); + } else if (frev >= 2 && crev >= 2) { + fw_usage_v2_2 = + (struct vram_usagebyfirmware_v2_2 *)(ctx->bios + data_offset); + amdgpu_atomfirmware_allocate_fb_v2_2(adev, + fw_usage_v2_2, + &usage_bytes); } } + ctx->scratch_size_bytes = 0; if (usage_bytes == 0) usage_bytes = 20 * 1024; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index e363f56c72af..30c28a69e847 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -317,6 +317,7 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) if (!found) return false; + pci_dev_put(pdev); adev->bios = kmalloc(size, GFP_KERNEL); if (!adev->bios) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 2168163aad2d..252a876b0725 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -209,6 +209,7 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list, list_add_tail(&e->tv.head, &bucket[priority]); e->user_pages = NULL; + e->range = NULL; } /* Connect the sorted buckets in the output list. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index 9caea1688fc3..e4d78491bcc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -26,6 +26,8 @@ #include <drm/ttm/ttm_execbuf_util.h> #include <drm/amdgpu_drm.h> +struct hmm_range; + struct amdgpu_device; struct amdgpu_bo; struct amdgpu_bo_va; @@ -36,6 +38,7 @@ struct amdgpu_bo_list_entry { struct amdgpu_bo_va *bo_va; uint32_t priority; struct page **user_pages; + struct hmm_range *range; bool user_invalidated; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 491d4846fc02..2ebbc6382a06 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -26,7 +26,6 @@ #include <drm/display/drm_dp_helper.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_probe_helper.h> #include <drm/amdgpu_drm.h> #include "amdgpu.h" @@ -328,7 +327,6 @@ static void amdgpu_connector_free_edid(struct drm_connector *connector) kfree(amdgpu_connector->edid); amdgpu_connector->edid = NULL; - drm_connector_update_edid_property(connector, NULL); } static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 1bbd39b3b0fc..8516c814bc9b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -109,6 +109,7 @@ static int amdgpu_cs_p1_ib(struct amdgpu_cs_parser *p, return r; ++(num_ibs[r]); + p->gang_leader_idx = r; return 0; } @@ -287,20 +288,18 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, } } - if (!p->gang_size) - return -EINVAL; + if (!p->gang_size) { + ret = -EINVAL; + goto free_partial_kdata; + } for (i = 0; i < p->gang_size; ++i) { - ret = amdgpu_job_alloc(p->adev, num_ibs[i], &p->jobs[i], vm); - if (ret) - goto free_all_kdata; - - ret = drm_sched_job_init(&p->jobs[i]->base, p->entities[i], - &fpriv->vm); + ret = amdgpu_job_alloc(p->adev, vm, p->entities[i], vm, + num_ibs[i], &p->jobs[i]); if (ret) goto free_all_kdata; } - p->gang_leader = p->jobs[p->gang_size - 1]; + p->gang_leader = p->jobs[p->gang_leader_idx]; if (p->ctx->vram_lost_counter != p->gang_leader->vram_lost_counter) { ret = -ECANCELED; @@ -430,7 +429,7 @@ static int amdgpu_cs_p2_dependencies(struct amdgpu_cs_parser *p, dma_fence_put(old); } - r = amdgpu_sync_fence(&p->gang_leader->sync, fence); + r = amdgpu_sync_fence(&p->sync, fence); dma_fence_put(fence); if (r) return r; @@ -452,9 +451,20 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p, return r; } - r = amdgpu_sync_fence(&p->gang_leader->sync, fence); - dma_fence_put(fence); + r = amdgpu_sync_fence(&p->sync, fence); + if (r) + goto error; + + /* + * When we have an explicit dependency it might be necessary to insert a + * pipeline sync to make sure that all caches etc are flushed and the + * next job actually sees the results from the previous one. + */ + if (fence->context == p->gang_leader->base.entity->fence_context) + r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence); +error: + dma_fence_put(fence); return r; } @@ -910,7 +920,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, goto out_free_user_pages; } - r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages); + r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages, &e->range); if (r) { kvfree(e->user_pages); e->user_pages = NULL; @@ -988,10 +998,12 @@ out_free_user_pages: if (!e->user_pages) continue; - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range); kvfree(e->user_pages); e->user_pages = NULL; + e->range = NULL; } + mutex_unlock(&p->bo_list->bo_list_mutex); return r; } @@ -1101,7 +1113,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_sync_fence(&job->sync, fpriv->prt_va->last_pt_update); + r = amdgpu_sync_fence(&p->sync, fpriv->prt_va->last_pt_update); if (r) return r; @@ -1112,7 +1124,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_sync_fence(&job->sync, bo_va->last_pt_update); + r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update); if (r) return r; } @@ -1131,7 +1143,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_sync_fence(&job->sync, bo_va->last_pt_update); + r = amdgpu_sync_fence(&p->sync, bo_va->last_pt_update); if (r) return r; } @@ -1144,7 +1156,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_sync_fence(&job->sync, vm->last_update); + r = amdgpu_sync_fence(&p->sync, vm->last_update); if (r) return r; @@ -1176,7 +1188,6 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; - struct amdgpu_job *leader = p->gang_leader; struct amdgpu_bo_list_entry *e; unsigned int i; int r; @@ -1188,22 +1199,21 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) sync_mode = amdgpu_bo_explicit_sync(bo) ? AMDGPU_SYNC_EXPLICIT : AMDGPU_SYNC_NE_OWNER; - r = amdgpu_sync_resv(p->adev, &leader->sync, resv, sync_mode, + r = amdgpu_sync_resv(p->adev, &p->sync, resv, sync_mode, &fpriv->vm); if (r) return r; } - for (i = 0; i < p->gang_size - 1; ++i) { - r = amdgpu_sync_clone(&leader->sync, &p->jobs[i]->sync); + for (i = 0; i < p->gang_size; ++i) { + r = amdgpu_sync_push_to_job(&p->sync, p->jobs[i]); if (r) return r; } - r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_size - 1]); + r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]); if (r && r != -ERESTARTSYS) DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n"); - return r; } @@ -1237,11 +1247,14 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, for (i = 0; i < p->gang_size; ++i) drm_sched_job_arm(&p->jobs[i]->base); - for (i = 0; i < (p->gang_size - 1); ++i) { + for (i = 0; i < p->gang_size; ++i) { struct dma_fence *fence; + if (p->jobs[i] == leader) + continue; + fence = &p->jobs[i]->base.s_fence->scheduled; - r = amdgpu_sync_fence(&leader->sync, fence); + r = drm_sched_job_add_dependency(&leader->base, fence); if (r) goto error_cleanup; } @@ -1264,7 +1277,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); - r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range); + e->range = NULL; } if (r) { r = -EAGAIN; @@ -1275,7 +1289,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, list_for_each_entry(e, &p->validated, tv.head) { /* Everybody except for the gang leader uses READ */ - for (i = 0; i < (p->gang_size - 1); ++i) { + for (i = 0; i < p->gang_size; ++i) { + if (p->jobs[i] == leader) + continue; + dma_resv_add_fence(e->tv.bo->base.resv, &p->jobs[i]->base.s_fence->finished, DMA_RESV_USAGE_READ); @@ -1285,7 +1302,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, e->tv.num_shared = 0; } - seq = amdgpu_ctx_add_fence(p->ctx, p->entities[p->gang_size - 1], + seq = amdgpu_ctx_add_fence(p->ctx, p->entities[p->gang_leader_idx], p->fence); amdgpu_cs_post_dependencies(p); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h index cbaa19b2b8a3..113f39510a72 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h @@ -54,6 +54,7 @@ struct amdgpu_cs_parser { /* scheduler job objects */ unsigned int gang_size; + unsigned int gang_leader_idx; struct drm_sched_entity *entities[AMDGPU_CS_GANG_SIZE]; struct amdgpu_job *jobs[AMDGPU_CS_GANG_SIZE]; struct amdgpu_job *gang_leader; @@ -75,6 +76,8 @@ struct amdgpu_cs_parser { unsigned num_post_deps; struct amdgpu_cs_post_dep *post_deps; + + struct amdgpu_sync sync; }; int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index de61a85c4b02..0f16d3c09309 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1969,7 +1969,7 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) amdgpu_ta_if_debugfs_init(adev); #if defined(CONFIG_DRM_AMD_DC) - if (amdgpu_device_has_dc_support(adev)) + if (adev->dc_enabled) dtn_debugfs_init(adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5b9f992e4607..afe6af9c0138 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -37,6 +37,7 @@ #include <linux/pci-p2pdma.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_fb_helper.h> #include <drm/drm_probe_helper.h> #include <drm/amdgpu_drm.h> #include <linux/vgaarb.h> @@ -1915,6 +1916,16 @@ static void amdgpu_device_enable_virtual_display(struct amdgpu_device *adev) } } +void amdgpu_device_set_sriov_virtual_display(struct amdgpu_device *adev) +{ + if (amdgpu_sriov_vf(adev) && !adev->enable_virtual_display) { + adev->mode_info.num_crtc = 1; + adev->enable_virtual_display = true; + DRM_INFO("virtual_display:%d, num_crtc:%d\n", + adev->enable_virtual_display, adev->mode_info.num_crtc); + } +} + /** * amdgpu_device_parse_gpu_info_fw - parse gpu info firmware * @@ -2462,6 +2473,11 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (!amdgpu_sriov_vf(adev)) { struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); + if (WARN_ON(!hive)) { + r = -ENOENT; + goto init_failed; + } + if (!hive->reset_domain || !amdgpu_reset_get_reset_domain(hive->reset_domain)) { r = -ENOENT; @@ -3000,14 +3016,15 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) continue; } - /* skip suspend of gfx and psp for S0ix + /* skip suspend of gfx/mes and psp for S0ix * gfx is in gfxoff state, so on resume it will exit gfxoff just * like at runtime. PSP is also part of the always on hardware * so no need to suspend it. */ if (adev->in_s0ix && (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || - adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)) + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_MES)) continue; /* XXX handle errors */ @@ -3347,8 +3364,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type) */ bool amdgpu_device_has_dc_support(struct amdgpu_device *adev) { - if (amdgpu_sriov_vf(adev) || - adev->enable_virtual_display || + if (adev->enable_virtual_display || (adev->harvest_ip_mask & AMD_HARVEST_IP_DMU_MASK)) return false; @@ -4097,6 +4113,11 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) adev->in_suspend = true; + /* Evict the majority of BOs before grabbing the full access */ + r = amdgpu_device_evict_resources(adev); + if (r) + return r; + if (amdgpu_sriov_vf(adev)) { amdgpu_virt_fini_data_exchange(adev); r = amdgpu_virt_request_full_gpu(adev, false); @@ -4171,21 +4192,15 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) r = amdgpu_device_ip_resume(adev); - /* no matter what r is, always need to properly release full GPU */ - if (amdgpu_sriov_vf(adev)) { - amdgpu_virt_init_data_exchange(adev); - amdgpu_virt_release_full_gpu(adev, true); - } - if (r) { dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r); - return r; + goto exit; } amdgpu_fence_driver_hw_init(adev); r = amdgpu_device_ip_late_init(adev); if (r) - return r; + goto exit; queue_delayed_work(system_wq, &adev->delayed_init_work, msecs_to_jiffies(AMDGPU_RESUME_MS)); @@ -4193,12 +4208,19 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) if (!adev->in_s0ix) { r = amdgpu_amdkfd_resume(adev, adev->in_runpm); if (r) - return r; + goto exit; } +exit: + if (amdgpu_sriov_vf(adev)) { + amdgpu_virt_init_data_exchange(adev); + amdgpu_virt_release_full_gpu(adev, true); + } + + if (r) + return r; + /* Make sure IB tests flushed */ - if (amdgpu_sriov_vf(adev)) - amdgpu_irq_gpu_reset_resume_helper(adev); flush_delayed_work(&adev->delayed_init_work); if (adev->in_s0ix) { @@ -4215,25 +4237,27 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) amdgpu_ras_resume(adev); - /* - * Most of the connector probing functions try to acquire runtime pm - * refs to ensure that the GPU is powered on when connector polling is - * performed. Since we're calling this from a runtime PM callback, - * trying to acquire rpm refs will cause us to deadlock. - * - * Since we're guaranteed to be holding the rpm lock, it's safe to - * temporarily disable the rpm helpers so this doesn't deadlock us. - */ + if (adev->mode_info.num_crtc) { + /* + * Most of the connector probing functions try to acquire runtime pm + * refs to ensure that the GPU is powered on when connector polling is + * performed. Since we're calling this from a runtime PM callback, + * trying to acquire rpm refs will cause us to deadlock. + * + * Since we're guaranteed to be holding the rpm lock, it's safe to + * temporarily disable the rpm helpers so this doesn't deadlock us. + */ #ifdef CONFIG_PM - dev->dev->power.disable_depth++; + dev->dev->power.disable_depth++; #endif - if (!amdgpu_device_has_dc_support(adev)) - drm_helper_hpd_irq_event(dev); - else - drm_kms_helper_hotplug_event(dev); + if (!adev->dc_enabled) + drm_helper_hpd_irq_event(dev); + else + drm_kms_helper_hotplug_event(dev); #ifdef CONFIG_PM - dev->dev->power.disable_depth--; + dev->dev->power.disable_depth--; #endif + } adev->in_suspend = false; if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0)) @@ -4582,6 +4606,10 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev) if (amdgpu_gpu_recovery == 0) goto disabled; + /* Skip soft reset check in fatal error mode */ + if (!amdgpu_ras_is_poison_mode_supported(adev)) + return true; + if (!amdgpu_device_ip_check_soft_reset(adev)) { dev_info(adev->dev,"Timeout, but no hardware hang detected.\n"); return false; @@ -5029,6 +5057,8 @@ static void amdgpu_device_resume_display_audio(struct amdgpu_device *adev) pm_runtime_enable(&(p->dev)); pm_runtime_resume(&(p->dev)); } + + pci_dev_put(p); } static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) @@ -5067,6 +5097,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) if (expires < ktime_get_mono_fast_ns()) { dev_warn(adev->dev, "failed to suspend display audio\n"); + pci_dev_put(p); /* TODO: abort the succeeding gpu reset? */ return -ETIMEDOUT; } @@ -5074,97 +5105,10 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) pm_runtime_disable(&(p->dev)); + pci_dev_put(p); return 0; } -static void amdgpu_device_recheck_guilty_jobs( - struct amdgpu_device *adev, struct list_head *device_list_handle, - struct amdgpu_reset_context *reset_context) -{ - int i, r = 0; - - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { - struct amdgpu_ring *ring = adev->rings[i]; - int ret = 0; - struct drm_sched_job *s_job; - - if (!ring || !ring->sched.thread) - continue; - - s_job = list_first_entry_or_null(&ring->sched.pending_list, - struct drm_sched_job, list); - if (s_job == NULL) - continue; - - /* clear job's guilty and depend the folowing step to decide the real one */ - drm_sched_reset_karma(s_job); - drm_sched_resubmit_jobs_ext(&ring->sched, 1); - - if (!s_job->s_fence->parent) { - DRM_WARN("Failed to get a HW fence for job!"); - continue; - } - - ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout); - if (ret == 0) { /* timeout */ - DRM_ERROR("Found the real bad job! ring:%s, job_id:%llx\n", - ring->sched.name, s_job->id); - - - amdgpu_fence_driver_isr_toggle(adev, true); - - /* Clear this failed job from fence array */ - amdgpu_fence_driver_clear_job_fences(ring); - - amdgpu_fence_driver_isr_toggle(adev, false); - - /* Since the job won't signal and we go for - * another resubmit drop this parent pointer - */ - dma_fence_put(s_job->s_fence->parent); - s_job->s_fence->parent = NULL; - - /* set guilty */ - drm_sched_increase_karma(s_job); - amdgpu_reset_prepare_hwcontext(adev, reset_context); -retry: - /* do hw reset */ - if (amdgpu_sriov_vf(adev)) { - amdgpu_virt_fini_data_exchange(adev); - r = amdgpu_device_reset_sriov(adev, false); - if (r) - adev->asic_reset_res = r; - } else { - clear_bit(AMDGPU_SKIP_HW_RESET, - &reset_context->flags); - r = amdgpu_do_asic_reset(device_list_handle, - reset_context); - if (r && r == -EAGAIN) - goto retry; - } - - /* - * add reset counter so that the following - * resubmitted job could flush vmid - */ - atomic_inc(&adev->gpu_reset_counter); - continue; - } - - /* got the hw fence, signal finished fence */ - atomic_dec(ring->sched.score); - dma_fence_get(&s_job->s_fence->finished); - dma_fence_signal(&s_job->s_fence->finished); - dma_fence_put(&s_job->s_fence->finished); - - /* remove node from list and free the job */ - spin_lock(&ring->sched.job_list_lock); - list_del_init(&s_job->list); - spin_unlock(&ring->sched.job_list_lock); - ring->sched.ops->free_job(s_job); - } -} - static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); @@ -5185,7 +5129,6 @@ static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev) } - /** * amdgpu_device_gpu_recover - reset the asic and recover scheduler * @@ -5208,7 +5151,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, int i, r = 0; bool need_emergency_restart = false; bool audio_suspended = false; - int tmp_vram_lost_counter; bool gpu_reset_for_dev_remove = false; gpu_reset_for_dev_remove = @@ -5354,7 +5296,6 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ amdgpu_device_stop_pending_resets(tmp_adev); } - tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter)); /* Actual ASIC resets if needed.*/ /* Host driver will handle XGMI hive reset for SRIOV */ if (amdgpu_sriov_vf(adev)) { @@ -5379,29 +5320,13 @@ skip_hw_reset: /* Post ASIC reset for all devs .*/ list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - /* - * Sometimes a later bad compute job can block a good gfx job as gfx - * and compute ring share internal GC HW mutually. We add an additional - * guilty jobs recheck step to find the real guilty job, it synchronously - * submits and pends for the first job being signaled. If it gets timeout, - * we identify it as a real guilty job. - */ - if (amdgpu_gpu_recovery == 2 && - !(tmp_vram_lost_counter < atomic_read(&adev->vram_lost_counter))) - amdgpu_device_recheck_guilty_jobs( - tmp_adev, device_list_handle, reset_context); - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = tmp_adev->rings[i]; if (!ring || !ring->sched.thread) continue; - /* No point to resubmit jobs if we didn't HW reset*/ - if (!tmp_adev->asic_reset_res && !job_signaled) - drm_sched_resubmit_jobs(&ring->sched); - - drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res); + drm_sched_start(&ring->sched, true); } if (adev->enable_mes && adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3)) @@ -5443,6 +5368,8 @@ skip_sched_resume: amdgpu_device_resume_display_audio(tmp_adev); amdgpu_device_unset_mp1_state(tmp_adev); + + amdgpu_ras_set_error_query_ready(tmp_adev, true); } recover_end: @@ -5854,8 +5781,6 @@ void amdgpu_pci_resume(struct pci_dev *pdev) if (!ring || !ring->sched.thread) continue; - - drm_sched_resubmit_jobs(&ring->sched); drm_sched_start(&ring->sched, true); } @@ -6046,3 +5971,44 @@ struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev, dma_fence_put(old); return NULL; } + +bool amdgpu_device_has_display_hardware(struct amdgpu_device *adev) +{ + switch (adev->asic_type) { +#ifdef CONFIG_DRM_AMDGPU_SI + case CHIP_HAINAN: +#endif + case CHIP_TOPAZ: + /* chips with no display hardware */ + return false; +#ifdef CONFIG_DRM_AMDGPU_SI + case CHIP_TAHITI: + case CHIP_PITCAIRN: + case CHIP_VERDE: + case CHIP_OLAND: +#endif +#ifdef CONFIG_DRM_AMDGPU_CIK + case CHIP_BONAIRE: + case CHIP_HAWAII: + case CHIP_KAVERI: + case CHIP_KABINI: + case CHIP_MULLINS: +#endif + case CHIP_TONGA: + case CHIP_FIJI: + case CHIP_POLARIS10: + case CHIP_POLARIS11: + case CHIP_POLARIS12: + case CHIP_VEGAM: + case CHIP_CARRIZO: + case CHIP_STONEY: + /* chips with display hardware */ + return true; + default: + /* IP discovery */ + if (!adev->ip_versions[DCE_HWIP][0] || + (adev->harvest_ip_mask & AMD_HARVEST_IP_DMU_MASK)) + return false; + return true; + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 3993e6134914..1bbd56029a4f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -305,8 +305,13 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev) goto out; } - if (!amdgpu_discovery_verify_binary_signature(adev->mman.discovery_bin)) { - dev_warn(adev->dev, "get invalid ip discovery binary signature from vram\n"); + if (!amdgpu_discovery_verify_binary_signature(adev->mman.discovery_bin) || amdgpu_discovery == 2) { + /* ignore the discovery binary from vram if discovery=2 in kernel module parameter */ + if (amdgpu_discovery == 2) + dev_info(adev->dev,"force read ip discovery binary from file"); + else + dev_warn(adev->dev, "get invalid ip discovery binary signature from vram\n"); + /* retry read ip discovery binary from file */ r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin); if (r) { @@ -1507,6 +1512,7 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): amdgpu_device_ip_block_add(adev, &soc21_common_ip_block); break; default: @@ -1551,6 +1557,7 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): amdgpu_device_ip_block_add(adev, &gmc_v11_0_ip_block); break; default: @@ -1636,6 +1643,7 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(13, 0, 7): case IP_VERSION(13, 0, 8): case IP_VERSION(13, 0, 10): + case IP_VERSION(13, 0, 11): amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block); break; case IP_VERSION(13, 0, 4): @@ -1686,6 +1694,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(13, 0, 7): case IP_VERSION(13, 0, 8): case IP_VERSION(13, 0, 10): + case IP_VERSION(13, 0, 11): amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block); break; default: @@ -1697,9 +1706,17 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) return 0; } +#if defined(CONFIG_DRM_AMD_DC) +static void amdgpu_discovery_set_sriov_display(struct amdgpu_device *adev) +{ + amdgpu_device_set_sriov_virtual_display(adev); + amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); +} +#endif + static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev) { - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) { + if (adev->enable_virtual_display) { amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); return 0; } @@ -1727,7 +1744,10 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(3, 1, 6): case IP_VERSION(3, 2, 0): case IP_VERSION(3, 2, 1): - amdgpu_device_ip_block_add(adev, &dm_ip_block); + if (amdgpu_sriov_vf(adev)) + amdgpu_discovery_set_sriov_display(adev); + else + amdgpu_device_ip_block_add(adev, &dm_ip_block); break; default: dev_err(adev->dev, @@ -1740,7 +1760,10 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): case IP_VERSION(12, 1, 0): - amdgpu_device_ip_block_add(adev, &dm_ip_block); + if (amdgpu_sriov_vf(adev)) + amdgpu_discovery_set_sriov_display(adev); + else + amdgpu_device_ip_block_add(adev, &dm_ip_block); break; default: dev_err(adev->dev, @@ -1785,6 +1808,7 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): amdgpu_device_ip_block_add(adev, &gfx_v11_0_ip_block); break; default: @@ -1948,6 +1972,7 @@ static int amdgpu_discovery_set_mes_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): amdgpu_device_ip_block_add(adev, &mes_v11_0_ip_block); adev->enable_mes = true; adev->enable_mes_kiq = true; @@ -2161,6 +2186,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) break; case IP_VERSION(10, 3, 1): adev->family = AMDGPU_FAMILY_VGH; + adev->apu_flags |= AMD_APU_IS_VANGOGH; break; case IP_VERSION(10, 3, 3): adev->family = AMDGPU_FAMILY_YC; @@ -2177,6 +2203,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->family = AMDGPU_FAMILY_GC_11_0_0; break; case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): adev->family = AMDGPU_FAMILY_GC_11_0_1; break; default: @@ -2194,6 +2221,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 7): case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): adev->flags |= AMD_IS_APU; break; default: @@ -2250,6 +2278,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->nbio.hdp_flush_reg = &nbio_v4_3_hdp_flush_reg; break; case IP_VERSION(7, 7, 0): + case IP_VERSION(7, 7, 1): adev->nbio.funcs = &nbio_v7_7_funcs; adev->nbio.hdp_flush_reg = &nbio_v7_7_hdp_flush_reg; break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 1a06b8d724f3..b22471b3bd63 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -39,11 +39,46 @@ #include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_edid.h> -#include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fb_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_vblank.h> +/** + * amdgpu_display_hotplug_work_func - work handler for display hotplug event + * + * @work: work struct pointer + * + * This is the hotplug event work handler (all ASICs). + * The work gets scheduled from the IRQ handler if there + * was a hotplug interrupt. It walks through the connector table + * and calls hotplug handler for each connector. After this, it sends + * a DRM hotplug event to alert userspace. + * + * This design approach is required in order to defer hotplug event handling + * from the IRQ handler to a work handler because hotplug handler has to use + * mutexes which cannot be locked in an IRQ handler (since &mutex_lock may + * sleep). + */ +void amdgpu_display_hotplug_work_func(struct work_struct *work) +{ + struct amdgpu_device *adev = container_of(work, struct amdgpu_device, + hotplug_work); + struct drm_device *dev = adev_to_drm(adev); + struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + + mutex_lock(&mode_config->mutex); + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) + amdgpu_connector_hotplug(connector); + drm_connector_list_iter_end(&iter); + mutex_unlock(&mode_config->mutex); + /* Just fire off a uevent and let userspace tell us what to do */ + drm_helper_hpd_irq_event(dev); +} + static int amdgpu_display_framebuffer_init(struct drm_device *dev, struct amdgpu_framebuffer *rfb, const struct drm_mode_fb_cmd2 *mode_cmd, @@ -514,7 +549,7 @@ uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, */ if ((bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) && amdgpu_bo_support_uswc(bo_flags) && - amdgpu_device_asic_has_dc_support(adev->asic_type) && + adev->dc_enabled && adev->mode_info.gpu_vm_support) domain |= AMDGPU_GEM_DOMAIN_GTT; #endif @@ -1214,7 +1249,6 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev, const struct drm_mode_config_funcs amdgpu_mode_funcs = { .fb_create = amdgpu_display_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, }; static const struct drm_prop_enum_list amdgpu_underscan_enum_list[] = @@ -1281,7 +1315,7 @@ int amdgpu_display_modeset_create_props(struct amdgpu_device *adev) "dither", amdgpu_dither_enum_list, sz); - if (amdgpu_device_has_dc_support(adev)) { + if (adev->dc_enabled) { adev->mode_info.abm_level_property = drm_property_create_range(adev_to_drm(adev), 0, "abm level", 0, 4); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h index 560352f7c317..9d19940f73c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h @@ -35,6 +35,7 @@ #define amdgpu_display_add_encoder(adev, e, s, c) (adev)->mode_info.funcs->add_encoder((adev), (e), (s), (c)) #define amdgpu_display_add_connector(adev, ci, sd, ct, ib, coi, h, r) (adev)->mode_info.funcs->add_connector((adev), (ci), (sd), (ct), (ib), (coi), (h), (r)) +void amdgpu_display_hotplug_work_func(struct work_struct *work); void amdgpu_display_update_priority(struct amdgpu_device *adev); uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, uint64_t bo_flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 7bd8e33b14be..271e30e34d93 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -328,7 +328,9 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) if (dma_buf->ops == &amdgpu_dmabuf_ops) { struct amdgpu_bo *other = gem_to_amdgpu_bo(dma_buf->priv); - flags |= other->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC; + flags |= other->flags & (AMDGPU_GEM_CREATE_CPU_GTT_USWC | + AMDGPU_GEM_CREATE_COHERENT | + AMDGPU_GEM_CREATE_UNCACHED); } ret = amdgpu_gem_object_create(adev, dma_buf->size, PAGE_SIZE, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bf2d50c8c92a..b4f2d61ea0d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -25,6 +25,7 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_aperture.h> #include <drm/drm_drv.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem.h> #include <drm/drm_vblank.h> #include <drm/drm_managed.h> @@ -230,17 +231,18 @@ module_param_named(vis_vramlimit, amdgpu_vis_vram_limit, int, 0444); /** * DOC: gartsize (uint) - * Restrict the size of GART in Mib (32, 64, etc.) for testing. The default is -1 (The size depends on asic). + * Restrict the size of GART (for kernel use) in Mib (32, 64, etc.) for testing. + * The default is -1 (The size depends on asic). */ -MODULE_PARM_DESC(gartsize, "Size of GART to setup in megabytes (32, 64, etc., -1=auto)"); +MODULE_PARM_DESC(gartsize, "Size of kernel GART to setup in megabytes (32, 64, etc., -1=auto)"); module_param_named(gartsize, amdgpu_gart_size, uint, 0600); /** * DOC: gttsize (int) - * Restrict the size of GTT domain in MiB for testing. The default is -1 (It's VRAM size if 3GB < VRAM < 3/4 RAM, - * otherwise 3/4 RAM size). + * Restrict the size of GTT domain (for userspace use) in MiB for testing. + * The default is -1 (Use 1/2 RAM, minimum value is 3GB). */ -MODULE_PARM_DESC(gttsize, "Size of the GTT domain in megabytes (-1 = auto)"); +MODULE_PARM_DESC(gttsize, "Size of the GTT userspace domain in megabytes (-1 = auto)"); module_param_named(gttsize, amdgpu_gtt_size, int, 0600); /** @@ -533,7 +535,7 @@ module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444); * DOC: gpu_recovery (int) * Set to enable GPU recovery mechanism (1 = enable, 0 = disable). The default is -1 (auto, disabled except SRIOV). */ -MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (2 = advanced tdr mode, 1 = enable, 0 = disable, -1 = auto)"); +MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)"); module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444); /** @@ -1924,9 +1926,6 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, - /* Van Gogh */ - {0x1002, 0x163F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VANGOGH|AMD_IS_APU}, - /* Yellow Carp */ {0x1002, 0x164D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU}, {0x1002, 0x1681, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU}, @@ -2040,6 +2039,15 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, "See modparam exp_hw_support\n"); return -ENODEV; } + /* differentiate between P10 and P11 asics with the same DID */ + if (pdev->device == 0x67FF && + (pdev->revision == 0xE3 || + pdev->revision == 0xE7 || + pdev->revision == 0xF3 || + pdev->revision == 0xF7)) { + flags &= ~AMD_ASIC_MASK; + flags |= CHIP_POLARIS10; + } /* Due to hardware bugs, S/G Display on raven requires a 1:1 IOMMU mapping, * however, SME requires an indirect IOMMU mapping because the encryption @@ -2109,12 +2117,12 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, ddev); - ret = amdgpu_driver_load_kms(adev, ent->driver_data); + ret = amdgpu_driver_load_kms(adev, flags); if (ret) goto err_pci; retry_init: - ret = drm_dev_register(ddev, ent->driver_data); + ret = drm_dev_register(ddev, flags); if (ret == -EAGAIN && ++retry <= 3) { DRM_INFO("retry init %d\n", retry); /* Don't request EX mode too frequently which is attacking */ @@ -2471,7 +2479,7 @@ static int amdgpu_runtime_idle_check_display(struct device *dev) if (ret) return ret; - if (amdgpu_device_has_dc_support(adev)) { + if (adev->dc_enabled) { struct drm_crtc *crtc; drm_for_each_crtc(crtc, drm_dev) { @@ -2572,6 +2580,8 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) amdgpu_device_baco_enter(drm_dev); } + dev_dbg(&pdev->dev, "asic/device is runtime suspended\n"); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c index 4d9eb0137f8c..7d2a908438e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c @@ -79,13 +79,15 @@ * That is, for an I2C EEPROM driver everything is controlled by * the "eeprom_addr". * + * See also top of amdgpu_ras_eeprom.c. + * * P.S. If you need to write, lock and read the Identification Page, * (M24M02-DR device only, which we do not use), change the "7" to * "0xF" in the macro below, and let the client set bit 20 to 1 in * "eeprom_addr", and set A10 to 0 to write into it, and A10 and A1 to * 1 to lock it permanently. */ -#define MAKE_I2C_ADDR(_aa) ((0xA << 3) | (((_aa) >> 16) & 7)) +#define MAKE_I2C_ADDR(_aa) ((0xA << 3) | (((_aa) >> 16) & 0xF)) static int __amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, u16 buf_size, bool read) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index d0d99ed607dd..00444203220d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -55,6 +55,7 @@ struct amdgpu_fence { /* RB, DMA, etc. */ struct amdgpu_ring *ring; + ktime_t start_timestamp; }; static struct kmem_cache *amdgpu_fence_slab; @@ -199,6 +200,8 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd } } + to_amdgpu_fence(fence)->start_timestamp = ktime_get(); + /* This function can't be called concurrently anyway, otherwise * emitting the fence would mess up the hardware ring buffer. */ @@ -407,6 +410,57 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring) } /** + * amdgpu_fence_last_unsignaled_time_us - the time fence emitted until now + * @ring: ring the fence is associated with + * + * Find the earliest fence unsignaled until now, calculate the time delta + * between the time fence emitted and now. + */ +u64 amdgpu_fence_last_unsignaled_time_us(struct amdgpu_ring *ring) +{ + struct amdgpu_fence_driver *drv = &ring->fence_drv; + struct dma_fence *fence; + uint32_t last_seq, sync_seq; + + last_seq = atomic_read(&ring->fence_drv.last_seq); + sync_seq = READ_ONCE(ring->fence_drv.sync_seq); + if (last_seq == sync_seq) + return 0; + + ++last_seq; + last_seq &= drv->num_fences_mask; + fence = drv->fences[last_seq]; + if (!fence) + return 0; + + return ktime_us_delta(ktime_get(), + to_amdgpu_fence(fence)->start_timestamp); +} + +/** + * amdgpu_fence_update_start_timestamp - update the timestamp of the fence + * @ring: ring the fence is associated with + * @seq: the fence seq number to update. + * @timestamp: the start timestamp to update. + * + * The function called at the time the fence and related ib is about to + * resubmit to gpu in MCBP scenario. Thus we do not consider race condition + * with amdgpu_fence_process to modify the same fence. + */ +void amdgpu_fence_update_start_timestamp(struct amdgpu_ring *ring, uint32_t seq, ktime_t timestamp) +{ + struct amdgpu_fence_driver *drv = &ring->fence_drv; + struct dma_fence *fence; + + seq &= drv->num_fences_mask; + fence = drv->fences[seq]; + if (!fence) + return; + + to_amdgpu_fence(fence)->start_timestamp = timestamp; +} + +/** * amdgpu_fence_driver_start_ring - make the fence driver * ready for use on the requested ring. * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c index e325150879df..4620c4712ce3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c @@ -29,9 +29,10 @@ #include "amdgpu_fru_eeprom.h" #include "amdgpu_eeprom.h" -#define FRU_EEPROM_MADDR 0x60000 +#define FRU_EEPROM_MADDR_6 0x60000 +#define FRU_EEPROM_MADDR_8 0x80000 -static bool is_fru_eeprom_supported(struct amdgpu_device *adev) +static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr) { /* Only server cards have the FRU EEPROM * TODO: See if we can figure this out dynamically instead of @@ -45,6 +46,11 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev)) return false; + /* The default I2C EEPROM address of the FRU. + */ + if (fru_addr) + *fru_addr = FRU_EEPROM_MADDR_8; + /* VBIOS is of the format ###-DXXXYYYY-##. For SKU identification, * we can use just the "DXXX" portion. If there were more models, we * could convert the 3 characters to a hex integer and use a switch @@ -57,21 +63,31 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev) if (strnstr(atom_ctx->vbios_version, "D161", sizeof(atom_ctx->vbios_version)) || strnstr(atom_ctx->vbios_version, "D163", - sizeof(atom_ctx->vbios_version))) + sizeof(atom_ctx->vbios_version))) { + if (fru_addr) + *fru_addr = FRU_EEPROM_MADDR_6; return true; - else + } else { return false; + } case CHIP_ALDEBARAN: - /* All Aldebaran SKUs have the FRU */ + /* All Aldebaran SKUs have an FRU */ + if (!strnstr(atom_ctx->vbios_version, "D673", + sizeof(atom_ctx->vbios_version))) + if (fru_addr) + *fru_addr = FRU_EEPROM_MADDR_6; return true; case CHIP_SIENNA_CICHLID: if (strnstr(atom_ctx->vbios_version, "D603", - sizeof(atom_ctx->vbios_version))) { + sizeof(atom_ctx->vbios_version))) { if (strnstr(atom_ctx->vbios_version, "D603GLXE", - sizeof(atom_ctx->vbios_version))) + sizeof(atom_ctx->vbios_version))) { return false; - else + } else { + if (fru_addr) + *fru_addr = FRU_EEPROM_MADDR_6; return true; + } } else { return false; } @@ -80,41 +96,14 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev) } } -static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr, - unsigned char *buf, size_t buf_size) -{ - int ret; - u8 size; - - ret = amdgpu_eeprom_read(adev->pm.fru_eeprom_i2c_bus, addrptr, buf, 1); - if (ret < 1) { - DRM_WARN("FRU: Failed to get size field"); - return ret; - } - - /* The size returned by the i2c requires subtraction of 0xC0 since the - * size apparently always reports as 0xC0+actual size. - */ - size = buf[0] & 0x3F; - size = min_t(size_t, size, buf_size); - - ret = amdgpu_eeprom_read(adev->pm.fru_eeprom_i2c_bus, addrptr + 1, - buf, size); - if (ret < 1) { - DRM_WARN("FRU: Failed to get data field"); - return ret; - } - - return size; -} - int amdgpu_fru_get_product_info(struct amdgpu_device *adev) { - unsigned char buf[AMDGPU_PRODUCT_NAME_LEN]; - u32 addrptr; + unsigned char buf[8], *pia; + u32 addr, fru_addr; int size, len; + u8 csum; - if (!is_fru_eeprom_supported(adev)) + if (!is_fru_eeprom_supported(adev, &fru_addr)) return 0; /* If algo exists, it means that the i2c_adapter's initialized */ @@ -123,88 +112,102 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev) return -ENODEV; } - /* There's a lot of repetition here. This is due to the FRU having - * variable-length fields. To get the information, we have to find the - * size of each field, and then keep reading along and reading along - * until we get all of the data that we want. We use addrptr to track - * the address as we go - */ - - /* The first fields are all of size 1-byte, from 0-7 are offsets that - * contain information that isn't useful to us. - * Bytes 8-a are all 1-byte and refer to the size of the entire struct, - * and the language field, so just start from 0xb, manufacturer size - */ - addrptr = FRU_EEPROM_MADDR + 0xb; - size = amdgpu_fru_read_eeprom(adev, addrptr, buf, sizeof(buf)); - if (size < 1) { - DRM_ERROR("Failed to read FRU Manufacturer, ret:%d", size); - return -EINVAL; + /* Read the IPMI Common header */ + len = amdgpu_eeprom_read(adev->pm.fru_eeprom_i2c_bus, fru_addr, buf, + sizeof(buf)); + if (len != 8) { + DRM_ERROR("Couldn't read the IPMI Common Header: %d", len); + return len < 0 ? len : -EIO; } - /* Increment the addrptr by the size of the field, and 1 due to the - * size field being 1 byte. This pattern continues below. - */ - addrptr += size + 1; - size = amdgpu_fru_read_eeprom(adev, addrptr, buf, sizeof(buf)); - if (size < 1) { - DRM_ERROR("Failed to read FRU product name, ret:%d", size); - return -EINVAL; + if (buf[0] != 1) { + DRM_ERROR("Bad IPMI Common Header version: 0x%02x", buf[0]); + return -EIO; } - len = size; - if (len >= AMDGPU_PRODUCT_NAME_LEN) { - DRM_WARN("FRU Product Name is larger than %d characters. This is likely a mistake", - AMDGPU_PRODUCT_NAME_LEN); - len = AMDGPU_PRODUCT_NAME_LEN - 1; - } - memcpy(adev->product_name, buf, len); - adev->product_name[len] = '\0'; - - addrptr += size + 1; - size = amdgpu_fru_read_eeprom(adev, addrptr, buf, sizeof(buf)); - if (size < 1) { - DRM_ERROR("Failed to read FRU product number, ret:%d", size); - return -EINVAL; + for (csum = 0; len > 0; len--) + csum += buf[len - 1]; + if (csum) { + DRM_ERROR("Bad IPMI Common Header checksum: 0x%02x", csum); + return -EIO; } - len = size; - /* Product number should only be 16 characters. Any more, - * and something could be wrong. Cap it at 16 to be safe - */ - if (len >= sizeof(adev->product_number)) { - DRM_WARN("FRU Product Number is larger than 16 characters. This is likely a mistake"); - len = sizeof(adev->product_number) - 1; - } - memcpy(adev->product_number, buf, len); - adev->product_number[len] = '\0'; + /* Get the offset to the Product Info Area (PIA). */ + addr = buf[4] * 8; + if (!addr) + return 0; - addrptr += size + 1; - size = amdgpu_fru_read_eeprom(adev, addrptr, buf, sizeof(buf)); + /* Get the absolute address to the PIA. */ + addr += fru_addr; - if (size < 1) { - DRM_ERROR("Failed to read FRU product version, ret:%d", size); - return -EINVAL; + /* Read the header of the PIA. */ + len = amdgpu_eeprom_read(adev->pm.fru_eeprom_i2c_bus, addr, buf, 3); + if (len != 3) { + DRM_ERROR("Couldn't read the Product Info Area header: %d", len); + return len < 0 ? len : -EIO; } - addrptr += size + 1; - size = amdgpu_fru_read_eeprom(adev, addrptr, buf, sizeof(buf)); + if (buf[0] != 1) { + DRM_ERROR("Bad IPMI Product Info Area version: 0x%02x", buf[0]); + return -EIO; + } - if (size < 1) { - DRM_ERROR("Failed to read FRU serial number, ret:%d", size); - return -EINVAL; + size = buf[1] * 8; + pia = kzalloc(size, GFP_KERNEL); + if (!pia) + return -ENOMEM; + + /* Read the whole PIA. */ + len = amdgpu_eeprom_read(adev->pm.fru_eeprom_i2c_bus, addr, pia, size); + if (len != size) { + kfree(pia); + DRM_ERROR("Couldn't read the Product Info Area: %d", len); + return len < 0 ? len : -EIO; } - len = size; - /* Serial number should only be 16 characters. Any more, - * and something could be wrong. Cap it at 16 to be safe - */ - if (len >= sizeof(adev->serial)) { - DRM_WARN("FRU Serial Number is larger than 16 characters. This is likely a mistake"); - len = sizeof(adev->serial) - 1; + for (csum = 0; size > 0; size--) + csum += pia[size - 1]; + if (csum) { + DRM_ERROR("Bad Product Info Area checksum: 0x%02x", csum); + return -EIO; } - memcpy(adev->serial, buf, len); - adev->serial[len] = '\0'; + /* Now extract useful information from the PIA. + * + * Skip the Manufacturer Name at [3] and go directly to + * the Product Name field. + */ + addr = 3 + 1 + (pia[3] & 0x3F); + if (addr + 1 >= len) + goto Out; + memcpy(adev->product_name, pia + addr + 1, + min_t(size_t, + sizeof(adev->product_name), + pia[addr] & 0x3F)); + adev->product_name[sizeof(adev->product_name) - 1] = '\0'; + + /* Go to the Product Part/Model Number field. */ + addr += 1 + (pia[addr] & 0x3F); + if (addr + 1 >= len) + goto Out; + memcpy(adev->product_number, pia + addr + 1, + min_t(size_t, + sizeof(adev->product_number), + pia[addr] & 0x3F)); + adev->product_number[sizeof(adev->product_number) - 1] = '\0'; + + /* Go to the Product Version field. */ + addr += 1 + (pia[addr] & 0x3F); + + /* Go to the Product Serial Number field. */ + addr += 1 + (pia[addr] & 0x3F); + if (addr + 1 >= len) + goto Out; + memcpy(adev->serial, pia + addr + 1, min_t(size_t, + sizeof(adev->serial), + pia[addr] & 0x3F)); + adev->serial[sizeof(adev->serial) - 1] = '\0'; +Out: + kfree(pia); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 8ef31d687ef3..bb7350ea1d75 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -38,6 +38,7 @@ #include "amdgpu.h" #include "amdgpu_display.h" #include "amdgpu_dma_buf.h" +#include "amdgpu_hmm.h" #include "amdgpu_xgmi.h" static const struct drm_gem_object_funcs amdgpu_gem_object_funcs; @@ -87,7 +88,7 @@ static void amdgpu_gem_object_free(struct drm_gem_object *gobj) struct amdgpu_bo *robj = gem_to_amdgpu_bo(gobj); if (robj) { - amdgpu_mn_unregister(robj); + amdgpu_hmm_unregister(robj); amdgpu_bo_unref(&robj); } } @@ -255,7 +256,7 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str * becoming writable and makes is_cow_mapping(vm_flags) false. */ if (is_cow_mapping(vma->vm_flags) && - !(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))) + !(vma->vm_flags & VM_ACCESS_FLAGS)) vma->vm_flags &= ~VM_MAYWRITE; return drm_gem_ttm_mmap(obj, vma); @@ -378,6 +379,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, struct amdgpu_device *adev = drm_to_adev(dev); struct drm_amdgpu_gem_userptr *args = data; struct drm_gem_object *gobj; + struct hmm_range *range; struct amdgpu_bo *bo; uint32_t handle; int r; @@ -413,14 +415,13 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, if (r) goto release_object; - if (args->flags & AMDGPU_GEM_USERPTR_REGISTER) { - r = amdgpu_mn_register(bo, args->addr); - if (r) - goto release_object; - } + r = amdgpu_hmm_register(bo, args->addr); + if (r) + goto release_object; if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) { - r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, + &range); if (r) goto release_object; @@ -443,7 +444,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, user_pages_done: if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range); release_object: drm_gem_object_put(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 9546adc8a76f..23692e5d4d13 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -583,10 +583,14 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) { /* If going to s2idle, no need to wait */ - if (adev->in_s0ix) - delay = GFX_OFF_NO_DELAY; - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + if (adev->in_s0ix) { + if (!amdgpu_dpm_set_powergating_by_smu(adev, + AMD_IP_BLOCK_TYPE_GFX, true)) + adev->gfx.gfx_off_state = true; + } else { + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, delay); + } } } else { if (adev->gfx.gfx_off_req_count == 0) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 832b3807f1d6..b3df4787877e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -33,6 +33,7 @@ #include "amdgpu_imu.h" #include "soc15.h" #include "amdgpu_ras.h" +#include "amdgpu_ring_mux.h" /* GFX current status */ #define AMDGPU_GFX_NORMAL_MODE 0x00000000L @@ -352,6 +353,9 @@ struct amdgpu_gfx { struct amdgpu_gfx_ras *ras; bool is_poweron; + + struct amdgpu_ring sw_gfx_ring[AMDGPU_MAX_SW_GFX_RINGS]; + struct amdgpu_ring_mux muxer; }; #define amdgpu_gfx_get_gpu_clock_counter(adev) (adev)->gfx.funcs->get_gpu_clock_counter((adev)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 9c0d9baab4e2..02a4c93673ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -479,6 +479,12 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev) unsigned i; unsigned vmhub, inv_eng; + if (adev->enable_mes) { + /* reserve engine 5 for firmware */ + for (vmhub = 0; vmhub < AMDGPU_MAX_VMHUBS; vmhub++) + vm_inv_engs[vmhub] &= ~(1 << 5); + } + for (i = 0; i < adev->num_rings; ++i) { ring = adev->rings[i]; vmhub = ring->funcs->vmhub; @@ -543,6 +549,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) /* YELLOW_CARP*/ case IP_VERSION(10, 3, 3): case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): /* Don't enable it by default yet. */ if (amdgpu_tmz < 1) { @@ -657,7 +664,7 @@ void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev) } if (amdgpu_sriov_vf(adev) || - !amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_DCE)) { + !amdgpu_device_has_display_hardware(adev)) { size = 0; } else { size = amdgpu_gmc_get_vbios_fb_size(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c index b86c0b8252a5..2dadcfe43d03 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c @@ -49,9 +49,12 @@ #include "amdgpu.h" #include "amdgpu_amdkfd.h" +#include "amdgpu_hmm.h" + +#define MAX_WALK_BYTE (2UL << 30) /** - * amdgpu_mn_invalidate_gfx - callback to notify about mm change + * amdgpu_hmm_invalidate_gfx - callback to notify about mm change * * @mni: the range (mm) is about to update * @range: details on the invalidation @@ -60,9 +63,9 @@ * Block for operations on BOs to finish and mark pages as accessed and * potentially dirty. */ -static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni, - const struct mmu_notifier_range *range, - unsigned long cur_seq) +static bool amdgpu_hmm_invalidate_gfx(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) { struct amdgpu_bo *bo = container_of(mni, struct amdgpu_bo, notifier); struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); @@ -83,12 +86,12 @@ static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni, return true; } -static const struct mmu_interval_notifier_ops amdgpu_mn_gfx_ops = { - .invalidate = amdgpu_mn_invalidate_gfx, +static const struct mmu_interval_notifier_ops amdgpu_hmm_gfx_ops = { + .invalidate = amdgpu_hmm_invalidate_gfx, }; /** - * amdgpu_mn_invalidate_hsa - callback to notify about mm change + * amdgpu_hmm_invalidate_hsa - callback to notify about mm change * * @mni: the range (mm) is about to update * @range: details on the invalidation @@ -97,32 +100,26 @@ static const struct mmu_interval_notifier_ops amdgpu_mn_gfx_ops = { * We temporarily evict the BO attached to this range. This necessitates * evicting all user-mode queues of the process. */ -static bool amdgpu_mn_invalidate_hsa(struct mmu_interval_notifier *mni, - const struct mmu_notifier_range *range, - unsigned long cur_seq) +static bool amdgpu_hmm_invalidate_hsa(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) { struct amdgpu_bo *bo = container_of(mni, struct amdgpu_bo, notifier); - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); if (!mmu_notifier_range_blockable(range)) return false; - mutex_lock(&adev->notifier_lock); - - mmu_interval_set_seq(mni, cur_seq); - - amdgpu_amdkfd_evict_userptr(bo->kfd_bo, bo->notifier.mm); - mutex_unlock(&adev->notifier_lock); + amdgpu_amdkfd_evict_userptr(mni, cur_seq, bo->kfd_bo); return true; } -static const struct mmu_interval_notifier_ops amdgpu_mn_hsa_ops = { - .invalidate = amdgpu_mn_invalidate_hsa, +static const struct mmu_interval_notifier_ops amdgpu_hmm_hsa_ops = { + .invalidate = amdgpu_hmm_invalidate_hsa, }; /** - * amdgpu_mn_register - register a BO for notifier updates + * amdgpu_hmm_register - register a BO for notifier updates * * @bo: amdgpu buffer object * @addr: userptr addr we should monitor @@ -130,25 +127,25 @@ static const struct mmu_interval_notifier_ops amdgpu_mn_hsa_ops = { * Registers a mmu_notifier for the given BO at the specified address. * Returns 0 on success, -ERRNO if anything goes wrong. */ -int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr) +int amdgpu_hmm_register(struct amdgpu_bo *bo, unsigned long addr) { if (bo->kfd_bo) return mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, amdgpu_bo_size(bo), - &amdgpu_mn_hsa_ops); + &amdgpu_hmm_hsa_ops); return mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, amdgpu_bo_size(bo), - &amdgpu_mn_gfx_ops); + &amdgpu_hmm_gfx_ops); } /** - * amdgpu_mn_unregister - unregister a BO for notifier updates + * amdgpu_hmm_unregister - unregister a BO for notifier updates * * @bo: amdgpu buffer object * * Remove any registration of mmu notifier updates from the buffer object. */ -void amdgpu_mn_unregister(struct amdgpu_bo *bo) +void amdgpu_hmm_unregister(struct amdgpu_bo *bo) { if (!bo->notifier.mm) return; @@ -157,12 +154,12 @@ void amdgpu_mn_unregister(struct amdgpu_bo *bo) } int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, - struct mm_struct *mm, struct page **pages, - uint64_t start, uint64_t npages, - struct hmm_range **phmm_range, bool readonly, - bool mmap_locked, void *owner) + uint64_t start, uint64_t npages, bool readonly, + void *owner, struct page **pages, + struct hmm_range **phmm_range) { struct hmm_range *hmm_range; + unsigned long end; unsigned long timeout; unsigned long i; unsigned long *pfns; @@ -184,32 +181,42 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, hmm_range->default_flags |= HMM_PFN_REQ_WRITE; hmm_range->hmm_pfns = pfns; hmm_range->start = start; - hmm_range->end = start + npages * PAGE_SIZE; + end = start + npages * PAGE_SIZE; hmm_range->dev_private_owner = owner; - /* Assuming 512MB takes maxmium 1 second to fault page address */ - timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT; - timeout = jiffies + msecs_to_jiffies(timeout); + do { + hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, end); + + pr_debug("hmm range: start = 0x%lx, end = 0x%lx", + hmm_range->start, hmm_range->end); + + /* Assuming 512MB takes maxmium 1 second to fault page address */ + timeout = max((hmm_range->end - hmm_range->start) >> 29, 1UL); + timeout *= HMM_RANGE_DEFAULT_TIMEOUT; + timeout = jiffies + msecs_to_jiffies(timeout); retry: - hmm_range->notifier_seq = mmu_interval_read_begin(notifier); - - if (likely(!mmap_locked)) - mmap_read_lock(mm); - - r = hmm_range_fault(hmm_range); - - if (likely(!mmap_locked)) - mmap_read_unlock(mm); - if (unlikely(r)) { - /* - * FIXME: This timeout should encompass the retry from - * mmu_interval_read_retry() as well. - */ - if (r == -EBUSY && !time_after(jiffies, timeout)) - goto retry; - goto out_free_pfns; - } + hmm_range->notifier_seq = mmu_interval_read_begin(notifier); + r = hmm_range_fault(hmm_range); + if (unlikely(r)) { + /* + * FIXME: This timeout should encompass the retry from + * mmu_interval_read_retry() as well. + */ + if (r == -EBUSY && !time_after(jiffies, timeout)) + goto retry; + goto out_free_pfns; + } + + if (hmm_range->end == end) + break; + hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT; + hmm_range->start = hmm_range->end; + schedule(); + } while (hmm_range->end < end); + + hmm_range->start = start; + hmm_range->hmm_pfns = pfns; /* * Due to default_flags, all pages are HMM_PFN_VALID or @@ -231,9 +238,9 @@ out_free_range: return r; } -int amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range) +bool amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range) { - int r; + bool r; r = mmu_interval_read_retry(hmm_range->notifier, hmm_range->notifier_seq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.h index 14a3c1864085..e2edcd010ccc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.h @@ -29,25 +29,25 @@ #include <linux/rwsem.h> #include <linux/workqueue.h> #include <linux/interval_tree.h> +#include <linux/mmu_notifier.h> int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, - struct mm_struct *mm, struct page **pages, - uint64_t start, uint64_t npages, - struct hmm_range **phmm_range, bool readonly, - bool mmap_locked, void *owner); -int amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range); + uint64_t start, uint64_t npages, bool readonly, + void *owner, struct page **pages, + struct hmm_range **phmm_range); +bool amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range); #if defined(CONFIG_HMM_MIRROR) -int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr); -void amdgpu_mn_unregister(struct amdgpu_bo *bo); +int amdgpu_hmm_register(struct amdgpu_bo *bo, unsigned long addr); +void amdgpu_hmm_unregister(struct amdgpu_bo *bo); #else -static inline int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr) +static inline int amdgpu_hmm_register(struct amdgpu_bo *bo, unsigned long addr) { DRM_WARN_ONCE("HMM_MIRROR kernel config option is not enabled, " "add CONFIG_ZONE_DEVICE=y in config file to fix this\n"); return -ENODEV; } -static inline void amdgpu_mn_unregister(struct amdgpu_bo *bo) {} +static inline void amdgpu_hmm_unregister(struct amdgpu_bo *bo) {} #endif #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 258cffe3c06a..bcccc348dbe2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -182,7 +182,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, need_ctx_switch = ring->current_ctx != fence_ctx; if (ring->funcs->emit_pipeline_sync && job && - ((tmp = amdgpu_sync_get_fence(&job->sched_sync)) || + ((tmp = amdgpu_sync_get_fence(&job->explicit_sync)) || (amdgpu_sriov_vf(adev) && need_ctx_switch) || amdgpu_vm_need_pipeline_sync(ring, job))) { need_pipe_sync = true; @@ -211,6 +211,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, } } + amdgpu_ring_ib_begin(ring); if (job && ring->funcs->init_cond_exec) patch_offset = amdgpu_ring_init_cond_exec(ring); @@ -285,6 +286,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, ring->hw_prio == AMDGPU_GFX_PIPE_PRIO_HIGH) ring->funcs->emit_wave_limit(ring, false); + amdgpu_ring_ib_end(ring); amdgpu_ring_commit(ring); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 03d115d2b5ed..fcb711a11a5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -165,31 +165,52 @@ bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev, atomic_read(&adev->gpu_reset_counter); } +/* Check if we need to switch to another set of resources */ +static bool amdgpu_vmid_gds_switch_needed(struct amdgpu_vmid *id, + struct amdgpu_job *job) +{ + return id->gds_base != job->gds_base || + id->gds_size != job->gds_size || + id->gws_base != job->gws_base || + id->gws_size != job->gws_size || + id->oa_base != job->oa_base || + id->oa_size != job->oa_size; +} + +/* Check if the id is compatible with the job */ +static bool amdgpu_vmid_compatible(struct amdgpu_vmid *id, + struct amdgpu_job *job) +{ + return id->pd_gpu_addr == job->vm_pd_addr && + !amdgpu_vmid_gds_switch_needed(id, job); +} + /** * amdgpu_vmid_grab_idle - grab idle VMID * * @vm: vm to allocate id for * @ring: ring we want to submit job to - * @sync: sync object where we add dependencies * @idle: resulting idle VMID + * @fence: fence to wait for if no id could be grabbed * * Try to find an idle VMID, if none is idle add a fence to wait to the sync * object. Returns -ENOMEM when we are out of memory. */ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm, struct amdgpu_ring *ring, - struct amdgpu_sync *sync, - struct amdgpu_vmid **idle) + struct amdgpu_vmid **idle, + struct dma_fence **fence) { struct amdgpu_device *adev = ring->adev; unsigned vmhub = ring->funcs->vmhub; struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; struct dma_fence **fences; unsigned i; - int r; - if (!dma_fence_is_signaled(ring->vmid_wait)) - return amdgpu_sync_fence(sync, ring->vmid_wait); + if (!dma_fence_is_signaled(ring->vmid_wait)) { + *fence = dma_fence_get(ring->vmid_wait); + return 0; + } fences = kmalloc_array(id_mgr->num_ids, sizeof(void *), GFP_KERNEL); if (!fences) @@ -228,10 +249,10 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm, return -ENOMEM; } - r = amdgpu_sync_fence(sync, &array->base); + *fence = dma_fence_get(&array->base); dma_fence_put(ring->vmid_wait); ring->vmid_wait = &array->base; - return r; + return 0; } kfree(fences); @@ -243,30 +264,29 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm, * * @vm: vm to allocate id for * @ring: ring we want to submit job to - * @sync: sync object where we add dependencies - * @fence: fence protecting ID from reuse * @job: job who wants to use the VMID * @id: resulting VMID + * @fence: fence to wait for if no id could be grabbed * * Try to assign a reserved VMID. */ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm, struct amdgpu_ring *ring, - struct amdgpu_sync *sync, - struct dma_fence *fence, struct amdgpu_job *job, - struct amdgpu_vmid **id) + struct amdgpu_vmid **id, + struct dma_fence **fence) { struct amdgpu_device *adev = ring->adev; unsigned vmhub = ring->funcs->vmhub; + struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; uint64_t fence_context = adev->fence_context + ring->idx; bool needs_flush = vm->use_cpu_for_update; uint64_t updates = amdgpu_vm_tlb_seq(vm); int r; - *id = vm->reserved_vmid[vmhub]; + *id = id_mgr->reserved; if ((*id)->owner != vm->immediate.fence_context || - (*id)->pd_gpu_addr != job->vm_pd_addr || + !amdgpu_vmid_compatible(*id, job) || (*id)->flushed_updates < updates || !(*id)->last_flush || ((*id)->last_flush->context != fence_context && @@ -282,7 +302,8 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm, tmp = amdgpu_sync_peek_fence(&(*id)->active, ring); if (tmp) { *id = NULL; - return amdgpu_sync_fence(sync, tmp); + *fence = dma_fence_get(tmp); + return 0; } needs_flush = true; } @@ -290,12 +311,12 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm, /* Good we can use this VMID. Remember this submission as * user of the VMID. */ - r = amdgpu_sync_fence(&(*id)->active, fence); + r = amdgpu_sync_fence(&(*id)->active, &job->base.s_fence->finished); if (r) return r; - (*id)->flushed_updates = updates; job->vm_needs_flush = needs_flush; + job->spm_update_needed = true; return 0; } @@ -304,19 +325,17 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm, * * @vm: vm to allocate id for * @ring: ring we want to submit job to - * @sync: sync object where we add dependencies - * @fence: fence protecting ID from reuse * @job: job who wants to use the VMID * @id: resulting VMID + * @fence: fence to wait for if no id could be grabbed * * Try to reuse a VMID for this submission. */ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm, struct amdgpu_ring *ring, - struct amdgpu_sync *sync, - struct dma_fence *fence, struct amdgpu_job *job, - struct amdgpu_vmid **id) + struct amdgpu_vmid **id, + struct dma_fence **fence) { struct amdgpu_device *adev = ring->adev; unsigned vmhub = ring->funcs->vmhub; @@ -335,7 +354,7 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm, if ((*id)->owner != vm->immediate.fence_context) continue; - if ((*id)->pd_gpu_addr != job->vm_pd_addr) + if (!amdgpu_vmid_compatible(*id, job)) continue; if (!(*id)->last_flush || @@ -352,11 +371,11 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm, /* Good, we can use this VMID. Remember this submission as * user of the VMID. */ - r = amdgpu_sync_fence(&(*id)->active, fence); + r = amdgpu_sync_fence(&(*id)->active, + &job->base.s_fence->finished); if (r) return r; - (*id)->flushed_updates = updates; job->vm_needs_flush |= needs_flush; return 0; } @@ -370,15 +389,13 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm, * * @vm: vm to allocate id for * @ring: ring we want to submit job to - * @sync: sync object where we add dependencies - * @fence: fence protecting ID from reuse * @job: job who wants to use the VMID + * @fence: fence to wait for if no id could be grabbed * * Allocate an id for the vm, adding fences to the sync obj as necessary. */ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring, - struct amdgpu_sync *sync, struct dma_fence *fence, - struct amdgpu_job *job) + struct amdgpu_job *job, struct dma_fence **fence) { struct amdgpu_device *adev = ring->adev; unsigned vmhub = ring->funcs->vmhub; @@ -388,16 +405,16 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring, int r = 0; mutex_lock(&id_mgr->lock); - r = amdgpu_vmid_grab_idle(vm, ring, sync, &idle); + r = amdgpu_vmid_grab_idle(vm, ring, &idle, fence); if (r || !idle) goto error; if (vm->reserved_vmid[vmhub]) { - r = amdgpu_vmid_grab_reserved(vm, ring, sync, fence, job, &id); + r = amdgpu_vmid_grab_reserved(vm, ring, job, &id, fence); if (r || !id) goto error; } else { - r = amdgpu_vmid_grab_used(vm, ring, sync, fence, job, &id); + r = amdgpu_vmid_grab_used(vm, ring, job, &id, fence); if (r) goto error; @@ -406,26 +423,35 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring, id = idle; /* Remember this submission as user of the VMID */ - r = amdgpu_sync_fence(&id->active, fence); + r = amdgpu_sync_fence(&id->active, + &job->base.s_fence->finished); if (r) goto error; - id->flushed_updates = amdgpu_vm_tlb_seq(vm); job->vm_needs_flush = true; } list_move_tail(&id->list, &id_mgr->ids_lru); } - id->pd_gpu_addr = job->vm_pd_addr; - id->owner = vm->immediate.fence_context; - + job->gds_switch_needed = amdgpu_vmid_gds_switch_needed(id, job); if (job->vm_needs_flush) { + id->flushed_updates = amdgpu_vm_tlb_seq(vm); dma_fence_put(id->last_flush); id->last_flush = NULL; } job->vmid = id - id_mgr->ids; job->pasid = vm->pasid; + + id->gds_base = job->gds_base; + id->gds_size = job->gds_size; + id->gws_base = job->gws_base; + id->gws_size = job->gws_size; + id->oa_base = job->oa_base; + id->oa_size = job->oa_size; + id->pd_gpu_addr = job->vm_pd_addr; + id->owner = vm->immediate.fence_context; + trace_amdgpu_vm_grab_id(vm, ring, job); error: @@ -437,31 +463,27 @@ int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned vmhub) { - struct amdgpu_vmid_mgr *id_mgr; - struct amdgpu_vmid *idle; - int r = 0; + struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; - id_mgr = &adev->vm_manager.id_mgr[vmhub]; mutex_lock(&id_mgr->lock); if (vm->reserved_vmid[vmhub]) goto unlock; - if (atomic_inc_return(&id_mgr->reserved_vmid_num) > - AMDGPU_VM_MAX_RESERVED_VMID) { - DRM_ERROR("Over limitation of reserved vmid\n"); - atomic_dec(&id_mgr->reserved_vmid_num); - r = -EINVAL; - goto unlock; + + ++id_mgr->reserved_use_count; + if (!id_mgr->reserved) { + struct amdgpu_vmid *id; + + id = list_first_entry(&id_mgr->ids_lru, struct amdgpu_vmid, + list); + /* Remove from normal round robin handling */ + list_del_init(&id->list); + id_mgr->reserved = id; } - /* Select the first entry VMID */ - idle = list_first_entry(&id_mgr->ids_lru, struct amdgpu_vmid, list); - list_del_init(&idle->list); - vm->reserved_vmid[vmhub] = idle; - mutex_unlock(&id_mgr->lock); + vm->reserved_vmid[vmhub] = true; - return 0; unlock: mutex_unlock(&id_mgr->lock); - return r; + return 0; } void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, @@ -471,12 +493,12 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; mutex_lock(&id_mgr->lock); - if (vm->reserved_vmid[vmhub]) { - list_add(&vm->reserved_vmid[vmhub]->list, - &id_mgr->ids_lru); - vm->reserved_vmid[vmhub] = NULL; - atomic_dec(&id_mgr->reserved_vmid_num); + if (vm->reserved_vmid[vmhub] && + !--id_mgr->reserved_use_count) { + /* give the reserved ID back to normal round robin */ + list_add(&id_mgr->reserved->list, &id_mgr->ids_lru); } + vm->reserved_vmid[vmhub] = false; mutex_unlock(&id_mgr->lock); } @@ -543,7 +565,7 @@ void amdgpu_vmid_mgr_init(struct amdgpu_device *adev) mutex_init(&id_mgr->lock); INIT_LIST_HEAD(&id_mgr->ids_lru); - atomic_set(&id_mgr->reserved_vmid_num, 0); + id_mgr->reserved_use_count = 0; /* manage only VMIDs not used by KFD */ id_mgr->num_ids = adev->vm_manager.first_kfd_vmid; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h index 06c8a0034fa5..d1cc09b45da4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h @@ -67,7 +67,8 @@ struct amdgpu_vmid_mgr { unsigned num_ids; struct list_head ids_lru; struct amdgpu_vmid ids[AMDGPU_NUM_VMID]; - atomic_t reserved_vmid_num; + struct amdgpu_vmid *reserved; + unsigned int reserved_use_count; }; int amdgpu_pasid_alloc(unsigned int bits); @@ -84,8 +85,7 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned vmhub); int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring, - struct amdgpu_sync *sync, struct dma_fence *fence, - struct amdgpu_job *job); + struct amdgpu_job *job, struct dma_fence **fence); void amdgpu_vmid_reset(struct amdgpu_device *adev, unsigned vmhub, unsigned vmid); void amdgpu_vmid_reset_all(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 89011bae7588..a6aef488a822 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -101,41 +101,6 @@ const char *soc15_ih_clientid_name[] = { }; /** - * amdgpu_hotplug_work_func - work handler for display hotplug event - * - * @work: work struct pointer - * - * This is the hotplug event work handler (all ASICs). - * The work gets scheduled from the IRQ handler if there - * was a hotplug interrupt. It walks through the connector table - * and calls hotplug handler for each connector. After this, it sends - * a DRM hotplug event to alert userspace. - * - * This design approach is required in order to defer hotplug event handling - * from the IRQ handler to a work handler because hotplug handler has to use - * mutexes which cannot be locked in an IRQ handler (since &mutex_lock may - * sleep). - */ -static void amdgpu_hotplug_work_func(struct work_struct *work) -{ - struct amdgpu_device *adev = container_of(work, struct amdgpu_device, - hotplug_work); - struct drm_device *dev = adev_to_drm(adev); - struct drm_mode_config *mode_config = &dev->mode_config; - struct drm_connector *connector; - struct drm_connector_list_iter iter; - - mutex_lock(&mode_config->mutex); - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) - amdgpu_connector_hotplug(connector); - drm_connector_list_iter_end(&iter); - mutex_unlock(&mode_config->mutex); - /* Just fire off a uevent and let userspace tell us what to do */ - drm_helper_hpd_irq_event(dev); -} - -/** * amdgpu_irq_disable_all - disable *all* interrupts * * @adev: amdgpu device pointer @@ -317,21 +282,6 @@ int amdgpu_irq_init(struct amdgpu_device *adev) } } - if (!amdgpu_device_has_dc_support(adev)) { - if (!adev->enable_virtual_display) - /* Disable vblank IRQs aggressively for power-saving */ - /* XXX: can this be enabled for DC? */ - adev_to_drm(adev)->vblank_disable_immediate = true; - - r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc); - if (r) - return r; - - /* Pre-DCE11 */ - INIT_WORK(&adev->hotplug_work, - amdgpu_hotplug_work_func); - } - INIT_WORK(&adev->irq.ih1_work, amdgpu_irq_handle_ih1); INIT_WORK(&adev->irq.ih2_work, amdgpu_irq_handle_ih2); INIT_WORK(&adev->irq.ih_soft_work, amdgpu_irq_handle_ih_soft); @@ -345,11 +295,8 @@ int amdgpu_irq_init(struct amdgpu_device *adev) /* PCI devices require shared interrupts. */ r = request_irq(irq, amdgpu_irq_handler, IRQF_SHARED, adev_to_drm(adev)->driver->name, adev_to_drm(adev)); - if (r) { - if (!amdgpu_device_has_dc_support(adev)) - flush_work(&adev->hotplug_work); + if (r) return r; - } adev->irq.installed = true; adev->irq.irq = irq; adev_to_drm(adev)->max_vblank_count = 0x00ffffff; @@ -366,9 +313,6 @@ void amdgpu_irq_fini_hw(struct amdgpu_device *adev) adev->irq.installed = false; if (adev->irq.msi_enabled) pci_free_irq_vectors(adev->pdev); - - if (!amdgpu_device_has_dc_support(adev)) - flush_work(&adev->hotplug_work); } amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index cd968e781077..9e549923622b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -88,8 +88,9 @@ exit: return DRM_GPU_SCHED_STAT_NOMINAL; } -int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, - struct amdgpu_job **job, struct amdgpu_vm *vm) +int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct drm_sched_entity *entity, void *owner, + unsigned int num_ibs, struct amdgpu_job **job) { if (num_ibs == 0) return -EINVAL; @@ -105,28 +106,34 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, (*job)->base.sched = &adev->rings[0]->sched; (*job)->vm = vm; - amdgpu_sync_create(&(*job)->sync); - amdgpu_sync_create(&(*job)->sched_sync); + amdgpu_sync_create(&(*job)->explicit_sync); (*job)->vram_lost_counter = atomic_read(&adev->vram_lost_counter); (*job)->vm_pd_addr = AMDGPU_BO_INVALID_OFFSET; - return 0; + if (!entity) + return 0; + + return drm_sched_job_init(&(*job)->base, entity, owner); } -int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, - enum amdgpu_ib_pool_type pool_type, - struct amdgpu_job **job) +int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, + struct drm_sched_entity *entity, void *owner, + size_t size, enum amdgpu_ib_pool_type pool_type, + struct amdgpu_job **job) { int r; - r = amdgpu_job_alloc(adev, 1, job, NULL); + r = amdgpu_job_alloc(adev, NULL, entity, owner, 1, job); if (r) return r; (*job)->num_ibs = 1; r = amdgpu_ib_get(adev, NULL, size, pool_type, &(*job)->ibs[0]); - if (r) + if (r) { + if (entity) + drm_sched_job_cleanup(&(*job)->base); kfree(*job); + } return r; } @@ -166,10 +173,13 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job) drm_sched_job_cleanup(s_job); - amdgpu_sync_free(&job->sync); - amdgpu_sync_free(&job->sched_sync); + amdgpu_sync_free(&job->explicit_sync); - dma_fence_put(&job->hw_fence); + /* only put the hw fence if has embedded fence */ + if (!job->hw_fence.ops) + kfree(job); + else + dma_fence_put(&job->hw_fence); } void amdgpu_job_set_gang_leader(struct amdgpu_job *job, @@ -190,9 +200,11 @@ void amdgpu_job_set_gang_leader(struct amdgpu_job *job, void amdgpu_job_free(struct amdgpu_job *job) { + if (job->base.entity) + drm_sched_job_cleanup(&job->base); + amdgpu_job_free_resources(job); - amdgpu_sync_free(&job->sync); - amdgpu_sync_free(&job->sched_sync); + amdgpu_sync_free(&job->explicit_sync); if (job->gang_submit != &job->base.s_fence->scheduled) dma_fence_put(job->gang_submit); @@ -202,25 +214,16 @@ void amdgpu_job_free(struct amdgpu_job *job) dma_fence_put(&job->hw_fence); } -int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, - void *owner, struct dma_fence **f) +struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job) { - int r; - - if (!f) - return -EINVAL; - - r = drm_sched_job_init(&job->base, entity, owner); - if (r) - return r; + struct dma_fence *f; drm_sched_job_arm(&job->base); - - *f = dma_fence_get(&job->base.s_fence->finished); + f = dma_fence_get(&job->base.s_fence->finished); amdgpu_job_free_resources(job); drm_sched_entity_push_job(&job->base); - return 0; + return f; } int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring, @@ -238,35 +241,24 @@ int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring, return 0; } -static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job, - struct drm_sched_entity *s_entity) +static struct dma_fence * +amdgpu_job_prepare_job(struct drm_sched_job *sched_job, + struct drm_sched_entity *s_entity) { struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->rq->sched); struct amdgpu_job *job = to_amdgpu_job(sched_job); - struct amdgpu_vm *vm = job->vm; - struct dma_fence *fence; + struct dma_fence *fence = NULL; int r; - fence = amdgpu_sync_get_fence(&job->sync); - if (fence && drm_sched_dependency_optimized(fence, s_entity)) { - r = amdgpu_sync_fence(&job->sched_sync, fence); - if (r) - DRM_ERROR("Error adding fence (%d)\n", r); - } + if (!fence && job->gang_submit) + fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); - while (fence == NULL && vm && !job->vmid) { - r = amdgpu_vmid_grab(vm, ring, &job->sync, - &job->base.s_fence->finished, - job); + while (!fence && job->vm && !job->vmid) { + r = amdgpu_vmid_grab(job->vm, ring, job, &fence); if (r) DRM_ERROR("Error getting VM ID (%d)\n", r); - - fence = amdgpu_sync_get_fence(&job->sync); } - if (!fence && job->gang_submit) - fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); - return fence; } @@ -281,8 +273,6 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) job = to_amdgpu_job(sched_job); finished = &job->base.s_fence->finished; - BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL)); - trace_amdgpu_sched_run_job(job); /* Skip job if VRAM is lost and never resubmit gangs */ @@ -341,7 +331,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) } const struct drm_sched_backend_ops amdgpu_sched_ops = { - .dependency = amdgpu_job_dependency, + .prepare_job = amdgpu_job_prepare_job, .run_job = amdgpu_job_run, .timedout_job = amdgpu_job_timedout, .free_job = amdgpu_job_free_cb diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h index ab7b150e5d50..52f2e313ea17 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h @@ -47,13 +47,14 @@ enum amdgpu_ib_pool_type; struct amdgpu_job { struct drm_sched_job base; struct amdgpu_vm *vm; - struct amdgpu_sync sync; - struct amdgpu_sync sched_sync; + struct amdgpu_sync explicit_sync; struct dma_fence hw_fence; struct dma_fence *gang_submit; uint32_t preamble_status; uint32_t preemption_status; bool vm_needs_flush; + bool gds_switch_needed; + bool spm_update_needed; uint64_t vm_pd_addr; unsigned vmid; unsigned pasid; @@ -78,18 +79,20 @@ static inline struct amdgpu_ring *amdgpu_job_ring(struct amdgpu_job *job) return to_amdgpu_ring(job->base.entity->rq->sched); } -int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, - struct amdgpu_job **job, struct amdgpu_vm *vm); -int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, - enum amdgpu_ib_pool_type pool, struct amdgpu_job **job); +int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct drm_sched_entity *entity, void *owner, + unsigned int num_ibs, struct amdgpu_job **job); +int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, + struct drm_sched_entity *entity, void *owner, + size_t size, enum amdgpu_ib_pool_type pool_type, + struct amdgpu_job **job); void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, struct amdgpu_bo *gws, struct amdgpu_bo *oa); void amdgpu_job_free_resources(struct amdgpu_job *job); void amdgpu_job_set_gang_leader(struct amdgpu_job *job, struct amdgpu_job *leader); void amdgpu_job_free(struct amdgpu_job *job); -int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity, - void *owner, struct dma_fence **f); +struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job); int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring, struct dma_fence **fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c index 518eb0e40d32..6f81ed4fb0d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c @@ -150,14 +150,15 @@ static int amdgpu_jpeg_dec_set_reg(struct amdgpu_ring *ring, uint32_t handle, const unsigned ib_size_dw = 16; int i, r; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, + AMDGPU_IB_POOL_DIRECT, &job); if (r) return r; ib = &job->ibs[0]; - ib->ptr[0] = PACKETJ(adev->jpeg.internal.jpeg_pitch, 0, 0, PACKETJ_TYPE0); + ib->ptr[0] = PACKETJ(adev->jpeg.internal.jpeg_pitch, 0, 0, + PACKETJ_TYPE0); ib->ptr[1] = 0xDEADBEEF; for (i = 2; i < 16; i += 2) { ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6); @@ -234,3 +235,20 @@ int amdgpu_jpeg_process_poison_irq(struct amdgpu_device *adev, return 0; } + +void jpeg_set_ras_funcs(struct amdgpu_device *adev) +{ + if (!adev->jpeg.ras) + return; + + amdgpu_ras_register_ras_block(adev, &adev->jpeg.ras->ras_block); + + strcpy(adev->jpeg.ras->ras_block.ras_comm.name, "jpeg"); + adev->jpeg.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__JPEG; + adev->jpeg.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__POISON; + adev->jpeg.ras_if = &adev->jpeg.ras->ras_block.ras_comm; + + /* If don't define special ras_late_init function, use default ras_late_init */ + if (!adev->jpeg.ras->ras_block.ras_late_init) + adev->jpeg.ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h index 635dca59a70a..e8ca3e32ad52 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h @@ -72,5 +72,6 @@ int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout); int amdgpu_jpeg_process_poison_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +void jpeg_set_ras_funcs(struct amdgpu_device *adev); #endif /*__AMDGPU_JPEG_H__*/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d75e0370a074..7aa7e52ca784 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -29,6 +29,7 @@ #include "amdgpu.h" #include <drm/amdgpu_drm.h> #include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> #include "amdgpu_uvd.h" #include "amdgpu_vce.h" #include "atom.h" @@ -430,7 +431,7 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev, case AMDGPU_HW_IP_VCN_DEC: type = AMD_IP_BLOCK_TYPE_VCN; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (adev->uvd.harvest_config & (1 << i)) + if (adev->vcn.harvest_config & (1 << i)) continue; if (adev->vcn.inst[i].ring_dec.sched.ready) @@ -442,7 +443,7 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev, case AMDGPU_HW_IP_VCN_ENC: type = AMD_IP_BLOCK_TYPE_VCN; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (adev->uvd.harvest_config & (1 << i)) + if (adev->vcn.harvest_config & (1 << i)) continue; for (j = 0; j < adev->vcn.num_enc_rings; j++) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 37322550d750..8a39300b1a84 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -36,7 +36,6 @@ #include <drm/drm_encoder.h> #include <drm/drm_fixed.h> #include <drm/drm_crtc_helper.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_probe_helper.h> #include <linux/i2c.h> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 974e85d8b6cc..4e684c2afc70 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -346,17 +346,16 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev, * @adev: amdgpu device object * @offset: offset of the BO * @size: size of the BO - * @domain: where to place it * @bo_ptr: used to initialize BOs in structures * @cpu_addr: optional CPU address mapping * - * Creates a kernel BO at a specific offset in the address space of the domain. + * Creates a kernel BO at a specific offset in VRAM. * * Returns: * 0 on success, negative error code otherwise. */ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, - uint64_t offset, uint64_t size, uint32_t domain, + uint64_t offset, uint64_t size, struct amdgpu_bo **bo_ptr, void **cpu_addr) { struct ttm_operation_ctx ctx = { false, false }; @@ -366,8 +365,9 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, offset &= PAGE_MASK; size = ALIGN(size, PAGE_SIZE); - r = amdgpu_bo_create_reserved(adev, size, PAGE_SIZE, domain, bo_ptr, - NULL, cpu_addr); + r = amdgpu_bo_create_reserved(adev, size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, bo_ptr, NULL, + cpu_addr); if (r) return r; @@ -422,6 +422,8 @@ void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr, if (*bo == NULL) return; + WARN_ON(amdgpu_ttm_adev((*bo)->tbo.bdev)->in_suspend); + if (likely(amdgpu_bo_reserve(*bo, true) == 0)) { if (cpu_addr) amdgpu_bo_kunmap(*bo); @@ -446,27 +448,24 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev, /* * If GTT is part of requested domains the check must succeed to - * allow fall back to GTT + * allow fall back to GTT. */ if (domain & AMDGPU_GEM_DOMAIN_GTT) { man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT); - if (size < man->size) + if (man && size < man->size) return true; - else - goto fail; - } - - if (domain & AMDGPU_GEM_DOMAIN_VRAM) { + else if (!man) + WARN_ON_ONCE("GTT domain requested but GTT mem manager uninitialized"); + goto fail; + } else if (domain & AMDGPU_GEM_DOMAIN_VRAM) { man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); - if (size < man->size) + if (man && size < man->size) return true; - else - goto fail; + goto fail; } - /* TODO add more domains checks, such as AMDGPU_GEM_DOMAIN_CPU */ return true; @@ -1510,7 +1509,8 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, uint32_t domain) { - if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) { + if ((domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) && + ((adev->asic_type == CHIP_CARRIZO) || (adev->asic_type == CHIP_STONEY))) { domain = AMDGPU_GEM_DOMAIN_VRAM; if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD) domain = AMDGPU_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 147b79c10cbb..93207badf83f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -284,7 +284,7 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev, u32 domain, struct amdgpu_bo **bo_ptr, u64 *gpu_addr, void **cpu_addr); int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, - uint64_t offset, uint64_t size, uint32_t domain, + uint64_t offset, uint64_t size, struct amdgpu_bo **bo_ptr, void **cpu_addr); int amdgpu_bo_create_user(struct amdgpu_device *adev, struct amdgpu_bo_param *bp, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 2fcb5bfbef89..7a2fc920739b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -52,6 +52,32 @@ static int psp_load_smu_fw(struct psp_context *psp); static int psp_rap_terminate(struct psp_context *psp); static int psp_securedisplay_terminate(struct psp_context *psp); +static int psp_ring_init(struct psp_context *psp, + enum psp_ring_type ring_type) +{ + int ret = 0; + struct psp_ring *ring; + struct amdgpu_device *adev = psp->adev; + + ring = &psp->km_ring; + + ring->ring_type = ring_type; + + /* allocate 4k Page of Local Frame Buffer memory for ring */ + ring->ring_size = 0x1000; + ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &adev->firmware.rbuf, + &ring->ring_mem_mc_addr, + (void **)&ring->ring_mem); + if (ret) { + ring->ring_size = 0; + return ret; + } + + return 0; +} + /* * Due to DF Cstate management centralized to PMFW, the firmware * loading sequence will be updated as below: @@ -139,6 +165,7 @@ static int psp_early_init(void *handle) case IP_VERSION(13, 0, 5): case IP_VERSION(13, 0, 8): case IP_VERSION(13, 0, 10): + case IP_VERSION(13, 0, 11): psp_v13_0_set_psp_funcs(psp); psp->autoload_supported = true; break; @@ -172,6 +199,7 @@ void psp_ta_free_shared_buf(struct ta_mem_context *mem_ctx) { amdgpu_bo_free_kernel(&mem_ctx->shared_bo, &mem_ctx->shared_mc_addr, &mem_ctx->shared_buf); + mem_ctx->shared_bo = NULL; } static void psp_free_shared_bufs(struct psp_context *psp) @@ -182,6 +210,7 @@ static void psp_free_shared_bufs(struct psp_context *psp) /* free TMR memory buffer */ pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr); + psp->tmr_bo = NULL; /* free xgmi shared memory */ psp_ta_free_shared_buf(&psp->xgmi_context.context.mem_context); @@ -484,26 +513,22 @@ static int psp_sw_fini(void *handle) struct psp_gfx_cmd_resp *cmd = psp->cmd; psp_memory_training_fini(psp); - if (psp->sos_fw) { - release_firmware(psp->sos_fw); - psp->sos_fw = NULL; - } - if (psp->asd_fw) { - release_firmware(psp->asd_fw); - psp->asd_fw = NULL; - } - if (psp->ta_fw) { - release_firmware(psp->ta_fw); - psp->ta_fw = NULL; - } - if (psp->cap_fw) { - release_firmware(psp->cap_fw); - psp->cap_fw = NULL; - } - if (psp->toc_fw) { - release_firmware(psp->toc_fw); - psp->toc_fw = NULL; - } + + release_firmware(psp->sos_fw); + psp->sos_fw = NULL; + + release_firmware(psp->asd_fw); + psp->asd_fw = NULL; + + release_firmware(psp->ta_fw); + psp->ta_fw = NULL; + + release_firmware(psp->cap_fw); + psp->cap_fw = NULL; + + release_firmware(psp->toc_fw); + psp->toc_fw = NULL; + if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 0) || adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 7)) psp_sysfs_fini(adev); @@ -743,7 +768,7 @@ static int psp_load_toc(struct psp_context *psp, /* Set up Trusted Memory Region */ static int psp_tmr_init(struct psp_context *psp) { - int ret; + int ret = 0; int tmr_size; void *tmr_buf; void **pptr; @@ -770,10 +795,12 @@ static int psp_tmr_init(struct psp_context *psp) } } - pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; - ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, - AMDGPU_GEM_DOMAIN_VRAM, - &psp->tmr_bo, &psp->tmr_mc_addr, pptr); + if (!psp->tmr_bo) { + pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; + ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, + AMDGPU_GEM_DOMAIN_VRAM, + &psp->tmr_bo, &psp->tmr_mc_addr, pptr); + } return ret; } @@ -831,7 +858,7 @@ static int psp_tmr_unload(struct psp_context *psp) struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp); psp_prep_tmr_unload_cmd_buf(psp, cmd); - dev_info(psp->adev->dev, "free PSP TMR buffer\n"); + dev_dbg(psp->adev->dev, "free PSP TMR buffer\n"); ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); @@ -1526,11 +1553,6 @@ int psp_ras_initialize(struct psp_context *psp) if (amdgpu_sriov_vf(adev)) return 0; - if (psp->ras_context.context.initialized) { - dev_warn(adev->dev, "RAS WARN: TA has already been loaded\n"); - return 0; - } - if (!adev->psp.ras_context.context.bin_desc.size_bytes || !adev->psp.ras_context.context.bin_desc.start_addr) { dev_info(adev->dev, "RAS: optional ras ta ucode is not available\n"); @@ -1602,6 +1624,9 @@ int psp_ras_initialize(struct psp_context *psp) else { if (ras_cmd->ras_status) dev_warn(psp->adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status); + + /* fail to load RAS TA */ + psp->ras_context.context.initialized = false; } return ret; @@ -2703,8 +2728,6 @@ static int psp_suspend(void *handle) } out: - psp_free_shared_bufs(psp); - return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index cbd4194a2883..cf4f60c66122 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -118,7 +118,6 @@ struct psp_funcs int (*bootloader_load_dbg_drv)(struct psp_context *psp); int (*bootloader_load_ras_drv)(struct psp_context *psp); int (*bootloader_load_sos)(struct psp_context *psp); - int (*ring_init)(struct psp_context *psp, enum psp_ring_type ring_type); int (*ring_create)(struct psp_context *psp, enum psp_ring_type ring_type); int (*ring_stop)(struct psp_context *psp, @@ -396,7 +395,6 @@ struct amdgpu_psp_funcs { }; -#define psp_ring_init(psp, type) (psp)->funcs->ring_init((psp), (type)) #define psp_ring_create(psp, type) (psp)->funcs->ring_create((psp), (type)) #define psp_ring_stop(psp, type) (psp)->funcs->ring_stop((psp), (type)) #define psp_ring_destroy(psp, type) ((psp)->funcs->ring_destroy((psp), (type))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 693bce07eb46..ad490c1e2f57 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1267,7 +1267,7 @@ static ssize_t amdgpu_ras_sysfs_features_read(struct device *dev, struct amdgpu_ras *con = container_of(attr, struct amdgpu_ras, features_attr); - return scnprintf(buf, PAGE_SIZE, "feature mask: 0x%x\n", con->features); + return sysfs_emit(buf, "feature mask: 0x%x\n", con->features); } static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev) @@ -1948,7 +1948,12 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) reset_context.method = AMD_RESET_METHOD_NONE; reset_context.reset_req_dev = adev; - clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + + /* Perform full reset in fatal error mode */ + if (!amdgpu_ras_is_poison_mode_supported(ras->adev)) + set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + else + clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context); } @@ -2343,7 +2348,8 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev) adev->ras_hw_enabled |= ~(1 << AMDGPU_RAS_BLOCK__UMC | 1 << AMDGPU_RAS_BLOCK__DF); - if (adev->ip_versions[VCN_HWIP][0] == IP_VERSION(2, 6, 0)) + if (adev->ip_versions[VCN_HWIP][0] == IP_VERSION(2, 6, 0) || + adev->ip_versions[VCN_HWIP][0] == IP_VERSION(4, 0, 0)) adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__VCN | 1 << AMDGPU_RAS_BLOCK__JPEG); else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 7268ae65c140..2d9f3f4cd79e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -33,12 +33,29 @@ #include "amdgpu_reset.h" -#define EEPROM_I2C_MADDR_VEGA20 0x0 -#define EEPROM_I2C_MADDR_ARCTURUS 0x40000 -#define EEPROM_I2C_MADDR_ARCTURUS_D342 0x0 -#define EEPROM_I2C_MADDR_SIENNA_CICHLID 0x0 -#define EEPROM_I2C_MADDR_ALDEBARAN 0x0 -#define EEPROM_I2C_MADDR_54H (0x54UL << 16) +/* These are memory addresses as would be seen by one or more EEPROM + * chips strung on the I2C bus, usually by manipulating pins 1-3 of a + * set of EEPROM devices. They form a continuous memory space. + * + * The I2C device address includes the device type identifier, 1010b, + * which is a reserved value and indicates that this is an I2C EEPROM + * device. It also includes the top 3 bits of the 19 bit EEPROM memory + * address, namely bits 18, 17, and 16. This makes up the 7 bit + * address sent on the I2C bus with bit 0 being the direction bit, + * which is not represented here, and sent by the hardware directly. + * + * For instance, + * 50h = 1010000b => device type identifier 1010b, bits 18:16 = 000b, address 0. + * 54h = 1010100b => --"--, bits 18:16 = 100b, address 40000h. + * 56h = 1010110b => --"--, bits 18:16 = 110b, address 60000h. + * Depending on the size of the I2C EEPROM device(s), bits 18:16 may + * address memory in a device or a device on the I2C bus, depending on + * the status of pins 1-3. See top of amdgpu_eeprom.c. + * + * The RAS table lives either at address 0 or address 40000h of EEPROM. + */ +#define EEPROM_I2C_MADDR_0 0x0 +#define EEPROM_I2C_MADDR_4 0x40000 /* * The 2 macros bellow represent the actual size in bytes that @@ -117,9 +134,9 @@ static bool __get_eeprom_i2c_addr_arct(struct amdgpu_device *adev, if (strnstr(atom_ctx->vbios_version, "D342", sizeof(atom_ctx->vbios_version))) - control->i2c_address = EEPROM_I2C_MADDR_ARCTURUS_D342; + control->i2c_address = EEPROM_I2C_MADDR_0; else - control->i2c_address = EEPROM_I2C_MADDR_ARCTURUS; + control->i2c_address = EEPROM_I2C_MADDR_4; return true; } @@ -130,7 +147,7 @@ static bool __get_eeprom_i2c_addr_ip_discovery(struct amdgpu_device *adev, switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 0): case IP_VERSION(13, 0, 10): - control->i2c_address = EEPROM_I2C_MADDR_54H; + control->i2c_address = EEPROM_I2C_MADDR_4; return true; default: return false; @@ -140,6 +157,7 @@ static bool __get_eeprom_i2c_addr_ip_discovery(struct amdgpu_device *adev, static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, struct amdgpu_ras_eeprom_control *control) { + struct atom_context *atom_ctx = adev->mode_info.atom_context; u8 i2c_addr; if (!control) @@ -162,18 +180,22 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, switch (adev->asic_type) { case CHIP_VEGA20: - control->i2c_address = EEPROM_I2C_MADDR_VEGA20; + control->i2c_address = EEPROM_I2C_MADDR_0; break; case CHIP_ARCTURUS: return __get_eeprom_i2c_addr_arct(adev, control); case CHIP_SIENNA_CICHLID: - control->i2c_address = EEPROM_I2C_MADDR_SIENNA_CICHLID; + control->i2c_address = EEPROM_I2C_MADDR_0; break; case CHIP_ALDEBARAN: - control->i2c_address = EEPROM_I2C_MADDR_ALDEBARAN; + if (strnstr(atom_ctx->vbios_version, "D673", + sizeof(atom_ctx->vbios_version))) + control->i2c_address = EEPROM_I2C_MADDR_4; + else + control->i2c_address = EEPROM_I2C_MADDR_0; break; case CHIP_IP_DISCOVERY: @@ -185,7 +207,7 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 0): - control->i2c_address = EEPROM_I2C_MADDR_54H; + control->i2c_address = EEPROM_I2C_MADDR_4; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index d3558c34d406..dc474b809604 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -569,3 +569,15 @@ int amdgpu_ring_init_mqd(struct amdgpu_ring *ring) return mqd_mgr->init_mqd(adev, ring->mqd_ptr, &prop); } + +void amdgpu_ring_ib_begin(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_begin(ring); +} + +void amdgpu_ring_ib_end(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_end(ring); +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 82c178a9033a..f752c7ae7f60 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -39,6 +39,7 @@ struct amdgpu_vm; #define AMDGPU_MAX_RINGS 28 #define AMDGPU_MAX_HWIP_RINGS 8 #define AMDGPU_MAX_GFX_RINGS 2 +#define AMDGPU_MAX_SW_GFX_RINGS 2 #define AMDGPU_MAX_COMPUTE_RINGS 8 #define AMDGPU_MAX_VCE_RINGS 3 #define AMDGPU_MAX_UVD_ENC_RINGS 2 @@ -59,6 +60,7 @@ enum amdgpu_ring_priority_level { #define AMDGPU_FENCE_FLAG_64BIT (1 << 0) #define AMDGPU_FENCE_FLAG_INT (1 << 1) #define AMDGPU_FENCE_FLAG_TC_WB_ONLY (1 << 2) +#define AMDGPU_FENCE_FLAG_EXEC (1 << 3) #define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched) @@ -143,8 +145,13 @@ signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring, uint32_t wait_seq, signed long timeout); unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring); + void amdgpu_fence_driver_isr_toggle(struct amdgpu_device *adev, bool stop); +u64 amdgpu_fence_last_unsignaled_time_us(struct amdgpu_ring *ring); +void amdgpu_fence_update_start_timestamp(struct amdgpu_ring *ring, uint32_t seq, + ktime_t timestamp); + /* * Rings. */ @@ -279,6 +286,10 @@ struct amdgpu_ring { bool is_mes_queue; uint32_t hw_queue_id; struct amdgpu_mes_ctx_data *mes_ctx; + + bool is_sw_ring; + unsigned int entry_index; + }; #define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib))) @@ -307,6 +318,9 @@ struct amdgpu_ring { #define amdgpu_ring_preempt_ib(r) (r)->funcs->preempt_ib(r) int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw); +void amdgpu_ring_ib_begin(struct amdgpu_ring *ring); +void amdgpu_ring_ib_end(struct amdgpu_ring *ring); + void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count); void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c new file mode 100644 index 000000000000..62079f0e3ee8 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c @@ -0,0 +1,514 @@ +/* + * Copyright 2022 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ +#include <linux/slab.h> +#include <drm/drm_print.h> + +#include "amdgpu_ring_mux.h" +#include "amdgpu_ring.h" +#include "amdgpu.h" + +#define AMDGPU_MUX_RESUBMIT_JIFFIES_TIMEOUT (HZ / 2) +#define AMDGPU_MAX_LAST_UNSIGNALED_THRESHOLD_US 10000 + +static const struct ring_info { + unsigned int hw_pio; + const char *ring_name; +} sw_ring_info[] = { + { AMDGPU_RING_PRIO_DEFAULT, "gfx_low"}, + { AMDGPU_RING_PRIO_2, "gfx_high"}, +}; + +static struct kmem_cache *amdgpu_mux_chunk_slab; + +static inline struct amdgpu_mux_entry *amdgpu_ring_mux_sw_entry(struct amdgpu_ring_mux *mux, + struct amdgpu_ring *ring) +{ + return ring->entry_index < mux->ring_entry_size ? + &mux->ring_entry[ring->entry_index] : NULL; +} + +/* copy packages on sw ring range[begin, end) */ +static void amdgpu_ring_mux_copy_pkt_from_sw_ring(struct amdgpu_ring_mux *mux, + struct amdgpu_ring *ring, + u64 s_start, u64 s_end) +{ + u64 start, end; + struct amdgpu_ring *real_ring = mux->real_ring; + + start = s_start & ring->buf_mask; + end = s_end & ring->buf_mask; + + if (start == end) { + DRM_ERROR("no more data copied from sw ring\n"); + return; + } + if (start > end) { + amdgpu_ring_alloc(real_ring, (ring->ring_size >> 2) + end - start); + amdgpu_ring_write_multiple(real_ring, (void *)&ring->ring[start], + (ring->ring_size >> 2) - start); + amdgpu_ring_write_multiple(real_ring, (void *)&ring->ring[0], end); + } else { + amdgpu_ring_alloc(real_ring, end - start); + amdgpu_ring_write_multiple(real_ring, (void *)&ring->ring[start], end - start); + } +} + +static void amdgpu_mux_resubmit_chunks(struct amdgpu_ring_mux *mux) +{ + struct amdgpu_mux_entry *e = NULL; + struct amdgpu_mux_chunk *chunk; + uint32_t seq, last_seq; + int i; + + /*find low priority entries:*/ + if (!mux->s_resubmit) + return; + + for (i = 0; i < mux->num_ring_entries; i++) { + if (mux->ring_entry[i].ring->hw_prio <= AMDGPU_RING_PRIO_DEFAULT) { + e = &mux->ring_entry[i]; + break; + } + } + + if (!e) { + DRM_ERROR("%s no low priority ring found\n", __func__); + return; + } + + last_seq = atomic_read(&e->ring->fence_drv.last_seq); + seq = mux->seqno_to_resubmit; + if (last_seq < seq) { + /*resubmit all the fences between (last_seq, seq]*/ + list_for_each_entry(chunk, &e->list, entry) { + if (chunk->sync_seq > last_seq && chunk->sync_seq <= seq) { + amdgpu_fence_update_start_timestamp(e->ring, + chunk->sync_seq, + ktime_get()); + amdgpu_ring_mux_copy_pkt_from_sw_ring(mux, e->ring, + chunk->start, + chunk->end); + mux->wptr_resubmit = chunk->end; + amdgpu_ring_commit(mux->real_ring); + } + } + } + + del_timer(&mux->resubmit_timer); + mux->s_resubmit = false; +} + +static void amdgpu_ring_mux_schedule_resubmit(struct amdgpu_ring_mux *mux) +{ + mod_timer(&mux->resubmit_timer, jiffies + AMDGPU_MUX_RESUBMIT_JIFFIES_TIMEOUT); +} + +static void amdgpu_mux_resubmit_fallback(struct timer_list *t) +{ + struct amdgpu_ring_mux *mux = from_timer(mux, t, resubmit_timer); + + if (!spin_trylock(&mux->lock)) { + amdgpu_ring_mux_schedule_resubmit(mux); + DRM_ERROR("reschedule resubmit\n"); + return; + } + amdgpu_mux_resubmit_chunks(mux); + spin_unlock(&mux->lock); +} + +int amdgpu_ring_mux_init(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring, + unsigned int entry_size) +{ + mux->real_ring = ring; + mux->num_ring_entries = 0; + + mux->ring_entry = kcalloc(entry_size, sizeof(struct amdgpu_mux_entry), GFP_KERNEL); + if (!mux->ring_entry) + return -ENOMEM; + + mux->ring_entry_size = entry_size; + mux->s_resubmit = false; + + amdgpu_mux_chunk_slab = kmem_cache_create("amdgpu_mux_chunk", + sizeof(struct amdgpu_mux_chunk), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!amdgpu_mux_chunk_slab) { + DRM_ERROR("create amdgpu_mux_chunk cache failed\n"); + return -ENOMEM; + } + + spin_lock_init(&mux->lock); + timer_setup(&mux->resubmit_timer, amdgpu_mux_resubmit_fallback, 0); + + return 0; +} + +void amdgpu_ring_mux_fini(struct amdgpu_ring_mux *mux) +{ + struct amdgpu_mux_entry *e; + struct amdgpu_mux_chunk *chunk, *chunk2; + int i; + + for (i = 0; i < mux->num_ring_entries; i++) { + e = &mux->ring_entry[i]; + list_for_each_entry_safe(chunk, chunk2, &e->list, entry) { + list_del(&chunk->entry); + kmem_cache_free(amdgpu_mux_chunk_slab, chunk); + } + } + kmem_cache_destroy(amdgpu_mux_chunk_slab); + kfree(mux->ring_entry); + mux->ring_entry = NULL; + mux->num_ring_entries = 0; + mux->ring_entry_size = 0; +} + +int amdgpu_ring_mux_add_sw_ring(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) +{ + struct amdgpu_mux_entry *e; + + if (mux->num_ring_entries >= mux->ring_entry_size) { + DRM_ERROR("add sw ring exceeding max entry size\n"); + return -ENOENT; + } + + e = &mux->ring_entry[mux->num_ring_entries]; + ring->entry_index = mux->num_ring_entries; + e->ring = ring; + + INIT_LIST_HEAD(&e->list); + mux->num_ring_entries += 1; + return 0; +} + +void amdgpu_ring_mux_set_wptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring, u64 wptr) +{ + struct amdgpu_mux_entry *e; + + spin_lock(&mux->lock); + + if (ring->hw_prio <= AMDGPU_RING_PRIO_DEFAULT) + amdgpu_mux_resubmit_chunks(mux); + + e = amdgpu_ring_mux_sw_entry(mux, ring); + if (!e) { + DRM_ERROR("cannot find entry for sw ring\n"); + spin_unlock(&mux->lock); + return; + } + + /* We could skip this set wptr as preemption in process. */ + if (ring->hw_prio <= AMDGPU_RING_PRIO_DEFAULT && mux->pending_trailing_fence_signaled) { + spin_unlock(&mux->lock); + return; + } + + e->sw_cptr = e->sw_wptr; + /* Update cptr if the package already copied in resubmit functions */ + if (ring->hw_prio <= AMDGPU_RING_PRIO_DEFAULT && e->sw_cptr < mux->wptr_resubmit) + e->sw_cptr = mux->wptr_resubmit; + e->sw_wptr = wptr; + e->start_ptr_in_hw_ring = mux->real_ring->wptr; + + /* Skip copying for the packages already resubmitted.*/ + if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT || mux->wptr_resubmit < wptr) { + amdgpu_ring_mux_copy_pkt_from_sw_ring(mux, ring, e->sw_cptr, wptr); + e->end_ptr_in_hw_ring = mux->real_ring->wptr; + amdgpu_ring_commit(mux->real_ring); + } else { + e->end_ptr_in_hw_ring = mux->real_ring->wptr; + } + spin_unlock(&mux->lock); +} + +u64 amdgpu_ring_mux_get_wptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) +{ + struct amdgpu_mux_entry *e; + + e = amdgpu_ring_mux_sw_entry(mux, ring); + if (!e) { + DRM_ERROR("cannot find entry for sw ring\n"); + return 0; + } + + return e->sw_wptr; +} + +/** + * amdgpu_ring_mux_get_rptr - get the readptr of the software ring + * @mux: the multiplexer the software rings attach to + * @ring: the software ring of which we calculate the readptr + * + * The return value of the readptr is not precise while the other rings could + * write data onto the real ring buffer.After overwriting on the real ring, we + * can not decide if our packages have been excuted or not read yet. However, + * this function is only called by the tools such as umr to collect the latest + * packages for the hang analysis. We assume the hang happens near our latest + * submit. Thus we could use the following logic to give the clue: + * If the readptr is between start and end, then we return the copy pointer + * plus the distance from start to readptr. If the readptr is before start, we + * return the copy pointer. Lastly, if the readptr is past end, we return the + * write pointer. + */ +u64 amdgpu_ring_mux_get_rptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) +{ + struct amdgpu_mux_entry *e; + u64 readp, offset, start, end; + + e = amdgpu_ring_mux_sw_entry(mux, ring); + if (!e) { + DRM_ERROR("no sw entry found!\n"); + return 0; + } + + readp = amdgpu_ring_get_rptr(mux->real_ring); + + start = e->start_ptr_in_hw_ring & mux->real_ring->buf_mask; + end = e->end_ptr_in_hw_ring & mux->real_ring->buf_mask; + if (start > end) { + if (readp <= end) + readp += mux->real_ring->ring_size >> 2; + end += mux->real_ring->ring_size >> 2; + } + + if (start <= readp && readp <= end) { + offset = readp - start; + e->sw_rptr = (e->sw_cptr + offset) & ring->buf_mask; + } else if (readp < start) { + e->sw_rptr = e->sw_cptr; + } else { + /* end < readptr */ + e->sw_rptr = e->sw_wptr; + } + + return e->sw_rptr; +} + +u64 amdgpu_sw_ring_get_rptr_gfx(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ring_mux *mux = &adev->gfx.muxer; + + WARN_ON(!ring->is_sw_ring); + return amdgpu_ring_mux_get_rptr(mux, ring); +} + +u64 amdgpu_sw_ring_get_wptr_gfx(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ring_mux *mux = &adev->gfx.muxer; + + WARN_ON(!ring->is_sw_ring); + return amdgpu_ring_mux_get_wptr(mux, ring); +} + +void amdgpu_sw_ring_set_wptr_gfx(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ring_mux *mux = &adev->gfx.muxer; + + WARN_ON(!ring->is_sw_ring); + amdgpu_ring_mux_set_wptr(mux, ring, ring->wptr); +} + +/* Override insert_nop to prevent emitting nops to the software rings */ +void amdgpu_sw_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) +{ + WARN_ON(!ring->is_sw_ring); +} + +const char *amdgpu_sw_ring_name(int idx) +{ + return idx < ARRAY_SIZE(sw_ring_info) ? + sw_ring_info[idx].ring_name : NULL; +} + +unsigned int amdgpu_sw_ring_priority(int idx) +{ + return idx < ARRAY_SIZE(sw_ring_info) ? + sw_ring_info[idx].hw_pio : AMDGPU_RING_PRIO_DEFAULT; +} + +/*Scan on low prio rings to have unsignaled fence and high ring has no fence.*/ +static int amdgpu_mcbp_scan(struct amdgpu_ring_mux *mux) +{ + struct amdgpu_ring *ring; + int i, need_preempt; + + need_preempt = 0; + for (i = 0; i < mux->num_ring_entries; i++) { + ring = mux->ring_entry[i].ring; + if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT && + amdgpu_fence_count_emitted(ring) > 0) + return 0; + if (ring->hw_prio <= AMDGPU_RING_PRIO_DEFAULT && + amdgpu_fence_last_unsignaled_time_us(ring) > + AMDGPU_MAX_LAST_UNSIGNALED_THRESHOLD_US) + need_preempt = 1; + } + return need_preempt && !mux->s_resubmit; +} + +/* Trigger Mid-Command Buffer Preemption (MCBP) and find if we need to resubmit. */ +static int amdgpu_mcbp_trigger_preempt(struct amdgpu_ring_mux *mux) +{ + int r; + + spin_lock(&mux->lock); + mux->pending_trailing_fence_signaled = true; + r = amdgpu_ring_preempt_ib(mux->real_ring); + spin_unlock(&mux->lock); + return r; +} + +void amdgpu_sw_ring_ib_begin(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ring_mux *mux = &adev->gfx.muxer; + + WARN_ON(!ring->is_sw_ring); + if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT) { + if (amdgpu_mcbp_scan(mux) > 0) + amdgpu_mcbp_trigger_preempt(mux); + return; + } + + amdgpu_ring_mux_start_ib(mux, ring); +} + +void amdgpu_sw_ring_ib_end(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ring_mux *mux = &adev->gfx.muxer; + + WARN_ON(!ring->is_sw_ring); + if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT) + return; + amdgpu_ring_mux_end_ib(mux, ring); +} + +void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) +{ + struct amdgpu_mux_entry *e; + struct amdgpu_mux_chunk *chunk; + + spin_lock(&mux->lock); + amdgpu_mux_resubmit_chunks(mux); + spin_unlock(&mux->lock); + + e = amdgpu_ring_mux_sw_entry(mux, ring); + if (!e) { + DRM_ERROR("cannot find entry!\n"); + return; + } + + chunk = kmem_cache_alloc(amdgpu_mux_chunk_slab, GFP_KERNEL); + if (!chunk) { + DRM_ERROR("alloc amdgpu_mux_chunk_slab failed\n"); + return; + } + + chunk->start = ring->wptr; + list_add_tail(&chunk->entry, &e->list); +} + +static void scan_and_remove_signaled_chunk(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) +{ + uint32_t last_seq = 0; + struct amdgpu_mux_entry *e; + struct amdgpu_mux_chunk *chunk, *tmp; + + e = amdgpu_ring_mux_sw_entry(mux, ring); + if (!e) { + DRM_ERROR("cannot find entry!\n"); + return; + } + + last_seq = atomic_read(&ring->fence_drv.last_seq); + + list_for_each_entry_safe(chunk, tmp, &e->list, entry) { + if (chunk->sync_seq <= last_seq) { + list_del(&chunk->entry); + kmem_cache_free(amdgpu_mux_chunk_slab, chunk); + } + } +} + +void amdgpu_ring_mux_end_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) +{ + struct amdgpu_mux_entry *e; + struct amdgpu_mux_chunk *chunk; + + e = amdgpu_ring_mux_sw_entry(mux, ring); + if (!e) { + DRM_ERROR("cannot find entry!\n"); + return; + } + + chunk = list_last_entry(&e->list, struct amdgpu_mux_chunk, entry); + if (!chunk) { + DRM_ERROR("cannot find chunk!\n"); + return; + } + + chunk->end = ring->wptr; + chunk->sync_seq = READ_ONCE(ring->fence_drv.sync_seq); + + scan_and_remove_signaled_chunk(mux, ring); +} + +bool amdgpu_mcbp_handle_trailing_fence_irq(struct amdgpu_ring_mux *mux) +{ + struct amdgpu_mux_entry *e; + struct amdgpu_ring *ring = NULL; + int i; + + if (!mux->pending_trailing_fence_signaled) + return false; + + if (mux->real_ring->trail_seq != le32_to_cpu(*mux->real_ring->trail_fence_cpu_addr)) + return false; + + for (i = 0; i < mux->num_ring_entries; i++) { + e = &mux->ring_entry[i]; + if (e->ring->hw_prio <= AMDGPU_RING_PRIO_DEFAULT) { + ring = e->ring; + break; + } + } + + if (!ring) { + DRM_ERROR("cannot find low priority ring\n"); + return false; + } + + amdgpu_fence_process(ring); + if (amdgpu_fence_count_emitted(ring) > 0) { + mux->s_resubmit = true; + mux->seqno_to_resubmit = ring->fence_drv.sync_seq; + amdgpu_ring_mux_schedule_resubmit(mux); + } + + mux->pending_trailing_fence_signaled = false; + return true; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h new file mode 100644 index 000000000000..4be45fc14954 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h @@ -0,0 +1,103 @@ +/* + * Copyright 2022 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __AMDGPU_RING_MUX__ +#define __AMDGPU_RING_MUX__ + +#include <linux/timer.h> +#include <linux/spinlock.h> +#include "amdgpu_ring.h" + +struct amdgpu_ring; + +/** + * struct amdgpu_mux_entry - the entry recording software rings copying information. + * @ring: the pointer to the software ring. + * @start_ptr_in_hw_ring: last start location copied to in the hardware ring. + * @end_ptr_in_hw_ring: last end location copied to in the hardware ring. + * @sw_cptr: the position of the copy pointer in the sw ring. + * @sw_rptr: the read pointer in software ring. + * @sw_wptr: the write pointer in software ring. + * @list: list head for amdgpu_mux_chunk + */ +struct amdgpu_mux_entry { + struct amdgpu_ring *ring; + u64 start_ptr_in_hw_ring; + u64 end_ptr_in_hw_ring; + u64 sw_cptr; + u64 sw_rptr; + u64 sw_wptr; + struct list_head list; +}; + +struct amdgpu_ring_mux { + struct amdgpu_ring *real_ring; + + struct amdgpu_mux_entry *ring_entry; + unsigned int num_ring_entries; + unsigned int ring_entry_size; + /*the lock for copy data from different software rings*/ + spinlock_t lock; + bool s_resubmit; + uint32_t seqno_to_resubmit; + u64 wptr_resubmit; + struct timer_list resubmit_timer; + + bool pending_trailing_fence_signaled; +}; + +/** + * struct amdgpu_mux_chunk - save the location of indirect buffer's package on softare rings. + * @entry: the list entry. + * @sync_seq: the fence seqno related with the saved IB. + * @start:- start location on the software ring. + * @end:- end location on the software ring. + */ +struct amdgpu_mux_chunk { + struct list_head entry; + uint32_t sync_seq; + u64 start; + u64 end; +}; + +int amdgpu_ring_mux_init(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring, + unsigned int entry_size); +void amdgpu_ring_mux_fini(struct amdgpu_ring_mux *mux); +int amdgpu_ring_mux_add_sw_ring(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); +void amdgpu_ring_mux_set_wptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring, u64 wptr); +u64 amdgpu_ring_mux_get_wptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); +u64 amdgpu_ring_mux_get_rptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); +void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); +void amdgpu_ring_mux_end_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); +bool amdgpu_mcbp_handle_trailing_fence_irq(struct amdgpu_ring_mux *mux); + +u64 amdgpu_sw_ring_get_rptr_gfx(struct amdgpu_ring *ring); +u64 amdgpu_sw_ring_get_wptr_gfx(struct amdgpu_ring *ring); +void amdgpu_sw_ring_set_wptr_gfx(struct amdgpu_ring *ring); +void amdgpu_sw_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count); +void amdgpu_sw_ring_ib_begin(struct amdgpu_ring *ring); +void amdgpu_sw_ring_ib_end(struct amdgpu_ring *ring); +const char *amdgpu_sw_ring_name(int idx); +unsigned int amdgpu_sw_ring_priority(int idx); + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 090e66a1b284..bac7976975bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -259,6 +259,14 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, return 0; } +/* Free the entry back to the slab */ +static void amdgpu_sync_entry_free(struct amdgpu_sync_entry *e) +{ + hash_del(&e->node); + dma_fence_put(e->fence); + kmem_cache_free(amdgpu_sync_slab, e); +} + /** * amdgpu_sync_peek_fence - get the next fence not signaled yet * @@ -280,9 +288,7 @@ struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync, struct drm_sched_fence *s_fence = to_drm_sched_fence(f); if (dma_fence_is_signaled(f)) { - hash_del(&e->node); - dma_fence_put(f); - kmem_cache_free(amdgpu_sync_slab, e); + amdgpu_sync_entry_free(e); continue; } if (ring && s_fence) { @@ -355,15 +361,42 @@ int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone) if (r) return r; } else { - hash_del(&e->node); - dma_fence_put(f); - kmem_cache_free(amdgpu_sync_slab, e); + amdgpu_sync_entry_free(e); } } return 0; } +/** + * amdgpu_sync_push_to_job - push fences into job + * @sync: sync object to get the fences from + * @job: job to push the fences into + * + * Add all unsignaled fences from sync to job. + */ +int amdgpu_sync_push_to_job(struct amdgpu_sync *sync, struct amdgpu_job *job) +{ + struct amdgpu_sync_entry *e; + struct hlist_node *tmp; + struct dma_fence *f; + int i, r; + + hash_for_each_safe(sync->fences, i, tmp, e, node) { + f = e->fence; + if (dma_fence_is_signaled(f)) { + amdgpu_sync_entry_free(e); + continue; + } + + dma_fence_get(f); + r = drm_sched_job_add_dependency(&job->base, f); + if (r) + return r; + } + return 0; +} + int amdgpu_sync_wait(struct amdgpu_sync *sync, bool intr) { struct amdgpu_sync_entry *e; @@ -375,9 +408,7 @@ int amdgpu_sync_wait(struct amdgpu_sync *sync, bool intr) if (r) return r; - hash_del(&e->node); - dma_fence_put(e->fence); - kmem_cache_free(amdgpu_sync_slab, e); + amdgpu_sync_entry_free(e); } return 0; @@ -396,11 +427,8 @@ void amdgpu_sync_free(struct amdgpu_sync *sync) struct hlist_node *tmp; unsigned int i; - hash_for_each_safe(sync->fences, i, tmp, e, node) { - hash_del(&e->node); - dma_fence_put(e->fence); - kmem_cache_free(amdgpu_sync_slab, e); - } + hash_for_each_safe(sync->fences, i, tmp, e, node) + amdgpu_sync_entry_free(e); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h index 2d5c613cda10..cf1e9e858efd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h @@ -30,6 +30,7 @@ struct dma_fence; struct dma_resv; struct amdgpu_device; struct amdgpu_ring; +struct amdgpu_job; enum amdgpu_sync_mode { AMDGPU_SYNC_ALWAYS, @@ -54,6 +55,7 @@ struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync, struct amdgpu_ring *ring); struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync); int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone); +int amdgpu_sync_push_to_job(struct amdgpu_sync *sync, struct amdgpu_job *job); int amdgpu_sync_wait(struct amdgpu_sync *sync, bool intr); void amdgpu_sync_free(struct amdgpu_sync *sync); int amdgpu_sync_init(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8c00a7a06c32..55e0284b2bdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -58,6 +58,7 @@ #include "amdgpu_amdkfd.h" #include "amdgpu_sdma.h" #include "amdgpu_ras.h" +#include "amdgpu_hmm.h" #include "amdgpu_atomfirmware.h" #include "amdgpu_res_cursor.h" #include "bif/bif_4_1_d.h" @@ -189,7 +190,6 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo, struct amdgpu_device *adev = ring->adev; unsigned offset, num_pages, num_dw, num_bytes; uint64_t src_addr, dst_addr; - struct dma_fence *fence; struct amdgpu_job *job; void *cpu_addr; uint64_t flags; @@ -229,7 +229,9 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo, num_dw = ALIGN(adev->mman.buffer_funcs->copy_num_dw, 8); num_bytes = num_pages * 8 * AMDGPU_GPU_PAGES_IN_CPU_PAGE; - r = amdgpu_job_alloc_with_ib(adev, num_dw * 4 + num_bytes, + r = amdgpu_job_alloc_with_ib(adev, &adev->mman.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + num_dw * 4 + num_bytes, AMDGPU_IB_POOL_DELAYED, &job); if (r) return r; @@ -269,18 +271,8 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo, } } - r = amdgpu_job_submit(job, &adev->mman.entity, - AMDGPU_FENCE_OWNER_UNDEFINED, &fence); - if (r) - goto error_free; - - dma_fence_put(fence); - - return r; - -error_free: - amdgpu_job_free(job); - return r; + dma_fence_put(amdgpu_job_submit(job)); + return 0; } /** @@ -643,9 +635,6 @@ struct amdgpu_ttm_tt { struct task_struct *usertask; uint32_t userflags; bool bound; -#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) - struct hmm_range *range; -#endif }; #define ttm_to_amdgpu_ttm_tt(ptr) container_of(ptr, struct amdgpu_ttm_tt, ttm) @@ -658,7 +647,8 @@ struct amdgpu_ttm_tt { * Calling function must call amdgpu_ttm_tt_userptr_range_done() once and only * once afterwards to stop HMM tracking */ -int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) +int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages, + struct hmm_range **range) { struct ttm_tt *ttm = bo->tbo.ttm; struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm); @@ -668,16 +658,15 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) bool readonly; int r = 0; + /* Make sure get_user_pages_done() can cleanup gracefully */ + *range = NULL; + mm = bo->notifier.mm; if (unlikely(!mm)) { DRM_DEBUG_DRIVER("BO is not registered?\n"); return -EFAULT; } - /* Another get_user_pages is running at the same time?? */ - if (WARN_ON(gtt->range)) - return -EFAULT; - if (!mmget_not_zero(mm)) /* Happens during process shutdown */ return -ESRCH; @@ -694,9 +683,8 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) } readonly = amdgpu_ttm_tt_is_readonly(ttm); - r = amdgpu_hmm_range_get_pages(&bo->notifier, mm, pages, start, - ttm->num_pages, >t->range, readonly, - true, NULL); + r = amdgpu_hmm_range_get_pages(&bo->notifier, start, ttm->num_pages, + readonly, NULL, pages, range); out_unlock: mmap_read_unlock(mm); if (r) @@ -707,36 +695,37 @@ out_unlock: return r; } +/* amdgpu_ttm_tt_discard_user_pages - Discard range and pfn array allocations + */ +void amdgpu_ttm_tt_discard_user_pages(struct ttm_tt *ttm, + struct hmm_range *range) +{ + struct amdgpu_ttm_tt *gtt = (void *)ttm; + + if (gtt && gtt->userptr && range) + amdgpu_hmm_range_get_pages_done(range); +} + /* - * amdgpu_ttm_tt_userptr_range_done - stop HMM track the CPU page table change + * amdgpu_ttm_tt_get_user_pages_done - stop HMM track the CPU page table change * Check if the pages backing this ttm range have been invalidated * * Returns: true if pages are still valid */ -bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) +bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range) { struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm); - bool r = false; - if (!gtt || !gtt->userptr) + if (!gtt || !gtt->userptr || !range) return false; DRM_DEBUG_DRIVER("user_pages_done 0x%llx pages 0x%x\n", gtt->userptr, ttm->num_pages); - WARN_ONCE(!gtt->range || !gtt->range->hmm_pfns, - "No user pages to check\n"); - - if (gtt->range) { - /* - * FIXME: Must always hold notifier_lock for this, and must - * not ignore the return code. - */ - r = amdgpu_hmm_range_get_pages_done(gtt->range); - gtt->range = NULL; - } + WARN_ONCE(!range->hmm_pfns, "No user pages to check\n"); - return !r; + return !amdgpu_hmm_range_get_pages_done(range); } #endif @@ -813,20 +802,6 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_device *bdev, /* unmap the pages mapped to the device */ dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0); sg_free_table(ttm->sg); - -#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) - if (gtt->range) { - unsigned long i; - - for (i = 0; i < ttm->num_pages; i++) { - if (ttm->pages[i] != - hmm_pfn_to_page(gtt->range->hmm_pfns[i])) - break; - } - - WARN((i == ttm->num_pages), "Missing get_user_page_done\n"); - } -#endif } static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev, @@ -1177,8 +1152,9 @@ int amdgpu_ttm_tt_get_userptr(const struct ttm_buffer_object *tbo, * @addr: The address in the current tasks VM space to use * @flags: Requirements of userptr object. * - * Called by amdgpu_gem_userptr_ioctl() to bind userptr pages - * to current task + * Called by amdgpu_gem_userptr_ioctl() and kfd_ioctl_alloc_memory_of_gpu() to + * bind userptr pages to current task and by kfd_ioctl_acquire_vm() to + * initialize GPU VM for a KFD process. */ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo, uint64_t addr, uint32_t flags) @@ -1417,7 +1393,8 @@ static void amdgpu_ttm_vram_mm_access(struct amdgpu_device *adev, loff_t pos, } static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo, - unsigned long offset, void *buf, int len, int write) + unsigned long offset, void *buf, + int len, int write) { struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo); struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev); @@ -1441,26 +1418,27 @@ static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo, memcpy(adev->mman.sdma_access_ptr, buf, len); num_dw = ALIGN(adev->mman.buffer_funcs->copy_num_dw, 8); - r = amdgpu_job_alloc_with_ib(adev, num_dw * 4, AMDGPU_IB_POOL_DELAYED, &job); + r = amdgpu_job_alloc_with_ib(adev, &adev->mman.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + num_dw * 4, AMDGPU_IB_POOL_DELAYED, + &job); if (r) goto out; amdgpu_res_first(abo->tbo.resource, offset, len, &src_mm); - src_addr = amdgpu_ttm_domain_start(adev, bo->resource->mem_type) + src_mm.start; + src_addr = amdgpu_ttm_domain_start(adev, bo->resource->mem_type) + + src_mm.start; dst_addr = amdgpu_bo_gpu_offset(adev->mman.sdma_access_bo); if (write) swap(src_addr, dst_addr); - amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_addr, dst_addr, PAGE_SIZE, false); + amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_addr, dst_addr, + PAGE_SIZE, false); amdgpu_ring_pad_ib(adev->mman.buffer_funcs_ring, &job->ibs[0]); WARN_ON(job->ibs[0].length_dw > num_dw); - r = amdgpu_job_submit(job, &adev->mman.entity, AMDGPU_FENCE_OWNER_UNDEFINED, &fence); - if (r) { - amdgpu_job_free(job); - goto out; - } + fence = amdgpu_job_submit(job); if (!dma_fence_wait_timeout(fence, false, adev->sdma_timeout)) r = -ETIMEDOUT; @@ -1560,6 +1538,23 @@ static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev) NULL, &adev->mman.fw_vram_usage_va); } +/* + * Driver Reservation functions + */ +/** + * amdgpu_ttm_drv_reserve_vram_fini - free drv reserved vram + * + * @adev: amdgpu_device pointer + * + * free drv reserved vram if it has been reserved. + */ +static void amdgpu_ttm_drv_reserve_vram_fini(struct amdgpu_device *adev) +{ + amdgpu_bo_free_kernel(&adev->mman.drv_vram_usage_reserved_bo, + NULL, + &adev->mman.drv_vram_usage_va); +} + /** * amdgpu_ttm_fw_reserve_vram_init - create bo vram reservation from fw * @@ -1581,11 +1576,35 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev) return amdgpu_bo_create_kernel_at(adev, adev->mman.fw_vram_usage_start_offset, adev->mman.fw_vram_usage_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.fw_vram_usage_reserved_bo, &adev->mman.fw_vram_usage_va); } +/** + * amdgpu_ttm_drv_reserve_vram_init - create bo vram reservation from driver + * + * @adev: amdgpu_device pointer + * + * create bo vram reservation from drv. + */ +static int amdgpu_ttm_drv_reserve_vram_init(struct amdgpu_device *adev) +{ + u64 vram_size = adev->gmc.visible_vram_size; + + adev->mman.drv_vram_usage_va = NULL; + adev->mman.drv_vram_usage_reserved_bo = NULL; + + if (adev->mman.drv_vram_usage_size == 0 || + adev->mman.drv_vram_usage_size > vram_size) + return 0; + + return amdgpu_bo_create_kernel_at(adev, + adev->mman.drv_vram_usage_start_offset, + adev->mman.drv_vram_usage_size, + &adev->mman.drv_vram_usage_reserved_bo, + &adev->mman.drv_vram_usage_va); +} + /* * Memoy training reservation functions */ @@ -1662,7 +1681,6 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) ret = amdgpu_bo_create_kernel_at(adev, ctx->c2p_train_data_offset, ctx->train_data_size, - AMDGPU_GEM_DOMAIN_VRAM, &ctx->c2p_bo, NULL); if (ret) { @@ -1676,7 +1694,6 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) ret = amdgpu_bo_create_kernel_at(adev, adev->gmc.real_vram_size - adev->mman.discovery_tmr_size, adev->mman.discovery_tmr_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.discovery_memory, NULL); if (ret) { @@ -1754,6 +1771,14 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) } /* + *The reserved vram for driver must be pinned to the specified + *place on the VRAM, so reserve it early. + */ + r = amdgpu_ttm_drv_reserve_vram_init(adev); + if (r) + return r; + + /* * only NAVI10 and onwards ASIC support for IP discovery. * If IP discovery enabled, a block of memory should be * reserved for IP discovey. @@ -1769,21 +1794,18 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) * avoid display artifacts while transitioning between pre-OS * and driver. */ r = amdgpu_bo_create_kernel_at(adev, 0, adev->mman.stolen_vga_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.stolen_vga_memory, NULL); if (r) return r; r = amdgpu_bo_create_kernel_at(adev, adev->mman.stolen_vga_size, adev->mman.stolen_extended_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.stolen_extended_memory, NULL); if (r) return r; r = amdgpu_bo_create_kernel_at(adev, adev->mman.stolen_reserved_offset, adev->mman.stolen_reserved_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.stolen_reserved_memory, NULL); if (r) @@ -1878,6 +1900,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) amdgpu_bo_free_kernel(&adev->mman.sdma_access_bo, NULL, &adev->mman.sdma_access_ptr); amdgpu_ttm_fw_reserve_vram_fini(adev); + amdgpu_ttm_drv_reserve_vram_fini(adev); if (drm_dev_enter(adev_to_drm(adev), &idx)) { @@ -1959,7 +1982,9 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev, AMDGPU_IB_POOL_DELAYED; int r; - r = amdgpu_job_alloc_with_ib(adev, num_dw * 4, pool, job); + r = amdgpu_job_alloc_with_ib(adev, &adev->mman.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + num_dw * 4, pool, job); if (r) return r; @@ -1969,17 +1994,11 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev, adev->gart.bo); (*job)->vm_needs_flush = true; } - if (resv) { - r = amdgpu_sync_resv(adev, &(*job)->sync, resv, - AMDGPU_SYNC_ALWAYS, - AMDGPU_FENCE_OWNER_UNDEFINED); - if (r) { - DRM_ERROR("sync failed (%d).\n", r); - amdgpu_job_free(*job); - return r; - } - } - return 0; + if (!resv) + return 0; + + return drm_sched_job_add_resv_dependencies(&(*job)->base, resv, + DMA_RESV_USAGE_BOOKKEEP); } int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset, @@ -2024,8 +2043,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset, if (direct_submit) r = amdgpu_job_submit_direct(job, ring, fence); else - r = amdgpu_job_submit(job, &adev->mman.entity, - AMDGPU_FENCE_OWNER_UNDEFINED, fence); + *fence = amdgpu_job_submit(job); if (r) goto error_free; @@ -2070,16 +2088,8 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring, uint32_t src_data, amdgpu_ring_pad_ib(ring, &job->ibs[0]); WARN_ON(job->ibs[0].length_dw > num_dw); - r = amdgpu_job_submit(job, &adev->mman.entity, - AMDGPU_FENCE_OWNER_UNDEFINED, fence); - if (r) - goto error_free; - + *fence = amdgpu_job_submit(job); return 0; - -error_free: - amdgpu_job_free(job); - return r; } int amdgpu_fill_buffer(struct amdgpu_bo *bo, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 6a70818039dd..e2cd5894afc9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -39,6 +39,8 @@ #define AMDGPU_POISON 0xd0bed0be +struct hmm_range; + struct amdgpu_gtt_mgr { struct ttm_resource_manager manager; struct drm_mm mm; @@ -84,6 +86,12 @@ struct amdgpu_mman { struct amdgpu_bo *fw_vram_usage_reserved_bo; void *fw_vram_usage_va; + /* driver VRAM reservation */ + u64 drv_vram_usage_start_offset; + u64 drv_vram_usage_size; + struct amdgpu_bo *drv_vram_usage_reserved_bo; + void *drv_vram_usage_va; + /* PAGE_SIZE'd BO for process memory r/w over SDMA. */ struct amdgpu_bo *sdma_access_bo; void *sdma_access_ptr; @@ -149,15 +157,25 @@ void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo); uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type); #if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) -int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages); -bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm); +int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages, + struct hmm_range **range); +void amdgpu_ttm_tt_discard_user_pages(struct ttm_tt *ttm, + struct hmm_range *range); +bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range); #else static inline int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, - struct page **pages) + struct page **pages, + struct hmm_range **range) { return -EPERM; } -static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) +static inline void amdgpu_ttm_tt_discard_user_pages(struct ttm_tt *ttm, + struct hmm_range *range) +{ +} +static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range) { return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 6eac649499d3..e00bb654e24b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1132,7 +1132,9 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, unsigned offset_idx = 0; unsigned offset[3] = { UVD_BASE_SI, 0, 0 }; - r = amdgpu_job_alloc_with_ib(adev, 64, direct ? AMDGPU_IB_POOL_DIRECT : + r = amdgpu_job_alloc_with_ib(ring->adev, &adev->uvd.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + 64, direct ? AMDGPU_IB_POOL_DIRECT : AMDGPU_IB_POOL_DELAYED, &job); if (r) return r; @@ -1175,16 +1177,13 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, if (r) goto err_free; } else { - r = amdgpu_sync_resv(adev, &job->sync, bo->tbo.base.resv, - AMDGPU_SYNC_ALWAYS, - AMDGPU_FENCE_OWNER_UNDEFINED); + r = drm_sched_job_add_resv_dependencies(&job->base, + bo->tbo.base.resv, + DMA_RESV_USAGE_KERNEL); if (r) goto err_free; - r = amdgpu_job_submit(job, &adev->uvd.entity, - AMDGPU_FENCE_OWNER_UNDEFINED, &f); - if (r) - goto err_free; + f = amdgpu_job_submit(job); } amdgpu_bo_reserve(bo, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 02cb3a12dd76..b239e874f2d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -450,8 +450,10 @@ static int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, uint64_t addr; int i, r; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, &ring->adev->vce.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, + &job); if (r) return r; @@ -538,7 +540,9 @@ static int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, struct dma_fence *f = NULL; int i, r; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, + r = amdgpu_job_alloc_with_ib(ring->adev, &ring->adev->vce.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + ib_size_dw * 4, direct ? AMDGPU_IB_POOL_DIRECT : AMDGPU_IB_POOL_DELAYED, &job); if (r) @@ -570,8 +574,7 @@ static int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, if (direct) r = amdgpu_job_submit_direct(job, ring, &f); else - r = amdgpu_job_submit(job, &ring->adev->vce.entity, - AMDGPU_FENCE_OWNER_UNDEFINED, &f); + f = amdgpu_job_submit(job); if (r) goto err; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 0b52af415b28..b1622ac9949f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -156,6 +156,9 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) break; case IP_VERSION(3, 0, 2): fw_name = FIRMWARE_VANGOGH; + if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && + (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) + adev->vcn.indirect_sram = true; break; case IP_VERSION(3, 0, 16): fw_name = FIRMWARE_DIMGREY_CAVEFISH; @@ -600,15 +603,16 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring, struct amdgpu_ib *ib_msg, struct dma_fence **fence) { + u64 addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr); struct amdgpu_device *adev = ring->adev; struct dma_fence *f = NULL; struct amdgpu_job *job; struct amdgpu_ib *ib; - uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr); int i, r; - r = amdgpu_job_alloc_with_ib(adev, 64, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, + 64, AMDGPU_IB_POOL_DIRECT, + &job); if (r) goto err; @@ -787,8 +791,9 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, if (sq) ib_size_dw += 8; - r = amdgpu_job_alloc_with_ib(adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, + ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, + &job); if (r) goto err; @@ -916,8 +921,9 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand if (sq) ib_size_dw += 8; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, + ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, + &job); if (r) return r; @@ -982,8 +988,9 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han if (sq) ib_size_dw += 8; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, + ib_size_dw * 4, AMDGPU_IB_POOL_DIRECT, + &job); if (r) return r; @@ -1248,3 +1255,20 @@ int amdgpu_vcn_process_poison_irq(struct amdgpu_device *adev, return 0; } + +void amdgpu_vcn_set_ras_funcs(struct amdgpu_device *adev) +{ + if (!adev->vcn.ras) + return; + + amdgpu_ras_register_ras_block(adev, &adev->vcn.ras->ras_block); + + strcpy(adev->vcn.ras->ras_block.ras_comm.name, "vcn"); + adev->vcn.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__VCN; + adev->vcn.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__POISON; + adev->vcn.ras_if = &adev->vcn.ras->ras_block.ras_comm; + + /* If don't define special ras_late_init function, use default ras_late_init */ + if (!adev->vcn.ras->ras_block.ras_late_init) + adev->vcn.ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 253ea6b159df..dbb8d68a30c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -399,5 +399,6 @@ void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, int amdgpu_vcn_process_poison_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +void amdgpu_vcn_set_ras_funcs(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index a226a6c48fb7..2994b9db196f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -395,7 +395,6 @@ static void amdgpu_virt_ras_reserve_bps(struct amdgpu_device *adev) */ if (amdgpu_bo_create_kernel_at(adev, bp << AMDGPU_GPU_PAGE_SHIFT, AMDGPU_GPU_PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &bo, NULL)) DRM_DEBUG("RAS WARN: reserve vram for retired page %llx fail\n", bp); @@ -428,11 +427,17 @@ static void amdgpu_virt_add_bad_page(struct amdgpu_device *adev, struct eeprom_table_record bp; uint64_t retired_page; uint32_t bp_idx, bp_cnt; + void *vram_usage_va = NULL; + + if (adev->mman.fw_vram_usage_va) + vram_usage_va = adev->mman.fw_vram_usage_va; + else + vram_usage_va = adev->mman.drv_vram_usage_va; if (bp_block_size) { bp_cnt = bp_block_size / sizeof(uint64_t); for (bp_idx = 0; bp_idx < bp_cnt; bp_idx++) { - retired_page = *(uint64_t *)(adev->mman.fw_vram_usage_va + + retired_page = *(uint64_t *)(vram_usage_va + bp_block_offset + bp_idx * sizeof(uint64_t)); bp.retired_page = retired_page; @@ -643,7 +648,9 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev) adev->virt.fw_reserve.p_vf2pf = NULL; adev->virt.vf2pf_update_interval_ms = 0; - if (adev->mman.fw_vram_usage_va != NULL) { + if (adev->mman.fw_vram_usage_va && adev->mman.drv_vram_usage_va) { + DRM_WARN("Currently fw_vram and drv_vram should not have values at the same time!"); + } else if (adev->mman.fw_vram_usage_va || adev->mman.drv_vram_usage_va) { /* go through this logic in ip_init and reset to init workqueue*/ amdgpu_virt_exchange_data(adev); @@ -666,32 +673,40 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev) uint32_t bp_block_size = 0; struct amd_sriov_msg_pf2vf_info *pf2vf_v2 = NULL; - if (adev->mman.fw_vram_usage_va != NULL) { - - adev->virt.fw_reserve.p_pf2vf = - (struct amd_sriov_msg_pf2vf_info_header *) - (adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10)); - adev->virt.fw_reserve.p_vf2pf = - (struct amd_sriov_msg_vf2pf_info_header *) - (adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10)); + if (adev->mman.fw_vram_usage_va || adev->mman.drv_vram_usage_va) { + if (adev->mman.fw_vram_usage_va) { + adev->virt.fw_reserve.p_pf2vf = + (struct amd_sriov_msg_pf2vf_info_header *) + (adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10)); + adev->virt.fw_reserve.p_vf2pf = + (struct amd_sriov_msg_vf2pf_info_header *) + (adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10)); + } else if (adev->mman.drv_vram_usage_va) { + adev->virt.fw_reserve.p_pf2vf = + (struct amd_sriov_msg_pf2vf_info_header *) + (adev->mman.drv_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10)); + adev->virt.fw_reserve.p_vf2pf = + (struct amd_sriov_msg_vf2pf_info_header *) + (adev->mman.drv_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10)); + } amdgpu_virt_read_pf2vf_data(adev); amdgpu_virt_write_vf2pf_data(adev); /* bad page handling for version 2 */ if (adev->virt.fw_reserve.p_pf2vf->version == 2) { - pf2vf_v2 = (struct amd_sriov_msg_pf2vf_info *)adev->virt.fw_reserve.p_pf2vf; + pf2vf_v2 = (struct amd_sriov_msg_pf2vf_info *)adev->virt.fw_reserve.p_pf2vf; - bp_block_offset = ((uint64_t)pf2vf_v2->bp_block_offset_low & 0xFFFFFFFF) | - ((((uint64_t)pf2vf_v2->bp_block_offset_high) << 32) & 0xFFFFFFFF00000000); - bp_block_size = pf2vf_v2->bp_block_size; + bp_block_offset = ((uint64_t)pf2vf_v2->bp_block_offset_low & 0xFFFFFFFF) | + ((((uint64_t)pf2vf_v2->bp_block_offset_high) << 32) & 0xFFFFFFFF00000000); + bp_block_size = pf2vf_v2->bp_block_size; - if (bp_block_size && !adev->virt.ras_init_done) - amdgpu_virt_init_ras_err_handler_data(adev); + if (bp_block_size && !adev->virt.ras_init_done) + amdgpu_virt_init_ras_err_handler_data(adev); - if (adev->virt.ras_init_done) - amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size); - } + if (adev->virt.ras_init_done) + amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size); + } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 9b81b6867db3..53ff91fc6cf6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -500,6 +500,8 @@ static int amdgpu_vkms_sw_init(void *handle) adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; + adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; + r = amdgpu_display_modeset_create_props(adev); if (r) return r; @@ -511,6 +513,10 @@ static int amdgpu_vkms_sw_init(void *handle) return r; } + r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc); + if (r) + return r; + drm_kms_helper_poll_init(adev_to_drm(adev)); adev->mode_info.mode_config_initialized = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 2291aa14d888..dc379dc22c77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -45,22 +45,43 @@ /** * DOC: GPUVM * - * GPUVM is similar to the legacy gart on older asics, however - * rather than there being a single global gart table - * for the entire GPU, there are multiple VM page tables active - * at any given time. The VM page tables can contain a mix - * vram pages and system memory pages and system memory pages + * GPUVM is the MMU functionality provided on the GPU. + * GPUVM is similar to the legacy GART on older asics, however + * rather than there being a single global GART table + * for the entire GPU, there can be multiple GPUVM page tables active + * at any given time. The GPUVM page tables can contain a mix + * VRAM pages and system pages (both memory and MMIO) and system pages * can be mapped as snooped (cached system pages) or unsnooped * (uncached system pages). - * Each VM has an ID associated with it and there is a page table - * associated with each VMID. When executing a command buffer, - * the kernel tells the ring what VMID to use for that command + * + * Each active GPUVM has an ID associated with it and there is a page table + * linked with each VMID. When executing a command buffer, + * the kernel tells the engine what VMID to use for that command * buffer. VMIDs are allocated dynamically as commands are submitted. * The userspace drivers maintain their own address space and the kernel * sets up their pages tables accordingly when they submit their * command buffers and a VMID is assigned. - * Cayman/Trinity support up to 8 active VMs at any given time; - * SI supports 16. + * The hardware supports up to 16 active GPUVMs at any given time. + * + * Each GPUVM is represented by a 1-2 or 1-5 level page table, depending + * on the ASIC family. GPUVM supports RWX attributes on each page as well + * as other features such as encryption and caching attributes. + * + * VMID 0 is special. It is the GPUVM used for the kernel driver. In + * addition to an aperture managed by a page table, VMID 0 also has + * several other apertures. There is an aperture for direct access to VRAM + * and there is a legacy AGP aperture which just forwards accesses directly + * to the matching system physical addresses (or IOVAs when an IOMMU is + * present). These apertures provide direct access to these memories without + * incurring the overhead of a page table. VMID 0 is used by the kernel + * driver for tasks like memory management. + * + * GPU clients (i.e., engines on the GPU) use GPUVM VMIDs to access memory. + * For user applications, each application can have their own unique GPUVM + * address space. The application manages the address space and the kernel + * driver manages the GPUVM page tables for each process. If an GPU client + * accesses an invalid page, it will generate a GPU page fault, similar to + * accessing an invalid page on a CPU. */ #define START(node) ((node)->start) @@ -143,32 +164,6 @@ int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm, return 0; } -/* - * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS - * happens while holding this lock anywhere to prevent deadlocks when - * an MMU notifier runs in reclaim-FS context. - */ -static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm) -{ - mutex_lock(&vm->eviction_lock); - vm->saved_flags = memalloc_noreclaim_save(); -} - -static inline int amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm) -{ - if (mutex_trylock(&vm->eviction_lock)) { - vm->saved_flags = memalloc_noreclaim_save(); - return 1; - } - return 0; -} - -static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm) -{ - memalloc_noreclaim_restore(vm->saved_flags); - mutex_unlock(&vm->eviction_lock); -} - /** * amdgpu_vm_bo_evicted - vm_bo is evicted * @@ -489,25 +484,20 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring, struct amdgpu_device *adev = ring->adev; unsigned vmhub = ring->funcs->vmhub; struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; - struct amdgpu_vmid *id; - bool gds_switch_needed; - bool vm_flush_needed = job->vm_needs_flush || ring->has_compute_vm_bug; if (job->vmid == 0) return false; - id = &id_mgr->ids[job->vmid]; - gds_switch_needed = ring->funcs->emit_gds_switch && ( - id->gds_base != job->gds_base || - id->gds_size != job->gds_size || - id->gws_base != job->gws_base || - id->gws_size != job->gws_size || - id->oa_base != job->oa_base || - id->oa_size != job->oa_size); - - if (amdgpu_vmid_had_gpu_reset(adev, id)) + + if (job->vm_needs_flush || ring->has_compute_vm_bug) + return true; + + if (ring->funcs->emit_gds_switch && job->gds_switch_needed) + return true; + + if (amdgpu_vmid_had_gpu_reset(adev, &id_mgr->ids[job->vmid])) return true; - return vm_flush_needed || gds_switch_needed; + return false; } /** @@ -529,27 +519,20 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, unsigned vmhub = ring->funcs->vmhub; struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub]; struct amdgpu_vmid *id = &id_mgr->ids[job->vmid]; - bool gds_switch_needed = ring->funcs->emit_gds_switch && ( - id->gds_base != job->gds_base || - id->gds_size != job->gds_size || - id->gws_base != job->gws_base || - id->gws_size != job->gws_size || - id->oa_base != job->oa_base || - id->oa_size != job->oa_size); + bool spm_update_needed = job->spm_update_needed; + bool gds_switch_needed = ring->funcs->emit_gds_switch && + job->gds_switch_needed; bool vm_flush_needed = job->vm_needs_flush; struct dma_fence *fence = NULL; bool pasid_mapping_needed = false; unsigned patch_offset = 0; - bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] != NULL)); int r; - if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) - adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid); - if (amdgpu_vmid_had_gpu_reset(adev, id)) { gds_switch_needed = true; vm_flush_needed = true; pasid_mapping_needed = true; + spm_update_needed = true; } mutex_lock(&id_mgr->lock); @@ -567,6 +550,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync) return 0; + amdgpu_ring_ib_begin(ring); if (ring->funcs->init_cond_exec) patch_offset = amdgpu_ring_init_cond_exec(ring); @@ -581,6 +565,17 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, if (pasid_mapping_needed) amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid); + if (spm_update_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid); + + if (!ring->is_mes_queue && ring->funcs->emit_gds_switch && + gds_switch_needed) { + amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base, + job->gds_size, job->gws_base, + job->gws_size, job->oa_base, + job->oa_size); + } + if (vm_flush_needed || pasid_mapping_needed) { r = amdgpu_fence_emit(ring, &fence, NULL, 0); if (r) @@ -605,20 +600,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, } dma_fence_put(fence); - if (!ring->is_mes_queue && ring->funcs->emit_gds_switch && - gds_switch_needed) { - id->gds_base = job->gds_base; - id->gds_size = job->gds_size; - id->gws_base = job->gws_base; - id->gws_size = job->gws_size; - id->oa_base = job->oa_base; - id->oa_size = job->oa_size; - amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base, - job->gds_size, job->gws_base, - job->gws_size, job->oa_base, - job->oa_size); - } - if (ring->funcs->patch_cond_exec) amdgpu_ring_patch_cond_exec(ring, patch_offset); @@ -627,6 +608,7 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, amdgpu_ring_emit_switch_buffer(ring); amdgpu_ring_emit_switch_buffer(ring); } + amdgpu_ring_ib_end(ring); return 0; } @@ -2386,7 +2368,6 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) union drm_amdgpu_vm *args = data; struct amdgpu_device *adev = drm_to_adev(dev); struct amdgpu_fpriv *fpriv = filp->driver_priv; - long timeout = msecs_to_jiffies(2000); int r; switch (args->in.op) { @@ -2398,21 +2379,6 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) return r; break; case AMDGPU_VM_OP_UNRESERVE_VMID: - if (amdgpu_sriov_runtime(adev)) - timeout = 8 * timeout; - - /* Wait vm idle to make sure the vmid set in SPM_VMID is - * not referenced anymore. - */ - r = amdgpu_bo_reserve(fpriv->vm.root.bo, true); - if (r) - return r; - - r = amdgpu_vm_wait_idle(&fpriv->vm, timeout); - if (r < 0) - return r; - - amdgpu_bo_unreserve(fpriv->vm.root.bo); amdgpu_vmid_free_reserved(adev, &fpriv->vm, AMDGPU_GFXHUB_0); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 83acb7bd80fe..094bb4807303 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -119,9 +119,6 @@ struct amdgpu_bo_vm; /* Reserve 2MB at top/bottom of address space for kernel use */ #define AMDGPU_VA_RESERVED_SIZE (2ULL << 20) -/* max vmids dedicated for process */ -#define AMDGPU_VM_MAX_RESERVED_VMID 1 - /* See vm_update_mode */ #define AMDGPU_VM_USE_CPU_FOR_GFX (1 << 0) #define AMDGPU_VM_USE_CPU_FOR_COMPUTE (1 << 1) @@ -298,8 +295,7 @@ struct amdgpu_vm { struct dma_fence *last_unlocked; unsigned int pasid; - /* dedicated to vm */ - struct amdgpu_vmid *reserved_vmid[AMDGPU_MAX_VMHUBS]; + bool reserved_vmid[AMDGPU_MAX_VMHUBS]; /* Flag to indicate if VM tables are updated by CPU or GPU (SDMA) */ bool use_cpu_for_update; @@ -492,7 +488,48 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m); */ static inline uint64_t amdgpu_vm_tlb_seq(struct amdgpu_vm *vm) { + unsigned long flags; + spinlock_t *lock; + + /* + * Workaround to stop racing between the fence signaling and handling + * the cb. The lock is static after initially setting it up, just make + * sure that the dma_fence structure isn't freed up. + */ + rcu_read_lock(); + lock = vm->last_tlb_flush->lock; + rcu_read_unlock(); + + spin_lock_irqsave(lock, flags); + spin_unlock_irqrestore(lock, flags); + return atomic64_read(&vm->tlb_seq); } +/* + * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS + * happens while holding this lock anywhere to prevent deadlocks when + * an MMU notifier runs in reclaim-FS context. + */ +static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm) +{ + mutex_lock(&vm->eviction_lock); + vm->saved_flags = memalloc_noreclaim_save(); +} + +static inline bool amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm) +{ + if (mutex_trylock(&vm->eviction_lock)) { + vm->saved_flags = memalloc_noreclaim_save(); + return true; + } + return false; +} + +static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm) +{ + memalloc_noreclaim_restore(vm->saved_flags); + mutex_unlock(&vm->eviction_lock); +} + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 358b91243e37..b5f3bba851db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -597,7 +597,9 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, if (entry->bo) return 0; + amdgpu_vm_eviction_unlock(vm); r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt); + amdgpu_vm_eviction_lock(vm); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 69e105fa41f6..535cd6569bcc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -47,6 +47,32 @@ static int amdgpu_vm_sdma_map_table(struct amdgpu_bo_vm *table) return r; } +/* Allocate a new job for @count PTE updates */ +static int amdgpu_vm_sdma_alloc_job(struct amdgpu_vm_update_params *p, + unsigned int count) +{ + enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE + : AMDGPU_IB_POOL_DELAYED; + struct drm_sched_entity *entity = p->immediate ? &p->vm->immediate + : &p->vm->delayed; + unsigned int ndw; + int r; + + /* estimate how many dw we need */ + ndw = AMDGPU_VM_SDMA_MIN_NUM_DW; + if (p->pages_addr) + ndw += count * 2; + ndw = min(ndw, AMDGPU_VM_SDMA_MAX_NUM_DW); + + r = amdgpu_job_alloc_with_ib(p->adev, entity, AMDGPU_FENCE_OWNER_VM, + ndw * 4, pool, &p->job); + if (r) + return r; + + p->num_dw_left = ndw; + return 0; +} + /** * amdgpu_vm_sdma_prepare - prepare SDMA command submission * @@ -61,21 +87,22 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p, struct dma_resv *resv, enum amdgpu_sync_mode sync_mode) { - enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE - : AMDGPU_IB_POOL_DELAYED; - unsigned int ndw = AMDGPU_VM_SDMA_MIN_NUM_DW; + struct amdgpu_sync sync; int r; - r = amdgpu_job_alloc_with_ib(p->adev, ndw * 4, pool, &p->job); + r = amdgpu_vm_sdma_alloc_job(p, 0); if (r) return r; - p->num_dw_left = ndw; - if (!resv) return 0; - return amdgpu_sync_resv(p->adev, &p->job->sync, resv, sync_mode, p->vm); + amdgpu_sync_create(&sync); + r = amdgpu_sync_resv(p->adev, &sync, resv, sync_mode, p->vm); + if (!r) + r = amdgpu_sync_push_to_job(&sync, p->job); + amdgpu_sync_free(&sync); + return r; } /** @@ -91,20 +118,16 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p, struct dma_fence **fence) { struct amdgpu_ib *ib = p->job->ibs; - struct drm_sched_entity *entity; struct amdgpu_ring *ring; struct dma_fence *f; - int r; - entity = p->immediate ? &p->vm->immediate : &p->vm->delayed; - ring = container_of(entity->rq->sched, struct amdgpu_ring, sched); + ring = container_of(p->vm->delayed.rq->sched, struct amdgpu_ring, + sched); WARN_ON(ib->length_dw == 0); amdgpu_ring_pad_ib(ring, ib); WARN_ON(ib->length_dw > p->num_dw_left); - r = amdgpu_job_submit(p->job, entity, AMDGPU_FENCE_OWNER_VM, &f); - if (r) - goto error; + f = amdgpu_job_submit(p->job); if (p->unlocked) { struct dma_fence *tmp = dma_fence_get(f); @@ -127,10 +150,6 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p, } dma_fence_put(f); return 0; - -error: - amdgpu_job_free(p->job); - return r; } /** @@ -210,8 +229,6 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, uint64_t flags) { struct amdgpu_bo *bo = &vmbo->bo; - enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE - : AMDGPU_IB_POOL_DELAYED; struct dma_resv_iter cursor; unsigned int i, ndw, nptes; struct dma_fence *fence; @@ -221,8 +238,10 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, /* Wait for PD/PT moves to be completed */ dma_resv_iter_begin(&cursor, bo->tbo.base.resv, DMA_RESV_USAGE_KERNEL); dma_resv_for_each_fence_unlocked(&cursor, fence) { - r = amdgpu_sync_fence(&p->job->sync, fence); + dma_fence_get(fence); + r = drm_sched_job_add_dependency(&p->job->base, fence); if (r) { + dma_fence_put(fence); dma_resv_iter_end(&cursor); return r; } @@ -238,19 +257,9 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, if (r) return r; - /* estimate how many dw we need */ - ndw = 32; - if (p->pages_addr) - ndw += count * 2; - ndw = max(ndw, AMDGPU_VM_SDMA_MIN_NUM_DW); - ndw = min(ndw, AMDGPU_VM_SDMA_MAX_NUM_DW); - - r = amdgpu_job_alloc_with_ib(p->adev, ndw * 4, pool, - &p->job); + r = amdgpu_vm_sdma_alloc_job(p, count); if (r) return r; - - p->num_dw_left = ndw; } if (!p->pages_addr) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 18c1a173d187..faa12146635c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -435,7 +435,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, if (place->flags & TTM_PL_FLAG_TOPDOWN) vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION; - if (fpfn || lpfn != man->size) + if (fpfn || lpfn != mgr->mm.size) /* Allocate blocks in desired range */ vres->flags |= DRM_BUDDY_RANGE_ALLOCATION; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 47159e9a0884..4b9e7b050ccd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -386,7 +386,6 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev) if (ret) { dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n"); kobject_put(&hive->kobj); - kfree(hive); hive = NULL; goto pro_end; } @@ -410,7 +409,6 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev) dev_err(adev->dev, "XGMI: failed initializing reset domain for xgmi hive\n"); ret = -ENOMEM; kobject_put(&hive->kobj); - kfree(hive); hive = NULL; goto pro_end; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 05051d5d2ec3..248f1a4e915f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -21,6 +21,7 @@ * */ +#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_vblank.h> @@ -2828,6 +2829,17 @@ static int dce_v10_0_sw_init(void *handle) if (r) return r; + /* Disable vblank IRQs aggressively for power-saving */ + /* XXX: can this be enabled for DC? */ + adev_to_drm(adev)->vblank_disable_immediate = true; + + r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc); + if (r) + return r; + + INIT_WORK(&adev->hotplug_work, + amdgpu_display_hotplug_work_func); + drm_kms_helper_poll_init(adev_to_drm(adev)); adev->mode_info.mode_config_initialized = true; @@ -2890,6 +2902,8 @@ static int dce_v10_0_hw_fini(void *handle) dce_v10_0_pageflip_interrupt_fini(adev); + flush_work(&adev->hotplug_work); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index c928bc9eb202..cd9c19060d89 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -21,6 +21,7 @@ * */ +#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_vblank.h> @@ -2947,6 +2948,17 @@ static int dce_v11_0_sw_init(void *handle) if (r) return r; + /* Disable vblank IRQs aggressively for power-saving */ + /* XXX: can this be enabled for DC? */ + adev_to_drm(adev)->vblank_disable_immediate = true; + + r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc); + if (r) + return r; + + INIT_WORK(&adev->hotplug_work, + amdgpu_display_hotplug_work_func); + drm_kms_helper_poll_init(adev_to_drm(adev)); adev->mode_info.mode_config_initialized = true; @@ -3020,6 +3032,8 @@ static int dce_v11_0_hw_fini(void *handle) dce_v11_0_pageflip_interrupt_fini(adev); + flush_work(&adev->hotplug_work); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 62315fd5a05f..76323deecc58 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -23,6 +23,7 @@ #include <linux/pci.h> +#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_vblank.h> @@ -2705,6 +2706,18 @@ static int dce_v6_0_sw_init(void *handle) if (r) return r; + /* Disable vblank IRQs aggressively for power-saving */ + /* XXX: can this be enabled for DC? */ + adev_to_drm(adev)->vblank_disable_immediate = true; + + r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc); + if (r) + return r; + + /* Pre-DCE11 */ + INIT_WORK(&adev->hotplug_work, + amdgpu_display_hotplug_work_func); + drm_kms_helper_poll_init(adev_to_drm(adev)); return r; @@ -2763,6 +2776,8 @@ static int dce_v6_0_hw_fini(void *handle) dce_v6_0_pageflip_interrupt_fini(adev); + flush_work(&adev->hotplug_work); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 87d5e4c21cb3..01cf3ab111cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -21,6 +21,7 @@ * */ +#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_vblank.h> @@ -2729,6 +2730,18 @@ static int dce_v8_0_sw_init(void *handle) if (r) return r; + /* Disable vblank IRQs aggressively for power-saving */ + /* XXX: can this be enabled for DC? */ + adev_to_drm(adev)->vblank_disable_immediate = true; + + r = drm_vblank_init(adev_to_drm(adev), adev->mode_info.num_crtc); + if (r) + return r; + + /* Pre-DCE11 */ + INIT_WORK(&adev->hotplug_work, + amdgpu_display_hotplug_work_func); + drm_kms_helper_poll_init(adev_to_drm(adev)); adev->mode_info.mode_config_initialized = true; @@ -2789,6 +2802,8 @@ static int dce_v8_0_hw_fini(void *handle) dce_v8_0_pageflip_interrupt_fini(adev); + flush_work(&adev->hotplug_work); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 9447999a3a48..a56c6e106d00 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -77,6 +77,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_3_pfp.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_me.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_rlc.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_pfp.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_me.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mec.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_rlc.bin"); static const struct soc15_reg_golden golden_settings_gc_11_0_1[] = { @@ -262,6 +266,7 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): soc15_program_register_sequence(adev, golden_settings_gc_11_0_1, (const u32)ARRAY_SIZE(golden_settings_gc_11_0_1)); @@ -855,6 +860,7 @@ static int gfx_v11_0_gpu_early_init(struct amdgpu_device *adev) adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0; break; case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): adev->gfx.config.max_hw_contexts = 8; adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; adev->gfx.config.sc_prim_fifo_size_backend = 0x100; @@ -1284,6 +1290,7 @@ static int gfx_v11_0_sw_init(void *handle) case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): adev->gfx.me.num_me = 1; adev->gfx.me.num_pipe_per_me = 1; adev->gfx.me.num_queue_per_pipe = 1; @@ -2486,7 +2493,8 @@ static int gfx_v11_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev) for (i = 0; i < adev->usec_timeout; i++) { cp_status = RREG32_SOC15(GC, 0, regCP_STAT); - if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(11, 0, 1)) + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(11, 0, 1) || + adev->ip_versions[GC_HWIP][0] == IP_VERSION(11, 0, 4)) bootload_status = RREG32_SOC15(GC, 0, regRLC_RLCS_BOOTLOAD_STATUS_gc_11_0_1); else @@ -4392,7 +4400,6 @@ static int gfx_v11_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; - uint32_t tmp; amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); @@ -4411,15 +4418,14 @@ static int gfx_v11_0_hw_fini(void *handle) amdgpu_mes_kiq_hw_fini(adev); } - if (amdgpu_sriov_vf(adev)) { - gfx_v11_0_cp_gfx_enable(adev, false); - /* Program KIQ position of RLC_CP_SCHEDULERS during destroy */ - tmp = RREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS); - tmp &= 0xffffff00; - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); - + if (amdgpu_sriov_vf(adev)) + /* Remove the steps disabling CPG and clearing KIQ position, + * so that CP could perform IDLE-SAVE during switch. Those + * steps are necessary to avoid a DMAR error in gfx9 but it is + * not reproduced on gfx11. + */ return 0; - } + gfx_v11_0_cp_enable(adev, false); gfx_v11_0_enable_gui_idle_interrupt(adev, false); @@ -5052,6 +5058,7 @@ static void gfx_v11_cntl_power_gating(struct amdgpu_device *adev, bool enable) if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): WREG32_SOC15(GC, 0, regRLC_PG_DELAY_3, RLC_PG_DELAY_3_DEFAULT_GC_11_0_1); break; default: @@ -5085,6 +5092,7 @@ static int gfx_v11_0_set_powergating_state(void *handle, amdgpu_gfx_off_ctrl(adev, enable); break; case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): gfx_v11_cntl_pg(adev, enable); amdgpu_gfx_off_ctrl(adev, enable); break; @@ -5108,6 +5116,7 @@ static int gfx_v11_0_set_clockgating_state(void *handle, case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): gfx_v11_0_update_gfx_clock_gating(adev, state == AMD_CG_STATE_GATE); break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 676832da75eb..f202b45c413c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -47,6 +47,7 @@ #include "amdgpu_ras.h" +#include "amdgpu_ring_mux.h" #include "gfx_v9_4.h" #include "gfx_v9_0.h" #include "gfx_v9_4_2.h" @@ -56,6 +57,7 @@ #include "asic_reg/gc/gc_9_0_default.h" #define GFX9_NUM_GFX_RINGS 1 +#define GFX9_NUM_SW_GFX_RINGS 2 #define GFX9_MEC_HPD_SIZE 4096 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L #define RLC_SAVE_RESTORE_ADDR_STARTING_OFFSET 0x00000000L @@ -753,7 +755,7 @@ static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev); static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info); static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev); -static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring); +static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume); static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring); static void gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev, void *ras_error_status); @@ -826,9 +828,10 @@ static void gfx_v9_0_kiq_unmap_queues(struct amdgpu_ring *kiq_ring, PACKET3_UNMAP_QUEUES_DOORBELL_OFFSET0(ring->doorbell_index)); if (action == PREEMPT_QUEUES_NO_UNMAP) { - amdgpu_ring_write(kiq_ring, lower_32_bits(gpu_addr)); - amdgpu_ring_write(kiq_ring, upper_32_bits(gpu_addr)); - amdgpu_ring_write(kiq_ring, seq); + amdgpu_ring_write(kiq_ring, lower_32_bits(ring->wptr & ring->buf_mask)); + amdgpu_ring_write(kiq_ring, 0); + amdgpu_ring_write(kiq_ring, 0); + } else { amdgpu_ring_write(kiq_ring, 0); amdgpu_ring_write(kiq_ring, 0); @@ -2103,6 +2106,7 @@ static int gfx_v9_0_sw_init(void *handle) struct amdgpu_ring *ring; struct amdgpu_kiq *kiq; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + unsigned int hw_prio; switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): @@ -2186,6 +2190,9 @@ static int gfx_v9_0_sw_init(void *handle) sprintf(ring->name, "gfx_%d", i); ring->use_doorbell = true; ring->doorbell_index = adev->doorbell_index.gfx_ring0 << 1; + + /* disable scheduler on the real ring */ + ring->no_scheduler = true; r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP, AMDGPU_RING_PRIO_DEFAULT, NULL); @@ -2193,6 +2200,41 @@ static int gfx_v9_0_sw_init(void *handle) return r; } + /* set up the software rings */ + if (adev->gfx.num_gfx_rings) { + for (i = 0; i < GFX9_NUM_SW_GFX_RINGS; i++) { + ring = &adev->gfx.sw_gfx_ring[i]; + ring->ring_obj = NULL; + sprintf(ring->name, amdgpu_sw_ring_name(i)); + ring->use_doorbell = true; + ring->doorbell_index = adev->doorbell_index.gfx_ring0 << 1; + ring->is_sw_ring = true; + hw_prio = amdgpu_sw_ring_priority(i); + r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, + AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP, hw_prio, + NULL); + if (r) + return r; + ring->wptr = 0; + } + + /* init the muxer and add software rings */ + r = amdgpu_ring_mux_init(&adev->gfx.muxer, &adev->gfx.gfx_ring[0], + GFX9_NUM_SW_GFX_RINGS); + if (r) { + DRM_ERROR("amdgpu_ring_mux_init failed(%d)\n", r); + return r; + } + for (i = 0; i < GFX9_NUM_SW_GFX_RINGS; i++) { + r = amdgpu_ring_mux_add_sw_ring(&adev->gfx.muxer, + &adev->gfx.sw_gfx_ring[i]); + if (r) { + DRM_ERROR("amdgpu_ring_mux_add_sw_ring failed(%d)\n", r); + return r; + } + } + } + /* set up the compute queues - allocate horizontally across pipes */ ring_id = 0; for (i = 0; i < adev->gfx.mec.num_mec; ++i) { @@ -2243,6 +2285,12 @@ static int gfx_v9_0_sw_fini(void *handle) int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (adev->gfx.num_gfx_rings) { + for (i = 0; i < GFX9_NUM_SW_GFX_RINGS; i++) + amdgpu_ring_fini(&adev->gfx.sw_gfx_ring[i]); + amdgpu_ring_mux_fini(&adev->gfx.muxer); + } + for (i = 0; i < adev->gfx.num_gfx_rings; i++) amdgpu_ring_fini(&adev->gfx.gfx_ring[i]); for (i = 0; i < adev->gfx.num_compute_rings; i++) @@ -5157,11 +5205,17 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, control |= ib->length_dw | (vmid << 24); - if (amdgpu_sriov_vf(ring->adev) && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) { + if (ib->flags & AMDGPU_IB_FLAG_PREEMPT) { control |= INDIRECT_BUFFER_PRE_ENB(1); + if (flags & AMDGPU_IB_PREEMPTED) + control |= INDIRECT_BUFFER_PRE_RESUME(1); + if (!(ib->flags & AMDGPU_IB_FLAG_CE) && vmid) - gfx_v9_0_ring_emit_de_meta(ring); + gfx_v9_0_ring_emit_de_meta(ring, + (!amdgpu_sriov_vf(ring->adev) && + flags & AMDGPU_IB_PREEMPTED) ? + true : false); } amdgpu_ring_write(ring, header); @@ -5216,17 +5270,24 @@ static void gfx_v9_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT; bool int_sel = flags & AMDGPU_FENCE_FLAG_INT; bool writeback = flags & AMDGPU_FENCE_FLAG_TC_WB_ONLY; + bool exec = flags & AMDGPU_FENCE_FLAG_EXEC; + uint32_t dw2 = 0; /* RELEASE_MEM - flush caches, send int */ amdgpu_ring_write(ring, PACKET3(PACKET3_RELEASE_MEM, 6)); - amdgpu_ring_write(ring, ((writeback ? (EOP_TC_WB_ACTION_EN | - EOP_TC_NC_ACTION_EN) : - (EOP_TCL1_ACTION_EN | - EOP_TC_ACTION_EN | - EOP_TC_WB_ACTION_EN | - EOP_TC_MD_ACTION_EN)) | - EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | - EVENT_INDEX(5))); + + if (writeback) { + dw2 = EOP_TC_NC_ACTION_EN; + } else { + dw2 = EOP_TCL1_ACTION_EN | EOP_TC_ACTION_EN | + EOP_TC_MD_ACTION_EN; + } + dw2 |= EOP_TC_WB_ACTION_EN | EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | + EVENT_INDEX(5); + if (exec) + dw2 |= EOP_EXEC; + + amdgpu_ring_write(ring, dw2); amdgpu_ring_write(ring, DATA_SEL(write64bit ? 2 : 1) | INT_SEL(int_sel ? 2 : 0)); /* @@ -5331,33 +5392,135 @@ static void gfx_v9_ring_emit_sb(struct amdgpu_ring *ring) amdgpu_ring_write(ring, 0); } -static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring) +static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume) { + struct amdgpu_device *adev = ring->adev; struct v9_ce_ib_state ce_payload = {0}; - uint64_t csa_addr; + uint64_t offset, ce_payload_gpu_addr; + void *ce_payload_cpu_addr; int cnt; cnt = (sizeof(ce_payload) >> 2) + 4 - 2; - csa_addr = amdgpu_csa_vaddr(ring->adev); + + if (ring->is_mes_queue) { + offset = offsetof(struct amdgpu_mes_ctx_meta_data, + gfx[0].gfx_meta_data) + + offsetof(struct v9_gfx_meta_data, ce_payload); + ce_payload_gpu_addr = + amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset); + ce_payload_cpu_addr = + amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset); + } else { + offset = offsetof(struct v9_gfx_meta_data, ce_payload); + ce_payload_gpu_addr = amdgpu_csa_vaddr(ring->adev) + offset; + ce_payload_cpu_addr = adev->virt.csa_cpu_addr + offset; + } amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, cnt)); amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(2) | WRITE_DATA_DST_SEL(8) | WR_CONFIRM) | WRITE_DATA_CACHE_POLICY(0)); - amdgpu_ring_write(ring, lower_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, ce_payload))); - amdgpu_ring_write(ring, upper_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, ce_payload))); - amdgpu_ring_write_multiple(ring, (void *)&ce_payload, sizeof(ce_payload) >> 2); + amdgpu_ring_write(ring, lower_32_bits(ce_payload_gpu_addr)); + amdgpu_ring_write(ring, upper_32_bits(ce_payload_gpu_addr)); + + if (resume) + amdgpu_ring_write_multiple(ring, ce_payload_cpu_addr, + sizeof(ce_payload) >> 2); + else + amdgpu_ring_write_multiple(ring, (void *)&ce_payload, + sizeof(ce_payload) >> 2); +} + +static int gfx_v9_0_ring_preempt_ib(struct amdgpu_ring *ring) +{ + int i, r = 0; + struct amdgpu_device *adev = ring->adev; + struct amdgpu_kiq *kiq = &adev->gfx.kiq; + struct amdgpu_ring *kiq_ring = &kiq->ring; + unsigned long flags; + + if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues) + return -EINVAL; + + spin_lock_irqsave(&kiq->ring_lock, flags); + + if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) { + spin_unlock_irqrestore(&kiq->ring_lock, flags); + return -ENOMEM; + } + + /* assert preemption condition */ + amdgpu_ring_set_preempt_cond_exec(ring, false); + + ring->trail_seq += 1; + amdgpu_ring_alloc(ring, 13); + gfx_v9_0_ring_emit_fence(ring, ring->trail_fence_gpu_addr, + ring->trail_seq, AMDGPU_FENCE_FLAG_EXEC | AMDGPU_FENCE_FLAG_INT); + /*reset the CP_VMID_PREEMPT after trailing fence*/ + amdgpu_ring_emit_wreg(ring, + SOC15_REG_OFFSET(GC, 0, mmCP_VMID_PREEMPT), + 0x0); + + /* assert IB preemption, emit the trailing fence */ + kiq->pmf->kiq_unmap_queues(kiq_ring, ring, PREEMPT_QUEUES_NO_UNMAP, + ring->trail_fence_gpu_addr, + ring->trail_seq); + + amdgpu_ring_commit(kiq_ring); + spin_unlock_irqrestore(&kiq->ring_lock, flags); + + /* poll the trailing fence */ + for (i = 0; i < adev->usec_timeout; i++) { + if (ring->trail_seq == + le32_to_cpu(*ring->trail_fence_cpu_addr)) + break; + udelay(1); + } + + if (i >= adev->usec_timeout) { + r = -EINVAL; + DRM_WARN("ring %d timeout to preempt ib\n", ring->idx); + } + + amdgpu_ring_commit(ring); + + /* deassert preemption condition */ + amdgpu_ring_set_preempt_cond_exec(ring, true); + return r; } -static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring) +static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume) { + struct amdgpu_device *adev = ring->adev; struct v9_de_ib_state de_payload = {0}; - uint64_t csa_addr, gds_addr; + uint64_t offset, gds_addr, de_payload_gpu_addr; + void *de_payload_cpu_addr; int cnt; - csa_addr = amdgpu_csa_vaddr(ring->adev); - gds_addr = csa_addr + 4096; + if (ring->is_mes_queue) { + offset = offsetof(struct amdgpu_mes_ctx_meta_data, + gfx[0].gfx_meta_data) + + offsetof(struct v9_gfx_meta_data, de_payload); + de_payload_gpu_addr = + amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset); + de_payload_cpu_addr = + amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset); + + offset = offsetof(struct amdgpu_mes_ctx_meta_data, + gfx[0].gds_backup) + + offsetof(struct v9_gfx_meta_data, de_payload); + gds_addr = amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset); + } else { + offset = offsetof(struct v9_gfx_meta_data, de_payload); + de_payload_gpu_addr = amdgpu_csa_vaddr(ring->adev) + offset; + de_payload_cpu_addr = adev->virt.csa_cpu_addr + offset; + + gds_addr = ALIGN(amdgpu_csa_vaddr(ring->adev) + + AMDGPU_CSA_SIZE - adev->gds.gds_size, + PAGE_SIZE); + } + de_payload.gds_backup_addrlo = lower_32_bits(gds_addr); de_payload.gds_backup_addrhi = upper_32_bits(gds_addr); @@ -5367,9 +5530,15 @@ static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring) WRITE_DATA_DST_SEL(8) | WR_CONFIRM) | WRITE_DATA_CACHE_POLICY(0)); - amdgpu_ring_write(ring, lower_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, de_payload))); - amdgpu_ring_write(ring, upper_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, de_payload))); - amdgpu_ring_write_multiple(ring, (void *)&de_payload, sizeof(de_payload) >> 2); + amdgpu_ring_write(ring, lower_32_bits(de_payload_gpu_addr)); + amdgpu_ring_write(ring, upper_32_bits(de_payload_gpu_addr)); + + if (resume) + amdgpu_ring_write_multiple(ring, de_payload_cpu_addr, + sizeof(de_payload) >> 2); + else + amdgpu_ring_write_multiple(ring, (void *)&de_payload, + sizeof(de_payload) >> 2); } static void gfx_v9_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, @@ -5385,8 +5554,9 @@ static void gfx_v9_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags) { uint32_t dw2 = 0; - if (amdgpu_sriov_vf(ring->adev)) - gfx_v9_0_ring_emit_ce_meta(ring); + gfx_v9_0_ring_emit_ce_meta(ring, + (!amdgpu_sriov_vf(ring->adev) && + flags & AMDGPU_IB_PREEMPTED) ? true : false); dw2 |= 0x80000000; /* set load_enable otherwise this package is just NOPs */ if (flags & AMDGPU_HAVE_CTX_SWITCH) { @@ -5712,7 +5882,12 @@ static int gfx_v9_0_eop_irq(struct amdgpu_device *adev, switch (me_id) { case 0: - amdgpu_fence_process(&adev->gfx.gfx_ring[0]); + if (adev->gfx.num_gfx_rings && + !amdgpu_mcbp_handle_trailing_fence_irq(&adev->gfx.muxer)) { + /* Fence signals are handled on the software rings*/ + for (i = 0; i < GFX9_NUM_SW_GFX_RINGS; i++) + amdgpu_fence_process(&adev->gfx.sw_gfx_ring[i]); + } break; case 1: case 2: @@ -6709,6 +6884,62 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = { .emit_cntxcntl = gfx_v9_ring_emit_cntxcntl, .init_cond_exec = gfx_v9_0_ring_emit_init_cond_exec, .patch_cond_exec = gfx_v9_0_ring_emit_patch_cond_exec, + .preempt_ib = gfx_v9_0_ring_preempt_ib, + .emit_frame_cntl = gfx_v9_0_ring_emit_frame_cntl, + .emit_wreg = gfx_v9_0_ring_emit_wreg, + .emit_reg_wait = gfx_v9_0_ring_emit_reg_wait, + .emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait, + .soft_recovery = gfx_v9_0_ring_soft_recovery, + .emit_mem_sync = gfx_v9_0_emit_mem_sync, +}; + +static const struct amdgpu_ring_funcs gfx_v9_0_sw_ring_funcs_gfx = { + .type = AMDGPU_RING_TYPE_GFX, + .align_mask = 0xff, + .nop = PACKET3(PACKET3_NOP, 0x3FFF), + .support_64bit_ptrs = true, + .secure_submission_supported = true, + .vmhub = AMDGPU_GFXHUB_0, + .get_rptr = amdgpu_sw_ring_get_rptr_gfx, + .get_wptr = amdgpu_sw_ring_get_wptr_gfx, + .set_wptr = amdgpu_sw_ring_set_wptr_gfx, + .emit_frame_size = /* totally 242 maximum if 16 IBs */ + 5 + /* COND_EXEC */ + 7 + /* PIPELINE_SYNC */ + SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + + 2 + /* VM_FLUSH */ + 8 + /* FENCE for VM_FLUSH */ + 20 + /* GDS switch */ + 4 + /* double SWITCH_BUFFER, + * the first COND_EXEC jump to the place just + * prior to this double SWITCH_BUFFER + */ + 5 + /* COND_EXEC */ + 7 + /* HDP_flush */ + 4 + /* VGT_flush */ + 14 + /* CE_META */ + 31 + /* DE_META */ + 3 + /* CNTX_CTRL */ + 5 + /* HDP_INVL */ + 8 + 8 + /* FENCE x2 */ + 2 + /* SWITCH_BUFFER */ + 7, /* gfx_v9_0_emit_mem_sync */ + .emit_ib_size = 4, /* gfx_v9_0_ring_emit_ib_gfx */ + .emit_ib = gfx_v9_0_ring_emit_ib_gfx, + .emit_fence = gfx_v9_0_ring_emit_fence, + .emit_pipeline_sync = gfx_v9_0_ring_emit_pipeline_sync, + .emit_vm_flush = gfx_v9_0_ring_emit_vm_flush, + .emit_gds_switch = gfx_v9_0_ring_emit_gds_switch, + .emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush, + .test_ring = gfx_v9_0_ring_test_ring, + .test_ib = gfx_v9_0_ring_test_ib, + .insert_nop = amdgpu_sw_ring_insert_nop, + .pad_ib = amdgpu_ring_generic_pad_ib, + .emit_switch_buffer = gfx_v9_ring_emit_sb, + .emit_cntxcntl = gfx_v9_ring_emit_cntxcntl, + .init_cond_exec = gfx_v9_0_ring_emit_init_cond_exec, + .patch_cond_exec = gfx_v9_0_ring_emit_patch_cond_exec, .emit_frame_cntl = gfx_v9_0_ring_emit_frame_cntl, .emit_wreg = gfx_v9_0_ring_emit_wreg, .emit_reg_wait = gfx_v9_0_ring_emit_reg_wait, @@ -6794,6 +7025,11 @@ static void gfx_v9_0_set_ring_funcs(struct amdgpu_device *adev) for (i = 0; i < adev->gfx.num_gfx_rings; i++) adev->gfx.gfx_ring[i].funcs = &gfx_v9_0_ring_funcs_gfx; + if (adev->gfx.num_gfx_rings) { + for (i = 0; i < GFX9_NUM_SW_GFX_RINGS; i++) + adev->gfx.sw_gfx_ring[i].funcs = &gfx_v9_0_sw_ring_funcs_gfx; + } + for (i = 0; i < adev->gfx.num_compute_rings; i++) adev->gfx.compute_ring[i].funcs = &gfx_v9_0_ring_funcs_compute; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c index 716ae6f2aefe..080ff11ca305 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c @@ -357,18 +357,6 @@ static void gfxhub_v3_0_3_program_invalidation(struct amdgpu_device *adev) static int gfxhub_v3_0_3_gart_enable(struct amdgpu_device *adev) { - if (amdgpu_sriov_vf(adev)) { - /* - * GCMC_VM_FB_LOCATION_BASE/TOP is NULL for VF, becuase they are - * VF copy registers so vbios post doesn't program them, for - * SRIOV driver need to program them - */ - WREG32_SOC15(GC, 0, regGCMC_VM_FB_LOCATION_BASE, - adev->gmc.vram_start >> 24); - WREG32_SOC15(GC, 0, regGCMC_VM_FB_LOCATION_TOP, - adev->gmc.vram_end >> 24); - } - /* GART Enable. */ gfxhub_v3_0_3_init_gart_aperture_regs(adev); gfxhub_v3_0_3_init_system_aperture_regs(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index f513e2c2e964..21e46817d82d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -371,7 +371,9 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, * translation. Avoid this by doing the invalidation from the SDMA * itself. */ - r = amdgpu_job_alloc_with_ib(adev, 16 * 4, AMDGPU_IB_POOL_IMMEDIATE, + r = amdgpu_job_alloc_with_ib(ring->adev, &adev->mman.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + 16 * 4, AMDGPU_IB_POOL_IMMEDIATE, &job); if (r) goto error_alloc; @@ -380,10 +382,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, job->vm_needs_flush = true; job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop; amdgpu_ring_pad_ib(ring, &job->ibs[0]); - r = amdgpu_job_submit(job, &adev->mman.entity, - AMDGPU_FENCE_OWNER_UNDEFINED, &fence); - if (r) - goto error_submit; + fence = amdgpu_job_submit(job); mutex_unlock(&adev->mman.gtt_window_lock); @@ -392,9 +391,6 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, return; -error_submit: - amdgpu_job_free(job); - error_alloc: mutex_unlock(&adev->mman.gtt_window_lock); DRM_ERROR("Error flushing GPU TLB using the SDMA (%d)!\n", r); @@ -612,6 +608,8 @@ static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *mapping, uint64_t *flags) { + struct amdgpu_bo *bo = mapping->bo_va->base.bo; + *flags &= ~AMDGPU_PTE_EXECUTABLE; *flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE; @@ -628,6 +626,11 @@ static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev, *flags |= AMDGPU_PTE_SYSTEM; *flags &= ~AMDGPU_PTE_VALID; } + + if (bo && bo->flags & (AMDGPU_GEM_CREATE_COHERENT | + AMDGPU_GEM_CREATE_UNCACHED)) + *flags = (*flags & ~AMDGPU_PTE_MTYPE_NV10_MASK) | + AMDGPU_PTE_MTYPE_NV10(MTYPE_UC); } static unsigned gmc_v10_0_get_vbios_fb_size(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 66dfb574cc7d..4326078689cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -503,6 +503,8 @@ static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *mapping, uint64_t *flags) { + struct amdgpu_bo *bo = mapping->bo_va->base.bo; + *flags &= ~AMDGPU_PTE_EXECUTABLE; *flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE; @@ -519,6 +521,11 @@ static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev, *flags |= AMDGPU_PTE_SYSTEM; *flags &= ~AMDGPU_PTE_VALID; } + + if (bo && bo->flags & (AMDGPU_GEM_CREATE_COHERENT | + AMDGPU_GEM_CREATE_UNCACHED)) + *flags = (*flags & ~AMDGPU_PTE_MTYPE_NV10_MASK) | + AMDGPU_PTE_MTYPE_NV10(MTYPE_UC); } static unsigned gmc_v11_0_get_vbios_fb_size(struct amdgpu_device *adev) @@ -551,7 +558,10 @@ static void gmc_v11_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.node_inst_num = adev->gmc.num_umc; adev->umc.max_ras_err_cnt_per_query = UMC_V8_10_TOTAL_CHANNEL_NUM(adev); adev->umc.channel_offs = UMC_V8_10_PER_CHANNEL_OFFSET; - adev->umc.channel_idx_tbl = &umc_v8_10_channel_idx_tbl[0][0][0]; + if (adev->umc.node_inst_num == 4) + adev->umc.channel_idx_tbl = &umc_v8_10_channel_idx_tbl_ext0[0][0][0]; + else + adev->umc.channel_idx_tbl = &umc_v8_10_channel_idx_tbl[0][0][0]; adev->umc.ras = &umc_v8_10_ras; break; case IP_VERSION(8, 11, 0): @@ -749,6 +759,7 @@ static int gmc_v11_0_sw_init(void *handle) case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): adev->num_vmhubs = 2; /* * To fulfill 4-level page support, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 67ca16a8027c..08d6cf79fb15 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1113,10 +1113,80 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level, } } +static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev, + struct amdgpu_bo *bo, + struct amdgpu_bo_va_mapping *mapping, + uint64_t *flags) +{ + struct amdgpu_device *bo_adev = amdgpu_ttm_adev(bo->tbo.bdev); + bool is_vram = bo->tbo.resource->mem_type == TTM_PL_VRAM; + bool coherent = bo->flags & AMDGPU_GEM_CREATE_COHERENT; + bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED; + unsigned int mtype; + bool snoop = false; + + switch (adev->ip_versions[GC_HWIP][0]) { + case IP_VERSION(9, 4, 1): + case IP_VERSION(9, 4, 2): + if (is_vram) { + if (bo_adev == adev) { + if (uncached) + mtype = MTYPE_UC; + else if (coherent) + mtype = MTYPE_CC; + else + mtype = MTYPE_RW; + /* FIXME: is this still needed? Or does + * amdgpu_ttm_tt_pde_flags already handle this? + */ + if (adev->ip_versions[GC_HWIP][0] == + IP_VERSION(9, 4, 2) && + adev->gmc.xgmi.connected_to_cpu) + snoop = true; + } else { + if (uncached || coherent) + mtype = MTYPE_UC; + else + mtype = MTYPE_NC; + if (mapping->bo_va->is_xgmi) + snoop = true; + } + } else { + if (uncached || coherent) + mtype = MTYPE_UC; + else + mtype = MTYPE_NC; + /* FIXME: is this still needed? Or does + * amdgpu_ttm_tt_pde_flags already handle this? + */ + snoop = true; + } + break; + default: + if (uncached || coherent) + mtype = MTYPE_UC; + else + mtype = MTYPE_NC; + + /* FIXME: is this still needed? Or does + * amdgpu_ttm_tt_pde_flags already handle this? + */ + if (!is_vram) + snoop = true; + } + + if (mtype != MTYPE_NC) + *flags = (*flags & ~AMDGPU_PTE_MTYPE_VG10_MASK) | + AMDGPU_PTE_MTYPE_VG10(mtype); + *flags |= snoop ? AMDGPU_PTE_SNOOPED : 0; +} + static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *mapping, uint64_t *flags) { + struct amdgpu_bo *bo = mapping->bo_va->base.bo; + *flags &= ~AMDGPU_PTE_EXECUTABLE; *flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE; @@ -1128,14 +1198,9 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev, *flags &= ~AMDGPU_PTE_VALID; } - if ((adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 1) || - adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2)) && - !(*flags & AMDGPU_PTE_SYSTEM) && - mapping->bo_va->is_xgmi) - *flags |= AMDGPU_PTE_SNOOPED; - - if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2)) - *flags |= mapping->flags & AMDGPU_PTE_SNOOPED; + if (bo && bo->tbo.resource) + gmc_v9_0_get_coherence_flags(adev, mapping->bo_va->base.bo, + mapping, flags); } static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index f87d0f6ffc93..f2b743a93915 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -807,16 +807,5 @@ static void jpeg_v2_5_set_ras_funcs(struct amdgpu_device *adev) break; } - if (adev->jpeg.ras) { - amdgpu_ras_register_ras_block(adev, &adev->jpeg.ras->ras_block); - - strcpy(adev->jpeg.ras->ras_block.ras_comm.name, "jpeg"); - adev->jpeg.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__JPEG; - adev->jpeg.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__POISON; - adev->jpeg.ras_if = &adev->jpeg.ras->ras_block.ras_comm; - - /* If don't define special ras_late_init function, use default ras_late_init */ - if (!adev->jpeg.ras->ras_block.ras_late_init) - adev->jpeg.ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; - } + jpeg_set_ras_funcs(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 63b0d0b810ec..3beb731b2ce5 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -27,6 +27,7 @@ #include "soc15.h" #include "soc15d.h" #include "jpeg_v2_0.h" +#include "jpeg_v4_0.h" #include "vcn/vcn_4_0_0_offset.h" #include "vcn/vcn_4_0_0_sh_mask.h" @@ -38,6 +39,7 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void jpeg_v4_0_set_irq_funcs(struct amdgpu_device *adev); static int jpeg_v4_0_set_powergating_state(void *handle, enum amd_powergating_state state); +static void jpeg_v4_0_set_ras_funcs(struct amdgpu_device *adev); /** * jpeg_v4_0_early_init - set function pointers @@ -55,6 +57,7 @@ static int jpeg_v4_0_early_init(void *handle) jpeg_v4_0_set_dec_ring_funcs(adev); jpeg_v4_0_set_irq_funcs(adev); + jpeg_v4_0_set_ras_funcs(adev); return 0; } @@ -78,6 +81,18 @@ static int jpeg_v4_0_sw_init(void *handle) if (r) return r; + /* JPEG DJPEG POISON EVENT */ + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, + VCN_4_0__SRCID_DJPEG0_POISON, &adev->jpeg.inst->irq); + if (r) + return r; + + /* JPEG EJPEG POISON EVENT */ + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, + VCN_4_0__SRCID_EJPEG0_POISON, &adev->jpeg.inst->irq); + if (r) + return r; + r = amdgpu_jpeg_sw_init(adev); if (r) return r; @@ -167,6 +182,8 @@ static int jpeg_v4_0_hw_fini(void *handle) RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS)) jpeg_v4_0_set_powergating_state(adev, AMD_PG_STATE_GATE); + amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0); + return 0; } @@ -524,6 +541,10 @@ static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev, case VCN_4_0__SRCID__JPEG_DECODE: amdgpu_fence_process(&adev->jpeg.inst->ring_dec); break; + case VCN_4_0__SRCID_DJPEG0_POISON: + case VCN_4_0__SRCID_EJPEG0_POISON: + amdgpu_jpeg_process_poison_irq(adev, source, entry); + break; default: DRM_DEV_ERROR(adev->dev, "Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -607,3 +628,63 @@ const struct amdgpu_ip_block_version jpeg_v4_0_ip_block = { .rev = 0, .funcs = &jpeg_v4_0_ip_funcs, }; + +static uint32_t jpeg_v4_0_query_poison_by_instance(struct amdgpu_device *adev, + uint32_t instance, uint32_t sub_block) +{ + uint32_t poison_stat = 0, reg_value = 0; + + switch (sub_block) { + case AMDGPU_JPEG_V4_0_JPEG0: + reg_value = RREG32_SOC15(JPEG, instance, regUVD_RAS_JPEG0_STATUS); + poison_stat = REG_GET_FIELD(reg_value, UVD_RAS_JPEG0_STATUS, POISONED_PF); + break; + case AMDGPU_JPEG_V4_0_JPEG1: + reg_value = RREG32_SOC15(JPEG, instance, regUVD_RAS_JPEG1_STATUS); + poison_stat = REG_GET_FIELD(reg_value, UVD_RAS_JPEG1_STATUS, POISONED_PF); + break; + default: + break; + } + + if (poison_stat) + dev_info(adev->dev, "Poison detected in JPEG%d sub_block%d\n", + instance, sub_block); + + return poison_stat; +} + +static bool jpeg_v4_0_query_ras_poison_status(struct amdgpu_device *adev) +{ + uint32_t inst = 0, sub = 0, poison_stat = 0; + + for (inst = 0; inst < adev->jpeg.num_jpeg_inst; inst++) + for (sub = 0; sub < AMDGPU_JPEG_V4_0_MAX_SUB_BLOCK; sub++) + poison_stat += + jpeg_v4_0_query_poison_by_instance(adev, inst, sub); + + return !!poison_stat; +} + +const struct amdgpu_ras_block_hw_ops jpeg_v4_0_ras_hw_ops = { + .query_poison_status = jpeg_v4_0_query_ras_poison_status, +}; + +static struct amdgpu_jpeg_ras jpeg_v4_0_ras = { + .ras_block = { + .hw_ops = &jpeg_v4_0_ras_hw_ops, + }, +}; + +static void jpeg_v4_0_set_ras_funcs(struct amdgpu_device *adev) +{ + switch (adev->ip_versions[JPEG_HWIP][0]) { + case IP_VERSION(4, 0, 0): + adev->jpeg.ras = &jpeg_v4_0_ras; + break; + default: + break; + } + + jpeg_set_ras_funcs(adev); +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h index f1ed6ccfedca..07d36c2abd6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h @@ -24,6 +24,13 @@ #ifndef __JPEG_V4_0_H__ #define __JPEG_V4_0_H__ +enum amdgpu_jpeg_v4_0_sub_block { + AMDGPU_JPEG_V4_0_JPEG0 = 0, + AMDGPU_JPEG_V4_0_JPEG1, + + AMDGPU_JPEG_V4_0_MAX_SUB_BLOCK, +}; + extern const struct amdgpu_ip_block_version jpeg_v4_0_ip_block; #endif /* __JPEG_V4_0_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 1395453a0662..970b066b37bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -388,6 +388,7 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes) mes_set_hw_res_pkt.disable_reset = 1; mes_set_hw_res_pkt.disable_mes_log = 1; mes_set_hw_res_pkt.use_different_vmid_compute = 1; + mes_set_hw_res_pkt.enable_reg_active_poll = 1; mes_set_hw_res_pkt.oversubscription_timer = 50; return mes_v11_0_submit_pkt_and_poll_completion(mes, @@ -1253,7 +1254,9 @@ static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev) if (adev->mes.ring.sched.ready) mes_v11_0_kiq_dequeue_sched(adev); - mes_v11_0_enable(adev, false); + if (!amdgpu_sriov_vf(adev)) + mes_v11_0_enable(adev, false); + return 0; } @@ -1339,7 +1342,8 @@ static int mes_v11_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (!amdgpu_in_reset(adev) && + /* it's only intended for use in mes_self_test case, not for s0ix and reset */ + if (!amdgpu_in_reset(adev) && !adev->in_s0ix && (adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))) amdgpu_mes_self_test(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 998b5d17b271..0e664d0cc8d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -319,7 +319,7 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev) tmp = mmMMVM_L2_CNTL5_DEFAULT; tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL5, L2_CACHE_SMALLK_FRAGMENT_SIZE, 0); - WREG32_SOC15(GC, 0, mmMMVM_L2_CNTL5, tmp); + WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL5, tmp); } static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c index 1b027d069ab4..4638ea7c2eec 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c @@ -243,7 +243,7 @@ static void mmhub_v2_3_init_cache_regs(struct amdgpu_device *adev) tmp = mmMMVM_L2_CNTL5_DEFAULT; tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL5, L2_CACHE_SMALLK_FRAGMENT_SIZE, 0); - WREG32_SOC15(GC, 0, mmMMVM_L2_CNTL5, tmp); + WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL5, tmp); } static void mmhub_v2_3_enable_system_domain(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c index a1d26c4d80b8..16cc82215e2e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c @@ -275,7 +275,7 @@ static void mmhub_v3_0_init_cache_regs(struct amdgpu_device *adev) tmp = regMMVM_L2_CNTL5_DEFAULT; tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL5, L2_CACHE_SMALLK_FRAGMENT_SIZE, 0); - WREG32_SOC15(GC, 0, regMMVM_L2_CNTL5, tmp); + WREG32_SOC15(MMHUB, 0, regMMVM_L2_CNTL5, tmp); } static void mmhub_v3_0_enable_system_domain(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c index e8058edc1d10..6bdf2ef0298d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c @@ -269,7 +269,7 @@ static void mmhub_v3_0_1_init_cache_regs(struct amdgpu_device *adev) tmp = regMMVM_L2_CNTL5_DEFAULT; tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL5, L2_CACHE_SMALLK_FRAGMENT_SIZE, 0); - WREG32_SOC15(GC, 0, regMMVM_L2_CNTL5, tmp); + WREG32_SOC15(MMHUB, 0, regMMVM_L2_CNTL5, tmp); } static void mmhub_v3_0_1_enable_system_domain(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c index 770be0a8f7ce..45465acaa943 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c @@ -268,7 +268,7 @@ static void mmhub_v3_0_2_init_cache_regs(struct amdgpu_device *adev) tmp = regMMVM_L2_CNTL5_DEFAULT; tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL5, L2_CACHE_SMALLK_FRAGMENT_SIZE, 0); - WREG32_SOC15(GC, 0, regMMVM_L2_CNTL5, tmp); + WREG32_SOC15(MMHUB, 0, regMMVM_L2_CNTL5, tmp); } static void mmhub_v3_0_2_enable_system_domain(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h b/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h index f772bb499f3e..0312c71c3af9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h +++ b/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h @@ -32,7 +32,6 @@ #define RB_ENABLED (1 << 0) #define RB4_ENABLED (1 << 1) -#define MMSCH_DOORBELL_OFFSET 0x8 #define MMSCH_VF_ENGINE_STATUS__PASS 0x1 diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index b3fba8dea63c..6853b93ac82e 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -82,10 +82,10 @@ static const struct amdgpu_video_codecs nv_video_codecs_encode = /* Navi1x */ static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, @@ -100,10 +100,10 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = /* Sienna Cichlid */ static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, @@ -125,10 +125,10 @@ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, @@ -149,7 +149,7 @@ static struct amdgpu_video_codecs sriov_sc_video_codecs_decode = /* Beige Goby*/ static const struct amdgpu_video_codec_info bg_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, }; @@ -166,7 +166,7 @@ static const struct amdgpu_video_codecs bg_video_codecs_encode = { /* Yellow Carp*/ static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c index ed2293686f0d..9de46fa8f46c 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c @@ -126,32 +126,6 @@ out: return err; } -static int psp_v10_0_ring_init(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct psp_ring *ring; - struct amdgpu_device *adev = psp->adev; - - ring = &psp->km_ring; - - ring->ring_type = ring_type; - - /* allocate 4k Page of Local Frame Buffer memory for ring */ - ring->ring_size = 0x1000; - ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->firmware.rbuf, - &ring->ring_mem_mc_addr, - (void **)&ring->ring_mem); - if (ret) { - ring->ring_size = 0; - return ret; - } - - return 0; -} - static int psp_v10_0_ring_create(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -245,7 +219,6 @@ static void psp_v10_0_ring_set_wptr(struct psp_context *psp, uint32_t value) static const struct psp_funcs psp_v10_0_funcs = { .init_microcode = psp_v10_0_init_microcode, - .ring_init = psp_v10_0_ring_init, .ring_create = psp_v10_0_ring_create, .ring_stop = psp_v10_0_ring_stop, .ring_destroy = psp_v10_0_ring_destroy, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 9518b4394a6e..bd3e3e23a939 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -360,32 +360,6 @@ static int psp_v11_0_bootloader_load_sos(struct psp_context *psp) return ret; } -static int psp_v11_0_ring_init(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct psp_ring *ring; - struct amdgpu_device *adev = psp->adev; - - ring = &psp->km_ring; - - ring->ring_type = ring_type; - - /* allocate 4k Page of Local Frame Buffer memory for ring */ - ring->ring_size = 0x1000; - ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->firmware.rbuf, - &ring->ring_mem_mc_addr, - (void **)&ring->ring_mem); - if (ret) { - ring->ring_size = 0; - return ret; - } - - return 0; -} - static int psp_v11_0_ring_stop(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -779,7 +753,6 @@ static const struct psp_funcs psp_v11_0_funcs = { .bootloader_load_spl = psp_v11_0_bootloader_load_spl, .bootloader_load_sysdrv = psp_v11_0_bootloader_load_sysdrv, .bootloader_load_sos = psp_v11_0_bootloader_load_sos, - .ring_init = psp_v11_0_ring_init, .ring_create = psp_v11_0_ring_create, .ring_stop = psp_v11_0_ring_stop, .ring_destroy = psp_v11_0_ring_destroy, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.c index ff13e1beb49b..5697760a819b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0_8.c @@ -28,32 +28,6 @@ #include "mp/mp_11_0_8_offset.h" -static int psp_v11_0_8_ring_init(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct psp_ring *ring; - struct amdgpu_device *adev = psp->adev; - - ring = &psp->km_ring; - - ring->ring_type = ring_type; - - /* allocate 4k Page of Local Frame Buffer memory for ring */ - ring->ring_size = 0x1000; - ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->firmware.rbuf, - &ring->ring_mem_mc_addr, - (void **)&ring->ring_mem); - if (ret) { - ring->ring_size = 0; - return ret; - } - - return 0; -} - static int psp_v11_0_8_ring_stop(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -194,7 +168,6 @@ static void psp_v11_0_8_ring_set_wptr(struct psp_context *psp, uint32_t value) } static const struct psp_funcs psp_v11_0_8_funcs = { - .ring_init = psp_v11_0_8_ring_init, .ring_create = psp_v11_0_8_ring_create, .ring_stop = psp_v11_0_8_ring_stop, .ring_destroy = psp_v11_0_8_ring_destroy, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index 0b2ac418e4ac..8ed2281b6557 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -236,34 +236,6 @@ static void psp_v12_0_reroute_ih(struct psp_context *psp) 0x80000000, 0x8000FFFF, false); } -static int psp_v12_0_ring_init(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct psp_ring *ring; - struct amdgpu_device *adev = psp->adev; - - psp_v12_0_reroute_ih(psp); - - ring = &psp->km_ring; - - ring->ring_type = ring_type; - - /* allocate 4k Page of Local Frame Buffer memory for ring */ - ring->ring_size = 0x1000; - ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->firmware.rbuf, - &ring->ring_mem_mc_addr, - (void **)&ring->ring_mem); - if (ret) { - ring->ring_size = 0; - return ret; - } - - return 0; -} - static int psp_v12_0_ring_create(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -272,6 +244,8 @@ static int psp_v12_0_ring_create(struct psp_context *psp, struct psp_ring *ring = &psp->km_ring; struct amdgpu_device *adev = psp->adev; + psp_v12_0_reroute_ih(psp); + if (amdgpu_sriov_vf(psp->adev)) { /* Write low address of the ring to C2PMSG_102 */ psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr); @@ -425,7 +399,6 @@ static const struct psp_funcs psp_v12_0_funcs = { .init_microcode = psp_v12_0_init_microcode, .bootloader_load_sysdrv = psp_v12_0_bootloader_load_sysdrv, .bootloader_load_sos = psp_v12_0_bootloader_load_sos, - .ring_init = psp_v12_0_ring_init, .ring_create = psp_v12_0_ring_create, .ring_stop = psp_v12_0_ring_stop, .ring_destroy = psp_v12_0_ring_destroy, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 21d822b1d589..e6a26a7e5e5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -45,6 +45,9 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_7_sos.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_7_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_13_0_10_sos.bin"); +MODULE_FIRMWARE("amdgpu/psp_13_0_10_ta.bin"); +MODULE_FIRMWARE("amdgpu/psp_13_0_11_toc.bin"); +MODULE_FIRMWARE("amdgpu/psp_13_0_11_ta.bin"); /* For large FW files the time to complete can be very long */ #define USBC_PD_POLLING_LIMIT_S 240 @@ -101,6 +104,7 @@ static int psp_v13_0_init_microcode(struct psp_context *psp) case IP_VERSION(13, 0, 3): case IP_VERSION(13, 0, 5): case IP_VERSION(13, 0, 8): + case IP_VERSION(13, 0, 11): err = psp_init_toc_microcode(psp, chip_name); if (err) return err; @@ -267,32 +271,6 @@ static int psp_v13_0_bootloader_load_sos(struct psp_context *psp) return ret; } -static int psp_v13_0_ring_init(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct psp_ring *ring; - struct amdgpu_device *adev = psp->adev; - - ring = &psp->km_ring; - - ring->ring_type = ring_type; - - /* allocate 4k Page of Local Frame Buffer memory for ring */ - ring->ring_size = 0x1000; - ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->firmware.rbuf, - &ring->ring_mem_mc_addr, - (void **)&ring->ring_mem); - if (ret) { - ring->ring_size = 0; - return ret; - } - - return 0; -} - static int psp_v13_0_ring_stop(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -728,7 +706,6 @@ static const struct psp_funcs psp_v13_0_funcs = { .bootloader_load_dbg_drv = psp_v13_0_bootloader_load_dbg_drv, .bootloader_load_ras_drv = psp_v13_0_bootloader_load_ras_drv, .bootloader_load_sos = psp_v13_0_bootloader_load_sos, - .ring_init = psp_v13_0_ring_init, .ring_create = psp_v13_0_ring_create, .ring_stop = psp_v13_0_ring_stop, .ring_destroy = psp_v13_0_ring_destroy, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c index 321089dfa7db..9d4e24e518e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c @@ -199,32 +199,6 @@ static int psp_v13_0_4_bootloader_load_sos(struct psp_context *psp) return ret; } -static int psp_v13_0_4_ring_init(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct psp_ring *ring; - struct amdgpu_device *adev = psp->adev; - - ring = &psp->km_ring; - - ring->ring_type = ring_type; - - /* allocate 4k Page of Local Frame Buffer memory for ring */ - ring->ring_size = 0x1000; - ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->firmware.rbuf, - &ring->ring_mem_mc_addr, - (void **)&ring->ring_mem); - if (ret) { - ring->ring_size = 0; - return ret; - } - - return 0; -} - static int psp_v13_0_4_ring_stop(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -373,7 +347,6 @@ static const struct psp_funcs psp_v13_0_4_funcs = { .bootloader_load_intf_drv = psp_v13_0_4_bootloader_load_intf_drv, .bootloader_load_dbg_drv = psp_v13_0_4_bootloader_load_dbg_drv, .bootloader_load_sos = psp_v13_0_4_bootloader_load_sos, - .ring_init = psp_v13_0_4_ring_init, .ring_create = psp_v13_0_4_ring_create, .ring_stop = psp_v13_0_4_ring_stop, .ring_destroy = psp_v13_0_4_ring_destroy, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c index 01f3bcc62a6c..157147c6c94e 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c @@ -160,32 +160,6 @@ static int psp_v3_1_bootloader_load_sos(struct psp_context *psp) return ret; } -static int psp_v3_1_ring_init(struct psp_context *psp, - enum psp_ring_type ring_type) -{ - int ret = 0; - struct psp_ring *ring; - struct amdgpu_device *adev = psp->adev; - - ring = &psp->km_ring; - - ring->ring_type = ring_type; - - /* allocate 4k Page of Local Frame Buffer memory for ring */ - ring->ring_size = 0x1000; - ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->firmware.rbuf, - &ring->ring_mem_mc_addr, - (void **)&ring->ring_mem); - if (ret) { - ring->ring_size = 0; - return ret; - } - - return 0; -} - static void psp_v3_1_reroute_ih(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; @@ -401,7 +375,6 @@ static const struct psp_funcs psp_v3_1_funcs = { .init_microcode = psp_v3_1_init_microcode, .bootloader_load_sysdrv = psp_v3_1_bootloader_load_sysdrv, .bootloader_load_sos = psp_v3_1_bootloader_load_sos, - .ring_init = psp_v3_1_ring_init, .ring_create = psp_v3_1_ring_create, .ring_stop = psp_v3_1_ring_stop, .ring_destroy = psp_v3_1_ring_destroy, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 1122bd4eae98..4d780e4430e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -907,13 +907,13 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se /** - * sdma_v4_0_gfx_stop - stop the gfx async dma engines + * sdma_v4_0_gfx_enable - enable the gfx async dma engines * * @adev: amdgpu_device pointer - * - * Stop the gfx async dma ring buffers (VEGA10). + * @enable: enable SDMA RB/IB + * control the gfx async dma ring buffers (VEGA10). */ -static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) +static void sdma_v4_0_gfx_enable(struct amdgpu_device *adev, bool enable) { u32 rb_cntl, ib_cntl; int i; @@ -922,10 +922,10 @@ static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL); - rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); + rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, enable ? 1 : 0); WREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL, rb_cntl); ib_cntl = RREG32_SDMA(i, mmSDMA0_GFX_IB_CNTL); - ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0); + ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, enable ? 1 : 0); WREG32_SDMA(i, mmSDMA0_GFX_IB_CNTL, ib_cntl); } } @@ -1044,7 +1044,7 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable) int i; if (!enable) { - sdma_v4_0_gfx_stop(adev); + sdma_v4_0_gfx_enable(adev, enable); sdma_v4_0_rlc_stop(adev); if (adev->sdma.has_page_queue) sdma_v4_0_page_stop(adev); @@ -1960,8 +1960,10 @@ static int sdma_v4_0_suspend(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SMU saves SDMA state for us */ - if (adev->in_s0ix) + if (adev->in_s0ix) { + sdma_v4_0_gfx_enable(adev, false); return 0; + } return sdma_v4_0_hw_fini(adev); } @@ -1971,8 +1973,12 @@ static int sdma_v4_0_resume(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SMU restores SDMA state for us */ - if (adev->in_s0ix) + if (adev->in_s0ix) { + sdma_v4_0_enable(adev, true); + sdma_v4_0_gfx_enable(adev, true); + amdgpu_ttm_set_buffer_funcs_status(adev, true); return 0; + } return sdma_v4_0_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index e3b2b6b4f1a6..7cd17dda32ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -103,10 +103,10 @@ static const struct amdgpu_video_codecs vega_video_codecs_encode = /* Vega */ static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, }; @@ -120,10 +120,10 @@ static const struct amdgpu_video_codecs vega_video_codecs_decode = /* Raven */ static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)}, @@ -138,10 +138,10 @@ static const struct amdgpu_video_codecs rv_video_codecs_decode = /* Renoir, Arcturus */ static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h index 799925d22fc8..2357ff39323f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15d.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h @@ -162,6 +162,7 @@ * 2 - Bypass */ #define INDIRECT_BUFFER_PRE_ENB(x) ((x) << 21) +#define INDIRECT_BUFFER_PRE_RESUME(x) ((x) << 30) #define PACKET3_COPY_DATA 0x40 #define PACKET3_PFP_SYNC_ME 0x42 #define PACKET3_COND_WRITE 0x45 @@ -184,6 +185,7 @@ #define EOP_TC_ACTION_EN (1 << 17) /* L2 */ #define EOP_TC_NC_ACTION_EN (1 << 19) #define EOP_TC_MD_ACTION_EN (1 << 21) /* L2 metadata */ +#define EOP_EXEC (1 << 28) /* For Trailing Fence */ #define DATA_SEL(x) ((x) << 29) /* 0 - discard diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 1d4013ed0d10..5562670b7b52 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -43,6 +43,7 @@ #include "soc15.h" #include "soc15_common.h" #include "soc21.h" +#include "mxgpu_nv.h" static const struct amd_ip_funcs soc21_common_ip_funcs; @@ -61,7 +62,7 @@ static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode = static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, @@ -322,8 +323,10 @@ soc21_asic_reset_method(struct amdgpu_device *adev) switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 0): case IP_VERSION(13, 0, 7): + case IP_VERSION(13, 0, 10): return AMD_RESET_METHOD_MODE1; case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): return AMD_RESET_METHOD_MODE2; default: if (amdgpu_dpm_is_baco_supported(adev)) @@ -643,24 +646,62 @@ static int soc21_common_early_init(void *handle) AMD_PG_SUPPORT_JPEG; adev->external_rev_id = adev->rev_id + 0x20; break; + case IP_VERSION(11, 0, 4): + adev->cg_flags = + AMD_CG_SUPPORT_GFX_CGCG | + AMD_CG_SUPPORT_GFX_CGLS | + AMD_CG_SUPPORT_GFX_MGCG | + AMD_CG_SUPPORT_GFX_FGCG | + AMD_CG_SUPPORT_REPEATER_FGCG | + AMD_CG_SUPPORT_GFX_PERF_CLK | + AMD_CG_SUPPORT_MC_MGCG | + AMD_CG_SUPPORT_MC_LS | + AMD_CG_SUPPORT_HDP_MGCG | + AMD_CG_SUPPORT_HDP_LS | + AMD_CG_SUPPORT_ATHUB_MGCG | + AMD_CG_SUPPORT_ATHUB_LS | + AMD_CG_SUPPORT_IH_CG | + AMD_CG_SUPPORT_BIF_MGCG | + AMD_CG_SUPPORT_BIF_LS | + AMD_CG_SUPPORT_VCN_MGCG | + AMD_CG_SUPPORT_JPEG_MGCG; + adev->pg_flags = AMD_PG_SUPPORT_VCN | + AMD_PG_SUPPORT_VCN_DPG | + AMD_PG_SUPPORT_GFX_PG | + AMD_PG_SUPPORT_JPEG; + adev->external_rev_id = adev->rev_id + 0x1; + break; + default: /* FIXME: not supported yet */ return -EINVAL; } - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { amdgpu_virt_init_setting(adev); + xgpu_nv_mailbox_set_irq_funcs(adev); + } return 0; } static int soc21_common_late_init(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (amdgpu_sriov_vf(adev)) + xgpu_nv_mailbox_get_irq(adev); + return 0; } static int soc21_common_sw_init(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (amdgpu_sriov_vf(adev)) + xgpu_nv_mailbox_add_irq_id(adev); + return 0; } @@ -698,6 +739,9 @@ static int soc21_common_hw_fini(void *handle) /* disable the doorbell aperture */ soc21_enable_doorbell_aperture(adev, false); + if (amdgpu_sriov_vf(adev)) + xgpu_nv_mailbox_put_irq(adev); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c index 91235df54e22..b7da4528cf0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c @@ -46,6 +46,16 @@ const struct channelnum_map_colbit umc_v8_10_channelnum_map_colbit_table[] = { }; const uint32_t + umc_v8_10_channel_idx_tbl_ext0[] + [UMC_V8_10_UMC_INSTANCE_NUM] + [UMC_V8_10_CHANNEL_INSTANCE_NUM] = { + {{1, 5}, {7, 3}}, + {{14, 15}, {13, 12}}, + {{10, 11}, {9, 8}}, + {{6, 2}, {0, 4}} + }; + +const uint32_t umc_v8_10_channel_idx_tbl[] [UMC_V8_10_UMC_INSTANCE_NUM] [UMC_V8_10_CHANNEL_INSTANCE_NUM] = { diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h index 849ede88e111..25eaf4af5fcf 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h @@ -66,5 +66,9 @@ extern const uint32_t [UMC_V8_10_UMC_INSTANCE_NUM] [UMC_V8_10_CHANNEL_INSTANCE_NUM]; +extern const uint32_t + umc_v8_10_channel_idx_tbl_ext0[] + [UMC_V8_10_UMC_INSTANCE_NUM] + [UMC_V8_10_CHANNEL_INSTANCE_NUM]; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 375c440957dc..5fe872f4bea7 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -216,8 +216,8 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle uint64_t addr; int i, r; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, + AMDGPU_IB_POOL_DIRECT, &job); if (r) return r; @@ -280,8 +280,8 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint64_t addr; int i, r; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, + AMDGPU_IB_POOL_DIRECT, &job); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index e668b3baa8c6..e407be6cb63c 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -213,7 +213,7 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring) * * Open up a stream for HW test */ -static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, +static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, u32 handle, struct amdgpu_bo *bo, struct dma_fence **fence) { @@ -224,8 +224,8 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle uint64_t addr; int i, r; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, + AMDGPU_IB_POOL_DIRECT, &job); if (r) return r; @@ -276,7 +276,7 @@ err: * * Close up a stream for HW test or if userspace failed to do so */ -static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, +static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, u32 handle, struct amdgpu_bo *bo, struct dma_fence **fence) { @@ -287,8 +287,8 @@ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handl uint64_t addr; int i, r; - r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, - AMDGPU_IB_POOL_DIRECT, &job); + r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, ib_size_dw * 4, + AMDGPU_IB_POOL_DIRECT, &job); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 8a7006d62a87..ec87b00f2e05 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -770,6 +770,33 @@ static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev) } } +static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx, + bool indirect) +{ + uint32_t tmp; + + if (adev->ip_versions[UVD_HWIP][0] != IP_VERSION(2, 6, 0)) + return; + + tmp = VCN_RAS_CNTL__VCPU_VCODEC_REARM_MASK | + VCN_RAS_CNTL__VCPU_VCODEC_IH_EN_MASK | + VCN_RAS_CNTL__VCPU_VCODEC_PMI_EN_MASK | + VCN_RAS_CNTL__VCPU_VCODEC_STALL_EN_MASK; + WREG32_SOC15_DPG_MODE(inst_idx, + SOC15_DPG_MODE_OFFSET(VCN, 0, mmVCN_RAS_CNTL), + tmp, 0, indirect); + + tmp = UVD_VCPU_INT_EN__RASCNTL_VCPU_VCODEC_EN_MASK; + WREG32_SOC15_DPG_MODE(inst_idx, + SOC15_DPG_MODE_OFFSET(VCN, 0, mmUVD_VCPU_INT_EN), + tmp, 0, indirect); + + tmp = UVD_SYS_INT_EN__RASCNTL_VCPU_VCODEC_EN_MASK; + WREG32_SOC15_DPG_MODE(inst_idx, + SOC15_DPG_MODE_OFFSET(VCN, 0, mmUVD_SYS_INT_EN), + tmp, 0, indirect); +} + static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) { volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; @@ -849,6 +876,8 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_LMI_CTRL2), 0, 0, indirect); + vcn_v2_6_enable_ras(adev, inst_idx, indirect); + /* unblock VCPU register access */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_RB_ARB_CTRL), 0, 0, indirect); @@ -2002,16 +2031,5 @@ static void vcn_v2_5_set_ras_funcs(struct amdgpu_device *adev) break; } - if (adev->vcn.ras) { - amdgpu_ras_register_ras_block(adev, &adev->vcn.ras->ras_block); - - strcpy(adev->vcn.ras->ras_block.ras_comm.name, "vcn"); - adev->vcn.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__VCN; - adev->vcn.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__POISON; - adev->vcn.ras_if = &adev->vcn.ras->ras_block.ras_comm; - - /* If don't define special ras_late_init function, use default ras_late_init */ - if (!adev->vcn.ras->ras_block.ras_late_init) - adev->vcn.ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; - } + amdgpu_vcn_set_ras_funcs(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 897a5ce9c9da..1e2b22299975 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -31,6 +31,7 @@ #include "soc15_hw_ip.h" #include "vcn_v2_0.h" #include "mmsch_v4_0.h" +#include "vcn_v4_0.h" #include "vcn/vcn_4_0_0_offset.h" #include "vcn/vcn_4_0_0_sh_mask.h" @@ -64,6 +65,7 @@ static int vcn_v4_0_set_powergating_state(void *handle, static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, struct dpg_pause_state *new_state); static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring); +static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev); /** * vcn_v4_0_early_init - set function pointers @@ -84,6 +86,7 @@ static int vcn_v4_0_early_init(void *handle) vcn_v4_0_set_unified_ring_funcs(adev); vcn_v4_0_set_irq_funcs(adev); + vcn_v4_0_set_ras_funcs(adev); return 0; } @@ -100,7 +103,6 @@ static int vcn_v4_0_sw_init(void *handle) struct amdgpu_ring *ring; struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i, r; - int vcn_doorbell_index = 0; r = amdgpu_vcn_sw_init(adev); if (r) @@ -112,12 +114,6 @@ static int vcn_v4_0_sw_init(void *handle) if (r) return r; - if (amdgpu_sriov_vf(adev)) { - vcn_doorbell_index = adev->doorbell_index.vcn.vcn_ring0_1 - MMSCH_DOORBELL_OFFSET; - /* get DWORD offset */ - vcn_doorbell_index = vcn_doorbell_index << 1; - } - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { volatile struct amdgpu_vcn4_fw_shared *fw_shared; @@ -132,10 +128,16 @@ static int vcn_v4_0_sw_init(void *handle) if (r) return r; + /* VCN POISON TRAP */ + r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i], + VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[i].irq); + if (r) + return r; + ring = &adev->vcn.inst[i].ring_enc[0]; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) - ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1; + ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i * (adev->vcn.num_enc_rings + 1) + 1; else ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i; @@ -296,6 +298,7 @@ static int vcn_v4_0_hw_fini(void *handle) } } + amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0); } return 0; @@ -859,6 +862,28 @@ static void vcn_v4_0_enable_clock_gating(struct amdgpu_device *adev, int inst) return; } +static void vcn_v4_0_enable_ras(struct amdgpu_device *adev, int inst_idx, + bool indirect) +{ + uint32_t tmp; + + if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) + return; + + tmp = VCN_RAS_CNTL__VCPU_VCODEC_REARM_MASK | + VCN_RAS_CNTL__VCPU_VCODEC_IH_EN_MASK | + VCN_RAS_CNTL__VCPU_VCODEC_PMI_EN_MASK | + VCN_RAS_CNTL__VCPU_VCODEC_STALL_EN_MASK; + WREG32_SOC15_DPG_MODE(inst_idx, + SOC15_DPG_MODE_OFFSET(VCN, 0, regVCN_RAS_CNTL), + tmp, 0, indirect); + + tmp = UVD_SYS_INT_EN__RASCNTL_VCPU_VCODEC_EN_MASK; + WREG32_SOC15_DPG_MODE(inst_idx, + SOC15_DPG_MODE_OFFSET(VCN, 0, regUVD_SYS_INT_EN), + tmp, 0, indirect); +} + /** * vcn_v4_0_start_dpg_mode - VCN start with dpg mode * @@ -947,6 +972,8 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, regUVD_LMI_CTRL2), tmp, 0, indirect); + vcn_v4_0_enable_ras(adev, inst_idx, indirect); + /* enable master interrupt */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, regUVD_MASTINT_EN), @@ -1939,6 +1966,9 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_ case VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE: amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[0]); break; + case VCN_4_0__SRCID_UVD_POISON: + amdgpu_vcn_process_poison_irq(adev, source, entry); + break; default: DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -2001,3 +2031,60 @@ const struct amdgpu_ip_block_version vcn_v4_0_ip_block = .rev = 0, .funcs = &vcn_v4_0_ip_funcs, }; + +static uint32_t vcn_v4_0_query_poison_by_instance(struct amdgpu_device *adev, + uint32_t instance, uint32_t sub_block) +{ + uint32_t poison_stat = 0, reg_value = 0; + + switch (sub_block) { + case AMDGPU_VCN_V4_0_VCPU_VCODEC: + reg_value = RREG32_SOC15(VCN, instance, regUVD_RAS_VCPU_VCODEC_STATUS); + poison_stat = REG_GET_FIELD(reg_value, UVD_RAS_VCPU_VCODEC_STATUS, POISONED_PF); + break; + default: + break; + } + + if (poison_stat) + dev_info(adev->dev, "Poison detected in VCN%d, sub_block%d\n", + instance, sub_block); + + return poison_stat; +} + +static bool vcn_v4_0_query_ras_poison_status(struct amdgpu_device *adev) +{ + uint32_t inst, sub; + uint32_t poison_stat = 0; + + for (inst = 0; inst < adev->vcn.num_vcn_inst; inst++) + for (sub = 0; sub < AMDGPU_VCN_V4_0_MAX_SUB_BLOCK; sub++) + poison_stat += + vcn_v4_0_query_poison_by_instance(adev, inst, sub); + + return !!poison_stat; +} + +const struct amdgpu_ras_block_hw_ops vcn_v4_0_ras_hw_ops = { + .query_poison_status = vcn_v4_0_query_ras_poison_status, +}; + +static struct amdgpu_vcn_ras vcn_v4_0_ras = { + .ras_block = { + .hw_ops = &vcn_v4_0_ras_hw_ops, + }, +}; + +static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev) +{ + switch (adev->ip_versions[VCN_HWIP][0]) { + case IP_VERSION(4, 0, 0): + adev->vcn.ras = &vcn_v4_0_ras; + break; + default: + break; + } + + amdgpu_vcn_set_ras_funcs(adev); +} diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.h index 7c5c9d91bb52..7d3d11f40f27 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.h +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.h @@ -24,6 +24,12 @@ #ifndef __VCN_V4_0_H__ #define __VCN_V4_0_H__ +enum amdgpu_vcn_v4_0_sub_block { + AMDGPU_VCN_V4_0_VCPU_VCODEC = 0, + + AMDGPU_VCN_V4_0_MAX_SUB_BLOCK, +}; + extern const struct amdgpu_ip_block_version vcn_v4_0_ip_block; #endif /* __VCN_V4_0_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index f6ffd7c96ff9..12ef782eb478 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -2111,6 +2111,8 @@ void vi_set_virt_ops(struct amdgpu_device *adev) int vi_set_ip_blocks(struct amdgpu_device *adev) { + amdgpu_device_set_sriov_virtual_display(adev); + switch (adev->asic_type) { case CHIP_TOPAZ: /* topaz has no DCE, UVD, VCE */ @@ -2130,7 +2132,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block); amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block); amdgpu_device_ip_block_add(adev, &pp_smu_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) + if (adev->enable_virtual_display) amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); #if defined(CONFIG_DRM_AMD_DC) else if (amdgpu_device_has_dc_support(adev)) @@ -2150,7 +2152,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &gfx_v8_0_ip_block); amdgpu_device_ip_block_add(adev, &sdma_v3_0_ip_block); amdgpu_device_ip_block_add(adev, &pp_smu_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) + if (adev->enable_virtual_display) amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); #if defined(CONFIG_DRM_AMD_DC) else if (amdgpu_device_has_dc_support(adev)) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 5feaba6a77de..6d291aa6386b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1950,7 +1950,7 @@ static int criu_checkpoint(struct file *filep, { int ret; uint32_t num_devices, num_bos, num_objects; - uint64_t priv_size, priv_offset = 0; + uint64_t priv_size, priv_offset = 0, bo_priv_offset; if (!args->devices || !args->bos || !args->priv_data) return -EINVAL; @@ -1994,38 +1994,34 @@ static int criu_checkpoint(struct file *filep, if (ret) goto exit_unlock; - ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos, - (uint8_t __user *)args->priv_data, &priv_offset); - if (ret) - goto exit_unlock; + /* Leave room for BOs in the private data. They need to be restored + * before events, but we checkpoint them last to simplify the error + * handling. + */ + bo_priv_offset = priv_offset; + priv_offset += num_bos * sizeof(struct kfd_criu_bo_priv_data); if (num_objects) { ret = kfd_criu_checkpoint_queues(p, (uint8_t __user *)args->priv_data, &priv_offset); if (ret) - goto close_bo_fds; + goto exit_unlock; ret = kfd_criu_checkpoint_events(p, (uint8_t __user *)args->priv_data, &priv_offset); if (ret) - goto close_bo_fds; + goto exit_unlock; ret = kfd_criu_checkpoint_svm(p, (uint8_t __user *)args->priv_data, &priv_offset); if (ret) - goto close_bo_fds; + goto exit_unlock; } -close_bo_fds: - if (ret) { - /* If IOCTL returns err, user assumes all FDs opened in criu_dump_bos are closed */ - uint32_t i; - struct kfd_criu_bo_bucket *bo_buckets = (struct kfd_criu_bo_bucket *) args->bos; - - for (i = 0; i < num_bos; i++) { - if (bo_buckets[i].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) - close_fd(bo_buckets[i].dmabuf_fd); - } - } + /* This must be the last thing in this function that can fail. + * Otherwise we leak dmabuf file descriptors. + */ + ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos, + (uint8_t __user *)args->priv_data, &bo_priv_offset); exit_unlock: mutex_unlock(&p->mutex); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 267dd69737fa..3251f4783ba1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1111,7 +1111,7 @@ static int kfd_parse_subtype_cache(struct crat_subtype_cache *cache, props->cache_latency = cache->cache_latency; memcpy(props->sibling_map, cache->sibling_map, - sizeof(props->sibling_map)); + CRAT_SIBLINGMAP_SIZE); /* set the sibling_map_size as 32 for CRAT from ACPI */ props->sibling_map_size = CRAT_SIBLINGMAP_SIZE; @@ -1521,6 +1521,7 @@ int kfd_get_gpu_cache_info(struct kfd_dev *kdev, struct kfd_gpu_cache_info **pca case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): num_of_cache_types = kfd_fill_gpu_cache_info_from_gfx_config(kdev, *pcache_info); break; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index ee8e5f8b007d..b8936340742b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -153,6 +153,7 @@ static void kfd_device_info_set_event_interrupt_class(struct kfd_dev *kfd) case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): + case IP_VERSION(11, 0, 4): kfd->device_info.event_interrupt_class = &event_interrupt_class_v11; break; default: @@ -394,6 +395,7 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) f2g = &gfx_v11_kfd2kgd; break; case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): gfx_target_version = 110003; f2g = &gfx_v11_kfd2kgd; break; @@ -495,7 +497,10 @@ static int kfd_gws_init(struct kfd_dev *kfd) (KFD_GC_VERSION(kfd) == IP_VERSION(9, 4, 1) && kfd->mec2_fw_version >= 0x30) || (KFD_GC_VERSION(kfd) == IP_VERSION(9, 4, 2) - && kfd->mec2_fw_version >= 0x28)))) + && kfd->mec2_fw_version >= 0x28) || + (KFD_GC_VERSION(kfd) >= IP_VERSION(10, 3, 0) + && KFD_GC_VERSION(kfd) < IP_VERSION(11, 0, 0) + && kfd->mec2_fw_version >= 0x6b)))) ret = amdgpu_amdkfd_alloc_gws(kfd->adev, kfd->adev->gds.gws_size, &kfd->gws); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 83e3ce9f6049..729d26d648af 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -506,6 +506,7 @@ int kfd_criu_restore_event(struct file *devkfd, ret = create_other_event(p, ev, &ev_priv->event_id); break; } + mutex_unlock(&p->event_mutex); exit: if (ret) @@ -513,8 +514,6 @@ exit: kfree(ev_priv); - mutex_unlock(&p->event_mutex); - return ret; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 3723e90e3a90..10048ce16aea 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -28,7 +28,6 @@ #include "amdgpu_sync.h" #include "amdgpu_object.h" #include "amdgpu_vm.h" -#include "amdgpu_mn.h" #include "amdgpu_res_cursor.h" #include "kfd_priv.h" #include "kfd_svm.h" @@ -65,8 +64,11 @@ svm_migrate_gart_map(struct amdgpu_ring *ring, uint64_t npages, num_dw = ALIGN(adev->mman.buffer_funcs->copy_num_dw, 8); num_bytes = npages * 8; - r = amdgpu_job_alloc_with_ib(adev, num_dw * 4 + num_bytes, - AMDGPU_IB_POOL_DELAYED, &job); + r = amdgpu_job_alloc_with_ib(adev, &adev->mman.entity, + AMDGPU_FENCE_OWNER_UNDEFINED, + num_dw * 4 + num_bytes, + AMDGPU_IB_POOL_DELAYED, + &job); if (r) return r; @@ -89,18 +91,10 @@ svm_migrate_gart_map(struct amdgpu_ring *ring, uint64_t npages, cpu_addr = &job->ibs[0].ptr[num_dw]; amdgpu_gart_map(adev, 0, npages, addr, pte_flags, cpu_addr); - r = amdgpu_job_submit(job, &adev->mman.entity, - AMDGPU_FENCE_OWNER_UNDEFINED, &fence); - if (r) - goto error_free; - + fence = amdgpu_job_submit(job); dma_fence_put(fence); return r; - -error_free: - amdgpu_job_free(job); - return r; } /** diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index a26257171ab7..51b1683ac5c1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -689,13 +689,13 @@ void kfd_process_destroy_wq(void) } static void kfd_process_free_gpuvm(struct kgd_mem *mem, - struct kfd_process_device *pdd, void *kptr) + struct kfd_process_device *pdd, void **kptr) { struct kfd_dev *dev = pdd->dev; - if (kptr) { + if (kptr && *kptr) { amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(mem); - kptr = NULL; + *kptr = NULL; } amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(dev->adev, mem, pdd->drm_priv); @@ -795,7 +795,7 @@ static void kfd_process_device_destroy_ib_mem(struct kfd_process_device *pdd) if (!qpd->ib_kaddr || !qpd->ib_base) return; - kfd_process_free_gpuvm(qpd->ib_mem, pdd, qpd->ib_kaddr); + kfd_process_free_gpuvm(qpd->ib_mem, pdd, &qpd->ib_kaddr); } struct kfd_process *kfd_create_process(struct file *filep) @@ -1277,7 +1277,7 @@ static void kfd_process_device_destroy_cwsr_dgpu(struct kfd_process_device *pdd) if (!dev->cwsr_enabled || !qpd->cwsr_kaddr || !qpd->cwsr_base) return; - kfd_process_free_gpuvm(qpd->cwsr_mem, pdd, qpd->cwsr_kaddr); + kfd_process_free_gpuvm(qpd->cwsr_mem, pdd, &qpd->cwsr_kaddr); } void kfd_process_set_trap_handler(struct qcm_process_device *qpd, @@ -1576,9 +1576,9 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd, p = pdd->process; dev = pdd->dev; - ret = amdgpu_amdkfd_gpuvm_acquire_process_vm( - dev->adev, drm_file, p->pasid, - &p->kgd_process_info, &p->ef); + ret = amdgpu_amdkfd_gpuvm_acquire_process_vm(dev->adev, drm_file, + &p->kgd_process_info, + &p->ef); if (ret) { pr_err("Failed to create process VM object\n"); return ret; @@ -1593,13 +1593,19 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd, if (ret) goto err_init_cwsr; + ret = amdgpu_amdkfd_gpuvm_set_vm_pasid(dev->adev, drm_file, p->pasid); + if (ret) + goto err_set_pasid; + pdd->drm_file = drm_file; return 0; +err_set_pasid: + kfd_process_device_destroy_cwsr_dgpu(pdd); err_init_cwsr: + kfd_process_device_destroy_ib_mem(pdd); err_reserve_ib_mem: - kfd_process_device_free_bos(pdd); pdd->drm_priv = NULL; return ret; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index afe7c4998676..814f99888ab1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -26,7 +26,7 @@ #include "amdgpu_sync.h" #include "amdgpu_object.h" #include "amdgpu_vm.h" -#include "amdgpu_mn.h" +#include "amdgpu_hmm.h" #include "amdgpu.h" #include "amdgpu_xgmi.h" #include "kfd_priv.h" @@ -1596,9 +1596,9 @@ static int svm_range_validate_and_map(struct mm_struct *mm, next = min(vma->vm_end, end); npages = (next - addr) >> PAGE_SHIFT; WRITE_ONCE(p->svms.faulting_task, current); - r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL, - addr, npages, &hmm_range, - readonly, true, owner); + r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages, + readonly, owner, NULL, + &hmm_range); WRITE_ONCE(p->svms.faulting_task, NULL); if (r) { pr_debug("failed %d to get svm range pages\n", r); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 1d9b90d979c4..bceb1a5b2518 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1723,7 +1723,7 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext, /* kfd_fill_cache_non_crat_info - Fill GPU cache info using kfd_gpu_cache_info * tables */ -void kfd_fill_cache_non_crat_info(struct kfd_topology_device *dev, struct kfd_dev *kdev) +static void kfd_fill_cache_non_crat_info(struct kfd_topology_device *dev, struct kfd_dev *kdev) { struct kfd_gpu_cache_info *pcache_info = NULL; int i, j, k; @@ -1805,21 +1805,75 @@ void kfd_fill_cache_non_crat_info(struct kfd_topology_device *dev, struct kfd_de pr_debug("Added [%d] GPU cache entries\n", num_of_entries); } +static int kfd_topology_add_device_locked(struct kfd_dev *gpu, uint32_t gpu_id, + struct kfd_topology_device **dev) +{ + int proximity_domain = ++topology_crat_proximity_domain; + struct list_head temp_topology_device_list; + void *crat_image = NULL; + size_t image_size = 0; + int res; + + res = kfd_create_crat_image_virtual(&crat_image, &image_size, + COMPUTE_UNIT_GPU, gpu, + proximity_domain); + if (res) { + pr_err("Error creating VCRAT for GPU (ID: 0x%x)\n", + gpu_id); + topology_crat_proximity_domain--; + goto err; + } + + INIT_LIST_HEAD(&temp_topology_device_list); + + res = kfd_parse_crat_table(crat_image, + &temp_topology_device_list, + proximity_domain); + if (res) { + pr_err("Error parsing VCRAT for GPU (ID: 0x%x)\n", + gpu_id); + topology_crat_proximity_domain--; + goto err; + } + + kfd_topology_update_device_list(&temp_topology_device_list, + &topology_device_list); + + *dev = kfd_assign_gpu(gpu); + if (WARN_ON(!*dev)) { + res = -ENODEV; + goto err; + } + + /* Fill the cache affinity information here for the GPUs + * using VCRAT + */ + kfd_fill_cache_non_crat_info(*dev, gpu); + + /* Update the SYSFS tree, since we added another topology + * device + */ + res = kfd_topology_update_sysfs(); + if (!res) + sys_props.generation_count++; + else + pr_err("Failed to update GPU (ID: 0x%x) to sysfs topology. res=%d\n", + gpu_id, res); + +err: + kfd_destroy_crat_image(crat_image); + return res; +} + int kfd_topology_add_device(struct kfd_dev *gpu) { uint32_t gpu_id; struct kfd_topology_device *dev; struct kfd_cu_info cu_info; int res = 0; - struct list_head temp_topology_device_list; - void *crat_image = NULL; - size_t image_size = 0; - int proximity_domain; int i; const char *asic_name = amdgpu_asic_name[gpu->adev->asic_type]; - INIT_LIST_HEAD(&temp_topology_device_list); - gpu_id = kfd_generate_gpu_id(gpu); pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id); @@ -1831,54 +1885,11 @@ int kfd_topology_add_device(struct kfd_dev *gpu) */ down_write(&topology_lock); dev = kfd_assign_gpu(gpu); - if (!dev) { - proximity_domain = ++topology_crat_proximity_domain; - - res = kfd_create_crat_image_virtual(&crat_image, &image_size, - COMPUTE_UNIT_GPU, gpu, - proximity_domain); - if (res) { - pr_err("Error creating VCRAT for GPU (ID: 0x%x)\n", - gpu_id); - topology_crat_proximity_domain--; - return res; - } - - res = kfd_parse_crat_table(crat_image, - &temp_topology_device_list, - proximity_domain); - if (res) { - pr_err("Error parsing VCRAT for GPU (ID: 0x%x)\n", - gpu_id); - topology_crat_proximity_domain--; - goto err; - } - - kfd_topology_update_device_list(&temp_topology_device_list, - &topology_device_list); - - dev = kfd_assign_gpu(gpu); - if (WARN_ON(!dev)) { - res = -ENODEV; - goto err; - } - - /* Fill the cache affinity information here for the GPUs - * using VCRAT - */ - kfd_fill_cache_non_crat_info(dev, gpu); - - /* Update the SYSFS tree, since we added another topology - * device - */ - res = kfd_topology_update_sysfs(); - if (!res) - sys_props.generation_count++; - else - pr_err("Failed to update GPU (ID: 0x%x) to sysfs topology. res=%d\n", - gpu_id, res); - } + if (!dev) + res = kfd_topology_add_device_locked(gpu, gpu_id, &dev); up_write(&topology_lock); + if (res) + return res; dev->gpu_id = gpu_id; gpu->id = gpu_id; @@ -2001,11 +2012,9 @@ int kfd_topology_add_device(struct kfd_dev *gpu) kfd_debug_print_topology(); - if (!res) - kfd_notify_gpu_change(gpu_id, 1); -err: - kfd_destroy_crat_image(crat_image); - return res; + kfd_notify_gpu_change(gpu_id, 1); + + return 0; } /** diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 1cdb379a90d7..2efe93f74f84 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -5,6 +5,7 @@ menu "Display Engine Configuration" config DRM_AMD_DC bool "AMD DC - Enable new display engine" default y + depends on BROKEN || !CC_IS_CLANG || X86_64 || SPARC64 || ARM64 select SND_HDA_COMPONENT if SND_HDA_CORE # !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752 select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128 || (ARM64 && KERNEL_MODE_NEON && !CC_IS_CLANG)) @@ -13,6 +14,12 @@ config DRM_AMD_DC support for AMDGPU. This adds required support for Vega and Raven ASICs. + calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 || ARM64) + architectures built with Clang (all released versions), whereby the stack + frame gets blown up to well over 5k. This would cause an immediate kernel + panic on most architectures. We'll revert this when the following bug report + has been resolved: https://github.com/llvm/llvm-project/issues/41896. + config DRM_AMD_DC_DCN def_bool n help diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 3db79f0b5a8f..50c783e19f5a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -82,7 +82,6 @@ #include <drm/drm_atomic_uapi.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_blend.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_edid.h> #include <drm/drm_vblank.h> @@ -1097,7 +1096,7 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) /* Initialize hardware. */ memset(&hw_params, 0, sizeof(hw_params)); hw_params.fb_base = adev->gmc.fb_start; - hw_params.fb_offset = adev->gmc.aper_base; + hw_params.fb_offset = adev->vm_manager.vram_base_offset; /* backdoor load firmware and trigger dmub running */ if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) @@ -1219,7 +1218,7 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ pa_config->system_aperture.agp_top = (uint64_t)agp_top << 24; pa_config->system_aperture.fb_base = adev->gmc.fb_start; - pa_config->system_aperture.fb_offset = adev->gmc.aper_base; + pa_config->system_aperture.fb_offset = adev->vm_manager.vram_base_offset; pa_config->system_aperture.fb_top = adev->gmc.fb_end; pa_config->gart_config.page_table_start_addr = page_table_start.quad_part << 12; @@ -1364,7 +1363,44 @@ static const struct dmi_system_id hpd_disconnect_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"), + }, + }, {} + /* TODO: refactor this from a fixed table to a dynamic option */ }; static void retrieve_dmi_info(struct amdgpu_display_manager *dm) @@ -1397,6 +1433,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) memset(&init_params, 0, sizeof(init_params)); #endif + mutex_init(&adev->dm.dpia_aux_lock); mutex_init(&adev->dm.dc_lock); mutex_init(&adev->dm.audio_lock); @@ -1466,6 +1503,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) case IP_VERSION(3, 0, 1): case IP_VERSION(3, 1, 2): case IP_VERSION(3, 1, 3): + case IP_VERSION(3, 1, 4): case IP_VERSION(3, 1, 5): case IP_VERSION(3, 1, 6): init_data.flags.gpu_vm_support = true; @@ -1636,12 +1674,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } } - if (amdgpu_dm_initialize_drm_device(adev)) { - DRM_ERROR( - "amdgpu: failed to initialize sw for display support.\n"); - goto error; - } - /* Enable outbox notification only after IRQ handlers are registered and DMUB is alive. * It is expected that DMUB will resend any pending notifications at this point, for * example HPD from DPIA. @@ -1649,6 +1681,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (dc_is_dmub_outbox_supported(adev->dm.dc)) dc_enable_dmub_outbox(adev->dm.dc); + if (amdgpu_dm_initialize_drm_device(adev)) { + DRM_ERROR( + "amdgpu: failed to initialize sw for display support.\n"); + goto error; + } + /* create fake encoders for MST */ dm_dp_create_fake_mst_encoders(adev); @@ -1761,6 +1799,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev) mutex_destroy(&adev->dm.audio_lock); mutex_destroy(&adev->dm.dc_lock); + mutex_destroy(&adev->dm.dpia_aux_lock); return; } @@ -2812,7 +2851,6 @@ const struct amdgpu_ip_block_version dm_ip_block = static const struct drm_mode_config_funcs amdgpu_dm_mode_funcs = { .fb_create = amdgpu_display_user_framebuffer_create, .get_format_info = amd_get_format_info, - .output_poll_changed = drm_fb_helper_output_poll_changed, .atomic_check = amdgpu_dm_atomic_check, .atomic_commit = drm_atomic_helper_commit, }; @@ -4592,6 +4630,7 @@ static int dm_early_init(void *handle) adev_to_drm(adev)->dev, &dev_attr_s3_debug); #endif + adev->dc_enabled = true; return 0; } @@ -4831,6 +4870,35 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, return 0; } +static inline void fill_dc_dirty_rect(struct drm_plane *plane, + struct rect *dirty_rect, int32_t x, + int32_t y, int32_t width, int32_t height, + int *i, bool ffu) +{ + if (*i > DC_MAX_DIRTY_RECTS) + return; + + if (*i == DC_MAX_DIRTY_RECTS) + goto out; + + dirty_rect->x = x; + dirty_rect->y = y; + dirty_rect->width = width; + dirty_rect->height = height; + + if (ffu) + drm_dbg(plane->dev, + "[PLANE:%d] PSR FFU dirty rect size (%d, %d)\n", + plane->base.id, width, height); + else + drm_dbg(plane->dev, + "[PLANE:%d] PSR SU dirty rect at (%d, %d) size (%d, %d)", + plane->base.id, x, y, width, height); + +out: + (*i)++; +} + /** * fill_dc_dirty_rects() - Fill DC dirty regions for PSR selective updates * @@ -4851,10 +4919,6 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, * addition, certain use cases - such as cursor and multi-plane overlay (MPO) - * implicitly provide damage clips without any client support via the plane * bounds. - * - * Today, amdgpu_dm only supports the MPO and cursor usecase. - * - * TODO: Also enable for FB_DAMAGE_CLIPS */ static void fill_dc_dirty_rects(struct drm_plane *plane, struct drm_plane_state *old_plane_state, @@ -4865,12 +4929,11 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state); struct rect *dirty_rects = flip_addrs->dirty_rects; uint32_t num_clips; + struct drm_mode_rect *clips; bool bb_changed; bool fb_changed; uint32_t i = 0; - flip_addrs->dirty_rect_count = 0; - /* * Cursor plane has it's own dirty rect update interface. See * dcn10_dmub_update_cursor_data and dmub_cmd_update_cursor_info_data @@ -4878,20 +4941,20 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, if (plane->type == DRM_PLANE_TYPE_CURSOR) return; - /* - * Today, we only consider MPO use-case for PSR SU. If MPO not - * requested, and there is a plane update, do FFU. - */ + num_clips = drm_plane_get_damage_clips_count(new_plane_state); + clips = drm_plane_get_damage_clips(new_plane_state); + if (!dm_crtc_state->mpo_requested) { - dirty_rects[0].x = 0; - dirty_rects[0].y = 0; - dirty_rects[0].width = dm_crtc_state->base.mode.crtc_hdisplay; - dirty_rects[0].height = dm_crtc_state->base.mode.crtc_vdisplay; - flip_addrs->dirty_rect_count = 1; - DRM_DEBUG_DRIVER("[PLANE:%d] PSR FFU dirty rect size (%d, %d)\n", - new_plane_state->plane->base.id, - dm_crtc_state->base.mode.crtc_hdisplay, - dm_crtc_state->base.mode.crtc_vdisplay); + if (!num_clips || num_clips > DC_MAX_DIRTY_RECTS) + goto ffu; + + for (; flip_addrs->dirty_rect_count < num_clips; clips++) + fill_dc_dirty_rect(new_plane_state->plane, + &dirty_rects[i], clips->x1, + clips->y1, clips->x2 - clips->x1, + clips->y2 - clips->y1, + &flip_addrs->dirty_rect_count, + false); return; } @@ -4902,7 +4965,6 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, * If plane is moved or resized, also add old bounding box to dirty * rects. */ - num_clips = drm_plane_get_damage_clips_count(new_plane_state); fb_changed = old_plane_state->fb->base.id != new_plane_state->fb->base.id; bb_changed = (old_plane_state->crtc_x != new_plane_state->crtc_x || @@ -4910,36 +4972,51 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, old_plane_state->crtc_w != new_plane_state->crtc_w || old_plane_state->crtc_h != new_plane_state->crtc_h); - DRM_DEBUG_DRIVER("[PLANE:%d] PSR bb_changed:%d fb_changed:%d num_clips:%d\n", - new_plane_state->plane->base.id, - bb_changed, fb_changed, num_clips); - - if (num_clips || fb_changed || bb_changed) { - dirty_rects[i].x = new_plane_state->crtc_x; - dirty_rects[i].y = new_plane_state->crtc_y; - dirty_rects[i].width = new_plane_state->crtc_w; - dirty_rects[i].height = new_plane_state->crtc_h; - DRM_DEBUG_DRIVER("[PLANE:%d] PSR SU dirty rect at (%d, %d) size (%d, %d)\n", - new_plane_state->plane->base.id, - dirty_rects[i].x, dirty_rects[i].y, - dirty_rects[i].width, dirty_rects[i].height); - i += 1; - } + drm_dbg(plane->dev, + "[PLANE:%d] PSR bb_changed:%d fb_changed:%d num_clips:%d\n", + new_plane_state->plane->base.id, + bb_changed, fb_changed, num_clips); - /* Add old plane bounding-box if plane is moved or resized */ if (bb_changed) { - dirty_rects[i].x = old_plane_state->crtc_x; - dirty_rects[i].y = old_plane_state->crtc_y; - dirty_rects[i].width = old_plane_state->crtc_w; - dirty_rects[i].height = old_plane_state->crtc_h; - DRM_DEBUG_DRIVER("[PLANE:%d] PSR SU dirty rect at (%d, %d) size (%d, %d)\n", - old_plane_state->plane->base.id, - dirty_rects[i].x, dirty_rects[i].y, - dirty_rects[i].width, dirty_rects[i].height); - i += 1; - } + fill_dc_dirty_rect(new_plane_state->plane, &dirty_rects[i], + new_plane_state->crtc_x, + new_plane_state->crtc_y, + new_plane_state->crtc_w, + new_plane_state->crtc_h, &i, false); + + /* Add old plane bounding-box if plane is moved or resized */ + fill_dc_dirty_rect(new_plane_state->plane, &dirty_rects[i], + old_plane_state->crtc_x, + old_plane_state->crtc_y, + old_plane_state->crtc_w, + old_plane_state->crtc_h, &i, false); + } + + if (num_clips) { + for (; i < num_clips; clips++) + fill_dc_dirty_rect(new_plane_state->plane, + &dirty_rects[i], clips->x1, + clips->y1, clips->x2 - clips->x1, + clips->y2 - clips->y1, &i, false); + } else if (fb_changed && !bb_changed) { + fill_dc_dirty_rect(new_plane_state->plane, &dirty_rects[i], + new_plane_state->crtc_x, + new_plane_state->crtc_y, + new_plane_state->crtc_w, + new_plane_state->crtc_h, &i, false); + } + + if (i > DC_MAX_DIRTY_RECTS) + goto ffu; flip_addrs->dirty_rect_count = i; + return; + +ffu: + fill_dc_dirty_rect(new_plane_state->plane, &dirty_rects[0], 0, 0, + dm_crtc_state->base.mode.crtc_hdisplay, + dm_crtc_state->base.mode.crtc_vdisplay, + &flip_addrs->dirty_rect_count, true); } static void update_stream_scaling_settings(const struct drm_display_mode *mode, @@ -5684,7 +5761,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, const struct drm_connector_state *con_state = dm_state ? &dm_state->base : NULL; struct dc_stream_state *stream = NULL; - struct drm_display_mode mode = *drm_mode; + struct drm_display_mode mode; struct drm_display_mode saved_mode; struct drm_display_mode *freesync_mode = NULL; bool native_mode_found = false; @@ -5699,6 +5776,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, struct dc_sink *sink = NULL; + drm_mode_init(&mode, drm_mode); memset(&saved_mode, 0, sizeof(saved_mode)); if (aconnector == NULL) { @@ -6529,7 +6607,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, struct drm_connector_state *new_con_state; struct amdgpu_dm_connector *aconnector; struct dm_connector_state *dm_conn_state; - int i, j; + int i, j, ret; int vcpi, pbn_div, pbn, slot_num = 0; for_each_new_connector_in_state(state, connector, new_con_state, i) { @@ -6576,8 +6654,11 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, dm_conn_state->pbn = pbn; dm_conn_state->vcpi_slots = slot_num; - drm_dp_mst_atomic_enable_dsc(state, aconnector->port, dm_conn_state->pbn, - false); + ret = drm_dp_mst_atomic_enable_dsc(state, aconnector->port, + dm_conn_state->pbn, false); + if (ret < 0) + return ret; + continue; } @@ -7684,9 +7765,10 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->surface_updates[planes_count].plane_info = &bundle->plane_infos[planes_count]; - fill_dc_dirty_rects(plane, old_plane_state, new_plane_state, - new_crtc_state, - &bundle->flip_addrs[planes_count]); + if (acrtc_state->stream->link->psr_settings.psr_feature_enabled) + fill_dc_dirty_rects(plane, old_plane_state, + new_plane_state, new_crtc_state, + &bundle->flip_addrs[planes_count]); /* * Only allow immediate flips for fast updates that don't @@ -9593,10 +9675,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, #if defined(CONFIG_DRM_AMD_DC_DCN) if (dc_resource_is_dsc_encoding_supported(dc)) { - if (!pre_validate_dsc(state, &dm_state, vars)) { - ret = -EINVAL; + ret = pre_validate_dsc(state, &dm_state, vars); + if (ret != 0) goto fail; - } } #endif @@ -9691,9 +9772,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } #if defined(CONFIG_DRM_AMD_DC_DCN) - if (!compute_mst_dsc_configs_for_state(state, dm_state->context, vars)) { + ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); + if (ret) { DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; goto fail; } @@ -10156,79 +10237,92 @@ uint32_t dm_read_reg_func(const struct dc_context *ctx, uint32_t address, return value; } -static int amdgpu_dm_set_dmub_async_sync_status(bool is_cmd_aux, - struct dc_context *ctx, - uint8_t status_type, - uint32_t *operation_result) +int amdgpu_dm_process_dmub_aux_transfer_sync( + struct dc_context *ctx, + unsigned int link_index, + struct aux_payload *payload, + enum aux_return_code_type *operation_result) { struct amdgpu_device *adev = ctx->driver_context; - int return_status = -1; struct dmub_notification *p_notify = adev->dm.dmub_notify; + int ret = -1; - if (is_cmd_aux) { - if (status_type == DMUB_ASYNC_TO_SYNC_ACCESS_SUCCESS) { - return_status = p_notify->aux_reply.length; - *operation_result = p_notify->result; - } else if (status_type == DMUB_ASYNC_TO_SYNC_ACCESS_TIMEOUT) { - *operation_result = AUX_RET_ERROR_TIMEOUT; - } else if (status_type == DMUB_ASYNC_TO_SYNC_ACCESS_FAIL) { - *operation_result = AUX_RET_ERROR_ENGINE_ACQUIRE; - } else { - *operation_result = AUX_RET_ERROR_UNKNOWN; + mutex_lock(&adev->dm.dpia_aux_lock); + if (!dc_process_dmub_aux_transfer_async(ctx->dc, link_index, payload)) { + *operation_result = AUX_RET_ERROR_ENGINE_ACQUIRE; + goto out; + } + + if (!wait_for_completion_timeout(&adev->dm.dmub_aux_transfer_done, 10 * HZ)) { + DRM_ERROR("wait_for_completion_timeout timeout!"); + *operation_result = AUX_RET_ERROR_TIMEOUT; + goto out; + } + + if (p_notify->result != AUX_RET_SUCCESS) { + /* + * Transient states before tunneling is enabled could + * lead to this error. We can ignore this for now. + */ + if (p_notify->result != AUX_RET_ERROR_PROTOCOL_ERROR) { + DRM_WARN("DPIA AUX failed on 0x%x(%d), error %d\n", + payload->address, payload->length, + p_notify->result); } - } else { - if (status_type == DMUB_ASYNC_TO_SYNC_ACCESS_SUCCESS) { - return_status = 0; - *operation_result = p_notify->sc_status; - } else { - *operation_result = SET_CONFIG_UNKNOWN_ERROR; + *operation_result = AUX_RET_ERROR_INVALID_REPLY; + goto out; + } + + + payload->reply[0] = adev->dm.dmub_notify->aux_reply.command; + if (!payload->write && p_notify->aux_reply.length && + (payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK)) { + + if (payload->length != p_notify->aux_reply.length) { + DRM_WARN("invalid read length %d from DPIA AUX 0x%x(%d)!\n", + p_notify->aux_reply.length, + payload->address, payload->length); + *operation_result = AUX_RET_ERROR_INVALID_REPLY; + goto out; } + + memcpy(payload->data, p_notify->aux_reply.data, + p_notify->aux_reply.length); } - return return_status; + /* success */ + ret = p_notify->aux_reply.length; + *operation_result = p_notify->result; +out: + mutex_unlock(&adev->dm.dpia_aux_lock); + return ret; } -int amdgpu_dm_process_dmub_aux_transfer_sync(bool is_cmd_aux, struct dc_context *ctx, - unsigned int link_index, void *cmd_payload, void *operation_result) +int amdgpu_dm_process_dmub_set_config_sync( + struct dc_context *ctx, + unsigned int link_index, + struct set_config_cmd_payload *payload, + enum set_config_status *operation_result) { struct amdgpu_device *adev = ctx->driver_context; - int ret = 0; + bool is_cmd_complete; + int ret; - if (is_cmd_aux) { - dc_process_dmub_aux_transfer_async(ctx->dc, - link_index, (struct aux_payload *)cmd_payload); - } else if (dc_process_dmub_set_config_async(ctx->dc, link_index, - (struct set_config_cmd_payload *)cmd_payload, - adev->dm.dmub_notify)) { - return amdgpu_dm_set_dmub_async_sync_status(is_cmd_aux, - ctx, DMUB_ASYNC_TO_SYNC_ACCESS_SUCCESS, - (uint32_t *)operation_result); - } + mutex_lock(&adev->dm.dpia_aux_lock); + is_cmd_complete = dc_process_dmub_set_config_async(ctx->dc, + link_index, payload, adev->dm.dmub_notify); - ret = wait_for_completion_timeout(&adev->dm.dmub_aux_transfer_done, 10 * HZ); - if (ret == 0) { + if (is_cmd_complete || wait_for_completion_timeout(&adev->dm.dmub_aux_transfer_done, 10 * HZ)) { + ret = 0; + *operation_result = adev->dm.dmub_notify->sc_status; + } else { DRM_ERROR("wait_for_completion_timeout timeout!"); - return amdgpu_dm_set_dmub_async_sync_status(is_cmd_aux, - ctx, DMUB_ASYNC_TO_SYNC_ACCESS_TIMEOUT, - (uint32_t *)operation_result); + ret = -1; + *operation_result = SET_CONFIG_UNKNOWN_ERROR; } - if (is_cmd_aux) { - if (adev->dm.dmub_notify->result == AUX_RET_SUCCESS) { - struct aux_payload *payload = (struct aux_payload *)cmd_payload; - - payload->reply[0] = adev->dm.dmub_notify->aux_reply.command; - if (!payload->write && adev->dm.dmub_notify->aux_reply.length && - payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK) { - memcpy(payload->data, adev->dm.dmub_notify->aux_reply.data, - adev->dm.dmub_notify->aux_reply.length); - } - } - } - - return amdgpu_dm_set_dmub_async_sync_status(is_cmd_aux, - ctx, DMUB_ASYNC_TO_SYNC_ACCESS_SUCCESS, - (uint32_t *)operation_result); + mutex_unlock(&adev->dm.dpia_aux_lock); + return ret; } /* @@ -10240,8 +10334,8 @@ int amdgpu_dm_process_dmub_aux_transfer_sync(bool is_cmd_aux, struct dc_context */ bool check_seamless_boot_capability(struct amdgpu_device *adev) { - switch (adev->asic_type) { - case CHIP_VANGOGH: + switch (adev->ip_versions[DCE_HWIP][0]) { + case IP_VERSION(3, 0, 1): if (!adev->mman.keep_stolen_vga_memory) return true; break; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index b618b2586e7b..df3c25e32c65 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -51,12 +51,6 @@ #define AMDGPU_DMUB_NOTIFICATION_MAX 5 /* - * DMUB Async to Sync Mechanism Status - */ -#define DMUB_ASYNC_TO_SYNC_ACCESS_FAIL 1 -#define DMUB_ASYNC_TO_SYNC_ACCESS_TIMEOUT 2 -#define DMUB_ASYNC_TO_SYNC_ACCESS_SUCCESS 3 -/* #include "include/amdgpu_dal_power_if.h" #include "amdgpu_dm_irq.h" */ @@ -65,7 +59,9 @@ #include "signal_types.h" #include "amdgpu_dm_crc.h" struct aux_payload; +struct set_config_cmd_payload; enum aux_return_code_type; +enum set_config_status; /* Forward declarations */ struct amdgpu_device; @@ -548,6 +544,13 @@ struct amdgpu_display_manager { * occurred on certain intel platform */ bool aux_hpd_discon_quirk; + + /** + * @dpia_aux_lock: + * + * Guards access to DPIA AUX + */ + struct mutex dpia_aux_lock; }; enum dsc_clock_force_state { @@ -791,9 +794,11 @@ void amdgpu_dm_update_connector_after_detect( extern const struct drm_encoder_helper_funcs amdgpu_dm_encoder_helper_funcs; -int amdgpu_dm_process_dmub_aux_transfer_sync(bool is_cmd_aux, - struct dc_context *ctx, unsigned int link_index, - void *payload, void *operation_result); +int amdgpu_dm_process_dmub_aux_transfer_sync(struct dc_context *ctx, unsigned int link_index, + struct aux_payload *payload, enum aux_return_code_type *operation_result); + +int amdgpu_dm_process_dmub_set_config_sync(struct dc_context *ctx, unsigned int link_index, + struct set_config_cmd_payload *payload, enum set_config_status *operation_result); bool check_seamless_boot_capability(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 3675b39e297a..22125daf9dcf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -415,7 +415,7 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm, { struct amdgpu_crtc *acrtc = NULL; struct drm_plane *cursor_plane; - + bool is_dcn; int res = -ENOMEM; cursor_plane = kzalloc(sizeof(*cursor_plane), GFP_KERNEL); @@ -453,8 +453,14 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm, acrtc->otg_inst = -1; dm->adev->mode_info.crtcs[crtc_index] = acrtc; - drm_crtc_enable_color_mgmt(&acrtc->base, MAX_COLOR_LUT_ENTRIES, + + /* Don't enable DRM CRTC degamma property for DCE since it doesn't + * support programmable degamma anywhere. + */ + is_dcn = dm->adev->dm.dc->caps.color.dpp.dcn_arch; + drm_crtc_enable_color_mgmt(&acrtc->base, is_dcn ? MAX_COLOR_LUT_ENTRIES : 0, true, MAX_COLOR_LUT_ENTRIES); + drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES); return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 2c43cdd2e707..461037a3dd75 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -2639,6 +2639,25 @@ static int dp_mst_progress_status_show(struct seq_file *m, void *unused) return 0; } +/* + * Reports whether the connected display is a USB4 DPIA tunneled display + * Example usage: cat /sys/kernel/debug/dri/0/DP-8/is_dpia_link + */ +static int is_dpia_link_show(struct seq_file *m, void *data) +{ + struct drm_connector *connector = m->private; + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + struct dc_link *link = aconnector->dc_link; + + if (connector->status != connector_status_connected) + return -ENODEV; + + seq_printf(m, "%s\n", (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) ? "yes" : + (link->ep_type == DISPLAY_ENDPOINT_PHY) ? "no" : "unknown"); + + return 0; +} + DEFINE_SHOW_ATTRIBUTE(dp_dsc_fec_support); DEFINE_SHOW_ATTRIBUTE(dmub_fw_state); DEFINE_SHOW_ATTRIBUTE(dmub_tracebuffer); @@ -2650,6 +2669,7 @@ DEFINE_SHOW_ATTRIBUTE(internal_display); DEFINE_SHOW_ATTRIBUTE(psr_capability); DEFINE_SHOW_ATTRIBUTE(dp_is_mst_connector); DEFINE_SHOW_ATTRIBUTE(dp_mst_progress_status); +DEFINE_SHOW_ATTRIBUTE(is_dpia_link); static const struct file_operations dp_dsc_clock_en_debugfs_fops = { .owner = THIS_MODULE, @@ -2794,7 +2814,8 @@ static const struct { {"max_bpc", &dp_max_bpc_debugfs_fops}, {"dsc_disable_passthrough", &dp_dsc_disable_passthrough_debugfs_fops}, {"is_mst_connector", &dp_is_mst_connector_fops}, - {"mst_progress_status", &dp_mst_progress_status_fops} + {"mst_progress_status", &dp_mst_progress_status_fops}, + {"is_dpia_link", &is_dpia_link_fops} }; #ifdef CONFIG_DRM_AMD_DC_HDCP diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index f72c013d3a5b..6994c9a1ed85 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -817,9 +817,8 @@ int dm_helper_dmub_aux_transfer_sync( struct aux_payload *payload, enum aux_return_code_type *operation_result) { - return amdgpu_dm_process_dmub_aux_transfer_sync(true, ctx, - link->link_index, (void *)payload, - (void *)operation_result); + return amdgpu_dm_process_dmub_aux_transfer_sync(ctx, link->link_index, payload, + operation_result); } int dm_helpers_dmub_set_config_sync(struct dc_context *ctx, @@ -827,9 +826,8 @@ int dm_helpers_dmub_set_config_sync(struct dc_context *ctx, struct set_config_cmd_payload *payload, enum set_config_status *operation_result) { - return amdgpu_dm_process_dmub_aux_transfer_sync(false, ctx, - link->link_index, (void *)payload, - (void *)operation_result); + return amdgpu_dm_process_dmub_set_config_sync(ctx, link->link_index, payload, + operation_result); } void dm_set_dcn_clocks(struct dc_context *ctx, struct dc_clocks *clks) @@ -971,3 +969,11 @@ void dm_helpers_enable_periodic_detection(struct dc_context *ctx, bool enable) { /* TODO: add periodic detection implementation */ } + +void dm_helpers_dp_mst_update_branch_bandwidth( + struct dc_context *ctx, + struct dc_link *link) +{ + // TODO +} + diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index d7907974f25a..1edf7385f8d8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -710,13 +710,13 @@ static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn) return dsc_config.bits_per_pixel; } -static bool increase_dsc_bpp(struct drm_atomic_state *state, - struct drm_dp_mst_topology_state *mst_state, - struct dc_link *dc_link, - struct dsc_mst_fairness_params *params, - struct dsc_mst_fairness_vars *vars, - int count, - int k) +static int increase_dsc_bpp(struct drm_atomic_state *state, + struct drm_dp_mst_topology_state *mst_state, + struct dc_link *dc_link, + struct dsc_mst_fairness_params *params, + struct dsc_mst_fairness_vars *vars, + int count, + int k) { int i; bool bpp_increased[MAX_PIPES]; @@ -726,6 +726,7 @@ static bool increase_dsc_bpp(struct drm_atomic_state *state, int remaining_to_increase = 0; int link_timeslots_used; int fair_pbn_alloc; + int ret = 0; for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled) { @@ -764,52 +765,60 @@ static bool increase_dsc_bpp(struct drm_atomic_state *state, if (initial_slack[next_index] > fair_pbn_alloc) { vars[next_index].pbn += fair_pbn_alloc; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; - if (!drm_dp_mst_atomic_check(state)) { + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; + + ret = drm_dp_mst_atomic_check(state); + if (ret == 0) { vars[next_index].bpp_x16 = bpp_x16_from_pbn(params[next_index], vars[next_index].pbn); } else { vars[next_index].pbn -= fair_pbn_alloc; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; } } else { vars[next_index].pbn += initial_slack[next_index]; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; - if (!drm_dp_mst_atomic_check(state)) { + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; + + ret = drm_dp_mst_atomic_check(state); + if (ret == 0) { vars[next_index].bpp_x16 = params[next_index].bw_range.max_target_bpp_x16; } else { vars[next_index].pbn -= initial_slack[next_index]; - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; } } bpp_increased[next_index] = true; remaining_to_increase--; } - return true; + return 0; } -static bool try_disable_dsc(struct drm_atomic_state *state, - struct dc_link *dc_link, - struct dsc_mst_fairness_params *params, - struct dsc_mst_fairness_vars *vars, - int count, - int k) +static int try_disable_dsc(struct drm_atomic_state *state, + struct dc_link *dc_link, + struct dsc_mst_fairness_params *params, + struct dsc_mst_fairness_vars *vars, + int count, + int k) { int i; bool tried[MAX_PIPES]; @@ -817,6 +826,7 @@ static bool try_disable_dsc(struct drm_atomic_state *state, int max_kbps_increase; int next_index; int remaining_to_try = 0; + int ret; for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled @@ -847,49 +857,52 @@ static bool try_disable_dsc(struct drm_atomic_state *state, break; vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps); - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; - if (!drm_dp_mst_atomic_check(state)) { + ret = drm_dp_mst_atomic_check(state); + if (ret == 0) { vars[next_index].dsc_enabled = false; vars[next_index].bpp_x16 = 0; } else { vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps); - if (drm_dp_atomic_find_time_slots(state, - params[next_index].port->mgr, - params[next_index].port, - vars[next_index].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, + params[next_index].port->mgr, + params[next_index].port, + vars[next_index].pbn); + if (ret < 0) + return ret; } tried[next_index] = true; remaining_to_try--; } - return true; + return 0; } -static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dc_link *dc_link, - struct dsc_mst_fairness_vars *vars, - struct drm_dp_mst_topology_mgr *mgr, - int *link_vars_start_index) +static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dc_link *dc_link, + struct dsc_mst_fairness_vars *vars, + struct drm_dp_mst_topology_mgr *mgr, + int *link_vars_start_index) { struct dc_stream_state *stream; struct dsc_mst_fairness_params params[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; struct drm_dp_mst_topology_state *mst_state = drm_atomic_get_mst_topology_state(state, mgr); int count = 0; - int i, k; + int i, k, ret; bool debugfs_overwrite = false; memset(params, 0, sizeof(params)); if (IS_ERR(mst_state)) - return false; + return PTR_ERR(mst_state); mst_state->pbn_div = dm_mst_get_pbn_divider(dc_link); #if defined(CONFIG_DRM_AMD_DC_DCN) @@ -940,7 +953,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (count == 0) { ASSERT(0); - return true; + return 0; } /* k is start index of vars for current phy link used by mst hub */ @@ -954,13 +967,17 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; - if (drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, - vars[i + k].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, + vars[i + k].pbn); + if (ret < 0) + return ret; } - if (!drm_dp_mst_atomic_check(state) && !debugfs_overwrite) { + ret = drm_dp_mst_atomic_check(state); + if (ret == 0 && !debugfs_overwrite) { set_dsc_configs_from_fairness_vars(params, vars, count, k); - return true; + return 0; + } else if (ret != -ENOSPC) { + return ret; } /* Try max compression */ @@ -969,31 +986,36 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); vars[i + k].dsc_enabled = true; vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; - if (drm_dp_atomic_find_time_slots(state, params[i].port->mgr, - params[i].port, vars[i + k].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, + params[i].port, vars[i + k].pbn); + if (ret < 0) + return ret; } else { vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; - if (drm_dp_atomic_find_time_slots(state, params[i].port->mgr, - params[i].port, vars[i + k].pbn) < 0) - return false; + ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, + params[i].port, vars[i + k].pbn); + if (ret < 0) + return ret; } } - if (drm_dp_mst_atomic_check(state)) - return false; + ret = drm_dp_mst_atomic_check(state); + if (ret != 0) + return ret; /* Optimize degree of compression */ - if (!increase_dsc_bpp(state, mst_state, dc_link, params, vars, count, k)) - return false; + ret = increase_dsc_bpp(state, mst_state, dc_link, params, vars, count, k); + if (ret < 0) + return ret; - if (!try_disable_dsc(state, dc_link, params, vars, count, k)) - return false; + ret = try_disable_dsc(state, dc_link, params, vars, count, k); + if (ret < 0) + return ret; set_dsc_configs_from_fairness_vars(params, vars, count, k); - return true; + return 0; } static bool is_dsc_need_re_compute( @@ -1094,15 +1116,17 @@ static bool is_dsc_need_re_compute( return is_dsc_need_re_compute; } -bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dsc_mst_fairness_vars *vars) +int compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars) { int i, j; struct dc_stream_state *stream; bool computed_streams[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; + struct drm_dp_mst_topology_mgr *mst_mgr; int link_vars_start_index = 0; + int ret = 0; for (i = 0; i < dc_state->stream_count; i++) computed_streams[i] = false; @@ -1115,7 +1139,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; - if (!aconnector || !aconnector->dc_sink) + if (!aconnector || !aconnector->dc_sink || !aconnector->port) continue; if (!aconnector->dc_sink->dsc_caps.dsc_dec_caps.is_dsc_supported) @@ -1125,19 +1149,16 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, continue; if (dcn20_remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK) - return false; + return -EINVAL; if (!is_dsc_need_re_compute(state, dc_state, stream->link)) continue; - mutex_lock(&aconnector->mst_mgr.lock); - if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, - &aconnector->mst_mgr, - &link_vars_start_index)) { - mutex_unlock(&aconnector->mst_mgr.lock); - return false; - } - mutex_unlock(&aconnector->mst_mgr.lock); + mst_mgr = aconnector->port->mgr; + ret = compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, mst_mgr, + &link_vars_start_index); + if (ret != 0) + return ret; for (j = 0; j < dc_state->stream_count; j++) { if (dc_state->streams[j]->link == stream->link) @@ -1150,22 +1171,23 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, if (stream->timing.flags.DSC == 1) if (dc_stream_add_dsc_to_resource(stream->ctx->dc, dc_state, stream) != DC_OK) - return false; + return -EINVAL; } - return true; + return ret; } -static bool - pre_compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dsc_mst_fairness_vars *vars) +static int pre_compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars) { int i, j; struct dc_stream_state *stream; bool computed_streams[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; + struct drm_dp_mst_topology_mgr *mst_mgr; int link_vars_start_index = 0; + int ret = 0; for (i = 0; i < dc_state->stream_count; i++) computed_streams[i] = false; @@ -1178,7 +1200,7 @@ static bool aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; - if (!aconnector || !aconnector->dc_sink) + if (!aconnector || !aconnector->dc_sink || !aconnector->port) continue; if (!aconnector->dc_sink->dsc_caps.dsc_dec_caps.is_dsc_supported) @@ -1190,14 +1212,11 @@ static bool if (!is_dsc_need_re_compute(state, dc_state, stream->link)) continue; - mutex_lock(&aconnector->mst_mgr.lock); - if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, - &aconnector->mst_mgr, - &link_vars_start_index)) { - mutex_unlock(&aconnector->mst_mgr.lock); - return false; - } - mutex_unlock(&aconnector->mst_mgr.lock); + mst_mgr = aconnector->port->mgr; + ret = compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars, mst_mgr, + &link_vars_start_index); + if (ret != 0) + return ret; for (j = 0; j < dc_state->stream_count; j++) { if (dc_state->streams[j]->link == stream->link) @@ -1205,7 +1224,7 @@ static bool } } - return true; + return ret; } static int find_crtc_index_in_state_by_stream(struct drm_atomic_state *state, @@ -1260,9 +1279,9 @@ static bool is_dsc_precompute_needed(struct drm_atomic_state *state) return ret; } -bool pre_validate_dsc(struct drm_atomic_state *state, - struct dm_atomic_state **dm_state_ptr, - struct dsc_mst_fairness_vars *vars) +int pre_validate_dsc(struct drm_atomic_state *state, + struct dm_atomic_state **dm_state_ptr, + struct dsc_mst_fairness_vars *vars) { int i; struct dm_atomic_state *dm_state; @@ -1271,11 +1290,12 @@ bool pre_validate_dsc(struct drm_atomic_state *state, if (!is_dsc_precompute_needed(state)) { DRM_INFO_ONCE("DSC precompute is not needed.\n"); - return true; + return 0; } - if (dm_atomic_get_state(state, dm_state_ptr)) { + ret = dm_atomic_get_state(state, dm_state_ptr); + if (ret != 0) { DRM_INFO_ONCE("dm_atomic_get_state() failed\n"); - return false; + return ret; } dm_state = *dm_state_ptr; @@ -1287,7 +1307,7 @@ bool pre_validate_dsc(struct drm_atomic_state *state, local_dc_state = kmemdup(dm_state->context, sizeof(struct dc_state), GFP_KERNEL); if (!local_dc_state) - return false; + return -ENOMEM; for (i = 0; i < local_dc_state->stream_count; i++) { struct dc_stream_state *stream = dm_state->context->streams[i]; @@ -1323,9 +1343,9 @@ bool pre_validate_dsc(struct drm_atomic_state *state, if (ret != 0) goto clean_exit; - if (!pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars)) { + ret = pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars); + if (ret != 0) { DRM_INFO_ONCE("pre_compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; goto clean_exit; } @@ -1356,7 +1376,7 @@ clean_exit: kfree(local_dc_state); - return (ret == 0); + return ret; } static unsigned int kbps_from_pbn(unsigned int pbn) @@ -1399,6 +1419,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0; unsigned int max_compressed_bw_in_kbps = 0; struct dc_dsc_bw_range bw_range = {0}; + struct drm_dp_mst_topology_mgr *mst_mgr; /* * check if the mode could be supported if DSC pass-through is supported @@ -1407,7 +1428,8 @@ enum dc_status dm_dp_mst_is_port_support_mode( */ if (is_dsc_common_config_possible(stream, &bw_range) && aconnector->port->passthrough_aux) { - mutex_lock(&aconnector->mst_mgr.lock); + mst_mgr = aconnector->port->mgr; + mutex_lock(&mst_mgr->lock); cur_link_settings = stream->link->verified_link_cap; @@ -1420,7 +1442,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps, down_link_bw_in_kbps); - mutex_unlock(&aconnector->mst_mgr.lock); + mutex_unlock(&mst_mgr->lock); /* * use the maximum dsc compression bandwidth as the required diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index b92a7c5671aa..97fd70df531b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -53,15 +53,15 @@ struct dsc_mst_fairness_vars { struct amdgpu_dm_connector *aconnector; }; -bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state, - struct dsc_mst_fairness_vars *vars); +int compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars); bool needs_dsc_aux_workaround(struct dc_link *link); -bool pre_validate_dsc(struct drm_atomic_state *state, - struct dm_atomic_state **dm_state_ptr, - struct dsc_mst_fairness_vars *vars); +int pre_validate_dsc(struct drm_atomic_state *state, + struct dm_atomic_state **dm_state_ptr, + struct dsc_mst_fairness_vars *vars); enum dc_status dm_dp_mst_is_port_support_mode( struct amdgpu_dm_connector *aconnector, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index e6854f7270a6..3c50b3ff7954 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1600,6 +1600,10 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, drm_plane_create_rotation_property(plane, DRM_MODE_ROTATE_0, supported_rotations); + if (dm->adev->ip_versions[DCE_HWIP][0] > IP_VERSION(3, 0, 1) && + plane->type != DRM_PLANE_TYPE_CURSOR) + drm_plane_enable_fb_damage_clips(plane); + drm_plane_helper_add(plane, &dm_plane_helper_funcs); #ifdef CONFIG_DRM_AMD_DC_HDR 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 9b8ea6e9a2b9..a1a00f432168 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -138,7 +138,9 @@ static uint8_t get_number_of_objects(struct bios_parser *bp, uint32_t offset) uint32_t object_table_offset = bp->object_info_tbl_offset + offset; - table = GET_IMAGE(ATOM_OBJECT_TABLE, object_table_offset); + table = ((ATOM_OBJECT_TABLE *) bios_get_image(&bp->base, + object_table_offset, + struct_size(table, asObjects, 1))); if (!table) return 0; @@ -166,8 +168,9 @@ static struct graphics_object_id bios_parser_get_connector_id( uint32_t connector_table_offset = bp->object_info_tbl_offset + le16_to_cpu(bp->object_info_tbl.v1_1->usConnectorObjectTableOffset); - ATOM_OBJECT_TABLE *tbl = - GET_IMAGE(ATOM_OBJECT_TABLE, connector_table_offset); + ATOM_OBJECT_TABLE *tbl = ((ATOM_OBJECT_TABLE *) bios_get_image(&bp->base, + connector_table_offset, + struct_size(tbl, asObjects, 1))); if (!tbl) { dm_error("Can't get connector table from atom bios.\n"); @@ -662,8 +665,9 @@ static enum bp_result get_ss_info_v3_1( if (!DATA_TABLES(ASIC_InternalSS_Info)) return BP_RESULT_UNSUPPORTED; - ss_table_header_include = GET_IMAGE(ATOM_ASIC_INTERNAL_SS_INFO_V3, - DATA_TABLES(ASIC_InternalSS_Info)); + ss_table_header_include = ((ATOM_ASIC_INTERNAL_SS_INFO_V3 *) bios_get_image(&bp->base, + DATA_TABLES(ASIC_InternalSS_Info), + struct_size(ss_table_header_include, asSpreadSpectrum, 1))); table_size = (le16_to_cpu(ss_table_header_include->sHeader.usStructureSize) - sizeof(ATOM_COMMON_TABLE_HEADER)) @@ -1029,8 +1033,10 @@ static enum bp_result get_ss_info_from_internal_ss_info_tbl_V2_1( if (!DATA_TABLES(ASIC_InternalSS_Info)) return result; - header = GET_IMAGE(ATOM_ASIC_INTERNAL_SS_INFO_V2, - DATA_TABLES(ASIC_InternalSS_Info)); + header = ((ATOM_ASIC_INTERNAL_SS_INFO_V2 *) bios_get_image( + &bp->base, + DATA_TABLES(ASIC_InternalSS_Info), + struct_size(header, asSpreadSpectrum, 1))); memset(info, 0, sizeof(struct spread_spectrum_info)); @@ -1709,8 +1715,10 @@ static uint32_t get_ss_entry_number_from_internal_ss_info_tbl_v2_1( if (!DATA_TABLES(ASIC_InternalSS_Info)) return 0; - header_include = GET_IMAGE(ATOM_ASIC_INTERNAL_SS_INFO_V2, - DATA_TABLES(ASIC_InternalSS_Info)); + header_include = ((ATOM_ASIC_INTERNAL_SS_INFO_V2 *) bios_get_image( + &bp->base, + DATA_TABLES(ASIC_InternalSS_Info), + struct_size(header_include, asSpreadSpectrum, 1))); size = (le16_to_cpu(header_include->sHeader.usStructureSize) - sizeof(ATOM_COMMON_TABLE_HEADER)) @@ -1746,8 +1754,9 @@ static uint32_t get_ss_entry_number_from_internal_ss_info_tbl_V3_1( if (!DATA_TABLES(ASIC_InternalSS_Info)) return number; - header_include = GET_IMAGE(ATOM_ASIC_INTERNAL_SS_INFO_V3, - DATA_TABLES(ASIC_InternalSS_Info)); + header_include = ((ATOM_ASIC_INTERNAL_SS_INFO_V3 *) bios_get_image(&bp->base, + DATA_TABLES(ASIC_InternalSS_Info), + struct_size(header_include, asSpreadSpectrum, 1))); size = (le16_to_cpu(header_include->sHeader.usStructureSize) - sizeof(ATOM_COMMON_TABLE_HEADER)) / sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3); @@ -1789,11 +1798,13 @@ static enum bp_result bios_parser_get_gpio_pin_info( if (!DATA_TABLES(GPIO_Pin_LUT)) return BP_RESULT_BADBIOSTABLE; - header = GET_IMAGE(ATOM_GPIO_PIN_LUT, DATA_TABLES(GPIO_Pin_LUT)); + header = ((ATOM_GPIO_PIN_LUT *) bios_get_image(&bp->base, + DATA_TABLES(GPIO_Pin_LUT), + struct_size(header, asGPIO_Pin, 1))); if (!header) return BP_RESULT_BADBIOSTABLE; - if (sizeof(ATOM_COMMON_TABLE_HEADER) + sizeof(ATOM_GPIO_PIN_LUT) + if (sizeof(ATOM_COMMON_TABLE_HEADER) + struct_size(header, asGPIO_Pin, 1) > le16_to_cpu(header->sHeader.usStructureSize)) return BP_RESULT_BADBIOSTABLE; @@ -1978,7 +1989,8 @@ static ATOM_OBJECT *get_bios_object(struct bios_parser *bp, offset += bp->object_info_tbl_offset; - tbl = GET_IMAGE(ATOM_OBJECT_TABLE, offset); + tbl = ((ATOM_OBJECT_TABLE *) bios_get_image(&bp->base, offset, + struct_size(tbl, asObjects, 1))); if (!tbl) return NULL; @@ -2600,8 +2612,7 @@ static enum bp_result update_slot_layout_info( for (;;) { - record_header = (ATOM_COMMON_RECORD_HEADER *) - GET_IMAGE(ATOM_COMMON_RECORD_HEADER, record_offset); + record_header = GET_IMAGE(ATOM_COMMON_RECORD_HEADER, record_offset); if (record_header == NULL) { result = BP_RESULT_BADBIOSTABLE; break; @@ -2615,7 +2626,7 @@ static enum bp_result update_slot_layout_info( if (record_header->ucRecordType == ATOM_BRACKET_LAYOUT_RECORD_TYPE && - sizeof(ATOM_BRACKET_LAYOUT_RECORD) + struct_size(record, asConnInfo, 1) <= record_header->ucRecordSize) { record = (ATOM_BRACKET_LAYOUT_RECORD *) (record_header); @@ -2709,8 +2720,9 @@ static enum bp_result get_bracket_layout_record( genericTableOffset = bp->object_info_tbl_offset + bp->object_info_tbl.v1_3->usMiscObjectTableOffset; - object_table = (ATOM_OBJECT_TABLE *) - GET_IMAGE(ATOM_OBJECT_TABLE, genericTableOffset); + object_table = ((ATOM_OBJECT_TABLE *) bios_get_image(&bp->base, + genericTableOffset, + struct_size(object_table, asObjects, 1))); if (!object_table) return BP_RESULT_FAILURE; diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index ee0456b5e14e..074e70a5c458 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -462,6 +462,7 @@ static enum bp_result get_gpio_i2c_info( uint32_t count = 0; unsigned int table_index = 0; bool find_valid = false; + struct atom_gpio_pin_assignment *pin; if (!info) return BP_RESULT_BADINPUT; @@ -489,20 +490,17 @@ static enum bp_result get_gpio_i2c_info( - sizeof(struct atom_common_table_header)) / sizeof(struct atom_gpio_pin_assignment); + pin = (struct atom_gpio_pin_assignment *) header->gpio_pin; + for (table_index = 0; table_index < count; table_index++) { - if (((record->i2c_id & I2C_HW_CAP) == ( - header->gpio_pin[table_index].gpio_id & - I2C_HW_CAP)) && - ((record->i2c_id & I2C_HW_ENGINE_ID_MASK) == - (header->gpio_pin[table_index].gpio_id & - I2C_HW_ENGINE_ID_MASK)) && - ((record->i2c_id & I2C_HW_LANE_MUX) == - (header->gpio_pin[table_index].gpio_id & - I2C_HW_LANE_MUX))) { + if (((record->i2c_id & I2C_HW_CAP) == (pin->gpio_id & I2C_HW_CAP)) && + ((record->i2c_id & I2C_HW_ENGINE_ID_MASK) == (pin->gpio_id & I2C_HW_ENGINE_ID_MASK)) && + ((record->i2c_id & I2C_HW_LANE_MUX) == (pin->gpio_id & I2C_HW_LANE_MUX))) { /* still valid */ find_valid = true; break; } + pin = (struct atom_gpio_pin_assignment *)((uint8_t *)pin + sizeof(struct atom_gpio_pin_assignment)); } /* If we don't find the entry that we are looking for then @@ -2393,6 +2391,26 @@ static enum bp_result get_vram_info_v25( return result; } +static enum bp_result get_vram_info_v30( + struct bios_parser *bp, + struct dc_vram_info *info) +{ + struct atom_vram_info_header_v3_0 *info_v30; + enum bp_result result = BP_RESULT_OK; + + info_v30 = GET_IMAGE(struct atom_vram_info_header_v3_0, + DATA_TABLES(vram_info)); + + if (info_v30 == NULL) + return BP_RESULT_BADBIOSTABLE; + + info->num_chans = info_v30->channel_num; + info->dram_channel_width_bytes = (1 << info_v30->channel_width) / 8; + + return result; +} + + /* * get_integrated_info_v11 * @@ -3060,6 +3078,16 @@ static enum bp_result bios_parser_get_vram_info( } break; + case 3: + switch (revision.minor) { + case 0: + result = get_vram_info_v30(bp, info); + break; + default: + break; + } + break; + default: return result; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_smu11_driver_if.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_smu11_driver_if.h index 8ea8ee57b39f..61bb1d86182e 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_smu11_driver_if.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_smu11_driver_if.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT // This is a stripped-down version of the smu11_driver_if.h file for the relevant DAL interfaces. #define SMU11_DRIVER_IF_VERSION 0x40 diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index c1eaf571407a..1c0569b1dc8f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -609,8 +609,10 @@ static void dcn31_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk } bw_params->vram_type = bios_info->memory_type; - bw_params->num_channels = bios_info->ma_channel_number; + bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4; + //bw_params->dram_channel_width_bytes = dc->ctx->asic_id.vram_width; + bw_params->num_channels = bios_info->ma_channel_number ? bios_info->ma_channel_number : 4; for (i = 0; i < WM_SET_COUNT; i++) { bw_params->wm_table.entries[i].wm_inst = i; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c index 090b2c02aee1..0827c7df2855 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c @@ -333,8 +333,8 @@ void dcn31_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zst (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY)) support = DCN_ZSTATE_SUPPORT_DISALLOW; - - if (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY) + if (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY || + support == DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY) param = 1; else param = 0; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 1131c6d73f6c..20a06c04e4a1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -363,32 +363,32 @@ static struct wm_table ddr5_wm_table = { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, } @@ -400,32 +400,32 @@ static struct wm_table lpddr5_wm_table = { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c index ef0795b14a1f..f47cfe6b42bd 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c @@ -123,9 +123,10 @@ static int dcn314_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, uint32_t result; result = dcn314_smu_wait_for_response(clk_mgr, 10, 200000); - ASSERT(result == VBIOSSMC_Result_OK); - smu_print("SMU response after wait: %d\n", result); + if (result != VBIOSSMC_Result_OK) + smu_print("SMU Response was not OK. SMU response after wait received is: %d\n", + result); if (result == VBIOSSMC_Status_BUSY) return -1; @@ -216,6 +217,12 @@ int dcn314_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int request VBIOSSMC_MSG_SetHardMinDcfclkByFreq, khz_to_mhz_ceil(requested_dcfclk_khz)); +#ifdef DBG + smu_print("actual_dcfclk_set_mhz %d is set to : %d\n", + actual_dcfclk_set_mhz, + actual_dcfclk_set_mhz * 1000); +#endif + return actual_dcfclk_set_mhz * 1000; } @@ -339,8 +346,6 @@ void dcn314_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zs if (!clk_mgr->smu_present) return; - // Arg[15:0] = 8/9/0 for Z8/Z9/disallow -> existing bits - // Arg[16] = Disallow Z9 -> new bit switch (support) { case DCN_ZSTATE_SUPPORT_ALLOW: @@ -359,6 +364,16 @@ void dcn314_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zs param = (1 << 10); break; + case DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY: + msg_id = VBIOSSMC_MSG_AllowZstatesEntry; + param = (1 << 10) | (1 << 8); + break; + + case DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY: + msg_id = VBIOSSMC_MSG_AllowZstatesEntry; + param = (1 << 8); + break; + default: //DCN_ZSTATE_SUPPORT_UNKNOWN msg_id = VBIOSSMC_MSG_AllowZstatesEntry; param = 0; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 187f5b27fdc8..3edc81e2d417 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -553,6 +553,7 @@ static void dcn316_clk_mgr_helper_populate_bw_params( bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; + bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4; for (i = 0; i < WM_SET_COUNT; i++) { bw_params->wm_table.entries[i].wm_inst = i; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index 6f77d8e538ab..200fcec19186 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -233,41 +233,6 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) DC_FP_END(); } -static void dcn32_update_clocks_update_dtb_dto(struct clk_mgr_internal *clk_mgr, - struct dc_state *context, - int ref_dtbclk_khz) -{ - struct dccg *dccg = clk_mgr->dccg; - uint32_t tg_mask = 0; - int i; - - for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; - struct dtbclk_dto_params dto_params = {0}; - - /* use mask to program DTO once per tg */ - if (pipe_ctx->stream_res.tg && - !(tg_mask & (1 << pipe_ctx->stream_res.tg->inst))) { - tg_mask |= (1 << pipe_ctx->stream_res.tg->inst); - - dto_params.otg_inst = pipe_ctx->stream_res.tg->inst; - dto_params.ref_dtbclk_khz = ref_dtbclk_khz; - - if (is_dp_128b_132b_signal(pipe_ctx)) { - dto_params.pixclk_khz = pipe_ctx->stream->phy_pix_clk; - - if (pipe_ctx->stream_res.audio != NULL) - dto_params.req_audio_dtbclk_khz = 24000; - } - if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) - dto_params.is_hdmi = true; - - dccg->funcs->set_dtbclk_dto(clk_mgr->dccg, &dto_params); - //dccg->funcs->set_audio_dtbclk_dto(clk_mgr->dccg, &dto_params); - } - } -} - /* Since DPPCLK request to PMFW needs to be exact (due to DPP DTO programming), * update DPPCLK to be the exact frequency that will be set after the DPPCLK * divider is updated. This will prevent rounding issues that could cause DPP @@ -438,7 +403,7 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, } if (!new_clocks->dtbclk_en) { - new_clocks->ref_dtbclk_khz = 0; + new_clocks->ref_dtbclk_khz = clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz * 1000; } /* clock limits are received with MHz precision, divide by 1000 to prevent setting clocks at every call */ @@ -447,8 +412,6 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, /* DCCG requires KHz precision for DTBCLK */ clk_mgr_base->clks.ref_dtbclk_khz = dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_DTBCLK, khz_to_mhz_ceil(new_clocks->ref_dtbclk_khz)); - - dcn32_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz); } if (dc->config.forced_clocks == false || (force_reset && safe_to_lower)) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_smu13_driver_if.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_smu13_driver_if.h index d30fbbdd1792..d3d5a8caccf8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_smu13_driver_if.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_smu13_driver_if.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT // This is a stripped-down version of the smu13_driver_if.h file for the relevant DAL interfaces. #define SMU13_DRIVER_IF_VERSION 0x18 diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index d446e6098948..0cb8d1f934d1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1054,6 +1054,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) int i, j; struct dc_state *dangling_context = dc_create_state(dc); struct dc_state *current_ctx; + struct pipe_ctx *pipe; + struct timing_generator *tg; if (dangling_context == NULL) return; @@ -1096,6 +1098,18 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) } if (should_disable && old_stream) { + pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + tg = pipe->stream_res.tg; + /* When disabling plane for a phantom pipe, we must turn on the + * phantom OTG so the disable programming gets the double buffer + * update. Otherwise the pipe will be left in a partially disabled + * state that can result in underflow or hang when enabling it + * again for different use. + */ + if (old_stream->mall_stream_config.type == SUBVP_PHANTOM) { + if (tg->funcs->enable_crtc) + tg->funcs->enable_crtc(tg); + } dc_rem_all_planes_for_stream(dc, old_stream, dangling_context); disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context); @@ -1111,6 +1125,15 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) dc->hwss.interdependent_update_lock(dc, dc->current_state, false); dc->hwss.post_unlock_program_front_end(dc, dangling_context); } + /* We need to put the phantom OTG back into it's default (disabled) state or we + * can get corruption when transition from one SubVP config to a different one. + * The OTG is set to disable on falling edge of VUPDATE so the plane disable + * will still get it's double buffer update. + */ + if (old_stream->mall_stream_config.type == SUBVP_PHANTOM) { + if (tg->funcs->disable_phantom_crtc) + tg->funcs->disable_phantom_crtc(tg); + } } } @@ -1533,6 +1556,9 @@ bool dc_validate_boot_timing(const struct dc *dc, if (tg_inst >= dc->res_pool->timing_generator_count) return false; + if (tg_inst != link->link_enc->preferred_engine) + return false; + tg = dc->res_pool->timing_generators[tg_inst]; if (!tg->funcs->get_hw_timing) @@ -1749,6 +1775,12 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c context->stream_count == 0) dc->hwss.prepare_bandwidth(dc, context); + /* When SubVP is active, all HW programming must be done while + * SubVP lock is acquired + */ + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, true, true, NULL, subvp_prev_use); + if (dc->debug.enable_double_buffered_dsc_pg_support) dc->hwss.update_dsc_pg(dc, context, false); @@ -1776,9 +1808,6 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, pipe); } - if (dc->hwss.subvp_pipe_control_lock) - dc->hwss.subvp_pipe_control_lock(dc, context, true, true, NULL, subvp_prev_use); - result = dc->hwss.apply_ctx_to_hw(dc, context); if (result != DC_OK) { @@ -1959,7 +1988,7 @@ context_alloc_fail: DC_LOG_DC("%s Finished.\n", __func__); - return (res == DC_OK); + return res; } /* TODO: When the transition to the new commit sequence is done, remove this @@ -3035,7 +3064,7 @@ static bool update_planes_and_stream_state(struct dc *dc, * Ensures that we have enough pipes for newly added MPO planes */ if (dc->res_pool->funcs->remove_phantom_pipes) - dc->res_pool->funcs->remove_phantom_pipes(dc, context); + dc->res_pool->funcs->remove_phantom_pipes(dc, context, false); /*remove old surfaces from context */ if (!dc_rem_all_planes_for_stream(dc, stream, context)) { @@ -3072,6 +3101,19 @@ static bool update_planes_and_stream_state(struct dc *dc, if (update_type == UPDATE_TYPE_FULL) { if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { + /* For phantom pipes we remove and create a new set of phantom pipes + * for each full update (because we don't know if we'll need phantom + * pipes until after the first round of validation). However, if validation + * fails we need to keep the existing phantom pipes (because we don't update + * the dc->current_state). + * + * The phantom stream/plane refcount is decremented for validation because + * we assume it'll be removed (the free comes when the dc_state is freed), + * but if validation fails we have to increment back the refcount so it's + * consistent. + */ + if (dc->res_pool->funcs->retain_phantom_pipes) + dc->res_pool->funcs->retain_phantom_pipes(dc, dc->current_state); BREAK_TO_DEBUGGER(); goto fail; } @@ -3382,22 +3424,6 @@ static void commit_planes_for_stream(struct dc *dc, dc->hwss.pipe_control_lock(dc, top_pipe_to_program, true); } - if (update_type != UPDATE_TYPE_FAST) { - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; - - if ((new_pipe->stream && new_pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) || - subvp_prev_use) { - // If old context or new context has phantom pipes, apply - // the phantom timings now. We can't change the phantom - // pipe configuration safely without driver acquiring - // the DMCUB lock first. - dc->hwss.apply_ctx_to_hw(dc, context); - break; - } - } - } - dc_dmub_update_dirty_rect(dc, surface_count, stream, srf_updates, context); if (update_type != UPDATE_TYPE_FAST) { @@ -3455,6 +3481,24 @@ static void commit_planes_for_stream(struct dc *dc, return; } + if (update_type != UPDATE_TYPE_FAST) { + for (j = 0; j < dc->res_pool->pipe_count; j++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j]; + + if (dc->debug.visual_confirm == VISUAL_CONFIRM_SUBVP && + pipe_ctx->stream && pipe_ctx->plane_state) { + /* Only update visual confirm for SUBVP here. + * The bar appears on all pipes, so we need to update the bar on all displays, + * so the information doesn't get stale. + */ + struct mpcc_blnd_cfg blnd_cfg = { 0 }; + + dc->hwss.update_visual_confirm_color(dc, pipe_ctx, &blnd_cfg.black_color, + pipe_ctx->plane_res.hubp->inst); + } + } + } + if (!IS_DIAG_DC(dc->ctx->dce_environment)) { for (i = 0; i < surface_count; i++) { struct dc_plane_state *plane_state = srf_updates[i].surface; @@ -3572,7 +3616,6 @@ static void commit_planes_for_stream(struct dc *dc, dc->hwss.update_plane_addr(dc, pipe_ctx); } } - } if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) { @@ -3609,6 +3652,44 @@ static void commit_planes_for_stream(struct dc *dc, top_pipe_to_program->stream_res.tg); } + /* For phantom pipe OTG enable, it has to be done after any previous pipe + * that was in use has already been programmed at gotten its double buffer + * update for "disable". + */ + if (update_type != UPDATE_TYPE_FAST) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + /* If an active, non-phantom pipe is being transitioned into a phantom + * pipe, wait for the double buffer update to complete first before we do + * ANY phantom pipe programming. + */ + if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM && + old_pipe->stream && old_pipe->stream->mall_stream_config.type != SUBVP_PHANTOM) { + old_pipe->stream_res.tg->funcs->wait_for_state( + old_pipe->stream_res.tg, + CRTC_STATE_VBLANK); + old_pipe->stream_res.tg->funcs->wait_for_state( + old_pipe->stream_res.tg, + CRTC_STATE_VACTIVE); + } + } + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; + + if ((new_pipe->stream && new_pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) || + subvp_prev_use) { + // If old context or new context has phantom pipes, apply + // the phantom timings now. We can't change the phantom + // pipe configuration safely without driver acquiring + // the DMCUB lock first. + dc->hwss.apply_ctx_to_hw(dc, context); + break; + } + } + } + if (update_type != UPDATE_TYPE_FAST) dc->hwss.post_unlock_program_front_end(dc, context); if (update_type != UPDATE_TYPE_FAST) @@ -3675,6 +3756,7 @@ static bool could_mpcc_tree_change_for_active_pipes(struct dc *dc, struct dc_stream_status *cur_stream_status = stream_get_status(dc->current_state, stream); bool force_minimal_pipe_splitting = false; + bool subvp_active = false; uint32_t i; *is_plane_addition = false; @@ -3707,33 +3789,31 @@ static bool could_mpcc_tree_change_for_active_pipes(struct dc *dc, } } - /* For SubVP pipe split case when adding MPO video - * we need to add a minimal transition. In this case - * there will be 2 streams (1 main stream, 1 phantom - * stream). - */ - if (cur_stream_status && - dc->current_state->stream_count == 2 && - stream->mall_stream_config.type == SUBVP_MAIN) { - bool is_pipe_split = false; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream && - (dc->current_state->res_ctx.pipe_ctx[i].bottom_pipe || - dc->current_state->res_ctx.pipe_ctx[i].next_odm_pipe)) { - is_pipe_split = true; - break; - } + if (pipe->stream && pipe->stream->mall_stream_config.type != SUBVP_NONE) { + subvp_active = true; + break; } + } + /* For SubVP when adding or removing planes we need to add a minimal transition + * (even when disabling all planes). Whenever disabling a phantom pipe, we + * must use the minimal transition path to disable the pipe correctly. + * + * We want to use the minimal transition whenever subvp is active, not only if + * a plane is being added / removed from a subvp stream (MPO plane can be added + * to a DRR pipe of SubVP + DRR config, in which case we still want to run through + * a min transition to disable subvp. + */ + if (cur_stream_status && subvp_active) { /* determine if minimal transition is required due to SubVP*/ - if (surface_count > 0 && is_pipe_split) { - if (cur_stream_status->plane_count > surface_count) { - force_minimal_pipe_splitting = true; - } else if (cur_stream_status->plane_count < surface_count) { - force_minimal_pipe_splitting = true; - *is_plane_addition = true; - } + if (cur_stream_status->plane_count > surface_count) { + force_minimal_pipe_splitting = true; + } else if (cur_stream_status->plane_count < surface_count) { + force_minimal_pipe_splitting = true; + *is_plane_addition = true; } } @@ -3768,6 +3848,7 @@ static bool commit_minimal_transition_state(struct dc *dc, enum dc_status ret = DC_ERROR_UNEXPECTED; unsigned int i, j; unsigned int pipe_in_use = 0; + bool subvp_in_use = false; if (!transition_context) return false; @@ -3784,6 +3865,18 @@ static bool commit_minimal_transition_state(struct dc *dc, pipe_in_use++; } + /* If SubVP is enabled and we are adding or removing planes from any main subvp + * pipe, we must use the minimal transition. + */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + subvp_in_use = true; + break; + } + } + /* When the OS add a new surface if we have been used all of pipes with odm combine * and mpc split feature, it need use commit_minimal_transition_state to transition safely. * After OS exit MPO, it will back to use odm and mpc split with all of pipes, we need @@ -3792,7 +3885,7 @@ static bool commit_minimal_transition_state(struct dc *dc, * Reduce the scenarios to use dc_commit_state_no_check in the stage of flip. Especially * enter/exit MPO when DCN still have enough resources. */ - if (pipe_in_use != dc->res_pool->pipe_count) { + if (pipe_in_use != dc->res_pool->pipe_count && !subvp_in_use) { dc_release_state(transition_context); return true; } @@ -3864,6 +3957,7 @@ bool dc_update_planes_and_stream(struct dc *dc, struct dc_state *context; enum surface_update_type update_type; int i; + struct mall_temp_config mall_temp_config; /* In cases where MPO and split or ODM are used transitions can * cause underflow. Apply stream configuration with minimal pipe @@ -3895,11 +3989,29 @@ bool dc_update_planes_and_stream(struct dc *dc, /* on plane removal, minimal state is the new one */ if (force_minimal_pipe_splitting && !is_plane_addition) { + /* Since all phantom pipes are removed in full validation, + * we have to save and restore the subvp/mall config when + * we do a minimal transition since the flags marking the + * pipe as subvp/phantom will be cleared (dc copy constructor + * creates a shallow copy). + */ + if (dc->res_pool->funcs->save_mall_state) + dc->res_pool->funcs->save_mall_state(dc, context, &mall_temp_config); if (!commit_minimal_transition_state(dc, context)) { dc_release_state(context); return false; } - + if (dc->res_pool->funcs->restore_mall_state) + dc->res_pool->funcs->restore_mall_state(dc, context, &mall_temp_config); + + /* If we do a minimal transition with plane removal and the context + * has subvp we also have to retain back the phantom stream / planes + * since the refcount is decremented as part of the min transition + * (we commit a state with no subvp, so the phantom streams / planes + * had to be removed). + */ + if (dc->res_pool->funcs->retain_phantom_pipes) + dc->res_pool->funcs->retain_phantom_pipes(dc, context); update_type = UPDATE_TYPE_FULL; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 24ed057414e1..342e906ae26e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3378,7 +3378,7 @@ bool dc_link_setup_psr(struct dc_link *link, case FAMILY_YELLOW_CARP: case AMDGPU_FAMILY_GC_10_3_6: case AMDGPU_FAMILY_GC_11_0_1: - if (dc->debug.disable_z10) + if (dc->debug.disable_z10 || dc->debug.psr_skip_crtc_disable) psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; break; default: @@ -4663,6 +4663,10 @@ void dc_link_set_preferred_training_settings(struct dc *dc, link->preferred_link_setting.link_rate = LINK_RATE_UNKNOWN; } + if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT && + link->type == dc_connection_mst_branch) + dm_helpers_dp_mst_update_branch_bandwidth(dc->ctx, link); + /* Retrain now, or wait until next stream update to apply */ if (skip_immediate_retrain == false) dc_link_set_preferred_link_settings(dc, &link->preferred_link_setting, link); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index 651231387043..ce8d6a54ca54 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -82,6 +82,7 @@ struct dp_hdmi_dongle_signature_data { #define HDMI_SCDC_STATUS_FLAGS 0x40 #define HDMI_SCDC_ERR_DETECT 0x50 #define HDMI_SCDC_TEST_CONFIG 0xC0 +#define HDMI_SCDC_DEVICE_ID 0xD3 union hdmi_scdc_update_read_data { uint8_t byte[2]; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index e5ab751a5ca1..dedd1246ce58 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1912,7 +1912,7 @@ enum dc_status dpcd_configure_lttpr_mode(struct dc_link *link, struct link_train return status; } -static void dpcd_exit_training_mode(struct dc_link *link) +static void dpcd_exit_training_mode(struct dc_link *link, enum dp_link_encoding encoding) { uint8_t sink_status = 0; uint8_t i; @@ -1920,12 +1920,14 @@ static void dpcd_exit_training_mode(struct dc_link *link) /* clear training pattern set */ dpcd_set_training_pattern(link, DP_TRAINING_PATTERN_VIDEOIDLE); - /* poll for intra-hop disable */ - for (i = 0; i < 10; i++) { - if ((core_link_read_dpcd(link, DP_SINK_STATUS, &sink_status, 1) == DC_OK) && - (sink_status & DP_INTRA_HOP_AUX_REPLY_INDICATION) == 0) - break; - udelay(1000); + if (encoding == DP_128b_132b_ENCODING) { + /* poll for intra-hop disable */ + for (i = 0; i < 10; i++) { + if ((core_link_read_dpcd(link, DP_SINK_STATUS, &sink_status, 1) == DC_OK) && + (sink_status & DP_INTRA_HOP_AUX_REPLY_INDICATION) == 0) + break; + udelay(1000); + } } } @@ -2649,7 +2651,7 @@ enum link_training_result dc_link_dp_perform_link_training( <_settings); /* reset previous training states */ - dpcd_exit_training_mode(link); + dpcd_exit_training_mode(link, encoding); /* configure link prior to entering training mode */ dpcd_configure_lttpr_mode(link, <_settings); @@ -2670,7 +2672,7 @@ enum link_training_result dc_link_dp_perform_link_training( ASSERT(0); /* exit training mode */ - dpcd_exit_training_mode(link); + dpcd_exit_training_mode(link, encoding); /* switch to video idle */ if ((status == LINK_TRAINING_SUCCESS) || !skip_video_pattern) @@ -2771,8 +2773,11 @@ bool perform_link_training_with_retries( /* Update verified link settings to current one * Because DPIA LT might fallback to lower link setting. */ - link->verified_link_cap.link_rate = link->cur_link_settings.link_rate; - link->verified_link_cap.lane_count = link->cur_link_settings.lane_count; + if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + link->verified_link_cap.link_rate = link->cur_link_settings.link_rate; + link->verified_link_cap.lane_count = link->cur_link_settings.lane_count; + dm_helpers_dp_mst_update_branch_bandwidth(link->ctx, link); + } } } else { status = dc_link_dp_perform_link_training(link, @@ -3020,7 +3025,7 @@ static enum dc_link_rate get_lttpr_max_link_rate(struct dc_link *link) static enum dc_link_rate get_cable_max_link_rate(struct dc_link *link) { - enum dc_link_rate cable_max_link_rate = LINK_RATE_HIGH3; + enum dc_link_rate cable_max_link_rate = LINK_RATE_UNKNOWN; if (link->dpcd_caps.cable_id.bits.UHBR10_20_CAPABILITY & DP_UHBR20) cable_max_link_rate = LINK_RATE_UHBR20; @@ -3083,15 +3088,29 @@ struct dc_link_settings dp_get_max_link_cap(struct dc_link *link) max_link_cap.link_spread = link->reported_link_cap.link_spread; - /* Lower link settings based on cable attributes */ + /* Lower link settings based on cable attributes + * Cable ID is a DP2 feature to identify max certified link rate that + * a cable can carry. The cable identification method requires both + * cable and display hardware support. Since the specs comes late, it is + * anticipated that the first round of DP2 cables and displays may not + * be fully compatible to reliably return cable ID data. Therefore the + * decision of our cable id policy is that if the cable can return non + * zero cable id data, we will take cable's link rate capability into + * account. However if we get zero data, the cable link rate capability + * is considered inconclusive. In this case, we will not take cable's + * capability into account to avoid of over limiting hardware capability + * from users. The max overall link rate capability is still determined + * after actual dp pre-training. Cable id is considered as an auxiliary + * method of determining max link bandwidth capability. + */ cable_max_link_rate = get_cable_max_link_rate(link); if (!link->dc->debug.ignore_cable_id && + cable_max_link_rate != LINK_RATE_UNKNOWN && cable_max_link_rate < max_link_cap.link_rate) max_link_cap.link_rate = cable_max_link_rate; - /* - * account for lttpr repeaters cap + /* account for lttpr repeaters cap * notes: repeaters do not snoop in the DPRX Capabilities addresses (3.6.3). */ if (dp_is_lttpr_present(link)) { @@ -4540,9 +4559,19 @@ void dc_link_dp_handle_link_loss(struct dc_link *link) for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; - if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off && - pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) + if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off + && pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) { + // Always use max settings here for DP 1.4a LL Compliance CTS + if (link->is_automated) { + pipe_ctx->link_config.dp_link_settings.lane_count = + link->verified_link_cap.lane_count; + pipe_ctx->link_config.dp_link_settings.link_rate = + link->verified_link_cap.link_rate; + pipe_ctx->link_config.dp_link_settings.link_spread = + link->verified_link_cap.link_spread; + } core_link_enable_stream(link->dc->current_state, pipe_ctx); + } } } @@ -4583,6 +4612,8 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd } if (hpd_irq_dpcd_data.bytes.device_service_irq.bits.AUTOMATED_TEST) { + // Workaround for DP 1.4a LL Compliance CTS as USB4 has to share encoders unlike DP and USBC + link->is_automated = true; device_service_clear.bits.AUTOMATED_TEST = 1; core_link_write_dpcd( link, @@ -7226,6 +7257,7 @@ void dp_retrain_link_dp_test(struct dc_link *link, struct pipe_ctx *pipes = &link->dc->current_state->res_ctx.pipe_ctx[0]; unsigned int i; + bool do_fallback = false; for (i = 0; i < MAX_PIPES; i++) { @@ -7258,13 +7290,16 @@ void dp_retrain_link_dp_test(struct dc_link *link, memset(&link->cur_link_settings, 0, sizeof(link->cur_link_settings)); + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + do_fallback = true; + perform_link_training_with_retries( link_setting, skip_video_pattern, LINK_TRAINING_ATTEMPTS, &pipes[i], SIGNAL_TYPE_DISPLAY_PORT, - false); + do_fallback); link->dc->hwss.enable_stream(&pipes[i]); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c index 74e36b34d3f7..d130d58ac08e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c @@ -791,10 +791,14 @@ static enum link_training_result dpia_training_eq_transparent( } if (dp_is_ch_eq_done(lane_count, dpcd_lane_status) && - dp_is_symbol_locked(link->cur_link_settings.lane_count, dpcd_lane_status) && - dp_is_interlane_aligned(dpcd_lane_status_updated)) { - result = LINK_TRAINING_SUCCESS; - break; + dp_is_symbol_locked(link->cur_link_settings.lane_count, dpcd_lane_status)) { + /* Take into consideration corner case for DP 1.4a LL Compliance CTS as USB4 + * has to share encoders unlike DP and USBC + */ + if (dp_is_interlane_aligned(dpcd_lane_status_updated) || (link->is_automated && retries_eq)) { + result = LINK_TRAINING_SUCCESS; + break; + } } /* Update VS/PE. */ @@ -1008,7 +1012,8 @@ enum link_training_result dc_link_dpia_perform_link_training( */ if (result == LINK_TRAINING_SUCCESS) { msleep(5); - result = dp_check_link_loss_status(link, <_settings); + if (!link->is_automated) + result = dp_check_link_loss_status(link, <_settings); } else if (result == LINK_TRAINING_ABORT) { dpia_training_abort(link, <_settings, repeater_id); } else { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 38d71b5c1f2d..20e534f73513 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -332,9 +332,21 @@ bool dc_stream_set_cursor_attributes( dc = stream->ctx->dc; - if (dc->debug.allow_sw_cursor_fallback && attributes->height * attributes->width * 4 > 16384) - if (stream->mall_stream_config.type == SUBVP_MAIN) + /* SubVP is not compatible with HW cursor larger than 64 x 64 x 4. + * Therefore, if cursor is greater than 64 x 64 x 4, fallback to SW cursor in the following case: + * 1. For single display cases, if resolution is >= 5K and refresh rate < 120hz + * 2. For multi display cases, if resolution is >= 4K and refresh rate < 120hz + * + * [< 120hz is a requirement for SubVP configs] + */ + if (dc->debug.allow_sw_cursor_fallback && attributes->height * attributes->width * 4 > 16384) { + if (dc->current_state->stream_count == 1 && stream->timing.v_addressable >= 2880 && + ((stream->timing.pix_clk_100hz * 100) / stream->timing.v_total / stream->timing.h_total) < 120) return false; + else if (dc->current_state->stream_count > 1 && stream->timing.v_addressable >= 2160 && + ((stream->timing.pix_clk_100hz * 100) / stream->timing.v_total / stream->timing.h_total) < 120) + return false; + } stream->cursor_attributes = *attributes; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 84c82d3a6761..85ebeaa2de18 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -47,7 +47,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.210" +#define DC_VER "3.2.215" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -261,11 +261,13 @@ struct dc_caps { uint32_t cache_line_size; uint32_t cache_num_ways; uint16_t subvp_fw_processing_delay_us; + uint8_t subvp_drr_max_vblank_margin_us; uint16_t subvp_prefetch_end_to_mall_start_us; uint8_t subvp_swath_height_margin_lines; // subvp start line must be aligned to 2 x swath height uint16_t subvp_pstate_allow_width_us; uint16_t subvp_vertical_int_margin_us; bool seamless_odm; + uint8_t subvp_drr_vblank_start_margin_us; }; struct dc_bug_wa { @@ -407,6 +409,7 @@ struct dc_config { bool use_default_clock_table; bool force_bios_enable_lttpr; uint8_t force_bios_fixed_vs; + int sdpif_request_limit_words_per_umc; }; @@ -456,15 +459,15 @@ enum pipe_split_policy { MPC_SPLIT_DYNAMIC = 0, /** - * @MPC_SPLIT_DYNAMIC: Avoid pipe split, which means that DC will not + * @MPC_SPLIT_AVOID: Avoid pipe split, which means that DC will not * try any sort of split optimization. */ MPC_SPLIT_AVOID = 1, /** - * @MPC_SPLIT_DYNAMIC: With this option, DC will only try to optimize - * the pipe utilization when using a single display; if the user - * connects to a second display, DC will avoid pipe split. + * @MPC_SPLIT_AVOID_MULT_DISP: With this option, DC will only try to + * optimize the pipe utilization when using a single display; if the + * user connects to a second display, DC will avoid pipe split. */ MPC_SPLIT_AVOID_MULT_DISP = 2, }; @@ -490,12 +493,14 @@ enum dcn_pwr_state { enum dcn_zstate_support_state { DCN_ZSTATE_SUPPORT_UNKNOWN, DCN_ZSTATE_SUPPORT_ALLOW, + DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY, + DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY, DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY, DCN_ZSTATE_SUPPORT_DISALLOW, }; /** - * dc_clocks - DC pipe clocks + * struct dc_clocks - DC pipe clocks * * For any clocks that may differ per pipe only the max is stored in this * structure @@ -526,7 +531,7 @@ struct dc_clocks { bool fclk_prev_p_state_change_support; int num_ways; - /** + /* * @fw_based_mclk_switching * * DC has a mechanism that leverage the variable refresh rate to switch @@ -839,6 +844,7 @@ struct dc_debug_options { int crb_alloc_policy_min_disp_count; bool disable_z10; bool enable_z9_disable_interface; + bool psr_skip_crtc_disable; union dpia_debug_options dpia_debug; bool disable_fixed_vs_aux_timeout_wa; bool force_disable_subvp; @@ -847,6 +853,7 @@ struct dc_debug_options { unsigned int force_subvp_num_ways; unsigned int force_mall_ss_num_ways; bool alloc_extra_way_for_cursor; + uint32_t subvp_extra_lines; bool force_usr_allow; /* uses value at boot and disables switch */ bool disable_dtb_ref_clk_switch; @@ -864,6 +871,7 @@ struct dc_debug_options { bool enable_dp_dig_pixel_rate_div_policy; enum lttpr_mode lttpr_mode_override; unsigned int dsc_delay_factor_wa_x1000; + unsigned int min_prefetch_in_strobe_ns; }; struct gpu_info_soc_bounding_box_v1_0; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index 67eef5beab95..6ccf477d1c4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -477,14 +477,23 @@ static void populate_subvp_cmd_drr_info(struct dc *dc, (((uint64_t)main_timing->pix_clk_100hz * 100))); drr_active_us = div64_u64(((uint64_t)drr_timing->v_addressable * drr_timing->h_total * 1000000), (((uint64_t)drr_timing->pix_clk_100hz * 100))); - max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us; - max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us; + max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us - + dc->caps.subvp_fw_processing_delay_us - drr_active_us), 2) + drr_active_us; + max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us - dc->caps.subvp_fw_processing_delay_us; max_drr_supported_us = max_drr_vblank_us > max_drr_mallregion_us ? max_drr_vblank_us : max_drr_mallregion_us; max_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * max_drr_supported_us), (((uint64_t)drr_timing->h_total * 1000000))); + /* When calculating the max vtotal supported for SubVP + DRR cases, add + * margin due to possible rounding errors (being off by 1 line in the + * FW calculation can incorrectly push the P-State switch to wait 1 frame + * longer). + */ + max_vtotal_supported = max_vtotal_supported - dc->caps.subvp_drr_max_vblank_margin_us; + pipe_data->pipe_config.vblank_data.drr_info.min_vtotal_supported = min_vtotal_supported; pipe_data->pipe_config.vblank_data.drr_info.max_vtotal_supported = max_vtotal_supported; + pipe_data->pipe_config.vblank_data.drr_info.drr_vblank_start_margin = dc->caps.subvp_drr_vblank_start_margin_us; } /** @@ -859,11 +868,59 @@ void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv) diag_data.is_cw6_enabled); } +static bool dc_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) +{ + struct pipe_ctx *test_pipe, *split_pipe; + const struct scaler_data *scl_data = &pipe_ctx->plane_res.scl_data; + struct rect r1 = scl_data->recout, r2, r2_half; + int r1_r = r1.x + r1.width, r1_b = r1.y + r1.height, r2_r, r2_b; + int cur_layer = pipe_ctx->plane_state->layer_index; + + /** + * Disable the cursor if there's another pipe above this with a + * plane that contains this pipe's viewport to prevent double cursor + * and incorrect scaling artifacts. + */ + for (test_pipe = pipe_ctx->top_pipe; test_pipe; + test_pipe = test_pipe->top_pipe) { + // Skip invisible layer and pipe-split plane on same layer + if (!test_pipe->plane_state->visible || test_pipe->plane_state->layer_index == cur_layer) + continue; + + r2 = test_pipe->plane_res.scl_data.recout; + r2_r = r2.x + r2.width; + r2_b = r2.y + r2.height; + split_pipe = test_pipe; + + /** + * There is another half plane on same layer because of + * pipe-split, merge together per same height. + */ + for (split_pipe = pipe_ctx->top_pipe; split_pipe; + split_pipe = split_pipe->top_pipe) + if (split_pipe->plane_state->layer_index == test_pipe->plane_state->layer_index) { + r2_half = split_pipe->plane_res.scl_data.recout; + r2.x = (r2_half.x < r2.x) ? r2_half.x : r2.x; + r2.width = r2.width + r2_half.width; + r2_r = r2.x + r2.width; + break; + } + + if (r1.x >= r2.x && r1.y >= r2.y && r1_r <= r2_r && r1_b <= r2_b) + return true; + } + + return false; +} + static bool dc_dmub_should_update_cursor_data(struct pipe_ctx *pipe_ctx) { if (pipe_ctx->plane_state != NULL) { if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) return false; + + if (dc_can_pipe_disable_cursor(pipe_ctx)) + return false; } if ((pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 || diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index edb4532eaa39..2e18bcf6b11a 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -151,6 +151,20 @@ struct dc_panel_config { bool optimize_edp_link_rate; /* eDP ILR */ } ilr; }; + +/* + * USB4 DPIA BW ALLOCATION STRUCTS + */ +struct dc_dpia_bw_alloc { + int sink_verified_bw; // The Verified BW that sink can allocated and use that has been verified already + int sink_allocated_bw; // The Actual Allocated BW that sink currently allocated + int padding_bw; // The Padding "Un-used" BW allocated by CM for padding reasons + int sink_max_bw; // The Max BW that sink can require/support + int estimated_bw; // The estimated available BW for this DPIA + int bw_granularity; // BW Granularity + bool bw_alloc_enabled; // The BW Alloc Mode Support is turned ON for all 3: DP-Tx & Dpia & CM +}; + /* * A link contains one or more sinks and their connected status. * The currently active signal type (HDMI, DP-SST, DP-MST) is also reported. @@ -184,6 +198,7 @@ struct dc_link { bool is_dig_mapping_flexible; bool hpd_status; /* HPD status of link without physical HPD pin. */ bool is_hpd_pending; /* Indicates a new received hpd */ + bool is_automated; /* Indicates automated testing */ bool edp_sink_present; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index f4dfd3a49b68..dfd3df1d2f7e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -144,7 +144,7 @@ struct test_pattern { unsigned int cust_pattern_size; }; -#define SUBVP_DRR_MARGIN_US 500 // 500us for DRR margin (SubVP + DRR) +#define SUBVP_DRR_MARGIN_US 600 // 600us for DRR margin (SubVP + DRR) enum mall_stream_type { SUBVP_NONE, // subvp not in use @@ -160,6 +160,17 @@ struct mall_stream_config { struct dc_stream_state *paired_stream; // master / slave stream }; +/* Temp struct used to save and restore MALL config + * during validation. + * + * TODO: Move MALL config into dc_state instead of stream struct + * to avoid needing to save/restore. + */ +struct mall_temp_config { + struct mall_stream_config mall_stream_config[MAX_PIPES]; + bool is_phantom_plane[MAX_PIPES]; +}; + struct dc_stream_state { // sink is deprecated, new code should not reference // this pointer diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index cda1592c3a5b..2d3201b77d6a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -413,6 +413,11 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub, else copy_settings_data->debug.bitfields.force_wakeup_by_tps3 = 0; + //WA for PSR1 on specific TCON, require frame delay for frame re-lock + copy_settings_data->relock_delay_frame_cnt = 0; + if (link->dpcd_caps.sink_dev_id == DP_BRANCH_DEVICE_ID_001CF8) + copy_settings_data->relock_delay_frame_cnt = 2; + dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd); dc_dmub_srv_cmd_execute(dc->dmub_srv); dc_dmub_srv_wait_idle(dc->dmub_srv); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index c5380ce70653..913a1fe6b3da 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1561,8 +1561,13 @@ static enum dc_status apply_single_controller_ctx_to_hw( pipe_ctx->plane_res.scl_data.lb_params.alpha_en = pipe_ctx->bottom_pipe != NULL; - pipe_ctx->stream->link->psr_settings.psr_feature_enabled = false; - + /* Phantom and main stream share the same link (because the stream + * is constructed with the same sink). Make sure not to override + * and link programming on the main. + */ + if (pipe_ctx->stream->mall_stream_config.type != SUBVP_PHANTOM) { + pipe_ctx->stream->link->psr_settings.psr_feature_enabled = false; + } return DC_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 1b70b78e2fa1..af631085e88c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -359,7 +359,8 @@ static const struct dce_audio_registers audio_regs[] = { audio_regs(2), audio_regs(3), audio_regs(4), - audio_regs(5) + audio_regs(5), + audio_regs(6), }; #define DCE120_AUD_COMMON_MASK_SH_LIST(mask_sh)\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c index b9765b3899e1..ef52e6b6eccf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c @@ -436,34 +436,48 @@ void dpp1_set_cursor_position( uint32_t height) { struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base); - int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - int src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; + int x_pos = pos->x - param->viewport.x; + int y_pos = pos->y - param->viewport.y; + int x_hotspot = pos->x_hotspot; + int y_hotspot = pos->y_hotspot; + int src_x_offset = x_pos - pos->x_hotspot; + int src_y_offset = y_pos - pos->y_hotspot; + int cursor_height = (int)height; + int cursor_width = (int)width; uint32_t cur_en = pos->enable ? 1 : 0; - // Cursor width/height and hotspots need to be rotated for offset calculation + // Transform cursor width / height and hotspots for offset calculations if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { - swap(width, height); + swap(cursor_height, cursor_width); + swap(x_hotspot, y_hotspot); + if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; + // hotspot = (-y, x) + src_x_offset = x_pos - (cursor_width - x_hotspot); + src_y_offset = y_pos - y_hotspot; + } else if (param->rotation == ROTATION_ANGLE_270) { + // hotspot = (y, -x) + src_x_offset = x_pos - x_hotspot; + src_y_offset = y_pos - (cursor_height - y_hotspot); } } else if (param->rotation == ROTATION_ANGLE_180) { + // hotspot = (-x, -y) if (!param->mirror) - src_x_offset = pos->x - param->viewport.x; + src_x_offset = x_pos - (cursor_width - x_hotspot); - src_y_offset = pos->y - param->viewport.y; + src_y_offset = y_pos - (cursor_height - y_hotspot); } if (src_x_offset >= (int)param->viewport.width) cur_en = 0; /* not visible beyond right edge*/ - if (src_x_offset + (int)width <= 0) + if (src_x_offset + cursor_width <= 0) cur_en = 0; /* not visible beyond left edge*/ if (src_y_offset >= (int)param->viewport.height) cur_en = 0; /* not visible beyond bottom edge*/ - if (src_y_offset + (int)height <= 0) + if (src_y_offset + cursor_height <= 0) cur_en = 0; /* not visible beyond top edge*/ REG_UPDATE(CURSOR0_CONTROL, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c index 0f746bb4e500..d51f1ce02874 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c @@ -55,7 +55,7 @@ void hubbub1_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A); s = &wm->sets[1]; s->wm_set = 1; @@ -65,7 +65,7 @@ void hubbub1_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B); s = &wm->sets[2]; s->wm_set = 2; @@ -75,7 +75,7 @@ void hubbub1_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C); s = &wm->sets[3]; s->wm_set = 3; @@ -85,7 +85,7 @@ void hubbub1_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D); } void hubbub1_allow_self_refresh_control(struct hubbub *hubbub, bool allow) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h index e48fd044f572..ba1c0621f0f8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h @@ -171,6 +171,7 @@ struct dcn_hubbub_registers { uint32_t DCHUBBUB_ARB_FCLK_PSTATE_CHANGE_WATERMARK_B; uint32_t DCHUBBUB_ARB_FCLK_PSTATE_CHANGE_WATERMARK_C; uint32_t DCHUBBUB_ARB_FCLK_PSTATE_CHANGE_WATERMARK_D; + uint32_t SDPIF_REQUEST_RATE_LIMIT; }; #define HUBBUB_REG_FIELD_LIST_DCN32(type) \ @@ -360,7 +361,8 @@ struct dcn_hubbub_registers { type DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_Z8_C;\ type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_C;\ type DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_Z8_D;\ - type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D + type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D;\ + type SDPIF_REQUEST_RATE_LIMIT struct dcn_hubbub_shift { diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c index 52e201e9b091..a142a00bc432 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -1179,10 +1179,12 @@ void hubp1_cursor_set_position( const struct dc_cursor_mi_param *param) { struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); - int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - int src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; + int x_pos = pos->x - param->viewport.x; + int y_pos = pos->y - param->viewport.y; int x_hotspot = pos->x_hotspot; int y_hotspot = pos->y_hotspot; + int src_x_offset = x_pos - pos->x_hotspot; + int src_y_offset = y_pos - pos->y_hotspot; int cursor_height = (int)hubp->curs_attr.height; int cursor_width = (int)hubp->curs_attr.width; uint32_t dst_x_offset; @@ -1200,18 +1202,26 @@ void hubp1_cursor_set_position( if (hubp->curs_attr.address.quad_part == 0) return; - // Rotated cursor width/height and hotspots tweaks for offset calculation + // Transform cursor width / height and hotspots for offset calculations if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { swap(cursor_height, cursor_width); + swap(x_hotspot, y_hotspot); + if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; + // hotspot = (-y, x) + src_x_offset = x_pos - (cursor_width - x_hotspot); + src_y_offset = y_pos - y_hotspot; + } else if (param->rotation == ROTATION_ANGLE_270) { + // hotspot = (y, -x) + src_x_offset = x_pos - x_hotspot; + src_y_offset = y_pos - (cursor_height - y_hotspot); } } else if (param->rotation == ROTATION_ANGLE_180) { + // hotspot = (-x, -y) if (!param->mirror) - src_x_offset = pos->x - param->viewport.x; + src_x_offset = x_pos - (cursor_width - x_hotspot); - src_y_offset = pos->y - param->viewport.y; + src_y_offset = y_pos - (cursor_height - y_hotspot); } dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0; @@ -1248,8 +1258,8 @@ void hubp1_cursor_set_position( CURSOR_Y_POSITION, pos->y); REG_SET_2(CURSOR_HOT_SPOT, 0, - CURSOR_HOT_SPOT_X, x_hotspot, - CURSOR_HOT_SPOT_Y, y_hotspot); + CURSOR_HOT_SPOT_X, pos->x_hotspot, + CURSOR_HOT_SPOT_Y, pos->y_hotspot); REG_SET(CURSOR_DST_OFFSET, 0, CURSOR_DST_X_OFFSET, dst_x_offset); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 11e4c4e46947..fe2023f18b7d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -97,10 +97,12 @@ void dcn10_lock_all_pipes(struct dc *dc, bool lock) { struct pipe_ctx *pipe_ctx; + struct pipe_ctx *old_pipe_ctx; struct timing_generator *tg; int i; for (i = 0; i < dc->res_pool->pipe_count; i++) { + old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; pipe_ctx = &context->res_ctx.pipe_ctx[i]; tg = pipe_ctx->stream_res.tg; @@ -110,7 +112,7 @@ void dcn10_lock_all_pipes(struct dc *dc, */ if (pipe_ctx->top_pipe || !pipe_ctx->stream || - !pipe_ctx->plane_state || + (!pipe_ctx->plane_state && !old_pipe_ctx->plane_state) || !tg->funcs->is_tg_enabled(tg)) continue; @@ -157,7 +159,7 @@ static void dcn10_log_hubbub_state(struct dc *dc, DTN_INFO_MICRO_SEC(s->pte_meta_urgent); DTN_INFO_MICRO_SEC(s->sr_enter); DTN_INFO_MICRO_SEC(s->sr_exit); - DTN_INFO_MICRO_SEC(s->dram_clk_chanage); + DTN_INFO_MICRO_SEC(s->dram_clk_change); DTN_INFO("\n"); } @@ -867,6 +869,32 @@ static void false_optc_underflow_wa( tg->funcs->clear_optc_underflow(tg); } +static int calculate_vready_offset_for_group(struct pipe_ctx *pipe) +{ + struct pipe_ctx *other_pipe; + int vready_offset = pipe->pipe_dlg_param.vready_offset; + + /* Always use the largest vready_offset of all connected pipes */ + for (other_pipe = pipe->bottom_pipe; other_pipe != NULL; other_pipe = other_pipe->bottom_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + for (other_pipe = pipe->top_pipe; other_pipe != NULL; other_pipe = other_pipe->top_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + for (other_pipe = pipe->next_odm_pipe; other_pipe != NULL; other_pipe = other_pipe->next_odm_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + for (other_pipe = pipe->prev_odm_pipe; other_pipe != NULL; other_pipe = other_pipe->prev_odm_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + + return vready_offset; +} + enum dc_status dcn10_enable_stream_timing( struct pipe_ctx *pipe_ctx, struct dc_state *context, @@ -910,7 +938,7 @@ enum dc_status dcn10_enable_stream_timing( pipe_ctx->stream_res.tg->funcs->program_timing( pipe_ctx->stream_res.tg, &stream->timing, - pipe_ctx->pipe_dlg_param.vready_offset, + calculate_vready_offset_for_group(pipe_ctx), pipe_ctx->pipe_dlg_param.vstartup_start, pipe_ctx->pipe_dlg_param.vupdate_offset, pipe_ctx->pipe_dlg_param.vupdate_width, @@ -2188,6 +2216,12 @@ void dcn10_enable_vblanks_synchronization( opp = grouped_pipes[i]->stream_res.opp; tg = grouped_pipes[i]->stream_res.tg; tg->funcs->get_otg_active_size(tg, &width, &height); + + if (!tg->funcs->is_tg_enabled(tg)) { + DC_SYNC_INFO("Skipping timing sync on disabled OTG\n"); + return; + } + if (opp->funcs->opp_program_dpg_dimensions) opp->funcs->opp_program_dpg_dimensions(opp, width, 2*(height) + 1); } @@ -2250,6 +2284,12 @@ void dcn10_enable_timing_synchronization( opp = grouped_pipes[i]->stream_res.opp; tg = grouped_pipes[i]->stream_res.tg; tg->funcs->get_otg_active_size(tg, &width, &height); + + if (!tg->funcs->is_tg_enabled(tg)) { + DC_SYNC_INFO("Skipping timing sync on disabled OTG\n"); + return; + } + if (opp->funcs->opp_program_dpg_dimensions) opp->funcs->opp_program_dpg_dimensions(opp, width, 2*(height) + 1); } @@ -2900,7 +2940,7 @@ void dcn10_program_pipe( pipe_ctx->stream_res.tg->funcs->program_global_sync( pipe_ctx->stream_res.tg, - pipe_ctx->pipe_dlg_param.vready_offset, + calculate_vready_offset_for_group(pipe_ctx), pipe_ctx->pipe_dlg_param.vstartup_start, pipe_ctx->pipe_dlg_param.vupdate_offset, pipe_ctx->pipe_dlg_param.vupdate_width); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c index e8b6065fffad..a0f8e31d2adc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c @@ -83,7 +83,7 @@ static unsigned int dcn10_get_hubbub_state(struct dc *dc, char *pBuf, unsigned i memset(&wm, 0, sizeof(struct dcn_hubbub_wm)); dc->res_pool->hubbub->funcs->wm_read_state(dc->res_pool->hubbub, &wm); - chars_printed = snprintf_count(pBuf, remaining_buffer, "wm_set_index,data_urgent,pte_meta_urgent,sr_enter,sr_exit,dram_clk_chanage\n"); + chars_printed = snprintf_count(pBuf, remaining_buffer, "wm_set_index,data_urgent,pte_meta_urgent,sr_enter,sr_exit,dram_clk_change\n"); remaining_buffer -= chars_printed; pBuf += chars_printed; @@ -98,7 +98,7 @@ static unsigned int dcn10_get_hubbub_state(struct dc *dc, char *pBuf, unsigned i (s->pte_meta_urgent * frac) / ref_clk_mhz / frac, (s->pte_meta_urgent * frac) / ref_clk_mhz % frac, (s->sr_enter * frac) / ref_clk_mhz / frac, (s->sr_enter * frac) / ref_clk_mhz % frac, (s->sr_exit * frac) / ref_clk_mhz / frac, (s->sr_exit * frac) / ref_clk_mhz % frac, - (s->dram_clk_chanage * frac) / ref_clk_mhz / frac, (s->dram_clk_chanage * frac) / ref_clk_mhz % frac); + (s->dram_clk_change * frac) / ref_clk_mhz / frac, (s->dram_clk_change * frac) / ref_clk_mhz % frac); remaining_buffer -= chars_printed; pBuf += chars_printed; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb.h index a85ed228dfc2..a9dd9ae23ec9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb.h @@ -27,204 +27,177 @@ #define TO_DCN20_DWBC(dwbc_base) \ container_of(dwbc_base, struct dcn20_dwbc, base) -/* DCN */ -#define BASE_INNER(seg) \ - DCE_BASE__INST0_SEG ## seg - -#define BASE(seg) \ - BASE_INNER(seg) - -#define SR(reg_name)\ - .reg_name = BASE(mm ## reg_name ## _BASE_IDX) + \ - mm ## reg_name - -#define SRI(reg_name, block, id)\ - .reg_name = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ - mm ## block ## id ## _ ## reg_name - -#define SRI2(reg_name, block, id)\ - .reg_name = BASE(mm ## reg_name ## _BASE_IDX) + \ - mm ## reg_name - -#define SRII(reg_name, block, id)\ - .reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ - mm ## block ## id ## _ ## reg_name - -#define SF(reg_name, field_name, post_fix)\ - .field_name = reg_name ## __ ## field_name ## post_fix - - #define DWBC_COMMON_REG_LIST_DCN2_0(inst) \ - SRI2(WB_ENABLE, CNV, inst),\ - SRI2(WB_EC_CONFIG, CNV, inst),\ - SRI2(CNV_MODE, CNV, inst),\ - SRI2(CNV_WINDOW_START, CNV, inst),\ - SRI2(CNV_WINDOW_SIZE, CNV, inst),\ - SRI2(CNV_UPDATE, CNV, inst),\ - SRI2(CNV_SOURCE_SIZE, CNV, inst),\ - SRI2(CNV_TEST_CNTL, CNV, inst),\ - SRI2(CNV_TEST_CRC_RED, CNV, inst),\ - SRI2(CNV_TEST_CRC_GREEN, CNV, inst),\ - SRI2(CNV_TEST_CRC_BLUE, CNV, inst),\ - SRI2(WBSCL_COEF_RAM_SELECT, WBSCL, inst),\ - SRI2(WBSCL_COEF_RAM_TAP_DATA, WBSCL, inst),\ - SRI2(WBSCL_MODE, WBSCL, inst),\ - SRI2(WBSCL_TAP_CONTROL, WBSCL, inst),\ - SRI2(WBSCL_DEST_SIZE, WBSCL, inst),\ - SRI2(WBSCL_HORZ_FILTER_SCALE_RATIO, WBSCL, inst),\ - SRI2(WBSCL_HORZ_FILTER_INIT_Y_RGB, WBSCL, inst),\ - SRI2(WBSCL_HORZ_FILTER_INIT_CBCR, WBSCL, inst),\ - SRI2(WBSCL_VERT_FILTER_SCALE_RATIO, WBSCL, inst),\ - SRI2(WBSCL_VERT_FILTER_INIT_Y_RGB, WBSCL, inst),\ - SRI2(WBSCL_VERT_FILTER_INIT_CBCR, WBSCL, inst),\ - SRI2(WBSCL_ROUND_OFFSET, WBSCL, inst),\ - SRI2(WBSCL_OVERFLOW_STATUS, WBSCL, inst),\ - SRI2(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL, inst),\ - SRI2(WBSCL_TEST_CNTL, WBSCL, inst),\ - SRI2(WBSCL_TEST_CRC_RED, WBSCL, inst),\ - SRI2(WBSCL_TEST_CRC_GREEN, WBSCL, inst),\ - SRI2(WBSCL_TEST_CRC_BLUE, WBSCL, inst),\ - SRI2(WBSCL_BACKPRESSURE_CNT_EN, WBSCL, inst),\ - SRI2(WB_MCIF_BACKPRESSURE_CNT, WBSCL, inst),\ - SRI2(WBSCL_CLAMP_Y_RGB, WBSCL, inst),\ - SRI2(WBSCL_CLAMP_CBCR, WBSCL, inst),\ - SRI2(WBSCL_OUTSIDE_PIX_STRATEGY, WBSCL, inst),\ - SRI2(WBSCL_OUTSIDE_PIX_STRATEGY_CBCR, WBSCL, inst),\ - SRI2(WBSCL_DEBUG, WBSCL, inst),\ - SRI2(WBSCL_TEST_DEBUG_INDEX, WBSCL, inst),\ - SRI2(WBSCL_TEST_DEBUG_DATA, WBSCL, inst),\ - SRI2(WB_DEBUG_CTRL, CNV, inst),\ - SRI2(WB_DBG_MODE, CNV, inst),\ - SRI2(WB_HW_DEBUG, CNV, inst),\ - SRI2(CNV_TEST_DEBUG_INDEX, CNV, inst),\ - SRI2(CNV_TEST_DEBUG_DATA, CNV, inst),\ - SRI2(WB_SOFT_RESET, CNV, inst),\ - SRI2(WB_WARM_UP_MODE_CTL1, CNV, inst),\ - SRI2(WB_WARM_UP_MODE_CTL2, CNV, inst) + SRI2_DWB(WB_ENABLE, CNV, inst),\ + SRI2_DWB(WB_EC_CONFIG, CNV, inst),\ + SRI2_DWB(CNV_MODE, CNV, inst),\ + SRI2_DWB(CNV_WINDOW_START, CNV, inst),\ + SRI2_DWB(CNV_WINDOW_SIZE, CNV, inst),\ + SRI2_DWB(CNV_UPDATE, CNV, inst),\ + SRI2_DWB(CNV_SOURCE_SIZE, CNV, inst),\ + SRI2_DWB(CNV_TEST_CNTL, CNV, inst),\ + SRI2_DWB(CNV_TEST_CRC_RED, CNV, inst),\ + SRI2_DWB(CNV_TEST_CRC_GREEN, CNV, inst),\ + SRI2_DWB(CNV_TEST_CRC_BLUE, CNV, inst),\ + SRI2_DWB(WBSCL_COEF_RAM_SELECT, WBSCL, inst),\ + SRI2_DWB(WBSCL_COEF_RAM_TAP_DATA, WBSCL, inst),\ + SRI2_DWB(WBSCL_MODE, WBSCL, inst),\ + SRI2_DWB(WBSCL_TAP_CONTROL, WBSCL, inst),\ + SRI2_DWB(WBSCL_DEST_SIZE, WBSCL, inst),\ + SRI2_DWB(WBSCL_HORZ_FILTER_SCALE_RATIO, WBSCL, inst),\ + SRI2_DWB(WBSCL_HORZ_FILTER_INIT_Y_RGB, WBSCL, inst),\ + SRI2_DWB(WBSCL_HORZ_FILTER_INIT_CBCR, WBSCL, inst),\ + SRI2_DWB(WBSCL_VERT_FILTER_SCALE_RATIO, WBSCL, inst),\ + SRI2_DWB(WBSCL_VERT_FILTER_INIT_Y_RGB, WBSCL, inst),\ + SRI2_DWB(WBSCL_VERT_FILTER_INIT_CBCR, WBSCL, inst),\ + SRI2_DWB(WBSCL_ROUND_OFFSET, WBSCL, inst),\ + SRI2_DWB(WBSCL_OVERFLOW_STATUS, WBSCL, inst),\ + SRI2_DWB(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL, inst),\ + SRI2_DWB(WBSCL_TEST_CNTL, WBSCL, inst),\ + SRI2_DWB(WBSCL_TEST_CRC_RED, WBSCL, inst),\ + SRI2_DWB(WBSCL_TEST_CRC_GREEN, WBSCL, inst),\ + SRI2_DWB(WBSCL_TEST_CRC_BLUE, WBSCL, inst),\ + SRI2_DWB(WBSCL_BACKPRESSURE_CNT_EN, WBSCL, inst),\ + SRI2_DWB(WB_MCIF_BACKPRESSURE_CNT, WBSCL, inst),\ + SRI2_DWB(WBSCL_CLAMP_Y_RGB, WBSCL, inst),\ + SRI2_DWB(WBSCL_CLAMP_CBCR, WBSCL, inst),\ + SRI2_DWB(WBSCL_OUTSIDE_PIX_STRATEGY, WBSCL, inst),\ + SRI2_DWB(WBSCL_OUTSIDE_PIX_STRATEGY_CBCR, WBSCL, inst),\ + SRI2_DWB(WBSCL_DEBUG, WBSCL, inst),\ + SRI2_DWB(WBSCL_TEST_DEBUG_INDEX, WBSCL, inst),\ + SRI2_DWB(WBSCL_TEST_DEBUG_DATA, WBSCL, inst),\ + SRI2_DWB(WB_DEBUG_CTRL, CNV, inst),\ + SRI2_DWB(WB_DBG_MODE, CNV, inst),\ + SRI2_DWB(WB_HW_DEBUG, CNV, inst),\ + SRI2_DWB(CNV_TEST_DEBUG_INDEX, CNV, inst),\ + SRI2_DWB(CNV_TEST_DEBUG_DATA, CNV, inst),\ + SRI2_DWB(WB_SOFT_RESET, CNV, inst),\ + SRI2_DWB(WB_WARM_UP_MODE_CTL1, CNV, inst),\ + SRI2_DWB(WB_WARM_UP_MODE_CTL2, CNV, inst) #define DWBC_COMMON_MASK_SH_LIST_DCN2_0(mask_sh) \ - SF(WB_ENABLE, WB_ENABLE, mask_sh),\ - SF(WB_EC_CONFIG, DISPCLK_R_WB_GATE_DIS, mask_sh),\ - SF(WB_EC_CONFIG, DISPCLK_G_WB_GATE_DIS, mask_sh),\ - SF(WB_EC_CONFIG, DISPCLK_G_WBSCL_GATE_DIS, mask_sh),\ - SF(WB_EC_CONFIG, WB_TEST_CLK_SEL, mask_sh),\ - SF(WB_EC_CONFIG, WB_LB_LS_DIS, mask_sh),\ - SF(WB_EC_CONFIG, WB_LB_SD_DIS, mask_sh),\ - SF(WB_EC_CONFIG, WB_LUT_LS_DIS, mask_sh),\ - SF(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_MODE_SEL, mask_sh),\ - SF(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_DIS, mask_sh),\ - SF(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_FORCE, mask_sh),\ - SF(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_STATE, mask_sh),\ - SF(WB_EC_CONFIG, WB_RAM_PW_SAVE_MODE, mask_sh),\ - SF(WB_EC_CONFIG, WBSCL_LUT_MEM_PWR_STATE, mask_sh),\ - SF(CNV_MODE, CNV_OUT_BPC, mask_sh),\ - SF(CNV_MODE, CNV_FRAME_CAPTURE_RATE, mask_sh),\ - SF(CNV_MODE, CNV_WINDOW_CROP_EN, mask_sh),\ - SF(CNV_MODE, CNV_STEREO_TYPE, mask_sh),\ - SF(CNV_MODE, CNV_INTERLACED_MODE, mask_sh),\ - SF(CNV_MODE, CNV_EYE_SELECTION, mask_sh),\ - SF(CNV_MODE, CNV_STEREO_POLARITY, mask_sh),\ - SF(CNV_MODE, CNV_INTERLACED_FIELD_ORDER, mask_sh),\ - SF(CNV_MODE, CNV_STEREO_SPLIT, mask_sh),\ - SF(CNV_MODE, CNV_NEW_CONTENT, mask_sh),\ - SF(CNV_MODE, CNV_FRAME_CAPTURE_EN_CURRENT, mask_sh),\ - SF(CNV_MODE, CNV_FRAME_CAPTURE_EN, mask_sh),\ - SF(CNV_WINDOW_START, CNV_WINDOW_START_X, mask_sh),\ - SF(CNV_WINDOW_START, CNV_WINDOW_START_Y, mask_sh),\ - SF(CNV_WINDOW_SIZE, CNV_WINDOW_WIDTH, mask_sh),\ - SF(CNV_WINDOW_SIZE, CNV_WINDOW_HEIGHT, mask_sh),\ - SF(CNV_UPDATE, CNV_UPDATE_PENDING, mask_sh),\ - SF(CNV_UPDATE, CNV_UPDATE_TAKEN, mask_sh),\ - SF(CNV_UPDATE, CNV_UPDATE_LOCK, mask_sh),\ - SF(CNV_SOURCE_SIZE, CNV_SOURCE_WIDTH, mask_sh),\ - SF(CNV_SOURCE_SIZE, CNV_SOURCE_HEIGHT, mask_sh),\ - SF(CNV_TEST_CNTL, CNV_TEST_CRC_EN, mask_sh),\ - SF(CNV_TEST_CNTL, CNV_TEST_CRC_CONT_EN, mask_sh),\ - SF(CNV_TEST_CRC_RED, CNV_TEST_CRC_RED_MASK, mask_sh),\ - SF(CNV_TEST_CRC_RED, CNV_TEST_CRC_SIG_RED, mask_sh),\ - SF(CNV_TEST_CRC_GREEN, CNV_TEST_CRC_GREEN_MASK, mask_sh),\ - SF(CNV_TEST_CRC_GREEN, CNV_TEST_CRC_SIG_GREEN, mask_sh),\ - SF(CNV_TEST_CRC_BLUE, CNV_TEST_CRC_BLUE_MASK, mask_sh),\ - SF(CNV_TEST_CRC_BLUE, CNV_TEST_CRC_SIG_BLUE, mask_sh),\ - SF(WB_DEBUG_CTRL, WB_DEBUG_EN, mask_sh),\ - SF(WB_DEBUG_CTRL, WB_DEBUG_SEL, mask_sh),\ - SF(WB_DBG_MODE, WB_DBG_MODE_EN, mask_sh),\ - SF(WB_DBG_MODE, WB_DBG_DIN_FMT, mask_sh),\ - SF(WB_DBG_MODE, WB_DBG_36MODE, mask_sh),\ - SF(WB_DBG_MODE, WB_DBG_CMAP, mask_sh),\ - SF(WB_DBG_MODE, WB_DBG_PXLRATE_ERROR, mask_sh),\ - SF(WB_DBG_MODE, WB_DBG_SOURCE_WIDTH, mask_sh),\ - SF(WB_HW_DEBUG, WB_HW_DEBUG, mask_sh),\ - SF(WB_SOFT_RESET, WB_SOFT_RESET, mask_sh),\ - SF(CNV_TEST_DEBUG_INDEX, CNV_TEST_DEBUG_INDEX, mask_sh),\ - SF(CNV_TEST_DEBUG_INDEX, CNV_TEST_DEBUG_WRITE_EN, mask_sh),\ - SF(CNV_TEST_DEBUG_DATA, CNV_TEST_DEBUG_DATA, mask_sh),\ - SF(WBSCL_COEF_RAM_SELECT, WBSCL_COEF_RAM_TAP_PAIR_IDX, mask_sh),\ - SF(WBSCL_COEF_RAM_SELECT, WBSCL_COEF_RAM_PHASE, mask_sh),\ - SF(WBSCL_COEF_RAM_SELECT, WBSCL_COEF_RAM_FILTER_TYPE, mask_sh),\ - SF(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_EVEN_TAP_COEF, mask_sh),\ - SF(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_EVEN_TAP_COEF_EN, mask_sh),\ - SF(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_ODD_TAP_COEF, mask_sh),\ - SF(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_ODD_TAP_COEF_EN, mask_sh),\ - SF(WBSCL_MODE, WBSCL_MODE, mask_sh),\ - SF(WBSCL_MODE, WBSCL_OUT_BIT_DEPTH, mask_sh),\ - SF(WBSCL_TAP_CONTROL, WBSCL_V_NUM_OF_TAPS_Y_RGB, mask_sh),\ - SF(WBSCL_TAP_CONTROL, WBSCL_V_NUM_OF_TAPS_CBCR, mask_sh),\ - SF(WBSCL_TAP_CONTROL, WBSCL_H_NUM_OF_TAPS_Y_RGB, mask_sh),\ - SF(WBSCL_TAP_CONTROL, WBSCL_H_NUM_OF_TAPS_CBCR, mask_sh),\ - SF(WBSCL_DEST_SIZE, WBSCL_DEST_HEIGHT, mask_sh),\ - SF(WBSCL_DEST_SIZE, WBSCL_DEST_WIDTH, mask_sh),\ - SF(WBSCL_HORZ_FILTER_SCALE_RATIO, WBSCL_H_SCALE_RATIO, mask_sh),\ - SF(WBSCL_HORZ_FILTER_INIT_Y_RGB, WBSCL_H_INIT_FRAC_Y_RGB, mask_sh),\ - SF(WBSCL_HORZ_FILTER_INIT_Y_RGB, WBSCL_H_INIT_INT_Y_RGB, mask_sh),\ - SF(WBSCL_HORZ_FILTER_INIT_CBCR, WBSCL_H_INIT_FRAC_CBCR, mask_sh),\ - SF(WBSCL_HORZ_FILTER_INIT_CBCR, WBSCL_H_INIT_INT_CBCR, mask_sh),\ - SF(WBSCL_VERT_FILTER_SCALE_RATIO, WBSCL_V_SCALE_RATIO, mask_sh),\ - SF(WBSCL_VERT_FILTER_INIT_Y_RGB, WBSCL_V_INIT_FRAC_Y_RGB, mask_sh),\ - SF(WBSCL_VERT_FILTER_INIT_Y_RGB, WBSCL_V_INIT_INT_Y_RGB, mask_sh),\ - SF(WBSCL_VERT_FILTER_INIT_CBCR, WBSCL_V_INIT_FRAC_CBCR, mask_sh),\ - SF(WBSCL_VERT_FILTER_INIT_CBCR, WBSCL_V_INIT_INT_CBCR, mask_sh),\ - SF(WBSCL_ROUND_OFFSET, WBSCL_ROUND_OFFSET_Y_RGB, mask_sh),\ - SF(WBSCL_ROUND_OFFSET, WBSCL_ROUND_OFFSET_CBCR, mask_sh),\ - SF(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_FLAG, mask_sh),\ - SF(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_ACK, mask_sh),\ - SF(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_MASK, mask_sh),\ - SF(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_INT_STATUS, mask_sh),\ - SF(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_INT_TYPE, mask_sh),\ - SF(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_FLAG, mask_sh),\ - SF(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_ACK, mask_sh),\ - SF(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_MASK, mask_sh),\ - SF(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_INT_STATUS, mask_sh),\ - SF(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_INT_TYPE, mask_sh),\ - SF(WBSCL_TEST_CNTL, WBSCL_TEST_CRC_EN, mask_sh),\ - SF(WBSCL_TEST_CNTL, WBSCL_TEST_CRC_CONT_EN, mask_sh),\ - SF(WBSCL_TEST_CRC_RED, WBSCL_TEST_CRC_RED_MASK, mask_sh),\ - SF(WBSCL_TEST_CRC_RED, WBSCL_TEST_CRC_SIG_RED, mask_sh),\ - SF(WBSCL_TEST_CRC_GREEN, WBSCL_TEST_CRC_GREEN_MASK, mask_sh),\ - SF(WBSCL_TEST_CRC_GREEN, WBSCL_TEST_CRC_SIG_GREEN, mask_sh),\ - SF(WBSCL_TEST_CRC_BLUE, WBSCL_TEST_CRC_BLUE_MASK, mask_sh),\ - SF(WBSCL_TEST_CRC_BLUE, WBSCL_TEST_CRC_SIG_BLUE, mask_sh),\ - SF(WBSCL_BACKPRESSURE_CNT_EN, WBSCL_BACKPRESSURE_CNT_EN, mask_sh),\ - SF(WB_MCIF_BACKPRESSURE_CNT, WB_MCIF_Y_MAX_BACKPRESSURE, mask_sh),\ - SF(WB_MCIF_BACKPRESSURE_CNT, WB_MCIF_C_MAX_BACKPRESSURE, mask_sh),\ - SF(WBSCL_CLAMP_Y_RGB, WBSCL_CLAMP_UPPER_Y_RGB, mask_sh),\ - SF(WBSCL_CLAMP_Y_RGB, WBSCL_CLAMP_LOWER_Y_RGB, mask_sh),\ - SF(WBSCL_CLAMP_CBCR, WBSCL_CLAMP_UPPER_CBCR, mask_sh),\ - SF(WBSCL_CLAMP_CBCR, WBSCL_CLAMP_LOWER_CBCR, mask_sh),\ - SF(WBSCL_OUTSIDE_PIX_STRATEGY, WBSCL_OUTSIDE_PIX_STRATEGY, mask_sh),\ - SF(WBSCL_OUTSIDE_PIX_STRATEGY, WBSCL_BLACK_COLOR_G_Y, mask_sh),\ - SF(WBSCL_OUTSIDE_PIX_STRATEGY_CBCR, WBSCL_BLACK_COLOR_B_CB, mask_sh),\ - SF(WBSCL_OUTSIDE_PIX_STRATEGY_CBCR, WBSCL_BLACK_COLOR_R_CR, mask_sh),\ - SF(WBSCL_DEBUG, WBSCL_DEBUG, mask_sh),\ - SF(WBSCL_TEST_DEBUG_INDEX, WBSCL_TEST_DEBUG_INDEX, mask_sh),\ - SF(WBSCL_TEST_DEBUG_INDEX, WBSCL_TEST_DEBUG_WRITE_EN, mask_sh),\ - SF(WBSCL_TEST_DEBUG_DATA, WBSCL_TEST_DEBUG_DATA, mask_sh),\ - SF(WB_WARM_UP_MODE_CTL1, WIDTH_WARMUP, mask_sh),\ - SF(WB_WARM_UP_MODE_CTL1, HEIGHT_WARMUP, mask_sh),\ - SF(WB_WARM_UP_MODE_CTL1, GMC_WARM_UP_ENABLE, mask_sh),\ - SF(WB_WARM_UP_MODE_CTL2, DATA_VALUE_WARMUP, mask_sh),\ - SF(WB_WARM_UP_MODE_CTL2, MODE_WARMUP, mask_sh),\ - SF(WB_WARM_UP_MODE_CTL2, DATA_DEPTH_WARMUP, mask_sh) + SF_DWB(WB_ENABLE, WB_ENABLE, mask_sh),\ + SF_DWB(WB_EC_CONFIG, DISPCLK_R_WB_GATE_DIS, mask_sh),\ + SF_DWB(WB_EC_CONFIG, DISPCLK_G_WB_GATE_DIS, mask_sh),\ + SF_DWB(WB_EC_CONFIG, DISPCLK_G_WBSCL_GATE_DIS, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WB_TEST_CLK_SEL, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WB_LB_LS_DIS, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WB_LB_SD_DIS, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WB_LUT_LS_DIS, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_MODE_SEL, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_DIS, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_FORCE, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WBSCL_LB_MEM_PWR_STATE, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WB_RAM_PW_SAVE_MODE, mask_sh),\ + SF_DWB(WB_EC_CONFIG, WBSCL_LUT_MEM_PWR_STATE, mask_sh),\ + SF_DWB(CNV_MODE, CNV_OUT_BPC, mask_sh),\ + SF_DWB(CNV_MODE, CNV_FRAME_CAPTURE_RATE, mask_sh),\ + SF_DWB(CNV_MODE, CNV_WINDOW_CROP_EN, mask_sh),\ + SF_DWB(CNV_MODE, CNV_STEREO_TYPE, mask_sh),\ + SF_DWB(CNV_MODE, CNV_INTERLACED_MODE, mask_sh),\ + SF_DWB(CNV_MODE, CNV_EYE_SELECTION, mask_sh),\ + SF_DWB(CNV_MODE, CNV_STEREO_POLARITY, mask_sh),\ + SF_DWB(CNV_MODE, CNV_INTERLACED_FIELD_ORDER, mask_sh),\ + SF_DWB(CNV_MODE, CNV_STEREO_SPLIT, mask_sh),\ + SF_DWB(CNV_MODE, CNV_NEW_CONTENT, mask_sh),\ + SF_DWB(CNV_MODE, CNV_FRAME_CAPTURE_EN_CURRENT, mask_sh),\ + SF_DWB(CNV_MODE, CNV_FRAME_CAPTURE_EN, mask_sh),\ + SF_DWB(CNV_WINDOW_START, CNV_WINDOW_START_X, mask_sh),\ + SF_DWB(CNV_WINDOW_START, CNV_WINDOW_START_Y, mask_sh),\ + SF_DWB(CNV_WINDOW_SIZE, CNV_WINDOW_WIDTH, mask_sh),\ + SF_DWB(CNV_WINDOW_SIZE, CNV_WINDOW_HEIGHT, mask_sh),\ + SF_DWB(CNV_UPDATE, CNV_UPDATE_PENDING, mask_sh),\ + SF_DWB(CNV_UPDATE, CNV_UPDATE_TAKEN, mask_sh),\ + SF_DWB(CNV_UPDATE, CNV_UPDATE_LOCK, mask_sh),\ + SF_DWB(CNV_SOURCE_SIZE, CNV_SOURCE_WIDTH, mask_sh),\ + SF_DWB(CNV_SOURCE_SIZE, CNV_SOURCE_HEIGHT, mask_sh),\ + SF_DWB(CNV_TEST_CNTL, CNV_TEST_CRC_EN, mask_sh),\ + SF_DWB(CNV_TEST_CNTL, CNV_TEST_CRC_CONT_EN, mask_sh),\ + SF_DWB(CNV_TEST_CRC_RED, CNV_TEST_CRC_RED_MASK, mask_sh),\ + SF_DWB(CNV_TEST_CRC_RED, CNV_TEST_CRC_SIG_RED, mask_sh),\ + SF_DWB(CNV_TEST_CRC_GREEN, CNV_TEST_CRC_GREEN_MASK, mask_sh),\ + SF_DWB(CNV_TEST_CRC_GREEN, CNV_TEST_CRC_SIG_GREEN, mask_sh),\ + SF_DWB(CNV_TEST_CRC_BLUE, CNV_TEST_CRC_BLUE_MASK, mask_sh),\ + SF_DWB(CNV_TEST_CRC_BLUE, CNV_TEST_CRC_SIG_BLUE, mask_sh),\ + SF_DWB(WB_DEBUG_CTRL, WB_DEBUG_EN, mask_sh),\ + SF_DWB(WB_DEBUG_CTRL, WB_DEBUG_SEL, mask_sh),\ + SF_DWB(WB_DBG_MODE, WB_DBG_MODE_EN, mask_sh),\ + SF_DWB(WB_DBG_MODE, WB_DBG_DIN_FMT, mask_sh),\ + SF_DWB(WB_DBG_MODE, WB_DBG_36MODE, mask_sh),\ + SF_DWB(WB_DBG_MODE, WB_DBG_CMAP, mask_sh),\ + SF_DWB(WB_DBG_MODE, WB_DBG_PXLRATE_ERROR, mask_sh),\ + SF_DWB(WB_DBG_MODE, WB_DBG_SOURCE_WIDTH, mask_sh),\ + SF_DWB(WB_HW_DEBUG, WB_HW_DEBUG, mask_sh),\ + SF_DWB(WB_SOFT_RESET, WB_SOFT_RESET, mask_sh),\ + SF_DWB(CNV_TEST_DEBUG_INDEX, CNV_TEST_DEBUG_INDEX, mask_sh),\ + SF_DWB(CNV_TEST_DEBUG_INDEX, CNV_TEST_DEBUG_WRITE_EN, mask_sh),\ + SF_DWB(CNV_TEST_DEBUG_DATA, CNV_TEST_DEBUG_DATA, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_SELECT, WBSCL_COEF_RAM_TAP_PAIR_IDX, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_SELECT, WBSCL_COEF_RAM_PHASE, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_SELECT, WBSCL_COEF_RAM_FILTER_TYPE, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_EVEN_TAP_COEF, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_EVEN_TAP_COEF_EN, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_ODD_TAP_COEF, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_TAP_DATA, WBSCL_COEF_RAM_ODD_TAP_COEF_EN, mask_sh),\ + SF_DWB(WBSCL_MODE, WBSCL_MODE, mask_sh),\ + SF_DWB(WBSCL_MODE, WBSCL_OUT_BIT_DEPTH, mask_sh),\ + SF_DWB(WBSCL_TAP_CONTROL, WBSCL_V_NUM_OF_TAPS_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_TAP_CONTROL, WBSCL_V_NUM_OF_TAPS_CBCR, mask_sh),\ + SF_DWB(WBSCL_TAP_CONTROL, WBSCL_H_NUM_OF_TAPS_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_TAP_CONTROL, WBSCL_H_NUM_OF_TAPS_CBCR, mask_sh),\ + SF_DWB(WBSCL_DEST_SIZE, WBSCL_DEST_HEIGHT, mask_sh),\ + SF_DWB(WBSCL_DEST_SIZE, WBSCL_DEST_WIDTH, mask_sh),\ + SF_DWB(WBSCL_HORZ_FILTER_SCALE_RATIO, WBSCL_H_SCALE_RATIO, mask_sh),\ + SF_DWB(WBSCL_HORZ_FILTER_INIT_Y_RGB, WBSCL_H_INIT_FRAC_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_HORZ_FILTER_INIT_Y_RGB, WBSCL_H_INIT_INT_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_HORZ_FILTER_INIT_CBCR, WBSCL_H_INIT_FRAC_CBCR, mask_sh),\ + SF_DWB(WBSCL_HORZ_FILTER_INIT_CBCR, WBSCL_H_INIT_INT_CBCR, mask_sh),\ + SF_DWB(WBSCL_VERT_FILTER_SCALE_RATIO, WBSCL_V_SCALE_RATIO, mask_sh),\ + SF_DWB(WBSCL_VERT_FILTER_INIT_Y_RGB, WBSCL_V_INIT_FRAC_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_VERT_FILTER_INIT_Y_RGB, WBSCL_V_INIT_INT_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_VERT_FILTER_INIT_CBCR, WBSCL_V_INIT_FRAC_CBCR, mask_sh),\ + SF_DWB(WBSCL_VERT_FILTER_INIT_CBCR, WBSCL_V_INIT_INT_CBCR, mask_sh),\ + SF_DWB(WBSCL_ROUND_OFFSET, WBSCL_ROUND_OFFSET_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_ROUND_OFFSET, WBSCL_ROUND_OFFSET_CBCR, mask_sh),\ + SF_DWB(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_FLAG, mask_sh),\ + SF_DWB(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_ACK, mask_sh),\ + SF_DWB(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_MASK, mask_sh),\ + SF_DWB(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_INT_STATUS, mask_sh),\ + SF_DWB(WBSCL_OVERFLOW_STATUS, WBSCL_DATA_OVERFLOW_INT_TYPE, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_FLAG, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_ACK, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_MASK, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_INT_STATUS, mask_sh),\ + SF_DWB(WBSCL_COEF_RAM_CONFLICT_STATUS, WBSCL_HOST_CONFLICT_INT_TYPE, mask_sh),\ + SF_DWB(WBSCL_TEST_CNTL, WBSCL_TEST_CRC_EN, mask_sh),\ + SF_DWB(WBSCL_TEST_CNTL, WBSCL_TEST_CRC_CONT_EN, mask_sh),\ + SF_DWB(WBSCL_TEST_CRC_RED, WBSCL_TEST_CRC_RED_MASK, mask_sh),\ + SF_DWB(WBSCL_TEST_CRC_RED, WBSCL_TEST_CRC_SIG_RED, mask_sh),\ + SF_DWB(WBSCL_TEST_CRC_GREEN, WBSCL_TEST_CRC_GREEN_MASK, mask_sh),\ + SF_DWB(WBSCL_TEST_CRC_GREEN, WBSCL_TEST_CRC_SIG_GREEN, mask_sh),\ + SF_DWB(WBSCL_TEST_CRC_BLUE, WBSCL_TEST_CRC_BLUE_MASK, mask_sh),\ + SF_DWB(WBSCL_TEST_CRC_BLUE, WBSCL_TEST_CRC_SIG_BLUE, mask_sh),\ + SF_DWB(WBSCL_BACKPRESSURE_CNT_EN, WBSCL_BACKPRESSURE_CNT_EN, mask_sh),\ + SF_DWB(WB_MCIF_BACKPRESSURE_CNT, WB_MCIF_Y_MAX_BACKPRESSURE, mask_sh),\ + SF_DWB(WB_MCIF_BACKPRESSURE_CNT, WB_MCIF_C_MAX_BACKPRESSURE, mask_sh),\ + SF_DWB(WBSCL_CLAMP_Y_RGB, WBSCL_CLAMP_UPPER_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_CLAMP_Y_RGB, WBSCL_CLAMP_LOWER_Y_RGB, mask_sh),\ + SF_DWB(WBSCL_CLAMP_CBCR, WBSCL_CLAMP_UPPER_CBCR, mask_sh),\ + SF_DWB(WBSCL_CLAMP_CBCR, WBSCL_CLAMP_LOWER_CBCR, mask_sh),\ + SF_DWB(WBSCL_OUTSIDE_PIX_STRATEGY, WBSCL_OUTSIDE_PIX_STRATEGY, mask_sh),\ + SF_DWB(WBSCL_OUTSIDE_PIX_STRATEGY, WBSCL_BLACK_COLOR_G_Y, mask_sh),\ + SF_DWB(WBSCL_OUTSIDE_PIX_STRATEGY_CBCR, WBSCL_BLACK_COLOR_B_CB, mask_sh),\ + SF_DWB(WBSCL_OUTSIDE_PIX_STRATEGY_CBCR, WBSCL_BLACK_COLOR_R_CR, mask_sh),\ + SF_DWB(WBSCL_DEBUG, WBSCL_DEBUG, mask_sh),\ + SF_DWB(WBSCL_TEST_DEBUG_INDEX, WBSCL_TEST_DEBUG_INDEX, mask_sh),\ + SF_DWB(WBSCL_TEST_DEBUG_INDEX, WBSCL_TEST_DEBUG_WRITE_EN, mask_sh),\ + SF_DWB(WBSCL_TEST_DEBUG_DATA, WBSCL_TEST_DEBUG_DATA, mask_sh),\ + SF_DWB(WB_WARM_UP_MODE_CTL1, WIDTH_WARMUP, mask_sh),\ + SF_DWB(WB_WARM_UP_MODE_CTL1, HEIGHT_WARMUP, mask_sh),\ + SF_DWB(WB_WARM_UP_MODE_CTL1, GMC_WARM_UP_ENABLE, mask_sh),\ + SF_DWB(WB_WARM_UP_MODE_CTL2, DATA_VALUE_WARMUP, mask_sh),\ + SF_DWB(WB_WARM_UP_MODE_CTL2, MODE_WARMUP, mask_sh),\ + SF_DWB(WB_WARM_UP_MODE_CTL2, DATA_DEPTH_WARMUP, mask_sh) #define DWBC_REG_FIELD_LIST_DCN2_0(type) \ type WB_ENABLE;\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c index aacb1fb5c73e..24bd93219936 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c @@ -500,7 +500,7 @@ void hubbub2_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A); s = &wm->sets[1]; s->wm_set = 1; @@ -511,7 +511,7 @@ void hubbub2_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B); s = &wm->sets[2]; s->wm_set = 2; @@ -522,7 +522,7 @@ void hubbub2_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C); s = &wm->sets[3]; s->wm_set = 3; @@ -533,7 +533,7 @@ void hubbub2_wm_read_state(struct hubbub *hubbub, s->sr_enter = REG_READ(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D); s->sr_exit = REG_READ(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D); } - s->dram_clk_chanage = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D); + s->dram_clk_change = REG_READ(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D); } void hubbub2_get_dchub_ref_freq(struct hubbub *hubbub, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 938dba5249d4..4566bc7abf17 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -973,10 +973,12 @@ void hubp2_cursor_set_position( const struct dc_cursor_mi_param *param) { struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); - int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - int src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; + int x_pos = pos->x - param->viewport.x; + int y_pos = pos->y - param->viewport.y; int x_hotspot = pos->x_hotspot; int y_hotspot = pos->y_hotspot; + int src_x_offset = x_pos - pos->x_hotspot; + int src_y_offset = y_pos - pos->y_hotspot; int cursor_height = (int)hubp->curs_attr.height; int cursor_width = (int)hubp->curs_attr.width; uint32_t dst_x_offset; @@ -994,18 +996,26 @@ void hubp2_cursor_set_position( if (hubp->curs_attr.address.quad_part == 0) return; - // Rotated cursor width/height and hotspots tweaks for offset calculation + // Transform cursor width / height and hotspots for offset calculations if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { swap(cursor_height, cursor_width); + swap(x_hotspot, y_hotspot); + if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; + // hotspot = (-y, x) + src_x_offset = x_pos - (cursor_width - x_hotspot); + src_y_offset = y_pos - y_hotspot; + } else if (param->rotation == ROTATION_ANGLE_270) { + // hotspot = (y, -x) + src_x_offset = x_pos - x_hotspot; + src_y_offset = y_pos - (cursor_height - y_hotspot); } } else if (param->rotation == ROTATION_ANGLE_180) { + // hotspot = (-x, -y) if (!param->mirror) - src_x_offset = pos->x - param->viewport.x; + src_x_offset = x_pos - (cursor_width - x_hotspot); - src_y_offset = pos->y - param->viewport.y; + src_y_offset = y_pos - (cursor_height - y_hotspot); } dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0; @@ -1042,8 +1052,8 @@ void hubp2_cursor_set_position( CURSOR_Y_POSITION, pos->y); REG_SET_2(CURSOR_HOT_SPOT, 0, - CURSOR_HOT_SPOT_X, x_hotspot, - CURSOR_HOT_SPOT_Y, y_hotspot); + CURSOR_HOT_SPOT_X, pos->x_hotspot, + CURSOR_HOT_SPOT_Y, pos->y_hotspot); REG_SET(CURSOR_DST_OFFSET, 0, CURSOR_DST_X_OFFSET, dst_x_offset); @@ -1052,8 +1062,8 @@ void hubp2_cursor_set_position( hubp->pos.cur_ctl.bits.cur_enable = cur_en; hubp->pos.position.bits.x_pos = pos->x; hubp->pos.position.bits.y_pos = pos->y; - hubp->pos.hot_spot.bits.x_hot = x_hotspot; - hubp->pos.hot_spot.bits.y_hot = y_hotspot; + hubp->pos.hot_spot.bits.x_hot = pos->x_hotspot; + hubp->pos.hot_spot.bits.y_hot = pos->y_hotspot; hubp->pos.dst_offset.bits.dst_x_offset = dst_x_offset; /* Cursor Rectangle Cache * Cursor bitmaps have different hotspot values diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index f3334f513eb4..6291a241158a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1310,6 +1310,19 @@ static void dcn20_detect_pipe_changes(struct pipe_ctx *old_pipe, struct pipe_ctx { new_pipe->update_flags.raw = 0; + /* If non-phantom pipe is being transitioned to a phantom pipe, + * set disable and return immediately. This is because the pipe + * that was previously in use must be fully disabled before we + * can "enable" it as a phantom pipe (since the OTG will certainly + * be different). The post_unlock sequence will set the correct + * update flags to enable the phantom pipe. + */ + if (old_pipe->plane_state && !old_pipe->plane_state->is_phantom && + new_pipe->plane_state && new_pipe->plane_state->is_phantom) { + new_pipe->update_flags.bits.disable = 1; + return; + } + /* Exit on unchanged, unused pipe */ if (!old_pipe->plane_state && !new_pipe->plane_state) return; @@ -1639,6 +1652,31 @@ static void dcn20_update_dchubp_dpp( hubp->funcs->phantom_hubp_post_enable(hubp); } +static int calculate_vready_offset_for_group(struct pipe_ctx *pipe) +{ + struct pipe_ctx *other_pipe; + int vready_offset = pipe->pipe_dlg_param.vready_offset; + + /* Always use the largest vready_offset of all connected pipes */ + for (other_pipe = pipe->bottom_pipe; other_pipe != NULL; other_pipe = other_pipe->bottom_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + for (other_pipe = pipe->top_pipe; other_pipe != NULL; other_pipe = other_pipe->top_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + for (other_pipe = pipe->next_odm_pipe; other_pipe != NULL; other_pipe = other_pipe->next_odm_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + for (other_pipe = pipe->prev_odm_pipe; other_pipe != NULL; other_pipe = other_pipe->prev_odm_pipe) { + if (other_pipe->pipe_dlg_param.vready_offset > vready_offset) + vready_offset = other_pipe->pipe_dlg_param.vready_offset; + } + + return vready_offset; +} static void dcn20_program_pipe( struct dc *dc, @@ -1657,12 +1695,13 @@ static void dcn20_program_pipe( && !pipe_ctx->prev_odm_pipe) { pipe_ctx->stream_res.tg->funcs->program_global_sync( pipe_ctx->stream_res.tg, - pipe_ctx->pipe_dlg_param.vready_offset, + calculate_vready_offset_for_group(pipe_ctx), pipe_ctx->pipe_dlg_param.vstartup_start, pipe_ctx->pipe_dlg_param.vupdate_offset, pipe_ctx->pipe_dlg_param.vupdate_width); if (pipe_ctx->stream->mall_stream_config.type != SUBVP_PHANTOM) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); } @@ -1702,7 +1741,10 @@ static void dcn20_program_pipe( * only do gamma programming for powering on, internal memcmp to avoid * updating on slave planes */ - if (pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.out_tf) + if (pipe_ctx->update_flags.bits.enable || + pipe_ctx->update_flags.bits.plane_changed || + pipe_ctx->stream->update_flags.bits.out_tf || + pipe_ctx->plane_state->update_flags.bits.output_tf_change) hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream); /* If the pipe has been enabled or has a different opp, we @@ -1833,6 +1875,17 @@ void dcn20_program_front_end_for_ctx( context->stream_status[0].plane_count > 1) { pipe->plane_res.hubp->funcs->hubp_wait_pipe_read_start(pipe->plane_res.hubp); } + + /* when dynamic ODM is active, pipes must be reconfigured when all planes are + * disabled, as some transitions will leave software and hardware state + * mismatched. + */ + if (dc->debug.enable_single_display_2to1_odm_policy && + pipe->stream && + pipe->update_flags.bits.disable && + !pipe->prev_odm_pipe && + hws->funcs.update_odm) + hws->funcs.update_odm(dc, context, pipe); } } @@ -1872,26 +1925,6 @@ void dcn20_post_unlock_program_front_end( for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; - - /* If an active, non-phantom pipe is being transitioned into a phantom - * pipe, wait for the double buffer update to complete first before we do - * phantom pipe programming (HUBP_VTG_SEL updates right away so that can - * cause issues). - */ - if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM && - old_pipe->stream && old_pipe->stream->mall_stream_config.type != SUBVP_PHANTOM) { - old_pipe->stream_res.tg->funcs->wait_for_state( - old_pipe->stream_res.tg, - CRTC_STATE_VBLANK); - old_pipe->stream_res.tg->funcs->wait_for_state( - old_pipe->stream_res.tg, - CRTC_STATE_VACTIVE); - } - } - - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; if (pipe->plane_state && !pipe->top_pipe) { /* Program phantom pipe here to prevent a frame of underflow in the MPO transition @@ -1901,6 +1934,11 @@ void dcn20_post_unlock_program_front_end( */ while (pipe) { if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + /* When turning on the phantom pipe we want to run through the + * entire enable sequence, so apply all the "enable" flags. + */ + if (dc->hwss.apply_update_flags_for_phantom) + dc->hwss.apply_update_flags_for_phantom(pipe); if (dc->hwss.update_phantom_vp_position) dc->hwss.update_phantom_vp_position(dc, context, pipe); dcn20_program_pipe(dc, pipe, context); @@ -1973,10 +2011,13 @@ void dcn20_prepare_bandwidth( /* decrease compbuf size */ if (hubbub->funcs->program_compbuf_size) { - if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) + if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) { compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes; - else + dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes); + } else { compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb; + dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb); + } hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false); } @@ -2057,7 +2098,7 @@ bool dcn20_update_bandwidth( pipe_ctx->stream_res.tg->funcs->program_global_sync( pipe_ctx->stream_res.tg, - pipe_ctx->pipe_dlg_param.vready_offset, + calculate_vready_offset_for_group(pipe_ctx), pipe_ctx->pipe_dlg_param.vstartup_start, pipe_ctx->pipe_dlg_param.vupdate_offset, pipe_ctx->pipe_dlg_param.vupdate_width); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.h index 7bcee5894d2e..5ab32aa51e13 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mmhubbub.h @@ -29,13 +29,6 @@ #define TO_DCN20_MMHUBBUB(mcif_wb_base) \ container_of(mcif_wb_base, struct dcn20_mmhubbub, base) -/* DCN */ -#define BASE_INNER(seg) \ - DCE_BASE__INST0_SEG ## seg - -#define BASE(seg) \ - BASE_INNER(seg) - #define MCIF_WB_COMMON_REG_LIST_DCN2_0(inst) \ SRI(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB, inst),\ SRI(MCIF_WB_BUFMGR_CUR_LINE_R, MCIF_WB, inst),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d0199ec045cb..8a0dd0d7134b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -124,8 +124,6 @@ enum dcn20_clk_src_array_id { * macros to expend register list macro defined in HW object header file */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -138,6 +136,15 @@ enum dcn20_clk_src_array_id { .reg_name = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name +#define SRI2_DWB(reg_name, block, id)\ + .reg_name = BASE(mm ## reg_name ## _BASE_IDX) + \ + mm ## reg_name +#define SF_DWB(reg_name, field_name, post_fix)\ + .field_name = reg_name ## __ ## field_name ## post_fix + +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define SRIR(var_name, reg_name, block, id)\ .var_name = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.h index f1ef46e8da5b..e7a1b7fa2cce 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.h @@ -28,12 +28,6 @@ #include "vmid.h" -#define BASE_INNER(seg) \ - DCE_BASE__INST0_SEG ## seg - -#define BASE(seg) \ - BASE_INNER(seg) - #define DCN20_VMID_REG_LIST(id)\ SRI(CNTL, DCN_VM_CONTEXT, id),\ SRI(PAGE_TABLE_BASE_ADDR_HI32, DCN_VM_CONTEXT, id),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c index c5e200d09038..aeb0e0d9b70a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c @@ -635,7 +635,7 @@ void hubbub21_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, &s->sr_exit); REG_GET(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, - DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, &s->dram_clk_chanage); + DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, &s->dram_clk_change); s = &wm->sets[1]; s->wm_set = 1; @@ -649,7 +649,7 @@ void hubbub21_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, &s->sr_exit); REG_GET(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, - DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, &s->dram_clk_chanage); + DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, &s->dram_clk_change); s = &wm->sets[2]; s->wm_set = 2; @@ -663,7 +663,7 @@ void hubbub21_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, &s->sr_exit); REG_GET(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, - DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, &s->dram_clk_chanage); + DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, &s->dram_clk_change); s = &wm->sets[3]; s->wm_set = 3; @@ -677,7 +677,7 @@ void hubbub21_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, &s->sr_exit); REG_GET(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, - DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, &s->dram_clk_chanage); + DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, &s->dram_clk_change); } static void hubbub21_apply_DEDCN21_147_wa(struct hubbub *hubbub) diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index ce6c70e25703..fbcf0afeae0d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -94,8 +94,6 @@ * macros to expend register list macro defined in HW object header file */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) DMU_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb.h index 1010930cf071..fc00ec0a0881 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb.h @@ -27,21 +27,6 @@ #define TO_DCN30_DWBC(dwbc_base) \ container_of(dwbc_base, struct dcn30_dwbc, base) -/* DCN */ -#define BASE_INNER(seg) \ - DCE_BASE__INST0_SEG ## seg - -#define BASE(seg) \ - BASE_INNER(seg) - -#define SF_DWB(reg_name, block, id, field_name, post_fix)\ - .field_name = block ## id ## _ ## reg_name ## __ ## field_name ## post_fix - - /* set field name */ -#define SF_DWB2(reg_name, block, id, field_name, post_fix)\ - .field_name = reg_name ## __ ## field_name ## post_fix - - #define DWBC_COMMON_REG_LIST_DCN30(inst) \ SR(DWB_ENABLE_CLK_CTRL),\ SR(DWB_MEM_PWR_CTRL),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h index 7446e54bf5aa..376620a8f02f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mmhubbub.h @@ -31,13 +31,6 @@ #define TO_DCN30_MMHUBBUB(mcif_wb_base) \ container_of(mcif_wb_base, struct dcn30_mmhubbub, base) -/* DCN */ -#define BASE_INNER(seg) \ - DCE_BASE__INST0_SEG ## seg - -#define BASE(seg) \ - BASE_INNER(seg) - #define MCIF_WB_COMMON_REG_LIST_DCN3_0(inst) \ SRI(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB, inst),\ SRI(MCIF_WB_BUFMGR_STATUS, MCIF_WB, inst),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index af4fe695535e..c18c52a60100 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -108,8 +108,6 @@ enum dcn30_clk_src_array_id { */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -142,6 +140,9 @@ enum dcn30_clk_src_array_id { .reg_name[id] = BASE(mm ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define DCCG_SRII(reg_name, block, id)\ .block ## _ ## reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name @@ -1328,6 +1329,7 @@ static struct clock_source *dcn30_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index f04595b750ab..8cf10351f271 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -107,8 +107,6 @@ enum dcn301_clk_src_array_id { */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -146,6 +144,9 @@ enum dcn301_clk_src_array_id { .reg_name[id] = BASE(mm ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define DCCG_SRII(reg_name, block, id)\ .block ## _ ## reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name @@ -1288,6 +1289,7 @@ static struct clock_source *dcn301_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } @@ -1491,6 +1493,8 @@ static bool dcn301_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + dc->caps.dp_hdmi21_pcon_support = true; + /* read VBIOS LTTPR caps */ if (ctx->dc_bios->funcs->get_lttpr_caps) { enum bp_result bp_query_result; diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index d3945876aced..47cffd0e6830 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -183,7 +183,6 @@ static const struct dc_plane_cap plane_cap = { mm ## reg_name /* DCN */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -216,6 +215,9 @@ static const struct dc_plane_cap plane_cap = { .reg_name[id] = BASE(mm ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define SRII_MPC_RMU(reg_name, block, id)\ .RMU##_##reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name @@ -464,6 +466,7 @@ static struct clock_source *dcn302_clock_source_create(struct dc_context *ctx, s return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } @@ -1278,6 +1281,8 @@ static bool dcn302_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + dc->caps.dp_hdmi21_pcon_support = true; + /* read VBIOS LTTPR caps */ if (ctx->dc_bios->funcs->get_lttpr_caps) { enum bp_result bp_query_result; diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index 7e7f18bef098..c14d35894b2e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -162,7 +162,6 @@ static const struct dc_plane_cap plane_cap = { mm ## reg_name /* DCN */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -195,6 +194,9 @@ static const struct dc_plane_cap plane_cap = { .reg_name[id] = BASE(mm ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define SRII_MPC_RMU(reg_name, block, id)\ .RMU##_##reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name @@ -431,6 +433,7 @@ static struct clock_source *dcn303_clock_source_create(struct dc_context *ctx, s return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } @@ -1209,6 +1212,8 @@ static bool dcn303_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + dc->caps.dp_hdmi21_pcon_support = true; + /* read VBIOS LTTPR caps */ if (ctx->dc_bios->funcs->get_lttpr_caps) { enum bp_result bp_query_result; diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c index 84e1486f3d51..39a57bcd7866 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c @@ -87,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .hubp_init = hubp3_init, .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, + .hubp_set_flip_int = hubp1_set_flip_int, .hubp_in_blank = hubp1_in_blank, .program_extended_blank = hubp31_program_extended_blank, }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 165c920ca776..4226a051df41 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -623,3 +623,43 @@ void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable) if (hws->ctx->dc->debug.hpo_optimization) REG_UPDATE(HPO_TOP_HW_CONTROL, HPO_IO_EN, !!enable); } +void dcn31_set_drr(struct pipe_ctx **pipe_ctx, + int num_pipes, struct dc_crtc_timing_adjust adjust) +{ + int i = 0; + struct drr_params params = {0}; + unsigned int event_triggers = 0x2;/*Bit[1]: OTG_TRIG_A*/ + unsigned int num_frames = 2; + params.vertical_total_max = adjust.v_total_max; + params.vertical_total_min = adjust.v_total_min; + params.vertical_total_mid = adjust.v_total_mid; + params.vertical_total_mid_frame_num = adjust.v_total_mid_frame_num; + for (i = 0; i < num_pipes; i++) { + if ((pipe_ctx[i]->stream_res.tg != NULL) && pipe_ctx[i]->stream_res.tg->funcs) { + if (pipe_ctx[i]->stream_res.tg->funcs->set_drr) + pipe_ctx[i]->stream_res.tg->funcs->set_drr( + pipe_ctx[i]->stream_res.tg, ¶ms); + if (adjust.v_total_max != 0 && adjust.v_total_min != 0) + if (pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control) + pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control( + pipe_ctx[i]->stream_res.tg, + event_triggers, num_frames); + } + } +} +void dcn31_set_static_screen_control(struct pipe_ctx **pipe_ctx, + int num_pipes, const struct dc_static_screen_params *params) +{ + unsigned int i; + unsigned int triggers = 0; + if (params->triggers.surface_update) + triggers |= 0x600;/*bit 9 and bit10 : 110 0000 0000*/ + if (params->triggers.cursor_update) + triggers |= 0x10;/*bit4*/ + if (params->triggers.force_trigger) + triggers |= 0x1; + for (i = 0; i < num_pipes; i++) + pipe_ctx[i]->stream_res.tg->funcs-> + set_static_screen_control(pipe_ctx[i]->stream_res.tg, + triggers, params->num_frames); +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h index edfc01d6ad73..e7e03a8722e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h @@ -56,4 +56,8 @@ bool dcn31_is_abm_supported(struct dc *dc, void dcn31_init_pipes(struct dc *dc, struct dc_state *context); void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable); +void dcn31_set_static_screen_control(struct pipe_ctx **pipe_ctx, + int num_pipes, const struct dc_static_screen_params *params); +void dcn31_set_drr(struct pipe_ctx **pipe_ctx, + int num_pipes, struct dc_crtc_timing_adjust adjust); #endif /* __DC_HWSS_DCN31_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index 3a32810bbe38..7c2da70ffe21 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -64,9 +64,9 @@ static const struct hw_sequencer_funcs dcn31_funcs = { .prepare_bandwidth = dcn20_prepare_bandwidth, .optimize_bandwidth = dcn20_optimize_bandwidth, .update_bandwidth = dcn20_update_bandwidth, - .set_drr = dcn10_set_drr, + .set_drr = dcn31_set_drr, .get_position = dcn10_get_position, - .set_static_screen_control = dcn10_set_static_screen_control, + .set_static_screen_control = dcn31_set_static_screen_control, .setup_stereo = dcn10_setup_stereo, .set_avmute = dcn30_set_avmute, .log_hw_state = dcn10_log_hw_state, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 63a677c8ee27..fe449f7aa771 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -40,6 +40,7 @@ #define FN(reg_name, field_name) \ optc1->tg_shift->field_name, optc1->tg_mask->field_name +#define STATIC_SCREEN_EVENT_MASK_DRR_DOUBLE_BUFFER_UPDATE_EN 0x2000 /*bit 13*/ static void optc31_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_cnt, struct dc_crtc_timing *timing) { @@ -231,6 +232,32 @@ void optc3_init_odm(struct timing_generator *optc) OPTC_MEM_SEL, 0); optc1->opp_count = 1; } +void optc31_set_static_screen_control( + struct timing_generator *optc, + uint32_t event_triggers, + uint32_t num_frames) +{ + struct optc *optc1 = DCN10TG_FROM_TG(optc); + uint32_t framecount; + uint32_t events; + + if (num_frames > 0xFF) + num_frames = 0xFF; + REG_GET_2(OTG_STATIC_SCREEN_CONTROL, + OTG_STATIC_SCREEN_EVENT_MASK, &events, + OTG_STATIC_SCREEN_FRAME_COUNT, &framecount); + + if (events == event_triggers && num_frames == framecount) + return; + if ((event_triggers & STATIC_SCREEN_EVENT_MASK_DRR_DOUBLE_BUFFER_UPDATE_EN) + != 0) + event_triggers = event_triggers & + ~STATIC_SCREEN_EVENT_MASK_DRR_DOUBLE_BUFFER_UPDATE_EN; + + REG_UPDATE_2(OTG_STATIC_SCREEN_CONTROL, + OTG_STATIC_SCREEN_EVENT_MASK, event_triggers, + OTG_STATIC_SCREEN_FRAME_COUNT, num_frames); +} static struct timing_generator_funcs dcn31_tg_funcs = { .validate_timing = optc1_validate_timing, @@ -266,7 +293,7 @@ static struct timing_generator_funcs dcn31_tg_funcs = { .set_drr = optc31_set_drr, .get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal, .set_vtotal_min_max = optc1_set_vtotal_min_max, - .set_static_screen_control = optc1_set_static_screen_control, + .set_static_screen_control = optc31_set_static_screen_control, .program_stereo = optc1_program_stereo, .is_stereo_left_eye = optc1_is_stereo_left_eye, .tg_init = optc3_tg_init, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.h index 30b81a448ce2..5fc6c63580d7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.h @@ -263,5 +263,8 @@ bool optc31_immediate_disable_crtc(struct timing_generator *optc); void optc31_set_drr(struct timing_generator *optc, const struct drr_params *params); void optc3_init_odm(struct timing_generator *optc); - +void optc31_set_static_screen_control( + struct timing_generator *optc, + uint32_t event_triggers, + uint32_t num_frames); #endif /* __DC_OPTC_DCN31_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 8f5e89cb9d3e..3ca517dcc82d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -119,8 +119,6 @@ enum dcn31_clk_src_array_id { */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -153,6 +151,9 @@ enum dcn31_clk_src_array_id { .reg_name[id] = BASE(reg ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define DCCG_SRII(reg_name, block, id)\ .block ## _ ## reg_name[id] = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name @@ -1629,6 +1630,7 @@ static struct clock_source *dcn31_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } @@ -1638,6 +1640,31 @@ static bool is_dual_plane(enum surface_pixel_format format) return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA; } +int dcn31x_populate_dml_pipes_from_context(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate) +{ + uint32_t pipe_cnt; + int i; + + dc_assert_fp_enabled(); + + pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + + for (i = 0; i < pipe_cnt; i++) { + pipes[i].pipe.src.gpuvm = 1; + if (dc->debug.dml_hostvm_override == DML_HOSTVM_NO_OVERRIDE) { + //pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active; + pipes[i].pipe.src.hostvm = dc->vm_pa_config.is_hvm_enabled; + } else if (dc->debug.dml_hostvm_override == DML_HOSTVM_OVERRIDE_FALSE) + pipes[i].pipe.src.hostvm = false; + else if (dc->debug.dml_hostvm_override == DML_HOSTVM_OVERRIDE_TRUE) + pipes[i].pipe.src.hostvm = true; + } + return pipe_cnt; +} + int dcn31_populate_dml_pipes_from_context( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, @@ -1649,7 +1676,7 @@ int dcn31_populate_dml_pipes_from_context( bool upscaled = false; DC_FP_START(); - dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + dcn31x_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); DC_FP_END(); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { @@ -1679,12 +1706,6 @@ int dcn31_populate_dml_pipes_from_context( dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt); DC_FP_END(); - if (dc->debug.dml_hostvm_override == DML_HOSTVM_NO_OVERRIDE) - pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active; - else if (dc->debug.dml_hostvm_override == DML_HOSTVM_OVERRIDE_FALSE) - pipes[pipe_cnt].pipe.src.hostvm = false; - else if (dc->debug.dml_hostvm_override == DML_HOSTVM_OVERRIDE_TRUE) - pipes[pipe_cnt].pipe.src.hostvm = true; if (pipes[pipe_cnt].dout.dsc_enable) { switch (timing->display_color_depth) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 367cb6e6d074..0b769ee71405 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -96,6 +96,13 @@ static void dccg314_set_pixel_rate_div( struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA; + // Don't program 0xF into the register field. Not valid since + // K1 / K2 field is only 1 / 2 bits wide + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) { + BREAK_TO_DEBUGGER(); + return; + } + dccg314_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); if (k1 == cur_k1 && k2 == cur_k2) return; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c index 7e773bf7b895..38842f938bed 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c @@ -49,18 +49,30 @@ #define CTX \ enc1->base.ctx +static void enc314_reset_fifo(struct stream_encoder *enc, bool reset) +{ + struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); + uint32_t reset_val = reset ? 1 : 0; + uint32_t is_symclk_on; + + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, reset_val); + REG_GET(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, &is_symclk_on); + + if (is_symclk_on) + REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, reset_val, 10, 5000); + else + udelay(10); +} static void enc314_enable_fifo(struct stream_encoder *enc) { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - /* TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON */ - REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000); REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1); - REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0); - REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 10, 5000); + + enc314_reset_fifo(enc, true); + enc314_reset_fifo(enc, false); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 1); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 588c1c71241f..a0741794db62 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -348,10 +348,8 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); odm_combine_factor = get_odm_config(pipe_ctx, NULL); - if (pipe_ctx->stream->signal == SIGNAL_TYPE_VIRTUAL) - return odm_combine_factor; - if (is_dp_128b_132b_signal(pipe_ctx)) { + *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_1; } else if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) || dc_is_dvi_signal(pipe_ctx->stream->signal)) { *k1_div = PIXEL_RATE_DIV_BY_1; @@ -359,7 +357,7 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig *k2_div = PIXEL_RATE_DIV_BY_2; else *k2_div = PIXEL_RATE_DIV_BY_4; - } else if (dc_is_dp_signal(pipe_ctx->stream->signal)) { + } else if (dc_is_dp_signal(pipe_ctx->stream->signal) || dc_is_virtual_signal(pipe_ctx->stream->signal)) { if (two_pix_per_container) { *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_2; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c index 5b6c2d94ec71..31feb4b0edee 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -66,9 +66,9 @@ static const struct hw_sequencer_funcs dcn314_funcs = { .prepare_bandwidth = dcn20_prepare_bandwidth, .optimize_bandwidth = dcn20_optimize_bandwidth, .update_bandwidth = dcn20_update_bandwidth, - .set_drr = dcn10_set_drr, + .set_drr = dcn31_set_drr, .get_position = dcn10_get_position, - .set_static_screen_control = dcn10_set_static_screen_control, + .set_static_screen_control = dcn31_set_static_screen_control, .setup_stereo = dcn10_setup_stereo, .set_avmute = dcn30_set_avmute, .log_hw_state = dcn10_log_hw_state, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c index 47eb162f1a75..41edbd64ea21 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c @@ -228,7 +228,7 @@ static struct timing_generator_funcs dcn314_tg_funcs = { .set_drr = optc31_set_drr, .get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal, .set_vtotal_min_max = optc1_set_vtotal_min_max, - .set_static_screen_control = optc1_set_static_screen_control, + .set_static_screen_control = optc31_set_static_screen_control, .program_stereo = optc1_program_stereo, .is_stereo_left_eye = optc1_is_stereo_left_eye, .tg_init = optc3_tg_init, @@ -237,11 +237,10 @@ static struct timing_generator_funcs dcn314_tg_funcs = { .clear_optc_underflow = optc1_clear_optc_underflow, .setup_global_swap_lock = NULL, .get_crc = optc1_get_crc, - .configure_crc = optc2_configure_crc, + .configure_crc = optc1_configure_crc, .set_dsc_config = optc3_set_dsc_config, .get_dsc_status = optc2_get_dsc_status, .set_dwb_source = NULL, - .set_odm_bypass = optc3_set_odm_bypass, .set_odm_combine = optc314_set_odm_combine, .get_optc_source = optc2_get_optc_source, .set_out_mux = optc3_set_out_mux, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 3b3e093e9447..f9ea1e86707f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -184,6 +184,9 @@ enum dcn31_clk_src_array_id { .reg_name[id] = BASE(reg ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define DCCG_SRII(reg_name, block, id)\ .block ## _ ## reg_name[id] = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name @@ -883,6 +886,7 @@ static const struct dc_plane_cap plane_cap = { static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = false, .enable_z9_disable_interface = true, + .psr_skip_crtc_disable = true, .disable_dmcu = true, .force_abm_enable = false, .timing_trace = false, diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c index 96a3d41febff..7887078c5f64 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c @@ -151,8 +151,6 @@ enum dcn31_clk_src_array_id { */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -185,6 +183,9 @@ enum dcn31_clk_src_array_id { .reg_name[id] = BASE(reg ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define DCCG_SRII(reg_name, block, id)\ .block ## _ ## reg_name[id] = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name @@ -1627,6 +1628,7 @@ static struct clock_source *dcn31_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } @@ -1647,7 +1649,7 @@ static int dcn315_populate_dml_pipes_from_context( const int max_usable_det = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes - DCN3_15_MIN_COMPBUF_SIZE_KB; DC_FP_START(); - dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + dcn31x_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); DC_FP_END(); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { @@ -1666,7 +1668,6 @@ static int dcn315_populate_dml_pipes_from_context( pipes[pipe_cnt].pipe.src.immediate_flip = true; pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; - pipes[pipe_cnt].pipe.src.gpuvm = true; pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; pipes[pipe_cnt].pipe.src.dcc_rate = 3; pipes[pipe_cnt].dout.dsc_input_bpc = 0; @@ -1707,7 +1708,9 @@ static int dcn315_populate_dml_pipes_from_context( dc->config.enable_4to1MPC = true; context->bw_ctx.dml.ip.det_buffer_size_kbytes = (max_usable_det / DCN3_15_CRB_SEGMENT_SIZE_KB / 4) * DCN3_15_CRB_SEGMENT_SIZE_KB; - } else if (!is_dual_plane(pipe->plane_state->format) && pipe->plane_state->src_rect.width <= 5120) { + } else if (!is_dual_plane(pipe->plane_state->format) + && pipe->plane_state->src_rect.width <= 5120 + && pipe->stream->timing.pix_clk_100hz < dcn_get_max_non_odm_pix_rate_100hz(&dc->dml.soc)) { /* Limit to 5k max to avoid forced pipe split when there is not enough detile for swath */ context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192; pipes[0].pipe.src.unbounded_req_mode = true; diff --git a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c index 2f643cdaf59f..b4d5076e124c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c @@ -142,8 +142,6 @@ enum dcn31_clk_src_array_id { */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) DCN_BASE__INST0_SEG ## seg #define BASE(seg) BASE_INNER(seg) @@ -176,6 +174,9 @@ enum dcn31_clk_src_array_id { .reg_name[id] = BASE(reg ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define DCCG_SRII(reg_name, block, id)\ .block ## _ ## reg_name[id] = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name @@ -1650,7 +1651,7 @@ static int dcn316_populate_dml_pipes_from_context( const int max_usable_det = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes - DCN3_16_MIN_COMPBUF_SIZE_KB; DC_FP_START(); - dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + dcn31x_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); DC_FP_END(); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { @@ -1669,7 +1670,6 @@ static int dcn316_populate_dml_pipes_from_context( pipes[pipe_cnt].pipe.src.immediate_flip = true; pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; - pipes[pipe_cnt].pipe.src.gpuvm = true; pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; pipes[pipe_cnt].pipe.src.dcc_rate = 3; pipes[pipe_cnt].dout.dsc_input_bpc = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c index e4daed44ef5f..e4472c6be6c3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c @@ -96,8 +96,10 @@ static void dccg32_set_pixel_rate_div( // Don't program 0xF into the register field. Not valid since // K1 / K2 field is only 1 / 2 bits wide - if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) { + BREAK_TO_DEBUGGER(); return; + } dccg32_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); if (k1 == cur_k1 && k2 == cur_k2) @@ -223,11 +225,7 @@ static void dccg32_set_dtbclk_dto( } else { REG_UPDATE_2(OTG_PIXEL_RATE_CNTL[params->otg_inst], DTBCLK_DTO_ENABLE[params->otg_inst], 0, - PIPE_DTO_SRC_SEL[params->otg_inst], 1); - if (params->is_hdmi) - REG_UPDATE(OTG_PIXEL_RATE_CNTL[params->otg_inst], - PIPE_DTO_SRC_SEL[params->otg_inst], 0); - + PIPE_DTO_SRC_SEL[params->otg_inst], params->is_hdmi ? 0 : 1); REG_WRITE(DTBCLK_DTO_MODULO[params->otg_inst], 0); REG_WRITE(DTBCLK_DTO_PHASE[params->otg_inst], 0); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c index a88a71460521..9501403a48a9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c @@ -72,6 +72,23 @@ static void dcn32_init_crb(struct hubbub *hubbub) REG_UPDATE(DCHUBBUB_DEBUG_CTRL_0, DET_DEPTH, 0x47F); } +void hubbub32_set_request_limit(struct hubbub *hubbub, int memory_channel_count, int words_per_channel) +{ + struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub); + + uint32_t request_limit = 3 * memory_channel_count * words_per_channel / 4; + + ASSERT((request_limit & (~0xFFF)) == 0); //field is only 24 bits long + ASSERT(request_limit > 0); //field is only 24 bits long + + if (request_limit > 0xFFF) + request_limit = 0xFFF; + + if (request_limit > 0) + REG_UPDATE(SDPIF_REQUEST_RATE_LIMIT, SDPIF_REQUEST_RATE_LIMIT, request_limit); +} + + void dcn32_program_det_size(struct hubbub *hubbub, int hubp_inst, unsigned int det_buffer_size_in_kbyte) { struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub); @@ -848,7 +865,7 @@ static void hubbub32_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, &s->sr_exit); REG_GET(DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_A, - DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_A, &s->dram_clk_chanage); + DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_A, &s->dram_clk_change); REG_GET(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_A, DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_A, &s->usr_retrain); @@ -868,7 +885,7 @@ static void hubbub32_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, &s->sr_exit); REG_GET(DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_B, - DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_B, &s->dram_clk_chanage); + DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_B, &s->dram_clk_change); REG_GET(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_B, DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_B, &s->usr_retrain); @@ -888,7 +905,7 @@ static void hubbub32_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, &s->sr_exit); REG_GET(DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_C, - DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_C, &s->dram_clk_chanage); + DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_C, &s->dram_clk_change); REG_GET(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_C, DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_C, &s->usr_retrain); @@ -908,7 +925,7 @@ static void hubbub32_wm_read_state(struct hubbub *hubbub, DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, &s->sr_exit); REG_GET(DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_D, - DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_D, &s->dram_clk_chanage); + DCHUBBUB_ARB_UCLK_PSTATE_CHANGE_WATERMARK_D, &s->dram_clk_change); REG_GET(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_D, DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_D, &s->usr_retrain); @@ -949,6 +966,7 @@ static const struct hubbub_funcs hubbub32_funcs = { .init_crb = dcn32_init_crb, .hubbub_read_state = hubbub2_read_state, .force_usr_retraining_allow = hubbub32_force_usr_retraining_allow, + .set_request_limit = hubbub32_set_request_limit }; void hubbub32_construct(struct dcn20_hubbub *hubbub2, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h index cda94e0e31bf..786f9ce07f92 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.h @@ -82,7 +82,8 @@ SR(DCN_VM_FAULT_ADDR_MSB),\ SR(DCN_VM_FAULT_ADDR_LSB),\ SR(DCN_VM_FAULT_CNTL),\ - SR(DCN_VM_FAULT_STATUS) + SR(DCN_VM_FAULT_STATUS),\ + SR(SDPIF_REQUEST_RATE_LIMIT) #define HUBBUB_MASK_SH_LIST_DCN32(mask_sh)\ HUBBUB_SF(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, mask_sh), \ @@ -159,7 +160,8 @@ HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_VMID, mask_sh), \ HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_TABLE_LEVEL, mask_sh), \ HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_PIPE, mask_sh), \ - HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh) + HUBBUB_SF(DCN_VM_FAULT_STATUS, DCN_VM_ERROR_INTERRUPT_STATUS, mask_sh),\ + HUBBUB_SF(SDPIF_REQUEST_RATE_LIMIT, SDPIF_REQUEST_RATE_LIMIT, mask_sh) bool hubbub32_program_urgent_watermarks( struct hubbub *hubbub, @@ -200,4 +202,6 @@ void hubbub32_construct(struct dcn20_hubbub *hubbub2, int pixel_chunk_size_kb, int config_return_buffer_size_kb); +void hubbub32_set_request_limit(struct hubbub *hubbub, int umc_count, int words_per_umc); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 5e0018efe055..b8767be1e4c5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -227,8 +227,13 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + /* If PSR is supported on an eDP panel that's connected, but that panel is + * not in PSR at the time of trying to enter MALL SS, we have to include it + * in the static screen CAB calculation + */ if (!pipe->stream || !pipe->plane_state || - pipe->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED || + (pipe->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED && + pipe->stream->link->psr_settings.psr_allow_active) || pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) continue; @@ -257,11 +262,11 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) * ((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height); - /* For DCC: - * meta_num_mblk = CEILING(full_mblk_width_ub_l*full_mblk_height_ub_l*Bpe/256/mblk_bytes, 1) + /*For DCC: + * meta_num_mblk = CEILING(meta_pitch*full_vp_height*Bpe/256/mblk_bytes, 1) */ if (pipe->plane_state->dcc.enable) - num_mblks += (mall_alloc_width_blk_aligned * mall_alloc_width_blk_aligned * bytes_per_pixel + + num_mblks += (pipe->plane_state->dcc.meta_pitch * pipe->plane_res.scl_data.viewport.height * bytes_per_pixel + (256 * DCN3_2_MALL_MBLK_SIZE_BYTES) - 1) / (256 * DCN3_2_MALL_MBLK_SIZE_BYTES); bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES; @@ -283,8 +288,7 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c using the max for calculation */ if (hubp->curs_attr.width > 0) { - // Round cursor width to next multiple of 64 - cursor_size = (((hubp->curs_attr.width + 63) / 64) * 64) * hubp->curs_attr.height; + cursor_size = hubp->curs_attr.pitch * hubp->curs_attr.height; switch (pipe->stream->cursor_attributes.color_format) { case CURSOR_MODE_MONO: @@ -309,11 +313,11 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c cursor_size > 16384) { /* cursor_num_mblk = CEILING(num_cursors*cursor_width*cursor_width*cursor_Bpe/mblk_bytes, 1) */ - cache_lines_used += (((hubp->curs_attr.width * hubp->curs_attr.height * cursor_bpp + - DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / DCN3_2_MALL_MBLK_SIZE_BYTES) * - DCN3_2_MALL_MBLK_SIZE_BYTES) / dc->caps.cache_line_size + 2; + cache_lines_used += (((cursor_size + DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / + DCN3_2_MALL_MBLK_SIZE_BYTES) * DCN3_2_MALL_MBLK_SIZE_BYTES) / + dc->caps.cache_line_size + 2; + break; } - break; } } @@ -699,11 +703,7 @@ void dcn32_subvp_update_force_pstate(struct dc *dc, struct dc_state *context) for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - // For SubVP + DRR, also force disallow on the DRR pipe - // (We will force allow in the DMUB sequence -- some DRR timings by default won't allow P-State so we have - // to force once the vblank is stretched). - if (pipe->stream && pipe->plane_state && (pipe->stream->mall_stream_config.type == SUBVP_MAIN || - (pipe->stream->mall_stream_config.type == SUBVP_NONE && pipe->stream->ignore_msa_timing_param))) { + if (pipe->stream && pipe->plane_state && (pipe->stream->mall_stream_config.type == SUBVP_MAIN)) { struct hubp *hubp = pipe->plane_res.hubp; if (hubp && hubp->funcs->hubp_update_force_pstate_disallow) @@ -727,10 +727,7 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context) struct hubp *hubp = pipe->plane_res.hubp; if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) { - //Round cursor width up to next multiple of 64 - int cursor_width = ((hubp->curs_attr.width + 63) / 64) * 64; - int cursor_height = hubp->curs_attr.height; - int cursor_size = cursor_width * cursor_height; + int cursor_size = hubp->curs_attr.pitch * hubp->curs_attr.height; switch (hubp->curs_attr.color_format) { case CURSOR_MODE_MONO: @@ -784,6 +781,10 @@ void dcn32_program_mall_pipe_config(struct dc *dc, struct dc_state *context) if (hws && hws->funcs.update_mall_sel) hws->funcs.update_mall_sel(dc, context); + //update subvp force pstate + if (hws && hws->funcs.subvp_update_force_pstate) + dc->hwseq->funcs.subvp_update_force_pstate(dc, context); + // Program FORCE_ONE_ROW_FOR_FRAME and CURSOR_REQ_MODE for main subvp pipes for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; @@ -984,6 +985,9 @@ void dcn32_init_hw(struct dc *dc) if (dc->res_pool->hubbub->funcs->init_crb) dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub); + if (dc->res_pool->hubbub->funcs->set_request_limit && dc->config.sdpif_request_limit_words_per_umc > 0) + dc->res_pool->hubbub->funcs->set_request_limit(dc->res_pool->hubbub, dc->ctx->dc_bios->vram_info.num_chans, dc->config.sdpif_request_limit_words_per_umc); + // Get DMCUB capabilities if (dc->ctx->dmub_srv) { dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub); @@ -1171,10 +1175,8 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); odm_combine_factor = get_odm_config(pipe_ctx, NULL); - if (pipe_ctx->stream->signal == SIGNAL_TYPE_VIRTUAL) - return odm_combine_factor; - if (is_dp_128b_132b_signal(pipe_ctx)) { + *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_1; } else if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) || dc_is_dvi_signal(pipe_ctx->stream->signal)) { *k1_div = PIXEL_RATE_DIV_BY_1; @@ -1367,6 +1369,33 @@ void dcn32_update_phantom_vp_position(struct dc *dc, } } +/* Treat the phantom pipe as if it needs to be fully enabled. + * If the pipe was previously in use but not phantom, it would + * have been disabled earlier in the sequence so we need to run + * the full enable sequence. + */ +void dcn32_apply_update_flags_for_phantom(struct pipe_ctx *phantom_pipe) +{ + phantom_pipe->update_flags.raw = 0; + if (phantom_pipe->stream && phantom_pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + if (phantom_pipe->stream && phantom_pipe->plane_state) { + phantom_pipe->update_flags.bits.enable = 1; + phantom_pipe->update_flags.bits.mpcc = 1; + phantom_pipe->update_flags.bits.dppclk = 1; + phantom_pipe->update_flags.bits.hubp_interdependent = 1; + phantom_pipe->update_flags.bits.hubp_rq_dlg_ttu = 1; + phantom_pipe->update_flags.bits.gamut_remap = 1; + phantom_pipe->update_flags.bits.scaler = 1; + phantom_pipe->update_flags.bits.viewport = 1; + phantom_pipe->update_flags.bits.det_size = 1; + if (!phantom_pipe->top_pipe && !phantom_pipe->prev_odm_pipe) { + phantom_pipe->update_flags.bits.odm = 1; + phantom_pipe->update_flags.bits.global_sync = 1; + } + } + } +} + bool dcn32_dsc_pg_status( struct dce_hwseq *hws, unsigned int dsc_inst) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h index ac3657a5b9ea..7de36529cf99 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h @@ -92,6 +92,8 @@ void dcn32_update_phantom_vp_position(struct dc *dc, struct dc_state *context, struct pipe_ctx *phantom_pipe); +void dcn32_apply_update_flags_for_phantom(struct pipe_ctx *phantom_pipe); + bool dcn32_dsc_pg_status( struct dce_hwseq *hws, unsigned int dsc_inst); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index 45a949ba6f3f..dc4649458567 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -110,6 +110,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .update_visual_confirm_color = dcn20_update_visual_confirm_color, .update_phantom_vp_position = dcn32_update_phantom_vp_position, .update_dsc_pg = dcn32_update_dsc_pg, + .apply_update_flags_for_phantom = dcn32_apply_update_flags_for_phantom, }; static const struct hwseq_private_funcs dcn32_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c index 2b33eeb213e2..2ee798965bc2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c @@ -167,6 +167,13 @@ static void optc32_phantom_crtc_post_enable(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); } +static void optc32_disable_phantom_otg(struct timing_generator *optc) +{ + struct optc *optc1 = DCN10TG_FROM_TG(optc); + + REG_UPDATE(OTG_CONTROL, OTG_MASTER_EN, 0); +} + static void optc32_set_odm_bypass(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing) { @@ -260,6 +267,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = { .enable_crtc = optc32_enable_crtc, .disable_crtc = optc32_disable_crtc, .phantom_crtc_post_enable = optc32_phantom_crtc_post_enable, + .disable_phantom_crtc = optc32_disable_phantom_otg, /* used by enable_timing_synchronization. Not need for FPGA */ .is_counter_moving = optc1_is_counter_moving, .get_position = optc1_get_position, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 4ba9a8662185..e4dbc8353ea3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -106,8 +106,6 @@ enum dcn32_clk_src_array_id { */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) ctx->dcn_reg_offsets[seg] #define BASE(seg) BASE_INNER(seg) @@ -167,6 +165,9 @@ enum dcn32_clk_src_array_id { REG_STRUCT.reg_name[id] = BASE(reg ## block ## id ## _ ## temp_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## temp_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define DCCG_SRII(reg_name, block, id)\ REG_STRUCT.block ## _ ## reg_name[id] = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name @@ -722,8 +723,9 @@ static const struct dc_debug_options debug_defaults_drv = { /* Must match enable_single_display_2to1_odm_policy to support dynamic ODM transitions*/ .enable_double_buffered_dsc_pg_support = true, .enable_dp_dig_pixel_rate_div_policy = 1, - .allow_sw_cursor_fallback = false, + .allow_sw_cursor_fallback = false, // Linux can't do SW cursor "fallback" .alloc_extra_way_for_cursor = true, + .min_prefetch_in_strobe_ns = 60000, // 60us }; static const struct dc_debug_options debug_defaults_diags = { @@ -829,6 +831,7 @@ static struct clock_source *dcn32_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } @@ -1678,7 +1681,7 @@ static void dcn32_enable_phantom_plane(struct dc *dc, /* Shadow pipe has small viewport. */ phantom_plane->clip_rect.y = 0; - phantom_plane->clip_rect.height = phantom_stream->timing.v_addressable; + phantom_plane->clip_rect.height = phantom_stream->src.height; phantom_plane->is_phantom = true; @@ -1718,8 +1721,29 @@ static struct dc_stream_state *dcn32_enable_phantom_stream(struct dc *dc, return phantom_stream; } +void dcn32_retain_phantom_pipes(struct dc *dc, struct dc_state *context) +{ + int i; + struct dc_plane_state *phantom_plane = NULL; + struct dc_stream_state *phantom_stream = NULL; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->top_pipe && !pipe->prev_odm_pipe && + pipe->plane_state && pipe->stream && + pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + phantom_plane = pipe->plane_state; + phantom_stream = pipe->stream; + + dc_plane_state_retain(phantom_plane); + dc_stream_retain(phantom_stream); + } + } +} + // return true if removed piped from ctx, false otherwise -bool dcn32_remove_phantom_pipes(struct dc *dc, struct dc_state *context) +bool dcn32_remove_phantom_pipes(struct dc *dc, struct dc_state *context, bool fast_update) { int i; bool removed_pipe = false; @@ -1746,14 +1770,23 @@ bool dcn32_remove_phantom_pipes(struct dc *dc, struct dc_state *context) removed_pipe = true; } - // Clear all phantom stream info - if (pipe->stream) { - pipe->stream->mall_stream_config.type = SUBVP_NONE; - pipe->stream->mall_stream_config.paired_stream = NULL; - } + /* For non-full updates, a shallow copy of the current state + * is created. In this case we don't want to erase the current + * state (there can be 2 HIRQL threads, one in flip, and one in + * checkMPO) that can cause a race condition. + * + * This is just a workaround, needs a proper fix. + */ + if (!fast_update) { + // Clear all phantom stream info + if (pipe->stream) { + pipe->stream->mall_stream_config.type = SUBVP_NONE; + pipe->stream->mall_stream_config.paired_stream = NULL; + } - if (pipe->plane_state) { - pipe->plane_state->is_phantom = false; + if (pipe->plane_state) { + pipe->plane_state->is_phantom = false; + } } } return removed_pipe; @@ -1900,7 +1933,7 @@ int dcn32_populate_dml_pipes_from_context( pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; if (context->stream_count == 1 && - context->stream_status[0].plane_count <= 1 && + context->stream_status[0].plane_count == 1 && !dc_is_hdmi_signal(res_ctx->pipe_ctx[i].stream->signal) && is_h_timing_divisible_by_2(res_ctx->pipe_ctx[i].stream) && pipe->stream->timing.pix_clk_100hz * 100 > DCN3_2_VMIN_DISPCLK_HZ && @@ -1926,23 +1959,28 @@ int dcn32_populate_dml_pipes_from_context( pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19; - switch (pipe->stream->mall_stream_config.type) { - case SUBVP_MAIN: - pipes[pipe_cnt].pipe.src.use_mall_for_pstate_change = dm_use_mall_pstate_change_sub_viewport; - subvp_in_use = true; - break; - case SUBVP_PHANTOM: - pipes[pipe_cnt].pipe.src.use_mall_for_pstate_change = dm_use_mall_pstate_change_phantom_pipe; - pipes[pipe_cnt].pipe.src.use_mall_for_static_screen = dm_use_mall_static_screen_disable; - // Disallow unbounded req for SubVP according to DCHUB programming guide - pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; - break; - case SUBVP_NONE: - pipes[pipe_cnt].pipe.src.use_mall_for_pstate_change = dm_use_mall_pstate_change_disable; - pipes[pipe_cnt].pipe.src.use_mall_for_static_screen = dm_use_mall_static_screen_disable; - break; - default: - break; + /* Only populate DML input with subvp info for full updates. + * This is just a workaround -- needs a proper fix. + */ + if (!fast_validate) { + switch (pipe->stream->mall_stream_config.type) { + case SUBVP_MAIN: + pipes[pipe_cnt].pipe.src.use_mall_for_pstate_change = dm_use_mall_pstate_change_sub_viewport; + subvp_in_use = true; + break; + case SUBVP_PHANTOM: + pipes[pipe_cnt].pipe.src.use_mall_for_pstate_change = dm_use_mall_pstate_change_phantom_pipe; + pipes[pipe_cnt].pipe.src.use_mall_for_static_screen = dm_use_mall_static_screen_disable; + // Disallow unbounded req for SubVP according to DCHUB programming guide + pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; + break; + case SUBVP_NONE: + pipes[pipe_cnt].pipe.src.use_mall_for_pstate_change = dm_use_mall_pstate_change_disable; + pipes[pipe_cnt].pipe.src.use_mall_for_static_screen = dm_use_mall_static_screen_disable; + break; + default: + break; + } } pipes[pipe_cnt].dout.dsc_input_bpc = 0; @@ -2030,6 +2068,9 @@ static struct resource_funcs dcn32_res_pool_funcs = { .update_soc_for_wm_a = dcn30_update_soc_for_wm_a, .add_phantom_pipes = dcn32_add_phantom_pipes, .remove_phantom_pipes = dcn32_remove_phantom_pipes, + .retain_phantom_pipes = dcn32_retain_phantom_pipes, + .save_mall_state = dcn32_save_mall_state, + .restore_mall_state = dcn32_restore_mall_state, }; @@ -2116,10 +2157,12 @@ static bool dcn32_resource_construct( dc->caps.cache_num_ways = 16; dc->caps.max_cab_allocation_bytes = 67108864; // 64MB = 1024 * 1024 * 64 dc->caps.subvp_fw_processing_delay_us = 15; + dc->caps.subvp_drr_max_vblank_margin_us = 40; dc->caps.subvp_prefetch_end_to_mall_start_us = 15; dc->caps.subvp_swath_height_margin_lines = 16; dc->caps.subvp_pstate_allow_width_us = 20; dc->caps.subvp_vertical_int_margin_us = 30; + dc->caps.subvp_drr_vblank_start_margin_us = 100; // 100us margin dc->caps.max_slave_planes = 2; dc->caps.max_slave_yuv_planes = 2; @@ -2411,6 +2454,9 @@ static bool dcn32_resource_construct( pool->base.oem_device = NULL; } + if (ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev) && (dc->config.sdpif_request_limit_words_per_umc == 0)) + dc->config.sdpif_request_limit_words_per_umc = 16; + DC_FP_END(); return true; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index f76120e67c16..13fbc574910b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -45,17 +45,6 @@ extern struct _vcs_dpi_ip_params_st dcn3_2_ip; extern struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc; -/* Temp struct used to save and restore MALL config - * during validation. - * - * TODO: Move MALL config into dc_state instead of stream struct - * to avoid needing to save/restore. - */ -struct mall_temp_config { - struct mall_stream_config mall_stream_config[MAX_PIPES]; - bool is_phantom_plane[MAX_PIPES]; -}; - struct dcn32_resource_pool { struct resource_pool base; }; @@ -81,6 +70,9 @@ bool dcn32_release_post_bldn_3dlut( struct dc_transfer_func **shaper); bool dcn32_remove_phantom_pipes(struct dc *dc, + struct dc_state *context, bool fast_update); + +void dcn32_retain_phantom_pipes(struct dc *dc, struct dc_state *context); void dcn32_add_phantom_pipes(struct dc *dc, @@ -1244,7 +1236,8 @@ void dcn32_restore_mall_state(struct dc *dc, SR(DCHUBBUB_ARB_FCLK_PSTATE_CHANGE_WATERMARK_C), \ SR(DCHUBBUB_ARB_FCLK_PSTATE_CHANGE_WATERMARK_D), \ SR(DCN_VM_FAULT_ADDR_MSB), SR(DCN_VM_FAULT_ADDR_LSB), \ - SR(DCN_VM_FAULT_CNTL), SR(DCN_VM_FAULT_STATUS) \ + SR(DCN_VM_FAULT_CNTL), SR(DCN_VM_FAULT_STATUS), \ + SR(SDPIF_REQUEST_RATE_LIMIT) \ ) /* DCCG */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index b03a7814e96d..783935c4e664 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -97,21 +97,21 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat * FLOOR(vp_x_start, blk_width) */ full_vp_width_blk_aligned = ((pipe->plane_res.scl_data.viewport.x + - pipe->plane_res.scl_data.viewport.width + mblk_width - 1) / mblk_width * mblk_width) + + pipe->plane_res.scl_data.viewport.width + mblk_width - 1) / mblk_width * mblk_width) - (pipe->plane_res.scl_data.viewport.x / mblk_width * mblk_width); /* full_vp_height_blk_aligned = FLOOR(vp_y_start + full_vp_height + blk_height - 1, blk_height) - * FLOOR(vp_y_start, blk_height) */ full_vp_height_blk_aligned = ((pipe->plane_res.scl_data.viewport.y + - full_vp_height + mblk_height - 1) / mblk_height * mblk_height) + + full_vp_height + mblk_height - 1) / mblk_height * mblk_height) - (pipe->plane_res.scl_data.viewport.y / mblk_height * mblk_height); /* mall_alloc_width_blk_aligned_l/c = full_vp_width_blk_aligned_l/c */ mall_alloc_width_blk_aligned = full_vp_width_blk_aligned; /* mall_alloc_height_blk_aligned_l/c = CEILING(sub_vp_height_l/c - 1, blk_height_l/c) + blk_height_l/c */ - mall_alloc_height_blk_aligned = (pipe->stream->timing.v_addressable - 1 + mblk_height - 1) / + mall_alloc_height_blk_aligned = (pipe->plane_res.scl_data.viewport.height - 1 + mblk_height - 1) / mblk_height * mblk_height + mblk_height; /* full_mblk_width_ub_l/c = mall_alloc_width_blk_aligned_l/c; @@ -121,14 +121,19 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat */ num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) * ((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height); + + /*For DCC: + * meta_num_mblk = CEILING(meta_pitch*full_vp_height*Bpe/256/mblk_bytes, 1) + */ + if (pipe->plane_state->dcc.enable) + num_mblks += (pipe->plane_state->dcc.meta_pitch * pipe->plane_res.scl_data.viewport.height * bytes_per_pixel + + (256 * DCN3_2_MALL_MBLK_SIZE_BYTES) - 1) / (256 * DCN3_2_MALL_MBLK_SIZE_BYTES); + bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES; // cache lines used is total bytes / cache_line size. Add +2 for worst case alignment // (MALL is 64-byte aligned) cache_lines_per_plane = bytes_in_mall / dc->caps.cache_line_size + 2; - /* For DCC divide by 256 */ - if (pipe->plane_state->dcc.enable) - cache_lines_per_plane = cache_lines_per_plane + (cache_lines_per_plane / 256) + 1; cache_lines_used += cache_lines_per_plane; } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index 61087f2385a9..d1f36df03c2e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -109,8 +109,6 @@ enum dcn321_clk_src_array_id { */ /* DCN */ -/* TODO awful hack. fixup dcn20_dwb.h */ -#undef BASE_INNER #define BASE_INNER(seg) ctx->dcn_reg_offsets[seg] #define BASE(seg) BASE_INNER(seg) @@ -174,6 +172,9 @@ enum dcn321_clk_src_array_id { REG_STRUCT.block ## _ ## reg_name[id] = BASE(reg ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ reg ## block ## id ## _ ## reg_name +#define SF_DWB2(reg_name, block, id, field_name, post_fix) \ + .field_name = reg_name ## __ ## field_name ## post_fix + #define VUPDATE_SRII(reg_name, block, id)\ REG_STRUCT.reg_name[id] = BASE(reg ## reg_name ## _ ## block ## id ## _BASE_IDX) + \ reg ## reg_name ## _ ## block ## id @@ -720,8 +721,9 @@ static const struct dc_debug_options debug_defaults_drv = { /*must match enable_single_display_2to1_odm_policy to support dynamic ODM transitions*/ .enable_double_buffered_dsc_pg_support = true, .enable_dp_dig_pixel_rate_div_policy = 1, - .allow_sw_cursor_fallback = false, + .allow_sw_cursor_fallback = false, // Linux can't do SW cursor "fallback" .alloc_extra_way_for_cursor = true, + .min_prefetch_in_strobe_ns = 60000, // 60us }; static const struct dc_debug_options debug_defaults_diags = { @@ -741,7 +743,7 @@ static const struct dc_debug_options debug_defaults_diags = { .dmub_command_table = true, .enable_tri_buf = true, .use_max_lb = true, - .force_disable_subvp = true + .force_disable_subvp = true, }; @@ -828,6 +830,7 @@ static struct clock_source *dcn321_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } @@ -1618,6 +1621,9 @@ static struct resource_funcs dcn321_res_pool_funcs = { .update_soc_for_wm_a = dcn30_update_soc_for_wm_a, .add_phantom_pipes = dcn32_add_phantom_pipes, .remove_phantom_pipes = dcn32_remove_phantom_pipes, + .retain_phantom_pipes = dcn32_retain_phantom_pipes, + .save_mall_state = dcn32_save_mall_state, + .restore_mall_state = dcn32_restore_mall_state, }; @@ -1703,10 +1709,12 @@ static bool dcn321_resource_construct( dc->caps.cache_num_ways = 16; dc->caps.max_cab_allocation_bytes = 33554432; // 32MB = 1024 * 1024 * 32 dc->caps.subvp_fw_processing_delay_us = 15; + dc->caps.subvp_drr_max_vblank_margin_us = 40; dc->caps.subvp_prefetch_end_to_mall_start_us = 15; dc->caps.subvp_swath_height_margin_lines = 16; dc->caps.subvp_pstate_allow_width_us = 20; dc->caps.subvp_vertical_int_margin_us = 30; + dc->caps.subvp_drr_vblank_start_margin_us = 100; // 100us margin dc->caps.max_slave_planes = 1; dc->caps.max_slave_yuv_planes = 1; dc->caps.max_slave_rgb_planes = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h index e3e5c39895a3..af1c50ed905a 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h +++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h @@ -116,6 +116,11 @@ bool dm_helpers_dp_mst_start_top_mgr( bool dm_helpers_dp_mst_stop_top_mgr( struct dc_context *ctx, struct dc_link *link); + +void dm_helpers_dp_mst_update_branch_bandwidth( + struct dc_context *ctx, + struct dc_link *link); + /** * OS specific aux read callback. */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 602e885ed52c..c26da3bb2892 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -565,7 +565,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .dppclk_mhz = 847.06, .phyclk_mhz = 810.0, .socclk_mhz = 953.0, - .dscclk_mhz = 489.0, + .dscclk_mhz = 300.0, .dram_speed_mts = 2400.0, }, { @@ -576,7 +576,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .dppclk_mhz = 960.00, .phyclk_mhz = 810.0, .socclk_mhz = 278.0, - .dscclk_mhz = 287.67, + .dscclk_mhz = 342.86, .dram_speed_mts = 2666.0, }, { @@ -587,7 +587,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .dppclk_mhz = 1028.57, .phyclk_mhz = 810.0, .socclk_mhz = 715.0, - .dscclk_mhz = 318.334, + .dscclk_mhz = 369.23, .dram_speed_mts = 3200.0, }, { @@ -949,6 +949,7 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc int plane_count; int i; unsigned int optimized_min_dst_y_next_start_us; + bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > 1000.0; plane_count = 0; optimized_min_dst_y_next_start_us = 0; @@ -963,6 +964,8 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc * 2. single eDP, on link 0, 1 plane and stutter period > 5ms * Z10 only cases: * 1. single eDP, on link 0, 1 plane and stutter period >= 5ms + * Z8 cases: + * 1. stutter period sufficient * Zstate not allowed cases: * 1. Everything else */ @@ -990,11 +993,14 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) return DCN_ZSTATE_SUPPORT_ALLOW; else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr) - return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; + return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; else - return DCN_ZSTATE_SUPPORT_DISALLOW; - } else + return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY : DCN_ZSTATE_SUPPORT_DISALLOW; + } else if (allow_z8) { + return DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY; + } else { return DCN_ZSTATE_SUPPORT_DISALLOW; + } } void dcn20_calculate_dlg_params( @@ -1296,6 +1302,8 @@ int dcn20_populate_dml_pipes_from_context( case SIGNAL_TYPE_DISPLAY_PORT_MST: case SIGNAL_TYPE_DISPLAY_PORT: pipes[pipe_cnt].dout.output_type = dm_dp; + if (is_dp_128b_132b_signal(&res_ctx->pipe_ctx[i])) + pipes[pipe_cnt].dout.output_type = dm_dp2p0; break; case SIGNAL_TYPE_EDP: pipes[pipe_cnt].dout.output_type = dm_edp; 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 479e2c1a1301..379729b02847 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 @@ -4851,7 +4851,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->HTotal[k] / v->PixelClock[k], - v->UrgentLatency, + v->UrgLatency[i], v->CursorBufferSize, v->CursorWidth[k][0], v->CursorBPP[k][0], diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index 7dd0845d1bd9..b37d14369a62 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -483,7 +483,7 @@ void dcn31_calculate_wm_and_dlg_fp( int pipe_cnt, int vlevel) { - int i, pipe_idx, active_dpp_count = 0; + int i, pipe_idx, active_hubp_count = 0; double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; dc_assert_fp_enabled(); @@ -529,7 +529,7 @@ void dcn31_calculate_wm_and_dlg_fp( continue; if (context->res_ctx.pipe_ctx[i].plane_state) - active_dpp_count++; + active_hubp_count++; pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); @@ -547,9 +547,22 @@ void dcn31_calculate_wm_and_dlg_fp( } dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); - /* For 31x apu pstate change is only supported if possible in vactive or if there are no active dpps */ + /* For 31x apu pstate change is only supported if possible in vactive*/ context->bw_ctx.bw.dcn.clk.p_state_change_support = - context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_vactive || !active_dpp_count; + context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_vactive; + /* If DCN isn't making memory requests we can allow pstate change and lower clocks */ + if (!active_hubp_count) { + context->bw_ctx.bw.dcn.clk.socclk_khz = 0; + context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; + context->bw_ctx.bw.dcn.clk.dcfclk_khz = 0; + context->bw_ctx.bw.dcn.clk.dcfclk_deep_sleep_khz = 0; + context->bw_ctx.bw.dcn.clk.dramclk_khz = 0; + context->bw_ctx.bw.dcn.clk.fclk_khz = 0; + context->bw_ctx.bw.dcn.clk.p_state_change_support = true; + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (context->res_ctx.pipe_ctx[i].stream) + context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = 0; + } } void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) @@ -797,3 +810,8 @@ void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param else dml_init_instance(&dc->dml, &dcn3_16_soc, &dcn3_16_ip, DML_PROJECT_DCN31_FPGA); } + +int dcn_get_max_non_odm_pix_rate_100hz(struct _vcs_dpi_soc_bounding_box_st *soc) +{ + return soc->clock_limits[0].dispclk_mhz * 10000.0 / (1.0 + soc->dcn_downspread_percent / 100.0); +} diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h index fd58b2561ec9..687d3522cc33 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h @@ -46,5 +46,10 @@ void dcn31_calculate_wm_and_dlg_fp( void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); +int dcn_get_max_non_odm_pix_rate_100hz(struct _vcs_dpi_soc_bounding_box_st *soc); +int dcn31x_populate_dml_pipes_from_context(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate); #endif /* __DCN31_FPU_H__*/ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index 45ab0ce50860..ec351c8418cb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -1056,14 +1056,12 @@ static bool CalculatePrefetchSchedule( prefetch_bw_pr = dml_min(1, myPipe->VRatio) * prefetch_bw_pr; max_Tsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime; prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC; - prefetch_bw_oto = dml_max(bytes_pp * myPipe->PixelClock / myPipe->DPPPerPlane, prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime)); prefetch_bw_oto = dml_max(prefetch_bw_pr, prefetch_sw_bytes / max_Tsw); min_Lsw = dml_max(1, dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / max_vratio_pre); Lsw_oto = dml_ceil(4 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1) / 4; Tsw_oto = Lsw_oto * LineTime; - prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC) / Tsw_oto; #ifdef __DML_VBA_DEBUG__ dml_print("DML: HTotal: %d\n", myPipe->HTotal); @@ -5084,7 +5082,7 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->HTotal[k] / v->PixelClock[k], - v->UrgentLatency, + v->UrgLatency[i], v->CursorBufferSize, v->CursorWidth[k][0], v->CursorBPP[k][0], @@ -5362,6 +5360,58 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->ModeSupport[i][j] = true; } else { v->ModeSupport[i][j] = false; +#ifdef __DML_VBA_DEBUG__ + if (v->ScaleRatioAndTapsSupport == false) + dml_print("DML SUPPORT: ScaleRatioAndTapsSupport failed"); + if (v->SourceFormatPixelAndScanSupport == false) + dml_print("DML SUPPORT: SourceFormatPixelAndScanSupport failed"); + if (v->ViewportSizeSupport[i][j] == false) + dml_print("DML SUPPORT: ViewportSizeSupport failed"); + if (v->LinkCapacitySupport[i] == false) + dml_print("DML SUPPORT: LinkCapacitySupport failed"); + if (v->ODMCombine4To1SupportCheckOK[i] == false) + dml_print("DML SUPPORT: DSC422NativeNotSupported failed"); + if (v->NotEnoughDSCUnits[i] == true) + dml_print("DML SUPPORT: NotEnoughDSCUnits"); + if (v->DTBCLKRequiredMoreThanSupported[i] == true) + dml_print("DML SUPPORT: DTBCLKRequiredMoreThanSupported"); + if (v->ROBSupport[i][j] == false) + dml_print("DML SUPPORT: ROBSupport failed"); + if (v->DISPCLK_DPPCLK_Support[i][j] == false) + dml_print("DML SUPPORT: DISPCLK_DPPCLK_Support failed"); + if (v->TotalAvailablePipesSupport[i][j] == false) + dml_print("DML SUPPORT: DSC422NativeNotSupported failed"); + if (EnoughWritebackUnits == false) + dml_print("DML SUPPORT: DSC422NativeNotSupported failed"); + if (v->WritebackLatencySupport == false) + dml_print("DML SUPPORT: WritebackLatencySupport failed"); + if (v->WritebackScaleRatioAndTapsSupport == false) + dml_print("DML SUPPORT: DSC422NativeNotSupported "); + if (v->CursorSupport == false) + dml_print("DML SUPPORT: DSC422NativeNotSupported failed"); + if (v->PitchSupport == false) + dml_print("DML SUPPORT: PitchSupport failed"); + if (ViewportExceedsSurface == true) + dml_print("DML SUPPORT: ViewportExceedsSurface failed"); + if (v->PrefetchSupported[i][j] == false) + dml_print("DML SUPPORT: PrefetchSupported failed"); + if (v->DynamicMetadataSupported[i][j] == false) + dml_print("DML SUPPORT: DSC422NativeNotSupported failed"); + if (v->TotalVerticalActiveBandwidthSupport[i][j] == false) + dml_print("DML SUPPORT: TotalVerticalActiveBandwidthSupport failed"); + if (v->VRatioInPrefetchSupported[i][j] == false) + dml_print("DML SUPPORT: VRatioInPrefetchSupported failed"); + if (v->PTEBufferSizeNotExceeded[i][j] == false) + dml_print("DML SUPPORT: PTEBufferSizeNotExceeded failed"); + if (v->NonsupportedDSCInputBPC == true) + dml_print("DML SUPPORT: NonsupportedDSCInputBPC failed"); + if (!((v->HostVMEnable == false + && v->ImmediateFlipRequirement[0] != dm_immediate_flip_required) + || v->ImmediateFlipSupportedForState[i][j] == true)) + dml_print("DML SUPPORT: ImmediateFlipRequirement failed"); + if (FMTBufferExceeded == true) + dml_print("DML SUPPORT: FMTBufferExceeded failed"); +#endif } } } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index cf420ad2b8dc..6a1cf6adea77 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -29,6 +29,7 @@ #include "dcn31/dcn31_hubbub.h" #include "dcn314_fpu.h" #include "dml/dcn20/dcn20_fpu.h" +#include "dml/dcn31/dcn31_fpu.h" #include "dml/display_mode_vba.h" struct _vcs_dpi_ip_params_st dcn3_14_ip = { @@ -146,10 +147,10 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 9.0, - .sr_enter_plus_exit_time_us = 11.0, - .sr_exit_z8_time_us = 442.0, - .sr_enter_plus_exit_z8_time_us = 560.0, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, + .sr_exit_z8_time_us = 280.0, + .sr_enter_plus_exit_z8_time_us = 350.0, .writeback_latency_us = 12.0, .dram_channel_width_bytes = 4, .round_trip_ping_latency_dcfclk_cycles = 106, @@ -264,11 +265,8 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p dc->dml.soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2; } - if ((int)(dcn3_14_soc.dram_clock_change_latency_us * 1000) - != dc->debug.dram_clock_change_latency_ns - && dc->debug.dram_clock_change_latency_ns) { - dcn3_14_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000; - } + dcn20_patch_bounding_box(dc, &dcn3_14_soc); + if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN314); else @@ -291,7 +289,7 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c dc_assert_fp_enabled(); - dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); + dcn31x_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { struct dc_crtc_timing *timing; @@ -318,8 +316,6 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c pipes[pipe_cnt].pipe.src.immediate_flip = true; pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; - pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active; - pipes[pipe_cnt].pipe.src.gpuvm = true; pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0; pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0; pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index 53e3e7364ec6..950669f2c10d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -1078,14 +1078,12 @@ static bool CalculatePrefetchSchedule( prefetch_bw_pr = dml_min(1, myPipe->VRatio) * prefetch_bw_pr; max_Tsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime; prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC; - prefetch_bw_oto = dml_max(bytes_pp * myPipe->PixelClock / myPipe->DPPPerPlane, prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime)); prefetch_bw_oto = dml_max(prefetch_bw_pr, prefetch_sw_bytes / max_Tsw); min_Lsw = dml_max(1, dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / max_vratio_pre); Lsw_oto = dml_ceil(4 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1) / 4; Tsw_oto = Lsw_oto * LineTime; - prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC) / Tsw_oto; #ifdef __DML_VBA_DEBUG__ dml_print("DML: HTotal: %d\n", myPipe->HTotal); @@ -5181,7 +5179,7 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->HTotal[k] / v->PixelClock[k], - v->UrgentLatency, + v->UrgLatency[i], v->CursorBufferSize, v->CursorWidth[k][0], v->CursorBPP[k][0], diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 0d704e302d03..f94abd124021 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -157,7 +157,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = { .dispclk_dppclk_vco_speed_mhz = 4300.0, .do_urgent_latency_adjustment = true, .urgent_latency_adjustment_fabric_clock_component_us = 1.0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 1000, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 3000, }; void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) @@ -211,7 +211,7 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) /* 'DalDummyClockChangeLatencyNs' registry key option set to 0x7FFFFFFF can be used to disable Set C for dummy p-state */ if (clk_mgr->base.ctx->dc->bb_overrides.dummy_clock_change_latency_ns != 0x7FFFFFFF) { clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].valid = true; - clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us = 38; + clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us = 50; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.fclk_change_latency_us = fclk_change_latency_us; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us = sr_exit_time_us; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us = sr_enter_plus_exit_time_us; @@ -221,7 +221,7 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].pmfw_breakdown.min_uclk = min_uclk_mhz; clk_mgr->base.bw_params->wm_table.nv_entries[WM_C].pmfw_breakdown.max_uclk = 0xFFFF; clk_mgr->base.bw_params->dummy_pstate_table[0].dram_speed_mts = clk_mgr->base.bw_params->clk_table.entries[0].memclk_mhz * 16; - clk_mgr->base.bw_params->dummy_pstate_table[0].dummy_pstate_latency_us = 38; + clk_mgr->base.bw_params->dummy_pstate_table[0].dummy_pstate_latency_us = 50; clk_mgr->base.bw_params->dummy_pstate_table[1].dram_speed_mts = clk_mgr->base.bw_params->clk_table.entries[1].memclk_mhz * 16; clk_mgr->base.bw_params->dummy_pstate_table[1].dummy_pstate_latency_us = 9; clk_mgr->base.bw_params->dummy_pstate_table[2].dram_speed_mts = clk_mgr->base.bw_params->clk_table.entries[2].memclk_mhz * 16; @@ -256,16 +256,24 @@ int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, int vlevel) { const int max_latency_table_entries = 4; - const struct vba_vars_st *vba = &context->bw_ctx.dml.vba; + struct vba_vars_st *vba = &context->bw_ctx.dml.vba; int dummy_latency_index = 0; + enum clock_change_support temp_clock_change_support = vba->DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; dc_assert_fp_enabled(); while (dummy_latency_index < max_latency_table_entries) { + if (temp_clock_change_support != dm_dram_clock_change_unsupported) + vba->DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = temp_clock_change_support; context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us; dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false); + /* for subvp + DRR case, if subvp pipes are still present we support pstate */ + if (vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported && + dcn32_subvp_in_use(dc, context)) + vba->DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = temp_clock_change_support; + if (vlevel < context->bw_ctx.dml.vba.soc.num_states && vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] != dm_dram_clock_change_unsupported) break; @@ -531,9 +539,12 @@ void dcn32_set_phantom_stream_timing(struct dc *dc, unsigned int i, pipe_idx; struct pipe_ctx *pipe; uint32_t phantom_vactive, phantom_bp, pstate_width_fw_delay_lines; + unsigned int num_dpp; unsigned int vlevel = context->bw_ctx.dml.vba.VoltageLevel; unsigned int dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; unsigned int socclk = context->bw_ctx.dml.vba.SOCCLKPerState[vlevel]; + struct vba_vars_st *vba = &context->bw_ctx.dml.vba; + struct dc_stream_state *main_stream = ref_pipe->stream; dc_assert_fp_enabled(); @@ -569,13 +580,26 @@ void dcn32_set_phantom_stream_timing(struct dc *dc, phantom_vactive = get_subviewport_lines_needed_in_mall(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx) + pstate_width_fw_delay_lines + dc->caps.subvp_swath_height_margin_lines; + // W/A for DCC corruption with certain high resolution timings. + // Determing if pipesplit is used. If so, add meta_row_height to the phantom vactive. + num_dpp = vba->NoOfDPP[vba->VoltageLevel][vba->maxMpcComb][vba->pipe_plane[pipe_idx]]; + phantom_vactive += num_dpp > 1 ? vba->meta_row_height[vba->pipe_plane[pipe_idx]] : 0; + + /* dc->debug.subvp_extra_lines 0 by default*/ + phantom_vactive += dc->debug.subvp_extra_lines; + // For backporch of phantom pipe, use vstartup of the main pipe phantom_bp = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); phantom_stream->dst.y = 0; phantom_stream->dst.height = phantom_vactive; + /* When scaling, DML provides the end to end required number of lines for MALL. + * dst.height is always correct for this case, but src.height is not which causes a + * delta between main and phantom pipe scaling outputs. Need to adjust src.height on + * phantom for this case. + */ phantom_stream->src.y = 0; - phantom_stream->src.height = phantom_vactive; + phantom_stream->src.height = (double)phantom_vactive * (double)main_stream->src.height / (double)main_stream->dst.height; phantom_stream->timing.v_addressable = phantom_vactive; phantom_stream->timing.v_front_porch = 1; @@ -1128,7 +1152,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final == dm_prefetch_support_uclk_fclk_and_stutter) { context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final = - dm_prefetch_support_stutter; + dm_prefetch_support_fclk_and_stutter; /* There are params (such as FabricClock) that need to be recalculated * after validation fails (otherwise it will be 0). Calculation for * phantom vactive requires call into DML, so we must ensure all the @@ -1179,7 +1203,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, // If SubVP pipe config is unsupported (or cannot be used for UCLK switching) // remove phantom pipes and repopulate dml pipes if (!found_supported_config) { - dc->res_pool->funcs->remove_phantom_pipes(dc, context); + dc->res_pool->funcs->remove_phantom_pipes(dc, context, false); vba->DRAMClockChangeSupport[*vlevel][vba->maxMpcComb] = dm_dram_clock_change_unsupported; *pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, false); @@ -1228,7 +1252,7 @@ static void dcn32_calculate_dlg_params(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, int pipe_cnt, int vlevel) { - int i, pipe_idx; + int i, pipe_idx, active_hubp_count = 0; bool usr_retraining_support = false; bool unbounded_req_enabled = false; @@ -1273,6 +1297,8 @@ static void dcn32_calculate_dlg_params(struct dc *dc, struct dc_state *context, for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { if (!context->res_ctx.pipe_ctx[i].stream) continue; + if (context->res_ctx.pipe_ctx[i].plane_state) + active_hubp_count++; pipes[pipe_idx].pipe.dest.vstartup_start = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, @@ -1294,10 +1320,23 @@ static void dcn32_calculate_dlg_params(struct dc *dc, struct dc_state *context, if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; - context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; + if (context->res_ctx.pipe_ctx[i].plane_state) + context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; + else + context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = 0; context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest; pipe_idx++; } + /* If DCN isn't making memory requests we can allow pstate change and lower clocks */ + if (!active_hubp_count) { + context->bw_ctx.bw.dcn.clk.socclk_khz = 0; + context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; + context->bw_ctx.bw.dcn.clk.dcfclk_khz = 0; + context->bw_ctx.bw.dcn.clk.dcfclk_deep_sleep_khz = 0; + context->bw_ctx.bw.dcn.clk.dramclk_khz = 0; + context->bw_ctx.bw.dcn.clk.fclk_khz = 0; + context->bw_ctx.bw.dcn.clk.p_state_change_support = true; + } /*save a original dppclock copy*/ context->bw_ctx.bw.dcn.clk.bw_dppclk_khz = context->bw_ctx.bw.dcn.clk.dppclk_khz; context->bw_ctx.bw.dcn.clk.bw_dispclk_khz = context->bw_ctx.bw.dcn.clk.dispclk_khz; @@ -1479,7 +1518,7 @@ bool dcn32_internal_validate_bw(struct dc *dc, return false; // For each full update, remove all existing phantom pipes first - dc->res_pool->funcs->remove_phantom_pipes(dc, context); + dc->res_pool->funcs->remove_phantom_pipes(dc, context, fast_validate); dc->res_pool->funcs->update_soc_for_wm_a(dc, context); @@ -1729,6 +1768,10 @@ bool dcn32_internal_validate_bw(struct dc *dc, } if (repopulate_pipes) { + int flag_max_mpc_comb = vba->maxMpcComb; + int flag_vlevel = vlevel; + int i; + pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); /* repopulate_pipes = 1 means the pipes were either split or merged. In this case @@ -1742,6 +1785,22 @@ bool dcn32_internal_validate_bw(struct dc *dc, if (vlevel == context->bw_ctx.dml.soc.num_states) { /* failed after DET size changes */ goto validate_fail; + } else if (flag_max_mpc_comb == 0 && + flag_max_mpc_comb != context->bw_ctx.dml.vba.maxMpcComb) { + /* check the context constructed with pipe split flags is still valid*/ + bool flags_valid = false; + for (i = flag_vlevel; i < context->bw_ctx.dml.soc.num_states; i++) { + if (vba->ModeSupport[i][flag_max_mpc_comb]) { + vba->maxMpcComb = flag_max_mpc_comb; + vba->VoltageLevel = i; + vlevel = i; + flags_valid = true; + } + } + + /* this should never happen */ + if (!flags_valid) + goto validate_fail; } } *vlevel_out = vlevel; @@ -1772,14 +1831,38 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, unsigned int dummy_latency_index = 0; int maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb; unsigned int min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed; + bool subvp_in_use = dcn32_subvp_in_use(dc, context); unsigned int min_dram_speed_mts_margin; + bool need_fclk_lat_as_dummy = false; + bool is_subvp_p_drr = true; dc_assert_fp_enabled(); - // Override DRAMClockChangeSupport for SubVP + DRR case where the DRR cannot switch without stretching it's VBLANK - if (!pstate_en && dcn32_subvp_in_use(dc, context)) { - context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = dm_dram_clock_change_vblank_w_mall_sub_vp; - pstate_en = true; + /* need to find dummy latency index for subvp */ + if (subvp_in_use) { + /* Override DRAMClockChangeSupport for SubVP + DRR case where the DRR cannot switch without stretching it's VBLANK */ + if (!pstate_en) { + context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = dm_dram_clock_change_vblank_w_mall_sub_vp; + pstate_en = true; + is_subvp_p_drr = true; + } + dummy_latency_index = dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(dc, + context, pipes, pipe_cnt, vlevel); + + /* For DCN32/321 need to validate with fclk pstate change latency equal to dummy so prefetch is + * scheduled correctly to account for dummy pstate. + */ + if (context->bw_ctx.dml.soc.fclk_change_latency_us < dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us) { + need_fclk_lat_as_dummy = true; + context->bw_ctx.dml.soc.fclk_change_latency_us = + dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us; + } + context->bw_ctx.dml.soc.dram_clock_change_latency_us = + dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; + dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false); + if (is_subvp_p_drr) { + context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] = dm_dram_clock_change_vblank_w_mall_sub_vp; + } } context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching = false; @@ -1800,6 +1883,14 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, */ context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; + /* For DCN32/321 need to validate with fclk pstate change latency equal to dummy so + * prefetch is scheduled correctly to account for dummy pstate. + */ + if (context->bw_ctx.dml.soc.fclk_change_latency_us < dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us) { + need_fclk_lat_as_dummy = true; + context->bw_ctx.dml.soc.fclk_change_latency_us = + dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us; + } dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false); maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb; dcfclk_from_fw_based_mclk_switching = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; @@ -1901,13 +1992,13 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, if (context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] == dm_dram_clock_change_unsupported) { - int min_dram_speed_mts_offset = dc->clk_mgr->bw_params->clk_table.num_entries - 1; + int min_dram_speed_mts_offset = dc->clk_mgr->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1; min_dram_speed_mts = dc->clk_mgr->bw_params->clk_table.entries[min_dram_speed_mts_offset].memclk_mhz * 16; } - if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && !subvp_in_use) { /* find largest table entry that is lower than dram speed, * but lower than DPM0 still uses DPM0 */ @@ -1987,6 +2078,11 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, context->perf_params.stutter_period_us = context->bw_ctx.dml.vba.StutterPeriod; + /* for proper prefetch calculations, if dummy lat > fclk lat, use fclk lat = dummy lat */ + if (need_fclk_lat_as_dummy) + context->bw_ctx.dml.soc.fclk_change_latency_us = + dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us; + dcn32_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); if (!pstate_en) @@ -1994,8 +2090,14 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { dcn30_setup_mclk_switch_using_fw_based_vblank_stretch(dc, context); + } + + /* revert fclk lat changes if required */ + if (need_fclk_lat_as_dummy) + context->bw_ctx.dml.soc.fclk_change_latency_us = + dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.fclk_change_latency_us; } static void dcn32_get_optimal_dcfclk_fclk_for_uclk(unsigned int uclk_mts, @@ -2351,6 +2453,8 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa /* DML DSC delay factor workaround */ dcn3_2_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0; + dcn3_2_ip.min_prefetch_in_strobe_us = dc->debug.min_prefetch_in_strobe_ns / 1000.0; + /* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */ dcn3_2_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 3d184679f129..4b8f5fa0f0ad 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -670,6 +670,25 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->cursor_bw[k] = mode_lib->vba.NumberOfCursors[k] * mode_lib->vba.CursorWidth[k][0] * mode_lib->vba.CursorBPP[k][0] / 8 / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]) * mode_lib->vba.VRatio[k]; } + v->NotEnoughDETSwathFillLatencyHiding = dml32_CalculateDETSwathFillLatencyHiding( + mode_lib->vba.NumberOfActiveSurfaces, + mode_lib->vba.ReturnBW, + v->UrgentLatency, + mode_lib->vba.SwathHeightY, + mode_lib->vba.SwathHeightC, + v->swath_width_luma_ub, + v->swath_width_chroma_ub, + v->BytePerPixelDETY, + v->BytePerPixelDETC, + mode_lib->vba.DETBufferSizeY, + mode_lib->vba.DETBufferSizeC, + mode_lib->vba.DPPPerPlane, + mode_lib->vba.HTotal, + mode_lib->vba.PixelClock, + mode_lib->vba.VRatio, + mode_lib->vba.VRatioChroma, + mode_lib->vba.UsesMALLForPStateChange); + for (k = 0; k < mode_lib->vba.NumberOfActiveSurfaces; ++k) { v->MaxVStartupLines[k] = ((mode_lib->vba.Interlace[k] && !mode_lib->vba.ProgressiveToInterlaceUnitInOPP) ? @@ -718,6 +737,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman do { MaxTotalRDBandwidth = 0; + DestinationLineTimesForPrefetchLessThan2 = false; + VRatioPrefetchMoreThanMax = false; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: Start loop: VStartup = %d\n", __func__, mode_lib->vba.VStartupLines); #endif @@ -786,6 +807,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, + v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ? + mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->DSTXAfterScaler[k], &v->DSTYAfterScaler[k], @@ -1661,6 +1684,8 @@ static void mode_support_configuration(struct vba_vars_st *v, && mode_lib->vba.DCCMetaBufferSizeNotExceeded[i][j] == true && mode_lib->vba.NonsupportedDSCInputBPC == false && !mode_lib->vba.ExceededMALLSize + && (mode_lib->vba.NotEnoughDETSwathFillLatencyHidingPerState[i][j] == false + || i == v->soc.num_states - 1) && ((mode_lib->vba.HostVMEnable == false && !mode_lib->vba.ImmediateFlipRequiredFinal) || mode_lib->vba.ImmediateFlipSupportedForState[i][j]) @@ -3154,6 +3179,25 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.UrgentBurstFactorChroma, mode_lib->vba.UrgentBurstFactorCursor); + mode_lib->vba.NotEnoughDETSwathFillLatencyHidingPerState[i][j] = dml32_CalculateDETSwathFillLatencyHiding( + mode_lib->vba.NumberOfActiveSurfaces, + mode_lib->vba.ReturnBWPerState[i][j], + mode_lib->vba.UrgLatency[i], + mode_lib->vba.SwathHeightYThisState, + mode_lib->vba.SwathHeightCThisState, + mode_lib->vba.swath_width_luma_ub_this_state, + mode_lib->vba.swath_width_chroma_ub_this_state, + mode_lib->vba.BytePerPixelInDETY, + mode_lib->vba.BytePerPixelInDETC, + mode_lib->vba.DETBufferSizeYThisState, + mode_lib->vba.DETBufferSizeCThisState, + mode_lib->vba.NoOfDPPThisState, + mode_lib->vba.HTotal, + mode_lib->vba.PixelClock, + mode_lib->vba.VRatio, + mode_lib->vba.VRatioChroma, + mode_lib->vba.UsesMALLForPStateChange); + v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.VMDataOnlyReturnBWPerState = dml32_get_return_bw_mbps_vm_only(&mode_lib->vba.soc, i, mode_lib->vba.DCFCLKState[i][j], mode_lib->vba.FabricClockPerState[i], mode_lib->vba.DRAMSpeedPerState[i]); @@ -3192,6 +3236,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.FCLKChangeLatency, mode_lib->vba.UrgLatency[i], mode_lib->vba.SREnterPlusExitTime); + memset(&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull, 0, sizeof(DmlPipe)); v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.Dppclk = mode_lib->vba.RequiredDPPCLK[i][j][k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.Dispclk = mode_lib->vba.RequiredDISPCLK[i][j]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.PixelClock = mode_lib->vba.PixelClock[k]; @@ -3244,6 +3289,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->swath_width_chroma_ub_this_state[k], v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, + v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ ? + mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k], diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h index c62e0991358b..c8b28c83ddf4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h @@ -46,9 +46,14 @@ // Prefetch schedule max vratio #define __DML_MAX_VRATIO_PRE__ 4.0 +#define __DML_VBA_MAX_DST_Y_PRE__ 63.75 + #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define MEM_STROBE_FREQ_MHZ 1600 +#define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0 + struct display_mode_lib; void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 968924c491c1..5af601cff1a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -3417,6 +3417,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, + double TPreReq, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, @@ -3667,6 +3668,7 @@ bool dml32_CalculatePrefetchSchedule( dst_y_prefetch_equ = VStartup - (*TSetup + dml_max(TWait + TCalc, *Tdmdl)) / LineTime - (*DSTYAfterScaler + (double) *DSTXAfterScaler / (double) myPipe->HTotal); + dst_y_prefetch_equ = dml_min(dst_y_prefetch_equ, __DML_VBA_MAX_DST_Y_PRE__); #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: HTotal = %d\n", __func__, myPipe->HTotal); dml_print("DML::%s: min_Lsw = %f\n", __func__, min_Lsw); @@ -3726,7 +3728,8 @@ bool dml32_CalculatePrefetchSchedule( *VRatioPrefetchY = 0; *VRatioPrefetchC = 0; *RequiredPrefetchPixDataBWLuma = 0; - if (dst_y_prefetch_equ > 1) { + if (dst_y_prefetch_equ > 1 && + (Tpre_rounded >= TPreReq || dst_y_prefetch_equ == __DML_VBA_MAX_DST_Y_PRE__)) { double PrefetchBandwidth1; double PrefetchBandwidth2; double PrefetchBandwidth3; @@ -3872,7 +3875,11 @@ bool dml32_CalculatePrefetchSchedule( } if (dst_y_prefetch_oto < dst_y_prefetch_equ) { - *DestinationLinesForPrefetch = dst_y_prefetch_oto; + if (dst_y_prefetch_oto * LineTime < TPreReq) { + *DestinationLinesForPrefetch = dst_y_prefetch_equ; + } else { + *DestinationLinesForPrefetch = dst_y_prefetch_oto; + } TimeForFetchingMetaPTE = Tvm_oto; TimeForFetchingRowInVBlank = Tr0_oto; *PrefetchBandwidth = prefetch_bw_oto; @@ -4397,7 +4404,7 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY - - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] + - (1.0 - 1.0 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } @@ -6221,3 +6228,72 @@ void dml32_CalculateImmediateFlipBandwithSupport(unsigned int NumberOfActiveSurf *ImmediateFlipBandwidthSupport = (*TotalBandwidth <= ReturnBW); *FractionOfUrgentBandwidth = *TotalBandwidth / ReturnBW; } + +bool dml32_CalculateDETSwathFillLatencyHiding(unsigned int NumberOfActiveSurfaces, + double ReturnBW, + double UrgentLatency, + unsigned int SwathHeightY[], + unsigned int SwathHeightC[], + unsigned int SwathWidthY[], + unsigned int SwathWidthC[], + double BytePerPixelInDETY[], + double BytePerPixelInDETC[], + unsigned int DETBufferSizeY[], + unsigned int DETBufferSizeC[], + unsigned int NumOfDPP[], + unsigned int HTotal[], + double PixelClock[], + double VRatioY[], + double VRatioC[], + enum dm_use_mall_for_pstate_change_mode UsesMALLForPStateChange[DC__NUM_DPP__MAX]) +{ + int k; + double SwathSizeAllSurfaces = 0; + double SwathSizeAllSurfacesInFetchTimeUs; + double DETSwathLatencyHidingUs; + double DETSwathLatencyHidingYUs; + double DETSwathLatencyHidingCUs; + double SwathSizePerSurfaceY[DC__NUM_DPP__MAX]; + double SwathSizePerSurfaceC[DC__NUM_DPP__MAX]; + bool NotEnoughDETSwathFillLatencyHiding = false; + + /* calculate sum of single swath size for all pipes in bytes*/ + for (k = 0; k < NumberOfActiveSurfaces; k++) { + SwathSizePerSurfaceY[k] += SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k]; + + if (SwathHeightC[k] != 0) + SwathSizePerSurfaceC[k] += SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k]; + else + SwathSizePerSurfaceC[k] = 0; + + SwathSizeAllSurfaces += SwathSizePerSurfaceY[k] + SwathSizePerSurfaceC[k]; + } + + SwathSizeAllSurfacesInFetchTimeUs = SwathSizeAllSurfaces / ReturnBW + UrgentLatency; + + /* ensure all DET - 1 swath can hide a fetch for all surfaces */ + for (k = 0; k < NumberOfActiveSurfaces; k++) { + double LineTime = HTotal[k] / PixelClock[k]; + + /* only care if surface is not phantom */ + if (UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) { + DETSwathLatencyHidingYUs = (dml_floor(DETBufferSizeY[k] / BytePerPixelInDETY[k] / SwathWidthY[k], 1.0) - SwathHeightY[k]) / VRatioY[k] * LineTime; + + if (SwathHeightC[k] != 0) { + DETSwathLatencyHidingCUs = (dml_floor(DETBufferSizeC[k] / BytePerPixelInDETC[k] / SwathWidthC[k], 1.0) - SwathHeightC[k]) / VRatioC[k] * LineTime; + + DETSwathLatencyHidingUs = dml_min(DETSwathLatencyHidingYUs, DETSwathLatencyHidingCUs); + } else { + DETSwathLatencyHidingUs = DETSwathLatencyHidingYUs; + } + + /* DET must be able to hide time to fetch 1 swath for each surface */ + if (DETSwathLatencyHidingUs < SwathSizeAllSurfacesInFetchTimeUs) { + NotEnoughDETSwathFillLatencyHiding = true; + break; + } + } + } + + return NotEnoughDETSwathFillLatencyHiding; +} diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index 2c3827546ac7..779c6805f599 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -30,7 +30,7 @@ #include "os_types.h" #include "../dc_features.h" #include "../display_mode_structs.h" -#include "dml/display_mode_vba.h" +#include "../display_mode_vba.h" unsigned int dml32_dscceComputeDelay( unsigned int bpc, @@ -743,6 +743,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, + double TPreReq, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, @@ -1140,4 +1141,22 @@ void dml32_CalculateImmediateFlipBandwithSupport(unsigned int NumberOfActiveSurf double *FractionOfUrgentBandwidth, bool *ImmediateFlipBandwidthSupport); +bool dml32_CalculateDETSwathFillLatencyHiding(unsigned int NumberOfActiveSurfaces, + double ReturnBW, + double UrgentLatency, + unsigned int SwathHeightY[], + unsigned int SwathHeightC[], + unsigned int SwathWidthY[], + unsigned int SwathWidthC[], + double BytePerPixelInDETY[], + double BytePerPixelInDETC[], + unsigned int DETBufferSizeY[], + unsigned int DETBufferSizeC[], + unsigned int NumOfDPP[], + unsigned int HTotal[], + double PixelClock[], + double VRatioY[], + double VRatioC[], + enum dm_use_mall_for_pstate_change_mode UsesMALLForPStateChange[DC__NUM_DPP__MAX]); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index ec0486efab14..f4b176599be7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -126,9 +126,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .sr_enter_plus_exit_z8_time_us = 320, .writeback_latency_us = 12.0, .round_trip_ping_latency_dcfclk_cycles = 263, - .urgent_latency_pixel_data_only_us = 9.35, - .urgent_latency_pixel_mixed_with_vm_data_us = 9.35, - .urgent_latency_vm_data_only_us = 9.35, + .urgent_latency_pixel_data_only_us = 4, + .urgent_latency_pixel_mixed_with_vm_data_us = 4, + .urgent_latency_vm_data_only_us = 4, .fclk_change_latency_us = 20, .usr_retraining_latency_us = 2, .smn_latency_us = 2, @@ -156,7 +156,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .dispclk_dppclk_vco_speed_mhz = 4300.0, .do_urgent_latency_adjustment = true, .urgent_latency_adjustment_fabric_clock_component_us = 1.0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 1000, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 3000, }; static void get_optimal_ntuple(struct _vcs_dpi_voltage_scaling_st *entry) @@ -544,6 +544,8 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p /* DML DSC delay factor workaround */ dcn3_21_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0; + dcn3_21_ip.min_prefetch_in_strobe_us = dc->debug.min_prefetch_in_strobe_ns / 1000.0; + /* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */ dcn3_21_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index d7be01ac0751..64d602e6412f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -367,6 +367,7 @@ struct _vcs_dpi_ip_params_st { /* DM workarounds */ double dsc_delay_factor_wa; // TODO: Remove after implementing root cause fix + double min_prefetch_in_strobe_us; }; struct _vcs_dpi_display_xfc_params_st { diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index d46aa4817e70..81e53e67cd0b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -1050,6 +1050,7 @@ struct vba_vars_st { double MinFullDETBufferingTime; double AverageReadBandwidthGBytePerSecond; bool FirstMainPlane; + bool NotEnoughDETSwathFillLatencyHiding; unsigned int ViewportWidthChroma[DC__NUM_DPP__MAX]; unsigned int ViewportHeightChroma[DC__NUM_DPP__MAX]; @@ -1162,7 +1163,7 @@ struct vba_vars_st { double UrgBurstFactorLumaPre[DC__NUM_DPP__MAX]; double UrgBurstFactorChromaPre[DC__NUM_DPP__MAX]; bool NotUrgentLatencyHidingPre[DC__NUM_DPP__MAX]; - bool LinkCapacitySupport[DC__NUM_DPP__MAX]; + bool LinkCapacitySupport[DC__VOLTAGE_STATES]; bool VREADY_AT_OR_AFTER_VSYNC[DC__NUM_DPP__MAX]; unsigned int MIN_DST_Y_NEXT_START[DC__NUM_DPP__MAX]; unsigned int VFrontPorch[DC__NUM_DPP__MAX]; @@ -1233,6 +1234,7 @@ struct vba_vars_st { unsigned int BlockWidthC[DC__NUM_DPP__MAX]; unsigned int SubViewportLinesNeededInMALL[DC__NUM_DPP__MAX]; bool VActiveBandwithSupport[DC__VOLTAGE_STATES][2]; + bool NotEnoughDETSwathFillLatencyHidingPerState[DC__VOLTAGE_STATES][2]; struct dummy_vars dummy_vars; }; diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c index d635b73af46f..9fd8b269dd79 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c @@ -108,6 +108,13 @@ static const struct ddc_registers ddc_data_regs_dcn[] = { ddc_data_regs_dcn2(4), ddc_data_regs_dcn2(5), { + // add a dummy entry for cases no such port + {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,}, + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + }, + { DDC_GPIO_VGA_REG_LIST(DATA), .ddc_setup = 0, .phy_aux_cntl = 0, @@ -122,6 +129,13 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = { ddc_clk_regs_dcn2(4), ddc_clk_regs_dcn2(5), { + // add a dummy entry for cases no such port + {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,}, + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + }, + { DDC_GPIO_VGA_REG_LIST(CLK), .ddc_setup = 0, .phy_aux_cntl = 0, @@ -242,8 +256,8 @@ static const struct hw_factory_funcs funcs = { */ void dal_hw_factory_dcn32_init(struct hw_factory *factory) { - factory->number_of_pins[GPIO_ID_DDC_DATA] = 6; - factory->number_of_pins[GPIO_ID_DDC_CLOCK] = 6; + factory->number_of_pins[GPIO_ID_DDC_DATA] = 8; + factory->number_of_pins[GPIO_ID_DDC_CLOCK] = 8; factory->number_of_pins[GPIO_ID_GENERIC] = 4; factory->number_of_pins[GPIO_ID_HPD] = 5; factory->number_of_pins[GPIO_ID_GPIO_PAD] = 28; diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c index 6fd38cdd68c0..525bc8881950 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c @@ -94,11 +94,14 @@ static enum gpio_result set_config( * is required for detection of AUX mode */ if (hw_gpio->base.en != GPIO_DDC_LINE_VIP_PAD) { if (!ddc_data_pd_en || !ddc_clk_pd_en) { - - REG_SET_2(gpio.MASK_reg, regval, + if (hw_gpio->base.en == GPIO_DDC_LINE_DDC_VGA) { + // bit 4 of mask has different usage in some cases + REG_SET(gpio.MASK_reg, regval, DC_GPIO_DDC1DATA_PD_EN, 1); + } else { + REG_SET_2(gpio.MASK_reg, regval, DC_GPIO_DDC1DATA_PD_EN, 1, DC_GPIO_DDC1CLK_PD_EN, 1); - + } if (config_data->type == GPIO_CONFIG_TYPE_I2C_AUX_DUAL_MODE) msleep(3); diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 85495ef026f5..525f8f0b8732 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -240,8 +240,11 @@ struct resource_funcs { unsigned int pipe_cnt, unsigned int index); - bool (*remove_phantom_pipes)(struct dc *dc, struct dc_state *context); + bool (*remove_phantom_pipes)(struct dc *dc, struct dc_state *context, bool fast_update); + void (*retain_phantom_pipes)(struct dc *dc, struct dc_state *context); void (*get_panel_config_defaults)(struct dc_panel_config *panel_config); + void (*save_mall_state)(struct dc *dc, struct dc_state *context, struct mall_temp_config *temp_config); + void (*restore_mall_state)(struct dc *dc, struct dc_state *context, struct mall_temp_config *temp_config); }; struct audio_support{ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h index 58f758fcbce1..5b0265c0df61 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h @@ -46,7 +46,7 @@ struct dcn_hubbub_wm_set { uint32_t pte_meta_urgent; uint32_t sr_enter; uint32_t sr_exit; - uint32_t dram_clk_chanage; + uint32_t dram_clk_change; uint32_t usr_retrain; uint32_t fclk_pstate_change; }; @@ -186,6 +186,7 @@ struct hubbub_funcs { void (*program_compbuf_size)(struct hubbub *hubbub, unsigned compbuf_size_kb, bool safe_to_increase); void (*init_crb)(struct hubbub *hubbub); void (*force_usr_retraining_allow)(struct hubbub *hubbub, bool allow); + void (*set_request_limit)(struct hubbub *hubbub, int memory_channel_count, int words_per_channel); }; struct hubbub { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h index dcb80c4747b0..131fcfa28bca 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h @@ -83,10 +83,15 @@ static const struct dpp_input_csc_matrix __maybe_unused dpp_input_csc_matrix[] = {COLOR_SPACE_YCBCR709, {0x3265, 0x2000, 0, 0xe6ce, 0xf105, 0x2000, 0xfa01, 0xa7d, 0, 0x2000, 0x3b61, 0xe24f} }, - {COLOR_SPACE_YCBCR709_LIMITED, {0x39a6, 0x2568, 0, 0xe0d6, 0xeedd, 0x2568, 0xf925, 0x9a8, 0, - 0x2568, 0x43ee, 0xdbb2} } + 0x2568, 0x43ee, 0xdbb2} }, + {COLOR_SPACE_2020_YCBCR, + {0x2F30, 0x2000, 0, 0xE869, 0xEDB7, 0x2000, 0xFABC, 0xBC6, 0, + 0x2000, 0x3C34, 0xE1E6} }, + {COLOR_SPACE_2020_RGB_LIMITEDRANGE, + {0x35E0, 0x255F, 0, 0xE2B3, 0xEB20, 0x255F, 0xF9FD, 0xB1E, 0, + 0x255F, 0x44BD, 0xDB43} } }; struct dpp_grph_csc_adjustment { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index 65f18f9dad34..0e42e721dd15 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -185,6 +185,7 @@ struct timing_generator_funcs { #ifdef CONFIG_DRM_AMD_DC_DCN void (*phantom_crtc_post_enable)(struct timing_generator *tg); #endif + void (*disable_phantom_crtc)(struct timing_generator *tg); bool (*immediate_disable_crtc)(struct timing_generator *tg); bool (*is_counter_moving)(struct timing_generator *tg); void (*get_position)(struct timing_generator *tg, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index d04b68dad413..c43523f9ff6d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -263,6 +263,7 @@ struct hw_sequencer_funcs { void (*update_phantom_vp_position)(struct dc *dc, struct dc_state *context, struct pipe_ctx *phantom_pipe); + void (*apply_update_flags_for_phantom)(struct pipe_ctx *phantom_pipe); void (*commit_subvp_config)(struct dc *dc, struct dc_state *context); void (*subvp_pipe_control_lock)(struct dc *dc, diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.c b/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.c index 45f99351a0ab..5f4f6dd79511 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.c @@ -28,20 +28,19 @@ #include "include/logger_interface.h" #include "../dce110/irq_service_dce110.h" +#include "irq_service_dcn201.h" #include "dcn/dcn_2_0_3_offset.h" #include "dcn/dcn_2_0_3_sh_mask.h" #include "cyan_skillfish_ip_offset.h" #include "soc15_hw_ip.h" - -#include "irq_service_dcn201.h" - #include "ivsrcid/dcn/irqsrcs_dcn_1_0.h" -static enum dc_irq_source to_dal_irq_source_dcn201(struct irq_service *irq_service, - uint32_t src_id, - uint32_t ext_id) +enum dc_irq_source to_dal_irq_source_dcn201( + struct irq_service *irq_service, + uint32_t src_id, + uint32_t ext_id) { switch (src_id) { case DCN_1_0__SRCID__DC_D1_OTG_VSTARTUP: @@ -79,7 +78,6 @@ static enum dc_irq_source to_dal_irq_source_dcn201(struct irq_service *irq_servi default: return DC_IRQ_SOURCE_INVALID; } - return DC_IRQ_SOURCE_INVALID; } static bool hpd_ack( @@ -138,6 +136,11 @@ static const struct irq_source_info_funcs vupdate_no_lock_irq_info_funcs = { .ack = NULL }; +static const struct irq_source_info_funcs dmub_outbox_irq_info_funcs = { + .set = NULL, + .ack = NULL +}; + #undef BASE_INNER #define BASE_INNER(seg) DMU_BASE__INST0_SEG ## seg diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.h b/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.h index 8e27c5e219a3..0cfd2f2d62e8 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.h +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn201/irq_service_dcn201.h @@ -1,5 +1,5 @@ /* - * Copyright 2018 Advanced Micro Devices, Inc. + * Copyright 2022 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/link_dp_dpia_bw.c new file mode 100644 index 000000000000..801a95b34e8c --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/link/link_dp_dpia_bw.c @@ -0,0 +1,28 @@ + +/* + * Copyright 2022 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ +/*********************************************************************/ +// USB4 DPIA BANDWIDTH ALLOCATION LOGIC +/*********************************************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/link_dp_dpia_bw.h new file mode 100644 index 000000000000..669e995f825f --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/link/link_dp_dpia_bw.h @@ -0,0 +1,69 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#ifndef DC_INC_LINK_DP_DPIA_BW_H_ +#define DC_INC_LINK_DP_DPIA_BW_H_ + +// XXX: TODO: Re-add for Phase 2 +/* Number of Host Routers per motherboard is 2 and 2 DPIA per host router */ +#define MAX_HR_NUM 2 + +struct dc_host_router_bw_alloc { + int max_bw[MAX_HR_NUM]; // The Max BW that each Host Router has available to be shared btw DPIAs + int total_estimated_bw[MAX_HR_NUM]; // The Total Verified and available BW that Host Router has +}; + +/* + * Enable BW Allocation Mode Support from the DP-Tx side + * + * @link: pointer to the dc_link struct instance + * + * return: SUCCESS or FAILURE + */ +bool set_dptx_usb4_bw_alloc_support(struct dc_link *link); + +/* + * Send a request from DP-Tx requesting to allocate BW remotely after + * allocating it locally. This will get processed by CM and a CB function + * will be called. + * + * @link: pointer to the dc_link struct instance + * @req_bw: The requested bw in Kbyte to allocated + * + * return: none + */ +void set_usb4_req_bw_req(struct dc_link *link, int req_bw); + +/* + * CB function for when the status of the Req above is complete. We will + * find out the result of allocating on CM and update structs accordingly + * + * @link: pointer to the dc_link struct instance + * + * return: none + */ +void get_usb4_req_bw_resp(struct dc_link *link); + +#endif /* DC_INC_LINK_DP_DPIA_BW_H_ */ diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 9df330c86a55..33907feefebb 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -407,8 +407,9 @@ union dmub_fw_boot_options { uint32_t gpint_scratch8: 1; /* 1 if GPINT is in scratch8*/ uint32_t usb4_cm_version: 1; /**< 1 CM support */ uint32_t dpia_hpd_int_enable_supported: 1; /* 1 if dpia hpd int enable supported */ + uint32_t usb4_dpia_bw_alloc_supported: 1; /* 1 if USB4 dpia BW allocation supported */ - uint32_t reserved : 16; /**< reserved */ + uint32_t reserved : 15; /**< reserved */ } bits; /**< boot bits */ uint32_t all; /**< 32-bit access to bits */ }; @@ -1028,13 +1029,14 @@ struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 { uint16_t vtotal; uint16_t htotal; uint8_t vblank_pipe_index; - uint8_t padding[2]; + uint8_t padding[1]; struct { uint8_t drr_in_use; uint8_t drr_window_size_ms; // Indicates largest VMIN/VMAX adjustment per frame uint16_t min_vtotal_supported; // Min VTOTAL that supports switching in VBLANK uint16_t max_vtotal_supported; // Max VTOTAL that can support SubVP static scheduling uint8_t use_ramping; // Use ramping or not + uint8_t drr_vblank_start_margin; } drr_info; // DRR considered as part of SubVP + VBLANK case } vblank_data; } pipe_config; @@ -1877,9 +1879,13 @@ struct dmub_cmd_psr_copy_settings_data { */ uint8_t use_phy_fsm; /** + * frame delay for frame re-lock + */ + uint8_t relock_delay_frame_cnt; + /** * Explicit padding to 2 byte boundary. */ - uint8_t pad3[2]; + uint8_t pad3; }; /** diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index 447a0ec9cbe2..f6034213c700 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -61,7 +61,7 @@ static const int32_t numerator01[] = { 31308, 180000, 0, 0, 0}; static const int32_t numerator02[] = { 12920, 4500, 0, 0, 0}; static const int32_t numerator03[] = { 55, 99, 0, 0, 0}; static const int32_t numerator04[] = { 55, 99, 0, 0, 0}; -static const int32_t numerator05[] = { 2400, 2200, 2200, 2400, 2600}; +static const int32_t numerator05[] = { 2400, 2222, 2200, 2400, 2600}; /* one-time setup of X points */ void setup_x_points_distribution(void) diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 0f39ab9dc5b4..c2e00f7b8381 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -688,10 +688,10 @@ static void build_vrr_infopacket_fs2_data(enum color_transfer_func app_tf, if (app_tf != TRANSFER_FUNC_UNKNOWN) { infopacket->valid = true; - infopacket->sb[6] |= 0x08; // PB6 = [Bit 3 = Native Color Active] - - if (app_tf == TRANSFER_FUNC_GAMMA_22) { - infopacket->sb[9] |= 0x04; // PB6 = [Bit 2 = Gamma 2.2 EOTF Active] + if (app_tf != TRANSFER_FUNC_PQ2084) { + infopacket->sb[6] |= 0x08; // PB6 = [Bit 3 = Native Color Active] + if (app_tf == TRANSFER_FUNC_GAMMA_22) + infopacket->sb[9] |= 0x04; // PB6 = [Bit 2 = Gamma 2.2 EOTF Active] } } } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 235259d6c5a1..9b5d9b2c9a6a 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -102,9 +102,18 @@ static const struct abm_parameters abm_settings_config1[abm_defines_max_level] = {0x82, 0x4d, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xcccc, 0xcccc}, }; +static const struct abm_parameters abm_settings_config2[abm_defines_max_level] = { +// min_red max_red bright_pos dark_pos bright_gain contrast dev min_knee max_knee blRed blStart + {0xf0, 0xbf, 0x20, 0x00, 0x88, 0x99, 0xb3, 0x40, 0xe0, 0x0000, 0xcccc}, + {0xd8, 0x85, 0x20, 0x00, 0x70, 0x90, 0xa8, 0x40, 0xc8, 0x0700, 0xb333}, + {0xb8, 0x58, 0x20, 0x00, 0x64, 0x88, 0x78, 0x70, 0xa0, 0x7000, 0x9999}, + {0x82, 0x40, 0x20, 0x00, 0x00, 0xb8, 0xb3, 0x70, 0x70, 0xc333, 0xb333}, +}; + static const struct abm_parameters * const abm_settings[] = { abm_settings_config0, abm_settings_config1, + abm_settings_config2, }; #define NUM_AMBI_LEVEL 5 diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h index 483769fb1736..537aee0536d3 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_offset.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT #ifndef _dcn_3_0_0_OFFSET_HEADER #define _dcn_3_0_0_OFFSET_HEADER diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h index b79be3a25a80..f9d90b098519 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_0_sh_mask.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT #ifndef _dcn_3_0_0_SH_MASK_HEADER #define _dcn_3_0_0_SH_MASK_HEADER diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h index 363d2139cea2..db7e22720d00 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h @@ -993,7 +993,8 @@ #define mmUVD_RAS_VCPU_VCODEC_STATUS_BASE_IDX 1 #define mmUVD_RAS_MMSCH_FATAL_ERROR 0x0058 #define mmUVD_RAS_MMSCH_FATAL_ERROR_BASE_IDX 1 - +#define mmVCN_RAS_CNTL 0x04b9 +#define mmVCN_RAS_CNTL_BASE_IDX 1 /* JPEG 2_6_0 regs */ #define mmUVD_RAS_JPEG0_STATUS 0x0059 diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_sh_mask.h index 8de883b76d90..874a8b7e1feb 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_sh_mask.h @@ -3618,6 +3618,33 @@ #define UVD_RAS_MMSCH_FATAL_ERROR__POISONED_VF_MASK 0x7FFFFFFFL #define UVD_RAS_MMSCH_FATAL_ERROR__POISONED_PF_MASK 0x80000000L +//VCN 2_6_0 VCN_RAS_CNTL +#define VCN_RAS_CNTL__VCPU_VCODEC_IH_EN__SHIFT 0x0 +#define VCN_RAS_CNTL__MMSCH_FATAL_ERROR_EN__SHIFT 0x1 +#define VCN_RAS_CNTL__VCPU_VCODEC_PMI_EN__SHIFT 0x4 +#define VCN_RAS_CNTL__MMSCH_PMI_EN__SHIFT 0x5 +#define VCN_RAS_CNTL__VCPU_VCODEC_REARM__SHIFT 0x8 +#define VCN_RAS_CNTL__MMSCH_REARM__SHIFT 0x9 +#define VCN_RAS_CNTL__VCPU_VCODEC_STALL_EN__SHIFT 0xc +#define VCN_RAS_CNTL__VCPU_VCODEC_READY__SHIFT 0x10 +#define VCN_RAS_CNTL__MMSCH_READY__SHIFT 0x11 +#define VCN_RAS_CNTL__VCPU_VCODEC_IH_EN_MASK 0x00000001L +#define VCN_RAS_CNTL__MMSCH_FATAL_ERROR_EN_MASK 0x00000002L +#define VCN_RAS_CNTL__VCPU_VCODEC_PMI_EN_MASK 0x00000010L +#define VCN_RAS_CNTL__MMSCH_PMI_EN_MASK 0x00000020L +#define VCN_RAS_CNTL__VCPU_VCODEC_REARM_MASK 0x00000100L +#define VCN_RAS_CNTL__MMSCH_REARM_MASK 0x00000200L +#define VCN_RAS_CNTL__VCPU_VCODEC_STALL_EN_MASK 0x00001000L +#define VCN_RAS_CNTL__VCPU_VCODEC_READY_MASK 0x00010000L +#define VCN_RAS_CNTL__MMSCH_READY_MASK 0x00020000L + +//VCN 2_6_0 UVD_VCPU_INT_EN +#define UVD_VCPU_INT_EN__RASCNTL_VCPU_VCODEC_EN__SHIFT 0x16 +#define UVD_VCPU_INT_EN__RASCNTL_VCPU_VCODEC_EN_MASK 0x00400000L + +//VCN 2_6_0 UVD_SYS_INT_EN +#define UVD_SYS_INT_EN__RASCNTL_VCPU_VCODEC_EN_MASK 0x04000000L + /* JPEG 2_6_0 UVD_RAS_JPEG0_STATUS */ #define UVD_RAS_JPEG0_STATUS__POISONED_VF__SHIFT 0x0 #define UVD_RAS_JPEG0_STATUS__POISONED_PF__SHIFT 0x1f diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h index b5b1d073f8e2..b78360a71bc9 100644 --- a/drivers/gpu/drm/amd/include/atombios.h +++ b/drivers/gpu/drm/amd/include/atombios.h @@ -4386,7 +4386,7 @@ typedef struct _ATOM_GPIO_PIN_ASSIGNMENT typedef struct _ATOM_GPIO_PIN_LUT { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_GPIO_PIN_ASSIGNMENT asGPIO_Pin[1]; + ATOM_GPIO_PIN_ASSIGNMENT asGPIO_Pin[]; }ATOM_GPIO_PIN_LUT; /****************************************************************************/ @@ -4513,7 +4513,7 @@ typedef struct _ATOM_DISPLAY_OBJECT_PATH USHORT usSize; //the size of ATOM_DISPLAY_OBJECT_PATH USHORT usConnObjectId; //Connector Object ID USHORT usGPUObjectId; //GPU ID - USHORT usGraphicObjIds[1]; //1st Encoder Obj source from GPU to last Graphic Obj destinate to connector. + USHORT usGraphicObjIds[]; //1st Encoder Obj source from GPU to last Graphic Obj destinate to connector. }ATOM_DISPLAY_OBJECT_PATH; typedef struct _ATOM_DISPLAY_EXTERNAL_OBJECT_PATH @@ -4530,7 +4530,7 @@ typedef struct _ATOM_DISPLAY_OBJECT_PATH_TABLE UCHAR ucNumOfDispPath; UCHAR ucVersion; UCHAR ucPadding[2]; - ATOM_DISPLAY_OBJECT_PATH asDispPath[1]; + ATOM_DISPLAY_OBJECT_PATH asDispPath[]; }ATOM_DISPLAY_OBJECT_PATH_TABLE; typedef struct _ATOM_OBJECT //each object has this structure @@ -4545,7 +4545,7 @@ typedef struct _ATOM_OBJECT_TABLE //Above 4 object table { UCHAR ucNumberOfObjects; UCHAR ucPadding[3]; - ATOM_OBJECT asObjects[1]; + ATOM_OBJECT asObjects[]; }ATOM_OBJECT_TABLE; typedef struct _ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT //usSrcDstTableOffset pointing to this structure @@ -4733,7 +4733,7 @@ typedef struct _ATOM_CONNECTOR_DEVICE_TAG_RECORD ATOM_COMMON_RECORD_HEADER sheader; UCHAR ucNumberOfDevice; UCHAR ucReserved; - ATOM_CONNECTOR_DEVICE_TAG asDeviceTag[1]; //This Id is same as "ATOM_DEVICE_XXX_SUPPORT", 1 is only for allocation + ATOM_CONNECTOR_DEVICE_TAG asDeviceTag[]; //This Id is same as "ATOM_DEVICE_XXX_SUPPORT" }ATOM_CONNECTOR_DEVICE_TAG_RECORD; @@ -4793,7 +4793,7 @@ typedef struct _ATOM_OBJECT_GPIO_CNTL_RECORD ATOM_COMMON_RECORD_HEADER sheader; UCHAR ucFlags; // Future expnadibility UCHAR ucNumberOfPins; // Number of GPIO pins used to control the object - ATOM_GPIO_PIN_CONTROL_PAIR asGpio[1]; // the real gpio pin pair determined by number of pins ucNumberOfPins + ATOM_GPIO_PIN_CONTROL_PAIR asGpio[]; // the real gpio pin pair determined by number of pins ucNumberOfPins }ATOM_OBJECT_GPIO_CNTL_RECORD; //Definitions for GPIO pin state @@ -4982,7 +4982,7 @@ typedef struct _ATOM_BRACKET_LAYOUT_RECORD UCHAR ucWidth; UCHAR ucConnNum; UCHAR ucReserved; - ATOM_CONNECTOR_LAYOUT_INFO asConnInfo[1]; + ATOM_CONNECTOR_LAYOUT_INFO asConnInfo[]; }ATOM_BRACKET_LAYOUT_RECORD; @@ -5146,7 +5146,7 @@ typedef struct _ATOM_I2C_VOLTAGE_OBJECT_V3 UCHAR ucVoltageControlOffset; UCHAR ucVoltageControlFlag; // Bit0: 0 - One byte data; 1 - Two byte data UCHAR ulReserved[3]; - VOLTAGE_LUT_ENTRY asVolI2cLut[1]; // end with 0xff + VOLTAGE_LUT_ENTRY asVolI2cLut[]; // end with 0xff }ATOM_I2C_VOLTAGE_OBJECT_V3; // ATOM_I2C_VOLTAGE_OBJECT_V3.ucVoltageControlFlag @@ -5161,7 +5161,7 @@ typedef struct _ATOM_GPIO_VOLTAGE_OBJECT_V3 UCHAR ucPhaseDelay; // phase delay in unit of micro second UCHAR ucReserved; ULONG ulGpioMaskVal; // GPIO Mask value - VOLTAGE_LUT_ENTRY_V2 asVolGpioLut[1]; + VOLTAGE_LUT_ENTRY_V2 asVolGpioLut[]; }ATOM_GPIO_VOLTAGE_OBJECT_V3; typedef struct _ATOM_LEAKAGE_VOLTAGE_OBJECT_V3 @@ -5171,7 +5171,7 @@ typedef struct _ATOM_LEAKAGE_VOLTAGE_OBJECT_V3 UCHAR ucLeakageEntryNum; // indicate the entry number of LeakageId/Voltage Lut table UCHAR ucReserved[2]; ULONG ulMaxVoltageLevel; - LEAKAGE_VOLTAGE_LUT_ENTRY_V2 asLeakageIdLut[1]; + LEAKAGE_VOLTAGE_LUT_ENTRY_V2 asLeakageIdLut[]; }ATOM_LEAKAGE_VOLTAGE_OBJECT_V3; @@ -6599,7 +6599,7 @@ typedef struct _ATOM_FUSION_SYSTEM_INFO_V3 typedef struct _ATOM_I2C_DATA_RECORD { UCHAR ucNunberOfBytes; //Indicates how many bytes SW needs to write to the external ASIC for one block, besides to "Start" and "Stop" - UCHAR ucI2CData[1]; //I2C data in bytes, should be less than 16 bytes usually + UCHAR ucI2CData[]; //I2C data in bytes, should be less than 16 bytes usually }ATOM_I2C_DATA_RECORD; @@ -6610,14 +6610,14 @@ typedef struct _ATOM_I2C_DEVICE_SETUP_INFO UCHAR ucSSChipID; //SS chip being used UCHAR ucSSChipSlaveAddr; //Slave Address to set up this SS chip UCHAR ucNumOfI2CDataRecords; //number of data block - ATOM_I2C_DATA_RECORD asI2CData[1]; + ATOM_I2C_DATA_RECORD asI2CData[]; }ATOM_I2C_DEVICE_SETUP_INFO; //========================================================================================== typedef struct _ATOM_ASIC_MVDD_INFO { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_I2C_DEVICE_SETUP_INFO asI2CSetup[1]; + ATOM_I2C_DEVICE_SETUP_INFO asI2CSetup[]; }ATOM_ASIC_MVDD_INFO; //========================================================================================== @@ -6679,7 +6679,7 @@ typedef struct _ATOM_ASIC_INTERNAL_SS_INFO typedef struct _ATOM_ASIC_INTERNAL_SS_INFO_V2 { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_ASIC_SS_ASSIGNMENT_V2 asSpreadSpectrum[1]; //this is point only. + ATOM_ASIC_SS_ASSIGNMENT_V2 asSpreadSpectrum[]; //this is point only. }ATOM_ASIC_INTERNAL_SS_INFO_V2; typedef struct _ATOM_ASIC_SS_ASSIGNMENT_V3 @@ -6701,7 +6701,7 @@ typedef struct _ATOM_ASIC_SS_ASSIGNMENT_V3 typedef struct _ATOM_ASIC_INTERNAL_SS_INFO_V3 { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_ASIC_SS_ASSIGNMENT_V3 asSpreadSpectrum[1]; //this is pointer only. + ATOM_ASIC_SS_ASSIGNMENT_V3 asSpreadSpectrum[]; //this is pointer only. }ATOM_ASIC_INTERNAL_SS_INFO_V3; @@ -9292,7 +9292,7 @@ typedef struct { typedef struct { VFCT_IMAGE_HEADER VbiosHeader; - UCHAR VbiosContent[1]; + UCHAR VbiosContent[]; }GOP_VBIOS_CONTENT; typedef struct { diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index ff855cb21d3f..bbe1337a8cee 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -705,20 +705,65 @@ struct atom_gpio_pin_lut_v2_1 }; -/* - *************************************************************************** - Data Table vram_usagebyfirmware structure - *************************************************************************** -*/ +/* + * VBIOS/PRE-OS always reserve a FB region at the top of frame buffer. driver should not write + * access that region. driver can allocate their own reservation region as long as it does not + * overlap firwmare's reservation region. + * if (pre-NV1X) atom data table firmwareInfoTable version < 3.3: + * in this case, atom data table vram_usagebyfirmwareTable version always <= 2.1 + * if VBIOS/UEFI GOP is posted: + * VBIOS/UEFIGOP update used_by_firmware_in_kb = total reserved size by VBIOS + * update start_address_in_kb = total_mem_size_in_kb - used_by_firmware_in_kb; + * ( total_mem_size_in_kb = reg(CONFIG_MEMSIZE)<<10) + * driver can allocate driver reservation region under firmware reservation, + * used_by_driver_in_kb = driver reservation size + * driver reservation start address = (start_address_in_kb - used_by_driver_in_kb) + * Comment1[hchan]: There is only one reservation at the beginning of the FB reserved by + * host driver. Host driver would overwrite the table with the following + * used_by_firmware_in_kb = total reserved size for pf-vf info exchange and + * set SRIOV_MSG_SHARE_RESERVATION mask start_address_in_kb = 0 + * else there is no VBIOS reservation region: + * driver must allocate driver reservation region at top of FB. + * driver set used_by_driver_in_kb = driver reservation size + * driver reservation start address = (total_mem_size_in_kb - used_by_driver_in_kb) + * same as Comment1 + * else (NV1X and after): + * if VBIOS/UEFI GOP is posted: + * VBIOS/UEFIGOP update: + * used_by_firmware_in_kb = atom_firmware_Info_v3_3.fw_reserved_size_in_kb; + * start_address_in_kb = total_mem_size_in_kb - used_by_firmware_in_kb; + * (total_mem_size_in_kb = reg(CONFIG_MEMSIZE)<<10) + * if vram_usagebyfirmwareTable version <= 2.1: + * driver can allocate driver reservation region under firmware reservation, + * driver set used_by_driver_in_kb = driver reservation size + * driver reservation start address = start_address_in_kb - used_by_driver_in_kb + * same as Comment1 + * else driver can: + * allocate it reservation any place as long as it does overlap pre-OS FW reservation area + * set used_by_driver_region0_in_kb = driver reservation size + * set driver_region0_start_address_in_kb = driver reservation region start address + * Comment2[hchan]: Host driver can set used_by_firmware_in_kb and start_address_in_kb to + * zero as the reservation for VF as it doesn’t exist. And Host driver should also + * update atom_firmware_Info table to remove the same VBIOS reservation as well. + */ struct vram_usagebyfirmware_v2_1 { - struct atom_common_table_header table_header; - uint32_t start_address_in_kb; - uint16_t used_by_firmware_in_kb; - uint16_t used_by_driver_in_kb; + struct atom_common_table_header table_header; + uint32_t start_address_in_kb; + uint16_t used_by_firmware_in_kb; + uint16_t used_by_driver_in_kb; }; +struct vram_usagebyfirmware_v2_2 { + struct atom_common_table_header table_header; + uint32_t fw_region_start_address_in_kb; + uint16_t used_by_firmware_in_kb; + uint16_t reserved; + uint32_t driver_region0_start_address_in_kb; + uint32_t used_by_driver_region0_in_kb; + uint32_t reserved32[7]; +}; /* *************************************************************************** diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_4_0.h index a81138c9e491..03cfa0517df2 100644 --- a/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_4_0.h +++ b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_4_0.h @@ -38,4 +38,7 @@ #define VCN_4_0__SRCID__JPEG6_DECODE 174 // 0xae JRBC6 Decode interrupt #define VCN_4_0__SRCID__JPEG7_DECODE 175 // 0xaf JRBC7 Decode interrupt +#define VCN_4_0__SRCID_UVD_POISON 160 +#define VCN_4_0__SRCID_DJPEG0_POISON 161 +#define VCN_4_0__SRCID_EJPEG0_POISON 162 #endif diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h index 7e85cdc5bd34..dc694cb246d9 100644 --- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h +++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h @@ -222,7 +222,11 @@ union MESAPI_SET_HW_RESOURCES { uint32_t apply_grbm_remote_register_dummy_read_wa : 1; uint32_t second_gfx_pipe_enabled : 1; uint32_t enable_level_process_quantum_check : 1; - uint32_t reserved : 25; + uint32_t legacy_sch_mode : 1; + uint32_t disable_add_queue_wptr_mc_addr : 1; + uint32_t enable_mes_event_int_logging : 1; + uint32_t enable_reg_active_poll : 1; + uint32_t reserved : 21; }; uint32_t uint32_t_all; }; diff --git a/drivers/gpu/drm/amd/include/yellow_carp_offset.h b/drivers/gpu/drm/amd/include/yellow_carp_offset.h index 28a56b56bcaf..0fea6a746611 100644 --- a/drivers/gpu/drm/amd/include/yellow_carp_offset.h +++ b/drivers/gpu/drm/amd/include/yellow_carp_offset.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT #ifndef YELLOW_CARP_OFFSET_H #define YELLOW_CARP_OFFSET_H diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 1159ae114dd0..304190d5c9d2 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1508,7 +1508,7 @@ static void pp_pm_compute_clocks(void *handle) struct pp_hwmgr *hwmgr = handle; struct amdgpu_device *adev = hwmgr->adev; - if (!amdgpu_device_has_dc_support(adev)) { + if (!adev->dc_enabled) { amdgpu_dpm_get_active_displays(adev); adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count; adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c index dad3e3741a4e..190af79f3236 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c @@ -67,22 +67,21 @@ int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr, int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr, uint32_t *speed) { - uint32_t current_rpm; - uint32_t percent = 0; - - if (hwmgr->thermal_controller.fanInfo.bNoFan) - return 0; + struct amdgpu_device *adev = hwmgr->adev; + uint32_t duty100, duty; + uint64_t tmp64; - if (vega10_get_current_rpm(hwmgr, ¤t_rpm)) - return -1; + duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1), + CG_FDO_CTRL1, FMAX_DUTY100); + duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS), + CG_THERMAL_STATUS, FDO_PWM_DUTY); - if (hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM != 0) - percent = current_rpm * 255 / - hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM; + if (!duty100) + return -EINVAL; - *speed = MIN(percent, 255); + tmp64 = (uint64_t)duty * 255; + do_div(tmp64, duty100); + *speed = MIN((uint32_t)tmp64, 255); return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 97b3ad369046..b30684c84e20 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -2961,7 +2961,8 @@ static int vega20_odn_edit_dpm_table(struct pp_hwmgr *hwmgr, data->od8_settings.od8_settings_array; OverDriveTable_t *od_table = &(data->smc_state_table.overdrive_table); - int32_t input_index, input_clk, input_vol, i; + int32_t input_clk, input_vol, i; + uint32_t input_index; int od8_id; int ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 4fe75dd2b329..ca3beb5d8f27 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -161,7 +161,7 @@ int smu_get_dpm_freq_range(struct smu_context *smu, int smu_set_gfx_power_up_by_imu(struct smu_context *smu) { - if (!smu->ppt_funcs && !smu->ppt_funcs->set_gfx_power_up_by_imu) + if (!smu->ppt_funcs || !smu->ppt_funcs->set_gfx_power_up_by_imu) return -EOPNOTSUPP; return smu->ppt_funcs->set_gfx_power_up_by_imu(smu); @@ -585,6 +585,7 @@ static int smu_set_funcs(struct amdgpu_device *adev) yellow_carp_set_ppt_funcs(smu); break; case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): smu_v13_0_4_set_ppt_funcs(smu); break; case IP_VERSION(13, 0, 5): @@ -1156,22 +1157,21 @@ static int smu_smc_hw_setup(struct smu_context *smu) uint64_t features_supported; int ret = 0; - if (adev->in_suspend && smu_is_dpm_running(smu)) { - dev_info(adev->dev, "dpm has been enabled\n"); - /* this is needed specifically */ - switch (adev->ip_versions[MP1_HWIP][0]) { - case IP_VERSION(11, 0, 7): - case IP_VERSION(11, 0, 11): - case IP_VERSION(11, 5, 0): - case IP_VERSION(11, 0, 12): + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(11, 0, 7): + case IP_VERSION(11, 0, 11): + case IP_VERSION(11, 5, 0): + case IP_VERSION(11, 0, 12): + if (adev->in_suspend && smu_is_dpm_running(smu)) { + dev_info(adev->dev, "dpm has been enabled\n"); ret = smu_system_features_control(smu, true); if (ret) dev_err(adev->dev, "Failed system features control!\n"); - break; - default: - break; + return ret; } - return ret; + break; + default: + break; } ret = smu_init_display_count(smu, 0); @@ -1449,6 +1449,7 @@ static int smu_disable_dpms(struct smu_context *smu) switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 0): case IP_VERSION(13, 0, 7): + case IP_VERSION(13, 0, 10): return 0; default: break; @@ -1517,7 +1518,7 @@ static int smu_disable_dpms(struct smu_context *smu) } if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2) && - adev->gfx.rlc.funcs->stop) + !amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs->stop) adev->gfx.rlc.funcs->stop(adev); return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index e2fa3b066b96..3bc4128a22ac 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -168,6 +168,7 @@ struct smu_temperature_range { int mem_crit_max; int mem_emergency_max; int software_shutdown_temp; + int software_shutdown_temp_offset; }; struct smu_state_validation_block { @@ -568,6 +569,10 @@ struct smu_context u32 param_reg; u32 msg_reg; u32 resp_reg; + + u32 debug_param_reg; + u32 debug_msg_reg; + u32 debug_resp_reg; }; struct i2c_adapter; @@ -1388,6 +1393,14 @@ enum smu_cmn2asic_mapping_type { CMN2ASIC_MAPPING_WORKLOAD, }; +enum smu_baco_seq { + BACO_SEQ_BACO = 0, + BACO_SEQ_MSR, + BACO_SEQ_BAMACO, + BACO_SEQ_ULPS, + BACO_SEQ_COUNT, +}; + #define MSG_MAP(msg, index, valid_in_vf) \ [SMU_MSG_##msg] = {1, (index), (valid_in_vf)} diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h index b76f0f7e4299..d6b964cf73bd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h @@ -522,9 +522,9 @@ typedef enum { TEMP_HOTSPOT_M, TEMP_MEM, TEMP_VR_GFX, + TEMP_VR_SOC, TEMP_VR_MEM0, TEMP_VR_MEM1, - TEMP_VR_SOC, TEMP_VR_U, TEMP_LIQUID0, TEMP_LIQUID1, diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h index 25c08f963f49..d6b13933a98f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h @@ -25,10 +25,10 @@ // *** IMPORTANT *** // PMFW TEAM: Always increment the interface version on any change to this file -#define SMU13_DRIVER_IF_VERSION 0x2C +#define SMU13_DRIVER_IF_VERSION 0x35 //Increment this version if SkuTable_t or BoardTable_t change -#define PPTABLE_VERSION 0x20 +#define PPTABLE_VERSION 0x27 #define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_SOCCLK_DPM_LEVELS 8 @@ -96,7 +96,7 @@ #define FEATURE_MEM_TEMP_READ_BIT 47 #define FEATURE_ATHUB_MMHUB_PG_BIT 48 #define FEATURE_SOC_PCC_BIT 49 -#define FEATURE_SPARE_50_BIT 50 +#define FEATURE_EDC_PWRBRK_BIT 50 #define FEATURE_SPARE_51_BIT 51 #define FEATURE_SPARE_52_BIT 52 #define FEATURE_SPARE_53_BIT 53 @@ -282,15 +282,15 @@ typedef enum { } I2cControllerPort_e; typedef enum { - I2C_CONTROLLER_NAME_VR_GFX = 0, - I2C_CONTROLLER_NAME_VR_SOC, - I2C_CONTROLLER_NAME_VR_VMEMP, - I2C_CONTROLLER_NAME_VR_VDDIO, - I2C_CONTROLLER_NAME_LIQUID0, - I2C_CONTROLLER_NAME_LIQUID1, - I2C_CONTROLLER_NAME_PLX, - I2C_CONTROLLER_NAME_OTHER, - I2C_CONTROLLER_NAME_COUNT, + I2C_CONTROLLER_NAME_VR_GFX = 0, + I2C_CONTROLLER_NAME_VR_SOC, + I2C_CONTROLLER_NAME_VR_VMEMP, + I2C_CONTROLLER_NAME_VR_VDDIO, + I2C_CONTROLLER_NAME_LIQUID0, + I2C_CONTROLLER_NAME_LIQUID1, + I2C_CONTROLLER_NAME_PLX, + I2C_CONTROLLER_NAME_FAN_INTAKE, + I2C_CONTROLLER_NAME_COUNT, } I2cControllerName_e; typedef enum { @@ -302,6 +302,7 @@ typedef enum { I2C_CONTROLLER_THROTTLER_LIQUID0, I2C_CONTROLLER_THROTTLER_LIQUID1, I2C_CONTROLLER_THROTTLER_PLX, + I2C_CONTROLLER_THROTTLER_FAN_INTAKE, I2C_CONTROLLER_THROTTLER_INA3221, I2C_CONTROLLER_THROTTLER_COUNT, } I2cControllerThrottler_e; @@ -309,8 +310,9 @@ typedef enum { typedef enum { I2C_CONTROLLER_PROTOCOL_VR_XPDE132G5, I2C_CONTROLLER_PROTOCOL_VR_IR35217, - I2C_CONTROLLER_PROTOCOL_TMP_TMP102A, + I2C_CONTROLLER_PROTOCOL_TMP_MAX31875, I2C_CONTROLLER_PROTOCOL_INA3221, + I2C_CONTROLLER_PROTOCOL_TMP_MAX6604, I2C_CONTROLLER_PROTOCOL_COUNT, } I2cControllerProtocol_e; @@ -690,6 +692,9 @@ typedef struct { #define PP_OD_FEATURE_UCLK_BIT 8 #define PP_OD_FEATURE_ZERO_FAN_BIT 9 #define PP_OD_FEATURE_TEMPERATURE_BIT 10 +#define PP_OD_FEATURE_POWER_FEATURE_CTRL_BIT 11 +#define PP_OD_FEATURE_ASIC_TDC_BIT 12 +#define PP_OD_FEATURE_COUNT 13 typedef enum { PP_OD_POWER_FEATURE_ALWAYS_ENABLED, @@ -697,6 +702,11 @@ typedef enum { PP_OD_POWER_FEATURE_ALWAYS_DISABLED, } PP_OD_POWER_FEATURE_e; +typedef enum { + FAN_MODE_AUTO = 0, + FAN_MODE_MANUAL_LINEAR, +} FanMode_e; + typedef struct { uint32_t FeatureCtrlMask; @@ -708,8 +718,8 @@ typedef struct { uint8_t RuntimePwrSavingFeaturesCtrl; //Frequency changes - int16_t GfxclkFmin; // MHz - int16_t GfxclkFmax; // MHz + int16_t GfxclkFmin; // MHz + int16_t GfxclkFmax; // MHz uint16_t UclkFmin; // MHz uint16_t UclkFmax; // MHz @@ -730,7 +740,12 @@ typedef struct { uint8_t MaxOpTemp; uint8_t Padding[4]; - uint32_t Spare[12]; + uint16_t GfxVoltageFullCtrlMode; + uint16_t GfxclkFullCtrlMode; + uint16_t UclkFullCtrlMode; + int16_t AsicTdc; + + uint32_t Spare[10]; uint32_t MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround } OverDriveTable_t; @@ -748,8 +763,8 @@ typedef struct { uint8_t IdlePwrSavingFeaturesCtrl; uint8_t RuntimePwrSavingFeaturesCtrl; - uint16_t GfxclkFmin; // MHz - uint16_t GfxclkFmax; // MHz + int16_t GfxclkFmin; // MHz + int16_t GfxclkFmax; // MHz uint16_t UclkFmin; // MHz uint16_t UclkFmax; // MHz @@ -769,7 +784,12 @@ typedef struct { uint8_t MaxOpTemp; uint8_t Padding[4]; - uint32_t Spare[12]; + uint16_t GfxVoltageFullCtrlMode; + uint16_t GfxclkFullCtrlMode; + uint16_t UclkFullCtrlMode; + int16_t AsicTdc; + + uint32_t Spare[10]; } OverDriveLimits_t; @@ -903,7 +923,8 @@ typedef struct { uint16_t FanStartTempMin; uint16_t FanStartTempMax; - uint32_t Spare[12]; + uint16_t PowerMinPpt0[POWER_SOURCE_COUNT]; + uint32_t Spare[11]; } MsgLimits_t; @@ -1086,11 +1107,13 @@ typedef struct { uint32_t GfxoffSpare[15]; // GFX GPO - float DfllBtcMasterScalerM; + uint32_t DfllBtcMasterScalerM; int32_t DfllBtcMasterScalerB; - float DfllBtcSlaveScalerM; + uint32_t DfllBtcSlaveScalerM; int32_t DfllBtcSlaveScalerB; - uint32_t GfxGpoSpare[12]; + uint32_t DfllPccAsWaitCtrl; //GDFLL_AS_WAIT_CTRL_PCC register value to be passed to RLC msg + uint32_t DfllPccAsStepCtrl; //GDFLL_AS_STEP_CTRL_PCC register value to be passed to RLC msg + uint32_t GfxGpoSpare[10]; // GFX DCS @@ -1106,7 +1129,10 @@ typedef struct { uint16_t DcsTimeout; //This is the amount of time SMU FW waits for RLC to put GFX into GFXOFF before reverting to the fallback mechanism of throttling GFXCLK to Fmin. - uint32_t DcsSpare[16]; + uint32_t DcsSpare[14]; + + // UCLK section + uint16_t ShadowFreqTableUclk[NUM_UCLK_DPM_LEVELS]; // In MHz // UCLK section uint8_t UseStrobeModeOptimizations; //Set to indicate that FW should use strobe mode optimizations @@ -1163,13 +1189,14 @@ typedef struct { uint16_t IntakeTempHighIntakeAcousticLimit; uint16_t IntakeTempAcouticLimitReleaseRate; - uint16_t FanStalledTempLimitOffset; + int16_t FanAbnormalTempLimitOffset; uint16_t FanStalledTriggerRpm; - uint16_t FanAbnormalTriggerRpm; - uint16_t FanPadding; - - uint32_t FanSpare[14]; + uint16_t FanAbnormalTriggerRpmCoeff; + uint16_t FanAbnormalDetectionEnable; + uint8_t FanIntakeSensorSupport; + uint8_t FanIntakePadding[3]; + uint32_t FanSpare[13]; // SECTION: VDD_GFX AVFS uint8_t OverrideGfxAvfsFuses; @@ -1193,7 +1220,6 @@ typedef struct { uint32_t dGbV_dT_vmin; uint32_t dGbV_dT_vmax; - //Unused: PMFW-9370 uint32_t V2F_vmin_range_low; uint32_t V2F_vmin_range_high; uint32_t V2F_vmax_range_low; @@ -1238,8 +1264,21 @@ typedef struct { // SECTION: Advanced Options uint32_t DebugOverrides; + // Section: Total Board Power idle vs active coefficients + uint8_t TotalBoardPowerSupport; + uint8_t TotalBoardPowerPadding[3]; + + int16_t TotalIdleBoardPowerM; + int16_t TotalIdleBoardPowerB; + int16_t TotalBoardPowerM; + int16_t TotalBoardPowerB; + + QuadraticInt_t qFeffCoeffGameClock[POWER_SOURCE_COUNT]; + QuadraticInt_t qFeffCoeffBaseClock[POWER_SOURCE_COUNT]; + QuadraticInt_t qFeffCoeffBoostClock[POWER_SOURCE_COUNT]; + // SECTION: Sku Reserved - uint32_t Spare[64]; + uint32_t Spare[43]; // Padding for MMHUB - do not modify this uint32_t MmHubPadding[8]; @@ -1304,7 +1343,8 @@ typedef struct { // SECTION: Clock Spread Spectrum // UCLK Spread Spectrum - uint16_t UclkSpreadPadding; + uint8_t UclkTrainingModeSpreadPercent; // Q4.4 + uint8_t UclkSpreadPadding; uint16_t UclkSpreadFreq; // kHz // UCLK Spread Spectrum @@ -1317,11 +1357,7 @@ typedef struct { // Section: Memory Config uint8_t DramWidth; // Width of interface to the channel for each DRAM module. See DRAM_BIT_WIDTH_TYPE_e - uint8_t PaddingMem1[3]; - - // Section: Total Board Power - uint16_t TotalBoardPower; //Only needed for TCP Estimated case, where TCP = TGP+Total Board Power - uint16_t BoardPowerPadding; + uint8_t PaddingMem1[7]; // SECTION: UMC feature flags uint8_t HsrEnabled; @@ -1423,8 +1459,11 @@ typedef struct { uint16_t Vcn1ActivityPercentage ; uint32_t EnergyAccumulator; - uint16_t AverageSocketPower ; + uint16_t AverageSocketPower; + uint16_t AverageTotalBoardPower; + uint16_t AvgTemperature[TEMP_COUNT]; + uint16_t AvgTemperatureFanIntake; uint8_t PcieRate ; uint8_t PcieWidth ; @@ -1592,5 +1631,7 @@ typedef struct { #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D0 0x5 #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D3 0x6 #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING 0x7 +#define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8 +#define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9 #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h index 9ebb8f39732a..8b8266890a10 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h @@ -131,7 +131,13 @@ #define PPSMC_MSG_EnableAudioStutterWA 0x44 #define PPSMC_MSG_PowerUpUmsch 0x45 #define PPSMC_MSG_PowerDownUmsch 0x46 -#define PPSMC_Message_Count 0x47 +#define PPSMC_MSG_SetDcsArch 0x47 +#define PPSMC_MSG_TriggerVFFLR 0x48 +#define PPSMC_MSG_SetNumBadMemoryPagesRetired 0x49 +#define PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel 0x4A +#define PPSMC_MSG_SetPriorityDeltaGain 0x4B +#define PPSMC_MSG_AllowIHHostInterrupt 0x4C +#define PPSMC_Message_Count 0x4D //Debug Dump Message #define DEBUGSMC_MSG_TestMessage 0x1 diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h index d9b0cd752200..f4d6c07b56ea 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h @@ -54,14 +54,14 @@ #define PPSMC_MSG_TestMessage 0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team #define PPSMC_MSG_GetPmfwVersion 0x02 ///< Get PMFW version #define PPSMC_MSG_GetDriverIfVersion 0x03 ///< Get PMFW_DRIVER_IF version -#define PPSMC_MSG_EnableGfxOff 0x04 ///< Enable GFXOFF -#define PPSMC_MSG_DisableGfxOff 0x05 ///< Disable GFXOFF +#define PPSMC_MSG_SPARE0 0x04 ///< SPARE +#define PPSMC_MSG_SPARE1 0x05 ///< SPARE #define PPSMC_MSG_PowerDownVcn 0x06 ///< Power down VCN #define PPSMC_MSG_PowerUpVcn 0x07 ///< Power up VCN; VCN is power gated by default #define PPSMC_MSG_SetHardMinVcn 0x08 ///< For wireless display #define PPSMC_MSG_SetSoftMinGfxclk 0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz -#define PPSMC_MSG_ActiveProcessNotify 0x0A ///< Needs update -#define PPSMC_MSG_ForcePowerDownGfx 0x0B ///< Force power down GFX, i.e. enter GFXOFF +#define PPSMC_MSG_SPARE2 0x0A ///< SPARE +#define PPSMC_MSG_SPARE3 0x0B ///< SPARE #define PPSMC_MSG_PrepareMp1ForUnload 0x0C ///< Prepare PMFW for GFX driver unload #define PPSMC_MSG_SetDriverDramAddrHigh 0x0D ///< Set high 32 bits of DRAM address for Driver table transfer #define PPSMC_MSG_SetDriverDramAddrLow 0x0E ///< Set low 32 bits of DRAM address for Driver table transfer @@ -73,8 +73,7 @@ #define PPSMC_MSG_SetSoftMinFclk 0x14 ///< Set hard min for FCLK #define PPSMC_MSG_SetSoftMinVcn 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK) - -#define PPSMC_MSG_EnableGfxImu 0x16 ///< Needs update +#define PPSMC_MSG_EnableGfxImu 0x16 ///< Enable GFX IMU #define PPSMC_MSG_GetGfxclkFrequency 0x17 ///< Get GFX clock frequency #define PPSMC_MSG_GetFclkFrequency 0x18 ///< Get FCLK frequency @@ -102,8 +101,8 @@ #define PPSMC_MSG_SetHardMinIspxclkByFreq 0x2C ///< Set HardMin by frequency for ISPXCLK #define PPSMC_MSG_PowerDownUmsch 0x2D ///< Power down VCN.UMSCH (aka VSCH) scheduler #define PPSMC_MSG_PowerUpUmsch 0x2E ///< Power up VCN.UMSCH (aka VSCH) scheduler -#define PPSMC_Message_IspStutterOn_MmhubPgDis 0x2F ///< ISP StutterOn mmHub PgDis -#define PPSMC_Message_IspStutterOff_MmhubPgEn 0x30 ///< ISP StufferOff mmHub PgEn +#define PPSMC_MSG_IspStutterOn_MmhubPgDis 0x2F ///< ISP StutterOn mmHub PgDis +#define PPSMC_MSG_IspStutterOff_MmhubPgEn 0x30 ///< ISP StufferOff mmHub PgEn #define PPSMC_Message_Count 0x31 ///< Total number of PPSMC messages /** @}*/ diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h index 58098b82df66..4180c71d930f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -239,7 +239,10 @@ __SMU_DUMMY_MAP(DriverMode2Reset), \ __SMU_DUMMY_MAP(GetGfxOffStatus), \ __SMU_DUMMY_MAP(GetGfxOffEntryCount), \ - __SMU_DUMMY_MAP(LogGfxOffResidency), + __SMU_DUMMY_MAP(LogGfxOffResidency), \ + __SMU_DUMMY_MAP(SetNumBadMemoryPagesRetired), \ + __SMU_DUMMY_MAP(SetBadMemoryPagesRetiredFlagsPerChannel), \ + __SMU_DUMMY_MAP(AllowGpo), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0.h index a9215494dcdd..d466db6f0ad4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v11_0.h @@ -147,14 +147,6 @@ struct smu_11_5_power_context { uint32_t max_fast_ppt_limit; }; -enum smu_v11_0_baco_seq { - BACO_SEQ_BACO = 0, - BACO_SEQ_MSR, - BACO_SEQ_BAMACO, - BACO_SEQ_ULPS, - BACO_SEQ_COUNT, -}; - #if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) int smu_v11_0_init_microcode(struct smu_context *smu); @@ -257,7 +249,7 @@ int smu_v11_0_baco_enter(struct smu_context *smu); int smu_v11_0_baco_exit(struct smu_context *smu); int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, - enum smu_v11_0_baco_seq baco_seq); + enum smu_baco_seq baco_seq); int smu_v11_0_mode1_reset(struct smu_context *smu); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 80fb583b18d9..e8c6febb8b64 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -28,10 +28,11 @@ #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08 +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x34 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x35 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms @@ -124,14 +125,6 @@ struct smu_13_0_power_context { enum smu_13_0_power_state power_state; }; -enum smu_v13_0_baco_seq { - BACO_SEQ_BACO = 0, - BACO_SEQ_MSR, - BACO_SEQ_BAMACO, - BACO_SEQ_ULPS, - BACO_SEQ_COUNT, -}; - #if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) int smu_v13_0_init_microcode(struct smu_context *smu); @@ -218,6 +211,9 @@ int smu_v13_0_set_azalia_d3_pme(struct smu_context *smu); int smu_v13_0_get_max_sustainable_clocks_by_dc(struct smu_context *smu, struct pp_smu_nv_clock_table *max_clocks); +int smu_v13_0_baco_set_armd3_sequence(struct smu_context *smu, + enum smu_baco_seq baco_seq); + bool smu_v13_0_baco_is_support(struct smu_context *smu); enum smu_baco_state smu_v13_0_baco_get_state(struct smu_context *smu); @@ -277,6 +273,9 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu); int smu_v13_0_run_btc(struct smu_context *smu); +int smu_v13_0_gpo_control(struct smu_context *smu, + bool enablement); + int smu_v13_0_deep_sleep_control(struct smu_context *smu, bool enablement); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 74996a8fb671..697e98a0a20a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -377,7 +377,13 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu) if (((adev->pdev->device == 0x73A1) && (adev->pdev->revision == 0x00)) || ((adev->pdev->device == 0x73BF) && - (adev->pdev->revision == 0xCF))) + (adev->pdev->revision == 0xCF)) || + ((adev->pdev->device == 0x7422) && + (adev->pdev->revision == 0x00)) || + ((adev->pdev->device == 0x73A3) && + (adev->pdev->revision == 0x00)) || + ((adev->pdev->device == 0x73E3) && + (adev->pdev->revision == 0x00))) smu_baco->platform_support = false; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index dccbd9f70723..ad66d57aa102 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -79,6 +79,17 @@ MODULE_FIRMWARE("amdgpu/beige_goby_smc.bin"); #define mmTHM_BACO_CNTL_ARCT 0xA7 #define mmTHM_BACO_CNTL_ARCT_BASE_IDX 0 +static void smu_v11_0_poll_baco_exit(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t data, loop = 0; + + do { + usleep_range(1000, 1100); + data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL); + } while ((data & 0x100) && (++loop < 100)); +} + int smu_v11_0_init_microcode(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -1576,7 +1587,7 @@ int smu_v11_0_set_azalia_d3_pme(struct smu_context *smu) } int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, - enum smu_v11_0_baco_seq baco_seq) + enum smu_baco_seq baco_seq) { return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ArmD3, baco_seq, NULL); } @@ -1588,6 +1599,10 @@ bool smu_v11_0_baco_is_support(struct smu_context *smu) if (amdgpu_sriov_vf(smu->adev) || !smu_baco->platform_support) return false; + /* return true if ASIC is in BACO state already */ + if (smu_v11_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER) + return true; + /* Arcturus does not support this bit mask */ if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) && !smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) @@ -1685,7 +1700,18 @@ int smu_v11_0_baco_enter(struct smu_context *smu) int smu_v11_0_baco_exit(struct smu_context *smu) { - return smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT); + int ret; + + ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT); + if (!ret) { + /* + * Poll BACO exit status to ensure FW has completed + * BACO exit process to avoid timing issues. + */ + smu_v11_0_poll_baco_exit(smu); + } + + return ret; } int smu_v11_0_mode1_reset(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 43fb102a65f5..e54b760b875b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -250,6 +250,7 @@ int smu_v13_0_check_fw_status(struct smu_context *smu) switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): mp1_fw_flags = RREG32_PCIE(MP1_Public | (smnMP1_V13_0_4_FIRMWARE_FLAGS & 0xffffffff)); break; @@ -289,6 +290,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_ALDE; break; case IP_VERSION(13, 0, 0): + smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0; + break; case IP_VERSION(13, 0, 10): smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10; break; @@ -301,6 +304,7 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_YELLOW_CARP; break; case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_4; break; case IP_VERSION(13, 0, 5): @@ -841,6 +845,7 @@ int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable) case IP_VERSION(13, 0, 7): case IP_VERSION(13, 0, 8): case IP_VERSION(13, 0, 10): + case IP_VERSION(13, 0, 11): if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) return 0; if (enable) @@ -1376,6 +1381,7 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, */ uint32_t ctxid = entry->src_data[0]; uint32_t data; + uint32_t high; if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { @@ -1432,6 +1438,36 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, schedule_work(&smu->throttling_logging_work); break; + case 0x8: + high = smu->thermal_range.software_shutdown_temp + + smu->thermal_range.software_shutdown_temp_offset; + high = min_t(typeof(high), + SMU_THERMAL_MAXIMUM_ALERT_TEMP, + high); + dev_emerg(adev->dev, "Reduce soft CTF limit to %d (by an offset %d)\n", + high, + smu->thermal_range.software_shutdown_temp_offset); + + data = RREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL); + data = REG_SET_FIELD(data, THM_THERMAL_INT_CTRL, + DIG_THERM_INTH, + (high & 0xff)); + data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); + WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); + break; + case 0x9: + high = min_t(typeof(high), + SMU_THERMAL_MAXIMUM_ALERT_TEMP, + smu->thermal_range.software_shutdown_temp); + dev_emerg(adev->dev, "Recover soft CTF limit to %d\n", high); + + data = RREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL); + data = REG_SET_FIELD(data, THM_THERMAL_INT_CTRL, + DIG_THERM_INTH, + (high & 0xff)); + data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); + WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); + break; } } } @@ -2146,6 +2182,21 @@ int smu_v13_0_run_btc(struct smu_context *smu) return res; } +int smu_v13_0_gpo_control(struct smu_context *smu, + bool enablement) +{ + int res; + + res = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_AllowGpo, + enablement ? 1 : 0, + NULL); + if (res) + dev_err(smu->adev->dev, "SetGpoAllow %d failed!\n", enablement); + + return res; +} + int smu_v13_0_deep_sleep_control(struct smu_context *smu, bool enablement) { @@ -2230,6 +2281,15 @@ int smu_v13_0_gfx_ulv_control(struct smu_context *smu, return ret; } +int smu_v13_0_baco_set_armd3_sequence(struct smu_context *smu, + enum smu_baco_seq baco_seq) +{ + return smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_ArmD3, + baco_seq, + NULL); +} + bool smu_v13_0_baco_is_support(struct smu_context *smu) { struct smu_baco_context *smu_baco = &smu->smu_baco; 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 29529328152d..9643b21c636a 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 @@ -70,6 +70,26 @@ #define MP0_MP1_DATA_REGION_SIZE_COMBOPPTABLE 0x4000 +#define mmMP1_SMN_C2PMSG_66 0x0282 +#define mmMP1_SMN_C2PMSG_66_BASE_IDX 0 + +#define mmMP1_SMN_C2PMSG_82 0x0292 +#define mmMP1_SMN_C2PMSG_82_BASE_IDX 0 + +#define mmMP1_SMN_C2PMSG_90 0x029a +#define mmMP1_SMN_C2PMSG_90_BASE_IDX 0 + +#define mmMP1_SMN_C2PMSG_75 0x028b +#define mmMP1_SMN_C2PMSG_75_BASE_IDX 0 + +#define mmMP1_SMN_C2PMSG_53 0x0275 +#define mmMP1_SMN_C2PMSG_53_BASE_IDX 0 + +#define mmMP1_SMN_C2PMSG_54 0x0276 +#define mmMP1_SMN_C2PMSG_54_BASE_IDX 0 + +#define DEBUGSMC_MSG_Mode1Reset 2 + static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 1), MSG_MAP(GetSmuVersion, PPSMC_MSG_GetSmuVersion, 1), @@ -120,6 +140,11 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(Mode1Reset, PPSMC_MSG_Mode1Reset, 0), MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareMp1ForUnload, 0), MSG_MAP(DFCstateControl, PPSMC_MSG_SetExternalClientDfCstateAllow, 0), + MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0), + MSG_MAP(SetNumBadMemoryPagesRetired, PPSMC_MSG_SetNumBadMemoryPagesRetired, 0), + MSG_MAP(SetBadMemoryPagesRetiredFlagsPerChannel, + PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel, 0), + MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), }; static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = { @@ -186,6 +211,8 @@ static struct cmn2asic_mapping smu_v13_0_0_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(MEM_TEMP_READ), FEA_MAP(ATHUB_MMHUB_PG), FEA_MAP(SOC_PCC), + [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, }; static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = { @@ -516,6 +543,23 @@ static int smu_v13_0_0_set_default_dpm_table(struct smu_context *smu) dpm_table); if (ret) return ret; + + /* + * Update the reported maximum shader clock to the value + * which can be guarded to be achieved on all cards. This + * is aligned with Window setting. And considering that value + * might be not the peak frequency the card can achieve, it + * is normal some real-time clock frequency can overtake this + * labelled maximum clock frequency(for example in pp_dpm_sclk + * sysfs output). + */ + if (skutable->DriverReportedClocks.GameClockAc && + (dpm_table->dpm_levels[dpm_table->count - 1].value > + skutable->DriverReportedClocks.GameClockAc)) { + dpm_table->dpm_levels[dpm_table->count - 1].value = + skutable->DriverReportedClocks.GameClockAc; + dpm_table->max = skutable->DriverReportedClocks.GameClockAc; + } } else { dpm_table->count = 1; dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.gfxclk / 100; @@ -778,6 +822,57 @@ static int smu_v13_0_0_get_smu_metrics_data(struct smu_context *smu, return ret; } +static int smu_v13_0_0_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + struct smu_13_0_dpm_context *dpm_context = + smu->smu_dpm.dpm_context; + struct smu_13_0_dpm_table *dpm_table; + + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + /* uclk dpm table */ + dpm_table = &dpm_context->dpm_tables.uclk_table; + break; + case SMU_GFXCLK: + case SMU_SCLK: + /* gfxclk dpm table */ + dpm_table = &dpm_context->dpm_tables.gfx_table; + break; + case SMU_SOCCLK: + /* socclk dpm table */ + dpm_table = &dpm_context->dpm_tables.soc_table; + break; + case SMU_FCLK: + /* fclk dpm table */ + dpm_table = &dpm_context->dpm_tables.fclk_table; + break; + case SMU_VCLK: + case SMU_VCLK1: + /* vclk dpm table */ + dpm_table = &dpm_context->dpm_tables.vclk_table; + break; + case SMU_DCLK: + case SMU_DCLK1: + /* dclk dpm table */ + dpm_table = &dpm_context->dpm_tables.dclk_table; + break; + default: + dev_err(smu->adev->dev, "Unsupported clock type!\n"); + return -EINVAL; + } + + if (min) + *min = dpm_table->min; + if (max) + *max = dpm_table->max; + + return 0; +} + static int smu_v13_0_0_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, void *data, @@ -1280,9 +1375,17 @@ static int smu_v13_0_0_populate_umd_state_clk(struct smu_context *smu) &dpm_context->dpm_tables.fclk_table; struct smu_umd_pstate_table *pstate_table = &smu->pstate_table; + struct smu_table_context *table_context = &smu->smu_table; + PPTable_t *pptable = table_context->driver_pptable; + DriverReportedClocks_t driver_clocks = + pptable->SkuTable.DriverReportedClocks; pstate_table->gfxclk_pstate.min = gfx_table->min; - pstate_table->gfxclk_pstate.peak = gfx_table->max; + if (driver_clocks.GameClockAc && + (driver_clocks.GameClockAc < gfx_table->max)) + pstate_table->gfxclk_pstate.peak = driver_clocks.GameClockAc; + else + pstate_table->gfxclk_pstate.peak = gfx_table->max; pstate_table->uclk_pstate.min = mem_table->min; pstate_table->uclk_pstate.peak = mem_table->max; @@ -1299,12 +1402,12 @@ static int smu_v13_0_0_populate_umd_state_clk(struct smu_context *smu) pstate_table->fclk_pstate.min = fclk_table->min; pstate_table->fclk_pstate.peak = fclk_table->max; - /* - * For now, just use the mininum clock frequency. - * TODO: update them when the real pstate settings available - */ - pstate_table->gfxclk_pstate.standard = gfx_table->min; - pstate_table->uclk_pstate.standard = mem_table->min; + if (driver_clocks.BaseClockAc && + driver_clocks.BaseClockAc < gfx_table->max) + pstate_table->gfxclk_pstate.standard = driver_clocks.BaseClockAc; + else + pstate_table->gfxclk_pstate.standard = gfx_table->max; + pstate_table->uclk_pstate.standard = mem_table->max; pstate_table->socclk_pstate.standard = soc_table->min; pstate_table->vclk_pstate.standard = vclk_table->min; pstate_table->dclk_pstate.standard = dclk_table->min; @@ -1338,12 +1441,23 @@ out: static int smu_v13_0_0_get_fan_speed_pwm(struct smu_context *smu, uint32_t *speed) { + int ret; + if (!speed) return -EINVAL; - return smu_v13_0_0_get_smu_metrics_data(smu, - METRICS_CURR_FANPWM, - speed); + ret = smu_v13_0_0_get_smu_metrics_data(smu, + METRICS_CURR_FANPWM, + speed); + if (ret) { + dev_err(smu->adev->dev, "Failed to get fan speed(PWM)!"); + return ret; + } + + /* Convert the PMFW output which is in percent to pwm(255) based */ + *speed = MIN(*speed * 255 / 100, 255); + + return 0; } static int smu_v13_0_0_get_fan_speed_rpm(struct smu_context *smu, @@ -1566,6 +1680,31 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, NULL); } +static int smu_v13_0_0_baco_enter(struct smu_context *smu) +{ + struct smu_baco_context *smu_baco = &smu->smu_baco; + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) + return smu_v13_0_baco_set_armd3_sequence(smu, + smu_baco->maco_support ? BACO_SEQ_BAMACO : BACO_SEQ_BACO); + else + return smu_v13_0_baco_enter(smu); +} + +static int smu_v13_0_0_baco_exit(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) { + /* Wait for PMFW handling for the Dstate change */ + usleep_range(10000, 11000); + return smu_v13_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); + } else { + return smu_v13_0_baco_exit(smu); + } +} + static bool smu_v13_0_0_is_mode1_reset_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -1763,6 +1902,69 @@ static int smu_v13_0_0_set_df_cstate(struct smu_context *smu, NULL); } +static int smu_v13_0_0_mode1_reset(struct smu_context *smu) +{ + int ret; + struct amdgpu_device *adev = smu->adev; + + if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 10)) + ret = smu_cmn_send_debug_smc_msg(smu, DEBUGSMC_MSG_Mode1Reset); + else + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_Mode1Reset, NULL); + + if (!ret) + msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS); + + return ret; +} + +static void smu_v13_0_0_set_smu_mailbox_registers(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + smu->param_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_82); + smu->msg_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_66); + smu->resp_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90); + + smu->debug_param_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_53); + smu->debug_msg_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_75); + smu->debug_resp_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_54); +} + +static int smu_v13_0_0_smu_send_bad_mem_page_num(struct smu_context *smu, + uint32_t size) +{ + int ret = 0; + + /* message SMU to update the bad page number on SMUBUS */ + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetNumBadMemoryPagesRetired, + size, NULL); + if (ret) + dev_err(smu->adev->dev, + "[%s] failed to message SMU to update bad memory pages number\n", + __func__); + + return ret; +} + +static int smu_v13_0_0_send_bad_mem_channel_flag(struct smu_context *smu, + uint32_t size) +{ + int ret = 0; + + /* message SMU to update the bad channel info on SMUBUS */ + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_SetBadMemoryPagesRetiredFlagsPerChannel, + size, NULL); + if (ret) + dev_err(smu->adev->dev, + "[%s] failed to message SMU to update bad memory pages channel info\n", + __func__); + + return ret; +} + static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .get_allowed_feature_mask = smu_v13_0_0_get_allowed_feature_mask, .set_default_dpm_table = smu_v13_0_0_set_default_dpm_table, @@ -1787,7 +1989,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .get_enabled_mask = smu_cmn_get_enabled_mask, .dpm_set_vcn_enable = smu_v13_0_set_vcn_enable, .dpm_set_jpeg_enable = smu_v13_0_set_jpeg_enable, - .get_dpm_ultimate_freq = smu_v13_0_get_dpm_ultimate_freq, + .get_dpm_ultimate_freq = smu_v13_0_0_get_dpm_ultimate_freq, .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .read_sensor = smu_v13_0_0_read_sensor, .feature_is_enabled = smu_cmn_feature_is_enabled, @@ -1827,12 +2029,15 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .baco_is_support = smu_v13_0_baco_is_support, .baco_get_state = smu_v13_0_baco_get_state, .baco_set_state = smu_v13_0_baco_set_state, - .baco_enter = smu_v13_0_baco_enter, - .baco_exit = smu_v13_0_baco_exit, + .baco_enter = smu_v13_0_0_baco_enter, + .baco_exit = smu_v13_0_0_baco_exit, .mode1_reset_is_support = smu_v13_0_0_is_mode1_reset_supported, - .mode1_reset = smu_v13_0_mode1_reset, + .mode1_reset = smu_v13_0_0_mode1_reset, .set_mp1_state = smu_v13_0_0_set_mp1_state, .set_df_cstate = smu_v13_0_0_set_df_cstate, + .send_hbm_bad_pages_num = smu_v13_0_0_smu_send_bad_mem_page_num, + .send_hbm_bad_channel_flag = smu_v13_0_0_send_bad_mem_channel_flag, + .gpo_control = smu_v13_0_gpo_control, }; void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) @@ -1844,5 +2049,5 @@ void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) smu->table_map = smu_v13_0_0_table_map; smu->pwr_src_map = smu_v13_0_0_pwr_src_map; smu->workload_map = smu_v13_0_0_workload_map; - smu_v13_0_set_smu_mailbox_registers(smu); + smu_v13_0_0_set_smu_mailbox_registers(smu); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index 97e1d55dcaad..8fa9a36c38b6 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -1026,6 +1026,15 @@ static const struct pptable_funcs smu_v13_0_4_ppt_funcs = { .set_gfx_power_up_by_imu = smu_v13_0_set_gfx_power_up_by_imu, }; +static void smu_v13_0_4_set_smu_mailbox_registers(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + smu->param_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_82); + smu->msg_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_66); + smu->resp_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90); +} + void smu_v13_0_4_set_ppt_funcs(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -1035,7 +1044,9 @@ void smu_v13_0_4_set_ppt_funcs(struct smu_context *smu) smu->feature_map = smu_v13_0_4_feature_mask_map; smu->table_map = smu_v13_0_4_table_map; smu->is_apu = true; - smu->param_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_82); - smu->msg_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_66); - smu->resp_reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90); + + if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 4)) + smu_v13_0_4_set_smu_mailbox_registers(smu); + else + smu_v13_0_set_smu_mailbox_registers(smu); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index c4102cfb734c..5c6c6ad011ca 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -122,6 +122,8 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareMp1ForUnload, 0), MSG_MAP(SetMGpuFanBoostLimitRpm, PPSMC_MSG_SetMGpuFanBoostLimitRpm, 0), MSG_MAP(DFCstateControl, PPSMC_MSG_SetExternalClientDfCstateAllow, 0), + MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0), + MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), }; static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = { @@ -188,6 +190,8 @@ static struct cmn2asic_mapping smu_v13_0_7_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(MEM_TEMP_READ), FEA_MAP(ATHUB_MMHUB_PG), FEA_MAP(SOC_PCC), + [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, }; static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = { @@ -1222,6 +1226,7 @@ static int smu_v13_0_7_get_thermal_temperature_range(struct smu_context *smu, range->mem_emergency_max = (pptable->SkuTable.TemperatureLimit[TEMP_MEM] + CTF_OFFSET_MEM)* SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; range->software_shutdown_temp = powerplay_table->software_shutdown_temp; + range->software_shutdown_temp_offset = pptable->SkuTable.FanAbnormalTempLimitOffset; return 0; } @@ -1358,12 +1363,23 @@ static int smu_v13_0_7_populate_umd_state_clk(struct smu_context *smu) static int smu_v13_0_7_get_fan_speed_pwm(struct smu_context *smu, uint32_t *speed) { + int ret; + if (!speed) return -EINVAL; - return smu_v13_0_7_get_smu_metrics_data(smu, - METRICS_CURR_FANPWM, - speed); + ret = smu_v13_0_7_get_smu_metrics_data(smu, + METRICS_CURR_FANPWM, + speed); + if (ret) { + dev_err(smu->adev->dev, "Failed to get fan speed(PWM)!"); + return ret; + } + + /* Convert the PMFW output which is in percent to pwm(255) based */ + *speed = MIN(*speed * 255 / 100, 255); + + return 0; } static int smu_v13_0_7_get_fan_speed_rpm(struct smu_context *smu, @@ -1435,7 +1451,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu, static int smu_v13_0_7_get_power_profile_mode(struct smu_context *smu, char *buf) { - DpmActivityMonitorCoeffIntExternal_t activity_monitor_external[PP_SMC_POWER_PROFILE_COUNT]; + DpmActivityMonitorCoeffIntExternal_t *activity_monitor_external; uint32_t i, j, size = 0; int16_t workload_type = 0; int result = 0; @@ -1443,6 +1459,12 @@ static int smu_v13_0_7_get_power_profile_mode(struct smu_context *smu, char *buf if (!buf) return -EINVAL; + activity_monitor_external = kcalloc(PP_SMC_POWER_PROFILE_COUNT, + sizeof(*activity_monitor_external), + GFP_KERNEL); + if (!activity_monitor_external) + return -ENOMEM; + size += sysfs_emit_at(buf, size, " "); for (i = 0; i <= PP_SMC_POWER_PROFILE_WINDOW3D; i++) size += sysfs_emit_at(buf, size, "%-14s%s", amdgpu_pp_profile_name[i], @@ -1455,15 +1477,17 @@ static int smu_v13_0_7_get_power_profile_mode(struct smu_context *smu, char *buf workload_type = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_WORKLOAD, i); - if (workload_type < 0) - return -EINVAL; + if (workload_type < 0) { + result = -EINVAL; + goto out; + } result = smu_cmn_update_table(smu, SMU_TABLE_ACTIVITY_MONITOR_COEFF, workload_type, (void *)(&activity_monitor_external[i]), false); if (result) { dev_err(smu->adev->dev, "[%s] Failed to get activity monitor!", __func__); - return result; + goto out; } } @@ -1491,7 +1515,10 @@ do { \ PRINT_DPM_MONITOR(Fclk_BoosterFreq); #undef PRINT_DPM_MONITOR - return size; + result = size; +out: + kfree(activity_monitor_external); + return result; } static int smu_v13_0_7_set_power_profile_mode(struct smu_context *smu, long *input, uint32_t size) @@ -1578,6 +1605,31 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu, return ret; } +static int smu_v13_0_7_baco_enter(struct smu_context *smu) +{ + struct smu_baco_context *smu_baco = &smu->smu_baco; + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) + return smu_v13_0_baco_set_armd3_sequence(smu, + smu_baco->maco_support ? BACO_SEQ_BAMACO : BACO_SEQ_BACO); + else + return smu_v13_0_baco_enter(smu); +} + +static int smu_v13_0_7_baco_exit(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) { + /* Wait for PMFW handling for the Dstate change */ + usleep_range(10000, 11000); + return smu_v13_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); + } else { + return smu_v13_0_baco_exit(smu); + } +} + static bool smu_v13_0_7_is_mode1_reset_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -1655,12 +1707,13 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .baco_is_support = smu_v13_0_baco_is_support, .baco_get_state = smu_v13_0_baco_get_state, .baco_set_state = smu_v13_0_baco_set_state, - .baco_enter = smu_v13_0_baco_enter, - .baco_exit = smu_v13_0_baco_exit, + .baco_enter = smu_v13_0_7_baco_enter, + .baco_exit = smu_v13_0_7_baco_exit, .mode1_reset_is_support = smu_v13_0_7_is_mode1_reset_supported, .mode1_reset = smu_v13_0_mode1_reset, .set_mp1_state = smu_v13_0_7_set_mp1_state, .set_df_cstate = smu_v13_0_7_set_df_cstate, + .gpo_control = smu_v13_0_gpo_control, }; void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index e4f8f90ac5aa..768b6e7dbd77 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -233,6 +233,18 @@ static void __smu_cmn_send_msg(struct smu_context *smu, WREG32(smu->msg_reg, msg); } +static int __smu_cmn_send_debug_msg(struct smu_context *smu, + u32 msg, + u32 param) +{ + struct amdgpu_device *adev = smu->adev; + + WREG32(smu->debug_param_reg, param); + WREG32(smu->debug_msg_reg, msg); + WREG32(smu->debug_resp_reg, 0); + + return 0; +} /** * smu_cmn_send_msg_without_waiting -- send the message; don't wait for status * @smu: pointer to an SMU context @@ -386,6 +398,12 @@ int smu_cmn_send_smc_msg(struct smu_context *smu, read_arg); } +int smu_cmn_send_debug_smc_msg(struct smu_context *smu, + uint32_t msg) +{ + return __smu_cmn_send_debug_msg(smu, msg, 0); +} + int smu_cmn_to_asic_specific_index(struct smu_context *smu, enum smu_cmn2asic_mapping_type type, uint32_t index) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index 1526ce09c399..f82cf76dd3a4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -42,6 +42,9 @@ int smu_cmn_send_smc_msg(struct smu_context *smu, enum smu_message_type msg, uint32_t *read_arg); +int smu_cmn_send_debug_smc_msg(struct smu_context *smu, + uint32_t msg); + int smu_cmn_wait_for_response(struct smu_context *smu); int smu_cmn_to_asic_specific_index(struct smu_context *smu, diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c index 9fce4239d4ad..3f4e719eebd8 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c @@ -9,7 +9,7 @@ #include <linux/platform_device.h> #include <linux/component.h> #include <linux/pm_runtime.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_module.h> #include <drm/drm_of.h> #include "komeda_dev.h" diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index 451746ebbe71..62dc64550793 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -10,7 +10,6 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_managed.h> @@ -59,7 +58,6 @@ static irqreturn_t komeda_kms_irq_handler(int irq, void *data) static const struct drm_driver komeda_kms_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, - .lastclose = drm_fb_helper_lastclose, DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(komeda_gem_dma_dumb_create), .fops = &komeda_cma_fops, .name = "komeda", diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c index 7030339fa232..3cfefadc7c9d 100644 --- a/drivers/gpu/drm/arm/hdlcd_crtc.c +++ b/drivers/gpu/drm/arm/hdlcd_crtc.c @@ -19,7 +19,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_of.h> @@ -275,7 +274,7 @@ static void hdlcd_plane_atomic_update(struct drm_plane *plane, dest_h = drm_rect_height(&new_plane_state->dst); scanout_start = drm_fb_dma_get_gem_addr(fb, new_plane_state, 0); - hdlcd = plane->dev->dev_private; + hdlcd = drm_to_hdlcd_priv(plane->dev); hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, fb->pitches[0]); hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_PITCH, fb->pitches[0]); hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_COUNT, dest_h - 1); @@ -290,7 +289,6 @@ static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = { static const struct drm_plane_funcs hdlcd_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, - .destroy = drm_plane_cleanup, .reset = drm_atomic_helper_plane_reset, .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, @@ -298,24 +296,19 @@ static const struct drm_plane_funcs hdlcd_plane_funcs = { static struct drm_plane *hdlcd_plane_init(struct drm_device *drm) { - struct hdlcd_drm_private *hdlcd = drm->dev_private; + struct hdlcd_drm_private *hdlcd = drm_to_hdlcd_priv(drm); struct drm_plane *plane = NULL; u32 formats[ARRAY_SIZE(supported_formats)], i; - int ret; - - plane = devm_kzalloc(drm->dev, sizeof(*plane), GFP_KERNEL); - if (!plane) - return ERR_PTR(-ENOMEM); for (i = 0; i < ARRAY_SIZE(supported_formats); i++) formats[i] = supported_formats[i].fourcc; - ret = drm_universal_plane_init(drm, plane, 0xff, &hdlcd_plane_funcs, - formats, ARRAY_SIZE(formats), - NULL, - DRM_PLANE_TYPE_PRIMARY, NULL); - if (ret) - return ERR_PTR(ret); + plane = drmm_universal_plane_alloc(drm, struct drm_plane, dev, 0xff, + &hdlcd_plane_funcs, + formats, ARRAY_SIZE(formats), + NULL, DRM_PLANE_TYPE_PRIMARY, NULL); + if (IS_ERR(plane)) + return plane; drm_plane_helper_add(plane, &hdlcd_plane_helper_funcs); hdlcd->plane = plane; @@ -325,7 +318,7 @@ static struct drm_plane *hdlcd_plane_init(struct drm_device *drm) int hdlcd_setup_crtc(struct drm_device *drm) { - struct hdlcd_drm_private *hdlcd = drm->dev_private; + struct hdlcd_drm_private *hdlcd = drm_to_hdlcd_priv(drm); struct drm_plane *primary; int ret; diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index a032003c340c..7043d1c9ed8f 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -26,7 +26,7 @@ #include <drm/drm_crtc.h> #include <drm/drm_debugfs.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_modeset_helper.h> @@ -98,7 +98,7 @@ static void hdlcd_irq_uninstall(struct hdlcd_drm_private *hdlcd) static int hdlcd_load(struct drm_device *drm, unsigned long flags) { - struct hdlcd_drm_private *hdlcd = drm->dev_private; + struct hdlcd_drm_private *hdlcd = drm_to_hdlcd_priv(drm); struct platform_device *pdev = to_platform_device(drm->dev); struct resource *res; u32 version; @@ -175,14 +175,21 @@ static const struct drm_mode_config_funcs hdlcd_mode_config_funcs = { .atomic_commit = drm_atomic_helper_commit, }; -static void hdlcd_setup_mode_config(struct drm_device *drm) +static int hdlcd_setup_mode_config(struct drm_device *drm) { - drm_mode_config_init(drm); + int ret; + + ret = drmm_mode_config_init(drm); + if (ret) + return ret; + drm->mode_config.min_width = 0; drm->mode_config.min_height = 0; drm->mode_config.max_width = HDLCD_MAX_XRES; drm->mode_config.max_height = HDLCD_MAX_YRES; drm->mode_config.funcs = &hdlcd_mode_config_funcs; + + return 0; } #ifdef CONFIG_DEBUG_FS @@ -190,7 +197,7 @@ static int hdlcd_show_underrun_count(struct seq_file *m, void *arg) { struct drm_info_node *node = (struct drm_info_node *)m->private; struct drm_device *drm = node->minor->dev; - struct hdlcd_drm_private *hdlcd = drm->dev_private; + struct hdlcd_drm_private *hdlcd = drm_to_hdlcd_priv(drm); seq_printf(m, "underrun : %d\n", atomic_read(&hdlcd->buffer_underrun_count)); seq_printf(m, "dma_end : %d\n", atomic_read(&hdlcd->dma_end_count)); @@ -203,7 +210,7 @@ static int hdlcd_show_pxlclock(struct seq_file *m, void *arg) { struct drm_info_node *node = (struct drm_info_node *)m->private; struct drm_device *drm = node->minor->dev; - struct hdlcd_drm_private *hdlcd = drm->dev_private; + struct hdlcd_drm_private *hdlcd = drm_to_hdlcd_priv(drm); unsigned long clkrate = clk_get_rate(hdlcd->clk); unsigned long mode_clock = hdlcd->crtc.mode.crtc_clock * 1000; @@ -247,18 +254,18 @@ static int hdlcd_drm_bind(struct device *dev) struct hdlcd_drm_private *hdlcd; int ret; - hdlcd = devm_kzalloc(dev, sizeof(*hdlcd), GFP_KERNEL); - if (!hdlcd) - return -ENOMEM; + hdlcd = devm_drm_dev_alloc(dev, &hdlcd_driver, typeof(*hdlcd), base); + if (IS_ERR(hdlcd)) + return PTR_ERR(hdlcd); - drm = drm_dev_alloc(&hdlcd_driver, dev); - if (IS_ERR(drm)) - return PTR_ERR(drm); + drm = &hdlcd->base; - drm->dev_private = hdlcd; dev_set_drvdata(dev, drm); - hdlcd_setup_mode_config(drm); + ret = hdlcd_setup_mode_config(drm); + if (ret) + goto err_free; + ret = hdlcd_load(drm, 0); if (ret) goto err_free; @@ -317,17 +324,14 @@ err_unload: hdlcd_irq_uninstall(hdlcd); of_reserved_mem_device_release(drm->dev); err_free: - drm_mode_config_cleanup(drm); dev_set_drvdata(dev, NULL); - drm_dev_put(drm); - return ret; } static void hdlcd_drm_unbind(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct hdlcd_drm_private *hdlcd = drm->dev_private; + struct hdlcd_drm_private *hdlcd = drm_to_hdlcd_priv(drm); drm_dev_unregister(drm); drm_kms_helper_poll_fini(drm); @@ -341,10 +345,7 @@ static void hdlcd_drm_unbind(struct device *dev) if (pm_runtime_enabled(dev)) pm_runtime_disable(dev); of_reserved_mem_device_release(dev); - drm_mode_config_cleanup(drm); - drm->dev_private = NULL; dev_set_drvdata(dev, NULL); - drm_dev_put(drm); } static const struct component_master_ops hdlcd_master_ops = { diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h index 909c39c28487..f1c1da2ac2db 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.h +++ b/drivers/gpu/drm/arm/hdlcd_drv.h @@ -7,6 +7,7 @@ #define __HDLCD_DRV_H__ struct hdlcd_drm_private { + struct drm_device base; void __iomem *mmio; struct clk *clk; struct drm_crtc crtc; @@ -20,6 +21,7 @@ struct hdlcd_drm_private { #endif }; +#define drm_to_hdlcd_priv(x) container_of(x, struct hdlcd_drm_private, base) #define crtc_to_hdlcd_priv(x) container_of(x, struct hdlcd_drm_private, crtc) static inline void hdlcd_write(struct hdlcd_drm_private *hdlcd, diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c index 962730772b2f..dc01c43f6193 100644 --- a/drivers/gpu/drm/arm/malidp_crtc.c +++ b/drivers/gpu/drm/arm/malidp_crtc.c @@ -514,7 +514,6 @@ static void malidp_crtc_disable_vblank(struct drm_crtc *crtc) } static const struct drm_crtc_funcs malidp_crtc_funcs = { - .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, .reset = malidp_crtc_reset, @@ -526,7 +525,7 @@ static const struct drm_crtc_funcs malidp_crtc_funcs = { int malidp_crtc_init(struct drm_device *drm) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct drm_plane *primary = NULL, *plane; int ret; @@ -548,8 +547,8 @@ int malidp_crtc_init(struct drm_device *drm) return -EINVAL; } - ret = drm_crtc_init_with_planes(drm, &malidp->crtc, primary, NULL, - &malidp_crtc_funcs, NULL); + ret = drmm_crtc_init_with_planes(drm, &malidp->crtc, primary, NULL, + &malidp_crtc_funcs, NULL); if (ret) return ret; diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c index 1d0b0c54ccc7..589c1c66a6dc 100644 --- a/drivers/gpu/drm/arm/malidp_drv.c +++ b/drivers/gpu/drm/arm/malidp_drv.c @@ -19,10 +19,11 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_managed.h> #include <drm/drm_modeset_helper.h> #include <drm/drm_module.h> #include <drm/drm_of.h> @@ -168,7 +169,7 @@ static void malidp_atomic_commit_se_config(struct drm_crtc *crtc, */ static int malidp_set_and_wait_config_valid(struct drm_device *drm) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; int ret; @@ -189,7 +190,7 @@ static int malidp_set_and_wait_config_valid(struct drm_device *drm) static void malidp_atomic_commit_hw_done(struct drm_atomic_state *state) { struct drm_device *drm = state->dev; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); int loop = 5; malidp->event = malidp->crtc.state->event; @@ -230,7 +231,7 @@ static void malidp_atomic_commit_hw_done(struct drm_atomic_state *state) static void malidp_atomic_commit_tail(struct drm_atomic_state *state) { struct drm_device *drm = state->dev; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state; int i; @@ -392,10 +393,12 @@ static const struct drm_mode_config_funcs malidp_mode_config_funcs = { static int malidp_init(struct drm_device *drm) { int ret; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; - drm_mode_config_init(drm); + ret = drmm_mode_config_init(drm); + if (ret) + goto out; drm->mode_config.min_width = hwdev->min_line_size; drm->mode_config.min_height = hwdev->min_line_size; @@ -406,29 +409,21 @@ static int malidp_init(struct drm_device *drm) ret = malidp_crtc_init(drm); if (ret) - goto crtc_fail; + goto out; ret = malidp_mw_connector_init(drm); if (ret) - goto crtc_fail; - - return 0; + goto out; -crtc_fail: - drm_mode_config_cleanup(drm); +out: return ret; } -static void malidp_fini(struct drm_device *drm) -{ - drm_mode_config_cleanup(drm); -} - static int malidp_irq_init(struct platform_device *pdev) { int irq_de, irq_se, ret = 0; struct drm_device *drm = dev_get_drvdata(&pdev->dev); - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; /* fetch the interrupts from DT */ @@ -462,7 +457,7 @@ static int malidp_dumb_create(struct drm_file *file_priv, struct drm_device *drm, struct drm_mode_create_dumb *args) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); /* allocate for the worst case scenario, i.e. rotated buffers */ u8 alignment = malidp_hw_get_pitch_align(malidp->dev, 1); @@ -508,7 +503,7 @@ static void malidp_error_stats_dump(const char *prefix, static int malidp_show_stats(struct seq_file *m, void *arg) { struct drm_device *drm = m->private; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); unsigned long irqflags; struct malidp_error_stats de_errors, se_errors; @@ -531,7 +526,7 @@ static ssize_t malidp_debugfs_write(struct file *file, const char __user *ubuf, { struct seq_file *m = file->private_data; struct drm_device *drm = m->private; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); unsigned long irqflags; spin_lock_irqsave(&malidp->errors_lock, irqflags); @@ -552,7 +547,7 @@ static const struct file_operations malidp_debugfs_fops = { static void malidp_debugfs_init(struct drm_minor *minor) { - struct malidp_drm *malidp = minor->dev->dev_private; + struct malidp_drm *malidp = drm_to_malidp(minor->dev); malidp_error_stats_init(&malidp->de_errors); malidp_error_stats_init(&malidp->se_errors); @@ -652,7 +647,7 @@ static ssize_t core_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct drm_device *drm = dev_get_drvdata(dev); - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); return snprintf(buf, PAGE_SIZE, "%08x\n", malidp->core_id); } @@ -670,7 +665,7 @@ ATTRIBUTE_GROUPS(mali_dp); static int malidp_runtime_pm_suspend(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; /* we can only suspend if the hardware is in config mode */ @@ -689,7 +684,7 @@ static int malidp_runtime_pm_suspend(struct device *dev) static int malidp_runtime_pm_resume(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; clk_prepare_enable(hwdev->pclk); @@ -716,11 +711,13 @@ static int malidp_bind(struct device *dev) int ret = 0, i; u32 version, out_depth = 0; - malidp = devm_kzalloc(dev, sizeof(*malidp), GFP_KERNEL); - if (!malidp) - return -ENOMEM; + malidp = devm_drm_dev_alloc(dev, &malidp_driver, typeof(*malidp), base); + if (IS_ERR(malidp)) + return PTR_ERR(malidp); + + drm = &malidp->base; - hwdev = devm_kzalloc(dev, sizeof(*hwdev), GFP_KERNEL); + hwdev = drmm_kzalloc(drm, sizeof(*hwdev), GFP_KERNEL); if (!hwdev) return -ENOMEM; @@ -753,13 +750,6 @@ static int malidp_bind(struct device *dev) if (ret && ret != -ENODEV) return ret; - drm = drm_dev_alloc(&malidp_driver, dev); - if (IS_ERR(drm)) { - ret = PTR_ERR(drm); - goto alloc_fail; - } - - drm->dev_private = malidp; dev_set_drvdata(dev, drm); /* Enable power management */ @@ -878,17 +868,13 @@ irq_init_fail: bind_fail: of_node_put(malidp->crtc.port); malidp->crtc.port = NULL; - malidp_fini(drm); query_hw_fail: pm_runtime_put(dev); if (pm_runtime_enabled(dev)) pm_runtime_disable(dev); else malidp_runtime_pm_suspend(dev); - drm->dev_private = NULL; dev_set_drvdata(dev, NULL); - drm_dev_put(drm); -alloc_fail: of_reserved_mem_device_release(dev); return ret; @@ -897,7 +883,7 @@ alloc_fail: static void malidp_unbind(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; drm_dev_unregister(drm); @@ -909,15 +895,12 @@ static void malidp_unbind(struct device *dev) component_unbind_all(dev, drm); of_node_put(malidp->crtc.port); malidp->crtc.port = NULL; - malidp_fini(drm); pm_runtime_put(dev); if (pm_runtime_enabled(dev)) pm_runtime_disable(dev); else malidp_runtime_pm_suspend(dev); - drm->dev_private = NULL; dev_set_drvdata(dev, NULL); - drm_dev_put(drm); of_reserved_mem_device_release(dev); } diff --git a/drivers/gpu/drm/arm/malidp_drv.h b/drivers/gpu/drm/arm/malidp_drv.h index cdfddfabf2d1..bc0387876dea 100644 --- a/drivers/gpu/drm/arm/malidp_drv.h +++ b/drivers/gpu/drm/arm/malidp_drv.h @@ -29,6 +29,7 @@ struct malidp_error_stats { }; struct malidp_drm { + struct drm_device base; struct malidp_hw_device *dev; struct drm_crtc crtc; struct drm_writeback_connector mw_connector; @@ -44,6 +45,7 @@ struct malidp_drm { #endif }; +#define drm_to_malidp(x) container_of(x, struct malidp_drm, base) #define crtc_to_malidp_device(x) container_of(x, struct malidp_drm, crtc) struct malidp_plane { diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c index e9de542f9b7c..9b845d3f34e1 100644 --- a/drivers/gpu/drm/arm/malidp_hw.c +++ b/drivers/gpu/drm/arm/malidp_hw.c @@ -1168,7 +1168,7 @@ static void malidp_hw_clear_irq(struct malidp_hw_device *hwdev, u8 block, u32 ir static irqreturn_t malidp_de_irq(int irq, void *arg) { struct drm_device *drm = arg; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev; struct malidp_hw *hw; const struct malidp_irq_map *de; @@ -1226,7 +1226,7 @@ static irqreturn_t malidp_de_irq(int irq, void *arg) static irqreturn_t malidp_de_irq_thread_handler(int irq, void *arg) { struct drm_device *drm = arg; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); wake_up(&malidp->wq); @@ -1252,7 +1252,7 @@ void malidp_de_irq_hw_init(struct malidp_hw_device *hwdev) int malidp_de_irq_init(struct drm_device *drm, int irq) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; int ret; @@ -1286,7 +1286,7 @@ void malidp_de_irq_fini(struct malidp_hw_device *hwdev) static irqreturn_t malidp_se_irq(int irq, void *arg) { struct drm_device *drm = arg; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; struct malidp_hw *hw = hwdev->hw; const struct malidp_irq_map *se = &hw->map.se_irq_map; @@ -1363,7 +1363,7 @@ static irqreturn_t malidp_se_irq_thread_handler(int irq, void *arg) int malidp_se_irq_init(struct drm_device *drm, int irq) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct malidp_hw_device *hwdev = malidp->dev; int ret; diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index ef76d0e6ee2f..626709bec6f5 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -129,7 +129,7 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder, struct drm_connector_state *conn_state) { struct malidp_mw_connector_state *mw_state = to_mw_state(conn_state); - struct malidp_drm *malidp = encoder->dev->dev_private; + struct malidp_drm *malidp = drm_to_malidp(encoder->dev); struct drm_framebuffer *fb; int i, n_planes; @@ -207,7 +207,7 @@ static u32 *get_writeback_formats(struct malidp_drm *malidp, int *n_formats) int malidp_mw_connector_init(struct drm_device *drm) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); u32 *formats; int ret, n_formats; @@ -236,7 +236,7 @@ int malidp_mw_connector_init(struct drm_device *drm) void malidp_mw_atomic_commit(struct drm_device *drm, struct drm_atomic_state *old_state) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); struct drm_writeback_connector *mw_conn = &malidp->mw_connector; struct drm_connector_state *conn_state = mw_conn->base.state; struct malidp_hw_device *hwdev = malidp->dev; diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c index 45f5e35e7f24..34547edf1ee3 100644 --- a/drivers/gpu/drm/arm/malidp_planes.c +++ b/drivers/gpu/drm/arm/malidp_planes.c @@ -68,14 +68,6 @@ /* readahead for partial-frame prefetch */ #define MALIDP_MMU_PREFETCH_READAHEAD 8 -static void malidp_de_plane_destroy(struct drm_plane *plane) -{ - struct malidp_plane *mp = to_malidp_plane(plane); - - drm_plane_cleanup(plane); - kfree(mp); -} - /* * Replicate what the default ->reset hook does: free the state pointer and * allocate a new empty object. We just need enough space to store @@ -151,7 +143,7 @@ bool malidp_format_mod_supported(struct drm_device *drm, { const struct drm_format_info *info; const u64 *modifiers; - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); const struct malidp_hw_regmap *map = &malidp->dev->hw->map; if (WARN_ON(modifier == DRM_FORMAT_MOD_INVALID)) @@ -260,7 +252,6 @@ static bool malidp_format_mod_supported_per_plane(struct drm_plane *plane, static const struct drm_plane_funcs malidp_de_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, - .destroy = malidp_de_plane_destroy, .reset = malidp_plane_reset, .atomic_duplicate_state = malidp_duplicate_plane_state, .atomic_destroy_state = malidp_destroy_plane_state, @@ -931,7 +922,7 @@ static const uint64_t linear_only_modifiers[] = { int malidp_de_planes_init(struct drm_device *drm) { - struct malidp_drm *malidp = drm->dev_private; + struct malidp_drm *malidp = drm_to_malidp(drm); const struct malidp_hw_regmap *map = &malidp->dev->hw->map; struct malidp_plane *plane = NULL; enum drm_plane_type plane_type; @@ -972,12 +963,6 @@ int malidp_de_planes_init(struct drm_device *drm) for (i = 0; i < map->n_layers; i++) { u8 id = map->layers[i].id; - plane = kzalloc(sizeof(*plane), GFP_KERNEL); - if (!plane) { - ret = -ENOMEM; - goto cleanup; - } - /* build the list of DRM supported formats based on the map */ for (n = 0, j = 0; j < map->n_pixel_formats; j++) { if ((map->pixel_formats[j].layer & id) == id) @@ -990,13 +975,14 @@ int malidp_de_planes_init(struct drm_device *drm) /* * All the layers except smart layer supports AFBC modifiers. */ - ret = drm_universal_plane_init(drm, &plane->base, crtcs, - &malidp_de_plane_funcs, formats, n, - (id == DE_SMART) ? linear_only_modifiers : modifiers, - plane_type, NULL); - - if (ret < 0) + plane = drmm_universal_plane_alloc(drm, struct malidp_plane, base, + crtcs, &malidp_de_plane_funcs, formats, n, + (id == DE_SMART) ? linear_only_modifiers : + modifiers, plane_type, NULL); + if (IS_ERR(plane)) { + ret = PTR_ERR(plane); goto cleanup; + } drm_plane_helper_add(&plane->base, &malidp_de_plane_helper_funcs); diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index 38f5170c0fea..584cee123bd8 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -19,6 +19,8 @@ static const struct fb_ops armada_fb_ops = { .owner = THIS_MODULE, DRM_FB_HELPER_DEFAULT_OPS, + .fb_read = drm_fb_helper_cfb_read, + .fb_write = drm_fb_helper_cfb_write, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -72,7 +74,7 @@ static int armada_fbdev_create(struct drm_fb_helper *fbh, if (IS_ERR(dfb)) return PTR_ERR(dfb); - info = drm_fb_helper_alloc_fbi(fbh); + info = drm_fb_helper_alloc_info(fbh); if (IS_ERR(info)) { ret = PTR_ERR(info); goto err_fballoc; @@ -155,7 +157,7 @@ void armada_fbdev_fini(struct drm_device *dev) struct drm_fb_helper *fbh = priv->fbdev; if (fbh) { - drm_fb_helper_unregister_fbi(fbh); + drm_fb_helper_unregister_info(fbh); drm_fb_helper_fini(fbh); diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c index a94f1a9e8f40..718119e168a6 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -16,7 +16,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_device.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index bbeb5defc8f5..420fc75c240e 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -33,6 +33,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_module.h> #include <drm/drm_probe_helper.h> diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 74f41282444f..d51b81fea9c8 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -38,7 +38,6 @@ #include <drm/drm_encoder.h> #include <drm/drm_mode.h> #include <drm/drm_framebuffer.h> -#include <drm/drm_fb_helper.h> #define DRIVER_AUTHOR "Dave Airlie" diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c index f7e7f4e919c7..a2bb5b916235 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c @@ -19,7 +19,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 5be6562c2a19..6a614e54b383 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -105,6 +105,7 @@ struct ps8640 { struct gpio_desc *gpio_powerdown; struct device_link *link; bool pre_enabled; + bool need_post_hpd_delay; }; static const struct regmap_config ps8640_regmap_config[] = { @@ -173,14 +174,31 @@ static int _ps8640_wait_hpd_asserted(struct ps8640 *ps_bridge, unsigned long wai { struct regmap *map = ps_bridge->regmap[PAGE2_TOP_CNTL]; int status; + int ret; /* * Apparently something about the firmware in the chip signals that * HPD goes high by reporting GPIO9 as high (even though HPD isn't * actually connected to GPIO9). */ - return regmap_read_poll_timeout(map, PAGE2_GPIO_H, status, - status & PS_GPIO9, wait_us / 10, wait_us); + ret = regmap_read_poll_timeout(map, PAGE2_GPIO_H, status, + status & PS_GPIO9, wait_us / 10, wait_us); + + /* + * The first time we see HPD go high after a reset we delay an extra + * 50 ms. The best guess is that the MCU is doing "stuff" during this + * time (maybe talking to the panel) and we don't want to interrupt it. + * + * No locking is done around "need_post_hpd_delay". If we're here we + * know we're holding a PM Runtime reference and the only other place + * that touches this is PM Runtime resume. + */ + if (!ret && ps_bridge->need_post_hpd_delay) { + ps_bridge->need_post_hpd_delay = false; + msleep(50); + } + + return ret; } static int ps8640_wait_hpd_asserted(struct drm_dp_aux *aux, unsigned long wait_us) @@ -388,6 +406,9 @@ static int __maybe_unused ps8640_resume(struct device *dev) msleep(50); gpiod_set_value(ps_bridge->gpio_reset, 0); + /* We just reset things, so we need a delay after the first HPD */ + ps_bridge->need_post_hpd_delay = true; + /* * Mystery 200 ms delay for the "MCU to be ready". It's unclear if * this is truly necessary since the MCU will already signal that diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 40d8ca37f5bc..aa51c61a78c7 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -2720,6 +2720,9 @@ static u32 *dw_hdmi_bridge_atomic_get_output_bus_fmts(struct drm_bridge *bridge, * if supported. In any case the default RGB888 format is added */ + /* Default 8bit RGB fallback */ + output_fmts[i++] = MEDIA_BUS_FMT_RGB888_1X24; + if (max_bpc >= 16 && info->bpc == 16) { if (info->color_formats & DRM_COLOR_FORMAT_YCBCR444) output_fmts[i++] = MEDIA_BUS_FMT_YUV16_1X48; @@ -2753,9 +2756,6 @@ static u32 *dw_hdmi_bridge_atomic_get_output_bus_fmts(struct drm_bridge *bridge, if (info->color_formats & DRM_COLOR_FORMAT_YCBCR444) output_fmts[i++] = MEDIA_BUS_FMT_YUV8_1X24; - /* Default 8bit RGB fallback */ - output_fmts[i++] = MEDIA_BUS_FMT_RGB888_1X24; - *num_output_fmts = i; return output_fmts; diff --git a/drivers/gpu/drm/bridge/tc358762.c b/drivers/gpu/drm/bridge/tc358762.c index 7f4fce1aa998..0b6a28436885 100644 --- a/drivers/gpu/drm/bridge/tc358762.c +++ b/drivers/gpu/drm/bridge/tc358762.c @@ -11,6 +11,7 @@ */ #include <linux/delay.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/of_graph.h> #include <linux/regulator/consumer.h> @@ -19,7 +20,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_of.h> #include <drm/drm_panel.h> diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 3c3561942eb6..05f8756d1aaf 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -931,9 +931,9 @@ static void ti_sn_bridge_set_video_timings(struct ti_sn65dsi86 *pdata) &pdata->bridge.encoder->crtc->state->adjusted_mode; u8 hsync_polarity = 0, vsync_polarity = 0; - if (mode->flags & DRM_MODE_FLAG_PHSYNC) + if (mode->flags & DRM_MODE_FLAG_NHSYNC) hsync_polarity = CHA_HSYNC_POLARITY; - if (mode->flags & DRM_MODE_FLAG_PVSYNC) + if (mode->flags & DRM_MODE_FLAG_NVSYNC) vsync_polarity = CHA_VSYNC_POLARITY; ti_sn65dsi86_write_u16(pdata, SN_CHA_ACTIVE_LINE_LENGTH_LOW_REG, @@ -1500,8 +1500,8 @@ out: return ret; } -static void ti_sn_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, - struct pwm_state *state) +static int ti_sn_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, + struct pwm_state *state) { struct ti_sn65dsi86 *pdata = pwm_chip_to_ti_sn_bridge(chip); unsigned int pwm_en_inv; @@ -1512,19 +1512,19 @@ static void ti_sn_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, ret = regmap_read(pdata->regmap, SN_PWM_EN_INV_REG, &pwm_en_inv); if (ret) - return; + return ret; ret = ti_sn65dsi86_read_u16(pdata, SN_BACKLIGHT_SCALE_REG, &scale); if (ret) - return; + return ret; ret = ti_sn65dsi86_read_u16(pdata, SN_BACKLIGHT_REG, &backlight); if (ret) - return; + return ret; ret = regmap_read(pdata->regmap, SN_PWM_PRE_DIV_REG, &pre_div); if (ret) - return; + return ret; state->enabled = FIELD_GET(SN_PWM_EN_MASK, pwm_en_inv); if (FIELD_GET(SN_PWM_INV_MASK, pwm_en_inv)) @@ -1539,6 +1539,8 @@ static void ti_sn_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, if (state->duty_cycle > state->period) state->duty_cycle = state->period; + + return 0; } static const struct pwm_ops ti_sn_pwm_ops = { diff --git a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c index 3ea53bb67d3b..bd61e20770a5 100644 --- a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c +++ b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c @@ -63,23 +63,45 @@ ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter, u8 offset, void *buffer, size_t size) { + u8 zero = 0; + char *tmpbuf = NULL; + /* + * As sub-addressing is not supported by all adaptors, + * always explicitly read from the start and discard + * any bytes that come before the requested offset. + * This way, no matter whether the adaptor supports it + * or not, we'll end up reading the proper data. + */ struct i2c_msg msgs[] = { { .addr = DP_DUAL_MODE_SLAVE_ADDRESS, .flags = 0, .len = 1, - .buf = &offset, + .buf = &zero, }, { .addr = DP_DUAL_MODE_SLAVE_ADDRESS, .flags = I2C_M_RD, - .len = size, + .len = size + offset, .buf = buffer, }, }; int ret; + if (offset) { + tmpbuf = kmalloc(size + offset, GFP_KERNEL); + if (!tmpbuf) + return -ENOMEM; + + msgs[1].buf = tmpbuf; + } + ret = i2c_transfer(adapter, msgs, ARRAY_SIZE(msgs)); + if (tmpbuf) + memcpy(buffer, tmpbuf + offset, size); + + kfree(tmpbuf); + if (ret < 0) return ret; if (ret != ARRAY_SIZE(msgs)) @@ -208,18 +230,6 @@ enum drm_dp_dual_mode_type drm_dp_dual_mode_detect(const struct drm_device *dev, if (ret) return DRM_DP_DUAL_MODE_UNKNOWN; - /* - * Sigh. Some (maybe all?) type 1 adaptors are broken and ack - * the offset but ignore it, and instead they just always return - * data from the start of the HDMI ID buffer. So for a broken - * type 1 HDMI adaptor a single byte read will always give us - * 0x44, and for a type 1 DVI adaptor it should give 0x00 - * (assuming it implements any registers). Fortunately neither - * of those values will match the type 2 signature of the - * DP_DUAL_MODE_ADAPTOR_ID register so we can proceed with - * the type 2 adaptor detection safely even in the presence - * of broken type 1 adaptors. - */ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_ADAPTOR_ID, &adaptor_id, sizeof(adaptor_id)); drm_dbg_kms(dev, "DP dual mode adaptor ID: %02x (err %zd)\n", adaptor_id, ret); @@ -233,11 +243,10 @@ enum drm_dp_dual_mode_type drm_dp_dual_mode_detect(const struct drm_device *dev, return DRM_DP_DUAL_MODE_TYPE2_DVI; } /* - * If neither a proper type 1 ID nor a broken type 1 adaptor - * as described above, assume type 1, but let the user know - * that we may have misdetected the type. + * If not a proper type 1 ID, still assume type 1, but let + * the user know that we may have misdetected the type. */ - if (!is_type1_adaptor(adaptor_id) && adaptor_id != hdmi_id[0]) + if (!is_type1_adaptor(adaptor_id)) drm_err(dev, "Unexpected DP dual mode adaptor ID %02x\n", adaptor_id); } @@ -343,10 +352,8 @@ EXPORT_SYMBOL(drm_dp_dual_mode_get_tmds_output); * @enable: enable (as opposed to disable) the TMDS output buffers * * Set the state of the TMDS output buffers in the adaptor. For - * type2 this is set via the DP_DUAL_MODE_TMDS_OEN register. As - * some type 1 adaptors have problems with registers (see comments - * in drm_dp_dual_mode_detect()) we avoid touching the register, - * making this function a no-op on type 1 adaptors. + * type2 this is set via the DP_DUAL_MODE_TMDS_OEN register. + * Type1 adaptors do not support any register writes. * * Returns: * 0 on success, negative error code on failure diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index ecd22c038c8c..51a46689cda7 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -5186,7 +5186,7 @@ int drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, struct drm mst_state = drm_atomic_get_mst_topology_state(state, mgr); if (IS_ERR(mst_state)) - return -EINVAL; + return PTR_ERR(mst_state); list_for_each_entry(pos, &mst_state->payloads, next) { diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 1a586b3c454b..d579fd8f7cb8 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2536,7 +2536,7 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev, if (funcs->prepare_fb) { ret = funcs->prepare_fb(plane, new_plane_state); if (ret) - goto fail; + goto fail_prepare_fb; } else { WARN_ON_ONCE(funcs->cleanup_fb); @@ -2545,13 +2545,34 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev, ret = drm_gem_plane_helper_prepare_fb(plane, new_plane_state); if (ret) - goto fail; + goto fail_prepare_fb; + } + } + + for_each_new_plane_in_state(state, plane, new_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->begin_fb_access) { + ret = funcs->begin_fb_access(plane, new_plane_state); + if (ret) + goto fail_begin_fb_access; } } return 0; -fail: +fail_begin_fb_access: + for_each_new_plane_in_state(state, plane, new_plane_state, j) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (j >= i) + continue; + + if (funcs->end_fb_access) + funcs->end_fb_access(plane, new_plane_state); + } + i = j; /* set i to upper limit to cleanup all planes */ +fail_prepare_fb: for_each_new_plane_in_state(state, plane, new_plane_state, j) { const struct drm_plane_helper_funcs *funcs; @@ -2828,6 +2849,13 @@ void drm_atomic_helper_cleanup_planes(struct drm_device *dev, int i; for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->end_fb_access) + funcs->end_fb_access(plane, new_plane_state); + } + + for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) { const struct drm_plane_helper_funcs *funcs; struct drm_plane_state *plane_state; diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index bbc535cc50dd..d553e793e673 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -1237,3 +1237,7 @@ int drm_client_modeset_dpms(struct drm_client_dev *client, int mode) return ret; } EXPORT_SYMBOL(drm_client_modeset_dpms); + +#ifdef CONFIG_DRM_KUNIT_TEST +#include "tests/drm_client_modeset_test.c" +#endif diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index f5fb22e0d033..a209659a996c 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -43,7 +43,6 @@ #include <drm/drm_drv.h> #include <drm/drm_edid.h> #include <drm/drm_encoder.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_print.h> diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 8214a0b1ab7f..73b845a75d52 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -35,6 +35,7 @@ #include <linux/slab.h> #include <linux/srcu.h> +#include <drm/drm_accel.h> #include <drm/drm_cache.h> #include <drm/drm_client.h> #include <drm/drm_color_mgmt.h> @@ -90,6 +91,8 @@ static struct drm_minor **drm_minor_get_slot(struct drm_device *dev, return &dev->primary; case DRM_MINOR_RENDER: return &dev->render; + case DRM_MINOR_ACCEL: + return &dev->accel; default: BUG(); } @@ -104,9 +107,13 @@ static void drm_minor_alloc_release(struct drm_device *dev, void *data) put_device(minor->kdev); - spin_lock_irqsave(&drm_minor_lock, flags); - idr_remove(&drm_minors_idr, minor->index); - spin_unlock_irqrestore(&drm_minor_lock, flags); + if (minor->type == DRM_MINOR_ACCEL) { + accel_minor_remove(minor->index); + } else { + spin_lock_irqsave(&drm_minor_lock, flags); + idr_remove(&drm_minors_idr, minor->index); + spin_unlock_irqrestore(&drm_minor_lock, flags); + } } static int drm_minor_alloc(struct drm_device *dev, unsigned int type) @@ -123,13 +130,17 @@ static int drm_minor_alloc(struct drm_device *dev, unsigned int type) minor->dev = dev; idr_preload(GFP_KERNEL); - spin_lock_irqsave(&drm_minor_lock, flags); - r = idr_alloc(&drm_minors_idr, - NULL, - 64 * type, - 64 * (type + 1), - GFP_NOWAIT); - spin_unlock_irqrestore(&drm_minor_lock, flags); + if (type == DRM_MINOR_ACCEL) { + r = accel_minor_alloc(); + } else { + spin_lock_irqsave(&drm_minor_lock, flags); + r = idr_alloc(&drm_minors_idr, + NULL, + 64 * type, + 64 * (type + 1), + GFP_NOWAIT); + spin_unlock_irqrestore(&drm_minor_lock, flags); + } idr_preload_end(); if (r < 0) @@ -161,10 +172,14 @@ static int drm_minor_register(struct drm_device *dev, unsigned int type) if (!minor) return 0; - ret = drm_debugfs_init(minor, minor->index, drm_debugfs_root); - if (ret) { - DRM_ERROR("DRM: Failed to initialize /sys/kernel/debug/dri.\n"); - goto err_debugfs; + if (minor->type == DRM_MINOR_ACCEL) { + accel_debugfs_init(minor, minor->index); + } else { + ret = drm_debugfs_init(minor, minor->index, drm_debugfs_root); + if (ret) { + DRM_ERROR("DRM: Failed to initialize /sys/kernel/debug/dri.\n"); + goto err_debugfs; + } } ret = device_add(minor->kdev); @@ -172,9 +187,13 @@ static int drm_minor_register(struct drm_device *dev, unsigned int type) goto err_debugfs; /* replace NULL with @minor so lookups will succeed from now on */ - spin_lock_irqsave(&drm_minor_lock, flags); - idr_replace(&drm_minors_idr, minor, minor->index); - spin_unlock_irqrestore(&drm_minor_lock, flags); + if (minor->type == DRM_MINOR_ACCEL) { + accel_minor_replace(minor, minor->index); + } else { + spin_lock_irqsave(&drm_minor_lock, flags); + idr_replace(&drm_minors_idr, minor, minor->index); + spin_unlock_irqrestore(&drm_minor_lock, flags); + } DRM_DEBUG("new minor registered %d\n", minor->index); return 0; @@ -194,9 +213,13 @@ static void drm_minor_unregister(struct drm_device *dev, unsigned int type) return; /* replace @minor with NULL so lookups will fail from now on */ - spin_lock_irqsave(&drm_minor_lock, flags); - idr_replace(&drm_minors_idr, NULL, minor->index); - spin_unlock_irqrestore(&drm_minor_lock, flags); + if (minor->type == DRM_MINOR_ACCEL) { + accel_minor_replace(NULL, minor->index); + } else { + spin_lock_irqsave(&drm_minor_lock, flags); + idr_replace(&drm_minors_idr, NULL, minor->index); + spin_unlock_irqrestore(&drm_minor_lock, flags); + } device_del(minor->kdev); dev_set_drvdata(minor->kdev, NULL); /* safety belt */ @@ -603,6 +626,13 @@ static int drm_dev_init(struct drm_device *dev, /* no per-device feature limits by default */ dev->driver_features = ~0u; + if (drm_core_check_feature(dev, DRIVER_COMPUTE_ACCEL) && + (drm_core_check_feature(dev, DRIVER_RENDER) || + drm_core_check_feature(dev, DRIVER_MODESET))) { + DRM_ERROR("DRM driver can't be both a compute acceleration and graphics driver\n"); + return -EINVAL; + } + drm_legacy_init_members(dev); INIT_LIST_HEAD(&dev->filelist); INIT_LIST_HEAD(&dev->filelist_internal); @@ -615,7 +645,7 @@ static int drm_dev_init(struct drm_device *dev, mutex_init(&dev->clientlist_mutex); mutex_init(&dev->master_mutex); - ret = drmm_add_action(dev, drm_dev_init_release, NULL); + ret = drmm_add_action_or_reset(dev, drm_dev_init_release, NULL); if (ret) return ret; @@ -628,15 +658,21 @@ static int drm_dev_init(struct drm_device *dev, dev->anon_inode = inode; - if (drm_core_check_feature(dev, DRIVER_RENDER)) { - ret = drm_minor_alloc(dev, DRM_MINOR_RENDER); + if (drm_core_check_feature(dev, DRIVER_COMPUTE_ACCEL)) { + ret = drm_minor_alloc(dev, DRM_MINOR_ACCEL); if (ret) goto err; - } + } else { + if (drm_core_check_feature(dev, DRIVER_RENDER)) { + ret = drm_minor_alloc(dev, DRM_MINOR_RENDER); + if (ret) + goto err; + } - ret = drm_minor_alloc(dev, DRM_MINOR_PRIMARY); - if (ret) - goto err; + ret = drm_minor_alloc(dev, DRM_MINOR_PRIMARY); + if (ret) + goto err; + } ret = drm_legacy_create_map_hash(dev); if (ret) @@ -883,6 +919,10 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) if (ret) goto err_minors; + ret = drm_minor_register(dev, DRM_MINOR_ACCEL); + if (ret) + goto err_minors; + ret = create_compat_control_link(dev); if (ret) goto err_minors; @@ -902,12 +942,13 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) driver->name, driver->major, driver->minor, driver->patchlevel, driver->date, dev->dev ? dev_name(dev->dev) : "virtual device", - dev->primary->index); + dev->primary ? dev->primary->index : dev->accel->index); goto out_unlock; err_minors: remove_compat_control_link(dev); + drm_minor_unregister(dev, DRM_MINOR_ACCEL); drm_minor_unregister(dev, DRM_MINOR_PRIMARY); drm_minor_unregister(dev, DRM_MINOR_RENDER); out_unlock: @@ -950,6 +991,7 @@ void drm_dev_unregister(struct drm_device *dev) drm_legacy_rmmaps(dev); remove_compat_control_link(dev); + drm_minor_unregister(dev, DRM_MINOR_ACCEL); drm_minor_unregister(dev, DRM_MINOR_PRIMARY); drm_minor_unregister(dev, DRM_MINOR_RENDER); } @@ -1034,6 +1076,7 @@ static const struct file_operations drm_stub_fops = { static void drm_core_exit(void) { drm_privacy_screen_lookup_exit(); + accel_core_exit(); unregister_chrdev(DRM_MAJOR, "drm"); debugfs_remove(drm_debugfs_root); drm_sysfs_destroy(); @@ -1061,6 +1104,10 @@ static int __init drm_core_init(void) if (ret < 0) goto error; + ret = accel_core_init(); + if (ret < 0) + goto error; + drm_privacy_screen_lookup_init(); drm_core_init_complete = true; diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 4671dc23abe0..3841aba17abd 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2807,6 +2807,8 @@ u32 drm_edid_get_panel_id(struct i2c_adapter *adapter) if (edid_block_status_valid(status, edid_block_tag(base_block))) panel_id = edid_extract_panel_id(base_block); + else + edid_block_dump(KERN_NOTICE, base_block, 0); kfree(base_block); diff --git a/drivers/gpu/drm/drm_edid_load.c b/drivers/gpu/drm/drm_edid_load.c index ef4ab59d6935..5d9ef267ebb3 100644 --- a/drivers/gpu/drm/drm_edid_load.c +++ b/drivers/gpu/drm/drm_edid_load.c @@ -172,20 +172,9 @@ static const struct drm_edid *edid_load(struct drm_connector *connector, const c fwdata = generic_edid[builtin]; fwsize = sizeof(generic_edid[builtin]); } else { - struct platform_device *pdev; int err; - pdev = platform_device_register_simple(connector->name, -1, NULL, 0); - if (IS_ERR(pdev)) { - drm_err(connector->dev, - "[CONNECTOR:%d:%s] Failed to register EDID firmware platform device for connector \"%s\"\n", - connector->base.id, connector->name, - connector->name); - return ERR_CAST(pdev); - } - - err = request_firmware(&fw, name, &pdev->dev); - platform_device_unregister(pdev); + err = request_firmware(&fw, name, connector->dev->dev); if (err) { drm_err(connector->dev, "[CONNECTOR:%d:%s] Requesting EDID firmware \"%s\" failed (err=%d)\n", diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 71edb80fe0fb..b3a731b9170a 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -30,24 +30,17 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/console.h> -#include <linux/dma-buf.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/slab.h> #include <linux/sysrq.h> -#include <linux/vmalloc.h> #include <drm/drm_atomic.h> -#include <drm/drm_crtc.h> -#include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> +#include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_print.h> #include <drm/drm_vblank.h> -#include "drm_crtc_helper_internal.h" #include "drm_internal.h" static bool drm_fbdev_emulation = true; @@ -74,7 +67,7 @@ MODULE_PARM_DESC(drm_fbdev_overalloc, * considered as a broken and legacy behaviour from a modern fbdev device. */ #if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) -static bool drm_leak_fbdev_smem = false; +static bool drm_leak_fbdev_smem; module_param_unsafe(drm_leak_fbdev_smem, bool, 0600); MODULE_PARM_DESC(drm_leak_fbdev_smem, "Allow unsafe leaking fbdev physical smem address [default=false]"); @@ -96,11 +89,13 @@ static DEFINE_MUTEX(kernel_fb_helper_lock); * It will automatically set up deferred I/O if the driver requires a shadow * buffer. * - * At runtime drivers should restore the fbdev console by using + * Existing fbdev implementations should restore the fbdev console by using * drm_fb_helper_lastclose() as their &drm_driver.lastclose callback. * They should also notify the fb helper code from updates to the output * configuration by using drm_fb_helper_output_poll_changed() as their - * &drm_mode_config_funcs.output_poll_changed callback. + * &drm_mode_config_funcs.output_poll_changed callback. New implementations + * of fbdev should be build on top of struct &drm_client_funcs, which handles + * this automatically. Setting the old callbacks should be avoided. * * For suspend/resume consider using drm_mode_config_helper_suspend() and * drm_mode_config_helper_resume() which takes care of fbdev as well. @@ -368,115 +363,30 @@ static void drm_fb_helper_resume_worker(struct work_struct *work) resume_work); console_lock(); - fb_set_suspend(helper->fbdev, 0); + fb_set_suspend(helper->info, 0); console_unlock(); } -static void drm_fb_helper_damage_blit_real(struct drm_fb_helper *fb_helper, - struct drm_clip_rect *clip, - struct iosys_map *dst) +static void drm_fb_helper_fb_dirty(struct drm_fb_helper *helper) { - struct drm_framebuffer *fb = fb_helper->fb; - size_t offset = clip->y1 * fb->pitches[0]; - size_t len = clip->x2 - clip->x1; - unsigned int y; - void *src; - - switch (drm_format_info_bpp(fb->format, 0)) { - case 1: - offset += clip->x1 / 8; - len = DIV_ROUND_UP(len + clip->x1 % 8, 8); - break; - case 2: - offset += clip->x1 / 4; - len = DIV_ROUND_UP(len + clip->x1 % 4, 4); - break; - case 4: - offset += clip->x1 / 2; - len = DIV_ROUND_UP(len + clip->x1 % 2, 2); - break; - default: - offset += clip->x1 * fb->format->cpp[0]; - len *= fb->format->cpp[0]; - break; - } - - src = fb_helper->fbdev->screen_buffer + offset; - iosys_map_incr(dst, offset); /* go to first pixel within clip rect */ - - for (y = clip->y1; y < clip->y2; y++) { - iosys_map_memcpy_to(dst, 0, src, len); - iosys_map_incr(dst, fb->pitches[0]); - src += fb->pitches[0]; - } -} - -static int drm_fb_helper_damage_blit(struct drm_fb_helper *fb_helper, - struct drm_clip_rect *clip) -{ - struct drm_client_buffer *buffer = fb_helper->buffer; - struct iosys_map map, dst; - int ret; - - /* - * We have to pin the client buffer to its current location while - * flushing the shadow buffer. In the general case, concurrent - * modesetting operations could try to move the buffer and would - * fail. The modeset has to be serialized by acquiring the reservation - * object of the underlying BO here. - * - * For fbdev emulation, we only have to protect against fbdev modeset - * operations. Nothing else will involve the client buffer's BO. So it - * is sufficient to acquire struct drm_fb_helper.lock here. - */ - mutex_lock(&fb_helper->lock); - - ret = drm_client_buffer_vmap(buffer, &map); - if (ret) - goto out; - - dst = map; - drm_fb_helper_damage_blit_real(fb_helper, clip, &dst); - - drm_client_buffer_vunmap(buffer); - -out: - mutex_unlock(&fb_helper->lock); - - return ret; -} - -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); struct drm_device *dev = helper->dev; struct drm_clip_rect *clip = &helper->damage_clip; struct drm_clip_rect clip_copy; unsigned long flags; int ret; + if (drm_WARN_ON_ONCE(dev, !helper->funcs->fb_dirty)) + return; + spin_lock_irqsave(&helper->damage_lock, flags); clip_copy = *clip; clip->x1 = clip->y1 = ~0; clip->x2 = clip->y2 = 0; spin_unlock_irqrestore(&helper->damage_lock, flags); - /* Call damage handlers only if necessary */ - if (!(clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2)) - return; - - if (helper->buffer) { - ret = drm_fb_helper_damage_blit(helper, &clip_copy); - if (drm_WARN_ONCE(dev, ret, "Damage blitter failed: ret=%d\n", ret)) - goto err; - } - - if (helper->fb->funcs->dirty) { - ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1); - if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret)) - goto err; - } + ret = helper->funcs->fb_dirty(helper, &clip_copy); + if (ret) + goto err; return; @@ -493,6 +403,13 @@ err: spin_unlock_irqrestore(&helper->damage_lock, flags); } +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); + + drm_fb_helper_fb_dirty(helper); +} + /** * drm_fb_helper_prepare - setup a drm_fb_helper structure * @dev: DRM device @@ -536,11 +453,6 @@ int drm_fb_helper_init(struct drm_device *dev, { int ret; - if (!drm_fbdev_emulation) { - dev->fb_helper = fb_helper; - return 0; - } - /* * If this is not the generic fbdev client, initialize a drm_client * without callbacks so we can use the modesets. @@ -558,7 +470,7 @@ int drm_fb_helper_init(struct drm_device *dev, EXPORT_SYMBOL(drm_fb_helper_init); /** - * drm_fb_helper_alloc_fbi - allocate fb_info and some of its members + * drm_fb_helper_alloc_info - allocate fb_info and some of its members * @fb_helper: driver-allocated fbdev helper * * A helper to alloc fb_info and the members cmap and apertures. Called @@ -570,7 +482,7 @@ EXPORT_SYMBOL(drm_fb_helper_init); * fb_info pointer if things went okay, pointer containing error code * otherwise */ -struct fb_info *drm_fb_helper_alloc_fbi(struct drm_fb_helper *fb_helper) +struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) { struct device *dev = fb_helper->dev->dev; struct fb_info *info; @@ -598,7 +510,7 @@ struct fb_info *drm_fb_helper_alloc_fbi(struct drm_fb_helper *fb_helper) goto err_free_cmap; } - fb_helper->fbdev = info; + fb_helper->info = info; info->skip_vt_switch = true; return info; @@ -609,22 +521,22 @@ err_release: framebuffer_release(info); return ERR_PTR(ret); } -EXPORT_SYMBOL(drm_fb_helper_alloc_fbi); +EXPORT_SYMBOL(drm_fb_helper_alloc_info); /** - * drm_fb_helper_unregister_fbi - unregister fb_info framebuffer device + * drm_fb_helper_unregister_info - unregister fb_info framebuffer device * @fb_helper: driver-allocated fbdev helper, can be NULL * * A wrapper around unregister_framebuffer, to release the fb_info * framebuffer device. This must be called before releasing all resources for * @fb_helper by calling drm_fb_helper_fini(). */ -void drm_fb_helper_unregister_fbi(struct drm_fb_helper *fb_helper) +void drm_fb_helper_unregister_info(struct drm_fb_helper *fb_helper) { - if (fb_helper && fb_helper->fbdev) - unregister_framebuffer(fb_helper->fbdev); + if (fb_helper && fb_helper->info) + unregister_framebuffer(fb_helper->info); } -EXPORT_SYMBOL(drm_fb_helper_unregister_fbi); +EXPORT_SYMBOL(drm_fb_helper_unregister_info); /** * drm_fb_helper_fini - finialize a &struct drm_fb_helper @@ -647,13 +559,13 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) cancel_work_sync(&fb_helper->resume_work); cancel_work_sync(&fb_helper->damage_work); - info = fb_helper->fbdev; + info = fb_helper->info; if (info) { if (info->cmap.len) fb_dealloc_cmap(&info->cmap); framebuffer_release(info); } - fb_helper->fbdev = NULL; + fb_helper->info = NULL; mutex_lock(&kernel_fb_helper_lock); if (!list_empty(&fb_helper->kernel_fb_list)) { @@ -670,32 +582,24 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) } EXPORT_SYMBOL(drm_fb_helper_fini); -static bool drm_fbdev_use_shadow_fb(struct drm_fb_helper *fb_helper) -{ - struct drm_device *dev = fb_helper->dev; - struct drm_framebuffer *fb = fb_helper->fb; - - return dev->mode_config.prefer_shadow_fbdev || - dev->mode_config.prefer_shadow || - fb->funcs->dirty; -} - -static void drm_fb_helper_damage(struct fb_info *info, u32 x, u32 y, - u32 width, u32 height) +static void drm_fb_helper_add_damage_clip(struct drm_fb_helper *helper, u32 x, u32 y, + u32 width, u32 height) { - struct drm_fb_helper *helper = info->par; struct drm_clip_rect *clip = &helper->damage_clip; unsigned long flags; - if (!drm_fbdev_use_shadow_fb(helper)) - return; - spin_lock_irqsave(&helper->damage_lock, flags); clip->x1 = min_t(u32, clip->x1, x); clip->y1 = min_t(u32, clip->y1, y); clip->x2 = max_t(u32, clip->x2, x + width); clip->y2 = max_t(u32, clip->y2, y + height); spin_unlock_irqrestore(&helper->damage_lock, flags); +} + +static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, + u32 width, u32 height) +{ + drm_fb_helper_add_damage_clip(helper, x, y, width, height); schedule_work(&helper->damage_work); } @@ -739,6 +643,7 @@ static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, */ void drm_fb_helper_deferred_io(struct fb_info *info, struct list_head *pagereflist) { + struct drm_fb_helper *helper = info->par; unsigned long start, end, min_off, max_off; struct fb_deferred_io_pageref *pageref; struct drm_rect damage_area; @@ -751,8 +656,6 @@ void drm_fb_helper_deferred_io(struct fb_info *info, struct list_head *pagerefli min_off = min(min_off, start); max_off = max(max_off, end); } - if (min_off >= max_off) - return; /* * As we can only track pages, we might reach beyond the end @@ -761,53 +664,160 @@ void drm_fb_helper_deferred_io(struct fb_info *info, struct list_head *pagerefli */ max_off = min(max_off, info->screen_size); - drm_fb_helper_memory_range_to_clip(info, min_off, max_off - min_off, &damage_area); - drm_fb_helper_damage(info, damage_area.x1, damage_area.y1, - drm_rect_width(&damage_area), - drm_rect_height(&damage_area)); + if (min_off < max_off) { + drm_fb_helper_memory_range_to_clip(info, min_off, max_off - min_off, &damage_area); + drm_fb_helper_damage(helper, damage_area.x1, damage_area.y1, + drm_rect_width(&damage_area), + drm_rect_height(&damage_area)); + } } EXPORT_SYMBOL(drm_fb_helper_deferred_io); +typedef ssize_t (*drm_fb_helper_read_screen)(struct fb_info *info, char __user *buf, + size_t count, loff_t pos); + +static ssize_t __drm_fb_helper_read(struct fb_info *info, char __user *buf, size_t count, + loff_t *ppos, drm_fb_helper_read_screen read_screen) +{ + loff_t pos = *ppos; + size_t total_size; + ssize_t ret; + + if (info->screen_size) + total_size = info->screen_size; + else + total_size = info->fix.smem_len; + + if (pos >= total_size) + return 0; + if (count >= total_size) + count = total_size; + if (total_size - count < pos) + count = total_size - pos; + + if (info->fbops->fb_sync) + info->fbops->fb_sync(info); + + ret = read_screen(info, buf, count, pos); + if (ret > 0) + *ppos += ret; + + return ret; +} + +typedef ssize_t (*drm_fb_helper_write_screen)(struct fb_info *info, const char __user *buf, + size_t count, loff_t pos); + +static ssize_t __drm_fb_helper_write(struct fb_info *info, const char __user *buf, size_t count, + loff_t *ppos, drm_fb_helper_write_screen write_screen) +{ + loff_t pos = *ppos; + size_t total_size; + ssize_t ret; + int err = 0; + + if (info->screen_size) + total_size = info->screen_size; + else + total_size = info->fix.smem_len; + + if (pos > total_size) + return -EFBIG; + if (count > total_size) { + err = -EFBIG; + count = total_size; + } + if (total_size - count < pos) { + if (!err) + err = -ENOSPC; + count = total_size - pos; + } + + if (info->fbops->fb_sync) + info->fbops->fb_sync(info); + + /* + * Copy to framebuffer even if we already logged an error. Emulates + * the behavior of the original fbdev implementation. + */ + ret = write_screen(info, buf, count, pos); + if (ret < 0) + return ret; /* return last error, if any */ + else if (!ret) + return err; /* return previous error, if any */ + + *ppos += ret; + + return ret; +} + +static ssize_t drm_fb_helper_read_screen_buffer(struct fb_info *info, char __user *buf, + size_t count, loff_t pos) +{ + const char *src = info->screen_buffer + pos; + + if (copy_to_user(buf, src, count)) + return -EFAULT; + + return count; +} + /** - * drm_fb_helper_sys_read - wrapper around fb_sys_read + * drm_fb_helper_sys_read - Implements struct &fb_ops.fb_read for system memory * @info: fb_info struct pointer * @buf: userspace buffer to read from framebuffer memory * @count: number of bytes to read from framebuffer memory * @ppos: read offset within framebuffer memory * - * A wrapper around fb_sys_read implemented by fbdev core + * Returns: + * The number of bytes read on success, or an error code otherwise. */ ssize_t drm_fb_helper_sys_read(struct fb_info *info, char __user *buf, size_t count, loff_t *ppos) { - return fb_sys_read(info, buf, count, ppos); + return __drm_fb_helper_read(info, buf, count, ppos, drm_fb_helper_read_screen_buffer); } EXPORT_SYMBOL(drm_fb_helper_sys_read); +static ssize_t drm_fb_helper_write_screen_buffer(struct fb_info *info, const char __user *buf, + size_t count, loff_t pos) +{ + char *dst = info->screen_buffer + pos; + + if (copy_from_user(dst, buf, count)) + return -EFAULT; + + return count; +} + /** - * drm_fb_helper_sys_write - wrapper around fb_sys_write + * drm_fb_helper_sys_write - Implements struct &fb_ops.fb_write for system memory * @info: fb_info struct pointer * @buf: userspace buffer to write to framebuffer memory * @count: number of bytes to write to framebuffer memory * @ppos: write offset within framebuffer memory * - * A wrapper around fb_sys_write implemented by fbdev core + * Returns: + * The number of bytes written on success, or an error code otherwise. */ ssize_t drm_fb_helper_sys_write(struct fb_info *info, const char __user *buf, size_t count, loff_t *ppos) { + struct drm_fb_helper *helper = info->par; loff_t pos = *ppos; ssize_t ret; struct drm_rect damage_area; - ret = fb_sys_write(info, buf, count, ppos); + ret = __drm_fb_helper_write(info, buf, count, ppos, drm_fb_helper_write_screen_buffer); if (ret <= 0) return ret; - drm_fb_helper_memory_range_to_clip(info, pos, ret, &damage_area); - drm_fb_helper_damage(info, damage_area.x1, damage_area.y1, - drm_rect_width(&damage_area), - drm_rect_height(&damage_area)); + if (helper->funcs->fb_dirty) { + drm_fb_helper_memory_range_to_clip(info, pos, ret, &damage_area); + drm_fb_helper_damage(helper, damage_area.x1, damage_area.y1, + drm_rect_width(&damage_area), + drm_rect_height(&damage_area)); + } return ret; } @@ -823,8 +833,12 @@ EXPORT_SYMBOL(drm_fb_helper_sys_write); void drm_fb_helper_sys_fillrect(struct fb_info *info, const struct fb_fillrect *rect) { + struct drm_fb_helper *helper = info->par; + sys_fillrect(info, rect); - drm_fb_helper_damage(info, rect->dx, rect->dy, rect->width, rect->height); + + if (helper->funcs->fb_dirty) + drm_fb_helper_damage(helper, rect->dx, rect->dy, rect->width, rect->height); } EXPORT_SYMBOL(drm_fb_helper_sys_fillrect); @@ -838,8 +852,12 @@ EXPORT_SYMBOL(drm_fb_helper_sys_fillrect); void drm_fb_helper_sys_copyarea(struct fb_info *info, const struct fb_copyarea *area) { + struct drm_fb_helper *helper = info->par; + sys_copyarea(info, area); - drm_fb_helper_damage(info, area->dx, area->dy, area->width, area->height); + + if (helper->funcs->fb_dirty) + drm_fb_helper_damage(helper, area->dx, area->dy, area->width, area->height); } EXPORT_SYMBOL(drm_fb_helper_sys_copyarea); @@ -853,11 +871,131 @@ EXPORT_SYMBOL(drm_fb_helper_sys_copyarea); void drm_fb_helper_sys_imageblit(struct fb_info *info, const struct fb_image *image) { + struct drm_fb_helper *helper = info->par; + sys_imageblit(info, image); - drm_fb_helper_damage(info, image->dx, image->dy, image->width, image->height); + + if (helper->funcs->fb_dirty) + drm_fb_helper_damage(helper, image->dx, image->dy, image->width, image->height); } EXPORT_SYMBOL(drm_fb_helper_sys_imageblit); +static ssize_t fb_read_screen_base(struct fb_info *info, char __user *buf, size_t count, + loff_t pos) +{ + const char __iomem *src = info->screen_base + pos; + size_t alloc_size = min_t(size_t, count, PAGE_SIZE); + ssize_t ret = 0; + int err = 0; + char *tmp; + + tmp = kmalloc(alloc_size, GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + while (count) { + size_t c = min_t(size_t, count, alloc_size); + + memcpy_fromio(tmp, src, c); + if (copy_to_user(buf, tmp, c)) { + err = -EFAULT; + break; + } + + src += c; + buf += c; + ret += c; + count -= c; + } + + kfree(tmp); + + return ret ? ret : err; +} + +/** + * drm_fb_helper_cfb_read - Implements struct &fb_ops.fb_read for I/O memory + * @info: fb_info struct pointer + * @buf: userspace buffer to read from framebuffer memory + * @count: number of bytes to read from framebuffer memory + * @ppos: read offset within framebuffer memory + * + * Returns: + * The number of bytes read on success, or an error code otherwise. + */ +ssize_t drm_fb_helper_cfb_read(struct fb_info *info, char __user *buf, + size_t count, loff_t *ppos) +{ + return __drm_fb_helper_read(info, buf, count, ppos, fb_read_screen_base); +} +EXPORT_SYMBOL(drm_fb_helper_cfb_read); + +static ssize_t fb_write_screen_base(struct fb_info *info, const char __user *buf, size_t count, + loff_t pos) +{ + char __iomem *dst = info->screen_base + pos; + size_t alloc_size = min_t(size_t, count, PAGE_SIZE); + ssize_t ret = 0; + int err = 0; + u8 *tmp; + + tmp = kmalloc(alloc_size, GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + while (count) { + size_t c = min_t(size_t, count, alloc_size); + + if (copy_from_user(tmp, buf, c)) { + err = -EFAULT; + break; + } + memcpy_toio(dst, tmp, c); + + dst += c; + buf += c; + ret += c; + count -= c; + } + + kfree(tmp); + + return ret ? ret : err; +} + +/** + * drm_fb_helper_cfb_write - Implements struct &fb_ops.fb_write for I/O memory + * @info: fb_info struct pointer + * @buf: userspace buffer to write to framebuffer memory + * @count: number of bytes to write to framebuffer memory + * @ppos: write offset within framebuffer memory + * + * Returns: + * The number of bytes written on success, or an error code otherwise. + */ +ssize_t drm_fb_helper_cfb_write(struct fb_info *info, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct drm_fb_helper *helper = info->par; + loff_t pos = *ppos; + ssize_t ret; + struct drm_rect damage_area; + + ret = __drm_fb_helper_write(info, buf, count, ppos, fb_write_screen_base); + if (ret <= 0) + return ret; + + if (helper->funcs->fb_dirty) { + drm_fb_helper_memory_range_to_clip(info, pos, ret, &damage_area); + drm_fb_helper_damage(helper, damage_area.x1, damage_area.y1, + drm_rect_width(&damage_area), + drm_rect_height(&damage_area)); + } + + return ret; +} +EXPORT_SYMBOL(drm_fb_helper_cfb_write); + /** * drm_fb_helper_cfb_fillrect - wrapper around cfb_fillrect * @info: fbdev registered by the helper @@ -868,8 +1006,12 @@ EXPORT_SYMBOL(drm_fb_helper_sys_imageblit); void drm_fb_helper_cfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect) { + struct drm_fb_helper *helper = info->par; + cfb_fillrect(info, rect); - drm_fb_helper_damage(info, rect->dx, rect->dy, rect->width, rect->height); + + if (helper->funcs->fb_dirty) + drm_fb_helper_damage(helper, rect->dx, rect->dy, rect->width, rect->height); } EXPORT_SYMBOL(drm_fb_helper_cfb_fillrect); @@ -883,8 +1025,12 @@ EXPORT_SYMBOL(drm_fb_helper_cfb_fillrect); void drm_fb_helper_cfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) { + struct drm_fb_helper *helper = info->par; + cfb_copyarea(info, area); - drm_fb_helper_damage(info, area->dx, area->dy, area->width, area->height); + + if (helper->funcs->fb_dirty) + drm_fb_helper_damage(helper, area->dx, area->dy, area->width, area->height); } EXPORT_SYMBOL(drm_fb_helper_cfb_copyarea); @@ -898,8 +1044,12 @@ EXPORT_SYMBOL(drm_fb_helper_cfb_copyarea); void drm_fb_helper_cfb_imageblit(struct fb_info *info, const struct fb_image *image) { + struct drm_fb_helper *helper = info->par; + cfb_imageblit(info, image); - drm_fb_helper_damage(info, image->dx, image->dy, image->width, image->height); + + if (helper->funcs->fb_dirty) + drm_fb_helper_damage(helper, image->dx, image->dy, image->width, image->height); } EXPORT_SYMBOL(drm_fb_helper_cfb_imageblit); @@ -914,8 +1064,8 @@ EXPORT_SYMBOL(drm_fb_helper_cfb_imageblit); */ void drm_fb_helper_set_suspend(struct drm_fb_helper *fb_helper, bool suspend) { - if (fb_helper && fb_helper->fbdev) - fb_set_suspend(fb_helper->fbdev, suspend); + if (fb_helper && fb_helper->info) + fb_set_suspend(fb_helper->info, suspend); } EXPORT_SYMBOL(drm_fb_helper_set_suspend); @@ -938,20 +1088,20 @@ EXPORT_SYMBOL(drm_fb_helper_set_suspend); void drm_fb_helper_set_suspend_unlocked(struct drm_fb_helper *fb_helper, bool suspend) { - if (!fb_helper || !fb_helper->fbdev) + if (!fb_helper || !fb_helper->info) return; /* make sure there's no pending/ongoing resume */ flush_work(&fb_helper->resume_work); if (suspend) { - if (fb_helper->fbdev->state != FBINFO_STATE_RUNNING) + if (fb_helper->info->state != FBINFO_STATE_RUNNING) return; console_lock(); } else { - if (fb_helper->fbdev->state == FBINFO_STATE_RUNNING) + if (fb_helper->info->state == FBINFO_STATE_RUNNING) return; if (!console_trylock()) { @@ -960,7 +1110,7 @@ void drm_fb_helper_set_suspend_unlocked(struct drm_fb_helper *fb_helper, } } - fb_set_suspend(fb_helper->fbdev, suspend); + fb_set_suspend(fb_helper->info, suspend); console_unlock(); } EXPORT_SYMBOL(drm_fb_helper_set_suspend_unlocked); @@ -1749,6 +1899,10 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, sizes.surface_height = config->max_height; } +#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) + fb_helper->hint_leak_smem_start = drm_leak_fbdev_smem; +#endif + /* push down into drivers */ ret = (*fb_helper->funcs->fb_probe)(fb_helper, &sizes); if (ret < 0) @@ -1850,7 +2004,7 @@ EXPORT_SYMBOL(drm_fb_helper_fill_info); /* * This is a continuation of drm_setup_crtcs() that sets up anything related * to the framebuffer. During initialization, drm_setup_crtcs() is called before - * the framebuffer has been allocated (fb_helper->fb and fb_helper->fbdev). + * the framebuffer has been allocated (fb_helper->fb and fb_helper->info). * So, any setup that touches those fields needs to be done here instead of in * drm_setup_crtcs(). */ @@ -1858,7 +2012,7 @@ static void drm_setup_crtcs_fb(struct drm_fb_helper *fb_helper) { struct drm_client_dev *client = &fb_helper->client; struct drm_connector_list_iter conn_iter; - struct fb_info *info = fb_helper->fbdev; + struct fb_info *info = fb_helper->info; unsigned int rotation, sw_rotations = 0; struct drm_connector *connector; struct drm_mode_set *modeset; @@ -1942,11 +2096,11 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper, fb_helper->deferred_setup = false; - info = fb_helper->fbdev; + info = fb_helper->info; info->var.pixclock = 0; /* Shamelessly allow physical address leaking to userspace */ #if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) - if (!drm_leak_fbdev_smem) + if (!fb_helper->hint_leak_smem_start) #endif /* don't leak any physical addresses to userspace */ info->flags |= FBINFO_HIDE_SMEM_START; @@ -2077,7 +2231,7 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) drm_setup_crtcs_fb(fb_helper); mutex_unlock(&fb_helper->lock); - drm_fb_helper_set_par(fb_helper->fbdev); + drm_fb_helper_set_par(fb_helper->info); return 0; } @@ -2103,530 +2257,10 @@ EXPORT_SYMBOL(drm_fb_helper_lastclose); * * This function can be used as the * &drm_mode_config_funcs.output_poll_changed callback for drivers that only - * need to call drm_fb_helper_hotplug_event(). + * need to call drm_fbdev.hotplug_event(). */ void drm_fb_helper_output_poll_changed(struct drm_device *dev) { drm_fb_helper_hotplug_event(dev->fb_helper); } EXPORT_SYMBOL(drm_fb_helper_output_poll_changed); - -/* @user: 1=userspace, 0=fbcon */ -static int drm_fbdev_fb_open(struct fb_info *info, int user) -{ - struct drm_fb_helper *fb_helper = info->par; - - /* No need to take a ref for fbcon because it unbinds on unregister */ - if (user && !try_module_get(fb_helper->dev->driver->fops->owner)) - return -ENODEV; - - return 0; -} - -static int drm_fbdev_fb_release(struct fb_info *info, int user) -{ - struct drm_fb_helper *fb_helper = info->par; - - if (user) - module_put(fb_helper->dev->driver->fops->owner); - - return 0; -} - -static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper) -{ - struct fb_info *fbi = fb_helper->fbdev; - void *shadow = NULL; - - if (!fb_helper->dev) - return; - - if (fbi) { - if (fbi->fbdefio) - fb_deferred_io_cleanup(fbi); - if (drm_fbdev_use_shadow_fb(fb_helper)) - shadow = fbi->screen_buffer; - } - - drm_fb_helper_fini(fb_helper); - - if (shadow) - vfree(shadow); - else if (fb_helper->buffer) - drm_client_buffer_vunmap(fb_helper->buffer); - - drm_client_framebuffer_delete(fb_helper->buffer); -} - -static void drm_fbdev_release(struct drm_fb_helper *fb_helper) -{ - drm_fbdev_cleanup(fb_helper); - drm_client_release(&fb_helper->client); - kfree(fb_helper); -} - -/* - * fb_ops.fb_destroy is called by the last put_fb_info() call at the end of - * unregister_framebuffer() or fb_release(). - */ -static void drm_fbdev_fb_destroy(struct fb_info *info) -{ - drm_fbdev_release(info->par); -} - -static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) -{ - struct drm_fb_helper *fb_helper = info->par; - - if (drm_fbdev_use_shadow_fb(fb_helper)) - return fb_deferred_io_mmap(info, vma); - else if (fb_helper->dev->driver->gem_prime_mmap) - return fb_helper->dev->driver->gem_prime_mmap(fb_helper->buffer->gem, vma); - else - return -ENODEV; -} - -static bool drm_fbdev_use_iomem(struct fb_info *info) -{ - struct drm_fb_helper *fb_helper = info->par; - struct drm_client_buffer *buffer = fb_helper->buffer; - - return !drm_fbdev_use_shadow_fb(fb_helper) && buffer->map.is_iomem; -} - -static ssize_t fb_read_screen_base(struct fb_info *info, char __user *buf, size_t count, - loff_t pos) -{ - const char __iomem *src = info->screen_base + pos; - size_t alloc_size = min_t(size_t, count, PAGE_SIZE); - ssize_t ret = 0; - int err = 0; - char *tmp; - - tmp = kmalloc(alloc_size, GFP_KERNEL); - if (!tmp) - return -ENOMEM; - - while (count) { - size_t c = min_t(size_t, count, alloc_size); - - memcpy_fromio(tmp, src, c); - if (copy_to_user(buf, tmp, c)) { - err = -EFAULT; - break; - } - - src += c; - buf += c; - ret += c; - count -= c; - } - - kfree(tmp); - - return ret ? ret : err; -} - -static ssize_t fb_read_screen_buffer(struct fb_info *info, char __user *buf, size_t count, - loff_t pos) -{ - const char *src = info->screen_buffer + pos; - - if (copy_to_user(buf, src, count)) - return -EFAULT; - - return count; -} - -static ssize_t drm_fbdev_fb_read(struct fb_info *info, char __user *buf, - size_t count, loff_t *ppos) -{ - loff_t pos = *ppos; - size_t total_size; - ssize_t ret; - - if (info->screen_size) - total_size = info->screen_size; - else - total_size = info->fix.smem_len; - - if (pos >= total_size) - return 0; - if (count >= total_size) - count = total_size; - if (total_size - count < pos) - count = total_size - pos; - - if (drm_fbdev_use_iomem(info)) - ret = fb_read_screen_base(info, buf, count, pos); - else - ret = fb_read_screen_buffer(info, buf, count, pos); - - if (ret > 0) - *ppos += ret; - - return ret; -} - -static ssize_t fb_write_screen_base(struct fb_info *info, const char __user *buf, size_t count, - loff_t pos) -{ - char __iomem *dst = info->screen_base + pos; - size_t alloc_size = min_t(size_t, count, PAGE_SIZE); - ssize_t ret = 0; - int err = 0; - u8 *tmp; - - tmp = kmalloc(alloc_size, GFP_KERNEL); - if (!tmp) - return -ENOMEM; - - while (count) { - size_t c = min_t(size_t, count, alloc_size); - - if (copy_from_user(tmp, buf, c)) { - err = -EFAULT; - break; - } - memcpy_toio(dst, tmp, c); - - dst += c; - buf += c; - ret += c; - count -= c; - } - - kfree(tmp); - - return ret ? ret : err; -} - -static ssize_t fb_write_screen_buffer(struct fb_info *info, const char __user *buf, size_t count, - loff_t pos) -{ - char *dst = info->screen_buffer + pos; - - if (copy_from_user(dst, buf, count)) - return -EFAULT; - - return count; -} - -static ssize_t drm_fbdev_fb_write(struct fb_info *info, const char __user *buf, - size_t count, loff_t *ppos) -{ - loff_t pos = *ppos; - size_t total_size; - ssize_t ret; - struct drm_rect damage_area; - int err = 0; - - if (info->screen_size) - total_size = info->screen_size; - else - total_size = info->fix.smem_len; - - if (pos > total_size) - return -EFBIG; - if (count > total_size) { - err = -EFBIG; - count = total_size; - } - if (total_size - count < pos) { - if (!err) - err = -ENOSPC; - count = total_size - pos; - } - - /* - * Copy to framebuffer even if we already logged an error. Emulates - * the behavior of the original fbdev implementation. - */ - if (drm_fbdev_use_iomem(info)) - ret = fb_write_screen_base(info, buf, count, pos); - else - ret = fb_write_screen_buffer(info, buf, count, pos); - - if (ret < 0) - return ret; /* return last error, if any */ - else if (!ret) - return err; /* return previous error, if any */ - - *ppos += ret; - - drm_fb_helper_memory_range_to_clip(info, pos, ret, &damage_area); - drm_fb_helper_damage(info, damage_area.x1, damage_area.y1, - drm_rect_width(&damage_area), - drm_rect_height(&damage_area)); - - return ret; -} - -static void drm_fbdev_fb_fillrect(struct fb_info *info, - const struct fb_fillrect *rect) -{ - if (drm_fbdev_use_iomem(info)) - drm_fb_helper_cfb_fillrect(info, rect); - else - drm_fb_helper_sys_fillrect(info, rect); -} - -static void drm_fbdev_fb_copyarea(struct fb_info *info, - const struct fb_copyarea *area) -{ - if (drm_fbdev_use_iomem(info)) - drm_fb_helper_cfb_copyarea(info, area); - else - drm_fb_helper_sys_copyarea(info, area); -} - -static void drm_fbdev_fb_imageblit(struct fb_info *info, - const struct fb_image *image) -{ - if (drm_fbdev_use_iomem(info)) - drm_fb_helper_cfb_imageblit(info, image); - else - drm_fb_helper_sys_imageblit(info, image); -} - -static const struct fb_ops drm_fbdev_fb_ops = { - .owner = THIS_MODULE, - DRM_FB_HELPER_DEFAULT_OPS, - .fb_open = drm_fbdev_fb_open, - .fb_release = drm_fbdev_fb_release, - .fb_destroy = drm_fbdev_fb_destroy, - .fb_mmap = drm_fbdev_fb_mmap, - .fb_read = drm_fbdev_fb_read, - .fb_write = drm_fbdev_fb_write, - .fb_fillrect = drm_fbdev_fb_fillrect, - .fb_copyarea = drm_fbdev_fb_copyarea, - .fb_imageblit = drm_fbdev_fb_imageblit, -}; - -static struct fb_deferred_io drm_fbdev_defio = { - .delay = HZ / 20, - .deferred_io = drm_fb_helper_deferred_io, -}; - -/* - * This function uses the client API to create a framebuffer backed by a dumb buffer. - * - * The _sys_ versions are used for &fb_ops.fb_read, fb_write, fb_fillrect, - * fb_copyarea, fb_imageblit. - */ -static int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, - struct drm_fb_helper_surface_size *sizes) -{ - struct drm_client_dev *client = &fb_helper->client; - struct drm_device *dev = fb_helper->dev; - struct drm_client_buffer *buffer; - struct drm_framebuffer *fb; - struct fb_info *fbi; - u32 format; - struct iosys_map map; - int ret; - - drm_dbg_kms(dev, "surface width(%d), height(%d) and bpp(%d)\n", - sizes->surface_width, sizes->surface_height, - sizes->surface_bpp); - - format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth); - buffer = drm_client_framebuffer_create(client, sizes->surface_width, - sizes->surface_height, format); - if (IS_ERR(buffer)) - return PTR_ERR(buffer); - - fb_helper->buffer = buffer; - fb_helper->fb = buffer->fb; - fb = buffer->fb; - - fbi = drm_fb_helper_alloc_fbi(fb_helper); - if (IS_ERR(fbi)) - return PTR_ERR(fbi); - - fbi->fbops = &drm_fbdev_fb_ops; - fbi->screen_size = sizes->surface_height * fb->pitches[0]; - fbi->fix.smem_len = fbi->screen_size; - fbi->flags = FBINFO_DEFAULT; - - drm_fb_helper_fill_info(fbi, fb_helper, sizes); - - if (drm_fbdev_use_shadow_fb(fb_helper)) { - fbi->screen_buffer = vzalloc(fbi->screen_size); - if (!fbi->screen_buffer) - return -ENOMEM; - fbi->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST; - - fbi->fbdefio = &drm_fbdev_defio; - fb_deferred_io_init(fbi); - } else { - /* buffer is mapped for HW framebuffer */ - ret = drm_client_buffer_vmap(fb_helper->buffer, &map); - if (ret) - return ret; - if (map.is_iomem) { - fbi->screen_base = map.vaddr_iomem; - } else { - fbi->screen_buffer = map.vaddr; - fbi->flags |= FBINFO_VIRTFB; - } - - /* - * Shamelessly leak the physical address to user-space. As - * page_to_phys() is undefined for I/O memory, warn in this - * case. - */ -#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) - if (drm_leak_fbdev_smem && fbi->fix.smem_start == 0 && - !drm_WARN_ON_ONCE(dev, map.is_iomem)) - fbi->fix.smem_start = - page_to_phys(virt_to_page(fbi->screen_buffer)); -#endif - } - - return 0; -} - -static const struct drm_fb_helper_funcs drm_fb_helper_generic_funcs = { - .fb_probe = drm_fb_helper_generic_probe, -}; - -static void drm_fbdev_client_unregister(struct drm_client_dev *client) -{ - struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); - - if (fb_helper->fbdev) - /* drm_fbdev_fb_destroy() takes care of cleanup */ - drm_fb_helper_unregister_fbi(fb_helper); - else - drm_fbdev_release(fb_helper); -} - -static int drm_fbdev_client_restore(struct drm_client_dev *client) -{ - drm_fb_helper_lastclose(client->dev); - - return 0; -} - -static int drm_fbdev_client_hotplug(struct drm_client_dev *client) -{ - struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); - struct drm_device *dev = client->dev; - int ret; - - /* Setup is not retried if it has failed */ - if (!fb_helper->dev && fb_helper->funcs) - return 0; - - if (dev->fb_helper) - return drm_fb_helper_hotplug_event(dev->fb_helper); - - if (!dev->mode_config.num_connector) { - drm_dbg_kms(dev, "No connectors found, will not create framebuffer!\n"); - return 0; - } - - drm_fb_helper_prepare(dev, fb_helper, &drm_fb_helper_generic_funcs); - - ret = drm_fb_helper_init(dev, fb_helper); - if (ret) - goto err; - - if (!drm_drv_uses_atomic_modeset(dev)) - drm_helper_disable_unused_functions(dev); - - ret = drm_fb_helper_initial_config(fb_helper, fb_helper->preferred_bpp); - if (ret) - goto err_cleanup; - - return 0; - -err_cleanup: - drm_fbdev_cleanup(fb_helper); -err: - fb_helper->dev = NULL; - fb_helper->fbdev = NULL; - - drm_err(dev, "fbdev: Failed to setup generic emulation (ret=%d)\n", ret); - - return ret; -} - -static const struct drm_client_funcs drm_fbdev_client_funcs = { - .owner = THIS_MODULE, - .unregister = drm_fbdev_client_unregister, - .restore = drm_fbdev_client_restore, - .hotplug = drm_fbdev_client_hotplug, -}; - -/** - * drm_fbdev_generic_setup() - Setup generic fbdev emulation - * @dev: DRM device - * @preferred_bpp: Preferred bits per pixel for the device. - * @dev->mode_config.preferred_depth is used if this is zero. - * - * This function sets up generic fbdev emulation for drivers that supports - * dumb buffers with a virtual address and that can be mmap'ed. - * drm_fbdev_generic_setup() shall be called after the DRM driver registered - * the new DRM device with drm_dev_register(). - * - * Restore, hotplug events and teardown are all taken care of. Drivers that do - * suspend/resume need to call drm_fb_helper_set_suspend_unlocked() themselves. - * Simple drivers might use drm_mode_config_helper_suspend(). - * - * Drivers that set the dirty callback on their framebuffer will get a shadow - * fbdev buffer that is blitted onto the real buffer. This is done in order to - * make deferred I/O work with all kinds of buffers. A shadow buffer can be - * requested explicitly by setting struct drm_mode_config.prefer_shadow or - * struct drm_mode_config.prefer_shadow_fbdev to true beforehand. This is - * required to use generic fbdev emulation with SHMEM helpers. - * - * This function is safe to call even when there are no connectors present. - * Setup will be retried on the next hotplug event. - * - * The fbdev is destroyed by drm_dev_unregister(). - */ -void drm_fbdev_generic_setup(struct drm_device *dev, - unsigned int preferred_bpp) -{ - struct drm_fb_helper *fb_helper; - int ret; - - drm_WARN(dev, !dev->registered, "Device has not been registered.\n"); - drm_WARN(dev, dev->fb_helper, "fb_helper is already set!\n"); - - if (!drm_fbdev_emulation) - return; - - fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL); - if (!fb_helper) { - drm_err(dev, "Failed to allocate fb_helper\n"); - return; - } - - ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs); - if (ret) { - kfree(fb_helper); - drm_err(dev, "Failed to register client: %d\n", ret); - return; - } - - /* - * FIXME: This mixes up depth with bpp, which results in a glorious - * mess, resulting in some drivers picking wrong fbdev defaults and - * others wrong preferred_depth defaults. - */ - if (!preferred_bpp) - preferred_bpp = dev->mode_config.preferred_depth; - if (!preferred_bpp) - preferred_bpp = 32; - fb_helper->preferred_bpp = preferred_bpp; - - ret = drm_fbdev_client_hotplug(&fb_helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - - drm_client_register(&fb_helper->client); -} -EXPORT_SYMBOL(drm_fbdev_generic_setup); diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c new file mode 100644 index 000000000000..ab8695669279 --- /dev/null +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -0,0 +1,494 @@ +// SPDX-License-Identifier: MIT + +#include <linux/moduleparam.h> +#include <linux/vmalloc.h> + +#include <drm/drm_crtc_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_framebuffer.h> +#include <drm/drm_print.h> + +#include <drm/drm_fbdev_generic.h> + +static bool drm_fbdev_use_shadow_fb(struct drm_fb_helper *fb_helper) +{ + struct drm_device *dev = fb_helper->dev; + struct drm_framebuffer *fb = fb_helper->fb; + + return dev->mode_config.prefer_shadow_fbdev || + dev->mode_config.prefer_shadow || + fb->funcs->dirty; +} + +/* @user: 1=userspace, 0=fbcon */ +static int drm_fbdev_fb_open(struct fb_info *info, int user) +{ + struct drm_fb_helper *fb_helper = info->par; + + /* No need to take a ref for fbcon because it unbinds on unregister */ + if (user && !try_module_get(fb_helper->dev->driver->fops->owner)) + return -ENODEV; + + return 0; +} + +static int drm_fbdev_fb_release(struct fb_info *info, int user) +{ + struct drm_fb_helper *fb_helper = info->par; + + if (user) + module_put(fb_helper->dev->driver->fops->owner); + + return 0; +} + +static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper) +{ + struct fb_info *fbi = fb_helper->info; + void *shadow = NULL; + + if (!fb_helper->dev) + return; + + if (fbi) { + if (fbi->fbdefio) + fb_deferred_io_cleanup(fbi); + if (drm_fbdev_use_shadow_fb(fb_helper)) + shadow = fbi->screen_buffer; + } + + drm_fb_helper_fini(fb_helper); + + if (shadow) + vfree(shadow); + else if (fb_helper->buffer) + drm_client_buffer_vunmap(fb_helper->buffer); + + drm_client_framebuffer_delete(fb_helper->buffer); +} + +static void drm_fbdev_release(struct drm_fb_helper *fb_helper) +{ + drm_fbdev_cleanup(fb_helper); + drm_client_release(&fb_helper->client); + kfree(fb_helper); +} + +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end of + * unregister_framebuffer() or fb_release(). + */ +static void drm_fbdev_fb_destroy(struct fb_info *info) +{ + drm_fbdev_release(info->par); +} + +static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) +{ + struct drm_fb_helper *fb_helper = info->par; + + if (drm_fbdev_use_shadow_fb(fb_helper)) + return fb_deferred_io_mmap(info, vma); + else if (fb_helper->dev->driver->gem_prime_mmap) + return fb_helper->dev->driver->gem_prime_mmap(fb_helper->buffer->gem, vma); + else + return -ENODEV; +} + +static bool drm_fbdev_use_iomem(struct fb_info *info) +{ + struct drm_fb_helper *fb_helper = info->par; + struct drm_client_buffer *buffer = fb_helper->buffer; + + return !drm_fbdev_use_shadow_fb(fb_helper) && buffer->map.is_iomem; +} + +static ssize_t drm_fbdev_fb_read(struct fb_info *info, char __user *buf, + size_t count, loff_t *ppos) +{ + ssize_t ret; + + if (drm_fbdev_use_iomem(info)) + ret = drm_fb_helper_cfb_read(info, buf, count, ppos); + else + ret = drm_fb_helper_sys_read(info, buf, count, ppos); + + return ret; +} + +static ssize_t drm_fbdev_fb_write(struct fb_info *info, const char __user *buf, + size_t count, loff_t *ppos) +{ + ssize_t ret; + + if (drm_fbdev_use_iomem(info)) + ret = drm_fb_helper_cfb_write(info, buf, count, ppos); + else + ret = drm_fb_helper_sys_write(info, buf, count, ppos); + + return ret; +} + +static void drm_fbdev_fb_fillrect(struct fb_info *info, + const struct fb_fillrect *rect) +{ + if (drm_fbdev_use_iomem(info)) + drm_fb_helper_cfb_fillrect(info, rect); + else + drm_fb_helper_sys_fillrect(info, rect); +} + +static void drm_fbdev_fb_copyarea(struct fb_info *info, + const struct fb_copyarea *area) +{ + if (drm_fbdev_use_iomem(info)) + drm_fb_helper_cfb_copyarea(info, area); + else + drm_fb_helper_sys_copyarea(info, area); +} + +static void drm_fbdev_fb_imageblit(struct fb_info *info, + const struct fb_image *image) +{ + if (drm_fbdev_use_iomem(info)) + drm_fb_helper_cfb_imageblit(info, image); + else + drm_fb_helper_sys_imageblit(info, image); +} + +static const struct fb_ops drm_fbdev_fb_ops = { + .owner = THIS_MODULE, + DRM_FB_HELPER_DEFAULT_OPS, + .fb_open = drm_fbdev_fb_open, + .fb_release = drm_fbdev_fb_release, + .fb_destroy = drm_fbdev_fb_destroy, + .fb_mmap = drm_fbdev_fb_mmap, + .fb_read = drm_fbdev_fb_read, + .fb_write = drm_fbdev_fb_write, + .fb_fillrect = drm_fbdev_fb_fillrect, + .fb_copyarea = drm_fbdev_fb_copyarea, + .fb_imageblit = drm_fbdev_fb_imageblit, +}; + +static struct fb_deferred_io drm_fbdev_defio = { + .delay = HZ / 20, + .deferred_io = drm_fb_helper_deferred_io, +}; + +/* + * This function uses the client API to create a framebuffer backed by a dumb buffer. + */ +static int drm_fbdev_fb_probe(struct drm_fb_helper *fb_helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct drm_client_dev *client = &fb_helper->client; + struct drm_device *dev = fb_helper->dev; + struct drm_client_buffer *buffer; + struct drm_framebuffer *fb; + struct fb_info *fbi; + u32 format; + struct iosys_map map; + int ret; + + drm_dbg_kms(dev, "surface width(%d), height(%d) and bpp(%d)\n", + sizes->surface_width, sizes->surface_height, + sizes->surface_bpp); + + format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth); + buffer = drm_client_framebuffer_create(client, sizes->surface_width, + sizes->surface_height, format); + if (IS_ERR(buffer)) + return PTR_ERR(buffer); + + fb_helper->buffer = buffer; + fb_helper->fb = buffer->fb; + fb = buffer->fb; + + fbi = drm_fb_helper_alloc_info(fb_helper); + if (IS_ERR(fbi)) + return PTR_ERR(fbi); + + fbi->fbops = &drm_fbdev_fb_ops; + fbi->screen_size = sizes->surface_height * fb->pitches[0]; + fbi->fix.smem_len = fbi->screen_size; + fbi->flags = FBINFO_DEFAULT; + + drm_fb_helper_fill_info(fbi, fb_helper, sizes); + + if (drm_fbdev_use_shadow_fb(fb_helper)) { + fbi->screen_buffer = vzalloc(fbi->screen_size); + if (!fbi->screen_buffer) + return -ENOMEM; + fbi->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST; + + fbi->fbdefio = &drm_fbdev_defio; + fb_deferred_io_init(fbi); + } else { + /* buffer is mapped for HW framebuffer */ + ret = drm_client_buffer_vmap(fb_helper->buffer, &map); + if (ret) + return ret; + if (map.is_iomem) { + fbi->screen_base = map.vaddr_iomem; + } else { + fbi->screen_buffer = map.vaddr; + fbi->flags |= FBINFO_VIRTFB; + } + + /* + * Shamelessly leak the physical address to user-space. As + * page_to_phys() is undefined for I/O memory, warn in this + * case. + */ +#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) + if (fb_helper->hint_leak_smem_start && fbi->fix.smem_start == 0 && + !drm_WARN_ON_ONCE(dev, map.is_iomem)) + fbi->fix.smem_start = + page_to_phys(virt_to_page(fbi->screen_buffer)); +#endif + } + + return 0; +} + +static void drm_fbdev_damage_blit_real(struct drm_fb_helper *fb_helper, + struct drm_clip_rect *clip, + struct iosys_map *dst) +{ + struct drm_framebuffer *fb = fb_helper->fb; + size_t offset = clip->y1 * fb->pitches[0]; + size_t len = clip->x2 - clip->x1; + unsigned int y; + void *src; + + switch (drm_format_info_bpp(fb->format, 0)) { + case 1: + offset += clip->x1 / 8; + len = DIV_ROUND_UP(len + clip->x1 % 8, 8); + break; + case 2: + offset += clip->x1 / 4; + len = DIV_ROUND_UP(len + clip->x1 % 4, 4); + break; + case 4: + offset += clip->x1 / 2; + len = DIV_ROUND_UP(len + clip->x1 % 2, 2); + break; + default: + offset += clip->x1 * fb->format->cpp[0]; + len *= fb->format->cpp[0]; + break; + } + + src = fb_helper->info->screen_buffer + offset; + iosys_map_incr(dst, offset); /* go to first pixel within clip rect */ + + for (y = clip->y1; y < clip->y2; y++) { + iosys_map_memcpy_to(dst, 0, src, len); + iosys_map_incr(dst, fb->pitches[0]); + src += fb->pitches[0]; + } +} + +static int drm_fbdev_damage_blit(struct drm_fb_helper *fb_helper, + struct drm_clip_rect *clip) +{ + struct drm_client_buffer *buffer = fb_helper->buffer; + struct iosys_map map, dst; + int ret; + + /* + * We have to pin the client buffer to its current location while + * flushing the shadow buffer. In the general case, concurrent + * modesetting operations could try to move the buffer and would + * fail. The modeset has to be serialized by acquiring the reservation + * object of the underlying BO here. + * + * For fbdev emulation, we only have to protect against fbdev modeset + * operations. Nothing else will involve the client buffer's BO. So it + * is sufficient to acquire struct drm_fb_helper.lock here. + */ + mutex_lock(&fb_helper->lock); + + ret = drm_client_buffer_vmap(buffer, &map); + if (ret) + goto out; + + dst = map; + drm_fbdev_damage_blit_real(fb_helper, clip, &dst); + + drm_client_buffer_vunmap(buffer); + +out: + mutex_unlock(&fb_helper->lock); + + return ret; +} + +static int drm_fbdev_fb_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip) +{ + struct drm_device *dev = helper->dev; + int ret; + + if (!drm_fbdev_use_shadow_fb(helper)) + return 0; + + /* Call damage handlers only if necessary */ + if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2)) + return 0; + + if (helper->buffer) { + ret = drm_fbdev_damage_blit(helper, clip); + if (drm_WARN_ONCE(dev, ret, "Damage blitter failed: ret=%d\n", ret)) + return ret; + } + + if (helper->fb->funcs->dirty) { + ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1); + if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret)) + return ret; + } + + return 0; +} + +static const struct drm_fb_helper_funcs drm_fb_helper_generic_funcs = { + .fb_probe = drm_fbdev_fb_probe, + .fb_dirty = drm_fbdev_fb_dirty, +}; + +static void drm_fbdev_client_unregister(struct drm_client_dev *client) +{ + struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); + + if (fb_helper->info) + /* drm_fbdev_fb_destroy() takes care of cleanup */ + drm_fb_helper_unregister_info(fb_helper); + else + drm_fbdev_release(fb_helper); +} + +static int drm_fbdev_client_restore(struct drm_client_dev *client) +{ + drm_fb_helper_lastclose(client->dev); + + return 0; +} + +static int drm_fbdev_client_hotplug(struct drm_client_dev *client) +{ + struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); + struct drm_device *dev = client->dev; + int ret; + + /* Setup is not retried if it has failed */ + if (!fb_helper->dev && fb_helper->funcs) + return 0; + + if (dev->fb_helper) + return drm_fb_helper_hotplug_event(dev->fb_helper); + + if (!dev->mode_config.num_connector) { + drm_dbg_kms(dev, "No connectors found, will not create framebuffer!\n"); + return 0; + } + + drm_fb_helper_prepare(dev, fb_helper, &drm_fb_helper_generic_funcs); + + ret = drm_fb_helper_init(dev, fb_helper); + if (ret) + goto err; + + if (!drm_drv_uses_atomic_modeset(dev)) + drm_helper_disable_unused_functions(dev); + + ret = drm_fb_helper_initial_config(fb_helper, fb_helper->preferred_bpp); + if (ret) + goto err_cleanup; + + return 0; + +err_cleanup: + drm_fbdev_cleanup(fb_helper); +err: + fb_helper->dev = NULL; + fb_helper->info = NULL; + + drm_err(dev, "fbdev: Failed to setup generic emulation (ret=%d)\n", ret); + + return ret; +} + +static const struct drm_client_funcs drm_fbdev_client_funcs = { + .owner = THIS_MODULE, + .unregister = drm_fbdev_client_unregister, + .restore = drm_fbdev_client_restore, + .hotplug = drm_fbdev_client_hotplug, +}; + +/** + * drm_fbdev_generic_setup() - Setup generic fbdev emulation + * @dev: DRM device + * @preferred_bpp: Preferred bits per pixel for the device. + * @dev->mode_config.preferred_depth is used if this is zero. + * + * This function sets up generic fbdev emulation for drivers that supports + * dumb buffers with a virtual address and that can be mmap'ed. + * drm_fbdev_generic_setup() shall be called after the DRM driver registered + * the new DRM device with drm_dev_register(). + * + * Restore, hotplug events and teardown are all taken care of. Drivers that do + * suspend/resume need to call drm_fb_helper_set_suspend_unlocked() themselves. + * Simple drivers might use drm_mode_config_helper_suspend(). + * + * Drivers that set the dirty callback on their framebuffer will get a shadow + * fbdev buffer that is blitted onto the real buffer. This is done in order to + * make deferred I/O work with all kinds of buffers. A shadow buffer can be + * requested explicitly by setting struct drm_mode_config.prefer_shadow or + * struct drm_mode_config.prefer_shadow_fbdev to true beforehand. This is + * required to use generic fbdev emulation with SHMEM helpers. + * + * This function is safe to call even when there are no connectors present. + * Setup will be retried on the next hotplug event. + * + * The fbdev is destroyed by drm_dev_unregister(). + */ +void drm_fbdev_generic_setup(struct drm_device *dev, + unsigned int preferred_bpp) +{ + struct drm_fb_helper *fb_helper; + int ret; + + drm_WARN(dev, !dev->registered, "Device has not been registered.\n"); + drm_WARN(dev, dev->fb_helper, "fb_helper is already set!\n"); + + fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL); + if (!fb_helper) + return; + + ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs); + if (ret) { + kfree(fb_helper); + drm_err(dev, "Failed to register client: %d\n", ret); + return; + } + + /* + * FIXME: This mixes up depth with bpp, which results in a glorious + * mess, resulting in some drivers picking wrong fbdev defaults and + * others wrong preferred_depth defaults. + */ + if (!preferred_bpp) + preferred_bpp = dev->mode_config.preferred_depth; + if (!preferred_bpp) + preferred_bpp = 32; + fb_helper->preferred_bpp = preferred_bpp; + + ret = drm_fbdev_client_hotplug(&fb_helper->client); + if (ret) + drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); + + drm_client_register(&fb_helper->client); +} +EXPORT_SYMBOL(drm_fbdev_generic_setup); diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index a8b4d918e9a3..64b4a3a87fbb 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -326,7 +326,7 @@ static int drm_cpu_valid(void) * Creates and initializes a drm_file structure for the file private data in \p * filp and add it into the double linked list in \p dev. */ -static int drm_open_helper(struct file *filp, struct drm_minor *minor) +int drm_open_helper(struct file *filp, struct drm_minor *minor) { struct drm_device *dev = minor->dev; struct drm_file *priv; diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index 653a5821dd53..74ff33c2ddaa 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -817,6 +817,38 @@ static bool is_listed_fourcc(const uint32_t *fourccs, size_t nfourccs, uint32_t return false; } +static const uint32_t conv_from_xrgb8888[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XRGB2101010, + DRM_FORMAT_ARGB2101010, + DRM_FORMAT_RGB565, + DRM_FORMAT_RGB888, +}; + +static const uint32_t conv_from_rgb565_888[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, +}; + +static bool is_conversion_supported(uint32_t from, uint32_t to) +{ + switch (from) { + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_ARGB8888: + return is_listed_fourcc(conv_from_xrgb8888, ARRAY_SIZE(conv_from_xrgb8888), to); + case DRM_FORMAT_RGB565: + case DRM_FORMAT_RGB888: + return is_listed_fourcc(conv_from_rgb565_888, ARRAY_SIZE(conv_from_rgb565_888), to); + case DRM_FORMAT_XRGB2101010: + return to == DRM_FORMAT_ARGB2101010; + case DRM_FORMAT_ARGB2101010: + return to == DRM_FORMAT_XRGB2101010; + default: + return false; + } +} + /** * drm_fb_build_fourcc_list - Filters a list of supported color formats against * the device's native formats @@ -837,7 +869,9 @@ static bool is_listed_fourcc(const uint32_t *fourccs, size_t nfourccs, uint32_t * be handed over to drm_universal_plane_init() et al. Native formats * will go before emulated formats. Other heuristics might be applied * to optimize the order. Formats near the beginning of the list are - * usually preferred over formats near the end of the list. + * usually preferred over formats near the end of the list. Formats + * without conversion helpers will be skipped. New drivers should only + * pass in XRGB8888 and avoid exposing additional emulated formats. * * Returns: * The number of color-formats 4CC codes returned in @fourccs_out. @@ -849,7 +883,7 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, { u32 *fourccs = fourccs_out; const u32 *fourccs_end = fourccs_out + nfourccs_out; - bool found_native = false; + uint32_t native_format = 0; size_t i; /* @@ -868,27 +902,19 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, drm_dbg_kms(dev, "adding native format %p4cc\n", &fourcc); - if (!found_native) - found_native = is_listed_fourcc(driver_fourccs, driver_nfourccs, fourcc); + /* + * There should only be one native format with the current API. + * This API needs to be refactored to correctly support arbitrary + * sets of native formats, since it needs to report which native + * format to use for each emulated format. + */ + if (!native_format) + native_format = fourcc; *fourccs = fourcc; ++fourccs; } /* - * The plane's atomic_update helper converts the framebuffer's color format - * to a native format when copying to device memory. - * - * If there is not a single format supported by both, device and - * driver, the native formats are likely not supported by the conversion - * helpers. Therefore *only* support the native formats and add a - * conversion helper ASAP. - */ - if (!found_native) { - drm_warn(dev, "Format conversion helpers required to add extra formats.\n"); - goto out; - } - - /* * The extra formats, emulated by the driver, go second. */ @@ -900,6 +926,9 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, } else if (fourccs == fourccs_end) { drm_warn(dev, "Ignoring emulated format %p4cc\n", &fourcc); continue; /* end of available output buffer */ + } else if (!is_conversion_supported(fourcc, native_format)) { + drm_dbg_kms(dev, "Unsupported emulated format %p4cc\n", &fourcc); + continue; /* format is not supported for conversion */ } drm_dbg_kms(dev, "adding emulated format %p4cc\n", &fourcc); @@ -908,7 +937,6 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, ++fourccs; } -out: return fourccs - fourccs_out; } EXPORT_SYMBOL(drm_fb_build_fourcc_list); diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index e09331bb3bc7..6242dfbe9240 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -297,12 +297,12 @@ const struct drm_format_info *__drm_format_info(u32 format) .vsub = 2, .is_yuv = true }, { .format = DRM_FORMAT_Q410, .depth = 0, .num_planes = 3, .char_per_block = { 2, 2, 2 }, - .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0, - .vsub = 0, .is_yuv = true }, + .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 1, + .vsub = 1, .is_yuv = true }, { .format = DRM_FORMAT_Q401, .depth = 0, .num_planes = 3, .char_per_block = { 2, 2, 2 }, - .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0, - .vsub = 0, .is_yuv = true }, + .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 1, + .vsub = 1, .is_yuv = true }, { .format = DRM_FORMAT_P030, .depth = 0, .num_planes = 2, .char_per_block = { 4, 8, 0 }, .block_w = { 3, 3, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true}, diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index b6a0110eb64a..e42800718f51 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -360,48 +360,43 @@ void drm_gem_reset_shadow_plane(struct drm_plane *plane) EXPORT_SYMBOL(drm_gem_reset_shadow_plane); /** - * drm_gem_prepare_shadow_fb - prepares shadow framebuffers + * drm_gem_begin_shadow_fb_access - prepares shadow framebuffers for CPU access * @plane: the plane * @plane_state: the plane state of type struct drm_shadow_plane_state * - * This function implements struct &drm_plane_helper_funcs.prepare_fb. It + * This function implements struct &drm_plane_helper_funcs.begin_fb_access. It * maps all buffer objects of the plane's framebuffer into kernel address - * space and stores them in &struct drm_shadow_plane_state.map. The - * framebuffer will be synchronized as part of the atomic commit. + * space and stores them in struct &drm_shadow_plane_state.map. The first data + * bytes are available in struct &drm_shadow_plane_state.data. * - * See drm_gem_cleanup_shadow_fb() for cleanup. + * See drm_gem_end_shadow_fb_access() for cleanup. * * Returns: * 0 on success, or a negative errno code otherwise. */ -int drm_gem_prepare_shadow_fb(struct drm_plane *plane, struct drm_plane_state *plane_state) +int drm_gem_begin_shadow_fb_access(struct drm_plane *plane, struct drm_plane_state *plane_state) { struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state); struct drm_framebuffer *fb = plane_state->fb; - int ret; if (!fb) return 0; - ret = drm_gem_plane_helper_prepare_fb(plane, plane_state); - if (ret) - return ret; - return drm_gem_fb_vmap(fb, shadow_plane_state->map, shadow_plane_state->data); } -EXPORT_SYMBOL(drm_gem_prepare_shadow_fb); +EXPORT_SYMBOL(drm_gem_begin_shadow_fb_access); /** - * drm_gem_cleanup_shadow_fb - releases shadow framebuffers + * drm_gem_end_shadow_fb_access - releases shadow framebuffers from CPU access * @plane: the plane * @plane_state: the plane state of type struct drm_shadow_plane_state * - * This function implements struct &drm_plane_helper_funcs.cleanup_fb. - * This function unmaps all buffer objects of the plane's framebuffer. + * This function implements struct &drm_plane_helper_funcs.end_fb_access. It + * undoes all effects of drm_gem_begin_shadow_fb_access() in reverse order. * - * See drm_gem_prepare_shadow_fb() for more information. + * See drm_gem_begin_shadow_fb_access() for more information. */ -void drm_gem_cleanup_shadow_fb(struct drm_plane *plane, struct drm_plane_state *plane_state) +void drm_gem_end_shadow_fb_access(struct drm_plane *plane, struct drm_plane_state *plane_state) { struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state); struct drm_framebuffer *fb = plane_state->fb; @@ -411,46 +406,45 @@ void drm_gem_cleanup_shadow_fb(struct drm_plane *plane, struct drm_plane_state * drm_gem_fb_vunmap(fb, shadow_plane_state->map); } -EXPORT_SYMBOL(drm_gem_cleanup_shadow_fb); +EXPORT_SYMBOL(drm_gem_end_shadow_fb_access); /** - * drm_gem_simple_kms_prepare_shadow_fb - prepares shadow framebuffers + * drm_gem_simple_kms_begin_shadow_fb_access - prepares shadow framebuffers for CPU access * @pipe: the simple display pipe * @plane_state: the plane state of type struct drm_shadow_plane_state * - * This function implements struct drm_simple_display_funcs.prepare_fb. It - * maps all buffer objects of the plane's framebuffer into kernel address - * space and stores them in struct drm_shadow_plane_state.map. The - * framebuffer will be synchronized as part of the atomic commit. + * This function implements struct drm_simple_display_funcs.begin_fb_access. * - * See drm_gem_simple_kms_cleanup_shadow_fb() for cleanup. + * See drm_gem_begin_shadow_fb_access() for details and + * drm_gem_simple_kms_cleanup_shadow_fb() for cleanup. * * Returns: * 0 on success, or a negative errno code otherwise. */ -int drm_gem_simple_kms_prepare_shadow_fb(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *plane_state) +int drm_gem_simple_kms_begin_shadow_fb_access(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *plane_state) { - return drm_gem_prepare_shadow_fb(&pipe->plane, plane_state); + return drm_gem_begin_shadow_fb_access(&pipe->plane, plane_state); } -EXPORT_SYMBOL(drm_gem_simple_kms_prepare_shadow_fb); +EXPORT_SYMBOL(drm_gem_simple_kms_begin_shadow_fb_access); /** - * drm_gem_simple_kms_cleanup_shadow_fb - releases shadow framebuffers + * drm_gem_simple_kms_end_shadow_fb_access - releases shadow framebuffers from CPU access * @pipe: the simple display pipe * @plane_state: the plane state of type struct drm_shadow_plane_state * - * This function implements struct drm_simple_display_funcs.cleanup_fb. - * This function unmaps all buffer objects of the plane's framebuffer. + * This function implements struct drm_simple_display_funcs.end_fb_access. + * It undoes all effects of drm_gem_simple_kms_begin_shadow_fb_access() in + * reverse order. * - * See drm_gem_simple_kms_prepare_shadow_fb(). + * See drm_gem_simple_kms_begin_shadow_fb_access(). */ -void drm_gem_simple_kms_cleanup_shadow_fb(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *plane_state) +void drm_gem_simple_kms_end_shadow_fb_access(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *plane_state) { - drm_gem_cleanup_shadow_fb(&pipe->plane, plane_state); + drm_gem_end_shadow_fb_access(&pipe->plane, plane_state); } -EXPORT_SYMBOL(drm_gem_simple_kms_cleanup_shadow_fb); +EXPORT_SYMBOL(drm_gem_simple_kms_end_shadow_fb_access); /** * drm_gem_simple_kms_reset_shadow_plane - resets a shadow-buffered plane diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index e35e224e6303..e93533b86037 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -9,7 +9,6 @@ #include <linux/module.h> #include <drm/drm_damage_helper.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem.h> diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 35138f8a375c..b602cd72a120 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -571,12 +571,20 @@ static void drm_gem_shmem_vm_open(struct vm_area_struct *vma) { struct drm_gem_object *obj = vma->vm_private_data; struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - int ret; WARN_ON(shmem->base.import_attach); - ret = drm_gem_shmem_get_pages(shmem); - WARN_ON_ONCE(ret != 0); + mutex_lock(&shmem->pages_lock); + + /* + * We should have already pinned the pages when the buffer was first + * mmap'd, vm_open() just grabs an additional reference for the new + * mm the vma is getting copied into (ie. on fork()). + */ + if (!WARN_ON_ONCE(!shmem->pages_use_count)) + shmem->pages_use_count++; + + mutex_unlock(&shmem->pages_lock); drm_gem_vm_open(vma); } @@ -622,10 +630,8 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct } ret = drm_gem_shmem_get_pages(shmem); - if (ret) { - drm_gem_vm_close(vma); + if (ret) return ret; - } vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 125160b534be..b6c7e3803bb3 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -433,25 +433,19 @@ int drm_gem_vram_vmap(struct drm_gem_vram_object *gbo, struct iosys_map *map) { int ret; - ret = ttm_bo_reserve(&gbo->bo, true, false, NULL); - if (ret) - return ret; + dma_resv_assert_held(gbo->bo.base.resv); ret = drm_gem_vram_pin_locked(gbo, 0); if (ret) - goto err_ttm_bo_unreserve; + return ret; ret = drm_gem_vram_kmap_locked(gbo, map); if (ret) goto err_drm_gem_vram_unpin_locked; - ttm_bo_unreserve(&gbo->bo); - return 0; err_drm_gem_vram_unpin_locked: drm_gem_vram_unpin_locked(gbo); -err_ttm_bo_unreserve: - ttm_bo_unreserve(&gbo->bo); return ret; } EXPORT_SYMBOL(drm_gem_vram_vmap); @@ -467,16 +461,10 @@ EXPORT_SYMBOL(drm_gem_vram_vmap); void drm_gem_vram_vunmap(struct drm_gem_vram_object *gbo, struct iosys_map *map) { - int ret; - - ret = ttm_bo_reserve(&gbo->bo, false, false, NULL); - if (WARN_ONCE(ret, "ttm_bo_reserve_failed(): ret=%d\n", ret)) - return; + dma_resv_assert_held(gbo->bo.base.resv); drm_gem_vram_kunmap_locked(gbo, map); drm_gem_vram_unpin_locked(gbo); - - ttm_bo_unreserve(&gbo->bo); } EXPORT_SYMBOL(drm_gem_vram_vunmap); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 7bb98e6a446d..5ea5e260118c 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -104,7 +104,8 @@ static inline void drm_vblank_flush_worker(struct drm_vblank_crtc *vblank) static inline void drm_vblank_destroy_worker(struct drm_vblank_crtc *vblank) { - kthread_destroy_worker(vblank->worker); + if (vblank->worker) + kthread_destroy_worker(vblank->worker); } int drm_vblank_worker_init(struct drm_vblank_crtc *vblank); diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 5d4ac79381c4..3c8034a8c27b 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1750,11 +1750,78 @@ static int drm_mode_parse_cmdline_options(const char *str, return 0; } -static const char * const drm_named_modes_whitelist[] = { - "NTSC", - "PAL", +struct drm_named_mode { + const char *name; + unsigned int pixel_clock_khz; + unsigned int xres; + unsigned int yres; + unsigned int flags; +}; + +#define NAMED_MODE(_name, _pclk, _x, _y, _flags) \ + { \ + .name = _name, \ + .pixel_clock_khz = _pclk, \ + .xres = _x, \ + .yres = _y, \ + .flags = _flags, \ + } + +static const struct drm_named_mode drm_named_modes[] = { + NAMED_MODE("NTSC", 13500, 720, 480, DRM_MODE_FLAG_INTERLACE), + NAMED_MODE("PAL", 13500, 720, 576, DRM_MODE_FLAG_INTERLACE), }; +static int drm_mode_parse_cmdline_named_mode(const char *name, + unsigned int name_end, + struct drm_cmdline_mode *cmdline_mode) +{ + unsigned int i; + + if (!name_end) + return 0; + + /* If the name starts with a digit, it's not a named mode */ + if (isdigit(name[0])) + return 0; + + /* + * If there's an equal sign in the name, the command-line + * contains only an option and no mode. + */ + if (strnchr(name, name_end, '=')) + return 0; + + /* The connection status extras can be set without a mode. */ + if (name_end == 1 && + (name[0] == 'd' || name[0] == 'D' || name[0] == 'e')) + return 0; + + /* + * We're sure we're a named mode at this point, iterate over the + * list of modes we're aware of. + */ + for (i = 0; i < ARRAY_SIZE(drm_named_modes); i++) { + const struct drm_named_mode *mode = &drm_named_modes[i]; + int ret; + + ret = str_has_prefix(name, mode->name); + if (ret != name_end) + continue; + + strcpy(cmdline_mode->name, mode->name); + cmdline_mode->pixel_clock = mode->pixel_clock_khz; + cmdline_mode->xres = mode->xres; + cmdline_mode->yres = mode->yres; + cmdline_mode->interlace = !!(mode->flags & DRM_MODE_FLAG_INTERLACE); + cmdline_mode->specified = true; + + return 1; + } + + return -EINVAL; +} + /** * drm_mode_parse_command_line_for_connector - parse command line modeline for connector * @mode_option: optional per connector mode option @@ -1791,7 +1858,7 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option, const char *bpp_ptr = NULL, *refresh_ptr = NULL, *extra_ptr = NULL; const char *options_ptr = NULL; char *bpp_end_ptr = NULL, *refresh_end_ptr = NULL; - int i, len, ret; + int len, ret; memset(mode, 0, sizeof(*mode)); mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_UNKNOWN; @@ -1832,18 +1899,19 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option, parse_extras = true; } - /* First check for a named mode */ - for (i = 0; i < ARRAY_SIZE(drm_named_modes_whitelist); i++) { - ret = str_has_prefix(name, drm_named_modes_whitelist[i]); - if (ret == mode_end) { - if (refresh_ptr) - return false; /* named + refresh is invalid */ + if (!mode_end) + return false; + + ret = drm_mode_parse_cmdline_named_mode(name, mode_end, mode); + if (ret < 0) + return false; - strcpy(mode->name, drm_named_modes_whitelist[i]); - mode->specified = true; - break; - } - } + /* + * Having a mode that starts by a letter (and thus is named) and + * an at-sign (used to specify a refresh rate) is disallowed. + */ + if (ret && refresh_ptr) + return false; /* No named mode? Check for a normal mode argument, e.g. 1024x768 */ if (!mode->specified && isdigit(name[0])) { diff --git a/drivers/gpu/drm/drm_nomodeset.c b/drivers/gpu/drm/drm_nomodeset.c deleted file mode 100644 index f3978d5bd3a1..000000000000 --- a/drivers/gpu/drm/drm_nomodeset.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <linux/module.h> -#include <linux/types.h> - -static bool drm_nomodeset; - -bool drm_firmware_drivers_only(void) -{ - return drm_nomodeset; -} -EXPORT_SYMBOL(drm_firmware_drivers_only); - -static int __init disable_modeset(char *str) -{ - drm_nomodeset = true; - - pr_warn("Booted with the nomodeset parameter. Only the system framebuffer will be available\n"); - - return 1; -} - -/* Disable kernel modesetting */ -__setup("nomodeset", disable_modeset); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 8a0c0e0bb5bd..52d8800a8ab8 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -134,6 +134,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Acer Switch V 10 (SW5-017) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SW5-017"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Anbernic Win600 */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Anbernic"), @@ -319,6 +325,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Nanote UMPC-01 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "RWC CO.,LTD"), + DMI_MATCH(DMI_PRODUCT_NAME, "UMPC-01"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* OneGX1 Pro */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SYSTEM_MANUFACTURER"), diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 20e109a802ae..f924b8b4ab6b 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -781,6 +781,8 @@ int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma) struct drm_gem_object *obj = dma_buf->priv; struct drm_device *dev = obj->dev; + dma_resv_assert_held(dma_buf->resv); + if (!dev->driver->gem_prime_mmap) return -ENOSYS; diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 2fc21df709bc..bcd9611dabfd 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -36,7 +36,6 @@ #include <drm/drm_client.h> #include <drm/drm_crtc.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_print.h> diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c index 31233c6ae3c4..3ef420ec4534 100644 --- a/drivers/gpu/drm/drm_simple_kms_helper.c +++ b/drivers/gpu/drm/drm_simple_kms_helper.c @@ -285,6 +285,30 @@ static void drm_simple_kms_plane_cleanup_fb(struct drm_plane *plane, pipe->funcs->cleanup_fb(pipe, state); } +static int drm_simple_kms_plane_begin_fb_access(struct drm_plane *plane, + struct drm_plane_state *new_plane_state) +{ + struct drm_simple_display_pipe *pipe; + + pipe = container_of(plane, struct drm_simple_display_pipe, plane); + if (!pipe->funcs || !pipe->funcs->begin_fb_access) + return 0; + + return pipe->funcs->begin_fb_access(pipe, new_plane_state); +} + +static void drm_simple_kms_plane_end_fb_access(struct drm_plane *plane, + struct drm_plane_state *new_plane_state) +{ + struct drm_simple_display_pipe *pipe; + + pipe = container_of(plane, struct drm_simple_display_pipe, plane); + if (!pipe->funcs || !pipe->funcs->end_fb_access) + return; + + pipe->funcs->end_fb_access(pipe, new_plane_state); +} + static bool drm_simple_kms_format_mod_supported(struct drm_plane *plane, uint32_t format, uint64_t modifier) @@ -295,6 +319,8 @@ static bool drm_simple_kms_format_mod_supported(struct drm_plane *plane, static const struct drm_plane_helper_funcs drm_simple_kms_plane_helper_funcs = { .prepare_fb = drm_simple_kms_plane_prepare_fb, .cleanup_fb = drm_simple_kms_plane_cleanup_fb, + .begin_fb_access = drm_simple_kms_plane_begin_fb_access, + .end_fb_access = drm_simple_kms_plane_end_fb_access, .atomic_check = drm_simple_kms_plane_atomic_check, .atomic_update = drm_simple_kms_plane_atomic_update, }; diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index 430e00b16eec..183130355997 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -19,6 +19,7 @@ #include <linux/kdev_t.h> #include <linux/slab.h> +#include <drm/drm_accel.h> #include <drm/drm_connector.h> #include <drm/drm_device.h> #include <drm/drm_file.h> @@ -90,7 +91,7 @@ static void drm_sysfs_acpi_register(void) { } static void drm_sysfs_acpi_unregister(void) { } #endif -static char *drm_devnode(struct device *dev, umode_t *mode) +static char *drm_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "dri/%s", dev_name(dev)); } @@ -471,19 +472,26 @@ struct device *drm_sysfs_minor_alloc(struct drm_minor *minor) struct device *kdev; int r; - if (minor->type == DRM_MINOR_RENDER) - minor_str = "renderD%d"; - else - minor_str = "card%d"; - kdev = kzalloc(sizeof(*kdev), GFP_KERNEL); if (!kdev) return ERR_PTR(-ENOMEM); device_initialize(kdev); - kdev->devt = MKDEV(DRM_MAJOR, minor->index); - kdev->class = drm_class; - kdev->type = &drm_sysfs_device_minor; + + if (minor->type == DRM_MINOR_ACCEL) { + minor_str = "accel%d"; + accel_set_device_instance_params(kdev, minor->index); + } else { + if (minor->type == DRM_MINOR_RENDER) + minor_str = "renderD%d"; + else + minor_str = "card%d"; + + kdev->devt = MKDEV(DRM_MAJOR, minor->index); + kdev->class = drm_class; + kdev->type = &drm_sysfs_device_minor; + } + kdev->parent = minor->dev->dev; kdev->release = drm_sysfs_release; dev_set_drvdata(kdev, minor); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h index f32f4771dada..2bb4c25565dc 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h @@ -6,13 +6,14 @@ #ifndef __ETNAVIV_DRV_H__ #define __ETNAVIV_DRV_H__ +#include <linux/io.h> #include <linux/list.h> #include <linux/mm_types.h> #include <linux/sizes.h> #include <linux/time64.h> #include <linux/types.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_drv.h> #include <drm/drm_gem.h> #include <drm/etnaviv_drm.h> #include <drm/gpu_scheduler.h> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index f418e0b75772..44b5f3c35aab 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -83,10 +83,15 @@ static void etnaviv_core_dump_registers(struct core_dump_iterator *iter, { struct etnaviv_dump_registers *reg = iter->data; unsigned int i; + u32 read_addr; for (i = 0; i < ARRAY_SIZE(etnaviv_dump_registers); i++, reg++) { + read_addr = etnaviv_dump_registers[i]; + if (read_addr >= VIVS_PM_POWER_CONTROLS && + read_addr <= VIVS_PM_PULSE_EATER) + read_addr = gpu_fix_power_address(gpu, read_addr); reg->reg = cpu_to_le32(etnaviv_dump_registers[i]); - reg->value = cpu_to_le32(gpu_read(gpu, etnaviv_dump_registers[i])); + reg->value = cpu_to_le32(gpu_read(gpu, read_addr)); } etnaviv_core_dump_header(iter, ETDUMP_BUF_REG, reg); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index cc386f8a7116..c5ae5492e1af 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -130,7 +130,7 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj, { pgprot_t vm_page_prot; - vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; vm_page_prot = vm_get_page_prot(vma->vm_flags); @@ -165,7 +165,8 @@ static vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct drm_gem_object *obj = vma->vm_private_data; struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); - struct page **pages, *page; + struct page **pages; + unsigned long pfn; pgoff_t pgoff; int err; @@ -189,12 +190,12 @@ static vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf) /* We don't use vmf->pgoff since that has the fake offset: */ pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT; - page = pages[pgoff]; + pfn = page_to_pfn(pages[pgoff]); VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address, - page_to_pfn(page), page_to_pfn(page) << PAGE_SHIFT); + pfn, pfn << PAGE_SHIFT); - return vmf_insert_page(vma, vmf->address, page); + return vmf_insert_pfn(vma, vmf->address, pfn); } int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset) @@ -258,7 +259,12 @@ struct etnaviv_vram_mapping *etnaviv_gem_mapping_get( if (mapping->use == 0) { mutex_lock(&mmu_context->lock); if (mapping->context == mmu_context) - mapping->use += 1; + if (va && mapping->iova != va) { + etnaviv_iommu_reap_mapping(mapping); + mapping = NULL; + } else { + mapping->use += 1; + } else mapping = NULL; mutex_unlock(&mmu_context->lock); @@ -504,7 +510,6 @@ void etnaviv_gem_free_object(struct drm_gem_object *obj) kfree(mapping); } - drm_gem_free_mmap_offset(obj); etnaviv_obj->ops->release(etnaviv_obj); drm_gem_object_release(obj); @@ -638,6 +643,7 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) struct page **pvec = NULL; struct etnaviv_gem_userptr *userptr = &etnaviv_obj->userptr; int ret, pinned = 0, npages = etnaviv_obj->base.size >> PAGE_SHIFT; + unsigned int gup_flags = FOLL_LONGTERM; might_lock_read(¤t->mm->mmap_lock); @@ -648,14 +654,15 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) if (!pvec) return -ENOMEM; + if (!userptr->ro) + gup_flags |= FOLL_WRITE; + do { unsigned num_pages = npages - pinned; uint64_t ptr = userptr->ptr + pinned * PAGE_SIZE; struct page **pages = pvec + pinned; - ret = pin_user_pages_fast(ptr, num_pages, - FOLL_WRITE | FOLL_FORCE | FOLL_LONGTERM, - pages); + ret = pin_user_pages_fast(ptr, num_pages, gup_flags, pages); if (ret < 0) { unpin_user_pages(pvec, pinned); kvfree(pvec); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.h b/drivers/gpu/drm/etnaviv/etnaviv_gem.h index 63688e6e4580..baa81cbf701a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.h @@ -96,6 +96,7 @@ struct etnaviv_gem_submit { int out_fence_id; struct list_head node; /* GPU active submit list */ struct etnaviv_cmdbuf cmdbuf; + struct pid *pid; /* submitting process */ bool runtime_resumed; u32 exec_state; u32 flags; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 1ac916b24891..1491159d0d20 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -399,6 +399,9 @@ static void submit_cleanup(struct kref *kref) mutex_unlock(&submit->gpu->fence_lock); dma_fence_put(submit->out_fence); } + + put_pid(submit->pid); + kfree(submit->pmrs); kfree(submit); } @@ -422,6 +425,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, struct sync_file *sync_file = NULL; struct ww_acquire_ctx ticket; int out_fence_fd = -1; + struct pid *pid = get_pid(task_pid(current)); void *stream; int ret; @@ -519,6 +523,8 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, goto err_submit_ww_acquire; } + submit->pid = pid; + ret = etnaviv_cmdbuf_init(priv->cmdbuf_suballoc, &submit->cmdbuf, ALIGN(args->stream_size, 8) + 8); if (ret) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 37018bc55810..51320eeebfcf 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -416,6 +416,12 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) if (gpu->identity.model == chipModel_GC700) gpu->identity.features &= ~chipFeatures_FAST_CLEAR; + /* These models/revisions don't have the 2D pipe bit */ + if ((gpu->identity.model == chipModel_GC500 && + gpu->identity.revision <= 2) || + gpu->identity.model == chipModel_GC300) + gpu->identity.features |= chipFeatures_PIPE_2D; + if ((gpu->identity.model == chipModel_GC500 && gpu->identity.revision < 2) || (gpu->identity.model == chipModel_GC300 && @@ -449,8 +455,9 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_5); } - /* GC600 idle register reports zero bits where modules aren't present */ - if (gpu->identity.model == chipModel_GC600) + /* GC600/300 idle register reports zero bits where modules aren't present */ + if (gpu->identity.model == chipModel_GC600 || + gpu->identity.model == chipModel_GC300) gpu->idle_mask = VIVS_HI_IDLE_STATE_TX | VIVS_HI_IDLE_STATE_RA | VIVS_HI_IDLE_STATE_SE | @@ -583,7 +590,7 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) u32 pmc, ppc; /* enable clock gating */ - ppc = gpu_read(gpu, VIVS_PM_POWER_CONTROLS); + ppc = gpu_read_power(gpu, VIVS_PM_POWER_CONTROLS); ppc |= VIVS_PM_POWER_CONTROLS_ENABLE_MODULE_CLOCK_GATING; /* Disable stall module clock gating for 4.3.0.1 and 4.3.0.2 revs */ @@ -591,9 +598,9 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) gpu->identity.revision == 0x4302) ppc |= VIVS_PM_POWER_CONTROLS_DISABLE_STALL_MODULE_CLOCK_GATING; - gpu_write(gpu, VIVS_PM_POWER_CONTROLS, ppc); + gpu_write_power(gpu, VIVS_PM_POWER_CONTROLS, ppc); - pmc = gpu_read(gpu, VIVS_PM_MODULE_CONTROLS); + pmc = gpu_read_power(gpu, VIVS_PM_MODULE_CONTROLS); /* Disable PA clock gating for GC400+ without bugfix except for GC420 */ if (gpu->identity.model >= chipModel_GC400 && @@ -616,19 +623,20 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) /* Disable TX clock gating on affected core revisions. */ if (etnaviv_is_model_rev(gpu, GC4000, 0x5222) || - etnaviv_is_model_rev(gpu, GC2000, 0x5108)) + etnaviv_is_model_rev(gpu, GC2000, 0x5108) || + etnaviv_is_model_rev(gpu, GC2000, 0x6202) || + etnaviv_is_model_rev(gpu, GC2000, 0x6203)) pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX; - /* Disable SE, RA and TX clock gating on affected core revisions. */ + /* Disable SE and RA clock gating on affected core revisions. */ if (etnaviv_is_model_rev(gpu, GC7000, 0x6202)) pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_SE | - VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA | - VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX; + VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA; pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_HZ; pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_EZ; - gpu_write(gpu, VIVS_PM_MODULE_CONTROLS, pmc); + gpu_write_power(gpu, VIVS_PM_MODULE_CONTROLS, pmc); } void etnaviv_gpu_start_fe(struct etnaviv_gpu *gpu, u32 address, u16 prefetch) @@ -688,11 +696,11 @@ static void etnaviv_gpu_setup_pulse_eater(struct etnaviv_gpu *gpu) (gpu->identity.features & chipFeatures_PIPE_3D)) { /* Performance fix: disable internal DFS */ - pulse_eater = gpu_read(gpu, VIVS_PM_PULSE_EATER); + pulse_eater = gpu_read_power(gpu, VIVS_PM_PULSE_EATER); pulse_eater |= BIT(18); } - gpu_write(gpu, VIVS_PM_PULSE_EATER, pulse_eater); + gpu_write_power(gpu, VIVS_PM_PULSE_EATER, pulse_eater); } static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu) @@ -1045,12 +1053,28 @@ pm_put: } #endif -void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu) +void etnaviv_gpu_recover_hang(struct etnaviv_gem_submit *submit) { + struct etnaviv_gpu *gpu = submit->gpu; + char *comm = NULL, *cmd = NULL; + struct task_struct *task; unsigned int i; dev_err(gpu->dev, "recover hung GPU!\n"); + task = get_pid_task(submit->pid, PIDTYPE_PID); + if (task) { + comm = kstrdup(task->comm, GFP_KERNEL); + cmd = kstrdup_quotable_cmdline(task, GFP_KERNEL); + put_task_struct(task); + } + + if (comm && cmd) + dev_err(gpu->dev, "offending task: %s (%s)\n", comm, cmd); + + kfree(cmd); + kfree(comm); + if (pm_runtime_get_sync(gpu->dev) < 0) goto pm_put; @@ -1294,9 +1318,9 @@ static void sync_point_perfmon_sample_pre(struct etnaviv_gpu *gpu, u32 val; /* disable clock gating */ - val = gpu_read(gpu, VIVS_PM_POWER_CONTROLS); + val = gpu_read_power(gpu, VIVS_PM_POWER_CONTROLS); val &= ~VIVS_PM_POWER_CONTROLS_ENABLE_MODULE_CLOCK_GATING; - gpu_write(gpu, VIVS_PM_POWER_CONTROLS, val); + gpu_write_power(gpu, VIVS_PM_POWER_CONTROLS, val); /* enable debug register */ val = gpu_read(gpu, VIVS_HI_CLOCK_CONTROL); @@ -1327,9 +1351,9 @@ static void sync_point_perfmon_sample_post(struct etnaviv_gpu *gpu, gpu_write(gpu, VIVS_HI_CLOCK_CONTROL, val); /* enable clock gating */ - val = gpu_read(gpu, VIVS_PM_POWER_CONTROLS); + val = gpu_read_power(gpu, VIVS_PM_POWER_CONTROLS); val |= VIVS_PM_POWER_CONTROLS_ENABLE_MODULE_CLOCK_GATING; - gpu_write(gpu, VIVS_PM_POWER_CONTROLS, val); + gpu_write_power(gpu, VIVS_PM_POWER_CONTROLS, val); } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index 85eddd492774..f1204b070fb8 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -10,6 +10,7 @@ #include "etnaviv_gem.h" #include "etnaviv_mmu.h" #include "etnaviv_drv.h" +#include "common.xml.h" struct etnaviv_gem_submit; struct etnaviv_vram_mapping; @@ -159,6 +160,26 @@ static inline u32 gpu_read(struct etnaviv_gpu *gpu, u32 reg) return readl(gpu->mmio + reg); } +static inline u32 gpu_fix_power_address(struct etnaviv_gpu *gpu, u32 reg) +{ + /* Power registers in GC300 < 2.0 are offset by 0x100 */ + if (gpu->identity.model == chipModel_GC300 && + gpu->identity.revision < 0x2000) + reg += 0x100; + + return reg; +} + +static inline void gpu_write_power(struct etnaviv_gpu *gpu, u32 reg, u32 data) +{ + writel(data, gpu->mmio + gpu_fix_power_address(gpu, reg)); +} + +static inline u32 gpu_read_power(struct etnaviv_gpu *gpu, u32 reg) +{ + return readl(gpu->mmio + gpu_fix_power_address(gpu, reg)); +} + int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value); int etnaviv_gpu_init(struct etnaviv_gpu *gpu); @@ -168,7 +189,7 @@ bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu); int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m); #endif -void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu); +void etnaviv_gpu_recover_hang(struct etnaviv_gem_submit *submit); void etnaviv_gpu_retire(struct etnaviv_gpu *gpu); int etnaviv_gpu_wait_fence_interruptible(struct etnaviv_gpu *gpu, u32 fence, struct drm_etnaviv_timespec *timeout); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index f2fc645c7956..57f334e24189 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -70,6 +70,37 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { }, { .model = 0x7000, + .revision = 0x6203, + .product_id = 0x70003, + .customer_id = 0x4, + .eco_id = 0, + .stream_count = 16, + .register_max = 64, + .thread_count = 512, + .shader_core_count = 2, + .vertex_cache_size = 16, + .vertex_output_buffer_size = 1024, + .pixel_pipes = 1, + .instruction_count = 512, + .num_constants = 320, + .buffer_size = 0, + .varyings_count = 16, + .features = 0xe0287c8d, + .minor_features0 = 0xc1589eff, + .minor_features1 = 0xfefbfad9, + .minor_features2 = 0xeb9d4fbf, + .minor_features3 = 0xedfffced, + .minor_features4 = 0xdb0dafc7, + .minor_features5 = 0x3b5ac333, + .minor_features6 = 0xfcce6000, + .minor_features7 = 0xfffbfa6f, + .minor_features8 = 0x00e10ef3, + .minor_features9 = 0x00c8003c, + .minor_features10 = 0x00004040, + .minor_features11 = 0x00000024, + }, + { + .model = 0x7000, .revision = 0x6204, .product_id = ~0U, .customer_id = ~0U, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index dc1aa738c4f1..67bdce5326c6 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -80,10 +80,10 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, return -EINVAL; for_each_sgtable_dma_sg(sgt, sg, i) { - u32 pa = sg_dma_address(sg) - sg->offset; + phys_addr_t pa = sg_dma_address(sg) - sg->offset; size_t bytes = sg_dma_len(sg) + sg->offset; - VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes); + VERB("map[%d]: %08x %pap(%zx)", i, iova, &pa, bytes); ret = etnaviv_context_map(context, da, pa, bytes, prot); if (ret) @@ -135,6 +135,19 @@ static void etnaviv_iommu_remove_mapping(struct etnaviv_iommu_context *context, drm_mm_remove_node(&mapping->vram_node); } +void etnaviv_iommu_reap_mapping(struct etnaviv_vram_mapping *mapping) +{ + struct etnaviv_iommu_context *context = mapping->context; + + lockdep_assert_held(&context->lock); + WARN_ON(mapping->use); + + etnaviv_iommu_remove_mapping(context, mapping); + etnaviv_iommu_context_put(mapping->context); + mapping->context = NULL; + list_del_init(&mapping->mmu_node); +} + static int etnaviv_iommu_find_iova(struct etnaviv_iommu_context *context, struct drm_mm_node *node, size_t size) { @@ -202,10 +215,7 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu_context *context, * this mapping. */ list_for_each_entry_safe(m, n, &list, scan_node) { - etnaviv_iommu_remove_mapping(context, m); - etnaviv_iommu_context_put(m->context); - m->context = NULL; - list_del_init(&m->mmu_node); + etnaviv_iommu_reap_mapping(m); list_del_init(&m->scan_node); } @@ -257,10 +267,7 @@ static int etnaviv_iommu_insert_exact(struct etnaviv_iommu_context *context, } list_for_each_entry_safe(m, n, &scan_list, scan_node) { - etnaviv_iommu_remove_mapping(context, m); - etnaviv_iommu_context_put(m->context); - m->context = NULL; - list_del_init(&m->mmu_node); + etnaviv_iommu_reap_mapping(m); list_del_init(&m->scan_node); } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h index e4a0b7d09c2e..c01a147f0dfd 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h @@ -91,6 +91,7 @@ int etnaviv_iommu_map_gem(struct etnaviv_iommu_context *context, struct etnaviv_vram_mapping *mapping, u64 va); void etnaviv_iommu_unmap_gem(struct etnaviv_iommu_context *context, struct etnaviv_vram_mapping *mapping); +void etnaviv_iommu_reap_mapping(struct etnaviv_vram_mapping *mapping); int etnaviv_iommu_get_suballoc_va(struct etnaviv_iommu_context *ctx, struct etnaviv_vram_mapping *mapping, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 72e2553fbc98..d29f467eee13 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -67,7 +67,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job /* get the GPU back into the init state */ etnaviv_core_dump(submit); - etnaviv_gpu_recover_hang(gpu); + etnaviv_gpu_recover_hang(submit); drm_sched_resubmit_jobs(&gpu->sched); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 767afd2bfa82..55c92372fca0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -49,6 +49,8 @@ static const struct fb_ops exynos_drm_fb_ops = { .owner = THIS_MODULE, DRM_FB_HELPER_DEFAULT_OPS, .fb_mmap = exynos_drm_fb_mmap, + .fb_read = drm_fb_helper_cfb_read, + .fb_write = drm_fb_helper_cfb_write, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -63,7 +65,7 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper, unsigned int size = fb->width * fb->height * fb->format->cpp[0]; unsigned long offset; - fbi = drm_fb_helper_alloc_fbi(helper); + fbi = drm_fb_helper_alloc_info(helper); if (IS_ERR(fbi)) { DRM_DEV_ERROR(to_dma_dev(helper->dev), "failed to allocate fb info.\n"); @@ -201,7 +203,7 @@ static void exynos_drm_fbdev_destroy(struct drm_device *dev, drm_framebuffer_remove(fb); } - drm_fb_helper_unregister_fbi(fb_helper); + drm_fb_helper_unregister_info(fb_helper); drm_fb_helper_fini(fb_helper); } diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 471fd6c8135f..e19c2ceb3759 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -477,7 +477,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d, } ret = pin_user_pages_fast(start, npages, - FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM, + FOLL_WRITE | FOLL_LONGTERM, g2d_userptr->pages); if (ret != npages) { DRM_DEV_ERROR(g2d->dev, diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c index b4acc3422ba4..8579c7629f5e 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c @@ -20,7 +20,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_modeset_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c index 4d4a715b429d..2c2b92324a2e 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c @@ -60,8 +60,9 @@ static int fsl_dcu_drm_connector_get_modes(struct drm_connector *connector) return drm_panel_get_modes(fsl_connector->panel, connector); } -static int fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { if (mode->hdisplay & 0xf) return MODE_ERROR; diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index 5f502a0048ab..8d5a37b8f110 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -147,6 +147,8 @@ static const struct fb_ops psbfb_unaccel_ops = { .owner = THIS_MODULE, DRM_FB_HELPER_DEFAULT_OPS, .fb_setcolreg = psbfb_setcolreg, + .fb_read = drm_fb_helper_cfb_read, + .fb_write = drm_fb_helper_cfb_write, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -268,7 +270,7 @@ static int psbfb_create(struct drm_fb_helper *fb_helper, memset(dev_priv->vram_addr + backing->offset, 0, size); - info = drm_fb_helper_alloc_fbi(fb_helper); + info = drm_fb_helper_alloc_info(fb_helper); if (IS_ERR(info)) { ret = PTR_ERR(info); goto err_drm_gem_object_put; @@ -383,7 +385,7 @@ static int psb_fbdev_destroy(struct drm_device *dev, { struct drm_framebuffer *fb = fb_helper->fb; - drm_fb_helper_unregister_fbi(fb_helper); + drm_fb_helper_unregister_info(fb_helper); drm_fb_helper_fini(fb_helper); drm_framebuffer_unregister_private(fb); diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index 8d1630b8edac..d57dab104358 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -18,7 +18,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_debugfs.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_framebuffer_helper.h> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index 5a2e1cac06b2..22053c613644 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -17,6 +17,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_gem_vram_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 4a0cd22c10e2..f957552c6c50 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -19,7 +19,6 @@ #include <linux/i2c.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_framebuffer.h> struct hibmc_connector { diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index c228091fb0e6..8c6d2ea2a472 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -11,6 +11,8 @@ * Jianhua Li <lijianhua@huawei.com> */ +#include <linux/io.h> + #include <drm/drm_atomic_helper.h> #include <drm/drm_probe_helper.h> #include <drm/drm_print.h> diff --git a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c index a0d5aa727d58..d9978b79828c 100644 --- a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c +++ b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c @@ -658,7 +658,7 @@ static enum drm_mode_status dsi_encoder_mode_valid(struct drm_encoder *encoder, * reset adj_mode to the mode value each time, * so we don't adjust the mode twice */ - drm_mode_copy(&adj_mode, mode); + drm_mode_init(&adj_mode, mode); crtc_funcs = crtc->helper_private; if (crtc_funcs && crtc_funcs->mode_fixup) diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c index 73ee7f25f734..9c5d49bf40c9 100644 --- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c @@ -19,7 +19,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index ca127ff797f7..427c20ba3404 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -11,7 +11,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_simple_kms_helper.h> diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c index 28e732f94bf2..6c6b57298797 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c @@ -8,7 +8,6 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_drv.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_format_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index d444e7fffb54..a14d2896aebb 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -1174,6 +1174,8 @@ static int tda998x_audio_codec_init(struct tda998x_priv *priv, struct hdmi_codec_pdata codec_data = { .ops = &audio_codec_ops, .max_i2s_channels = 2, + .no_i2s_capture = 1, + .no_spdif_capture = 1, }; if (priv->audio_port_enable[AUDIO_ROUTE_I2S]) diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 0ed5985c03b5..7046e435a155 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -130,9 +130,11 @@ gt-y += \ gt/intel_sseu.o \ gt/intel_sseu_debugfs.o \ gt/intel_timeline.o \ + gt/intel_wopcm.o \ gt/intel_workarounds.o \ gt/shmem_utils.o \ gt/sysfs_engines.o + # x86 intel-gtt module support gt-$(CONFIG_X86) += gt/intel_ggtt_gmch.o # autogenerated null render state @@ -186,8 +188,7 @@ i915-y += \ i915_trace_points.o \ i915_ttm_buddy_manager.o \ i915_vma.o \ - i915_vma_resource.o \ - intel_wopcm.o + i915_vma_resource.o # general-purpose microcontroller (GuC) support i915-y += gt/uc/intel_uc.o \ diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index ab385d18ddcc..5575d7abdc09 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -124,6 +124,8 @@ static const struct fb_ops intelfb_ops = { .owner = THIS_MODULE, DRM_FB_HELPER_DEFAULT_OPS, .fb_set_par = intel_fbdev_set_par, + .fb_read = drm_fb_helper_cfb_read, + .fb_write = drm_fb_helper_cfb_write, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -254,7 +256,7 @@ static int intelfb_create(struct drm_fb_helper *helper, goto out_unlock; } - info = drm_fb_helper_alloc_fbi(helper); + info = drm_fb_helper_alloc_info(helper); if (IS_ERR(info)) { drm_err(&dev_priv->drm, "Failed to allocate fb_info (%pe)\n", info); ret = PTR_ERR(info); @@ -584,7 +586,7 @@ void intel_fbdev_unregister(struct drm_i915_private *dev_priv) if (!current_is_async()) intel_fbdev_sync(ifbdev); - drm_fb_helper_unregister_fbi(&ifbdev->helper); + drm_fb_helper_unregister_info(&ifbdev->helper); } void intel_fbdev_fini(struct drm_i915_private *dev_priv) @@ -627,7 +629,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous if (!ifbdev || !ifbdev->vma) goto set_suspend; - info = ifbdev->helper.fbdev; + info = ifbdev->helper.info; if (synchronous) { /* Flush any pending work to turn the console on, and then diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 01402f3c58f6..7f2831efc798 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -546,7 +546,7 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data) } if (intel_engine_uses_guc(master)) { - DRM_DEBUG("bonding extension not supported with GuC submission"); + drm_dbg(&i915->drm, "bonding extension not supported with GuC submission"); return -ENODEV; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index ec6f7ae47783..fd556a076d05 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -97,6 +97,8 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct * struct drm_i915_private *i915 = to_i915(obj->base.dev); int ret; + dma_resv_assert_held(dma_buf->resv); + if (obj->base.size < vma->vm_end - vma->vm_start) return -EINVAL; @@ -238,7 +240,6 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = to_i915(obj->base.dev); struct sg_table *sgt; - unsigned int sg_page_sizes; assert_object_held(obj); @@ -262,8 +263,7 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) (!HAS_LLC(i915) && !IS_DG1(i915))) wbinvd_on_all_cpus(); - sg_page_sizes = i915_sg_dma_sizes(sgt->sgl); - __i915_gem_object_set_pages(obj, sgt, sg_page_sizes); + __i915_gem_object_set_pages(obj, sgt); return 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index ffa30d2dd47f..da09767fda07 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -54,13 +54,13 @@ enum { #define DBG_FORCE_RELOC 0 /* choose one of the above! */ }; -/* __EXEC_OBJECT_NO_RESERVE is BIT(31), defined in i915_vma.h */ -#define __EXEC_OBJECT_HAS_PIN BIT(30) -#define __EXEC_OBJECT_HAS_FENCE BIT(29) -#define __EXEC_OBJECT_USERPTR_INIT BIT(28) -#define __EXEC_OBJECT_NEEDS_MAP BIT(27) -#define __EXEC_OBJECT_NEEDS_BIAS BIT(26) -#define __EXEC_OBJECT_INTERNAL_FLAGS (~0u << 26) /* all of the above + */ +/* __EXEC_OBJECT_ flags > BIT(29) defined in i915_vma.h */ +#define __EXEC_OBJECT_HAS_PIN BIT(29) +#define __EXEC_OBJECT_HAS_FENCE BIT(28) +#define __EXEC_OBJECT_USERPTR_INIT BIT(27) +#define __EXEC_OBJECT_NEEDS_MAP BIT(26) +#define __EXEC_OBJECT_NEEDS_BIAS BIT(25) +#define __EXEC_OBJECT_INTERNAL_FLAGS (~0u << 25) /* all of the above + */ #define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE) #define __EXEC_HAS_RELOC BIT(31) @@ -2102,7 +2102,8 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) eb->composite_fence ? eb->composite_fence : &eb->requests[j]->fence, - flags | __EXEC_OBJECT_NO_RESERVE); + flags | __EXEC_OBJECT_NO_RESERVE | + __EXEC_OBJECT_NO_REQUEST_AWAIT); } } @@ -2149,7 +2150,8 @@ err_skip: return err; } -static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) +static int i915_gem_check_execbuffer(struct drm_i915_private *i915, + struct drm_i915_gem_execbuffer2 *exec) { if (exec->flags & __I915_EXEC_ILLEGAL_FLAGS) return -EINVAL; @@ -2162,7 +2164,7 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) } if (exec->DR4 == 0xffffffff) { - DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); + drm_dbg(&i915->drm, "UXA submitting garbage DR4, fixing up\n"); exec->DR4 = 0; } if (exec->DR1 || exec->DR4) @@ -2425,7 +2427,7 @@ gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv, /* Check whether the file_priv has already selected one ring. */ if ((int)file_priv->bsd_engine < 0) file_priv->bsd_engine = - prandom_u32_max(num_vcs_engines(dev_priv)); + get_random_u32_below(num_vcs_engines(dev_priv)); return file_priv->bsd_engine; } @@ -2800,7 +2802,8 @@ add_timeline_fence_array(struct i915_execbuffer *eb, syncobj = drm_syncobj_find(eb->file, user_fence.handle); if (!syncobj) { - DRM_DEBUG("Invalid syncobj handle provided\n"); + drm_dbg(&eb->i915->drm, + "Invalid syncobj handle provided\n"); return -ENOENT; } @@ -2808,7 +2811,8 @@ add_timeline_fence_array(struct i915_execbuffer *eb, if (!fence && user_fence.flags && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) { - DRM_DEBUG("Syncobj handle has no fence\n"); + drm_dbg(&eb->i915->drm, + "Syncobj handle has no fence\n"); drm_syncobj_put(syncobj); return -EINVAL; } @@ -2817,7 +2821,9 @@ add_timeline_fence_array(struct i915_execbuffer *eb, err = dma_fence_chain_find_seqno(&fence, point); if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) { - DRM_DEBUG("Syncobj handle missing requested point %llu\n", point); + drm_dbg(&eb->i915->drm, + "Syncobj handle missing requested point %llu\n", + point); dma_fence_put(fence); drm_syncobj_put(syncobj); return err; @@ -2843,7 +2849,8 @@ add_timeline_fence_array(struct i915_execbuffer *eb, * 0) would break the timeline. */ if (user_fence.flags & I915_EXEC_FENCE_WAIT) { - DRM_DEBUG("Trying to wait & signal the same timeline point.\n"); + drm_dbg(&eb->i915->drm, + "Trying to wait & signal the same timeline point.\n"); dma_fence_put(fence); drm_syncobj_put(syncobj); return -EINVAL; @@ -2914,14 +2921,16 @@ static int add_fence_array(struct i915_execbuffer *eb) syncobj = drm_syncobj_find(eb->file, user_fence.handle); if (!syncobj) { - DRM_DEBUG("Invalid syncobj handle provided\n"); + drm_dbg(&eb->i915->drm, + "Invalid syncobj handle provided\n"); return -ENOENT; } if (user_fence.flags & I915_EXEC_FENCE_WAIT) { fence = drm_syncobj_fence_get(syncobj); if (!fence) { - DRM_DEBUG("Syncobj handle has no fence\n"); + drm_dbg(&eb->i915->drm, + "Syncobj handle has no fence\n"); drm_syncobj_put(syncobj); return -EINVAL; } @@ -3516,7 +3525,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, return -EINVAL; } - err = i915_gem_check_execbuffer(args); + err = i915_gem_check_execbuffer(i915, args); if (err) return err; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index 629acb403a2c..f66bcefc09ec 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -35,7 +35,6 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct sg_table *st; struct scatterlist *sg; - unsigned int sg_page_sizes; unsigned int npages; int max_order = MAX_ORDER; unsigned int max_segment; @@ -64,7 +63,6 @@ create_st: sg = st->sgl; st->nents = 0; - sg_page_sizes = 0; do { int order = min(fls(npages) - 1, max_order); @@ -83,7 +81,6 @@ create_st: } while (1); sg_set_page(sg, page, PAGE_SIZE << order, 0); - sg_page_sizes |= PAGE_SIZE << order; st->nents++; npages -= 1 << order; @@ -105,7 +102,7 @@ create_st: goto err; } - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index e63329bc8065..c29efdef8313 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -330,7 +330,7 @@ retry: if (ret) goto err_rpm; - ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu); + ret = intel_gt_reset_lock_interruptible(ggtt->vm.gt, &srcu); if (ret) goto err_pages; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 733696057761..1a0886b8aaa1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -785,6 +785,9 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj) if (!HAS_FLAT_CCS(to_i915(obj->base.dev))) return false; + if (obj->flags & I915_BO_ALLOC_CCS_AUX) + return true; + for (i = 0; i < obj->mm.n_placements; i++) { /* Compression is not allowed for the objects with smem placement */ if (obj->mm.placements[i]->type == INTEL_MEMORY_SYSTEM) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 6b9ecff42bb5..3db53769864c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -403,8 +403,7 @@ i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, unsigned long n); void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, - struct sg_table *pages, - unsigned int sg_page_sizes); + struct sg_table *pages); int ____i915_gem_object_get_pages(struct drm_i915_gem_object *obj); int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index d0d6772e6f36..ab4c2f90a564 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -327,16 +327,18 @@ struct drm_i915_gem_object { * dealing with userspace objects the CPU fault handler is free to ignore this. */ #define I915_BO_ALLOC_GPU_ONLY BIT(6) +#define I915_BO_ALLOC_CCS_AUX BIT(7) #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \ I915_BO_ALLOC_VOLATILE | \ I915_BO_ALLOC_CPU_CLEAR | \ I915_BO_ALLOC_USER | \ I915_BO_ALLOC_PM_VOLATILE | \ I915_BO_ALLOC_PM_EARLY | \ - I915_BO_ALLOC_GPU_ONLY) -#define I915_BO_READONLY BIT(7) -#define I915_TILING_QUIRK_BIT 8 /* unknown swizzling; do not release! */ -#define I915_BO_PROTECTED BIT(9) + I915_BO_ALLOC_GPU_ONLY | \ + I915_BO_ALLOC_CCS_AUX) +#define I915_BO_READONLY BIT(8) +#define I915_TILING_QUIRK_BIT 9 /* unknown swizzling; do not release! */ +#define I915_BO_PROTECTED BIT(10) /** * @mem_flags - Mutable placement-related flags * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 16f845663ff2..05a27723ebb8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -16,8 +16,7 @@ #include "i915_gem_mman.h" void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, - struct sg_table *pages, - unsigned int sg_page_sizes) + struct sg_table *pages) { struct drm_i915_private *i915 = to_i915(obj->base.dev); unsigned long supported = RUNTIME_INFO(i915)->page_sizes; @@ -45,8 +44,8 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, obj->mm.pages = pages; - GEM_BUG_ON(!sg_page_sizes); - obj->mm.page_sizes.phys = sg_page_sizes; + obj->mm.page_sizes.phys = i915_sg_dma_sizes(pages->sgl); + GEM_BUG_ON(!obj->mm.page_sizes.phys); /* * Calculate the supported page-sizes which fit into the given diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 0d0e46dae559..68453572275b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -79,7 +79,7 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) /* We're no longer struct page backed */ obj->mem_flags &= ~I915_BO_FLAG_STRUCT_PAGE; - __i915_gem_object_set_pages(obj, st, sg->length); + __i915_gem_object_set_pages(obj, st); return 0; @@ -209,11 +209,8 @@ static int i915_gem_object_shmem_to_phys(struct drm_i915_gem_object *obj) return 0; err_xfer: - if (!IS_ERR_OR_NULL(pages)) { - unsigned int sg_page_sizes = i915_sg_dma_sizes(pages->sgl); - - __i915_gem_object_set_pages(obj, pages, sg_page_sizes); - } + if (!IS_ERR_OR_NULL(pages)) + __i915_gem_object_set_pages(obj, pages); return err; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 2f7804492cd5..9c759df700ca 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -247,7 +247,7 @@ rebuild_st: if (i915_gem_object_can_bypass_llc(obj)) obj->cache_dirty = true; - __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); + __i915_gem_object_set_pages(obj, st); return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 0c70711818ed..bc9521078807 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -628,7 +628,7 @@ static int i915_gem_object_get_pages_stolen(struct drm_i915_gem_object *obj) sg_dma_len(pages->sgl), POISON_INUSE); - __i915_gem_object_set_pages(obj, pages, obj->stolen->size); + __i915_gem_object_set_pages(obj, pages); return 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 25129af70f70..1e50fb0d6bfc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -603,6 +603,10 @@ static int i915_ttm_truncate(struct drm_i915_gem_object *obj) WARN_ON_ONCE(obj->mm.madv == I915_MADV_WILLNEED); + err = ttm_bo_wait(bo, true, false); + if (err) + return err; + err = i915_ttm_move_notify(bo); if (err) return err; @@ -815,8 +819,7 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, GEM_BUG_ON(obj->mm.rsgt); obj->mm.rsgt = rsgt; - __i915_gem_object_set_pages(obj, &rsgt->table, - i915_sg_dma_sizes(rsgt->table.sgl)); + __i915_gem_object_set_pages(obj, &rsgt->table); } GEM_BUG_ON(bo->ttm && ((obj->base.size >> PAGE_SHIFT) < bo->ttm->num_pages)); @@ -1031,9 +1034,6 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) vm_fault_t ret; int idx; - if (i915_ttm_is_ghost_object(bo)) - return VM_FAULT_SIGBUS; - /* Sanity check that we allow writing into this object */ if (unlikely(i915_gem_object_is_readonly(obj) && area->vm_flags & VM_WRITE)) @@ -1048,9 +1048,6 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - if (i915_ttm_cpu_maps_iomem(bo->resource)) - wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm); - if (!i915_ttm_resource_mappable(bo->resource)) { int err = -ENODEV; int i; @@ -1078,6 +1075,9 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) } } + if (i915_ttm_cpu_maps_iomem(bo->resource)) + wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm); + if (drm_dev_enter(dev, &idx)) { ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, TTM_BO_VM_NUM_PREFAULT); @@ -1098,6 +1098,8 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) spin_lock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock); list_add(&obj->userfault_link, &to_i915(obj->base.dev)->runtime_pm.lmem_userfault_list); spin_unlock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock); + + GEM_WARN_ON(!i915_ttm_cpu_maps_iomem(bo->resource)); } if (wakeref & CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) @@ -1180,6 +1182,8 @@ static void i915_ttm_unmap_virtual(struct drm_i915_gem_object *obj) } } + GEM_WARN_ON(obj->userfault_count); + ttm_bo_unmap_virtual(i915_gem_to_ttm(obj)); if (wakeref) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c index 07e49f22f2de..7e67742bc65e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c @@ -50,6 +50,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply, container_of(bo->bdev, typeof(*i915), bdev); struct drm_i915_gem_object *backup; struct ttm_operation_ctx ctx = {}; + unsigned int flags; int err = 0; if (bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup) @@ -65,7 +66,22 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply, if (obj->flags & I915_BO_ALLOC_PM_VOLATILE) return 0; - backup = i915_gem_object_create_shmem(i915, obj->base.size); + /* + * It seems that we might have some framebuffers still pinned at this + * stage, but for such objects we might also need to deal with the CCS + * aux state. Make sure we force the save/restore of the CCS state, + * otherwise we might observe display corruption, when returning from + * suspend. + */ + flags = 0; + if (i915_gem_object_needs_ccs_pages(obj)) { + WARN_ON_ONCE(!i915_gem_object_is_framebuffer(obj)); + WARN_ON_ONCE(!pm_apply->allow_gpu); + + flags = I915_BO_ALLOC_CCS_AUX; + } + backup = i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_SMEM], + obj->base.size, 0, flags); if (IS_ERR(backup)) return PTR_ERR(backup); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 1b1a22716722..9348b1804d53 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -131,7 +131,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) const unsigned long num_pages = obj->base.size >> PAGE_SHIFT; unsigned int max_segment = i915_sg_segment_size(obj->base.dev->dev); struct sg_table *st; - unsigned int sg_page_sizes; struct page **pvec; int ret; @@ -170,8 +169,7 @@ alloc_table: if (i915_gem_object_can_bypass_llc(obj)) obj->cache_dirty = true; - sg_page_sizes = i915_sg_dma_sizes(st->sgl); - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; @@ -427,9 +425,10 @@ probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { VMA_ITERATOR(vmi, mm, addr); struct vm_area_struct *vma; + unsigned long end = addr + len; mmap_read_lock(mm); - for_each_vma_range(vmi, vma, addr + len) { + for_each_vma_range(vmi, vma, end) { /* Check for holes, note that we also update the addr below */ if (vma->vm_start > addr) break; @@ -441,7 +440,7 @@ probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len) } mmap_read_unlock(mm); - if (vma) + if (vma || addr < end) return -EFAULT; return 0; } diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c index f963b8e1e37b..cbd9b624a788 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c @@ -68,7 +68,7 @@ static int huge_get_pages(struct drm_i915_gem_object *obj) if (i915_gem_gtt_prepare_pages(obj, pages)) goto err; - __i915_gem_object_set_pages(obj, pages, PAGE_SIZE); + __i915_gem_object_set_pages(obj, pages); return 0; diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index 0cb99e75b0bc..beaf27e09e8a 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -136,7 +136,7 @@ static int get_huge_pages(struct drm_i915_gem_object *obj) goto err; GEM_BUG_ON(sg_page_sizes != obj->mm.page_mask); - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; @@ -210,7 +210,6 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) const u64 max_len = rounddown_pow_of_two(UINT_MAX); struct sg_table *st; struct scatterlist *sg; - unsigned int sg_page_sizes; u64 rem; st = kmalloc(sizeof(*st), GFP); @@ -226,7 +225,6 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) rem = obj->base.size; sg = st->sgl; st->nents = 0; - sg_page_sizes = 0; do { unsigned int page_size = get_largest_page_size(i915, rem); unsigned int len = min(page_size * div_u64(rem, page_size), @@ -239,8 +237,6 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) sg_dma_len(sg) = len; sg_dma_address(sg) = page_size; - sg_page_sizes |= len; - st->nents++; rem -= len; @@ -254,7 +250,7 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) i915_sg_trim(st); - __i915_gem_object_set_pages(obj, st, sg_page_sizes); + __i915_gem_object_set_pages(obj, st); return 0; } @@ -286,7 +282,7 @@ static int fake_get_huge_pages_single(struct drm_i915_gem_object *obj) sg_dma_len(sg) = obj->base.size; sg_dma_address(sg) = page_size; - __i915_gem_object_set_pages(obj, st, sg->length); + __i915_gem_object_set_pages(obj, st); return 0; #undef GFP diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index 9a6a6b5b722b..692a16914ca0 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -13,6 +13,7 @@ #include "gt/intel_gt_regs.h" #include "gem/i915_gem_lmem.h" +#include "gem/selftests/igt_gem_utils.h" #include "selftests/igt_flush_test.h" #include "selftests/mock_drm.h" #include "selftests/i915_random.h" @@ -457,21 +458,6 @@ static int verify_buffer(const struct tiled_blits *t, return ret; } -static int move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - static int pin_buffer(struct i915_vma *vma, u64 addr) { int err; @@ -525,11 +511,11 @@ tiled_blit(struct tiled_blits *t, goto err_bb; } - err = move_to_active(t->batch, rq, 0); + err = igt_vma_move_to_active_unlocked(t->batch, rq, 0); if (!err) - err = move_to_active(src->vma, rq, 0); + err = igt_vma_move_to_active_unlocked(src->vma, rq, 0); if (!err) - err = move_to_active(dst->vma, rq, 0); + err = igt_vma_move_to_active_unlocked(dst->vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, t->batch->node.start, diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c index a666d7e610f5..c228fe4aba50 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c @@ -239,9 +239,7 @@ static int gpu_set(struct context *ctx, unsigned long offset, u32 v) } intel_ring_advance(rq, cs); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); out_rq: i915_request_add(rq); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index d8864444432b..a0ff51d71d07 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -984,15 +984,11 @@ retry: goto err_batch; } - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); if (err) goto skip_request; - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); if (err) goto skip_request; @@ -1553,9 +1549,7 @@ static int write_to_scratch(struct i915_gem_context *ctx, } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); i915_vma_unlock(vma); if (err) goto skip_request; @@ -1689,9 +1683,7 @@ static int read_from_scratch(struct i915_gem_context *ctx, } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); if (err) goto skip_request; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 3c486efe0bac..3f658d5717d8 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -566,10 +566,8 @@ retry: goto err_unpin; } - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, - EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, + EXEC_OBJECT_WRITE); i915_request_add(rq); err_unpin: @@ -1609,9 +1607,7 @@ retry: goto out_unpin; } - err = i915_request_await_object(rq, vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); err = engine->emit_bb_start(rq, vma->node.start, 0, 0); i915_request_get(rq); diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c index 3c55e77b0f1b..374b10ac430e 100644 --- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c +++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c @@ -131,17 +131,13 @@ int igt_gpu_fill_dw(struct intel_context *ce, } i915_vma_lock(batch); - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); i915_vma_unlock(batch); if (err) goto skip_request; i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); if (err) goto skip_request; diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h index 4221cf84d175..1379fbc14431 100644 --- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h +++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h @@ -9,6 +9,8 @@ #include <linux/types.h> +#include "i915_vma.h" + struct i915_request; struct i915_gem_context; struct i915_vma; @@ -29,4 +31,16 @@ int igt_gpu_fill_dw(struct intel_context *ce, struct i915_vma *vma, u64 offset, unsigned long count, u32 val); +static inline int __must_check +igt_vma_move_to_active_unlocked(struct i915_vma *vma, struct i915_request *rq, + unsigned int flags) +{ + int err; + + i915_vma_lock(vma); + err = _i915_vma_move_to_active(vma, rq, &rq->fence, flags); + i915_vma_unlock(vma); + return err; +} + #endif /* __IGT_GEM_UTILS_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 6ae8b07cfaa1..c33e0d72d670 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -246,6 +246,13 @@ static const struct engine_info intel_engines[] = { { .graphics_ver = 12, .base = GEN12_COMPUTE3_RING_BASE } } }, + [GSC0] = { + .class = OTHER_CLASS, + .instance = OTHER_GSC_INSTANCE, + .mmio_bases = { + { .graphics_ver = 12, .base = MTL_GSC_RING_BASE } + } + }, }; /** @@ -326,6 +333,7 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class) case VIDEO_DECODE_CLASS: case VIDEO_ENHANCEMENT_CLASS: case COPY_ENGINE_CLASS: + case OTHER_CLASS: if (GRAPHICS_VER(gt->i915) < 8) return 0; return GEN8_LR_CONTEXT_OTHER_SIZE; @@ -417,6 +425,7 @@ static u32 get_reset_domain(u8 ver, enum intel_engine_id id) [CCS1] = GEN11_GRDOM_RENDER, [CCS2] = GEN11_GRDOM_RENDER, [CCS3] = GEN11_GRDOM_RENDER, + [GSC0] = GEN12_GRDOM_GSC, }; GEM_BUG_ON(id >= ARRAY_SIZE(engine_reset_domains) || !engine_reset_domains[id]); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 6b5d4ea22b67..4fd54fb8810f 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -136,6 +136,7 @@ enum intel_engine_id { CCS2, CCS3, #define _CCS(n) (CCS0 + (n)) + GSC0, I915_NUM_ENGINES #define INVALID_ENGINE ((enum intel_engine_id)-1) }; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index 46a174f8aa00..cd4f1b126f75 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -140,6 +140,7 @@ const char *intel_engine_class_repr(u8 class) [COPY_ENGINE_CLASS] = "bcs", [VIDEO_DECODE_CLASS] = "vcs", [VIDEO_ENHANCEMENT_CLASS] = "vecs", + [OTHER_CLASS] = "other", [COMPUTE_CLASS] = "ccs", }; @@ -190,6 +191,15 @@ static void add_legacy_ring(struct legacy_ring *ring, ring->instance++; } +static void engine_rename(struct intel_engine_cs *engine, const char *name, u16 instance) +{ + char old[sizeof(engine->name)]; + + memcpy(old, engine->name, sizeof(engine->name)); + scnprintf(engine->name, sizeof(engine->name), "%s%u", name, instance); + drm_dbg(&engine->i915->drm, "renamed %s to %s\n", old, engine->name); +} + void intel_engines_driver_register(struct drm_i915_private *i915) { struct legacy_ring ring = {}; @@ -205,11 +215,19 @@ void intel_engines_driver_register(struct drm_i915_private *i915) struct intel_engine_cs *engine = container_of((struct rb_node *)it, typeof(*engine), uabi_node); - char old[sizeof(engine->name)]; if (intel_gt_has_unrecoverable_error(engine->gt)) continue; /* ignore incomplete engines */ + /* + * We don't want to expose the GSC engine to the users, but we + * still rename it so it is easier to identify in the debug logs + */ + if (engine->id == GSC0) { + engine_rename(engine, "gsc", 0); + continue; + } + GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes)); engine->uabi_class = uabi_classes[engine->class]; @@ -219,11 +237,9 @@ void intel_engines_driver_register(struct drm_i915_private *i915) i915->engine_uabi_class_count[engine->uabi_class]++; /* Replace the internal name with the final user facing name */ - memcpy(old, engine->name, sizeof(engine->name)); - scnprintf(engine->name, sizeof(engine->name), "%s%u", - intel_engine_class_repr(engine->class), - engine->uabi_instance); - DRM_DEBUG_DRIVER("renamed %s to %s\n", old, engine->name); + engine_rename(engine, + intel_engine_class_repr(engine->class), + engine->uabi_instance); rb_link_node(&engine->uabi_node, prev, p); rb_insert_color(&engine->uabi_node, &i915->uabi_engines); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index b23ef1faa501..2daffa7c7dfd 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3690,7 +3690,7 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve) * NB This does not force us to execute on this engine, it will just * typically be the first we inspect for submission. */ - swp = prandom_u32_max(ve->num_siblings); + swp = get_random_u32_below(ve->num_siblings); if (swp) swap(ve->siblings[swp], ve->siblings[0]); } @@ -3922,6 +3922,7 @@ static struct intel_context * execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, unsigned long flags) { + struct drm_i915_private *i915 = siblings[0]->i915; struct virtual_engine *ve; unsigned int n; int err; @@ -3930,7 +3931,7 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, if (!ve) return ERR_PTR(-ENOMEM); - ve->base.i915 = siblings[0]->i915; + ve->base.i915 = i915; ve->base.gt = siblings[0]->gt; ve->base.uncore = siblings[0]->uncore; ve->base.id = -1; @@ -3989,8 +3990,9 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, GEM_BUG_ON(!is_power_of_2(sibling->mask)); if (sibling->mask & ve->base.mask) { - DRM_DEBUG("duplicate %s entry in load balancer\n", - sibling->name); + drm_dbg(&i915->drm, + "duplicate %s entry in load balancer\n", + sibling->name); err = -EINVAL; goto err_put; } @@ -4024,8 +4026,9 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, */ if (ve->base.class != OTHER_CLASS) { if (ve->base.class != sibling->class) { - DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", - sibling->class, ve->base.class); + drm_dbg(&i915->drm, + "invalid mixing of engine class, sibling %d, already %d\n", + sibling->class, ve->base.class); err = -EINVAL; goto err_put; } diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 2518cebbf931..8145851ad23d 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -560,7 +560,7 @@ static int init_ggtt(struct i915_ggtt *ggtt) * why. */ ggtt->pin_bias = max_t(u32, I915_GTT_PAGE_SIZE, - intel_wopcm_guc_size(&ggtt->vm.i915->wopcm)); + intel_wopcm_guc_size(&ggtt->vm.gt->wopcm)); ret = intel_vgt_balloon(ggtt); if (ret) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index ea775e601686..995082d45cb2 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -816,8 +816,8 @@ i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj, if (obj->bit_17 == NULL) { obj->bit_17 = bitmap_zalloc(page_count, GFP_KERNEL); if (obj->bit_17 == NULL) { - DRM_ERROR("Failed to allocate memory for bit 17 " - "record\n"); + drm_err(&to_i915(obj->base.dev)->drm, + "Failed to allocate memory for bit 17 record\n"); return; } } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 53b8dcf7b34d..767e329e1cc5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -55,6 +55,7 @@ void intel_gt_common_init_early(struct intel_gt *gt) seqcount_mutex_init(>->tlb.seqno, >->tlb.invalidate_lock); intel_gt_pm_init_early(gt); + intel_wopcm_init_early(>->wopcm); intel_uc_init_early(>->uc); intel_rps_init_early(>->rps); } @@ -191,7 +192,7 @@ int intel_gt_init_hw(struct intel_gt *gt) ret = i915_ppgtt_init_hw(gt); if (ret) { - DRM_ERROR("Enabling PPGTT failed (%d)\n", ret); + drm_err(&i915->drm, "Enabling PPGTT failed (%d)\n", ret); goto out; } @@ -263,7 +264,7 @@ intel_gt_clear_error_registers(struct intel_gt *gt, * some errors might have become stuck, * mask them. */ - DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masking\n", eir); + drm_dbg(>->i915->drm, "EIR stuck: 0x%08x, masking\n", eir); rmw_set(uncore, EMR, eir); intel_uncore_write(uncore, GEN2_IIR, I915_MASTER_ERROR_INTERRUPT); @@ -676,8 +677,13 @@ int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout) return -EINTR; } - return timeout ? timeout : intel_uc_wait_for_idle(>->uc, - remaining_timeout); + if (timeout) + return timeout; + + if (remaining_timeout < 0) + remaining_timeout = 0; + + return intel_uc_wait_for_idle(>->uc, remaining_timeout); } int intel_gt_init(struct intel_gt *gt) @@ -1034,9 +1040,9 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb) { if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50)) - return intel_gt_mcr_wait_for_reg_fw(gt, rb.mcr_reg, rb.bit, 0, - TLB_INVAL_TIMEOUT_US, - TLB_INVAL_TIMEOUT_MS); + return intel_gt_mcr_wait_for_reg(gt, rb.mcr_reg, rb.bit, 0, + TLB_INVAL_TIMEOUT_US, + TLB_INVAL_TIMEOUT_MS); else return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0, TLB_INVAL_TIMEOUT_US, @@ -1111,6 +1117,11 @@ static void mmio_invalidate_full(struct intel_gt *gt) if (!i915_mmio_reg_offset(rb.reg)) continue; + if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS || + engine->class == COMPUTE_CLASS)) + rb.bit = _MASKED_BIT_ENABLE(rb.bit); + intel_uncore_write_fw(uncore, rb.reg, rb.bit); } awake |= engine->mask; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index f26882fdc24c..6f6b9e04d916 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -17,6 +17,9 @@ static void guc_irq_handler(struct intel_guc *guc, u16 iir) { + if (unlikely(!guc->interrupts.enabled)) + return; + if (iir & GUC_INTR_GUC2HOST) intel_guc_to_host_event_handler(guc); } @@ -44,8 +47,9 @@ gen11_gt_engine_identity(struct intel_gt *gt, !time_after32(local_clock() >> 10, timeout_ts)); if (unlikely(!(ident & GEN11_INTR_DATA_VALID))) { - DRM_ERROR("INTR_IDENTITY_REG%u:%u 0x%08x not valid!\n", - bank, bit, ident); + drm_err(>->i915->drm, + "INTR_IDENTITY_REG%u:%u 0x%08x not valid!\n", + bank, bit, ident); return 0; } @@ -81,35 +85,27 @@ gen11_other_irq_handler(struct intel_gt *gt, const u8 instance, instance, iir); } -static void -gen11_engine_irq_handler(struct intel_gt *gt, const u8 class, - const u8 instance, const u16 iir) +static struct intel_gt *pick_gt(struct intel_gt *gt, u8 class, u8 instance) { - struct intel_engine_cs *engine; - - /* - * Platforms with standalone media have their media engines in another - * GT. - */ - if (MEDIA_VER(gt->i915) >= 13 && - (class == VIDEO_DECODE_CLASS || class == VIDEO_ENHANCEMENT_CLASS)) { - if (!gt->i915->media_gt) - goto err; + struct intel_gt *media_gt = gt->i915->media_gt; - gt = gt->i915->media_gt; + /* we expect the non-media gt to be passed in */ + GEM_BUG_ON(gt == media_gt); + + if (!media_gt) + return gt; + + switch (class) { + case VIDEO_DECODE_CLASS: + case VIDEO_ENHANCEMENT_CLASS: + return media_gt; + case OTHER_CLASS: + if (instance == OTHER_GSC_INSTANCE && HAS_ENGINE(media_gt, GSC0)) + return media_gt; + fallthrough; + default: + return gt; } - - if (instance <= MAX_ENGINE_INSTANCE) - engine = gt->engine_class[class][instance]; - else - engine = NULL; - - if (likely(engine)) - return intel_engine_cs_irq(engine, iir); - -err: - WARN_ONCE(1, "unhandled engine interrupt class=0x%x, instance=0x%x\n", - class, instance); } static void @@ -122,8 +118,17 @@ gen11_gt_identity_handler(struct intel_gt *gt, const u32 identity) if (unlikely(!intr)) return; - if (class <= COPY_ENGINE_CLASS || class == COMPUTE_CLASS) - return gen11_engine_irq_handler(gt, class, instance, intr); + /* + * Platforms with standalone media have the media and GSC engines in + * another GT. + */ + gt = pick_gt(gt, class, instance); + + if (class <= MAX_ENGINE_CLASS && instance <= MAX_ENGINE_INSTANCE) { + struct intel_engine_cs *engine = gt->engine_class[class][instance]; + if (engine) + return intel_engine_cs_irq(engine, intr); + } if (class == OTHER_CLASS) return gen11_other_irq_handler(gt, instance, intr); @@ -206,7 +211,7 @@ void gen11_gt_irq_reset(struct intel_gt *gt) intel_uncore_write(uncore, GEN11_VCS_VECS_INTR_ENABLE, 0); if (CCS_MASK(gt)) intel_uncore_write(uncore, GEN12_CCS_RSVD_INTR_ENABLE, 0); - if (HAS_HECI_GSC(gt->i915)) + if (HAS_HECI_GSC(gt->i915) || HAS_ENGINE(gt, GSC0)) intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, 0); /* Restore masks irqs on RCS, BCS, VCS and VECS engines. */ @@ -233,7 +238,7 @@ void gen11_gt_irq_reset(struct intel_gt *gt) intel_uncore_write(uncore, GEN12_CCS0_CCS1_INTR_MASK, ~0); if (HAS_ENGINE(gt, CCS2) || HAS_ENGINE(gt, CCS3)) intel_uncore_write(uncore, GEN12_CCS2_CCS3_INTR_MASK, ~0); - if (HAS_HECI_GSC(gt->i915)) + if (HAS_HECI_GSC(gt->i915) || HAS_ENGINE(gt, GSC0)) intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_MASK, ~0); intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0); @@ -249,7 +254,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) { struct intel_uncore *uncore = gt->uncore; u32 irqs = GT_RENDER_USER_INTERRUPT; - const u32 gsc_mask = GSC_IRQ_INTF(0) | GSC_IRQ_INTF(1); + u32 guc_mask = intel_uc_wants_guc(>->uc) ? GUC_INTR_GUC2HOST : 0; + u32 gsc_mask = 0; u32 dmask; u32 smask; @@ -261,6 +267,11 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) dmask = irqs << 16 | irqs; smask = irqs << 16; + if (HAS_ENGINE(gt, GSC0)) + gsc_mask = irqs; + else if (HAS_HECI_GSC(gt->i915)) + gsc_mask = GSC_IRQ_INTF(0) | GSC_IRQ_INTF(1); + BUILD_BUG_ON(irqs & 0xffff0000); /* Enable RCS, BCS, VCS and VECS class interrupts. */ @@ -268,9 +279,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) intel_uncore_write(uncore, GEN11_VCS_VECS_INTR_ENABLE, dmask); if (CCS_MASK(gt)) intel_uncore_write(uncore, GEN12_CCS_RSVD_INTR_ENABLE, smask); - if (HAS_HECI_GSC(gt->i915)) - intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, - gsc_mask); + if (gsc_mask) + intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, gsc_mask); /* Unmask irqs on RCS, BCS, VCS and VECS engines. */ intel_uncore_write(uncore, GEN11_RCS0_RSVD_INTR_MASK, ~smask); @@ -296,9 +306,22 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) intel_uncore_write(uncore, GEN12_CCS0_CCS1_INTR_MASK, ~dmask); if (HAS_ENGINE(gt, CCS2) || HAS_ENGINE(gt, CCS3)) intel_uncore_write(uncore, GEN12_CCS2_CCS3_INTR_MASK, ~dmask); - if (HAS_HECI_GSC(gt->i915)) + if (gsc_mask) intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_MASK, ~gsc_mask); + if (guc_mask) { + /* the enable bit is common for both GTs but the masks are separate */ + u32 mask = gt->type == GT_MEDIA ? + REG_FIELD_PREP(ENGINE0_MASK, guc_mask) : + REG_FIELD_PREP(ENGINE1_MASK, guc_mask); + + intel_uncore_write(uncore, GEN11_GUC_SG_INTR_ENABLE, + REG_FIELD_PREP(ENGINE1_MASK, guc_mask)); + + /* we might not be the first GT to write this reg */ + intel_uncore_rmw(uncore, MTL_GUC_MGUC_INTR_MASK, mask, 0); + } + /* * RPS interrupts will get enabled/disabled on demand when RPS itself * is enabled/disabled. @@ -307,10 +330,6 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) gt->pm_imr = ~gt->pm_ier; intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE, 0); intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK, ~0); - - /* Same thing for GuC interrupts */ - intel_uncore_write(uncore, GEN11_GUC_SG_INTR_ENABLE, 0); - intel_uncore_write(uncore, GEN11_GUC_SG_INTR_MASK, ~0); } void gen5_gt_irq_handler(struct intel_gt *gt, u32 gt_iir) @@ -359,7 +378,8 @@ void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir) if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT | GT_BSD_CS_ERROR_INTERRUPT | GT_CS_MASTER_ERROR_INTERRUPT)) - DRM_DEBUG("Command parser error, gt_iir 0x%08x\n", gt_iir); + drm_dbg(>->i915->drm, "Command parser error, gt_iir 0x%08x\n", + gt_iir); if (gt_iir & GT_PARITY_ERROR(gt->i915)) gen7_parity_error_irq_handler(gt, gt_iir); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c index 830edffe88cc..ea86c1ab5dc5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c @@ -702,7 +702,7 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss, } /** - * intel_gt_mcr_wait_for_reg_fw - wait until MCR register matches expected state + * intel_gt_mcr_wait_for_reg - wait until MCR register matches expected state * @gt: GT structure * @reg: the register to read * @mask: mask to apply to register value @@ -730,17 +730,19 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss, * * Return: 0 if the register matches the desired condition, or -ETIMEDOUT. */ -int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt, - i915_mcr_reg_t reg, - u32 mask, - u32 value, - unsigned int fast_timeout_us, - unsigned int slow_timeout_ms) +int intel_gt_mcr_wait_for_reg(struct intel_gt *gt, + i915_mcr_reg_t reg, + u32 mask, + u32 value, + unsigned int fast_timeout_us, + unsigned int slow_timeout_ms) { - u32 reg_value = 0; -#define done (((reg_value = intel_gt_mcr_read_any_fw(gt, reg)) & mask) == value) int ret; + lockdep_assert_not_held(>->uncore->lock); + +#define done ((intel_gt_mcr_read_any(gt, reg) & mask) == value) + /* Catch any overuse of this function */ might_sleep_if(slow_timeout_ms); GEM_BUG_ON(fast_timeout_us > 20000); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h index 3fb0502bff22..ae93b20e1c17 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h @@ -37,12 +37,12 @@ void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt, void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss, unsigned int *group, unsigned int *instance); -int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt, - i915_mcr_reg_t reg, - u32 mask, - u32 value, - unsigned int fast_timeout_us, - unsigned int slow_timeout_ms); +int intel_gt_mcr_wait_for_reg(struct intel_gt *gt, + i915_mcr_reg_t reg, + u32 mask, + u32 value, + unsigned int fast_timeout_us, + unsigned int slow_timeout_ms); /* * Helper for for_each_ss_steering loop. On pre-Xe_HP platforms, subslice diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 3fbf70a58747..16db85fab0b1 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -20,10 +20,31 @@ #include "intel_rc6.h" #include "intel_rps.h" #include "intel_wakeref.h" +#include "intel_pcode.h" #include "pxp/intel_pxp_pm.h" #define I915_GT_SUSPEND_IDLE_TIMEOUT (HZ / 2) +static void mtl_media_busy(struct intel_gt *gt) +{ + /* Wa_14017073508: mtl */ + if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) + snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, + PCODE_MBOX_GT_STATE_MEDIA_BUSY, + PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); +} + +static void mtl_media_idle(struct intel_gt *gt) +{ + /* Wa_14017073508: mtl */ + if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) + snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, + PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY, + PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); +} + static void user_forcewake(struct intel_gt *gt, bool suspend) { int count = atomic_read(>->user_wakeref); @@ -71,6 +92,9 @@ static int __gt_unpark(struct intel_wakeref *wf) GT_TRACE(gt, "\n"); + /* Wa_14017073508: mtl */ + mtl_media_busy(gt); + /* * It seems that the DMC likes to transition between the DC states a lot * when there are no connected displays (no active power domains) during @@ -120,6 +144,9 @@ static int __gt_park(struct intel_wakeref *wf) GEM_BUG_ON(!wakeref); intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref); + /* Wa_14017073508: mtl */ + mtl_media_idle(gt); + return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c index 40d0a3be42ac..83df4cd5e06c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c @@ -83,19 +83,6 @@ static int fw_domains_show(struct seq_file *m, void *data) } DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(fw_domains); -static void print_rc6_res(struct seq_file *m, - const char *title, - const i915_reg_t reg) -{ - struct intel_gt *gt = m->private; - intel_wakeref_t wakeref; - - with_intel_runtime_pm(gt->uncore->rpm, wakeref) - seq_printf(m, "%s %u (%llu us)\n", title, - intel_uncore_read(gt->uncore, reg), - intel_rc6_residency_us(>->rc6, reg)); -} - static int vlv_drpc(struct seq_file *m) { struct intel_gt *gt = m->private; @@ -115,8 +102,8 @@ static int vlv_drpc(struct seq_file *m) seq_printf(m, "Media Power Well: %s\n", (pw_status & VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down"); - print_rc6_res(m, "Render RC6 residency since boot:", GEN6_GT_GFX_RC6); - print_rc6_res(m, "Media RC6 residency since boot:", VLV_GT_MEDIA_RC6); + intel_rc6_print_residency(m, "Render RC6 residency since boot:", INTEL_RC6_RES_RC6); + intel_rc6_print_residency(m, "Media RC6 residency since boot:", INTEL_RC6_RES_VLV_MEDIA); return fw_domains_show(m, NULL); } @@ -192,11 +179,11 @@ static int gen6_drpc(struct seq_file *m) } /* Not exactly sure what this is */ - print_rc6_res(m, "RC6 \"Locked to RPn\" residency since boot:", - GEN6_GT_GFX_RC6_LOCKED); - print_rc6_res(m, "RC6 residency since boot:", GEN6_GT_GFX_RC6); - print_rc6_res(m, "RC6+ residency since boot:", GEN6_GT_GFX_RC6p); - print_rc6_res(m, "RC6++ residency since boot:", GEN6_GT_GFX_RC6pp); + intel_rc6_print_residency(m, "RC6 \"Locked to RPn\" residency since boot:", + INTEL_RC6_RES_RC6_LOCKED); + intel_rc6_print_residency(m, "RC6 residency since boot:", INTEL_RC6_RES_RC6); + intel_rc6_print_residency(m, "RC6+ residency since boot:", INTEL_RC6_RES_RC6p); + intel_rc6_print_residency(m, "RC6++ residency since boot:", INTEL_RC6_RES_RC6pp); if (GRAPHICS_VER(i915) <= 7) { seq_printf(m, "RC6 voltage: %dmV\n", @@ -269,6 +256,61 @@ static int ilk_drpc(struct seq_file *m) return 0; } +static int mtl_drpc(struct seq_file *m) +{ + struct intel_gt *gt = m->private; + struct intel_uncore *uncore = gt->uncore; + u32 gt_core_status, rcctl1, mt_fwake_req; + u32 mtl_powergate_enable = 0, mtl_powergate_status = 0; + + mt_fwake_req = intel_uncore_read_fw(uncore, FORCEWAKE_MT); + gt_core_status = intel_uncore_read(uncore, MTL_MIRROR_TARGET_WP1); + + rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL); + mtl_powergate_enable = intel_uncore_read(uncore, GEN9_PG_ENABLE); + mtl_powergate_status = intel_uncore_read(uncore, + GEN9_PWRGT_DOMAIN_STATUS); + + seq_printf(m, "RC6 Enabled: %s\n", + str_yes_no(rcctl1 & GEN6_RC_CTL_RC6_ENABLE)); + if (gt->type == GT_MEDIA) { + seq_printf(m, "Media Well Gating Enabled: %s\n", + str_yes_no(mtl_powergate_enable & GEN9_MEDIA_PG_ENABLE)); + } else { + seq_printf(m, "Render Well Gating Enabled: %s\n", + str_yes_no(mtl_powergate_enable & GEN9_RENDER_PG_ENABLE)); + } + + seq_puts(m, "Current RC state: "); + switch (REG_FIELD_GET(MTL_CC_MASK, gt_core_status)) { + case MTL_CC0: + seq_puts(m, "RC0\n"); + break; + case MTL_CC6: + seq_puts(m, "RC6\n"); + break; + default: + MISSING_CASE(REG_FIELD_GET(MTL_CC_MASK, gt_core_status)); + seq_puts(m, "Unknown\n"); + break; + } + + seq_printf(m, "Multi-threaded Forcewake Request: 0x%x\n", mt_fwake_req); + if (gt->type == GT_MEDIA) + seq_printf(m, "Media Power Well: %s\n", + (mtl_powergate_status & + GEN9_PWRGT_MEDIA_STATUS_MASK) ? "Up" : "Down"); + else + seq_printf(m, "Render Power Well: %s\n", + (mtl_powergate_status & + GEN9_PWRGT_RENDER_STATUS_MASK) ? "Up" : "Down"); + + /* Works for both render and media gt's */ + intel_rc6_print_residency(m, "RC6 residency since boot:", INTEL_RC6_RES_RC6); + + return fw_domains_show(m, NULL); +} + static int drpc_show(struct seq_file *m, void *unused) { struct intel_gt *gt = m->private; @@ -277,7 +319,9 @@ static int drpc_show(struct seq_file *m, void *unused) int err = -ENODEV; with_intel_runtime_pm(gt->uncore->rpm, wakeref) { - if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + err = mtl_drpc(m); + else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) err = vlv_drpc(m); else if (GRAPHICS_VER(i915) >= 6) err = gen6_drpc(m); @@ -307,7 +351,7 @@ void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *p) drm_printf(p, "Current VID: %d\n", (rgvstat & MEMSTAT_VID_MASK) >> MEMSTAT_VID_SHIFT); drm_printf(p, "Current P-state: %d\n", - (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT); + REG_FIELD_GET(MEMSTAT_PSTATE_MASK, rgvstat)); } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { u32 rpmodectl, freq_sts; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 5051d8ac7ae9..c3cd92691795 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -22,6 +22,13 @@ */ #define PERF_REG(offset) _MMIO(offset) +/* MTL workpoint reg to get core C state and actual freq of 3D, SAMedia */ +#define MTL_MIRROR_TARGET_WP1 _MMIO(0xc60) +#define MTL_CAGF_MASK REG_GENMASK(8, 0) +#define MTL_CC0 0x0 +#define MTL_CC6 0x3 +#define MTL_CC_MASK REG_GENMASK(12, 9) + /* RPM unit config (Gen8+) */ #define RPM_CONFIG0 _MMIO(0xd00) #define GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT 3 @@ -644,6 +651,7 @@ #define XEHPC_GRDOM_BLT3 REG_BIT(26) #define XEHPC_GRDOM_BLT2 REG_BIT(25) #define XEHPC_GRDOM_BLT1 REG_BIT(24) +#define GEN12_GRDOM_GSC REG_BIT(21) #define GEN11_GRDOM_SFC3 REG_BIT(20) #define GEN11_GRDOM_SFC2 REG_BIT(19) #define GEN11_GRDOM_SFC1 REG_BIT(18) @@ -799,12 +807,9 @@ #define GEN6_RP_DOWN_TIMEOUT _MMIO(0xa010) #define GEN6_RP_INTERRUPT_LIMITS _MMIO(0xa014) #define GEN6_RPSTAT1 _MMIO(0xa01c) -#define GEN6_CAGF_SHIFT 8 -#define HSW_CAGF_SHIFT 7 -#define GEN9_CAGF_SHIFT 23 -#define GEN6_CAGF_MASK (0x7f << GEN6_CAGF_SHIFT) -#define HSW_CAGF_MASK (0x7f << HSW_CAGF_SHIFT) -#define GEN9_CAGF_MASK (0x1ff << GEN9_CAGF_SHIFT) +#define GEN6_CAGF_MASK REG_GENMASK(14, 8) +#define HSW_CAGF_MASK REG_GENMASK(13, 7) +#define GEN9_CAGF_MASK REG_GENMASK(31, 23) #define GEN6_RP_CONTROL _MMIO(0xa024) #define GEN6_RP_MEDIA_TURBO (1 << 11) #define GEN6_RP_MEDIA_MODE_MASK (3 << 9) @@ -1376,8 +1381,7 @@ #define MEMSTAT_ILK _MMIO(0x111f8) #define MEMSTAT_VID_MASK 0x7f00 #define MEMSTAT_VID_SHIFT 8 -#define MEMSTAT_PSTATE_MASK 0x00f8 -#define MEMSTAT_PSTATE_SHIFT 3 +#define MEMSTAT_PSTATE_MASK REG_GENMASK(7, 3) #define MEMSTAT_MON_ACTV (1 << 2) #define MEMSTAT_SRC_CTL_MASK 0x0003 #define MEMSTAT_SRC_CTL_CORE 0 @@ -1518,6 +1522,8 @@ #define FORCEWAKE_MEDIA_VLV _MMIO(0x1300b8) #define FORCEWAKE_ACK_MEDIA_VLV _MMIO(0x1300bc) +#define MTL_MEDIA_MC6 _MMIO(0x138048) + #define GEN6_GT_THREAD_STATUS_REG _MMIO(0x13805c) #define GEN6_GT_THREAD_STATUS_CORE_MASK 0x7 @@ -1549,11 +1555,13 @@ #define GEN12_RPSTAT1 _MMIO(0x1381b4) #define GEN12_VOLTAGE_MASK REG_GENMASK(10, 0) +#define GEN12_CAGF_MASK REG_GENMASK(19, 11) #define GEN11_GT_INTR_DW(x) _MMIO(0x190018 + ((x) * 4)) #define GEN11_CSME (31) #define GEN11_GUNIT (28) #define GEN11_GUC (25) +#define MTL_MGUC (24) #define GEN11_WDPERF (20) #define GEN11_KCR (19) #define GEN11_GTPM (16) @@ -1608,6 +1616,7 @@ #define GEN11_VECS0_VECS1_INTR_MASK _MMIO(0x1900d0) #define GEN12_VECS2_VECS3_INTR_MASK _MMIO(0x1900d4) #define GEN11_GUC_SG_INTR_MASK _MMIO(0x1900e8) +#define MTL_GUC_MGUC_INTR_MASK _MMIO(0x1900e8) /* MTL+ */ #define GEN11_GPM_WGBOXPERF_INTR_MASK _MMIO(0x1900ec) #define GEN11_CRYPTO_RSVD_INTR_MASK _MMIO(0x1900f0) #define GEN11_GUNIT_CSME_INTR_MASK _MMIO(0x1900f4) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index edb881d75630..1dfd01668c79 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -199,7 +199,7 @@ out_active: spin_lock(&timelines->lock); if (remaining_timeout) *remaining_timeout = timeout; - return active_count ? timeout : 0; + return active_count ? timeout ?: -ETIME : 0; } static void retire_work_handler(struct work_struct *work) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c index 2b5f05b31187..cf71305ad586 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c @@ -165,13 +165,13 @@ sysfs_gt_attribute_r_func(struct kobject *kobj, struct attribute *attr, INTEL_GT_ATTR_RO(_name) #ifdef CONFIG_PM -static u32 get_residency(struct intel_gt *gt, i915_reg_t reg) +static u32 get_residency(struct intel_gt *gt, enum intel_rc6_res_type id) { intel_wakeref_t wakeref; u64 res = 0; with_intel_runtime_pm(gt->uncore->rpm, wakeref) - res = intel_rc6_residency_us(>->rc6, reg); + res = intel_rc6_residency_us(>->rc6, id); return DIV_ROUND_CLOSEST_ULL(res, 1000); } @@ -210,22 +210,22 @@ static ssize_t rc6_enable_dev_show(struct device *dev, static u32 __rc6_residency_ms_show(struct intel_gt *gt) { - return get_residency(gt, GEN6_GT_GFX_RC6); + return get_residency(gt, INTEL_RC6_RES_RC6); } static u32 __rc6p_residency_ms_show(struct intel_gt *gt) { - return get_residency(gt, GEN6_GT_GFX_RC6p); + return get_residency(gt, INTEL_RC6_RES_RC6p); } static u32 __rc6pp_residency_ms_show(struct intel_gt *gt) { - return get_residency(gt, GEN6_GT_GFX_RC6pp); + return get_residency(gt, INTEL_RC6_RES_RC6pp); } static u32 __media_rc6_residency_ms_show(struct intel_gt *gt) { - return get_residency(gt, VLV_GT_MEDIA_RC6); + return get_residency(gt, INTEL_RC6_RES_VLV_MEDIA); } INTEL_GT_SYSFS_SHOW_MIN(rc6_residency_ms); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index a0cc73b401ef..c1d9cd255e06 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -31,6 +31,7 @@ #include "intel_migrate_types.h" #include "intel_wakeref.h" #include "pxp/intel_pxp_types.h" +#include "intel_wopcm.h" struct drm_i915_private; struct i915_ggtt; @@ -101,6 +102,7 @@ struct intel_gt { struct intel_uc uc; struct intel_gsc gsc; + struct intel_wopcm wopcm; struct { /* Serialize global tlb invalidations */ diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c index b405a04135ca..5fb74e71f27b 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.c +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c @@ -342,6 +342,16 @@ static int emit_no_arbitration(struct i915_request *rq) return 0; } +static int max_pte_pkt_size(struct i915_request *rq, int pkt) +{ + struct intel_ring *ring = rq->ring; + + pkt = min_t(int, pkt, (ring->space - rq->reserved_space) / sizeof(u32) + 5); + pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); + + return pkt; +} + static int emit_pte(struct i915_request *rq, struct sgt_dma *it, enum i915_cache_level cache_level, @@ -388,8 +398,7 @@ static int emit_pte(struct i915_request *rq, return PTR_ERR(cs); /* Pack as many PTE updates as possible into a single MI command */ - pkt = min_t(int, dword_length, ring->space / sizeof(u32) + 5); - pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); + pkt = max_pte_pkt_size(rq, dword_length); hdr = cs; *cs++ = MI_STORE_DATA_IMM | REG_BIT(21); /* as qword elements */ @@ -422,8 +431,7 @@ static int emit_pte(struct i915_request *rq, } } - pkt = min_t(int, dword_rem, ring->space / sizeof(u32) + 5); - pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5); + pkt = max_pte_pkt_size(rq, dword_rem); hdr = cs; *cs++ = MI_STORE_DATA_IMM | REG_BIT(21); @@ -829,14 +837,35 @@ intel_context_migrate_copy(struct intel_context *ce, if (err) goto out_rq; - /* - * While we can't always restore/manage the CCS state, - * we still need to ensure we don't leak the CCS state - * from the previous user, so make sure we overwrite it - * with something. - */ - err = emit_copy_ccs(rq, dst_offset, INDIRECT_ACCESS, - dst_offset, DIRECT_ACCESS, len); + if (src_is_lmem) { + /* + * If the src is already in lmem, then we must + * be doing an lmem -> lmem transfer, and so + * should be safe to directly copy the CCS + * state. In this case we have either + * initialised the CCS aux state when first + * clearing the pages (since it is already + * allocated in lmem), or the user has + * potentially populated it, in which case we + * need to copy the CCS state as-is. + */ + err = emit_copy_ccs(rq, + dst_offset, INDIRECT_ACCESS, + src_offset, INDIRECT_ACCESS, + len); + } else { + /* + * While we can't always restore/manage the CCS + * state, we still need to ensure we don't leak + * the CCS state from the previous user, so make + * sure we overwrite it with something. + */ + err = emit_copy_ccs(rq, + dst_offset, INDIRECT_ACCESS, + dst_offset, DIRECT_ACCESS, + len); + } + if (err) goto out_rq; diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index f8d0523f4c18..2ee4051e4d96 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -551,6 +551,23 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6) intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL); } +static void rc6_res_reg_init(struct intel_rc6 *rc6) +{ + memset(rc6->res_reg, INVALID_MMIO_REG.reg, sizeof(rc6->res_reg)); + + switch (rc6_to_gt(rc6)->type) { + case GT_MEDIA: + rc6->res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6; + break; + default: + rc6->res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED; + rc6->res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6; + rc6->res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p; + rc6->res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp; + break; + } +} + void intel_rc6_init(struct intel_rc6 *rc6) { struct drm_i915_private *i915 = rc6_to_i915(rc6); @@ -562,6 +579,8 @@ void intel_rc6_init(struct intel_rc6 *rc6) if (!rc6_supported(rc6)) return; + rc6_res_reg_init(rc6); + if (IS_CHERRYVIEW(i915)) err = chv_rc6_init(rc6); else if (IS_VALLEYVIEW(i915)) @@ -736,31 +755,19 @@ static u64 vlv_residency_raw(struct intel_uncore *uncore, const i915_reg_t reg) return lower | (u64)upper << 8; } -u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) +u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, enum intel_rc6_res_type id) { struct drm_i915_private *i915 = rc6_to_i915(rc6); struct intel_uncore *uncore = rc6_to_uncore(rc6); u64 time_hw, prev_hw, overflow_hw; + i915_reg_t reg = rc6->res_reg[id]; unsigned int fw_domains; unsigned long flags; - unsigned int i; u32 mul, div; if (!rc6->supported) return 0; - /* - * Store previous hw counter values for counter wrap-around handling. - * - * There are only four interesting registers and they live next to each - * other so we can use the relative address, compared to the smallest - * one as the index into driver storage. - */ - i = (i915_mmio_reg_offset(reg) - - i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32); - if (drm_WARN_ON_ONCE(&i915->drm, i >= ARRAY_SIZE(rc6->cur_residency))) - return 0; - fw_domains = intel_uncore_forcewake_for_reg(uncore, reg, FW_REG_READ); spin_lock_irqsave(&uncore->lock, flags); @@ -789,11 +796,11 @@ u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) /* * Counter wrap handling. * - * But relying on a sufficient frequency of queries otherwise counters - * can still wrap. + * Store previous hw counter values for counter wrap-around handling. But + * relying on a sufficient frequency of queries otherwise counters can still wrap. */ - prev_hw = rc6->prev_hw_residency[i]; - rc6->prev_hw_residency[i] = time_hw; + prev_hw = rc6->prev_hw_residency[id]; + rc6->prev_hw_residency[id] = time_hw; /* RC6 delta from last sample. */ if (time_hw >= prev_hw) @@ -802,8 +809,8 @@ u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) time_hw += overflow_hw - prev_hw; /* Add delta to RC6 extended raw driver copy. */ - time_hw += rc6->cur_residency[i]; - rc6->cur_residency[i] = time_hw; + time_hw += rc6->cur_residency[id]; + rc6->cur_residency[id] = time_hw; intel_uncore_forcewake_put__locked(uncore, fw_domains); spin_unlock_irqrestore(&uncore->lock, flags); @@ -811,9 +818,22 @@ u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg) return mul_u64_u32_div(time_hw, mul, div); } -u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg) +u64 intel_rc6_residency_us(struct intel_rc6 *rc6, enum intel_rc6_res_type id) +{ + return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, id), 1000); +} + +void intel_rc6_print_residency(struct seq_file *m, const char *title, + enum intel_rc6_res_type id) { - return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000); + struct intel_gt *gt = m->private; + i915_reg_t reg = gt->rc6.res_reg[id]; + intel_wakeref_t wakeref; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + seq_printf(m, "%s %u (%llu us)\n", title, + intel_uncore_read(gt->uncore, reg), + intel_rc6_residency_us(>->rc6, id)); } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.h b/drivers/gpu/drm/i915/gt/intel_rc6.h index b6fea71afc22..456fa668a276 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.h +++ b/drivers/gpu/drm/i915/gt/intel_rc6.h @@ -6,10 +6,11 @@ #ifndef INTEL_RC6_H #define INTEL_RC6_H -#include "i915_reg_defs.h" +#include <linux/types.h> -struct intel_engine_cs; +enum intel_rc6_res_type; struct intel_rc6; +struct seq_file; void intel_rc6_init(struct intel_rc6 *rc6); void intel_rc6_fini(struct intel_rc6 *rc6); @@ -21,7 +22,9 @@ void intel_rc6_sanitize(struct intel_rc6 *rc6); void intel_rc6_enable(struct intel_rc6 *rc6); void intel_rc6_disable(struct intel_rc6 *rc6); -u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, i915_reg_t reg); -u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg); +u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, enum intel_rc6_res_type id); +u64 intel_rc6_residency_us(struct intel_rc6 *rc6, enum intel_rc6_res_type id); +void intel_rc6_print_residency(struct seq_file *m, const char *title, + enum intel_rc6_res_type id); #endif /* INTEL_RC6_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_rc6_types.h b/drivers/gpu/drm/i915/gt/intel_rc6_types.h index e747492b2f46..fa23c4dce00b 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6_types.h +++ b/drivers/gpu/drm/i915/gt/intel_rc6_types.h @@ -13,9 +13,20 @@ struct drm_i915_gem_object; +/* RC6 residency types */ +enum intel_rc6_res_type { + INTEL_RC6_RES_RC6_LOCKED, + INTEL_RC6_RES_RC6, + INTEL_RC6_RES_RC6p, + INTEL_RC6_RES_RC6pp, + INTEL_RC6_RES_MAX, + INTEL_RC6_RES_VLV_MEDIA = INTEL_RC6_RES_RC6p, +}; + struct intel_rc6 { - u64 prev_hw_residency[4]; - u64 cur_residency[4]; + i915_reg_t res_reg[INTEL_RC6_RES_MAX]; + u64 prev_hw_residency[INTEL_RC6_RES_MAX]; + u64 cur_residency[INTEL_RC6_RES_MAX]; u32 ctl_enable; diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c index 5121e6dc2fa5..9c1ae070ee7b 100644 --- a/drivers/gpu/drm/i915/gt/intel_renderstate.c +++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c @@ -215,9 +215,7 @@ int intel_renderstate_emit(struct intel_renderstate *so, if (!so->vma) return 0; - err = i915_request_await_object(rq, so->vma->obj, false); - if (err == 0) - err = i915_vma_move_to_active(so->vma, rq, 0); + err = i915_vma_move_to_active(so->vma, rq, 0); if (err) return err; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 3159df6cdd49..24736ebee17c 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1407,15 +1407,19 @@ out: intel_runtime_pm_put(gt->uncore->rpm, wakeref); } -int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu) +static int _intel_gt_reset_lock(struct intel_gt *gt, int *srcu, bool retry) { might_lock(>->reset.backoff_srcu); - might_sleep(); + if (retry) + might_sleep(); rcu_read_lock(); while (test_bit(I915_RESET_BACKOFF, >->reset.flags)) { rcu_read_unlock(); + if (!retry) + return -EBUSY; + if (wait_event_interruptible(gt->reset.queue, !test_bit(I915_RESET_BACKOFF, >->reset.flags))) @@ -1429,6 +1433,16 @@ int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu) return 0; } +int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu) +{ + return _intel_gt_reset_lock(gt, srcu, false); +} + +int intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu) +{ + return _intel_gt_reset_lock(gt, srcu, true); +} + void intel_gt_reset_unlock(struct intel_gt *gt, int tag) __releases(>->reset.backoff_srcu) { diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index adc734e67387..25c975b6e8fc 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -39,6 +39,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, void __i915_request_reset(struct i915_request *rq, bool guilty); int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu); +int __must_check intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu); void intel_gt_reset_unlock(struct intel_gt *gt, int tag); void intel_gt_set_wedged(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 6c34a83c24b3..9ad3bc7201cb 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -430,7 +430,8 @@ static int __gen5_rps_set(struct intel_rps *rps, u8 val) rgvswctl = intel_uncore_read16(uncore, MEMSWCTL); if (rgvswctl & MEMCTL_CMD_STS) { - DRM_DEBUG("gpu busy, RCS change rejected\n"); + drm_dbg(&rps_to_i915(rps)->drm, + "gpu busy, RCS change rejected\n"); return -EBUSY; /* still busy with another command */ } @@ -1953,7 +1954,8 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir) intel_engine_cs_irq(gt->engine[VECS0], pm_iir >> 10); if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) - DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir); + drm_dbg(&rps_to_i915(rps)->drm, + "Command parser error, pm_iir 0x%08x\n", pm_iir); } void gen5_rps_irq_handler(struct intel_rps *rps) @@ -2072,22 +2074,45 @@ void intel_rps_sanitize(struct intel_rps *rps) rps_disable_interrupts(rps); } +u32 intel_rps_read_rpstat_fw(struct intel_rps *rps) +{ + struct drm_i915_private *i915 = rps_to_i915(rps); + i915_reg_t rpstat; + + rpstat = (GRAPHICS_VER(i915) >= 12) ? GEN12_RPSTAT1 : GEN6_RPSTAT1; + + return intel_uncore_read_fw(rps_to_gt(rps)->uncore, rpstat); +} + +u32 intel_rps_read_rpstat(struct intel_rps *rps) +{ + struct drm_i915_private *i915 = rps_to_i915(rps); + i915_reg_t rpstat; + + rpstat = (GRAPHICS_VER(i915) >= 12) ? GEN12_RPSTAT1 : GEN6_RPSTAT1; + + return intel_uncore_read(rps_to_gt(rps)->uncore, rpstat); +} + u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat) { struct drm_i915_private *i915 = rps_to_i915(rps); u32 cagf; - if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) - cagf = (rpstat >> 8) & 0xff; + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + cagf = REG_FIELD_GET(MTL_CAGF_MASK, rpstat); + else if (GRAPHICS_VER(i915) >= 12) + cagf = REG_FIELD_GET(GEN12_CAGF_MASK, rpstat); + else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) + cagf = REG_FIELD_GET(RPE_MASK, rpstat); else if (GRAPHICS_VER(i915) >= 9) - cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT; + cagf = REG_FIELD_GET(GEN9_CAGF_MASK, rpstat); else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) - cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT; + cagf = REG_FIELD_GET(HSW_CAGF_MASK, rpstat); else if (GRAPHICS_VER(i915) >= 6) - cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT; + cagf = REG_FIELD_GET(GEN6_CAGF_MASK, rpstat); else - cagf = gen5_invert_freq(rps, (rpstat & MEMSTAT_PSTATE_MASK) >> - MEMSTAT_PSTATE_SHIFT); + cagf = gen5_invert_freq(rps, REG_FIELD_GET(MEMSTAT_PSTATE_MASK, rpstat)); return cagf; } @@ -2098,7 +2123,15 @@ static u32 read_cagf(struct intel_rps *rps) struct intel_uncore *uncore = rps_to_uncore(rps); u32 freq; - if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { + /* + * For Gen12+ reading freq from HW does not need a forcewake and + * registers will return 0 freq when GT is in RC6 + */ + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) { + freq = intel_uncore_read(uncore, MTL_MIRROR_TARGET_WP1); + } else if (GRAPHICS_VER(i915) >= 12) { + freq = intel_uncore_read(uncore, GEN12_RPSTAT1); + } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { vlv_punit_get(i915); freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS); vlv_punit_put(i915); @@ -2264,7 +2297,7 @@ static void rps_frequency_dump(struct intel_rps *rps, struct drm_printer *p) rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD); rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD); - rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1); + rpstat = intel_rps_read_rpstat(rps); rpcurupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK; rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK; rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK; @@ -2399,7 +2432,7 @@ static void slpc_frequency_dump(struct intel_rps *rps, struct drm_printer *p) drm_printf(p, "PM MASK=0x%08x\n", pm_mask); drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n", rps->pm_intrmsk_mbz); - drm_printf(p, "RPSTAT1: 0x%08x\n", intel_uncore_read(uncore, GEN6_RPSTAT1)); + drm_printf(p, "RPSTAT1: 0x%08x\n", intel_rps_read_rpstat(rps)); drm_printf(p, "RPNSWREQ: %dMHz\n", intel_rps_get_requested_frequency(rps)); drm_printf(p, "Lowest (RPN) frequency: %dMHz\n", intel_gpu_freq(rps, caps.min_freq)); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h index 110300dfd438..9e1cad9ba0e9 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -48,6 +48,8 @@ u32 intel_rps_get_rp1_frequency(struct intel_rps *rps); u32 intel_rps_get_rpn_frequency(struct intel_rps *rps); u32 intel_rps_read_punit_req(struct intel_rps *rps); u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps); +u32 intel_rps_read_rpstat(struct intel_rps *rps); +u32 intel_rps_read_rpstat_fw(struct intel_rps *rps); void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps); void intel_rps_raise_unslice(struct intel_rps *rps); void intel_rps_lower_unslice(struct intel_rps *rps); diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/gt/intel_wopcm.c index 322fb9eeb880..7ebbcc191c2d 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.c +++ b/drivers/gpu/drm/i915/gt/intel_wopcm.c @@ -64,9 +64,9 @@ #define GEN9_GUC_FW_RESERVED SZ_128K #define GEN9_GUC_WOPCM_OFFSET (GUC_WOPCM_RESERVED + GEN9_GUC_FW_RESERVED) -static inline struct drm_i915_private *wopcm_to_i915(struct intel_wopcm *wopcm) +static inline struct intel_gt *wopcm_to_gt(struct intel_wopcm *wopcm) { - return container_of(wopcm, struct drm_i915_private, wopcm); + return container_of(wopcm, struct intel_gt, wopcm); } /** @@ -77,7 +77,8 @@ static inline struct drm_i915_private *wopcm_to_i915(struct intel_wopcm *wopcm) */ void intel_wopcm_init_early(struct intel_wopcm *wopcm) { - struct drm_i915_private *i915 = wopcm_to_i915(wopcm); + struct intel_gt *gt = wopcm_to_gt(wopcm); + struct drm_i915_private *i915 = gt->i915; if (!HAS_GT_UC(i915)) return; @@ -157,10 +158,11 @@ static bool check_hw_restrictions(struct drm_i915_private *i915, return true; } -static bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size, +static bool __check_layout(struct intel_gt *gt, u32 wopcm_size, u32 guc_wopcm_base, u32 guc_wopcm_size, u32 guc_fw_size, u32 huc_fw_size) { + struct drm_i915_private *i915 = gt->i915; const u32 ctx_rsvd = context_reserved_size(i915); u32 size; @@ -181,12 +183,14 @@ static bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size, return false; } - size = huc_fw_size + WOPCM_RESERVED_SIZE; - if (unlikely(guc_wopcm_base < size)) { - drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n", - intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), - guc_wopcm_base / SZ_1K, size / SZ_1K); - return false; + if (intel_uc_supports_huc(>->uc)) { + size = huc_fw_size + WOPCM_RESERVED_SIZE; + if (unlikely(guc_wopcm_base < size)) { + drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n", + intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), + guc_wopcm_base / SZ_1K, size / SZ_1K); + return false; + } } return check_hw_restrictions(i915, guc_wopcm_base, guc_wopcm_size, @@ -228,8 +232,8 @@ static bool __wopcm_regs_writable(struct intel_uncore *uncore) */ void intel_wopcm_init(struct intel_wopcm *wopcm) { - struct drm_i915_private *i915 = wopcm_to_i915(wopcm); - struct intel_gt *gt = to_gt(i915); + struct intel_gt *gt = wopcm_to_gt(wopcm); + struct drm_i915_private *i915 = gt->i915; u32 guc_fw_size = intel_uc_fw_get_upload_size(>->uc.guc.fw); u32 huc_fw_size = intel_uc_fw_get_upload_size(>->uc.huc.fw); u32 ctx_rsvd = context_reserved_size(i915); @@ -275,6 +279,19 @@ void intel_wopcm_init(struct intel_wopcm *wopcm) } /* + * On platforms with a media GT, the WOPCM is partitioned between the + * two GTs, so we would have to take that into account when doing the + * math below. There is also a new section reserved for the GSC context + * that would have to be factored in. However, all platforms with a + * media GT also have GuC depriv enabled, so the WOPCM regs are + * pre-locked and therefore we don't have to do the math ourselves. + */ + if (unlikely(i915->media_gt)) { + drm_err(&i915->drm, "Unlocked WOPCM regs with media GT\n"); + return; + } + + /* * Aligned value of guc_wopcm_base will determine available WOPCM space * for HuC firmware and mandatory reserved area. */ @@ -295,7 +312,7 @@ void intel_wopcm_init(struct intel_wopcm *wopcm) guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K); check: - if (__check_layout(i915, wopcm_size, guc_wopcm_base, guc_wopcm_size, + if (__check_layout(gt, wopcm_size, guc_wopcm_base, guc_wopcm_size, guc_fw_size, huc_fw_size)) { wopcm->guc.base = guc_wopcm_base; wopcm->guc.size = guc_wopcm_size; diff --git a/drivers/gpu/drm/i915/intel_wopcm.h b/drivers/gpu/drm/i915/gt/intel_wopcm.h index 17d6aa86008a..17d6aa86008a 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.h +++ b/drivers/gpu/drm/i915/gt/intel_wopcm.h diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index ffc80d2e9952..2afb4f80a954 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -18,46 +18,68 @@ /** * DOC: Hardware workarounds * - * This file is intended as a central place to implement most [1]_ of the - * required workarounds for hardware to work as originally intended. They fall - * in five basic categories depending on how/when they are applied: + * Hardware workarounds are register programming documented to be executed in + * the driver that fall outside of the normal programming sequences for a + * platform. There are some basic categories of workarounds, depending on + * how/when they are applied: * - * - Workarounds that touch registers that are saved/restored to/from the HW - * context image. The list is emitted (via Load Register Immediate commands) - * everytime a new context is created. - * - GT workarounds. The list of these WAs is applied whenever these registers - * revert to default values (on GPU reset, suspend/resume [2]_, etc..). - * - Display workarounds. The list is applied during display clock-gating - * initialization. - * - Workarounds that whitelist a privileged register, so that UMDs can manage - * them directly. This is just a special case of a MMMIO workaround (as we - * write the list of these to/be-whitelisted registers to some special HW - * registers). - * - Workaround batchbuffers, that get executed automatically by the hardware - * on every HW context restore. + * - Context workarounds: workarounds that touch registers that are + * saved/restored to/from the HW context image. The list is emitted (via Load + * Register Immediate commands) once when initializing the device and saved in + * the default context. That default context is then used on every context + * creation to have a "primed golden context", i.e. a context image that + * already contains the changes needed to all the registers. * - * .. [1] Please notice that there are other WAs that, due to their nature, - * cannot be applied from a central place. Those are peppered around the rest - * of the code, as needed. + * - Engine workarounds: the list of these WAs is applied whenever the specific + * engine is reset. It's also possible that a set of engine classes share a + * common power domain and they are reset together. This happens on some + * platforms with render and compute engines. In this case (at least) one of + * them need to keeep the workaround programming: the approach taken in the + * driver is to tie those workarounds to the first compute/render engine that + * is registered. When executing with GuC submission, engine resets are + * outside of kernel driver control, hence the list of registers involved in + * written once, on engine initialization, and then passed to GuC, that + * saves/restores their values before/after the reset takes place. See + * ``drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c`` for reference. * - * .. [2] Technically, some registers are powercontext saved & restored, so they - * survive a suspend/resume. In practice, writing them again is not too - * costly and simplifies things. We can revisit this in the future. + * - GT workarounds: the list of these WAs is applied whenever these registers + * revert to their default values: on GPU reset, suspend/resume [1]_, etc. + * + * - Register whitelist: some workarounds need to be implemented in userspace, + * but need to touch privileged registers. The whitelist in the kernel + * instructs the hardware to allow the access to happen. From the kernel side, + * this is just a special case of a MMIO workaround (as we write the list of + * these to/be-whitelisted registers to some special HW registers). + * + * - Workaround batchbuffers: buffers that get executed automatically by the + * hardware on every HW context restore. These buffers are created and + * programmed in the default context so the hardware always go through those + * programming sequences when switching contexts. The support for workaround + * batchbuffers is enabled these hardware mechanisms: * - * Layout - * ~~~~~~ + * #. INDIRECT_CTX: A batchbuffer and an offset are provided in the default + * context, pointing the hardware to jump to that location when that offset + * is reached in the context restore. Workaround batchbuffer in the driver + * currently uses this mechanism for all platforms. * - * Keep things in this file ordered by WA type, as per the above (context, GT, - * display, register whitelist, batchbuffer). Then, inside each type, keep the - * following order: + * #. BB_PER_CTX_PTR: A batchbuffer is provided in the default context, + * pointing the hardware to a buffer to continue executing after the + * engine registers are restored in a context restore sequence. This is + * currently not used in the driver. * - * - Infrastructure functions and macros - * - WAs per platform in standard gen/chrono order - * - Public functions to init or apply the given workaround type. + * - Other: There are WAs that, due to their nature, cannot be applied from a + * central place. Those are peppered around the rest of the code, as needed. + * Workarounds related to the display IP are the main example. + * + * .. [1] Technically, some registers are powercontext saved & restored, so they + * survive a suspend/resume. In practice, writing them again is not too + * costly and simplifies things, so it's the approach taken in the driver. */ -static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name) +static void wa_init_start(struct i915_wa_list *wal, struct intel_gt *gt, + const char *name, const char *engine_name) { + wal->gt = gt; wal->name = name; wal->engine_name = engine_name; } @@ -81,13 +103,14 @@ static void wa_init_finish(struct i915_wa_list *wal) if (!wal->count) return; - DRM_DEBUG_DRIVER("Initialized %u %s workarounds on %s\n", - wal->wa_count, wal->name, wal->engine_name); + drm_dbg(&wal->gt->i915->drm, "Initialized %u %s workarounds on %s\n", + wal->wa_count, wal->name, wal->engine_name); } static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) { unsigned int addr = i915_mmio_reg_offset(wa->reg); + struct drm_i915_private *i915 = wal->gt->i915; unsigned int start = 0, end = wal->count; const unsigned int grow = WA_LIST_CHUNK; struct i915_wa *wa_; @@ -100,7 +123,7 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa), GFP_KERNEL); if (!list) { - DRM_ERROR("No space for workaround init!\n"); + drm_err(&i915->drm, "No space for workaround init!\n"); return; } @@ -123,9 +146,10 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) wa_ = &wal->list[mid]; if ((wa->clr | wa_->clr) && !(wa->clr & ~wa_->clr)) { - DRM_ERROR("Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n", - i915_mmio_reg_offset(wa_->reg), - wa_->clr, wa_->set); + drm_err(&i915->drm, + "Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n", + i915_mmio_reg_offset(wa_->reg), + wa_->clr, wa_->set); wa_->set &= ~wa->clr; } @@ -827,7 +851,7 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, { struct drm_i915_private *i915 = engine->i915; - wa_init_start(wal, name, engine->name); + wa_init_start(wal, engine->gt, name, engine->name); /* Applies to all engines */ /* @@ -1677,7 +1701,7 @@ void intel_gt_init_workarounds(struct intel_gt *gt) { struct i915_wa_list *wal = >->wa_list; - wa_init_start(wal, "GT", "global"); + wa_init_start(wal, gt, "GT", "global"); gt_init_workarounds(gt, wal); wa_init_finish(wal); } @@ -1699,12 +1723,14 @@ wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal) } static bool -wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from) +wa_verify(struct intel_gt *gt, const struct i915_wa *wa, u32 cur, + const char *name, const char *from) { if ((cur ^ wa->set) & wa->read) { - DRM_ERROR("%s workaround lost on %s! (reg[%x]=0x%x, relevant bits were 0x%x vs expected 0x%x)\n", - name, from, i915_mmio_reg_offset(wa->reg), - cur, cur & wa->read, wa->set & wa->read); + drm_err(>->i915->drm, + "%s workaround lost on %s! (reg[%x]=0x%x, relevant bits were 0x%x vs expected 0x%x)\n", + name, from, i915_mmio_reg_offset(wa->reg), + cur, cur & wa->read, wa->set & wa->read); return false; } @@ -1712,9 +1738,9 @@ wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from) return true; } -static void -wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) +static void wa_list_apply(const struct i915_wa_list *wal) { + struct intel_gt *gt = wal->gt; struct intel_uncore *uncore = gt->uncore; enum forcewake_domains fw; unsigned long flags; @@ -1750,7 +1776,7 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : intel_uncore_read_fw(uncore, wa->reg); - wa_verify(wa, val, wal->name, "application"); + wa_verify(gt, wa, val, wal->name, "application"); } } @@ -1760,7 +1786,7 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) void intel_gt_apply_workarounds(struct intel_gt *gt) { - wa_list_apply(gt, >->wa_list); + wa_list_apply(>->wa_list); } static bool wa_list_verify(struct intel_gt *gt, @@ -1780,7 +1806,7 @@ static bool wa_list_verify(struct intel_gt *gt, intel_uncore_forcewake_get__locked(uncore, fw); for (i = 0, wa = wal->list; i < wal->count; i++, wa++) - ok &= wa_verify(wa, wa->is_mcr ? + ok &= wa_verify(wal->gt, wa, wa->is_mcr ? intel_gt_mcr_read_any_fw(gt, wa->mcr_reg) : intel_uncore_read_fw(uncore, wa->reg), wal->name, from); @@ -2128,7 +2154,7 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) struct drm_i915_private *i915 = engine->i915; struct i915_wa_list *w = &engine->whitelist; - wa_init_start(w, "whitelist", engine->name); + wa_init_start(w, engine->gt, "whitelist", engine->name); if (IS_PONTEVECCHIO(i915)) pvc_whitelist_build(engine); @@ -2985,7 +3011,7 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li static void engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal) { - if (I915_SELFTEST_ONLY(GRAPHICS_VER(engine->i915) < 4)) + if (GRAPHICS_VER(engine->i915) < 4) return; engine_fake_wa_init(engine, wal); @@ -3010,17 +3036,14 @@ void intel_engine_init_workarounds(struct intel_engine_cs *engine) { struct i915_wa_list *wal = &engine->wa_list; - if (GRAPHICS_VER(engine->i915) < 4) - return; - - wa_init_start(wal, "engine", engine->name); + wa_init_start(wal, engine->gt, "engine", engine->name); engine_init_workarounds(engine, wal); wa_init_finish(wal); } void intel_engine_apply_workarounds(struct intel_engine_cs *engine) { - wa_list_apply(engine->gt, &engine->wa_list); + wa_list_apply(&engine->wa_list); } static const struct i915_range mcr_ranges_gen8[] = { @@ -3164,9 +3187,7 @@ retry: goto err_vma; } - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); if (err == 0) err = wa_list_srm(rq, wal, vma); @@ -3194,7 +3215,7 @@ retry: if (mcr_range(rq->engine->i915, i915_mmio_reg_offset(wa->reg))) continue; - if (!wa_verify(wa, results[i], wal->name, from)) + if (!wa_verify(wal->gt, wa, results[i], wal->name, from)) err = -ENXIO; } diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h index 7c8b01d00043..e14188120e66 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h +++ b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h @@ -10,6 +10,8 @@ #include "i915_reg_defs.h" +struct intel_gt; + struct i915_wa { union { i915_reg_t reg; @@ -24,6 +26,7 @@ struct i915_wa { }; struct i915_wa_list { + struct intel_gt *gt; const char *name; const char *engine_name; struct i915_wa *list; diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c index 0dcb3ed44a73..87c94314cf67 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c @@ -317,7 +317,7 @@ static int live_engine_busy_stats(void *arg) ENGINE_TRACE(engine, "measuring busy time\n"); preempt_disable(); de = intel_engine_get_busy_time(engine, &t[0]); - mdelay(10); + mdelay(100); de = ktime_sub(intel_engine_get_busy_time(engine, &t[1]), de); preempt_enable(); dt = ktime_sub(t[1], t[0]); diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 2c7c053a8808..ab2e9a6a2452 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -2764,9 +2764,7 @@ static int create_gang(struct intel_engine_cs *engine, i915_request_get(rq); i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, @@ -3180,15 +3178,11 @@ create_gpr_client(struct intel_engine_cs *engine, } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); i915_vma_unlock(vma); i915_vma_lock(batch); if (!err) - err = i915_request_await_object(rq, batch->obj, false); - if (!err) err = i915_vma_move_to_active(batch, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, @@ -3521,9 +3515,7 @@ static int smoke_submit(struct preempt_smoke *smoke, if (vma) { i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 71263058a7b0..bc05ef48c194 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -99,22 +99,6 @@ static u64 hws_address(const struct i915_vma *hws, return hws->node.start + offset_in_page(sizeof(u32)*rq->fence.context); } -static int move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, - flags & EXEC_OBJECT_WRITE); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - static struct i915_request * hang_create_request(struct hang *h, struct intel_engine_cs *engine) { @@ -175,11 +159,11 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine) goto unpin_hws; } - err = move_to_active(vma, rq, 0); + err = igt_vma_move_to_active_unlocked(vma, rq, 0); if (err) goto cancel_rq; - err = move_to_active(hws, rq, 0); + err = igt_vma_move_to_active_unlocked(hws, rq, 0); if (err) goto cancel_rq; @@ -1519,18 +1503,9 @@ static int __igt_reset_evict_vma(struct intel_gt *gt, } } - i915_vma_lock(arg.vma); - err = i915_request_await_object(rq, arg.vma->obj, - flags & EXEC_OBJECT_WRITE); - if (err == 0) { - err = i915_vma_move_to_active(arg.vma, rq, flags); - if (err) - pr_err("[%s] Move to active failed: %d!\n", engine->name, err); - } else { - pr_err("[%s] Request await failed: %d!\n", engine->name, err); - } - - i915_vma_unlock(arg.vma); + err = igt_vma_move_to_active_unlocked(arg.vma, rq, flags); + if (err) + pr_err("[%s] Move to active failed: %d!\n", engine->name, err); if (flags & EXEC_OBJECT_NEEDS_FENCE) i915_vma_unpin_fence(arg.vma); diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 82d3f8058995..7c56ffd2c659 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -452,9 +452,7 @@ retry: *cs++ = i915_ggtt_offset(scratch) + RING_TAIL_IDX * sizeof(u32); *cs++ = 0; - err = i915_request_await_object(rq, scratch->obj, true); - if (!err) - err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); i915_request_get(rq); i915_request_add(rq); @@ -602,9 +600,7 @@ __gpr_read(struct intel_context *ce, struct i915_vma *scratch, u32 *slot) } i915_vma_lock(scratch); - err = i915_request_await_object(rq, scratch->obj, true); - if (!err) - err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(scratch); i915_request_get(rq); @@ -1053,21 +1049,6 @@ store_context(struct intel_context *ce, struct i915_vma *scratch) return batch; } -static int move_to_active(struct i915_request *rq, - struct i915_vma *vma, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, flags); - if (!err) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - static struct i915_request * record_registers(struct intel_context *ce, struct i915_vma *before, @@ -1093,19 +1074,19 @@ record_registers(struct intel_context *ce, if (IS_ERR(rq)) goto err_after; - err = move_to_active(rq, before, EXEC_OBJECT_WRITE); + err = igt_vma_move_to_active_unlocked(before, rq, EXEC_OBJECT_WRITE); if (err) goto err_rq; - err = move_to_active(rq, b_before, 0); + err = igt_vma_move_to_active_unlocked(b_before, rq, 0); if (err) goto err_rq; - err = move_to_active(rq, after, EXEC_OBJECT_WRITE); + err = igt_vma_move_to_active_unlocked(after, rq, EXEC_OBJECT_WRITE); if (err) goto err_rq; - err = move_to_active(rq, b_after, 0); + err = igt_vma_move_to_active_unlocked(b_after, rq, 0); if (err) goto err_rq; @@ -1243,7 +1224,7 @@ static int poison_registers(struct intel_context *ce, u32 poison, u32 *sema) goto err_batch; } - err = move_to_active(rq, batch, 0); + err = igt_vma_move_to_active_unlocked(batch, rq, 0); if (err) goto err_rq; diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c index c1d861333c44..f27cc28608d4 100644 --- a/drivers/gpu/drm/i915/gt/selftest_mocs.c +++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c @@ -7,6 +7,7 @@ #include "gt/intel_gpu_commands.h" #include "i915_selftest.h" +#include "gem/selftests/igt_gem_utils.h" #include "gem/selftests/mock_context.h" #include "selftests/igt_reset.h" #include "selftests/igt_spinner.h" @@ -228,9 +229,7 @@ static int check_mocs_engine(struct live_mocs *arg, return PTR_ERR(rq); i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (!err) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); /* Read the mocs tables back using SRM */ diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c index 8c70b7e12074..2ceeadecc639 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rc6.c +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c @@ -19,11 +19,11 @@ static u64 rc6_residency(struct intel_rc6 *rc6) /* XXX VLV_GT_MEDIA_RC6? */ - result = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6); + result = intel_rc6_residency_ns(rc6, INTEL_RC6_RES_RC6); if (HAS_RC6p(rc6_to_i915(rc6))) - result += intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6p); + result += intel_rc6_residency_ns(rc6, INTEL_RC6_RES_RC6p); if (HAS_RC6pp(rc6_to_i915(rc6))) - result += intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6pp); + result += intel_rc6_residency_ns(rc6, INTEL_RC6_RES_RC6pp); return result; } diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c index 99a372486fb7..39f1b7564170 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rps.c +++ b/drivers/gpu/drm/i915/gt/selftest_rps.c @@ -652,9 +652,7 @@ int live_rps_frequency_cs(void *arg) goto err_vma; } - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, @@ -793,9 +791,7 @@ int live_rps_frequency_srm(void *arg) goto err_vma; } - err = i915_request_await_object(rq, vma->obj, false); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, vma->node.start, diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c index 82ec95a299f6..bd44ce73a504 100644 --- a/drivers/gpu/drm/i915/gt/selftest_slpc.c +++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c @@ -13,6 +13,14 @@ enum test_type { VARY_MAX, MAX_GRANTED, SLPC_POWER, + TILE_INTERACTION, +}; + +struct slpc_thread { + struct kthread_worker *worker; + struct kthread_work work; + struct intel_gt *gt; + int result; }; static int slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 freq) @@ -212,7 +220,8 @@ static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, *max_act_freq = intel_rps_read_actual_frequency(rps); if (*max_act_freq != slpc->rp0_freq) { /* Check if there was some throttling by pcode */ - perf_limit_reasons = intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS); + perf_limit_reasons = intel_uncore_read(gt->uncore, + intel_gt_perf_limit_reasons_reg(gt)); /* If not, this is an error */ if (!(perf_limit_reasons & GT0_PERF_LIMIT_REASONS_MASK)) { @@ -310,9 +319,10 @@ static int run_test(struct intel_gt *gt, int test_type) break; case MAX_GRANTED: + case TILE_INTERACTION: /* Media engines have a different RP0 */ - if (engine->class == VIDEO_DECODE_CLASS || - engine->class == VIDEO_ENHANCEMENT_CLASS) { + if (gt->type != GT_MEDIA && (engine->class == VIDEO_DECODE_CLASS || + engine->class == VIDEO_ENHANCEMENT_CLASS)) { igt_spinner_end(&spin); st_engine_heartbeat_enable(engine); err = 0; @@ -335,7 +345,8 @@ static int run_test(struct intel_gt *gt, int test_type) if (max_act_freq <= slpc->min_freq) { pr_err("Actual freq did not rise above min\n"); pr_err("Perf Limit Reasons: 0x%x\n", - intel_uncore_read(gt->uncore, GT0_PERF_LIMIT_REASONS)); + intel_uncore_read(gt->uncore, + intel_gt_perf_limit_reasons_reg(gt))); err = -EINVAL; } } @@ -426,6 +437,56 @@ static int live_slpc_power(void *arg) return ret; } +static void slpc_spinner_thread(struct kthread_work *work) +{ + struct slpc_thread *thread = container_of(work, typeof(*thread), work); + + thread->result = run_test(thread->gt, TILE_INTERACTION); +} + +static int live_slpc_tile_interaction(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_gt *gt; + struct slpc_thread *threads; + int i = 0, ret = 0; + + threads = kcalloc(I915_MAX_GT, sizeof(*threads), GFP_KERNEL); + if (!threads) + return -ENOMEM; + + for_each_gt(gt, i915, i) { + threads[i].worker = kthread_create_worker(0, "igt/slpc_parallel:%d", gt->info.id); + + if (IS_ERR(threads[i].worker)) { + ret = PTR_ERR(threads[i].worker); + break; + } + + threads[i].gt = gt; + kthread_init_work(&threads[i].work, slpc_spinner_thread); + kthread_queue_work(threads[i].worker, &threads[i].work); + } + + for_each_gt(gt, i915, i) { + int status; + + if (IS_ERR_OR_NULL(threads[i].worker)) + continue; + + kthread_flush_work(&threads[i].work); + status = READ_ONCE(threads[i].result); + if (status && !ret) { + pr_err("%s GT %d failed ", __func__, gt->info.id); + ret = status; + } + kthread_destroy_worker(threads[i].worker); + } + + kfree(threads); + return ret; +} + int intel_slpc_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { @@ -433,6 +494,7 @@ int intel_slpc_live_selftests(struct drm_i915_private *i915) SUBTEST(live_slpc_vary_min), SUBTEST(live_slpc_max_granted), SUBTEST(live_slpc_power), + SUBTEST(live_slpc_tile_interaction), }; struct intel_gt *gt; diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c index 21b1edc052f8..96e3861706d6 100644 --- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c +++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c @@ -66,14 +66,14 @@ reference_lists_init(struct intel_gt *gt, struct wa_lists *lists) memset(lists, 0, sizeof(*lists)); - wa_init_start(&lists->gt_wa_list, "GT_REF", "global"); + wa_init_start(&lists->gt_wa_list, gt, "GT_REF", "global"); gt_init_workarounds(gt, &lists->gt_wa_list); wa_init_finish(&lists->gt_wa_list); for_each_engine(engine, gt, id) { struct i915_wa_list *wal = &lists->engine[id].wa_list; - wa_init_start(wal, "REF", engine->name); + wa_init_start(wal, gt, "REF", engine->name); engine_init_workarounds(engine, wal); wa_init_finish(wal); @@ -139,9 +139,7 @@ read_nonprivs(struct intel_context *ce) } i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, true); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(vma); if (err) goto err_req; @@ -632,16 +630,12 @@ retry: goto err_request; } - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); if (err) goto err_request; - err = i915_request_await_object(rq, scratch->obj, true); - if (err == 0) - err = i915_vma_move_to_active(scratch, rq, - EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(scratch, rq, + EXEC_OBJECT_WRITE); if (err) goto err_request; @@ -860,9 +854,7 @@ static int read_whitelisted_registers(struct intel_context *ce, return PTR_ERR(rq); i915_vma_lock(results); - err = i915_request_await_object(rq, results->obj, true); - if (err == 0) - err = i915_vma_move_to_active(results, rq, EXEC_OBJECT_WRITE); + err = i915_vma_move_to_active(results, rq, EXEC_OBJECT_WRITE); i915_vma_unlock(results); if (err) goto err_req; @@ -944,9 +936,7 @@ static int scrub_whitelisted_registers(struct intel_context *ce) } i915_vma_lock(batch); - err = i915_request_await_object(rq, batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, rq, 0); + err = i915_vma_move_to_active(batch, rq, 0); i915_vma_unlock(batch); if (err) goto err_request; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 27b09ba1d295..52aede324788 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -98,6 +98,8 @@ static void gen9_enable_guc_interrupts(struct intel_guc *guc) gt->pm_guc_events); gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); spin_unlock_irq(gt->irq_lock); + + guc->interrupts.enabled = true; } static void gen9_disable_guc_interrupts(struct intel_guc *guc) @@ -105,6 +107,7 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) struct intel_gt *gt = guc_to_gt(guc); assert_rpm_wakelock_held(>->i915->runtime_pm); + guc->interrupts.enabled = false; spin_lock_irq(gt->irq_lock); @@ -116,39 +119,39 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) gen9_reset_guc_interrupts(guc); } +static bool __gen11_reset_guc_interrupts(struct intel_gt *gt) +{ + u32 irq = gt->type == GT_MEDIA ? MTL_MGUC : GEN11_GUC; + + lockdep_assert_held(gt->irq_lock); + return gen11_gt_reset_one_iir(gt, 0, irq); +} + static void gen11_reset_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); spin_lock_irq(gt->irq_lock); - gen11_gt_reset_one_iir(gt, 0, GEN11_GUC); + __gen11_reset_guc_interrupts(gt); spin_unlock_irq(gt->irq_lock); } static void gen11_enable_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); spin_lock_irq(gt->irq_lock); - WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); - intel_uncore_write(gt->uncore, - GEN11_GUC_SG_INTR_ENABLE, events); - intel_uncore_write(gt->uncore, - GEN11_GUC_SG_INTR_MASK, ~events); + __gen11_reset_guc_interrupts(gt); spin_unlock_irq(gt->irq_lock); + + guc->interrupts.enabled = true; } static void gen11_disable_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - spin_lock_irq(gt->irq_lock); - - intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0); - intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0); - - spin_unlock_irq(gt->irq_lock); + guc->interrupts.enabled = false; intel_synchronize_irq(gt->i915); gen11_reset_guc_interrupts(guc); @@ -156,7 +159,8 @@ static void gen11_disable_guc_interrupts(struct intel_guc *guc) void intel_guc_init_early(struct intel_guc *guc) { - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; + struct intel_gt *gt = guc_to_gt(guc); + struct drm_i915_private *i915 = gt->i915; intel_uc_fw_init_early(&guc->fw, INTEL_UC_FW_TYPE_GUC); intel_guc_ct_init_early(&guc->ct); @@ -168,12 +172,17 @@ void intel_guc_init_early(struct intel_guc *guc) mutex_init(&guc->send_mutex); spin_lock_init(&guc->irq_lock); if (GRAPHICS_VER(i915) >= 11) { - guc->notify_reg = GEN11_GUC_HOST_INTERRUPT; guc->interrupts.reset = gen11_reset_guc_interrupts; guc->interrupts.enable = gen11_enable_guc_interrupts; guc->interrupts.disable = gen11_disable_guc_interrupts; - guc->send_regs.base = - i915_mmio_reg_offset(GEN11_SOFT_SCRATCH(0)); + if (gt->type == GT_MEDIA) { + guc->notify_reg = MEDIA_GUC_HOST_INTERRUPT; + guc->send_regs.base = i915_mmio_reg_offset(MEDIA_SOFT_SCRATCH(0)); + } else { + guc->notify_reg = GEN11_GUC_HOST_INTERRUPT; + guc->send_regs.base = i915_mmio_reg_offset(GEN11_SOFT_SCRATCH(0)); + } + guc->send_regs.count = GEN11_SOFT_SCRATCH_COUNT; } else { @@ -871,14 +880,14 @@ void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p) u32 status = intel_uncore_read(uncore, GUC_STATUS); u32 i; - drm_printf(p, "\nGuC status 0x%08x:\n", status); + drm_printf(p, "GuC status 0x%08x:\n", status); drm_printf(p, "\tBootrom status = 0x%x\n", (status & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT); drm_printf(p, "\tuKernel status = 0x%x\n", (status & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT); drm_printf(p, "\tMIA Core status = 0x%x\n", (status & GS_MIA_MASK) >> GS_MIA_SHIFT); - drm_puts(p, "\nScratch registers:\n"); + drm_puts(p, "Scratch registers:\n"); for (i = 0; i < 16; i++) { drm_printf(p, "\t%2d: \t0x%x\n", i, intel_uncore_read(uncore, SOFT_SCRATCH(i))); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 357873ef692b..1bb3f9829286 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -78,6 +78,7 @@ struct intel_guc { /** @interrupts: pointers to GuC interrupt-managing functions. */ struct { + bool enabled; void (*reset)(struct intel_guc *guc); void (*enable)(struct intel_guc *guc); void (*disable)(struct intel_guc *guc); @@ -330,9 +331,11 @@ retry: return err; } +/* Only call this from the interrupt handler code */ static inline void intel_guc_to_host_event_handler(struct intel_guc *guc) { - intel_guc_ct_event_handler(&guc->ct); + if (guc->interrupts.enabled) + intel_guc_ct_event_handler(&guc->ct); } /* GuC addresses above GUC_GGTT_TOP also don't map through the GTT */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c index a419d60166c8..a7f737c4792e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -488,6 +488,11 @@ static void fill_engine_enable_masks(struct intel_gt *gt, info_map_write(info_map, engine_enabled_masks[GUC_BLITTER_CLASS], BCS_MASK(gt)); info_map_write(info_map, engine_enabled_masks[GUC_VIDEO_CLASS], VDBOX_MASK(gt)); info_map_write(info_map, engine_enabled_masks[GUC_VIDEOENHANCE_CLASS], VEBOX_MASK(gt)); + + /* The GSC engine is an instance (6) of OTHER_CLASS */ + if (gt->engine[GSC0]) + info_map_write(info_map, engine_enabled_masks[GUC_GSC_OTHER_CLASS], + BIT(gt->engine[GSC0]->instance)); } #define LR_HW_CONTEXT_SIZE (80 * sizeof(u32)) @@ -529,9 +534,6 @@ static int guc_prep_golden_context(struct intel_guc *guc) } for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { - if (engine_class == OTHER_CLASS) - continue; - guc_class = engine_class_to_guc_class(engine_class); if (!info_map_read(&info_map, engine_enabled_masks[guc_class])) @@ -609,9 +611,6 @@ static void guc_init_golden_context(struct intel_guc *guc) addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { - if (engine_class == OTHER_CLASS) - continue; - guc_class = engine_class_to_guc_class(engine_class); if (!ads_blob_read(guc, system_info.engine_enabled_masks[guc_class])) continue; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c index 4e6dca707d94..1c1b85073b4b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c @@ -132,6 +132,11 @@ static const struct __guc_mmio_reg_descr xe_lpd_blt_inst_regs[] = { COMMON_BASE_ENGINE_INSTANCE, }; +/* XE_LPD - GSC Per-Engine-Instance */ +static const struct __guc_mmio_reg_descr xe_lpd_gsc_inst_regs[] = { + COMMON_BASE_ENGINE_INSTANCE, +}; + /* GEN9 - Global */ static const struct __guc_mmio_reg_descr default_global_regs[] = { COMMON_BASE_GLOBAL, @@ -165,7 +170,7 @@ static const struct __guc_mmio_reg_descr empty_regs_list[] = { } /* List of lists */ -static struct __guc_mmio_reg_descr_group default_lists[] = { +static const struct __guc_mmio_reg_descr_group default_lists[] = { MAKE_REGLIST(default_global_regs, PF, GLOBAL, 0), MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS), MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS), @@ -177,6 +182,8 @@ static struct __guc_mmio_reg_descr_group default_lists[] = { MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS), MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS), MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS), + MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_GSC_OTHER_CLASS), + MAKE_REGLIST(xe_lpd_gsc_inst_regs, PF, ENGINE_INSTANCE, GUC_GSC_OTHER_CLASS), {} }; @@ -192,6 +199,8 @@ static const struct __guc_mmio_reg_descr_group xe_lpd_lists[] = { MAKE_REGLIST(xe_lpd_vec_inst_regs, PF, ENGINE_INSTANCE, GUC_VIDEOENHANCE_CLASS), MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_BLITTER_CLASS), MAKE_REGLIST(xe_lpd_blt_inst_regs, PF, ENGINE_INSTANCE, GUC_BLITTER_CLASS), + MAKE_REGLIST(empty_regs_list, PF, ENGINE_CLASS, GUC_GSC_OTHER_CLASS), + MAKE_REGLIST(xe_lpd_gsc_inst_regs, PF, ENGINE_INSTANCE, GUC_GSC_OTHER_CLASS), {} }; @@ -454,6 +463,8 @@ __stringify_engclass(u32 class) return "Blitter"; case GUC_COMPUTE_CLASS: return "Compute"; + case GUC_GSC_OTHER_CLASS: + return "GSC-Other"; default: break; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 968ebd79dce7..4ae5fc2f6002 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -47,7 +47,8 @@ #define GUC_VIDEOENHANCE_CLASS 2 #define GUC_BLITTER_CLASS 3 #define GUC_COMPUTE_CLASS 4 -#define GUC_LAST_ENGINE_CLASS GUC_COMPUTE_CLASS +#define GUC_GSC_OTHER_CLASS 5 +#define GUC_LAST_ENGINE_CLASS GUC_GSC_OTHER_CLASS #define GUC_MAX_ENGINE_CLASSES 16 #define GUC_MAX_INSTANCES_PER_CLASS 32 @@ -169,6 +170,7 @@ static u8 engine_class_guc_class_map[] = { [COPY_ENGINE_CLASS] = GUC_BLITTER_CLASS, [VIDEO_DECODE_CLASS] = GUC_VIDEO_CLASS, [VIDEO_ENHANCEMENT_CLASS] = GUC_VIDEOENHANCE_CLASS, + [OTHER_CLASS] = GUC_GSC_OTHER_CLASS, [COMPUTE_CLASS] = GUC_COMPUTE_CLASS, }; @@ -178,12 +180,13 @@ static u8 guc_class_engine_class_map[] = { [GUC_VIDEO_CLASS] = VIDEO_DECODE_CLASS, [GUC_VIDEOENHANCE_CLASS] = VIDEO_ENHANCEMENT_CLASS, [GUC_COMPUTE_CLASS] = COMPUTE_CLASS, + [GUC_GSC_OTHER_CLASS] = OTHER_CLASS, }; static inline u8 engine_class_to_guc_class(u8 class) { BUILD_BUG_ON(ARRAY_SIZE(engine_class_guc_class_map) != MAX_ENGINE_CLASS + 1); - GEM_BUG_ON(class > MAX_ENGINE_CLASS || class == OTHER_CLASS); + GEM_BUG_ON(class > MAX_ENGINE_CLASS); return engine_class_guc_class_map[class]; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c index 8f8dd05835c5..b5855091cf6a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c @@ -11,9 +11,20 @@ static bool __guc_rc_supported(struct intel_guc *guc) { + struct intel_gt *gt = guc_to_gt(guc); + + /* + * Wa_14017073508: mtl + * Do not enable gucrc to avoid additional interrupts which + * may disrupt pcode wa. + */ + if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) + return false; + /* GuC RC is unavailable for pre-Gen12 */ return guc->submission_supported && - GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12; + GRAPHICS_VER(gt->i915) >= 12; } static bool __guc_rc_selected(struct intel_guc *guc) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h index a7092f711e9c..9915de32e894 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h @@ -36,6 +36,7 @@ #define SOFT_SCRATCH_COUNT 16 #define GEN11_SOFT_SCRATCH(n) _MMIO(0x190240 + (n) * 4) +#define MEDIA_SOFT_SCRATCH(n) _MMIO(0x190310 + (n) * 4) #define GEN11_SOFT_SCRATCH_COUNT 4 #define UOS_RSA_SCRATCH(i) _MMIO(0xc200 + (i) * 4) @@ -101,6 +102,7 @@ #define GUC_SEND_INTERRUPT _MMIO(0xc4c8) #define GUC_SEND_TRIGGER (1<<0) #define GEN11_GUC_HOST_INTERRUPT _MMIO(0x1901f0) +#define MEDIA_GUC_HOST_INTERRUPT _MMIO(0x190304) #define GEN12_GUC_SEM_INTR_ENABLES _MMIO(0xc71c) #define GUC_SEM_INTR_ROUTE_TO_GUC BIT(31) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 1b8b8ad27f26..0a42f1807f52 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1402,7 +1402,9 @@ static void guc_timestamp_ping(struct work_struct *wrk) /* * Synchronize with gt reset to make sure the worker does not - * corrupt the engine/guc stats. + * corrupt the engine/guc stats. NB: can't actually block waiting + * for a reset to complete as the reset requires flushing out + * this worker thread if started. So waiting would deadlock. */ ret = intel_gt_reset_trylock(gt, &srcu); if (ret) @@ -4112,6 +4114,9 @@ static inline void guc_kernel_context_pin(struct intel_guc *guc, if (context_guc_id_invalid(ce)) pin_guc_id(guc, ce); + if (!test_bit(CONTEXT_GUC_INIT, &ce->flags)) + guc_context_init(ce); + try_context_registration(ce, true); } @@ -4902,7 +4907,7 @@ void intel_guc_submission_print_info(struct intel_guc *guc, drm_printf(p, "GuC Number Outstanding Submission G2H: %u\n", atomic_read(&guc->outstanding_submission_g2h)); - drm_printf(p, "GuC tasklet count: %u\n\n", + drm_printf(p, "GuC tasklet count: %u\n", atomic_read(&sched_engine->tasklet.count)); spin_lock_irqsave(&sched_engine->lock, flags); @@ -4950,7 +4955,7 @@ static inline void guc_log_context(struct drm_printer *p, atomic_read(&ce->pin_count)); drm_printf(p, "\t\tGuC ID Ref Count: %u\n", atomic_read(&ce->guc_id.ref)); - drm_printf(p, "\t\tSchedule State: 0x%x\n\n", + drm_printf(p, "\t\tSchedule State: 0x%x\n", ce->guc_state.sched_state); } @@ -4979,7 +4984,7 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, READ_ONCE(*ce->parallel.guc.wq_head)); drm_printf(p, "\t\tWQI Tail: %u\n", READ_ONCE(*ce->parallel.guc.wq_tail)); - drm_printf(p, "\t\tWQI Status: %u\n\n", + drm_printf(p, "\t\tWQI Status: %u\n", READ_ONCE(*ce->parallel.guc.wq_status)); } @@ -4987,7 +4992,7 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, emit_bb_start_parent_no_preempt_mid_batch) { u8 i; - drm_printf(p, "\t\tChildren Go: %u\n\n", + drm_printf(p, "\t\tChildren Go: %u\n", get_children_go_value(ce)); for (i = 0; i < ce->parallel.number_children; ++i) drm_printf(p, "\t\tChildren Join: %u\n", diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index fbc8bae14f76..410905da8e97 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -211,12 +211,74 @@ void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *b huc->delayed_load.nb.notifier_call = NULL; } +static void delayed_huc_load_init(struct intel_huc *huc) +{ + /* + * Initialize fence to be complete as this is expected to be complete + * unless there is a delayed HuC load in progress. + */ + i915_sw_fence_init(&huc->delayed_load.fence, + sw_fence_dummy_notify); + i915_sw_fence_commit(&huc->delayed_load.fence); + + hrtimer_init(&huc->delayed_load.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + huc->delayed_load.timer.function = huc_delayed_load_timer_callback; +} + +static void delayed_huc_load_fini(struct intel_huc *huc) +{ + /* + * the fence is initialized in init_early, so we need to clean it up + * even if HuC loading is off. + */ + delayed_huc_load_complete(huc); + i915_sw_fence_fini(&huc->delayed_load.fence); +} + +static bool vcs_supported(struct intel_gt *gt) +{ + intel_engine_mask_t mask = gt->info.engine_mask; + + /* + * We reach here from i915_driver_early_probe for the primary GT before + * its engine mask is set, so we use the device info engine mask for it; + * this means we're not taking VCS fusing into account, but if the + * primary GT supports VCS engines we expect at least one of them to + * remain unfused so we're fine. + * For other GTs we expect the GT-specific mask to be set before we + * call this function. + */ + GEM_BUG_ON(!gt_is_root(gt) && !gt->info.engine_mask); + + if (gt_is_root(gt)) + mask = RUNTIME_INFO(gt->i915)->platform_engine_mask; + else + mask = gt->info.engine_mask; + + return __ENGINE_INSTANCES_MASK(mask, VCS0, I915_MAX_VCS); +} + void intel_huc_init_early(struct intel_huc *huc) { struct drm_i915_private *i915 = huc_to_gt(huc)->i915; + struct intel_gt *gt = huc_to_gt(huc); intel_uc_fw_init_early(&huc->fw, INTEL_UC_FW_TYPE_HUC); + /* + * we always init the fence as already completed, even if HuC is not + * supported. This way we don't have to distinguish between HuC not + * supported/disabled or already loaded, and can focus on if the load + * is currently in progress (fence not complete) or not, which is what + * we care about for stalling userspace submissions. + */ + delayed_huc_load_init(huc); + + if (!vcs_supported(gt)) { + intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_NOT_SUPPORTED); + return; + } + if (GRAPHICS_VER(i915) >= 11) { huc->status.reg = GEN11_HUC_KERNEL_LOAD_INFO; huc->status.mask = HUC_LOAD_SUCCESSFUL; @@ -226,17 +288,6 @@ void intel_huc_init_early(struct intel_huc *huc) huc->status.mask = HUC_FW_VERIFIED; huc->status.value = HUC_FW_VERIFIED; } - - /* - * Initialize fence to be complete as this is expected to be complete - * unless there is a delayed HuC reload in progress. - */ - i915_sw_fence_init(&huc->delayed_load.fence, - sw_fence_dummy_notify); - i915_sw_fence_commit(&huc->delayed_load.fence); - - hrtimer_init(&huc->delayed_load.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - huc->delayed_load.timer.function = huc_delayed_load_timer_callback; } #define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy") @@ -300,13 +351,14 @@ out: void intel_huc_fini(struct intel_huc *huc) { - if (!intel_uc_fw_is_loadable(&huc->fw)) - return; - - delayed_huc_load_complete(huc); + /* + * the fence is initialized in init_early, so we need to clean it up + * even if HuC loading is off. + */ + delayed_huc_load_fini(huc); - i915_sw_fence_fini(&huc->delayed_load.fence); - intel_uc_fw_fini(&huc->fw); + if (intel_uc_fw_is_loadable(&huc->fw)) + intel_uc_fw_fini(&huc->fw); } void intel_huc_suspend(struct intel_huc *huc) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index dbd048b77e19..2a508b137e90 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -357,8 +357,8 @@ static int uc_init_wopcm(struct intel_uc *uc) { struct intel_gt *gt = uc_to_gt(uc); struct intel_uncore *uncore = gt->uncore; - u32 base = intel_wopcm_guc_base(>->i915->wopcm); - u32 size = intel_wopcm_guc_size(>->i915->wopcm); + u32 base = intel_wopcm_guc_base(>->wopcm); + u32 size = intel_wopcm_guc_size(>->wopcm); u32 huc_agent = intel_uc_uses_huc(uc) ? HUC_LOADING_AGENT_GUC : 0; u32 mask; int err; @@ -636,8 +636,10 @@ void intel_uc_runtime_suspend(struct intel_uc *uc) { struct intel_guc *guc = &uc->guc; - if (!intel_guc_is_ready(guc)) + if (!intel_guc_is_ready(guc)) { + guc->interrupts.enabled = false; return; + } /* * Wait for any outstanding CTB before tearing down communication /w the @@ -657,8 +659,10 @@ void intel_uc_suspend(struct intel_uc *uc) intel_wakeref_t wakeref; int err; - if (!intel_guc_is_ready(guc)) + if (!intel_guc_is_ready(guc)) { + guc->interrupts.enabled = false; return; + } with_intel_runtime_pm(&uc_to_gt(uc)->i915->runtime_pm, wakeref) { err = intel_guc_suspend(guc); @@ -718,6 +722,7 @@ int intel_uc_runtime_resume(struct intel_uc *uc) static const struct intel_uc_ops uc_ops_off = { .init_hw = __uc_check_hw, + .fini = __uc_fini, /* to clean-up the init_early initialization */ }; static const struct intel_uc_ops uc_ops_on = { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index de2843dc1307..0c80ba51a4bd 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -478,10 +478,11 @@ static int check_gsc_manifest(const struct firmware *fw, return 0; } -static int check_ccs_header(struct drm_i915_private *i915, +static int check_ccs_header(struct intel_gt *gt, const struct firmware *fw, struct intel_uc_fw *uc_fw) { + struct drm_i915_private *i915 = gt->i915; struct uc_css_header *css; size_t size; @@ -523,10 +524,10 @@ static int check_ccs_header(struct drm_i915_private *i915, /* Sanity check whether this fw is not larger than whole WOPCM memory */ size = __intel_uc_fw_get_upload_size(uc_fw); - if (unlikely(size >= i915->wopcm.size)) { + if (unlikely(size >= gt->wopcm.size)) { drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu > %zu\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, - size, (size_t)i915->wopcm.size); + size, (size_t)gt->wopcm.size); return -E2BIG; } @@ -554,7 +555,8 @@ static int check_ccs_header(struct drm_i915_private *i915, */ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) { - struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915; + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); + struct drm_i915_private *i915 = gt->i915; struct intel_uc_fw_file file_ideal; struct device *dev = i915->drm.dev; struct drm_i915_gem_object *obj; @@ -562,7 +564,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) bool old_ver = false; int err; - GEM_BUG_ON(!i915->wopcm.size); + GEM_BUG_ON(!gt->wopcm.size); GEM_BUG_ON(!intel_uc_fw_is_enabled(uc_fw)); err = i915_inject_probe_error(i915, -ENXIO); @@ -575,6 +577,17 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev); memcpy(&file_ideal, &uc_fw->file_wanted, sizeof(file_ideal)); + if (!err && fw->size > INTEL_UC_RSVD_GGTT_PER_FW) { + drm_err(&i915->drm, + "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n", + intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path, + fw->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K); + + /* try to find another blob to load */ + release_firmware(fw); + err = -ENOENT; + } + /* Any error is terminal if overriding. Don't bother searching for older versions */ if (err && intel_uc_fw_is_overridden(uc_fw)) goto fail; @@ -604,7 +617,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) if (uc_fw->loaded_via_gsc) err = check_gsc_manifest(fw, uc_fw); else - err = check_ccs_header(i915, fw, uc_fw); + err = check_ccs_header(gt, fw, uc_fw); if (err) goto fail; @@ -677,14 +690,30 @@ fail: static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw) { - struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt; + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); + struct i915_ggtt *ggtt = gt->ggtt; struct drm_mm_node *node = &ggtt->uc_fw; + u32 offset = uc_fw->type * INTEL_UC_RSVD_GGTT_PER_FW; + + /* + * The media GT shares the GGTT with the root GT, which means that + * we need to use different offsets for the binaries on the media GT. + * To keep the math simple, we use 8MB for the root tile and 8MB for + * the media one. This will need to be updated if we ever have more + * than 1 media GT. + */ + BUILD_BUG_ON(INTEL_UC_FW_NUM_TYPES * INTEL_UC_RSVD_GGTT_PER_FW > SZ_8M); + GEM_BUG_ON(gt->type == GT_MEDIA && gt->info.id > 1); + if (gt->type == GT_MEDIA) + offset += SZ_8M; GEM_BUG_ON(!drm_mm_node_allocated(node)); GEM_BUG_ON(upper_32_bits(node->start)); GEM_BUG_ON(upper_32_bits(node->start + node->size - 1)); + GEM_BUG_ON(offset + uc_fw->obj->base.size > node->size); + GEM_BUG_ON(uc_fw->obj->base.size > INTEL_UC_RSVD_GGTT_PER_FW); - return lower_32_bits(node->start); + return lower_32_bits(node->start + offset); } static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw) @@ -699,7 +728,6 @@ static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw) dummy->bi.pages = obj->mm.pages; GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); - GEM_BUG_ON(dummy->node_size > ggtt->uc_fw.size); /* uc_fw->obj cache domains were not controlled across suspend */ if (i915_gem_object_has_struct_page(obj)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index cb586f7df270..bc898ba5355d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -6,6 +6,7 @@ #ifndef _INTEL_UC_FW_H_ #define _INTEL_UC_FW_H_ +#include <linux/sizes.h> #include <linux/types.h> #include "intel_uc_fw_abi.h" #include "intel_device_info.h" @@ -114,6 +115,19 @@ struct intel_uc_fw { (uc)->fw.file_selected.minor_ver, \ (uc)->fw.file_selected.patch_ver)) +/* + * When we load the uC binaries, we pin them in a reserved section at the top of + * the GGTT, which is ~18 MBs. On multi-GT systems where the GTs share the GGTT, + * we also need to make sure that each binary is pinned to a unique location + * during load, because the different GT can go through the FW load at the same + * time (see uc_fw_ggtt_offset() for details). + * Given that the available space is much greater than what is required by the + * binaries, to keep things simple instead of dynamically partitioning the + * reserved section to make space for all the blobs we can just reserve a static + * chunk for each binary. + */ +#define INTEL_UC_RSVD_GGTT_PER_FW SZ_2M + #ifdef CONFIG_DRM_I915_DEBUG_GUC void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, enum intel_uc_fw_status status); diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c index 01f8cd3c3134..d91b58f70403 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_hangcheck.c @@ -35,11 +35,14 @@ static int intel_hang_guc(void *arg) struct i915_request *rq; intel_wakeref_t wakeref; struct i915_gpu_error *global = >->i915->gpu_error; - struct intel_engine_cs *engine; + struct intel_engine_cs *engine = intel_selftest_find_any_engine(gt); unsigned int reset_count; u32 guc_status; u32 old_beat; + if (!engine) + return 0; + ctx = kernel_context(gt->i915, NULL); if (IS_ERR(ctx)) { drm_err(>->i915->drm, "Failed get kernel context: %ld\n", PTR_ERR(ctx)); @@ -48,14 +51,13 @@ static int intel_hang_guc(void *arg) wakeref = intel_runtime_pm_get(gt->uncore->rpm); - ce = intel_context_create(gt->engine[BCS0]); + ce = intel_context_create(engine); if (IS_ERR(ce)) { ret = PTR_ERR(ce); drm_err(>->i915->drm, "Failed to create spinner request: %d\n", ret); goto err; } - engine = ce->engine; reset_count = i915_reset_count(global); old_beat = engine->props.heartbeat_interval_ms; diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 01e54b45c5c1..355f1c0e8664 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -88,7 +88,7 @@ static int vgpu_gem_get_pages( sg_dma_address(sg) = dma_addr; } - __i915_gem_object_set_pages(obj, st, PAGE_SIZE); + __i915_gem_object_set_pages(obj, st); out: if (ret) { dma_addr_t dma_addr; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 897b6fdbbaed..f5451adcd489 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -664,18 +664,14 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev) return -ESRCH; } - kvm_get_kvm(vgpu->vfio_device.kvm); - if (__kvmgt_vgpu_exist(vgpu)) return -EEXIST; vgpu->attached = true; - kvmgt_protect_table_init(vgpu); - gvt_cache_init(vgpu); - vgpu->track_node.track_write = kvmgt_page_track_write; vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot; + kvm_get_kvm(vgpu->vfio_device.kvm); kvm_page_track_register_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); @@ -711,15 +707,19 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev) kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm, &vgpu->track_node); + kvm_put_kvm(vgpu->vfio_device.kvm); + kvmgt_protect_table_destroy(vgpu); gvt_cache_destroy(vgpu); + WARN_ON(vgpu->nr_cache_entries); + + vgpu->gfn_cache = RB_ROOT; + vgpu->dma_addr_cache = RB_ROOT; + intel_vgpu_release_msi_eventfd_ctx(vgpu); vgpu->attached = false; - - if (vgpu->vfio_device.kvm) - kvm_put_kvm(vgpu->vfio_device.kvm); } static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar) @@ -1447,9 +1447,17 @@ static int intel_vgpu_init_dev(struct vfio_device *vfio_dev) struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); struct intel_vgpu_type *type = container_of(mdev->type, struct intel_vgpu_type, type); + int ret; vgpu->gvt = kdev_to_i915(mdev->type->parent->dev)->gvt; - return intel_gvt_create_vgpu(vgpu, type->conf); + ret = intel_gvt_create_vgpu(vgpu, type->conf); + if (ret) + return ret; + + kvmgt_protect_table_init(vgpu); + gvt_cache_init(vgpu); + + return 0; } static void intel_vgpu_release_dev(struct vfio_device *vfio_dev) @@ -1457,7 +1465,6 @@ static void intel_vgpu_release_dev(struct vfio_device *vfio_dev) struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); intel_gvt_destroy_vgpu(vgpu); - vfio_free_device(vfio_dev); } static const struct vfio_device_ops intel_vgpu_dev_ops = { @@ -1470,6 +1477,9 @@ static const struct vfio_device_ops intel_vgpu_dev_ops = { .mmap = intel_vgpu_mmap, .ioctl = intel_vgpu_ioctl, .dma_unmap = intel_vgpu_dma_unmap, + .bind_iommufd = vfio_iommufd_emulated_bind, + .unbind_iommufd = vfio_iommufd_emulated_unbind, + .attach_ioas = vfio_iommufd_emulated_attach_ioas, }; static int intel_vgpu_probe(struct mdev_device *mdev) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index d6fe94cd0fdb..9cd8fcbf7cad 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -570,9 +570,8 @@ retry: if (gmadr_bytes == 8) bb->bb_start_cmd_va[2] = 0; - ret = i915_vma_move_to_active(bb->vma, - workload->req, - 0); + ret = i915_vma_move_to_active(bb->vma, workload->req, + __EXEC_OBJECT_NO_REQUEST_AWAIT); if (ret) goto err; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index ae987e92251d..6c7ac73b69a5 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -688,8 +688,8 @@ i915_drop_caches_set(void *data, u64 val) unsigned int flags; int ret; - DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n", - val, val & DROP_ALL); + drm_dbg(&i915->drm, "Dropping caches: 0x%08llx [0x%08llx]\n", + val, val & DROP_ALL); ret = gt_drop_caches(to_gt(i915), val); if (ret) diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 9ceea52ad9db..ef94baebb337 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -373,8 +373,6 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) if (ret) goto err_ttm; - intel_wopcm_init_early(&dev_priv->wopcm); - ret = intel_root_gt_init_early(dev_priv); if (ret < 0) goto err_rootgt; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 05b84196216c..360743a8a163 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -63,7 +63,6 @@ #include "intel_runtime_pm.h" #include "intel_step.h" #include "intel_uncore.h" -#include "intel_wopcm.h" struct drm_i915_clock_gating_funcs; struct drm_i915_gem_object; @@ -236,8 +235,6 @@ struct drm_i915_private { struct intel_gvt *gvt; - struct intel_wopcm wopcm; - struct pci_dev *bridge_dev; struct rb_root uabi_engines; @@ -727,6 +724,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_XEHPSDV_GRAPHICS_STEP(__i915, since, until) \ (IS_XEHPSDV(__i915) && IS_GRAPHICS_STEP(__i915, since, until)) +#define IS_MTL_GRAPHICS_STEP(__i915, variant, since, until) \ + (IS_SUBPLATFORM(__i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_##variant) && \ + IS_GRAPHICS_STEP(__i915, since, until)) + #define IS_MTL_DISPLAY_STEP(__i915, since, until) \ (IS_METEORLAKE(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) @@ -769,12 +770,15 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define __HAS_ENGINE(engine_mask, id) ((engine_mask) & BIT(id)) #define HAS_ENGINE(gt, id) __HAS_ENGINE((gt)->info.engine_mask, id) -#define ENGINE_INSTANCES_MASK(gt, first, count) ({ \ +#define __ENGINE_INSTANCES_MASK(mask, first, count) ({ \ unsigned int first__ = (first); \ unsigned int count__ = (count); \ - ((gt)->info.engine_mask & \ - GENMASK(first__ + count__ - 1, first__)) >> first__; \ + ((mask) & GENMASK(first__ + count__ - 1, first__)) >> first__; \ }) + +#define ENGINE_INSTANCES_MASK(gt, first, count) \ + __ENGINE_INSTANCES_MASK((gt)->info.engine_mask, first, count) + #define RCS_MASK(gt) \ ENGINE_INSTANCES_MASK(gt, RCS0, I915_MAX_RCS) #define BCS_MASK(gt) \ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 299f94a9fb87..8468ca9885fd 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1140,8 +1140,10 @@ int i915_gem_init(struct drm_i915_private *dev_priv) if (ret) return ret; - intel_uc_fetch_firmwares(&to_gt(dev_priv)->uc); - intel_wopcm_init(&dev_priv->wopcm); + for_each_gt(gt, dev_priv, i) { + intel_uc_fetch_firmwares(>->uc); + intel_wopcm_init(>->wopcm); + } ret = i915_init_ggtt(dev_priv); if (ret) { @@ -1286,7 +1288,7 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file) struct i915_drm_client *client; int ret = -ENOMEM; - DRM_DEBUG("\n"); + drm_dbg(&i915->drm, "\n"); file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL); if (!file_priv) diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 3047e80e1163..61ef2d9cfa62 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -179,7 +179,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, value = i915_perf_oa_timestamp_frequency(i915); break; default: - DRM_DEBUG("Unknown parameter %d\n", param->param); + drm_dbg(&i915->drm, "Unknown parameter %d\n", param->param); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index c4e46da6502c..54ea28cf8a1a 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1085,8 +1085,9 @@ static void ivb_parity_work(struct work_struct *work) kobject_uevent_env(&dev_priv->drm.primary->kdev->kobj, KOBJ_CHANGE, parity_event); - DRM_DEBUG("Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n", - slice, row, bank, subbank); + drm_dbg(&dev_priv->drm, + "Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n", + slice, row, bank, subbank); kfree(parity_event[4]); kfree(parity_event[3]); @@ -2776,7 +2777,8 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg) master_ctl = raw_reg_read(regs, GEN11_GFX_MSTR_IRQ); raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, master_ctl); } else { - DRM_ERROR("Tile not supported: 0x%08x\n", master_tile_ctl); + drm_err(&i915->drm, "Tile not supported: 0x%08x\n", + master_tile_ctl); dg1_master_intr_enable(regs); return IRQ_NONE; } @@ -3942,7 +3944,7 @@ static void i8xx_error_irq_ack(struct drm_i915_private *i915, static void i8xx_error_irq_handler(struct drm_i915_private *dev_priv, u16 eir, u16 eir_stuck) { - DRM_DEBUG("Master Error: EIR 0x%04x\n", eir); + drm_dbg(&dev_priv->drm, "Master Error: EIR 0x%04x\n", eir); if (eir_stuck) drm_dbg(&dev_priv->drm, "EIR stuck: 0x%04x, masked\n", @@ -3977,7 +3979,7 @@ static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv, static void i9xx_error_irq_handler(struct drm_i915_private *dev_priv, u32 eir, u32 eir_stuck) { - DRM_DEBUG("Master Error, EIR 0x%08x\n", eir); + drm_dbg(&dev_priv->drm, "Master Error, EIR 0x%08x\n", eir); if (eir_stuck) drm_dbg(&dev_priv->drm, "EIR stuck: 0x%08x, masked\n", diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index b28ccbebc821..48225bf6efe7 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1145,6 +1145,7 @@ static const struct intel_device_info mtl_info = { .extra_gt_list = xelpmp_extra_gt, .has_flat_ccs = 0, .has_gmd_id = 1, + .has_guc_deprivilege = 1, .has_mslice_steering = 0, .has_snoop = 1, .__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index b07b5a40630a..125b6ca25a75 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -531,9 +531,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) if (OA_TAKEN(hw_tail, tail) > report_size && __ratelimit(&stream->perf->tail_pointer_race)) - DRM_NOTE("unlanded report(s) head=0x%x " - "tail=0x%x hw_tail=0x%x\n", - head, tail, hw_tail); + drm_notice(&stream->uncore->i915->drm, + "unlanded report(s) head=0x%x tail=0x%x hw_tail=0x%x\n", + head, tail, hw_tail); stream->oa_buffer.tail = gtt_offset + tail; stream->oa_buffer.aging_tail = gtt_offset + hw_tail; @@ -1016,7 +1016,8 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, */ if (report32[0] == 0) { if (__ratelimit(&stream->perf->spurious_report_rs)) - DRM_NOTE("Skipping spurious, invalid OA report\n"); + drm_notice(&uncore->i915->drm, + "Skipping spurious, invalid OA report\n"); continue; } @@ -1382,6 +1383,9 @@ static u32 oa_context_image_offset(struct intel_context *ce, u32 reg) u32 offset, len = (ce->engine->context_size - PAGE_SIZE) / 4; u32 *state = ce->lrc_reg_state; + if (drm_WARN_ON(&ce->engine->i915->drm, !state)) + return U32_MAX; + for (offset = 0; offset < len; ) { if (IS_MI_LRI_CMD(state[offset])) { /* @@ -1446,7 +1450,8 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) if (IS_ERR(ce)) return PTR_ERR(ce); - if (engine_supports_mi_query(stream->engine)) { + if (engine_supports_mi_query(stream->engine) && + HAS_LOGICAL_RING_CONTEXTS(stream->perf->i915)) { /* * We are enabling perf query here. If we don't find the context * offset here, just return an error. @@ -1603,8 +1608,9 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) free_noa_wait(stream); if (perf->spurious_report_rs.missed) { - DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n", - perf->spurious_report_rs.missed); + drm_notice(>->i915->drm, + "%d spurious OA report notices suppressed due to ratelimiting\n", + perf->spurious_report_rs.missed); } } @@ -2252,9 +2258,7 @@ retry: goto err_add_request; } - err = i915_request_await_object(rq, vma->obj, 0); - if (!err) - err = i915_vma_move_to_active(vma, rq, 0); + err = i915_vma_move_to_active(vma, rq, 0); if (err) goto err_add_request; diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index e0c96b44eda8..ca150b7af3f2 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -146,8 +146,8 @@ struct i915_perf_stream { */ struct intel_engine_cs *engine; - /* - * Lock associated with operations on stream + /** + * @lock: Lock associated with operations on stream */ struct mutex lock; diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 958b37123bf1..52531ab28c5f 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -148,13 +148,13 @@ static u64 __get_rc6(struct intel_gt *gt) struct drm_i915_private *i915 = gt->i915; u64 val; - val = intel_rc6_residency_ns(>->rc6, GEN6_GT_GFX_RC6); + val = intel_rc6_residency_ns(>->rc6, INTEL_RC6_RES_RC6); if (HAS_RC6p(i915)) - val += intel_rc6_residency_ns(>->rc6, GEN6_GT_GFX_RC6p); + val += intel_rc6_residency_ns(>->rc6, INTEL_RC6_RES_RC6p); if (HAS_RC6pp(i915)) - val += intel_rc6_residency_ns(>->rc6, GEN6_GT_GFX_RC6pp); + val += intel_rc6_residency_ns(>->rc6, INTEL_RC6_RES_RC6pp); return val; } @@ -371,7 +371,6 @@ static void frequency_sample(struct intel_gt *gt, unsigned int period_ns) { struct drm_i915_private *i915 = gt->i915; - struct intel_uncore *uncore = gt->uncore; struct i915_pmu *pmu = &i915->pmu; struct intel_rps *rps = >->rps; @@ -394,7 +393,7 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns) * case we assume the system is running at the intended * frequency. Fortunately, the read should rarely fail! */ - val = intel_uncore_read_fw(uncore, GEN6_RPSTAT1); + val = intel_rps_read_rpstat_fw(rps); if (val) val = intel_rps_get_cagf(rps, val); else diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 6ec9c9fb7b0d..00871ef99792 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -250,8 +250,9 @@ static int query_perf_config_data(struct drm_i915_private *i915, return total_size; if (query_item->length < total_size) { - DRM_DEBUG("Invalid query config data item size=%u expected=%u\n", - query_item->length, total_size); + drm_dbg(&i915->drm, + "Invalid query config data item size=%u expected=%u\n", + query_item->length, total_size); return -EINVAL; } @@ -418,9 +419,10 @@ static int query_perf_config_list(struct drm_i915_private *i915, } while (n_configs > alloc); if (query_item->length < sizeof_perf_config_list(n_configs)) { - DRM_DEBUG("Invalid query config list item size=%u expected=%zu\n", - query_item->length, - sizeof_perf_config_list(n_configs)); + drm_dbg(&i915->drm, + "Invalid query config list item size=%u expected=%zu\n", + query_item->length, + sizeof_perf_config_list(n_configs)); kfree(oa_config_ids); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 37452140cb93..c76a02c6d22c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -902,6 +902,7 @@ #define GEN11_VEBOX2_RING_BASE 0x1d8000 #define XEHP_VEBOX3_RING_BASE 0x1e8000 #define XEHP_VEBOX4_RING_BASE 0x1f8000 +#define MTL_GSC_RING_BASE 0x11a000 #define GEN12_COMPUTE0_RING_BASE 0x1a000 #define GEN12_COMPUTE1_RING_BASE 0x1c000 #define GEN12_COMPUTE2_RING_BASE 0x1e000 @@ -6591,6 +6592,15 @@ /* XEHP_PCODE_FREQUENCY_CONFIG param2 */ #define PCODE_MBOX_DOMAIN_NONE 0x0 #define PCODE_MBOX_DOMAIN_MEDIAFF 0x3 + +/* Wa_14017210380: mtl */ +#define PCODE_MBOX_GT_STATE 0x50 +/* sub-commands (param1) */ +#define PCODE_MBOX_GT_STATE_MEDIA_BUSY 0x1 +#define PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY 0x2 +/* param2 */ +#define PCODE_MBOX_GT_STATE_DOMAIN_MEDIA 0x1 + #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index cc2a8821d22a..8a9aad523eec 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -465,7 +465,7 @@ static void irq_i915_sw_fence_work(struct irq_work *wrk) struct i915_sw_dma_fence_cb_timer *cb = container_of(wrk, typeof(*cb), work); - del_timer_sync(&cb->timer); + timer_shutdown_sync(&cb->timer); dma_fence_put(cb->dma); kfree_rcu(cb, rcu); diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 1e2750210831..595e8b574990 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -218,7 +218,8 @@ static const struct bin_attribute error_state_attr = { static void i915_setup_error_capture(struct device *kdev) { if (sysfs_create_bin_file(&kdev->kobj, &error_state_attr)) - DRM_ERROR("error_state sysfs setup failed\n"); + drm_err(&kdev_minor_to_i915(kdev)->drm, + "error_state sysfs setup failed\n"); } static void i915_teardown_error_capture(struct device *kdev) diff --git a/drivers/gpu/drm/i915/i915_user_extensions.c b/drivers/gpu/drm/i915/i915_user_extensions.c index c822d0aafd2d..e3f808372c47 100644 --- a/drivers/gpu/drm/i915/i915_user_extensions.c +++ b/drivers/gpu/drm/i915/i915_user_extensions.c @@ -51,7 +51,7 @@ int i915_user_extensions(struct i915_user_extension __user *ext, return err; if (get_user(next, &ext->next_extension) || - overflows_type(next, ext)) + overflows_type(next, uintptr_t)) return -EFAULT; ext = u64_to_user_ptr(next); diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index 6c14d13364bf..67a66d4d5c70 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -111,10 +111,6 @@ bool i915_error_injected(void); #define range_overflows_end_t(type, start, size, max) \ range_overflows_end((type)(start), (type)(size), (type)(max)) -/* Note we don't consider signbits :| */ -#define overflows_type(x, T) \ - (sizeof(x) > sizeof(T) && (x) >> BITS_PER_TYPE(T)) - #define ptr_mask_bits(ptr, n) ({ \ unsigned long __v = (unsigned long)(ptr); \ (typeof(ptr))(__v & -BIT(n)); \ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index c39488eb9eeb..703fee6b5f75 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -73,14 +73,16 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason) char buf[512]; if (!vma->node.stack) { - DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: unknown owner\n", - vma->node.start, vma->node.size, reason); + drm_dbg(&to_i915(vma->obj->base.dev)->drm, + "vma.node [%08llx + %08llx] %s: unknown owner\n", + vma->node.start, vma->node.size, reason); return; } stack_depot_snprint(vma->node.stack, buf, sizeof(buf), 0); - DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n", - vma->node.start, vma->node.size, reason, buf); + drm_dbg(&to_i915(vma->obj->base.dev)->drm, + "vma.node [%08llx + %08llx] %s: inserted at %s\n", + vma->node.start, vma->node.size, reason, buf); } #else @@ -782,9 +784,9 @@ i915_vma_insert(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, * attempt to find space. */ if (size > end) { - DRM_DEBUG("Attempting to bind an object larger than the aperture: request=%llu > %s aperture=%llu\n", - size, flags & PIN_MAPPABLE ? "mappable" : "total", - end); + drm_dbg(&to_i915(vma->obj->base.dev)->drm, + "Attempting to bind an object larger than the aperture: request=%llu > %s aperture=%llu\n", + size, flags & PIN_MAPPABLE ? "mappable" : "total", end); return -ENOSPC; } @@ -1842,6 +1844,11 @@ int _i915_vma_move_to_active(struct i915_vma *vma, GEM_BUG_ON(!vma->pages); + if (!(flags & __EXEC_OBJECT_NO_REQUEST_AWAIT)) { + err = i915_request_await_object(rq, vma->obj, flags & EXEC_OBJECT_WRITE); + if (unlikely(err)) + return err; + } err = __i915_vma_move_to_active(vma, rq); if (unlikely(err)) return err; diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index aecd9c64486b..0757977a489b 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -55,6 +55,7 @@ static inline bool i915_vma_is_active(const struct i915_vma *vma) /* do not reserve memory to prevent deadlocks */ #define __EXEC_OBJECT_NO_RESERVE BIT(31) +#define __EXEC_OBJECT_NO_REQUEST_AWAIT BIT(30) int __must_check _i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq, diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index 9a4a7fb55582..b9a164efd6ae 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -38,7 +38,7 @@ static int __iopagetest(struct intel_memory_region *mem, u8 value, resource_size_t offset, const void *caller) { - int byte = prandom_u32_max(pagesize); + int byte = get_random_u32_below(pagesize); u8 result[3]; memset_io(va, value, pagesize); /* or GPF! */ @@ -92,7 +92,7 @@ static int iopagetest(struct intel_memory_region *mem, static resource_size_t random_page(resource_size_t last) { /* Limited to low 44b (16TiB), but should suffice for a spot check */ - return prandom_u32_max(last >> PAGE_SHIFT) << PAGE_SHIFT; + return get_random_u32_below(last >> PAGE_SHIFT) << PAGE_SHIFT; } static int iomemtest(struct intel_memory_region *mem, diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 9995f478152c..614013745fca 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -179,8 +179,9 @@ static inline void fw_domain_wait_ack_clear(const struct intel_uncore_forcewake_domain *d) { if (wait_ack_clear(d, FORCEWAKE_KERNEL)) { - DRM_ERROR("%s: timed out waiting for forcewake ack to clear.\n", - intel_uncore_forcewake_domain_to_str(d->id)); + drm_err(&d->uncore->i915->drm, + "%s: timed out waiting for forcewake ack to clear.\n", + intel_uncore_forcewake_domain_to_str(d->id)); add_taint_for_CI(d->uncore->i915, TAINT_WARN); /* CI now unreliable */ } } @@ -227,11 +228,12 @@ fw_domain_wait_ack_with_fallback(const struct intel_uncore_forcewake_domain *d, fw_clear(d, FORCEWAKE_KERNEL_FALLBACK); } while (!ack_detected && pass++ < 10); - DRM_DEBUG_DRIVER("%s had to use fallback to %s ack, 0x%x (passes %u)\n", - intel_uncore_forcewake_domain_to_str(d->id), - type == ACK_SET ? "set" : "clear", - fw_ack(d), - pass); + drm_dbg(&d->uncore->i915->drm, + "%s had to use fallback to %s ack, 0x%x (passes %u)\n", + intel_uncore_forcewake_domain_to_str(d->id), + type == ACK_SET ? "set" : "clear", + fw_ack(d), + pass); return ack_detected ? 0 : -ETIMEDOUT; } @@ -256,8 +258,9 @@ static inline void fw_domain_wait_ack_set(const struct intel_uncore_forcewake_domain *d) { if (wait_ack_set(d, FORCEWAKE_KERNEL)) { - DRM_ERROR("%s: timed out waiting for forcewake ack request.\n", - intel_uncore_forcewake_domain_to_str(d->id)); + drm_err(&d->uncore->i915->drm, + "%s: timed out waiting for forcewake ack request.\n", + intel_uncore_forcewake_domain_to_str(d->id)); add_taint_for_CI(d->uncore->i915, TAINT_WARN); /* CI now unreliable */ } } diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index 5449146a0624..e9e38490815d 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -382,20 +382,6 @@ __uncore_write(write_notrace, 32, l, false) */ __uncore_read(read64, 64, q, true) -static inline u64 -intel_uncore_read64_2x32(struct intel_uncore *uncore, - i915_reg_t lower_reg, i915_reg_t upper_reg) -{ - u32 upper, lower, old_upper, loop = 0; - upper = intel_uncore_read(uncore, upper_reg); - do { - old_upper = upper; - lower = intel_uncore_read(uncore, lower_reg); - upper = intel_uncore_read(uncore, upper_reg); - } while (upper != old_upper && loop++ < 2); - return (u64)upper << 32 | lower; -} - #define intel_uncore_posting_read(...) ((void)intel_uncore_read_notrace(__VA_ARGS__)) #define intel_uncore_posting_read16(...) ((void)intel_uncore_read16_notrace(__VA_ARGS__)) @@ -455,6 +441,36 @@ static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore, intel_uncore_write_fw(uncore, reg, val); } +static inline u64 +intel_uncore_read64_2x32(struct intel_uncore *uncore, + i915_reg_t lower_reg, i915_reg_t upper_reg) +{ + u32 upper, lower, old_upper, loop = 0; + enum forcewake_domains fw_domains; + unsigned long flags; + + fw_domains = intel_uncore_forcewake_for_reg(uncore, lower_reg, + FW_REG_READ); + + fw_domains |= intel_uncore_forcewake_for_reg(uncore, upper_reg, + FW_REG_READ); + + spin_lock_irqsave(&uncore->lock, flags); + intel_uncore_forcewake_get__locked(uncore, fw_domains); + + upper = intel_uncore_read_fw(uncore, upper_reg); + do { + old_upper = upper; + lower = intel_uncore_read_fw(uncore, lower_reg); + upper = intel_uncore_read_fw(uncore, upper_reg); + } while (upper != old_upper && loop++ < 2); + + intel_uncore_forcewake_put__locked(uncore, fw_domains); + spin_unlock_irqrestore(&uncore->lock, flags); + + return (u64)upper << 32 | lower; +} + static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore, i915_reg_t reg, u32 val, u32 mask, u32 expected_val) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_42.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_42.h new file mode 100644 index 000000000000..739f9072fa5f --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_42.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_FW_INTERFACE_42_H__ +#define __INTEL_PXP_FW_INTERFACE_42_H__ + +#include <linux/types.h> +#include "intel_pxp_cmd_interface_cmn.h" + +/* PXP-Opcode for Init Session */ +#define PXP42_CMDID_INIT_SESSION 0x1e + +/* PXP-Input-Packet: Init Session (Arb-Session) */ +struct pxp42_create_arb_in { + struct pxp_cmd_header header; + u32 protection_mode; +#define PXP42_ARB_SESSION_MODE_HEAVY 0x2 + u32 session_id; +} __packed; + +/* PXP-Output-Packet: Init Session */ +struct pxp42_create_arb_out { + struct pxp_cmd_header header; +} __packed; + +#endif /* __INTEL_PXP_FW_INTERFACE_42_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h new file mode 100644 index 000000000000..ad67e3f49c20 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2022, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_FW_INTERFACE_43_H__ +#define __INTEL_PXP_FW_INTERFACE_43_H__ + +#include <linux/types.h> +#include "intel_pxp_cmd_interface_cmn.h" + +/* PXP-Cmd-Op definitions */ +#define PXP43_CMDID_START_HUC_AUTH 0x0000003A + +/* PXP-Input-Packet: HUC-Authentication */ +struct pxp43_start_huc_auth_in { + struct pxp_cmd_header header; + __le64 huc_base_address; +} __packed; + +/* PXP-Output-Packet: HUC-Authentication */ +struct pxp43_start_huc_auth_out { + struct pxp_cmd_header header; +} __packed; + +#endif /* __INTEL_PXP_FW_INTERFACE_43_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h new file mode 100644 index 000000000000..c2f23394f9b8 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2022, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_FW_INTERFACE_CMN_H__ +#define __INTEL_PXP_FW_INTERFACE_CMN_H__ + +#include <linux/types.h> + +#define PXP_APIVER(x, y) (((x) & 0xFFFF) << 16 | ((y) & 0xFFFF)) + +/* + * there are a lot of status codes for PXP, but we only define the cross-API + * common ones that we actually can handle in the kernel driver. Other failure + * codes should be printed to error msg for debug. + */ +enum pxp_status { + PXP_STATUS_SUCCESS = 0x0, + PXP_STATUS_OP_NOT_PERMITTED = 0x4013 +}; + +/* Common PXP FW message header */ +struct pxp_cmd_header { + u32 api_version; + u32 command_id; + union { + u32 status; /* out */ + u32 stream_id; /* in */ + }; + /* Length of the message (excluding the header) */ + u32 buffer_len; +} __packed; + +#endif /* __INTEL_PXP_FW_INTERFACE_CMN_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c index 7ec36d94e758..2e1165522950 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_huc.c @@ -3,7 +3,8 @@ * Copyright(c) 2021-2022, Intel Corporation. All rights reserved. */ -#include "drm/i915_drm.h" +#include <drm/i915_drm.h> + #include "i915_drv.h" #include "gem/i915_gem_region.h" @@ -13,14 +14,14 @@ #include "intel_pxp_huc.h" #include "intel_pxp_tee.h" #include "intel_pxp_types.h" -#include "intel_pxp_tee_interface.h" +#include "intel_pxp_cmd_interface_43.h" int intel_pxp_huc_load_and_auth(struct intel_pxp *pxp) { struct intel_gt *gt = pxp_to_gt(pxp); struct intel_huc *huc = >->uc.huc; - struct pxp_tee_start_huc_auth_in huc_in = {0}; - struct pxp_tee_start_huc_auth_out huc_out = {0}; + struct pxp43_start_huc_auth_in huc_in = {0}; + struct pxp43_start_huc_auth_out huc_out = {0}; dma_addr_t huc_phys_addr; u8 client_id = 0; u8 fence_id = 0; @@ -32,8 +33,8 @@ int intel_pxp_huc_load_and_auth(struct intel_pxp *pxp) huc_phys_addr = i915_gem_object_get_dma_address(huc->fw.obj, 0); /* write the PXP message into the lmem (the sg list) */ - huc_in.header.api_version = PXP_TEE_43_APIVER; - huc_in.header.command_id = PXP_TEE_43_START_HUC_AUTH; + huc_in.header.api_version = PXP_APIVER(4, 3); + huc_in.header.command_id = PXP43_CMDID_START_HUC_AUTH; huc_in.header.status = 0; huc_in.header.buffer_len = sizeof(huc_in.huc_base_address); huc_in.huc_base_address = huc_phys_addr; diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c index 052fd2f9a583..b0c9170b1395 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c @@ -14,7 +14,7 @@ #include "intel_pxp.h" #include "intel_pxp_session.h" #include "intel_pxp_tee.h" -#include "intel_pxp_tee_interface.h" +#include "intel_pxp_cmd_interface_42.h" #include "intel_pxp_huc.h" static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) @@ -286,14 +286,14 @@ int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, int arb_session_id) { struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; - struct pxp_tee_create_arb_in msg_in = {0}; - struct pxp_tee_create_arb_out msg_out = {0}; + struct pxp42_create_arb_in msg_in = {0}; + struct pxp42_create_arb_out msg_out = {0}; int ret; - msg_in.header.api_version = PXP_TEE_APIVER; - msg_in.header.command_id = PXP_TEE_ARB_CMDID; + msg_in.header.api_version = PXP_APIVER(4, 2); + msg_in.header.command_id = PXP42_CMDID_INIT_SESSION; msg_in.header.buffer_len = sizeof(msg_in) - sizeof(msg_in.header); - msg_in.protection_mode = PXP_TEE_ARB_PROTECTION_MODE; + msg_in.protection_mode = PXP42_ARB_SESSION_MODE_HEAVY; msg_in.session_id = arb_session_id; ret = intel_pxp_tee_io_message(pxp, diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h deleted file mode 100644 index 7edc1760f142..000000000000 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright(c) 2020-2022, Intel Corporation. All rights reserved. - */ - -#ifndef __INTEL_PXP_TEE_INTERFACE_H__ -#define __INTEL_PXP_TEE_INTERFACE_H__ - -#include <linux/types.h> - -#define PXP_TEE_APIVER 0x40002 -#define PXP_TEE_43_APIVER 0x00040003 -#define PXP_TEE_ARB_CMDID 0x1e -#define PXP_TEE_ARB_PROTECTION_MODE 0x2 -#define PXP_TEE_43_START_HUC_AUTH 0x0000003A - -/* - * there are a lot of status codes for PXP, but we only define the ones we - * actually can handle in the driver. other failure codes will be printed to - * error msg for debug. - */ -enum pxp_status { - PXP_STATUS_SUCCESS = 0x0, - PXP_STATUS_OP_NOT_PERMITTED = 0x4013 -}; - -/* PXP TEE message header */ -struct pxp_tee_cmd_header { - u32 api_version; - u32 command_id; - u32 status; - /* Length of the message (excluding the header) */ - u32 buffer_len; -} __packed; - -/* PXP TEE message input to create a arbitrary session */ -struct pxp_tee_create_arb_in { - struct pxp_tee_cmd_header header; - u32 protection_mode; - u32 session_id; -} __packed; - -/* PXP TEE message output to create a arbitrary session */ -struct pxp_tee_create_arb_out { - struct pxp_tee_cmd_header header; -} __packed; - -struct pxp_tee_start_huc_auth_in { - struct pxp_tee_cmd_header header; - __le64 huc_base_address; -}; - -struct pxp_tee_start_huc_auth_out { - struct pxp_tee_cmd_header header; -}; - -#endif /* __INTEL_PXP_TEE_INTERFACE_H__ */ diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 27c733b00976..eae7d947d7de 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -61,7 +61,6 @@ static int fake_get_pages(struct drm_i915_gem_object *obj) #define PFN_BIAS 0x1000 struct sg_table *pages; struct scatterlist *sg; - unsigned int sg_page_sizes; typeof(obj->base.size) rem; pages = kmalloc(sizeof(*pages), GFP); @@ -74,7 +73,6 @@ static int fake_get_pages(struct drm_i915_gem_object *obj) return -ENOMEM; } - sg_page_sizes = 0; rem = obj->base.size; for (sg = pages->sgl; sg; sg = sg_next(sg)) { unsigned long len = min_t(typeof(rem), rem, BIT(31)); @@ -83,13 +81,12 @@ static int fake_get_pages(struct drm_i915_gem_object *obj) sg_set_page(sg, pfn_to_page(PFN_BIAS), len, 0); sg_dma_address(sg) = page_to_phys(sg_page(sg)); sg_dma_len(sg) = len; - sg_page_sizes |= len; rem -= len; } GEM_BUG_ON(rem); - __i915_gem_object_set_pages(obj, pages, sg_page_sizes); + __i915_gem_object_set_pages(obj, pages); return 0; #undef GFP diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index a46350c37e9d..0daa8669181d 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -1223,9 +1223,7 @@ static int live_all_engines(void *arg) goto out_request; } - err = i915_request_await_object(request[idx], batch->obj, 0); - if (err == 0) - err = i915_vma_move_to_active(batch, request[idx], 0); + err = i915_vma_move_to_active(batch, request[idx], 0); GEM_BUG_ON(err); err = engine->emit_bb_start(request[idx], @@ -1352,10 +1350,7 @@ static int live_sequential_engines(void *arg) } } - err = i915_request_await_object(request[idx], - batch->obj, false); - if (err == 0) - err = i915_vma_move_to_active(batch, request[idx], 0); + err = i915_vma_move_to_active(batch, request[idx], 0); GEM_BUG_ON(err); err = engine->emit_bb_start(request[idx], @@ -1710,7 +1705,8 @@ static int live_breadcrumbs_smoketest(void *arg) { struct drm_i915_private *i915 = arg; const unsigned int nengines = num_uabi_engines(i915); - const unsigned int ncpus = num_online_cpus(); + const unsigned int ncpus = /* saturate with nengines * ncpus */ + max_t(int, 2, DIV_ROUND_UP(num_online_cpus(), nengines)); unsigned long num_waits, num_fences; struct intel_engine_cs *engine; struct smoke_thread *threads; @@ -1782,7 +1778,7 @@ static int live_breadcrumbs_smoketest(void *arg) goto out_flush; } /* One ring interleaved between requests from all cpus */ - smoke[idx].max_batch /= num_online_cpus() + 1; + smoke[idx].max_batch /= ncpus + 1; pr_debug("Limiting batches to %d requests on %s\n", smoke[idx].max_batch, engine->name); diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c index 0c22594ae274..16978ac59797 100644 --- a/drivers/gpu/drm/i915/selftests/igt_spinner.c +++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c @@ -119,22 +119,6 @@ static u64 hws_address(const struct i915_vma *hws, return hws->node.start + seqno_offset(rq->fence.context); } -static int move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags) -{ - int err; - - i915_vma_lock(vma); - err = i915_request_await_object(rq, vma->obj, - flags & EXEC_OBJECT_WRITE); - if (err == 0) - err = i915_vma_move_to_active(vma, rq, flags); - i915_vma_unlock(vma); - - return err; -} - struct i915_request * igt_spinner_create_request(struct igt_spinner *spin, struct intel_context *ce, @@ -165,11 +149,11 @@ igt_spinner_create_request(struct igt_spinner *spin, if (IS_ERR(rq)) return ERR_CAST(rq); - err = move_to_active(vma, rq, 0); + err = igt_vma_move_to_active_unlocked(vma, rq, 0); if (err) goto cancel_rq; - err = move_to_active(hws, rq, 0); + err = igt_vma_move_to_active_unlocked(hws, rq, 0); if (err) goto cancel_rq; diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index bac21fe84ca5..6324eb32d4dd 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -41,7 +41,7 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj) } pages = &obj->mm.rsgt->table; - __i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl)); + __i915_gem_object_set_pages(obj, pages); return 0; diff --git a/drivers/gpu/drm/imx/Kconfig b/drivers/gpu/drm/imx/Kconfig index 975de4ff7313..fd5b2471fdf0 100644 --- a/drivers/gpu/drm/imx/Kconfig +++ b/drivers/gpu/drm/imx/Kconfig @@ -4,7 +4,6 @@ config DRM_IMX select DRM_KMS_HELPER select VIDEOMODE_HELPERS select DRM_GEM_DMA_HELPER - select DRM_KMS_HELPER depends on DRM && (ARCH_MXC || ARCH_MULTIPLATFORM || COMPILE_TEST) depends on IMX_IPUV3_CORE help diff --git a/drivers/gpu/drm/imx/dcss/dcss-kms.c b/drivers/gpu/drm/imx/dcss/dcss-kms.c index b4f82ebca532..18df3888b7f9 100644 --- a/drivers/gpu/drm/imx/dcss/dcss-kms.c +++ b/drivers/gpu/drm/imx/dcss/dcss-kms.c @@ -7,7 +7,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge_connector.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_of.h> @@ -21,7 +21,6 @@ DEFINE_DRM_GEM_DMA_FOPS(dcss_cma_fops); static const struct drm_mode_config_funcs dcss_drm_mode_config_funcs = { .fb_create = drm_gem_fb_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 8dd8b0f912af..e060fa6cbcb9 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -16,7 +16,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 41799011f73b..c45fc8f4744d 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -7,6 +7,7 @@ #include <linux/clk.h> #include <linux/component.h> +#include <linux/i2c.h> #include <linux/media-bus-format.h> #include <linux/mfd/syscon.h> #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> @@ -23,7 +24,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_managed.h> #include <drm/drm_of.h> #include <drm/drm_panel.h> diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 6b34fac3f73a..d6832f506322 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -19,7 +19,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_managed.h> #include <drm/drm_probe_helper.h> #include <drm/drm_simple_kms_helper.h> @@ -218,8 +217,9 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector) return ret; } -static int imx_tve_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +imx_tve_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct imx_tve *tve = con_to_tve(connector); unsigned long rate; diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 06723b2e9b84..0fa0b590830b 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -8,6 +8,7 @@ #include <linux/component.h> #include <linux/media-bus-format.h> #include <linux/module.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/videodev2.h> @@ -16,7 +17,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_managed.h> #include <drm/drm_of.h> #include <drm/drm_panel.h> diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index ab0515d2c420..3d5af44bf92d 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -32,7 +32,7 @@ #include <drm/drm_encoder.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> @@ -1018,7 +1018,6 @@ static const struct drm_bridge_funcs ingenic_drm_bridge_funcs = { static const struct drm_mode_config_funcs ingenic_drm_mode_config_funcs = { .fb_create = ingenic_drm_gem_fb_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; @@ -1629,7 +1628,11 @@ static int ingenic_drm_init(void) return err; } - return platform_driver_register(&ingenic_drm_driver); + err = platform_driver_register(&ingenic_drm_driver); + if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU) && err) + platform_driver_unregister(ingenic_ipu_driver_ptr); + + return err; } module_init(ingenic_drm_init); diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c index 2382ccb3ee99..d29c678f6c91 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.c +++ b/drivers/gpu/drm/kmb/kmb_drv.c @@ -15,7 +15,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/kmb/kmb_plane.c b/drivers/gpu/drm/kmb/kmb_plane.c index a42f63f6f957..d172a302f902 100644 --- a/drivers/gpu/drm/kmb/kmb_plane.c +++ b/drivers/gpu/drm/kmb/kmb_plane.c @@ -9,7 +9,6 @@ #include <drm/drm_crtc.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_dma_helper.h> diff --git a/drivers/gpu/drm/lima/lima_devfreq.c b/drivers/gpu/drm/lima/lima_devfreq.c index 011be7ff51e1..bc8fb4e38d0a 100644 --- a/drivers/gpu/drm/lima/lima_devfreq.c +++ b/drivers/gpu/drm/lima/lima_devfreq.c @@ -112,11 +112,6 @@ int lima_devfreq_init(struct lima_device *ldev) unsigned long cur_freq; int ret; const char *regulator_names[] = { "mali", NULL }; - const char *clk_names[] = { "core", NULL }; - struct dev_pm_opp_config config = { - .regulator_names = regulator_names, - .clk_names = clk_names, - }; if (!device_property_present(dev, "operating-points-v2")) /* Optional, continue without devfreq */ @@ -124,7 +119,15 @@ int lima_devfreq_init(struct lima_device *ldev) spin_lock_init(&ldevfreq->lock); - ret = devm_pm_opp_set_config(dev, &config); + /* + * clkname is set separately so it is not affected by the optional + * regulator setting which may return error. + */ + ret = devm_pm_opp_set_clkname(dev, "core"); + if (ret) + return ret; + + ret = devm_pm_opp_set_regulators(dev, regulator_names); if (ret) { /* Continue if the optional regulator is missing */ if (ret != -ENODEV) diff --git a/drivers/gpu/drm/logicvc/logicvc_drm.c b/drivers/gpu/drm/logicvc/logicvc_drm.c index cc9a4e965f77..9de24d9f0c96 100644 --- a/drivers/gpu/drm/logicvc/logicvc_drm.c +++ b/drivers/gpu/drm/logicvc/logicvc_drm.c @@ -17,7 +17,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_print.h> diff --git a/drivers/gpu/drm/logicvc/logicvc_mode.c b/drivers/gpu/drm/logicvc/logicvc_mode.c index d8207ffda1af..9971950ebd4e 100644 --- a/drivers/gpu/drm/logicvc/logicvc_mode.c +++ b/drivers/gpu/drm/logicvc/logicvc_mode.c @@ -10,7 +10,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_mode_config.h> @@ -26,7 +25,6 @@ static const struct drm_mode_config_funcs logicvc_mode_config_funcs = { .fb_create = drm_gem_fb_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index 1c4482ad507d..4aedb050d2a5 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -69,7 +69,7 @@ #include <drm/drm_bridge.h> #include <drm/drm_drv.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> @@ -203,7 +203,6 @@ DEFINE_DRM_GEM_DMA_FOPS(drm_fops); static const struct drm_driver mcde_drm_driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, - .lastclose = drm_fb_helper_lastclose, .ioctls = NULL, .fops = &drm_fops, .name = "mcde", diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 002b0f6cae1a..84daeaffab6a 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -29,17 +29,22 @@ #define DISP_REG_OVL_DATAPATH_CON 0x0024 #define OVL_LAYER_SMI_ID_EN BIT(0) #define OVL_BGCLR_SEL_IN BIT(2) +#define OVL_LAYER_AFBC_EN(n) BIT(4+n) #define DISP_REG_OVL_ROI_BGCLR 0x0028 #define DISP_REG_OVL_SRC_CON 0x002c #define DISP_REG_OVL_CON(n) (0x0030 + 0x20 * (n)) #define DISP_REG_OVL_SRC_SIZE(n) (0x0038 + 0x20 * (n)) #define DISP_REG_OVL_OFFSET(n) (0x003c + 0x20 * (n)) +#define DISP_REG_OVL_PITCH_MSB(n) (0x0040 + 0x20 * (n)) +#define OVL_PITCH_MSB_2ND_SUBBUF BIT(16) #define DISP_REG_OVL_PITCH(n) (0x0044 + 0x20 * (n)) #define DISP_REG_OVL_RDMA_CTRL(n) (0x00c0 + 0x20 * (n)) #define DISP_REG_OVL_RDMA_GMC(n) (0x00c8 + 0x20 * (n)) #define DISP_REG_OVL_ADDR_MT2701 0x0040 #define DISP_REG_OVL_ADDR_MT8173 0x0f40 #define DISP_REG_OVL_ADDR(ovl, n) ((ovl)->data->addr + 0x20 * (n)) +#define DISP_REG_OVL_HDR_ADDR(ovl, n) ((ovl)->data->addr + 0x20 * (n) + 0x04) +#define DISP_REG_OVL_HDR_PITCH(ovl, n) ((ovl)->data->addr + 0x20 * (n) + 0x08) #define GMC_THRESHOLD_BITS 16 #define GMC_THRESHOLD_HIGH ((1 << GMC_THRESHOLD_BITS) / 4) @@ -67,6 +72,7 @@ struct mtk_disp_ovl_data { unsigned int layer_nr; bool fmt_rgb565_is_0; bool smi_id_en; + bool supports_afbc; }; /* @@ -172,7 +178,14 @@ void mtk_ovl_stop(struct device *dev) reg = reg & ~OVL_LAYER_SMI_ID_EN; writel_relaxed(reg, ovl->regs + DISP_REG_OVL_DATAPATH_CON); } +} +static void mtk_ovl_set_afbc(struct mtk_disp_ovl *ovl, struct cmdq_pkt *cmdq_pkt, + int idx, bool enabled) +{ + mtk_ddp_write_mask(cmdq_pkt, enabled ? OVL_LAYER_AFBC_EN(idx) : 0, + &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_DATAPATH_CON, OVL_LAYER_AFBC_EN(idx)); } void mtk_ovl_config(struct device *dev, unsigned int w, @@ -310,11 +323,23 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); struct mtk_plane_pending_state *pending = &state->pending; unsigned int addr = pending->addr; - unsigned int pitch = pending->pitch & 0xffff; + unsigned int hdr_addr = pending->hdr_addr; + unsigned int pitch = pending->pitch; + unsigned int hdr_pitch = pending->hdr_pitch; unsigned int fmt = pending->format; unsigned int offset = (pending->y << 16) | pending->x; unsigned int src_size = (pending->height << 16) | pending->width; unsigned int con; + bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR; + union overlay_pitch { + struct split_pitch { + u16 lsb; + u16 msb; + } split_pitch; + u32 pitch; + } overlay_pitch; + + overlay_pitch.pitch = pitch; if (!pending->enable) { mtk_ovl_layer_off(dev, idx, cmdq_pkt); @@ -335,9 +360,12 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, addr += pending->pitch - 1; } + if (ovl->data->supports_afbc) + mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, is_afbc); + mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_CON(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, pitch, &ovl->cmdq_reg, ovl->regs, + mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx)); mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_SRC_SIZE(idx)); @@ -346,6 +374,20 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, mtk_ddp_write_relaxed(cmdq_pkt, addr, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ADDR(ovl, idx)); + if (is_afbc) { + mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_ADDR(ovl, idx)); + mtk_ddp_write_relaxed(cmdq_pkt, + OVL_PITCH_MSB_2ND_SUBBUF | overlay_pitch.split_pitch.msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_PITCH(ovl, idx)); + } else { + mtk_ddp_write_relaxed(cmdq_pkt, + overlay_pitch.split_pitch.msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + } + mtk_ovl_layer_on(dev, idx, cmdq_pkt); } @@ -492,6 +534,15 @@ static const struct mtk_disp_ovl_data mt8192_ovl_2l_driver_data = { .smi_id_en = true, }; +static const struct mtk_disp_ovl_data mt8195_ovl_driver_data = { + .addr = DISP_REG_OVL_ADDR_MT8173, + .gmc_bits = 10, + .layer_nr = 4, + .fmt_rgb565_is_0 = true, + .smi_id_en = true, + .supports_afbc = true, +}; + static const struct of_device_id mtk_disp_ovl_driver_dt_match[] = { { .compatible = "mediatek,mt2701-disp-ovl", .data = &mt2701_ovl_driver_data}, @@ -505,6 +556,8 @@ static const struct of_device_id mtk_disp_ovl_driver_dt_match[] = { .data = &mt8192_ovl_driver_data}, { .compatible = "mediatek,mt8192-disp-ovl-2l", .data = &mt8192_ovl_2l_driver_data}, + { .compatible = "mediatek,mt8195-disp-ovl", + .data = &mt8195_ovl_driver_data}, {}, }; MODULE_DEVICE_TABLE(of, mtk_disp_ovl_driver_dt_match); diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 508a6d994e83..4317595a15d1 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -461,9 +461,6 @@ static void mtk_dpi_power_off(struct mtk_dpi *dpi) if (--dpi->refcount != 0) return; - if (dpi->pinctrl && dpi->pins_gpio) - pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio); - mtk_dpi_disable(dpi); clk_disable_unprepare(dpi->pixel_clk); clk_disable_unprepare(dpi->engine_clk); @@ -488,9 +485,6 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi) goto err_pixel; } - if (dpi->pinctrl && dpi->pins_dpi) - pinctrl_select_state(dpi->pinctrl, dpi->pins_dpi); - return 0; err_pixel: @@ -721,12 +715,18 @@ static void mtk_dpi_bridge_disable(struct drm_bridge *bridge) struct mtk_dpi *dpi = bridge_to_dpi(bridge); mtk_dpi_power_off(dpi); + + if (dpi->pinctrl && dpi->pins_gpio) + pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio); } static void mtk_dpi_bridge_enable(struct drm_bridge *bridge) { struct mtk_dpi *dpi = bridge_to_dpi(bridge); + if (dpi->pinctrl && dpi->pins_dpi) + pinctrl_select_state(dpi->pinctrl, dpi->pins_dpi); + mtk_dpi_power_on(dpi); mtk_dpi_set_display_mode(dpi, &dpi->mode); mtk_dpi_enable(dpi); @@ -929,6 +929,20 @@ static const struct mtk_dpi_conf mt8183_conf = { .csc_enable_bit = CSC_ENABLE, }; +static const struct mtk_dpi_conf mt8188_dpintf_conf = { + .cal_factor = mt8195_dpintf_calculate_factor, + .max_clock_khz = 600000, + .output_fmts = mt8195_output_fmts, + .num_output_fmts = ARRAY_SIZE(mt8195_output_fmts), + .pixels_per_iter = 4, + .input_2pixel = false, + .dimension_mask = DPINTF_HPW_MASK, + .hvsize_mask = DPINTF_HSIZE_MASK, + .channel_swap_shift = DPINTF_CH_SWAP, + .yuv422_en_bit = DPINTF_YUV422_EN, + .csc_enable_bit = DPINTF_CSC_ENABLE, +}; + static const struct mtk_dpi_conf mt8192_conf = { .cal_factor = mt8183_calculate_factor, .reg_h_fre_con = 0xe0, @@ -1079,6 +1093,9 @@ static const struct of_device_id mtk_dpi_of_ids[] = { { .compatible = "mediatek,mt8183-dpi", .data = &mt8183_conf, }, + { .compatible = "mediatek,mt8188-dp-intf", + .data = &mt8188_dpintf_conf, + }, { .compatible = "mediatek,mt8192-dpi", .data = &mt8192_conf, }, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 91f58db5915f..cd5b18ef7951 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -17,7 +17,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem.h> #include <drm/drm_gem_dma_helper.h> @@ -387,6 +387,12 @@ static int mtk_drm_kms_init(struct drm_device *drm) goto put_mutex_dev; /* + * Ensure internal panels are at the top of the connector list before + * crtc creation. + */ + drm_helper_move_panel_connectors_to_head(drm); + + /* * We currently support two fixed data streams, each optional, * and each statically assigned to a crtc: * OVL0 -> COLOR0 -> AAL -> OD -> RDMA0 -> UFOE -> DSI0 ... @@ -631,6 +637,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = { .data = (void *)MTK_DPI }, { .compatible = "mediatek,mt8183-dpi", .data = (void *)MTK_DPI }, + { .compatible = "mediatek,mt8188-dp-intf", + .data = (void *)MTK_DP_INTF }, { .compatible = "mediatek,mt8192-dpi", .data = (void *)MTK_DPI }, { .compatible = "mediatek,mt8195-dp-intf", diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index 2f5e007dd380..d54fbf34b000 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -11,6 +11,7 @@ #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> +#include <linux/align.h> #include "mtk_drm_crtc.h" #include "mtk_drm_ddp_comp.h" @@ -32,6 +33,14 @@ static const u32 formats[] = { DRM_FORMAT_YUYV, }; +static const u64 modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_SPLIT | + AFBC_FORMAT_MOD_SPARSE), + DRM_FORMAT_MOD_INVALID, +}; + static void mtk_plane_reset(struct drm_plane *plane) { struct mtk_plane_state *state; @@ -51,6 +60,7 @@ static void mtk_plane_reset(struct drm_plane *plane) state->base.plane = plane; state->pending.format = DRM_FORMAT_RGB565; + state->pending.modifier = DRM_FORMAT_MOD_LINEAR; } static struct drm_plane_state *mtk_plane_duplicate_state(struct drm_plane *plane) @@ -71,6 +81,32 @@ static struct drm_plane_state *mtk_plane_duplicate_state(struct drm_plane *plane return &state->base; } +static bool mtk_plane_format_mod_supported(struct drm_plane *plane, + uint32_t format, + uint64_t modifier) +{ + if (modifier == DRM_FORMAT_MOD_LINEAR) + return true; + + if (modifier != DRM_FORMAT_MOD_ARM_AFBC( + AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_SPLIT | + AFBC_FORMAT_MOD_SPARSE)) + return false; + + if (format != DRM_FORMAT_XRGB8888 && + format != DRM_FORMAT_ARGB8888 && + format != DRM_FORMAT_BGRX8888 && + format != DRM_FORMAT_BGRA8888 && + format != DRM_FORMAT_ABGR8888 && + format != DRM_FORMAT_XBGR8888 && + format != DRM_FORMAT_RGB888 && + format != DRM_FORMAT_BGR888) + return false; + + return true; +} + static void mtk_drm_plane_destroy_state(struct drm_plane *plane, struct drm_plane_state *state) { @@ -119,21 +155,52 @@ static void mtk_plane_update_new_state(struct drm_plane_state *new_state, struct drm_gem_object *gem; struct mtk_drm_gem_obj *mtk_gem; unsigned int pitch, format; + u64 modifier; dma_addr_t addr; + dma_addr_t hdr_addr = 0; + unsigned int hdr_pitch = 0; gem = fb->obj[0]; mtk_gem = to_mtk_gem_obj(gem); addr = mtk_gem->dma_addr; pitch = fb->pitches[0]; format = fb->format->format; + modifier = fb->modifier; - addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; - addr += (new_state->src.y1 >> 16) * pitch; + if (modifier == DRM_FORMAT_MOD_LINEAR) { + addr += (new_state->src.x1 >> 16) * fb->format->cpp[0]; + addr += (new_state->src.y1 >> 16) * pitch; + } else { + int width_in_blocks = ALIGN(fb->width, AFBC_DATA_BLOCK_WIDTH) + / AFBC_DATA_BLOCK_WIDTH; + int height_in_blocks = ALIGN(fb->height, AFBC_DATA_BLOCK_HEIGHT) + / AFBC_DATA_BLOCK_HEIGHT; + int x_offset_in_blocks = (new_state->src.x1 >> 16) / AFBC_DATA_BLOCK_WIDTH; + int y_offset_in_blocks = (new_state->src.y1 >> 16) / AFBC_DATA_BLOCK_HEIGHT; + int hdr_size; + + hdr_pitch = width_in_blocks * AFBC_HEADER_BLOCK_SIZE; + pitch = width_in_blocks * AFBC_DATA_BLOCK_WIDTH * + AFBC_DATA_BLOCK_HEIGHT * fb->format->cpp[0]; + + hdr_size = ALIGN(hdr_pitch * height_in_blocks, AFBC_HEADER_ALIGNMENT); + + hdr_addr = addr + hdr_pitch * y_offset_in_blocks + + AFBC_HEADER_BLOCK_SIZE * x_offset_in_blocks; + /* The data plane is offset by 1 additional block. */ + addr = addr + hdr_size + + pitch * y_offset_in_blocks + + AFBC_DATA_BLOCK_WIDTH * AFBC_DATA_BLOCK_HEIGHT * + fb->format->cpp[0] * (x_offset_in_blocks + 1); + } mtk_plane_state->pending.enable = true; mtk_plane_state->pending.pitch = pitch; + mtk_plane_state->pending.hdr_pitch = hdr_pitch; mtk_plane_state->pending.format = format; + mtk_plane_state->pending.modifier = modifier; mtk_plane_state->pending.addr = addr; + mtk_plane_state->pending.hdr_addr = hdr_addr; mtk_plane_state->pending.x = new_state->dst.x1; mtk_plane_state->pending.y = new_state->dst.y1; mtk_plane_state->pending.width = drm_rect_width(&new_state->dst); @@ -172,6 +239,7 @@ static const struct drm_plane_funcs mtk_plane_funcs = { .reset = mtk_plane_reset, .atomic_duplicate_state = mtk_plane_duplicate_state, .atomic_destroy_state = mtk_drm_plane_destroy_state, + .format_mod_supported = mtk_plane_format_mod_supported, }; static int mtk_plane_atomic_check(struct drm_plane *plane, @@ -253,7 +321,7 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, err = drm_universal_plane_init(dev, plane, possible_crtcs, &mtk_plane_funcs, formats, - ARRAY_SIZE(formats), NULL, type, NULL); + ARRAY_SIZE(formats), modifiers, type, NULL); if (err) { DRM_ERROR("failed to initialize plane\n"); return err; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.h b/drivers/gpu/drm/mediatek/mtk_drm_plane.h index 2d5ec66e3df1..8f39011cdbfc 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.h @@ -10,12 +10,20 @@ #include <drm/drm_crtc.h> #include <linux/types.h> +#define AFBC_DATA_BLOCK_WIDTH 32 +#define AFBC_DATA_BLOCK_HEIGHT 8 +#define AFBC_HEADER_BLOCK_SIZE 16 +#define AFBC_HEADER_ALIGNMENT 1024 + struct mtk_plane_pending_state { bool config; bool enable; dma_addr_t addr; + dma_addr_t hdr_addr; unsigned int pitch; + unsigned int hdr_pitch; unsigned int format; + unsigned long long modifier; unsigned int x; unsigned int y; unsigned int width; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 4c80b6896dc3..0a8e0a13f516 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1202,9 +1202,10 @@ static enum drm_connector_status mtk_hdmi_detect(struct mtk_hdmi *hdmi) return mtk_hdmi_update_plugged_status(hdmi); } -static int mtk_hdmi_bridge_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode) +static enum drm_mode_status +mtk_hdmi_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) { struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); struct drm_bridge *next_bridge; @@ -1217,7 +1218,7 @@ static int mtk_hdmi_bridge_mode_valid(struct drm_bridge *bridge, if (next_bridge) { struct drm_display_mode adjusted_mode; - drm_mode_copy(&adjusted_mode, mode); + drm_mode_init(&adjusted_mode, mode); if (!drm_bridge_chain_mode_fixup(next_bridge, mode, &adjusted_mode)) return MODE_BAD; diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 3b24a924b7b9..79bfe3938d3c 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -18,7 +18,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_modeset_helper_vtables.h> diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c index 5675bc2a92cf..3f73b211fa8e 100644 --- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c +++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c @@ -116,9 +116,10 @@ static int meson_encoder_cvbs_get_modes(struct drm_bridge *bridge, return i; } -static int meson_encoder_cvbs_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *display_info, - const struct drm_display_mode *mode) +static enum drm_mode_status +meson_encoder_cvbs_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *display_info, + const struct drm_display_mode *mode) { if (meson_cvbs_get_mode(mode)) return MODE_OK; diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index ece6cd102dbb..976f0ab2006b 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -11,6 +11,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_drv.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include <drm/drm_ioctl.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index f0c2349404b4..9e604dbb8e44 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -18,7 +18,6 @@ #include <drm/drm_connector.h> #include <drm/drm_crtc.h> #include <drm/drm_encoder.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_gem.h> #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_plane.h> diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 4e0cbd682725..3c9dfdb0b328 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -155,7 +155,7 @@ config DRM_MSM_HDMI Compile in support for the HDMI output MSM DRM driver. It can be a primary or a secondary display on device. Note that this is used only for the direct HDMI output. If the device outputs HDMI data - throught some kind of DSI-to-HDMI bridge, this option can be disabled. + through some kind of DSI-to-HDMI bridge, this option can be disabled. config DRM_MSM_HDMI_HDCP bool "Enable HDMI HDCP support in MSM DRM driver" diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 2c8b9899625b..948785ed07bb 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -500,7 +500,7 @@ static const struct adreno_gpu_funcs funcs = { #endif .gpu_state_get = a3xx_gpu_state_get, .gpu_state_put = adreno_gpu_state_put, - .create_address_space = adreno_iommu_create_address_space, + .create_address_space = adreno_create_address_space, .get_rptr = a3xx_get_rptr, }, }; diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 7cb8d9849c07..3e09d3a7a0ac 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -606,8 +606,7 @@ static int a4xx_pm_suspend(struct msm_gpu *gpu) { static int a4xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO, - REG_A4XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO); return 0; } @@ -635,7 +634,7 @@ static const struct adreno_gpu_funcs funcs = { #endif .gpu_state_get = a4xx_gpu_state_get, .gpu_state_put = adreno_gpu_state_put, - .create_address_space = adreno_iommu_create_address_space, + .create_address_space = adreno_create_address_space, .get_rptr = a4xx_get_rptr, }, .get_timestamp = a4xx_get_timestamp, diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 3dcec7acb384..660ba0db8900 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -605,11 +605,9 @@ static int a5xx_ucode_init(struct msm_gpu *gpu) a5xx_ucode_check_version(a5xx_gpu, a5xx_gpu->pfp_bo); } - gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, - REG_A5XX_CP_ME_INSTR_BASE_HI, a5xx_gpu->pm4_iova); + gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, a5xx_gpu->pm4_iova); - gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, - REG_A5XX_CP_PFP_INSTR_BASE_HI, a5xx_gpu->pfp_iova); + gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, a5xx_gpu->pfp_iova); return 0; } @@ -868,8 +866,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) * memory rendering at this point in time and we don't want to block off * part of the virtual memory space. */ - gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, - REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); + gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000); gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); /* Put the GPU into 64 bit by default */ @@ -908,8 +905,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) return ret; /* Set the ringbuffer address */ - gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI, - gpu->rb[0]->iova); + gpu_write64(gpu, REG_A5XX_CP_RB_BASE, gpu->rb[0]->iova); /* * If the microcode supports the WHERE_AM_I opcode then we can use that @@ -936,7 +932,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) } gpu_write64(gpu, REG_A5XX_CP_RB_RPTR_ADDR, - REG_A5XX_CP_RB_RPTR_ADDR_HI, shadowptr(a5xx_gpu, gpu->rb[0])); + shadowptr(a5xx_gpu, gpu->rb[0])); } else if (gpu->nr_rings > 1) { /* Disable preemption if WHERE_AM_I isn't available */ a5xx_preempt_fini(gpu); @@ -1239,9 +1235,9 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A5XX_RBBM_STATUS), gpu_read(gpu, REG_A5XX_CP_RB_RPTR), gpu_read(gpu, REG_A5XX_CP_RB_WPTR), - gpu_read64(gpu, REG_A5XX_CP_IB1_BASE, REG_A5XX_CP_IB1_BASE_HI), + gpu_read64(gpu, REG_A5XX_CP_IB1_BASE), gpu_read(gpu, REG_A5XX_CP_IB1_BUFSZ), - gpu_read64(gpu, REG_A5XX_CP_IB2_BASE, REG_A5XX_CP_IB2_BASE_HI), + gpu_read64(gpu, REG_A5XX_CP_IB2_BASE), gpu_read(gpu, REG_A5XX_CP_IB2_BUFSZ)); /* Turn off the hangcheck timer to keep it from bothering us */ @@ -1427,8 +1423,7 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO, - REG_A5XX_RBBM_ALWAYSON_COUNTER_HI); + *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO); return 0; } @@ -1465,8 +1460,7 @@ static int a5xx_crashdumper_run(struct msm_gpu *gpu, if (IS_ERR_OR_NULL(dumper->ptr)) return -EINVAL; - gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, - REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova); gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1); @@ -1666,8 +1660,7 @@ static u64 a5xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate) { u64 busy_cycles; - busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO, - REG_A5XX_RBBM_PERFCTR_RBBM_0_HI); + busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO); *out_sample_rate = clk_get_rate(gpu->core_clk); return busy_cycles; @@ -1705,7 +1698,7 @@ static const struct adreno_gpu_funcs funcs = { .gpu_busy = a5xx_gpu_busy, .gpu_state_get = a5xx_gpu_state_get, .gpu_state_put = a5xx_gpu_state_put, - .create_address_space = adreno_iommu_create_address_space, + .create_address_space = adreno_create_address_space, .get_rptr = a5xx_get_rptr, }, .get_timestamp = a5xx_get_timestamp, diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 8abc9a2b114a..7658e89844b4 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -137,7 +137,6 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) /* Set the address of the incoming preemption record */ gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_LO, - REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_HI, a5xx_gpu->preempt_iova[ring->id]); a5xx_gpu->next_ring = ring; @@ -211,8 +210,7 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) } /* Write a 0 to signal that we aren't switching pagetables */ - gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, - REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_HI, 0); + gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, 0); /* Reset the preemption state */ set_preempt_state(a5xx_gpu, PREEMPT_NONE); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index e033d6a67a20..6484b97c5344 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -1213,19 +1213,17 @@ static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo, static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu) { - struct iommu_domain *domain; struct msm_mmu *mmu; - domain = iommu_domain_alloc(&platform_bus_type); - if (!domain) + mmu = msm_iommu_new(gmu->dev, 0); + if (!mmu) return -ENODEV; + if (IS_ERR(mmu)) + return PTR_ERR(mmu); - mmu = msm_iommu_new(gmu->dev, domain); gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x80000000); - if (IS_ERR(gmu->aspace)) { - iommu_domain_free(domain); + if (IS_ERR(gmu->aspace)) return PTR_ERR(gmu->aspace); - } return 0; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index fdc578016e0b..36c8fb699b56 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -247,8 +247,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, submit->seqno); trace_msm_gpu_submit_flush(submit, - gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, - REG_A6XX_CP_ALWAYS_ON_COUNTER_HI)); + gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO)); a6xx_flush(gpu, ring); } @@ -947,8 +946,7 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) } } - gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, - REG_A6XX_CP_SQE_INSTR_BASE+1, a6xx_gpu->sqe_iova); + gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova); return 0; } @@ -999,8 +997,7 @@ static int hw_init(struct msm_gpu *gpu) * memory rendering at this point in time and we don't want to block off * part of the virtual memory space. */ - gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, - REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); + gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000); gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); /* Turn on 64 bit addressing for all blocks */ @@ -1049,11 +1046,9 @@ static int hw_init(struct msm_gpu *gpu) if (!adreno_is_a650_family(adreno_gpu)) { /* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */ - gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO, - REG_A6XX_UCHE_GMEM_RANGE_MIN_HI, 0x00100000); + gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000); gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MAX_LO, - REG_A6XX_UCHE_GMEM_RANGE_MAX_HI, 0x00100000 + adreno_gpu->gmem - 1); } @@ -1145,8 +1140,7 @@ static int hw_init(struct msm_gpu *gpu) goto out; /* Set the ringbuffer address */ - gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI, - gpu->rb[0]->iova); + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, gpu->rb[0]->iova); /* Targets that support extended APRIV can use the RPTR shadow from * hardware but all the other ones need to disable the feature. Targets @@ -1178,7 +1172,6 @@ static int hw_init(struct msm_gpu *gpu) } gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR_LO, - REG_A6XX_CP_RB_RPTR_ADDR_HI, shadowptr(a6xx_gpu, gpu->rb[0])); } @@ -1499,9 +1492,9 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A6XX_RBBM_STATUS), gpu_read(gpu, REG_A6XX_CP_RB_RPTR), gpu_read(gpu, REG_A6XX_CP_RB_WPTR), - gpu_read64(gpu, REG_A6XX_CP_IB1_BASE, REG_A6XX_CP_IB1_BASE_HI), + gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), - gpu_read64(gpu, REG_A6XX_CP_IB2_BASE, REG_A6XX_CP_IB2_BASE_HI), + gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE)); /* Turn off the hangcheck timer to keep it from bothering us */ @@ -1712,8 +1705,7 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) /* Force the GPU power on so we can read this register */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, - REG_A6XX_CP_ALWAYS_ON_COUNTER_HI); + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO); a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); @@ -1786,43 +1778,16 @@ a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); - struct iommu_domain *iommu; - struct msm_mmu *mmu; - struct msm_gem_address_space *aspace; - u64 start, size; - - iommu = iommu_domain_alloc(&platform_bus_type); - if (!iommu) - return NULL; + unsigned long quirks = 0; /* * This allows GPU to set the bus attributes required to use system * cache on behalf of the iommu page table walker. */ if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice)) - adreno_set_llc_attributes(iommu); - - mmu = msm_iommu_new(&pdev->dev, iommu); - if (IS_ERR(mmu)) { - iommu_domain_free(iommu); - return ERR_CAST(mmu); - } - - /* - * Use the aperture start or SZ_16M, whichever is greater. This will - * ensure that we align with the allocated pagetable range while still - * allowing room in the lower 32 bits for GMEM and whatnot - */ - start = max_t(u64, SZ_16M, iommu->geometry.aperture_start); - size = iommu->geometry.aperture_end - start + 1; - - aspace = msm_gem_address_space_create(mmu, "gpu", - start & GENMASK_ULL(48, 0), size); + quirks |= IO_PGTABLE_QUIRK_ARM_OUTER_WBWA; - if (IS_ERR(aspace) && !IS_ERR(mmu)) - mmu->funcs->destroy(mmu); - - return aspace; + return adreno_iommu_create_address_space(gpu, pdev, quirks); } static struct msm_gem_address_space * @@ -1851,6 +1816,39 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR); } +static bool a6xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct msm_cp_state cp_state = { + .ib1_base = gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), + .ib2_base = gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), + .ib1_rem = gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), + .ib2_rem = gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE), + }; + bool progress; + + /* + * Adjust the remaining data to account for what has already been + * fetched from memory, but not yet consumed by the SQE. + * + * This is not *technically* correct, the amount buffered could + * exceed the IB size due to hw prefetching ahead, but: + * + * (1) We aren't trying to find the exact position, just whether + * progress has been made + * (2) The CP_REG_TO_MEM at the end of a submit should be enough + * to prevent prefetching into an unrelated submit. (And + * either way, at some point the ROQ will be full.) + */ + cp_state.ib1_rem += gpu_read(gpu, REG_A6XX_CP_CSQ_IB1_STAT) >> 16; + cp_state.ib2_rem += gpu_read(gpu, REG_A6XX_CP_CSQ_IB2_STAT) >> 16; + + progress = !!memcmp(&cp_state, &ring->last_cp_state, sizeof(cp_state)); + + ring->last_cp_state = cp_state; + + return progress; +} + static u32 a618_get_speed_bin(u32 fuse) { if (fuse == 0) @@ -1906,7 +1904,7 @@ static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse) if (val == UINT_MAX) { DRM_DEV_ERROR(dev, - "missing support for speed-bin: %u. Some OPPs may not be supported by hardware", + "missing support for speed-bin: %u. Some OPPs may not be supported by hardware\n", fuse); return UINT_MAX; } @@ -1916,7 +1914,7 @@ static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse) static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev) { - u32 supp_hw = UINT_MAX; + u32 supp_hw; u32 speedbin; int ret; @@ -1928,15 +1926,13 @@ static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev) if (ret == -ENOENT) { return 0; } else if (ret) { - DRM_DEV_ERROR(dev, - "failed to read speed-bin (%d). Some OPPs may not be supported by hardware", - ret); - goto done; + dev_err_probe(dev, ret, + "failed to read speed-bin. Some OPPs may not be supported by hardware\n"); + return ret; } supp_hw = fuse_to_supp_hw(dev, rev, speedbin); -done: ret = devm_pm_opp_set_supported_hw(dev, &supp_hw, 1); if (ret) return ret; @@ -1969,6 +1965,7 @@ static const struct adreno_gpu_funcs funcs = { .create_address_space = a6xx_create_address_space, .create_private_address_space = a6xx_create_private_address_space, .get_rptr = a6xx_get_rptr, + .progress = a6xx_progress, }, .get_timestamp = a6xx_get_timestamp, }; @@ -2005,13 +2002,6 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), info->rev))) adreno_gpu->base.hw_apriv = true; - /* - * For now only clamp to idle freq for devices where this is known not - * to cause power supply issues: - */ - if (info && (info->revn == 618)) - gpu->clamp_to_idle = true; - a6xx_llc_slices_init(pdev, a6xx_gpu); ret = a6xx_set_supported_hw(&pdev->dev, config->rev); @@ -2026,6 +2016,13 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) return ERR_PTR(ret); } + /* + * For now only clamp to idle freq for devices where this is known not + * to cause power supply issues: + */ + if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu)) + gpu->clamp_to_idle = true; + /* Check if there is a GMU phandle and set it up */ node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 55f443328d8e..a023d5f962dc 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -91,7 +91,7 @@ struct a6xx_state_memobj { static void *state_kcalloc(struct a6xx_gpu_state *a6xx_state, int nr, size_t objsize) { struct a6xx_state_memobj *obj = - kzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL); + kvzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL); if (!obj) return NULL; @@ -147,8 +147,7 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu, /* Make sure all pending memory writes are posted */ wmb(); - gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, - REG_A6XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova); gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 1); @@ -813,6 +812,9 @@ static struct msm_gpu_state_bo *a6xx_snapshot_gmu_bo( { struct msm_gpu_state_bo *snapshot; + if (!bo->size) + return NULL; + snapshot = state_kcalloc(a6xx_state, 1, sizeof(*snapshot)); if (!snapshot) return NULL; @@ -1040,8 +1042,13 @@ static void a6xx_gpu_state_destroy(struct kref *kref) if (a6xx_state->gmu_hfi) kvfree(a6xx_state->gmu_hfi->data); - list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node) - kfree(obj); + if (a6xx_state->gmu_debug) + kvfree(a6xx_state->gmu_debug->data); + + list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node) { + list_del(&obj->node); + kvfree(obj); + } adreno_gpu_state_destroy(state); kfree(a6xx_state); diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 24b489b6129a..628806423f7d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -679,6 +679,9 @@ static int adreno_system_suspend(struct device *dev) struct msm_gpu *gpu = dev_to_gpu(dev); int remaining, ret; + if (!gpu) + return 0; + suspend_scheduler(gpu); remaining = wait_event_timeout(gpu->retire_event, @@ -700,7 +703,12 @@ out: static int adreno_system_resume(struct device *dev) { - resume_scheduler(dev_to_gpu(dev)); + struct msm_gpu *gpu = dev_to_gpu(dev); + + if (!gpu) + return 0; + + resume_scheduler(gpu); return pm_runtime_force_resume(dev); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 382fb7f9e497..57586c794b84 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -191,37 +191,38 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid) return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid); } -void adreno_set_llc_attributes(struct iommu_domain *iommu) +struct msm_gem_address_space * +adreno_create_address_space(struct msm_gpu *gpu, + struct platform_device *pdev) { - iommu_set_pgtable_quirks(iommu, IO_PGTABLE_QUIRK_ARM_OUTER_WBWA); + return adreno_iommu_create_address_space(gpu, pdev, 0); } struct msm_gem_address_space * adreno_iommu_create_address_space(struct msm_gpu *gpu, - struct platform_device *pdev) + struct platform_device *pdev, + unsigned long quirks) { - struct iommu_domain *iommu; + struct iommu_domain_geometry *geometry; struct msm_mmu *mmu; struct msm_gem_address_space *aspace; u64 start, size; - iommu = iommu_domain_alloc(&platform_bus_type); - if (!iommu) - return NULL; - - mmu = msm_iommu_new(&pdev->dev, iommu); - if (IS_ERR(mmu)) { - iommu_domain_free(iommu); + mmu = msm_iommu_new(&pdev->dev, quirks); + if (IS_ERR_OR_NULL(mmu)) return ERR_CAST(mmu); - } + + geometry = msm_iommu_get_geometry(mmu); + if (IS_ERR(geometry)) + return ERR_CAST(geometry); /* * Use the aperture start or SZ_16M, whichever is greater. This will * ensure that we align with the allocated pagetable range while still * allowing room in the lower 32 bits for GMEM and whatnot */ - start = max_t(u64, SZ_16M, iommu->geometry.aperture_start); - size = iommu->geometry.aperture_end - start + 1; + start = max_t(u64, SZ_16M, geometry->aperture_start); + size = geometry->aperture_end - start + 1; aspace = msm_gem_address_space_create(mmu, "gpu", start & GENMASK_ULL(48, 0), size); @@ -729,7 +730,12 @@ static char *adreno_gpu_ascii85_encode(u32 *src, size_t len) return buf; } -/* len is expected to be in bytes */ +/* len is expected to be in bytes + * + * WARNING: *ptr should be allocated with kvmalloc or friends. It can be free'd + * with kvfree() and replaced with a newly kvmalloc'd buffer on the first call + * when the unencoded raw data is encoded + */ void adreno_show_object(struct drm_printer *p, void **ptr, int len, bool *encoded) { diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index e7adc5c632d0..5d4b1c95033f 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -335,10 +335,13 @@ void adreno_show_object(struct drm_printer *p, void **ptr, int len, * attached targets */ struct msm_gem_address_space * -adreno_iommu_create_address_space(struct msm_gpu *gpu, - struct platform_device *pdev); +adreno_create_address_space(struct msm_gpu *gpu, + struct platform_device *pdev); -void adreno_set_llc_attributes(struct iommu_domain *iommu); +struct msm_gem_address_space * +adreno_iommu_create_address_space(struct msm_gpu *gpu, + struct platform_device *pdev, + unsigned long quirks); int adreno_read_speedbin(struct device *dev, u32 *speedbin); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index 2c14646661b7..0f71e8fe7be7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -237,12 +237,13 @@ static void dpu_encoder_phys_vid_setup_timing_engine( unsigned long lock_flags; struct dpu_hw_intf_cfg intf_cfg = { 0 }; + drm_mode_init(&mode, &phys_enc->cached_mode); + if (!phys_enc->hw_ctl->ops.setup_intf_cfg) { DPU_ERROR("invalid encoder %d\n", phys_enc != NULL); return; } - mode = phys_enc->cached_mode; if (!phys_enc->hw_intf->ops.setup_timing_gen) { DPU_ERROR("timing engine setup is not supported\n"); return; @@ -634,7 +635,9 @@ static int dpu_encoder_phys_vid_get_frame_count( { struct intf_status s = {0}; u32 fetch_start = 0; - struct drm_display_mode mode = phys_enc->cached_mode; + struct drm_display_mode mode; + + drm_mode_init(&mode, &phys_enc->cached_mode); if (!dpu_encoder_phys_vid_is_master(phys_enc)) return -EINVAL; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c index f436a1f3419d..d95540309d4d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c @@ -434,6 +434,12 @@ static const struct dpu_format dpu_format_map[] = { DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV, DPU_FETCH_LINEAR, 2), + PSEUDO_YUV_FMT_LOOSE(P010, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + INTERLEAVED_YUV_FMT(VYUY, 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, C2_R_Cr, C0_G_Y, C1_B_Cb, C0_G_Y, @@ -524,12 +530,26 @@ static const struct dpu_format dpu_format_map_ubwc[] = { true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED, DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC), + INTERLEAVED_RGB_FMT_TILED(XRGB2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC), + PSEUDO_YUV_FMT_TILED(NV12, 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, C1_B_Cb, C2_R_Cr, DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_COMPRESSED, DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12), + + PSEUDO_YUV_FMT_TILED(P010, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, DPU_FORMAT_FLAG_DX | + DPU_FORMAT_FLAG_YUV | + DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_UBWC), }; /* _dpu_get_v_h_subsample_rate - Get subsample rates for all formats we support @@ -571,13 +591,15 @@ static int _dpu_format_get_media_color_ubwc(const struct dpu_format *fmt) {DRM_FORMAT_XBGR8888, COLOR_FMT_RGBA8888_UBWC}, {DRM_FORMAT_XRGB8888, COLOR_FMT_RGBA8888_UBWC}, {DRM_FORMAT_ABGR2101010, COLOR_FMT_RGBA1010102_UBWC}, + {DRM_FORMAT_XRGB2101010, COLOR_FMT_RGBA1010102_UBWC}, {DRM_FORMAT_XBGR2101010, COLOR_FMT_RGBA1010102_UBWC}, {DRM_FORMAT_BGR565, COLOR_FMT_RGB565_UBWC}, }; int color_fmt = -1; int i; - if (fmt->base.pixel_format == DRM_FORMAT_NV12) { + if (fmt->base.pixel_format == DRM_FORMAT_NV12 || + fmt->base.pixel_format == DRM_FORMAT_P010) { if (DPU_FORMAT_IS_DX(fmt)) { if (fmt->unpack_tight) color_fmt = COLOR_FMT_NV12_BPP10_UBWC; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 27f029fdc682..2196e205efa5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -156,6 +156,7 @@ static const uint32_t plane_formats[] = { DRM_FORMAT_RGBX8888, DRM_FORMAT_BGRX8888, DRM_FORMAT_XBGR8888, + DRM_FORMAT_XRGB2101010, DRM_FORMAT_RGB888, DRM_FORMAT_BGR888, DRM_FORMAT_RGB565, @@ -184,6 +185,7 @@ static const uint32_t plane_formats_yuv[] = { DRM_FORMAT_RGBA8888, DRM_FORMAT_BGRX8888, DRM_FORMAT_BGRA8888, + DRM_FORMAT_XRGB2101010, DRM_FORMAT_XRGB8888, DRM_FORMAT_XBGR8888, DRM_FORMAT_RGBX8888, @@ -208,6 +210,7 @@ static const uint32_t plane_formats_yuv[] = { DRM_FORMAT_RGBX4444, DRM_FORMAT_BGRX4444, + DRM_FORMAT_P010, DRM_FORMAT_NV12, DRM_FORMAT_NV21, DRM_FORMAT_NV16, @@ -318,6 +321,18 @@ static const struct dpu_caps sc7180_dpu_caps = { .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, }; +static const struct dpu_caps sm6115_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0x4, + .qseed_type = DPU_SSPP_SCALER_QSEED3LITE, + .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ + .ubwc_version = DPU_HW_UBWC_VER_20, + .has_dim_layer = true, + .has_idle_pc = true, + .max_linewidth = 2160, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, +}; + static const struct dpu_caps sm8150_dpu_caps = { .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .max_mixer_blendstages = 0xb, @@ -472,6 +487,19 @@ static const struct dpu_mdp_cfg sc8180x_mdp[] = { }, }; +static const struct dpu_mdp_cfg sm6115_mdp[] = { + { + .name = "top_0", .id = MDP_TOP, + .base = 0x0, .len = 0x494, + .features = 0, + .highest_bank_bit = 0x1, + .clk_ctrls[DPU_CLK_CTRL_VIG0] = { + .reg_off = 0x2ac, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_DMA0] = { + .reg_off = 0x2ac, .bit_off = 8}, + }, +}; + static const struct dpu_mdp_cfg sm8250_mdp[] = { { .name = "top_0", .id = MDP_TOP, @@ -849,6 +877,16 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = { sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), }; +static const struct dpu_sspp_sub_blks sm6115_vig_sblk_0 = + _VIG_SBLK("0", 2, DPU_SSPP_SCALER_QSEED3LITE); + +static const struct dpu_sspp_cfg sm6115_sspp[] = { + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SM8250_MASK, + sm6115_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), + SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, + sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), +}; + static const struct dpu_sspp_sub_blks sm8250_vig_sblk_0 = _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3LITE); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_1 = @@ -1175,6 +1213,13 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = { -1), }; +static const struct dpu_pingpong_cfg sc7280_pp[] = { + PP_BLK("pingpong_0", PINGPONG_0, 0x59000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), +}; + static struct dpu_pingpong_cfg qcm2290_pp[] = { PP_BLK("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), @@ -1198,13 +1243,6 @@ static const struct dpu_merge_3d_cfg sm8150_merge_3d[] = { MERGE_3D_BLK("merge_3d_2", MERGE_3D_2, 0x83200), }; -static const struct dpu_pingpong_cfg sc7280_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x59000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), -}; - /************************************************************* * DSC sub blocks config *************************************************************/ @@ -1587,6 +1625,35 @@ static const struct dpu_perf_cfg sc7180_perf_data = { .bw_inefficiency_factor = 120, }; +static const struct dpu_perf_cfg sm6115_perf_data = { + .max_bw_low = 3100000, + .max_bw_high = 4000000, + .min_core_ib = 2400000, + .min_llcc_ib = 800000, + .min_dram_ib = 800000, + .min_prefill_lines = 24, + .danger_lut_tbl = {0xff, 0xffff, 0x0}, + .safe_lut_tbl = {0xfff0, 0xff00, 0xffff}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sc7180_qos_linear), + .entries = sc7180_qos_linear + }, + {.nentry = ARRAY_SIZE(sc7180_qos_macrotile), + .entries = sc7180_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_nrt), + .entries = sc7180_qos_nrt + }, + /* TODO: macrotile-qseed is different from macrotile */ + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + static const struct dpu_perf_cfg sm8150_perf_data = { .max_bw_low = 12800000, .max_bw_high = 12800000, @@ -1798,6 +1865,28 @@ static const struct dpu_mdss_cfg sc7180_dpu_cfg = { .mdss_irqs = IRQ_SC7180_MASK, }; +static const struct dpu_mdss_cfg sm6115_dpu_cfg = { + .caps = &sm6115_dpu_caps, + .mdp_count = ARRAY_SIZE(sm6115_mdp), + .mdp = sm6115_mdp, + .ctl_count = ARRAY_SIZE(qcm2290_ctl), + .ctl = qcm2290_ctl, + .sspp_count = ARRAY_SIZE(sm6115_sspp), + .sspp = sm6115_sspp, + .mixer_count = ARRAY_SIZE(qcm2290_lm), + .mixer = qcm2290_lm, + .dspp_count = ARRAY_SIZE(qcm2290_dspp), + .dspp = qcm2290_dspp, + .pingpong_count = ARRAY_SIZE(qcm2290_pp), + .pingpong = qcm2290_pp, + .intf_count = ARRAY_SIZE(qcm2290_intf), + .intf = qcm2290_intf, + .vbif_count = ARRAY_SIZE(sdm845_vbif), + .vbif = sdm845_vbif, + .perf = &sm6115_perf_data, + .mdss_irqs = IRQ_SC7180_MASK, +}; + static const struct dpu_mdss_cfg sm8150_dpu_cfg = { .caps = &sm8150_dpu_caps, .mdp_count = ARRAY_SIZE(sdm845_mdp), @@ -1932,6 +2021,7 @@ static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = { { .hw_rev = DPU_HW_VER_510, .dpu_cfg = &sc8180x_dpu_cfg}, { .hw_rev = DPU_HW_VER_600, .dpu_cfg = &sm8250_dpu_cfg}, { .hw_rev = DPU_HW_VER_620, .dpu_cfg = &sc7180_dpu_cfg}, + { .hw_rev = DPU_HW_VER_630, .dpu_cfg = &sm6115_dpu_cfg}, { .hw_rev = DPU_HW_VER_650, .dpu_cfg = &qcm2290_dpu_cfg}, { .hw_rev = DPU_HW_VER_720, .dpu_cfg = &sc7280_dpu_cfg}, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index 38aa38ab1568..3b645d5aa9aa 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -44,6 +44,7 @@ #define DPU_HW_VER_510 DPU_HW_VER(5, 1, 1) /* sc8180 */ #define DPU_HW_VER_600 DPU_HW_VER(6, 0, 0) /* sm8250 */ #define DPU_HW_VER_620 DPU_HW_VER(6, 2, 0) /* sc7180 v1.0 */ +#define DPU_HW_VER_630 DPU_HW_VER(6, 3, 0) /* sm6115|sm4250 */ #define DPU_HW_VER_650 DPU_HW_VER(6, 5, 0) /* qcm2290|sm4125 */ #define DPU_HW_VER_720 DPU_HW_VER(7, 2, 0) /* sc7280 */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c index f2ddcfb6f7ee..3662df698dae 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c @@ -42,7 +42,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc, u32 initial_lines) { struct dpu_hw_blk_reg_map *c = &hw_dsc->hw; - u32 data, lsb, bpp; + u32 data; u32 slice_last_group_size; u32 det_thresh_flatness; bool is_cmd_mode = !(mode & DSC_MODE_VIDEO); @@ -56,14 +56,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc, data = (initial_lines << 20); data |= ((slice_last_group_size - 1) << 18); /* bpp is 6.4 format, 4 LSBs bits are for fractional part */ - data |= dsc->bits_per_pixel << 12; - lsb = dsc->bits_per_pixel % 4; - bpp = dsc->bits_per_pixel / 4; - bpp *= 4; - bpp <<= 4; - bpp |= lsb; - - data |= bpp << 8; + data |= (dsc->bits_per_pixel << 8); data |= (dsc->block_pred_enable << 7); data |= (dsc->line_buf_depth << 3); data |= (dsc->simple_422 << 2); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 5e6e2626151e..b71199511a52 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -194,7 +194,7 @@ struct dpu_debugfs_regset32 { struct dpu_kms *dpu_kms; }; -static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data) +static int dpu_regset32_show(struct seq_file *s, void *data) { struct dpu_debugfs_regset32 *regset = s->private; struct dpu_kms *dpu_kms = regset->dpu_kms; @@ -227,19 +227,7 @@ static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data) return 0; } - -static int dpu_debugfs_open_regset32(struct inode *inode, - struct file *file) -{ - return single_open(file, _dpu_debugfs_show_regset32, inode->i_private); -} - -static const struct file_operations dpu_fops_regset32 = { - .open = dpu_debugfs_open_regset32, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(dpu_regset32); void dpu_debugfs_create_regset32(const char *name, umode_t mode, void *parent, @@ -259,7 +247,7 @@ void dpu_debugfs_create_regset32(const char *name, umode_t mode, regset->blk_len = length; regset->dpu_kms = dpu_kms; - debugfs_create_file(name, mode, parent, regset, &dpu_fops_regset32); + debugfs_create_file(name, mode, parent, regset, &dpu_regset32_fops); } static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) @@ -1304,6 +1292,7 @@ static const struct of_device_id dpu_dt_match[] = { { .compatible = "qcom,sc7180-dpu", }, { .compatible = "qcom,sc7280-dpu", }, { .compatible = "qcom,sc8180x-dpu", }, + { .compatible = "qcom,sm6115-dpu", }, { .compatible = "qcom,sm8150-dpu", }, { .compatible = "qcom,sm8250-dpu", }, {} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 658005f609f4..86719020afe2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -69,9 +69,11 @@ static const uint32_t qcom_compressed_supported_formats[] = { DRM_FORMAT_ARGB8888, DRM_FORMAT_XBGR8888, DRM_FORMAT_XRGB8888, + DRM_FORMAT_XRGB2101010, DRM_FORMAT_BGR565, DRM_FORMAT_NV12, + DRM_FORMAT_P010, }; /** diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index 964573d26d26..9a1a0769575d 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -387,7 +387,7 @@ static int mdp4_kms_init(struct drm_device *dev) struct msm_drm_private *priv = dev->dev_private; struct mdp4_kms *mdp4_kms; struct msm_kms *kms = NULL; - struct iommu_domain *iommu; + struct msm_mmu *mmu; struct msm_gem_address_space *aspace; int irq, ret; u32 major, minor; @@ -499,10 +499,15 @@ static int mdp4_kms_init(struct drm_device *dev) mdp4_disable(mdp4_kms); mdelay(16); - iommu = iommu_domain_alloc(pdev->dev.bus); - if (iommu) { - struct msm_mmu *mmu = msm_iommu_new(&pdev->dev, iommu); - + mmu = msm_iommu_new(&pdev->dev, 0); + if (IS_ERR(mmu)) { + ret = PTR_ERR(mmu); + goto fail; + } else if (!mmu) { + DRM_DEV_INFO(dev->dev, "no iommu, fallback to phys " + "contig buffers for scanout\n"); + aspace = NULL; + } else { aspace = msm_gem_address_space_create(mmu, "mdp4", 0x1000, 0x100000000 - 0x1000); @@ -514,10 +519,6 @@ static int mdp4_kms_init(struct drm_device *dev) } kms->aspace = aspace; - } else { - DRM_DEV_INFO(dev->dev, "no iommu, fallback to phys " - "contig buffers for scanout\n"); - aspace = NULL; } ret = modeset_init(mdp4_kms); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c index 7288041dd86a..7444b75c4215 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c @@ -56,8 +56,9 @@ static int mdp4_lvds_connector_get_modes(struct drm_connector *connector) return ret; } -static int mdp4_lvds_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +mdp4_lvds_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct mdp4_lvds_connector *mdp4_lvds_connector = to_mdp4_lvds_connector(connector); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index b0d21838a134..29ae5c9613f3 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -203,7 +203,7 @@ static int mdp5_set_split_display(struct msm_kms *kms, slave_encoder); } -static void mdp5_destroy(struct platform_device *pdev); +static void mdp5_destroy(struct mdp5_kms *mdp5_kms); static void mdp5_kms_destroy(struct msm_kms *kms) { @@ -223,7 +223,7 @@ static void mdp5_kms_destroy(struct msm_kms *kms) } mdp_kms_destroy(&mdp5_kms->base); - mdp5_destroy(mdp5_kms->pdev); + mdp5_destroy(mdp5_kms); } #ifdef CONFIG_DEBUG_FS @@ -559,6 +559,8 @@ static int mdp5_kms_init(struct drm_device *dev) int irq, i, ret; ret = mdp5_init(to_platform_device(dev->dev), dev); + if (ret) + return ret; /* priv->kms would have been populated by the MDP5 driver */ kms = priv->kms; @@ -632,9 +634,8 @@ fail: return ret; } -static void mdp5_destroy(struct platform_device *pdev) +static void mdp5_destroy(struct mdp5_kms *mdp5_kms) { - struct mdp5_kms *mdp5_kms = platform_get_drvdata(pdev); int i; if (mdp5_kms->ctlm) @@ -648,7 +649,7 @@ static void mdp5_destroy(struct platform_device *pdev) kfree(mdp5_kms->intfs[i]); if (mdp5_kms->rpm_enabled) - pm_runtime_disable(&pdev->dev); + pm_runtime_disable(&mdp5_kms->pdev->dev); drm_atomic_private_obj_fini(&mdp5_kms->glob_state); drm_modeset_lock_fini(&mdp5_kms->glob_state_lock); @@ -797,8 +798,6 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev) goto fail; } - platform_set_drvdata(pdev, mdp5_kms); - spin_lock_init(&mdp5_kms->resource_lock); mdp5_kms->dev = dev; @@ -839,6 +838,9 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev) */ clk_set_rate(mdp5_kms->core_clk, 200000000); + /* set uninit-ed kms */ + priv->kms = &mdp5_kms->base.base; + pm_runtime_enable(&pdev->dev); mdp5_kms->rpm_enabled = true; @@ -890,13 +892,10 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev) if (ret) goto fail; - /* set uninit-ed kms */ - priv->kms = &mdp5_kms->base.base; - return 0; fail: if (mdp5_kms) - mdp5_destroy(pdev); + mdp5_destroy(mdp5_kms); return ret; } @@ -953,7 +952,8 @@ static int mdp5_dev_remove(struct platform_device *pdev) static __maybe_unused int mdp5_runtime_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); - struct mdp5_kms *mdp5_kms = platform_get_drvdata(pdev); + struct msm_drm_private *priv = platform_get_drvdata(pdev); + struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms)); DBG(""); @@ -963,7 +963,8 @@ static __maybe_unused int mdp5_runtime_suspend(struct device *dev) static __maybe_unused int mdp5_runtime_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); - struct mdp5_kms *mdp5_kms = platform_get_drvdata(pdev); + struct msm_drm_private *priv = platform_get_drvdata(pdev); + struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms)); DBG(""); diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 3854c9f1f7e9..dd26ca651a05 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1243,8 +1243,7 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, { int ret = 0; const u8 *dpcd = ctrl->panel->dpcd; - u8 encoding = DP_SET_ANSI_8B10B; - u8 ssc; + u8 encoding[] = { 0, DP_SET_ANSI_8B10B }; u8 assr; struct dp_link_info link_info = {0}; @@ -1256,13 +1255,11 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, dp_aux_link_configure(ctrl->aux, &link_info); - if (drm_dp_max_downspread(dpcd)) { - ssc = DP_SPREAD_AMP_0_5; - drm_dp_dpcd_write(ctrl->aux, DP_DOWNSPREAD_CTRL, &ssc, 1); - } + if (drm_dp_max_downspread(dpcd)) + encoding[0] |= DP_SPREAD_AMP_0_5; - drm_dp_dpcd_write(ctrl->aux, DP_MAIN_LINK_CHANNEL_CODING_SET, - &encoding, 1); + /* config DOWNSPREAD_CTRL and MAIN_LINK_CHANNEL_CODING_SET */ + drm_dp_dpcd_write(ctrl->aux, DP_DOWNSPREAD_CTRL, encoding, 2); if (drm_dp_alternate_scrambler_reset_cap(dpcd)) { assr = DP_ALTERNATE_SCRAMBLER_RESET_ENABLE; diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index bfd0aeff3f0d..7ff60e5ff325 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -857,7 +857,7 @@ static int dp_display_set_mode(struct msm_dp *dp_display, dp = container_of(dp_display, struct dp_display_private, dp_display); - dp->panel->dp_mode.drm_mode = mode->drm_mode; + drm_mode_copy(&dp->panel->dp_mode.drm_mode, &mode->drm_mode); dp->panel->dp_mode.bpp = mode->bpp; dp->panel->dp_mode.capabilities = mode->capabilities; dp_panel_init_panel_info(dp->panel); @@ -1249,7 +1249,7 @@ int dp_display_request_irq(struct msm_dp *dp_display) return -EINVAL; } - rc = devm_request_irq(&dp->pdev->dev, dp->irq, + rc = devm_request_irq(dp_display->drm_dev->dev, dp->irq, dp_display_irq_handler, IRQF_TRIGGER_HIGH, "dp_display_isr", dp); if (rc < 0) { @@ -1528,6 +1528,11 @@ void msm_dp_debugfs_init(struct msm_dp *dp_display, struct drm_minor *minor) } } +static void of_dp_aux_depopulate_bus_void(void *data) +{ + of_dp_aux_depopulate_bus(data); +} + static int dp_display_get_next_bridge(struct msm_dp *dp) { int rc; @@ -1552,10 +1557,16 @@ static int dp_display_get_next_bridge(struct msm_dp *dp) * panel driver is probed asynchronously but is the best we * can do without a bigger driver reorganization. */ - rc = devm_of_dp_aux_populate_ep_devices(dp_priv->aux); + rc = of_dp_aux_populate_bus(dp_priv->aux, NULL); of_node_put(aux_bus); if (rc) goto error; + + rc = devm_add_action_or_reset(dp->drm_dev->dev, + of_dp_aux_depopulate_bus_void, + dp_priv->aux); + if (rc) + goto error; } else if (dp->is_edp) { DRM_ERROR("eDP aux_bus not found\n"); return -ENODEV; @@ -1568,7 +1579,7 @@ static int dp_display_get_next_bridge(struct msm_dp *dp) * For DisplayPort interfaces external bridges are optional, so * silently ignore an error if one is not present (-ENODEV). */ - rc = dp_parser_find_next_bridge(dp_priv->parser); + rc = devm_dp_parser_find_next_bridge(dp->drm_dev->dev, dp_priv->parser); if (!dp->is_edp && rc == -ENODEV) return 0; @@ -1589,14 +1600,10 @@ error: int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev, struct drm_encoder *encoder) { - struct msm_drm_private *priv; + struct msm_drm_private *priv = dev->dev_private; struct dp_display_private *dp_priv; int ret; - if (WARN_ON(!encoder) || WARN_ON(!dp_display) || WARN_ON(!dev)) - return -EINVAL; - - priv = dev->dev_private; dp_display->drm_dev = dev; dp_priv = container_of(dp_display, struct dp_display_private, dp_display); diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index 6df25f7662e7..6db82f9b03af 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -31,6 +31,36 @@ static enum drm_connector_status dp_bridge_detect(struct drm_bridge *bridge) connector_status_disconnected; } +static int dp_bridge_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct msm_dp *dp; + + dp = to_dp_bridge(bridge)->dp_display; + + drm_dbg_dp(dp->drm_dev, "is_connected = %s\n", + (dp->is_connected) ? "true" : "false"); + + /* + * There is no protection in the DRM framework to check if the display + * pipeline has been already disabled before trying to disable it again. + * Hence if the sink is unplugged, the pipeline gets disabled, but the + * crtc->active is still true. Any attempt to set the mode or manually + * disable this encoder will result in the crash. + * + * TODO: add support for telling the DRM subsystem that the pipeline is + * disabled by the hardware and thus all access to it should be forbidden. + * After that this piece of code can be removed. + */ + if (bridge->ops & DRM_BRIDGE_OP_HPD) + return (dp->is_connected) ? 0 : -ENOTCONN; + + return 0; +} + + /** * dp_bridge_get_modes - callback to add drm modes via drm_mode_probed_add() * @bridge: Poiner to drm bridge @@ -61,6 +91,9 @@ static int dp_bridge_get_modes(struct drm_bridge *bridge, struct drm_connector * } static const struct drm_bridge_funcs dp_bridge_ops = { + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, .enable = dp_bridge_enable, .disable = dp_bridge_disable, .post_disable = dp_bridge_post_disable, @@ -68,6 +101,7 @@ static const struct drm_bridge_funcs dp_bridge_ops = { .mode_valid = dp_bridge_mode_valid, .get_modes = dp_bridge_get_modes, .detect = dp_bridge_detect, + .atomic_check = dp_bridge_atomic_check, }; struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *dev, diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 36bb6191d2f0..f1f1d646539d 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -49,23 +49,26 @@ static int dp_aux_link_power_up(struct drm_dp_aux *aux, struct dp_link_info *link) { u8 value; - int err; + ssize_t len; + int i; if (link->revision < 0x11) return 0; - err = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); - if (err < 0) - return err; + len = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); + if (len < 0) + return len; value &= ~DP_SET_POWER_MASK; value |= DP_SET_POWER_D0; - err = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); - if (err < 0) - return err; - - usleep_range(1000, 2000); + /* retry for 1ms to give the sink time to wake up */ + for (i = 0; i < 3; i++) { + len = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); + usleep_range(1000, 2000); + if (len == 1) + break; + } return 0; } diff --git a/drivers/gpu/drm/msm/dp/dp_parser.c b/drivers/gpu/drm/msm/dp/dp_parser.c index dd732215d55b..dcbe893d66d7 100644 --- a/drivers/gpu/drm/msm/dp/dp_parser.c +++ b/drivers/gpu/drm/msm/dp/dp_parser.c @@ -240,12 +240,12 @@ static int dp_parser_clock(struct dp_parser *parser) return 0; } -int dp_parser_find_next_bridge(struct dp_parser *parser) +int devm_dp_parser_find_next_bridge(struct device *dev, struct dp_parser *parser) { - struct device *dev = &parser->pdev->dev; + struct platform_device *pdev = parser->pdev; struct drm_bridge *bridge; - bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0); + bridge = devm_drm_of_get_bridge(dev, pdev->dev.of_node, 1, 0); if (IS_ERR(bridge)) return PTR_ERR(bridge); diff --git a/drivers/gpu/drm/msm/dp/dp_parser.h b/drivers/gpu/drm/msm/dp/dp_parser.h index 866c1a82bf1a..d30ab773db46 100644 --- a/drivers/gpu/drm/msm/dp/dp_parser.h +++ b/drivers/gpu/drm/msm/dp/dp_parser.h @@ -138,8 +138,9 @@ struct dp_parser { struct dp_parser *dp_parser_get(struct platform_device *pdev); /** - * dp_parser_find_next_bridge() - find an additional bridge to DP + * devm_dp_parser_find_next_bridge() - find an additional bridge to DP * + * @dev: device to tie bridge lifetime to * @parser: dp_parser data from client * * This function is used to find any additional bridge attached to @@ -147,6 +148,6 @@ struct dp_parser *dp_parser_get(struct platform_device *pdev); * * Return: 0 if able to get the bridge, otherwise negative errno for failure. */ -int dp_parser_find_next_bridge(struct dp_parser *parser); +int devm_dp_parser_find_next_bridge(struct device *dev, struct dp_parser *parser); #endif diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index 39bbabb5daf6..31fdee2052be 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -211,13 +211,14 @@ void __exit msm_dsi_unregister(void) int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev, struct drm_encoder *encoder) { - struct msm_drm_private *priv; + struct msm_drm_private *priv = dev->dev_private; int ret; - if (WARN_ON(!encoder) || WARN_ON(!msm_dsi) || WARN_ON(!dev)) - return -EINVAL; + if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) { + DRM_DEV_ERROR(dev->dev, "too many bridges\n"); + return -ENOSPC; + } - priv = dev->dev_private; msm_dsi->dev = dev; ret = msm_dsi_host_modeset_init(msm_dsi->host, dev); diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 7fbf391c024f..89aadd3b3202 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -21,6 +21,7 @@ #include <video/mipi_display.h> +#include <drm/display/drm_dsc_helper.h> #include <drm/drm_of.h> #include "dsi.h" @@ -33,7 +34,7 @@ #define DSI_RESET_TOGGLE_DELAY_MS 20 -static int dsi_populate_dsc_params(struct drm_dsc_config *dsc); +static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc_config *dsc); static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor) { @@ -842,17 +843,15 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable, static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode, u32 hdisplay) { struct drm_dsc_config *dsc = msm_host->dsc; - u32 reg, intf_width, reg_ctrl, reg_ctrl2; + u32 reg, reg_ctrl, reg_ctrl2; u32 slice_per_intf, total_bytes_per_intf; u32 pkt_per_line; - u32 bytes_in_slice; u32 eol_byte_num; /* first calculate dsc parameters and then program * compress mode registers */ - intf_width = hdisplay; - slice_per_intf = DIV_ROUND_UP(intf_width, dsc->slice_width); + slice_per_intf = DIV_ROUND_UP(hdisplay, dsc->slice_width); /* If slice_per_pkt is greater than slice_per_intf * then default to 1. This can happen during partial @@ -861,12 +860,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod if (slice_per_intf > dsc->slice_count) dsc->slice_count = 1; - slice_per_intf = DIV_ROUND_UP(hdisplay, dsc->slice_width); - bytes_in_slice = DIV_ROUND_UP(dsc->slice_width * dsc->bits_per_pixel, 8); - - dsc->slice_chunk_size = bytes_in_slice; - - total_bytes_per_intf = bytes_in_slice * slice_per_intf; + total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf; eol_byte_num = total_bytes_per_intf % 3; pkt_per_line = slice_per_intf / dsc->slice_count; @@ -892,7 +886,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod reg_ctrl |= reg; reg_ctrl2 &= ~DSI_COMMAND_COMPRESSION_MODE_CTRL2_STREAM0_SLICE_WIDTH__MASK; - reg_ctrl2 |= DSI_COMMAND_COMPRESSION_MODE_CTRL2_STREAM0_SLICE_WIDTH(bytes_in_slice); + reg_ctrl2 |= DSI_COMMAND_COMPRESSION_MODE_CTRL2_STREAM0_SLICE_WIDTH(dsc->slice_chunk_size); dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL, reg_ctrl); dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL2, reg_ctrl2); @@ -915,6 +909,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) u32 va_end = va_start + mode->vdisplay; u32 hdisplay = mode->hdisplay; u32 wc; + int ret; DBG(""); @@ -950,7 +945,9 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) /* we do the calculations for dsc parameters here so that * panel can use these parameters */ - dsi_populate_dsc_params(dsc); + ret = dsi_populate_dsc_params(msm_host, dsc); + if (ret) + return; /* Divide the display by 3 but keep back/font porch and * pulse width same @@ -1754,18 +1751,20 @@ static char bpg_offset[DSC_NUM_BUF_RANGES] = { 2, 0, 0, -2, -4, -6, -8, -8, -8, -10, -10, -12, -12, -12, -12 }; -static int dsi_populate_dsc_params(struct drm_dsc_config *dsc) -{ - int mux_words_size; - int groups_per_line, groups_total; - int min_rate_buffer_size; - int hrd_delay; - int pre_num_extra_mux_bits, num_extra_mux_bits; - int slice_bits; - int target_bpp_x16; - int data; - int final_value, final_scale; +static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc_config *dsc) +{ int i; + u16 bpp = dsc->bits_per_pixel >> 4; + + if (dsc->bits_per_pixel & 0xf) { + DRM_DEV_ERROR(&msm_host->pdev->dev, "DSI does not support fractional bits_per_pixel\n"); + return -EINVAL; + } + + if (dsc->bits_per_component != 8) { + DRM_DEV_ERROR(&msm_host->pdev->dev, "DSI does not support bits_per_component != 8 yet\n"); + return -EOPNOTSUPP; + } dsc->rc_model_size = 8192; dsc->first_line_bpg_offset = 12; @@ -1783,16 +1782,21 @@ static int dsi_populate_dsc_params(struct drm_dsc_config *dsc) for (i = 0; i < DSC_NUM_BUF_RANGES; i++) { dsc->rc_range_params[i].range_min_qp = min_qp[i]; dsc->rc_range_params[i].range_max_qp = max_qp[i]; - dsc->rc_range_params[i].range_bpg_offset = bpg_offset[i]; + /* + * Range BPG Offset contains two's-complement signed values that fill + * 8 bits, yet the registers and DCS PPS field are only 6 bits wide. + */ + dsc->rc_range_params[i].range_bpg_offset = bpg_offset[i] & DSC_RANGE_BPG_OFFSET_MASK; } - dsc->initial_offset = 6144; /* Not bpp 12 */ - if (dsc->bits_per_pixel != 8) + dsc->initial_offset = 6144; /* Not bpp 12 */ + if (bpp != 8) dsc->initial_offset = 2048; /* bpp = 12 */ - mux_words_size = 48; /* bpc == 8/10 */ - if (dsc->bits_per_component == 12) - mux_words_size = 64; + if (dsc->bits_per_component <= 10) + dsc->mux_word_size = DSC_MUX_WORD_SIZE_8_10_BPC; + else + dsc->mux_word_size = DSC_MUX_WORD_SIZE_12_BPC; dsc->initial_xmit_delay = 512; dsc->initial_scale_value = 32; @@ -1804,63 +1808,8 @@ static int dsi_populate_dsc_params(struct drm_dsc_config *dsc) dsc->flatness_max_qp = 12; dsc->rc_quant_incr_limit0 = 11; dsc->rc_quant_incr_limit1 = 11; - dsc->mux_word_size = DSC_MUX_WORD_SIZE_8_10_BPC; - - /* FIXME: need to call drm_dsc_compute_rc_parameters() so that rest of - * params are calculated - */ - groups_per_line = DIV_ROUND_UP(dsc->slice_width, 3); - dsc->slice_chunk_size = dsc->slice_width * dsc->bits_per_pixel / 8; - if ((dsc->slice_width * dsc->bits_per_pixel) % 8) - dsc->slice_chunk_size++; - /* rbs-min */ - min_rate_buffer_size = dsc->rc_model_size - dsc->initial_offset + - dsc->initial_xmit_delay * dsc->bits_per_pixel + - groups_per_line * dsc->first_line_bpg_offset; - - hrd_delay = DIV_ROUND_UP(min_rate_buffer_size, dsc->bits_per_pixel); - - dsc->initial_dec_delay = hrd_delay - dsc->initial_xmit_delay; - - dsc->initial_scale_value = 8 * dsc->rc_model_size / - (dsc->rc_model_size - dsc->initial_offset); - - slice_bits = 8 * dsc->slice_chunk_size * dsc->slice_height; - - groups_total = groups_per_line * dsc->slice_height; - - data = dsc->first_line_bpg_offset * 2048; - - dsc->nfl_bpg_offset = DIV_ROUND_UP(data, (dsc->slice_height - 1)); - - pre_num_extra_mux_bits = 3 * (mux_words_size + (4 * dsc->bits_per_component + 4) - 2); - - num_extra_mux_bits = pre_num_extra_mux_bits - (mux_words_size - - ((slice_bits - pre_num_extra_mux_bits) % mux_words_size)); - - data = 2048 * (dsc->rc_model_size - dsc->initial_offset + num_extra_mux_bits); - dsc->slice_bpg_offset = DIV_ROUND_UP(data, groups_total); - - /* bpp * 16 + 0.5 */ - data = dsc->bits_per_pixel * 16; - data *= 2; - data++; - data /= 2; - target_bpp_x16 = data; - - data = (dsc->initial_xmit_delay * target_bpp_x16) / 16; - final_value = dsc->rc_model_size - data + num_extra_mux_bits; - dsc->final_offset = final_value; - - final_scale = 8 * dsc->rc_model_size / (dsc->rc_model_size - final_value); - - data = (final_scale - 9) * (dsc->nfl_bpg_offset + dsc->slice_bpg_offset); - dsc->scale_increment_interval = (2048 * dsc->final_offset) / data; - - dsc->scale_decrement_interval = groups_per_line / (dsc->initial_scale_value - 8); - - return 0; + return drm_dsc_compute_rc_parameters(dsc); } static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 7fc0975cb869..ee6051367679 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -549,6 +549,8 @@ static const struct of_device_id dsi_phy_dt_match[] = { #ifdef CONFIG_DRM_MSM_DSI_14NM_PHY { .compatible = "qcom,dsi-phy-14nm", .data = &dsi_phy_14nm_cfgs }, + { .compatible = "qcom,dsi-phy-14nm-2290", + .data = &dsi_phy_14nm_2290_cfgs }, { .compatible = "qcom,dsi-phy-14nm-660", .data = &dsi_phy_14nm_660_cfgs }, { .compatible = "qcom,dsi-phy-14nm-8953", diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index 60a99c6525b2..1096afedd616 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -50,6 +50,7 @@ extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 0f8f4ca46429..9f488adea7f5 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -1081,3 +1081,20 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs = { .io_start = { 0x1a94400, 0x1a96400 }, .num_dsi_phy = 2, }; + +const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs = { + .has_phy_lane = true, + .regulator_data = dsi_phy_14nm_17mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_14nm_17mA_regulators), + .ops = { + .enable = dsi_14nm_phy_enable, + .disable = dsi_14nm_phy_disable, + .pll_init = dsi_pll_14nm_init, + .save_pll_state = dsi_14nm_pll_save_state, + .restore_pll_state = dsi_14nm_pll_restore_state, + }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, + .io_start = { 0x5e94400 }, + .num_dsi_phy = 1, +}; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 93fe61b86967..4d3fdc806bef 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -68,16 +68,17 @@ static void msm_hdmi_destroy(struct hdmi *hdmi) destroy_workqueue(hdmi->workq); msm_hdmi_hdcp_destroy(hdmi); + if (hdmi->i2c) + msm_hdmi_i2c_destroy(hdmi->i2c); +} + +static void msm_hdmi_put_phy(struct hdmi *hdmi) +{ if (hdmi->phy_dev) { put_device(hdmi->phy_dev); hdmi->phy = NULL; hdmi->phy_dev = NULL; } - - if (hdmi->i2c) - msm_hdmi_i2c_destroy(hdmi->i2c); - - platform_set_drvdata(hdmi->pdev, NULL); } static int msm_hdmi_get_phy(struct hdmi *hdmi) @@ -93,22 +94,18 @@ static int msm_hdmi_get_phy(struct hdmi *hdmi) } phy_pdev = of_find_device_by_node(phy_node); - if (phy_pdev) - hdmi->phy = platform_get_drvdata(phy_pdev); - of_node_put(phy_node); - if (!phy_pdev) { - DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); - return -EPROBE_DEFER; - } + if (!phy_pdev) + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, "phy driver is not ready\n"); + + hdmi->phy = platform_get_drvdata(phy_pdev); if (!hdmi->phy) { - DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); put_device(&phy_pdev->dev); - return -EPROBE_DEFER; + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, "phy driver is not ready\n"); } - hdmi->phy_dev = get_device(&phy_pdev->dev); + hdmi->phy_dev = &phy_pdev->dev; return 0; } @@ -117,142 +114,10 @@ static int msm_hdmi_get_phy(struct hdmi *hdmi) * we are to EPROBE_DEFER we want to do it here, rather than later * at modeset_init() time */ -static struct hdmi *msm_hdmi_init(struct platform_device *pdev) +static int msm_hdmi_init(struct hdmi *hdmi) { - struct hdmi_platform_config *config = pdev->dev.platform_data; - struct hdmi *hdmi = NULL; - struct resource *res; - int i, ret; - - hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); - if (!hdmi) { - ret = -ENOMEM; - goto fail; - } - - hdmi->pdev = pdev; - hdmi->config = config; - spin_lock_init(&hdmi->reg_lock); - - ret = drm_of_find_panel_or_bridge(pdev->dev.of_node, 1, 0, NULL, &hdmi->next_bridge); - if (ret && ret != -ENODEV) - goto fail; - - hdmi->mmio = msm_ioremap(pdev, config->mmio_name); - if (IS_ERR(hdmi->mmio)) { - ret = PTR_ERR(hdmi->mmio); - goto fail; - } - - /* HDCP needs physical address of hdmi register */ - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, - config->mmio_name); - if (!res) { - ret = -EINVAL; - goto fail; - } - hdmi->mmio_phy_addr = res->start; - - hdmi->qfprom_mmio = msm_ioremap(pdev, config->qfprom_mmio_name); - if (IS_ERR(hdmi->qfprom_mmio)) { - DRM_DEV_INFO(&pdev->dev, "can't find qfprom resource\n"); - hdmi->qfprom_mmio = NULL; - } - - hdmi->hpd_regs = devm_kcalloc(&pdev->dev, - config->hpd_reg_cnt, - sizeof(hdmi->hpd_regs[0]), - GFP_KERNEL); - if (!hdmi->hpd_regs) { - ret = -ENOMEM; - goto fail; - } - for (i = 0; i < config->hpd_reg_cnt; i++) - hdmi->hpd_regs[i].supply = config->hpd_reg_names[i]; - - ret = devm_regulator_bulk_get(&pdev->dev, config->hpd_reg_cnt, hdmi->hpd_regs); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to get hpd regulator: %d\n", ret); - goto fail; - } - - hdmi->pwr_regs = devm_kcalloc(&pdev->dev, - config->pwr_reg_cnt, - sizeof(hdmi->pwr_regs[0]), - GFP_KERNEL); - if (!hdmi->pwr_regs) { - ret = -ENOMEM; - goto fail; - } - - for (i = 0; i < config->pwr_reg_cnt; i++) - hdmi->pwr_regs[i].supply = config->pwr_reg_names[i]; - - ret = devm_regulator_bulk_get(&pdev->dev, config->pwr_reg_cnt, hdmi->pwr_regs); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to get pwr regulator: %d\n", ret); - goto fail; - } - - hdmi->hpd_clks = devm_kcalloc(&pdev->dev, - config->hpd_clk_cnt, - sizeof(hdmi->hpd_clks[0]), - GFP_KERNEL); - if (!hdmi->hpd_clks) { - ret = -ENOMEM; - goto fail; - } - for (i = 0; i < config->hpd_clk_cnt; i++) { - struct clk *clk; - - clk = msm_clk_get(pdev, config->hpd_clk_names[i]); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - DRM_DEV_ERROR(&pdev->dev, "failed to get hpd clk: %s (%d)\n", - config->hpd_clk_names[i], ret); - goto fail; - } - - hdmi->hpd_clks[i] = clk; - } - - hdmi->pwr_clks = devm_kcalloc(&pdev->dev, - config->pwr_clk_cnt, - sizeof(hdmi->pwr_clks[0]), - GFP_KERNEL); - if (!hdmi->pwr_clks) { - ret = -ENOMEM; - goto fail; - } - for (i = 0; i < config->pwr_clk_cnt; i++) { - struct clk *clk; - - clk = msm_clk_get(pdev, config->pwr_clk_names[i]); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - DRM_DEV_ERROR(&pdev->dev, "failed to get pwr clk: %s (%d)\n", - config->pwr_clk_names[i], ret); - goto fail; - } - - hdmi->pwr_clks[i] = clk; - } - - hdmi->hpd_gpiod = devm_gpiod_get_optional(&pdev->dev, "hpd", GPIOD_IN); - /* This will catch e.g. -EPROBE_DEFER */ - if (IS_ERR(hdmi->hpd_gpiod)) { - ret = PTR_ERR(hdmi->hpd_gpiod); - DRM_DEV_ERROR(&pdev->dev, "failed to get hpd gpio: (%d)\n", ret); - goto fail; - } - - if (!hdmi->hpd_gpiod) - DBG("failed to get HPD gpio"); - - if (hdmi->hpd_gpiod) - gpiod_set_consumer_name(hdmi->hpd_gpiod, "HDMI_HPD"); - - pm_runtime_enable(&pdev->dev); + struct platform_device *pdev = hdmi->pdev; + int ret; hdmi->workq = alloc_ordered_workqueue("msm_hdmi", 0); @@ -264,25 +129,18 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev) goto fail; } - ret = msm_hdmi_get_phy(hdmi); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to get phy\n"); - goto fail; - } - hdmi->hdcp_ctrl = msm_hdmi_hdcp_init(hdmi); if (IS_ERR(hdmi->hdcp_ctrl)) { dev_warn(&pdev->dev, "failed to init hdcp: disabled\n"); hdmi->hdcp_ctrl = NULL; } - return hdmi; + return 0; fail: - if (hdmi) - msm_hdmi_destroy(hdmi); + msm_hdmi_destroy(hdmi); - return ERR_PTR(ret); + return ret; } /* Second part of initialization, the drm/kms level modeset_init, @@ -297,9 +155,13 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, struct drm_device *dev, struct drm_encoder *encoder) { struct msm_drm_private *priv = dev->dev_private; - struct platform_device *pdev = hdmi->pdev; int ret; + if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) { + DRM_DEV_ERROR(dev->dev, "too many bridges\n"); + return -ENOSPC; + } + hdmi->dev = dev; hdmi->encoder = encoder; @@ -332,14 +194,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, drm_connector_attach_encoder(hdmi->connector, hdmi->encoder); - hdmi->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (!hdmi->irq) { - ret = -EINVAL; - DRM_DEV_ERROR(dev->dev, "failed to get irq\n"); - goto fail; - } - - ret = devm_request_irq(&pdev->dev, hdmi->irq, + ret = devm_request_irq(dev->dev, hdmi->irq, msm_hdmi_irq, IRQF_TRIGGER_HIGH, "hdmi_isr", hdmi); if (ret < 0) { @@ -358,8 +213,6 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, priv->bridges[priv->num_bridges++] = hdmi->bridge; - platform_set_drvdata(pdev, hdmi); - return 0; fail: @@ -387,7 +240,7 @@ fail: static const char *hpd_reg_names_8960[] = {"core-vdda"}; static const char *hpd_clk_names_8960[] = {"core", "master_iface", "slave_iface"}; -static struct hdmi_platform_config hdmi_tx_8960_config = { +static const struct hdmi_platform_config hdmi_tx_8960_config = { HDMI_CFG(hpd_reg, 8960), HDMI_CFG(hpd_clk, 8960), }; @@ -397,7 +250,7 @@ static const char *pwr_clk_names_8x74[] = {"extp", "alt_iface"}; static const char *hpd_clk_names_8x74[] = {"iface", "core", "mdp_core"}; static unsigned long hpd_clk_freq_8x74[] = {0, 19200000, 0}; -static struct hdmi_platform_config hdmi_tx_8974_config = { +static const struct hdmi_platform_config hdmi_tx_8974_config = { HDMI_CFG(pwr_reg, 8x74), HDMI_CFG(pwr_clk, 8x74), HDMI_CFG(hpd_clk, 8x74), @@ -512,26 +365,12 @@ static int msm_hdmi_register_audio_driver(struct hdmi *hdmi, struct device *dev) static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) { struct msm_drm_private *priv = dev_get_drvdata(master); - struct hdmi_platform_config *hdmi_cfg; - struct hdmi *hdmi; - struct device_node *of_node = dev->of_node; + struct hdmi *hdmi = dev_get_drvdata(dev); int err; - hdmi_cfg = (struct hdmi_platform_config *) - of_device_get_match_data(dev); - if (!hdmi_cfg) { - DRM_DEV_ERROR(dev, "unknown hdmi_cfg: %pOFn\n", of_node); - return -ENXIO; - } - - hdmi_cfg->mmio_name = "core_physical"; - hdmi_cfg->qfprom_mmio_name = "qfprom_physical"; - - dev->platform_data = hdmi_cfg; - - hdmi = msm_hdmi_init(to_platform_device(dev)); - if (IS_ERR(hdmi)) - return PTR_ERR(hdmi); + err = msm_hdmi_init(hdmi); + if (err) + return err; priv->hdmi = hdmi; err = msm_hdmi_register_audio_driver(hdmi, dev); @@ -564,12 +403,150 @@ static const struct component_ops msm_hdmi_ops = { static int msm_hdmi_dev_probe(struct platform_device *pdev) { + const struct hdmi_platform_config *config; + struct device *dev = &pdev->dev; + struct hdmi *hdmi; + struct resource *res; + int i, ret; + + config = of_device_get_match_data(dev); + if (!config) + return -EINVAL; + + hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); + if (!hdmi) + return -ENOMEM; + + hdmi->pdev = pdev; + hdmi->config = config; + spin_lock_init(&hdmi->reg_lock); + + ret = drm_of_find_panel_or_bridge(pdev->dev.of_node, 1, 0, NULL, &hdmi->next_bridge); + if (ret && ret != -ENODEV) + return ret; + + hdmi->mmio = msm_ioremap(pdev, "core_physical"); + if (IS_ERR(hdmi->mmio)) + return PTR_ERR(hdmi->mmio); + + /* HDCP needs physical address of hdmi register */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "core_physical"); + if (!res) + return -EINVAL; + hdmi->mmio_phy_addr = res->start; + + hdmi->qfprom_mmio = msm_ioremap(pdev, "qfprom_physical"); + if (IS_ERR(hdmi->qfprom_mmio)) { + DRM_DEV_INFO(&pdev->dev, "can't find qfprom resource\n"); + hdmi->qfprom_mmio = NULL; + } + + hdmi->irq = platform_get_irq(pdev, 0); + if (hdmi->irq < 0) + return hdmi->irq; + + hdmi->hpd_regs = devm_kcalloc(&pdev->dev, + config->hpd_reg_cnt, + sizeof(hdmi->hpd_regs[0]), + GFP_KERNEL); + if (!hdmi->hpd_regs) + return -ENOMEM; + + for (i = 0; i < config->hpd_reg_cnt; i++) + hdmi->hpd_regs[i].supply = config->hpd_reg_names[i]; + + ret = devm_regulator_bulk_get(&pdev->dev, config->hpd_reg_cnt, hdmi->hpd_regs); + if (ret) + return dev_err_probe(dev, ret, "failed to get hpd regulators\n"); + + hdmi->pwr_regs = devm_kcalloc(&pdev->dev, + config->pwr_reg_cnt, + sizeof(hdmi->pwr_regs[0]), + GFP_KERNEL); + if (!hdmi->pwr_regs) + return -ENOMEM; + + for (i = 0; i < config->pwr_reg_cnt; i++) + hdmi->pwr_regs[i].supply = config->pwr_reg_names[i]; + + ret = devm_regulator_bulk_get(&pdev->dev, config->pwr_reg_cnt, hdmi->pwr_regs); + if (ret) + return dev_err_probe(dev, ret, "failed to get pwr regulators\n"); + + hdmi->hpd_clks = devm_kcalloc(&pdev->dev, + config->hpd_clk_cnt, + sizeof(hdmi->hpd_clks[0]), + GFP_KERNEL); + if (!hdmi->hpd_clks) + return -ENOMEM; + + for (i = 0; i < config->hpd_clk_cnt; i++) { + struct clk *clk; + + clk = msm_clk_get(pdev, config->hpd_clk_names[i]); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), + "failed to get hpd clk: %s\n", + config->hpd_clk_names[i]); + + hdmi->hpd_clks[i] = clk; + } + + hdmi->pwr_clks = devm_kcalloc(&pdev->dev, + config->pwr_clk_cnt, + sizeof(hdmi->pwr_clks[0]), + GFP_KERNEL); + if (!hdmi->pwr_clks) + return -ENOMEM; + + for (i = 0; i < config->pwr_clk_cnt; i++) { + struct clk *clk; + + clk = msm_clk_get(pdev, config->pwr_clk_names[i]); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), + "failed to get pwr clk: %s\n", + config->pwr_clk_names[i]); + + hdmi->pwr_clks[i] = clk; + } + + hdmi->hpd_gpiod = devm_gpiod_get_optional(&pdev->dev, "hpd", GPIOD_IN); + /* This will catch e.g. -EPROBE_DEFER */ + if (IS_ERR(hdmi->hpd_gpiod)) + return dev_err_probe(dev, PTR_ERR(hdmi->hpd_gpiod), + "failed to get hpd gpio\n"); + + if (!hdmi->hpd_gpiod) + DBG("failed to get HPD gpio"); + + if (hdmi->hpd_gpiod) + gpiod_set_consumer_name(hdmi->hpd_gpiod, "HDMI_HPD"); + + ret = msm_hdmi_get_phy(hdmi); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to get phy\n"); + return ret; + } + + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; + + platform_set_drvdata(pdev, hdmi); + return component_add(&pdev->dev, &msm_hdmi_ops); } static int msm_hdmi_dev_remove(struct platform_device *pdev) { + struct hdmi *hdmi = dev_get_drvdata(&pdev->dev); + component_del(&pdev->dev, &msm_hdmi_ops); + + msm_hdmi_put_phy(hdmi); + return 0; } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index 04a74381aaf7..e8dbee50637f 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -86,9 +86,6 @@ struct hdmi { /* platform config data (ie. from DT, or pdata) */ struct hdmi_platform_config { - const char *mmio_name; - const char *qfprom_mmio_name; - /* regulators that need to be on for hpd: */ const char **hpd_reg_names; int hpd_reg_cnt; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 28034c21f6bc..8b0b0ac74a6f 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -247,6 +247,7 @@ static int msm_drm_uninit(struct device *dev) for (i = 0; i < priv->num_bridges; i++) drm_bridge_remove(priv->bridges[i]); + priv->num_bridges = 0; pm_runtime_get_sync(dev); msm_irq_uninstall(ddev); @@ -276,7 +277,6 @@ static int msm_drm_uninit(struct device *dev) struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) { - struct iommu_domain *domain; struct msm_gem_address_space *aspace; struct msm_mmu *mmu; struct device *mdp_dev = dev->dev; @@ -292,22 +292,21 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) else iommu_dev = mdss_dev; - domain = iommu_domain_alloc(iommu_dev->bus); - if (!domain) { + mmu = msm_iommu_new(iommu_dev, 0); + if (IS_ERR(mmu)) + return ERR_CAST(mmu); + + if (!mmu) { drm_info(dev, "no IOMMU, fallback to phys contig buffers for scanout\n"); return NULL; } - mmu = msm_iommu_new(iommu_dev, domain); - if (IS_ERR(mmu)) { - iommu_domain_free(domain); - return ERR_CAST(mmu); - } - aspace = msm_gem_address_space_create(mmu, "mdp_kms", 0x1000, 0x100000000 - 0x1000); - if (IS_ERR(aspace)) + if (IS_ERR(aspace)) { + dev_err(mdp_dev, "aspace create, error %pe\n", aspace); mmu->funcs->destroy(mmu); + } return aspace; } @@ -419,7 +418,6 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) priv->dev = ddev; priv->wq = alloc_ordered_workqueue("msm", 0); - priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; INIT_LIST_HEAD(&priv->objects); mutex_init(&priv->obj_lock); @@ -818,6 +816,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data, case MSM_INFO_GET_OFFSET: case MSM_INFO_GET_IOVA: case MSM_INFO_SET_IOVA: + case MSM_INFO_GET_FLAGS: /* value returned as immediate, not pointer, so len==0: */ if (args->len) return -EINVAL; @@ -845,6 +844,15 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data, case MSM_INFO_SET_IOVA: ret = msm_ioctl_gem_info_set_iova(dev, file, obj, args->value); break; + case MSM_INFO_GET_FLAGS: + if (obj->import_attach) { + ret = -EINVAL; + break; + } + /* Hide internal kernel-only flags: */ + args->value = to_msm_bo(obj)->flags & MSM_BO_FLAGS; + ret = 0; + break; case MSM_INFO_SET_NAME: /* length check should leave room for terminating null: */ if (args->len >= sizeof(msm_obj->name)) { diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index b2ea262296a4..d4e0ef608950 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -224,7 +224,13 @@ struct msm_drm_private { struct drm_atomic_state *pm_state; - /* For hang detection, in ms */ + /** + * hangcheck_period: For hang detection, in ms + * + * Note that in practice, a submit/job will get at least two hangcheck + * periods, due to checking for progress being implemented as simply + * "have the CP position registers changed since last time?" + */ unsigned int hangcheck_period; /** diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index b373e3000320..31e1e30cb52a 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -93,7 +93,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper, goto fail; } - fbi = drm_fb_helper_alloc_fbi(helper); + fbi = drm_fb_helper_alloc_info(helper); if (IS_ERR(fbi)) { DRM_DEV_ERROR(dev->dev, "failed to allocate fb info\n"); ret = PTR_ERR(fbi); @@ -182,7 +182,7 @@ void msm_fbdev_free(struct drm_device *dev) DBG(); - drm_fb_helper_unregister_fbi(helper); + drm_fb_helper_unregister_info(helper); drm_fb_helper_fini(helper); diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 1de14e67f96b..051bdbc093cf 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -15,7 +15,7 @@ /* Default disabled for now until it has some more testing on the different * iommu combinations that can be paired with the driver: */ -static bool enable_eviction = false; +static bool enable_eviction = true; MODULE_PARM_DESC(enable_eviction, "Enable swappable GEM buffers"); module_param(enable_eviction, bool, 0600); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 5599d93ec0d2..73a2ca122c57 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -334,8 +334,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) if (ret) return ret; - /* exclusive fences must be ordered */ - if (no_implicit && !write) + if (no_implicit) continue; ret = drm_sched_job_add_implicit_dependencies(&submit->base, @@ -501,11 +500,11 @@ out: */ static void submit_cleanup(struct msm_gem_submit *submit, bool error) { - unsigned cleanup_flags = BO_LOCKED | BO_OBJ_PINNED; + unsigned cleanup_flags = BO_LOCKED; unsigned i; if (error) - cleanup_flags |= BO_VMA_PINNED; + cleanup_flags |= BO_VMA_PINNED | BO_OBJ_PINNED; for (i = 0; i < submit->nr_bos; i++) { struct msm_gem_object *msm_obj = submit->bos[i].obj; @@ -706,7 +705,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_file_private *ctx = file->driver_priv; - struct msm_gem_submit *submit = NULL; + struct msm_gem_submit *submit; struct msm_gpu *gpu = priv->gpu; struct msm_gpu_submitqueue *queue; struct msm_ringbuffer *ring; @@ -946,8 +945,7 @@ out_unlock: put_unused_fd(out_fence_fd); mutex_unlock(&queue->lock); out_post_unlock: - if (submit) - msm_gem_submit_put(submit); + msm_gem_submit_put(submit); if (!IS_ERR_OR_NULL(post_deps)) { for (i = 0; i < args->nr_out_syncobjs; ++i) { kfree(post_deps[i].chain); diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 0098ee8438aa..30ed45af76ad 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -492,6 +492,21 @@ static void hangcheck_timer_reset(struct msm_gpu *gpu) round_jiffies_up(jiffies + msecs_to_jiffies(priv->hangcheck_period))); } +static bool made_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + if (ring->hangcheck_progress_retries >= DRM_MSM_HANGCHECK_PROGRESS_RETRIES) + return false; + + if (!gpu->funcs->progress) + return false; + + if (!gpu->funcs->progress(gpu, ring)) + return false; + + ring->hangcheck_progress_retries++; + return true; +} + static void hangcheck_handler(struct timer_list *t) { struct msm_gpu *gpu = from_timer(gpu, t, hangcheck_timer); @@ -502,9 +517,12 @@ static void hangcheck_handler(struct timer_list *t) if (fence != ring->hangcheck_fence) { /* some progress has been made.. ya! */ ring->hangcheck_fence = fence; - } else if (fence_before(fence, ring->fctx->last_fence)) { + ring->hangcheck_progress_retries = 0; + } else if (fence_before(fence, ring->fctx->last_fence) && + !made_progress(gpu, ring)) { /* no progress and not done.. hung! */ ring->hangcheck_fence = fence; + ring->hangcheck_progress_retries = 0; DRM_DEV_ERROR(dev->dev, "%s: hangcheck detected gpu lockup rb %d!\n", gpu->name, ring->id); DRM_DEV_ERROR(dev->dev, "%s: completed fence: %u\n", @@ -830,6 +848,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs, const char *name, struct msm_gpu_config *config) { + struct msm_drm_private *priv = drm->dev_private; int i, ret, nr_rings = config->nr_rings; void *memptrs; uint64_t memptrs_iova; @@ -857,6 +876,16 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, kthread_init_work(&gpu->recover_work, recover_worker); kthread_init_work(&gpu->fault_work, fault_worker); + priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; + + /* + * If progress detection is supported, halve the hangcheck timer + * duration, as it takes two iterations of the hangcheck handler + * to detect a hang. + */ + if (funcs->progress) + priv->hangcheck_period /= 2; + timer_setup(&gpu->hangcheck_timer, hangcheck_handler, 0); spin_lock_init(&gpu->perf_lock); @@ -997,4 +1026,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu) } msm_devfreq_cleanup(gpu); + + platform_set_drvdata(gpu->pdev, NULL); } diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index ff911e7305ce..651786bc55e5 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -78,6 +78,15 @@ struct msm_gpu_funcs { struct msm_gem_address_space *(*create_private_address_space) (struct msm_gpu *gpu); uint32_t (*get_rptr)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); + + /** + * progress: Has the GPU made progress? + * + * Return true if GPU position in cmdstream has advanced (or changed) + * since the last call. To avoid false negatives, this should account + * for cmdstream that is buffered in this FIFO upstream of the CP fw. + */ + bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); }; /* Additional state for iommu faults: */ @@ -237,6 +246,7 @@ struct msm_gpu { #define DRM_MSM_INACTIVE_PERIOD 66 /* in ms (roughly four frames) */ #define DRM_MSM_HANGCHECK_DEFAULT_PERIOD 500 /* in ms */ +#define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3 struct timer_list hangcheck_timer; /* Fault info for most recent iova fault: */ @@ -280,6 +290,10 @@ struct msm_gpu { static inline struct msm_gpu *dev_to_gpu(struct device *dev) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev); + + if (!adreno_smmu) + return NULL; + return container_of(adreno_smmu, struct msm_gpu, adreno_smmu); } @@ -536,7 +550,7 @@ static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or) msm_rmw(gpu->mmio + (reg << 2), mask, or); } -static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi) +static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg) { u64 val; @@ -554,17 +568,17 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi) * when the lo is read, so make sure to read the lo first to trigger * that */ - val = (u64) msm_readl(gpu->mmio + (lo << 2)); - val |= ((u64) msm_readl(gpu->mmio + (hi << 2)) << 32); + val = (u64) msm_readl(gpu->mmio + (reg << 2)); + val |= ((u64) msm_readl(gpu->mmio + ((reg + 1) << 2)) << 32); return val; } -static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val) +static inline void gpu_write64(struct msm_gpu *gpu, u32 reg, u64 val) { /* Why not a writeq here? Read the screed above */ - msm_writel(lower_32_bits(val), gpu->mmio + (lo << 2)); - msm_writel(upper_32_bits(val), gpu->mmio + (hi << 2)); + msm_writel(lower_32_bits(val), gpu->mmio + (reg << 2)); + msm_writel(upper_32_bits(val), gpu->mmio + ((reg + 1) << 2)); } int msm_gpu_pm_suspend(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 5577cea7c009..c2507582ecf3 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -186,6 +186,13 @@ int msm_iommu_pagetable_params(struct msm_mmu *mmu, return 0; } +struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu) +{ + struct msm_iommu *iommu = to_msm_iommu(mmu); + + return &iommu->domain->geometry; +} + static const struct msm_mmu_funcs pagetable_funcs = { .map = msm_iommu_pagetable_map, .unmap = msm_iommu_pagetable_unmap, @@ -367,17 +374,23 @@ static const struct msm_mmu_funcs funcs = { .resume_translation = msm_iommu_resume_translation, }; -struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain) +struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) { + struct iommu_domain *domain; struct msm_iommu *iommu; int ret; + domain = iommu_domain_alloc(dev->bus); if (!domain) - return ERR_PTR(-ENODEV); + return NULL; + + iommu_set_pgtable_quirks(domain, quirks); iommu = kzalloc(sizeof(*iommu), GFP_KERNEL); - if (!iommu) + if (!iommu) { + iommu_domain_free(domain); return ERR_PTR(-ENOMEM); + } iommu->domain = domain; msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); @@ -386,6 +399,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain) ret = iommu_attach_device(iommu->domain, dev); if (ret) { + iommu_domain_free(domain); kfree(iommu); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index e13c5c12b775..86b28add1fff 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -22,6 +22,7 @@ #define HW_REV 0x0 #define HW_INTR_STATUS 0x0010 +#define UBWC_DEC_HW_VERSION 0x58 #define UBWC_STATIC 0x144 #define UBWC_CTRL_2 0x150 #define UBWC_PREDICTION_MODE 0x154 @@ -174,9 +175,63 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss) return 0; } +#define UBWC_1_0 0x10000000 +#define UBWC_2_0 0x20000000 +#define UBWC_3_0 0x30000000 +#define UBWC_4_0 0x40000000 + +static void msm_mdss_setup_ubwc_dec_20(struct msm_mdss *msm_mdss, + u32 ubwc_static) +{ + writel_relaxed(ubwc_static, msm_mdss->mmio + UBWC_STATIC); +} + +static void msm_mdss_setup_ubwc_dec_30(struct msm_mdss *msm_mdss, + unsigned int ubwc_version, + u32 ubwc_swizzle, + u32 highest_bank_bit, + u32 macrotile_mode) +{ + u32 value = (ubwc_swizzle & 0x1) | + (highest_bank_bit & 0x3) << 4 | + (macrotile_mode & 0x1) << 12; + + if (ubwc_version == UBWC_3_0) + value |= BIT(10); + + if (ubwc_version == UBWC_1_0) + value |= BIT(8); + + writel_relaxed(value, msm_mdss->mmio + UBWC_STATIC); +} + +static void msm_mdss_setup_ubwc_dec_40(struct msm_mdss *msm_mdss, + unsigned int ubwc_version, + u32 ubwc_swizzle, + u32 ubwc_static, + u32 highest_bank_bit, + u32 macrotile_mode) +{ + u32 value = (ubwc_swizzle & 0x7) | + (ubwc_static & 0x1) << 3 | + (highest_bank_bit & 0x7) << 4 | + (macrotile_mode & 0x1) << 12; + + writel_relaxed(value, msm_mdss->mmio + UBWC_STATIC); + + if (ubwc_version == UBWC_3_0) { + writel_relaxed(1, msm_mdss->mmio + UBWC_CTRL_2); + writel_relaxed(0, msm_mdss->mmio + UBWC_PREDICTION_MODE); + } else { + writel_relaxed(2, msm_mdss->mmio + UBWC_CTRL_2); + writel_relaxed(1, msm_mdss->mmio + UBWC_PREDICTION_MODE); + } +} + static int msm_mdss_enable(struct msm_mdss *msm_mdss) { int ret; + u32 hw_rev; /* * Several components have AXI clocks that can only be turned on if @@ -198,26 +253,39 @@ static int msm_mdss_enable(struct msm_mdss *msm_mdss) if (msm_mdss->is_mdp5) return 0; + hw_rev = readl_relaxed(msm_mdss->mmio + HW_REV); + dev_dbg(msm_mdss->dev, "HW_REV: 0x%x\n", hw_rev); + dev_dbg(msm_mdss->dev, "UBWC_DEC_HW_VERSION: 0x%x\n", + readl_relaxed(msm_mdss->mmio + UBWC_DEC_HW_VERSION)); + /* * ubwc config is part of the "mdss" region which is not accessible * from the rest of the driver. hardcode known configurations here + * + * Decoder version can be read from the UBWC_DEC_HW_VERSION reg, + * UBWC_n and the rest of params comes from hw_catalog. + * Unforunately this driver can not access hw catalog, so we have to + * hardcode them here. */ - switch (readl_relaxed(msm_mdss->mmio + HW_REV)) { + switch (hw_rev) { case DPU_HW_VER_500: case DPU_HW_VER_501: - writel_relaxed(0x420, msm_mdss->mmio + UBWC_STATIC); + msm_mdss_setup_ubwc_dec_30(msm_mdss, UBWC_3_0, 0, 2, 0); break; case DPU_HW_VER_600: - /* TODO: 0x102e for LP_DDR4 */ - writel_relaxed(0x103e, msm_mdss->mmio + UBWC_STATIC); - writel_relaxed(2, msm_mdss->mmio + UBWC_CTRL_2); - writel_relaxed(1, msm_mdss->mmio + UBWC_PREDICTION_MODE); + /* TODO: highest_bank_bit = 2 for LP_DDR4 */ + msm_mdss_setup_ubwc_dec_40(msm_mdss, UBWC_4_0, 6, 1, 3, 1); break; case DPU_HW_VER_620: - writel_relaxed(0x1e, msm_mdss->mmio + UBWC_STATIC); + /* UBWC_2_0 */ + msm_mdss_setup_ubwc_dec_20(msm_mdss, 0x1e); + break; + case DPU_HW_VER_630: + /* UBWC_2_0 */ + msm_mdss_setup_ubwc_dec_20(msm_mdss, 0x11f); break; case DPU_HW_VER_720: - writel_relaxed(0x101e, msm_mdss->mmio + UBWC_STATIC); + msm_mdss_setup_ubwc_dec_40(msm_mdss, UBWC_3_0, 6, 1, 1, 1); break; } @@ -445,6 +513,7 @@ static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,sc7180-mdss" }, { .compatible = "qcom,sc7280-mdss" }, { .compatible = "qcom,sc8180x-mdss" }, + { .compatible = "qcom,sm6115-mdss" }, { .compatible = "qcom,sm8150-mdss" }, { .compatible = "qcom,sm8250-mdss" }, {} diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h index de158e1bf765..74cd81e701ff 100644 --- a/drivers/gpu/drm/msm/msm_mmu.h +++ b/drivers/gpu/drm/msm/msm_mmu.h @@ -40,7 +40,7 @@ static inline void msm_mmu_init(struct msm_mmu *mmu, struct device *dev, mmu->type = type; } -struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain); +struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks); struct msm_mmu *msm_gpummu_new(struct device *dev, struct msm_gpu *gpu); static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, @@ -58,5 +58,6 @@ void msm_gpummu_params(struct msm_mmu *mmu, dma_addr_t *pt_base, int msm_iommu_pagetable_params(struct msm_mmu *mmu, phys_addr_t *ttbr, int *asid); +struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu); #endif /* __MSM_MMU_H__ */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index cad4c3525f0b..57a8e9564540 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -25,7 +25,8 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) msm_gem_lock(obj); msm_gem_unpin_vma_fenced(submit->bos[i].vma, fctx); - submit->bos[i].flags &= ~BO_VMA_PINNED; + msm_gem_unpin_locked(obj); + submit->bos[i].flags &= ~(BO_VMA_PINNED | BO_OBJ_PINNED); msm_gem_unlock(obj); } diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h index 2a5045abe46e..698b333abccd 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.h +++ b/drivers/gpu/drm/msm/msm_ringbuffer.h @@ -35,6 +35,11 @@ struct msm_rbmemptrs { volatile u64 ttbr0; }; +struct msm_cp_state { + uint64_t ib1_base, ib2_base; + uint32_t ib1_rem, ib2_rem; +}; + struct msm_ringbuffer { struct msm_gpu *gpu; int id; @@ -64,6 +69,29 @@ struct msm_ringbuffer { uint64_t memptrs_iova; struct msm_fence_context *fctx; + /** + * hangcheck_progress_retries: + * + * The number of extra hangcheck duration cycles that we have given + * due to it appearing that the GPU is making forward progress. + * + * For GPU generations which support progress detection (see. + * msm_gpu_funcs::progress()), if the GPU appears to be making progress + * (ie. the CP has advanced in the command stream, we'll allow up to + * DRM_MSM_HANGCHECK_PROGRESS_RETRIES expirations of the hangcheck timer + * before killing the job. But to detect progress we need two sample + * points, so the duration of the hangcheck timer is halved. In other + * words we'll let the submit run for up to: + * + * (DRM_MSM_HANGCHECK_DEFAULT_PERIOD / 2) * (DRM_MSM_HANGCHECK_PROGRESS_RETRIES + 1) + */ + int hangcheck_progress_retries; + + /** + * last_cp_state: The state of the CP at the last call to gpu->progress() + */ + struct msm_cp_state last_cp_state; + /* * preempt_lock protects preemption and serializes wptr updates against * preemption. Can be aquired from irq context. diff --git a/drivers/gpu/drm/mxsfb/lcdif_drv.c b/drivers/gpu/drm/mxsfb/lcdif_drv.c index 075002ed6fb0..cc2ceb301b96 100644 --- a/drivers/gpu/drm/mxsfb/lcdif_drv.c +++ b/drivers/gpu/drm/mxsfb/lcdif_drv.c @@ -16,7 +16,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_mode_config.h> diff --git a/drivers/gpu/drm/mxsfb/lcdif_kms.c b/drivers/gpu/drm/mxsfb/lcdif_kms.c index f0ad6e2a9352..262bc43b1079 100644 --- a/drivers/gpu/drm/mxsfb/lcdif_kms.c +++ b/drivers/gpu/drm/mxsfb/lcdif_kms.c @@ -5,6 +5,7 @@ * This code is based on drivers/gpu/drm/mxsfb/mxsfb* */ +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/io.h> #include <linux/iopoll.h> @@ -332,6 +333,18 @@ static void lcdif_enable_controller(struct lcdif_drm_private *lcdif) { u32 reg; + /* Set FIFO Panic watermarks, low 1/3, high 2/3 . */ + writel(FIELD_PREP(PANIC0_THRES_LOW_MASK, 1 * PANIC0_THRES_MAX / 3) | + FIELD_PREP(PANIC0_THRES_HIGH_MASK, 2 * PANIC0_THRES_MAX / 3), + lcdif->base + LCDC_V8_PANIC0_THRES); + + /* + * Enable FIFO Panic, this does not generate interrupt, but + * boosts NoC priority based on FIFO Panic watermarks. + */ + writel(INT_ENABLE_D1_PLANE_PANIC_EN, + lcdif->base + LCDC_V8_INT_ENABLE_D1); + reg = readl(lcdif->base + LCDC_V8_DISP_PARA); reg |= DISP_PARA_DISP_ON; writel(reg, lcdif->base + LCDC_V8_DISP_PARA); @@ -359,6 +372,9 @@ static void lcdif_disable_controller(struct lcdif_drm_private *lcdif) reg = readl(lcdif->base + LCDC_V8_DISP_PARA); reg &= ~DISP_PARA_DISP_ON; writel(reg, lcdif->base + LCDC_V8_DISP_PARA); + + /* Disable FIFO Panic NoC priority booster. */ + writel(0, lcdif->base + LCDC_V8_INT_ENABLE_D1); } static void lcdif_reset_block(struct lcdif_drm_private *lcdif) diff --git a/drivers/gpu/drm/mxsfb/lcdif_regs.h b/drivers/gpu/drm/mxsfb/lcdif_regs.h index fb74eb5ccbf1..c55dfb236c1d 100644 --- a/drivers/gpu/drm/mxsfb/lcdif_regs.h +++ b/drivers/gpu/drm/mxsfb/lcdif_regs.h @@ -255,6 +255,7 @@ #define PANIC0_THRES_LOW_MASK GENMASK(24, 16) #define PANIC0_THRES_HIGH_MASK GENMASK(8, 0) +#define PANIC0_THRES_MAX 511 #define LCDIF_MIN_XRES 120 #define LCDIF_MIN_YRES 120 diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c index b29b332ed381..810edea0a31e 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c @@ -20,7 +20,7 @@ #include <drm/drm_bridge.h> #include <drm/drm_connector.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index a614582779ca..40409a29f5b6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -264,7 +264,11 @@ nva3_set_intensity(struct backlight_device *bd) u32 div, val; div = nvif_rd32(device, NV50_PDISP_SOR_PWM_DIV(or)); - val = (bd->props.brightness * div) / 100; + + val = backlight_get_brightness(bd); + if (val) + val = (val * div) / 100; + if (div) { nvif_wr32(device, NV50_PDISP_SOR_PWM_CTL(or), val | diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index a19f18b251f3..80f154b6adab 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -34,6 +34,7 @@ #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_ttm_helper.h> #include <drm/drm_ioctl.h> #include <drm/drm_vblank.h> diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c new file mode 100644 index 000000000000..e87de7906f78 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -0,0 +1,613 @@ +/* + * Copyright © 2007 David Airlie + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Authors: + * David Airlie + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/tty.h> +#include <linux/sysrq.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/screen_info.h> +#include <linux/vga_switcheroo.h> +#include <linux/console.h> + +#include <drm/drm_crtc.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_atomic.h> + +#include "nouveau_drv.h" +#include "nouveau_gem.h" +#include "nouveau_bo.h" +#include "nouveau_fbcon.h" +#include "nouveau_chan.h" +#include "nouveau_vmm.h" + +#include "nouveau_crtc.h" + +MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration"); +int nouveau_nofbaccel = 0; +module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400); + +MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)"); +static int nouveau_fbcon_bpp; +module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400); + +static void +nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); + struct nvif_device *device = &drm->client.device; + int ret; + + if (info->state != FBINFO_STATE_RUNNING) + return; + + ret = -ENODEV; + if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) && + mutex_trylock(&drm->client.mutex)) { + if (device->info.family < NV_DEVICE_INFO_V0_TESLA) + ret = nv04_fbcon_fillrect(info, rect); + else + if (device->info.family < NV_DEVICE_INFO_V0_FERMI) + ret = nv50_fbcon_fillrect(info, rect); + else + ret = nvc0_fbcon_fillrect(info, rect); + mutex_unlock(&drm->client.mutex); + } + + if (ret == 0) + return; + + if (ret != -ENODEV) + nouveau_fbcon_gpu_lockup(info); + drm_fb_helper_cfb_fillrect(info, rect); +} + +static void +nouveau_fbcon_copyarea(struct fb_info *info, const struct fb_copyarea *image) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); + struct nvif_device *device = &drm->client.device; + int ret; + + if (info->state != FBINFO_STATE_RUNNING) + return; + + ret = -ENODEV; + if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) && + mutex_trylock(&drm->client.mutex)) { + if (device->info.family < NV_DEVICE_INFO_V0_TESLA) + ret = nv04_fbcon_copyarea(info, image); + else + if (device->info.family < NV_DEVICE_INFO_V0_FERMI) + ret = nv50_fbcon_copyarea(info, image); + else + ret = nvc0_fbcon_copyarea(info, image); + mutex_unlock(&drm->client.mutex); + } + + if (ret == 0) + return; + + if (ret != -ENODEV) + nouveau_fbcon_gpu_lockup(info); + drm_fb_helper_cfb_copyarea(info, image); +} + +static void +nouveau_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); + struct nvif_device *device = &drm->client.device; + int ret; + + if (info->state != FBINFO_STATE_RUNNING) + return; + + ret = -ENODEV; + if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) && + mutex_trylock(&drm->client.mutex)) { + if (device->info.family < NV_DEVICE_INFO_V0_TESLA) + ret = nv04_fbcon_imageblit(info, image); + else + if (device->info.family < NV_DEVICE_INFO_V0_FERMI) + ret = nv50_fbcon_imageblit(info, image); + else + ret = nvc0_fbcon_imageblit(info, image); + mutex_unlock(&drm->client.mutex); + } + + if (ret == 0) + return; + + if (ret != -ENODEV) + nouveau_fbcon_gpu_lockup(info); + drm_fb_helper_cfb_imageblit(info, image); +} + +static int +nouveau_fbcon_sync(struct fb_info *info) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); + struct nouveau_channel *chan = drm->channel; + int ret; + + if (!chan || !chan->accel_done || in_interrupt() || + info->state != FBINFO_STATE_RUNNING || + info->flags & FBINFO_HWACCEL_DISABLED) + return 0; + + if (!mutex_trylock(&drm->client.mutex)) + return 0; + + ret = nouveau_channel_idle(chan); + mutex_unlock(&drm->client.mutex); + if (ret) { + nouveau_fbcon_gpu_lockup(info); + return 0; + } + + chan->accel_done = false; + return 0; +} + +static int +nouveau_fbcon_open(struct fb_info *info, int user) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); + int ret = pm_runtime_get_sync(drm->dev->dev); + if (ret < 0 && ret != -EACCES) { + pm_runtime_put(drm->dev->dev); + return ret; + } + return 0; +} + +static int +nouveau_fbcon_release(struct fb_info *info, int user) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); + pm_runtime_put(drm->dev->dev); + return 0; +} + +static const struct fb_ops nouveau_fbcon_ops = { + .owner = THIS_MODULE, + DRM_FB_HELPER_DEFAULT_OPS, + .fb_open = nouveau_fbcon_open, + .fb_release = nouveau_fbcon_release, + .fb_fillrect = nouveau_fbcon_fillrect, + .fb_copyarea = nouveau_fbcon_copyarea, + .fb_imageblit = nouveau_fbcon_imageblit, + .fb_sync = nouveau_fbcon_sync, +}; + +static const struct fb_ops nouveau_fbcon_sw_ops = { + .owner = THIS_MODULE, + DRM_FB_HELPER_DEFAULT_OPS, + .fb_open = nouveau_fbcon_open, + .fb_release = nouveau_fbcon_release, + .fb_fillrect = drm_fb_helper_cfb_fillrect, + .fb_copyarea = drm_fb_helper_cfb_copyarea, + .fb_imageblit = drm_fb_helper_cfb_imageblit, +}; + +void +nouveau_fbcon_accel_save_disable(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + if (drm->fbcon && drm->fbcon->helper.info) { + drm->fbcon->saved_flags = drm->fbcon->helper.info->flags; + drm->fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED; + } +} + +void +nouveau_fbcon_accel_restore(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + if (drm->fbcon && drm->fbcon->helper.info) + drm->fbcon->helper.info->flags = drm->fbcon->saved_flags; +} + +static void +nouveau_fbcon_accel_fini(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon = drm->fbcon; + if (fbcon && drm->channel) { + console_lock(); + if (fbcon->helper.info) + fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED; + console_unlock(); + nouveau_channel_idle(drm->channel); + nvif_object_dtor(&fbcon->twod); + nvif_object_dtor(&fbcon->blit); + nvif_object_dtor(&fbcon->gdi); + nvif_object_dtor(&fbcon->patt); + nvif_object_dtor(&fbcon->rop); + nvif_object_dtor(&fbcon->clip); + nvif_object_dtor(&fbcon->surf2d); + } +} + +static void +nouveau_fbcon_accel_init(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon = drm->fbcon; + struct fb_info *info = fbcon->helper.info; + int ret; + + if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) + ret = nv04_fbcon_accel_init(info); + else + if (drm->client.device.info.family < NV_DEVICE_INFO_V0_FERMI) + ret = nv50_fbcon_accel_init(info); + else + ret = nvc0_fbcon_accel_init(info); + + if (ret == 0) + info->fbops = &nouveau_fbcon_ops; +} + +static void +nouveau_fbcon_zfill(struct drm_device *dev, struct nouveau_fbdev *fbcon) +{ + struct fb_info *info = fbcon->helper.info; + struct fb_fillrect rect; + + /* Clear the entire fbcon. The drm will program every connector + * with it's preferred mode. If the sizes differ, one display will + * quite likely have garbage around the console. + */ + rect.dx = rect.dy = 0; + rect.width = info->var.xres_virtual; + rect.height = info->var.yres_virtual; + rect.color = 0; + rect.rop = ROP_COPY; + info->fbops->fb_fillrect(info, &rect); +} + +static int +nouveau_fbcon_create(struct drm_fb_helper *helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct nouveau_fbdev *fbcon = + container_of(helper, struct nouveau_fbdev, helper); + struct drm_device *dev = fbcon->helper.dev; + struct nouveau_drm *drm = nouveau_drm(dev); + struct nvif_device *device = &drm->client.device; + struct fb_info *info; + struct drm_framebuffer *fb; + struct nouveau_channel *chan; + struct nouveau_bo *nvbo; + struct drm_mode_fb_cmd2 mode_cmd = {}; + int ret; + + mode_cmd.width = sizes->surface_width; + mode_cmd.height = sizes->surface_height; + + mode_cmd.pitches[0] = mode_cmd.width * (sizes->surface_bpp >> 3); + mode_cmd.pitches[0] = roundup(mode_cmd.pitches[0], 256); + + mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, + sizes->surface_depth); + + ret = nouveau_gem_new(&drm->client, mode_cmd.pitches[0] * + mode_cmd.height, 0, NOUVEAU_GEM_DOMAIN_VRAM, + 0, 0x0000, &nvbo); + if (ret) { + NV_ERROR(drm, "failed to allocate framebuffer\n"); + goto out; + } + + ret = nouveau_framebuffer_new(dev, &mode_cmd, &nvbo->bo.base, &fb); + if (ret) + goto out_unref; + + ret = nouveau_bo_pin(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, false); + if (ret) { + NV_ERROR(drm, "failed to pin fb: %d\n", ret); + goto out_unref; + } + + ret = nouveau_bo_map(nvbo); + if (ret) { + NV_ERROR(drm, "failed to map fb: %d\n", ret); + goto out_unpin; + } + + chan = nouveau_nofbaccel ? NULL : drm->channel; + if (chan && device->info.family >= NV_DEVICE_INFO_V0_TESLA) { + ret = nouveau_vma_new(nvbo, chan->vmm, &fbcon->vma); + if (ret) { + NV_ERROR(drm, "failed to map fb into chan: %d\n", ret); + chan = NULL; + } + } + + info = drm_fb_helper_alloc_info(helper); + if (IS_ERR(info)) { + ret = PTR_ERR(info); + goto out_unlock; + } + + /* setup helper */ + fbcon->helper.fb = fb; + + if (!chan) + info->flags = FBINFO_HWACCEL_DISABLED; + else + info->flags = FBINFO_HWACCEL_COPYAREA | + FBINFO_HWACCEL_FILLRECT | + FBINFO_HWACCEL_IMAGEBLIT; + info->fbops = &nouveau_fbcon_sw_ops; + info->fix.smem_start = nvbo->bo.resource->bus.offset; + info->fix.smem_len = nvbo->bo.base.size; + + info->screen_base = nvbo_kmap_obj_iovirtual(nvbo); + info->screen_size = nvbo->bo.base.size; + + drm_fb_helper_fill_info(info, &fbcon->helper, sizes); + + /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */ + + if (chan) + nouveau_fbcon_accel_init(dev); + nouveau_fbcon_zfill(dev, fbcon); + + /* To allow resizeing without swapping buffers */ + NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n", + fb->width, fb->height, nvbo->offset, nvbo); + + if (dev_is_pci(dev->dev)) + vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), info); + + return 0; + +out_unlock: + if (chan) + nouveau_vma_del(&fbcon->vma); + nouveau_bo_unmap(nvbo); +out_unpin: + nouveau_bo_unpin(nvbo); +out_unref: + nouveau_bo_ref(NULL, &nvbo); +out: + return ret; +} + +static int +nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon) +{ + struct drm_framebuffer *fb = fbcon->helper.fb; + struct nouveau_bo *nvbo; + + drm_fb_helper_unregister_info(&fbcon->helper); + drm_fb_helper_fini(&fbcon->helper); + + if (fb && fb->obj[0]) { + nvbo = nouveau_gem_object(fb->obj[0]); + nouveau_vma_del(&fbcon->vma); + nouveau_bo_unmap(nvbo); + nouveau_bo_unpin(nvbo); + drm_framebuffer_put(fb); + } + + return 0; +} + +void nouveau_fbcon_gpu_lockup(struct fb_info *info) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); + + NV_ERROR(drm, "GPU lockup - switching to software fbcon\n"); + info->flags |= FBINFO_HWACCEL_DISABLED; +} + +static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = { + .fb_probe = nouveau_fbcon_create, +}; + +static void +nouveau_fbcon_set_suspend_work(struct work_struct *work) +{ + struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work); + int state = READ_ONCE(drm->fbcon_new_state); + + if (state == FBINFO_STATE_RUNNING) + pm_runtime_get_sync(drm->dev->dev); + + console_lock(); + if (state == FBINFO_STATE_RUNNING) + nouveau_fbcon_accel_restore(drm->dev); + drm_fb_helper_set_suspend(&drm->fbcon->helper, state); + if (state != FBINFO_STATE_RUNNING) + nouveau_fbcon_accel_save_disable(drm->dev); + console_unlock(); + + if (state == FBINFO_STATE_RUNNING) { + nouveau_fbcon_hotplug_resume(drm->fbcon); + pm_runtime_mark_last_busy(drm->dev->dev); + pm_runtime_put_autosuspend(drm->dev->dev); + } +} + +void +nouveau_fbcon_set_suspend(struct drm_device *dev, int state) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + + if (!drm->fbcon) + return; + + drm->fbcon_new_state = state; + /* Since runtime resume can happen as a result of a sysfs operation, + * it's possible we already have the console locked. So handle fbcon + * init/deinit from a seperate work thread + */ + schedule_work(&drm->fbcon_work); +} + +void +nouveau_fbcon_output_poll_changed(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon = drm->fbcon; + int ret; + + if (!fbcon) + return; + + mutex_lock(&fbcon->hotplug_lock); + + ret = pm_runtime_get(dev->dev); + if (ret == 1 || ret == -EACCES) { + drm_fb_helper_hotplug_event(&fbcon->helper); + + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); + } else if (ret == 0) { + /* If the GPU was already in the process of suspending before + * this event happened, then we can't block here as we'll + * deadlock the runtime pmops since they wait for us to + * finish. So, just defer this event for when we runtime + * resume again. It will be handled by fbcon_work. + */ + NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n"); + fbcon->hotplug_waiting = true; + pm_runtime_put_noidle(drm->dev->dev); + } else { + DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n", + ret); + } + + mutex_unlock(&fbcon->hotplug_lock); +} + +void +nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon) +{ + struct nouveau_drm *drm; + + if (!fbcon) + return; + drm = nouveau_drm(fbcon->helper.dev); + + mutex_lock(&fbcon->hotplug_lock); + if (fbcon->hotplug_waiting) { + fbcon->hotplug_waiting = false; + + NV_DEBUG(drm, "Handling deferred fbcon HPD events\n"); + drm_fb_helper_hotplug_event(&fbcon->helper); + } + mutex_unlock(&fbcon->hotplug_lock); +} + +int +nouveau_fbcon_init(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon; + int preferred_bpp = nouveau_fbcon_bpp; + int ret; + + if (!dev->mode_config.num_crtc || + (to_pci_dev(dev->dev)->class >> 8) != PCI_CLASS_DISPLAY_VGA) + return 0; + + fbcon = kzalloc(sizeof(struct nouveau_fbdev), GFP_KERNEL); + if (!fbcon) + return -ENOMEM; + + drm->fbcon = fbcon; + INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work); + mutex_init(&fbcon->hotplug_lock); + + drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs); + + ret = drm_fb_helper_init(dev, &fbcon->helper); + if (ret) + goto free; + + if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) { + if (drm->client.device.info.ram_size <= 32 * 1024 * 1024) + preferred_bpp = 8; + else + if (drm->client.device.info.ram_size <= 64 * 1024 * 1024) + preferred_bpp = 16; + else + preferred_bpp = 32; + } + + /* disable all the possible outputs/crtcs before entering KMS mode */ + if (!drm_drv_uses_atomic_modeset(dev)) + drm_helper_disable_unused_functions(dev); + + ret = drm_fb_helper_initial_config(&fbcon->helper, preferred_bpp); + if (ret) + goto fini; + + if (fbcon->helper.info) + fbcon->helper.info->pixmap.buf_align = 4; + return 0; + +fini: + drm_fb_helper_fini(&fbcon->helper); +free: + kfree(fbcon); + drm->fbcon = NULL; + return ret; +} + +void +nouveau_fbcon_fini(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + + if (!drm->fbcon) + return; + + drm_kms_helper_poll_fini(dev); + nouveau_fbcon_accel_fini(dev); + nouveau_fbcon_destroy(dev, drm->fbcon); + kfree(drm->fbcon); + drm->fbcon = NULL; +} diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index ed67dd25794c..98d8758048fc 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -38,7 +38,7 @@ static struct drm_fb_helper *get_fb(struct fb_info *fbi); static void pan_worker(struct work_struct *work) { struct omap_fbdev *fbdev = container_of(work, struct omap_fbdev, work); - struct fb_info *fbi = fbdev->base.fbdev; + struct fb_info *fbi = fbdev->base.info; int npages; /* DMM roll shifts in 4K pages: */ @@ -161,7 +161,7 @@ static int omap_fbdev_create(struct drm_fb_helper *helper, goto fail; } - fbi = drm_fb_helper_alloc_fbi(helper); + fbi = drm_fb_helper_alloc_info(helper); if (IS_ERR(fbi)) { dev_err(dev->dev, "failed to allocate fb info\n"); ret = PTR_ERR(fbi); @@ -272,7 +272,7 @@ void omap_fbdev_fini(struct drm_device *dev) if (!helper) return; - drm_fb_helper_unregister_fbi(helper); + drm_fb_helper_unregister_info(helper); drm_fb_helper_fini(helper); diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index 8e194dbc9506..3abc47521b2c 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -66,6 +66,8 @@ static int omap_gem_dmabuf_mmap(struct dma_buf *buffer, struct drm_gem_object *obj = buffer->priv; int ret = 0; + dma_resv_assert_held(buffer->resv); + ret = drm_gem_mmap_obj(obj, omap_gem_mmap_size(obj), vma); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index a582ddd583c2..737edcdf9eef 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -203,6 +203,16 @@ config DRM_PANEL_INNOLUX_P079ZCA 24 bit RGB per pixel. It provides a MIPI DSI interface to the host and has a built-in LED backlight. +config DRM_PANEL_JADARD_JD9365DA_H3 + tristate "Jadard JD9365DA-H3 WXGA DSI panel" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + help + Say Y here if you want to enable support for Jadard JD9365DA-H3 + WXGA MIPI DSI panel. The panel support TFT dot matrix LCD with + 800RGBx1280 dots at maximum. + config DRM_PANEL_JDI_LT070ME05000 tristate "JDI LT070ME05000 WUXGA DSI panel" depends on OF @@ -296,6 +306,15 @@ config DRM_PANEL_NEC_NL8048HL11 panel (found on the Zoom2/3/3630 SDP boards). To compile this driver as a module, choose M here. +config DRM_PANEL_NEWVISION_NV3051D + tristate "NewVision NV3051D DSI panel" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + help + This driver supports the NV3051D based panel found on the Anbernic + RG353P and RG353V. + config DRM_PANEL_NEWVISION_NV3052C tristate "NewVision NV3052C RGB/SPI panel" depends on OF && SPI diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile index 34e717382dbb..f8f9d9f6a307 100644 --- a/drivers/gpu/drm/panel/Makefile +++ b/drivers/gpu/drm/panel/Makefile @@ -18,6 +18,7 @@ obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9341) += panel-ilitek-ili9341.o obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9881C) += panel-ilitek-ili9881c.o obj-$(CONFIG_DRM_PANEL_INNOLUX_EJ030NA) += panel-innolux-ej030na.o obj-$(CONFIG_DRM_PANEL_INNOLUX_P079ZCA) += panel-innolux-p079zca.o +obj-$(CONFIG_DRM_PANEL_JADARD_JD9365DA_H3) += panel-jadard-jd9365da-h3.o obj-$(CONFIG_DRM_PANEL_JDI_LT070ME05000) += panel-jdi-lt070me05000.o obj-$(CONFIG_DRM_PANEL_JDI_R63452) += panel-jdi-fhd-r63452.o obj-$(CONFIG_DRM_PANEL_KHADAS_TS050) += panel-khadas-ts050.o @@ -27,6 +28,7 @@ obj-$(CONFIG_DRM_PANEL_LEADTEK_LTK500HD1829) += panel-leadtek-ltk500hd1829.o obj-$(CONFIG_DRM_PANEL_LG_LB035Q02) += panel-lg-lb035q02.o obj-$(CONFIG_DRM_PANEL_LG_LG4573) += panel-lg-lg4573.o obj-$(CONFIG_DRM_PANEL_NEC_NL8048HL11) += panel-nec-nl8048hl11.o +obj-$(CONFIG_DRM_PANEL_NEWVISION_NV3051D) += panel-newvision-nv3051d.o obj-$(CONFIG_DRM_PANEL_NEWVISION_NV3052C) += panel-newvision-nv3052c.o obj-$(CONFIG_DRM_PANEL_NOVATEK_NT35510) += panel-novatek-nt35510.o obj-$(CONFIG_DRM_PANEL_NOVATEK_NT35560) += panel-novatek-nt35560.o diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index 39dc40cf681f..384a724f2822 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -18,6 +18,7 @@ * Copyright 2018 David Lechner <david@lechnology.com> */ +#include <linux/backlight.h> #include <linux/bitops.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> @@ -30,7 +31,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c new file mode 100644 index 000000000000..48c1702a863b --- /dev/null +++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c @@ -0,0 +1,473 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2019 Radxa Limited + * Copyright (c) 2022 Edgeble AI Technologies Pvt. Ltd. + * + * Author: + * - Jagan Teki <jagan@amarulasolutions.com> + * - Stephen Chen <stephen@radxa.com> + */ + +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> +#include <drm/drm_print.h> + +#include <linux/gpio/consumer.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regulator/consumer.h> + +#define JD9365DA_INIT_CMD_LEN 2 + +struct jadard_init_cmd { + u8 data[JD9365DA_INIT_CMD_LEN]; +}; + +struct jadard_panel_desc { + const struct drm_display_mode mode; + unsigned int lanes; + enum mipi_dsi_pixel_format format; + const struct jadard_init_cmd *init_cmds; + u32 num_init_cmds; +}; + +struct jadard { + struct drm_panel panel; + struct mipi_dsi_device *dsi; + const struct jadard_panel_desc *desc; + + struct regulator *vdd; + struct regulator *vccio; + struct gpio_desc *reset; +}; + +static inline struct jadard *panel_to_jadard(struct drm_panel *panel) +{ + return container_of(panel, struct jadard, panel); +} + +static int jadard_enable(struct drm_panel *panel) +{ + struct device *dev = panel->dev; + struct jadard *jadard = panel_to_jadard(panel); + const struct jadard_panel_desc *desc = jadard->desc; + struct mipi_dsi_device *dsi = jadard->dsi; + unsigned int i; + int err; + + msleep(10); + + for (i = 0; i < desc->num_init_cmds; i++) { + const struct jadard_init_cmd *cmd = &desc->init_cmds[i]; + + err = mipi_dsi_dcs_write_buffer(dsi, cmd->data, JD9365DA_INIT_CMD_LEN); + if (err < 0) + return err; + } + + msleep(120); + + err = mipi_dsi_dcs_exit_sleep_mode(dsi); + if (err < 0) + DRM_DEV_ERROR(dev, "failed to exit sleep mode ret = %d\n", err); + + err = mipi_dsi_dcs_set_display_on(dsi); + if (err < 0) + DRM_DEV_ERROR(dev, "failed to set display on ret = %d\n", err); + + return 0; +} + +static int jadard_disable(struct drm_panel *panel) +{ + struct device *dev = panel->dev; + struct jadard *jadard = panel_to_jadard(panel); + int ret; + + ret = mipi_dsi_dcs_set_display_off(jadard->dsi); + if (ret < 0) + DRM_DEV_ERROR(dev, "failed to set display off: %d\n", ret); + + ret = mipi_dsi_dcs_enter_sleep_mode(jadard->dsi); + if (ret < 0) + DRM_DEV_ERROR(dev, "failed to enter sleep mode: %d\n", ret); + + return 0; +} + +static int jadard_prepare(struct drm_panel *panel) +{ + struct jadard *jadard = panel_to_jadard(panel); + int ret; + + ret = regulator_enable(jadard->vccio); + if (ret) + return ret; + + ret = regulator_enable(jadard->vdd); + if (ret) + return ret; + + gpiod_set_value(jadard->reset, 1); + msleep(5); + + gpiod_set_value(jadard->reset, 0); + msleep(10); + + gpiod_set_value(jadard->reset, 1); + msleep(120); + + return 0; +} + +static int jadard_unprepare(struct drm_panel *panel) +{ + struct jadard *jadard = panel_to_jadard(panel); + + gpiod_set_value(jadard->reset, 1); + msleep(120); + + regulator_disable(jadard->vdd); + regulator_disable(jadard->vccio); + + return 0; +} + +static int jadard_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + struct jadard *jadard = panel_to_jadard(panel); + const struct drm_display_mode *desc_mode = &jadard->desc->mode; + struct drm_display_mode *mode; + + mode = drm_mode_duplicate(connector->dev, desc_mode); + if (!mode) { + DRM_DEV_ERROR(&jadard->dsi->dev, "failed to add mode %ux%ux@%u\n", + desc_mode->hdisplay, desc_mode->vdisplay, + drm_mode_vrefresh(desc_mode)); + return -ENOMEM; + } + + drm_mode_set_name(mode); + drm_mode_probed_add(connector, mode); + + connector->display_info.width_mm = mode->width_mm; + connector->display_info.height_mm = mode->height_mm; + + return 1; +} + +static const struct drm_panel_funcs jadard_funcs = { + .disable = jadard_disable, + .unprepare = jadard_unprepare, + .prepare = jadard_prepare, + .enable = jadard_enable, + .get_modes = jadard_get_modes, +}; + +static const struct jadard_init_cmd cz101b4001_init_cmds[] = { + { .data = { 0xE0, 0x00 } }, + { .data = { 0xE1, 0x93 } }, + { .data = { 0xE2, 0x65 } }, + { .data = { 0xE3, 0xF8 } }, + { .data = { 0x80, 0x03 } }, + { .data = { 0xE0, 0x01 } }, + { .data = { 0x00, 0x00 } }, + { .data = { 0x01, 0x3B } }, + { .data = { 0x0C, 0x74 } }, + { .data = { 0x17, 0x00 } }, + { .data = { 0x18, 0xAF } }, + { .data = { 0x19, 0x00 } }, + { .data = { 0x1A, 0x00 } }, + { .data = { 0x1B, 0xAF } }, + { .data = { 0x1C, 0x00 } }, + { .data = { 0x35, 0x26 } }, + { .data = { 0x37, 0x09 } }, + { .data = { 0x38, 0x04 } }, + { .data = { 0x39, 0x00 } }, + { .data = { 0x3A, 0x01 } }, + { .data = { 0x3C, 0x78 } }, + { .data = { 0x3D, 0xFF } }, + { .data = { 0x3E, 0xFF } }, + { .data = { 0x3F, 0x7F } }, + { .data = { 0x40, 0x06 } }, + { .data = { 0x41, 0xA0 } }, + { .data = { 0x42, 0x81 } }, + { .data = { 0x43, 0x14 } }, + { .data = { 0x44, 0x23 } }, + { .data = { 0x45, 0x28 } }, + { .data = { 0x55, 0x02 } }, + { .data = { 0x57, 0x69 } }, + { .data = { 0x59, 0x0A } }, + { .data = { 0x5A, 0x2A } }, + { .data = { 0x5B, 0x17 } }, + { .data = { 0x5D, 0x7F } }, + { .data = { 0x5E, 0x6B } }, + { .data = { 0x5F, 0x5C } }, + { .data = { 0x60, 0x4F } }, + { .data = { 0x61, 0x4D } }, + { .data = { 0x62, 0x3F } }, + { .data = { 0x63, 0x42 } }, + { .data = { 0x64, 0x2B } }, + { .data = { 0x65, 0x44 } }, + { .data = { 0x66, 0x43 } }, + { .data = { 0x67, 0x43 } }, + { .data = { 0x68, 0x63 } }, + { .data = { 0x69, 0x52 } }, + { .data = { 0x6A, 0x5A } }, + { .data = { 0x6B, 0x4F } }, + { .data = { 0x6C, 0x4E } }, + { .data = { 0x6D, 0x20 } }, + { .data = { 0x6E, 0x0F } }, + { .data = { 0x6F, 0x00 } }, + { .data = { 0x70, 0x7F } }, + { .data = { 0x71, 0x6B } }, + { .data = { 0x72, 0x5C } }, + { .data = { 0x73, 0x4F } }, + { .data = { 0x74, 0x4D } }, + { .data = { 0x75, 0x3F } }, + { .data = { 0x76, 0x42 } }, + { .data = { 0x77, 0x2B } }, + { .data = { 0x78, 0x44 } }, + { .data = { 0x79, 0x43 } }, + { .data = { 0x7A, 0x43 } }, + { .data = { 0x7B, 0x63 } }, + { .data = { 0x7C, 0x52 } }, + { .data = { 0x7D, 0x5A } }, + { .data = { 0x7E, 0x4F } }, + { .data = { 0x7F, 0x4E } }, + { .data = { 0x80, 0x20 } }, + { .data = { 0x81, 0x0F } }, + { .data = { 0x82, 0x00 } }, + { .data = { 0xE0, 0x02 } }, + { .data = { 0x00, 0x02 } }, + { .data = { 0x01, 0x02 } }, + { .data = { 0x02, 0x00 } }, + { .data = { 0x03, 0x00 } }, + { .data = { 0x04, 0x1E } }, + { .data = { 0x05, 0x1E } }, + { .data = { 0x06, 0x1F } }, + { .data = { 0x07, 0x1F } }, + { .data = { 0x08, 0x1F } }, + { .data = { 0x09, 0x17 } }, + { .data = { 0x0A, 0x17 } }, + { .data = { 0x0B, 0x37 } }, + { .data = { 0x0C, 0x37 } }, + { .data = { 0x0D, 0x47 } }, + { .data = { 0x0E, 0x47 } }, + { .data = { 0x0F, 0x45 } }, + { .data = { 0x10, 0x45 } }, + { .data = { 0x11, 0x4B } }, + { .data = { 0x12, 0x4B } }, + { .data = { 0x13, 0x49 } }, + { .data = { 0x14, 0x49 } }, + { .data = { 0x15, 0x1F } }, + { .data = { 0x16, 0x01 } }, + { .data = { 0x17, 0x01 } }, + { .data = { 0x18, 0x00 } }, + { .data = { 0x19, 0x00 } }, + { .data = { 0x1A, 0x1E } }, + { .data = { 0x1B, 0x1E } }, + { .data = { 0x1C, 0x1F } }, + { .data = { 0x1D, 0x1F } }, + { .data = { 0x1E, 0x1F } }, + { .data = { 0x1F, 0x17 } }, + { .data = { 0x20, 0x17 } }, + { .data = { 0x21, 0x37 } }, + { .data = { 0x22, 0x37 } }, + { .data = { 0x23, 0x46 } }, + { .data = { 0x24, 0x46 } }, + { .data = { 0x25, 0x44 } }, + { .data = { 0x26, 0x44 } }, + { .data = { 0x27, 0x4A } }, + { .data = { 0x28, 0x4A } }, + { .data = { 0x29, 0x48 } }, + { .data = { 0x2A, 0x48 } }, + { .data = { 0x2B, 0x1F } }, + { .data = { 0x2C, 0x01 } }, + { .data = { 0x2D, 0x01 } }, + { .data = { 0x2E, 0x00 } }, + { .data = { 0x2F, 0x00 } }, + { .data = { 0x30, 0x1F } }, + { .data = { 0x31, 0x1F } }, + { .data = { 0x32, 0x1E } }, + { .data = { 0x33, 0x1E } }, + { .data = { 0x34, 0x1F } }, + { .data = { 0x35, 0x17 } }, + { .data = { 0x36, 0x17 } }, + { .data = { 0x37, 0x37 } }, + { .data = { 0x38, 0x37 } }, + { .data = { 0x39, 0x08 } }, + { .data = { 0x3A, 0x08 } }, + { .data = { 0x3B, 0x0A } }, + { .data = { 0x3C, 0x0A } }, + { .data = { 0x3D, 0x04 } }, + { .data = { 0x3E, 0x04 } }, + { .data = { 0x3F, 0x06 } }, + { .data = { 0x40, 0x06 } }, + { .data = { 0x41, 0x1F } }, + { .data = { 0x42, 0x02 } }, + { .data = { 0x43, 0x02 } }, + { .data = { 0x44, 0x00 } }, + { .data = { 0x45, 0x00 } }, + { .data = { 0x46, 0x1F } }, + { .data = { 0x47, 0x1F } }, + { .data = { 0x48, 0x1E } }, + { .data = { 0x49, 0x1E } }, + { .data = { 0x4A, 0x1F } }, + { .data = { 0x4B, 0x17 } }, + { .data = { 0x4C, 0x17 } }, + { .data = { 0x4D, 0x37 } }, + { .data = { 0x4E, 0x37 } }, + { .data = { 0x4F, 0x09 } }, + { .data = { 0x50, 0x09 } }, + { .data = { 0x51, 0x0B } }, + { .data = { 0x52, 0x0B } }, + { .data = { 0x53, 0x05 } }, + { .data = { 0x54, 0x05 } }, + { .data = { 0x55, 0x07 } }, + { .data = { 0x56, 0x07 } }, + { .data = { 0x57, 0x1F } }, + { .data = { 0x58, 0x40 } }, + { .data = { 0x5B, 0x30 } }, + { .data = { 0x5C, 0x16 } }, + { .data = { 0x5D, 0x34 } }, + { .data = { 0x5E, 0x05 } }, + { .data = { 0x5F, 0x02 } }, + { .data = { 0x63, 0x00 } }, + { .data = { 0x64, 0x6A } }, + { .data = { 0x67, 0x73 } }, + { .data = { 0x68, 0x1D } }, + { .data = { 0x69, 0x08 } }, + { .data = { 0x6A, 0x6A } }, + { .data = { 0x6B, 0x08 } }, + { .data = { 0x6C, 0x00 } }, + { .data = { 0x6D, 0x00 } }, + { .data = { 0x6E, 0x00 } }, + { .data = { 0x6F, 0x88 } }, + { .data = { 0x75, 0xFF } }, + { .data = { 0x77, 0xDD } }, + { .data = { 0x78, 0x3F } }, + { .data = { 0x79, 0x15 } }, + { .data = { 0x7A, 0x17 } }, + { .data = { 0x7D, 0x14 } }, + { .data = { 0x7E, 0x82 } }, + { .data = { 0xE0, 0x04 } }, + { .data = { 0x00, 0x0E } }, + { .data = { 0x02, 0xB3 } }, + { .data = { 0x09, 0x61 } }, + { .data = { 0x0E, 0x48 } }, + { .data = { 0xE0, 0x00 } }, + { .data = { 0xE6, 0x02 } }, + { .data = { 0xE7, 0x0C } }, +}; + +static const struct jadard_panel_desc cz101b4001_desc = { + .mode = { + .clock = 70000, + + .hdisplay = 800, + .hsync_start = 800 + 40, + .hsync_end = 800 + 40 + 18, + .htotal = 800 + 40 + 18 + 20, + + .vdisplay = 1280, + .vsync_start = 1280 + 20, + .vsync_end = 1280 + 20 + 4, + .vtotal = 1280 + 20 + 4 + 20, + + .width_mm = 62, + .height_mm = 110, + .type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED, + }, + .lanes = 4, + .format = MIPI_DSI_FMT_RGB888, + .init_cmds = cz101b4001_init_cmds, + .num_init_cmds = ARRAY_SIZE(cz101b4001_init_cmds), +}; + +static int jadard_dsi_probe(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + const struct jadard_panel_desc *desc; + struct jadard *jadard; + int ret; + + jadard = devm_kzalloc(&dsi->dev, sizeof(*jadard), GFP_KERNEL); + if (!jadard) + return -ENOMEM; + + desc = of_device_get_match_data(dev); + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | + MIPI_DSI_MODE_NO_EOT_PACKET; + dsi->format = desc->format; + dsi->lanes = desc->lanes; + + jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(jadard->reset)) { + DRM_DEV_ERROR(&dsi->dev, "failed to get our reset GPIO\n"); + return PTR_ERR(jadard->reset); + } + + jadard->vdd = devm_regulator_get(dev, "vdd"); + if (IS_ERR(jadard->vdd)) { + DRM_DEV_ERROR(&dsi->dev, "failed to get vdd regulator\n"); + return PTR_ERR(jadard->vdd); + } + + jadard->vccio = devm_regulator_get(dev, "vccio"); + if (IS_ERR(jadard->vccio)) { + DRM_DEV_ERROR(&dsi->dev, "failed to get vccio regulator\n"); + return PTR_ERR(jadard->vccio); + } + + drm_panel_init(&jadard->panel, dev, &jadard_funcs, + DRM_MODE_CONNECTOR_DSI); + + ret = drm_panel_of_backlight(&jadard->panel); + if (ret) + return ret; + + drm_panel_add(&jadard->panel); + + mipi_dsi_set_drvdata(dsi, jadard); + jadard->dsi = dsi; + jadard->desc = desc; + + ret = mipi_dsi_attach(dsi); + if (ret < 0) + drm_panel_remove(&jadard->panel); + + return ret; +} + +static void jadard_dsi_remove(struct mipi_dsi_device *dsi) +{ + struct jadard *jadard = mipi_dsi_get_drvdata(dsi); + + mipi_dsi_detach(dsi); + drm_panel_remove(&jadard->panel); +} + +static const struct of_device_id jadard_of_match[] = { + { .compatible = "chongzhou,cz101b4001", .data = &cz101b4001_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, jadard_of_match); + +static struct mipi_dsi_driver jadard_driver = { + .probe = jadard_dsi_probe, + .remove = jadard_dsi_remove, + .driver = { + .name = "jadard-jd9365da", + .of_match_table = jadard_of_match, + }, +}; +module_mipi_dsi_driver(jadard_driver); + +MODULE_AUTHOR("Jagan Teki <jagan@edgeble.ai>"); +MODULE_AUTHOR("Stephen Chen <stephen@radxa.com>"); +MODULE_DESCRIPTION("Jadard JD9365DA-H3 WXGA DSI panel"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-newvision-nv3051d.c b/drivers/gpu/drm/panel/panel-newvision-nv3051d.c new file mode 100644 index 000000000000..a07958038ffd --- /dev/null +++ b/drivers/gpu/drm/panel/panel-newvision-nv3051d.c @@ -0,0 +1,504 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NV3051D MIPI-DSI panel driver for Anbernic RG353x + * Copyright (C) 2022 Chris Morgan + * + * based on + * + * Elida kd35t133 3.5" MIPI-DSI panel driver + * Copyright (C) Theobroma Systems 2020 + */ + +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/media-bus-format.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regulator/consumer.h> + +#include <video/display_timing.h> +#include <video/mipi_display.h> + +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> + +struct nv3051d_panel_info { + const struct drm_display_mode *display_modes; + unsigned int num_modes; + u16 width_mm, height_mm; + u32 bus_flags; +}; + +struct panel_nv3051d { + struct device *dev; + struct drm_panel panel; + struct gpio_desc *reset_gpio; + const struct nv3051d_panel_info *panel_info; + struct regulator *vdd; +}; + +static inline struct panel_nv3051d *panel_to_panelnv3051d(struct drm_panel *panel) +{ + return container_of(panel, struct panel_nv3051d, panel); +} + +static int panel_nv3051d_init_sequence(struct panel_nv3051d *ctx) +{ + struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev); + + /* + * Init sequence was supplied by device vendor with no + * documentation. + */ + + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x30); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x52); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0xE3, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0x03, 0x40); + mipi_dsi_dcs_write_seq(dsi, 0x04, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0x05, 0x03); + mipi_dsi_dcs_write_seq(dsi, 0x24, 0x12); + mipi_dsi_dcs_write_seq(dsi, 0x25, 0x1E); + mipi_dsi_dcs_write_seq(dsi, 0x26, 0x28); + mipi_dsi_dcs_write_seq(dsi, 0x27, 0x52); + mipi_dsi_dcs_write_seq(dsi, 0x28, 0x57); + mipi_dsi_dcs_write_seq(dsi, 0x29, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0x2A, 0xDF); + mipi_dsi_dcs_write_seq(dsi, 0x38, 0x9C); + mipi_dsi_dcs_write_seq(dsi, 0x39, 0xA7); + mipi_dsi_dcs_write_seq(dsi, 0x3A, 0x53); + mipi_dsi_dcs_write_seq(dsi, 0x44, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0x49, 0x3C); + mipi_dsi_dcs_write_seq(dsi, 0x59, 0xFE); + mipi_dsi_dcs_write_seq(dsi, 0x5C, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0x91, 0x77); + mipi_dsi_dcs_write_seq(dsi, 0x92, 0x77); + mipi_dsi_dcs_write_seq(dsi, 0xA0, 0x55); + mipi_dsi_dcs_write_seq(dsi, 0xA1, 0x50); + mipi_dsi_dcs_write_seq(dsi, 0xA4, 0x9C); + mipi_dsi_dcs_write_seq(dsi, 0xA7, 0x02); + mipi_dsi_dcs_write_seq(dsi, 0xA8, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0xA9, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0xAA, 0xFC); + mipi_dsi_dcs_write_seq(dsi, 0xAB, 0x28); + mipi_dsi_dcs_write_seq(dsi, 0xAC, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0xAD, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0xAE, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0xAF, 0x03); + mipi_dsi_dcs_write_seq(dsi, 0xB0, 0x08); + mipi_dsi_dcs_write_seq(dsi, 0xB1, 0x26); + mipi_dsi_dcs_write_seq(dsi, 0xB2, 0x28); + mipi_dsi_dcs_write_seq(dsi, 0xB3, 0x28); + mipi_dsi_dcs_write_seq(dsi, 0xB4, 0x33); + mipi_dsi_dcs_write_seq(dsi, 0xB5, 0x08); + mipi_dsi_dcs_write_seq(dsi, 0xB6, 0x26); + mipi_dsi_dcs_write_seq(dsi, 0xB7, 0x08); + mipi_dsi_dcs_write_seq(dsi, 0xB8, 0x26); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x30); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x52); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x02); + mipi_dsi_dcs_write_seq(dsi, 0xB1, 0x0E); + mipi_dsi_dcs_write_seq(dsi, 0xD1, 0x0E); + mipi_dsi_dcs_write_seq(dsi, 0xB4, 0x29); + mipi_dsi_dcs_write_seq(dsi, 0xD4, 0x2B); + mipi_dsi_dcs_write_seq(dsi, 0xB2, 0x0C); + mipi_dsi_dcs_write_seq(dsi, 0xD2, 0x0A); + mipi_dsi_dcs_write_seq(dsi, 0xB3, 0x28); + mipi_dsi_dcs_write_seq(dsi, 0xD3, 0x28); + mipi_dsi_dcs_write_seq(dsi, 0xB6, 0x11); + mipi_dsi_dcs_write_seq(dsi, 0xD6, 0x0D); + mipi_dsi_dcs_write_seq(dsi, 0xB7, 0x32); + mipi_dsi_dcs_write_seq(dsi, 0xD7, 0x30); + mipi_dsi_dcs_write_seq(dsi, 0xC1, 0x04); + mipi_dsi_dcs_write_seq(dsi, 0xE1, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0xB8, 0x0A); + mipi_dsi_dcs_write_seq(dsi, 0xD8, 0x0A); + mipi_dsi_dcs_write_seq(dsi, 0xB9, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0xD9, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0xBD, 0x13); + mipi_dsi_dcs_write_seq(dsi, 0xDD, 0x13); + mipi_dsi_dcs_write_seq(dsi, 0xBC, 0x11); + mipi_dsi_dcs_write_seq(dsi, 0xDC, 0x11); + mipi_dsi_dcs_write_seq(dsi, 0xBB, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xDB, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xBA, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xDA, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xBE, 0x18); + mipi_dsi_dcs_write_seq(dsi, 0xDE, 0x18); + mipi_dsi_dcs_write_seq(dsi, 0xBF, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xDF, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xC0, 0x17); + mipi_dsi_dcs_write_seq(dsi, 0xE0, 0x17); + mipi_dsi_dcs_write_seq(dsi, 0xB5, 0x3B); + mipi_dsi_dcs_write_seq(dsi, 0xD5, 0x3C); + mipi_dsi_dcs_write_seq(dsi, 0xB0, 0x0B); + mipi_dsi_dcs_write_seq(dsi, 0xD0, 0x0C); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x30); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x52); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x03); + mipi_dsi_dcs_write_seq(dsi, 0x00, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x01, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x02, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x03, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x04, 0x61); + mipi_dsi_dcs_write_seq(dsi, 0x05, 0x80); + mipi_dsi_dcs_write_seq(dsi, 0x06, 0xC7); + mipi_dsi_dcs_write_seq(dsi, 0x07, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0x08, 0x82); + mipi_dsi_dcs_write_seq(dsi, 0x09, 0x83); + mipi_dsi_dcs_write_seq(dsi, 0x30, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x31, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x32, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x33, 0x2A); + mipi_dsi_dcs_write_seq(dsi, 0x34, 0x61); + mipi_dsi_dcs_write_seq(dsi, 0x35, 0xC5); + mipi_dsi_dcs_write_seq(dsi, 0x36, 0x80); + mipi_dsi_dcs_write_seq(dsi, 0x37, 0x23); + mipi_dsi_dcs_write_seq(dsi, 0x40, 0x82); + mipi_dsi_dcs_write_seq(dsi, 0x41, 0x83); + mipi_dsi_dcs_write_seq(dsi, 0x42, 0x80); + mipi_dsi_dcs_write_seq(dsi, 0x43, 0x81); + mipi_dsi_dcs_write_seq(dsi, 0x44, 0x11); + mipi_dsi_dcs_write_seq(dsi, 0x45, 0xF2); + mipi_dsi_dcs_write_seq(dsi, 0x46, 0xF1); + mipi_dsi_dcs_write_seq(dsi, 0x47, 0x11); + mipi_dsi_dcs_write_seq(dsi, 0x48, 0xF4); + mipi_dsi_dcs_write_seq(dsi, 0x49, 0xF3); + mipi_dsi_dcs_write_seq(dsi, 0x50, 0x02); + mipi_dsi_dcs_write_seq(dsi, 0x51, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0x52, 0x04); + mipi_dsi_dcs_write_seq(dsi, 0x53, 0x03); + mipi_dsi_dcs_write_seq(dsi, 0x54, 0x11); + mipi_dsi_dcs_write_seq(dsi, 0x55, 0xF6); + mipi_dsi_dcs_write_seq(dsi, 0x56, 0xF5); + mipi_dsi_dcs_write_seq(dsi, 0x57, 0x11); + mipi_dsi_dcs_write_seq(dsi, 0x58, 0xF8); + mipi_dsi_dcs_write_seq(dsi, 0x59, 0xF7); + mipi_dsi_dcs_write_seq(dsi, 0x7E, 0x02); + mipi_dsi_dcs_write_seq(dsi, 0x7F, 0x80); + mipi_dsi_dcs_write_seq(dsi, 0xE0, 0x5A); + mipi_dsi_dcs_write_seq(dsi, 0xB1, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0xB4, 0x0E); + mipi_dsi_dcs_write_seq(dsi, 0xB5, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xB6, 0x04); + mipi_dsi_dcs_write_seq(dsi, 0xB7, 0x07); + mipi_dsi_dcs_write_seq(dsi, 0xB8, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0xB9, 0x05); + mipi_dsi_dcs_write_seq(dsi, 0xBA, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xC7, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0xCA, 0x0E); + mipi_dsi_dcs_write_seq(dsi, 0xCB, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0xCC, 0x04); + mipi_dsi_dcs_write_seq(dsi, 0xCD, 0x07); + mipi_dsi_dcs_write_seq(dsi, 0xCE, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0xCF, 0x05); + mipi_dsi_dcs_write_seq(dsi, 0xD0, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0x81, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0x84, 0x0E); + mipi_dsi_dcs_write_seq(dsi, 0x85, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0x86, 0x07); + mipi_dsi_dcs_write_seq(dsi, 0x87, 0x04); + mipi_dsi_dcs_write_seq(dsi, 0x88, 0x05); + mipi_dsi_dcs_write_seq(dsi, 0x89, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0x8A, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0x97, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0x9A, 0x0E); + mipi_dsi_dcs_write_seq(dsi, 0x9B, 0x0F); + mipi_dsi_dcs_write_seq(dsi, 0x9C, 0x07); + mipi_dsi_dcs_write_seq(dsi, 0x9D, 0x04); + mipi_dsi_dcs_write_seq(dsi, 0x9E, 0x05); + mipi_dsi_dcs_write_seq(dsi, 0x9F, 0x06); + mipi_dsi_dcs_write_seq(dsi, 0xA0, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x30); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x52); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x02); + mipi_dsi_dcs_write_seq(dsi, 0x01, 0x01); + mipi_dsi_dcs_write_seq(dsi, 0x02, 0xDA); + mipi_dsi_dcs_write_seq(dsi, 0x03, 0xBA); + mipi_dsi_dcs_write_seq(dsi, 0x04, 0xA8); + mipi_dsi_dcs_write_seq(dsi, 0x05, 0x9A); + mipi_dsi_dcs_write_seq(dsi, 0x06, 0x70); + mipi_dsi_dcs_write_seq(dsi, 0x07, 0xFF); + mipi_dsi_dcs_write_seq(dsi, 0x08, 0x91); + mipi_dsi_dcs_write_seq(dsi, 0x09, 0x90); + mipi_dsi_dcs_write_seq(dsi, 0x0A, 0xFF); + mipi_dsi_dcs_write_seq(dsi, 0x0B, 0x8F); + mipi_dsi_dcs_write_seq(dsi, 0x0C, 0x60); + mipi_dsi_dcs_write_seq(dsi, 0x0D, 0x58); + mipi_dsi_dcs_write_seq(dsi, 0x0E, 0x48); + mipi_dsi_dcs_write_seq(dsi, 0x0F, 0x38); + mipi_dsi_dcs_write_seq(dsi, 0x10, 0x2B); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x30); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x52); + mipi_dsi_dcs_write_seq(dsi, 0xFF, 0x00); + mipi_dsi_dcs_write_seq(dsi, 0x36, 0x02); + mipi_dsi_dcs_write_seq(dsi, 0x3A, 0x70); + + dev_dbg(ctx->dev, "Panel init sequence done\n"); + + return 0; +} + +static int panel_nv3051d_unprepare(struct drm_panel *panel) +{ + struct panel_nv3051d *ctx = panel_to_panelnv3051d(panel); + struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev); + int ret; + + ret = mipi_dsi_dcs_set_display_off(dsi); + if (ret < 0) + dev_err(ctx->dev, "failed to set display off: %d\n", ret); + + msleep(20); + + ret = mipi_dsi_dcs_enter_sleep_mode(dsi); + if (ret < 0) { + dev_err(ctx->dev, "failed to enter sleep mode: %d\n", ret); + return ret; + } + + usleep_range(10000, 15000); + + regulator_disable(ctx->vdd); + + return 0; +} + +static int panel_nv3051d_prepare(struct drm_panel *panel) +{ + struct panel_nv3051d *ctx = panel_to_panelnv3051d(panel); + struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev); + int ret; + + dev_dbg(ctx->dev, "Resetting the panel\n"); + ret = regulator_enable(ctx->vdd); + if (ret < 0) { + dev_err(ctx->dev, "Failed to enable vdd supply: %d\n", ret); + return ret; + } + + usleep_range(2000, 3000); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + msleep(150); + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + msleep(20); + + ret = panel_nv3051d_init_sequence(ctx); + if (ret < 0) { + dev_err(ctx->dev, "Panel init sequence failed: %d\n", ret); + goto disable_vdd; + } + + ret = mipi_dsi_dcs_exit_sleep_mode(dsi); + if (ret < 0) { + dev_err(ctx->dev, "Failed to exit sleep mode: %d\n", ret); + goto disable_vdd; + } + + msleep(200); + + ret = mipi_dsi_dcs_set_display_on(dsi); + if (ret < 0) { + dev_err(ctx->dev, "Failed to set display on: %d\n", ret); + goto disable_vdd; + } + + usleep_range(10000, 15000); + + return 0; + +disable_vdd: + regulator_disable(ctx->vdd); + return ret; +} + +static int panel_nv3051d_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + struct panel_nv3051d *ctx = panel_to_panelnv3051d(panel); + const struct nv3051d_panel_info *panel_info = ctx->panel_info; + struct drm_display_mode *mode; + unsigned int i; + + for (i = 0; i < panel_info->num_modes; i++) { + mode = drm_mode_duplicate(connector->dev, + &panel_info->display_modes[i]); + if (!mode) + return -ENOMEM; + + drm_mode_set_name(mode); + + mode->type = DRM_MODE_TYPE_DRIVER; + if (panel_info->num_modes == 1) + mode->type |= DRM_MODE_TYPE_PREFERRED; + + drm_mode_probed_add(connector, mode); + } + + connector->display_info.bpc = 8; + connector->display_info.width_mm = panel_info->width_mm; + connector->display_info.height_mm = panel_info->height_mm; + connector->display_info.bus_flags = panel_info->bus_flags; + + return panel_info->num_modes; +} + +static const struct drm_panel_funcs panel_nv3051d_funcs = { + .unprepare = panel_nv3051d_unprepare, + .prepare = panel_nv3051d_prepare, + .get_modes = panel_nv3051d_get_modes, +}; + +static int panel_nv3051d_probe(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + struct panel_nv3051d *ctx; + int ret; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->dev = dev; + + ctx->panel_info = of_device_get_match_data(dev); + if (!ctx->panel_info) + return -EINVAL; + + ctx->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(ctx->reset_gpio)) { + dev_err(dev, "cannot get reset gpio\n"); + return PTR_ERR(ctx->reset_gpio); + } + + ctx->vdd = devm_regulator_get(dev, "vdd"); + if (IS_ERR(ctx->vdd)) { + ret = PTR_ERR(ctx->vdd); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to request vdd regulator: %d\n", ret); + return ret; + } + + mipi_dsi_set_drvdata(dsi, ctx); + + dsi->lanes = 4; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | + MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET; + + drm_panel_init(&ctx->panel, &dsi->dev, &panel_nv3051d_funcs, + DRM_MODE_CONNECTOR_DSI); + + ret = drm_panel_of_backlight(&ctx->panel); + if (ret) + return ret; + + drm_panel_add(&ctx->panel); + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + dev_err(dev, "mipi_dsi_attach failed: %d\n", ret); + drm_panel_remove(&ctx->panel); + return ret; + } + + return 0; +} + +static void panel_nv3051d_shutdown(struct mipi_dsi_device *dsi) +{ + struct panel_nv3051d *ctx = mipi_dsi_get_drvdata(dsi); + int ret; + + ret = drm_panel_unprepare(&ctx->panel); + if (ret < 0) + dev_err(&dsi->dev, "Failed to unprepare panel: %d\n", ret); + + ret = drm_panel_disable(&ctx->panel); + if (ret < 0) + dev_err(&dsi->dev, "Failed to disable panel: %d\n", ret); +} + +static void panel_nv3051d_remove(struct mipi_dsi_device *dsi) +{ + struct panel_nv3051d *ctx = mipi_dsi_get_drvdata(dsi); + int ret; + + panel_nv3051d_shutdown(dsi); + + ret = mipi_dsi_detach(dsi); + if (ret < 0) + dev_err(&dsi->dev, "Failed to detach from DSI host: %d\n", ret); + + drm_panel_remove(&ctx->panel); +} + +static const struct drm_display_mode nv3051d_rgxx3_modes[] = { + { /* 120hz */ + .hdisplay = 640, + .hsync_start = 640 + 40, + .hsync_end = 640 + 40 + 2, + .htotal = 640 + 40 + 2 + 80, + .vdisplay = 480, + .vsync_start = 480 + 18, + .vsync_end = 480 + 18 + 2, + .vtotal = 480 + 18 + 2 + 28, + .clock = 48300, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + }, + { /* 100hz */ + .hdisplay = 640, + .hsync_start = 640 + 40, + .hsync_end = 640 + 40 + 2, + .htotal = 640 + 40 + 2 + 80, + .vdisplay = 480, + .vsync_start = 480 + 18, + .vsync_end = 480 + 18 + 2, + .vtotal = 480 + 18 + 2 + 28, + .clock = 40250, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + }, + { /* 60hz */ + .hdisplay = 640, + .hsync_start = 640 + 40, + .hsync_end = 640 + 40 + 2, + .htotal = 640 + 40 + 2 + 80, + .vdisplay = 480, + .vsync_start = 480 + 18, + .vsync_end = 480 + 18 + 2, + .vtotal = 480 + 18 + 2 + 28, + .clock = 24150, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + }, +}; + +static const struct nv3051d_panel_info nv3051d_rgxx3_info = { + .display_modes = nv3051d_rgxx3_modes, + .num_modes = ARRAY_SIZE(nv3051d_rgxx3_modes), + .width_mm = 70, + .height_mm = 57, + .bus_flags = DRM_BUS_FLAG_DE_LOW | DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE, +}; + +static const struct of_device_id newvision_nv3051d_of_match[] = { + { .compatible = "newvision,nv3051d", .data = &nv3051d_rgxx3_info }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, newvision_nv3051d_of_match); + +static struct mipi_dsi_driver newvision_nv3051d_driver = { + .driver = { + .name = "panel-newvision-nv3051d", + .of_match_table = newvision_nv3051d_of_match, + }, + .probe = panel_nv3051d_probe, + .remove = panel_nv3051d_remove, + .shutdown = panel_nv3051d_shutdown, +}; +module_mipi_dsi_driver(newvision_nv3051d_driver); + +MODULE_AUTHOR("Chris Morgan <macromorgan@hotmail.com>"); +MODULE_DESCRIPTION("DRM driver for Newvision NV3051D based MIPI DSI panels"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 2944228a8e2c..8a3b685c2fcc 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2500,6 +2500,7 @@ static const struct display_timing logictechno_lt161010_2nh_timing = { static const struct panel_desc logictechno_lt161010_2nh = { .timings = &logictechno_lt161010_2nh_timing, .num_timings = 1, + .bpc = 6, .size = { .width = 154, .height = 86, @@ -2529,6 +2530,7 @@ static const struct display_timing logictechno_lt170410_2whc_timing = { static const struct panel_desc logictechno_lt170410_2whc = { .timings = &logictechno_lt170410_2whc_timing, .num_timings = 1, + .bpc = 8, .size = { .width = 217, .height = 136, diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index e246d914e7f6..4e83a1891f3e 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -250,13 +250,22 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev) static size_t get_pgsize(u64 addr, size_t size, size_t *count) { + /* + * io-pgtable only operates on multiple pages within a single table + * entry, so we need to split at boundaries of the table size, i.e. + * the next block size up. The distance from address A to the next + * boundary of block size B is logically B - A % B, but in unsigned + * two's complement where B is a power of two we get the equivalence + * B - A % B == (B - A) % B == (n * B - A) % B, and choose n = 0 :) + */ size_t blk_offset = -addr % SZ_2M; if (blk_offset || size < SZ_2M) { *count = min_not_zero(blk_offset, size) / SZ_4K; return SZ_4K; } - *count = size / SZ_2M; + blk_offset = -addr % SZ_1G ?: SZ_1G; + *count = min(blk_offset, size) / SZ_2M; return SZ_2M; } diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index eb25eedb5ee0..00deba0b7271 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -48,7 +48,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index 3044ca948ce2..a3b83f89e061 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -37,6 +37,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include <drm/drm_gem_ttm_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 432758ad39a3..76f060810f63 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -38,7 +38,6 @@ #include <drm/drm_crtc.h> #include <drm/drm_encoder.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_gem_ttm_helper.h> #include <drm/drm_ioctl.h> #include <drm/drm_gem.h> diff --git a/drivers/gpu/drm/radeon/Kconfig b/drivers/gpu/drm/radeon/Kconfig index 52819e7f1fca..97a277f9a25e 100644 --- a/drivers/gpu/drm/radeon/Kconfig +++ b/drivers/gpu/drm/radeon/Kconfig @@ -1,4 +1,34 @@ # SPDX-License-Identifier: MIT + +config DRM_RADEON + tristate "ATI Radeon" + depends on DRM && PCI && MMU + depends on AGP || !AGP + select FW_LOADER + select DRM_DISPLAY_DP_HELPER + select DRM_DISPLAY_HELPER + select DRM_KMS_HELPER + select DRM_TTM + select DRM_TTM_HELPER + select SND_HDA_COMPONENT if SND_HDA_CORE + select POWER_SUPPLY + select HWMON + select BACKLIGHT_CLASS_DEVICE + select INTERVAL_TREE + # radeon depends on ACPI_VIDEO when ACPI is enabled, for select to work + # ACPI_VIDEO's dependencies must also be selected. + select INPUT if ACPI + select ACPI_VIDEO if ACPI + # On x86 ACPI_VIDEO also needs ACPI_WMI + select X86_PLATFORM_DEVICES if ACPI && X86 + select ACPI_WMI if ACPI && X86 + help + Choose this option if you have an ATI Radeon graphics card. There + are both PCI and AGP versions. You don't need to choose this to + run the Radeon in plain VGA mode. + + If M is selected, the module will be called radeon. + config DRM_RADEON_USERPTR bool "Always enable userptr support" depends on DRM_RADEON diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 166c18d62f6d..2e7161acd443 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -79,6 +79,7 @@ #include <drm/ttm/ttm_execbuf_util.h> #include <drm/drm_gem.h> +#include <drm/drm_audio_component.h> #include "radeon_family.h" #include "radeon_mode.h" @@ -1796,6 +1797,9 @@ struct r600_audio { struct radeon_audio_funcs *hdmi_funcs; struct radeon_audio_funcs *dp_funcs; struct radeon_audio_basic_funcs *funcs; + struct drm_audio_component *component; + bool component_registered; + struct mutex component_mutex; }; /* @@ -2994,6 +2998,10 @@ void radeon_irq_kms_set_irq_n_enabled(struct radeon_device *rdev, bool enable, const char *name, unsigned n); +/* Audio component binding */ +void radeon_audio_component_init(struct radeon_device *rdev); +void radeon_audio_component_fini(struct radeon_device *rdev); + #include "radeon_object.h" #endif diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index 7c5e80d03fc9..d6ccaf24ee0c 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -23,6 +23,7 @@ */ #include <linux/gcd.h> +#include <linux/component.h> #include <drm/drm_crtc.h> #include "dce6_afmt.h" @@ -180,6 +181,8 @@ static struct radeon_audio_funcs dce6_dp_funcs = { .dpms = evergreen_dp_enable, }; +static void radeon_audio_component_notify(struct radeon_device *rdev, int port); + static void radeon_audio_enable(struct radeon_device *rdev, struct r600_audio_pin *pin, u8 enable_mask) { @@ -207,6 +210,8 @@ static void radeon_audio_enable(struct radeon_device *rdev, if (rdev->audio.funcs->enable) rdev->audio.funcs->enable(rdev, pin, enable_mask); + + radeon_audio_component_notify(rdev, pin->id); } static void radeon_audio_interface_init(struct radeon_device *rdev) @@ -721,3 +726,115 @@ unsigned int radeon_audio_decode_dfs_div(unsigned int div) else return 0; } + +/* + * Audio component support + */ +static void radeon_audio_component_notify(struct radeon_device *rdev, int port) +{ + struct drm_audio_component *acomp; + + mutex_lock(&rdev->audio.component_mutex); + acomp = rdev->audio.component; + if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) + acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, + port, -1); + mutex_unlock(&rdev->audio.component_mutex); +} + +static int radeon_audio_component_get_eld(struct device *kdev, int port, + int pipe, bool *enabled, + unsigned char *buf, int max_bytes) +{ + struct drm_device *dev = dev_get_drvdata(kdev); + struct radeon_device *rdev = dev->dev_private; + struct drm_encoder *encoder; + struct radeon_encoder *radeon_encoder; + struct radeon_encoder_atom_dig *dig; + struct drm_connector *connector; + int ret = 0; + + *enabled = false; + if (!rdev->audio.enabled || !rdev->mode_info.mode_config_initialized) + return 0; + + list_for_each_entry(encoder, &rdev->ddev->mode_config.encoder_list, head) { + if (!radeon_encoder_is_digital(encoder)) + continue; + radeon_encoder = to_radeon_encoder(encoder); + dig = radeon_encoder->enc_priv; + if (!dig->pin || dig->pin->id != port) + continue; + connector = radeon_get_connector_for_encoder(encoder); + if (!connector) + continue; + *enabled = true; + ret = drm_eld_size(connector->eld); + memcpy(buf, connector->eld, min(max_bytes, ret)); + break; + } + + return ret; +} + +static const struct drm_audio_component_ops radeon_audio_component_ops = { + .get_eld = radeon_audio_component_get_eld, +}; + +static int radeon_audio_component_bind(struct device *kdev, + struct device *hda_kdev, void *data) +{ + struct drm_device *dev = dev_get_drvdata(kdev); + struct radeon_device *rdev = dev->dev_private; + struct drm_audio_component *acomp = data; + + if (WARN_ON(!device_link_add(hda_kdev, kdev, DL_FLAG_STATELESS))) + return -ENOMEM; + + mutex_lock(&rdev->audio.component_mutex); + acomp->ops = &radeon_audio_component_ops; + acomp->dev = kdev; + rdev->audio.component = acomp; + mutex_unlock(&rdev->audio.component_mutex); + + return 0; +} + +static void radeon_audio_component_unbind(struct device *kdev, + struct device *hda_kdev, void *data) +{ + struct drm_device *dev = dev_get_drvdata(kdev); + struct radeon_device *rdev = dev->dev_private; + struct drm_audio_component *acomp = data; + + device_link_remove(hda_kdev, kdev); + + mutex_lock(&rdev->audio.component_mutex); + rdev->audio.component = NULL; + acomp->ops = NULL; + acomp->dev = NULL; + mutex_unlock(&rdev->audio.component_mutex); +} + +static const struct component_ops radeon_audio_component_bind_ops = { + .bind = radeon_audio_component_bind, + .unbind = radeon_audio_component_unbind, +}; + +void radeon_audio_component_init(struct radeon_device *rdev) +{ + if (rdev->audio.component_registered || + !radeon_audio || !radeon_audio_chipset_supported(rdev)) + return; + + if (!component_add(rdev->dev, &radeon_audio_component_bind_ops)) + rdev->audio.component_registered = true; +} + +void radeon_audio_component_fini(struct radeon_device *rdev) +{ + if (rdev->audio.component_registered) { + component_del(rdev->dev, &radeon_audio_component_bind_ops); + rdev->audio.component_registered = false; + } +} diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 33121655d50b..63bdc9f6fc24 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -227,6 +227,7 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev) if (!found) return false; + pci_dev_put(pdev); rdev->bios = kmalloc(size, GFP_KERNEL); if (!rdev->bios) { @@ -612,13 +613,14 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev) acpi_size tbl_size; UEFI_ACPI_VFCT *vfct; unsigned offset; + bool r = false; if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr))) return false; tbl_size = hdr->length; if (tbl_size < sizeof(UEFI_ACPI_VFCT)) { DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n"); - return false; + goto out; } vfct = (UEFI_ACPI_VFCT *)hdr; @@ -631,13 +633,13 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev) offset += sizeof(VFCT_IMAGE_HEADER); if (offset > tbl_size) { DRM_ERROR("ACPI VFCT image header truncated\n"); - return false; + goto out; } offset += vhdr->ImageLength; if (offset > tbl_size) { DRM_ERROR("ACPI VFCT image truncated\n"); - return false; + goto out; } if (vhdr->ImageLength && @@ -649,15 +651,18 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev) rdev->bios = kmemdup(&vbios->VbiosContent, vhdr->ImageLength, GFP_KERNEL); + if (rdev->bios) + r = true; - if (!rdev->bios) - return false; - return true; + goto out; } } DRM_ERROR("ACPI VFCT table present but broken (too short #2)\n"); - return false; + +out: + acpi_put_table(hdr); + return r; } #else static inline bool radeon_acpi_vfct_bios(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 262e2bcb30c3..6344454a7721 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1312,6 +1312,7 @@ int radeon_device_init(struct radeon_device *rdev, mutex_init(&rdev->pm.mutex); mutex_init(&rdev->gpu_clock_mutex); mutex_init(&rdev->srbm_mutex); + mutex_init(&rdev->audio.component_mutex); init_rwsem(&rdev->pm.mclk_lock); init_rwsem(&rdev->exclusive_lock); init_waitqueue_head(&rdev->irq.vblank_queue); @@ -1451,6 +1452,8 @@ int radeon_device_init(struct radeon_device *rdev, goto failed; } + radeon_audio_component_init(rdev); + r = radeon_ib_ring_tests(rdev); if (r) DRM_ERROR("ib ring test failed (%d).\n", r); @@ -1513,6 +1516,7 @@ void radeon_device_fini(struct radeon_device *rdev) rdev->shutdown = true; /* evict vram memory */ radeon_bo_evict_vram(rdev); + radeon_audio_component_fini(rdev); radeon_fini(rdev); if (!pci_is_thunderbolt_attached(rdev->pdev)) vga_switcheroo_unregister_client(rdev->pdev); diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c index cc6754d88b81..c1710ed1cab8 100644 --- a/drivers/gpu/drm/radeon/radeon_fb.c +++ b/drivers/gpu/drm/radeon/radeon_fb.c @@ -80,6 +80,8 @@ static const struct fb_ops radeonfb_ops = { DRM_FB_HELPER_DEFAULT_OPS, .fb_open = radeonfb_open, .fb_release = radeonfb_release, + .fb_read = drm_fb_helper_cfb_read, + .fb_write = drm_fb_helper_cfb_write, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -243,7 +245,7 @@ static int radeonfb_create(struct drm_fb_helper *helper, rbo = gem_to_radeon_bo(gobj); /* okay we have an object now allocate the framebuffer */ - info = drm_fb_helper_alloc_fbi(helper); + info = drm_fb_helper_alloc_info(helper); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; @@ -309,7 +311,7 @@ static int radeon_fbdev_destroy(struct drm_device *dev, struct radeon_fbdev *rfb { struct drm_framebuffer *fb = &rfbdev->fb; - drm_fb_helper_unregister_fbi(&rfbdev->helper); + drm_fb_helper_unregister_info(&rfbdev->helper); if (fb->obj[0]) { radeonfb_destroy_pinned_object(fb->obj[0]); diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig index c959e8c6be7d..b2bddbeca878 100644 --- a/drivers/gpu/drm/rcar-du/Kconfig +++ b/drivers/gpu/drm/rcar-du/Kconfig @@ -41,15 +41,26 @@ config DRM_RCAR_LVDS depends on DRM_RCAR_USE_LVDS select DRM_KMS_HELPER select DRM_PANEL - select OF_FLATTREE - select OF_OVERLAY + +config DRM_RCAR_USE_MIPI_DSI + bool "R-Car DU MIPI DSI Encoder Support" + depends on DRM_BRIDGE && OF + default DRM_RCAR_DU + help + Enable support for the R-Car Display Unit embedded MIPI DSI encoders. config DRM_RCAR_MIPI_DSI - tristate "R-Car DU MIPI DSI Encoder Support" + def_tristate DRM_RCAR_DU + depends on DRM_RCAR_USE_MIPI_DSI + select DRM_MIPI_DSI + +config DRM_RZG2L_MIPI_DSI + tristate "RZ/G2L MIPI DSI Encoder Support" depends on DRM && DRM_BRIDGE && OF + depends on ARCH_RENESAS || COMPILE_TEST select DRM_MIPI_DSI help - Enable support for the R-Car Display Unit embedded MIPI DSI encoders. + Enable support for the RZ/G2L Display Unit embedded MIPI DSI encoders. config DRM_RCAR_VSP bool "R-Car DU VSP Compositor Support" if ARM diff --git a/drivers/gpu/drm/rcar-du/Makefile b/drivers/gpu/drm/rcar-du/Makefile index 6f132325c8b7..b8f2c82651d9 100644 --- a/drivers/gpu/drm/rcar-du/Makefile +++ b/drivers/gpu/drm/rcar-du/Makefile @@ -14,3 +14,5 @@ obj-$(CONFIG_DRM_RCAR_DU) += rcar-du-drm.o obj-$(CONFIG_DRM_RCAR_DW_HDMI) += rcar_dw_hdmi.o obj-$(CONFIG_DRM_RCAR_LVDS) += rcar_lvds.o obj-$(CONFIG_DRM_RCAR_MIPI_DSI) += rcar_mipi_dsi.o + +obj-$(CONFIG_DRM_RZG2L_MIPI_DSI) += rzg2l_mipi_dsi.o diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index a2776f1d6f2c..d003e8d9e7a2 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -20,7 +20,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> #include <drm/drm_probe_helper.h> diff --git a/drivers/gpu/drm/rcar-du/rzg2l_mipi_dsi.c b/drivers/gpu/drm/rcar-du/rzg2l_mipi_dsi.c new file mode 100644 index 000000000000..aa95b85a2964 --- /dev/null +++ b/drivers/gpu/drm/rcar-du/rzg2l_mipi_dsi.c @@ -0,0 +1,816 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RZ/G2L MIPI DSI Encoder Driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_graph.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> +#include <linux/slab.h> + +#include <drm/drm_atomic.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_of.h> +#include <drm/drm_panel.h> +#include <drm/drm_probe_helper.h> + +#include "rzg2l_mipi_dsi_regs.h" + +struct rzg2l_mipi_dsi { + struct device *dev; + void __iomem *mmio; + + struct reset_control *rstc; + struct reset_control *arstc; + struct reset_control *prstc; + + struct mipi_dsi_host host; + struct drm_bridge bridge; + struct drm_bridge *next_bridge; + + struct clk *vclk; + + enum mipi_dsi_pixel_format format; + unsigned int num_data_lanes; + unsigned int lanes; + unsigned long mode_flags; +}; + +static inline struct rzg2l_mipi_dsi * +bridge_to_rzg2l_mipi_dsi(struct drm_bridge *bridge) +{ + return container_of(bridge, struct rzg2l_mipi_dsi, bridge); +} + +static inline struct rzg2l_mipi_dsi * +host_to_rzg2l_mipi_dsi(struct mipi_dsi_host *host) +{ + return container_of(host, struct rzg2l_mipi_dsi, host); +} + +struct rzg2l_mipi_dsi_timings { + unsigned long hsfreq_max; + u32 t_init; + u32 tclk_prepare; + u32 ths_prepare; + u32 tclk_zero; + u32 tclk_pre; + u32 tclk_post; + u32 tclk_trail; + u32 ths_zero; + u32 ths_trail; + u32 ths_exit; + u32 tlpx; +}; + +static const struct rzg2l_mipi_dsi_timings rzg2l_mipi_dsi_global_timings[] = { + { + .hsfreq_max = 80000, + .t_init = 79801, + .tclk_prepare = 8, + .ths_prepare = 13, + .tclk_zero = 33, + .tclk_pre = 24, + .tclk_post = 94, + .tclk_trail = 10, + .ths_zero = 23, + .ths_trail = 17, + .ths_exit = 13, + .tlpx = 6, + }, + { + .hsfreq_max = 125000, + .t_init = 79801, + .tclk_prepare = 8, + .ths_prepare = 12, + .tclk_zero = 33, + .tclk_pre = 15, + .tclk_post = 94, + .tclk_trail = 10, + .ths_zero = 23, + .ths_trail = 17, + .ths_exit = 13, + .tlpx = 6, + }, + { + .hsfreq_max = 250000, + .t_init = 79801, + .tclk_prepare = 8, + .ths_prepare = 12, + .tclk_zero = 33, + .tclk_pre = 13, + .tclk_post = 94, + .tclk_trail = 10, + .ths_zero = 23, + .ths_trail = 16, + .ths_exit = 13, + .tlpx = 6, + }, + { + .hsfreq_max = 360000, + .t_init = 79801, + .tclk_prepare = 8, + .ths_prepare = 10, + .tclk_zero = 33, + .tclk_pre = 4, + .tclk_post = 35, + .tclk_trail = 7, + .ths_zero = 16, + .ths_trail = 9, + .ths_exit = 13, + .tlpx = 6, + }, + { + .hsfreq_max = 720000, + .t_init = 79801, + .tclk_prepare = 8, + .ths_prepare = 9, + .tclk_zero = 33, + .tclk_pre = 4, + .tclk_post = 35, + .tclk_trail = 7, + .ths_zero = 16, + .ths_trail = 9, + .ths_exit = 13, + .tlpx = 6, + }, + { + .hsfreq_max = 1500000, + .t_init = 79801, + .tclk_prepare = 8, + .ths_prepare = 9, + .tclk_zero = 33, + .tclk_pre = 4, + .tclk_post = 35, + .tclk_trail = 7, + .ths_zero = 16, + .ths_trail = 9, + .ths_exit = 13, + .tlpx = 6, + }, +}; + +static void rzg2l_mipi_dsi_phy_write(struct rzg2l_mipi_dsi *dsi, u32 reg, u32 data) +{ + iowrite32(data, dsi->mmio + reg); +} + +static void rzg2l_mipi_dsi_link_write(struct rzg2l_mipi_dsi *dsi, u32 reg, u32 data) +{ + iowrite32(data, dsi->mmio + LINK_REG_OFFSET + reg); +} + +static u32 rzg2l_mipi_dsi_phy_read(struct rzg2l_mipi_dsi *dsi, u32 reg) +{ + return ioread32(dsi->mmio + reg); +} + +static u32 rzg2l_mipi_dsi_link_read(struct rzg2l_mipi_dsi *dsi, u32 reg) +{ + return ioread32(dsi->mmio + LINK_REG_OFFSET + reg); +} + +/* ----------------------------------------------------------------------------- + * Hardware Setup + */ + +static int rzg2l_mipi_dsi_dphy_init(struct rzg2l_mipi_dsi *dsi, + unsigned long hsfreq) +{ + const struct rzg2l_mipi_dsi_timings *dphy_timings; + unsigned int i; + u32 dphyctrl0; + u32 dphytim0; + u32 dphytim1; + u32 dphytim2; + u32 dphytim3; + int ret; + + /* All DSI global operation timings are set with recommended setting */ + for (i = 0; i < ARRAY_SIZE(rzg2l_mipi_dsi_global_timings); ++i) { + dphy_timings = &rzg2l_mipi_dsi_global_timings[i]; + if (hsfreq <= dphy_timings->hsfreq_max) + break; + } + + /* Initializing DPHY before accessing LINK */ + dphyctrl0 = DSIDPHYCTRL0_CAL_EN_HSRX_OFS | DSIDPHYCTRL0_CMN_MASTER_EN | + DSIDPHYCTRL0_RE_VDD_DETVCCQLV18 | DSIDPHYCTRL0_EN_BGR; + + rzg2l_mipi_dsi_phy_write(dsi, DSIDPHYCTRL0, dphyctrl0); + usleep_range(20, 30); + + dphyctrl0 |= DSIDPHYCTRL0_EN_LDO1200; + rzg2l_mipi_dsi_phy_write(dsi, DSIDPHYCTRL0, dphyctrl0); + usleep_range(10, 20); + + dphytim0 = DSIDPHYTIM0_TCLK_MISS(0) | + DSIDPHYTIM0_T_INIT(dphy_timings->t_init); + dphytim1 = DSIDPHYTIM1_THS_PREPARE(dphy_timings->ths_prepare) | + DSIDPHYTIM1_TCLK_PREPARE(dphy_timings->tclk_prepare) | + DSIDPHYTIM1_THS_SETTLE(0) | + DSIDPHYTIM1_TCLK_SETTLE(0); + dphytim2 = DSIDPHYTIM2_TCLK_TRAIL(dphy_timings->tclk_trail) | + DSIDPHYTIM2_TCLK_POST(dphy_timings->tclk_post) | + DSIDPHYTIM2_TCLK_PRE(dphy_timings->tclk_pre) | + DSIDPHYTIM2_TCLK_ZERO(dphy_timings->tclk_zero); + dphytim3 = DSIDPHYTIM3_TLPX(dphy_timings->tlpx) | + DSIDPHYTIM3_THS_EXIT(dphy_timings->ths_exit) | + DSIDPHYTIM3_THS_TRAIL(dphy_timings->ths_trail) | + DSIDPHYTIM3_THS_ZERO(dphy_timings->ths_zero); + + rzg2l_mipi_dsi_phy_write(dsi, DSIDPHYTIM0, dphytim0); + rzg2l_mipi_dsi_phy_write(dsi, DSIDPHYTIM1, dphytim1); + rzg2l_mipi_dsi_phy_write(dsi, DSIDPHYTIM2, dphytim2); + rzg2l_mipi_dsi_phy_write(dsi, DSIDPHYTIM3, dphytim3); + + ret = reset_control_deassert(dsi->rstc); + if (ret < 0) + return ret; + + udelay(1); + + return 0; +} + +static void rzg2l_mipi_dsi_dphy_exit(struct rzg2l_mipi_dsi *dsi) +{ + u32 dphyctrl0; + + dphyctrl0 = rzg2l_mipi_dsi_phy_read(dsi, DSIDPHYCTRL0); + + dphyctrl0 &= ~(DSIDPHYCTRL0_EN_LDO1200 | DSIDPHYCTRL0_EN_BGR); + rzg2l_mipi_dsi_phy_write(dsi, DSIDPHYCTRL0, dphyctrl0); + + reset_control_assert(dsi->rstc); +} + +static int rzg2l_mipi_dsi_startup(struct rzg2l_mipi_dsi *dsi, + const struct drm_display_mode *mode) +{ + unsigned long hsfreq; + unsigned int bpp; + u32 txsetr; + u32 clstptsetr; + u32 lptrnstsetr; + u32 clkkpt; + u32 clkbfht; + u32 clkstpt; + u32 golpbkt; + int ret; + + /* + * Relationship between hsclk and vclk must follow + * vclk * bpp = hsclk * 8 * lanes + * where vclk: video clock (Hz) + * bpp: video pixel bit depth + * hsclk: DSI HS Byte clock frequency (Hz) + * lanes: number of data lanes + * + * hsclk(bit) = hsclk(byte) * 8 + */ + bpp = mipi_dsi_pixel_format_to_bpp(dsi->format); + hsfreq = (mode->clock * bpp * 8) / (8 * dsi->lanes); + + ret = pm_runtime_resume_and_get(dsi->dev); + if (ret < 0) + return ret; + + clk_set_rate(dsi->vclk, mode->clock * 1000); + + ret = rzg2l_mipi_dsi_dphy_init(dsi, hsfreq); + if (ret < 0) + goto err_phy; + + /* Enable Data lanes and Clock lanes */ + txsetr = TXSETR_DLEN | TXSETR_NUMLANEUSE(dsi->lanes - 1) | TXSETR_CLEN; + rzg2l_mipi_dsi_link_write(dsi, TXSETR, txsetr); + + /* + * Global timings characteristic depends on high speed Clock Frequency + * Currently MIPI DSI-IF just supports maximum FHD@60 with: + * - videoclock = 148.5 (MHz) + * - bpp: maximum 24bpp + * - data lanes: maximum 4 lanes + * Therefore maximum hsclk will be 891 Mbps. + */ + if (hsfreq > 445500) { + clkkpt = 12; + clkbfht = 15; + clkstpt = 48; + golpbkt = 75; + } else if (hsfreq > 250000) { + clkkpt = 7; + clkbfht = 8; + clkstpt = 27; + golpbkt = 40; + } else { + clkkpt = 8; + clkbfht = 6; + clkstpt = 24; + golpbkt = 29; + } + + clstptsetr = CLSTPTSETR_CLKKPT(clkkpt) | CLSTPTSETR_CLKBFHT(clkbfht) | + CLSTPTSETR_CLKSTPT(clkstpt); + rzg2l_mipi_dsi_link_write(dsi, CLSTPTSETR, clstptsetr); + + lptrnstsetr = LPTRNSTSETR_GOLPBKT(golpbkt); + rzg2l_mipi_dsi_link_write(dsi, LPTRNSTSETR, lptrnstsetr); + + return 0; + +err_phy: + rzg2l_mipi_dsi_dphy_exit(dsi); + pm_runtime_put(dsi->dev); + + return ret; +} + +static void rzg2l_mipi_dsi_stop(struct rzg2l_mipi_dsi *dsi) +{ + rzg2l_mipi_dsi_dphy_exit(dsi); + pm_runtime_put(dsi->dev); +} + +static void rzg2l_mipi_dsi_set_display_timing(struct rzg2l_mipi_dsi *dsi, + const struct drm_display_mode *mode) +{ + u32 vich1ppsetr; + u32 vich1vssetr; + u32 vich1vpsetr; + u32 vich1hssetr; + u32 vich1hpsetr; + int dsi_format; + u32 delay[2]; + u8 index; + + /* Configuration for Pixel Packet */ + dsi_format = mipi_dsi_pixel_format_to_bpp(dsi->format); + switch (dsi_format) { + case 24: + vich1ppsetr = VICH1PPSETR_DT_RGB24; + break; + case 18: + vich1ppsetr = VICH1PPSETR_DT_RGB18; + break; + } + + if ((dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) && + !(dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST)) + vich1ppsetr |= VICH1PPSETR_TXESYNC_PULSE; + + rzg2l_mipi_dsi_link_write(dsi, VICH1PPSETR, vich1ppsetr); + + /* Configuration for Video Parameters */ + vich1vssetr = VICH1VSSETR_VACTIVE(mode->vdisplay) | + VICH1VSSETR_VSA(mode->vsync_end - mode->vsync_start); + vich1vssetr |= (mode->flags & DRM_MODE_FLAG_PVSYNC) ? + VICH1VSSETR_VSPOL_HIGH : VICH1VSSETR_VSPOL_LOW; + + vich1vpsetr = VICH1VPSETR_VFP(mode->vsync_start - mode->vdisplay) | + VICH1VPSETR_VBP(mode->vtotal - mode->vsync_end); + + vich1hssetr = VICH1HSSETR_HACTIVE(mode->hdisplay) | + VICH1HSSETR_HSA(mode->hsync_end - mode->hsync_start); + vich1hssetr |= (mode->flags & DRM_MODE_FLAG_PHSYNC) ? + VICH1HSSETR_HSPOL_HIGH : VICH1HSSETR_HSPOL_LOW; + + vich1hpsetr = VICH1HPSETR_HFP(mode->hsync_start - mode->hdisplay) | + VICH1HPSETR_HBP(mode->htotal - mode->hsync_end); + + rzg2l_mipi_dsi_link_write(dsi, VICH1VSSETR, vich1vssetr); + rzg2l_mipi_dsi_link_write(dsi, VICH1VPSETR, vich1vpsetr); + rzg2l_mipi_dsi_link_write(dsi, VICH1HSSETR, vich1hssetr); + rzg2l_mipi_dsi_link_write(dsi, VICH1HPSETR, vich1hpsetr); + + /* + * Configuration for Delay Value + * Delay value based on 2 ranges of video clock. + * 74.25MHz is videoclock of HD@60p or FHD@30p + */ + if (mode->clock > 74250) { + delay[0] = 231; + delay[1] = 216; + } else { + delay[0] = 220; + delay[1] = 212; + } + + if (dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) + index = 0; + else + index = 1; + + rzg2l_mipi_dsi_link_write(dsi, VICH1SET1R, + VICH1SET1R_DLY(delay[index])); +} + +static int rzg2l_mipi_dsi_start_hs_clock(struct rzg2l_mipi_dsi *dsi) +{ + bool is_clk_cont; + u32 hsclksetr; + u32 status; + int ret; + + is_clk_cont = !(dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS); + + /* Start HS clock */ + hsclksetr = HSCLKSETR_HSCLKRUN_HS | (is_clk_cont ? + HSCLKSETR_HSCLKMODE_CONT : + HSCLKSETR_HSCLKMODE_NON_CONT); + rzg2l_mipi_dsi_link_write(dsi, HSCLKSETR, hsclksetr); + + if (is_clk_cont) { + ret = read_poll_timeout(rzg2l_mipi_dsi_link_read, status, + status & PLSR_CLLP2HS, + 2000, 20000, false, dsi, PLSR); + if (ret < 0) { + dev_err(dsi->dev, "failed to start HS clock\n"); + return ret; + } + } + + dev_dbg(dsi->dev, "Start High Speed Clock with %s clock mode", + is_clk_cont ? "continuous" : "non-continuous"); + + return 0; +} + +static int rzg2l_mipi_dsi_stop_hs_clock(struct rzg2l_mipi_dsi *dsi) +{ + bool is_clk_cont; + u32 status; + int ret; + + is_clk_cont = !(dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS); + + /* Stop HS clock */ + rzg2l_mipi_dsi_link_write(dsi, HSCLKSETR, + is_clk_cont ? HSCLKSETR_HSCLKMODE_CONT : + HSCLKSETR_HSCLKMODE_NON_CONT); + + if (is_clk_cont) { + ret = read_poll_timeout(rzg2l_mipi_dsi_link_read, status, + status & PLSR_CLHS2LP, + 2000, 20000, false, dsi, PLSR); + if (ret < 0) { + dev_err(dsi->dev, "failed to stop HS clock\n"); + return ret; + } + } + + return 0; +} + +static int rzg2l_mipi_dsi_start_video(struct rzg2l_mipi_dsi *dsi) +{ + u32 vich1set0r; + u32 status; + int ret; + + /* Configuration for Blanking sequence and start video input*/ + vich1set0r = VICH1SET0R_HFPNOLP | VICH1SET0R_HBPNOLP | + VICH1SET0R_HSANOLP | VICH1SET0R_VSTART; + rzg2l_mipi_dsi_link_write(dsi, VICH1SET0R, vich1set0r); + + ret = read_poll_timeout(rzg2l_mipi_dsi_link_read, status, + status & VICH1SR_VIRDY, + 2000, 20000, false, dsi, VICH1SR); + if (ret < 0) + dev_err(dsi->dev, "Failed to start video signal input\n"); + + return ret; +} + +static int rzg2l_mipi_dsi_stop_video(struct rzg2l_mipi_dsi *dsi) +{ + u32 status; + int ret; + + rzg2l_mipi_dsi_link_write(dsi, VICH1SET0R, VICH1SET0R_VSTPAFT); + ret = read_poll_timeout(rzg2l_mipi_dsi_link_read, status, + (status & VICH1SR_STOP) && (!(status & VICH1SR_RUNNING)), + 2000, 20000, false, dsi, VICH1SR); + if (ret < 0) + goto err; + + ret = read_poll_timeout(rzg2l_mipi_dsi_link_read, status, + !(status & LINKSR_HSBUSY), + 2000, 20000, false, dsi, LINKSR); + if (ret < 0) + goto err; + + return 0; + +err: + dev_err(dsi->dev, "Failed to stop video signal input\n"); + return ret; +} + +/* ----------------------------------------------------------------------------- + * Bridge + */ + +static int rzg2l_mipi_dsi_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct rzg2l_mipi_dsi *dsi = bridge_to_rzg2l_mipi_dsi(bridge); + + return drm_bridge_attach(bridge->encoder, dsi->next_bridge, bridge, + flags); +} + +static void rzg2l_mipi_dsi_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct drm_atomic_state *state = old_bridge_state->base.state; + struct rzg2l_mipi_dsi *dsi = bridge_to_rzg2l_mipi_dsi(bridge); + const struct drm_display_mode *mode; + struct drm_connector *connector; + struct drm_crtc *crtc; + int ret; + + connector = drm_atomic_get_new_connector_for_encoder(state, bridge->encoder); + crtc = drm_atomic_get_new_connector_state(state, connector)->crtc; + mode = &drm_atomic_get_new_crtc_state(state, crtc)->adjusted_mode; + + ret = rzg2l_mipi_dsi_startup(dsi, mode); + if (ret < 0) + return; + + rzg2l_mipi_dsi_set_display_timing(dsi, mode); + + ret = rzg2l_mipi_dsi_start_hs_clock(dsi); + if (ret < 0) + goto err_stop; + + ret = rzg2l_mipi_dsi_start_video(dsi); + if (ret < 0) + goto err_stop_clock; + + return; + +err_stop_clock: + rzg2l_mipi_dsi_stop_hs_clock(dsi); +err_stop: + rzg2l_mipi_dsi_stop(dsi); +} + +static void rzg2l_mipi_dsi_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct rzg2l_mipi_dsi *dsi = bridge_to_rzg2l_mipi_dsi(bridge); + + rzg2l_mipi_dsi_stop_video(dsi); + rzg2l_mipi_dsi_stop_hs_clock(dsi); + rzg2l_mipi_dsi_stop(dsi); +} + +static enum drm_mode_status +rzg2l_mipi_dsi_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + if (mode->clock > 148500) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static const struct drm_bridge_funcs rzg2l_mipi_dsi_bridge_ops = { + .attach = rzg2l_mipi_dsi_attach, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_enable = rzg2l_mipi_dsi_atomic_enable, + .atomic_disable = rzg2l_mipi_dsi_atomic_disable, + .mode_valid = rzg2l_mipi_dsi_bridge_mode_valid, +}; + +/* ----------------------------------------------------------------------------- + * Host setting + */ + +static int rzg2l_mipi_dsi_host_attach(struct mipi_dsi_host *host, + struct mipi_dsi_device *device) +{ + struct rzg2l_mipi_dsi *dsi = host_to_rzg2l_mipi_dsi(host); + int ret; + + if (device->lanes > dsi->num_data_lanes) { + dev_err(dsi->dev, + "Number of lines of device (%u) exceeds host (%u)\n", + device->lanes, dsi->num_data_lanes); + return -EINVAL; + } + + switch (mipi_dsi_pixel_format_to_bpp(device->format)) { + case 24: + case 18: + break; + default: + dev_err(dsi->dev, "Unsupported format 0x%04x\n", device->format); + return -EINVAL; + } + + dsi->lanes = device->lanes; + dsi->format = device->format; + dsi->mode_flags = device->mode_flags; + + dsi->next_bridge = devm_drm_of_get_bridge(dsi->dev, dsi->dev->of_node, + 1, 0); + if (IS_ERR(dsi->next_bridge)) { + ret = PTR_ERR(dsi->next_bridge); + dev_err(dsi->dev, "failed to get next bridge: %d\n", ret); + return ret; + } + + drm_bridge_add(&dsi->bridge); + + return 0; +} + +static int rzg2l_mipi_dsi_host_detach(struct mipi_dsi_host *host, + struct mipi_dsi_device *device) +{ + struct rzg2l_mipi_dsi *dsi = host_to_rzg2l_mipi_dsi(host); + + drm_bridge_remove(&dsi->bridge); + + return 0; +} + +static const struct mipi_dsi_host_ops rzg2l_mipi_dsi_host_ops = { + .attach = rzg2l_mipi_dsi_host_attach, + .detach = rzg2l_mipi_dsi_host_detach, +}; + +/* ----------------------------------------------------------------------------- + * Power Management + */ + +static int __maybe_unused rzg2l_mipi_pm_runtime_suspend(struct device *dev) +{ + struct rzg2l_mipi_dsi *dsi = dev_get_drvdata(dev); + + reset_control_assert(dsi->prstc); + reset_control_assert(dsi->arstc); + + return 0; +} + +static int __maybe_unused rzg2l_mipi_pm_runtime_resume(struct device *dev) +{ + struct rzg2l_mipi_dsi *dsi = dev_get_drvdata(dev); + int ret; + + ret = reset_control_deassert(dsi->arstc); + if (ret < 0) + return ret; + + ret = reset_control_deassert(dsi->prstc); + if (ret < 0) + reset_control_assert(dsi->arstc); + + return ret; +} + +static const struct dev_pm_ops rzg2l_mipi_pm_ops = { + SET_RUNTIME_PM_OPS(rzg2l_mipi_pm_runtime_suspend, rzg2l_mipi_pm_runtime_resume, NULL) +}; + +/* ----------------------------------------------------------------------------- + * Probe & Remove + */ + +static int rzg2l_mipi_dsi_probe(struct platform_device *pdev) +{ + unsigned int num_data_lanes; + struct rzg2l_mipi_dsi *dsi; + u32 txsetr; + int ret; + + dsi = devm_kzalloc(&pdev->dev, sizeof(*dsi), GFP_KERNEL); + if (!dsi) + return -ENOMEM; + + platform_set_drvdata(pdev, dsi); + dsi->dev = &pdev->dev; + + ret = drm_of_get_data_lanes_count_ep(dsi->dev->of_node, 1, 0, 1, 4); + if (ret < 0) + return dev_err_probe(dsi->dev, ret, + "missing or invalid data-lanes property\n"); + + num_data_lanes = ret; + + dsi->mmio = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(dsi->mmio)) + return PTR_ERR(dsi->mmio); + + dsi->vclk = devm_clk_get(dsi->dev, "vclk"); + if (IS_ERR(dsi->vclk)) + return PTR_ERR(dsi->vclk); + + dsi->rstc = devm_reset_control_get_exclusive(dsi->dev, "rst"); + if (IS_ERR(dsi->rstc)) + return dev_err_probe(dsi->dev, PTR_ERR(dsi->rstc), + "failed to get rst\n"); + + dsi->arstc = devm_reset_control_get_exclusive(dsi->dev, "arst"); + if (IS_ERR(dsi->arstc)) + return dev_err_probe(&pdev->dev, PTR_ERR(dsi->arstc), + "failed to get arst\n"); + + dsi->prstc = devm_reset_control_get_exclusive(dsi->dev, "prst"); + if (IS_ERR(dsi->prstc)) + return dev_err_probe(dsi->dev, PTR_ERR(dsi->prstc), + "failed to get prst\n"); + + platform_set_drvdata(pdev, dsi); + + pm_runtime_enable(dsi->dev); + + ret = pm_runtime_resume_and_get(dsi->dev); + if (ret < 0) + goto err_pm_disable; + + /* + * TXSETR register can be read only after DPHY init. But during probe + * mode->clock and format are not available. So initialize DPHY with + * timing parameters for 80Mbps. + */ + ret = rzg2l_mipi_dsi_dphy_init(dsi, 80000); + if (ret < 0) + goto err_phy; + + txsetr = rzg2l_mipi_dsi_link_read(dsi, TXSETR); + dsi->num_data_lanes = min(((txsetr >> 16) & 3) + 1, num_data_lanes); + rzg2l_mipi_dsi_dphy_exit(dsi); + pm_runtime_put(dsi->dev); + + /* Initialize the DRM bridge. */ + dsi->bridge.funcs = &rzg2l_mipi_dsi_bridge_ops; + dsi->bridge.of_node = dsi->dev->of_node; + + /* Init host device */ + dsi->host.dev = dsi->dev; + dsi->host.ops = &rzg2l_mipi_dsi_host_ops; + ret = mipi_dsi_host_register(&dsi->host); + if (ret < 0) + goto err_pm_disable; + + return 0; + +err_phy: + rzg2l_mipi_dsi_dphy_exit(dsi); + pm_runtime_put(dsi->dev); +err_pm_disable: + pm_runtime_disable(dsi->dev); + return ret; +} + +static int rzg2l_mipi_dsi_remove(struct platform_device *pdev) +{ + struct rzg2l_mipi_dsi *dsi = platform_get_drvdata(pdev); + + mipi_dsi_host_unregister(&dsi->host); + pm_runtime_disable(&pdev->dev); + + return 0; +} + +static const struct of_device_id rzg2l_mipi_dsi_of_table[] = { + { .compatible = "renesas,rzg2l-mipi-dsi" }, + { /* sentinel */ } +}; + +MODULE_DEVICE_TABLE(of, rzg2l_mipi_dsi_of_table); + +static struct platform_driver rzg2l_mipi_dsi_platform_driver = { + .probe = rzg2l_mipi_dsi_probe, + .remove = rzg2l_mipi_dsi_remove, + .driver = { + .name = "rzg2l-mipi-dsi", + .pm = &rzg2l_mipi_pm_ops, + .of_match_table = rzg2l_mipi_dsi_of_table, + }, +}; + +module_platform_driver(rzg2l_mipi_dsi_platform_driver); + +MODULE_AUTHOR("Biju Das <biju.das.jz@bp.renesas.com>"); +MODULE_DESCRIPTION("Renesas RZ/G2L MIPI DSI Encoder Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/rcar-du/rzg2l_mipi_dsi_regs.h b/drivers/gpu/drm/rcar-du/rzg2l_mipi_dsi_regs.h new file mode 100644 index 000000000000..1dbc16ec64a4 --- /dev/null +++ b/drivers/gpu/drm/rcar-du/rzg2l_mipi_dsi_regs.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * RZ/G2L MIPI DSI Interface Registers Definitions + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ + +#ifndef __RZG2L_MIPI_DSI_REGS_H__ +#define __RZG2L_MIPI_DSI_REGS_H__ + +#include <linux/bits.h> + +/* DPHY Registers */ +#define DSIDPHYCTRL0 0x00 +#define DSIDPHYCTRL0_CAL_EN_HSRX_OFS BIT(16) +#define DSIDPHYCTRL0_CMN_MASTER_EN BIT(8) +#define DSIDPHYCTRL0_RE_VDD_DETVCCQLV18 BIT(2) +#define DSIDPHYCTRL0_EN_LDO1200 BIT(1) +#define DSIDPHYCTRL0_EN_BGR BIT(0) + +#define DSIDPHYTIM0 0x04 +#define DSIDPHYTIM0_TCLK_MISS(x) ((x) << 24) +#define DSIDPHYTIM0_T_INIT(x) ((x) << 0) + +#define DSIDPHYTIM1 0x08 +#define DSIDPHYTIM1_THS_PREPARE(x) ((x) << 24) +#define DSIDPHYTIM1_TCLK_PREPARE(x) ((x) << 16) +#define DSIDPHYTIM1_THS_SETTLE(x) ((x) << 8) +#define DSIDPHYTIM1_TCLK_SETTLE(x) ((x) << 0) + +#define DSIDPHYTIM2 0x0c +#define DSIDPHYTIM2_TCLK_TRAIL(x) ((x) << 24) +#define DSIDPHYTIM2_TCLK_POST(x) ((x) << 16) +#define DSIDPHYTIM2_TCLK_PRE(x) ((x) << 8) +#define DSIDPHYTIM2_TCLK_ZERO(x) ((x) << 0) + +#define DSIDPHYTIM3 0x10 +#define DSIDPHYTIM3_TLPX(x) ((x) << 24) +#define DSIDPHYTIM3_THS_EXIT(x) ((x) << 16) +#define DSIDPHYTIM3_THS_TRAIL(x) ((x) << 8) +#define DSIDPHYTIM3_THS_ZERO(x) ((x) << 0) + +/* --------------------------------------------------------*/ +/* Link Registers */ +#define LINK_REG_OFFSET 0x10000 + +/* Link Status Register */ +#define LINKSR 0x10 +#define LINKSR_LPBUSY BIT(13) +#define LINKSR_HSBUSY BIT(12) +#define LINKSR_VICHRUN1 BIT(8) +#define LINKSR_SQCHRUN1 BIT(4) +#define LINKSR_SQCHRUN0 BIT(0) + +/* Tx Set Register */ +#define TXSETR 0x100 +#define TXSETR_NUMLANECAP (0x3 << 16) +#define TXSETR_DLEN (1 << 9) +#define TXSETR_CLEN (1 << 8) +#define TXSETR_NUMLANEUSE(x) (((x) & 0x3) << 0) + +/* HS Clock Set Register */ +#define HSCLKSETR 0x104 +#define HSCLKSETR_HSCLKMODE_CONT (1 << 1) +#define HSCLKSETR_HSCLKMODE_NON_CONT (0 << 1) +#define HSCLKSETR_HSCLKRUN_HS (1 << 0) +#define HSCLKSETR_HSCLKRUN_LP (0 << 0) + +/* Reset Control Register */ +#define RSTCR 0x110 +#define RSTCR_SWRST BIT(0) +#define RSTCR_FCETXSTP BIT(16) + +/* Reset Status Register */ +#define RSTSR 0x114 +#define RSTSR_DL0DIR (1 << 15) +#define RSTSR_DLSTPST (0xf << 8) +#define RSTSR_SWRSTV1 (1 << 4) +#define RSTSR_SWRSTIB (1 << 3) +#define RSTSR_SWRSTAPB (1 << 2) +#define RSTSR_SWRSTLP (1 << 1) +#define RSTSR_SWRSTHS (1 << 0) + +/* Clock Lane Stop Time Set Register */ +#define CLSTPTSETR 0x314 +#define CLSTPTSETR_CLKKPT(x) ((x) << 24) +#define CLSTPTSETR_CLKBFHT(x) ((x) << 16) +#define CLSTPTSETR_CLKSTPT(x) ((x) << 2) + +/* LP Transition Time Set Register */ +#define LPTRNSTSETR 0x318 +#define LPTRNSTSETR_GOLPBKT(x) ((x) << 0) + +/* Physical Lane Status Register */ +#define PLSR 0x320 +#define PLSR_CLHS2LP BIT(27) +#define PLSR_CLLP2HS BIT(26) + +/* Video-Input Channel 1 Set 0 Register */ +#define VICH1SET0R 0x400 +#define VICH1SET0R_VSEN BIT(12) +#define VICH1SET0R_HFPNOLP BIT(10) +#define VICH1SET0R_HBPNOLP BIT(9) +#define VICH1SET0R_HSANOLP BIT(8) +#define VICH1SET0R_VSTPAFT BIT(1) +#define VICH1SET0R_VSTART BIT(0) + +/* Video-Input Channel 1 Set 1 Register */ +#define VICH1SET1R 0x404 +#define VICH1SET1R_DLY(x) (((x) & 0xfff) << 2) + +/* Video-Input Channel 1 Status Register */ +#define VICH1SR 0x410 +#define VICH1SR_VIRDY BIT(3) +#define VICH1SR_RUNNING BIT(2) +#define VICH1SR_STOP BIT(1) +#define VICH1SR_START BIT(0) + +/* Video-Input Channel 1 Pixel Packet Set Register */ +#define VICH1PPSETR 0x420 +#define VICH1PPSETR_DT_RGB18 (0x1e << 16) +#define VICH1PPSETR_DT_RGB18_LS (0x2e << 16) +#define VICH1PPSETR_DT_RGB24 (0x3e << 16) +#define VICH1PPSETR_TXESYNC_PULSE (1 << 15) +#define VICH1PPSETR_VC(x) ((x) << 22) + +/* Video-Input Channel 1 Vertical Size Set Register */ +#define VICH1VSSETR 0x428 +#define VICH1VSSETR_VACTIVE(x) (((x) & 0x7fff) << 16) +#define VICH1VSSETR_VSPOL_LOW (1 << 15) +#define VICH1VSSETR_VSPOL_HIGH (0 << 15) +#define VICH1VSSETR_VSA(x) (((x) & 0xfff) << 0) + +/* Video-Input Channel 1 Vertical Porch Set Register */ +#define VICH1VPSETR 0x42c +#define VICH1VPSETR_VFP(x) (((x) & 0x1fff) << 16) +#define VICH1VPSETR_VBP(x) (((x) & 0x1fff) << 0) + +/* Video-Input Channel 1 Horizontal Size Set Register */ +#define VICH1HSSETR 0x430 +#define VICH1HSSETR_HACTIVE(x) (((x) & 0x7fff) << 16) +#define VICH1HSSETR_HSPOL_LOW (1 << 15) +#define VICH1HSSETR_HSPOL_HIGH (0 << 15) +#define VICH1HSSETR_HSA(x) (((x) & 0xfff) << 0) + +/* Video-Input Channel 1 Horizontal Porch Set Register */ +#define VICH1HPSETR 0x434 +#define VICH1HPSETR_HFP(x) (((x) & 0x1fff) << 16) +#define VICH1HPSETR_HBP(x) (((x) & 0x1fff) << 0) + +#endif /* __RZG2L_MIPI_DSI_REGS_H__ */ diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index 518ee13b1d6f..8526dda91931 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -571,7 +571,7 @@ static void cdn_dp_encoder_mode_set(struct drm_encoder *encoder, video->v_sync_polarity = !!(mode->flags & DRM_MODE_FLAG_NVSYNC); video->h_sync_polarity = !!(mode->flags & DRM_MODE_FLAG_NHSYNC); - memcpy(&dp->mode, adjusted, sizeof(*mode)); + drm_mode_copy(&dp->mode, adjusted); } static bool cdn_dp_check_link_status(struct cdn_dp_device *dp) diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c index 92b599b089f9..7901c3babc8c 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c @@ -746,7 +746,7 @@ static void dw_mipi_dsi_rockchip_config(struct dw_mipi_dsi_rockchip *dsi) static void dw_mipi_dsi_rockchip_set_lcdsel(struct dw_mipi_dsi_rockchip *dsi, int mux) { - if (dsi->cdata->lcdsel_grf_reg < 0) + if (dsi->cdata->lcdsel_grf_reg) regmap_write(dsi->grf_regmap, dsi->cdata->lcdsel_grf_reg, mux ? dsi->cdata->lcdsel_lit : dsi->cdata->lcdsel_big); } @@ -1045,23 +1045,31 @@ static int dw_mipi_dsi_rockchip_host_attach(void *priv_data, if (ret) { DRM_DEV_ERROR(dsi->dev, "Failed to register component: %d\n", ret); - return ret; + goto out; } second = dw_mipi_dsi_rockchip_find_second(dsi); - if (IS_ERR(second)) - return PTR_ERR(second); + if (IS_ERR(second)) { + ret = PTR_ERR(second); + goto out; + } if (second) { ret = component_add(second, &dw_mipi_dsi_rockchip_ops); if (ret) { DRM_DEV_ERROR(second, "Failed to register component: %d\n", ret); - return ret; + goto out; } } return 0; + +out: + mutex_lock(&dsi->usage_mutex); + dsi->usage_mode = DW_DSI_USAGE_IDLE; + mutex_unlock(&dsi->usage_mutex); + return ret; } static int dw_mipi_dsi_rockchip_host_detach(void *priv_data, @@ -1629,7 +1637,6 @@ static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = { static const struct rockchip_dw_dsi_chip_data rk3568_chip_data[] = { { .reg = 0xfe060000, - .lcdsel_grf_reg = -1, .lanecfg1_grf_reg = RK3568_GRF_VO_CON2, .lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI0_SKEWCALHS | RK3568_DSI0_FORCETXSTOPMODE | @@ -1639,7 +1646,6 @@ static const struct rockchip_dw_dsi_chip_data rk3568_chip_data[] = { }, { .reg = 0xfe070000, - .lcdsel_grf_reg = -1, .lanecfg1_grf_reg = RK3568_GRF_VO_CON3, .lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI1_SKEWCALHS | RK3568_DSI1_FORCETXSTOPMODE | @@ -1675,5 +1681,11 @@ struct platform_driver dw_mipi_dsi_rockchip_driver = { .of_match_table = dw_mipi_dsi_rockchip_dt_ids, .pm = &dw_mipi_dsi_rockchip_pm_ops, .name = "dw-mipi-dsi-rockchip", + /* + * For dual-DSI display, one DSI pokes at the other DSI's + * drvdata in dw_mipi_dsi_rockchip_find_second(). This is not + * safe for asynchronous probe. + */ + .probe_type = PROBE_FORCE_SYNCHRONOUS, }, }; diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index c14f88893868..2f4b8f64cbad 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -565,7 +565,8 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master, ret = rockchip_hdmi_parse_dt(hdmi); if (ret) { - DRM_DEV_ERROR(hdmi->dev, "Unable to parse OF data\n"); + if (ret != -EPROBE_DEFER) + DRM_DEV_ERROR(hdmi->dev, "Unable to parse OF data\n"); return ret; } diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index 87b2243ea23e..f51774866f41 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -499,7 +499,7 @@ static void inno_hdmi_encoder_mode_set(struct drm_encoder *encoder, inno_hdmi_setup(hdmi, adj_mode); /* Store the display mode for plugin/DPMS poweron events */ - memcpy(&hdmi->previous_mode, adj_mode, sizeof(hdmi->previous_mode)); + drm_mode_copy(&hdmi->previous_mode, adj_mode); } static void inno_hdmi_encoder_enable(struct drm_encoder *encoder) diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.c b/drivers/gpu/drm/rockchip/rk3066_hdmi.c index cf2cf51091a3..90145ad96984 100644 --- a/drivers/gpu/drm/rockchip/rk3066_hdmi.c +++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.c @@ -395,7 +395,7 @@ rk3066_hdmi_encoder_mode_set(struct drm_encoder *encoder, struct rk3066_hdmi *hdmi = encoder_to_rk3066_hdmi(encoder); /* Store the display mode for plugin/DPMS poweron events. */ - memcpy(&hdmi->previous_mode, adj_mode, sizeof(hdmi->previous_mode)); + drm_mode_copy(&hdmi->previous_mode, adj_mode); } static void rk3066_hdmi_encoder_enable(struct drm_encoder *encoder) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 813f9f8c8698..6e0788d14c10 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -17,7 +17,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_of.h> #include <drm/drm_probe_helper.h> diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h index 1641440837af..aeb03a57240f 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -9,10 +9,10 @@ #ifndef _ROCKCHIP_DRM_DRV_H #define _ROCKCHIP_DRM_DRV_H -#include <drm/drm_fb_helper.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_gem.h> +#include <linux/i2c.h> #include <linux/module.h> #include <linux/component.h> diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index 409eaa1bf092..cfe8b793d344 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -9,7 +9,6 @@ #include <drm/drm.h> #include <drm/drm_atomic.h> #include <drm/drm_damage_helper.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_framebuffer_helper.h> @@ -72,7 +71,6 @@ rockchip_fb_create(struct drm_device *dev, struct drm_file *file, static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = { .fb_create = rockchip_fb_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index 614e97aaac80..6edb7c52cb3d 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -9,6 +9,7 @@ #include <linux/vmalloc.h> #include <drm/drm.h> +#include <drm/drm_fb_helper.h> #include <drm/drm_gem.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_prime.h> @@ -364,9 +365,12 @@ rockchip_gem_create_with_handle(struct drm_file *file_priv, { struct rockchip_gem_object *rk_obj; struct drm_gem_object *obj; + bool is_framebuffer; int ret; - rk_obj = rockchip_gem_create_object(drm, size, false); + is_framebuffer = drm->fb_helper && file_priv == drm->fb_helper->client.file; + + rk_obj = rockchip_gem_create_object(drm, size, is_framebuffer); if (IS_ERR(rk_obj)) return ERR_CAST(rk_obj); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index ad87db2fcaf6..8cecf81a5ae0 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -877,10 +877,14 @@ static void vop2_crtc_atomic_disable(struct drm_crtc *crtc, { struct vop2_video_port *vp = to_vop2_video_port(crtc); struct vop2 *vop2 = vp->vop2; + struct drm_crtc_state *old_crtc_state; int ret; vop2_lock(vop2); + old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); + drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, false); + drm_crtc_vblank_off(crtc); /* @@ -996,13 +1000,15 @@ static int vop2_plane_atomic_check(struct drm_plane *plane, static void vop2_plane_atomic_disable(struct drm_plane *plane, struct drm_atomic_state *state) { - struct drm_plane_state *old_pstate = drm_atomic_get_old_plane_state(state, plane); + struct drm_plane_state *old_pstate = NULL; struct vop2_win *win = to_vop2_win(plane); struct vop2 *vop2 = win->vop2; drm_dbg(vop2->drm, "%s disable\n", win->data->name); - if (!old_pstate->crtc) + if (state) + old_pstate = drm_atomic_get_old_plane_state(state, plane); + if (old_pstate && !old_pstate->crtc) return; vop2_win_disable(win); diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index c97bc1149663..fe09e5be79bd 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -140,6 +140,73 @@ bool drm_sched_entity_is_ready(struct drm_sched_entity *entity) return true; } +static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk) +{ + struct drm_sched_job *job = container_of(wrk, typeof(*job), work); + + drm_sched_fence_finished(job->s_fence); + WARN_ON(job->s_fence->parent); + job->sched->ops->free_job(job); +} + +/* Signal the scheduler finished fence when the entity in question is killed. */ +static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, + struct dma_fence_cb *cb) +{ + struct drm_sched_job *job = container_of(cb, struct drm_sched_job, + finish_cb); + int r; + + dma_fence_put(f); + + /* Wait for all dependencies to avoid data corruptions */ + while (!xa_empty(&job->dependencies)) { + f = xa_erase(&job->dependencies, job->last_dependency++); + r = dma_fence_add_callback(f, &job->finish_cb, + drm_sched_entity_kill_jobs_cb); + if (!r) + return; + + dma_fence_put(f); + } + + INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work); + schedule_work(&job->work); +} + +/* Remove the entity from the scheduler and kill all pending jobs */ +static void drm_sched_entity_kill(struct drm_sched_entity *entity) +{ + struct drm_sched_job *job; + struct dma_fence *prev; + + if (!entity->rq) + return; + + spin_lock(&entity->rq_lock); + entity->stopped = true; + drm_sched_rq_remove_entity(entity->rq, entity); + spin_unlock(&entity->rq_lock); + + /* Make sure this entity is not used by the scheduler at the moment */ + wait_for_completion(&entity->entity_idle); + + prev = dma_fence_get(entity->last_scheduled); + while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) { + struct drm_sched_fence *s_fence = job->s_fence; + + dma_fence_set_error(&s_fence->finished, -ESRCH); + + dma_fence_get(&s_fence->finished); + if (!prev || dma_fence_add_callback(prev, &job->finish_cb, + drm_sched_entity_kill_jobs_cb)) + drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb); + + prev = &s_fence->finished; + } + dma_fence_put(prev); +} + /** * drm_sched_entity_flush - Flush a context entity * @@ -180,91 +247,13 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) /* For killed process disable any more IBs enqueue right now */ last_user = cmpxchg(&entity->last_user, current->group_leader, NULL); if ((!last_user || last_user == current->group_leader) && - (current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) { - spin_lock(&entity->rq_lock); - entity->stopped = true; - drm_sched_rq_remove_entity(entity->rq, entity); - spin_unlock(&entity->rq_lock); - } + (current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) + drm_sched_entity_kill(entity); return ret; } EXPORT_SYMBOL(drm_sched_entity_flush); -static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk) -{ - struct drm_sched_job *job = container_of(wrk, typeof(*job), work); - - drm_sched_fence_finished(job->s_fence); - WARN_ON(job->s_fence->parent); - job->sched->ops->free_job(job); -} - - -/* Signal the scheduler finished fence when the entity in question is killed. */ -static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, - struct dma_fence_cb *cb) -{ - struct drm_sched_job *job = container_of(cb, struct drm_sched_job, - finish_cb); - - dma_fence_put(f); - INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work); - schedule_work(&job->work); -} - -static struct dma_fence * -drm_sched_job_dependency(struct drm_sched_job *job, - struct drm_sched_entity *entity) -{ - if (!xa_empty(&job->dependencies)) - return xa_erase(&job->dependencies, job->last_dependency++); - - if (job->sched->ops->dependency) - return job->sched->ops->dependency(job, entity); - - return NULL; -} - -static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) -{ - struct drm_sched_job *job; - struct dma_fence *f; - int r; - - while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) { - struct drm_sched_fence *s_fence = job->s_fence; - - /* Wait for all dependencies to avoid data corruptions */ - while ((f = drm_sched_job_dependency(job, entity))) { - dma_fence_wait(f, false); - dma_fence_put(f); - } - - drm_sched_fence_scheduled(s_fence); - dma_fence_set_error(&s_fence->finished, -ESRCH); - - /* - * When pipe is hanged by older entity, new entity might - * not even have chance to submit it's first job to HW - * and so entity->last_scheduled will remain NULL - */ - if (!entity->last_scheduled) { - drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb); - continue; - } - - dma_fence_get(entity->last_scheduled); - r = dma_fence_add_callback(entity->last_scheduled, - &job->finish_cb, - drm_sched_entity_kill_jobs_cb); - if (r == -ENOENT) - drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb); - else if (r) - DRM_ERROR("fence add callback failed (%d)\n", r); - } -} - /** * drm_sched_entity_fini - Destroy a context entity * @@ -278,33 +267,17 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) */ void drm_sched_entity_fini(struct drm_sched_entity *entity) { - struct drm_gpu_scheduler *sched = NULL; - - if (entity->rq) { - sched = entity->rq->sched; - drm_sched_rq_remove_entity(entity->rq, entity); - } - - /* Consumption of existing IBs wasn't completed. Forcefully - * remove them here. + /* + * If consumption of existing IBs wasn't completed. Forcefully remove + * them here. Also makes sure that the scheduler won't touch this entity + * any more. */ - if (spsc_queue_count(&entity->job_queue)) { - if (sched) { - /* - * Wait for thread to idle to make sure it isn't processing - * this entity. - */ - wait_for_completion(&entity->entity_idle); + drm_sched_entity_kill(entity); - } - if (entity->dependency) { - dma_fence_remove_callback(entity->dependency, - &entity->cb); - dma_fence_put(entity->dependency); - entity->dependency = NULL; - } - - drm_sched_entity_kill_jobs(entity); + if (entity->dependency) { + dma_fence_remove_callback(entity->dependency, &entity->cb); + dma_fence_put(entity->dependency); + entity->dependency = NULL; } dma_fence_put(entity->last_scheduled); @@ -417,6 +390,19 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) return false; } +static struct dma_fence * +drm_sched_job_dependency(struct drm_sched_job *job, + struct drm_sched_entity *entity) +{ + if (!xa_empty(&job->dependencies)) + return xa_erase(&job->dependencies, job->last_dependency++); + + if (job->sched->ops->prepare_job) + return job->sched->ops->prepare_job(job, entity); + + return NULL; +} + struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) { struct drm_sched_job *sched_job; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index d0ff9e11cb69..31f3a1267be4 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -286,32 +286,6 @@ static void drm_sched_job_done_cb(struct dma_fence *f, struct dma_fence_cb *cb) } /** - * drm_sched_dependency_optimized - test if the dependency can be optimized - * - * @fence: the dependency fence - * @entity: the entity which depends on the above fence - * - * Returns true if the dependency can be optimized and false otherwise - */ -bool drm_sched_dependency_optimized(struct dma_fence* fence, - struct drm_sched_entity *entity) -{ - struct drm_gpu_scheduler *sched = entity->rq->sched; - struct drm_sched_fence *s_fence; - - if (!fence || dma_fence_is_signaled(fence)) - return false; - if (fence->context == entity->fence_context) - return true; - s_fence = to_drm_sched_fence(fence); - if (s_fence && s_fence->sched == sched) - return true; - - return false; -} -EXPORT_SYMBOL(drm_sched_dependency_optimized); - -/** * drm_sched_start_timeout - start timeout for reset worker * * @sched: scheduler instance to start the worker for @@ -443,27 +417,6 @@ static void drm_sched_job_timedout(struct work_struct *work) } } - /** - * drm_sched_increase_karma - Update sched_entity guilty flag - * - * @bad: The job guilty of time out - * - * Increment on every hang caused by the 'bad' job. If this exceeds the hang - * limit of the scheduler then the respective sched entity is marked guilty and - * jobs from it will not be scheduled further - */ -void drm_sched_increase_karma(struct drm_sched_job *bad) -{ - drm_sched_increase_karma_ext(bad, 1); -} -EXPORT_SYMBOL(drm_sched_increase_karma); - -void drm_sched_reset_karma(struct drm_sched_job *bad) -{ - drm_sched_increase_karma_ext(bad, 0); -} -EXPORT_SYMBOL(drm_sched_reset_karma); - /** * drm_sched_stop - stop the scheduler * @@ -605,31 +558,14 @@ EXPORT_SYMBOL(drm_sched_start); */ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) { - drm_sched_resubmit_jobs_ext(sched, INT_MAX); -} -EXPORT_SYMBOL(drm_sched_resubmit_jobs); - -/** - * drm_sched_resubmit_jobs_ext - helper to relunch certain number of jobs from mirror ring list - * - * @sched: scheduler instance - * @max: job numbers to relaunch - * - */ -void drm_sched_resubmit_jobs_ext(struct drm_gpu_scheduler *sched, int max) -{ struct drm_sched_job *s_job, *tmp; uint64_t guilty_context; bool found_guilty = false; struct dma_fence *fence; - int i = 0; list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) { struct drm_sched_fence *s_fence = s_job->s_fence; - if (i >= max) - break; - if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) { found_guilty = true; guilty_context = s_job->s_fence->scheduled.context; @@ -639,7 +575,6 @@ void drm_sched_resubmit_jobs_ext(struct drm_gpu_scheduler *sched, int max) dma_fence_set_error(&s_fence->finished, -ECANCELED); fence = sched->ops->run_job(s_job); - i++; if (IS_ERR_OR_NULL(fence)) { if (IS_ERR(fence)) @@ -655,7 +590,7 @@ void drm_sched_resubmit_jobs_ext(struct drm_gpu_scheduler *sched, int max) } } } -EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext); +EXPORT_SYMBOL(drm_sched_resubmit_jobs); /** * drm_sched_job_init - init a scheduler job @@ -773,32 +708,28 @@ int drm_sched_job_add_dependency(struct drm_sched_job *job, EXPORT_SYMBOL(drm_sched_job_add_dependency); /** - * drm_sched_job_add_implicit_dependencies - adds implicit dependencies as job - * dependencies + * drm_sched_job_add_resv_dependencies - add all fences from the resv to the job * @job: scheduler job to add the dependencies to - * @obj: the gem object to add new dependencies from. - * @write: whether the job might write the object (so we need to depend on - * shared fences in the reservation object). + * @resv: the dma_resv object to get the fences from + * @usage: the dma_resv_usage to use to filter the fences * - * This should be called after drm_gem_lock_reservations() on your array of - * GEM objects used in the job but before updating the reservations with your - * own fences. + * This adds all fences matching the given usage from @resv to @job. + * Must be called with the @resv lock held. * * Returns: * 0 on success, or an error on failing to expand the array. */ -int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, - struct drm_gem_object *obj, - bool write) +int drm_sched_job_add_resv_dependencies(struct drm_sched_job *job, + struct dma_resv *resv, + enum dma_resv_usage usage) { struct dma_resv_iter cursor; struct dma_fence *fence; int ret; - dma_resv_assert_held(obj->resv); + dma_resv_assert_held(resv); - dma_resv_for_each_fence(&cursor, obj->resv, dma_resv_usage_rw(write), - fence) { + dma_resv_for_each_fence(&cursor, resv, usage, fence) { /* Make sure to grab an additional ref on the added fence */ dma_fence_get(fence); ret = drm_sched_job_add_dependency(job, fence); @@ -809,8 +740,31 @@ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, } return 0; } -EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies); +EXPORT_SYMBOL(drm_sched_job_add_resv_dependencies); +/** + * drm_sched_job_add_implicit_dependencies - adds implicit dependencies as job + * dependencies + * @job: scheduler job to add the dependencies to + * @obj: the gem object to add new dependencies from. + * @write: whether the job might write the object (so we need to depend on + * shared fences in the reservation object). + * + * This should be called after drm_gem_lock_reservations() on your array of + * GEM objects used in the job but before updating the reservations with your + * own fences. + * + * Returns: + * 0 on success, or an error on failing to expand the array. + */ +int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, + struct drm_gem_object *obj, + bool write) +{ + return drm_sched_job_add_resv_dependencies(job, obj->resv, + dma_resv_usage_rw(write)); +} +EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies); /** * drm_sched_job_cleanup - clean up scheduler job resources @@ -1172,13 +1126,15 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) EXPORT_SYMBOL(drm_sched_fini); /** - * drm_sched_increase_karma_ext - Update sched_entity guilty flag + * drm_sched_increase_karma - Update sched_entity guilty flag * * @bad: The job guilty of time out - * @type: type for increase/reset karma * + * Increment on every hang caused by the 'bad' job. If this exceeds the hang + * limit of the scheduler then the respective sched entity is marked guilty and + * jobs from it will not be scheduled further */ -void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type) +void drm_sched_increase_karma(struct drm_sched_job *bad) { int i; struct drm_sched_entity *tmp; @@ -1190,10 +1146,7 @@ void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type) * corrupt but keep in mind that kernel jobs always considered good. */ if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) { - if (type == 0) - atomic_set(&bad->karma, 0); - else if (type == 1) - atomic_inc(&bad->karma); + atomic_inc(&bad->karma); for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; i++) { @@ -1204,7 +1157,7 @@ void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type) if (bad->s_fence->scheduled.context == entity->fence_context) { if (entity->guilty) - atomic_set(entity->guilty, type); + atomic_set(entity->guilty, 1); break; } } @@ -1214,4 +1167,4 @@ void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type) } } } -EXPORT_SYMBOL(drm_sched_increase_karma_ext); +EXPORT_SYMBOL(drm_sched_increase_karma); diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index f2795f90ea69..53464afc2b9a 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -23,7 +23,7 @@ #include <drm/drm_crtc_helper.h> #include <drm/drm_damage_helper.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_format_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c index 7abf010a3293..ef6a4e63198f 100644 --- a/drivers/gpu/drm/sti/sti_drv.c +++ b/drivers/gpu/drm/sti/sti_drv.c @@ -14,7 +14,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_debugfs.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_of.h> diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c index b6ee8a82e656..577c477b5f46 100644 --- a/drivers/gpu/drm/sti/sti_dvo.c +++ b/drivers/gpu/drm/sti/sti_dvo.c @@ -288,7 +288,7 @@ static void sti_dvo_set_mode(struct drm_bridge *bridge, DRM_DEBUG_DRIVER("\n"); - memcpy(&dvo->mode, mode, sizeof(struct drm_display_mode)); + drm_mode_copy(&dvo->mode, mode); /* According to the path used (main or aux), the dvo clocks should * have a different parent clock. */ @@ -346,8 +346,9 @@ static int sti_dvo_connector_get_modes(struct drm_connector *connector) #define CLK_TOLERANCE_HZ 50 -static int sti_dvo_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +sti_dvo_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { int target = mode->clock * 1000; int target_min = target - CLK_TOLERANCE_HZ; diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 03cc401ed593..15097ac67931 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -524,7 +524,7 @@ static void sti_hda_set_mode(struct drm_bridge *bridge, DRM_DEBUG_DRIVER("\n"); - memcpy(&hda->mode, mode, sizeof(struct drm_display_mode)); + drm_mode_copy(&hda->mode, mode); if (!hda_get_mode_idx(hda->mode, &mode_idx)) { DRM_ERROR("Undefined mode\n"); @@ -601,8 +601,9 @@ static int sti_hda_connector_get_modes(struct drm_connector *connector) #define CLK_TOLERANCE_HZ 50 -static int sti_hda_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +sti_hda_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { int target = mode->clock * 1000; int target_min = target - CLK_TOLERANCE_HZ; diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index cb82622877d2..8539fe1fedc4 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -941,7 +941,7 @@ static void sti_hdmi_set_mode(struct drm_bridge *bridge, DRM_DEBUG_DRIVER("\n"); /* Copy the drm display mode in the connector local structure */ - memcpy(&hdmi->mode, mode, sizeof(struct drm_display_mode)); + drm_mode_copy(&hdmi->mode, mode); /* Update clock framerate according to the selected mode */ ret = clk_set_rate(hdmi->clk_pix, mode->clock * 1000); @@ -1004,8 +1004,9 @@ fail: #define CLK_TOLERANCE_HZ 50 -static int sti_hdmi_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +sti_hdmi_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { int target = mode->clock * 1000; int target_min = target - CLK_TOLERANCE_HZ; diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index d7914f5122df..50410bd99dfe 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -18,7 +18,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index d06ffd99d86e..cc94efbbf2d4 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -17,7 +17,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_module.h> #include <drm/drm_of.h> diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 34234a144e87..760ff05eabf4 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -1101,12 +1101,16 @@ static const struct component_ops sun6i_dsi_ops = { static int sun6i_dsi_probe(struct platform_device *pdev) { + const struct sun6i_dsi_variant *variant; struct device *dev = &pdev->dev; - const char *bus_clk_name = NULL; struct sun6i_dsi *dsi; void __iomem *base; int ret; + variant = device_get_match_data(dev); + if (!variant) + return -EINVAL; + dsi = devm_kzalloc(dev, sizeof(*dsi), GFP_KERNEL); if (!dsi) return -ENOMEM; @@ -1114,10 +1118,7 @@ static int sun6i_dsi_probe(struct platform_device *pdev) dsi->dev = dev; dsi->host.ops = &sun6i_dsi_host_ops; dsi->host.dev = dev; - - if (of_device_is_compatible(dev->of_node, - "allwinner,sun6i-a31-mipi-dsi")) - bus_clk_name = "bus"; + dsi->variant = variant; base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) { @@ -1142,7 +1143,7 @@ static int sun6i_dsi_probe(struct platform_device *pdev) return PTR_ERR(dsi->regs); } - dsi->bus_clk = devm_clk_get(dev, bus_clk_name); + dsi->bus_clk = devm_clk_get(dev, variant->has_mod_clk ? "bus" : NULL); if (IS_ERR(dsi->bus_clk)) return dev_err_probe(dev, PTR_ERR(dsi->bus_clk), "Couldn't get the DSI bus clock\n"); @@ -1151,21 +1152,21 @@ static int sun6i_dsi_probe(struct platform_device *pdev) if (ret) return ret; - if (of_device_is_compatible(dev->of_node, - "allwinner,sun6i-a31-mipi-dsi")) { + if (variant->has_mod_clk) { dsi->mod_clk = devm_clk_get(dev, "mod"); if (IS_ERR(dsi->mod_clk)) { dev_err(dev, "Couldn't get the DSI mod clock\n"); ret = PTR_ERR(dsi->mod_clk); goto err_attach_clk; } - } - /* - * In order to operate properly, that clock seems to be always - * set to 297MHz. - */ - clk_set_rate_exclusive(dsi->mod_clk, 297000000); + /* + * In order to operate properly, the module clock on the + * A31 variant always seems to be set to 297MHz. + */ + if (variant->set_mod_clk) + clk_set_rate_exclusive(dsi->mod_clk, 297000000); + } dsi->dphy = devm_phy_get(dev, "dphy"); if (IS_ERR(dsi->dphy)) { @@ -1191,7 +1192,8 @@ static int sun6i_dsi_probe(struct platform_device *pdev) err_remove_dsi_host: mipi_dsi_host_unregister(&dsi->host); err_unprotect_clk: - clk_rate_exclusive_put(dsi->mod_clk); + if (dsi->variant->has_mod_clk && dsi->variant->set_mod_clk) + clk_rate_exclusive_put(dsi->mod_clk); err_attach_clk: regmap_mmio_detach_clk(dsi->regs); @@ -1205,16 +1207,39 @@ static int sun6i_dsi_remove(struct platform_device *pdev) component_del(&pdev->dev, &sun6i_dsi_ops); mipi_dsi_host_unregister(&dsi->host); - clk_rate_exclusive_put(dsi->mod_clk); + if (dsi->variant->has_mod_clk && dsi->variant->set_mod_clk) + clk_rate_exclusive_put(dsi->mod_clk); regmap_mmio_detach_clk(dsi->regs); return 0; } +static const struct sun6i_dsi_variant sun6i_a31_mipi_dsi_variant = { + .has_mod_clk = true, + .set_mod_clk = true, +}; + +static const struct sun6i_dsi_variant sun50i_a64_mipi_dsi_variant = { +}; + +static const struct sun6i_dsi_variant sun50i_a100_mipi_dsi_variant = { + .has_mod_clk = true, +}; + static const struct of_device_id sun6i_dsi_of_table[] = { - { .compatible = "allwinner,sun6i-a31-mipi-dsi" }, - { .compatible = "allwinner,sun50i-a64-mipi-dsi" }, + { + .compatible = "allwinner,sun6i-a31-mipi-dsi", + .data = &sun6i_a31_mipi_dsi_variant, + }, + { + .compatible = "allwinner,sun50i-a64-mipi-dsi", + .data = &sun50i_a64_mipi_dsi_variant, + }, + { + .compatible = "allwinner,sun50i-a100-mipi-dsi", + .data = &sun50i_a100_mipi_dsi_variant, + }, { } }; MODULE_DEVICE_TABLE(of, sun6i_dsi_of_table); diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h index c863900ae3b4..f1ddefe0f554 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h @@ -15,6 +15,11 @@ #define SUN6I_DSI_TCON_DIV 4 +struct sun6i_dsi_variant { + bool has_mod_clk; + bool set_mod_clk; +}; + struct sun6i_dsi { struct drm_connector connector; struct drm_encoder encoder; @@ -31,6 +36,8 @@ struct sun6i_dsi { struct mipi_dsi_device *device; struct drm_device *drm; struct drm_panel *panel; + + const struct sun6i_dsi_variant *variant; }; static inline struct sun6i_dsi *host_to_sun6i_dsi(struct mipi_dsi_host *host) diff --git a/drivers/gpu/drm/tegra/Makefile b/drivers/gpu/drm/tegra/Makefile index df6cc986aeba..bb0d2c144b55 100644 --- a/drivers/gpu/drm/tegra/Makefile +++ b/drivers/gpu/drm/tegra/Makefile @@ -24,7 +24,8 @@ tegra-drm-y := \ gr3d.o \ falcon.o \ vic.o \ - nvdec.o + nvdec.o \ + riscv.o tegra-drm-y += trace.o diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index bd0f60704467..a67453cee883 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -3205,8 +3205,10 @@ static int tegra_dc_probe(struct platform_device *pdev) usleep_range(2000, 4000); err = reset_control_assert(dc->rst); - if (err < 0) + if (err < 0) { + clk_disable_unprepare(dc->clk); return err; + } usleep_range(2000, 4000); diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 6748ec1e0005..7bd2e65c2a16 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1093,6 +1093,10 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) struct host1x *host1x = dev_get_drvdata(dev->dev.parent); struct iommu_domain *domain; + /* Our IOMMU usage policy doesn't currently play well with GART */ + if (of_machine_is_compatible("nvidia,tegra20")) + return false; + /* * If the Tegra DRM clients are backed by an IOMMU, push buffers are * likely to be allocated beyond the 32-bit boundary if sufficient @@ -1382,6 +1386,7 @@ static const struct of_device_id host1x_drm_subdevs[] = { { .compatible = "nvidia,tegra194-vic", }, { .compatible = "nvidia,tegra194-nvdec", }, { .compatible = "nvidia,tegra234-vic", }, + { .compatible = "nvidia,tegra234-nvdec", }, { /* sentinel */ } }; diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c index bce71c0ccc9e..a900300ae5bd 100644 --- a/drivers/gpu/drm/tegra/fb.c +++ b/drivers/gpu/drm/tegra/fb.c @@ -206,6 +206,8 @@ static int tegra_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) static const struct fb_ops tegra_fb_ops = { .owner = THIS_MODULE, DRM_FB_HELPER_DEFAULT_OPS, + .fb_read = drm_fb_helper_sys_read, + .fb_write = drm_fb_helper_sys_write, .fb_fillrect = drm_fb_helper_sys_fillrect, .fb_copyarea = drm_fb_helper_sys_copyarea, .fb_imageblit = drm_fb_helper_sys_imageblit, @@ -243,7 +245,7 @@ static int tegra_fbdev_probe(struct drm_fb_helper *helper, if (IS_ERR(bo)) return PTR_ERR(bo); - info = drm_fb_helper_alloc_fbi(helper); + info = drm_fb_helper_alloc_info(helper); if (IS_ERR(info)) { dev_err(drm->dev, "failed to allocate framebuffer info\n"); drm_gem_object_put(&bo->gem); @@ -261,7 +263,7 @@ static int tegra_fbdev_probe(struct drm_fb_helper *helper, fb = fbdev->fb; helper->fb = fb; - helper->fbdev = info; + helper->info = info; info->fbops = &tegra_fb_ops; @@ -347,7 +349,7 @@ fini: static void tegra_fbdev_exit(struct tegra_fbdev *fbdev) { - drm_fb_helper_unregister_fbi(&fbdev->base); + drm_fb_helper_unregister_info(&fbdev->base); if (fbdev->fb) { struct tegra_bo *bo = tegra_fb_get_plane(fbdev->fb, 0); diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index b09b8ab40ae4..979e7bc902f6 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -694,6 +694,8 @@ static int tegra_gem_prime_mmap(struct dma_buf *buf, struct vm_area_struct *vma) struct drm_gem_object *gem = buf->priv; int err; + dma_resv_assert_held(buf->resv); + err = drm_gem_mmap_obj(gem, gem->size, vma); if (err < 0) return err; diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index bf240767dad9..40ec3e6cf204 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -867,14 +867,7 @@ static int tegra_hdmi_reconfigure_audio(struct tegra_hdmi *hdmi) static bool tegra_output_is_hdmi(struct tegra_output *output) { - struct edid *edid; - - if (!output->connector.edid_blob_ptr) - return false; - - edid = (struct edid *)output->connector.edid_blob_ptr->data; - - return drm_detect_hdmi_monitor(edid); + return output->connector.display_info.is_hdmi; } static enum drm_connector_status diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c index 276fe0472730..10fd21517281 100644 --- a/drivers/gpu/drm/tegra/nvdec.c +++ b/drivers/gpu/drm/tegra/nvdec.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2015-2021, NVIDIA Corporation. + * Copyright (c) 2015-2022, NVIDIA Corporation. */ #include <linux/clk.h> @@ -8,6 +8,7 @@ #include <linux/dma-mapping.h> #include <linux/host1x.h> #include <linux/iommu.h> +#include <linux/iopoll.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_device.h> @@ -16,18 +17,22 @@ #include <linux/pm_runtime.h> #include <linux/reset.h> -#include <soc/tegra/pmc.h> +#include <soc/tegra/mc.h> #include "drm.h" #include "falcon.h" +#include "riscv.h" #include "vic.h" +#define NVDEC_FALCON_DEBUGINFO 0x1094 #define NVDEC_TFBIF_TRANSCFG 0x2c44 struct nvdec_config { const char *firmware; unsigned int version; bool supports_sid; + bool has_riscv; + bool has_extra_clocks; }; struct nvdec { @@ -37,10 +42,16 @@ struct nvdec { struct tegra_drm_client client; struct host1x_channel *channel; struct device *dev; - struct clk *clk; + struct clk_bulk_data clks[3]; + unsigned int num_clks; + struct reset_control *reset; /* Platform configuration */ const struct nvdec_config *config; + + /* RISC-V specific data */ + struct tegra_drm_riscv riscv; + phys_addr_t carveout_base; }; static inline struct nvdec *to_nvdec(struct tegra_drm_client *client) @@ -54,7 +65,7 @@ static inline void nvdec_writel(struct nvdec *nvdec, u32 value, writel(value, nvdec->regs + offset); } -static int nvdec_boot(struct nvdec *nvdec) +static int nvdec_boot_falcon(struct nvdec *nvdec) { #ifdef CONFIG_IOMMU_API struct iommu_fwspec *spec = dev_iommu_fwspec_get(nvdec->dev); @@ -90,6 +101,64 @@ static int nvdec_boot(struct nvdec *nvdec) return 0; } +static int nvdec_wait_debuginfo(struct nvdec *nvdec, const char *phase) +{ + int err; + u32 val; + + err = readl_poll_timeout(nvdec->regs + NVDEC_FALCON_DEBUGINFO, val, val == 0x0, 10, 100000); + if (err) { + dev_err(nvdec->dev, "failed to boot %s, debuginfo=0x%x\n", phase, val); + return err; + } + + return 0; +} + +static int nvdec_boot_riscv(struct nvdec *nvdec) +{ + int err; + + err = reset_control_acquire(nvdec->reset); + if (err) + return err; + + nvdec_writel(nvdec, 0xabcd1234, NVDEC_FALCON_DEBUGINFO); + + err = tegra_drm_riscv_boot_bootrom(&nvdec->riscv, nvdec->carveout_base, 1, + &nvdec->riscv.bl_desc); + if (err) { + dev_err(nvdec->dev, "failed to execute bootloader\n"); + goto release_reset; + } + + err = nvdec_wait_debuginfo(nvdec, "bootloader"); + if (err) + goto release_reset; + + err = reset_control_reset(nvdec->reset); + if (err) + goto release_reset; + + nvdec_writel(nvdec, 0xabcd1234, NVDEC_FALCON_DEBUGINFO); + + err = tegra_drm_riscv_boot_bootrom(&nvdec->riscv, nvdec->carveout_base, 1, + &nvdec->riscv.os_desc); + if (err) { + dev_err(nvdec->dev, "failed to execute firmware\n"); + goto release_reset; + } + + err = nvdec_wait_debuginfo(nvdec, "firmware"); + if (err) + goto release_reset; + +release_reset: + reset_control_release(nvdec->reset); + + return err; +} + static int nvdec_init(struct host1x_client *client) { struct tegra_drm_client *drm = host1x_to_drm_client(client); @@ -189,7 +258,7 @@ static const struct host1x_client_ops nvdec_client_ops = { .exit = nvdec_exit, }; -static int nvdec_load_firmware(struct nvdec *nvdec) +static int nvdec_load_falcon_firmware(struct nvdec *nvdec) { struct host1x_client *client = &nvdec->client.base; struct tegra_drm *tegra = nvdec->client.drm; @@ -252,30 +321,35 @@ cleanup: return err; } - static __maybe_unused int nvdec_runtime_resume(struct device *dev) { struct nvdec *nvdec = dev_get_drvdata(dev); int err; - err = clk_prepare_enable(nvdec->clk); + err = clk_bulk_prepare_enable(nvdec->num_clks, nvdec->clks); if (err < 0) return err; usleep_range(10, 20); - err = nvdec_load_firmware(nvdec); - if (err < 0) - goto disable; + if (nvdec->config->has_riscv) { + err = nvdec_boot_riscv(nvdec); + if (err < 0) + goto disable; + } else { + err = nvdec_load_falcon_firmware(nvdec); + if (err < 0) + goto disable; - err = nvdec_boot(nvdec); - if (err < 0) - goto disable; + err = nvdec_boot_falcon(nvdec); + if (err < 0) + goto disable; + } return 0; disable: - clk_disable_unprepare(nvdec->clk); + clk_bulk_disable_unprepare(nvdec->num_clks, nvdec->clks); return err; } @@ -285,7 +359,7 @@ static __maybe_unused int nvdec_runtime_suspend(struct device *dev) host1x_channel_stop(nvdec->channel); - clk_disable_unprepare(nvdec->clk); + clk_bulk_disable_unprepare(nvdec->num_clks, nvdec->clks); return 0; } @@ -346,10 +420,18 @@ static const struct nvdec_config nvdec_t194_config = { .supports_sid = true, }; +static const struct nvdec_config nvdec_t234_config = { + .version = 0x23, + .supports_sid = true, + .has_riscv = true, + .has_extra_clocks = true, +}; + static const struct of_device_id tegra_nvdec_of_match[] = { { .compatible = "nvidia,tegra210-nvdec", .data = &nvdec_t210_config }, { .compatible = "nvidia,tegra186-nvdec", .data = &nvdec_t186_config }, { .compatible = "nvidia,tegra194-nvdec", .data = &nvdec_t194_config }, + { .compatible = "nvidia,tegra234-nvdec", .data = &nvdec_t234_config }, { }, }; MODULE_DEVICE_TABLE(of, tegra_nvdec_of_match); @@ -383,13 +465,22 @@ static int nvdec_probe(struct platform_device *pdev) if (IS_ERR(nvdec->regs)) return PTR_ERR(nvdec->regs); - nvdec->clk = devm_clk_get(dev, NULL); - if (IS_ERR(nvdec->clk)) { - dev_err(&pdev->dev, "failed to get clock\n"); - return PTR_ERR(nvdec->clk); + nvdec->clks[0].id = "nvdec"; + nvdec->num_clks = 1; + + if (nvdec->config->has_extra_clocks) { + nvdec->num_clks = 3; + nvdec->clks[1].id = "fuse"; + nvdec->clks[2].id = "tsec_pka"; } - err = clk_set_rate(nvdec->clk, ULONG_MAX); + err = devm_clk_bulk_get(dev, nvdec->num_clks, nvdec->clks); + if (err) { + dev_err(&pdev->dev, "failed to get clock(s)\n"); + return err; + } + + err = clk_set_rate(nvdec->clks[0].clk, ULONG_MAX); if (err < 0) { dev_err(&pdev->dev, "failed to set clock rate\n"); return err; @@ -399,12 +490,42 @@ static int nvdec_probe(struct platform_device *pdev) if (err < 0) host_class = HOST1X_CLASS_NVDEC; - nvdec->falcon.dev = dev; - nvdec->falcon.regs = nvdec->regs; + if (nvdec->config->has_riscv) { + struct tegra_mc *mc; - err = falcon_init(&nvdec->falcon); - if (err < 0) - return err; + mc = devm_tegra_memory_controller_get(dev); + if (IS_ERR(mc)) { + dev_err_probe(dev, PTR_ERR(mc), + "failed to get memory controller handle\n"); + return PTR_ERR(mc); + } + + err = tegra_mc_get_carveout_info(mc, 1, &nvdec->carveout_base, NULL); + if (err) { + dev_err(dev, "failed to get carveout info: %d\n", err); + return err; + } + + nvdec->reset = devm_reset_control_get_exclusive_released(dev, "nvdec"); + if (IS_ERR(nvdec->reset)) { + dev_err_probe(dev, PTR_ERR(nvdec->reset), "failed to get reset\n"); + return PTR_ERR(nvdec->reset); + } + + nvdec->riscv.dev = dev; + nvdec->riscv.regs = nvdec->regs; + + err = tegra_drm_riscv_read_descriptors(&nvdec->riscv); + if (err < 0) + return err; + } else { + nvdec->falcon.dev = dev; + nvdec->falcon.regs = nvdec->regs; + + err = falcon_init(&nvdec->falcon); + if (err < 0) + return err; + } platform_set_drvdata(pdev, nvdec); diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 47d26b5d9945..a8925dcd7edd 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -133,11 +133,11 @@ int tegra_output_probe(struct tegra_output *output) } } - output->hpd_gpio = devm_gpiod_get_from_of_node(output->dev, - output->of_node, - "nvidia,hpd-gpio", 0, - GPIOD_IN, - "HDMI hotplug detect"); + output->hpd_gpio = devm_fwnode_gpiod_get(output->dev, + of_fwnode_handle(output->of_node), + "nvidia,hpd", + GPIOD_IN, + "HDMI hotplug detect"); if (IS_ERR(output->hpd_gpio)) { if (PTR_ERR(output->hpd_gpio) != -ENOENT) return PTR_ERR(output->hpd_gpio); diff --git a/drivers/gpu/drm/tegra/riscv.c b/drivers/gpu/drm/tegra/riscv.c new file mode 100644 index 000000000000..6580416408f8 --- /dev/null +++ b/drivers/gpu/drm/tegra/riscv.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022, NVIDIA Corporation. + */ + +#include <linux/dev_printk.h> +#include <linux/device.h> +#include <linux/iopoll.h> +#include <linux/of.h> + +#include "riscv.h" + +#define RISCV_CPUCTL 0x4388 +#define RISCV_CPUCTL_STARTCPU_TRUE (1 << 0) +#define RISCV_BR_RETCODE 0x465c +#define RISCV_BR_RETCODE_RESULT_V(x) ((x) & 0x3) +#define RISCV_BR_RETCODE_RESULT_PASS_V 3 +#define RISCV_BCR_CTRL 0x4668 +#define RISCV_BCR_CTRL_CORE_SELECT_RISCV (1 << 4) +#define RISCV_BCR_DMACFG 0x466c +#define RISCV_BCR_DMACFG_TARGET_LOCAL_FB (0 << 0) +#define RISCV_BCR_DMACFG_LOCK_LOCKED (1 << 31) +#define RISCV_BCR_DMAADDR_PKCPARAM_LO 0x4670 +#define RISCV_BCR_DMAADDR_PKCPARAM_HI 0x4674 +#define RISCV_BCR_DMAADDR_FMCCODE_LO 0x4678 +#define RISCV_BCR_DMAADDR_FMCCODE_HI 0x467c +#define RISCV_BCR_DMAADDR_FMCDATA_LO 0x4680 +#define RISCV_BCR_DMAADDR_FMCDATA_HI 0x4684 +#define RISCV_BCR_DMACFG_SEC 0x4694 +#define RISCV_BCR_DMACFG_SEC_GSCID(v) ((v) << 16) + +static void riscv_writel(struct tegra_drm_riscv *riscv, u32 value, u32 offset) +{ + writel(value, riscv->regs + offset); +} + +int tegra_drm_riscv_read_descriptors(struct tegra_drm_riscv *riscv) +{ + struct tegra_drm_riscv_descriptor *bl = &riscv->bl_desc; + struct tegra_drm_riscv_descriptor *os = &riscv->os_desc; + const struct device_node *np = riscv->dev->of_node; + int err; + +#define READ_PROP(name, location) \ + err = of_property_read_u32(np, name, location); \ + if (err) { \ + dev_err(riscv->dev, "failed to read " name ": %d\n", err); \ + return err; \ + } + + READ_PROP("nvidia,bl-manifest-offset", &bl->manifest_offset); + READ_PROP("nvidia,bl-code-offset", &bl->code_offset); + READ_PROP("nvidia,bl-data-offset", &bl->data_offset); + READ_PROP("nvidia,os-manifest-offset", &os->manifest_offset); + READ_PROP("nvidia,os-code-offset", &os->code_offset); + READ_PROP("nvidia,os-data-offset", &os->data_offset); +#undef READ_PROP + + if (bl->manifest_offset == 0 && bl->code_offset == 0 && + bl->data_offset == 0 && os->manifest_offset == 0 && + os->code_offset == 0 && os->data_offset == 0) { + dev_err(riscv->dev, "descriptors not available\n"); + return -EINVAL; + } + + return 0; +} + +int tegra_drm_riscv_boot_bootrom(struct tegra_drm_riscv *riscv, phys_addr_t image_address, + u32 gscid, const struct tegra_drm_riscv_descriptor *desc) +{ + phys_addr_t addr; + int err; + u32 val; + + riscv_writel(riscv, RISCV_BCR_CTRL_CORE_SELECT_RISCV, RISCV_BCR_CTRL); + + addr = image_address + desc->manifest_offset; + riscv_writel(riscv, lower_32_bits(addr >> 8), RISCV_BCR_DMAADDR_PKCPARAM_LO); + riscv_writel(riscv, upper_32_bits(addr >> 8), RISCV_BCR_DMAADDR_PKCPARAM_HI); + + addr = image_address + desc->code_offset; + riscv_writel(riscv, lower_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCCODE_LO); + riscv_writel(riscv, upper_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCCODE_HI); + + addr = image_address + desc->data_offset; + riscv_writel(riscv, lower_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCDATA_LO); + riscv_writel(riscv, upper_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCDATA_HI); + + riscv_writel(riscv, RISCV_BCR_DMACFG_SEC_GSCID(gscid), RISCV_BCR_DMACFG_SEC); + riscv_writel(riscv, + RISCV_BCR_DMACFG_TARGET_LOCAL_FB | RISCV_BCR_DMACFG_LOCK_LOCKED, RISCV_BCR_DMACFG); + + riscv_writel(riscv, RISCV_CPUCTL_STARTCPU_TRUE, RISCV_CPUCTL); + + err = readl_poll_timeout( + riscv->regs + RISCV_BR_RETCODE, val, + RISCV_BR_RETCODE_RESULT_V(val) == RISCV_BR_RETCODE_RESULT_PASS_V, + 10, 100000); + if (err) { + dev_err(riscv->dev, "error during bootrom execution. BR_RETCODE=%d\n", val); + return err; + } + + return 0; +} diff --git a/drivers/gpu/drm/tegra/riscv.h b/drivers/gpu/drm/tegra/riscv.h new file mode 100644 index 000000000000..bbeb2db078b6 --- /dev/null +++ b/drivers/gpu/drm/tegra/riscv.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022, NVIDIA Corporation. + */ + +#ifndef DRM_TEGRA_RISCV_H +#define DRM_TEGRA_RISCV_H + +struct tegra_drm_riscv_descriptor { + u32 manifest_offset; + u32 code_offset; + u32 code_size; + u32 data_offset; + u32 data_size; +}; + +struct tegra_drm_riscv { + /* User initializes */ + struct device *dev; + void __iomem *regs; + + struct tegra_drm_riscv_descriptor bl_desc; + struct tegra_drm_riscv_descriptor os_desc; +}; + +int tegra_drm_riscv_read_descriptors(struct tegra_drm_riscv *riscv); +int tegra_drm_riscv_boot_bootrom(struct tegra_drm_riscv *riscv, phys_addr_t image_address, + u32 gscid, const struct tegra_drm_riscv_descriptor *desc); + +#endif diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c index b24738bdf3df..066f88564169 100644 --- a/drivers/gpu/drm/tegra/submit.c +++ b/drivers/gpu/drm/tegra/submit.c @@ -133,7 +133,7 @@ static void gather_bo_munmap(struct host1x_bo *host_bo, void *addr) { } -const struct host1x_bo_ops gather_bo_ops = { +static const struct host1x_bo_ops gather_bo_ops = { .get = gather_bo_get, .put = gather_bo_put, .pin = gather_bo_pin, @@ -169,14 +169,9 @@ static void *alloc_copy_user_array(void __user *from, size_t count, size_t size) if (copy_len > 0x4000) return ERR_PTR(-E2BIG); - data = kvmalloc(copy_len, GFP_KERNEL); - if (!data) - return ERR_PTR(-ENOMEM); - - if (copy_from_user(data, from, copy_len)) { - kvfree(data); - return ERR_PTR(-EFAULT); - } + data = vmemdup_user(from, copy_len); + if (IS_ERR(data)) + return ERR_CAST(data); return data; } diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index a98239cb0e29..5adab6b22916 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -116,7 +116,7 @@ int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_ if (supported) context->memory_context = host1x_memory_context_alloc( - host, get_task_pid(current, PIDTYPE_TGID)); + host, client->base.dev, get_task_pid(current, PIDTYPE_TGID)); if (IS_ERR(context->memory_context)) { if (PTR_ERR(context->memory_context) != -EOPNOTSUPP) { diff --git a/drivers/gpu/drm/tests/Makefile b/drivers/gpu/drm/tests/Makefile index 2d9f49b62ecb..b29ef1085cad 100644 --- a/drivers/gpu/drm/tests/Makefile +++ b/drivers/gpu/drm/tests/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_DRM_KUNIT_TEST) += \ drm_format_helper_test.o \ drm_format_test.o \ drm_framebuffer_test.o \ + drm_kunit_helpers.o \ drm_mm_test.o \ drm_plane_helper_test.o \ drm_rect_test.o diff --git a/drivers/gpu/drm/tests/drm_client_modeset_test.c b/drivers/gpu/drm/tests/drm_client_modeset_test.c new file mode 100644 index 000000000000..362a5fbd82f5 --- /dev/null +++ b/drivers/gpu/drm/tests/drm_client_modeset_test.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Maxime Ripard <mripard@kernel.org> + */ + +#include <kunit/test.h> + +#include <drm/drm_connector.h> +#include <drm/drm_edid.h> +#include <drm/drm_drv.h> +#include <drm/drm_modes.h> +#include <drm/drm_modeset_helper_vtables.h> +#include <drm/drm_probe_helper.h> + +#include "drm_kunit_helpers.h" + +struct drm_client_modeset_test_priv { + struct drm_device *drm; + struct drm_connector connector; +}; + +static int drm_client_modeset_connector_get_modes(struct drm_connector *connector) +{ + return drm_add_modes_noedid(connector, 1920, 1200); +} + +static const struct drm_connector_helper_funcs drm_client_modeset_connector_helper_funcs = { + .get_modes = drm_client_modeset_connector_get_modes, +}; + +static const struct drm_connector_funcs drm_client_modeset_connector_funcs = { +}; + +static int drm_client_modeset_test_init(struct kunit *test) +{ + struct drm_client_modeset_test_priv *priv; + int ret; + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, priv); + + test->priv = priv; + + priv->drm = drm_kunit_device_init(test, DRIVER_MODESET, "drm-client-modeset-test"); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv->drm); + + ret = drmm_connector_init(priv->drm, &priv->connector, + &drm_client_modeset_connector_funcs, + DRM_MODE_CONNECTOR_Unknown, + NULL); + KUNIT_ASSERT_EQ(test, ret, 0); + + drm_connector_helper_add(&priv->connector, &drm_client_modeset_connector_helper_funcs); + + return 0; +} + +static void drm_test_pick_cmdline_res_1920_1080_60(struct kunit *test) +{ + struct drm_client_modeset_test_priv *priv = test->priv; + struct drm_device *drm = priv->drm; + struct drm_connector *connector = &priv->connector; + struct drm_cmdline_mode *cmdline_mode = &connector->cmdline_mode; + struct drm_display_mode *expected_mode, *mode; + const char *cmdline = "1920x1080@60"; + int ret; + + expected_mode = drm_mode_find_dmt(priv->drm, 1920, 1080, 60, false); + KUNIT_ASSERT_NOT_NULL(test, expected_mode); + + KUNIT_ASSERT_TRUE(test, + drm_mode_parse_command_line_for_connector(cmdline, + connector, + cmdline_mode)); + + mutex_lock(&drm->mode_config.mutex); + ret = drm_helper_probe_single_connector_modes(connector, 1920, 1080); + mutex_unlock(&drm->mode_config.mutex); + KUNIT_ASSERT_GT(test, ret, 0); + + mode = drm_connector_pick_cmdline_mode(connector); + KUNIT_ASSERT_NOT_NULL(test, mode); + + KUNIT_EXPECT_TRUE(test, drm_mode_equal(expected_mode, mode)); +} + +static struct kunit_case drm_test_pick_cmdline_tests[] = { + KUNIT_CASE(drm_test_pick_cmdline_res_1920_1080_60), + {} +}; + +static struct kunit_suite drm_test_pick_cmdline_test_suite = { + .name = "drm_test_pick_cmdline", + .init = drm_client_modeset_test_init, + .test_cases = drm_test_pick_cmdline_tests +}; + +kunit_test_suite(drm_test_pick_cmdline_test_suite); diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c index 2191e57f2297..567c71f95edc 100644 --- a/drivers/gpu/drm/tests/drm_format_helper_test.c +++ b/drivers/gpu/drm/tests/drm_format_helper_test.c @@ -315,7 +315,7 @@ static void drm_test_fb_xrgb8888_to_gray8(struct kunit *test) iosys_map_set_vaddr(&src, xrgb8888); drm_fb_xrgb8888_to_gray8(&dst, &result->dst_pitch, &src, &fb, ¶ms->clip); - KUNIT_EXPECT_EQ(test, memcmp(buf, result->expected, dst_size), 0); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } static void drm_test_fb_xrgb8888_to_rgb332(struct kunit *test) @@ -345,7 +345,7 @@ static void drm_test_fb_xrgb8888_to_rgb332(struct kunit *test) iosys_map_set_vaddr(&src, xrgb8888); drm_fb_xrgb8888_to_rgb332(&dst, &result->dst_pitch, &src, &fb, ¶ms->clip); - KUNIT_EXPECT_EQ(test, memcmp(buf, result->expected, dst_size), 0); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } static void drm_test_fb_xrgb8888_to_rgb565(struct kunit *test) @@ -375,10 +375,10 @@ static void drm_test_fb_xrgb8888_to_rgb565(struct kunit *test) iosys_map_set_vaddr(&src, xrgb8888); drm_fb_xrgb8888_to_rgb565(&dst, &result->dst_pitch, &src, &fb, ¶ms->clip, false); - KUNIT_EXPECT_EQ(test, memcmp(buf, result->expected, dst_size), 0); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); drm_fb_xrgb8888_to_rgb565(&dst, &result->dst_pitch, &src, &fb, ¶ms->clip, true); - KUNIT_EXPECT_EQ(test, memcmp(buf, result->expected_swab, dst_size), 0); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected_swab, dst_size); } static void drm_test_fb_xrgb8888_to_rgb888(struct kunit *test) @@ -408,7 +408,7 @@ static void drm_test_fb_xrgb8888_to_rgb888(struct kunit *test) iosys_map_set_vaddr(&src, xrgb8888); drm_fb_xrgb8888_to_rgb888(&dst, &result->dst_pitch, &src, &fb, ¶ms->clip); - KUNIT_EXPECT_EQ(test, memcmp(buf, result->expected, dst_size), 0); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test) @@ -439,7 +439,7 @@ static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test) drm_fb_xrgb8888_to_xrgb2101010(&dst, &result->dst_pitch, &src, &fb, ¶ms->clip); buf = le32buf_to_cpu(test, buf, dst_size / sizeof(u32)); - KUNIT_EXPECT_EQ(test, memcmp(buf, result->expected, dst_size), 0); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } static struct kunit_case drm_format_helper_test_cases[] = { diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c new file mode 100644 index 000000000000..f1662091f250 --- /dev/null +++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <drm/drm_drv.h> +#include <drm/drm_managed.h> + +#include <kunit/resource.h> + +#include <linux/device.h> + +#include "drm_kunit_helpers.h" + +struct kunit_dev { + struct drm_device base; +}; + +static const struct drm_mode_config_funcs drm_mode_config_funcs = { +}; + +static int dev_init(struct kunit_resource *res, void *ptr) +{ + char *name = ptr; + struct device *dev; + + dev = root_device_register(name); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + res->data = dev; + return 0; +} + +static void dev_free(struct kunit_resource *res) +{ + struct device *dev = res->data; + + root_device_unregister(dev); +} + +struct drm_device *drm_kunit_device_init(struct kunit *test, u32 features, char *name) +{ + struct kunit_dev *kdev; + struct drm_device *drm; + struct drm_driver *driver; + struct device *dev; + int ret; + + dev = kunit_alloc_resource(test, dev_init, dev_free, GFP_KERNEL, name); + if (!dev) + return ERR_PTR(-ENOMEM); + + driver = kunit_kzalloc(test, sizeof(*driver), GFP_KERNEL); + if (!driver) + return ERR_PTR(-ENOMEM); + + driver->driver_features = features; + kdev = devm_drm_dev_alloc(dev, driver, struct kunit_dev, base); + if (IS_ERR(kdev)) + return ERR_CAST(kdev); + + drm = &kdev->base; + drm->mode_config.funcs = &drm_mode_config_funcs; + + ret = drmm_mode_config_init(drm); + if (ret) + return ERR_PTR(ret); + + return drm; +} + +MODULE_AUTHOR("Maxime Ripard <maxime@cerno.tech>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.h b/drivers/gpu/drm/tests/drm_kunit_helpers.h new file mode 100644 index 000000000000..20ab6eec4c89 --- /dev/null +++ b/drivers/gpu/drm/tests/drm_kunit_helpers.h @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef DRM_KUNIT_HELPERS_H_ +#define DRM_KUNIT_HELPERS_H_ + +struct drm_device; +struct kunit; + +struct drm_device *drm_kunit_device_init(struct kunit *test, u32 features, char *name); + +#endif // DRM_KUNIT_HELPERS_H_ diff --git a/drivers/gpu/drm/tidss/tidss_drv.c b/drivers/gpu/drm/tidss/tidss_drv.c index 15cd9b91b7e2..07d94b1e8089 100644 --- a/drivers/gpu/drm/tidss/tidss_drv.c +++ b/drivers/gpu/drm/tidss/tidss_drv.c @@ -14,7 +14,7 @@ #include <drm/drm_crtc.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/tidss/tidss_kms.c b/drivers/gpu/drm/tidss/tidss_kms.c index afb2879980c6..345bcc3011e4 100644 --- a/drivers/gpu/drm/tidss/tidss_kms.c +++ b/drivers/gpu/drm/tidss/tidss_kms.c @@ -10,7 +10,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> #include <drm/drm_crtc_helper.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_of.h> #include <drm/drm_panel.h> diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index f72755b8ea14..80615ecdae0b 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -16,7 +16,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_debugfs.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index a300b03a3c7a..f6889f649bc1 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -53,7 +53,7 @@ config DRM_GM12U320 config DRM_OFDRM tristate "Open Firmware display driver" - depends on DRM && OF && (PPC || COMPILE_TEST) + depends on DRM && MMU && OF && (PPC || COMPILE_TEST) select APERTURE_HELPERS select DRM_GEM_SHMEM_HELPER select DRM_KMS_HELPER diff --git a/drivers/gpu/drm/tiny/arcpgu.c b/drivers/gpu/drm/tiny/arcpgu.c index bb302a3fd6b5..611bbee15071 100644 --- a/drivers/gpu/drm/tiny/arcpgu.c +++ b/drivers/gpu/drm/tiny/arcpgu.c @@ -12,7 +12,7 @@ #include <drm/drm_drv.h> #include <drm/drm_edid.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_dma_helper.h> diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 04682f831544..024346054c70 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -7,7 +7,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_framebuffer_helper.h> diff --git a/drivers/gpu/drm/tiny/cirrus.c b/drivers/gpu/drm/tiny/cirrus.c index 354d5e854a6f..678c2ef1cae7 100644 --- a/drivers/gpu/drm/tiny/cirrus.c +++ b/drivers/gpu/drm/tiny/cirrus.c @@ -30,7 +30,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_drv.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include <drm/drm_format_helper.h> #include <drm/drm_fourcc.h> diff --git a/drivers/gpu/drm/tiny/gm12u320.c b/drivers/gpu/drm/tiny/gm12u320.c index 7441d992a5d7..130fd07a967d 100644 --- a/drivers/gpu/drm/tiny/gm12u320.c +++ b/drivers/gpu/drm/tiny/gm12u320.c @@ -12,7 +12,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_drv.h> #include <drm/drm_edid.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include <drm/drm_format_helper.h> #include <drm/drm_fourcc.h> diff --git a/drivers/gpu/drm/tiny/hx8357d.c b/drivers/gpu/drm/tiny/hx8357d.c index 48c24aa8c28a..9f634f720817 100644 --- a/drivers/gpu/drm/tiny/hx8357d.c +++ b/drivers/gpu/drm/tiny/hx8357d.c @@ -18,7 +18,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/tiny/ili9163.c b/drivers/gpu/drm/tiny/ili9163.c index 9a1a5943bee0..ca0451f79962 100644 --- a/drivers/gpu/drm/tiny/ili9163.c +++ b/drivers/gpu/drm/tiny/ili9163.c @@ -9,7 +9,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_mipi_dbi.h> diff --git a/drivers/gpu/drm/tiny/ili9225.c b/drivers/gpu/drm/tiny/ili9225.c index a79da2b4af64..815bab285823 100644 --- a/drivers/gpu/drm/tiny/ili9225.c +++ b/drivers/gpu/drm/tiny/ili9225.c @@ -20,7 +20,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> diff --git a/drivers/gpu/drm/tiny/ili9341.c b/drivers/gpu/drm/tiny/ili9341.c index 69b265e78096..420f6005a956 100644 --- a/drivers/gpu/drm/tiny/ili9341.c +++ b/drivers/gpu/drm/tiny/ili9341.c @@ -17,7 +17,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/tiny/ili9486.c b/drivers/gpu/drm/tiny/ili9486.c index c80028bb1d11..1bb847466b10 100644 --- a/drivers/gpu/drm/tiny/ili9486.c +++ b/drivers/gpu/drm/tiny/ili9486.c @@ -16,7 +16,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/tiny/mi0283qt.c b/drivers/gpu/drm/tiny/mi0283qt.c index bc522fb3d94d..47df2b5a3048 100644 --- a/drivers/gpu/drm/tiny/mi0283qt.c +++ b/drivers/gpu/drm/tiny/mi0283qt.c @@ -15,7 +15,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/tiny/ofdrm.c b/drivers/gpu/drm/tiny/ofdrm.c index 0e1cc2369afc..dc9e4d71b12a 100644 --- a/drivers/gpu/drm/tiny/ofdrm.c +++ b/drivers/gpu/drm/tiny/ofdrm.c @@ -11,7 +11,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_device.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_format_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> @@ -231,7 +231,7 @@ static u64 display_get_address_of(struct drm_device *dev, struct device_node *of return address; } -static bool is_avivo(__be32 vendor, __be32 device) +static bool is_avivo(u32 vendor, u32 device) { /* This will match most R5xx */ return (vendor == PCI_VENDOR_ID_ATI) && @@ -265,8 +265,13 @@ static enum ofdrm_model display_get_model_of(struct drm_device *dev, struct devi of_parent = of_get_parent(of_node); vendor_p = of_get_property(of_parent, "vendor-id", NULL); device_p = of_get_property(of_parent, "device-id", NULL); - if (vendor_p && device_p && is_avivo(*vendor_p, *device_p)) - model = OFDRM_MODEL_AVIVO; + if (vendor_p && device_p) { + u32 vendor = be32_to_cpup(vendor_p); + u32 device = be32_to_cpup(device_p); + + if (is_avivo(vendor, device)) + model = OFDRM_MODEL_AVIVO; + } of_node_put(of_parent); } else if (of_device_is_compatible(of_node, "qemu,std-vga")) { model = OFDRM_MODEL_QEMU; @@ -433,21 +438,21 @@ static void __iomem *get_cmap_address_of(struct ofdrm_device *odev, struct devic if (!addr_p) addr_p = of_get_address(of_node, bar_no, &max_size, &flags); if (!addr_p) - return ERR_PTR(-ENODEV); + return IOMEM_ERR_PTR(-ENODEV); if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0) - return ERR_PTR(-ENODEV); + return IOMEM_ERR_PTR(-ENODEV); if ((offset + size) >= max_size) - return ERR_PTR(-ENODEV); + return IOMEM_ERR_PTR(-ENODEV); address = of_translate_address(of_node, addr_p); if (address == OF_BAD_ADDR) - return ERR_PTR(-ENODEV); + return IOMEM_ERR_PTR(-ENODEV); mem = devm_ioremap(dev->dev, address + offset, size); if (!mem) - return ERR_PTR(-ENOMEM); + return IOMEM_ERR_PTR(-ENOMEM); return mem; } @@ -465,7 +470,7 @@ static void __iomem *ofdrm_mach64_cmap_ioremap(struct ofdrm_device *odev, cmap_base = devm_ioremap(dev->dev, address, 0x1000); if (!cmap_base) - return ERR_PTR(-ENOMEM); + return IOMEM_ERR_PTR(-ENOMEM); return cmap_base; } @@ -624,11 +629,11 @@ static void __iomem *ofdrm_qemu_cmap_ioremap(struct ofdrm_device *odev, address = of_translate_address(of_node, io_of_addr); if (address == OF_BAD_ADDR) - return ERR_PTR(-ENODEV); + return IOMEM_ERR_PTR(-ENODEV); cmap_base = devm_ioremap(dev->dev, address + 0x3c8, 2); if (!cmap_base) - return ERR_PTR(-ENOMEM); + return IOMEM_ERR_PTR(-ENOMEM); return cmap_base; } diff --git a/drivers/gpu/drm/tiny/panel-mipi-dbi.c b/drivers/gpu/drm/tiny/panel-mipi-dbi.c index 955a61d628e7..03a7d569cd56 100644 --- a/drivers/gpu/drm/tiny/panel-mipi-dbi.c +++ b/drivers/gpu/drm/tiny/panel-mipi-dbi.c @@ -16,7 +16,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c index e62f4d16b2c6..c2677d081a7b 100644 --- a/drivers/gpu/drm/tiny/repaper.c +++ b/drivers/gpu/drm/tiny/repaper.c @@ -26,7 +26,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_format_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c index cbb100753154..162eb44dcba8 100644 --- a/drivers/gpu/drm/tiny/simpledrm.c +++ b/drivers/gpu/drm/tiny/simpledrm.c @@ -15,7 +15,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_device.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_format_helper.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_framebuffer_helper.h> diff --git a/drivers/gpu/drm/tiny/st7586.c b/drivers/gpu/drm/tiny/st7586.c index b6f620b902e6..ce57fa9917e5 100644 --- a/drivers/gpu/drm/tiny/st7586.c +++ b/drivers/gpu/drm/tiny/st7586.c @@ -16,7 +16,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fb_dma_helper.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_format_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> diff --git a/drivers/gpu/drm/tiny/st7735r.c b/drivers/gpu/drm/tiny/st7735r.c index c36ba08acda1..15d9cf283c66 100644 --- a/drivers/gpu/drm/tiny/st7735r.c +++ b/drivers/gpu/drm/tiny/st7735r.c @@ -18,7 +18,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 21b61631f73a..9f6764bf3b15 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -344,6 +344,28 @@ static unsigned int ttm_pool_page_order(struct ttm_pool *pool, struct page *p) return p->private; } +/* Called when we got a page, either from a pool or newly allocated */ +static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order, + struct page *p, dma_addr_t **dma_addr, + unsigned long *num_pages, + struct page ***pages) +{ + unsigned int i; + int r; + + if (*dma_addr) { + r = ttm_pool_map(pool, order, p, dma_addr); + if (r) + return r; + } + + *num_pages -= 1 << order; + for (i = 1 << order; i; --i, ++(*pages), ++p) + **pages = p; + + return 0; +} + /** * ttm_pool_alloc - Fill a ttm_tt object * @@ -385,45 +407,57 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages)); num_pages; order = min_t(unsigned int, order, __fls(num_pages))) { - bool apply_caching = false; struct ttm_pool_type *pt; pt = ttm_pool_select_type(pool, tt->caching, order); p = pt ? ttm_pool_type_take(pt) : NULL; if (p) { - apply_caching = true; - } else { - p = ttm_pool_alloc_page(pool, gfp_flags, order); - if (p && PageHighMem(p)) - apply_caching = true; - } - - if (!p) { - if (order) { - --order; - continue; - } - r = -ENOMEM; - goto error_free_all; - } - - if (apply_caching) { r = ttm_pool_apply_caching(caching, pages, tt->caching); if (r) goto error_free_page; - caching = pages + (1 << order); + + do { + r = ttm_pool_page_allocated(pool, order, p, + &dma_addr, + &num_pages, + &pages); + if (r) + goto error_free_page; + + if (num_pages < (1 << order)) + break; + + p = ttm_pool_type_take(pt); + } while (p); + caching = pages; } - if (dma_addr) { - r = ttm_pool_map(pool, order, p, &dma_addr); + while (num_pages >= (1 << order) && + (p = ttm_pool_alloc_page(pool, gfp_flags, order))) { + + if (PageHighMem(p)) { + r = ttm_pool_apply_caching(caching, pages, + tt->caching); + if (r) + goto error_free_page; + } + r = ttm_pool_page_allocated(pool, order, p, &dma_addr, + &num_pages, &pages); if (r) goto error_free_page; + if (PageHighMem(p)) + caching = pages; } - num_pages -= 1 << order; - for (i = 1 << order; i; --i) - *(pages++) = p++; + if (!p) { + if (order) { + --order; + continue; + } + r = -ENOMEM; + goto error_free_all; + } } r = ttm_pool_apply_caching(caching, pages, tt->caching); diff --git a/drivers/gpu/drm/tve200/tve200_drv.c b/drivers/gpu/drm/tve200/tve200_drv.c index 04db72e3fa9c..0d05c386d303 100644 --- a/drivers/gpu/drm/tve200/tve200_drv.c +++ b/drivers/gpu/drm/tve200/tve200_drv.c @@ -32,6 +32,7 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/shmem_fs.h> #include <linux/slab.h> @@ -39,7 +40,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_dma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c index 91effdcefb6d..e81352126a0f 100644 --- a/drivers/gpu/drm/udl/udl_drv.c +++ b/drivers/gpu/drm/udl/udl_drv.c @@ -7,7 +7,7 @@ #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_managed.h> diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index e8c975b81585..478f1f0f60de 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -22,7 +22,6 @@ #include <linux/reset.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_managed.h> #include <uapi/drm/v3d_drm.h> diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index b8980440d137..96af1cb5202a 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -10,6 +10,7 @@ #include <linux/sched/signal.h> #include <linux/uaccess.h> +#include <drm/drm_managed.h> #include <drm/drm_syncobj.h> #include <uapi/drm/v3d_drm.h> @@ -1075,10 +1076,18 @@ v3d_gem_init(struct drm_device *dev) spin_lock_init(&v3d->mm_lock); spin_lock_init(&v3d->job_lock); - mutex_init(&v3d->bo_lock); - mutex_init(&v3d->reset_lock); - mutex_init(&v3d->sched_lock); - mutex_init(&v3d->cache_clean_lock); + ret = drmm_mutex_init(dev, &v3d->bo_lock); + if (ret) + return ret; + ret = drmm_mutex_init(dev, &v3d->reset_lock); + if (ret) + return ret; + ret = drmm_mutex_init(dev, &v3d->sched_lock); + if (ret) + return ret; + ret = drmm_mutex_init(dev, &v3d->cache_clean_lock); + if (ret) + return ret; /* Note: We don't allocate address 0. Various bits of HW * treat 0 as special, such as the occlusion query counters diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c index 48aaaa972c49..e1be7368b87d 100644 --- a/drivers/gpu/drm/v3d/v3d_perfmon.c +++ b/drivers/gpu/drm/v3d/v3d_perfmon.c @@ -17,8 +17,10 @@ void v3d_perfmon_get(struct v3d_perfmon *perfmon) void v3d_perfmon_put(struct v3d_perfmon *perfmon) { - if (perfmon && refcount_dec_and_test(&perfmon->refcnt)) + if (perfmon && refcount_dec_and_test(&perfmon->refcnt)) { + mutex_destroy(&perfmon->lock); kfree(perfmon); + } } void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon) @@ -113,6 +115,7 @@ void v3d_perfmon_close_file(struct v3d_file_priv *v3d_priv) idr_for_each(&v3d_priv->perfmon.idr, v3d_perfmon_idr_del, NULL); idr_destroy(&v3d_priv->perfmon.idr); mutex_unlock(&v3d_priv->perfmon.lock); + mutex_destroy(&v3d_priv->perfmon.lock); } int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data, @@ -154,6 +157,7 @@ int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data, mutex_unlock(&v3d_priv->perfmon.lock); if (ret < 0) { + mutex_destroy(&perfmon->lock); kfree(perfmon); return ret; } diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c index f4f2bd79a7cb..b450f449a3ab 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.c +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c @@ -14,7 +14,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include <drm/drm_ioctl.h> #include <drm/drm_managed.h> @@ -178,8 +178,6 @@ static const struct drm_driver driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, - .lastclose = drm_fb_helper_lastclose, - .fops = &vbox_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, diff --git a/drivers/gpu/drm/vboxvideo/vbox_main.c b/drivers/gpu/drm/vboxvideo/vbox_main.c index c9e8b3a63c62..3b83e550f4df 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_main.c +++ b/drivers/gpu/drm/vboxvideo/vbox_main.c @@ -11,7 +11,6 @@ #include <linux/pci.h> #include <linux/vbox_err.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_damage_helper.h> diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 2027063fdc30..5990d8f8c363 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -33,7 +33,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_vblank.h> #include <soc/bcm2835/raspberrypi-firmware.h> @@ -476,7 +476,12 @@ static int __init vc4_drm_register(void) if (ret) return ret; - return platform_driver_register(&vc4_platform_driver); + ret = platform_driver_register(&vc4_platform_driver); + if (ret) + platform_unregister_drivers(component_drivers, + ARRAY_SIZE(component_drivers)); + + return ret; } static void __exit vc4_drm_unregister(void) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 0d78c800ed51..12a00d644b61 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -124,9 +124,8 @@ static unsigned long long vc4_hdmi_encoder_compute_mode_clock(const struct drm_display_mode *mode, unsigned int bpc, enum vc4_hdmi_output_format fmt); -static bool vc4_hdmi_supports_scrambling(struct drm_encoder *encoder) +static bool vc4_hdmi_supports_scrambling(struct vc4_hdmi *vc4_hdmi) { - struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); struct drm_display_info *display = &vc4_hdmi->connector.display_info; lockdep_assert_held(&vc4_hdmi->mutex); @@ -319,9 +318,8 @@ out: static int vc4_hdmi_reset_link(struct drm_connector *connector, struct drm_modeset_acquire_ctx *ctx) { - struct drm_device *drm = connector->dev; - struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); - struct drm_encoder *encoder = &vc4_hdmi->encoder.base; + struct drm_device *drm; + struct vc4_hdmi *vc4_hdmi; struct drm_connector_state *conn_state; struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; @@ -332,6 +330,7 @@ static int vc4_hdmi_reset_link(struct drm_connector *connector, if (!connector) return 0; + drm = connector->dev; ret = drm_modeset_lock(&drm->mode_config.connection_mutex, ctx); if (ret) return ret; @@ -349,27 +348,41 @@ static int vc4_hdmi_reset_link(struct drm_connector *connector, if (!crtc_state->active) return 0; - if (!vc4_hdmi_supports_scrambling(encoder)) + vc4_hdmi = connector_to_vc4_hdmi(connector); + mutex_lock(&vc4_hdmi->mutex); + + if (!vc4_hdmi_supports_scrambling(vc4_hdmi)) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } scrambling_needed = vc4_hdmi_mode_needs_scrambling(&vc4_hdmi->saved_adjusted_mode, vc4_hdmi->output_bpc, vc4_hdmi->output_format); - if (!scrambling_needed) + if (!scrambling_needed) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } if (conn_state->commit && - !try_wait_for_completion(&conn_state->commit->hw_done)) + !try_wait_for_completion(&conn_state->commit->hw_done)) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } ret = drm_scdc_readb(connector->ddc, SCDC_TMDS_CONFIG, &config); if (ret < 0) { drm_err(drm, "Failed to read TMDS config: %d\n", ret); + mutex_unlock(&vc4_hdmi->mutex); return 0; } - if (!!(config & SCDC_SCRAMBLING_ENABLE) == scrambling_needed) + if (!!(config & SCDC_SCRAMBLING_ENABLE) == scrambling_needed) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } + + mutex_unlock(&vc4_hdmi->mutex); /* * HDMI 2.0 says that one should not send scrambled data @@ -397,9 +410,8 @@ static void vc4_hdmi_handle_hotplug(struct vc4_hdmi *vc4_hdmi, * .adap_enable, which leads to that funtion being called with * our mutex held. * - * A similar situation occurs with - * drm_atomic_helper_connector_hdmi_reset_link() that will call - * into our KMS hooks if the scrambling was enabled. + * A similar situation occurs with vc4_hdmi_reset_link() that + * will call into our KMS hooks if the scrambling was enabled. * * Concurrency isn't an issue at the moment since we don't share * any state with any of the other frameworks so we can ignore @@ -867,7 +879,7 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder) lockdep_assert_held(&vc4_hdmi->mutex); - if (!vc4_hdmi_supports_scrambling(encoder)) + if (!vc4_hdmi_supports_scrambling(vc4_hdmi)) return; if (!vc4_hdmi_mode_needs_scrambling(mode, @@ -3169,9 +3181,16 @@ static int vc4_hdmi_init_resources(struct drm_device *drm, DRM_ERROR("Failed to get HDMI state machine clock\n"); return PTR_ERR(vc4_hdmi->hsm_clock); } + vc4_hdmi->audio_clock = vc4_hdmi->hsm_clock; vc4_hdmi->cec_clock = vc4_hdmi->hsm_clock; + vc4_hdmi->hsm_rpm_clock = devm_clk_get(dev, "hdmi"); + if (IS_ERR(vc4_hdmi->hsm_rpm_clock)) { + DRM_ERROR("Failed to get HDMI state machine clock\n"); + return PTR_ERR(vc4_hdmi->hsm_rpm_clock); + } + return 0; } @@ -3254,6 +3273,12 @@ static int vc5_hdmi_init_resources(struct drm_device *drm, return PTR_ERR(vc4_hdmi->hsm_clock); } + vc4_hdmi->hsm_rpm_clock = devm_clk_get(dev, "hdmi"); + if (IS_ERR(vc4_hdmi->hsm_rpm_clock)) { + DRM_ERROR("Failed to get HDMI state machine clock\n"); + return PTR_ERR(vc4_hdmi->hsm_rpm_clock); + } + vc4_hdmi->pixel_bvb_clock = devm_clk_get(dev, "bvb"); if (IS_ERR(vc4_hdmi->pixel_bvb_clock)) { DRM_ERROR("Failed to get pixel bvb clock\n"); @@ -3317,7 +3342,7 @@ static int vc4_hdmi_runtime_suspend(struct device *dev) { struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); - clk_disable_unprepare(vc4_hdmi->hsm_clock); + clk_disable_unprepare(vc4_hdmi->hsm_rpm_clock); return 0; } @@ -3335,11 +3360,11 @@ static int vc4_hdmi_runtime_resume(struct device *dev) * its frequency while the power domain is active so that it * keeps its rate. */ - ret = clk_set_min_rate(vc4_hdmi->hsm_clock, HSM_MIN_CLOCK_FREQ); + ret = clk_set_min_rate(vc4_hdmi->hsm_rpm_clock, HSM_MIN_CLOCK_FREQ); if (ret) return ret; - ret = clk_prepare_enable(vc4_hdmi->hsm_clock); + ret = clk_prepare_enable(vc4_hdmi->hsm_rpm_clock); if (ret) return ret; @@ -3352,7 +3377,7 @@ static int vc4_hdmi_runtime_resume(struct device *dev) * case, it will lead to a silent CPU stall. Let's make sure we * prevent such a case. */ - rate = clk_get_rate(vc4_hdmi->hsm_clock); + rate = clk_get_rate(vc4_hdmi->hsm_rpm_clock); if (!rate) { ret = -EINVAL; goto err_disable_clk; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index e3619836ca17..dc3ccd8002a0 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -164,6 +164,7 @@ struct vc4_hdmi { struct clk *cec_clock; struct clk *pixel_clock; struct clk *hsm_clock; + struct clk *hsm_rpm_clock; struct clk *audio_clock; struct clk *pixel_bvb_clock; diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 5c97642ed66a..8fbeecdf2ec4 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -197,8 +197,8 @@ vc4_hvs_get_new_global_state(struct drm_atomic_state *state) struct drm_private_state *priv_state; priv_state = drm_atomic_get_new_private_obj_state(state, &vc4->hvs_channels); - if (IS_ERR(priv_state)) - return ERR_CAST(priv_state); + if (!priv_state) + return ERR_PTR(-EINVAL); return to_vc4_hvs_state(priv_state); } @@ -210,8 +210,8 @@ vc4_hvs_get_old_global_state(struct drm_atomic_state *state) struct drm_private_state *priv_state; priv_state = drm_atomic_get_old_private_obj_state(state, &vc4->hvs_channels); - if (IS_ERR(priv_state)) - return ERR_CAST(priv_state); + if (!priv_state) + return ERR_PTR(-EINVAL); return to_vc4_hvs_state(priv_state); } diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 0035affc3e59..ae97b98750b6 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -35,6 +35,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include "virtgpu_drv.h" diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 9b98470593b0..b7a64c7dcc2c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -35,7 +35,6 @@ #include <drm/drm_atomic.h> #include <drm/drm_drv.h> #include <drm/drm_encoder.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem.h> diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 0ffe5f0e33f7..293dbca50c31 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -17,7 +17,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_file.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_ioctl.h> diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 63496773f714..bd02cb0e6837 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -35,7 +35,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_drv.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_gem_ttm_helper.h> #include <drm/drm_ioctl.h> #include <drm/drm_module.h> diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 06d9e106e3c5..e76976a95a1e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -1097,21 +1097,21 @@ int vmw_mksstat_add_ioctl(struct drm_device *dev, void *data, reset_ppn_array(pdesc->strsPPNs, ARRAY_SIZE(pdesc->strsPPNs)); /* Pin mksGuestStat user pages and store those in the instance descriptor */ - nr_pinned_stat = pin_user_pages(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat, NULL); + nr_pinned_stat = pin_user_pages_fast(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat); if (num_pages_stat != nr_pinned_stat) goto err_pin_stat; for (i = 0; i < num_pages_stat; ++i) pdesc->statPPNs[i] = page_to_pfn(pages_stat[i]); - nr_pinned_info = pin_user_pages(arg->info, num_pages_info, FOLL_LONGTERM, pages_info, NULL); + nr_pinned_info = pin_user_pages_fast(arg->info, num_pages_info, FOLL_LONGTERM, pages_info); if (num_pages_info != nr_pinned_info) goto err_pin_info; for (i = 0; i < num_pages_info; ++i) pdesc->infoPPNs[i] = page_to_pfn(pages_info[i]); - nr_pinned_strs = pin_user_pages(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs, NULL); + nr_pinned_strs = pin_user_pages_fast(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs); if (num_pages_strs != nr_pinned_strs) goto err_pin_strs; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 8db61c541a80..e1f36a09c59c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -926,6 +926,10 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv) struct drm_device *dev = &dev_priv->drm; int i; + /* Screen objects won't work if GMR's aren't available */ + if (!dev_priv->has_gmr) + return -ENOSYS; + if (!(dev_priv->capabilities & SVGA_CAP_SCREEN_OBJECT_2)) { return -ENOSYS; } diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index e31554d7139f..4c95ebcdcc2d 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -12,7 +12,6 @@ #include <linux/scatterlist.h> #include <linux/shmem_fs.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_gem.h> #include <drm/drm_prime.h> #include <drm/drm_probe_helper.h> diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c index 7c9ae167eac7..0a7b466446fb 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dp.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c @@ -1362,9 +1362,10 @@ static void zynqmp_dp_bridge_detach(struct drm_bridge *bridge) zynqmp_dp_aux_cleanup(dp); } -static int zynqmp_dp_bridge_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode) +static enum drm_mode_status +zynqmp_dp_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) { struct zynqmp_dp *dp = bridge_to_dp(bridge); int rate; diff --git a/drivers/gpu/drm/xlnx/zynqmp_kms.c b/drivers/gpu/drm/xlnx/zynqmp_kms.c index 1847792cf13d..776ef5480206 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_kms.c +++ b/drivers/gpu/drm/xlnx/zynqmp_kms.c @@ -19,7 +19,7 @@ #include <drm/drm_device.h> #include <drm/drm_drv.h> #include <drm/drm_encoder.h> -#include <drm/drm_fb_helper.h> +#include <drm/drm_fbdev_generic.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem_dma_helper.h> |