diff options
Diffstat (limited to 'drivers/gpu')
73 files changed, 770 insertions, 764 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig index f6e5c0282fc1..2e98c016cb47 100644 --- a/drivers/gpu/drm/amd/amdgpu/Kconfig +++ b/drivers/gpu/drm/amd/amdgpu/Kconfig @@ -27,7 +27,9 @@ config DRM_AMDGPU_CIK config DRM_AMDGPU_USERPTR bool "Always enable userptr write support" depends on DRM_AMDGPU - depends on HMM_MIRROR + depends on MMU + select HMM_MIRROR + select MMU_NOTIFIER help This option selects CONFIG_HMM and CONFIG_HMM_MIRROR if it isn't already selected to enabled full userptr support. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 42b936b6bbf1..6d021ecc8d59 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1103,7 +1103,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( alloc_flags = 0; if (!offset || !*offset) return -EINVAL; - user_addr = *offset; + user_addr = untagged_addr(*offset); } else if (flags & (ALLOC_MEM_FLAGS_DOORBELL | ALLOC_MEM_FLAGS_MMIO_REMAP)) { domain = AMDGPU_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 5da72ca6f3e1..264677ab248a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -35,6 +35,7 @@ #include <linux/pm_runtime.h> #include <linux/vga_switcheroo.h> #include <drm/drm_probe_helper.h> +#include <linux/mmu_notifier.h> #include "amdgpu.h" #include "amdgpu_irq.h" @@ -1474,6 +1475,7 @@ static void __exit amdgpu_exit(void) amdgpu_unregister_atpx_handler(); amdgpu_sync_fini(); amdgpu_fence_slab_fini(); + mmu_notifier_synchronize(); } module_init(amdgpu_init); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index b174bd5eb38e..8ceb44925947 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -291,6 +291,8 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, uint32_t handle; int r; + args->addr = untagged_addr(args->addr); + if (offset_in_page(args->addr | args->size)) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index f1f8cdd695d3..31d4deb5d294 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -195,13 +195,14 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node, * Block for operations on BOs to finish and mark pages as accessed and * potentially dirty. */ -static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, - const struct hmm_update *update) +static int +amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, + const struct mmu_notifier_range *update) { struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror); unsigned long start = update->start; unsigned long end = update->end; - bool blockable = update->blockable; + bool blockable = mmu_notifier_range_blockable(update); struct interval_tree_node *it; /* notification is exclusive, but interval is inclusive */ @@ -243,13 +244,14 @@ static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, * necessitates evicting all user-mode queues of the process. The BOs * are restorted in amdgpu_mn_invalidate_range_end_hsa. */ -static int amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror, - const struct hmm_update *update) +static int +amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror, + const struct mmu_notifier_range *update) { struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror); unsigned long start = update->start; unsigned long end = update->end; - bool blockable = update->blockable; + bool blockable = mmu_notifier_range_blockable(update); struct interval_tree_node *it; /* notification is exclusive, but interval is inclusive */ @@ -482,6 +484,5 @@ void amdgpu_hmm_init_range(struct hmm_range *range) range->flags = hmm_range_flags; range->values = hmm_range_values; range->pfn_shift = PAGE_SHIFT; - INIT_LIST_HEAD(&range->list); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 13b144c8f67d..dff41d0a85fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -794,7 +794,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) struct hmm_range *range; unsigned long i; uint64_t *pfns; - int retry = 0; int r = 0; if (!mm) /* Happens during process shutdown */ @@ -835,10 +834,11 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) 0 : range->flags[HMM_PFN_WRITE]; range->pfn_flags_mask = 0; range->pfns = pfns; - hmm_range_register(range, mirror, start, - start + ttm->num_pages * PAGE_SIZE, PAGE_SHIFT); + range->start = start; + range->end = start + ttm->num_pages * PAGE_SIZE; + + hmm_range_register(range, mirror); -retry: /* * Just wait for range to be valid, safe to ignore return value as we * will use the return value of hmm_range_fault() below under the @@ -847,24 +847,12 @@ retry: hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT); down_read(&mm->mmap_sem); - - r = hmm_range_fault(range, true); - if (unlikely(r < 0)) { - if (likely(r == -EAGAIN)) { - /* - * return -EAGAIN, mmap_sem is dropped - */ - if (retry++ < MAX_RETRY_HMM_RANGE_FAULT) - goto retry; - else - pr_err("Retry hmm fault too many times\n"); - } - - goto out_up_read; - } - + r = hmm_range_fault(range, 0); up_read(&mm->mmap_sem); + if (unlikely(r < 0)) + goto out_free_pfns; + for (i = 0; i < ttm->num_pages; i++) { pages[i] = hmm_device_entry_to_page(range, pfns[i]); if (unlikely(!pages[i])) { @@ -880,9 +868,6 @@ retry: return 0; -out_up_read: - if (likely(r != -EAGAIN)) - up_read(&mm->mmap_sem); out_free_pfns: hmm_range_unregister(range); kvfree(pfns); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 26b15cc56c31..1d3cd5c50d5f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1567,32 +1567,6 @@ copy_from_user_failed: return err; } -static int kfd_ioctl_alloc_queue_gws(struct file *filep, - struct kfd_process *p, void *data) -{ - int retval; - struct kfd_ioctl_alloc_queue_gws_args *args = data; - struct kfd_dev *dev; - - if (!hws_gws_support) - return -ENODEV; - - dev = kfd_device_by_id(args->gpu_id); - if (!dev) { - pr_debug("Could not find gpu id 0x%x\n", args->gpu_id); - return -ENODEV; - } - if (dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS) - return -ENODEV; - - mutex_lock(&p->mutex); - retval = pqm_set_gws(&p->pqm, args->queue_id, args->num_gws ? dev->gws : NULL); - mutex_unlock(&p->mutex); - - args->first_gws = 0; - return retval; -} - static int kfd_ioctl_get_dmabuf_info(struct file *filep, struct kfd_process *p, void *data) { @@ -1795,8 +1769,6 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_IMPORT_DMABUF, kfd_ioctl_import_dmabuf, 0), - AMDKFD_IOCTL_DEF(AMDKFD_IOC_ALLOC_QUEUE_GWS, - kfd_ioctl_alloc_queue_gws, 0), }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 3bb75d11a662..c89326125d71 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -687,9 +687,6 @@ struct kfd_process { /* We want to receive a notification when the mm_struct is destroyed */ struct mmu_notifier mmu_notifier; - /* Use for delayed freeing of kfd_process structure */ - struct rcu_head rcu; - unsigned int pasid; unsigned int doorbell_index; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 0c6ac043ae3c..40e3fc0c6942 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -62,8 +62,8 @@ static struct workqueue_struct *kfd_restore_wq; static struct kfd_process *find_process(const struct task_struct *thread); static void kfd_process_ref_release(struct kref *ref); -static struct kfd_process *create_process(const struct task_struct *thread, - struct file *filep); +static struct kfd_process *create_process(const struct task_struct *thread); +static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep); static void evict_process_worker(struct work_struct *work); static void restore_process_worker(struct work_struct *work); @@ -289,7 +289,15 @@ struct kfd_process *kfd_create_process(struct file *filep) if (process) { pr_debug("Process already found\n"); } else { - process = create_process(thread, filep); + process = create_process(thread); + if (IS_ERR(process)) + goto out; + + ret = kfd_process_init_cwsr_apu(process, filep); + if (ret) { + process = ERR_PTR(ret); + goto out; + } if (!procfs.kobj) goto out; @@ -478,11 +486,9 @@ static void kfd_process_ref_release(struct kref *ref) queue_work(kfd_process_wq, &p->release_work); } -static void kfd_process_destroy_delayed(struct rcu_head *rcu) +static void kfd_process_free_notifier(struct mmu_notifier *mn) { - struct kfd_process *p = container_of(rcu, struct kfd_process, rcu); - - kfd_unref_process(p); + kfd_unref_process(container_of(mn, struct kfd_process, mmu_notifier)); } static void kfd_process_notifier_release(struct mmu_notifier *mn, @@ -534,12 +540,12 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, mutex_unlock(&p->mutex); - mmu_notifier_unregister_no_release(&p->mmu_notifier, mm); - mmu_notifier_call_srcu(&p->rcu, &kfd_process_destroy_delayed); + mmu_notifier_put(&p->mmu_notifier); } static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = { .release = kfd_process_notifier_release, + .free_notifier = kfd_process_free_notifier, }; static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep) @@ -609,81 +615,69 @@ static int kfd_process_device_init_cwsr_dgpu(struct kfd_process_device *pdd) return 0; } -static struct kfd_process *create_process(const struct task_struct *thread, - struct file *filep) +/* + * On return the kfd_process is fully operational and will be freed when the + * mm is released + */ +static struct kfd_process *create_process(const struct task_struct *thread) { struct kfd_process *process; int err = -ENOMEM; process = kzalloc(sizeof(*process), GFP_KERNEL); - if (!process) goto err_alloc_process; - process->pasid = kfd_pasid_alloc(); - if (process->pasid == 0) - goto err_alloc_pasid; - - if (kfd_alloc_process_doorbells(process) < 0) - goto err_alloc_doorbells; - kref_init(&process->ref); - mutex_init(&process->mutex); - process->mm = thread->mm; - - /* register notifier */ - process->mmu_notifier.ops = &kfd_process_mmu_notifier_ops; - err = mmu_notifier_register(&process->mmu_notifier, process->mm); - if (err) - goto err_mmu_notifier; - - hash_add_rcu(kfd_processes_table, &process->kfd_processes, - (uintptr_t)process->mm); - process->lead_thread = thread->group_leader; - get_task_struct(process->lead_thread); - INIT_LIST_HEAD(&process->per_device_data); - + INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker); + INIT_DELAYED_WORK(&process->restore_work, restore_process_worker); + process->last_restore_timestamp = get_jiffies_64(); kfd_event_init_process(process); + process->is_32bit_user_mode = in_compat_syscall(); + + process->pasid = kfd_pasid_alloc(); + if (process->pasid == 0) + goto err_alloc_pasid; + + if (kfd_alloc_process_doorbells(process) < 0) + goto err_alloc_doorbells; err = pqm_init(&process->pqm, process); if (err != 0) goto err_process_pqm_init; /* init process apertures*/ - process->is_32bit_user_mode = in_compat_syscall(); err = kfd_init_apertures(process); if (err != 0) goto err_init_apertures; - INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker); - INIT_DELAYED_WORK(&process->restore_work, restore_process_worker); - process->last_restore_timestamp = get_jiffies_64(); - - err = kfd_process_init_cwsr_apu(process, filep); + /* Must be last, have to use release destruction after this */ + process->mmu_notifier.ops = &kfd_process_mmu_notifier_ops; + err = mmu_notifier_register(&process->mmu_notifier, process->mm); if (err) - goto err_init_cwsr; + goto err_register_notifier; + + get_task_struct(process->lead_thread); + hash_add_rcu(kfd_processes_table, &process->kfd_processes, + (uintptr_t)process->mm); return process; -err_init_cwsr: +err_register_notifier: kfd_process_free_outstanding_kfd_bos(process); kfd_process_destroy_pdds(process); err_init_apertures: pqm_uninit(&process->pqm); err_process_pqm_init: - hash_del_rcu(&process->kfd_processes); - synchronize_rcu(); - mmu_notifier_unregister_no_release(&process->mmu_notifier, process->mm); -err_mmu_notifier: - mutex_destroy(&process->mutex); kfd_free_process_doorbells(process); err_alloc_doorbells: kfd_pasid_free(process->pasid); err_alloc_pasid: + mutex_destroy(&process->mutex); kfree(process); err_alloc_process: return ERR_PTR(err); diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile index 16614d73a5fc..985633c08a26 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile +++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile @@ -36,9 +36,9 @@ ifdef CONFIG_CC_IS_CLANG calcs_ccflags += -msse2 endif -CFLAGS_dcn_calcs.o := $(calcs_ccflags) -CFLAGS_dcn_calc_auto.o := $(calcs_ccflags) -CFLAGS_dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare +CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags) +CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_ccflags) +CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile index f57a3b281408..ddb8d5649e79 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile @@ -16,10 +16,10 @@ else ifneq ($(call cc-option, -mstack-alignment=16),) cc_stack_align := -mstack-alignment=16 endif -CFLAGS_dcn20_resource.o := -mhard-float -msse $(cc_stack_align) +CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse $(cc_stack_align) ifdef CONFIG_CC_IS_CLANG -CFLAGS_dcn20_resource.o += -msse2 +CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2 endif AMD_DAL_DCN20 = $(addprefix $(AMDDALPATH)/dc/dcn20/,$(DCN20)) diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile index b2b39090fb57..8cd9de8b1a7a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile @@ -3,7 +3,7 @@ DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o -CFLAGS_dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4 +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4 AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21)) diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index af2a864a6da0..5b2a65b42403 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -36,25 +36,22 @@ ifdef CONFIG_CC_IS_CLANG dml_ccflags += -msse2 endif -CFLAGS_display_mode_lib.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) ifdef CONFIG_DRM_AMD_DC_DCN2_0 -CFLAGS_display_mode_vba.o := $(dml_ccflags) -CFLAGS_display_mode_vba_20.o := $(dml_ccflags) -CFLAGS_display_rq_dlg_calc_20.o := $(dml_ccflags) -CFLAGS_display_mode_vba_20v2.o := $(dml_ccflags) -CFLAGS_display_rq_dlg_calc_20v2.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags) endif ifdef CONFIG_DRM_AMD_DC_DCN2_1 -CFLAGS_display_mode_vba_21.o := $(dml_ccflags) -CFLAGS_display_rq_dlg_calc_21.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags) endif -ifdef CONFIG_DRM_AMD_DCN3AG -CFLAGS_display_mode_vba_3ag.o := $(dml_ccflags) -endif -CFLAGS_dml1_display_rq_dlg_calc.o := $(dml_ccflags) -CFLAGS_display_rq_dlg_helpers.o := $(dml_ccflags) -CFLAGS_dml_common_defs.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dml_common_defs.o := $(dml_ccflags) DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \ dml_common_defs.o diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile index 17db603f2d1f..b456cd23c6fa 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile @@ -13,10 +13,9 @@ ifdef CONFIG_CC_IS_CLANG dsc_ccflags += -msse2 endif -CFLAGS_rc_calc.o := $(dsc_ccflags) -CFLAGS_rc_calc_dpi.o := $(dsc_ccflags) -CFLAGS_codec_main_amd.o := $(dsc_ccflags) -CFLAGS_dc_dsc.o := $(dsc_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dsc/dc_dsc.o := $(dsc_ccflags) DSC = dc_dsc.o rc_calc.o rc_calc_dpi.o diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 320ac20146fd..6109815a0401 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -748,8 +748,6 @@ struct smu_funcs ((smu)->funcs->set_azalia_d3_pme ? (smu)->funcs->set_azalia_d3_pme((smu)) : 0) #define smu_get_dpm_ultimate_freq(smu, param, min, max) \ ((smu)->funcs->get_dpm_ultimate_freq ? (smu)->funcs->get_dpm_ultimate_freq((smu), (param), (min), (max)) : 0) -#define smu_get_uclk_dpm_states(smu, clocks_in_khz, num_states) \ - ((smu)->ppt_funcs->get_uclk_dpm_states ? (smu)->ppt_funcs->get_uclk_dpm_states((smu), (clocks_in_khz), (num_states)) : 0) #define smu_get_max_sustainable_clocks_by_dc(smu, max_clocks) \ ((smu)->funcs->get_max_sustainable_clocks_by_dc ? (smu)->funcs->get_max_sustainable_clocks_by_dc((smu), (max_clocks)) : 0) #define smu_get_uclk_dpm_states(smu, clocks_in_khz, num_states) \ diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c index 0142ee991957..ca64a129c594 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c @@ -130,7 +130,7 @@ static int komeda_parse_pipe_dt(struct komeda_dev *mdev, struct device_node *np) of_graph_get_port_by_id(np, KOMEDA_OF_PORT_OUTPUT); pipe->dual_link = pipe->of_output_links[0] && pipe->of_output_links[1]; - pipe->of_node = np; + pipe->of_node = of_node_get(np); return 0; } diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.c b/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.c index cd4d9f53ddef..c9a1edb9a000 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.c @@ -35,6 +35,25 @@ komeda_get_format_caps(struct komeda_format_caps_table *table, return NULL; } +u32 komeda_get_afbc_format_bpp(const struct drm_format_info *info, u64 modifier) +{ + u32 bpp; + + switch (info->format) { + case DRM_FORMAT_YUV420_8BIT: + bpp = 12; + break; + case DRM_FORMAT_YUV420_10BIT: + bpp = 15; + break; + default: + bpp = info->cpp[0] * 8; + break; + } + + return bpp; +} + /* Two assumptions * 1. RGB always has YTR * 2. Tiled RGB always has SC diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.h b/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.h index 3631910d33b5..32273cf18f7c 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.h +++ b/drivers/gpu/drm/arm/display/komeda/komeda_format_caps.h @@ -97,6 +97,9 @@ const struct komeda_format_caps * komeda_get_format_caps(struct komeda_format_caps_table *table, u32 fourcc, u64 modifier); +u32 komeda_get_afbc_format_bpp(const struct drm_format_info *info, + u64 modifier); + u32 *komeda_get_layer_fourcc_list(struct komeda_format_caps_table *table, u32 layer_type, u32 *n_fmts); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c b/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c index 3b0a70ed6aa0..1b01a625f40e 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_framebuffer.c @@ -43,7 +43,7 @@ komeda_fb_afbc_size_check(struct komeda_fb *kfb, struct drm_file *file, struct drm_framebuffer *fb = &kfb->base; const struct drm_format_info *info = fb->format; struct drm_gem_object *obj; - u32 alignment_w = 0, alignment_h = 0, alignment_header, n_blocks; + u32 alignment_w = 0, alignment_h = 0, alignment_header, n_blocks, bpp; u64 min_size; obj = drm_gem_object_lookup(file, mode_cmd->handles[0]); @@ -88,8 +88,9 @@ komeda_fb_afbc_size_check(struct komeda_fb *kfb, struct drm_file *file, kfb->offset_payload = ALIGN(n_blocks * AFBC_HEADER_SIZE, alignment_header); + bpp = komeda_get_afbc_format_bpp(info, fb->modifier); kfb->afbc_size = kfb->offset_payload + n_blocks * - ALIGN(info->cpp[0] * AFBC_SUPERBLK_PIXELS, + ALIGN(bpp * AFBC_SUPERBLK_PIXELS / 8, AFBC_SUPERBLK_ALIGNMENT); min_size = kfb->afbc_size + fb->offsets[0]; if (min_size > obj->size) { diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index 89191a555c84..8820ce15ce37 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -14,6 +14,7 @@ #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_irq.h> +#include <drm/drm_probe_helper.h> #include <drm/drm_vblank.h> #include "komeda_dev.h" @@ -143,7 +144,6 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc, struct komeda_crtc_state *kcrtc_st = to_kcrtc_st(crtc_st); struct komeda_plane_state *kplane_st; struct drm_plane_state *plane_st; - struct drm_framebuffer *fb; struct drm_plane *plane; struct list_head zorder_list; int order = 0, err; @@ -169,7 +169,6 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc, list_for_each_entry(kplane_st, &zorder_list, zlist_node) { plane_st = &kplane_st->base; - fb = plane_st->fb; plane = plane_st->plane; plane_st->normalized_zpos = order++; @@ -202,7 +201,7 @@ static int komeda_kms_check(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; - struct drm_crtc_state *old_crtc_st, *new_crtc_st; + struct drm_crtc_state *new_crtc_st; int i, err; err = drm_atomic_helper_check_modeset(dev, state); @@ -213,7 +212,7 @@ static int komeda_kms_check(struct drm_device *dev, * so need to add all affected_planes (even unchanged) to * drm_atomic_state. */ - for_each_oldnew_crtc_in_state(state, crtc, old_crtc_st, new_crtc_st, i) { + for_each_new_crtc_in_state(state, crtc, new_crtc_st, i) { err = drm_atomic_add_affected_planes(state, crtc); if (err) return err; @@ -304,24 +303,33 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev) komeda_kms_irq_handler, IRQF_SHARED, drm->driver->name, drm); if (err) - goto cleanup_mode_config; + goto free_component_binding; err = mdev->funcs->enable_irq(mdev); if (err) - goto cleanup_mode_config; + goto free_component_binding; drm->irq_enabled = true; + drm_kms_helper_poll_init(drm); + err = drm_dev_register(drm, 0); if (err) - goto cleanup_mode_config; + goto free_interrupts; return kms; -cleanup_mode_config: +free_interrupts: + drm_kms_helper_poll_fini(drm); drm->irq_enabled = false; + mdev->funcs->disable_irq(mdev); +free_component_binding: + component_unbind_all(mdev->dev, drm); +cleanup_mode_config: drm_mode_config_cleanup(drm); komeda_kms_cleanup_private_objs(kms); + drm->dev_private = NULL; + drm_dev_put(drm); free_kms: kfree(kms); return ERR_PTR(err); @@ -332,12 +340,14 @@ void komeda_kms_detach(struct komeda_kms_dev *kms) struct drm_device *drm = &kms->base; struct komeda_dev *mdev = drm->dev_private; + drm_dev_unregister(drm); + drm_kms_helper_poll_fini(drm); + drm_atomic_helper_shutdown(drm); drm->irq_enabled = false; mdev->funcs->disable_irq(mdev); - drm_dev_unregister(drm); component_unbind_all(mdev->dev, drm); - komeda_kms_cleanup_private_objs(kms); drm_mode_config_cleanup(drm); + komeda_kms_cleanup_private_objs(kms); drm->dev_private = NULL; drm_dev_put(drm); } diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h index a7a84e66549d..cf5bea578ad9 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h @@ -482,6 +482,7 @@ void komeda_pipeline_dump_register(struct komeda_pipeline *pipe, struct seq_file *sf); /* component APIs */ +extern __printf(10, 11) struct komeda_component * komeda_component_add(struct komeda_pipeline *pipe, size_t comp_sz, u32 id, u32 hw_id, diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c index 617e1f7b8472..2851cac94d86 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c @@ -148,7 +148,7 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms, if (!kcrtc->master->wb_layer) return 0; - kwb_conn = kzalloc(sizeof(*wb_conn), GFP_KERNEL); + kwb_conn = kzalloc(sizeof(*kwb_conn), GFP_KERNEL); if (!kwb_conn) return -ENOMEM; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index dab77b2bc8ac..50de8e47659c 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -136,8 +136,8 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) /* Enable extended register access */ - ast_enable_mmio(dev); ast_open_key(ast); + ast_enable_mmio(dev); /* Find out whether P2A works or whether to use device-tree */ ast_detect_config_mode(dev, &scu_rev); @@ -522,6 +522,9 @@ void ast_driver_unload(struct drm_device *dev) { struct ast_private *ast = dev->dev_private; + /* enable standard VGA decode */ + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x04); + ast_release_firmware(dev); kfree(ast->dp501_fw_addr); ast_mode_fini(dev); diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 1c899a6e87b7..d349c721501c 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -585,7 +585,7 @@ static int ast_crtc_mode_set(struct drm_crtc *crtc, return -EINVAL; ast_open_key(ast); - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa1, 0xff, 0x04); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06); ast_set_std_reg(crtc, adjusted_mode, &vbios_mode); ast_set_crtc_reg(crtc, adjusted_mode, &vbios_mode); diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index e1d9cdf6ec1d..2d1b18619743 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -49,7 +49,7 @@ void ast_enable_mmio(struct drm_device *dev) { struct ast_private *ast = dev->dev_private; - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa1, 0xff, 0x04); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06); } diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index f6d2681f6927..9e13e466e72c 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -981,10 +981,10 @@ static int adv7511_init_cec_regmap(struct adv7511 *adv) { int ret; - adv->i2c_cec = i2c_new_secondary_device(adv->i2c_main, "cec", + adv->i2c_cec = i2c_new_ancillary_device(adv->i2c_main, "cec", ADV7511_CEC_I2C_ADDR_DEFAULT); - if (!adv->i2c_cec) - return -EINVAL; + if (IS_ERR(adv->i2c_cec)) + return PTR_ERR(adv->i2c_cec); i2c_set_clientdata(adv->i2c_cec, adv); adv->regmap_cec = devm_regmap_init_i2c(adv->i2c_cec, @@ -1165,20 +1165,20 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) adv7511_packet_disable(adv7511, 0xffff); - adv7511->i2c_edid = i2c_new_secondary_device(i2c, "edid", + adv7511->i2c_edid = i2c_new_ancillary_device(i2c, "edid", ADV7511_EDID_I2C_ADDR_DEFAULT); - if (!adv7511->i2c_edid) { - ret = -EINVAL; + if (IS_ERR(adv7511->i2c_edid)) { + ret = PTR_ERR(adv7511->i2c_edid); goto uninit_regulators; } regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR, adv7511->i2c_edid->addr << 1); - adv7511->i2c_packet = i2c_new_secondary_device(i2c, "packet", + adv7511->i2c_packet = i2c_new_ancillary_device(i2c, "packet", ADV7511_PACKET_I2C_ADDR_DEFAULT); - if (!adv7511->i2c_packet) { - ret = -EINVAL; + if (IS_ERR(adv7511->i2c_packet)) { + ret = PTR_ERR(adv7511->i2c_packet); goto err_i2c_unregister_edid; } diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index ad19df0686c9..bd2498bbd74a 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -93,11 +93,6 @@ static struct bus_type mipi_dsi_bus_type = { .pm = &mipi_dsi_device_pm_ops, }; -static int of_device_match(struct device *dev, const void *data) -{ - return dev->of_node == data; -} - /** * of_find_mipi_dsi_device_by_node() - find the MIPI DSI device matching a * device tree node @@ -110,7 +105,7 @@ struct mipi_dsi_device *of_find_mipi_dsi_device_by_node(struct device_node *np) { struct device *dev; - dev = bus_find_device(&mipi_dsi_bus_type, NULL, np, of_device_match); + dev = bus_find_device_by_of_node(&mipi_dsi_bus_type, np); return dev ? to_mipi_dsi_device(dev) : NULL; } diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 226a1d0720cf..88232698d7a0 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1454,6 +1454,7 @@ static int drm_mode_parse_cmdline_refresh(const char *str, char **end_ptr, } static int drm_mode_parse_cmdline_extra(const char *str, int length, + bool freestanding, const struct drm_connector *connector, struct drm_cmdline_mode *mode) { @@ -1462,9 +1463,15 @@ static int drm_mode_parse_cmdline_extra(const char *str, int length, for (i = 0; i < length; i++) { switch (str[i]) { case 'i': + if (freestanding) + return -EINVAL; + mode->interlace = true; break; case 'm': + if (freestanding) + return -EINVAL; + mode->margins = true; break; case 'D': @@ -1542,6 +1549,7 @@ static int drm_mode_parse_cmdline_res_mode(const char *str, unsigned int length, if (extras) { int ret = drm_mode_parse_cmdline_extra(end_ptr + i, 1, + false, connector, mode); if (ret) @@ -1669,6 +1677,22 @@ static int drm_mode_parse_cmdline_options(char *str, size_t len, return 0; } +static const char * const drm_named_modes_whitelist[] = { + "NTSC", + "PAL", +}; + +static bool drm_named_mode_is_in_whitelist(const char *mode, unsigned int size) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(drm_named_modes_whitelist); i++) + if (!strncmp(mode, drm_named_modes_whitelist[i], size)) + return true; + + return false; +} + /** * drm_mode_parse_command_line_for_connector - parse command line modeline for connector * @mode_option: optional per connector mode option @@ -1725,16 +1749,30 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option, * bunch of things: * - We need to make sure that the first character (which * would be our resolution in X) is a digit. - * - However, if the X resolution is missing, then we end up - * with something like x<yres>, with our first character - * being an alpha-numerical character, which would be - * considered a named mode. + * - If not, then it's either a named mode or a force on/off. + * To distinguish between the two, we need to run the + * extra parsing function, and if not, then we consider it + * a named mode. * * If this isn't enough, we should add more heuristics here, * and matching unit-tests. */ - if (!isdigit(name[0]) && name[0] != 'x') + if (!isdigit(name[0]) && name[0] != 'x') { + unsigned int namelen = strlen(name); + + /* + * Only the force on/off options can be in that case, + * and they all take a single character. + */ + if (namelen == 1) { + ret = drm_mode_parse_cmdline_extra(name, namelen, true, + connector, mode); + if (!ret) + return true; + } + named_mode = true; + } /* Try to locate the bpp and refresh specifiers, if any */ bpp_ptr = strchr(name, '-'); @@ -1770,7 +1808,13 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option, } if (named_mode) { - strncpy(mode->name, name, mode_end); + if (mode_end + 1 > DRM_DISPLAY_MODE_LEN) + return false; + + if (!drm_named_mode_is_in_whitelist(name, mode_end)) + return false; + + strscpy(mode->name, name, mode_end + 1); } else { ret = drm_mode_parse_cmdline_res_mode(name, mode_end, parse_extras, @@ -1809,7 +1853,7 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option, extra_ptr != options_ptr) { int len = strlen(name) - (extra_ptr - name); - ret = drm_mode_parse_cmdline_extra(extra_ptr, len, + ret = drm_mode_parse_cmdline_extra(extra_ptr, len, false, connector, mode); if (ret) return false; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 8a03a33c32cb..ba0f868b2477 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -249,9 +249,7 @@ static struct component_match *exynos_drm_match_add(struct device *dev) if (!info->driver || !(info->flags & DRM_COMPONENT_DRIVER)) continue; - while ((d = bus_find_device(&platform_bus_type, p, - &info->driver->driver, - (void *)platform_bus_type.match))) { + while ((d = platform_find_device_by_driver(p, &info->driver->driver))) { put_device(p); if (!(info->flags & DRM_FIMC_DEVICE) || @@ -419,9 +417,8 @@ static void exynos_drm_unregister_devices(void) if (!info->driver || !(info->flags & DRM_VIRTUAL_DEVICE)) continue; - while ((dev = bus_find_device(&platform_bus_type, NULL, - &info->driver->driver, - (void *)platform_bus_type.match))) { + while ((dev = platform_find_device_by_driver(NULL, + &info->driver->driver))) { put_device(dev); platform_device_unregister(to_platform_device(dev)); } diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 658b930d34a8..2587ea834f06 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -26,7 +26,7 @@ subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror # Fine grained warnings disable CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init) -CFLAGS_intel_fbdev.o = $(call cc-disable-warning, override-init) +CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init) subdir-ccflags-y += \ $(call as-instr,movntdqa (%eax)$(comma)%xmm0,-DCONFIG_AS_MOVNTDQA) diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 2c5ac3dd647f..6df240a01b8c 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -128,7 +128,15 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder, limits.max_lane_count = intel_dp_max_lane_count(intel_dp); limits.min_bpp = intel_dp_min_bpp(pipe_config); - limits.max_bpp = pipe_config->pipe_bpp; + /* + * FIXME: If all the streams can't fit into the link with + * their current pipe_bpp we should reduce pipe_bpp across + * the board until things start to fit. Until then we + * limit to <= 8bpc since that's what was hardcoded for all + * MST streams previously. This hack should be removed once + * we have the proper retry logic in place. + */ + limits.max_bpp = min(pipe_config->pipe_bpp, 24); intel_dp_adjust_compliance_config(intel_dp, pipe_config, &limits); diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 598ddb60f9fb..d4fb7f16f9f6 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -547,7 +547,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder, pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) | DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances); DRM_INFO("PPS2 = 0x%08x\n", pps_val); - if (encoder->type == INTEL_OUTPUT_EDP) { + if (cpu_transcoder == TRANSCODER_EDP) { I915_WRITE(DSCA_PICTURE_PARAMETER_SET_2, pps_val); /* * If 2 VDSC instances are needed, configure PPS for second diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index f813fcb8ceb6..b5f6937369ea 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -1574,6 +1574,7 @@ static int check_relocations(const struct drm_i915_gem_exec_object2 *entry) static int eb_copy_relocations(const struct i915_execbuffer *eb) { + struct drm_i915_gem_relocation_entry *relocs; const unsigned int count = eb->buffer_count; unsigned int i; int err; @@ -1581,7 +1582,6 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb) for (i = 0; i < count; i++) { const unsigned int nreloc = eb->exec[i].relocation_count; struct drm_i915_gem_relocation_entry __user *urelocs; - struct drm_i915_gem_relocation_entry *relocs; unsigned long size; unsigned long copied; @@ -1609,14 +1609,8 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb) if (__copy_from_user((char *)relocs + copied, (char __user *)urelocs + copied, - len)) { -end_user: - user_access_end(); -end: - kvfree(relocs); - err = -EFAULT; - goto err; - } + len)) + goto end; copied += len; } while (copied < size); @@ -1645,10 +1639,14 @@ end: return 0; +end_user: + user_access_end(); +end: + kvfree(relocs); + err = -EFAULT; err: while (i--) { - struct drm_i915_gem_relocation_entry *relocs = - u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr); + relocs = u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr); if (eb->exec[i].relocation_count) kvfree(relocs); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 74da35611d7c..11b231c187c5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -672,15 +672,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, for_each_sgt_page(page, sgt_iter, pages) { if (obj->mm.dirty) - /* - * As this may not be anonymous memory (e.g. shmem) - * but exist on a real mapping, we have to lock - * the page in order to dirty it -- holding - * the page reference is not sufficient to - * prevent the inode from being truncated. - * Play safe and take the lock. - */ - set_page_dirty_lock(page); + set_page_dirty(page); mark_page_accessed(page); put_page(page); diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 126ab3667919..45481eb1fa3c 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -297,11 +297,6 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine, FLOW_CONTROL_ENABLE | PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); - /* Syncing dependencies between camera and graphics:skl,bxt,kbl */ - if (!IS_COFFEELAKE(i915)) - WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, - GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC); - /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */ /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */ WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7, diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 37f502ca95ad..6c79d16b381e 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1561,9 +1561,9 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, if (!intel_gvt_ggtt_validate_range(vgpu, workload->wa_ctx.indirect_ctx.guest_gma, workload->wa_ctx.indirect_ctx.size)) { - kmem_cache_free(s->workloads, workload); gvt_vgpu_err("invalid wa_ctx at: 0x%lx\n", workload->wa_ctx.indirect_ctx.guest_gma); + kmem_cache_free(s->workloads, workload); return ERR_PTR(-EINVAL); } } @@ -1575,9 +1575,9 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, if (!intel_gvt_ggtt_validate_range(vgpu, workload->wa_ctx.per_ctx.guest_gma, CACHELINE_BYTES)) { - kmem_cache_free(s->workloads, workload); gvt_vgpu_err("invalid per_ctx at: 0x%lx\n", workload->wa_ctx.per_ctx.guest_gma); + kmem_cache_free(s->workloads, workload); return ERR_PTR(-EINVAL); } } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index b5b2a64753e6..020696726f9e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1279,6 +1279,12 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) pci_set_master(pdev); + /* + * We don't have a max segment size, so set it to the max so sg's + * debugging layer doesn't complain + */ + dma_set_max_seg_size(&pdev->dev, UINT_MAX); + /* overlay on gen2 is broken and can't address above 1G */ if (IS_GEN(dev_priv, 2)) { ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(30)); diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c index ce1fae3a78a9..2e2ed653e9c6 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm.c @@ -675,10 +675,9 @@ static int ingenic_drm_probe(struct platform_device *pdev) return ret; } - if (panel) { + if (panel) bridge = devm_drm_panel_bridge_add(dev, panel, - DRM_MODE_CONNECTOR_Unknown); - } + DRM_MODE_CONNECTOR_DPI); priv->dma_hwdesc = dma_alloc_coherent(dev, sizeof(*priv->dma_hwdesc), &priv->dma_hwdesc_phys, diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index ff3d9acc24fc..4da21353c3a2 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -342,7 +342,7 @@ int lima_gem_wait(struct drm_file *file, u32 handle, u32 op, s64 timeout_ns) timeout = drm_timeout_abs_to_jiffies(timeout_ns); ret = drm_gem_dma_resv_wait(file, handle, write, timeout); - if (ret == 0) + if (ret == -ETIME) ret = timeout ? -ETIMEDOUT : -EBUSY; return ret; diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index 982fe8485a61..9a09eba53182 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -475,8 +475,7 @@ static int mcde_probe(struct platform_device *pdev) struct device_driver *drv = &mcde_component_drivers[i]->driver; struct device *p = NULL, *d; - while ((d = bus_find_device(&platform_bus_type, p, drv, - (void *)platform_bus_type.match))) { + while ((d = platform_find_device_by_driver(p, drv))) { put_device(p); component_match_add(dev, &match, mcde_compare_dev, d); p = d; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 2ee809a6f3dc..352b81a7a670 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -10,6 +10,7 @@ #include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/pm_runtime.h> +#include <linux/dma-mapping.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> @@ -207,6 +208,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) struct mtk_drm_private *private = drm->dev_private; struct platform_device *pdev; struct device_node *np; + struct device *dma_dev; int ret; if (!iommu_present(&platform_bus_type)) @@ -269,7 +271,29 @@ static int mtk_drm_kms_init(struct drm_device *drm) goto err_component_unbind; } - private->dma_dev = &pdev->dev; + dma_dev = &pdev->dev; + private->dma_dev = dma_dev; + + /* + * Configure the DMA segment size to make sure we get contiguous IOVA + * when importing PRIME buffers. + */ + if (!dma_dev->dma_parms) { + private->dma_parms_allocated = true; + dma_dev->dma_parms = + devm_kzalloc(drm->dev, sizeof(*dma_dev->dma_parms), + GFP_KERNEL); + } + if (!dma_dev->dma_parms) { + ret = -ENOMEM; + goto err_component_unbind; + } + + ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32)); + if (ret) { + dev_err(dma_dev, "Failed to set DMA segment size\n"); + goto err_unset_dma_parms; + } /* * We don't use the drm_irq_install() helpers provided by the DRM @@ -279,13 +303,16 @@ static int mtk_drm_kms_init(struct drm_device *drm) drm->irq_enabled = true; ret = drm_vblank_init(drm, MAX_CRTC); if (ret < 0) - goto err_component_unbind; + goto err_unset_dma_parms; drm_kms_helper_poll_init(drm); drm_mode_config_reset(drm); return 0; +err_unset_dma_parms: + if (private->dma_parms_allocated) + dma_dev->dma_parms = NULL; err_component_unbind: component_unbind_all(drm->dev, drm); err_config_cleanup: @@ -296,9 +323,14 @@ err_config_cleanup: static void mtk_drm_kms_deinit(struct drm_device *drm) { + struct mtk_drm_private *private = drm->dev_private; + drm_kms_helper_poll_fini(drm); drm_atomic_helper_shutdown(drm); + if (private->dma_parms_allocated) + private->dma_dev->dma_parms = NULL; + component_unbind_all(drm->dev, drm); drm_mode_config_cleanup(drm); } @@ -314,6 +346,18 @@ static const struct file_operations mtk_drm_fops = { .compat_ioctl = drm_compat_ioctl, }; +/* + * We need to override this because the device used to import the memory is + * not dev->dev, as drm_gem_prime_import() expects. + */ +struct drm_gem_object *mtk_drm_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct mtk_drm_private *private = dev->dev_private; + + return drm_gem_prime_import_dev(dev, dma_buf, private->dma_dev); +} + static struct drm_driver mtk_drm_driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, @@ -323,6 +367,7 @@ static struct drm_driver mtk_drm_driver = { .prime_handle_to_fd = drm_gem_prime_handle_to_fd, .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_import = mtk_drm_gem_prime_import, .gem_prime_get_sg_table = mtk_gem_prime_get_sg_table, .gem_prime_import_sg_table = mtk_gem_prime_import_sg_table, .gem_prime_mmap = mtk_drm_gem_mmap_buf, @@ -515,12 +560,15 @@ static int mtk_drm_probe(struct platform_device *pdev) comp = devm_kzalloc(dev, sizeof(*comp), GFP_KERNEL); if (!comp) { ret = -ENOMEM; + of_node_put(node); goto err_node; } ret = mtk_ddp_comp_init(dev, node, comp, comp_id, NULL); - if (ret) + if (ret) { + of_node_put(node); goto err_node; + } private->ddp_comp[comp_id] = comp; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h index 598ff3e70446..e03fea12ff59 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h @@ -51,6 +51,8 @@ struct mtk_drm_private { } commit; struct drm_atomic_state *suspend_state; + + bool dma_parms_allocated; }; extern struct platform_driver mtk_ddp_driver; diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig index 96b9814e6d06..3558df043592 100644 --- a/drivers/gpu/drm/nouveau/Kconfig +++ b/drivers/gpu/drm/nouveau/Kconfig @@ -86,9 +86,10 @@ config DRM_NOUVEAU_SVM bool "(EXPERIMENTAL) Enable SVM (Shared Virtual Memory) support" depends on DEVICE_PRIVATE depends on DRM_NOUVEAU - depends on HMM_MIRROR + depends on MMU depends on STAGING - select MIGRATE_VMA_HELPER + select HMM_MIRROR + select MMU_NOTIFIER default n help Say Y here if you want to enable experimental support for diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 064a69d161e3..b46be8a091e9 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -771,16 +771,20 @@ nv50_msto_atomic_check(struct drm_encoder *encoder, struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); int slots; - /* When restoring duplicated states, we need to make sure that the - * bw remains the same and avoid recalculating it, as the connector's - * bpc may have changed after the state was duplicated - */ - if (!state->duplicated) - asyh->dp.pbn = - drm_dp_calc_pbn_mode(crtc_state->adjusted_mode.clock, - connector->display_info.bpc * 3); + if (crtc_state->mode_changed || crtc_state->connectors_changed) { + /* + * When restoring duplicated states, we need to make sure that + * the bw remains the same and avoid recalculating it, as the + * connector's bpc may have changed after the state was + * duplicated + */ + if (!state->duplicated) { + const int bpp = connector->display_info.bpc * 3; + const int clock = crtc_state->adjusted_mode.clock; + + asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, bpp); + } - if (crtc_state->mode_changed) { slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port, asyh->dp.pbn); diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 1333220787a1..fa1439941596 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -44,8 +44,6 @@ #define DMEM_CHUNK_SIZE (2UL << 20) #define DMEM_CHUNK_NPAGES (DMEM_CHUNK_SIZE >> PAGE_SHIFT) -struct nouveau_migrate; - enum nouveau_aper { NOUVEAU_APER_VIRT, NOUVEAU_APER_VRAM, @@ -86,21 +84,13 @@ static inline struct nouveau_dmem *page_to_dmem(struct page *page) return container_of(page->pgmap, struct nouveau_dmem, pagemap); } -struct nouveau_dmem_fault { - struct nouveau_drm *drm; - struct nouveau_fence *fence; - dma_addr_t *dma; - unsigned long npages; -}; +static unsigned long nouveau_dmem_page_addr(struct page *page) +{ + struct nouveau_dmem_chunk *chunk = page->zone_device_data; + unsigned long idx = page_to_pfn(page) - chunk->pfn_first; -struct nouveau_migrate { - struct vm_area_struct *vma; - struct nouveau_drm *drm; - struct nouveau_fence *fence; - unsigned long npages; - dma_addr_t *dma; - unsigned long dma_nr; -}; + return (idx << PAGE_SHIFT) + chunk->bo->bo.offset; +} static void nouveau_dmem_page_free(struct page *page) { @@ -125,165 +115,90 @@ static void nouveau_dmem_page_free(struct page *page) spin_unlock(&chunk->lock); } -static void -nouveau_dmem_fault_alloc_and_copy(struct vm_area_struct *vma, - const unsigned long *src_pfns, - unsigned long *dst_pfns, - unsigned long start, - unsigned long end, - void *private) +static void nouveau_dmem_fence_done(struct nouveau_fence **fence) { - struct nouveau_dmem_fault *fault = private; - struct nouveau_drm *drm = fault->drm; - struct device *dev = drm->dev->dev; - unsigned long addr, i, npages = 0; - nouveau_migrate_copy_t copy; - int ret; - - - /* First allocate new memory */ - for (addr = start, i = 0; addr < end; addr += PAGE_SIZE, i++) { - struct page *dpage, *spage; - - dst_pfns[i] = 0; - spage = migrate_pfn_to_page(src_pfns[i]); - if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) - continue; - - dpage = alloc_page_vma(GFP_HIGHUSER, vma, addr); - if (!dpage) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - continue; - } - lock_page(dpage); - - dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)) | - MIGRATE_PFN_LOCKED; - npages++; - } - - /* Allocate storage for DMA addresses, so we can unmap later. */ - fault->dma = kmalloc(sizeof(*fault->dma) * npages, GFP_KERNEL); - if (!fault->dma) - goto error; - - /* Copy things over */ - copy = drm->dmem->migrate.copy_func; - for (addr = start, i = 0; addr < end; addr += PAGE_SIZE, i++) { - struct nouveau_dmem_chunk *chunk; - struct page *spage, *dpage; - u64 src_addr, dst_addr; - - dpage = migrate_pfn_to_page(dst_pfns[i]); - if (!dpage || dst_pfns[i] == MIGRATE_PFN_ERROR) - continue; - - spage = migrate_pfn_to_page(src_pfns[i]); - if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - __free_page(dpage); - continue; - } - - fault->dma[fault->npages] = - dma_map_page_attrs(dev, dpage, 0, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL, - DMA_ATTR_SKIP_CPU_SYNC); - if (dma_mapping_error(dev, fault->dma[fault->npages])) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - __free_page(dpage); - continue; - } - - dst_addr = fault->dma[fault->npages++]; - - chunk = spage->zone_device_data; - src_addr = page_to_pfn(spage) - chunk->pfn_first; - src_addr = (src_addr << PAGE_SHIFT) + chunk->bo->bo.offset; - - ret = copy(drm, 1, NOUVEAU_APER_HOST, dst_addr, - NOUVEAU_APER_VRAM, src_addr); - if (ret) { - dst_pfns[i] = MIGRATE_PFN_ERROR; - __free_page(dpage); - continue; - } + if (fence) { + nouveau_fence_wait(*fence, true, false); + nouveau_fence_unref(fence); + } else { + /* + * FIXME wait for channel to be IDLE before calling finalizing + * the hmem object. + */ } +} - nouveau_fence_new(drm->dmem->migrate.chan, false, &fault->fence); - - return; - -error: - for (addr = start, i = 0; addr < end; addr += PAGE_SIZE, ++i) { - struct page *page; +static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, + struct vm_fault *vmf, struct migrate_vma *args, + dma_addr_t *dma_addr) +{ + struct device *dev = drm->dev->dev; + struct page *dpage, *spage; - if (!dst_pfns[i] || dst_pfns[i] == MIGRATE_PFN_ERROR) - continue; + spage = migrate_pfn_to_page(args->src[0]); + if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) + return 0; - page = migrate_pfn_to_page(dst_pfns[i]); - dst_pfns[i] = MIGRATE_PFN_ERROR; - if (page == NULL) - continue; + dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + if (!dpage) + return VM_FAULT_SIGBUS; + lock_page(dpage); - __free_page(page); - } -} + *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, *dma_addr)) + goto error_free_page; -void nouveau_dmem_fault_finalize_and_map(struct vm_area_struct *vma, - const unsigned long *src_pfns, - const unsigned long *dst_pfns, - unsigned long start, - unsigned long end, - void *private) -{ - struct nouveau_dmem_fault *fault = private; - struct nouveau_drm *drm = fault->drm; + if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr, + NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) + goto error_dma_unmap; - if (fault->fence) { - nouveau_fence_wait(fault->fence, true, false); - nouveau_fence_unref(&fault->fence); - } else { - /* - * FIXME wait for channel to be IDLE before calling finalizing - * the hmem object below (nouveau_migrate_hmem_fini()). - */ - } + args->dst[0] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + return 0; - while (fault->npages--) { - dma_unmap_page(drm->dev->dev, fault->dma[fault->npages], - PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - } - kfree(fault->dma); +error_dma_unmap: + dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); +error_free_page: + __free_page(dpage); + return VM_FAULT_SIGBUS; } -static const struct migrate_vma_ops nouveau_dmem_fault_migrate_ops = { - .alloc_and_copy = nouveau_dmem_fault_alloc_and_copy, - .finalize_and_map = nouveau_dmem_fault_finalize_and_map, -}; - static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) { struct nouveau_dmem *dmem = page_to_dmem(vmf->page); - unsigned long src[1] = {0}, dst[1] = {0}; - struct nouveau_dmem_fault fault = { .drm = dmem->drm }; - int ret; + struct nouveau_drm *drm = dmem->drm; + struct nouveau_fence *fence; + unsigned long src = 0, dst = 0; + dma_addr_t dma_addr = 0; + vm_fault_t ret; + struct migrate_vma args = { + .vma = vmf->vma, + .start = vmf->address, + .end = vmf->address + PAGE_SIZE, + .src = &src, + .dst = &dst, + }; /* * FIXME what we really want is to find some heuristic to migrate more * than just one page on CPU fault. When such fault happens it is very * likely that more surrounding page will CPU fault too. */ - ret = migrate_vma(&nouveau_dmem_fault_migrate_ops, vmf->vma, - vmf->address, vmf->address + PAGE_SIZE, - src, dst, &fault); - if (ret) + if (migrate_vma_setup(&args) < 0) return VM_FAULT_SIGBUS; + if (!args.cpages) + return 0; - if (dst[0] == MIGRATE_PFN_ERROR) - return VM_FAULT_SIGBUS; + ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr); + if (ret || dst == 0) + goto done; - return 0; + nouveau_fence_new(dmem->migrate.chan, false, &fence); + migrate_vma_pages(&args); + nouveau_dmem_fence_done(&fence); + dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); +done: + migrate_vma_finalize(&args); + return ret; } static const struct dev_pagemap_ops nouveau_dmem_pagemap_ops = { @@ -642,188 +557,115 @@ out_free: drm->dmem = NULL; } -static void -nouveau_dmem_migrate_alloc_and_copy(struct vm_area_struct *vma, - const unsigned long *src_pfns, - unsigned long *dst_pfns, - unsigned long start, - unsigned long end, - void *private) +static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, + unsigned long src, dma_addr_t *dma_addr) { - struct nouveau_migrate *migrate = private; - struct nouveau_drm *drm = migrate->drm; struct device *dev = drm->dev->dev; - unsigned long addr, i, npages = 0; - nouveau_migrate_copy_t copy; - int ret; - - /* First allocate new memory */ - for (addr = start, i = 0; addr < end; addr += PAGE_SIZE, i++) { - struct page *dpage, *spage; - - dst_pfns[i] = 0; - spage = migrate_pfn_to_page(src_pfns[i]); - if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) - continue; - - dpage = nouveau_dmem_page_alloc_locked(drm); - if (!dpage) - continue; - - dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)) | - MIGRATE_PFN_LOCKED | - MIGRATE_PFN_DEVICE; - npages++; - } - - if (!npages) - return; - - /* Allocate storage for DMA addresses, so we can unmap later. */ - migrate->dma = kmalloc(sizeof(*migrate->dma) * npages, GFP_KERNEL); - if (!migrate->dma) - goto error; - - /* Copy things over */ - copy = drm->dmem->migrate.copy_func; - for (addr = start, i = 0; addr < end; addr += PAGE_SIZE, i++) { - struct nouveau_dmem_chunk *chunk; - struct page *spage, *dpage; - u64 src_addr, dst_addr; - - dpage = migrate_pfn_to_page(dst_pfns[i]); - if (!dpage || dst_pfns[i] == MIGRATE_PFN_ERROR) - continue; - - chunk = dpage->zone_device_data; - dst_addr = page_to_pfn(dpage) - chunk->pfn_first; - dst_addr = (dst_addr << PAGE_SHIFT) + chunk->bo->bo.offset; - - spage = migrate_pfn_to_page(src_pfns[i]); - if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) { - nouveau_dmem_page_free_locked(drm, dpage); - dst_pfns[i] = 0; - continue; - } - - migrate->dma[migrate->dma_nr] = - dma_map_page_attrs(dev, spage, 0, PAGE_SIZE, - PCI_DMA_BIDIRECTIONAL, - DMA_ATTR_SKIP_CPU_SYNC); - if (dma_mapping_error(dev, migrate->dma[migrate->dma_nr])) { - nouveau_dmem_page_free_locked(drm, dpage); - dst_pfns[i] = 0; - continue; - } - - src_addr = migrate->dma[migrate->dma_nr++]; + struct page *dpage, *spage; - ret = copy(drm, 1, NOUVEAU_APER_VRAM, dst_addr, - NOUVEAU_APER_HOST, src_addr); - if (ret) { - nouveau_dmem_page_free_locked(drm, dpage); - dst_pfns[i] = 0; - continue; - } - } - - nouveau_fence_new(drm->dmem->migrate.chan, false, &migrate->fence); + spage = migrate_pfn_to_page(src); + if (!spage || !(src & MIGRATE_PFN_MIGRATE)) + goto out; - return; + dpage = nouveau_dmem_page_alloc_locked(drm); + if (!dpage) + return 0; -error: - for (addr = start, i = 0; addr < end; addr += PAGE_SIZE, ++i) { - struct page *page; + *dma_addr = dma_map_page(dev, spage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, *dma_addr)) + goto out_free_page; - if (!dst_pfns[i] || dst_pfns[i] == MIGRATE_PFN_ERROR) - continue; + if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_VRAM, + nouveau_dmem_page_addr(dpage), NOUVEAU_APER_HOST, + *dma_addr)) + goto out_dma_unmap; - page = migrate_pfn_to_page(dst_pfns[i]); - dst_pfns[i] = MIGRATE_PFN_ERROR; - if (page == NULL) - continue; + return migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; - __free_page(page); - } +out_dma_unmap: + dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); +out_free_page: + nouveau_dmem_page_free_locked(drm, dpage); +out: + return 0; } -void nouveau_dmem_migrate_finalize_and_map(struct vm_area_struct *vma, - const unsigned long *src_pfns, - const unsigned long *dst_pfns, - unsigned long start, - unsigned long end, - void *private) +static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, + struct migrate_vma *args, dma_addr_t *dma_addrs) { - struct nouveau_migrate *migrate = private; - struct nouveau_drm *drm = migrate->drm; - - if (migrate->fence) { - nouveau_fence_wait(migrate->fence, true, false); - nouveau_fence_unref(&migrate->fence); - } else { - /* - * FIXME wait for channel to be IDLE before finalizing - * the hmem object below (nouveau_migrate_hmem_fini()) ? - */ + struct nouveau_fence *fence; + unsigned long addr = args->start, nr_dma = 0, i; + + for (i = 0; addr < args->end; i++) { + args->dst[i] = nouveau_dmem_migrate_copy_one(drm, args->src[i], + dma_addrs + nr_dma); + if (args->dst[i]) + nr_dma++; + addr += PAGE_SIZE; } - while (migrate->dma_nr--) { - dma_unmap_page(drm->dev->dev, migrate->dma[migrate->dma_nr], - PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - } - kfree(migrate->dma); + nouveau_fence_new(drm->dmem->migrate.chan, false, &fence); + migrate_vma_pages(args); + nouveau_dmem_fence_done(&fence); + while (nr_dma--) { + dma_unmap_page(drm->dev->dev, dma_addrs[nr_dma], PAGE_SIZE, + DMA_BIDIRECTIONAL); + } /* - * FIXME optimization: update GPU page table to point to newly - * migrated memory. + * FIXME optimization: update GPU page table to point to newly migrated + * memory. */ + migrate_vma_finalize(args); } -static const struct migrate_vma_ops nouveau_dmem_migrate_ops = { - .alloc_and_copy = nouveau_dmem_migrate_alloc_and_copy, - .finalize_and_map = nouveau_dmem_migrate_finalize_and_map, -}; - int nouveau_dmem_migrate_vma(struct nouveau_drm *drm, struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long *src_pfns, *dst_pfns, npages; - struct nouveau_migrate migrate = {0}; - unsigned long i, c, max; - int ret = 0; - - npages = (end - start) >> PAGE_SHIFT; - max = min(SG_MAX_SINGLE_ALLOC, npages); - src_pfns = kzalloc(sizeof(long) * max, GFP_KERNEL); - if (src_pfns == NULL) - return -ENOMEM; - dst_pfns = kzalloc(sizeof(long) * max, GFP_KERNEL); - if (dst_pfns == NULL) { - kfree(src_pfns); - return -ENOMEM; - } + unsigned long npages = (end - start) >> PAGE_SHIFT; + unsigned long max = min(SG_MAX_SINGLE_ALLOC, npages); + dma_addr_t *dma_addrs; + struct migrate_vma args = { + .vma = vma, + .start = start, + }; + unsigned long c, i; + int ret = -ENOMEM; + + args.src = kcalloc(max, sizeof(args.src), GFP_KERNEL); + if (!args.src) + goto out; + args.dst = kcalloc(max, sizeof(args.dst), GFP_KERNEL); + if (!args.dst) + goto out_free_src; - migrate.drm = drm; - migrate.vma = vma; - migrate.npages = npages; - for (i = 0; i < npages; i += c) { - unsigned long next; + dma_addrs = kmalloc_array(max, sizeof(*dma_addrs), GFP_KERNEL); + if (!dma_addrs) + goto out_free_dst; + for (i = 0; i < npages; i += c) { c = min(SG_MAX_SINGLE_ALLOC, npages); - next = start + (c << PAGE_SHIFT); - ret = migrate_vma(&nouveau_dmem_migrate_ops, vma, start, - next, src_pfns, dst_pfns, &migrate); + args.end = start + (c << PAGE_SHIFT); + ret = migrate_vma_setup(&args); if (ret) - goto out; - start = next; + goto out_free_dma; + + if (args.cpages) + nouveau_dmem_migrate_chunk(drm, &args, dma_addrs); + args.start = args.end; } + ret = 0; +out_free_dma: + kfree(dma_addrs); +out_free_dst: + kfree(args.dst); +out_free_src: + kfree(args.src); out: - kfree(dst_pfns); - kfree(src_pfns); return ret; } @@ -841,11 +683,10 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, npages = (range->end - range->start) >> PAGE_SHIFT; for (i = 0; i < npages; ++i) { - struct nouveau_dmem_chunk *chunk; struct page *page; uint64_t addr; - page = hmm_pfn_to_page(range, range->pfns[i]); + page = hmm_device_entry_to_page(range, range->pfns[i]); if (page == NULL) continue; @@ -859,10 +700,7 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, continue; } - chunk = page->zone_device_data; - addr = page_to_pfn(page) - chunk->pfn_first; - addr = (addr + chunk->bo->bo.mem.start) << PAGE_SHIFT; - + addr = nouveau_dmem_page_addr(page); range->pfns[i] &= ((1UL << range->pfn_shift) - 1); range->pfns[i] |= (addr >> PAGE_SHIFT) << range->pfn_shift; } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.h b/drivers/gpu/drm/nouveau/nouveau_dmem.h index 9d97d756fb7d..92394be5d649 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.h +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.h @@ -45,16 +45,5 @@ static inline void nouveau_dmem_init(struct nouveau_drm *drm) {} static inline void nouveau_dmem_fini(struct nouveau_drm *drm) {} static inline void nouveau_dmem_suspend(struct nouveau_drm *drm) {} static inline void nouveau_dmem_resume(struct nouveau_drm *drm) {} - -static inline int nouveau_dmem_migrate_vma(struct nouveau_drm *drm, - struct vm_area_struct *vma, - unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline void nouveau_dmem_convert_pfn(struct nouveau_drm *drm, - struct hmm_range *range) {} #endif /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */ #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index bdc948352467..2cd83849600f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -28,6 +28,7 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <linux/vga_switcheroo.h> +#include <linux/mmu_notifier.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_ioctl.h> @@ -1290,6 +1291,8 @@ nouveau_drm_exit(void) #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER platform_driver_unregister(&nouveau_platform_driver); #endif + if (IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM)) + mmu_notifier_synchronize(); } module_init(nouveau_drm_init); diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index a835cebb6d90..668d4bd0c118 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -252,13 +252,13 @@ nouveau_svmm_invalidate(struct nouveau_svmm *svmm, u64 start, u64 limit) static int nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror, - const struct hmm_update *update) + const struct mmu_notifier_range *update) { struct nouveau_svmm *svmm = container_of(mirror, typeof(*svmm), mirror); unsigned long start = update->start; unsigned long limit = update->end; - if (!update->blockable) + if (!mmu_notifier_range_blockable(update)) return -EAGAIN; SVMM_DBG(svmm, "invalidate %016lx-%016lx", start, limit); @@ -485,31 +485,29 @@ nouveau_range_done(struct hmm_range *range) } static int -nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) +nouveau_range_fault(struct nouveau_svmm *svmm, struct hmm_range *range) { long ret; range->default_flags = 0; range->pfn_flags_mask = -1UL; - ret = hmm_range_register(range, mirror, - range->start, range->end, - PAGE_SHIFT); + ret = hmm_range_register(range, &svmm->mirror); if (ret) { - up_read(&range->vma->vm_mm->mmap_sem); + up_read(&svmm->mm->mmap_sem); return (int)ret; } if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { - up_read(&range->vma->vm_mm->mmap_sem); - return -EAGAIN; + up_read(&svmm->mm->mmap_sem); + return -EBUSY; } - ret = hmm_range_fault(range, true); + ret = hmm_range_fault(range, 0); if (ret <= 0) { if (ret == 0) ret = -EBUSY; - up_read(&range->vma->vm_mm->mmap_sem); + up_read(&svmm->mm->mmap_sem); hmm_range_unregister(range); return ret; } @@ -682,7 +680,6 @@ nouveau_svm_fault(struct nvif_notify *notify) args.i.p.addr + args.i.p.size, fn - fi); /* Have HMM fault pages within the fault window to the GPU. */ - range.vma = vma; range.start = args.i.p.addr; range.end = args.i.p.addr + args.i.p.size; range.pfns = args.phys; @@ -690,7 +687,7 @@ nouveau_svm_fault(struct nvif_notify *notify) range.values = nouveau_svm_pfn_values; range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT; again: - ret = nouveau_range_fault(&svmm->mirror, &range); + ret = nouveau_range_fault(svmm, &range); if (ret == 0) { mutex_lock(&svmm->mutex); if (!nouveau_range_done(&range)) { diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c index b4e7404fe660..a11637b0f6cc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c @@ -40,8 +40,7 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) u8 *ptr = msg->buf; while (remaining) { - u8 cnt = (remaining > 16) ? 16 : remaining; - u8 cmd; + u8 cnt, retries, cmd; if (msg->flags & I2C_M_RD) cmd = 1; @@ -51,10 +50,19 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) if (mcnt || remaining > 16) cmd |= 4; /* MOT */ - ret = aux->func->xfer(aux, true, cmd, msg->addr, ptr, &cnt); - if (ret < 0) { - nvkm_i2c_aux_release(aux); - return ret; + for (retries = 0, cnt = 0; + retries < 32 && !cnt; + retries++) { + cnt = min_t(u8, remaining, 16); + ret = aux->func->xfer(aux, true, cmd, + msg->addr, ptr, &cnt); + if (ret < 0) + goto out; + } + if (!cnt) { + AUX_TRACE(aux, "no data after 32 retries"); + ret = -EIO; + goto out; } ptr += cnt; @@ -64,8 +72,10 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) msg++; } + ret = num; +out: nvkm_i2c_aux_release(aux); - return num; + return ret; } static u32 diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c index 84a2f243ed9b..4695f1c8e33f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c @@ -190,6 +190,9 @@ MODULE_FIRMWARE("nvidia/gp102/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/gp102/sec2/desc.bin"); MODULE_FIRMWARE("nvidia/gp102/sec2/image.bin"); MODULE_FIRMWARE("nvidia/gp102/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/gp102/sec2/desc-1.bin"); +MODULE_FIRMWARE("nvidia/gp102/sec2/image-1.bin"); +MODULE_FIRMWARE("nvidia/gp102/sec2/sig-1.bin"); MODULE_FIRMWARE("nvidia/gp104/acr/bl.bin"); MODULE_FIRMWARE("nvidia/gp104/acr/unload_bl.bin"); MODULE_FIRMWARE("nvidia/gp104/acr/ucode_load.bin"); @@ -210,6 +213,9 @@ MODULE_FIRMWARE("nvidia/gp104/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/gp104/sec2/desc.bin"); MODULE_FIRMWARE("nvidia/gp104/sec2/image.bin"); MODULE_FIRMWARE("nvidia/gp104/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/gp104/sec2/desc-1.bin"); +MODULE_FIRMWARE("nvidia/gp104/sec2/image-1.bin"); +MODULE_FIRMWARE("nvidia/gp104/sec2/sig-1.bin"); MODULE_FIRMWARE("nvidia/gp106/acr/bl.bin"); MODULE_FIRMWARE("nvidia/gp106/acr/unload_bl.bin"); MODULE_FIRMWARE("nvidia/gp106/acr/ucode_load.bin"); @@ -230,6 +236,9 @@ MODULE_FIRMWARE("nvidia/gp106/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/gp106/sec2/desc.bin"); MODULE_FIRMWARE("nvidia/gp106/sec2/image.bin"); MODULE_FIRMWARE("nvidia/gp106/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/gp106/sec2/desc-1.bin"); +MODULE_FIRMWARE("nvidia/gp106/sec2/image-1.bin"); +MODULE_FIRMWARE("nvidia/gp106/sec2/sig-1.bin"); MODULE_FIRMWARE("nvidia/gp107/acr/bl.bin"); MODULE_FIRMWARE("nvidia/gp107/acr/unload_bl.bin"); MODULE_FIRMWARE("nvidia/gp107/acr/ucode_load.bin"); @@ -250,3 +259,6 @@ MODULE_FIRMWARE("nvidia/gp107/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/gp107/sec2/desc.bin"); MODULE_FIRMWARE("nvidia/gp107/sec2/image.bin"); MODULE_FIRMWARE("nvidia/gp107/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/gp107/sec2/desc-1.bin"); +MODULE_FIRMWARE("nvidia/gp107/sec2/image-1.bin"); +MODULE_FIRMWARE("nvidia/gp107/sec2/sig-1.bin"); diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c index 785c5546067a..ed0ccbeed70f 100644 --- a/drivers/gpu/drm/omapdrm/dss/dispc.c +++ b/drivers/gpu/drm/omapdrm/dss/dispc.c @@ -4609,11 +4609,10 @@ static int dispc_errata_i734_wa_init(struct dispc_device *dispc) i734_buf.size = i734.ovli.width * i734.ovli.height * color_mode_to_bpp(i734.ovli.fourcc) / 8; - i734_buf.vaddr = dma_alloc_writecombine(&dispc->pdev->dev, - i734_buf.size, &i734_buf.paddr, - GFP_KERNEL); + i734_buf.vaddr = dma_alloc_wc(&dispc->pdev->dev, i734_buf.size, + &i734_buf.paddr, GFP_KERNEL); if (!i734_buf.vaddr) { - dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed\n", + dev_err(&dispc->pdev->dev, "%s: dma_alloc_wc failed\n", __func__); return -ENOMEM; } @@ -4626,8 +4625,8 @@ static void dispc_errata_i734_wa_fini(struct dispc_device *dispc) if (!dispc->feat->has_gamma_i734_bug) return; - dma_free_writecombine(&dispc->pdev->dev, i734_buf.size, i734_buf.vaddr, - i734_buf.paddr); + dma_free_wc(&dispc->pdev->dev, i734_buf.size, i734_buf.vaddr, + i734_buf.paddr); } static void dispc_errata_i734_wa(struct dispc_device *dispc) diff --git a/drivers/gpu/drm/omapdrm/dss/output.c b/drivers/gpu/drm/omapdrm/dss/output.c index de0f882f0f7b..14b41de44ebc 100644 --- a/drivers/gpu/drm/omapdrm/dss/output.c +++ b/drivers/gpu/drm/omapdrm/dss/output.c @@ -4,6 +4,7 @@ * Author: Archit Taneja <archit@ti.com> */ +#include <linux/bitops.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/platform_device.h> @@ -20,7 +21,8 @@ int omapdss_device_init_output(struct omap_dss_device *out) { struct device_node *remote_node; - remote_node = of_graph_get_remote_node(out->dev->of_node, 0, 0); + remote_node = of_graph_get_remote_node(out->dev->of_node, + ffs(out->of_ports) - 1, 0); if (!remote_node) { dev_dbg(out->dev, "failed to find video sink\n"); return 0; diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index 9f652d2e7af1..2983c003698e 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -675,7 +675,7 @@ static int pdev_probe(struct platform_device *pdev) if (omapdss_is_initialized() == false) return -EPROBE_DEFER; - ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (ret) { dev_err(&pdev->dev, "Failed to set the DMA mask\n"); return ret; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 6e7891ded464..bdd990568476 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -311,7 +311,7 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo) size_t pgsize = get_pgsize(iova, len - unmapped_len); if (ops->iova_to_phys(ops, iova)) { - unmapped_page = ops->unmap(ops, iova, pgsize); + unmapped_page = ops->unmap(ops, iova, pgsize, NULL); WARN_ON(unmapped_page != pgsize); } iova += pgsize; @@ -325,20 +325,28 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo) static void mmu_tlb_inv_context_s1(void *cookie) {} -static void mmu_tlb_inv_range_nosync(unsigned long iova, size_t size, - size_t granule, bool leaf, void *cookie) -{} - static void mmu_tlb_sync_context(void *cookie) { //struct panfrost_device *pfdev = cookie; // TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X } -static const struct iommu_gather_ops mmu_tlb_ops = { +static void mmu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule, + void *cookie) +{ + mmu_tlb_sync_context(cookie); +} + +static void mmu_tlb_flush_leaf(unsigned long iova, size_t size, size_t granule, + void *cookie) +{ + mmu_tlb_sync_context(cookie); +} + +static const struct iommu_flush_ops mmu_tlb_ops = { .tlb_flush_all = mmu_tlb_inv_context_s1, - .tlb_add_flush = mmu_tlb_inv_range_nosync, - .tlb_sync = mmu_tlb_sync_context, + .tlb_flush_walk = mmu_tlb_flush_walk, + .tlb_flush_leaf = mmu_tlb_flush_leaf, }; int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv) diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index c1802e01d9f6..265bfe9f8016 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -63,6 +63,11 @@ module_param_named(num_heads, qxl_num_crtc, int, 0400); static struct drm_driver qxl_driver; static struct pci_driver qxl_pci_driver; +static bool is_vga(struct pci_dev *pdev) +{ + return pdev->class == PCI_CLASS_DISPLAY_VGA << 8; +} + static int qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -87,9 +92,17 @@ qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) goto disable_pci; + if (is_vga(pdev)) { + ret = vga_get_interruptible(pdev, VGA_RSRC_LEGACY_IO); + if (ret) { + DRM_ERROR("can't get legacy vga ioports\n"); + goto disable_pci; + } + } + ret = qxl_device_init(qdev, &qxl_driver, pdev); if (ret) - goto disable_pci; + goto put_vga; ret = qxl_modeset_init(qdev); if (ret) @@ -109,6 +122,9 @@ modeset_cleanup: qxl_modeset_fini(qdev); unload: qxl_device_fini(qdev); +put_vga: + if (is_vga(pdev)) + vga_put(pdev, VGA_RSRC_LEGACY_IO); disable_pci: pci_disable_device(pdev); free_dev: @@ -126,6 +142,8 @@ qxl_pci_remove(struct pci_dev *pdev) qxl_modeset_fini(qdev); qxl_device_fini(qdev); + if (is_vga(pdev)) + vga_put(pdev, VGA_RSRC_LEGACY_IO); dev->dev_private = NULL; kfree(qdev); diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 05b88491ccb9..d59b004f6695 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2449,9 +2449,6 @@ struct radeon_device { /* tracking pinned memory */ u64 vram_pin_size; u64 gart_pin_size; - - struct mutex mn_lock; - DECLARE_HASHTABLE(mn_hash, 7); }; bool radeon_is_px(struct drm_device *dev); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 88eb7cb522bb..5d017f0aec66 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1325,8 +1325,6 @@ int radeon_device_init(struct radeon_device *rdev, init_rwsem(&rdev->pm.mclk_lock); init_rwsem(&rdev->exclusive_lock); init_waitqueue_head(&rdev->irq.vblank_queue); - mutex_init(&rdev->mn_lock); - hash_init(rdev->mn_hash); r = radeon_gem_init(rdev); if (r) return r; diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 4267cb55bc33..d0bc91ed7c90 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -35,6 +35,7 @@ #include <linux/module.h> #include <linux/pm_runtime.h> #include <linux/vga_switcheroo.h> +#include <linux/mmu_notifier.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> @@ -654,6 +655,7 @@ static void __exit radeon_exit(void) { pci_unregister_driver(pdriver); radeon_unregister_atpx_handler(); + mmu_notifier_synchronize(); } module_init(radeon_init); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 4cf58dbbe439..b2b076606f54 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -296,6 +296,8 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data, uint32_t handle; int r; + args->addr = untagged_addr(args->addr); + if (offset_in_page(args->addr | args->size)) return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index 6902f998ede9..dbab9a3a969b 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -37,17 +37,8 @@ #include "radeon.h" struct radeon_mn { - /* constant after initialisation */ - struct radeon_device *rdev; - struct mm_struct *mm; struct mmu_notifier mn; - /* only used on destruction */ - struct work_struct work; - - /* protected by rdev->mn_lock */ - struct hlist_node node; - /* objects protected by lock */ struct mutex lock; struct rb_root_cached objects; @@ -59,55 +50,6 @@ struct radeon_mn_node { }; /** - * radeon_mn_destroy - destroy the rmn - * - * @work: previously sheduled work item - * - * Lazy destroys the notifier from a work item - */ -static void radeon_mn_destroy(struct work_struct *work) -{ - struct radeon_mn *rmn = container_of(work, struct radeon_mn, work); - struct radeon_device *rdev = rmn->rdev; - struct radeon_mn_node *node, *next_node; - struct radeon_bo *bo, *next_bo; - - mutex_lock(&rdev->mn_lock); - mutex_lock(&rmn->lock); - hash_del(&rmn->node); - rbtree_postorder_for_each_entry_safe(node, next_node, - &rmn->objects.rb_root, it.rb) { - - interval_tree_remove(&node->it, &rmn->objects); - list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) { - bo->mn = NULL; - list_del_init(&bo->mn_list); - } - kfree(node); - } - mutex_unlock(&rmn->lock); - mutex_unlock(&rdev->mn_lock); - mmu_notifier_unregister(&rmn->mn, rmn->mm); - kfree(rmn); -} - -/** - * radeon_mn_release - callback to notify about mm destruction - * - * @mn: our notifier - * @mn: the mm this callback is about - * - * Shedule a work item to lazy destroy our notifier. - */ -static void radeon_mn_release(struct mmu_notifier *mn, - struct mm_struct *mm) -{ - struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn); - INIT_WORK(&rmn->work, radeon_mn_destroy); - schedule_work(&rmn->work); -} - -/** * radeon_mn_invalidate_range_start - callback to notify about mm change * * @mn: our notifier @@ -183,65 +125,44 @@ out_unlock: return ret; } -static const struct mmu_notifier_ops radeon_mn_ops = { - .release = radeon_mn_release, - .invalidate_range_start = radeon_mn_invalidate_range_start, -}; +static void radeon_mn_release(struct mmu_notifier *mn, struct mm_struct *mm) +{ + struct mmu_notifier_range range = { + .mm = mm, + .start = 0, + .end = ULONG_MAX, + .flags = 0, + .event = MMU_NOTIFY_UNMAP, + }; + + radeon_mn_invalidate_range_start(mn, &range); +} -/** - * radeon_mn_get - create notifier context - * - * @rdev: radeon device pointer - * - * Creates a notifier context for current->mm. - */ -static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev) +static struct mmu_notifier *radeon_mn_alloc_notifier(struct mm_struct *mm) { - struct mm_struct *mm = current->mm; struct radeon_mn *rmn; - int r; - - if (down_write_killable(&mm->mmap_sem)) - return ERR_PTR(-EINTR); - - mutex_lock(&rdev->mn_lock); - - hash_for_each_possible(rdev->mn_hash, rmn, node, (unsigned long)mm) - if (rmn->mm == mm) - goto release_locks; rmn = kzalloc(sizeof(*rmn), GFP_KERNEL); - if (!rmn) { - rmn = ERR_PTR(-ENOMEM); - goto release_locks; - } + if (!rmn) + return ERR_PTR(-ENOMEM); - rmn->rdev = rdev; - rmn->mm = mm; - rmn->mn.ops = &radeon_mn_ops; mutex_init(&rmn->lock); rmn->objects = RB_ROOT_CACHED; - - r = __mmu_notifier_register(&rmn->mn, mm); - if (r) - goto free_rmn; - - hash_add(rdev->mn_hash, &rmn->node, (unsigned long)mm); - -release_locks: - mutex_unlock(&rdev->mn_lock); - up_write(&mm->mmap_sem); - - return rmn; - -free_rmn: - mutex_unlock(&rdev->mn_lock); - up_write(&mm->mmap_sem); - kfree(rmn); + return &rmn->mn; +} - return ERR_PTR(r); +static void radeon_mn_free_notifier(struct mmu_notifier *mn) +{ + kfree(container_of(mn, struct radeon_mn, mn)); } +static const struct mmu_notifier_ops radeon_mn_ops = { + .release = radeon_mn_release, + .invalidate_range_start = radeon_mn_invalidate_range_start, + .alloc_notifier = radeon_mn_alloc_notifier, + .free_notifier = radeon_mn_free_notifier, +}; + /** * radeon_mn_register - register a BO for notifier updates * @@ -254,15 +175,16 @@ free_rmn: int radeon_mn_register(struct radeon_bo *bo, unsigned long addr) { unsigned long end = addr + radeon_bo_size(bo) - 1; - struct radeon_device *rdev = bo->rdev; + struct mmu_notifier *mn; struct radeon_mn *rmn; struct radeon_mn_node *node = NULL; struct list_head bos; struct interval_tree_node *it; - rmn = radeon_mn_get(rdev); - if (IS_ERR(rmn)) - return PTR_ERR(rmn); + mn = mmu_notifier_get(&radeon_mn_ops, current->mm); + if (IS_ERR(mn)) + return PTR_ERR(mn); + rmn = container_of(mn, struct radeon_mn, mn); INIT_LIST_HEAD(&bos); @@ -309,22 +231,16 @@ int radeon_mn_register(struct radeon_bo *bo, unsigned long addr) */ void radeon_mn_unregister(struct radeon_bo *bo) { - struct radeon_device *rdev = bo->rdev; - struct radeon_mn *rmn; + struct radeon_mn *rmn = bo->mn; struct list_head *head; - mutex_lock(&rdev->mn_lock); - rmn = bo->mn; - if (rmn == NULL) { - mutex_unlock(&rdev->mn_lock); + if (!rmn) return; - } mutex_lock(&rmn->lock); /* save the next list entry for later */ head = bo->mn_list.next; - bo->mn = NULL; list_del(&bo->mn_list); if (list_empty(head)) { @@ -335,5 +251,7 @@ void radeon_mn_unregister(struct radeon_bo *bo) } mutex_unlock(&rmn->lock); - mutex_unlock(&rdev->mn_lock); + + mmu_notifier_put(&rmn->mn); + bo->mn = NULL; } diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c index 52c5f1ab8277..3fc7e6899cab 100644 --- a/drivers/gpu/drm/rcar-du/rcar_lvds.c +++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c @@ -673,10 +673,8 @@ static int rcar_lvds_parse_dt_companion(struct rcar_lvds *lvds) /* Locate the companion LVDS encoder for dual-link operation, if any. */ companion = of_parse_phandle(dev->of_node, "renesas,companion", 0); - if (!companion) { - dev_err(dev, "Companion LVDS encoder not found\n"); - return -ENXIO; - } + if (!companion) + return 0; /* * Sanity check: the companion encoder must have the same compatible diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index 7d7cb57410fc..f38f5e113c6b 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -436,7 +436,7 @@ static int rockchip_dp_resume(struct device *dev) static const struct dev_pm_ops rockchip_dp_pm_ops = { #ifdef CONFIG_PM_SLEEP - .suspend = rockchip_dp_suspend, + .suspend_late = rockchip_dp_suspend, .resume_early = rockchip_dp_resume, #endif }; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 30c177eb3022..20ecb1508a22 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -329,8 +329,7 @@ static struct component_match *rockchip_drm_match_add(struct device *dev) struct device *p = NULL, *d; do { - d = bus_find_device(&platform_bus_type, p, &drv->driver, - (void *)platform_bus_type.match); + d = platform_find_device_by_driver(p, &drv->driver); put_device(p); p = d; diff --git a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h index b45824ec7c8f..6d61a0eb5d64 100644 --- a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h +++ b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h @@ -9,6 +9,13 @@ #define cmdline_test(test) selftest(test, test) +cmdline_test(drm_cmdline_test_force_d_only) +cmdline_test(drm_cmdline_test_force_D_only_dvi) +cmdline_test(drm_cmdline_test_force_D_only_hdmi) +cmdline_test(drm_cmdline_test_force_D_only_not_digital) +cmdline_test(drm_cmdline_test_force_e_only) +cmdline_test(drm_cmdline_test_margin_only) +cmdline_test(drm_cmdline_test_interlace_only) cmdline_test(drm_cmdline_test_res) cmdline_test(drm_cmdline_test_res_missing_x) cmdline_test(drm_cmdline_test_res_missing_y) diff --git a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c index 14c96edb13df..013de9d27c35 100644 --- a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c +++ b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c @@ -17,6 +17,136 @@ static const struct drm_connector no_connector = {}; +static int drm_cmdline_test_force_e_only(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(!drm_mode_parse_command_line_for_connector("e", + &no_connector, + &mode)); + FAIL_ON(mode.specified); + FAIL_ON(mode.refresh_specified); + FAIL_ON(mode.bpp_specified); + + FAIL_ON(mode.rb); + FAIL_ON(mode.cvt); + FAIL_ON(mode.interlace); + FAIL_ON(mode.margins); + FAIL_ON(mode.force != DRM_FORCE_ON); + + return 0; +} + +static int drm_cmdline_test_force_D_only_not_digital(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(!drm_mode_parse_command_line_for_connector("D", + &no_connector, + &mode)); + FAIL_ON(mode.specified); + FAIL_ON(mode.refresh_specified); + FAIL_ON(mode.bpp_specified); + + FAIL_ON(mode.rb); + FAIL_ON(mode.cvt); + FAIL_ON(mode.interlace); + FAIL_ON(mode.margins); + FAIL_ON(mode.force != DRM_FORCE_ON); + + return 0; +} + +static const struct drm_connector connector_hdmi = { + .connector_type = DRM_MODE_CONNECTOR_HDMIB, +}; + +static int drm_cmdline_test_force_D_only_hdmi(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(!drm_mode_parse_command_line_for_connector("D", + &connector_hdmi, + &mode)); + FAIL_ON(mode.specified); + FAIL_ON(mode.refresh_specified); + FAIL_ON(mode.bpp_specified); + + FAIL_ON(mode.rb); + FAIL_ON(mode.cvt); + FAIL_ON(mode.interlace); + FAIL_ON(mode.margins); + FAIL_ON(mode.force != DRM_FORCE_ON_DIGITAL); + + return 0; +} + +static const struct drm_connector connector_dvi = { + .connector_type = DRM_MODE_CONNECTOR_DVII, +}; + +static int drm_cmdline_test_force_D_only_dvi(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(!drm_mode_parse_command_line_for_connector("D", + &connector_dvi, + &mode)); + FAIL_ON(mode.specified); + FAIL_ON(mode.refresh_specified); + FAIL_ON(mode.bpp_specified); + + FAIL_ON(mode.rb); + FAIL_ON(mode.cvt); + FAIL_ON(mode.interlace); + FAIL_ON(mode.margins); + FAIL_ON(mode.force != DRM_FORCE_ON_DIGITAL); + + return 0; +} + +static int drm_cmdline_test_force_d_only(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(!drm_mode_parse_command_line_for_connector("d", + &no_connector, + &mode)); + FAIL_ON(mode.specified); + FAIL_ON(mode.refresh_specified); + FAIL_ON(mode.bpp_specified); + + FAIL_ON(mode.rb); + FAIL_ON(mode.cvt); + FAIL_ON(mode.interlace); + FAIL_ON(mode.margins); + FAIL_ON(mode.force != DRM_FORCE_OFF); + + return 0; +} + +static int drm_cmdline_test_margin_only(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(drm_mode_parse_command_line_for_connector("m", + &no_connector, + &mode)); + + return 0; +} + +static int drm_cmdline_test_interlace_only(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(drm_mode_parse_command_line_for_connector("i", + &no_connector, + &mode)); + + return 0; +} + static int drm_cmdline_test_res(void *ignored) { struct drm_cmdline_mode mode = { }; diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 690aeb822704..04c721d0d3b9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -316,6 +316,7 @@ static void sun4i_tcon0_mode_set_dithering(struct sun4i_tcon *tcon, /* R and B components are only 5 bits deep */ val |= SUN4I_TCON0_FRM_CTL_MODE_R; val |= SUN4I_TCON0_FRM_CTL_MODE_B; + /* Fall through */ case MEDIA_BUS_FMT_RGB666_1X18: case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: /* Fall through: enable dithering */ diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 472f73985deb..1636344ba9ec 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -994,6 +994,7 @@ static ssize_t sun6i_dsi_transfer(struct mipi_dsi_host *host, ret = sun6i_dsi_dcs_read(dsi, msg); break; } + /* Else, fall through */ default: ret = -EINVAL; diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 274cb955e2e1..bdcaa4c7168c 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -126,8 +126,12 @@ int tegra_output_probe(struct tegra_output *output) "nvidia,hpd-gpio", 0, GPIOD_IN, "HDMI hotplug detect"); - if (IS_ERR(output->hpd_gpio)) - return PTR_ERR(output->hpd_gpio); + if (IS_ERR(output->hpd_gpio)) { + if (PTR_ERR(output->hpd_gpio) != -ENOENT) + return PTR_ERR(output->hpd_gpio); + + output->hpd_gpio = NULL; + } if (output->hpd_gpio) { err = gpiod_to_irq(output->hpd_gpio); diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 048c70a7b592..5e6fb6c2307f 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -240,8 +240,7 @@ static void vc4_match_add_drivers(struct device *dev, struct device_driver *drv = &drivers[i]->driver; struct device *p = NULL, *d; - while ((d = bus_find_device(&platform_bus_type, p, drv, - (void *)platform_bus_type.match))) { + while ((d = platform_find_device_by_driver(p, drv))) { put_device(p); component_match_add(dev, match, compare_dev, d); p = d; diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index feaa538026a0..3db000aacd26 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -174,7 +174,6 @@ via_map_blit_for_device(struct pci_dev *pdev, static void via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg) { - struct page *page; int i; switch (vsg->state) { @@ -189,13 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg) kfree(vsg->desc_pages); /* fall through */ case dr_via_pages_locked: - for (i = 0; i < vsg->num_pages; ++i) { - if (NULL != (page = vsg->pages[i])) { - if (!PageReserved(page) && (DMA_FROM_DEVICE == vsg->direction)) - SetPageDirty(page); - put_page(page); - } - } + put_user_pages_dirty_lock(vsg->pages, vsg->num_pages, + (vsg->direction == DMA_FROM_DEVICE)); /* fall through */ case dr_via_pages_alloc: vfree(vsg->pages); diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index b2da31310d24..09b526518f5a 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -204,6 +204,7 @@ int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev, .interruptible = false, .no_wait_gpu = false }; + size_t max_segment; /* wtf swapping */ if (bo->pages) @@ -215,8 +216,13 @@ int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev, if (!bo->pages) goto out; - ret = sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, GFP_KERNEL); + max_segment = virtio_max_dma_size(qdev->vdev); + max_segment &= PAGE_MASK; + if (max_segment > SCATTERLIST_MAX_SEGMENT) + max_segment = SCATTERLIST_MAX_SEGMENT; + ret = __sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0, + nr_pages << PAGE_SHIFT, + max_segment, GFP_KERNEL); if (ret) goto out; return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 81a86c3b77bc..b6c5e4c2ac3c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -45,8 +45,6 @@ #define RETRIES 3 #define VMW_HYPERVISOR_MAGIC 0x564D5868 -#define VMW_HYPERVISOR_PORT 0x5658 -#define VMW_HYPERVISOR_HB_PORT 0x5659 #define VMW_PORT_CMD_MSG 30 #define VMW_PORT_CMD_HB_MSG 0 @@ -92,7 +90,7 @@ static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol) VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL, (protocol | GUESTMSG_FLAG_COOKIE), si, di, - VMW_HYPERVISOR_PORT, + 0, VMW_HYPERVISOR_MAGIC, eax, ebx, ecx, edx, si, di); @@ -125,7 +123,7 @@ static int vmw_close_channel(struct rpc_channel *channel) VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL, 0, si, di, - (VMW_HYPERVISOR_PORT | (channel->channel_id << 16)), + channel->channel_id << 16, VMW_HYPERVISOR_MAGIC, eax, ebx, ecx, edx, si, di); @@ -159,7 +157,8 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, VMW_PORT_HB_OUT( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, msg_len, si, di, - VMW_HYPERVISOR_HB_PORT | (channel->channel_id << 16), + VMWARE_HYPERVISOR_HB | (channel->channel_id << 16) | + VMWARE_HYPERVISOR_OUT, VMW_HYPERVISOR_MAGIC, bp, eax, ebx, ecx, edx, si, di); @@ -180,7 +179,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16), word, si, di, - VMW_HYPERVISOR_PORT | (channel->channel_id << 16), + channel->channel_id << 16, VMW_HYPERVISOR_MAGIC, eax, ebx, ecx, edx, si, di); } @@ -212,7 +211,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, VMW_PORT_HB_IN( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, reply_len, si, di, - VMW_HYPERVISOR_HB_PORT | (channel->channel_id << 16), + VMWARE_HYPERVISOR_HB | (channel->channel_id << 16), VMW_HYPERVISOR_MAGIC, bp, eax, ebx, ecx, edx, si, di); @@ -229,7 +228,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_RECVPAYLOAD << 16), MESSAGE_STATUS_SUCCESS, si, di, - VMW_HYPERVISOR_PORT | (channel->channel_id << 16), + channel->channel_id << 16, VMW_HYPERVISOR_MAGIC, eax, ebx, ecx, edx, si, di); @@ -268,7 +267,7 @@ static int vmw_send_msg(struct rpc_channel *channel, const char *msg) VMW_PORT(VMW_PORT_CMD_SENDSIZE, msg_len, si, di, - VMW_HYPERVISOR_PORT | (channel->channel_id << 16), + channel->channel_id << 16, VMW_HYPERVISOR_MAGIC, eax, ebx, ecx, edx, si, di); @@ -326,7 +325,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, VMW_PORT(VMW_PORT_CMD_RECVSIZE, 0, si, di, - (VMW_HYPERVISOR_PORT | (channel->channel_id << 16)), + channel->channel_id << 16, VMW_HYPERVISOR_MAGIC, eax, ebx, ecx, edx, si, di); @@ -352,7 +351,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, !!(HIGH_WORD(ecx) & MESSAGE_STATUS_HB)); if ((HIGH_WORD(ebx) & MESSAGE_STATUS_SUCCESS) == 0) { kfree(reply); - + reply = NULL; if ((HIGH_WORD(ebx) & MESSAGE_STATUS_CPT) != 0) { /* A checkpoint occurred. Retry. */ continue; @@ -370,13 +369,13 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, VMW_PORT(VMW_PORT_CMD_RECVSTATUS, MESSAGE_STATUS_SUCCESS, si, di, - (VMW_HYPERVISOR_PORT | (channel->channel_id << 16)), + channel->channel_id << 16, VMW_HYPERVISOR_MAGIC, eax, ebx, ecx, edx, si, di); if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) { kfree(reply); - + reply = NULL; if ((HIGH_WORD(ecx) & MESSAGE_STATUS_CPT) != 0) { /* A checkpoint occurred. Retry. */ continue; @@ -388,7 +387,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg, break; } - if (retries == RETRIES) + if (!reply) return -EINVAL; *msg_len = reply_len; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h index 4907e50fb20a..f685c7071dec 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h @@ -32,6 +32,7 @@ #ifndef _VMWGFX_MSG_H #define _VMWGFX_MSG_H +#include <asm/vmware.h> /** * Hypervisor-specific bi-directional communication channel. Should never @@ -44,7 +45,7 @@ * @in_ebx: [IN] Message Len, through EBX * @in_si: [IN] Input argument through SI, set to 0 if not used * @in_di: [IN] Input argument through DI, set ot 0 if not used - * @port_num: [IN] port number + [channel id] + * @flags: [IN] hypercall flags + [channel id] * @magic: [IN] hypervisor magic value * @eax: [OUT] value of EAX register * @ebx: [OUT] e.g. status from an HB message status command @@ -54,10 +55,10 @@ * @di: [OUT] */ #define VMW_PORT(cmd, in_ebx, in_si, in_di, \ - port_num, magic, \ + flags, magic, \ eax, ebx, ecx, edx, si, di) \ ({ \ - asm volatile ("inl %%dx, %%eax;" : \ + asm volatile (VMWARE_HYPERCALL : \ "=a"(eax), \ "=b"(ebx), \ "=c"(ecx), \ @@ -67,7 +68,7 @@ "a"(magic), \ "b"(in_ebx), \ "c"(cmd), \ - "d"(port_num), \ + "d"(flags), \ "S"(in_si), \ "D"(in_di) : \ "memory"); \ @@ -85,7 +86,7 @@ * @in_ecx: [IN] Message Len, through ECX * @in_si: [IN] Input argument through SI, set to 0 if not used * @in_di: [IN] Input argument through DI, set to 0 if not used - * @port_num: [IN] port number + [channel id] + * @flags: [IN] hypercall flags + [channel id] * @magic: [IN] hypervisor magic value * @bp: [IN] * @eax: [OUT] value of EAX register @@ -98,12 +99,12 @@ #ifdef __x86_64__ #define VMW_PORT_HB_OUT(cmd, in_ecx, in_si, in_di, \ - port_num, magic, bp, \ + flags, magic, bp, \ eax, ebx, ecx, edx, si, di) \ ({ \ asm volatile ("push %%rbp;" \ "mov %12, %%rbp;" \ - "rep outsb;" \ + VMWARE_HYPERCALL_HB_OUT \ "pop %%rbp;" : \ "=a"(eax), \ "=b"(ebx), \ @@ -114,7 +115,7 @@ "a"(magic), \ "b"(cmd), \ "c"(in_ecx), \ - "d"(port_num), \ + "d"(flags), \ "S"(in_si), \ "D"(in_di), \ "r"(bp) : \ @@ -123,12 +124,12 @@ #define VMW_PORT_HB_IN(cmd, in_ecx, in_si, in_di, \ - port_num, magic, bp, \ + flags, magic, bp, \ eax, ebx, ecx, edx, si, di) \ ({ \ asm volatile ("push %%rbp;" \ "mov %12, %%rbp;" \ - "rep insb;" \ + VMWARE_HYPERCALL_HB_IN \ "pop %%rbp" : \ "=a"(eax), \ "=b"(ebx), \ @@ -139,7 +140,7 @@ "a"(magic), \ "b"(cmd), \ "c"(in_ecx), \ - "d"(port_num), \ + "d"(flags), \ "S"(in_si), \ "D"(in_di), \ "r"(bp) : \ @@ -157,13 +158,13 @@ * just pushed it. */ #define VMW_PORT_HB_OUT(cmd, in_ecx, in_si, in_di, \ - port_num, magic, bp, \ + flags, magic, bp, \ eax, ebx, ecx, edx, si, di) \ ({ \ asm volatile ("push %12;" \ "push %%ebp;" \ "mov 0x04(%%esp), %%ebp;" \ - "rep outsb;" \ + VMWARE_HYPERCALL_HB_OUT \ "pop %%ebp;" \ "add $0x04, %%esp;" : \ "=a"(eax), \ @@ -175,7 +176,7 @@ "a"(magic), \ "b"(cmd), \ "c"(in_ecx), \ - "d"(port_num), \ + "d"(flags), \ "S"(in_si), \ "D"(in_di), \ "m"(bp) : \ @@ -184,13 +185,13 @@ #define VMW_PORT_HB_IN(cmd, in_ecx, in_si, in_di, \ - port_num, magic, bp, \ + flags, magic, bp, \ eax, ebx, ecx, edx, si, di) \ ({ \ asm volatile ("push %12;" \ "push %%ebp;" \ "mov 0x04(%%esp), %%ebp;" \ - "rep insb;" \ + VMWARE_HYPERCALL_HB_IN \ "pop %%ebp;" \ "add $0x04, %%esp;" : \ "=a"(eax), \ @@ -202,7 +203,7 @@ "a"(magic), \ "b"(cmd), \ "c"(in_ecx), \ - "d"(port_num), \ + "d"(flags), \ "S"(in_si), \ "D"(in_di), \ "m"(bp) : \ |