diff options
Diffstat (limited to 'drivers/gpu')
187 files changed, 12801 insertions, 5907 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 5e43178d..3fa1397 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -79,6 +79,8 @@ extern int amdgpu_bapm; extern int amdgpu_deep_color; extern int amdgpu_vm_size; extern int amdgpu_vm_block_size; +extern int amdgpu_vm_fault_stop; +extern int amdgpu_vm_debug; extern int amdgpu_enable_scheduler; extern int amdgpu_sched_jobs; extern int amdgpu_sched_hw_submission; @@ -960,6 +962,11 @@ struct amdgpu_ring { #define AMDGPU_PTE_FRAG_64KB (4 << 7) #define AMDGPU_LOG2_PAGES_PER_FRAG 4 +/* How to programm VM fault handling */ +#define AMDGPU_VM_FAULT_STOP_NEVER 0 +#define AMDGPU_VM_FAULT_STOP_FIRST 1 +#define AMDGPU_VM_FAULT_STOP_ALWAYS 2 + struct amdgpu_vm_pt { struct amdgpu_bo *bo; uint64_t addr; @@ -1708,7 +1715,7 @@ struct amdgpu_vce { /* * SDMA */ -struct amdgpu_sdma { +struct amdgpu_sdma_instance { /* SDMA firmware */ const struct firmware *fw; uint32_t fw_version; @@ -1718,6 +1725,13 @@ struct amdgpu_sdma { bool burst_nop; }; +struct amdgpu_sdma { + struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES]; + struct amdgpu_irq_src trap_irq; + struct amdgpu_irq_src illegal_inst_irq; + int num_instances; +}; + /* * Firmware */ @@ -2064,9 +2078,7 @@ struct amdgpu_device { struct amdgpu_gfx gfx; /* sdma */ - struct amdgpu_sdma sdma[AMDGPU_MAX_SDMA_INSTANCES]; - struct amdgpu_irq_src sdma_trap_irq; - struct amdgpu_irq_src sdma_illegal_inst_irq; + struct amdgpu_sdma sdma; /* uvd */ bool has_uvd; @@ -2203,17 +2215,18 @@ static inline void amdgpu_ring_write(struct amdgpu_ring *ring, uint32_t v) ring->ring_free_dw--; } -static inline struct amdgpu_sdma * amdgpu_get_sdma_instance(struct amdgpu_ring *ring) +static inline struct amdgpu_sdma_instance * +amdgpu_get_sdma_instance(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; int i; - for (i = 0; i < AMDGPU_MAX_SDMA_INSTANCES; i++) - if (&adev->sdma[i].ring == ring) + for (i = 0; i < adev->sdma.num_instances; i++) + if (&adev->sdma.instance[i].ring == ring) break; if (i < AMDGPU_MAX_SDMA_INSTANCES) - return &adev->sdma[i]; + return &adev->sdma.instance[i]; else return NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index aef4a7a..a142d5a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -25,7 +25,6 @@ #include <linux/acpi.h> #include <linux/slab.h> #include <linux/power_supply.h> -#include <linux/vga_switcheroo.h> #include <acpi/video.h> #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index dd2037b..0e13763 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -649,12 +649,12 @@ static uint16_t get_fw_version(struct kgd_dev *kgd, enum kgd_engine_type type) case KGD_ENGINE_SDMA1: hdr = (const union amdgpu_firmware_header *) - adev->sdma[0].fw->data; + adev->sdma.instance[0].fw->data; break; case KGD_ENGINE_SDMA2: hdr = (const union amdgpu_firmware_header *) - adev->sdma[1].fw->data; + adev->sdma.instance[1].fw->data; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c index dfd1d50..79fa5c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c @@ -523,12 +523,12 @@ static uint16_t get_fw_version(struct kgd_dev *kgd, enum kgd_engine_type type) case KGD_ENGINE_SDMA1: hdr = (const union amdgpu_firmware_header *) - adev->sdma[0].fw->data; + adev->sdma.instance[0].fw->data; break; case KGD_ENGINE_SDMA2: hdr = (const union amdgpu_firmware_header *) - adev->sdma[1].fw->data; + adev->sdma.instance[1].fw->data; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 3f7aaa4..1a6b239 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -536,7 +536,7 @@ static bool amdgpu_atpx_detect(void) if (has_atpx && vga_count == 2) { acpi_get_name(amdgpu_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer); - printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n", + printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); amdgpu_atpx_priv.atpx_detected = true; return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 02add0a..c44c0c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -29,7 +29,6 @@ #include "amdgpu.h" #include "atom.h" -#include <linux/vga_switcheroo.h> #include <linux/slab.h> #include <linux/acpi.h> /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 1c3fc99..8e99514 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -208,44 +208,6 @@ static int amdgpu_cgs_alloc_gpu_mem(void *cgs_device, return ret; } -static int amdgpu_cgs_import_gpu_mem(void *cgs_device, int dmabuf_fd, - cgs_handle_t *handle) -{ - CGS_FUNC_ADEV; - int r; - uint32_t dma_handle; - struct drm_gem_object *obj; - struct amdgpu_bo *bo; - struct drm_device *dev = adev->ddev; - struct drm_file *file_priv = NULL, *priv; - - mutex_lock(&dev->struct_mutex); - list_for_each_entry(priv, &dev->filelist, lhead) { - rcu_read_lock(); - if (priv->pid == get_pid(task_pid(current))) - file_priv = priv; - rcu_read_unlock(); - if (file_priv) - break; - } - mutex_unlock(&dev->struct_mutex); - r = dev->driver->prime_fd_to_handle(dev, - file_priv, dmabuf_fd, - &dma_handle); - spin_lock(&file_priv->table_lock); - - /* Check if we currently have a reference on the object */ - obj = idr_find(&file_priv->object_idr, dma_handle); - if (obj == NULL) { - spin_unlock(&file_priv->table_lock); - return -EINVAL; - } - spin_unlock(&file_priv->table_lock); - bo = gem_to_amdgpu_bo(obj); - *handle = (cgs_handle_t)bo; - return 0; -} - static int amdgpu_cgs_free_gpu_mem(void *cgs_device, cgs_handle_t handle) { struct amdgpu_bo *obj = (struct amdgpu_bo *)handle; @@ -810,7 +772,6 @@ static const struct cgs_ops amdgpu_cgs_ops = { }; static const struct cgs_os_ops amdgpu_cgs_os_ops = { - amdgpu_cgs_import_gpu_mem, amdgpu_cgs_add_irq_source, amdgpu_cgs_irq_get, amdgpu_cgs_irq_put diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 749420f..baf0061 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -104,10 +104,11 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, } break; case AMDGPU_HW_IP_DMA: - if (ring < 2) { - *out_ring = &adev->sdma[ring].ring; + if (ring < adev->sdma.num_instances) { + *out_ring = &adev->sdma.instance[ring].ring; } else { - DRM_ERROR("only two SDMA rings are supported\n"); + DRM_ERROR("only %d SDMA rings are supported\n", + adev->sdma.num_instances); return -EINVAL; } break; @@ -156,7 +157,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) uint64_t *chunk_array_user; uint64_t *chunk_array; struct amdgpu_fpriv *fpriv = p->filp->driver_priv; - unsigned size, i; + unsigned size; + int i; int ret; if (cs->in.num_chunks == 0) @@ -176,7 +178,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) /* get chunks */ INIT_LIST_HEAD(&p->validated); - chunk_array_user = (uint64_t __user *)(cs->in.chunks); + chunk_array_user = (uint64_t __user *)(unsigned long)(cs->in.chunks); if (copy_from_user(chunk_array, chunk_array_user, sizeof(uint64_t)*cs->in.num_chunks)) { ret = -EFAULT; @@ -196,7 +198,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) struct drm_amdgpu_cs_chunk user_chunk; uint32_t __user *cdata; - chunk_ptr = (void __user *)chunk_array[i]; + chunk_ptr = (void __user *)(unsigned long)chunk_array[i]; if (copy_from_user(&user_chunk, chunk_ptr, sizeof(struct drm_amdgpu_cs_chunk))) { ret = -EFAULT; @@ -207,7 +209,7 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) p->chunks[i].length_dw = user_chunk.length_dw; size = p->chunks[i].length_dw; - cdata = (void __user *)user_chunk.chunk_data; + cdata = (void __user *)(unsigned long)user_chunk.chunk_data; p->chunks[i].user_ptr = cdata; p->chunks[i].kdata = drm_malloc_ab(size, sizeof(uint32_t)); @@ -566,9 +568,24 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p, if (r) return r; } + } - return amdgpu_vm_clear_invalids(adev, vm, &p->ibs[0].sync); + r = amdgpu_vm_clear_invalids(adev, vm, &p->ibs[0].sync); + + if (amdgpu_vm_debug && p->bo_list) { + /* Invalidate all BOs to test for userspace bugs */ + for (i = 0; i < p->bo_list->num_entries; i++) { + /* ignore duplicates */ + bo = p->bo_list->array[i].robj; + if (!bo) + continue; + + amdgpu_vm_bo_invalidate(adev, bo); + } + } + + return r; } static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6068d82..901a460 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1022,7 +1022,7 @@ static void amdgpu_check_arguments(struct amdgpu_device *adev) * amdgpu_switcheroo_set_state - set switcheroo state * * @pdev: pci dev pointer - * @state: vga switcheroo state + * @state: vga_switcheroo state * * Callback for the switcheroo driver. Suspends or resumes the * the asics before or after it is powered up using ACPI methods. @@ -1657,11 +1657,21 @@ int amdgpu_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon) } drm_modeset_unlock_all(dev); - /* unpin the front buffers */ + /* unpin the front buffers and cursors */ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct amdgpu_framebuffer *rfb = to_amdgpu_framebuffer(crtc->primary->fb); struct amdgpu_bo *robj; + if (amdgpu_crtc->cursor_bo) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, false); + if (r == 0) { + amdgpu_bo_unpin(aobj); + amdgpu_bo_unreserve(aobj); + } + } + if (rfb == NULL || rfb->obj == NULL) { continue; } @@ -1713,6 +1723,7 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) { struct drm_connector *connector; struct amdgpu_device *adev = dev->dev_private; + struct drm_crtc *crtc; int r; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) @@ -1746,6 +1757,24 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) if (r) return r; + /* pin cursors */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + + if (amdgpu_crtc->cursor_bo) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, false); + if (r == 0) { + r = amdgpu_bo_pin(aobj, + AMDGPU_GEM_DOMAIN_VRAM, + &amdgpu_crtc->cursor_addr); + if (r != 0) + DRM_ERROR("Failed to pin cursor BO (%d)\n", r); + amdgpu_bo_unreserve(aobj); + } + } + } + /* blat the mode back in */ if (fbcon) { drm_helper_resume_force_mode(dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index adb4835..ef58774 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -75,11 +75,13 @@ int amdgpu_bapm = -1; int amdgpu_deep_color = 0; int amdgpu_vm_size = 8; int amdgpu_vm_block_size = -1; +int amdgpu_vm_fault_stop = 0; +int amdgpu_vm_debug = 0; int amdgpu_exp_hw_support = 0; -int amdgpu_enable_scheduler = 0; +int amdgpu_enable_scheduler = 1; int amdgpu_sched_jobs = 16; int amdgpu_sched_hw_submission = 2; -int amdgpu_enable_semaphores = 1; +int amdgpu_enable_semaphores = 0; MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes"); module_param_named(vramlimit, amdgpu_vram_limit, int, 0600); @@ -141,10 +143,16 @@ module_param_named(vm_size, amdgpu_vm_size, int, 0444); MODULE_PARM_DESC(vm_block_size, "VM page table size in bits (default depending on vm_size)"); module_param_named(vm_block_size, amdgpu_vm_block_size, int, 0444); +MODULE_PARM_DESC(vm_fault_stop, "Stop on VM fault (0 = never (default), 1 = print first, 2 = always)"); +module_param_named(vm_fault_stop, amdgpu_vm_fault_stop, int, 0444); + +MODULE_PARM_DESC(vm_debug, "Debug VM handling (0 = disabled (default), 1 = enabled)"); +module_param_named(vm_debug, amdgpu_vm_debug, int, 0644); + MODULE_PARM_DESC(exp_hw_support, "experimental hw support (1 = enable, 0 = disable (default))"); module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444); -MODULE_PARM_DESC(enable_scheduler, "enable SW GPU scheduler (1 = enable, 0 = disable ((default))"); +MODULE_PARM_DESC(enable_scheduler, "enable SW GPU scheduler (1 = enable (default), 0 = disable)"); module_param_named(enable_scheduler, amdgpu_enable_scheduler, int, 0444); MODULE_PARM_DESC(sched_jobs, "the max number of jobs supported in the sw queue (default 16)"); @@ -153,7 +161,7 @@ module_param_named(sched_jobs, amdgpu_sched_jobs, int, 0444); MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)"); module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444); -MODULE_PARM_DESC(enable_semaphores, "Enable semaphores (1 = enable (default), 0 = disable)"); +MODULE_PARM_DESC(enable_semaphores, "Enable semaphores (1 = enable, 0 = disable (default))"); module_param_named(enable_semaphores, amdgpu_enable_semaphores, int, 0644); static struct pci_device_id pciidlist[] = { @@ -242,11 +250,11 @@ static struct pci_device_id pciidlist[] = { {0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU}, #endif /* topaz */ - {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, - {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, /* tonga */ {0x1002, 0x6920, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, {0x1002, 0x6921, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 8a122b1..96290d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -402,3 +402,19 @@ bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj) return true; return false; } + +void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev) +{ + struct amdgpu_fbdev *afbdev = adev->mode_info.rfbdev; + struct drm_fb_helper *fb_helper; + int ret; + + if (!afbdev) + return; + + fb_helper = &afbdev->helper; + + ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); + if (ret) + DRM_DEBUG("failed to restore crtc mode\n"); +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index b3fc26c..fcad7e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -628,8 +628,20 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring) init_waitqueue_head(&ring->fence_drv.fence_queue); if (amdgpu_enable_scheduler) { + long timeout = msecs_to_jiffies(amdgpu_lockup_timeout); + if (timeout == 0) { + /* + * FIXME: + * Delayed workqueue cannot use it directly, + * so the scheduler will not use delayed workqueue if + * MAX_SCHEDULE_TIMEOUT is set. + * Currently keep it simple and silly. + */ + timeout = MAX_SCHEDULE_TIMEOUT; + } r = amd_sched_init(&ring->sched, &amdgpu_sched_ops, - amdgpu_sched_hw_submission, ring->name); + amdgpu_sched_hw_submission, + timeout, ring->name); if (r) { DRM_ERROR("Failed to create scheduler on ring %s.\n", ring->name); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 371f015..1618e22 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -218,8 +218,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file break; case AMDGPU_HW_IP_DMA: type = AMD_IP_BLOCK_TYPE_SDMA; - ring_mask = adev->sdma[0].ring.ready ? 1 : 0; - ring_mask |= ((adev->sdma[1].ring.ready ? 1 : 0) << 1); + for (i = 0; i < adev->sdma.num_instances; i++) + ring_mask |= ((adev->sdma.instance[i].ring.ready ? 1 : 0) << i); ib_start_alignment = AMDGPU_GPU_PAGE_SIZE; ib_size_alignment = 1; break; @@ -341,10 +341,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file fw_info.feature = 0; break; case AMDGPU_INFO_FW_SDMA: - if (info->query_fw.index >= 2) + if (info->query_fw.index >= adev->sdma.num_instances) return -EINVAL; - fw_info.ver = adev->sdma[info->query_fw.index].fw_version; - fw_info.feature = adev->sdma[info->query_fw.index].feature_version; + fw_info.ver = adev->sdma.instance[info->query_fw.index].fw_version; + fw_info.feature = adev->sdma.instance[info->query_fw.index].feature_version; break; default: return -EINVAL; @@ -485,14 +485,17 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file * Outdated mess for old drm with Xorg being in charge (void function now). */ /** - * amdgpu_driver_firstopen_kms - drm callback for last close + * amdgpu_driver_lastclose_kms - drm callback for last close * * @dev: drm dev pointer * - * Switch vga switcheroo state after last close (all asics). + * Switch vga_switcheroo state after last close (all asics). */ void amdgpu_driver_lastclose_kms(struct drm_device *dev) { + struct amdgpu_device *adev = dev->dev_private; + + amdgpu_fbdev_restore_mode(adev); vga_switcheroo_process_delayed_switch(); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index f6b0299..b62c171 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -373,6 +373,10 @@ struct amdgpu_crtc { uint32_t crtc_offset; struct drm_gem_object *cursor_bo; uint64_t cursor_addr; + int cursor_x; + int cursor_y; + int cursor_hot_x; + int cursor_hot_y; int cursor_width; int cursor_height; int max_cursor_width; @@ -567,6 +571,7 @@ void amdgpu_fbdev_fini(struct amdgpu_device *adev); void amdgpu_fbdev_set_suspend(struct amdgpu_device *adev, int state); int amdgpu_fbdev_total_size(struct amdgpu_device *adev); bool amdgpu_fbdev_robj_is_fb(struct amdgpu_device *adev, struct amdgpu_bo *robj); +void amdgpu_fbdev_restore_mode(struct amdgpu_device *adev); void amdgpu_fb_output_poll_changed(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 1a7708f..0d52438 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -132,6 +132,8 @@ static void amdgpu_ttm_placement_init(struct amdgpu_device *adev, placements[c].fpfn = 0; placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM; + if (!(flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)) + placements[c - 1].flags |= TTM_PL_FLAG_TOPDOWN; } if (domain & AMDGPU_GEM_DOMAIN_GTT) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 30dce23..b13a74b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -540,8 +540,8 @@ static int amdgpu_debugfs_ring_info(struct seq_file *m, void *data) static int amdgpu_gfx_index = offsetof(struct amdgpu_device, gfx.gfx_ring[0]); static int cayman_cp1_index = offsetof(struct amdgpu_device, gfx.compute_ring[0]); static int cayman_cp2_index = offsetof(struct amdgpu_device, gfx.compute_ring[1]); -static int amdgpu_dma1_index = offsetof(struct amdgpu_device, sdma[0].ring); -static int amdgpu_dma2_index = offsetof(struct amdgpu_device, sdma[1].ring); +static int amdgpu_dma1_index = offsetof(struct amdgpu_device, sdma.instance[0].ring); +static int amdgpu_dma2_index = offsetof(struct amdgpu_device, sdma.instance[1].ring); static int r600_uvd_index = offsetof(struct amdgpu_device, uvd.ring); static int si_vce1_index = offsetof(struct amdgpu_device, vce.ring[0]); static int si_vce2_index = offsetof(struct amdgpu_device, vce.ring[1]); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 961d726..76ecbaf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -111,7 +111,7 @@ TRACE_EVENT(amdgpu_vm_bo_unmap, __entry->offset, __entry->flags) ); -TRACE_EVENT(amdgpu_vm_bo_update, +DECLARE_EVENT_CLASS(amdgpu_vm_mapping, TP_PROTO(struct amdgpu_bo_va_mapping *mapping), TP_ARGS(mapping), TP_STRUCT__entry( @@ -129,6 +129,16 @@ TRACE_EVENT(amdgpu_vm_bo_update, __entry->soffset, __entry->eoffset, __entry->flags) ); +DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_update, + TP_PROTO(struct amdgpu_bo_va_mapping *mapping), + TP_ARGS(mapping) +); + +DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_mapping, + TP_PROTO(struct amdgpu_bo_va_mapping *mapping), + TP_ARGS(mapping) +); + TRACE_EVENT(amdgpu_vm_set_page, TP_PROTO(uint64_t pe, uint64_t addr, unsigned count, uint32_t incr, uint32_t flags), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 364cbe9..a089e69 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1072,6 +1072,11 @@ static int amdgpu_mm_dump_table(struct seq_file *m, void *data) spin_lock(&glob->lru_lock); ret = drm_mm_dump_table(m, mm); spin_unlock(&glob->lru_lock); + if (ttm_pl == TTM_PL_VRAM) + seq_printf(m, "man size:%llu pages, ram usage:%luMB, vis usage:%luMB\n", + adev->mman.bdev.man[ttm_pl].size, + atomic64_read(&adev->vram_usage) >> 20, + atomic64_read(&adev->vram_vis_usage) >> 20); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 1e14531..644fd9b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -147,8 +147,10 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, /* check if the id is still valid */ if (vm_id->id && vm_id->last_id_use && - vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) + vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) { + trace_amdgpu_vm_grab_id(vm_id->id, ring->idx); return 0; + } /* we definately need to flush */ vm_id->pd_gpu_addr = ~0ll; @@ -455,8 +457,10 @@ int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, return -ENOMEM; r = amdgpu_ib_get(ring, NULL, ndw * 4, ib); - if (r) + if (r) { + kfree(ib); return r; + } ib->length_dw = 0; /* walk over the address space and update the page directory */ @@ -850,6 +854,14 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, return r; } + if (trace_amdgpu_vm_bo_mapping_enabled()) { + list_for_each_entry(mapping, &bo_va->valids, list) + trace_amdgpu_vm_bo_mapping(mapping); + + list_for_each_entry(mapping, &bo_va->invalids, list) + trace_amdgpu_vm_bo_mapping(mapping); + } + spin_lock(&vm->status_lock); list_splice_init(&bo_va->invalids, &bo_va->valids); list_del_init(&bo_va->vm_status); diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index a0346a9..1b50e6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -685,6 +685,27 @@ static void atom_op_div(atom_exec_context *ctx, int *ptr, int arg) } } +static void atom_op_div32(atom_exec_context *ctx, int *ptr, int arg) +{ + uint64_t val64; + uint8_t attr = U8((*ptr)++); + uint32_t dst, src; + SDEBUG(" src1: "); + dst = atom_get_dst(ctx, arg, attr, ptr, NULL, 1); + SDEBUG(" src2: "); + src = atom_get_src(ctx, attr, ptr); + if (src != 0) { + val64 = dst; + val64 |= ((uint64_t)ctx->ctx->divmul[1]) << 32; + do_div(val64, src); + ctx->ctx->divmul[0] = lower_32_bits(val64); + ctx->ctx->divmul[1] = upper_32_bits(val64); + } else { + ctx->ctx->divmul[0] = 0; + ctx->ctx->divmul[1] = 0; + } +} + static void atom_op_eot(atom_exec_context *ctx, int *ptr, int arg) { /* functionally, a nop */ @@ -788,6 +809,20 @@ static void atom_op_mul(atom_exec_context *ctx, int *ptr, int arg) ctx->ctx->divmul[0] = dst * src; } +static void atom_op_mul32(atom_exec_context *ctx, int *ptr, int arg) +{ + uint64_t val64; + uint8_t attr = U8((*ptr)++); + uint32_t dst, src; + SDEBUG(" src1: "); + dst = atom_get_dst(ctx, arg, attr, ptr, NULL, 1); + SDEBUG(" src2: "); + src = atom_get_src(ctx, attr, ptr); + val64 = (uint64_t)dst * (uint64_t)src; + ctx->ctx->divmul[0] = lower_32_bits(val64); + ctx->ctx->divmul[1] = upper_32_bits(val64); +} + static void atom_op_nop(atom_exec_context *ctx, int *ptr, int arg) { /* nothing */ @@ -1022,7 +1057,15 @@ static void atom_op_xor(atom_exec_context *ctx, int *ptr, int arg) static void atom_op_debug(atom_exec_context *ctx, int *ptr, int arg) { - printk(KERN_INFO "unimplemented!\n"); + uint8_t val = U8((*ptr)++); + SDEBUG("DEBUG output: 0x%02X\n", val); +} + +static void atom_op_processds(atom_exec_context *ctx, int *ptr, int arg) +{ + uint16_t val = U16(*ptr); + (*ptr) += val + 2; + SDEBUG("PROCESSDS output: 0x%02X\n", val); } static struct { @@ -1151,7 +1194,13 @@ static struct { atom_op_shr, ATOM_ARG_FB}, { atom_op_shr, ATOM_ARG_PLL}, { atom_op_shr, ATOM_ARG_MC}, { -atom_op_debug, 0},}; + atom_op_debug, 0}, { + atom_op_processds, 0}, { + atom_op_mul32, ATOM_ARG_PS}, { + atom_op_mul32, ATOM_ARG_WS}, { + atom_op_div32, ATOM_ARG_PS}, { + atom_op_div32, ATOM_ARG_WS}, +}; static int amdgpu_atom_execute_table_locked(struct atom_context *ctx, int index, uint32_t * params) { diff --git a/drivers/gpu/drm/amd/amdgpu/atom.h b/drivers/gpu/drm/amd/amdgpu/atom.h index 09d0f82..fece8f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.h +++ b/drivers/gpu/drm/amd/amdgpu/atom.h @@ -60,7 +60,7 @@ #define ATOM_CT_PS_MASK 0x7F #define ATOM_CT_CODE_PTR 6 -#define ATOM_OP_CNT 123 +#define ATOM_OP_CNT 127 #define ATOM_OP_EOT 91 #define ATOM_CASE_MAGIC 0x63 diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index cd6edc4..1e0bba2 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -1279,8 +1279,7 @@ amdgpu_atombios_encoder_setup_dig(struct drm_encoder *encoder, int action) amdgpu_atombios_encoder_setup_dig_encoder(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0); } if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) - amdgpu_atombios_encoder_setup_dig_transmitter(encoder, - ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0); + amdgpu_atombios_encoder_set_backlight_level(amdgpu_encoder, dig->backlight_level); if (ext_encoder) amdgpu_atombios_encoder_setup_external_encoder(encoder, ext_encoder, ATOM_ENABLE); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index 82e8d07..a1a35a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -6185,6 +6185,11 @@ static int ci_dpm_late_init(void *handle) if (!amdgpu_dpm) return 0; + /* init the sysfs and debugfs files late */ + ret = amdgpu_pm_sysfs_init(adev); + if (ret) + return ret; + ret = ci_set_temperature_range(adev); if (ret) return ret; @@ -6232,9 +6237,6 @@ static int ci_dpm_sw_init(void *handle) adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; if (amdgpu_dpm == 1) amdgpu_pm_print_power_states(adev); - ret = amdgpu_pm_sysfs_init(adev); - if (ret) - goto dpm_failed; mutex_unlock(&adev->pm.mutex); DRM_INFO("amdgpu: dpm initialized\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 4b6ce74..484710c 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1567,6 +1567,9 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev) int ret, i; u16 tmp16; + if (pci_is_root_bus(adev->pdev->bus)) + return; + if (amdgpu_pcie_gen2 == 0) return; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 9ea9de4..814598e 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -96,7 +96,7 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev) { const char *chip_name; char fw_name[30]; - int err, i; + int err = 0, i; DRM_DEBUG("\n"); @@ -119,24 +119,24 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev) default: BUG(); } - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { if (i == 0) snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma1.bin", chip_name); - err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev); + err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); if (err) goto out; - err = amdgpu_ucode_validate(adev->sdma[i].fw); + err = amdgpu_ucode_validate(adev->sdma.instance[i].fw); } out: if (err) { printk(KERN_ERR "cik_sdma: Failed to load firmware \"%s\"\n", fw_name); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - release_firmware(adev->sdma[i].fw); - adev->sdma[i].fw = NULL; + for (i = 0; i < adev->sdma.num_instances; i++) { + release_firmware(adev->sdma.instance[i].fw); + adev->sdma.instance[i].fw = NULL; } } return err; @@ -168,7 +168,7 @@ static uint32_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring) static uint32_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - u32 me = (ring == &adev->sdma[0].ring) ? 0 : 1; + u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1; return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) & 0x3fffc) >> 2; } @@ -183,14 +183,14 @@ static uint32_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring) static void cik_sdma_ring_set_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - u32 me = (ring == &adev->sdma[0].ring) ? 0 : 1; + u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1; WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], (ring->wptr << 2) & 0x3fffc); } static void cik_sdma_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) { - struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring); + struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring); int i; for (i = 0; i < count; i++) @@ -248,7 +248,7 @@ static void cik_sdma_ring_emit_hdp_flush(struct amdgpu_ring *ring) SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */ u32 ref_and_mask; - if (ring == &ring->adev->sdma[0].ring) + if (ring == &ring->adev->sdma.instance[0].ring) ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA0_MASK; else ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA1_MASK; @@ -327,8 +327,8 @@ static bool cik_sdma_ring_emit_semaphore(struct amdgpu_ring *ring, */ static void cik_sdma_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma[1].ring; + struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; + struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl; int i; @@ -336,7 +336,7 @@ static void cik_sdma_gfx_stop(struct amdgpu_device *adev) (adev->mman.buffer_funcs_ring == sdma1)) amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); rb_cntl &= ~SDMA0_GFX_RB_CNTL__RB_ENABLE_MASK; WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl); @@ -376,7 +376,7 @@ static void cik_sdma_enable(struct amdgpu_device *adev, bool enable) cik_sdma_rlc_stop(adev); } - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { me_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]); if (enable) me_cntl &= ~SDMA0_F32_CNTL__HALT_MASK; @@ -402,8 +402,8 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev) u32 wb_offset; int i, j, r; - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - ring = &adev->sdma[i].ring; + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; wb_offset = (ring->rptr_offs * 4); mutex_lock(&adev->srbm_mutex); @@ -502,26 +502,25 @@ static int cik_sdma_load_microcode(struct amdgpu_device *adev) u32 fw_size; int i, j; - if (!adev->sdma[0].fw || !adev->sdma[1].fw) - return -EINVAL; - /* halt the MEs */ cik_sdma_enable(adev, false); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; + for (i = 0; i < adev->sdma.num_instances; i++) { + if (!adev->sdma.instance[i].fw) + return -EINVAL; + hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; amdgpu_ucode_print_sdma_hdr(&hdr->header); fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; - adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); - adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); - if (adev->sdma[i].feature_version >= 20) - adev->sdma[i].burst_nop = true; + adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); + if (adev->sdma.instance[i].feature_version >= 20) + adev->sdma.instance[i].burst_nop = true; fw_data = (const __le32 *) - (adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); + (adev->sdma.instance[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0); for (j = 0; j < fw_size; j++) WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++)); - WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version); + WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version); } return 0; @@ -830,7 +829,7 @@ static void cik_sdma_vm_set_pte_pde(struct amdgpu_ib *ib, */ static void cik_sdma_vm_pad_ib(struct amdgpu_ib *ib) { - struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring); + struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring); u32 pad_count; int i; @@ -934,6 +933,8 @@ static int cik_sdma_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + adev->sdma.num_instances = SDMA_MAX_INSTANCE; + cik_sdma_set_ring_funcs(adev); cik_sdma_set_irq_funcs(adev); cik_sdma_set_buffer_funcs(adev); @@ -946,7 +947,7 @@ static int cik_sdma_sw_init(void *handle) { struct amdgpu_ring *ring; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - int r; + int r, i; r = cik_sdma_init_microcode(adev); if (r) { @@ -955,43 +956,33 @@ static int cik_sdma_sw_init(void *handle) } /* SDMA trap event */ - r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq); + r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq); + r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq); - if (r) - return r; - - ring = &adev->sdma[0].ring; - ring->ring_obj = NULL; - - ring = &adev->sdma[1].ring; - ring->ring_obj = NULL; - - ring = &adev->sdma[0].ring; - sprintf(ring->name, "sdma0"); - r = amdgpu_ring_init(adev, ring, 256 * 1024, - SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf, - &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0, - AMDGPU_RING_TYPE_SDMA); + r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq); if (r) return r; - ring = &adev->sdma[1].ring; - sprintf(ring->name, "sdma1"); - r = amdgpu_ring_init(adev, ring, 256 * 1024, - SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf, - &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1, - AMDGPU_RING_TYPE_SDMA); - if (r) - return r; + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; + ring->ring_obj = NULL; + sprintf(ring->name, "sdma%d", i); + r = amdgpu_ring_init(adev, ring, 256 * 1024, + SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf, + &adev->sdma.trap_irq, + (i == 0) ? + AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1, + AMDGPU_RING_TYPE_SDMA); + if (r) + return r; + } return r; } @@ -999,9 +990,10 @@ static int cik_sdma_sw_init(void *handle) static int cik_sdma_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int i; - amdgpu_ring_fini(&adev->sdma[0].ring); - amdgpu_ring_fini(&adev->sdma[1].ring); + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ring_fini(&adev->sdma.instance[i].ring); return 0; } @@ -1078,7 +1070,7 @@ static void cik_sdma_print_status(void *handle) dev_info(adev->dev, "CIK SDMA registers\n"); dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n", RREG32(mmSRBM_STATUS2)); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n", i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i])); dev_info(adev->dev, " SDMA%d_ME_CNTL=0x%08X\n", @@ -1223,7 +1215,7 @@ static int cik_sdma_process_trap_irq(struct amdgpu_device *adev, case 0: switch (queue_id) { case 0: - amdgpu_fence_process(&adev->sdma[0].ring); + amdgpu_fence_process(&adev->sdma.instance[0].ring); break; case 1: /* XXX compute */ @@ -1236,7 +1228,7 @@ static int cik_sdma_process_trap_irq(struct amdgpu_device *adev, case 1: switch (queue_id) { case 0: - amdgpu_fence_process(&adev->sdma[1].ring); + amdgpu_fence_process(&adev->sdma.instance[1].ring); break; case 1: /* XXX compute */ @@ -1334,8 +1326,10 @@ static const struct amdgpu_ring_funcs cik_sdma_ring_funcs = { static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev) { - adev->sdma[0].ring.funcs = &cik_sdma_ring_funcs; - adev->sdma[1].ring.funcs = &cik_sdma_ring_funcs; + int i; + + for (i = 0; i < adev->sdma.num_instances; i++) + adev->sdma.instance[i].ring.funcs = &cik_sdma_ring_funcs; } static const struct amdgpu_irq_src_funcs cik_sdma_trap_irq_funcs = { @@ -1349,9 +1343,9 @@ static const struct amdgpu_irq_src_funcs cik_sdma_illegal_inst_irq_funcs = { static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev) { - adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST; - adev->sdma_trap_irq.funcs = &cik_sdma_trap_irq_funcs; - adev->sdma_illegal_inst_irq.funcs = &cik_sdma_illegal_inst_irq_funcs; + adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST; + adev->sdma.trap_irq.funcs = &cik_sdma_trap_irq_funcs; + adev->sdma.illegal_inst_irq.funcs = &cik_sdma_illegal_inst_irq_funcs; } /** @@ -1416,7 +1410,7 @@ static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev) { if (adev->mman.buffer_funcs == NULL) { adev->mman.buffer_funcs = &cik_sdma_buffer_funcs; - adev->mman.buffer_funcs_ring = &adev->sdma[0].ring; + adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring; } } @@ -1431,7 +1425,7 @@ static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev) { if (adev->vm_manager.vm_pte_funcs == NULL) { adev->vm_manager.vm_pte_funcs = &cik_sdma_vm_pte_funcs; - adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring; + adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring; adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true; } } diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 44fa96a..2e3373e 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -596,6 +596,12 @@ static int cz_dpm_late_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (amdgpu_dpm) { + int ret; + /* init the sysfs and debugfs files late */ + ret = amdgpu_pm_sysfs_init(adev); + if (ret) + return ret; + /* powerdown unused blocks for now */ cz_dpm_powergate_uvd(adev, true); cz_dpm_powergate_vce(adev, true); @@ -632,10 +638,6 @@ static int cz_dpm_sw_init(void *handle) if (amdgpu_dpm == 1) amdgpu_pm_print_power_states(adev); - ret = amdgpu_pm_sysfs_init(adev); - if (ret) - goto dpm_init_failed; - mutex_unlock(&adev->pm.mutex); DRM_INFO("amdgpu: dpm initialized\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index e4d101b..3707393 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2499,26 +2499,19 @@ static void dce_v10_0_show_cursor(struct drm_crtc *crtc) struct amdgpu_device *adev = crtc->dev->dev_private; u32 tmp; + WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, + upper_32_bits(amdgpu_crtc->cursor_addr)); + WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, + lower_32_bits(amdgpu_crtc->cursor_addr)); + tmp = RREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset); tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_EN, 1); tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_MODE, 2); WREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset, tmp); } -static void dce_v10_0_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj, - uint64_t gpu_addr) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; - - WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, - upper_32_bits(gpu_addr)); - WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, - lower_32_bits(gpu_addr)); -} - -static int dce_v10_0_crtc_cursor_move(struct drm_crtc *crtc, - int x, int y) +static int dce_v10_0_cursor_move_locked(struct drm_crtc *crtc, + int x, int y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct amdgpu_device *adev = crtc->dev->dev_private; @@ -2538,26 +2531,40 @@ static int dce_v10_0_crtc_cursor_move(struct drm_crtc *crtc, y = 0; } - dce_v10_0_lock_cursor(crtc, true); WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); - dce_v10_0_lock_cursor(crtc, false); + + amdgpu_crtc->cursor_x = x; + amdgpu_crtc->cursor_y = y; return 0; } -static int dce_v10_0_crtc_cursor_set(struct drm_crtc *crtc, - struct drm_file *file_priv, - uint32_t handle, - uint32_t width, - uint32_t height) +static int dce_v10_0_crtc_cursor_move(struct drm_crtc *crtc, + int x, int y) +{ + int ret; + + dce_v10_0_lock_cursor(crtc, true); + ret = dce_v10_0_cursor_move_locked(crtc, x, y); + dce_v10_0_lock_cursor(crtc, false); + + return ret; +} + +static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc, + struct drm_file *file_priv, + uint32_t handle, + uint32_t width, + uint32_t height, + int32_t hot_x, + int32_t hot_y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct drm_gem_object *obj; - struct amdgpu_bo *robj; - uint64_t gpu_addr; + struct amdgpu_bo *aobj; int ret; if (!handle) { @@ -2579,41 +2586,71 @@ static int dce_v10_0_crtc_cursor_set(struct drm_crtc *crtc, return -ENOENT; } - robj = gem_to_amdgpu_bo(obj); - ret = amdgpu_bo_reserve(robj, false); - if (unlikely(ret != 0)) - goto fail; - ret = amdgpu_bo_pin_restricted(robj, AMDGPU_GEM_DOMAIN_VRAM, - 0, 0, &gpu_addr); - amdgpu_bo_unreserve(robj); - if (ret) - goto fail; + aobj = gem_to_amdgpu_bo(obj); + ret = amdgpu_bo_reserve(aobj, false); + if (ret != 0) { + drm_gem_object_unreference_unlocked(obj); + return ret; + } + + ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr); + amdgpu_bo_unreserve(aobj); + if (ret) { + DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret); + drm_gem_object_unreference_unlocked(obj); + return ret; + } amdgpu_crtc->cursor_width = width; amdgpu_crtc->cursor_height = height; dce_v10_0_lock_cursor(crtc, true); - dce_v10_0_set_cursor(crtc, obj, gpu_addr); + + if (hot_x != amdgpu_crtc->cursor_hot_x || + hot_y != amdgpu_crtc->cursor_hot_y) { + int x, y; + + x = amdgpu_crtc->cursor_x + amdgpu_crtc->cursor_hot_x - hot_x; + y = amdgpu_crtc->cursor_y + amdgpu_crtc->cursor_hot_y - hot_y; + + dce_v10_0_cursor_move_locked(crtc, x, y); + + amdgpu_crtc->cursor_hot_x = hot_x; + amdgpu_crtc->cursor_hot_y = hot_y; + } + dce_v10_0_show_cursor(crtc); dce_v10_0_lock_cursor(crtc, false); unpin: if (amdgpu_crtc->cursor_bo) { - robj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - ret = amdgpu_bo_reserve(robj, false); + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + ret = amdgpu_bo_reserve(aobj, false); if (likely(ret == 0)) { - amdgpu_bo_unpin(robj); - amdgpu_bo_unreserve(robj); + amdgpu_bo_unpin(aobj); + amdgpu_bo_unreserve(aobj); } drm_gem_object_unreference_unlocked(amdgpu_crtc->cursor_bo); } amdgpu_crtc->cursor_bo = obj; return 0; -fail: - drm_gem_object_unreference_unlocked(obj); +} - return ret; +static void dce_v10_0_cursor_reset(struct drm_crtc *crtc) +{ + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + + if (amdgpu_crtc->cursor_bo) { + dce_v10_0_lock_cursor(crtc, true); + + dce_v10_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, + amdgpu_crtc->cursor_y); + + dce_v10_0_show_cursor(crtc); + + dce_v10_0_lock_cursor(crtc, false); + } } static void dce_v10_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, @@ -2641,7 +2678,7 @@ static void dce_v10_0_crtc_destroy(struct drm_crtc *crtc) } static const struct drm_crtc_funcs dce_v10_0_crtc_funcs = { - .cursor_set = dce_v10_0_crtc_cursor_set, + .cursor_set2 = dce_v10_0_crtc_cursor_set2, .cursor_move = dce_v10_0_crtc_cursor_move, .gamma_set = dce_v10_0_crtc_gamma_set, .set_config = amdgpu_crtc_set_config, @@ -2774,6 +2811,7 @@ static int dce_v10_0_crtc_mode_set(struct drm_crtc *crtc, dce_v10_0_crtc_do_set_base(crtc, old_fb, x, y, 0); amdgpu_atombios_crtc_overscan_setup(crtc, mode, adjusted_mode); amdgpu_atombios_crtc_scaler_setup(crtc); + dce_v10_0_cursor_reset(crtc); /* update the hw version fpr dpm */ amdgpu_crtc->hw_mode = *adjusted_mode; @@ -3267,37 +3305,20 @@ static int dce_v10_0_set_pageflip_irq_state(struct amdgpu_device *adev, unsigned type, enum amdgpu_interrupt_state state) { - u32 reg, reg_block; - /* now deal with page flip IRQ */ - switch (type) { - case AMDGPU_PAGEFLIP_IRQ_D1: - reg_block = CRTC0_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D2: - reg_block = CRTC1_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D3: - reg_block = CRTC2_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D4: - reg_block = CRTC3_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D5: - reg_block = CRTC4_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D6: - reg_block = CRTC5_REGISTER_OFFSET; - break; - default: - DRM_ERROR("invalid pageflip crtc %d\n", type); - return -EINVAL; + u32 reg; + + if (type >= adev->mode_info.num_crtc) { + DRM_ERROR("invalid pageflip crtc %d\n", type); + return -EINVAL; } - reg = RREG32(mmGRPH_INTERRUPT_CONTROL + reg_block); + reg = RREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type]); if (state == AMDGPU_IRQ_STATE_DISABLE) - WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); + WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], + reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); else - WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); + WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], + reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); return 0; } @@ -3306,7 +3327,6 @@ static int dce_v10_0_pageflip_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - int reg_block; unsigned long flags; unsigned crtc_id; struct amdgpu_crtc *amdgpu_crtc; @@ -3315,33 +3335,15 @@ static int dce_v10_0_pageflip_irq(struct amdgpu_device *adev, crtc_id = (entry->src_id - 8) >> 1; amdgpu_crtc = adev->mode_info.crtcs[crtc_id]; - /* ack the interrupt */ - switch(crtc_id){ - case AMDGPU_PAGEFLIP_IRQ_D1: - reg_block = CRTC0_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D2: - reg_block = CRTC1_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D3: - reg_block = CRTC2_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D4: - reg_block = CRTC3_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D5: - reg_block = CRTC4_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D6: - reg_block = CRTC5_REGISTER_OFFSET; - break; - default: - DRM_ERROR("invalid pageflip crtc %d\n", crtc_id); - return -EINVAL; + if (crtc_id >= adev->mode_info.num_crtc) { + DRM_ERROR("invalid pageflip crtc %d\n", crtc_id); + return -EINVAL; } - if (RREG32(mmGRPH_INTERRUPT_STATUS + reg_block) & GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK) - WREG32(mmGRPH_INTERRUPT_STATUS + reg_block, GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK); + if (RREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id]) & + GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK) + WREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id], + GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK); /* IRQ could occur when in initial stage */ if (amdgpu_crtc == NULL) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 6411e82..5be83a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -2476,26 +2476,19 @@ static void dce_v11_0_show_cursor(struct drm_crtc *crtc) struct amdgpu_device *adev = crtc->dev->dev_private; u32 tmp; + WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, + upper_32_bits(amdgpu_crtc->cursor_addr)); + WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, + lower_32_bits(amdgpu_crtc->cursor_addr)); + tmp = RREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset); tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_EN, 1); tmp = REG_SET_FIELD(tmp, CUR_CONTROL, CURSOR_MODE, 2); WREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset, tmp); } -static void dce_v11_0_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj, - uint64_t gpu_addr) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; - - WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, - upper_32_bits(gpu_addr)); - WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, - lower_32_bits(gpu_addr)); -} - -static int dce_v11_0_crtc_cursor_move(struct drm_crtc *crtc, - int x, int y) +static int dce_v11_0_cursor_move_locked(struct drm_crtc *crtc, + int x, int y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct amdgpu_device *adev = crtc->dev->dev_private; @@ -2515,26 +2508,40 @@ static int dce_v11_0_crtc_cursor_move(struct drm_crtc *crtc, y = 0; } - dce_v11_0_lock_cursor(crtc, true); WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); - dce_v11_0_lock_cursor(crtc, false); + + amdgpu_crtc->cursor_x = x; + amdgpu_crtc->cursor_y = y; return 0; } -static int dce_v11_0_crtc_cursor_set(struct drm_crtc *crtc, - struct drm_file *file_priv, - uint32_t handle, - uint32_t width, - uint32_t height) +static int dce_v11_0_crtc_cursor_move(struct drm_crtc *crtc, + int x, int y) +{ + int ret; + + dce_v11_0_lock_cursor(crtc, true); + ret = dce_v11_0_cursor_move_locked(crtc, x, y); + dce_v11_0_lock_cursor(crtc, false); + + return ret; +} + +static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc, + struct drm_file *file_priv, + uint32_t handle, + uint32_t width, + uint32_t height, + int32_t hot_x, + int32_t hot_y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct drm_gem_object *obj; - struct amdgpu_bo *robj; - uint64_t gpu_addr; + struct amdgpu_bo *aobj; int ret; if (!handle) { @@ -2556,41 +2563,71 @@ static int dce_v11_0_crtc_cursor_set(struct drm_crtc *crtc, return -ENOENT; } - robj = gem_to_amdgpu_bo(obj); - ret = amdgpu_bo_reserve(robj, false); - if (unlikely(ret != 0)) - goto fail; - ret = amdgpu_bo_pin_restricted(robj, AMDGPU_GEM_DOMAIN_VRAM, - 0, 0, &gpu_addr); - amdgpu_bo_unreserve(robj); - if (ret) - goto fail; + aobj = gem_to_amdgpu_bo(obj); + ret = amdgpu_bo_reserve(aobj, false); + if (ret != 0) { + drm_gem_object_unreference_unlocked(obj); + return ret; + } + + ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr); + amdgpu_bo_unreserve(aobj); + if (ret) { + DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret); + drm_gem_object_unreference_unlocked(obj); + return ret; + } amdgpu_crtc->cursor_width = width; amdgpu_crtc->cursor_height = height; dce_v11_0_lock_cursor(crtc, true); - dce_v11_0_set_cursor(crtc, obj, gpu_addr); + + if (hot_x != amdgpu_crtc->cursor_hot_x || + hot_y != amdgpu_crtc->cursor_hot_y) { + int x, y; + + x = amdgpu_crtc->cursor_x + amdgpu_crtc->cursor_hot_x - hot_x; + y = amdgpu_crtc->cursor_y + amdgpu_crtc->cursor_hot_y - hot_y; + + dce_v11_0_cursor_move_locked(crtc, x, y); + + amdgpu_crtc->cursor_hot_x = hot_x; + amdgpu_crtc->cursor_hot_y = hot_y; + } + dce_v11_0_show_cursor(crtc); dce_v11_0_lock_cursor(crtc, false); unpin: if (amdgpu_crtc->cursor_bo) { - robj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - ret = amdgpu_bo_reserve(robj, false); + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + ret = amdgpu_bo_reserve(aobj, false); if (likely(ret == 0)) { - amdgpu_bo_unpin(robj); - amdgpu_bo_unreserve(robj); + amdgpu_bo_unpin(aobj); + amdgpu_bo_unreserve(aobj); } drm_gem_object_unreference_unlocked(amdgpu_crtc->cursor_bo); } amdgpu_crtc->cursor_bo = obj; return 0; -fail: - drm_gem_object_unreference_unlocked(obj); +} - return ret; +static void dce_v11_0_cursor_reset(struct drm_crtc *crtc) +{ + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + + if (amdgpu_crtc->cursor_bo) { + dce_v11_0_lock_cursor(crtc, true); + + dce_v11_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, + amdgpu_crtc->cursor_y); + + dce_v11_0_show_cursor(crtc); + + dce_v11_0_lock_cursor(crtc, false); + } } static void dce_v11_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, @@ -2618,7 +2655,7 @@ static void dce_v11_0_crtc_destroy(struct drm_crtc *crtc) } static const struct drm_crtc_funcs dce_v11_0_crtc_funcs = { - .cursor_set = dce_v11_0_crtc_cursor_set, + .cursor_set2 = dce_v11_0_crtc_cursor_set2, .cursor_move = dce_v11_0_crtc_cursor_move, .gamma_set = dce_v11_0_crtc_gamma_set, .set_config = amdgpu_crtc_set_config, @@ -2751,6 +2788,7 @@ static int dce_v11_0_crtc_mode_set(struct drm_crtc *crtc, dce_v11_0_crtc_do_set_base(crtc, old_fb, x, y, 0); amdgpu_atombios_crtc_overscan_setup(crtc, mode, adjusted_mode); amdgpu_atombios_crtc_scaler_setup(crtc); + dce_v11_0_cursor_reset(crtc); /* update the hw version fpr dpm */ amdgpu_crtc->hw_mode = *adjusted_mode; @@ -2888,7 +2926,7 @@ static int dce_v11_0_early_init(void *handle) switch (adev->asic_type) { case CHIP_CARRIZO: - adev->mode_info.num_crtc = 4; + adev->mode_info.num_crtc = 3; adev->mode_info.num_hpd = 6; adev->mode_info.num_dig = 9; break; @@ -3243,37 +3281,20 @@ static int dce_v11_0_set_pageflip_irq_state(struct amdgpu_device *adev, unsigned type, enum amdgpu_interrupt_state state) { - u32 reg, reg_block; - /* now deal with page flip IRQ */ - switch (type) { - case AMDGPU_PAGEFLIP_IRQ_D1: - reg_block = CRTC0_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D2: - reg_block = CRTC1_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D3: - reg_block = CRTC2_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D4: - reg_block = CRTC3_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D5: - reg_block = CRTC4_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D6: - reg_block = CRTC5_REGISTER_OFFSET; - break; - default: - DRM_ERROR("invalid pageflip crtc %d\n", type); - return -EINVAL; + u32 reg; + + if (type >= adev->mode_info.num_crtc) { + DRM_ERROR("invalid pageflip crtc %d\n", type); + return -EINVAL; } - reg = RREG32(mmGRPH_INTERRUPT_CONTROL + reg_block); + reg = RREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type]); if (state == AMDGPU_IRQ_STATE_DISABLE) - WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); + WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], + reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); else - WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); + WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], + reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); return 0; } @@ -3282,7 +3303,6 @@ static int dce_v11_0_pageflip_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - int reg_block; unsigned long flags; unsigned crtc_id; struct amdgpu_crtc *amdgpu_crtc; @@ -3291,33 +3311,15 @@ static int dce_v11_0_pageflip_irq(struct amdgpu_device *adev, crtc_id = (entry->src_id - 8) >> 1; amdgpu_crtc = adev->mode_info.crtcs[crtc_id]; - /* ack the interrupt */ - switch(crtc_id){ - case AMDGPU_PAGEFLIP_IRQ_D1: - reg_block = CRTC0_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D2: - reg_block = CRTC1_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D3: - reg_block = CRTC2_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D4: - reg_block = CRTC3_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D5: - reg_block = CRTC4_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D6: - reg_block = CRTC5_REGISTER_OFFSET; - break; - default: - DRM_ERROR("invalid pageflip crtc %d\n", crtc_id); - return -EINVAL; + if (crtc_id >= adev->mode_info.num_crtc) { + DRM_ERROR("invalid pageflip crtc %d\n", crtc_id); + return -EINVAL; } - if (RREG32(mmGRPH_INTERRUPT_STATUS + reg_block) & GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK) - WREG32(mmGRPH_INTERRUPT_STATUS + reg_block, GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK); + if (RREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id]) & + GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK) + WREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id], + GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK); /* IRQ could occur when in initial stage */ if(amdgpu_crtc == NULL) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index c86911c..d784fb4 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -2411,26 +2411,19 @@ static void dce_v8_0_show_cursor(struct drm_crtc *crtc) struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct amdgpu_device *adev = crtc->dev->dev_private; + WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, + upper_32_bits(amdgpu_crtc->cursor_addr)); + WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, + lower_32_bits(amdgpu_crtc->cursor_addr)); + WREG32_IDX(mmCUR_CONTROL + amdgpu_crtc->crtc_offset, CUR_CONTROL__CURSOR_EN_MASK | (CURSOR_24_8_PRE_MULT << CUR_CONTROL__CURSOR_MODE__SHIFT) | (CURSOR_URGENT_1_2 << CUR_CONTROL__CURSOR_URGENT_CONTROL__SHIFT)); } -static void dce_v8_0_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj, - uint64_t gpu_addr) -{ - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct amdgpu_device *adev = crtc->dev->dev_private; - - WREG32(mmCUR_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, - upper_32_bits(gpu_addr)); - WREG32(mmCUR_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, - gpu_addr & 0xffffffff); -} - -static int dce_v8_0_crtc_cursor_move(struct drm_crtc *crtc, - int x, int y) +static int dce_v8_0_cursor_move_locked(struct drm_crtc *crtc, + int x, int y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct amdgpu_device *adev = crtc->dev->dev_private; @@ -2450,26 +2443,40 @@ static int dce_v8_0_crtc_cursor_move(struct drm_crtc *crtc, y = 0; } - dce_v8_0_lock_cursor(crtc, true); WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y); WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin); WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset, ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1)); - dce_v8_0_lock_cursor(crtc, false); + + amdgpu_crtc->cursor_x = x; + amdgpu_crtc->cursor_y = y; return 0; } -static int dce_v8_0_crtc_cursor_set(struct drm_crtc *crtc, - struct drm_file *file_priv, - uint32_t handle, - uint32_t width, - uint32_t height) +static int dce_v8_0_crtc_cursor_move(struct drm_crtc *crtc, + int x, int y) +{ + int ret; + + dce_v8_0_lock_cursor(crtc, true); + ret = dce_v8_0_cursor_move_locked(crtc, x, y); + dce_v8_0_lock_cursor(crtc, false); + + return ret; +} + +static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc, + struct drm_file *file_priv, + uint32_t handle, + uint32_t width, + uint32_t height, + int32_t hot_x, + int32_t hot_y) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); struct drm_gem_object *obj; - struct amdgpu_bo *robj; - uint64_t gpu_addr; + struct amdgpu_bo *aobj; int ret; if (!handle) { @@ -2491,41 +2498,71 @@ static int dce_v8_0_crtc_cursor_set(struct drm_crtc *crtc, return -ENOENT; } - robj = gem_to_amdgpu_bo(obj); - ret = amdgpu_bo_reserve(robj, false); - if (unlikely(ret != 0)) - goto fail; - ret = amdgpu_bo_pin_restricted(robj, AMDGPU_GEM_DOMAIN_VRAM, - 0, 0, &gpu_addr); - amdgpu_bo_unreserve(robj); - if (ret) - goto fail; + aobj = gem_to_amdgpu_bo(obj); + ret = amdgpu_bo_reserve(aobj, false); + if (ret != 0) { + drm_gem_object_unreference_unlocked(obj); + return ret; + } + + ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr); + amdgpu_bo_unreserve(aobj); + if (ret) { + DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret); + drm_gem_object_unreference_unlocked(obj); + return ret; + } amdgpu_crtc->cursor_width = width; amdgpu_crtc->cursor_height = height; dce_v8_0_lock_cursor(crtc, true); - dce_v8_0_set_cursor(crtc, obj, gpu_addr); + + if (hot_x != amdgpu_crtc->cursor_hot_x || + hot_y != amdgpu_crtc->cursor_hot_y) { + int x, y; + + x = amdgpu_crtc->cursor_x + amdgpu_crtc->cursor_hot_x - hot_x; + y = amdgpu_crtc->cursor_y + amdgpu_crtc->cursor_hot_y - hot_y; + + dce_v8_0_cursor_move_locked(crtc, x, y); + + amdgpu_crtc->cursor_hot_x = hot_x; + amdgpu_crtc->cursor_hot_y = hot_y; + } + dce_v8_0_show_cursor(crtc); dce_v8_0_lock_cursor(crtc, false); unpin: if (amdgpu_crtc->cursor_bo) { - robj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - ret = amdgpu_bo_reserve(robj, false); + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + ret = amdgpu_bo_reserve(aobj, false); if (likely(ret == 0)) { - amdgpu_bo_unpin(robj); - amdgpu_bo_unreserve(robj); + amdgpu_bo_unpin(aobj); + amdgpu_bo_unreserve(aobj); } drm_gem_object_unreference_unlocked(amdgpu_crtc->cursor_bo); } amdgpu_crtc->cursor_bo = obj; return 0; -fail: - drm_gem_object_unreference_unlocked(obj); +} - return ret; +static void dce_v8_0_cursor_reset(struct drm_crtc *crtc) +{ + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + + if (amdgpu_crtc->cursor_bo) { + dce_v8_0_lock_cursor(crtc, true); + + dce_v8_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x, + amdgpu_crtc->cursor_y); + + dce_v8_0_show_cursor(crtc); + + dce_v8_0_lock_cursor(crtc, false); + } } static void dce_v8_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, @@ -2553,7 +2590,7 @@ static void dce_v8_0_crtc_destroy(struct drm_crtc *crtc) } static const struct drm_crtc_funcs dce_v8_0_crtc_funcs = { - .cursor_set = dce_v8_0_crtc_cursor_set, + .cursor_set2 = dce_v8_0_crtc_cursor_set2, .cursor_move = dce_v8_0_crtc_cursor_move, .gamma_set = dce_v8_0_crtc_gamma_set, .set_config = amdgpu_crtc_set_config, @@ -2693,6 +2730,7 @@ static int dce_v8_0_crtc_mode_set(struct drm_crtc *crtc, dce_v8_0_crtc_do_set_base(crtc, old_fb, x, y, 0); amdgpu_atombios_crtc_overscan_setup(crtc, mode, adjusted_mode); amdgpu_atombios_crtc_scaler_setup(crtc); + dce_v8_0_cursor_reset(crtc); /* update the hw version fpr dpm */ amdgpu_crtc->hw_mode = *adjusted_mode; @@ -3274,37 +3312,20 @@ static int dce_v8_0_set_pageflip_interrupt_state(struct amdgpu_device *adev, unsigned type, enum amdgpu_interrupt_state state) { - u32 reg, reg_block; - /* now deal with page flip IRQ */ - switch (type) { - case AMDGPU_PAGEFLIP_IRQ_D1: - reg_block = CRTC0_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D2: - reg_block = CRTC1_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D3: - reg_block = CRTC2_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D4: - reg_block = CRTC3_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D5: - reg_block = CRTC4_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D6: - reg_block = CRTC5_REGISTER_OFFSET; - break; - default: - DRM_ERROR("invalid pageflip crtc %d\n", type); - return -EINVAL; + u32 reg; + + if (type >= adev->mode_info.num_crtc) { + DRM_ERROR("invalid pageflip crtc %d\n", type); + return -EINVAL; } - reg = RREG32(mmGRPH_INTERRUPT_CONTROL + reg_block); + reg = RREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type]); if (state == AMDGPU_IRQ_STATE_DISABLE) - WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); + WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], + reg & ~GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); else - WREG32(mmGRPH_INTERRUPT_CONTROL + reg_block, reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); + WREG32(mmGRPH_INTERRUPT_CONTROL + crtc_offsets[type], + reg | GRPH_INTERRUPT_CONTROL__GRPH_PFLIP_INT_MASK_MASK); return 0; } @@ -3313,7 +3334,6 @@ static int dce_v8_0_pageflip_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - int reg_block; unsigned long flags; unsigned crtc_id; struct amdgpu_crtc *amdgpu_crtc; @@ -3322,33 +3342,15 @@ static int dce_v8_0_pageflip_irq(struct amdgpu_device *adev, crtc_id = (entry->src_id - 8) >> 1; amdgpu_crtc = adev->mode_info.crtcs[crtc_id]; - /* ack the interrupt */ - switch(crtc_id){ - case AMDGPU_PAGEFLIP_IRQ_D1: - reg_block = CRTC0_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D2: - reg_block = CRTC1_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D3: - reg_block = CRTC2_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D4: - reg_block = CRTC3_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D5: - reg_block = CRTC4_REGISTER_OFFSET; - break; - case AMDGPU_PAGEFLIP_IRQ_D6: - reg_block = CRTC5_REGISTER_OFFSET; - break; - default: - DRM_ERROR("invalid pageflip crtc %d\n", crtc_id); - return -EINVAL; + if (crtc_id >= adev->mode_info.num_crtc) { + DRM_ERROR("invalid pageflip crtc %d\n", crtc_id); + return -EINVAL; } - if (RREG32(mmGRPH_INTERRUPT_STATUS + reg_block) & GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK) - WREG32(mmGRPH_INTERRUPT_STATUS + reg_block, GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK); + if (RREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id]) & + GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_OCCURRED_MASK) + WREG32(mmGRPH_INTERRUPT_STATUS + crtc_offsets[crtc_id], + GRPH_INTERRUPT_STATUS__GRPH_PFLIP_INT_CLEAR_MASK); /* IRQ could occur when in initial stage */ if (amdgpu_crtc == NULL) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index cb4f68f..718250a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -903,6 +903,191 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev) return 0; } +static void gfx_v8_0_gpu_early_init(struct amdgpu_device *adev) +{ + u32 gb_addr_config; + u32 mc_shared_chmap, mc_arb_ramcfg; + u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map; + u32 tmp; + + switch (adev->asic_type) { + case CHIP_TOPAZ: + adev->gfx.config.max_shader_engines = 1; + adev->gfx.config.max_tile_pipes = 2; + adev->gfx.config.max_cu_per_sh = 6; + adev->gfx.config.max_sh_per_se = 1; + adev->gfx.config.max_backends_per_se = 2; + adev->gfx.config.max_texture_channel_caches = 2; + adev->gfx.config.max_gprs = 256; + adev->gfx.config.max_gs_threads = 32; + adev->gfx.config.max_hw_contexts = 8; + + adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; + adev->gfx.config.sc_prim_fifo_size_backend = 0x100; + adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; + adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; + gb_addr_config = TOPAZ_GB_ADDR_CONFIG_GOLDEN; + break; + case CHIP_FIJI: + adev->gfx.config.max_shader_engines = 4; + adev->gfx.config.max_tile_pipes = 16; + adev->gfx.config.max_cu_per_sh = 16; + adev->gfx.config.max_sh_per_se = 1; + adev->gfx.config.max_backends_per_se = 4; + adev->gfx.config.max_texture_channel_caches = 8; + adev->gfx.config.max_gprs = 256; + adev->gfx.config.max_gs_threads = 32; + adev->gfx.config.max_hw_contexts = 8; + + adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; + adev->gfx.config.sc_prim_fifo_size_backend = 0x100; + adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; + adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; + gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN; + break; + case CHIP_TONGA: + adev->gfx.config.max_shader_engines = 4; + adev->gfx.config.max_tile_pipes = 8; + adev->gfx.config.max_cu_per_sh = 8; + adev->gfx.config.max_sh_per_se = 1; + adev->gfx.config.max_backends_per_se = 2; + adev->gfx.config.max_texture_channel_caches = 8; + adev->gfx.config.max_gprs = 256; + adev->gfx.config.max_gs_threads = 32; + adev->gfx.config.max_hw_contexts = 8; + + adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; + adev->gfx.config.sc_prim_fifo_size_backend = 0x100; + adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; + adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; + gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN; + break; + case CHIP_CARRIZO: + adev->gfx.config.max_shader_engines = 1; + adev->gfx.config.max_tile_pipes = 2; + adev->gfx.config.max_sh_per_se = 1; + adev->gfx.config.max_backends_per_se = 2; + + switch (adev->pdev->revision) { + case 0xc4: + case 0x84: + case 0xc8: + case 0xcc: + /* B10 */ + adev->gfx.config.max_cu_per_sh = 8; + break; + case 0xc5: + case 0x81: + case 0x85: + case 0xc9: + case 0xcd: + /* B8 */ + adev->gfx.config.max_cu_per_sh = 6; + break; + case 0xc6: + case 0xca: + case 0xce: + /* B6 */ + adev->gfx.config.max_cu_per_sh = 6; + break; + case 0xc7: + case 0x87: + case 0xcb: + default: + /* B4 */ + adev->gfx.config.max_cu_per_sh = 4; + break; + } + + adev->gfx.config.max_texture_channel_caches = 2; + adev->gfx.config.max_gprs = 256; + adev->gfx.config.max_gs_threads = 32; + adev->gfx.config.max_hw_contexts = 8; + + adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; + adev->gfx.config.sc_prim_fifo_size_backend = 0x100; + adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; + adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; + gb_addr_config = CARRIZO_GB_ADDR_CONFIG_GOLDEN; + break; + default: + adev->gfx.config.max_shader_engines = 2; + adev->gfx.config.max_tile_pipes = 4; + adev->gfx.config.max_cu_per_sh = 2; + adev->gfx.config.max_sh_per_se = 1; + adev->gfx.config.max_backends_per_se = 2; + adev->gfx.config.max_texture_channel_caches = 4; + adev->gfx.config.max_gprs = 256; + adev->gfx.config.max_gs_threads = 32; + adev->gfx.config.max_hw_contexts = 8; + + adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; + adev->gfx.config.sc_prim_fifo_size_backend = 0x100; + adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; + adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; + gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN; + break; + } + + mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP); + adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG); + mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg; + + adev->gfx.config.num_tile_pipes = adev->gfx.config.max_tile_pipes; + adev->gfx.config.mem_max_burst_length_bytes = 256; + if (adev->flags & AMD_IS_APU) { + /* Get memory bank mapping mode. */ + tmp = RREG32(mmMC_FUS_DRAM0_BANK_ADDR_MAPPING); + dimm00_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM0ADDRMAP); + dimm01_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM1ADDRMAP); + + tmp = RREG32(mmMC_FUS_DRAM1_BANK_ADDR_MAPPING); + dimm10_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM0ADDRMAP); + dimm11_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM1ADDRMAP); + + /* Validate settings in case only one DIMM installed. */ + if ((dimm00_addr_map == 0) || (dimm00_addr_map == 3) || (dimm00_addr_map == 4) || (dimm00_addr_map > 12)) + dimm00_addr_map = 0; + if ((dimm01_addr_map == 0) || (dimm01_addr_map == 3) || (dimm01_addr_map == 4) || (dimm01_addr_map > 12)) + dimm01_addr_map = 0; + if ((dimm10_addr_map == 0) || (dimm10_addr_map == 3) || (dimm10_addr_map == 4) || (dimm10_addr_map > 12)) + dimm10_addr_map = 0; + if ((dimm11_addr_map == 0) || (dimm11_addr_map == 3) || (dimm11_addr_map == 4) || (dimm11_addr_map > 12)) + dimm11_addr_map = 0; + + /* If DIMM Addr map is 8GB, ROW size should be 2KB. Otherwise 1KB. */ + /* If ROW size(DIMM1) != ROW size(DMIMM0), ROW size should be larger one. */ + if ((dimm00_addr_map == 11) || (dimm01_addr_map == 11) || (dimm10_addr_map == 11) || (dimm11_addr_map == 11)) + adev->gfx.config.mem_row_size_in_kb = 2; + else + adev->gfx.config.mem_row_size_in_kb = 1; + } else { + tmp = REG_GET_FIELD(mc_arb_ramcfg, MC_ARB_RAMCFG, NOOFCOLS); + adev->gfx.config.mem_row_size_in_kb = (4 * (1 << (8 + tmp))) / 1024; + if (adev->gfx.config.mem_row_size_in_kb > 4) + adev->gfx.config.mem_row_size_in_kb = 4; + } + + adev->gfx.config.shader_engine_tile_size = 32; + adev->gfx.config.num_gpus = 1; + adev->gfx.config.multi_gpu_tile_size = 64; + + /* fix up row size */ + switch (adev->gfx.config.mem_row_size_in_kb) { + case 1: + default: + gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 0); + break; + case 2: + gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 1); + break; + case 4: + gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 2); + break; + } + adev->gfx.config.gb_addr_config = gb_addr_config; +} + static int gfx_v8_0_sw_init(void *handle) { int i, r; @@ -1010,6 +1195,8 @@ static int gfx_v8_0_sw_init(void *handle) adev->gfx.ce_ram_size = 0x8000; + gfx_v8_0_gpu_early_init(adev); + return 0; } @@ -2043,203 +2230,23 @@ static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev) static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) { - u32 gb_addr_config; - u32 mc_shared_chmap, mc_arb_ramcfg; - u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map; u32 tmp; int i; - switch (adev->asic_type) { - case CHIP_TOPAZ: - adev->gfx.config.max_shader_engines = 1; - adev->gfx.config.max_tile_pipes = 2; - adev->gfx.config.max_cu_per_sh = 6; - adev->gfx.config.max_sh_per_se = 1; - adev->gfx.config.max_backends_per_se = 2; - adev->gfx.config.max_texture_channel_caches = 2; - adev->gfx.config.max_gprs = 256; - adev->gfx.config.max_gs_threads = 32; - adev->gfx.config.max_hw_contexts = 8; - - adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; - adev->gfx.config.sc_prim_fifo_size_backend = 0x100; - adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; - adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; - gb_addr_config = TOPAZ_GB_ADDR_CONFIG_GOLDEN; - break; - case CHIP_FIJI: - adev->gfx.config.max_shader_engines = 4; - adev->gfx.config.max_tile_pipes = 16; - adev->gfx.config.max_cu_per_sh = 16; - adev->gfx.config.max_sh_per_se = 1; - adev->gfx.config.max_backends_per_se = 4; - adev->gfx.config.max_texture_channel_caches = 8; - adev->gfx.config.max_gprs = 256; - adev->gfx.config.max_gs_threads = 32; - adev->gfx.config.max_hw_contexts = 8; - - adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; - adev->gfx.config.sc_prim_fifo_size_backend = 0x100; - adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; - adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; - gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN; - break; - case CHIP_TONGA: - adev->gfx.config.max_shader_engines = 4; - adev->gfx.config.max_tile_pipes = 8; - adev->gfx.config.max_cu_per_sh = 8; - adev->gfx.config.max_sh_per_se = 1; - adev->gfx.config.max_backends_per_se = 2; - adev->gfx.config.max_texture_channel_caches = 8; - adev->gfx.config.max_gprs = 256; - adev->gfx.config.max_gs_threads = 32; - adev->gfx.config.max_hw_contexts = 8; - - adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; - adev->gfx.config.sc_prim_fifo_size_backend = 0x100; - adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; - adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; - gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN; - break; - case CHIP_CARRIZO: - adev->gfx.config.max_shader_engines = 1; - adev->gfx.config.max_tile_pipes = 2; - adev->gfx.config.max_sh_per_se = 1; - adev->gfx.config.max_backends_per_se = 2; - - switch (adev->pdev->revision) { - case 0xc4: - case 0x84: - case 0xc8: - case 0xcc: - /* B10 */ - adev->gfx.config.max_cu_per_sh = 8; - break; - case 0xc5: - case 0x81: - case 0x85: - case 0xc9: - case 0xcd: - /* B8 */ - adev->gfx.config.max_cu_per_sh = 6; - break; - case 0xc6: - case 0xca: - case 0xce: - /* B6 */ - adev->gfx.config.max_cu_per_sh = 6; - break; - case 0xc7: - case 0x87: - case 0xcb: - default: - /* B4 */ - adev->gfx.config.max_cu_per_sh = 4; - break; - } - - adev->gfx.config.max_texture_channel_caches = 2; - adev->gfx.config.max_gprs = 256; - adev->gfx.config.max_gs_threads = 32; - adev->gfx.config.max_hw_contexts = 8; - - adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; - adev->gfx.config.sc_prim_fifo_size_backend = 0x100; - adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; - adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; - gb_addr_config = CARRIZO_GB_ADDR_CONFIG_GOLDEN; - break; - default: - adev->gfx.config.max_shader_engines = 2; - adev->gfx.config.max_tile_pipes = 4; - adev->gfx.config.max_cu_per_sh = 2; - adev->gfx.config.max_sh_per_se = 1; - adev->gfx.config.max_backends_per_se = 2; - adev->gfx.config.max_texture_channel_caches = 4; - adev->gfx.config.max_gprs = 256; - adev->gfx.config.max_gs_threads = 32; - adev->gfx.config.max_hw_contexts = 8; - - adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; - adev->gfx.config.sc_prim_fifo_size_backend = 0x100; - adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; - adev->gfx.config.sc_earlyz_tile_fifo_size = 0x130; - gb_addr_config = TONGA_GB_ADDR_CONFIG_GOLDEN; - break; - } - tmp = RREG32(mmGRBM_CNTL); tmp = REG_SET_FIELD(tmp, GRBM_CNTL, READ_TIMEOUT, 0xff); WREG32(mmGRBM_CNTL, tmp); - mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP); - adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG); - mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg; - - adev->gfx.config.num_tile_pipes = adev->gfx.config.max_tile_pipes; - adev->gfx.config.mem_max_burst_length_bytes = 256; - if (adev->flags & AMD_IS_APU) { - /* Get memory bank mapping mode. */ - tmp = RREG32(mmMC_FUS_DRAM0_BANK_ADDR_MAPPING); - dimm00_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM0ADDRMAP); - dimm01_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM0_BANK_ADDR_MAPPING, DIMM1ADDRMAP); - - tmp = RREG32(mmMC_FUS_DRAM1_BANK_ADDR_MAPPING); - dimm10_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM0ADDRMAP); - dimm11_addr_map = REG_GET_FIELD(tmp, MC_FUS_DRAM1_BANK_ADDR_MAPPING, DIMM1ADDRMAP); - - /* Validate settings in case only one DIMM installed. */ - if ((dimm00_addr_map == 0) || (dimm00_addr_map == 3) || (dimm00_addr_map == 4) || (dimm00_addr_map > 12)) - dimm00_addr_map = 0; - if ((dimm01_addr_map == 0) || (dimm01_addr_map == 3) || (dimm01_addr_map == 4) || (dimm01_addr_map > 12)) - dimm01_addr_map = 0; - if ((dimm10_addr_map == 0) || (dimm10_addr_map == 3) || (dimm10_addr_map == 4) || (dimm10_addr_map > 12)) - dimm10_addr_map = 0; - if ((dimm11_addr_map == 0) || (dimm11_addr_map == 3) || (dimm11_addr_map == 4) || (dimm11_addr_map > 12)) - dimm11_addr_map = 0; - - /* If DIMM Addr map is 8GB, ROW size should be 2KB. Otherwise 1KB. */ - /* If ROW size(DIMM1) != ROW size(DMIMM0), ROW size should be larger one. */ - if ((dimm00_addr_map == 11) || (dimm01_addr_map == 11) || (dimm10_addr_map == 11) || (dimm11_addr_map == 11)) - adev->gfx.config.mem_row_size_in_kb = 2; - else - adev->gfx.config.mem_row_size_in_kb = 1; - } else { - tmp = REG_GET_FIELD(mc_arb_ramcfg, MC_ARB_RAMCFG, NOOFCOLS); - adev->gfx.config.mem_row_size_in_kb = (4 * (1 << (8 + tmp))) / 1024; - if (adev->gfx.config.mem_row_size_in_kb > 4) - adev->gfx.config.mem_row_size_in_kb = 4; - } - - adev->gfx.config.shader_engine_tile_size = 32; - adev->gfx.config.num_gpus = 1; - adev->gfx.config.multi_gpu_tile_size = 64; - - /* fix up row size */ - switch (adev->gfx.config.mem_row_size_in_kb) { - case 1: - default: - gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 0); - break; - case 2: - gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 1); - break; - case 4: - gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 2); - break; - } - adev->gfx.config.gb_addr_config = gb_addr_config; - - WREG32(mmGB_ADDR_CONFIG, gb_addr_config); - WREG32(mmHDP_ADDR_CONFIG, gb_addr_config); - WREG32(mmDMIF_ADDR_CALC, gb_addr_config); + WREG32(mmGB_ADDR_CONFIG, adev->gfx.config.gb_addr_config); + WREG32(mmHDP_ADDR_CONFIG, adev->gfx.config.gb_addr_config); + WREG32(mmDMIF_ADDR_CALC, adev->gfx.config.gb_addr_config); WREG32(mmSDMA0_TILING_CONFIG + SDMA0_REGISTER_OFFSET, - gb_addr_config & 0x70); + adev->gfx.config.gb_addr_config & 0x70); WREG32(mmSDMA0_TILING_CONFIG + SDMA1_REGISTER_OFFSET, - gb_addr_config & 0x70); - WREG32(mmUVD_UDEC_ADDR_CONFIG, gb_addr_config); - WREG32(mmUVD_UDEC_DB_ADDR_CONFIG, gb_addr_config); - WREG32(mmUVD_UDEC_DBW_ADDR_CONFIG, gb_addr_config); + adev->gfx.config.gb_addr_config & 0x70); + WREG32(mmUVD_UDEC_ADDR_CONFIG, adev->gfx.config.gb_addr_config); + WREG32(mmUVD_UDEC_DB_ADDR_CONFIG, adev->gfx.config.gb_addr_config); + WREG32(mmUVD_UDEC_DBW_ADDR_CONFIG, adev->gfx.config.gb_addr_config); gfx_v8_0_tiling_mode_table_init(adev); @@ -2256,13 +2263,13 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) if (i == 0) { tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_UC); tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_UC); - tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE, + tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE, SH_MEM_ALIGNMENT_MODE_UNALIGNED); WREG32(mmSH_MEM_CONFIG, tmp); } else { tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, DEFAULT_MTYPE, MTYPE_NC); tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, APE1_MTYPE, MTYPE_NC); - tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE, + tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, ALIGNMENT_MODE, SH_MEM_ALIGNMENT_MODE_UNALIGNED); WREG32(mmSH_MEM_CONFIG, tmp); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 774528a..4883482 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -436,6 +436,33 @@ static int gmc_v7_0_gart_set_pte_pde(struct amdgpu_device *adev, } /** + * gmc_v8_0_set_fault_enable_default - update VM fault handling + * + * @adev: amdgpu_device pointer + * @value: true redirects VM faults to the default page + */ +static void gmc_v7_0_set_fault_enable_default(struct amdgpu_device *adev, + bool value) +{ + u32 tmp; + + tmp = RREG32(mmVM_CONTEXT1_CNTL); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + VALID_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + READ_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, value); + WREG32(mmVM_CONTEXT1_CNTL, tmp); +} + +/** * gmc_v7_0_gart_enable - gart enable * * @adev: amdgpu_device pointer @@ -523,15 +550,13 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev) tmp = RREG32(mmVM_CONTEXT1_CNTL); tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, ENABLE_CONTEXT, 1); tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_DEPTH, 1); - tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1); - tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1); - tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1); - tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1); - tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1); - tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1); tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_BLOCK_SIZE, amdgpu_vm_block_size - 9); WREG32(mmVM_CONTEXT1_CNTL, tmp); + if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) + gmc_v7_0_set_fault_enable_default(adev, false); + else + gmc_v7_0_set_fault_enable_default(adev, true); if (adev->asic_type == CHIP_KAVERI) { tmp = RREG32(mmCHUB_CONTROL); @@ -1262,6 +1287,15 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev, addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT); + /* reset addr and status */ + WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); + + if (!addr && !status) + return 0; + + if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST) + gmc_v7_0_set_fault_enable_default(adev, false); + dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", entry->src_id, entry->src_data); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", @@ -1269,8 +1303,6 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev, dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); gmc_v7_0_vm_decode_fault(adev, status, addr, mc_client); - /* reset addr and status */ - WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 9a07742..42b5ff8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -550,6 +550,35 @@ static int gmc_v8_0_gart_set_pte_pde(struct amdgpu_device *adev, } /** + * gmc_v8_0_set_fault_enable_default - update VM fault handling + * + * @adev: amdgpu_device pointer + * @value: true redirects VM faults to the default page + */ +static void gmc_v8_0_set_fault_enable_default(struct amdgpu_device *adev, + bool value) +{ + u32 tmp; + + tmp = RREG32(mmVM_CONTEXT1_CNTL); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + VALID_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + READ_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, value); + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, value); + WREG32(mmVM_CONTEXT1_CNTL, tmp); +} + +/** * gmc_v8_0_gart_enable - gart enable * * @adev: amdgpu_device pointer @@ -663,6 +692,10 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_BLOCK_SIZE, amdgpu_vm_block_size - 9); WREG32(mmVM_CONTEXT1_CNTL, tmp); + if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) + gmc_v8_0_set_fault_enable_default(adev, false); + else + gmc_v8_0_set_fault_enable_default(adev, true); gmc_v8_0_gart_flush_gpu_tlb(adev, 0); DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n", @@ -1262,6 +1295,15 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT); + /* reset addr and status */ + WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); + + if (!addr && !status) + return 0; + + if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST) + gmc_v8_0_set_fault_enable_default(adev, false); + dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", entry->src_id, entry->src_data); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", @@ -1269,8 +1311,6 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client); - /* reset addr and status */ - WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index 94ec04a..9745ed3 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -2995,6 +2995,12 @@ static int kv_dpm_late_init(void *handle) { /* powerdown unused blocks for now */ struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int ret; + + /* init the sysfs and debugfs files late */ + ret = amdgpu_pm_sysfs_init(adev); + if (ret) + return ret; kv_dpm_powergate_acp(adev, true); kv_dpm_powergate_samu(adev, true); @@ -3038,9 +3044,6 @@ static int kv_dpm_sw_init(void *handle) adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; if (amdgpu_dpm == 1) amdgpu_pm_print_power_states(adev); - ret = amdgpu_pm_sysfs_init(adev); - if (ret) - goto dpm_failed; mutex_unlock(&adev->pm.mutex); DRM_INFO("amdgpu: dpm initialized\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 14e8723..f8b868c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -118,7 +118,7 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev) { const char *chip_name; char fw_name[30]; - int err, i; + int err = 0, i; struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; const struct sdma_firmware_header_v1_0 *hdr; @@ -132,27 +132,27 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev) default: BUG(); } - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { if (i == 0) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name); - err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev); + err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); if (err) goto out; - err = amdgpu_ucode_validate(adev->sdma[i].fw); + err = amdgpu_ucode_validate(adev->sdma.instance[i].fw); if (err) goto out; - hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; - adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); - adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); - if (adev->sdma[i].feature_version >= 20) - adev->sdma[i].burst_nop = true; + hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; + adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); + if (adev->sdma.instance[i].feature_version >= 20) + adev->sdma.instance[i].burst_nop = true; if (adev->firmware.smu_load) { info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i; - info->fw = adev->sdma[i].fw; + info->fw = adev->sdma.instance[i].fw; header = (const struct common_firmware_header *)info->fw->data; adev->firmware.fw_size += ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); @@ -164,9 +164,9 @@ out: printk(KERN_ERR "sdma_v2_4: Failed to load firmware \"%s\"\n", fw_name); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - release_firmware(adev->sdma[i].fw); - adev->sdma[i].fw = NULL; + for (i = 0; i < adev->sdma.num_instances; i++) { + release_firmware(adev->sdma.instance[i].fw); + adev->sdma.instance[i].fw = NULL; } } return err; @@ -199,7 +199,7 @@ static uint32_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring) static uint32_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1; + int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1; u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2; return wptr; @@ -215,14 +215,14 @@ static uint32_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring) static void sdma_v2_4_ring_set_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1; + int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1; WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2); } static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) { - struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring); + struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring); int i; for (i = 0; i < count; i++) @@ -284,7 +284,7 @@ static void sdma_v2_4_ring_emit_hdp_flush(struct amdgpu_ring *ring) { u32 ref_and_mask = 0; - if (ring == &ring->adev->sdma[0].ring) + if (ring == &ring->adev->sdma.instance[0].ring) ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1); else ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1); @@ -368,8 +368,8 @@ static bool sdma_v2_4_ring_emit_semaphore(struct amdgpu_ring *ring, */ static void sdma_v2_4_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma[1].ring; + struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; + struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; @@ -377,7 +377,7 @@ static void sdma_v2_4_gfx_stop(struct amdgpu_device *adev) (adev->mman.buffer_funcs_ring == sdma1)) amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl); @@ -419,7 +419,7 @@ static void sdma_v2_4_enable(struct amdgpu_device *adev, bool enable) sdma_v2_4_rlc_stop(adev); } - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { f32_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]); if (enable) f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 0); @@ -445,8 +445,8 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev) u32 wb_offset; int i, j, r; - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - ring = &adev->sdma[i].ring; + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; wb_offset = (ring->rptr_offs * 4); mutex_lock(&adev->srbm_mutex); @@ -545,29 +545,23 @@ static int sdma_v2_4_load_microcode(struct amdgpu_device *adev) const __le32 *fw_data; u32 fw_size; int i, j; - bool smc_loads_fw = false; /* XXX fix me */ - - if (!adev->sdma[0].fw || !adev->sdma[1].fw) - return -EINVAL; /* halt the MEs */ sdma_v2_4_enable(adev, false); - if (smc_loads_fw) { - /* XXX query SMC for fw load complete */ - } else { - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; - amdgpu_ucode_print_sdma_hdr(&hdr->header); - fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; - fw_data = (const __le32 *) - (adev->sdma[i].fw->data + - le32_to_cpu(hdr->header.ucode_array_offset_bytes)); - WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0); - for (j = 0; j < fw_size; j++) - WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++)); - WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version); - } + for (i = 0; i < adev->sdma.num_instances; i++) { + if (!adev->sdma.instance[i].fw) + return -EINVAL; + hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; + amdgpu_ucode_print_sdma_hdr(&hdr->header); + fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; + fw_data = (const __le32 *) + (adev->sdma.instance[i].fw->data + + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); + WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0); + for (j = 0; j < fw_size; j++) + WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++)); + WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version); } return 0; @@ -894,7 +888,7 @@ static void sdma_v2_4_vm_set_pte_pde(struct amdgpu_ib *ib, */ static void sdma_v2_4_vm_pad_ib(struct amdgpu_ib *ib) { - struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring); + struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring); u32 pad_count; int i; @@ -952,6 +946,8 @@ static int sdma_v2_4_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + adev->sdma.num_instances = SDMA_MAX_INSTANCE; + sdma_v2_4_set_ring_funcs(adev); sdma_v2_4_set_buffer_funcs(adev); sdma_v2_4_set_vm_pte_funcs(adev); @@ -963,21 +959,21 @@ static int sdma_v2_4_early_init(void *handle) static int sdma_v2_4_sw_init(void *handle) { struct amdgpu_ring *ring; - int r; + int r, i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SDMA trap event */ - r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq); + r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq); + r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq); + r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq); if (r) return r; @@ -987,31 +983,20 @@ static int sdma_v2_4_sw_init(void *handle) return r; } - ring = &adev->sdma[0].ring; - ring->ring_obj = NULL; - ring->use_doorbell = false; - - ring = &adev->sdma[1].ring; - ring->ring_obj = NULL; - ring->use_doorbell = false; - - ring = &adev->sdma[0].ring; - sprintf(ring->name, "sdma0"); - r = amdgpu_ring_init(adev, ring, 256 * 1024, - SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf, - &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0, - AMDGPU_RING_TYPE_SDMA); - if (r) - return r; - - ring = &adev->sdma[1].ring; - sprintf(ring->name, "sdma1"); - r = amdgpu_ring_init(adev, ring, 256 * 1024, - SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf, - &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1, - AMDGPU_RING_TYPE_SDMA); - if (r) - return r; + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; + ring->ring_obj = NULL; + ring->use_doorbell = false; + sprintf(ring->name, "sdma%d", i); + r = amdgpu_ring_init(adev, ring, 256 * 1024, + SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf, + &adev->sdma.trap_irq, + (i == 0) ? + AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1, + AMDGPU_RING_TYPE_SDMA); + if (r) + return r; + } return r; } @@ -1019,9 +1004,10 @@ static int sdma_v2_4_sw_init(void *handle) static int sdma_v2_4_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int i; - amdgpu_ring_fini(&adev->sdma[0].ring); - amdgpu_ring_fini(&adev->sdma[1].ring); + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ring_fini(&adev->sdma.instance[i].ring); return 0; } @@ -1100,7 +1086,7 @@ static void sdma_v2_4_print_status(void *handle) dev_info(adev->dev, "VI SDMA registers\n"); dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n", RREG32(mmSRBM_STATUS2)); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n", i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i])); dev_info(adev->dev, " SDMA%d_F32_CNTL=0x%08X\n", @@ -1243,7 +1229,7 @@ static int sdma_v2_4_process_trap_irq(struct amdgpu_device *adev, case 0: switch (queue_id) { case 0: - amdgpu_fence_process(&adev->sdma[0].ring); + amdgpu_fence_process(&adev->sdma.instance[0].ring); break; case 1: /* XXX compute */ @@ -1256,7 +1242,7 @@ static int sdma_v2_4_process_trap_irq(struct amdgpu_device *adev, case 1: switch (queue_id) { case 0: - amdgpu_fence_process(&adev->sdma[1].ring); + amdgpu_fence_process(&adev->sdma.instance[1].ring); break; case 1: /* XXX compute */ @@ -1345,8 +1331,10 @@ static const struct amdgpu_ring_funcs sdma_v2_4_ring_funcs = { static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev) { - adev->sdma[0].ring.funcs = &sdma_v2_4_ring_funcs; - adev->sdma[1].ring.funcs = &sdma_v2_4_ring_funcs; + int i; + + for (i = 0; i < adev->sdma.num_instances; i++) + adev->sdma.instance[i].ring.funcs = &sdma_v2_4_ring_funcs; } static const struct amdgpu_irq_src_funcs sdma_v2_4_trap_irq_funcs = { @@ -1360,9 +1348,9 @@ static const struct amdgpu_irq_src_funcs sdma_v2_4_illegal_inst_irq_funcs = { static void sdma_v2_4_set_irq_funcs(struct amdgpu_device *adev) { - adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST; - adev->sdma_trap_irq.funcs = &sdma_v2_4_trap_irq_funcs; - adev->sdma_illegal_inst_irq.funcs = &sdma_v2_4_illegal_inst_irq_funcs; + adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST; + adev->sdma.trap_irq.funcs = &sdma_v2_4_trap_irq_funcs; + adev->sdma.illegal_inst_irq.funcs = &sdma_v2_4_illegal_inst_irq_funcs; } /** @@ -1428,7 +1416,7 @@ static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev) { if (adev->mman.buffer_funcs == NULL) { adev->mman.buffer_funcs = &sdma_v2_4_buffer_funcs; - adev->mman.buffer_funcs_ring = &adev->sdma[0].ring; + adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring; } } @@ -1443,7 +1431,7 @@ static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev) { if (adev->vm_manager.vm_pte_funcs == NULL) { adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs; - adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring; + adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring; adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true; } } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 9bfe92d..670555a 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -184,7 +184,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) { const char *chip_name; char fw_name[30]; - int err, i; + int err = 0, i; struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; const struct sdma_firmware_header_v1_0 *hdr; @@ -204,27 +204,27 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) default: BUG(); } - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { if (i == 0) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name); - err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev); + err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); if (err) goto out; - err = amdgpu_ucode_validate(adev->sdma[i].fw); + err = amdgpu_ucode_validate(adev->sdma.instance[i].fw); if (err) goto out; - hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; - adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version); - adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); - if (adev->sdma[i].feature_version >= 20) - adev->sdma[i].burst_nop = true; + hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; + adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version); + adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version); + if (adev->sdma.instance[i].feature_version >= 20) + adev->sdma.instance[i].burst_nop = true; if (adev->firmware.smu_load) { info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i; - info->fw = adev->sdma[i].fw; + info->fw = adev->sdma.instance[i].fw; header = (const struct common_firmware_header *)info->fw->data; adev->firmware.fw_size += ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); @@ -235,9 +235,9 @@ out: printk(KERN_ERR "sdma_v3_0: Failed to load firmware \"%s\"\n", fw_name); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - release_firmware(adev->sdma[i].fw); - adev->sdma[i].fw = NULL; + for (i = 0; i < adev->sdma.num_instances; i++) { + release_firmware(adev->sdma.instance[i].fw); + adev->sdma.instance[i].fw = NULL; } } return err; @@ -276,7 +276,7 @@ static uint32_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring) /* XXX check if swapping is necessary on BE */ wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2; } else { - int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1; + int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1; wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2; } @@ -300,7 +300,7 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring) adev->wb.wb[ring->wptr_offs] = ring->wptr << 2; WDOORBELL32(ring->doorbell_index, ring->wptr << 2); } else { - int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1; + int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1; WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2); } @@ -308,7 +308,7 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring) static void sdma_v3_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) { - struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring); + struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring); int i; for (i = 0; i < count; i++) @@ -369,7 +369,7 @@ static void sdma_v3_0_ring_emit_hdp_flush(struct amdgpu_ring *ring) { u32 ref_and_mask = 0; - if (ring == &ring->adev->sdma[0].ring) + if (ring == &ring->adev->sdma.instance[0].ring) ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1); else ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1); @@ -454,8 +454,8 @@ static bool sdma_v3_0_ring_emit_semaphore(struct amdgpu_ring *ring, */ static void sdma_v3_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma[1].ring; + struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; + struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; @@ -463,7 +463,7 @@ static void sdma_v3_0_gfx_stop(struct amdgpu_device *adev) (adev->mman.buffer_funcs_ring == sdma1)) amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl); @@ -500,7 +500,7 @@ static void sdma_v3_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable) u32 f32_cntl; int i; - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { f32_cntl = RREG32(mmSDMA0_CNTL + sdma_offsets[i]); if (enable) f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL, @@ -530,7 +530,7 @@ static void sdma_v3_0_enable(struct amdgpu_device *adev, bool enable) sdma_v3_0_rlc_stop(adev); } - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { f32_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]); if (enable) f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 0); @@ -557,8 +557,8 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev) u32 doorbell; int i, j, r; - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - ring = &adev->sdma[i].ring; + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; wb_offset = (ring->rptr_offs * 4); mutex_lock(&adev->srbm_mutex); @@ -669,23 +669,22 @@ static int sdma_v3_0_load_microcode(struct amdgpu_device *adev) u32 fw_size; int i, j; - if (!adev->sdma[0].fw || !adev->sdma[1].fw) - return -EINVAL; - /* halt the MEs */ sdma_v3_0_enable(adev, false); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { - hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data; + for (i = 0; i < adev->sdma.num_instances; i++) { + if (!adev->sdma.instance[i].fw) + return -EINVAL; + hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; amdgpu_ucode_print_sdma_hdr(&hdr->header); fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4; fw_data = (const __le32 *) - (adev->sdma[i].fw->data + + (adev->sdma.instance[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0); for (j = 0; j < fw_size; j++) WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++)); - WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version); + WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version); } return 0; @@ -701,21 +700,21 @@ static int sdma_v3_0_load_microcode(struct amdgpu_device *adev) */ static int sdma_v3_0_start(struct amdgpu_device *adev) { - int r; + int r, i; if (!adev->firmware.smu_load) { r = sdma_v3_0_load_microcode(adev); if (r) return r; } else { - r = adev->smu.smumgr_funcs->check_fw_load_finish(adev, - AMDGPU_UCODE_ID_SDMA0); - if (r) - return -EINVAL; - r = adev->smu.smumgr_funcs->check_fw_load_finish(adev, - AMDGPU_UCODE_ID_SDMA1); - if (r) - return -EINVAL; + for (i = 0; i < adev->sdma.num_instances; i++) { + r = adev->smu.smumgr_funcs->check_fw_load_finish(adev, + (i == 0) ? + AMDGPU_UCODE_ID_SDMA0 : + AMDGPU_UCODE_ID_SDMA1); + if (r) + return -EINVAL; + } } /* unhalt the MEs */ @@ -1013,7 +1012,7 @@ static void sdma_v3_0_vm_set_pte_pde(struct amdgpu_ib *ib, */ static void sdma_v3_0_vm_pad_ib(struct amdgpu_ib *ib) { - struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring); + struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring); u32 pad_count; int i; @@ -1071,6 +1070,12 @@ static int sdma_v3_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + switch (adev->asic_type) { + default: + adev->sdma.num_instances = SDMA_MAX_INSTANCE; + break; + } + sdma_v3_0_set_ring_funcs(adev); sdma_v3_0_set_buffer_funcs(adev); sdma_v3_0_set_vm_pte_funcs(adev); @@ -1082,21 +1087,21 @@ static int sdma_v3_0_early_init(void *handle) static int sdma_v3_0_sw_init(void *handle) { struct amdgpu_ring *ring; - int r; + int r, i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SDMA trap event */ - r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq); + r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq); + r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq); + r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq); if (r) return r; @@ -1106,33 +1111,23 @@ static int sdma_v3_0_sw_init(void *handle) return r; } - ring = &adev->sdma[0].ring; - ring->ring_obj = NULL; - ring->use_doorbell = true; - ring->doorbell_index = AMDGPU_DOORBELL_sDMA_ENGINE0; - - ring = &adev->sdma[1].ring; - ring->ring_obj = NULL; - ring->use_doorbell = true; - ring->doorbell_index = AMDGPU_DOORBELL_sDMA_ENGINE1; - - ring = &adev->sdma[0].ring; - sprintf(ring->name, "sdma0"); - r = amdgpu_ring_init(adev, ring, 256 * 1024, - SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf, - &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0, - AMDGPU_RING_TYPE_SDMA); - if (r) - return r; - - ring = &adev->sdma[1].ring; - sprintf(ring->name, "sdma1"); - r = amdgpu_ring_init(adev, ring, 256 * 1024, - SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf, - &adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1, - AMDGPU_RING_TYPE_SDMA); - if (r) - return r; + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; + ring->ring_obj = NULL; + ring->use_doorbell = true; + ring->doorbell_index = (i == 0) ? + AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1; + + sprintf(ring->name, "sdma%d", i); + r = amdgpu_ring_init(adev, ring, 256 * 1024, + SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf, + &adev->sdma.trap_irq, + (i == 0) ? + AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1, + AMDGPU_RING_TYPE_SDMA); + if (r) + return r; + } return r; } @@ -1140,9 +1135,10 @@ static int sdma_v3_0_sw_init(void *handle) static int sdma_v3_0_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int i; - amdgpu_ring_fini(&adev->sdma[0].ring); - amdgpu_ring_fini(&adev->sdma[1].ring); + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ring_fini(&adev->sdma.instance[i].ring); return 0; } @@ -1222,7 +1218,7 @@ static void sdma_v3_0_print_status(void *handle) dev_info(adev->dev, "VI SDMA registers\n"); dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n", RREG32(mmSRBM_STATUS2)); - for (i = 0; i < SDMA_MAX_INSTANCE; i++) { + for (i = 0; i < adev->sdma.num_instances; i++) { dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n", i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i])); dev_info(adev->dev, " SDMA%d_F32_CNTL=0x%08X\n", @@ -1367,7 +1363,7 @@ static int sdma_v3_0_process_trap_irq(struct amdgpu_device *adev, case 0: switch (queue_id) { case 0: - amdgpu_fence_process(&adev->sdma[0].ring); + amdgpu_fence_process(&adev->sdma.instance[0].ring); break; case 1: /* XXX compute */ @@ -1380,7 +1376,7 @@ static int sdma_v3_0_process_trap_irq(struct amdgpu_device *adev, case 1: switch (queue_id) { case 0: - amdgpu_fence_process(&adev->sdma[1].ring); + amdgpu_fence_process(&adev->sdma.instance[1].ring); break; case 1: /* XXX compute */ @@ -1468,8 +1464,10 @@ static const struct amdgpu_ring_funcs sdma_v3_0_ring_funcs = { static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev) { - adev->sdma[0].ring.funcs = &sdma_v3_0_ring_funcs; - adev->sdma[1].ring.funcs = &sdma_v3_0_ring_funcs; + int i; + + for (i = 0; i < adev->sdma.num_instances; i++) + adev->sdma.instance[i].ring.funcs = &sdma_v3_0_ring_funcs; } static const struct amdgpu_irq_src_funcs sdma_v3_0_trap_irq_funcs = { @@ -1483,9 +1481,9 @@ static const struct amdgpu_irq_src_funcs sdma_v3_0_illegal_inst_irq_funcs = { static void sdma_v3_0_set_irq_funcs(struct amdgpu_device *adev) { - adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST; - adev->sdma_trap_irq.funcs = &sdma_v3_0_trap_irq_funcs; - adev->sdma_illegal_inst_irq.funcs = &sdma_v3_0_illegal_inst_irq_funcs; + adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST; + adev->sdma.trap_irq.funcs = &sdma_v3_0_trap_irq_funcs; + adev->sdma.illegal_inst_irq.funcs = &sdma_v3_0_illegal_inst_irq_funcs; } /** @@ -1551,7 +1549,7 @@ static void sdma_v3_0_set_buffer_funcs(struct amdgpu_device *adev) { if (adev->mman.buffer_funcs == NULL) { adev->mman.buffer_funcs = &sdma_v3_0_buffer_funcs; - adev->mman.buffer_funcs_ring = &adev->sdma[0].ring; + adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring; } } @@ -1566,7 +1564,7 @@ static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev) { if (adev->vm_manager.vm_pte_funcs == NULL) { adev->vm_manager.vm_pte_funcs = &sdma_v3_0_vm_pte_funcs; - adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring; + adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring; adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true; } } diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index b55ceb1..0bac8702 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -1005,6 +1005,9 @@ static void vi_pcie_gen3_enable(struct amdgpu_device *adev) u32 mask; int ret; + if (pci_is_root_bus(adev->pdev->bus)) + return; + if (amdgpu_pcie_gen2 == 0) return; diff --git a/drivers/gpu/drm/amd/include/cgs_linux.h b/drivers/gpu/drm/amd/include/cgs_linux.h index 488642f..3b47ae3 100644 --- a/drivers/gpu/drm/amd/include/cgs_linux.h +++ b/drivers/gpu/drm/amd/include/cgs_linux.h @@ -27,19 +27,6 @@ #include "cgs_common.h" /** - * cgs_import_gpu_mem() - Import dmabuf handle - * @cgs_device: opaque device handle - * @dmabuf_fd: DMABuf file descriptor - * @handle: memory handle (output) - * - * Must be called in the process context that dmabuf_fd belongs to. - * - * Return: 0 on success, -errno otherwise - */ -typedef int (*cgs_import_gpu_mem_t)(void *cgs_device, int dmabuf_fd, - cgs_handle_t *handle); - -/** * cgs_irq_source_set_func() - Callback for enabling/disabling interrupt sources * @private_data: private data provided to cgs_add_irq_source * @src_id: interrupt source ID @@ -114,16 +101,12 @@ typedef int (*cgs_irq_get_t)(void *cgs_device, unsigned src_id, unsigned type); typedef int (*cgs_irq_put_t)(void *cgs_device, unsigned src_id, unsigned type); struct cgs_os_ops { - cgs_import_gpu_mem_t import_gpu_mem; - /* IRQ handling */ cgs_add_irq_source_t add_irq_source; cgs_irq_get_t irq_get; cgs_irq_put_t irq_put; }; -#define cgs_import_gpu_mem(dev,dmabuf_fd,handle) \ - CGS_OS_CALL(import_gpu_mem,dev,dmabuf_fd,handle) #define cgs_add_irq_source(dev,src_id,num_types,set,handler,private_data) \ CGS_OS_CALL(add_irq_source,dev,src_id,num_types,set,handler, \ private_data) diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 3697eee..7fa1d7a 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -327,19 +327,49 @@ static void amd_sched_process_job(struct fence *f, struct fence_cb *cb) struct amd_sched_fence *s_fence = container_of(cb, struct amd_sched_fence, cb); struct amd_gpu_scheduler *sched = s_fence->sched; + unsigned long flags; atomic_dec(&sched->hw_rq_count); amd_sched_fence_signal(s_fence); + if (sched->timeout != MAX_SCHEDULE_TIMEOUT) { + cancel_delayed_work_sync(&s_fence->dwork); + spin_lock_irqsave(&sched->fence_list_lock, flags); + list_del_init(&s_fence->list); + spin_unlock_irqrestore(&sched->fence_list_lock, flags); + } fence_put(&s_fence->base); wake_up_interruptible(&sched->wake_up_worker); } +static void amd_sched_fence_work_func(struct work_struct *work) +{ + struct amd_sched_fence *s_fence = + container_of(work, struct amd_sched_fence, dwork.work); + struct amd_gpu_scheduler *sched = s_fence->sched; + struct amd_sched_fence *entity, *tmp; + unsigned long flags; + + DRM_ERROR("[%s] scheduler is timeout!\n", sched->name); + + /* Clean all pending fences */ + spin_lock_irqsave(&sched->fence_list_lock, flags); + list_for_each_entry_safe(entity, tmp, &sched->fence_list, list) { + DRM_ERROR(" fence no %d\n", entity->base.seqno); + cancel_delayed_work(&entity->dwork); + list_del_init(&entity->list); + fence_put(&entity->base); + } + spin_unlock_irqrestore(&sched->fence_list_lock, flags); +} + static int amd_sched_main(void *param) { struct sched_param sparam = {.sched_priority = 1}; struct amd_gpu_scheduler *sched = (struct amd_gpu_scheduler *)param; int r, count; + spin_lock_init(&sched->fence_list_lock); + INIT_LIST_HEAD(&sched->fence_list); sched_setscheduler(current, SCHED_FIFO, &sparam); while (!kthread_should_stop()) { @@ -347,6 +377,7 @@ static int amd_sched_main(void *param) struct amd_sched_fence *s_fence; struct amd_sched_job *sched_job; struct fence *fence; + unsigned long flags; wait_event_interruptible(sched->wake_up_worker, kthread_should_stop() || @@ -357,6 +388,15 @@ static int amd_sched_main(void *param) entity = sched_job->s_entity; s_fence = sched_job->s_fence; + + if (sched->timeout != MAX_SCHEDULE_TIMEOUT) { + INIT_DELAYED_WORK(&s_fence->dwork, amd_sched_fence_work_func); + schedule_delayed_work(&s_fence->dwork, sched->timeout); + spin_lock_irqsave(&sched->fence_list_lock, flags); + list_add_tail(&s_fence->list, &sched->fence_list); + spin_unlock_irqrestore(&sched->fence_list_lock, flags); + } + atomic_inc(&sched->hw_rq_count); fence = sched->ops->run_job(sched_job); if (fence) { @@ -392,11 +432,12 @@ static int amd_sched_main(void *param) */ int amd_sched_init(struct amd_gpu_scheduler *sched, struct amd_sched_backend_ops *ops, - unsigned hw_submission, const char *name) + unsigned hw_submission, long timeout, const char *name) { sched->ops = ops; sched->hw_submission_limit = hw_submission; sched->name = name; + sched->timeout = timeout; amd_sched_rq_init(&sched->sched_rq); amd_sched_rq_init(&sched->kernel_rq); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h index 80b64dc..929e9ac 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h @@ -68,6 +68,8 @@ struct amd_sched_fence { struct amd_gpu_scheduler *sched; spinlock_t lock; void *owner; + struct delayed_work dwork; + struct list_head list; }; struct amd_sched_job { @@ -103,18 +105,21 @@ struct amd_sched_backend_ops { struct amd_gpu_scheduler { struct amd_sched_backend_ops *ops; uint32_t hw_submission_limit; + long timeout; const char *name; struct amd_sched_rq sched_rq; struct amd_sched_rq kernel_rq; wait_queue_head_t wake_up_worker; wait_queue_head_t job_scheduled; atomic_t hw_rq_count; + struct list_head fence_list; + spinlock_t fence_list_lock; struct task_struct *thread; }; int amd_sched_init(struct amd_gpu_scheduler *sched, struct amd_sched_backend_ops *ops, - uint32_t hw_submission, const char *name); + uint32_t hw_submission, long timeout, const char *name); void amd_sched_fini(struct amd_gpu_scheduler *sched); int amd_sched_entity_init(struct amd_gpu_scheduler *sched, diff --git a/drivers/gpu/drm/armada/Kconfig b/drivers/gpu/drm/armada/Kconfig index 50ae88a..eb773e9 100644 --- a/drivers/gpu/drm/armada/Kconfig +++ b/drivers/gpu/drm/armada/Kconfig @@ -14,12 +14,3 @@ config DRM_ARMADA This driver provides no built-in acceleration; acceleration is performed by other IP found on the SoC. This driver provides kernel mode setting and buffer management to userspace. - -config DRM_ARMADA_TDA1998X - bool "Support TDA1998X HDMI output" - depends on DRM_ARMADA != n - depends on I2C && DRM_I2C_NXP_TDA998X = y - default y - help - Support the TDA1998x HDMI output device found on the Solid-Run - CuBox. diff --git a/drivers/gpu/drm/armada/Makefile b/drivers/gpu/drm/armada/Makefile index d6f43e0..ffd6736 100644 --- a/drivers/gpu/drm/armada/Makefile +++ b/drivers/gpu/drm/armada/Makefile @@ -1,6 +1,5 @@ armada-y := armada_crtc.o armada_drv.o armada_fb.o armada_fbdev.o \ - armada_gem.o armada_output.o armada_overlay.o \ - armada_slave.o + armada_gem.o armada_overlay.o armada-y += armada_510.o armada-$(CONFIG_DEBUG_FS) += armada_debugfs.o diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index 01ffe9b..cebcab5 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -20,6 +20,7 @@ #include "armada_hw.h" struct armada_frame_work { + struct armada_plane_work work; struct drm_pending_vblank_event *event; struct armada_regs regs[4]; struct drm_framebuffer *old_fb; @@ -33,6 +34,23 @@ enum csc_mode { CSC_RGB_STUDIO = 2, }; +static const uint32_t armada_primary_formats[] = { + DRM_FORMAT_UYVY, + DRM_FORMAT_YUYV, + DRM_FORMAT_VYUY, + DRM_FORMAT_YVYU, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_RGB888, + DRM_FORMAT_BGR888, + DRM_FORMAT_ARGB1555, + DRM_FORMAT_ABGR1555, + DRM_FORMAT_RGB565, + DRM_FORMAT_BGR565, +}; + /* * A note about interlacing. Let's consider HDMI 1920x1080i. * The timing parameters we have from X are: @@ -173,49 +191,82 @@ static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb, return i; } -static int armada_drm_crtc_queue_frame_work(struct armada_crtc *dcrtc, - struct armada_frame_work *work) +static void armada_drm_plane_work_run(struct armada_crtc *dcrtc, + struct armada_plane *plane) +{ + struct armada_plane_work *work = xchg(&plane->work, NULL); + + /* Handle any pending frame work. */ + if (work) { + work->fn(dcrtc, plane, work); + drm_vblank_put(dcrtc->crtc.dev, dcrtc->num); + } + + wake_up(&plane->frame_wait); +} + +int armada_drm_plane_work_queue(struct armada_crtc *dcrtc, + struct armada_plane *plane, struct armada_plane_work *work) { - struct drm_device *dev = dcrtc->crtc.dev; - unsigned long flags; int ret; - ret = drm_vblank_get(dev, dcrtc->num); + ret = drm_vblank_get(dcrtc->crtc.dev, dcrtc->num); if (ret) { DRM_ERROR("failed to acquire vblank counter\n"); return ret; } - spin_lock_irqsave(&dev->event_lock, flags); - if (!dcrtc->frame_work) - dcrtc->frame_work = work; - else - ret = -EBUSY; - spin_unlock_irqrestore(&dev->event_lock, flags); - + ret = cmpxchg(&plane->work, NULL, work) ? -EBUSY : 0; if (ret) - drm_vblank_put(dev, dcrtc->num); + drm_vblank_put(dcrtc->crtc.dev, dcrtc->num); return ret; } -static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc) +int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout) { - struct drm_device *dev = dcrtc->crtc.dev; - struct armada_frame_work *work = dcrtc->frame_work; + return wait_event_timeout(plane->frame_wait, !plane->work, timeout); +} - dcrtc->frame_work = NULL; +struct armada_plane_work *armada_drm_plane_work_cancel( + struct armada_crtc *dcrtc, struct armada_plane *plane) +{ + struct armada_plane_work *work = xchg(&plane->work, NULL); - armada_drm_crtc_update_regs(dcrtc, work->regs); + if (work) + drm_vblank_put(dcrtc->crtc.dev, dcrtc->num); - if (work->event) - drm_send_vblank_event(dev, dcrtc->num, work->event); + return work; +} - drm_vblank_put(dev, dcrtc->num); +static int armada_drm_crtc_queue_frame_work(struct armada_crtc *dcrtc, + struct armada_frame_work *work) +{ + struct armada_plane *plane = drm_to_armada_plane(dcrtc->crtc.primary); + + return armada_drm_plane_work_queue(dcrtc, plane, &work->work); +} + +static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc, + struct armada_plane *plane, struct armada_plane_work *work) +{ + struct armada_frame_work *fwork = container_of(work, struct armada_frame_work, work); + struct drm_device *dev = dcrtc->crtc.dev; + unsigned long flags; + + spin_lock_irqsave(&dcrtc->irq_lock, flags); + armada_drm_crtc_update_regs(dcrtc, fwork->regs); + spin_unlock_irqrestore(&dcrtc->irq_lock, flags); + + if (fwork->event) { + spin_lock_irqsave(&dev->event_lock, flags); + drm_send_vblank_event(dev, dcrtc->num, fwork->event); + spin_unlock_irqrestore(&dev->event_lock, flags); + } /* Finally, queue the process-half of the cleanup. */ - __armada_drm_queue_unref_work(dcrtc->crtc.dev, work->old_fb); - kfree(work); + __armada_drm_queue_unref_work(dcrtc->crtc.dev, fwork->old_fb); + kfree(fwork); } static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc, @@ -235,6 +286,7 @@ static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc, work = kmalloc(sizeof(*work), GFP_KERNEL); if (work) { int i = 0; + work->work.fn = armada_drm_crtc_complete_frame_work; work->event = NULL; work->old_fb = fb; armada_reg_queue_end(work->regs, i); @@ -255,19 +307,14 @@ static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc, static void armada_drm_vblank_off(struct armada_crtc *dcrtc) { - struct drm_device *dev = dcrtc->crtc.dev; + struct armada_plane *plane = drm_to_armada_plane(dcrtc->crtc.primary); /* * Tell the DRM core that vblank IRQs aren't going to happen for * a while. This cleans up any pending vblank events for us. */ drm_crtc_vblank_off(&dcrtc->crtc); - - /* Handle any pending flip event. */ - spin_lock_irq(&dev->event_lock); - if (dcrtc->frame_work) - armada_drm_crtc_complete_frame_work(dcrtc); - spin_unlock_irq(&dev->event_lock); + armada_drm_plane_work_run(dcrtc, plane); } void armada_drm_crtc_gamma_set(struct drm_crtc *crtc, u16 r, u16 g, u16 b, @@ -287,7 +334,11 @@ static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms) if (dcrtc->dpms != dpms) { dcrtc->dpms = dpms; + if (!IS_ERR(dcrtc->clk) && !dpms_blanked(dpms)) + WARN_ON(clk_prepare_enable(dcrtc->clk)); armada_drm_crtc_update(dcrtc); + if (!IS_ERR(dcrtc->clk) && dpms_blanked(dpms)) + clk_disable_unprepare(dcrtc->clk); if (dpms_blanked(dpms)) armada_drm_vblank_off(dcrtc); else @@ -310,17 +361,11 @@ static void armada_drm_crtc_prepare(struct drm_crtc *crtc) /* * If we have an overlay plane associated with this CRTC, disable * it before the modeset to avoid its coordinates being outside - * the new mode parameters. DRM doesn't provide help with this. + * the new mode parameters. */ plane = dcrtc->plane; - if (plane) { - struct drm_framebuffer *fb = plane->fb; - - plane->funcs->disable_plane(plane); - plane->fb = NULL; - plane->crtc = NULL; - drm_framebuffer_unreference(fb); - } + if (plane) + drm_plane_force_disable(plane); } /* The mode_config.mutex will be held for this call */ @@ -356,8 +401,8 @@ static bool armada_drm_crtc_mode_fixup(struct drm_crtc *crtc, static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat) { - struct armada_vbl_event *e, *n; void __iomem *base = dcrtc->base; + struct drm_plane *ovl_plane; if (stat & DMA_FF_UNDERFLOW) DRM_ERROR("video underflow on crtc %u\n", dcrtc->num); @@ -368,11 +413,10 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat) drm_handle_vblank(dcrtc->crtc.dev, dcrtc->num); spin_lock(&dcrtc->irq_lock); - - list_for_each_entry_safe(e, n, &dcrtc->vbl_list, node) { - list_del_init(&e->node); - drm_vblank_put(dcrtc->crtc.dev, dcrtc->num); - e->fn(dcrtc, e->data); + ovl_plane = dcrtc->plane; + if (ovl_plane) { + struct armada_plane *plane = drm_to_armada_plane(ovl_plane); + armada_drm_plane_work_run(dcrtc, plane); } if (stat & GRA_FRAME_IRQ && dcrtc->interlaced) { @@ -404,14 +448,8 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat) spin_unlock(&dcrtc->irq_lock); if (stat & GRA_FRAME_IRQ) { - struct drm_device *dev = dcrtc->crtc.dev; - - spin_lock(&dev->event_lock); - if (dcrtc->frame_work) - armada_drm_crtc_complete_frame_work(dcrtc); - spin_unlock(&dev->event_lock); - - wake_up(&dcrtc->frame_wait); + struct armada_plane *plane = drm_to_armada_plane(dcrtc->crtc.primary); + armada_drm_plane_work_run(dcrtc, plane); } } @@ -527,7 +565,8 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc, adj->crtc_vtotal, tm, bm); /* Wait for pending flips to complete */ - wait_event(dcrtc->frame_wait, !dcrtc->frame_work); + armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary), + MAX_SCHEDULE_TIMEOUT); drm_crtc_vblank_off(crtc); @@ -537,6 +576,13 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc, writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL); } + /* + * If we are blanked, we would have disabled the clock. Re-enable + * it so that compute_clock() does the right thing. + */ + if (!IS_ERR(dcrtc->clk) && dpms_blanked(dcrtc->dpms)) + WARN_ON(clk_prepare_enable(dcrtc->clk)); + /* Now compute the divider for real */ dcrtc->variant->compute_clock(dcrtc, adj, &sclk); @@ -637,7 +683,8 @@ static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, armada_reg_queue_end(regs, i); /* Wait for pending flips to complete */ - wait_event(dcrtc->frame_wait, !dcrtc->frame_work); + armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary), + MAX_SCHEDULE_TIMEOUT); /* Take a reference to the new fb as we're using it */ drm_framebuffer_reference(crtc->primary->fb); @@ -651,18 +698,47 @@ static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, return 0; } +void armada_drm_crtc_plane_disable(struct armada_crtc *dcrtc, + struct drm_plane *plane) +{ + u32 sram_para1, dma_ctrl0_mask; + + /* + * Drop our reference on any framebuffer attached to this plane. + * We don't need to NULL this out as drm_plane_force_disable(), + * and __setplane_internal() will do so for an overlay plane, and + * __drm_helper_disable_unused_functions() will do so for the + * primary plane. + */ + if (plane->fb) + drm_framebuffer_unreference(plane->fb); + + /* Power down the Y/U/V FIFOs */ + sram_para1 = CFG_PDWN16x66 | CFG_PDWN32x66; + + /* Power down most RAMs and FIFOs if this is the primary plane */ + if (plane->type == DRM_PLANE_TYPE_PRIMARY) { + sram_para1 |= CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 | + CFG_PDWN32x32 | CFG_PDWN64x66; + dma_ctrl0_mask = CFG_GRA_ENA; + } else { + dma_ctrl0_mask = CFG_DMA_ENA; + } + + spin_lock_irq(&dcrtc->irq_lock); + armada_updatel(0, dma_ctrl0_mask, dcrtc->base + LCD_SPU_DMA_CTRL0); + spin_unlock_irq(&dcrtc->irq_lock); + + armada_updatel(sram_para1, 0, dcrtc->base + LCD_SPU_SRAM_PARA1); +} + /* The mode_config.mutex will be held for this call */ static void armada_drm_crtc_disable(struct drm_crtc *crtc) { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); armada_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF); - armada_drm_crtc_finish_fb(dcrtc, crtc->primary->fb, true); - - /* Power down most RAMs and FIFOs */ - writel_relaxed(CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 | - CFG_PDWN32x32 | CFG_PDWN16x66 | CFG_PDWN32x66 | - CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1); + armada_drm_crtc_plane_disable(dcrtc, crtc->primary); } static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = { @@ -920,8 +996,6 @@ static int armada_drm_crtc_page_flip(struct drm_crtc *crtc, { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); struct armada_frame_work *work; - struct drm_device *dev = crtc->dev; - unsigned long flags; unsigned i; int ret; @@ -933,6 +1007,7 @@ static int armada_drm_crtc_page_flip(struct drm_crtc *crtc, if (!work) return -ENOMEM; + work->work.fn = armada_drm_crtc_complete_frame_work; work->event = event; work->old_fb = dcrtc->crtc.primary->fb; @@ -966,12 +1041,8 @@ static int armada_drm_crtc_page_flip(struct drm_crtc *crtc, * Finally, if the display is blanked, we won't receive an * interrupt, so complete it now. */ - if (dpms_blanked(dcrtc->dpms)) { - spin_lock_irqsave(&dev->event_lock, flags); - if (dcrtc->frame_work) - armada_drm_crtc_complete_frame_work(dcrtc); - spin_unlock_irqrestore(&dev->event_lock, flags); - } + if (dpms_blanked(dcrtc->dpms)) + armada_drm_plane_work_run(dcrtc, drm_to_armada_plane(dcrtc->crtc.primary)); return 0; } @@ -1012,6 +1083,19 @@ static struct drm_crtc_funcs armada_crtc_funcs = { .set_property = armada_drm_crtc_set_property, }; +static const struct drm_plane_funcs armada_primary_plane_funcs = { + .update_plane = drm_primary_helper_update, + .disable_plane = drm_primary_helper_disable, + .destroy = drm_primary_helper_destroy, +}; + +int armada_drm_plane_init(struct armada_plane *plane) +{ + init_waitqueue_head(&plane->frame_wait); + + return 0; +} + static struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = { { CSC_AUTO, "Auto" }, { CSC_YUV_CCIR601, "CCIR601" }, @@ -1044,12 +1128,13 @@ static int armada_drm_crtc_create_properties(struct drm_device *dev) return 0; } -int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, +static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, struct resource *res, int irq, const struct armada_variant *variant, struct device_node *port) { struct armada_private *priv = drm->dev_private; struct armada_crtc *dcrtc; + struct armada_plane *primary; void __iomem *base; int ret; @@ -1080,8 +1165,6 @@ int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, dcrtc->spu_iopad_ctrl = CFG_VSCALE_LN_EN | CFG_IOPAD_DUMB24; spin_lock_init(&dcrtc->irq_lock); dcrtc->irq_ena = CLEAN_SPU_IRQ_ISR; - INIT_LIST_HEAD(&dcrtc->vbl_list); - init_waitqueue_head(&dcrtc->frame_wait); /* Initialize some registers which we don't otherwise set */ writel_relaxed(0x00000001, dcrtc->base + LCD_CFG_SCLK_DIV); @@ -1118,7 +1201,32 @@ int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, priv->dcrtc[dcrtc->num] = dcrtc; dcrtc->crtc.port = port; - drm_crtc_init(drm, &dcrtc->crtc, &armada_crtc_funcs); + + primary = kzalloc(sizeof(*primary), GFP_KERNEL); + if (!primary) + return -ENOMEM; + + ret = armada_drm_plane_init(primary); + if (ret) { + kfree(primary); + return ret; + } + + ret = drm_universal_plane_init(drm, &primary->base, 0, + &armada_primary_plane_funcs, + armada_primary_formats, + ARRAY_SIZE(armada_primary_formats), + DRM_PLANE_TYPE_PRIMARY); + if (ret) { + kfree(primary); + return ret; + } + + ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, &primary->base, NULL, + &armada_crtc_funcs); + if (ret) + goto err_crtc_init; + drm_crtc_helper_add(&dcrtc->crtc, &armada_crtc_helper_funcs); drm_object_attach_property(&dcrtc->crtc.base, priv->csc_yuv_prop, @@ -1127,6 +1235,10 @@ int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, dcrtc->csc_rgb_mode); return armada_overlay_plane_create(drm, 1 << dcrtc->num); + +err_crtc_init: + primary->base.funcs->destroy(&primary->base); + return ret; } static int diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h index 98102a5..04fdd22 100644 --- a/drivers/gpu/drm/armada/armada_crtc.h +++ b/drivers/gpu/drm/armada/armada_crtc.h @@ -31,9 +31,30 @@ struct armada_regs { #define armada_reg_queue_end(_r, _i) \ armada_reg_queue_mod(_r, _i, 0, 0, ~0) -struct armada_frame_work; +struct armada_crtc; +struct armada_plane; struct armada_variant; +struct armada_plane_work { + void (*fn)(struct armada_crtc *, + struct armada_plane *, + struct armada_plane_work *); +}; + +struct armada_plane { + struct drm_plane base; + wait_queue_head_t frame_wait; + struct armada_plane_work *work; +}; +#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base) + +int armada_drm_plane_init(struct armada_plane *plane); +int armada_drm_plane_work_queue(struct armada_crtc *dcrtc, + struct armada_plane *plane, struct armada_plane_work *work); +int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout); +struct armada_plane_work *armada_drm_plane_work_cancel( + struct armada_crtc *dcrtc, struct armada_plane *plane); + struct armada_crtc { struct drm_crtc crtc; const struct armada_variant *variant; @@ -66,25 +87,20 @@ struct armada_crtc { uint32_t dumb_ctrl; uint32_t spu_iopad_ctrl; - wait_queue_head_t frame_wait; - struct armada_frame_work *frame_work; - spinlock_t irq_lock; uint32_t irq_ena; - struct list_head vbl_list; }; #define drm_to_armada_crtc(c) container_of(c, struct armada_crtc, crtc) -struct device_node; -int armada_drm_crtc_create(struct drm_device *, struct device *, - struct resource *, int, const struct armada_variant *, - struct device_node *); void armada_drm_crtc_gamma_set(struct drm_crtc *, u16, u16, u16, int); void armada_drm_crtc_gamma_get(struct drm_crtc *, u16 *, u16 *, u16 *, int); void armada_drm_crtc_disable_irq(struct armada_crtc *, u32); void armada_drm_crtc_enable_irq(struct armada_crtc *, u32); void armada_drm_crtc_update_regs(struct armada_crtc *, struct armada_regs *); +void armada_drm_crtc_plane_disable(struct armada_crtc *dcrtc, + struct drm_plane *plane); + extern struct platform_driver armada_lcd_platform_driver; #endif diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h index 5f6aef0..4df6f2a 100644 --- a/drivers/gpu/drm/armada/armada_drm.h +++ b/drivers/gpu/drm/armada/armada_drm.h @@ -37,22 +37,6 @@ static inline uint32_t armada_pitch(uint32_t width, uint32_t bpp) return ALIGN(pitch, 128); } -struct armada_vbl_event { - struct list_head node; - void *data; - void (*fn)(struct armada_crtc *, void *); -}; -void armada_drm_vbl_event_add(struct armada_crtc *, - struct armada_vbl_event *); -void armada_drm_vbl_event_remove(struct armada_crtc *, - struct armada_vbl_event *); -#define armada_drm_vbl_event_init(_e, _f, _d) do { \ - struct armada_vbl_event *__e = _e; \ - INIT_LIST_HEAD(&__e->node); \ - __e->data = _d; \ - __e->fn = _f; \ -} while (0) - struct armada_private; diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 5646b54..1cbb080 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -18,47 +18,6 @@ #include <drm/armada_drm.h> #include "armada_ioctlP.h" -#ifdef CONFIG_DRM_ARMADA_TDA1998X -#include <drm/i2c/tda998x.h> -#include "armada_slave.h" - -static struct tda998x_encoder_params params = { - /* With 0x24, there is no translation between vp_out and int_vp - FB LCD out Pins VIP Int Vp - R:23:16 R:7:0 VPC7:0 7:0 7:0[R] - G:15:8 G:15:8 VPB7:0 23:16 23:16[G] - B:7:0 B:23:16 VPA7:0 15:8 15:8[B] - */ - .swap_a = 2, - .swap_b = 3, - .swap_c = 4, - .swap_d = 5, - .swap_e = 0, - .swap_f = 1, - .audio_cfg = BIT(2), - .audio_frame[1] = 1, - .audio_format = AFMT_SPDIF, - .audio_sample_rate = 44100, -}; - -static const struct armada_drm_slave_config tda19988_config = { - .i2c_adapter_id = 0, - .crtcs = 1 << 0, /* Only LCD0 at the moment */ - .polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT, - .interlace_allowed = true, - .info = { - .type = "tda998x", - .addr = 0x70, - .platform_data = ¶ms, - }, -}; -#endif - -static bool is_componentized(struct device *dev) -{ - return dev->of_node || dev->platform_data; -} - static void armada_drm_unref_work(struct work_struct *work) { struct armada_private *priv = @@ -91,16 +50,11 @@ void armada_drm_queue_unref_work(struct drm_device *dev, static int armada_drm_load(struct drm_device *dev, unsigned long flags) { - const struct platform_device_id *id; - const struct armada_variant *variant; struct armada_private *priv; - struct resource *res[ARRAY_SIZE(priv->dcrtc)]; struct resource *mem = NULL; - int ret, n, i; - - memset(res, 0, sizeof(res)); + int ret, n; - for (n = i = 0; ; n++) { + for (n = 0; ; n++) { struct resource *r = platform_get_resource(dev->platformdev, IORESOURCE_MEM, n); if (!r) @@ -109,8 +63,6 @@ static int armada_drm_load(struct drm_device *dev, unsigned long flags) /* Resources above 64K are graphics memory */ if (resource_size(r) > SZ_64K) mem = r; - else if (i < ARRAY_SIZE(priv->dcrtc)) - res[i++] = r; else return -EINVAL; } @@ -131,13 +83,6 @@ static int armada_drm_load(struct drm_device *dev, unsigned long flags) platform_set_drvdata(dev->platformdev, dev); dev->dev_private = priv; - /* Get the implementation specific driver data. */ - id = platform_get_device_id(dev->platformdev); - if (!id) - return -ENXIO; - - variant = (const struct armada_variant *)id->driver_data; - INIT_WORK(&priv->fb_unref_work, armada_drm_unref_work); INIT_KFIFO(priv->fb_unref); @@ -157,34 +102,9 @@ static int armada_drm_load(struct drm_device *dev, unsigned long flags) dev->mode_config.funcs = &armada_drm_mode_config_funcs; drm_mm_init(&priv->linear, mem->start, resource_size(mem)); - /* Create all LCD controllers */ - for (n = 0; n < ARRAY_SIZE(priv->dcrtc); n++) { - int irq; - - if (!res[n]) - break; - - irq = platform_get_irq(dev->platformdev, n); - if (irq < 0) - goto err_kms; - - ret = armada_drm_crtc_create(dev, dev->dev, res[n], irq, - variant, NULL); - if (ret) - goto err_kms; - } - - if (is_componentized(dev->dev)) { - ret = component_bind_all(dev->dev, dev); - if (ret) - goto err_kms; - } else { -#ifdef CONFIG_DRM_ARMADA_TDA1998X - ret = armada_drm_connector_slave_create(dev, &tda19988_config); - if (ret) - goto err_kms; -#endif - } + ret = component_bind_all(dev->dev, dev); + if (ret) + goto err_kms; ret = drm_vblank_init(dev, dev->mode_config.num_crtc); if (ret) @@ -202,8 +122,7 @@ static int armada_drm_load(struct drm_device *dev, unsigned long flags) return 0; err_comp: - if (is_componentized(dev->dev)) - component_unbind_all(dev->dev, dev); + component_unbind_all(dev->dev, dev); err_kms: drm_mode_config_cleanup(dev); drm_mm_takedown(&priv->linear); @@ -219,8 +138,7 @@ static int armada_drm_unload(struct drm_device *dev) drm_kms_helper_poll_fini(dev); armada_fbdev_fini(dev); - if (is_componentized(dev->dev)) - component_unbind_all(dev->dev, dev); + component_unbind_all(dev->dev, dev); drm_mode_config_cleanup(dev); drm_mm_takedown(&priv->linear); @@ -230,29 +148,6 @@ static int armada_drm_unload(struct drm_device *dev) return 0; } -void armada_drm_vbl_event_add(struct armada_crtc *dcrtc, - struct armada_vbl_event *evt) -{ - unsigned long flags; - - spin_lock_irqsave(&dcrtc->irq_lock, flags); - if (list_empty(&evt->node)) { - list_add_tail(&evt->node, &dcrtc->vbl_list); - - drm_vblank_get(dcrtc->crtc.dev, dcrtc->num); - } - spin_unlock_irqrestore(&dcrtc->irq_lock, flags); -} - -void armada_drm_vbl_event_remove(struct armada_crtc *dcrtc, - struct armada_vbl_event *evt) -{ - if (!list_empty(&evt->node)) { - list_del_init(&evt->node); - drm_vblank_put(dcrtc->crtc.dev, dcrtc->num); - } -} - /* These are called under the vbl_lock. */ static int armada_drm_enable_vblank(struct drm_device *dev, unsigned int pipe) { @@ -432,37 +327,28 @@ static const struct component_master_ops armada_master_ops = { static int armada_drm_probe(struct platform_device *pdev) { - if (is_componentized(&pdev->dev)) { - struct component_match *match = NULL; - int ret; - - ret = armada_drm_find_components(&pdev->dev, &match); - if (ret < 0) - return ret; - - return component_master_add_with_match(&pdev->dev, - &armada_master_ops, match); - } else { - return drm_platform_init(&armada_drm_driver, pdev); - } + struct component_match *match = NULL; + int ret; + + ret = armada_drm_find_components(&pdev->dev, &match); + if (ret < 0) + return ret; + + return component_master_add_with_match(&pdev->dev, &armada_master_ops, + match); } static int armada_drm_remove(struct platform_device *pdev) { - if (is_componentized(&pdev->dev)) - component_master_del(&pdev->dev, &armada_master_ops); - else - drm_put_dev(platform_get_drvdata(pdev)); + component_master_del(&pdev->dev, &armada_master_ops); return 0; } static const struct platform_device_id armada_drm_platform_ids[] = { { .name = "armada-drm", - .driver_data = (unsigned long)&armada510_ops, }, { .name = "armada-510-drm", - .driver_data = (unsigned long)&armada510_ops, }, { }, }; diff --git a/drivers/gpu/drm/armada/armada_output.c b/drivers/gpu/drm/armada/armada_output.c deleted file mode 100644 index 5a982317..0000000 --- a/drivers/gpu/drm/armada/armada_output.c +++ /dev/null @@ -1,142 +0,0 @@ -/* - * Copyright (C) 2012 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <drm/drmP.h> -#include <drm/drm_crtc_helper.h> -#include <drm/drm_edid.h> -#include <drm/drm_encoder_slave.h> -#include "armada_output.h" -#include "armada_drm.h" - -struct armada_connector { - struct drm_connector conn; - const struct armada_output_type *type; -}; - -#define drm_to_armada_conn(c) container_of(c, struct armada_connector, conn) - -struct drm_encoder *armada_drm_connector_encoder(struct drm_connector *conn) -{ - struct drm_encoder *enc = conn->encoder; - - return enc ? enc : drm_encoder_find(conn->dev, conn->encoder_ids[0]); -} - -static enum drm_connector_status armada_drm_connector_detect( - struct drm_connector *conn, bool force) -{ - struct armada_connector *dconn = drm_to_armada_conn(conn); - enum drm_connector_status status = connector_status_disconnected; - - if (dconn->type->detect) { - status = dconn->type->detect(conn, force); - } else { - struct drm_encoder *enc = armada_drm_connector_encoder(conn); - - if (enc) - status = encoder_helper_funcs(enc)->detect(enc, conn); - } - - return status; -} - -static void armada_drm_connector_destroy(struct drm_connector *conn) -{ - struct armada_connector *dconn = drm_to_armada_conn(conn); - - drm_connector_unregister(conn); - drm_connector_cleanup(conn); - kfree(dconn); -} - -static int armada_drm_connector_set_property(struct drm_connector *conn, - struct drm_property *property, uint64_t value) -{ - struct armada_connector *dconn = drm_to_armada_conn(conn); - - if (!dconn->type->set_property) - return -EINVAL; - - return dconn->type->set_property(conn, property, value); -} - -static const struct drm_connector_funcs armada_drm_conn_funcs = { - .dpms = drm_helper_connector_dpms, - .fill_modes = drm_helper_probe_single_connector_modes, - .detect = armada_drm_connector_detect, - .destroy = armada_drm_connector_destroy, - .set_property = armada_drm_connector_set_property, -}; - -/* Shouldn't this be a generic helper function? */ -int armada_drm_slave_encoder_mode_valid(struct drm_connector *conn, - struct drm_display_mode *mode) -{ - struct drm_encoder *encoder = armada_drm_connector_encoder(conn); - int valid = MODE_BAD; - - if (encoder) { - struct drm_encoder_slave *slave = to_encoder_slave(encoder); - - valid = slave->slave_funcs->mode_valid(encoder, mode); - } - return valid; -} - -int armada_drm_slave_encoder_set_property(struct drm_connector *conn, - struct drm_property *property, uint64_t value) -{ - struct drm_encoder *encoder = armada_drm_connector_encoder(conn); - int rc = -EINVAL; - - if (encoder) { - struct drm_encoder_slave *slave = to_encoder_slave(encoder); - - rc = slave->slave_funcs->set_property(encoder, conn, property, - value); - } - return rc; -} - -int armada_output_create(struct drm_device *dev, - const struct armada_output_type *type, const void *data) -{ - struct armada_connector *dconn; - int ret; - - dconn = kzalloc(sizeof(*dconn), GFP_KERNEL); - if (!dconn) - return -ENOMEM; - - dconn->type = type; - - ret = drm_connector_init(dev, &dconn->conn, &armada_drm_conn_funcs, - type->connector_type); - if (ret) { - DRM_ERROR("unable to init connector\n"); - goto err_destroy_dconn; - } - - ret = type->create(&dconn->conn, data); - if (ret) - goto err_conn; - - ret = drm_connector_register(&dconn->conn); - if (ret) - goto err_sysfs; - - return 0; - - err_sysfs: - if (dconn->conn.encoder) - dconn->conn.encoder->funcs->destroy(dconn->conn.encoder); - err_conn: - drm_connector_cleanup(&dconn->conn); - err_destroy_dconn: - kfree(dconn); - return ret; -} diff --git a/drivers/gpu/drm/armada/armada_output.h b/drivers/gpu/drm/armada/armada_output.h deleted file mode 100644 index f448785..0000000 --- a/drivers/gpu/drm/armada/armada_output.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * Copyright (C) 2012 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef ARMADA_CONNETOR_H -#define ARMADA_CONNETOR_H - -#define encoder_helper_funcs(encoder) \ - ((const struct drm_encoder_helper_funcs *)encoder->helper_private) - -struct armada_output_type { - int connector_type; - enum drm_connector_status (*detect)(struct drm_connector *, bool); - int (*create)(struct drm_connector *, const void *); - int (*set_property)(struct drm_connector *, struct drm_property *, - uint64_t); -}; - -struct drm_encoder *armada_drm_connector_encoder(struct drm_connector *conn); - -int armada_drm_slave_encoder_mode_valid(struct drm_connector *conn, - struct drm_display_mode *mode); - -int armada_drm_slave_encoder_set_property(struct drm_connector *conn, - struct drm_property *property, uint64_t value); - -int armada_output_create(struct drm_device *dev, - const struct armada_output_type *type, const void *data); - -#endif diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c index e939fab..5c22b38 100644 --- a/drivers/gpu/drm/armada/armada_overlay.c +++ b/drivers/gpu/drm/armada/armada_overlay.c @@ -16,7 +16,7 @@ #include <drm/armada_drm.h> #include "armada_ioctlP.h" -struct armada_plane_properties { +struct armada_ovl_plane_properties { uint32_t colorkey_yr; uint32_t colorkey_ug; uint32_t colorkey_vb; @@ -29,26 +29,25 @@ struct armada_plane_properties { uint32_t colorkey_mode; }; -struct armada_plane { - struct drm_plane base; - spinlock_t lock; +struct armada_ovl_plane { + struct armada_plane base; struct drm_framebuffer *old_fb; uint32_t src_hw; uint32_t dst_hw; uint32_t dst_yx; uint32_t ctrl0; struct { - struct armada_vbl_event update; + struct armada_plane_work work; struct armada_regs regs[13]; - wait_queue_head_t wait; } vbl; - struct armada_plane_properties prop; + struct armada_ovl_plane_properties prop; }; -#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base) +#define drm_to_armada_ovl_plane(p) \ + container_of(p, struct armada_ovl_plane, base.base) static void -armada_ovl_update_attr(struct armada_plane_properties *prop, +armada_ovl_update_attr(struct armada_ovl_plane_properties *prop, struct armada_crtc *dcrtc) { writel_relaxed(prop->colorkey_yr, dcrtc->base + LCD_SPU_COLORKEY_Y); @@ -71,32 +70,34 @@ armada_ovl_update_attr(struct armada_plane_properties *prop, spin_unlock_irq(&dcrtc->irq_lock); } -/* === Plane support === */ -static void armada_plane_vbl(struct armada_crtc *dcrtc, void *data) +static void armada_ovl_retire_fb(struct armada_ovl_plane *dplane, + struct drm_framebuffer *fb) { - struct armada_plane *dplane = data; - struct drm_framebuffer *fb; + struct drm_framebuffer *old_fb; - armada_drm_crtc_update_regs(dcrtc, dplane->vbl.regs); + old_fb = xchg(&dplane->old_fb, fb); - spin_lock(&dplane->lock); - fb = dplane->old_fb; - dplane->old_fb = NULL; - spin_unlock(&dplane->lock); + if (old_fb) + armada_drm_queue_unref_work(dplane->base.base.dev, old_fb); +} - if (fb) - armada_drm_queue_unref_work(dcrtc->crtc.dev, fb); +/* === Plane support === */ +static void armada_ovl_plane_work(struct armada_crtc *dcrtc, + struct armada_plane *plane, struct armada_plane_work *work) +{ + struct armada_ovl_plane *dplane = container_of(plane, struct armada_ovl_plane, base); - wake_up(&dplane->vbl.wait); + armada_drm_crtc_update_regs(dcrtc, dplane->vbl.regs); + armada_ovl_retire_fb(dplane, NULL); } static int -armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, +armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, struct drm_framebuffer *fb, int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h, uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h) { - struct armada_plane *dplane = drm_to_armada_plane(plane); + struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane); struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); struct drm_rect src = { .x1 = src_x, @@ -160,9 +161,8 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, dcrtc->base + LCD_SPU_SRAM_PARA1); } - wait_event_timeout(dplane->vbl.wait, - list_empty(&dplane->vbl.update.node), - HZ/25); + if (armada_drm_plane_work_wait(&dplane->base, HZ / 25) == 0) + armada_drm_plane_work_cancel(dcrtc, &dplane->base); if (plane->fb != fb) { struct armada_gem_object *obj = drm_fb_obj(fb); @@ -175,17 +175,8 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, */ drm_framebuffer_reference(fb); - if (plane->fb) { - struct drm_framebuffer *older_fb; - - spin_lock_irq(&dplane->lock); - older_fb = dplane->old_fb; - dplane->old_fb = plane->fb; - spin_unlock_irq(&dplane->lock); - if (older_fb) - armada_drm_queue_unref_work(dcrtc->crtc.dev, - older_fb); - } + if (plane->fb) + armada_ovl_retire_fb(dplane, plane->fb); src_y = src.y1 >> 16; src_x = src.x1 >> 16; @@ -262,60 +253,50 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, } if (idx) { armada_reg_queue_end(dplane->vbl.regs, idx); - armada_drm_vbl_event_add(dcrtc, &dplane->vbl.update); + armada_drm_plane_work_queue(dcrtc, &dplane->base, + &dplane->vbl.work); } return 0; } -static int armada_plane_disable(struct drm_plane *plane) +static int armada_ovl_plane_disable(struct drm_plane *plane) { - struct armada_plane *dplane = drm_to_armada_plane(plane); + struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane); struct drm_framebuffer *fb; struct armada_crtc *dcrtc; - if (!dplane->base.crtc) + if (!dplane->base.base.crtc) return 0; - dcrtc = drm_to_armada_crtc(dplane->base.crtc); - dcrtc->plane = NULL; - - spin_lock_irq(&dcrtc->irq_lock); - armada_drm_vbl_event_remove(dcrtc, &dplane->vbl.update); - armada_updatel(0, CFG_DMA_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0); - dplane->ctrl0 = 0; - spin_unlock_irq(&dcrtc->irq_lock); + dcrtc = drm_to_armada_crtc(dplane->base.base.crtc); - /* Power down the Y/U/V FIFOs */ - armada_updatel(CFG_PDWN16x66 | CFG_PDWN32x66, 0, - dcrtc->base + LCD_SPU_SRAM_PARA1); + armada_drm_plane_work_cancel(dcrtc, &dplane->base); + armada_drm_crtc_plane_disable(dcrtc, plane); - if (plane->fb) - drm_framebuffer_unreference(plane->fb); + dcrtc->plane = NULL; + dplane->ctrl0 = 0; - spin_lock_irq(&dplane->lock); - fb = dplane->old_fb; - dplane->old_fb = NULL; - spin_unlock_irq(&dplane->lock); + fb = xchg(&dplane->old_fb, NULL); if (fb) drm_framebuffer_unreference(fb); return 0; } -static void armada_plane_destroy(struct drm_plane *plane) +static void armada_ovl_plane_destroy(struct drm_plane *plane) { - struct armada_plane *dplane = drm_to_armada_plane(plane); + struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane); drm_plane_cleanup(plane); kfree(dplane); } -static int armada_plane_set_property(struct drm_plane *plane, +static int armada_ovl_plane_set_property(struct drm_plane *plane, struct drm_property *property, uint64_t val) { struct armada_private *priv = plane->dev->dev_private; - struct armada_plane *dplane = drm_to_armada_plane(plane); + struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane); bool update_attr = false; if (property == priv->colorkey_prop) { @@ -372,21 +353,21 @@ static int armada_plane_set_property(struct drm_plane *plane, update_attr = true; } - if (update_attr && dplane->base.crtc) + if (update_attr && dplane->base.base.crtc) armada_ovl_update_attr(&dplane->prop, - drm_to_armada_crtc(dplane->base.crtc)); + drm_to_armada_crtc(dplane->base.base.crtc)); return 0; } -static const struct drm_plane_funcs armada_plane_funcs = { - .update_plane = armada_plane_update, - .disable_plane = armada_plane_disable, - .destroy = armada_plane_destroy, - .set_property = armada_plane_set_property, +static const struct drm_plane_funcs armada_ovl_plane_funcs = { + .update_plane = armada_ovl_plane_update, + .disable_plane = armada_ovl_plane_disable, + .destroy = armada_ovl_plane_destroy, + .set_property = armada_ovl_plane_set_property, }; -static const uint32_t armada_formats[] = { +static const uint32_t armada_ovl_formats[] = { DRM_FORMAT_UYVY, DRM_FORMAT_YUYV, DRM_FORMAT_YUV420, @@ -456,7 +437,7 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs) { struct armada_private *priv = dev->dev_private; struct drm_mode_object *mobj; - struct armada_plane *dplane; + struct armada_ovl_plane *dplane; int ret; ret = armada_overlay_create_properties(dev); @@ -467,13 +448,23 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs) if (!dplane) return -ENOMEM; - spin_lock_init(&dplane->lock); - init_waitqueue_head(&dplane->vbl.wait); - armada_drm_vbl_event_init(&dplane->vbl.update, armada_plane_vbl, - dplane); + ret = armada_drm_plane_init(&dplane->base); + if (ret) { + kfree(dplane); + return ret; + } + + dplane->vbl.work.fn = armada_ovl_plane_work; - drm_plane_init(dev, &dplane->base, crtcs, &armada_plane_funcs, - armada_formats, ARRAY_SIZE(armada_formats), false); + ret = drm_universal_plane_init(dev, &dplane->base.base, crtcs, + &armada_ovl_plane_funcs, + armada_ovl_formats, + ARRAY_SIZE(armada_ovl_formats), + DRM_PLANE_TYPE_OVERLAY); + if (ret) { + kfree(dplane); + return ret; + } dplane->prop.colorkey_yr = 0xfefefe00; dplane->prop.colorkey_ug = 0x01010100; @@ -483,7 +474,7 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs) dplane->prop.contrast = 0x4000; dplane->prop.saturation = 0x4000; - mobj = &dplane->base.base; + mobj = &dplane->base.base.base; drm_object_attach_property(mobj, priv->colorkey_prop, 0x0101fe); drm_object_attach_property(mobj, priv->colorkey_min_prop, diff --git a/drivers/gpu/drm/armada/armada_slave.c b/drivers/gpu/drm/armada/armada_slave.c deleted file mode 100644 index 00d0fac..0000000 --- a/drivers/gpu/drm/armada/armada_slave.c +++ /dev/null @@ -1,139 +0,0 @@ -/* - * Copyright (C) 2012 Russell King - * Rewritten from the dovefb driver, and Armada510 manuals. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <drm/drmP.h> -#include <drm/drm_crtc_helper.h> -#include <drm/drm_edid.h> -#include <drm/drm_encoder_slave.h> -#include "armada_drm.h" -#include "armada_output.h" -#include "armada_slave.h" - -static int armada_drm_slave_get_modes(struct drm_connector *conn) -{ - struct drm_encoder *enc = armada_drm_connector_encoder(conn); - int count = 0; - - if (enc) { - struct drm_encoder_slave *slave = to_encoder_slave(enc); - - count = slave->slave_funcs->get_modes(enc, conn); - } - - return count; -} - -static void armada_drm_slave_destroy(struct drm_encoder *enc) -{ - struct drm_encoder_slave *slave = to_encoder_slave(enc); - struct i2c_client *client = drm_i2c_encoder_get_client(enc); - - if (slave->slave_funcs) - slave->slave_funcs->destroy(enc); - if (client) - i2c_put_adapter(client->adapter); - - drm_encoder_cleanup(&slave->base); - kfree(slave); -} - -static const struct drm_encoder_funcs armada_drm_slave_encoder_funcs = { - .destroy = armada_drm_slave_destroy, -}; - -static const struct drm_connector_helper_funcs armada_drm_slave_helper_funcs = { - .get_modes = armada_drm_slave_get_modes, - .mode_valid = armada_drm_slave_encoder_mode_valid, - .best_encoder = armada_drm_connector_encoder, -}; - -static const struct drm_encoder_helper_funcs drm_slave_encoder_helpers = { - .dpms = drm_i2c_encoder_dpms, - .save = drm_i2c_encoder_save, - .restore = drm_i2c_encoder_restore, - .mode_fixup = drm_i2c_encoder_mode_fixup, - .prepare = drm_i2c_encoder_prepare, - .commit = drm_i2c_encoder_commit, - .mode_set = drm_i2c_encoder_mode_set, - .detect = drm_i2c_encoder_detect, -}; - -static int -armada_drm_conn_slave_create(struct drm_connector *conn, const void *data) -{ - const struct armada_drm_slave_config *config = data; - struct drm_encoder_slave *slave; - struct i2c_adapter *adap; - int ret; - - conn->interlace_allowed = config->interlace_allowed; - conn->doublescan_allowed = config->doublescan_allowed; - conn->polled = config->polled; - - drm_connector_helper_add(conn, &armada_drm_slave_helper_funcs); - - slave = kzalloc(sizeof(*slave), GFP_KERNEL); - if (!slave) - return -ENOMEM; - - slave->base.possible_crtcs = config->crtcs; - - adap = i2c_get_adapter(config->i2c_adapter_id); - if (!adap) { - kfree(slave); - return -EPROBE_DEFER; - } - - ret = drm_encoder_init(conn->dev, &slave->base, - &armada_drm_slave_encoder_funcs, - DRM_MODE_ENCODER_TMDS); - if (ret) { - DRM_ERROR("unable to init encoder\n"); - i2c_put_adapter(adap); - kfree(slave); - return ret; - } - - ret = drm_i2c_encoder_init(conn->dev, slave, adap, &config->info); - i2c_put_adapter(adap); - if (ret) { - DRM_ERROR("unable to init encoder slave\n"); - armada_drm_slave_destroy(&slave->base); - return ret; - } - - drm_encoder_helper_add(&slave->base, &drm_slave_encoder_helpers); - - ret = slave->slave_funcs->create_resources(&slave->base, conn); - if (ret) { - armada_drm_slave_destroy(&slave->base); - return ret; - } - - ret = drm_mode_connector_attach_encoder(conn, &slave->base); - if (ret) { - armada_drm_slave_destroy(&slave->base); - return ret; - } - - conn->encoder = &slave->base; - - return ret; -} - -static const struct armada_output_type armada_drm_conn_slave = { - .connector_type = DRM_MODE_CONNECTOR_HDMIA, - .create = armada_drm_conn_slave_create, - .set_property = armada_drm_slave_encoder_set_property, -}; - -int armada_drm_connector_slave_create(struct drm_device *dev, - const struct armada_drm_slave_config *config) -{ - return armada_output_create(dev, &armada_drm_conn_slave, config); -} diff --git a/drivers/gpu/drm/armada/armada_slave.h b/drivers/gpu/drm/armada/armada_slave.h deleted file mode 100644 index bf2374c..0000000 --- a/drivers/gpu/drm/armada/armada_slave.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * Copyright (C) 2012 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef ARMADA_SLAVE_H -#define ARMADA_SLAVE_H - -#include <linux/i2c.h> -#include <drm/drmP.h> - -struct armada_drm_slave_config { - int i2c_adapter_id; - uint32_t crtcs; - uint8_t polled; - bool interlace_allowed; - bool doublescan_allowed; - struct i2c_board_info info; -}; - -int armada_drm_connector_slave_create(struct drm_device *dev, - const struct armada_drm_slave_config *); - -#endif diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 2de52a5..6dddd39 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -11,6 +11,18 @@ config DRM_DW_HDMI tristate select DRM_KMS_HELPER +config DRM_DW_HDMI_AHB_AUDIO + tristate "Synopsis Designware AHB Audio interface" + depends on DRM_DW_HDMI && SND + select SND_PCM + select SND_PCM_ELD + select SND_PCM_IEC958 + help + Support the AHB Audio interface which is part of the Synopsis + Designware HDMI block. This is used in conjunction with + the i.MX6 HDMI driver. + + config DRM_NXP_PTN3460 tristate "NXP PTN3460 DP/LVDS bridge" depends on OF diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index e2eef1c..d4e28be 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -1,5 +1,6 @@ ccflags-y := -Iinclude/drm obj-$(CONFIG_DRM_DW_HDMI) += dw_hdmi.o +obj-$(CONFIG_DRM_DW_HDMI_AHB_AUDIO) += dw_hdmi-ahb-audio.o obj-$(CONFIG_DRM_NXP_PTN3460) += nxp-ptn3460.o obj-$(CONFIG_DRM_PARADE_PS8622) += parade-ps8622.o diff --git a/drivers/gpu/drm/bridge/dw_hdmi-ahb-audio.c b/drivers/gpu/drm/bridge/dw_hdmi-ahb-audio.c new file mode 100644 index 0000000..59f630f --- /dev/null +++ b/drivers/gpu/drm/bridge/dw_hdmi-ahb-audio.c @@ -0,0 +1,653 @@ +/* + * DesignWare HDMI audio driver + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Written and tested against the Designware HDMI Tx found in iMX6. + */ +#include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <drm/bridge/dw_hdmi.h> +#include <drm/drm_edid.h> + +#include <sound/asoundef.h> +#include <sound/core.h> +#include <sound/initval.h> +#include <sound/pcm.h> +#include <sound/pcm_drm_eld.h> +#include <sound/pcm_iec958.h> + +#include "dw_hdmi-audio.h" + +#define DRIVER_NAME "dw-hdmi-ahb-audio" + +/* Provide some bits rather than bit offsets */ +enum { + HDMI_AHB_DMA_CONF0_SW_FIFO_RST = BIT(7), + HDMI_AHB_DMA_CONF0_EN_HLOCK = BIT(3), + HDMI_AHB_DMA_START_START = BIT(0), + HDMI_AHB_DMA_STOP_STOP = BIT(0), + HDMI_IH_MUTE_AHBDMAAUD_STAT0_ERROR = BIT(5), + HDMI_IH_MUTE_AHBDMAAUD_STAT0_LOST = BIT(4), + HDMI_IH_MUTE_AHBDMAAUD_STAT0_RETRY = BIT(3), + HDMI_IH_MUTE_AHBDMAAUD_STAT0_DONE = BIT(2), + HDMI_IH_MUTE_AHBDMAAUD_STAT0_BUFFFULL = BIT(1), + HDMI_IH_MUTE_AHBDMAAUD_STAT0_BUFFEMPTY = BIT(0), + HDMI_IH_MUTE_AHBDMAAUD_STAT0_ALL = + HDMI_IH_MUTE_AHBDMAAUD_STAT0_ERROR | + HDMI_IH_MUTE_AHBDMAAUD_STAT0_LOST | + HDMI_IH_MUTE_AHBDMAAUD_STAT0_RETRY | + HDMI_IH_MUTE_AHBDMAAUD_STAT0_DONE | + HDMI_IH_MUTE_AHBDMAAUD_STAT0_BUFFFULL | + HDMI_IH_MUTE_AHBDMAAUD_STAT0_BUFFEMPTY, + HDMI_IH_AHBDMAAUD_STAT0_ERROR = BIT(5), + HDMI_IH_AHBDMAAUD_STAT0_LOST = BIT(4), + HDMI_IH_AHBDMAAUD_STAT0_RETRY = BIT(3), + HDMI_IH_AHBDMAAUD_STAT0_DONE = BIT(2), + HDMI_IH_AHBDMAAUD_STAT0_BUFFFULL = BIT(1), + HDMI_IH_AHBDMAAUD_STAT0_BUFFEMPTY = BIT(0), + HDMI_IH_AHBDMAAUD_STAT0_ALL = + HDMI_IH_AHBDMAAUD_STAT0_ERROR | + HDMI_IH_AHBDMAAUD_STAT0_LOST | + HDMI_IH_AHBDMAAUD_STAT0_RETRY | + HDMI_IH_AHBDMAAUD_STAT0_DONE | + HDMI_IH_AHBDMAAUD_STAT0_BUFFFULL | + HDMI_IH_AHBDMAAUD_STAT0_BUFFEMPTY, + HDMI_AHB_DMA_CONF0_INCR16 = 2 << 1, + HDMI_AHB_DMA_CONF0_INCR8 = 1 << 1, + HDMI_AHB_DMA_CONF0_INCR4 = 0, + HDMI_AHB_DMA_CONF0_BURST_MODE = BIT(0), + HDMI_AHB_DMA_MASK_DONE = BIT(7), + + HDMI_REVISION_ID = 0x0001, + HDMI_IH_AHBDMAAUD_STAT0 = 0x0109, + HDMI_IH_MUTE_AHBDMAAUD_STAT0 = 0x0189, + HDMI_FC_AUDICONF2 = 0x1027, + HDMI_FC_AUDSCONF = 0x1063, + HDMI_FC_AUDSCONF_LAYOUT1 = 1 << 0, + HDMI_FC_AUDSCONF_LAYOUT0 = 0 << 0, + HDMI_AHB_DMA_CONF0 = 0x3600, + HDMI_AHB_DMA_START = 0x3601, + HDMI_AHB_DMA_STOP = 0x3602, + HDMI_AHB_DMA_THRSLD = 0x3603, + HDMI_AHB_DMA_STRADDR0 = 0x3604, + HDMI_AHB_DMA_STPADDR0 = 0x3608, + HDMI_AHB_DMA_MASK = 0x3614, + HDMI_AHB_DMA_POL = 0x3615, + HDMI_AHB_DMA_CONF1 = 0x3616, + HDMI_AHB_DMA_BUFFPOL = 0x361a, +}; + +struct dw_hdmi_channel_conf { + u8 conf1; + u8 ca; +}; + +/* + * The default mapping of ALSA channels to HDMI channels and speaker + * allocation bits. Note that we can't do channel remapping here - + * channels must be in the same order. + * + * Mappings for alsa-lib pcm/surround*.conf files: + * + * Front Sur4.0 Sur4.1 Sur5.0 Sur5.1 Sur7.1 + * Channels 2 4 6 6 6 8 + * + * Our mapping from ALSA channel to CEA686D speaker name and HDMI channel: + * + * Number of ALSA channels + * ALSA Channel 2 3 4 5 6 7 8 + * 0 FL:0 = = = = = = + * 1 FR:1 = = = = = = + * 2 FC:3 RL:4 LFE:2 = = = + * 3 RR:5 RL:4 FC:3 = = + * 4 RR:5 RL:4 = = + * 5 RR:5 = = + * 6 RC:6 = + * 7 RLC/FRC RLC/FRC + */ +static struct dw_hdmi_channel_conf default_hdmi_channel_config[7] = { + { 0x03, 0x00 }, /* FL,FR */ + { 0x0b, 0x02 }, /* FL,FR,FC */ + { 0x33, 0x08 }, /* FL,FR,RL,RR */ + { 0x37, 0x09 }, /* FL,FR,LFE,RL,RR */ + { 0x3f, 0x0b }, /* FL,FR,LFE,FC,RL,RR */ + { 0x7f, 0x0f }, /* FL,FR,LFE,FC,RL,RR,RC */ + { 0xff, 0x13 }, /* FL,FR,LFE,FC,RL,RR,[FR]RC,[FR]LC */ +}; + +struct snd_dw_hdmi { + struct snd_card *card; + struct snd_pcm *pcm; + spinlock_t lock; + struct dw_hdmi_audio_data data; + struct snd_pcm_substream *substream; + void (*reformat)(struct snd_dw_hdmi *, size_t, size_t); + void *buf_src; + void *buf_dst; + dma_addr_t buf_addr; + unsigned buf_offset; + unsigned buf_period; + unsigned buf_size; + unsigned channels; + u8 revision; + u8 iec_offset; + u8 cs[192][8]; +}; + +static void dw_hdmi_writel(u32 val, void __iomem *ptr) +{ + writeb_relaxed(val, ptr); + writeb_relaxed(val >> 8, ptr + 1); + writeb_relaxed(val >> 16, ptr + 2); + writeb_relaxed(val >> 24, ptr + 3); +} + +/* + * Convert to hardware format: The userspace buffer contains IEC958 samples, + * with the PCUV bits in bits 31..28 and audio samples in bits 27..4. We + * need these to be in bits 27..24, with the IEC B bit in bit 28, and audio + * samples in 23..0. + * + * Default preamble in bits 3..0: 8 = block start, 4 = even 2 = odd + * + * Ideally, we could do with having the data properly formatted in userspace. + */ +static void dw_hdmi_reformat_iec958(struct snd_dw_hdmi *dw, + size_t offset, size_t bytes) +{ + u32 *src = dw->buf_src + offset; + u32 *dst = dw->buf_dst + offset; + u32 *end = dw->buf_src + offset + bytes; + + do { + u32 b, sample = *src++; + + b = (sample & 8) << (28 - 3); + + sample >>= 4; + + *dst++ = sample | b; + } while (src < end); +} + +static u32 parity(u32 sample) +{ + sample ^= sample >> 16; + sample ^= sample >> 8; + sample ^= sample >> 4; + sample ^= sample >> 2; + sample ^= sample >> 1; + return (sample & 1) << 27; +} + +static void dw_hdmi_reformat_s24(struct snd_dw_hdmi *dw, + size_t offset, size_t bytes) +{ + u32 *src = dw->buf_src + offset; + u32 *dst = dw->buf_dst + offset; + u32 *end = dw->buf_src + offset + bytes; + + do { + unsigned i; + u8 *cs; + + cs = dw->cs[dw->iec_offset++]; + if (dw->iec_offset >= 192) + dw->iec_offset = 0; + + i = dw->channels; + do { + u32 sample = *src++; + + sample &= ~0xff000000; + sample |= *cs++ << 24; + sample |= parity(sample & ~0xf8000000); + + *dst++ = sample; + } while (--i); + } while (src < end); +} + +static void dw_hdmi_create_cs(struct snd_dw_hdmi *dw, + struct snd_pcm_runtime *runtime) +{ + u8 cs[4]; + unsigned ch, i, j; + + snd_pcm_create_iec958_consumer(runtime, cs, sizeof(cs)); + + memset(dw->cs, 0, sizeof(dw->cs)); + + for (ch = 0; ch < 8; ch++) { + cs[2] &= ~IEC958_AES2_CON_CHANNEL; + cs[2] |= (ch + 1) << 4; + + for (i = 0; i < ARRAY_SIZE(cs); i++) { + unsigned c = cs[i]; + + for (j = 0; j < 8; j++, c >>= 1) + dw->cs[i * 8 + j][ch] = (c & 1) << 2; + } + } + dw->cs[0][0] |= BIT(4); +} + +static void dw_hdmi_start_dma(struct snd_dw_hdmi *dw) +{ + void __iomem *base = dw->data.base; + unsigned offset = dw->buf_offset; + unsigned period = dw->buf_period; + u32 start, stop; + + dw->reformat(dw, offset, period); + + /* Clear all irqs before enabling irqs and starting DMA */ + writeb_relaxed(HDMI_IH_AHBDMAAUD_STAT0_ALL, + base + HDMI_IH_AHBDMAAUD_STAT0); + + start = dw->buf_addr + offset; + stop = start + period - 1; + + /* Setup the hardware start/stop addresses */ + dw_hdmi_writel(start, base + HDMI_AHB_DMA_STRADDR0); + dw_hdmi_writel(stop, base + HDMI_AHB_DMA_STPADDR0); + + writeb_relaxed((u8)~HDMI_AHB_DMA_MASK_DONE, base + HDMI_AHB_DMA_MASK); + writeb(HDMI_AHB_DMA_START_START, base + HDMI_AHB_DMA_START); + + offset += period; + if (offset >= dw->buf_size) + offset = 0; + dw->buf_offset = offset; +} + +static void dw_hdmi_stop_dma(struct snd_dw_hdmi *dw) +{ + /* Disable interrupts before disabling DMA */ + writeb_relaxed(~0, dw->data.base + HDMI_AHB_DMA_MASK); + writeb_relaxed(HDMI_AHB_DMA_STOP_STOP, dw->data.base + HDMI_AHB_DMA_STOP); +} + +static irqreturn_t snd_dw_hdmi_irq(int irq, void *data) +{ + struct snd_dw_hdmi *dw = data; + struct snd_pcm_substream *substream; + unsigned stat; + + stat = readb_relaxed(dw->data.base + HDMI_IH_AHBDMAAUD_STAT0); + if (!stat) + return IRQ_NONE; + + writeb_relaxed(stat, dw->data.base + HDMI_IH_AHBDMAAUD_STAT0); + + substream = dw->substream; + if (stat & HDMI_IH_AHBDMAAUD_STAT0_DONE && substream) { + snd_pcm_period_elapsed(substream); + + spin_lock(&dw->lock); + if (dw->substream) + dw_hdmi_start_dma(dw); + spin_unlock(&dw->lock); + } + + return IRQ_HANDLED; +} + +static struct snd_pcm_hardware dw_hdmi_hw = { + .info = SNDRV_PCM_INFO_INTERLEAVED | + SNDRV_PCM_INFO_BLOCK_TRANSFER | + SNDRV_PCM_INFO_MMAP | + SNDRV_PCM_INFO_MMAP_VALID, + .formats = SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE | + SNDRV_PCM_FMTBIT_S24_LE, + .rates = SNDRV_PCM_RATE_32000 | + SNDRV_PCM_RATE_44100 | + SNDRV_PCM_RATE_48000 | + SNDRV_PCM_RATE_88200 | + SNDRV_PCM_RATE_96000 | + SNDRV_PCM_RATE_176400 | + SNDRV_PCM_RATE_192000, + .channels_min = 2, + .channels_max = 8, + .buffer_bytes_max = 1024 * 1024, + .period_bytes_min = 256, + .period_bytes_max = 8192, /* ERR004323: must limit to 8k */ + .periods_min = 2, + .periods_max = 16, + .fifo_size = 0, +}; + +static int dw_hdmi_open(struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct snd_dw_hdmi *dw = substream->private_data; + void __iomem *base = dw->data.base; + int ret; + + runtime->hw = dw_hdmi_hw; + + ret = snd_pcm_hw_constraint_eld(runtime, dw->data.eld); + if (ret < 0) + return ret; + + ret = snd_pcm_limit_hw_rates(runtime); + if (ret < 0) + return ret; + + ret = snd_pcm_hw_constraint_integer(runtime, + SNDRV_PCM_HW_PARAM_PERIODS); + if (ret < 0) + return ret; + + /* Limit the buffer size to the size of the preallocated buffer */ + ret = snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_BUFFER_SIZE, + 0, substream->dma_buffer.bytes); + if (ret < 0) + return ret; + + /* Clear FIFO */ + writeb_relaxed(HDMI_AHB_DMA_CONF0_SW_FIFO_RST, + base + HDMI_AHB_DMA_CONF0); + + /* Configure interrupt polarities */ + writeb_relaxed(~0, base + HDMI_AHB_DMA_POL); + writeb_relaxed(~0, base + HDMI_AHB_DMA_BUFFPOL); + + /* Keep interrupts masked, and clear any pending */ + writeb_relaxed(~0, base + HDMI_AHB_DMA_MASK); + writeb_relaxed(~0, base + HDMI_IH_AHBDMAAUD_STAT0); + + ret = request_irq(dw->data.irq, snd_dw_hdmi_irq, IRQF_SHARED, + "dw-hdmi-audio", dw); + if (ret) + return ret; + + /* Un-mute done interrupt */ + writeb_relaxed(HDMI_IH_MUTE_AHBDMAAUD_STAT0_ALL & + ~HDMI_IH_MUTE_AHBDMAAUD_STAT0_DONE, + base + HDMI_IH_MUTE_AHBDMAAUD_STAT0); + + return 0; +} + +static int dw_hdmi_close(struct snd_pcm_substream *substream) +{ + struct snd_dw_hdmi *dw = substream->private_data; + + /* Mute all interrupts */ + writeb_relaxed(HDMI_IH_MUTE_AHBDMAAUD_STAT0_ALL, + dw->data.base + HDMI_IH_MUTE_AHBDMAAUD_STAT0); + + free_irq(dw->data.irq, dw); + + return 0; +} + +static int dw_hdmi_hw_free(struct snd_pcm_substream *substream) +{ + return snd_pcm_lib_free_vmalloc_buffer(substream); +} + +static int dw_hdmi_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) +{ + /* Allocate the PCM runtime buffer, which is exposed to userspace. */ + return snd_pcm_lib_alloc_vmalloc_buffer(substream, + params_buffer_bytes(params)); +} + +static int dw_hdmi_prepare(struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct snd_dw_hdmi *dw = substream->private_data; + u8 threshold, conf0, conf1, layout, ca; + + /* Setup as per 3.0.5 FSL 4.1.0 BSP */ + switch (dw->revision) { + case 0x0a: + conf0 = HDMI_AHB_DMA_CONF0_BURST_MODE | + HDMI_AHB_DMA_CONF0_INCR4; + if (runtime->channels == 2) + threshold = 126; + else + threshold = 124; + break; + case 0x1a: + conf0 = HDMI_AHB_DMA_CONF0_BURST_MODE | + HDMI_AHB_DMA_CONF0_INCR8; + threshold = 128; + break; + default: + /* NOTREACHED */ + return -EINVAL; + } + + dw_hdmi_set_sample_rate(dw->data.hdmi, runtime->rate); + + /* Minimum number of bytes in the fifo. */ + runtime->hw.fifo_size = threshold * 32; + + conf0 |= HDMI_AHB_DMA_CONF0_EN_HLOCK; + conf1 = default_hdmi_channel_config[runtime->channels - 2].conf1; + ca = default_hdmi_channel_config[runtime->channels - 2].ca; + + /* + * For >2 channel PCM audio, we need to select layout 1 + * and set an appropriate channel map. + */ + if (runtime->channels > 2) + layout = HDMI_FC_AUDSCONF_LAYOUT1; + else + layout = HDMI_FC_AUDSCONF_LAYOUT0; + + writeb_relaxed(threshold, dw->data.base + HDMI_AHB_DMA_THRSLD); + writeb_relaxed(conf0, dw->data.base + HDMI_AHB_DMA_CONF0); + writeb_relaxed(conf1, dw->data.base + HDMI_AHB_DMA_CONF1); + writeb_relaxed(layout, dw->data.base + HDMI_FC_AUDSCONF); + writeb_relaxed(ca, dw->data.base + HDMI_FC_AUDICONF2); + + switch (runtime->format) { + case SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE: + dw->reformat = dw_hdmi_reformat_iec958; + break; + case SNDRV_PCM_FORMAT_S24_LE: + dw_hdmi_create_cs(dw, runtime); + dw->reformat = dw_hdmi_reformat_s24; + break; + } + dw->iec_offset = 0; + dw->channels = runtime->channels; + dw->buf_src = runtime->dma_area; + dw->buf_dst = substream->dma_buffer.area; + dw->buf_addr = substream->dma_buffer.addr; + dw->buf_period = snd_pcm_lib_period_bytes(substream); + dw->buf_size = snd_pcm_lib_buffer_bytes(substream); + + return 0; +} + +static int dw_hdmi_trigger(struct snd_pcm_substream *substream, int cmd) +{ + struct snd_dw_hdmi *dw = substream->private_data; + unsigned long flags; + int ret = 0; + + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + spin_lock_irqsave(&dw->lock, flags); + dw->buf_offset = 0; + dw->substream = substream; + dw_hdmi_start_dma(dw); + dw_hdmi_audio_enable(dw->data.hdmi); + spin_unlock_irqrestore(&dw->lock, flags); + substream->runtime->delay = substream->runtime->period_size; + break; + + case SNDRV_PCM_TRIGGER_STOP: + spin_lock_irqsave(&dw->lock, flags); + dw->substream = NULL; + dw_hdmi_stop_dma(dw); + dw_hdmi_audio_disable(dw->data.hdmi); + spin_unlock_irqrestore(&dw->lock, flags); + break; + + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static snd_pcm_uframes_t dw_hdmi_pointer(struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct snd_dw_hdmi *dw = substream->private_data; + + /* + * We are unable to report the exact hardware position as + * reading the 32-bit DMA position using 8-bit reads is racy. + */ + return bytes_to_frames(runtime, dw->buf_offset); +} + +static struct snd_pcm_ops snd_dw_hdmi_ops = { + .open = dw_hdmi_open, + .close = dw_hdmi_close, + .ioctl = snd_pcm_lib_ioctl, + .hw_params = dw_hdmi_hw_params, + .hw_free = dw_hdmi_hw_free, + .prepare = dw_hdmi_prepare, + .trigger = dw_hdmi_trigger, + .pointer = dw_hdmi_pointer, + .page = snd_pcm_lib_get_vmalloc_page, +}; + +static int snd_dw_hdmi_probe(struct platform_device *pdev) +{ + const struct dw_hdmi_audio_data *data = pdev->dev.platform_data; + struct device *dev = pdev->dev.parent; + struct snd_dw_hdmi *dw; + struct snd_card *card; + struct snd_pcm *pcm; + unsigned revision; + int ret; + + writeb_relaxed(HDMI_IH_MUTE_AHBDMAAUD_STAT0_ALL, + data->base + HDMI_IH_MUTE_AHBDMAAUD_STAT0); + revision = readb_relaxed(data->base + HDMI_REVISION_ID); + if (revision != 0x0a && revision != 0x1a) { + dev_err(dev, "dw-hdmi-audio: unknown revision 0x%02x\n", + revision); + return -ENXIO; + } + + ret = snd_card_new(dev, SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1, + THIS_MODULE, sizeof(struct snd_dw_hdmi), &card); + if (ret < 0) + return ret; + + strlcpy(card->driver, DRIVER_NAME, sizeof(card->driver)); + strlcpy(card->shortname, "DW-HDMI", sizeof(card->shortname)); + snprintf(card->longname, sizeof(card->longname), + "%s rev 0x%02x, irq %d", card->shortname, revision, + data->irq); + + dw = card->private_data; + dw->card = card; + dw->data = *data; + dw->revision = revision; + + spin_lock_init(&dw->lock); + + ret = snd_pcm_new(card, "DW HDMI", 0, 1, 0, &pcm); + if (ret < 0) + goto err; + + dw->pcm = pcm; + pcm->private_data = dw; + strlcpy(pcm->name, DRIVER_NAME, sizeof(pcm->name)); + snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &snd_dw_hdmi_ops); + + /* + * To support 8-channel 96kHz audio reliably, we need 512k + * to satisfy alsa with our restricted period (ERR004323). + */ + snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, + dev, 128 * 1024, 1024 * 1024); + + ret = snd_card_register(card); + if (ret < 0) + goto err; + + platform_set_drvdata(pdev, dw); + + return 0; + +err: + snd_card_free(card); + return ret; +} + +static int snd_dw_hdmi_remove(struct platform_device *pdev) +{ + struct snd_dw_hdmi *dw = platform_get_drvdata(pdev); + + snd_card_free(dw->card); + + return 0; +} + +#if defined(CONFIG_PM_SLEEP) && defined(IS_NOT_BROKEN) +/* + * This code is fine, but requires implementation in the dw_hdmi_trigger() + * method which is currently missing as I have no way to test this. + */ +static int snd_dw_hdmi_suspend(struct device *dev) +{ + struct snd_dw_hdmi *dw = dev_get_drvdata(dev); + + snd_power_change_state(dw->card, SNDRV_CTL_POWER_D3cold); + snd_pcm_suspend_all(dw->pcm); + + return 0; +} + +static int snd_dw_hdmi_resume(struct device *dev) +{ + struct snd_dw_hdmi *dw = dev_get_drvdata(dev); + + snd_power_change_state(dw->card, SNDRV_CTL_POWER_D0); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(snd_dw_hdmi_pm, snd_dw_hdmi_suspend, + snd_dw_hdmi_resume); +#define PM_OPS &snd_dw_hdmi_pm +#else +#define PM_OPS NULL +#endif + +static struct platform_driver snd_dw_hdmi_driver = { + .probe = snd_dw_hdmi_probe, + .remove = snd_dw_hdmi_remove, + .driver = { + .name = DRIVER_NAME, + .owner = THIS_MODULE, + .pm = PM_OPS, + }, +}; + +module_platform_driver(snd_dw_hdmi_driver); + +MODULE_AUTHOR("Russell King <rmk+kernel@arm.linux.org.uk>"); +MODULE_DESCRIPTION("Synopsis Designware HDMI AHB ALSA interface"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/drivers/gpu/drm/bridge/dw_hdmi-audio.h b/drivers/gpu/drm/bridge/dw_hdmi-audio.h new file mode 100644 index 0000000..91f631b --- /dev/null +++ b/drivers/gpu/drm/bridge/dw_hdmi-audio.h @@ -0,0 +1,14 @@ +#ifndef DW_HDMI_AUDIO_H +#define DW_HDMI_AUDIO_H + +struct dw_hdmi; + +struct dw_hdmi_audio_data { + phys_addr_t phys; + void __iomem *base; + int irq; + struct dw_hdmi *hdmi; + u8 *eld; +}; + +#endif diff --git a/drivers/gpu/drm/bridge/dw_hdmi.c b/drivers/gpu/drm/bridge/dw_hdmi.c index 0083d4e..56de9f1 100644 --- a/drivers/gpu/drm/bridge/dw_hdmi.c +++ b/drivers/gpu/drm/bridge/dw_hdmi.c @@ -28,6 +28,7 @@ #include <drm/bridge/dw_hdmi.h> #include "dw_hdmi.h" +#include "dw_hdmi-audio.h" #define HDMI_EDID_LEN 512 @@ -104,6 +105,7 @@ struct dw_hdmi { struct drm_encoder *encoder; struct drm_bridge *bridge; + struct platform_device *audio; enum dw_hdmi_devtype dev_type; struct device *dev; struct clk *isfr_clk; @@ -126,7 +128,11 @@ struct dw_hdmi { bool sink_has_audio; struct mutex mutex; /* for state below and previous_mode */ + enum drm_connector_force force; /* mutex-protected force state */ bool disabled; /* DRM has disabled our bridge */ + bool bridge_is_on; /* indicates the bridge is on */ + bool rxsense; /* rxsense state */ + u8 phy_mask; /* desired phy int mask settings */ spinlock_t audio_lock; struct mutex audio_mutex; @@ -134,12 +140,19 @@ struct dw_hdmi { unsigned int audio_cts; unsigned int audio_n; bool audio_enable; - int ratio; void (*write)(struct dw_hdmi *hdmi, u8 val, int offset); u8 (*read)(struct dw_hdmi *hdmi, int offset); }; +#define HDMI_IH_PHY_STAT0_RX_SENSE \ + (HDMI_IH_PHY_STAT0_RX_SENSE0 | HDMI_IH_PHY_STAT0_RX_SENSE1 | \ + HDMI_IH_PHY_STAT0_RX_SENSE2 | HDMI_IH_PHY_STAT0_RX_SENSE3) + +#define HDMI_PHY_RX_SENSE \ + (HDMI_PHY_RX_SENSE0 | HDMI_PHY_RX_SENSE1 | \ + HDMI_PHY_RX_SENSE2 | HDMI_PHY_RX_SENSE3) + static void dw_hdmi_writel(struct dw_hdmi *hdmi, u8 val, int offset) { writel(val, hdmi->regs + (offset << 2)); @@ -203,61 +216,53 @@ static void hdmi_set_cts_n(struct dw_hdmi *hdmi, unsigned int cts, hdmi_writeb(hdmi, n & 0xff, HDMI_AUD_N1); } -static unsigned int hdmi_compute_n(unsigned int freq, unsigned long pixel_clk, - unsigned int ratio) +static unsigned int hdmi_compute_n(unsigned int freq, unsigned long pixel_clk) { unsigned int n = (128 * freq) / 1000; + unsigned int mult = 1; + + while (freq > 48000) { + mult *= 2; + freq /= 2; + } switch (freq) { case 32000: - if (pixel_clk == 25170000) - n = (ratio == 150) ? 9152 : 4576; - else if (pixel_clk == 27020000) - n = (ratio == 150) ? 8192 : 4096; - else if (pixel_clk == 74170000 || pixel_clk == 148350000) + if (pixel_clk == 25175000) + n = 4576; + else if (pixel_clk == 27027000) + n = 4096; + else if (pixel_clk == 74176000 || pixel_clk == 148352000) n = 11648; else n = 4096; + n *= mult; break; case 44100: - if (pixel_clk == 25170000) + if (pixel_clk == 25175000) n = 7007; - else if (pixel_clk == 74170000) + else if (pixel_clk == 74176000) n = 17836; - else if (pixel_clk == 148350000) - n = (ratio == 150) ? 17836 : 8918; + else if (pixel_clk == 148352000) + n = 8918; else n = 6272; + n *= mult; break; case 48000: - if (pixel_clk == 25170000) - n = (ratio == 150) ? 9152 : 6864; - else if (pixel_clk == 27020000) - n = (ratio == 150) ? 8192 : 6144; - else if (pixel_clk == 74170000) + if (pixel_clk == 25175000) + n = 6864; + else if (pixel_clk == 27027000) + n = 6144; + else if (pixel_clk == 74176000) n = 11648; - else if (pixel_clk == 148350000) - n = (ratio == 150) ? 11648 : 5824; + else if (pixel_clk == 148352000) + n = 5824; else n = 6144; - break; - - case 88200: - n = hdmi_compute_n(44100, pixel_clk, ratio) * 2; - break; - - case 96000: - n = hdmi_compute_n(48000, pixel_clk, ratio) * 2; - break; - - case 176400: - n = hdmi_compute_n(44100, pixel_clk, ratio) * 4; - break; - - case 192000: - n = hdmi_compute_n(48000, pixel_clk, ratio) * 4; + n *= mult; break; default: @@ -267,93 +272,29 @@ static unsigned int hdmi_compute_n(unsigned int freq, unsigned long pixel_clk, return n; } -static unsigned int hdmi_compute_cts(unsigned int freq, unsigned long pixel_clk, - unsigned int ratio) -{ - unsigned int cts = 0; - - pr_debug("%s: freq: %d pixel_clk: %ld ratio: %d\n", __func__, freq, - pixel_clk, ratio); - - switch (freq) { - case 32000: - if (pixel_clk == 297000000) { - cts = 222750; - break; - } - case 48000: - case 96000: - case 192000: - switch (pixel_clk) { - case 25200000: - case 27000000: - case 54000000: - case 74250000: - case 148500000: - cts = pixel_clk / 1000; - break; - case 297000000: - cts = 247500; - break; - /* - * All other TMDS clocks are not supported by - * DWC_hdmi_tx. The TMDS clocks divided or - * multiplied by 1,001 coefficients are not - * supported. - */ - default: - break; - } - break; - case 44100: - case 88200: - case 176400: - switch (pixel_clk) { - case 25200000: - cts = 28000; - break; - case 27000000: - cts = 30000; - break; - case 54000000: - cts = 60000; - break; - case 74250000: - cts = 82500; - break; - case 148500000: - cts = 165000; - break; - case 297000000: - cts = 247500; - break; - default: - break; - } - break; - default: - break; - } - if (ratio == 100) - return cts; - return (cts * ratio) / 100; -} - static void hdmi_set_clk_regenerator(struct dw_hdmi *hdmi, - unsigned long pixel_clk, unsigned int sample_rate, unsigned int ratio) + unsigned long pixel_clk, unsigned int sample_rate) { + unsigned long ftdms = pixel_clk; unsigned int n, cts; + u64 tmp; - n = hdmi_compute_n(sample_rate, pixel_clk, ratio); - cts = hdmi_compute_cts(sample_rate, pixel_clk, ratio); - if (!cts) { - dev_err(hdmi->dev, - "%s: pixel clock/sample rate not supported: %luMHz / %ukHz\n", - __func__, pixel_clk, sample_rate); - } + n = hdmi_compute_n(sample_rate, pixel_clk); + + /* + * Compute the CTS value from the N value. Note that CTS and N + * can be up to 20 bits in total, so we need 64-bit math. Also + * note that our TDMS clock is not fully accurate; it is accurate + * to kHz. This can introduce an unnecessary remainder in the + * calculation below, so we don't try to warn about that. + */ + tmp = (u64)ftdms * n; + do_div(tmp, 128 * sample_rate); + cts = tmp; - dev_dbg(hdmi->dev, "%s: samplerate=%ukHz ratio=%d pixelclk=%luMHz N=%d cts=%d\n", - __func__, sample_rate, ratio, pixel_clk, n, cts); + dev_dbg(hdmi->dev, "%s: fs=%uHz ftdms=%lu.%03luMHz N=%d cts=%d\n", + __func__, sample_rate, ftdms / 1000000, (ftdms / 1000) % 1000, + n, cts); spin_lock_irq(&hdmi->audio_lock); hdmi->audio_n = n; @@ -365,8 +306,7 @@ static void hdmi_set_clk_regenerator(struct dw_hdmi *hdmi, static void hdmi_init_clk_regenerator(struct dw_hdmi *hdmi) { mutex_lock(&hdmi->audio_mutex); - hdmi_set_clk_regenerator(hdmi, 74250000, hdmi->sample_rate, - hdmi->ratio); + hdmi_set_clk_regenerator(hdmi, 74250000, hdmi->sample_rate); mutex_unlock(&hdmi->audio_mutex); } @@ -374,7 +314,7 @@ static void hdmi_clk_regenerator_update_pixel_clock(struct dw_hdmi *hdmi) { mutex_lock(&hdmi->audio_mutex); hdmi_set_clk_regenerator(hdmi, hdmi->hdmi_data.video_mode.mpixelclock, - hdmi->sample_rate, hdmi->ratio); + hdmi->sample_rate); mutex_unlock(&hdmi->audio_mutex); } @@ -383,7 +323,7 @@ void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate) mutex_lock(&hdmi->audio_mutex); hdmi->sample_rate = rate; hdmi_set_clk_regenerator(hdmi, hdmi->hdmi_data.video_mode.mpixelclock, - hdmi->sample_rate, hdmi->ratio); + hdmi->sample_rate); mutex_unlock(&hdmi->audio_mutex); } EXPORT_SYMBOL_GPL(dw_hdmi_set_sample_rate); @@ -1063,6 +1003,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, u8 inv_val; struct hdmi_vmode *vmode = &hdmi->hdmi_data.video_mode; int hblank, vblank, h_de_hs, v_de_vs, hsync_len, vsync_len; + unsigned int vdisplay; vmode->mpixelclock = mode->clock * 1000; @@ -1102,13 +1043,29 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, hdmi_writeb(hdmi, inv_val, HDMI_FC_INVIDCONF); + vdisplay = mode->vdisplay; + vblank = mode->vtotal - mode->vdisplay; + v_de_vs = mode->vsync_start - mode->vdisplay; + vsync_len = mode->vsync_end - mode->vsync_start; + + /* + * When we're setting an interlaced mode, we need + * to adjust the vertical timing to suit. + */ + if (mode->flags & DRM_MODE_FLAG_INTERLACE) { + vdisplay /= 2; + vblank /= 2; + v_de_vs /= 2; + vsync_len /= 2; + } + /* Set up horizontal active pixel width */ hdmi_writeb(hdmi, mode->hdisplay >> 8, HDMI_FC_INHACTV1); hdmi_writeb(hdmi, mode->hdisplay, HDMI_FC_INHACTV0); /* Set up vertical active lines */ - hdmi_writeb(hdmi, mode->vdisplay >> 8, HDMI_FC_INVACTV1); - hdmi_writeb(hdmi, mode->vdisplay, HDMI_FC_INVACTV0); + hdmi_writeb(hdmi, vdisplay >> 8, HDMI_FC_INVACTV1); + hdmi_writeb(hdmi, vdisplay, HDMI_FC_INVACTV0); /* Set up horizontal blanking pixel region width */ hblank = mode->htotal - mode->hdisplay; @@ -1116,7 +1073,6 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, hdmi_writeb(hdmi, hblank, HDMI_FC_INHBLANK0); /* Set up vertical blanking pixel region width */ - vblank = mode->vtotal - mode->vdisplay; hdmi_writeb(hdmi, vblank, HDMI_FC_INVBLANK); /* Set up HSYNC active edge delay width (in pixel clks) */ @@ -1125,7 +1081,6 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, hdmi_writeb(hdmi, h_de_hs, HDMI_FC_HSYNCINDELAY0); /* Set up VSYNC active edge delay (in lines) */ - v_de_vs = mode->vsync_start - mode->vdisplay; hdmi_writeb(hdmi, v_de_vs, HDMI_FC_VSYNCINDELAY); /* Set up HSYNC active pulse width (in pixel clks) */ @@ -1134,7 +1089,6 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, hdmi_writeb(hdmi, hsync_len, HDMI_FC_HSYNCINWIDTH0); /* Set up VSYNC active edge delay (in lines) */ - vsync_len = mode->vsync_end - mode->vsync_start; hdmi_writeb(hdmi, vsync_len, HDMI_FC_VSYNCINWIDTH); } @@ -1302,10 +1256,11 @@ static int dw_hdmi_fb_registered(struct dw_hdmi *hdmi) HDMI_PHY_I2CM_CTLINT_ADDR); /* enable cable hot plug irq */ - hdmi_writeb(hdmi, (u8)~HDMI_PHY_HPD, HDMI_PHY_MASK0); + hdmi_writeb(hdmi, hdmi->phy_mask, HDMI_PHY_MASK0); /* Clear Hotplug interrupts */ - hdmi_writeb(hdmi, HDMI_IH_PHY_STAT0_HPD, HDMI_IH_PHY_STAT0); + hdmi_writeb(hdmi, HDMI_IH_PHY_STAT0_HPD | HDMI_IH_PHY_STAT0_RX_SENSE, + HDMI_IH_PHY_STAT0); return 0; } @@ -1364,12 +1319,61 @@ static void initialize_hdmi_ih_mutes(struct dw_hdmi *hdmi) static void dw_hdmi_poweron(struct dw_hdmi *hdmi) { + hdmi->bridge_is_on = true; dw_hdmi_setup(hdmi, &hdmi->previous_mode); } static void dw_hdmi_poweroff(struct dw_hdmi *hdmi) { dw_hdmi_phy_disable(hdmi); + hdmi->bridge_is_on = false; +} + +static void dw_hdmi_update_power(struct dw_hdmi *hdmi) +{ + int force = hdmi->force; + + if (hdmi->disabled) { + force = DRM_FORCE_OFF; + } else if (force == DRM_FORCE_UNSPECIFIED) { + if (hdmi->rxsense) + force = DRM_FORCE_ON; + else + force = DRM_FORCE_OFF; + } + + if (force == DRM_FORCE_OFF) { + if (hdmi->bridge_is_on) + dw_hdmi_poweroff(hdmi); + } else { + if (!hdmi->bridge_is_on) + dw_hdmi_poweron(hdmi); + } +} + +/* + * Adjust the detection of RXSENSE according to whether we have a forced + * connection mode enabled, or whether we have been disabled. There is + * no point processing RXSENSE interrupts if we have a forced connection + * state, or DRM has us disabled. + * + * We also disable rxsense interrupts when we think we're disconnected + * to avoid floating TDMS signals giving false rxsense interrupts. + * + * Note: we still need to listen for HPD interrupts even when DRM has us + * disabled so that we can detect a connect event. + */ +static void dw_hdmi_update_phy_mask(struct dw_hdmi *hdmi) +{ + u8 old_mask = hdmi->phy_mask; + + if (hdmi->force || hdmi->disabled || !hdmi->rxsense) + hdmi->phy_mask |= HDMI_PHY_RX_SENSE; + else + hdmi->phy_mask &= ~HDMI_PHY_RX_SENSE; + + if (old_mask != hdmi->phy_mask) + hdmi_writeb(hdmi, hdmi->phy_mask, HDMI_PHY_MASK0); } static void dw_hdmi_bridge_mode_set(struct drm_bridge *bridge, @@ -1399,7 +1403,8 @@ static void dw_hdmi_bridge_disable(struct drm_bridge *bridge) mutex_lock(&hdmi->mutex); hdmi->disabled = true; - dw_hdmi_poweroff(hdmi); + dw_hdmi_update_power(hdmi); + dw_hdmi_update_phy_mask(hdmi); mutex_unlock(&hdmi->mutex); } @@ -1408,8 +1413,9 @@ static void dw_hdmi_bridge_enable(struct drm_bridge *bridge) struct dw_hdmi *hdmi = bridge->driver_private; mutex_lock(&hdmi->mutex); - dw_hdmi_poweron(hdmi); hdmi->disabled = false; + dw_hdmi_update_power(hdmi); + dw_hdmi_update_phy_mask(hdmi); mutex_unlock(&hdmi->mutex); } @@ -1424,6 +1430,12 @@ dw_hdmi_connector_detect(struct drm_connector *connector, bool force) struct dw_hdmi *hdmi = container_of(connector, struct dw_hdmi, connector); + mutex_lock(&hdmi->mutex); + hdmi->force = DRM_FORCE_UNSPECIFIED; + dw_hdmi_update_power(hdmi); + dw_hdmi_update_phy_mask(hdmi); + mutex_unlock(&hdmi->mutex); + return hdmi_readb(hdmi, HDMI_PHY_STAT0) & HDMI_PHY_HPD ? connector_status_connected : connector_status_disconnected; } @@ -1447,6 +1459,8 @@ static int dw_hdmi_connector_get_modes(struct drm_connector *connector) hdmi->sink_has_audio = drm_detect_monitor_audio(edid); drm_mode_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); + /* Store the ELD */ + drm_edid_to_eld(connector, edid); kfree(edid); } else { dev_dbg(hdmi->dev, "failed to get edid\n"); @@ -1488,11 +1502,24 @@ static void dw_hdmi_connector_destroy(struct drm_connector *connector) drm_connector_cleanup(connector); } +static void dw_hdmi_connector_force(struct drm_connector *connector) +{ + struct dw_hdmi *hdmi = container_of(connector, struct dw_hdmi, + connector); + + mutex_lock(&hdmi->mutex); + hdmi->force = connector->force; + dw_hdmi_update_power(hdmi); + dw_hdmi_update_phy_mask(hdmi); + mutex_unlock(&hdmi->mutex); +} + static struct drm_connector_funcs dw_hdmi_connector_funcs = { .dpms = drm_helper_connector_dpms, .fill_modes = drm_helper_probe_single_connector_modes, .detect = dw_hdmi_connector_detect, .destroy = dw_hdmi_connector_destroy, + .force = dw_hdmi_connector_force, }; static struct drm_connector_helper_funcs dw_hdmi_connector_helper_funcs = { @@ -1525,33 +1552,69 @@ static irqreturn_t dw_hdmi_hardirq(int irq, void *dev_id) static irqreturn_t dw_hdmi_irq(int irq, void *dev_id) { struct dw_hdmi *hdmi = dev_id; - u8 intr_stat; - u8 phy_int_pol; + u8 intr_stat, phy_int_pol, phy_pol_mask, phy_stat; intr_stat = hdmi_readb(hdmi, HDMI_IH_PHY_STAT0); - phy_int_pol = hdmi_readb(hdmi, HDMI_PHY_POL0); + phy_stat = hdmi_readb(hdmi, HDMI_PHY_STAT0); + + phy_pol_mask = 0; + if (intr_stat & HDMI_IH_PHY_STAT0_HPD) + phy_pol_mask |= HDMI_PHY_HPD; + if (intr_stat & HDMI_IH_PHY_STAT0_RX_SENSE0) + phy_pol_mask |= HDMI_PHY_RX_SENSE0; + if (intr_stat & HDMI_IH_PHY_STAT0_RX_SENSE1) + phy_pol_mask |= HDMI_PHY_RX_SENSE1; + if (intr_stat & HDMI_IH_PHY_STAT0_RX_SENSE2) + phy_pol_mask |= HDMI_PHY_RX_SENSE2; + if (intr_stat & HDMI_IH_PHY_STAT0_RX_SENSE3) + phy_pol_mask |= HDMI_PHY_RX_SENSE3; + + if (phy_pol_mask) + hdmi_modb(hdmi, ~phy_int_pol, phy_pol_mask, HDMI_PHY_POL0); - if (intr_stat & HDMI_IH_PHY_STAT0_HPD) { - hdmi_modb(hdmi, ~phy_int_pol, HDMI_PHY_HPD, HDMI_PHY_POL0); + /* + * RX sense tells us whether the TDMS transmitters are detecting + * load - in other words, there's something listening on the + * other end of the link. Use this to decide whether we should + * power on the phy as HPD may be toggled by the sink to merely + * ask the source to re-read the EDID. + */ + if (intr_stat & + (HDMI_IH_PHY_STAT0_RX_SENSE | HDMI_IH_PHY_STAT0_HPD)) { mutex_lock(&hdmi->mutex); - if (phy_int_pol & HDMI_PHY_HPD) { - dev_dbg(hdmi->dev, "EVENT=plugin\n"); - - if (!hdmi->disabled) - dw_hdmi_poweron(hdmi); - } else { - dev_dbg(hdmi->dev, "EVENT=plugout\n"); - - if (!hdmi->disabled) - dw_hdmi_poweroff(hdmi); + if (!hdmi->disabled && !hdmi->force) { + /* + * If the RX sense status indicates we're disconnected, + * clear the software rxsense status. + */ + if (!(phy_stat & HDMI_PHY_RX_SENSE)) + hdmi->rxsense = false; + + /* + * Only set the software rxsense status when both + * rxsense and hpd indicates we're connected. + * This avoids what seems to be bad behaviour in + * at least iMX6S versions of the phy. + */ + if (phy_stat & HDMI_PHY_HPD) + hdmi->rxsense = true; + + dw_hdmi_update_power(hdmi); + dw_hdmi_update_phy_mask(hdmi); } mutex_unlock(&hdmi->mutex); + } + + if (intr_stat & HDMI_IH_PHY_STAT0_HPD) { + dev_dbg(hdmi->dev, "EVENT=%s\n", + phy_int_pol & HDMI_PHY_HPD ? "plugin" : "plugout"); drm_helper_hpd_irq_event(hdmi->bridge->dev); } hdmi_writeb(hdmi, intr_stat, HDMI_IH_PHY_STAT0); - hdmi_writeb(hdmi, ~HDMI_IH_PHY_STAT0_HPD, HDMI_IH_MUTE_PHY_STAT0); + hdmi_writeb(hdmi, ~(HDMI_IH_PHY_STAT0_HPD | HDMI_IH_PHY_STAT0_RX_SENSE), + HDMI_IH_MUTE_PHY_STAT0); return IRQ_HANDLED; } @@ -1599,7 +1662,9 @@ int dw_hdmi_bind(struct device *dev, struct device *master, { struct drm_device *drm = data; struct device_node *np = dev->of_node; + struct platform_device_info pdevinfo; struct device_node *ddc_node; + struct dw_hdmi_audio_data audio; struct dw_hdmi *hdmi; int ret; u32 val = 1; @@ -1608,13 +1673,16 @@ int dw_hdmi_bind(struct device *dev, struct device *master, if (!hdmi) return -ENOMEM; + hdmi->connector.interlace_allowed = 1; + hdmi->plat_data = plat_data; hdmi->dev = dev; hdmi->dev_type = plat_data->dev_type; hdmi->sample_rate = 48000; - hdmi->ratio = 100; hdmi->encoder = encoder; hdmi->disabled = true; + hdmi->rxsense = true; + hdmi->phy_mask = (u8)~(HDMI_PHY_HPD | HDMI_PHY_RX_SENSE); mutex_init(&hdmi->mutex); mutex_init(&hdmi->audio_mutex); @@ -1705,10 +1773,11 @@ int dw_hdmi_bind(struct device *dev, struct device *master, * Configure registers related to HDMI interrupt * generation before registering IRQ. */ - hdmi_writeb(hdmi, HDMI_PHY_HPD, HDMI_PHY_POL0); + hdmi_writeb(hdmi, HDMI_PHY_HPD | HDMI_PHY_RX_SENSE, HDMI_PHY_POL0); /* Clear Hotplug interrupts */ - hdmi_writeb(hdmi, HDMI_IH_PHY_STAT0_HPD, HDMI_IH_PHY_STAT0); + hdmi_writeb(hdmi, HDMI_IH_PHY_STAT0_HPD | HDMI_IH_PHY_STAT0_RX_SENSE, + HDMI_IH_PHY_STAT0); ret = dw_hdmi_fb_registered(hdmi); if (ret) @@ -1719,7 +1788,26 @@ int dw_hdmi_bind(struct device *dev, struct device *master, goto err_iahb; /* Unmute interrupts */ - hdmi_writeb(hdmi, ~HDMI_IH_PHY_STAT0_HPD, HDMI_IH_MUTE_PHY_STAT0); + hdmi_writeb(hdmi, ~(HDMI_IH_PHY_STAT0_HPD | HDMI_IH_PHY_STAT0_RX_SENSE), + HDMI_IH_MUTE_PHY_STAT0); + + memset(&pdevinfo, 0, sizeof(pdevinfo)); + pdevinfo.parent = dev; + pdevinfo.id = PLATFORM_DEVID_AUTO; + + if (hdmi_readb(hdmi, HDMI_CONFIG1_ID) & HDMI_CONFIG1_AHB) { + audio.phys = iores->start; + audio.base = hdmi->regs; + audio.irq = irq; + audio.hdmi = hdmi; + audio.eld = hdmi->connector.eld; + + pdevinfo.name = "dw-hdmi-ahb-audio"; + pdevinfo.data = &audio; + pdevinfo.size_data = sizeof(audio); + pdevinfo.dma_mask = DMA_BIT_MASK(32); + hdmi->audio = platform_device_register_full(&pdevinfo); + } dev_set_drvdata(dev, hdmi); @@ -1738,6 +1826,9 @@ void dw_hdmi_unbind(struct device *dev, struct device *master, void *data) { struct dw_hdmi *hdmi = dev_get_drvdata(dev); + if (hdmi->audio && !IS_ERR(hdmi->audio)) + platform_device_unregister(hdmi->audio); + /* Disable all interrupts */ hdmi_writeb(hdmi, ~0, HDMI_IH_MUTE_PHY_STAT0); diff --git a/drivers/gpu/drm/bridge/dw_hdmi.h b/drivers/gpu/drm/bridge/dw_hdmi.h index ee7f7ed..fc9a560 100644 --- a/drivers/gpu/drm/bridge/dw_hdmi.h +++ b/drivers/gpu/drm/bridge/dw_hdmi.h @@ -545,6 +545,9 @@ #define HDMI_I2CM_FS_SCL_LCNT_0_ADDR 0x7E12 enum { +/* CONFIG1_ID field values */ + HDMI_CONFIG1_AHB = 0x01, + /* IH_FC_INT2 field values */ HDMI_IH_FC_INT2_OVERFLOW_MASK = 0x03, HDMI_IH_FC_INT2_LOW_PRIORITY_OVERFLOW = 0x02, diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index e4c9b4a..2d46fc6 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -53,8 +53,8 @@ static int drm_dp_send_dpcd_write(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, int offset, int size, u8 *bytes); -static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_branch *mstb); +static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_branch *mstb); static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_branch *mstb, struct drm_dp_mst_port *port); @@ -804,8 +804,6 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) struct drm_dp_mst_port *port, *tmp; bool wake_tx = false; - cancel_work_sync(&mstb->mgr->work); - /* * destroy all ports - don't need lock * as there are no more references to the mst branch @@ -863,29 +861,33 @@ static void drm_dp_destroy_port(struct kref *kref) { struct drm_dp_mst_port *port = container_of(kref, struct drm_dp_mst_port, kref); struct drm_dp_mst_topology_mgr *mgr = port->mgr; + if (!port->input) { port->vcpi.num_slots = 0; kfree(port->cached_edid); - /* we can't destroy the connector here, as - we might be holding the mode_config.mutex - from an EDID retrieval */ + /* + * The only time we don't have a connector + * on an output port is if the connector init + * fails. + */ if (port->connector) { + /* we can't destroy the connector here, as + * we might be holding the mode_config.mutex + * from an EDID retrieval */ + mutex_lock(&mgr->destroy_connector_lock); list_add(&port->next, &mgr->destroy_connector_list); mutex_unlock(&mgr->destroy_connector_lock); schedule_work(&mgr->destroy_connector_work); return; } + /* no need to clean up vcpi + * as if we have no connector we never setup a vcpi */ drm_dp_port_teardown_pdt(port, port->pdt); - - if (!port->input && port->vcpi.vcpi > 0) - drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); } kfree(port); - - (*mgr->cbs->hotplug)(mgr); } static void drm_dp_put_port(struct drm_dp_mst_port *port) @@ -1027,8 +1029,8 @@ static void drm_dp_check_port_guid(struct drm_dp_mst_branch *mstb, } } -static void build_mst_prop_path(struct drm_dp_mst_port *port, - struct drm_dp_mst_branch *mstb, +static void build_mst_prop_path(const struct drm_dp_mst_branch *mstb, + int pnum, char *proppath, size_t proppath_size) { @@ -1041,7 +1043,7 @@ static void build_mst_prop_path(struct drm_dp_mst_port *port, snprintf(temp, sizeof(temp), "-%d", port_num); strlcat(proppath, temp, proppath_size); } - snprintf(temp, sizeof(temp), "-%d", port->port_num); + snprintf(temp, sizeof(temp), "-%d", pnum); strlcat(proppath, temp, proppath_size); } @@ -1105,22 +1107,32 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, drm_dp_port_teardown_pdt(port, old_pdt); ret = drm_dp_port_setup_pdt(port); - if (ret == true) { + if (ret == true) drm_dp_send_link_address(mstb->mgr, port->mstb); - port->mstb->link_address_sent = true; - } } if (created && !port->input) { char proppath[255]; - build_mst_prop_path(port, mstb, proppath, sizeof(proppath)); - port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath); - if (port->port_num >= 8) { + build_mst_prop_path(mstb, port->port_num, proppath, sizeof(proppath)); + port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath); + if (!port->connector) { + /* remove it from the port list */ + mutex_lock(&mstb->mgr->lock); + list_del(&port->next); + mutex_unlock(&mstb->mgr->lock); + /* drop port list reference */ + drm_dp_put_port(port); + goto out; + } + if (port->port_num >= DP_MST_LOGICAL_PORT_0) { port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); + drm_mode_connector_set_tile_property(port->connector); } + (*mstb->mgr->cbs->register_connector)(port->connector); } +out: /* put reference to this port */ drm_dp_put_port(port); } @@ -1203,10 +1215,9 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m { struct drm_dp_mst_port *port; struct drm_dp_mst_branch *mstb_child; - if (!mstb->link_address_sent) { + if (!mstb->link_address_sent) drm_dp_send_link_address(mgr, mstb); - mstb->link_address_sent = true; - } + list_for_each_entry(port, &mstb->ports, next) { if (port->input) continue; @@ -1459,8 +1470,8 @@ static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr, mutex_unlock(&mgr->qlock); } -static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_branch *mstb) +static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_branch *mstb) { int len; struct drm_dp_sideband_msg_tx *txmsg; @@ -1468,11 +1479,12 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL); if (!txmsg) - return -ENOMEM; + return; txmsg->dst = mstb; len = build_link_address(txmsg); + mstb->link_address_sent = true; drm_dp_queue_down_tx(mgr, txmsg); ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); @@ -1500,11 +1512,12 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, } (*mgr->cbs->hotplug)(mgr); } - } else + } else { + mstb->link_address_sent = false; DRM_DEBUG_KMS("link address failed %d\n", ret); + } kfree(txmsg); - return 0; } static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, @@ -1979,6 +1992,8 @@ void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr) drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, DP_MST_EN | DP_UPSTREAM_IS_SRC); mutex_unlock(&mgr->lock); + flush_work(&mgr->work); + flush_work(&mgr->destroy_connector_work); } EXPORT_SYMBOL(drm_dp_mst_topology_mgr_suspend); @@ -2264,10 +2279,10 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_ if (port->cached_edid) edid = drm_edid_duplicate(port->cached_edid); - else + else { edid = drm_get_edid(connector, &port->aux.ddc); - - drm_mode_connector_set_tile_property(connector); + drm_mode_connector_set_tile_property(connector); + } drm_dp_put_port(port); return edid; } @@ -2672,7 +2687,7 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) { struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work); struct drm_dp_mst_port *port; - + bool send_hotplug = false; /* * Not a regular list traverse as we have to drop the destroy * connector lock before destroying the connector, to avoid AB->BA @@ -2695,7 +2710,10 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) if (!port->input && port->vcpi.vcpi > 0) drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); kfree(port); + send_hotplug = true; } + if (send_hotplug) + (*mgr->cbs->hotplug)(mgr); } /** @@ -2748,6 +2766,7 @@ EXPORT_SYMBOL(drm_dp_mst_topology_mgr_init); */ void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr) { + flush_work(&mgr->work); flush_work(&mgr->destroy_connector_work); mutex_lock(&mgr->payload_lock); kfree(mgr->payloads); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 5b2de1b..e673c13 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -438,7 +438,11 @@ static int restore_fbdev_mode(struct drm_fb_helper *fb_helper) struct drm_crtc *crtc = mode_set->crtc; int ret; - if (crtc->funcs->cursor_set) { + if (crtc->funcs->cursor_set2) { + ret = crtc->funcs->cursor_set2(crtc, NULL, 0, 0, 0, 0, 0); + if (ret) + return ret; + } else if (crtc->funcs->cursor_set) { ret = crtc->funcs->cursor_set(crtc, NULL, 0, 0, 0); if (ret) return ret; diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index d734780..a18164f 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -94,7 +94,18 @@ static int drm_helper_probe_add_cmdline_mode(struct drm_connector *connector) } #define DRM_OUTPUT_POLL_PERIOD (10*HZ) -static void __drm_kms_helper_poll_enable(struct drm_device *dev) +/** + * drm_kms_helper_poll_enable_locked - re-enable output polling. + * @dev: drm_device + * + * This function re-enables the output polling work without + * locking the mode_config mutex. + * + * This is like drm_kms_helper_poll_enable() however it is to be + * called from a context where the mode_config mutex is locked + * already. + */ +void drm_kms_helper_poll_enable_locked(struct drm_device *dev) { bool poll = false; struct drm_connector *connector; @@ -113,6 +124,8 @@ static void __drm_kms_helper_poll_enable(struct drm_device *dev) if (poll) schedule_delayed_work(&dev->mode_config.output_poll_work, DRM_OUTPUT_POLL_PERIOD); } +EXPORT_SYMBOL(drm_kms_helper_poll_enable_locked); + static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connector *connector, uint32_t maxX, uint32_t maxY, bool merge_type_bits) @@ -174,7 +187,7 @@ static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connect /* Re-enable polling in case the global poll config changed. */ if (drm_kms_helper_poll != dev->mode_config.poll_running) - __drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable_locked(dev); dev->mode_config.poll_running = drm_kms_helper_poll; @@ -428,7 +441,7 @@ EXPORT_SYMBOL(drm_kms_helper_poll_disable); void drm_kms_helper_poll_enable(struct drm_device *dev) { mutex_lock(&dev->mode_config.mutex); - __drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable_locked(dev); mutex_unlock(&dev->mode_config.mutex); } EXPORT_SYMBOL(drm_kms_helper_poll_enable); diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index f08873f..615b7e6 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -230,18 +230,12 @@ static ssize_t dpms_show(struct device *device, char *buf) { struct drm_connector *connector = to_drm_connector(device); - struct drm_device *dev = connector->dev; - uint64_t dpms_status; - int ret; + int dpms; - ret = drm_object_property_get_value(&connector->base, - dev->mode_config.dpms_property, - &dpms_status); - if (ret) - return 0; + dpms = READ_ONCE(connector->dpms); return snprintf(buf, PAGE_SIZE, "%s\n", - drm_get_dpms_name((int)dpms_status)); + drm_get_dpms_name(dpms)); } static ssize_t enabled_show(struct device *device, diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index cbdb78e..e6cbaca 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -37,7 +37,6 @@ * DECON stands for Display and Enhancement controller. */ -#define DECON_DEFAULT_FRAMERATE 60 #define MIN_FB_WIDTH_FOR_16WORD_BURST 128 #define WINDOWS_NR 2 @@ -165,16 +164,6 @@ static u32 decon_calc_clkdiv(struct decon_context *ctx, return (clkdiv < 0x100) ? clkdiv : 0xff; } -static bool decon_mode_fixup(struct exynos_drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - if (adjusted_mode->vrefresh == 0) - adjusted_mode->vrefresh = DECON_DEFAULT_FRAMERATE; - - return true; -} - static void decon_commit(struct exynos_drm_crtc *crtc) { struct decon_context *ctx = crtc->ctx; @@ -637,7 +626,6 @@ static void decon_disable(struct exynos_drm_crtc *crtc) static const struct exynos_drm_crtc_ops decon_crtc_ops = { .enable = decon_enable, .disable = decon_disable, - .mode_fixup = decon_mode_fixup, .commit = decon_commit, .enable_vblank = decon_enable_vblank, .disable_vblank = decon_disable_vblank, diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c index d66ade0..124fb9a 100644 --- a/drivers/gpu/drm/exynos/exynos_dp_core.c +++ b/drivers/gpu/drm/exynos/exynos_dp_core.c @@ -1383,28 +1383,6 @@ static int exynos_dp_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP -static int exynos_dp_suspend(struct device *dev) -{ - struct exynos_dp_device *dp = dev_get_drvdata(dev); - - exynos_dp_disable(&dp->encoder); - return 0; -} - -static int exynos_dp_resume(struct device *dev) -{ - struct exynos_dp_device *dp = dev_get_drvdata(dev); - - exynos_dp_enable(&dp->encoder); - return 0; -} -#endif - -static const struct dev_pm_ops exynos_dp_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(exynos_dp_suspend, exynos_dp_resume) -}; - static const struct of_device_id exynos_dp_match[] = { { .compatible = "samsung,exynos5-dp" }, {}, @@ -1417,7 +1395,6 @@ struct platform_driver dp_driver = { .driver = { .name = "exynos-dp", .owner = THIS_MODULE, - .pm = &exynos_dp_pm_ops, .of_match_table = exynos_dp_match, }, }; diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c index c68a6a2..7f55ba6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_core.c +++ b/drivers/gpu/drm/exynos/exynos_drm_core.c @@ -28,7 +28,6 @@ int exynos_drm_subdrv_register(struct exynos_drm_subdrv *subdrv) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_register); int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv) { @@ -39,7 +38,6 @@ int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_unregister); int exynos_drm_device_subdrv_probe(struct drm_device *dev) { @@ -69,7 +67,6 @@ int exynos_drm_device_subdrv_probe(struct drm_device *dev) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_probe); int exynos_drm_device_subdrv_remove(struct drm_device *dev) { @@ -87,7 +84,6 @@ int exynos_drm_device_subdrv_remove(struct drm_device *dev) return 0; } -EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_remove); int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file) { @@ -111,7 +107,6 @@ err: } return ret; } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_open); void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file) { @@ -122,4 +117,3 @@ void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file) subdrv->close(dev, subdrv->dev, file); } } -EXPORT_SYMBOL_GPL(exynos_drm_subdrv_close); diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index f364d69..50dec0d 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -41,20 +41,6 @@ static void exynos_drm_crtc_disable(struct drm_crtc *crtc) exynos_crtc->ops->disable(exynos_crtc); } -static bool -exynos_drm_crtc_mode_fixup(struct drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); - - if (exynos_crtc->ops->mode_fixup) - return exynos_crtc->ops->mode_fixup(exynos_crtc, mode, - adjusted_mode); - - return true; -} - static void exynos_drm_crtc_mode_set_nofb(struct drm_crtc *crtc) { @@ -99,7 +85,6 @@ static void exynos_crtc_atomic_flush(struct drm_crtc *crtc, static struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = { .enable = exynos_drm_crtc_enable, .disable = exynos_drm_crtc_disable, - .mode_fixup = exynos_drm_crtc_mode_fixup, .mode_set_nofb = exynos_drm_crtc_mode_set_nofb, .atomic_begin = exynos_crtc_atomic_begin, .atomic_flush = exynos_crtc_atomic_flush, diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 3d565be..09c4c6a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -304,6 +304,7 @@ int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state, return 0; } +#ifdef CONFIG_PM_SLEEP static int exynos_drm_suspend(struct drm_device *dev, pm_message_t state) { struct drm_connector *connector; @@ -340,6 +341,7 @@ static int exynos_drm_resume(struct drm_device *dev) return 0; } +#endif static int exynos_drm_open(struct drm_device *dev, struct drm_file *file) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index b7ba21d..6c717ba 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -82,7 +82,6 @@ struct exynos_drm_plane { * * @enable: enable the device * @disable: disable the device - * @mode_fixup: fix mode data before applying it * @commit: set current hw specific display mode to hw. * @enable_vblank: specific driver callback for enabling vblank interrupt. * @disable_vblank: specific driver callback for disabling vblank interrupt. @@ -103,9 +102,6 @@ struct exynos_drm_crtc; struct exynos_drm_crtc_ops { void (*enable)(struct exynos_drm_crtc *crtc); void (*disable)(struct exynos_drm_crtc *crtc); - bool (*mode_fixup)(struct exynos_drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode); void (*commit)(struct exynos_drm_crtc *crtc); int (*enable_vblank)(struct exynos_drm_crtc *crtc); void (*disable_vblank)(struct exynos_drm_crtc *crtc); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 2a65235..dd3a5e6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -1206,23 +1206,6 @@ static struct exynos_drm_ipp_ops fimc_dst_ops = { .set_addr = fimc_dst_set_addr, }; -static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable) -{ - DRM_DEBUG_KMS("enable[%d]\n", enable); - - if (enable) { - clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]); - clk_prepare_enable(ctx->clocks[FIMC_CLK_WB_A]); - ctx->suspended = false; - } else { - clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]); - clk_disable_unprepare(ctx->clocks[FIMC_CLK_WB_A]); - ctx->suspended = true; - } - - return 0; -} - static irqreturn_t fimc_irq_handler(int irq, void *dev_id) { struct fimc_context *ctx = dev_id; @@ -1780,6 +1763,24 @@ static int fimc_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM +static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable) +{ + DRM_DEBUG_KMS("enable[%d]\n", enable); + + if (enable) { + clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]); + clk_prepare_enable(ctx->clocks[FIMC_CLK_WB_A]); + ctx->suspended = false; + } else { + clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]); + clk_disable_unprepare(ctx->clocks[FIMC_CLK_WB_A]); + ctx->suspended = true; + } + + return 0; +} + #ifdef CONFIG_PM_SLEEP static int fimc_suspend(struct device *dev) { @@ -1806,7 +1807,6 @@ static int fimc_resume(struct device *dev) } #endif -#ifdef CONFIG_PM static int fimc_runtime_suspend(struct device *dev) { struct fimc_context *ctx = get_fimc_context(dev); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 750a9e6..3d1aba6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -41,7 +41,6 @@ * CPU Interface. */ -#define FIMD_DEFAULT_FRAMERATE 60 #define MIN_FB_WIDTH_FOR_16WORD_BURST 128 /* position control register for hardware window 0, 2 ~ 4.*/ @@ -377,16 +376,6 @@ static u32 fimd_calc_clkdiv(struct fimd_context *ctx, return (clkdiv < 0x100) ? clkdiv : 0xff; } -static bool fimd_mode_fixup(struct exynos_drm_crtc *crtc, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - if (adjusted_mode->vrefresh == 0) - adjusted_mode->vrefresh = FIMD_DEFAULT_FRAMERATE; - - return true; -} - static void fimd_commit(struct exynos_drm_crtc *crtc) { struct fimd_context *ctx = crtc->ctx; @@ -882,13 +871,12 @@ static void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable) return; val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE; - writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON); + writel(val, ctx->regs + DP_MIE_CLKCON); } static const struct exynos_drm_crtc_ops fimd_crtc_ops = { .enable = fimd_enable, .disable = fimd_disable, - .mode_fixup = fimd_mode_fixup, .commit = fimd_commit, .enable_vblank = fimd_enable_vblank, .disable_vblank = fimd_disable_vblank, diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 3734c34..c17efdb 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1059,7 +1059,6 @@ int exynos_g2d_get_ver_ioctl(struct drm_device *drm_dev, void *data, return 0; } -EXPORT_SYMBOL_GPL(exynos_g2d_get_ver_ioctl); int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data, struct drm_file *file) @@ -1230,7 +1229,6 @@ err: g2d_put_cmdlist(g2d, node); return ret; } -EXPORT_SYMBOL_GPL(exynos_g2d_set_cmdlist_ioctl); int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data, struct drm_file *file) @@ -1293,7 +1291,6 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data, out: return 0; } -EXPORT_SYMBOL_GPL(exynos_g2d_exec_ioctl); static int g2d_subdrv_probe(struct drm_device *drm_dev, struct device *dev) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index f12fbc3..407afed 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -56,39 +56,35 @@ static int exynos_drm_alloc_buf(struct exynos_drm_gem_obj *obj) nr_pages = obj->size >> PAGE_SHIFT; if (!is_drm_iommu_supported(dev)) { - dma_addr_t start_addr; - unsigned int i = 0; - obj->pages = drm_calloc_large(nr_pages, sizeof(struct page *)); if (!obj->pages) { DRM_ERROR("failed to allocate pages.\n"); return -ENOMEM; } + } - obj->cookie = dma_alloc_attrs(dev->dev, - obj->size, - &obj->dma_addr, GFP_KERNEL, - &obj->dma_attrs); - if (!obj->cookie) { - DRM_ERROR("failed to allocate buffer.\n"); + obj->cookie = dma_alloc_attrs(dev->dev, obj->size, &obj->dma_addr, + GFP_KERNEL, &obj->dma_attrs); + if (!obj->cookie) { + DRM_ERROR("failed to allocate buffer.\n"); + if (obj->pages) drm_free_large(obj->pages); - return -ENOMEM; - } + return -ENOMEM; + } + + if (obj->pages) { + dma_addr_t start_addr; + unsigned int i = 0; start_addr = obj->dma_addr; while (i < nr_pages) { - obj->pages[i] = phys_to_page(start_addr); + obj->pages[i] = pfn_to_page(dma_to_pfn(dev->dev, + start_addr)); start_addr += PAGE_SIZE; i++; } } else { - obj->pages = dma_alloc_attrs(dev->dev, obj->size, - &obj->dma_addr, GFP_KERNEL, - &obj->dma_attrs); - if (!obj->pages) { - DRM_ERROR("failed to allocate buffer.\n"); - return -ENOMEM; - } + obj->pages = obj->cookie; } DRM_DEBUG_KMS("dma_addr(0x%lx), size(0x%lx)\n", @@ -110,15 +106,11 @@ static void exynos_drm_free_buf(struct exynos_drm_gem_obj *obj) DRM_DEBUG_KMS("dma_addr(0x%lx), size(0x%lx)\n", (unsigned long)obj->dma_addr, obj->size); - if (!is_drm_iommu_supported(dev)) { - dma_free_attrs(dev->dev, obj->size, obj->cookie, - (dma_addr_t)obj->dma_addr, &obj->dma_attrs); - drm_free_large(obj->pages); - } else - dma_free_attrs(dev->dev, obj->size, obj->pages, - (dma_addr_t)obj->dma_addr, &obj->dma_attrs); + dma_free_attrs(dev->dev, obj->size, obj->cookie, + (dma_addr_t)obj->dma_addr, &obj->dma_attrs); - obj->dma_addr = (dma_addr_t)NULL; + if (!is_drm_iommu_supported(dev)) + drm_free_large(obj->pages); } static int exynos_drm_gem_handle_create(struct drm_gem_object *obj, @@ -156,18 +148,14 @@ void exynos_drm_gem_destroy(struct exynos_drm_gem_obj *exynos_gem_obj) * once dmabuf's refcount becomes 0. */ if (obj->import_attach) - goto out; - - exynos_drm_free_buf(exynos_gem_obj); - -out: - drm_gem_free_mmap_offset(obj); + drm_prime_gem_destroy(obj, exynos_gem_obj->sgt); + else + exynos_drm_free_buf(exynos_gem_obj); /* release file pointer to gem object. */ drm_gem_object_release(obj); kfree(exynos_gem_obj); - exynos_gem_obj = NULL; } unsigned long exynos_drm_gem_get_size(struct drm_device *dev, @@ -190,8 +178,7 @@ unsigned long exynos_drm_gem_get_size(struct drm_device *dev, return exynos_gem_obj->size; } - -struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, +static struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, unsigned long size) { struct exynos_drm_gem_obj *exynos_gem_obj; @@ -212,6 +199,13 @@ struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, return ERR_PTR(ret); } + ret = drm_gem_create_mmap_offset(obj); + if (ret < 0) { + drm_gem_object_release(obj); + kfree(exynos_gem_obj); + return ERR_PTR(ret); + } + DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp); return exynos_gem_obj; @@ -313,7 +307,7 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev, drm_gem_object_unreference_unlocked(obj); } -int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj, +static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj, struct vm_area_struct *vma) { struct drm_device *drm_dev = exynos_gem_obj->base.dev; @@ -342,7 +336,8 @@ int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj, int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) -{ struct exynos_drm_gem_obj *exynos_gem_obj; +{ + struct exynos_drm_gem_obj *exynos_gem_obj; struct drm_exynos_gem_info *args = data; struct drm_gem_object *obj; @@ -402,6 +397,7 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv, struct drm_mode_create_dumb *args) { struct exynos_drm_gem_obj *exynos_gem_obj; + unsigned int flags; int ret; /* @@ -413,16 +409,12 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv, args->pitch = args->width * ((args->bpp + 7) / 8); args->size = args->pitch * args->height; - if (is_drm_iommu_supported(dev)) { - exynos_gem_obj = exynos_drm_gem_create(dev, - EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC, - args->size); - } else { - exynos_gem_obj = exynos_drm_gem_create(dev, - EXYNOS_BO_CONTIG | EXYNOS_BO_WC, - args->size); - } + if (is_drm_iommu_supported(dev)) + flags = EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC; + else + flags = EXYNOS_BO_CONTIG | EXYNOS_BO_WC; + exynos_gem_obj = exynos_drm_gem_create(dev, flags, args->size); if (IS_ERR(exynos_gem_obj)) { dev_warn(dev->dev, "FB allocation failed.\n"); return PTR_ERR(exynos_gem_obj); @@ -460,14 +452,9 @@ int exynos_drm_gem_dumb_map_offset(struct drm_file *file_priv, goto unlock; } - ret = drm_gem_create_mmap_offset(obj); - if (ret) - goto out; - *offset = drm_vma_node_offset_addr(&obj->vma_node); DRM_DEBUG_KMS("offset = 0x%lx\n", (unsigned long)*offset); -out: drm_gem_object_unreference(obj); unlock: mutex_unlock(&dev->struct_mutex); @@ -543,7 +530,6 @@ int exynos_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) err_close_vm: drm_gem_vm_close(vma); - drm_gem_free_mmap_offset(obj); return ret; } @@ -588,6 +574,8 @@ exynos_drm_gem_prime_import_sg_table(struct drm_device *dev, if (ret < 0) goto err_free_large; + exynos_gem_obj->sgt = sgt; + if (sgt->nents == 1) { /* always physically continuous memory if sgt->nents is 1. */ exynos_gem_obj->flags |= EXYNOS_BO_CONTIG; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h index cd62f84..b62d100 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.h +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h @@ -39,6 +39,7 @@ * - this address could be physical address without IOMMU and * device address with IOMMU. * @pages: Array of backing pages. + * @sgt: Imported sg_table. * * P.S. this object would be transferred to user as kms_bo.handle so * user can access the buffer through kms_bo.handle. @@ -52,6 +53,7 @@ struct exynos_drm_gem_obj { dma_addr_t dma_addr; struct dma_attrs dma_attrs; struct page **pages; + struct sg_table *sgt; }; struct page **exynos_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask); @@ -59,10 +61,6 @@ struct page **exynos_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask); /* destroy a buffer with gem object */ void exynos_drm_gem_destroy(struct exynos_drm_gem_obj *exynos_gem_obj); -/* create a private gem object and initialize it. */ -struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev, - unsigned long size); - /* create a new buffer with gem object */ struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev, unsigned int flags, diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index 425e706..2f5c118 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -786,6 +786,7 @@ static int rotator_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM static int rotator_clk_crtl(struct rot_context *rot, bool enable) { if (enable) { @@ -822,7 +823,6 @@ static int rotator_resume(struct device *dev) } #endif -#ifdef CONFIG_PM static int rotator_runtime_suspend(struct device *dev) { struct rot_context *rot = dev_get_drvdata(dev); diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 424228b..896b6aa 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -23,7 +23,6 @@ #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> -#include <drm/drm_encoder_slave.h> #include <drm/drm_edid.h> #include <drm/drm_of.h> #include <drm/i2c/tda998x.h> @@ -34,9 +33,8 @@ struct tda998x_priv { struct i2c_client *cec; struct i2c_client *hdmi; struct mutex mutex; - struct delayed_work dwork; - uint16_t rev; - uint8_t current_page; + u16 rev; + u8 current_page; int dpms; bool is_hdmi_sink; u8 vip_cntrl_0; @@ -46,10 +44,21 @@ struct tda998x_priv { wait_queue_head_t wq_edid; volatile int wq_edid_wait; - struct drm_encoder *encoder; + + struct work_struct detect_work; + struct timer_list edid_delay_timer; + wait_queue_head_t edid_delay_waitq; + bool edid_delay_active; + + struct drm_encoder encoder; + struct drm_connector connector; }; -#define to_tda998x_priv(x) ((struct tda998x_priv *)to_encoder_slave(x)->slave_priv) +#define conn_to_tda998x_priv(x) \ + container_of(x, struct tda998x_priv, connector) + +#define enc_to_tda998x_priv(x) \ + container_of(x, struct tda998x_priv, encoder) /* The TDA9988 series of devices use a paged register scheme.. to simplify * things we encode the page # in upper bits of the register #. To read/ @@ -326,6 +335,8 @@ struct tda998x_priv { # define CEC_FRO_IM_CLK_CTRL_FRO_DIV (1 << 0) #define REG_CEC_RXSHPDINTENA 0xfc /* read/write */ #define REG_CEC_RXSHPDINT 0xfd /* read */ +# define CEC_RXSHPDINT_RXSENS BIT(0) +# define CEC_RXSHPDINT_HPD BIT(1) #define REG_CEC_RXSHPDLEV 0xfe /* read */ # define CEC_RXSHPDLEV_RXSENS (1 << 0) # define CEC_RXSHPDLEV_HPD (1 << 1) @@ -345,10 +356,10 @@ struct tda998x_priv { #define TDA19988 0x0301 static void -cec_write(struct tda998x_priv *priv, uint16_t addr, uint8_t val) +cec_write(struct tda998x_priv *priv, u16 addr, u8 val) { struct i2c_client *client = priv->cec; - uint8_t buf[] = {addr, val}; + u8 buf[] = {addr, val}; int ret; ret = i2c_master_send(client, buf, sizeof(buf)); @@ -356,11 +367,11 @@ cec_write(struct tda998x_priv *priv, uint16_t addr, uint8_t val) dev_err(&client->dev, "Error %d writing to cec:0x%x\n", ret, addr); } -static uint8_t -cec_read(struct tda998x_priv *priv, uint8_t addr) +static u8 +cec_read(struct tda998x_priv *priv, u8 addr) { struct i2c_client *client = priv->cec; - uint8_t val; + u8 val; int ret; ret = i2c_master_send(client, &addr, sizeof(addr)); @@ -379,11 +390,11 @@ fail: } static int -set_page(struct tda998x_priv *priv, uint16_t reg) +set_page(struct tda998x_priv *priv, u16 reg) { if (REG2PAGE(reg) != priv->current_page) { struct i2c_client *client = priv->hdmi; - uint8_t buf[] = { + u8 buf[] = { REG_CURPAGE, REG2PAGE(reg) }; int ret = i2c_master_send(client, buf, sizeof(buf)); @@ -399,10 +410,10 @@ set_page(struct tda998x_priv *priv, uint16_t reg) } static int -reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt) +reg_read_range(struct tda998x_priv *priv, u16 reg, char *buf, int cnt) { struct i2c_client *client = priv->hdmi; - uint8_t addr = REG2ADDR(reg); + u8 addr = REG2ADDR(reg); int ret; mutex_lock(&priv->mutex); @@ -428,10 +439,10 @@ out: } static void -reg_write_range(struct tda998x_priv *priv, uint16_t reg, uint8_t *p, int cnt) +reg_write_range(struct tda998x_priv *priv, u16 reg, u8 *p, int cnt) { struct i2c_client *client = priv->hdmi; - uint8_t buf[cnt+1]; + u8 buf[cnt+1]; int ret; buf[0] = REG2ADDR(reg); @@ -450,9 +461,9 @@ out: } static int -reg_read(struct tda998x_priv *priv, uint16_t reg) +reg_read(struct tda998x_priv *priv, u16 reg) { - uint8_t val = 0; + u8 val = 0; int ret; ret = reg_read_range(priv, reg, &val, sizeof(val)); @@ -462,10 +473,10 @@ reg_read(struct tda998x_priv *priv, uint16_t reg) } static void -reg_write(struct tda998x_priv *priv, uint16_t reg, uint8_t val) +reg_write(struct tda998x_priv *priv, u16 reg, u8 val) { struct i2c_client *client = priv->hdmi; - uint8_t buf[] = {REG2ADDR(reg), val}; + u8 buf[] = {REG2ADDR(reg), val}; int ret; mutex_lock(&priv->mutex); @@ -481,10 +492,10 @@ out: } static void -reg_write16(struct tda998x_priv *priv, uint16_t reg, uint16_t val) +reg_write16(struct tda998x_priv *priv, u16 reg, u16 val) { struct i2c_client *client = priv->hdmi; - uint8_t buf[] = {REG2ADDR(reg), val >> 8, val}; + u8 buf[] = {REG2ADDR(reg), val >> 8, val}; int ret; mutex_lock(&priv->mutex); @@ -500,7 +511,7 @@ out: } static void -reg_set(struct tda998x_priv *priv, uint16_t reg, uint8_t val) +reg_set(struct tda998x_priv *priv, u16 reg, u8 val) { int old_val; @@ -510,7 +521,7 @@ reg_set(struct tda998x_priv *priv, uint16_t reg, uint8_t val) } static void -reg_clear(struct tda998x_priv *priv, uint16_t reg, uint8_t val) +reg_clear(struct tda998x_priv *priv, u16 reg, u8 val) { int old_val; @@ -551,15 +562,50 @@ tda998x_reset(struct tda998x_priv *priv) reg_write(priv, REG_MUX_VP_VIP_OUT, 0x24); } -/* handle HDMI connect/disconnect */ -static void tda998x_hpd(struct work_struct *work) +/* + * The TDA998x has a problem when trying to read the EDID close to a + * HPD assertion: it needs a delay of 100ms to avoid timing out while + * trying to read EDID data. + * + * However, tda998x_encoder_get_modes() may be called at any moment + * after tda998x_connector_detect() indicates that we are connected, so + * we need to delay probing modes in tda998x_encoder_get_modes() after + * we have seen a HPD inactive->active transition. This code implements + * that delay. + */ +static void tda998x_edid_delay_done(unsigned long data) +{ + struct tda998x_priv *priv = (struct tda998x_priv *)data; + + priv->edid_delay_active = false; + wake_up(&priv->edid_delay_waitq); + schedule_work(&priv->detect_work); +} + +static void tda998x_edid_delay_start(struct tda998x_priv *priv) +{ + priv->edid_delay_active = true; + mod_timer(&priv->edid_delay_timer, jiffies + HZ/10); +} + +static int tda998x_edid_delay_wait(struct tda998x_priv *priv) +{ + return wait_event_killable(priv->edid_delay_waitq, !priv->edid_delay_active); +} + +/* + * We need to run the KMS hotplug event helper outside of our threaded + * interrupt routine as this can call back into our get_modes method, + * which will want to make use of interrupts. + */ +static void tda998x_detect_work(struct work_struct *work) { - struct delayed_work *dwork = to_delayed_work(work); struct tda998x_priv *priv = - container_of(dwork, struct tda998x_priv, dwork); + container_of(work, struct tda998x_priv, detect_work); + struct drm_device *dev = priv->encoder.dev; - if (priv->encoder && priv->encoder->dev) - drm_kms_helper_hotplug_event(priv->encoder->dev); + if (dev) + drm_kms_helper_hotplug_event(dev); } /* @@ -569,9 +615,8 @@ static irqreturn_t tda998x_irq_thread(int irq, void *data) { struct tda998x_priv *priv = data; u8 sta, cec, lvl, flag0, flag1, flag2; + bool handled = false; - if (!priv) - return IRQ_HANDLED; sta = cec_read(priv, REG_CEC_INTSTATUS); cec = cec_read(priv, REG_CEC_RXSHPDINT); lvl = cec_read(priv, REG_CEC_RXSHPDLEV); @@ -581,75 +626,76 @@ static irqreturn_t tda998x_irq_thread(int irq, void *data) DRM_DEBUG_DRIVER( "tda irq sta %02x cec %02x lvl %02x f0 %02x f1 %02x f2 %02x\n", sta, cec, lvl, flag0, flag1, flag2); + + if (cec & CEC_RXSHPDINT_HPD) { + if (lvl & CEC_RXSHPDLEV_HPD) + tda998x_edid_delay_start(priv); + else + schedule_work(&priv->detect_work); + + handled = true; + } + if ((flag2 & INT_FLAGS_2_EDID_BLK_RD) && priv->wq_edid_wait) { priv->wq_edid_wait = 0; wake_up(&priv->wq_edid); - } else if (cec != 0) { /* HPD change */ - schedule_delayed_work(&priv->dwork, HZ/10); + handled = true; } - return IRQ_HANDLED; -} -static uint8_t tda998x_cksum(uint8_t *buf, size_t bytes) -{ - int sum = 0; - - while (bytes--) - sum -= *buf++; - return sum; + return IRQ_RETVAL(handled); } -#define HB(x) (x) -#define PB(x) (HB(2) + 1 + (x)) - static void -tda998x_write_if(struct tda998x_priv *priv, uint8_t bit, uint16_t addr, - uint8_t *buf, size_t size) +tda998x_write_if(struct tda998x_priv *priv, u8 bit, u16 addr, + union hdmi_infoframe *frame) { + u8 buf[32]; + ssize_t len; + + len = hdmi_infoframe_pack(frame, buf, sizeof(buf)); + if (len < 0) { + dev_err(&priv->hdmi->dev, + "hdmi_infoframe_pack() type=0x%02x failed: %zd\n", + frame->any.type, len); + return; + } + reg_clear(priv, REG_DIP_IF_FLAGS, bit); - reg_write_range(priv, addr, buf, size); + reg_write_range(priv, addr, buf, len); reg_set(priv, REG_DIP_IF_FLAGS, bit); } static void tda998x_write_aif(struct tda998x_priv *priv, struct tda998x_encoder_params *p) { - u8 buf[PB(HDMI_AUDIO_INFOFRAME_SIZE) + 1]; + union hdmi_infoframe frame; + + hdmi_audio_infoframe_init(&frame.audio); - memset(buf, 0, sizeof(buf)); - buf[HB(0)] = HDMI_INFOFRAME_TYPE_AUDIO; - buf[HB(1)] = 0x01; - buf[HB(2)] = HDMI_AUDIO_INFOFRAME_SIZE; - buf[PB(1)] = p->audio_frame[1] & 0x07; /* CC */ - buf[PB(2)] = p->audio_frame[2] & 0x1c; /* SF */ - buf[PB(4)] = p->audio_frame[4]; - buf[PB(5)] = p->audio_frame[5] & 0xf8; /* DM_INH + LSV */ + frame.audio.channels = p->audio_frame[1] & 0x07; + frame.audio.channel_allocation = p->audio_frame[4]; + frame.audio.level_shift_value = (p->audio_frame[5] & 0x78) >> 3; + frame.audio.downmix_inhibit = (p->audio_frame[5] & 0x80) >> 7; - buf[PB(0)] = tda998x_cksum(buf, sizeof(buf)); + /* + * L-PCM and IEC61937 compressed audio shall always set sample + * frequency to "refer to stream". For others, see the HDMI + * specification. + */ + frame.audio.sample_frequency = (p->audio_frame[2] & 0x1c) >> 2; - tda998x_write_if(priv, DIP_IF_FLAGS_IF4, REG_IF4_HB0, buf, - sizeof(buf)); + tda998x_write_if(priv, DIP_IF_FLAGS_IF4, REG_IF4_HB0, &frame); } static void tda998x_write_avi(struct tda998x_priv *priv, struct drm_display_mode *mode) { - struct hdmi_avi_infoframe frame; - u8 buf[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE]; - ssize_t len; + union hdmi_infoframe frame; - drm_hdmi_avi_infoframe_from_display_mode(&frame, mode); + drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, mode); + frame.avi.quantization_range = HDMI_QUANTIZATION_RANGE_FULL; - frame.quantization_range = HDMI_QUANTIZATION_RANGE_FULL; - - len = hdmi_avi_infoframe_pack(&frame, buf, sizeof(buf)); - if (len < 0) { - dev_err(&priv->hdmi->dev, - "hdmi_avi_infoframe_pack() failed: %zd\n", len); - return; - } - - tda998x_write_if(priv, DIP_IF_FLAGS_IF2, REG_IF2_HB0, buf, len); + tda998x_write_if(priv, DIP_IF_FLAGS_IF2, REG_IF2_HB0, &frame); } static void tda998x_audio_mute(struct tda998x_priv *priv, bool on) @@ -667,8 +713,8 @@ static void tda998x_configure_audio(struct tda998x_priv *priv, struct drm_display_mode *mode, struct tda998x_encoder_params *p) { - uint8_t buf[6], clksel_aip, clksel_fs, cts_n, adiv; - uint32_t n; + u8 buf[6], clksel_aip, clksel_fs, cts_n, adiv; + u32 n; /* Enable audio ports */ reg_write(priv, REG_ENA_AP, p->audio_cfg); @@ -776,8 +822,10 @@ static void tda998x_encoder_set_config(struct tda998x_priv *priv, priv->params = *p; } -static void tda998x_encoder_dpms(struct tda998x_priv *priv, int mode) +static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode) { + struct tda998x_priv *priv = enc_to_tda998x_priv(encoder); + /* we only care about on or off: */ if (mode != DRM_MODE_DPMS_ON) mode = DRM_MODE_DPMS_OFF; @@ -827,8 +875,8 @@ tda998x_encoder_mode_fixup(struct drm_encoder *encoder, return true; } -static int tda998x_encoder_mode_valid(struct tda998x_priv *priv, - struct drm_display_mode *mode) +static int tda998x_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { if (mode->clock > 150000) return MODE_CLOCK_HIGH; @@ -840,18 +888,19 @@ static int tda998x_encoder_mode_valid(struct tda998x_priv *priv, } static void -tda998x_encoder_mode_set(struct tda998x_priv *priv, +tda998x_encoder_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { - uint16_t ref_pix, ref_line, n_pix, n_line; - uint16_t hs_pix_s, hs_pix_e; - uint16_t vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e; - uint16_t vs2_pix_s, vs2_pix_e, vs2_line_s, vs2_line_e; - uint16_t vwin1_line_s, vwin1_line_e; - uint16_t vwin2_line_s, vwin2_line_e; - uint16_t de_pix_s, de_pix_e; - uint8_t reg, div, rep; + struct tda998x_priv *priv = enc_to_tda998x_priv(encoder); + u16 ref_pix, ref_line, n_pix, n_line; + u16 hs_pix_s, hs_pix_e; + u16 vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e; + u16 vs2_pix_s, vs2_pix_e, vs2_line_s, vs2_line_e; + u16 vwin1_line_s, vwin1_line_e; + u16 vwin2_line_s, vwin2_line_e; + u16 de_pix_s, de_pix_e; + u8 reg, div, rep; /* * Internally TDA998x is using ITU-R BT.656 style sync but @@ -1031,9 +1080,10 @@ tda998x_encoder_mode_set(struct tda998x_priv *priv, } static enum drm_connector_status -tda998x_encoder_detect(struct tda998x_priv *priv) +tda998x_connector_detect(struct drm_connector *connector, bool force) { - uint8_t val = cec_read(priv, REG_CEC_RXSHPDLEV); + struct tda998x_priv *priv = conn_to_tda998x_priv(connector); + u8 val = cec_read(priv, REG_CEC_RXSHPDLEV); return (val & CEC_RXSHPDLEV_HPD) ? connector_status_connected : connector_status_disconnected; @@ -1042,7 +1092,7 @@ tda998x_encoder_detect(struct tda998x_priv *priv) static int read_edid_block(void *data, u8 *buf, unsigned int blk, size_t length) { struct tda998x_priv *priv = data; - uint8_t offset, segptr; + u8 offset, segptr; int ret, i; offset = (blk & 1) ? 128 : 0; @@ -1095,13 +1145,20 @@ static int read_edid_block(void *data, u8 *buf, unsigned int blk, size_t length) return 0; } -static int -tda998x_encoder_get_modes(struct tda998x_priv *priv, - struct drm_connector *connector) +static int tda998x_connector_get_modes(struct drm_connector *connector) { + struct tda998x_priv *priv = conn_to_tda998x_priv(connector); struct edid *edid; int n; + /* + * If we get killed while waiting for the HPD timeout, return + * no modes found: we are not in a restartable path, so we + * can't handle signals gracefully. + */ + if (tda998x_edid_delay_wait(priv)) + return 0; + if (priv->rev == TDA19988) reg_clear(priv, REG_TX4, TX4_PD_RAM); @@ -1133,101 +1190,21 @@ static void tda998x_encoder_set_polling(struct tda998x_priv *priv, DRM_CONNECTOR_POLL_DISCONNECT; } -static int -tda998x_encoder_set_property(struct drm_encoder *encoder, - struct drm_connector *connector, - struct drm_property *property, - uint64_t val) -{ - DBG(""); - return 0; -} - static void tda998x_destroy(struct tda998x_priv *priv) { /* disable all IRQs and free the IRQ handler */ cec_write(priv, REG_CEC_RXSHPDINTENA, 0); reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD); - if (priv->hdmi->irq) { - free_irq(priv->hdmi->irq, priv); - cancel_delayed_work_sync(&priv->dwork); - } - - i2c_unregister_device(priv->cec); -} - -/* Slave encoder support */ - -static void -tda998x_encoder_slave_set_config(struct drm_encoder *encoder, void *params) -{ - tda998x_encoder_set_config(to_tda998x_priv(encoder), params); -} -static void tda998x_encoder_slave_destroy(struct drm_encoder *encoder) -{ - struct tda998x_priv *priv = to_tda998x_priv(encoder); - - tda998x_destroy(priv); - drm_i2c_encoder_destroy(encoder); - kfree(priv); -} - -static void tda998x_encoder_slave_dpms(struct drm_encoder *encoder, int mode) -{ - tda998x_encoder_dpms(to_tda998x_priv(encoder), mode); -} - -static int tda998x_encoder_slave_mode_valid(struct drm_encoder *encoder, - struct drm_display_mode *mode) -{ - return tda998x_encoder_mode_valid(to_tda998x_priv(encoder), mode); -} + if (priv->hdmi->irq) + free_irq(priv->hdmi->irq, priv); -static void -tda998x_encoder_slave_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - tda998x_encoder_mode_set(to_tda998x_priv(encoder), mode, adjusted_mode); -} + del_timer_sync(&priv->edid_delay_timer); + cancel_work_sync(&priv->detect_work); -static enum drm_connector_status -tda998x_encoder_slave_detect(struct drm_encoder *encoder, - struct drm_connector *connector) -{ - return tda998x_encoder_detect(to_tda998x_priv(encoder)); -} - -static int tda998x_encoder_slave_get_modes(struct drm_encoder *encoder, - struct drm_connector *connector) -{ - return tda998x_encoder_get_modes(to_tda998x_priv(encoder), connector); -} - -static int -tda998x_encoder_slave_create_resources(struct drm_encoder *encoder, - struct drm_connector *connector) -{ - tda998x_encoder_set_polling(to_tda998x_priv(encoder), connector); - return 0; + i2c_unregister_device(priv->cec); } -static struct drm_encoder_slave_funcs tda998x_encoder_slave_funcs = { - .set_config = tda998x_encoder_slave_set_config, - .destroy = tda998x_encoder_slave_destroy, - .dpms = tda998x_encoder_slave_dpms, - .save = tda998x_encoder_save, - .restore = tda998x_encoder_restore, - .mode_fixup = tda998x_encoder_mode_fixup, - .mode_valid = tda998x_encoder_slave_mode_valid, - .mode_set = tda998x_encoder_slave_mode_set, - .detect = tda998x_encoder_slave_detect, - .get_modes = tda998x_encoder_slave_get_modes, - .create_resources = tda998x_encoder_slave_create_resources, - .set_property = tda998x_encoder_set_property, -}; - /* I2C driver functions */ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) @@ -1252,6 +1229,10 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) priv->dpms = DRM_MODE_DPMS_OFF; mutex_init(&priv->mutex); /* protect the page access */ + init_waitqueue_head(&priv->edid_delay_waitq); + setup_timer(&priv->edid_delay_timer, tda998x_edid_delay_done, + (unsigned long)priv); + INIT_WORK(&priv->detect_work, tda998x_detect_work); /* wake up the device: */ cec_write(priv, REG_CEC_ENAMODS, @@ -1310,7 +1291,6 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) /* init read EDID waitqueue and HDP work */ init_waitqueue_head(&priv->wq_edid); - INIT_DELAYED_WORK(&priv->dwork, tda998x_hpd); /* clear pending interrupts */ reg_read(priv, REG_INT_FLAGS_0); @@ -1359,84 +1339,31 @@ fail: return -ENXIO; } -static int tda998x_encoder_init(struct i2c_client *client, - struct drm_device *dev, - struct drm_encoder_slave *encoder_slave) -{ - struct tda998x_priv *priv; - int ret; - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - priv->encoder = &encoder_slave->base; - - ret = tda998x_create(client, priv); - if (ret) { - kfree(priv); - return ret; - } - - encoder_slave->slave_priv = priv; - encoder_slave->slave_funcs = &tda998x_encoder_slave_funcs; - - return 0; -} - -struct tda998x_priv2 { - struct tda998x_priv base; - struct drm_encoder encoder; - struct drm_connector connector; -}; - -#define conn_to_tda998x_priv2(x) \ - container_of(x, struct tda998x_priv2, connector); - -#define enc_to_tda998x_priv2(x) \ - container_of(x, struct tda998x_priv2, encoder); - -static void tda998x_encoder2_dpms(struct drm_encoder *encoder, int mode) -{ - struct tda998x_priv2 *priv = enc_to_tda998x_priv2(encoder); - - tda998x_encoder_dpms(&priv->base, mode); -} - static void tda998x_encoder_prepare(struct drm_encoder *encoder) { - tda998x_encoder2_dpms(encoder, DRM_MODE_DPMS_OFF); + tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_OFF); } static void tda998x_encoder_commit(struct drm_encoder *encoder) { - tda998x_encoder2_dpms(encoder, DRM_MODE_DPMS_ON); -} - -static void tda998x_encoder2_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - struct tda998x_priv2 *priv = enc_to_tda998x_priv2(encoder); - - tda998x_encoder_mode_set(&priv->base, mode, adjusted_mode); + tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_ON); } static const struct drm_encoder_helper_funcs tda998x_encoder_helper_funcs = { - .dpms = tda998x_encoder2_dpms, + .dpms = tda998x_encoder_dpms, .save = tda998x_encoder_save, .restore = tda998x_encoder_restore, .mode_fixup = tda998x_encoder_mode_fixup, .prepare = tda998x_encoder_prepare, .commit = tda998x_encoder_commit, - .mode_set = tda998x_encoder2_mode_set, + .mode_set = tda998x_encoder_mode_set, }; static void tda998x_encoder_destroy(struct drm_encoder *encoder) { - struct tda998x_priv2 *priv = enc_to_tda998x_priv2(encoder); + struct tda998x_priv *priv = enc_to_tda998x_priv(encoder); - tda998x_destroy(&priv->base); + tda998x_destroy(priv); drm_encoder_cleanup(encoder); } @@ -1444,25 +1371,10 @@ static const struct drm_encoder_funcs tda998x_encoder_funcs = { .destroy = tda998x_encoder_destroy, }; -static int tda998x_connector_get_modes(struct drm_connector *connector) -{ - struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector); - - return tda998x_encoder_get_modes(&priv->base, connector); -} - -static int tda998x_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector); - - return tda998x_encoder_mode_valid(&priv->base, mode); -} - static struct drm_encoder * tda998x_connector_best_encoder(struct drm_connector *connector) { - struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector); + struct tda998x_priv *priv = conn_to_tda998x_priv(connector); return &priv->encoder; } @@ -1474,14 +1386,6 @@ const struct drm_connector_helper_funcs tda998x_connector_helper_funcs = { .best_encoder = tda998x_connector_best_encoder, }; -static enum drm_connector_status -tda998x_connector_detect(struct drm_connector *connector, bool force) -{ - struct tda998x_priv2 *priv = conn_to_tda998x_priv2(connector); - - return tda998x_encoder_detect(&priv->base); -} - static void tda998x_connector_destroy(struct drm_connector *connector) { drm_connector_unregister(connector); @@ -1500,8 +1404,8 @@ static int tda998x_bind(struct device *dev, struct device *master, void *data) struct tda998x_encoder_params *params = dev->platform_data; struct i2c_client *client = to_i2c_client(dev); struct drm_device *drm = data; - struct tda998x_priv2 *priv; - uint32_t crtcs = 0; + struct tda998x_priv *priv; + u32 crtcs = 0; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -1519,18 +1423,17 @@ static int tda998x_bind(struct device *dev, struct device *master, void *data) crtcs = 1 << 0; } - priv->base.encoder = &priv->encoder; priv->connector.interlace_allowed = 1; priv->encoder.possible_crtcs = crtcs; - ret = tda998x_create(client, &priv->base); + ret = tda998x_create(client, priv); if (ret) return ret; if (!dev->of_node && params) - tda998x_encoder_set_config(&priv->base, params); + tda998x_encoder_set_config(priv, params); - tda998x_encoder_set_polling(&priv->base, &priv->connector); + tda998x_encoder_set_polling(priv, &priv->connector); drm_encoder_helper_add(&priv->encoder, &tda998x_encoder_helper_funcs); ret = drm_encoder_init(drm, &priv->encoder, &tda998x_encoder_funcs, @@ -1560,18 +1463,18 @@ err_sysfs: err_connector: drm_encoder_cleanup(&priv->encoder); err_encoder: - tda998x_destroy(&priv->base); + tda998x_destroy(priv); return ret; } static void tda998x_unbind(struct device *dev, struct device *master, void *data) { - struct tda998x_priv2 *priv = dev_get_drvdata(dev); + struct tda998x_priv *priv = dev_get_drvdata(dev); drm_connector_cleanup(&priv->connector); drm_encoder_cleanup(&priv->encoder); - tda998x_destroy(&priv->base); + tda998x_destroy(priv); } static const struct component_ops tda998x_ops = { @@ -1605,38 +1508,18 @@ static struct i2c_device_id tda998x_ids[] = { }; MODULE_DEVICE_TABLE(i2c, tda998x_ids); -static struct drm_i2c_encoder_driver tda998x_driver = { - .i2c_driver = { - .probe = tda998x_probe, - .remove = tda998x_remove, - .driver = { - .name = "tda998x", - .of_match_table = of_match_ptr(tda998x_dt_ids), - }, - .id_table = tda998x_ids, +static struct i2c_driver tda998x_driver = { + .probe = tda998x_probe, + .remove = tda998x_remove, + .driver = { + .name = "tda998x", + .of_match_table = of_match_ptr(tda998x_dt_ids), }, - .encoder_init = tda998x_encoder_init, + .id_table = tda998x_ids, }; -/* Module initialization */ - -static int __init -tda998x_init(void) -{ - DBG(""); - return drm_i2c_encoder_register(THIS_MODULE, &tda998x_driver); -} - -static void __exit -tda998x_exit(void) -{ - DBG(""); - drm_i2c_encoder_unregister(&tda998x_driver); -} +module_i2c_driver(tda998x_driver); MODULE_AUTHOR("Rob Clark <robdclark@gmail.com"); MODULE_DESCRIPTION("NXP Semiconductors TDA998X HDMI Encoder"); MODULE_LICENSE("GPL"); - -module_init(tda998x_init); -module_exit(tda998x_exit); diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 998b464..44d290a 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -40,6 +40,10 @@ i915-y += i915_cmd_parser.o \ intel_ringbuffer.o \ intel_uncore.o +# general-purpose microcontroller (GuC) support +i915-y += intel_guc_loader.o \ + i915_guc_submission.o + # autogenerated null render state i915-y += intel_renderstate_gen6.o \ intel_renderstate_gen7.o \ diff --git a/drivers/gpu/drm/i915/dvo.h b/drivers/gpu/drm/i915/dvo.h index 3121633..0e2c1b9 100644 --- a/drivers/gpu/drm/i915/dvo.h +++ b/drivers/gpu/drm/i915/dvo.h @@ -94,8 +94,8 @@ struct intel_dvo_dev_ops { * after this function is called. */ void (*mode_set)(struct intel_dvo_device *dvo, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode); + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode); /* * Probe for a connected output, and return detect_status. diff --git a/drivers/gpu/drm/i915/dvo_ch7017.c b/drivers/gpu/drm/i915/dvo_ch7017.c index 86b27d1..cbb2202 100644 --- a/drivers/gpu/drm/i915/dvo_ch7017.c +++ b/drivers/gpu/drm/i915/dvo_ch7017.c @@ -255,8 +255,8 @@ static enum drm_mode_status ch7017_mode_valid(struct intel_dvo_device *dvo, } static void ch7017_mode_set(struct intel_dvo_device *dvo, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) { uint8_t lvds_pll_feedback_div, lvds_pll_vco_control; uint8_t outputs_enable, lvds_control_2, lvds_power_down; diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c index 80449f4..4b4acc1 100644 --- a/drivers/gpu/drm/i915/dvo_ch7xxx.c +++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c @@ -275,8 +275,8 @@ static enum drm_mode_status ch7xxx_mode_valid(struct intel_dvo_device *dvo, } static void ch7xxx_mode_set(struct intel_dvo_device *dvo, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) { uint8_t tvco, tpcp, tpd, tlpf, idf; diff --git a/drivers/gpu/drm/i915/dvo_ivch.c b/drivers/gpu/drm/i915/dvo_ivch.c index 732ce87..ff9f1b0 100644 --- a/drivers/gpu/drm/i915/dvo_ivch.c +++ b/drivers/gpu/drm/i915/dvo_ivch.c @@ -394,8 +394,8 @@ static bool ivch_get_hw_state(struct intel_dvo_device *dvo) } static void ivch_mode_set(struct intel_dvo_device *dvo, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) { struct ivch_priv *priv = dvo->dev_priv; uint16_t vr40 = 0; @@ -414,16 +414,16 @@ static void ivch_mode_set(struct intel_dvo_device *dvo, vr40 = (VR40_STALL_ENABLE | VR40_VERTICAL_INTERP_ENABLE | VR40_HORIZONTAL_INTERP_ENABLE); - if (mode->hdisplay != adjusted_mode->hdisplay || - mode->vdisplay != adjusted_mode->vdisplay) { + if (mode->hdisplay != adjusted_mode->crtc_hdisplay || + mode->vdisplay != adjusted_mode->crtc_vdisplay) { uint16_t x_ratio, y_ratio; vr01 |= VR01_PANEL_FIT_ENABLE; vr40 |= VR40_CLOCK_GATING_ENABLE; x_ratio = (((mode->hdisplay - 1) << 16) / - (adjusted_mode->hdisplay - 1)) >> 2; + (adjusted_mode->crtc_hdisplay - 1)) >> 2; y_ratio = (((mode->vdisplay - 1) << 16) / - (adjusted_mode->vdisplay - 1)) >> 2; + (adjusted_mode->crtc_vdisplay - 1)) >> 2; ivch_write(dvo, VR42, x_ratio); ivch_write(dvo, VR41, y_ratio); } else { diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c index 97ae8aa..063859f 100644 --- a/drivers/gpu/drm/i915/dvo_ns2501.c +++ b/drivers/gpu/drm/i915/dvo_ns2501.c @@ -546,8 +546,8 @@ static enum drm_mode_status ns2501_mode_valid(struct intel_dvo_device *dvo, } static void ns2501_mode_set(struct intel_dvo_device *dvo, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) { const struct ns2501_configuration *conf; struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv); diff --git a/drivers/gpu/drm/i915/dvo_sil164.c b/drivers/gpu/drm/i915/dvo_sil164.c index fa01149..26f13eb 100644 --- a/drivers/gpu/drm/i915/dvo_sil164.c +++ b/drivers/gpu/drm/i915/dvo_sil164.c @@ -190,8 +190,8 @@ static enum drm_mode_status sil164_mode_valid(struct intel_dvo_device *dvo, } static void sil164_mode_set(struct intel_dvo_device *dvo, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) { /* As long as the basics are set up, since we don't have clock * dependencies in the mode setup, we can just leave the diff --git a/drivers/gpu/drm/i915/dvo_tfp410.c b/drivers/gpu/drm/i915/dvo_tfp410.c index 7853719..6f1a0a6 100644 --- a/drivers/gpu/drm/i915/dvo_tfp410.c +++ b/drivers/gpu/drm/i915/dvo_tfp410.c @@ -222,8 +222,8 @@ static enum drm_mode_status tfp410_mode_valid(struct intel_dvo_device *dvo, } static void tfp410_mode_set(struct intel_dvo_device *dvo, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) { /* As long as the basics are set up, since we don't have clock dependencies * in the mode setup, we can just leave the registers alone and everything diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 237ff68..db58c8d 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -94,7 +94,7 @@ #define CMD(op, opm, f, lm, fl, ...) \ { \ .flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \ - .cmd = { (op), (opm) }, \ + .cmd = { (op), (opm) }, \ .length = { (lm) }, \ __VA_ARGS__ \ } @@ -124,14 +124,14 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_STORE_DWORD_INDEX, SMI, !F, 0xFF, R ), CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), - CMD( MI_STORE_REGISTER_MEM(1), SMI, !F, 0xFF, W | B, + CMD( MI_STORE_REGISTER_MEM, SMI, F, 3, W | B, .reg = { .offset = 1, .mask = 0x007FFFFC }, .bits = {{ .offset = 0, .mask = MI_GLOBAL_GTT, .expected = 0, }}, ), - CMD( MI_LOAD_REGISTER_MEM(1), SMI, !F, 0xFF, W | B, + CMD( MI_LOAD_REGISTER_MEM, SMI, F, 3, W | B, .reg = { .offset = 1, .mask = 0x007FFFFC }, .bits = {{ .offset = 0, @@ -448,6 +448,9 @@ static const struct drm_i915_reg_descriptor gen7_render_regs[] = { REG32(GEN7_3DPRIM_INSTANCE_COUNT), REG32(GEN7_3DPRIM_START_INSTANCE), REG32(GEN7_3DPRIM_BASE_VERTEX), + REG32(GEN7_GPGPU_DISPATCHDIMX), + REG32(GEN7_GPGPU_DISPATCHDIMY), + REG32(GEN7_GPGPU_DISPATCHDIMZ), REG64(GEN7_SO_NUM_PRIMS_WRITTEN(0)), REG64(GEN7_SO_NUM_PRIMS_WRITTEN(1)), REG64(GEN7_SO_NUM_PRIMS_WRITTEN(2)), @@ -1021,7 +1024,7 @@ static bool check_cmd(const struct intel_engine_cs *ring, * only MI_LOAD_REGISTER_IMM commands. */ if (reg_addr == OACONTROL) { - if (desc->cmd.value == MI_LOAD_REGISTER_MEM(1)) { + if (desc->cmd.value == MI_LOAD_REGISTER_MEM) { DRM_DEBUG_DRIVER("CMD: Rejected LRM to OACONTROL\n"); return false; } @@ -1035,7 +1038,7 @@ static bool check_cmd(const struct intel_engine_cs *ring, * allowed mask/value pair given in the whitelist entry. */ if (reg->mask) { - if (desc->cmd.value == MI_LOAD_REGISTER_MEM(1)) { + if (desc->cmd.value == MI_LOAD_REGISTER_MEM) { DRM_DEBUG_DRIVER("CMD: Rejected LRM to masked register 0x%08X\n", reg_addr); return false; @@ -1213,6 +1216,8 @@ int i915_cmd_parser_get_version(void) * 2. Allow access to the MI_PREDICATE_SRC0 and * MI_PREDICATE_SRC1 registers. * 3. Allow access to the GPGPU_THREADS_DISPATCHED register. + * 4. L3 atomic chicken bits of HSW_SCRATCH1 and HSW_ROW_CHICKEN3. + * 5. GPGPU dispatch compute indirect registers. */ - return 3; + return 5; } diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 40e77fd..3f2a7a7 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -46,11 +46,6 @@ enum { PINNED_LIST, }; -static const char *yesno(int v) -{ - return v ? "yes" : "no"; -} - /* As the drm_debugfs_init() routines are called before dev->dev_private is * allocated we need to hook into the minor for release. */ static int @@ -258,7 +253,11 @@ static int obj_rank_by_stolen(void *priv, struct drm_i915_gem_object *b = container_of(B, struct drm_i915_gem_object, obj_exec_link); - return a->stolen->start - b->stolen->start; + if (a->stolen->start < b->stolen->start) + return -1; + if (a->stolen->start > b->stolen->start) + return 1; + return 0; } static int i915_gem_stolen_list_info(struct seq_file *m, void *data) @@ -1313,6 +1312,10 @@ static int i915_frequency_info(struct seq_file *m, void *unused) seq_puts(m, "no P-state info available\n"); } + seq_printf(m, "Current CD clock frequency: %d kHz\n", dev_priv->cdclk_freq); + seq_printf(m, "Max CD clock frequency: %d kHz\n", dev_priv->max_cdclk_freq); + seq_printf(m, "Max pixel clock frequency: %d kHz\n", dev_priv->max_dotclk_freq); + out: intel_runtime_pm_put(dev_priv); return ret; @@ -1386,17 +1389,16 @@ static int ironlake_drpc_info(struct seq_file *m) intel_runtime_pm_put(dev_priv); mutex_unlock(&dev->struct_mutex); - seq_printf(m, "HD boost: %s\n", (rgvmodectl & MEMMODE_BOOST_EN) ? - "yes" : "no"); + seq_printf(m, "HD boost: %s\n", yesno(rgvmodectl & MEMMODE_BOOST_EN)); seq_printf(m, "Boost freq: %d\n", (rgvmodectl & MEMMODE_BOOST_FREQ_MASK) >> MEMMODE_BOOST_FREQ_SHIFT); seq_printf(m, "HW control enabled: %s\n", - rgvmodectl & MEMMODE_HWIDLE_EN ? "yes" : "no"); + yesno(rgvmodectl & MEMMODE_HWIDLE_EN)); seq_printf(m, "SW control enabled: %s\n", - rgvmodectl & MEMMODE_SWMODE_EN ? "yes" : "no"); + yesno(rgvmodectl & MEMMODE_SWMODE_EN)); seq_printf(m, "Gated voltage change: %s\n", - rgvmodectl & MEMMODE_RCLK_GATE ? "yes" : "no"); + yesno(rgvmodectl & MEMMODE_RCLK_GATE)); seq_printf(m, "Starting frequency: P%d\n", (rgvmodectl & MEMMODE_FSTART_MASK) >> MEMMODE_FSTART_SHIFT); seq_printf(m, "Max P-state: P%d\n", @@ -1405,7 +1407,7 @@ static int ironlake_drpc_info(struct seq_file *m) seq_printf(m, "RS1 VID: %d\n", (crstandvid & 0x3f)); seq_printf(m, "RS2 VID: %d\n", ((crstandvid >> 8) & 0x3f)); seq_printf(m, "Render standby enabled: %s\n", - (rstdbyctl & RCX_SW_EXIT) ? "no" : "yes"); + yesno(!(rstdbyctl & RCX_SW_EXIT))); seq_puts(m, "Current RS state: "); switch (rstdbyctl & RSX_STATUS_MASK) { case RSX_STATUS_ON: @@ -1994,7 +1996,7 @@ static void i915_dump_lrc_obj(struct seq_file *m, return; } - page = i915_gem_object_get_page(ctx_obj, 1); + page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN); if (!WARN_ON(page == NULL)) { reg_state = kmap_atomic(page); @@ -2074,8 +2076,8 @@ static int i915_execlists(struct seq_file *m, void *data) seq_printf(m, "%s\n", ring->name); - status = I915_READ(RING_EXECLIST_STATUS(ring)); - ctx_id = I915_READ(RING_EXECLIST_STATUS(ring) + 4); + status = I915_READ(RING_EXECLIST_STATUS_LO(ring)); + ctx_id = I915_READ(RING_EXECLIST_STATUS_HI(ring)); seq_printf(m, "\tExeclist status: 0x%08X, context: %u\n", status, ctx_id); @@ -2090,8 +2092,8 @@ static int i915_execlists(struct seq_file *m, void *data) read_pointer, write_pointer); for (i = 0; i < 6; i++) { - status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + 8*i); - ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + 8*i + 4); + status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, i)); + ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, i)); seq_printf(m, "\tStatus buffer %d: 0x%08X, context: %u\n", i, status, ctx_id); @@ -2236,10 +2238,9 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) for_each_ring(ring, dev_priv, unused) { seq_printf(m, "%s\n", ring->name); for (i = 0; i < 4; i++) { - u32 offset = 0x270 + i * 8; - u64 pdp = I915_READ(ring->mmio_base + offset + 4); + u64 pdp = I915_READ(GEN8_RING_PDP_UDW(ring, i)); pdp <<= 32; - pdp |= I915_READ(ring->mmio_base + offset); + pdp |= I915_READ(GEN8_RING_PDP_LDW(ring, i)); seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp); } } @@ -2249,7 +2250,6 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_engine_cs *ring; - struct drm_file *file; int i; if (INTEL_INFO(dev)->gen == 6) @@ -2272,13 +2272,6 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) ppgtt->debug_dump(ppgtt, m); } - list_for_each_entry_reverse(file, &dev->filelist, lhead) { - struct drm_i915_file_private *file_priv = file->driver_priv; - - seq_printf(m, "proc: %s\n", - get_pid_task(file->pid, PIDTYPE_PID)->comm); - idr_for_each(&file_priv->context_idr, per_file_ctx, m); - } seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK)); } @@ -2287,6 +2280,7 @@ static int i915_ppgtt_info(struct seq_file *m, void *data) struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_file *file; int ret = mutex_lock_interruptible(&dev->struct_mutex); if (ret) @@ -2298,10 +2292,26 @@ static int i915_ppgtt_info(struct seq_file *m, void *data) else if (INTEL_INFO(dev)->gen >= 6) gen6_ppgtt_info(m, dev); + list_for_each_entry_reverse(file, &dev->filelist, lhead) { + struct drm_i915_file_private *file_priv = file->driver_priv; + struct task_struct *task; + + task = get_pid_task(file->pid, PIDTYPE_PID); + if (!task) { + ret = -ESRCH; + goto out_put; + } + seq_printf(m, "\nproc: %s\n", task->comm); + put_task_struct(task); + idr_for_each(&file_priv->context_idr, per_file_ctx, + (void *)(unsigned long)m); + } + +out_put: intel_runtime_pm_put(dev_priv); mutex_unlock(&dev->struct_mutex); - return 0; + return ret; } static int count_irq_waiters(struct drm_i915_private *i915) @@ -2371,6 +2381,147 @@ static int i915_llc(struct seq_file *m, void *data) return 0; } +static int i915_guc_load_status_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct drm_i915_private *dev_priv = node->minor->dev->dev_private; + struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw; + u32 tmp, i; + + if (!HAS_GUC_UCODE(dev_priv->dev)) + return 0; + + seq_printf(m, "GuC firmware status:\n"); + seq_printf(m, "\tpath: %s\n", + guc_fw->guc_fw_path); + seq_printf(m, "\tfetch: %s\n", + intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status)); + seq_printf(m, "\tload: %s\n", + intel_guc_fw_status_repr(guc_fw->guc_fw_load_status)); + seq_printf(m, "\tversion wanted: %d.%d\n", + guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted); + seq_printf(m, "\tversion found: %d.%d\n", + guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found); + + tmp = I915_READ(GUC_STATUS); + + seq_printf(m, "\nGuC status 0x%08x:\n", tmp); + seq_printf(m, "\tBootrom status = 0x%x\n", + (tmp & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT); + seq_printf(m, "\tuKernel status = 0x%x\n", + (tmp & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT); + seq_printf(m, "\tMIA Core status = 0x%x\n", + (tmp & GS_MIA_MASK) >> GS_MIA_SHIFT); + seq_puts(m, "\nScratch registers:\n"); + for (i = 0; i < 16; i++) + seq_printf(m, "\t%2d: \t0x%x\n", i, I915_READ(SOFT_SCRATCH(i))); + + return 0; +} + +static void i915_guc_client_info(struct seq_file *m, + struct drm_i915_private *dev_priv, + struct i915_guc_client *client) +{ + struct intel_engine_cs *ring; + uint64_t tot = 0; + uint32_t i; + + seq_printf(m, "\tPriority %d, GuC ctx index: %u, PD offset 0x%x\n", + client->priority, client->ctx_index, client->proc_desc_offset); + seq_printf(m, "\tDoorbell id %d, offset: 0x%x, cookie 0x%x\n", + client->doorbell_id, client->doorbell_offset, client->cookie); + seq_printf(m, "\tWQ size %d, offset: 0x%x, tail %d\n", + client->wq_size, client->wq_offset, client->wq_tail); + + seq_printf(m, "\tFailed to queue: %u\n", client->q_fail); + seq_printf(m, "\tFailed doorbell: %u\n", client->b_fail); + seq_printf(m, "\tLast submission result: %d\n", client->retcode); + + for_each_ring(ring, dev_priv, i) { + seq_printf(m, "\tSubmissions: %llu %s\n", + client->submissions[i], + ring->name); + tot += client->submissions[i]; + } + seq_printf(m, "\tTotal: %llu\n", tot); +} + +static int i915_guc_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct drm_device *dev = node->minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc guc; + struct i915_guc_client client = {}; + struct intel_engine_cs *ring; + enum intel_ring_id i; + u64 total = 0; + + if (!HAS_GUC_SCHED(dev_priv->dev)) + return 0; + + /* Take a local copy of the GuC data, so we can dump it at leisure */ + spin_lock(&dev_priv->guc.host2guc_lock); + guc = dev_priv->guc; + if (guc.execbuf_client) { + spin_lock(&guc.execbuf_client->wq_lock); + client = *guc.execbuf_client; + spin_unlock(&guc.execbuf_client->wq_lock); + } + spin_unlock(&dev_priv->guc.host2guc_lock); + + seq_printf(m, "GuC total action count: %llu\n", guc.action_count); + seq_printf(m, "GuC action failure count: %u\n", guc.action_fail); + seq_printf(m, "GuC last action command: 0x%x\n", guc.action_cmd); + seq_printf(m, "GuC last action status: 0x%x\n", guc.action_status); + seq_printf(m, "GuC last action error code: %d\n", guc.action_err); + + seq_printf(m, "\nGuC submissions:\n"); + for_each_ring(ring, dev_priv, i) { + seq_printf(m, "\t%-24s: %10llu, last seqno 0x%08x %9d\n", + ring->name, guc.submissions[i], + guc.last_seqno[i], guc.last_seqno[i]); + total += guc.submissions[i]; + } + seq_printf(m, "\t%s: %llu\n", "Total", total); + + seq_printf(m, "\nGuC execbuf client @ %p:\n", guc.execbuf_client); + i915_guc_client_info(m, dev_priv, &client); + + /* Add more as required ... */ + + return 0; +} + +static int i915_guc_log_dump(struct seq_file *m, void *data) +{ + struct drm_info_node *node = m->private; + struct drm_device *dev = node->minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_object *log_obj = dev_priv->guc.log_obj; + u32 *log; + int i = 0, pg; + + if (!log_obj) + return 0; + + for (pg = 0; pg < log_obj->base.size / PAGE_SIZE; pg++) { + log = kmap_atomic(i915_gem_object_get_page(log_obj, pg)); + + for (i = 0; i < PAGE_SIZE / sizeof(u32); i += 4) + seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n", + *(log + i), *(log + i + 1), + *(log + i + 2), *(log + i + 3)); + + kunmap_atomic(log); + } + + seq_putc(m, '\n'); + + return 0; +} + static int i915_edp_psr_status(struct seq_file *m, void *data) { struct drm_info_node *node = m->private; @@ -2679,11 +2830,13 @@ static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc) struct drm_device *dev = node->minor->dev; struct drm_crtc *crtc = &intel_crtc->base; struct intel_encoder *intel_encoder; + struct drm_plane_state *plane_state = crtc->primary->state; + struct drm_framebuffer *fb = plane_state->fb; - if (crtc->primary->fb) + if (fb) seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n", - crtc->primary->fb->base.id, crtc->x, crtc->y, - crtc->primary->fb->width, crtc->primary->fb->height); + fb->base.id, plane_state->src_x >> 16, + plane_state->src_y >> 16, fb->width, fb->height); else seq_puts(m, "\tprimary plane disabled\n"); for_each_encoder_on_crtc(dev, crtc, intel_encoder) @@ -2705,8 +2858,7 @@ static void intel_dp_info(struct seq_file *m, struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base); seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]); - seq_printf(m, "\taudio support: %s\n", intel_dp->has_audio ? "yes" : - "no"); + seq_printf(m, "\taudio support: %s\n", yesno(intel_dp->has_audio)); if (intel_encoder->type == INTEL_OUTPUT_EDP) intel_panel_info(m, &intel_connector->panel); } @@ -2717,8 +2869,7 @@ static void intel_hdmi_info(struct seq_file *m, struct intel_encoder *intel_encoder = intel_connector->encoder; struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base); - seq_printf(m, "\taudio support: %s\n", intel_hdmi->has_audio ? "yes" : - "no"); + seq_printf(m, "\taudio support: %s\n", yesno(intel_hdmi->has_audio)); } static void intel_lvds_info(struct seq_file *m, @@ -2768,7 +2919,7 @@ static bool cursor_active(struct drm_device *dev, int pipe) u32 state; if (IS_845G(dev) || IS_I865G(dev)) - state = I915_READ(_CURACNTR) & CURSOR_ENABLE; + state = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE; else state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; @@ -3006,7 +3157,7 @@ static int i915_ddb_info(struct seq_file *m, void *unused) skl_ddb_entry_size(entry)); } - entry = &ddb->cursor[pipe]; + entry = &ddb->plane[pipe][PLANE_CURSOR]; seq_printf(m, " %-13s%8u%8u%8u\n", "Cursor", entry->start, entry->end, skl_ddb_entry_size(entry)); } @@ -4806,7 +4957,7 @@ static void cherryview_sseu_device_status(struct drm_device *dev, struct sseu_dev_status *stat) { struct drm_i915_private *dev_priv = dev->dev_private; - const int ss_max = 2; + int ss_max = 2; int ss; u32 sig1[ss_max], sig2[ss_max]; @@ -4899,13 +5050,38 @@ static void gen9_sseu_device_status(struct drm_device *dev, } } +static void broadwell_sseu_device_status(struct drm_device *dev, + struct sseu_dev_status *stat) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int s; + u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO); + + stat->slice_total = hweight32(slice_info & GEN8_LSLICESTAT_MASK); + + if (stat->slice_total) { + stat->subslice_per_slice = INTEL_INFO(dev)->subslice_per_slice; + stat->subslice_total = stat->slice_total * + stat->subslice_per_slice; + stat->eu_per_subslice = INTEL_INFO(dev)->eu_per_subslice; + stat->eu_total = stat->eu_per_subslice * stat->subslice_total; + + /* subtract fused off EU(s) from enabled slice(s) */ + for (s = 0; s < stat->slice_total; s++) { + u8 subslice_7eu = INTEL_INFO(dev)->subslice_7eu[s]; + + stat->eu_total -= hweight8(subslice_7eu); + } + } +} + static int i915_sseu_status(struct seq_file *m, void *unused) { struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; struct sseu_dev_status stat; - if ((INTEL_INFO(dev)->gen < 8) || IS_BROADWELL(dev)) + if (INTEL_INFO(dev)->gen < 8) return -ENODEV; seq_puts(m, "SSEU Device Info\n"); @@ -4930,6 +5106,8 @@ static int i915_sseu_status(struct seq_file *m, void *unused) memset(&stat, 0, sizeof(stat)); if (IS_CHERRYVIEW(dev)) { cherryview_sseu_device_status(dev, &stat); + } else if (IS_BROADWELL(dev)) { + broadwell_sseu_device_status(dev, &stat); } else if (INTEL_INFO(dev)->gen >= 9) { gen9_sseu_device_status(dev, &stat); } @@ -5032,6 +5210,9 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gem_hws_bsd", i915_hws_info, 0, (void *)VCS}, {"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS}, {"i915_gem_batch_pool", i915_gem_batch_pool_info, 0}, + {"i915_guc_info", i915_guc_info, 0}, + {"i915_guc_load_status", i915_guc_load_status_info, 0}, + {"i915_guc_log_dump", i915_guc_log_dump, 0}, {"i915_frequency_info", i915_frequency_info, 0}, {"i915_hangcheck_info", i915_hangcheck_info, 0}, {"i915_drpc_info", i915_drpc_info, 0}, diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 68b0c9e..2336af9 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -335,12 +335,12 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_ dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; /* i915 resume handler doesn't set to D0 */ pci_set_power_state(dev->pdev, PCI_D0); - i915_resume_legacy(dev); + i915_resume_switcheroo(dev); dev->switch_power_state = DRM_SWITCH_POWER_ON; } else { pr_err("switched off\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; - i915_suspend_legacy(dev, pmm); + i915_suspend_switcheroo(dev, pmm); dev->switch_power_state = DRM_SWITCH_POWER_OFF; } } @@ -406,6 +406,11 @@ static int i915_load_modeset_init(struct drm_device *dev) * working irqs for e.g. gmbus and dp aux transfers. */ intel_modeset_init(dev); + /* intel_guc_ucode_init() needs the mutex to allocate GEM objects */ + mutex_lock(&dev->struct_mutex); + intel_guc_ucode_init(dev); + mutex_unlock(&dev->struct_mutex); + ret = i915_gem_init(dev); if (ret) goto cleanup_irq; @@ -447,6 +452,9 @@ cleanup_gem: i915_gem_context_fini(dev); mutex_unlock(&dev->struct_mutex); cleanup_irq: + mutex_lock(&dev->struct_mutex); + intel_guc_ucode_fini(dev); + mutex_unlock(&dev->struct_mutex); drm_irq_uninstall(dev); cleanup_gem_stolen: i915_gem_cleanup_stolen(dev); @@ -594,17 +602,6 @@ static void gen9_sseu_info_init(struct drm_device *dev) u32 fuse2, s_enable, ss_disable, eu_disable; u8 eu_mask = 0xff; - /* - * BXT has a single slice. BXT also has at most 6 EU per subslice, - * and therefore only the lowest 6 bits of the 8-bit EU disable - * fields are valid. - */ - if (IS_BROXTON(dev)) { - s_max = 1; - eu_max = 6; - eu_mask = 0x3f; - } - info = (struct intel_device_info *)&dev_priv->info; fuse2 = I915_READ(GEN8_FUSE2); s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >> @@ -676,6 +673,82 @@ static void gen9_sseu_info_init(struct drm_device *dev) info->has_eu_pg = (info->eu_per_subslice > 2); } +static void broadwell_sseu_info_init(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_device_info *info; + const int s_max = 3, ss_max = 3, eu_max = 8; + int s, ss; + u32 fuse2, eu_disable[s_max], s_enable, ss_disable; + + fuse2 = I915_READ(GEN8_FUSE2); + s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT; + ss_disable = (fuse2 & GEN8_F2_SS_DIS_MASK) >> GEN8_F2_SS_DIS_SHIFT; + + eu_disable[0] = I915_READ(GEN8_EU_DISABLE0) & GEN8_EU_DIS0_S0_MASK; + eu_disable[1] = (I915_READ(GEN8_EU_DISABLE0) >> GEN8_EU_DIS0_S1_SHIFT) | + ((I915_READ(GEN8_EU_DISABLE1) & GEN8_EU_DIS1_S1_MASK) << + (32 - GEN8_EU_DIS0_S1_SHIFT)); + eu_disable[2] = (I915_READ(GEN8_EU_DISABLE1) >> GEN8_EU_DIS1_S2_SHIFT) | + ((I915_READ(GEN8_EU_DISABLE2) & GEN8_EU_DIS2_S2_MASK) << + (32 - GEN8_EU_DIS1_S2_SHIFT)); + + + info = (struct intel_device_info *)&dev_priv->info; + info->slice_total = hweight32(s_enable); + + /* + * The subslice disable field is global, i.e. it applies + * to each of the enabled slices. + */ + info->subslice_per_slice = ss_max - hweight32(ss_disable); + info->subslice_total = info->slice_total * info->subslice_per_slice; + + /* + * Iterate through enabled slices and subslices to + * count the total enabled EU. + */ + for (s = 0; s < s_max; s++) { + if (!(s_enable & (0x1 << s))) + /* skip disabled slice */ + continue; + + for (ss = 0; ss < ss_max; ss++) { + u32 n_disabled; + + if (ss_disable & (0x1 << ss)) + /* skip disabled subslice */ + continue; + + n_disabled = hweight8(eu_disable[s] >> (ss * eu_max)); + + /* + * Record which subslices have 7 EUs. + */ + if (eu_max - n_disabled == 7) + info->subslice_7eu[s] |= 1 << ss; + + info->eu_total += eu_max - n_disabled; + } + } + + /* + * BDW is expected to always have a uniform distribution of EU across + * subslices with the exception that any one EU in any one subslice may + * be fused off for die recovery. + */ + info->eu_per_subslice = info->subslice_total ? + DIV_ROUND_UP(info->eu_total, info->subslice_total) : 0; + + /* + * BDW supports slice power gating on devices with more than + * one slice. + */ + info->has_slice_pg = (info->slice_total > 1); + info->has_subslice_pg = 0; + info->has_eu_pg = 0; +} + /* * Determine various intel_device_info fields at runtime. * @@ -746,6 +819,8 @@ static void intel_device_info_runtime_init(struct drm_device *dev) /* Initialize slice/subslice/EU info */ if (IS_CHERRYVIEW(dev)) cherryview_sseu_info_init(dev); + else if (IS_BROADWELL(dev)) + broadwell_sseu_info_init(dev); else if (INTEL_INFO(dev)->gen >= 9) gen9_sseu_info_init(dev); @@ -762,6 +837,24 @@ static void intel_device_info_runtime_init(struct drm_device *dev) info->has_eu_pg ? "y" : "n"); } +static void intel_init_dpio(struct drm_i915_private *dev_priv) +{ + if (!IS_VALLEYVIEW(dev_priv)) + return; + + /* + * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C), + * CHV x1 PHY (DP/HDMI D) + * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C) + */ + if (IS_CHERRYVIEW(dev_priv)) { + DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2; + DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO; + } else { + DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO; + } +} + /** * i915_driver_load - setup chip and create an initial config * @dev: DRM device @@ -803,6 +896,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) mutex_init(&dev_priv->sb_lock); mutex_init(&dev_priv->modeset_restore_lock); mutex_init(&dev_priv->csr_lock); + mutex_init(&dev_priv->av_mutex); intel_pm_setup(dev); @@ -942,8 +1036,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) intel_setup_gmbus(dev); intel_opregion_setup(dev); - intel_setup_bios(dev); - i915_gem_load(dev); /* On the 945G/GM, the chipset reports the MSI capability on the @@ -962,6 +1054,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) intel_device_info_runtime_init(dev); + intel_init_dpio(dev_priv); + if (INTEL_INFO(dev)->num_pipes) { ret = drm_vblank_init(dev, INTEL_INFO(dev)->num_pipes); if (ret) @@ -1030,12 +1124,9 @@ out_freecsr: put_bridge: pci_dev_put(dev_priv->bridge_dev); free_priv: - if (dev_priv->requests) - kmem_cache_destroy(dev_priv->requests); - if (dev_priv->vmas) - kmem_cache_destroy(dev_priv->vmas); - if (dev_priv->objects) - kmem_cache_destroy(dev_priv->objects); + kmem_cache_destroy(dev_priv->requests); + kmem_cache_destroy(dev_priv->vmas); + kmem_cache_destroy(dev_priv->objects); kfree(dev_priv); return ret; } @@ -1082,6 +1173,10 @@ int i915_driver_unload(struct drm_device *dev) dev_priv->vbt.child_dev = NULL; dev_priv->vbt.child_dev_num = 0; } + kfree(dev_priv->vbt.sdvo_lvds_vbt_mode); + dev_priv->vbt.sdvo_lvds_vbt_mode = NULL; + kfree(dev_priv->vbt.lfp_lvds_vbt_mode); + dev_priv->vbt.lfp_lvds_vbt_mode = NULL; vga_switcheroo_unregister_client(dev->pdev); vga_client_register(dev->pdev, NULL, NULL, NULL); @@ -1099,6 +1194,7 @@ int i915_driver_unload(struct drm_device *dev) flush_workqueue(dev_priv->wq); mutex_lock(&dev->struct_mutex); + intel_guc_ucode_fini(dev); i915_gem_cleanup_ringbuffer(dev); i915_gem_context_fini(dev); mutex_unlock(&dev->struct_mutex); @@ -1121,13 +1217,9 @@ int i915_driver_unload(struct drm_device *dev) if (dev_priv->regs != NULL) pci_iounmap(dev->pdev, dev_priv->regs); - if (dev_priv->requests) - kmem_cache_destroy(dev_priv->requests); - if (dev_priv->vmas) - kmem_cache_destroy(dev_priv->vmas); - if (dev_priv->objects) - kmem_cache_destroy(dev_priv->objects); - + kmem_cache_destroy(dev_priv->requests); + kmem_cache_destroy(dev_priv->vmas); + kmem_cache_destroy(dev_priv->objects); pci_dev_put(dev_priv->bridge_dev); kfree(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index ab64d68..760e0ce 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -362,6 +362,7 @@ static const struct intel_device_info intel_skylake_info = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, .has_llc = 1, .has_ddi = 1, + .has_fpga_dbg = 1, .has_fbc = 1, GEN_DEFAULT_PIPEOFFSETS, IVB_CURSOR_OFFSETS, @@ -374,6 +375,7 @@ static const struct intel_device_info intel_skylake_gt3_info = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, .has_llc = 1, .has_ddi = 1, + .has_fpga_dbg = 1, .has_fbc = 1, GEN_DEFAULT_PIPEOFFSETS, IVB_CURSOR_OFFSETS, @@ -386,6 +388,7 @@ static const struct intel_device_info intel_broxton_info = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, .num_pipes = 3, .has_ddi = 1, + .has_fpga_dbg = 1, .has_fbc = 1, GEN_DEFAULT_PIPEOFFSETS, IVB_CURSOR_OFFSETS, @@ -440,6 +443,34 @@ static const struct pci_device_id pciidlist[] = { /* aka */ MODULE_DEVICE_TABLE(pci, pciidlist); +static enum intel_pch intel_virt_detect_pch(struct drm_device *dev) +{ + enum intel_pch ret = PCH_NOP; + + /* + * In a virtualized passthrough environment we can be in a + * setup where the ISA bridge is not able to be passed through. + * In this case, a south bridge can be emulated and we have to + * make an educated guess as to which PCH is really there. + */ + + if (IS_GEN5(dev)) { + ret = PCH_IBX; + DRM_DEBUG_KMS("Assuming Ibex Peak PCH\n"); + } else if (IS_GEN6(dev) || IS_IVYBRIDGE(dev)) { + ret = PCH_CPT; + DRM_DEBUG_KMS("Assuming CouarPoint PCH\n"); + } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { + ret = PCH_LPT; + DRM_DEBUG_KMS("Assuming LynxPoint PCH\n"); + } else if (IS_SKYLAKE(dev)) { + ret = PCH_SPT; + DRM_DEBUG_KMS("Assuming SunrisePoint PCH\n"); + } + + return ret; +} + void intel_detect_pch(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -500,6 +531,8 @@ void intel_detect_pch(struct drm_device *dev) dev_priv->pch_type = PCH_SPT; DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n"); WARN_ON(!IS_SKYLAKE(dev)); + } else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE) { + dev_priv->pch_type = intel_virt_detect_pch(dev); } else continue; @@ -605,6 +638,8 @@ static int i915_drm_suspend(struct drm_device *dev) return error; } + intel_guc_suspend(dev); + intel_suspend_gt_powersave(dev); /* @@ -679,7 +714,7 @@ static int i915_drm_suspend_late(struct drm_device *drm_dev, bool hibernation) return 0; } -int i915_suspend_legacy(struct drm_device *dev, pm_message_t state) +int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state) { int error; @@ -734,6 +769,8 @@ static int i915_drm_resume(struct drm_device *dev) } mutex_unlock(&dev->struct_mutex); + intel_guc_resume(dev); + intel_modeset_init_hw(dev); spin_lock_irq(&dev_priv->irq_lock); @@ -812,7 +849,7 @@ static int i915_drm_resume_early(struct drm_device *dev) return ret; } -int i915_resume_legacy(struct drm_device *dev) +int i915_resume_switcheroo(struct drm_device *dev) { int ret; @@ -1018,12 +1055,6 @@ static int skl_suspend_complete(struct drm_i915_private *dev_priv) { /* Enabling DC6 is not a hard requirement to enter runtime D3 */ - /* - * This is to ensure that CSR isn't identified as loaded before - * CSR-loading program is called during runtime-resume. - */ - intel_csr_load_status_set(dev_priv, FW_UNINITIALIZED); - skl_uninit_cdclk(dev_priv); return 0; @@ -1117,7 +1148,7 @@ static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv) s->gfx_pend_tlb1 = I915_READ(GEN7_GFX_PEND_TLB1); for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++) - s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4); + s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS(i)); s->media_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); s->gfx_max_req_count = I915_READ(GEN7_GFX_MAX_REQ_COUNT); @@ -1161,7 +1192,7 @@ static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv) s->pm_ier = I915_READ(GEN6_PMIER); for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++) - s->gt_scratch[i] = I915_READ(GEN7_GT_SCRATCH_BASE + i * 4); + s->gt_scratch[i] = I915_READ(GEN7_GT_SCRATCH(i)); /* GT SA CZ domain, 0x100000-0x138124 */ s->tilectl = I915_READ(TILECTL); @@ -1199,7 +1230,7 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv) I915_WRITE(GEN7_GFX_PEND_TLB1, s->gfx_pend_tlb1); for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++) - I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]); + I915_WRITE(GEN7_LRA_LIMITS(i), s->lra_limits[i]); I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count); I915_WRITE(GEN7_GFX_MAX_REQ_COUNT, s->gfx_max_req_count); @@ -1243,7 +1274,7 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv) I915_WRITE(GEN6_PMIER, s->pm_ier); for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++) - I915_WRITE(GEN7_GT_SCRATCH_BASE + i * 4, s->gt_scratch[i]); + I915_WRITE(GEN7_GT_SCRATCH(i), s->gt_scratch[i]); /* GT SA CZ domain, 0x100000-0x138124 */ I915_WRITE(TILECTL, s->tilectl); @@ -1473,6 +1504,8 @@ static int intel_runtime_suspend(struct device *device) i915_gem_release_all_mmaps(dev_priv); mutex_unlock(&dev->struct_mutex); + intel_guc_suspend(dev); + intel_suspend_gt_powersave(dev); intel_runtime_pm_disable_interrupts(dev_priv); @@ -1532,6 +1565,8 @@ static int intel_runtime_resume(struct device *device) intel_opregion_notify_adapter(dev, PCI_D0); dev_priv->pm.suspended = false; + intel_guc_resume(dev); + if (IS_GEN6(dev_priv)) intel_init_pch_refclk(dev); @@ -1552,6 +1587,15 @@ static int intel_runtime_resume(struct device *device) gen6_update_ring_freq(dev); intel_runtime_pm_enable_interrupts(dev_priv); + + /* + * On VLV/CHV display interrupts are part of the display + * power well, so hpd is reinitialized from there. For + * everyone else do it here. + */ + if (!IS_VALLEYVIEW(dev_priv)) + intel_hpd_init(dev_priv); + intel_enable_gt_powersave(dev); if (ret) @@ -1649,7 +1693,7 @@ static struct drm_driver driver = { */ .driver_features = DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | DRIVER_PRIME | - DRIVER_RENDER, + DRIVER_RENDER | DRIVER_MODESET, .load = i915_driver_load, .unload = i915_driver_unload, .open = i915_driver_open, @@ -1658,10 +1702,6 @@ static struct drm_driver driver = { .postclose = i915_driver_postclose, .set_busid = drm_pci_set_busid, - /* Used in place of i915_pm_ops for non-DRIVER_MODESET */ - .suspend = i915_suspend_legacy, - .resume = i915_resume_legacy, - #if defined(CONFIG_DEBUG_FS) .debugfs_init = i915_debugfs_init, .debugfs_cleanup = i915_debugfs_cleanup, @@ -1704,7 +1744,6 @@ static int __init i915_init(void) * either the i915.modeset prarameter or by the * vga_text_mode_force boot option. */ - driver.driver_features |= DRIVER_MODESET; if (i915.modeset == 0) driver.driver_features &= ~DRIVER_MODESET; @@ -1715,18 +1754,12 @@ static int __init i915_init(void) #endif if (!(driver.driver_features & DRIVER_MODESET)) { - driver.get_vblank_timestamp = NULL; /* Silently fail loading to not upset userspace. */ DRM_DEBUG_DRIVER("KMS and UMS disabled.\n"); return 0; } - /* - * FIXME: Note that we're lying to the DRM core here so that we can get access - * to the atomic ioctl and the atomic properties. Only plane operations on - * a single CRTC will actually work. - */ - if (driver.driver_features & DRIVER_MODESET) + if (i915.nuclear_pageflip) driver.driver_features |= DRIVER_ATOMIC; return drm_pci_init(&driver, &i915_pci_driver); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9e13a77..5adba06 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -50,13 +50,14 @@ #include <linux/intel-iommu.h> #include <linux/kref.h> #include <linux/pm_qos.h> +#include "intel_guc.h" /* General customization: */ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20150731" +#define DRIVER_DATE "20151010" #undef WARN_ON /* Many gcc seem to no see through this and fall over :( */ @@ -67,11 +68,11 @@ BUILD_BUG_ON(__i915_warn_cond); \ WARN(__i915_warn_cond, "WARN_ON(" #x ")"); }) #else -#define WARN_ON(x) WARN((x), "WARN_ON(" #x ")") +#define WARN_ON(x) WARN((x), "WARN_ON(%s)", #x ) #endif #undef WARN_ON_ONCE -#define WARN_ON_ONCE(x) WARN_ONCE((x), "WARN_ON_ONCE(" #x ")") +#define WARN_ON_ONCE(x) WARN_ONCE((x), "WARN_ON_ONCE(%s)", #x ) #define MISSING_CASE(x) WARN(1, "Missing switch case (%lu) in %s\n", \ (long) (x), __func__); @@ -105,6 +106,11 @@ unlikely(__ret_warn_on); \ }) +static inline const char *yesno(bool v) +{ + return v ? "yes" : "no"; +} + enum pipe { INVALID_PIPE = -1, PIPE_A = 0, @@ -125,17 +131,17 @@ enum transcoder { #define transcoder_name(t) ((t) + 'A') /* - * This is the maximum (across all platforms) number of planes (primary + - * sprites) that can be active at the same time on one pipe. - * - * This value doesn't count the cursor plane. + * I915_MAX_PLANES in the enum below is the maximum (across all platforms) + * number of planes per CRTC. Not all platforms really have this many planes, + * which means some arrays of size I915_MAX_PLANES may have unused entries + * between the topmost sprite plane and the cursor plane. */ -#define I915_MAX_PLANES 4 - enum plane { PLANE_A = 0, PLANE_B, PLANE_C, + PLANE_CURSOR, + I915_MAX_PLANES, }; #define plane_name(p) ((p) + 'A') @@ -549,7 +555,7 @@ struct drm_i915_error_state { struct drm_i915_error_object { int page_count; - u32 gtt_offset; + u64 gtt_offset; u32 *pages[0]; } *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page; @@ -575,7 +581,7 @@ struct drm_i915_error_state { u32 size; u32 name; u32 rseqno[I915_NUM_RINGS], wseqno; - u32 gtt_offset; + u64 gtt_offset; u32 read_domains; u32 write_domain; s32 fence_reg:I915_MAX_NUM_FENCE_BITS; @@ -622,10 +628,6 @@ struct drm_i915_display_funcs { struct dpll *match_clock, struct dpll *best_clock); void (*update_wm)(struct drm_crtc *crtc); - void (*update_sprite_wm)(struct drm_plane *plane, - struct drm_crtc *crtc, - uint32_t sprite_width, uint32_t sprite_height, - int pixel_size, bool enable, bool scaled); int (*modeset_calc_cdclk)(struct drm_atomic_state *state); void (*modeset_commit_cdclk)(struct drm_atomic_state *state); /* Returns the active state of the crtc, and if the crtc is active, @@ -640,7 +642,7 @@ struct drm_i915_display_funcs { void (*crtc_disable)(struct drm_crtc *crtc); void (*audio_codec_enable)(struct drm_connector *connector, struct intel_encoder *encoder, - struct drm_display_mode *mode); + const struct drm_display_mode *adjusted_mode); void (*audio_codec_disable)(struct intel_encoder *encoder); void (*fdi_link_train)(struct drm_crtc *crtc); void (*init_clock_gating)(struct drm_device *dev); @@ -658,13 +660,6 @@ struct drm_i915_display_funcs { /* render clock increase/decrease */ /* display clock increase/decrease */ /* pll clock increase/decrease */ - - int (*setup_backlight)(struct intel_connector *connector, enum pipe pipe); - uint32_t (*get_backlight)(struct intel_connector *connector); - void (*set_backlight)(struct intel_connector *connector, - uint32_t level); - void (*disable_backlight)(struct intel_connector *connector); - void (*enable_backlight)(struct intel_connector *connector); }; enum forcewake_domain_id { @@ -882,7 +877,6 @@ struct intel_context { } legacy_hw_ctx; /* Execlists */ - bool rcs_initialized; struct { struct drm_i915_gem_object *state; struct intel_ringbuffer *ringbuf; @@ -941,6 +935,9 @@ struct i915_fbc { FBC_CHIP_DEFAULT, /* disabled by default on this chip */ FBC_ROTATION, /* rotation is not supported */ FBC_IN_DBG_MASTER, /* kernel debugger is active */ + FBC_BAD_STRIDE, /* stride is not supported */ + FBC_PIXEL_RATE, /* pixel rate is too big */ + FBC_PIXEL_FORMAT /* pixel format is invalid */ } no_fbc_reason; bool (*fbc_enabled)(struct drm_i915_private *dev_priv); @@ -1136,7 +1133,6 @@ struct intel_gen6_power_mgmt { u8 efficient_freq; /* AKA RPe. Pre-determined balanced frequency */ u8 rp1_freq; /* "less than" RP0 power/freqency */ u8 rp0_freq; /* Non-overclocked max frequency. */ - u32 cz_freq; u8 up_threshold; /* Current %busy required to uplock */ u8 down_threshold; /* Current %busy required to downclock */ @@ -1578,8 +1574,7 @@ static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1, struct skl_ddb_allocation { struct skl_ddb_entry pipe[I915_MAX_PIPES]; struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* packed/uv */ - struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES]; /* y-plane */ - struct skl_ddb_entry cursor[I915_MAX_PIPES]; + struct skl_ddb_entry y_plane[I915_MAX_PIPES][I915_MAX_PLANES]; }; struct skl_wm_values { @@ -1587,18 +1582,13 @@ struct skl_wm_values { struct skl_ddb_allocation ddb; uint32_t wm_linetime[I915_MAX_PIPES]; uint32_t plane[I915_MAX_PIPES][I915_MAX_PLANES][8]; - uint32_t cursor[I915_MAX_PIPES][8]; uint32_t plane_trans[I915_MAX_PIPES][I915_MAX_PLANES]; - uint32_t cursor_trans[I915_MAX_PIPES]; }; struct skl_wm_level { bool plane_en[I915_MAX_PLANES]; - bool cursor_en; uint16_t plane_res_b[I915_MAX_PLANES]; uint8_t plane_res_l[I915_MAX_PLANES]; - uint16_t cursor_res_b; - uint8_t cursor_res_l; }; /* @@ -1693,7 +1683,7 @@ struct i915_execbuffer_params { struct drm_file *file; uint32_t dispatch_flags; uint32_t args_batch_start_offset; - uint32_t batch_obj_vm_offset; + uint64_t batch_obj_vm_offset; struct intel_engine_cs *ring; struct drm_i915_gem_object *batch_obj; struct intel_context *ctx; @@ -1716,6 +1706,8 @@ struct drm_i915_private { struct i915_virtual_gpu vgpu; + struct intel_guc guc; + struct intel_csr csr; /* Display CSR-related protection */ @@ -1795,7 +1787,9 @@ struct drm_i915_private { unsigned int fsb_freq, mem_freq, is_ddr3; unsigned int skl_boot_cdclk; unsigned int cdclk_freq, max_cdclk_freq; + unsigned int max_dotclk_freq; unsigned int hpll_freq; + unsigned int czclk_freq; /** * wq - Driver workqueue for GEM. @@ -1884,6 +1878,11 @@ struct drm_i915_private { /* hda/i915 audio component */ struct i915_audio_component *audio_component; bool audio_component_registered; + /** + * av_mutex - mutex for audio/video sync + * + */ + struct mutex av_mutex; uint32_t hw_context_size; struct list_head context_list; @@ -1946,6 +1945,9 @@ struct drm_i915_private { bool edp_low_vswing; + /* perform PHY state sanity checks? */ + bool chv_phy_assert[2]; + /* * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch * will be rejected. Instead look for a better place. @@ -1962,6 +1964,11 @@ static inline struct drm_i915_private *dev_to_i915(struct device *dev) return to_i915(dev_get_drvdata(dev)); } +static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc) +{ + return container_of(guc, struct drm_i915_private, guc); +} + /* Iterate over initialised rings */ #define for_each_ring(ring__, dev_priv__, i__) \ for ((i__) = 0; (i__) < I915_NUM_RINGS; (i__)++) \ @@ -1998,25 +2005,26 @@ struct drm_i915_gem_object_ops { /* * Frontbuffer tracking bits. Set in obj->frontbuffer_bits while a gem bo is - * considered to be the frontbuffer for the given plane interface-vise. This + * considered to be the frontbuffer for the given plane interface-wise. This * doesn't mean that the hw necessarily already scans it out, but that any * rendering (by the cpu or gpu) will land in the frontbuffer eventually. * * We have one bit per pipe and per scanout plane type. */ -#define INTEL_FRONTBUFFER_BITS_PER_PIPE 4 +#define INTEL_MAX_SPRITE_BITS_PER_PIPE 5 +#define INTEL_FRONTBUFFER_BITS_PER_PIPE 8 #define INTEL_FRONTBUFFER_BITS \ (INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES) #define INTEL_FRONTBUFFER_PRIMARY(pipe) \ (1 << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))) #define INTEL_FRONTBUFFER_CURSOR(pipe) \ - (1 << (1 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))) -#define INTEL_FRONTBUFFER_SPRITE(pipe) \ - (1 << (2 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))) + (1 << (1 + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))) +#define INTEL_FRONTBUFFER_SPRITE(pipe, plane) \ + (1 << (2 + plane + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))) #define INTEL_FRONTBUFFER_OVERLAY(pipe) \ - (1 << (3 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))) + (1 << (2 + INTEL_MAX_SPRITE_BITS_PER_PIPE + (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))) #define INTEL_FRONTBUFFER_ALL_MASK(pipe) \ - (0xf << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))) + (0xff << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))) struct drm_i915_gem_object { struct drm_gem_object base; @@ -2474,6 +2482,11 @@ struct drm_i915_cmd_table { #define IS_SKL_ULX(dev) (INTEL_DEVID(dev) == 0x190E || \ INTEL_DEVID(dev) == 0x1915 || \ INTEL_DEVID(dev) == 0x191E) +#define IS_SKL_GT3(dev) (IS_SKYLAKE(dev) && \ + (INTEL_DEVID(dev) & 0x00F0) == 0x0020) +#define IS_SKL_GT4(dev) (IS_SKYLAKE(dev) && \ + (INTEL_DEVID(dev) & 0x00F0) == 0x0030) + #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary) #define SKL_REVID_A0 (0x0) @@ -2485,7 +2498,7 @@ struct drm_i915_cmd_table { #define BXT_REVID_A0 (0x0) #define BXT_REVID_B0 (0x3) -#define BXT_REVID_C0 (0x6) +#define BXT_REVID_C0 (0x9) /* * The genX designation typically refers to the render engine, so render @@ -2519,7 +2532,8 @@ struct drm_i915_cmd_table { #define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 6) #define HAS_LOGICAL_RING_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 8) #define USES_PPGTT(dev) (i915.enable_ppgtt) -#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt == 2) +#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt >= 2) +#define USES_FULL_48BIT_PPGTT(dev) (i915.enable_ppgtt == 3) #define HAS_OVERLAY(dev) (INTEL_INFO(dev)->has_overlay) #define OVERLAY_NEEDS_PHYSICAL(dev) (INTEL_INFO(dev)->overlay_needs_physical) @@ -2563,7 +2577,10 @@ struct drm_i915_cmd_table { #define HAS_RC6(dev) (INTEL_INFO(dev)->gen >= 6) #define HAS_RC6p(dev) (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev)) -#define HAS_CSR(dev) (IS_SKYLAKE(dev)) +#define HAS_CSR(dev) (IS_GEN9(dev)) + +#define HAS_GUC_UCODE(dev) (IS_GEN9(dev)) +#define HAS_GUC_SCHED(dev) (IS_GEN9(dev)) #define HAS_RESOURCE_STREAMER(dev) (IS_HASWELL(dev) || \ INTEL_INFO(dev)->gen >= 8) @@ -2579,10 +2596,12 @@ struct drm_i915_cmd_table { #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE 0x9c00 #define INTEL_PCH_SPT_DEVICE_ID_TYPE 0xA100 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE 0x9D00 +#define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type) #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT) #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT) +#define HAS_PCH_LPT_LP(dev) (__I915__(dev)->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) #define HAS_PCH_CPT(dev) (INTEL_PCH_TYPE(dev) == PCH_CPT) #define HAS_PCH_IBX(dev) (INTEL_PCH_TYPE(dev) == PCH_IBX) #define HAS_PCH_NOP(dev) (INTEL_PCH_TYPE(dev) == PCH_NOP) @@ -2602,8 +2621,8 @@ struct drm_i915_cmd_table { extern const struct drm_ioctl_desc i915_ioctls[]; extern int i915_max_ioctl; -extern int i915_suspend_legacy(struct drm_device *dev, pm_message_t state); -extern int i915_resume_legacy(struct drm_device *dev); +extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state); +extern int i915_resume_switcheroo(struct drm_device *dev); /* i915_params.c */ struct i915_params { @@ -2625,7 +2644,6 @@ struct i915_params { int enable_cmd_parser; /* leave bools at the end to not create holes */ bool enable_hangcheck; - bool fastboot; bool prefault_disable; bool load_detect_test; bool reset; @@ -2636,6 +2654,7 @@ struct i915_params { int use_mmio_flip; int mmio_debug; bool verbose_state_checks; + bool nuclear_pageflip; int edp_vswing; }; extern struct i915_params i915 __read_mostly; @@ -2715,6 +2734,9 @@ i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe, void valleyview_enable_display_irqs(struct drm_i915_private *dev_priv); void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv); +void i915_hotplug_interrupt_update(struct drm_i915_private *dev_priv, + uint32_t mask, + uint32_t bits); void ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask); void @@ -2782,8 +2804,6 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, size_t size); struct drm_i915_gem_object *i915_gem_object_create_from_data( struct drm_device *dev, const void *data, size_t size); -void i915_init_vm(struct drm_i915_private *dev_priv, - struct i915_address_space *vm); void i915_gem_free_object(struct drm_gem_object *obj); void i915_gem_vma_destroy(struct i915_vma *vma); @@ -2794,6 +2814,8 @@ void i915_gem_vma_destroy(struct i915_vma *vma); #define PIN_OFFSET_BIAS (1<<3) #define PIN_USER (1<<4) #define PIN_UPDATE (1<<5) +#define PIN_ZONE_4G (1<<6) +#define PIN_HIGH (1<<7) #define PIN_OFFSET_MASK (~4095) int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj, @@ -2809,6 +2831,11 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, u32 flags); int __must_check i915_vma_unbind(struct i915_vma *vma); +/* + * BEWARE: Do not use the function below unless you can _absolutely_ + * _guarantee_ VMA in question is _not in use_ anywhere. + */ +int __must_check __i915_vma_unbind_no_wait(struct i915_vma *vma); int i915_gem_object_put_pages(struct drm_i915_gem_object *obj); void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv); void i915_gem_release_mmap(struct drm_i915_gem_object *obj); @@ -2985,13 +3012,11 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, struct dma_buf *i915_gem_prime_export(struct drm_device *dev, struct drm_gem_object *gem_obj, int flags); -unsigned long -i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o, - const struct i915_ggtt_view *view); -unsigned long -i915_gem_obj_offset(struct drm_i915_gem_object *o, - struct i915_address_space *vm); -static inline unsigned long +u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o, + const struct i915_ggtt_view *view); +u64 i915_gem_obj_offset(struct drm_i915_gem_object *o, + struct i915_address_space *vm); +static inline u64 i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o) { return i915_gem_obj_ggtt_offset_view(o, &i915_ggtt_view_normal); @@ -3139,7 +3164,6 @@ int __must_check i915_gem_evict_something(struct drm_device *dev, unsigned long end, unsigned flags); int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); -int i915_gem_evict_everything(struct drm_device *dev); /* belongs in i915_gem_gtt.h */ static inline void i915_gem_chipset_flush(struct drm_device *dev) @@ -3152,6 +3176,10 @@ static inline void i915_gem_chipset_flush(struct drm_device *dev) int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv, struct drm_mm_node *node, u64 size, unsigned alignment); +int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, + struct drm_mm_node *node, u64 size, + unsigned alignment, u64 start, + u64 end); void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv, struct drm_mm_node *node); int i915_gem_init_stolen(struct drm_device *dev); @@ -3166,11 +3194,12 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, /* i915_gem_shrinker.c */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, - long target, + unsigned long target, unsigned flags); #define I915_SHRINK_PURGEABLE 0x1 #define I915_SHRINK_UNBOUND 0x2 #define I915_SHRINK_BOUND 0x4 +#define I915_SHRINK_ACTIVE 0x8 unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv); void i915_gem_shrinker_init(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 4d631a9..1e67484 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1005,12 +1005,14 @@ out: if (!needs_clflush_after && obj->base.write_domain != I915_GEM_DOMAIN_CPU) { if (i915_gem_clflush_object(obj, obj->pin_display)) - i915_gem_chipset_flush(dev); + needs_clflush_after = true; } } if (needs_clflush_after) i915_gem_chipset_flush(dev); + else + obj->cache_dirty = true; intel_fb_obj_flush(obj, false, ORIGIN_CPU); return ret; @@ -1711,8 +1713,8 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, /** * i915_gem_fault - fault a page into the GTT - * vma: VMA in question - * vmf: fault info + * @vma: VMA in question + * @vmf: fault info * * The fault handler is set up by drm_gem_mmap() when a object is GTT mapped * from userspace. The fault handler takes care of binding the object to @@ -3206,7 +3208,7 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj) old_write_domain); } -int i915_vma_unbind(struct i915_vma *vma) +static int __i915_vma_unbind(struct i915_vma *vma, bool wait) { struct drm_i915_gem_object *obj = vma->obj; struct drm_i915_private *dev_priv = obj->base.dev->dev_private; @@ -3225,13 +3227,11 @@ int i915_vma_unbind(struct i915_vma *vma) BUG_ON(obj->pages == NULL); - ret = i915_gem_object_wait_rendering(obj, false); - if (ret) - return ret; - /* Continue on if we fail due to EIO, the GPU is hung so we - * should be safe and we need to cleanup or else we might - * cause memory corruption through use-after-free. - */ + if (wait) { + ret = i915_gem_object_wait_rendering(obj, false); + if (ret) + return ret; + } if (i915_is_ggtt(vma->vm) && vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) { @@ -3276,6 +3276,16 @@ int i915_vma_unbind(struct i915_vma *vma) return 0; } +int i915_vma_unbind(struct i915_vma *vma) +{ + return __i915_vma_unbind(vma, true); +} + +int __i915_vma_unbind_no_wait(struct i915_vma *vma) +{ + return __i915_vma_unbind(vma, false); +} + int i915_gpu_idle(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3355,11 +3365,10 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - u32 size, fence_size, fence_alignment, unfenced_alignment; - u64 start = - flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0; - u64 end = - flags & PIN_MAPPABLE ? dev_priv->gtt.mappable_end : vm->total; + u32 fence_alignment, unfenced_alignment; + u32 search_flag, alloc_flag; + u64 start, end; + u64 size, fence_size; struct i915_vma *vma; int ret; @@ -3399,6 +3408,13 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, size = flags & PIN_MAPPABLE ? fence_size : obj->base.size; } + start = flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0; + end = vm->total; + if (flags & PIN_MAPPABLE) + end = min_t(u64, end, dev_priv->gtt.mappable_end); + if (flags & PIN_ZONE_4G) + end = min_t(u64, end, (1ULL << 32)); + if (alignment == 0) alignment = flags & PIN_MAPPABLE ? fence_alignment : unfenced_alignment; @@ -3414,7 +3430,7 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, * attempt to find space. */ if (size > end) { - DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%u > %s aperture=%llu\n", + DRM_DEBUG("Attempting to bind an object (view type=%u) larger than the aperture: size=%llu > %s aperture=%llu\n", ggtt_view ? ggtt_view->type : 0, size, flags & PIN_MAPPABLE ? "mappable" : "total", @@ -3434,13 +3450,21 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, if (IS_ERR(vma)) goto err_unpin; + if (flags & PIN_HIGH) { + search_flag = DRM_MM_SEARCH_BELOW; + alloc_flag = DRM_MM_CREATE_TOP; + } else { + search_flag = DRM_MM_SEARCH_DEFAULT; + alloc_flag = DRM_MM_CREATE_DEFAULT; + } + search_free: ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node, size, alignment, obj->cache_level, start, end, - DRM_MM_SEARCH_DEFAULT, - DRM_MM_CREATE_DEFAULT); + search_flag, + alloc_flag); if (ret) { ret = i915_gem_evict_something(dev, vm, size, alignment, obj->cache_level, @@ -3638,10 +3662,10 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; struct i915_vma *vma, *next; - int ret; + int ret = 0; if (obj->cache_level == cache_level) - return 0; + goto out; if (i915_gem_obj_is_pinned(obj)) { DRM_DEBUG("can not change the cache level of pinned objects\n"); @@ -3686,6 +3710,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, vma->node.color = cache_level; obj->cache_level = cache_level; +out: if (obj->cache_dirty && obj->base.write_domain != I915_GEM_DOMAIN_CPU && cpu_write_needs_clflush(obj)) { @@ -3738,6 +3763,15 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data, level = I915_CACHE_NONE; break; case I915_CACHING_CACHED: + /* + * Due to a HW issue on BXT A stepping, GPU stores via a + * snooped mapping may leave stale data in a corresponding CPU + * cacheline, whereas normally such cachelines would get + * invalidated. + */ + if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) + return -ENODEV; + level = I915_CACHE_LLC; break; case I915_CACHING_DISPLAY: @@ -4011,15 +4045,13 @@ i915_gem_object_do_pin(struct drm_i915_gem_object *obj, return -EBUSY; if (i915_vma_misplaced(vma, alignment, flags)) { - unsigned long offset; - offset = ggtt_view ? i915_gem_obj_ggtt_offset_view(obj, ggtt_view) : - i915_gem_obj_offset(obj, vm); WARN(vma->pin_count, "bo is already pinned in %s with incorrect alignment:" - " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d," + " offset=%08x %08x, req.alignment=%x, req.map_and_fenceable=%d," " obj->map_and_fenceable=%d\n", ggtt_view ? "ggtt" : "ppgtt", - offset, + upper_32_bits(vma->node.start), + lower_32_bits(vma->node.start), alignment, !!(flags & PIN_MAPPABLE), obj->map_and_fenceable); @@ -4526,22 +4558,6 @@ void i915_gem_init_swizzling(struct drm_device *dev) BUG(); } -static bool -intel_enable_blt(struct drm_device *dev) -{ - if (!HAS_BLT(dev)) - return false; - - /* The blitter was dysfunctional on early prototypes */ - if (IS_GEN6(dev) && dev->pdev->revision < 8) { - DRM_INFO("BLT not supported on this pre-production hardware;" - " graphics performance will be degraded.\n"); - return false; - } - - return true; -} - static void init_unused_ring(struct drm_device *dev, u32 base) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -4584,7 +4600,7 @@ int i915_gem_init_rings(struct drm_device *dev) goto cleanup_render_ring; } - if (intel_enable_blt(dev)) { + if (HAS_BLT(dev)) { ret = intel_init_blt_ring_buffer(dev); if (ret) goto cleanup_bsd_ring; @@ -4602,14 +4618,8 @@ int i915_gem_init_rings(struct drm_device *dev) goto cleanup_vebox_ring; } - ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000)); - if (ret) - goto cleanup_bsd2_ring; - return 0; -cleanup_bsd2_ring: - intel_cleanup_ring_buffer(&dev_priv->ring[VCS2]); cleanup_vebox_ring: intel_cleanup_ring_buffer(&dev_priv->ring[VECS]); cleanup_blt_ring: @@ -4679,6 +4689,33 @@ i915_gem_init_hw(struct drm_device *dev) goto out; } + /* We can't enable contexts until all firmware is loaded */ + if (HAS_GUC_UCODE(dev)) { + ret = intel_guc_ucode_load(dev); + if (ret) { + /* + * If we got an error and GuC submission is enabled, map + * the error to -EIO so the GPU will be declared wedged. + * OTOH, if we didn't intend to use the GuC anyway, just + * discard the error and carry on. + */ + DRM_ERROR("Failed to initialize GuC, error %d%s\n", ret, + i915.enable_guc_submission ? "" : + " (ignored)"); + ret = i915.enable_guc_submission ? -EIO : 0; + if (ret) + goto out; + } + } + + /* + * Increment the next seqno by 0x100 so we have a visible break + * on re-initialisation + */ + ret = i915_gem_set_seqno(dev, dev_priv->next_seqno+0x100); + if (ret) + goto out; + /* Now it is safe to go back round and do everything else: */ for_each_ring(ring, dev_priv, i) { struct drm_i915_gem_request *req; @@ -4816,18 +4853,6 @@ init_ring_lists(struct intel_engine_cs *ring) INIT_LIST_HEAD(&ring->request_list); } -void i915_init_vm(struct drm_i915_private *dev_priv, - struct i915_address_space *vm) -{ - if (!i915_is_ggtt(vm)) - drm_mm_init(&vm->mm, vm->start, vm->total); - vm->dev = dev_priv->dev; - INIT_LIST_HEAD(&vm->active_list); - INIT_LIST_HEAD(&vm->inactive_list); - INIT_LIST_HEAD(&vm->global_link); - list_add_tail(&vm->global_link, &dev_priv->vm_list); -} - void i915_gem_load(struct drm_device *dev) { @@ -4851,8 +4876,6 @@ i915_gem_load(struct drm_device *dev) NULL); INIT_LIST_HEAD(&dev_priv->vm_list); - i915_init_vm(dev_priv, &dev_priv->gtt.base); - INIT_LIST_HEAD(&dev_priv->context_list); INIT_LIST_HEAD(&dev_priv->mm.unbound_list); INIT_LIST_HEAD(&dev_priv->mm.bound_list); @@ -4880,6 +4903,14 @@ i915_gem_load(struct drm_device *dev) dev_priv->num_fence_regs = I915_READ(vgtif_reg(avail_rs.fence_num)); + /* + * Set initial sequence number for requests. + * Using this number allows the wraparound to happen early, + * catching any obvious problems. + */ + dev_priv->next_seqno = ((u32)~0 - 0x1100); + dev_priv->last_seqno = ((u32)~0 - 0x1101); + /* Initialize fence registers to zero */ INIT_LIST_HEAD(&dev_priv->mm.fence_list); i915_gem_restore_fences(dev); @@ -4949,9 +4980,9 @@ int i915_gem_open(struct drm_device *dev, struct drm_file *file) /** * i915_gem_track_fb - update frontbuffer tracking - * old: current GEM buffer for the frontbuffer slots - * new: new GEM buffer for the frontbuffer slots - * frontbuffer_bits: bitmask of frontbuffer slots + * @old: current GEM buffer for the frontbuffer slots + * @new: new GEM buffer for the frontbuffer slots + * @frontbuffer_bits: bitmask of frontbuffer slots * * This updates the frontbuffer tracking bits @frontbuffer_bits by clearing them * from @old and setting them in @new. Both @old and @new can be NULL. @@ -4974,9 +5005,8 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old, } /* All the new VM stuff */ -unsigned long -i915_gem_obj_offset(struct drm_i915_gem_object *o, - struct i915_address_space *vm) +u64 i915_gem_obj_offset(struct drm_i915_gem_object *o, + struct i915_address_space *vm) { struct drm_i915_private *dev_priv = o->base.dev->dev_private; struct i915_vma *vma; @@ -4996,9 +5026,8 @@ i915_gem_obj_offset(struct drm_i915_gem_object *o, return -1; } -unsigned long -i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o, - const struct i915_ggtt_view *view) +u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o, + const struct i915_ggtt_view *view) { struct i915_address_space *ggtt = i915_obj_to_ggtt(o); struct i915_vma *vma; diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 8e893b3..8c688a5 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -133,6 +133,23 @@ static int get_context_size(struct drm_device *dev) return ret; } +static void i915_gem_context_clean(struct intel_context *ctx) +{ + struct i915_hw_ppgtt *ppgtt = ctx->ppgtt; + struct i915_vma *vma, *next; + + if (!ppgtt) + return; + + WARN_ON(!list_empty(&ppgtt->base.active_list)); + + list_for_each_entry_safe(vma, next, &ppgtt->base.inactive_list, + mm_list) { + if (WARN_ON(__i915_vma_unbind_no_wait(vma))) + break; + } +} + void i915_gem_context_free(struct kref *ctx_ref) { struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref); @@ -142,6 +159,13 @@ void i915_gem_context_free(struct kref *ctx_ref) if (i915.enable_execlists) intel_lr_context_free(ctx); + /* + * This context is going away and we need to remove all VMAs still + * around. This is to handle imported shared objects for which + * destructor did not run when their handles were closed. + */ + i915_gem_context_clean(ctx); + i915_ppgtt_put(ctx->ppgtt); if (ctx->legacy_hw_ctx.rcs_state) @@ -332,6 +356,13 @@ int i915_gem_context_init(struct drm_device *dev) if (WARN_ON(dev_priv->ring[RCS].default_context)) return 0; + if (intel_vgpu_active(dev) && HAS_LOGICAL_RING_CONTEXTS(dev)) { + if (!i915.enable_execlists) { + DRM_INFO("Only EXECLIST mode is supported in vgpu.\n"); + return -EINVAL; + } + } + if (i915.enable_execlists) { /* NB: intentionally left blank. We will allocate our own * backing objects as we need them, thank you very much */ diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index d09e35e..d71a133 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -237,48 +237,3 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle) return 0; } - -/** - * i915_gem_evict_everything - Try to evict all objects - * @dev: Device to evict objects for - * - * This functions tries to evict all gem objects from all address spaces. Used - * by the shrinker as a last-ditch effort and for suspend, before releasing the - * backing storage of all unbound objects. - */ -int -i915_gem_evict_everything(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_address_space *vm, *v; - bool lists_empty = true; - int ret; - - list_for_each_entry(vm, &dev_priv->vm_list, global_link) { - lists_empty = (list_empty(&vm->inactive_list) && - list_empty(&vm->active_list)); - if (!lists_empty) - lists_empty = false; - } - - if (lists_empty) - return -ENOSPC; - - trace_i915_gem_evict_everything(dev); - - /* The gpu_idle will flush everything in the write domain to the - * active list. Then we must move everything off the active list - * with retire requests. - */ - ret = i915_gpu_idle(dev); - if (ret) - return ret; - - i915_gem_retire_requests(dev); - - /* Having flushed everything, unbind() should never raise an error */ - list_for_each_entry_safe(vm, v, &dev_priv->vm_list, global_link) - WARN_ON(i915_gem_evict_vm(vm, false)); - - return 0; -} diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index a953d49..6ed7d63a 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -590,10 +590,17 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, flags |= PIN_GLOBAL; if (!drm_mm_node_allocated(&vma->node)) { + /* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, + * limit address to the first 4GBs for unflagged objects. + */ + if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0) + flags |= PIN_ZONE_4G; if (entry->flags & __EXEC_OBJECT_NEEDS_MAP) flags |= PIN_GLOBAL | PIN_MAPPABLE; if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS) flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS; + if ((flags & PIN_MAPPABLE) == 0) + flags |= PIN_HIGH; } ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, flags); @@ -671,6 +678,10 @@ eb_vma_misplaced(struct i915_vma *vma) if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable) return !only_mappable_for_reloc(entry->flags); + if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0 && + (vma->node.start + vma->node.size - 1) >> 32) + return true; + return false; } @@ -934,7 +945,21 @@ i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) if (exec->flags & __I915_EXEC_UNKNOWN_FLAGS) return false; - return ((exec->batch_start_offset | exec->batch_len) & 0x7) == 0; + /* Kernel clipping was a DRI1 misfeature */ + if (exec->num_cliprects || exec->cliprects_ptr) + return false; + + if (exec->DR4 == 0xffffffff) { + DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); + exec->DR4 = 0; + } + if (exec->DR1 || exec->DR4) + return false; + + if ((exec->batch_start_offset | exec->batch_len) & 0x7) + return false; + + return true; } static int @@ -1009,7 +1034,7 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, } if (i915.enable_execlists && !ctx->engine[ring->id].state) { - int ret = intel_lr_context_deferred_create(ctx, ring); + int ret = intel_lr_context_deferred_alloc(ctx, ring); if (ret) { DRM_DEBUG("Could not create LRC %u: %d\n", ctx_id, ret); return ERR_PTR(ret); @@ -1098,47 +1123,6 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev, return 0; } -static int -i915_emit_box(struct drm_i915_gem_request *req, - struct drm_clip_rect *box, - int DR1, int DR4) -{ - struct intel_engine_cs *ring = req->ring; - int ret; - - if (box->y2 <= box->y1 || box->x2 <= box->x1 || - box->y2 <= 0 || box->x2 <= 0) { - DRM_ERROR("Bad box %d,%d..%d,%d\n", - box->x1, box->y1, box->x2, box->y2); - return -EINVAL; - } - - if (INTEL_INFO(ring->dev)->gen >= 4) { - ret = intel_ring_begin(req, 4); - if (ret) - return ret; - - intel_ring_emit(ring, GFX_OP_DRAWRECT_INFO_I965); - intel_ring_emit(ring, (box->x1 & 0xffff) | box->y1 << 16); - intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16); - intel_ring_emit(ring, DR4); - } else { - ret = intel_ring_begin(req, 6); - if (ret) - return ret; - - intel_ring_emit(ring, GFX_OP_DRAWRECT_INFO); - intel_ring_emit(ring, DR1); - intel_ring_emit(ring, (box->x1 & 0xffff) | box->y1 << 16); - intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16); - intel_ring_emit(ring, DR4); - intel_ring_emit(ring, 0); - } - intel_ring_advance(ring); - - return 0; -} - static struct drm_i915_gem_object* i915_gem_execbuffer_parse(struct intel_engine_cs *ring, struct drm_i915_gem_exec_object2 *shadow_exec_entry, @@ -1197,65 +1181,21 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params, struct drm_i915_gem_execbuffer2 *args, struct list_head *vmas) { - struct drm_clip_rect *cliprects = NULL; struct drm_device *dev = params->dev; struct intel_engine_cs *ring = params->ring; struct drm_i915_private *dev_priv = dev->dev_private; u64 exec_start, exec_len; int instp_mode; u32 instp_mask; - int i, ret = 0; - - if (args->num_cliprects != 0) { - if (ring != &dev_priv->ring[RCS]) { - DRM_DEBUG("clip rectangles are only valid with the render ring\n"); - return -EINVAL; - } - - if (INTEL_INFO(dev)->gen >= 5) { - DRM_DEBUG("clip rectangles are only valid on pre-gen5\n"); - return -EINVAL; - } - - if (args->num_cliprects > UINT_MAX / sizeof(*cliprects)) { - DRM_DEBUG("execbuf with %u cliprects\n", - args->num_cliprects); - return -EINVAL; - } - - cliprects = kcalloc(args->num_cliprects, - sizeof(*cliprects), - GFP_KERNEL); - if (cliprects == NULL) { - ret = -ENOMEM; - goto error; - } - - if (copy_from_user(cliprects, - to_user_ptr(args->cliprects_ptr), - sizeof(*cliprects)*args->num_cliprects)) { - ret = -EFAULT; - goto error; - } - } else { - if (args->DR4 == 0xffffffff) { - DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); - args->DR4 = 0; - } - - if (args->DR1 || args->DR4 || args->cliprects_ptr) { - DRM_DEBUG("0 cliprects but dirt in cliprects fields\n"); - return -EINVAL; - } - } + int ret; ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas); if (ret) - goto error; + return ret; ret = i915_switch_context(params->request); if (ret) - goto error; + return ret; WARN(params->ctx->ppgtt && params->ctx->ppgtt->pd_dirty_rings & (1<<ring->id), "%s didn't clear reload\n", ring->name); @@ -1268,22 +1208,19 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params, case I915_EXEC_CONSTANTS_REL_SURFACE: if (instp_mode != 0 && ring != &dev_priv->ring[RCS]) { DRM_DEBUG("non-0 rel constants mode on non-RCS\n"); - ret = -EINVAL; - goto error; + return -EINVAL; } if (instp_mode != dev_priv->relative_constants_mode) { if (INTEL_INFO(dev)->gen < 4) { DRM_DEBUG("no rel constants on pre-gen4\n"); - ret = -EINVAL; - goto error; + return -EINVAL; } if (INTEL_INFO(dev)->gen > 5 && instp_mode == I915_EXEC_CONSTANTS_REL_SURFACE) { DRM_DEBUG("rel surface constants mode invalid on gen5+\n"); - ret = -EINVAL; - goto error; + return -EINVAL; } /* The HW changed the meaning on this bit on gen6 */ @@ -1293,15 +1230,14 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params, break; default: DRM_DEBUG("execbuf with unknown constants: %d\n", instp_mode); - ret = -EINVAL; - goto error; + return -EINVAL; } if (ring == &dev_priv->ring[RCS] && - instp_mode != dev_priv->relative_constants_mode) { + instp_mode != dev_priv->relative_constants_mode) { ret = intel_ring_begin(params->request, 4); if (ret) - goto error; + return ret; intel_ring_emit(ring, MI_NOOP); intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1)); @@ -1315,42 +1251,25 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params, if (args->flags & I915_EXEC_GEN7_SOL_RESET) { ret = i915_reset_gen7_sol_offsets(dev, params->request); if (ret) - goto error; + return ret; } exec_len = args->batch_len; exec_start = params->batch_obj_vm_offset + params->args_batch_start_offset; - if (cliprects) { - for (i = 0; i < args->num_cliprects; i++) { - ret = i915_emit_box(params->request, &cliprects[i], - args->DR1, args->DR4); - if (ret) - goto error; - - ret = ring->dispatch_execbuffer(params->request, - exec_start, exec_len, - params->dispatch_flags); - if (ret) - goto error; - } - } else { - ret = ring->dispatch_execbuffer(params->request, - exec_start, exec_len, - params->dispatch_flags); - if (ret) - return ret; - } + ret = ring->dispatch_execbuffer(params->request, + exec_start, exec_len, + params->dispatch_flags); + if (ret) + return ret; trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags); i915_gem_execbuffer_move_to_active(vmas, params->request); i915_gem_execbuffer_retire_commands(params); -error: - kfree(cliprects); - return ret; + return 0; } /** diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c index caa271b..40a10b2 100644 --- a/drivers/gpu/drm/i915/i915_gem_fence.c +++ b/drivers/gpu/drm/i915/i915_gem_fence.c @@ -59,19 +59,19 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, struct drm_i915_gem_object *obj) { struct drm_i915_private *dev_priv = dev->dev_private; - int fence_reg; + int fence_reg_lo, fence_reg_hi; int fence_pitch_shift; if (INTEL_INFO(dev)->gen >= 6) { - fence_reg = FENCE_REG_SANDYBRIDGE_0; - fence_pitch_shift = SANDYBRIDGE_FENCE_PITCH_SHIFT; + fence_reg_lo = FENCE_REG_GEN6_LO(reg); + fence_reg_hi = FENCE_REG_GEN6_HI(reg); + fence_pitch_shift = GEN6_FENCE_PITCH_SHIFT; } else { - fence_reg = FENCE_REG_965_0; + fence_reg_lo = FENCE_REG_965_LO(reg); + fence_reg_hi = FENCE_REG_965_HI(reg); fence_pitch_shift = I965_FENCE_PITCH_SHIFT; } - fence_reg += reg * 8; - /* To w/a incoherency with non-atomic 64-bit register updates, * we split the 64-bit update into two 32-bit writes. In order * for a partial fence not to be evaluated between writes, we @@ -81,8 +81,8 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, * For extra levels of paranoia, we make sure each step lands * before applying the next step. */ - I915_WRITE(fence_reg, 0); - POSTING_READ(fence_reg); + I915_WRITE(fence_reg_lo, 0); + POSTING_READ(fence_reg_lo); if (obj) { u32 size = i915_gem_obj_ggtt_size(obj); @@ -103,14 +103,14 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, val |= 1 << I965_FENCE_TILING_Y_SHIFT; val |= I965_FENCE_REG_VALID; - I915_WRITE(fence_reg + 4, val >> 32); - POSTING_READ(fence_reg + 4); + I915_WRITE(fence_reg_hi, val >> 32); + POSTING_READ(fence_reg_hi); - I915_WRITE(fence_reg + 0, val); - POSTING_READ(fence_reg); + I915_WRITE(fence_reg_lo, val); + POSTING_READ(fence_reg_lo); } else { - I915_WRITE(fence_reg + 4, 0); - POSTING_READ(fence_reg + 4); + I915_WRITE(fence_reg_hi, 0); + POSTING_READ(fence_reg_hi); } } @@ -128,7 +128,7 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg, WARN((i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) || (size & -size) != size || (i915_gem_obj_ggtt_offset(obj) & (size - 1)), - "object 0x%08lx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n", + "object 0x%08llx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n", i915_gem_obj_ggtt_offset(obj), obj->map_and_fenceable, size); if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)) @@ -149,13 +149,8 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg, } else val = 0; - if (reg < 8) - reg = FENCE_REG_830_0 + reg * 4; - else - reg = FENCE_REG_945_8 + (reg - 8) * 4; - - I915_WRITE(reg, val); - POSTING_READ(reg); + I915_WRITE(FENCE_REG(reg), val); + POSTING_READ(FENCE_REG(reg)); } static void i830_write_fence_reg(struct drm_device *dev, int reg, @@ -171,7 +166,7 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg, WARN((i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) || (size & -size) != size || (i915_gem_obj_ggtt_offset(obj) & (size - 1)), - "object 0x%08lx not 512K or pot-size 0x%08x aligned\n", + "object 0x%08llx not 512K or pot-size 0x%08x aligned\n", i915_gem_obj_ggtt_offset(obj), size); pitch_val = obj->stride / 128; @@ -186,8 +181,8 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg, } else val = 0; - I915_WRITE(FENCE_REG_830_0 + reg * 4, val); - POSTING_READ(FENCE_REG_830_0 + reg * 4); + I915_WRITE(FENCE_REG(reg), val); + POSTING_READ(FENCE_REG(reg)); } inline static bool i915_gem_object_needs_mb(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 96054a5..620d57e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -204,6 +204,9 @@ static gen8_pde_t gen8_pde_encode(const dma_addr_t addr, return pde; } +#define gen8_pdpe_encode gen8_pde_encode +#define gen8_pml4e_encode gen8_pde_encode + static gen6_pte_t snb_pte_encode(dma_addr_t addr, enum i915_cache_level level, bool valid, u32 unused) @@ -522,6 +525,127 @@ static void gen8_initialize_pd(struct i915_address_space *vm, fill_px(vm->dev, pd, scratch_pde); } +static int __pdp_init(struct drm_device *dev, + struct i915_page_directory_pointer *pdp) +{ + size_t pdpes = I915_PDPES_PER_PDP(dev); + + pdp->used_pdpes = kcalloc(BITS_TO_LONGS(pdpes), + sizeof(unsigned long), + GFP_KERNEL); + if (!pdp->used_pdpes) + return -ENOMEM; + + pdp->page_directory = kcalloc(pdpes, sizeof(*pdp->page_directory), + GFP_KERNEL); + if (!pdp->page_directory) { + kfree(pdp->used_pdpes); + /* the PDP might be the statically allocated top level. Keep it + * as clean as possible */ + pdp->used_pdpes = NULL; + return -ENOMEM; + } + + return 0; +} + +static void __pdp_fini(struct i915_page_directory_pointer *pdp) +{ + kfree(pdp->used_pdpes); + kfree(pdp->page_directory); + pdp->page_directory = NULL; +} + +static struct +i915_page_directory_pointer *alloc_pdp(struct drm_device *dev) +{ + struct i915_page_directory_pointer *pdp; + int ret = -ENOMEM; + + WARN_ON(!USES_FULL_48BIT_PPGTT(dev)); + + pdp = kzalloc(sizeof(*pdp), GFP_KERNEL); + if (!pdp) + return ERR_PTR(-ENOMEM); + + ret = __pdp_init(dev, pdp); + if (ret) + goto fail_bitmap; + + ret = setup_px(dev, pdp); + if (ret) + goto fail_page_m; + + return pdp; + +fail_page_m: + __pdp_fini(pdp); +fail_bitmap: + kfree(pdp); + + return ERR_PTR(ret); +} + +static void free_pdp(struct drm_device *dev, + struct i915_page_directory_pointer *pdp) +{ + __pdp_fini(pdp); + if (USES_FULL_48BIT_PPGTT(dev)) { + cleanup_px(dev, pdp); + kfree(pdp); + } +} + +static void gen8_initialize_pdp(struct i915_address_space *vm, + struct i915_page_directory_pointer *pdp) +{ + gen8_ppgtt_pdpe_t scratch_pdpe; + + scratch_pdpe = gen8_pdpe_encode(px_dma(vm->scratch_pd), I915_CACHE_LLC); + + fill_px(vm->dev, pdp, scratch_pdpe); +} + +static void gen8_initialize_pml4(struct i915_address_space *vm, + struct i915_pml4 *pml4) +{ + gen8_ppgtt_pml4e_t scratch_pml4e; + + scratch_pml4e = gen8_pml4e_encode(px_dma(vm->scratch_pdp), + I915_CACHE_LLC); + + fill_px(vm->dev, pml4, scratch_pml4e); +} + +static void +gen8_setup_page_directory(struct i915_hw_ppgtt *ppgtt, + struct i915_page_directory_pointer *pdp, + struct i915_page_directory *pd, + int index) +{ + gen8_ppgtt_pdpe_t *page_directorypo; + + if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) + return; + + page_directorypo = kmap_px(pdp); + page_directorypo[index] = gen8_pdpe_encode(px_dma(pd), I915_CACHE_LLC); + kunmap_px(ppgtt, page_directorypo); +} + +static void +gen8_setup_page_directory_pointer(struct i915_hw_ppgtt *ppgtt, + struct i915_pml4 *pml4, + struct i915_page_directory_pointer *pdp, + int index) +{ + gen8_ppgtt_pml4e_t *pagemap = kmap_px(pml4); + + WARN_ON(!USES_FULL_48BIT_PPGTT(ppgtt->base.dev)); + pagemap[index] = gen8_pml4e_encode(px_dma(pdp), I915_CACHE_LLC); + kunmap_px(ppgtt, pagemap); +} + /* Broadwell Page Directory Pointer Descriptors */ static int gen8_write_pdp(struct drm_i915_gem_request *req, unsigned entry, @@ -547,8 +671,8 @@ static int gen8_write_pdp(struct drm_i915_gem_request *req, return 0; } -static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct drm_i915_gem_request *req) +static int gen8_legacy_mm_switch(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_request *req) { int i, ret; @@ -563,31 +687,38 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt, return 0; } -static void gen8_ppgtt_clear_range(struct i915_address_space *vm, - uint64_t start, - uint64_t length, - bool use_scratch) +static int gen8_48b_mm_switch(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_request *req) +{ + return gen8_write_pdp(req, 0, px_dma(&ppgtt->pml4)); +} + +static void gen8_ppgtt_clear_pte_range(struct i915_address_space *vm, + struct i915_page_directory_pointer *pdp, + uint64_t start, + uint64_t length, + gen8_pte_t scratch_pte) { struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); - gen8_pte_t *pt_vaddr, scratch_pte; - unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK; - unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK; - unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK; + gen8_pte_t *pt_vaddr; + unsigned pdpe = gen8_pdpe_index(start); + unsigned pde = gen8_pde_index(start); + unsigned pte = gen8_pte_index(start); unsigned num_entries = length >> PAGE_SHIFT; unsigned last_pte, i; - scratch_pte = gen8_pte_encode(px_dma(ppgtt->base.scratch_page), - I915_CACHE_LLC, use_scratch); + if (WARN_ON(!pdp)) + return; while (num_entries) { struct i915_page_directory *pd; struct i915_page_table *pt; - if (WARN_ON(!ppgtt->pdp.page_directory[pdpe])) + if (WARN_ON(!pdp->page_directory[pdpe])) break; - pd = ppgtt->pdp.page_directory[pdpe]; + pd = pdp->page_directory[pdpe]; if (WARN_ON(!pd->page_table[pde])) break; @@ -612,45 +743,69 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, pte = 0; if (++pde == I915_PDES) { - pdpe++; + if (++pdpe == I915_PDPES_PER_PDP(vm->dev)) + break; pde = 0; } } } -static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, - struct sg_table *pages, - uint64_t start, - enum i915_cache_level cache_level, u32 unused) +static void gen8_ppgtt_clear_range(struct i915_address_space *vm, + uint64_t start, + uint64_t length, + bool use_scratch) +{ + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + gen8_pte_t scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page), + I915_CACHE_LLC, use_scratch); + + if (!USES_FULL_48BIT_PPGTT(vm->dev)) { + gen8_ppgtt_clear_pte_range(vm, &ppgtt->pdp, start, length, + scratch_pte); + } else { + uint64_t templ4, pml4e; + struct i915_page_directory_pointer *pdp; + + gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, templ4, pml4e) { + gen8_ppgtt_clear_pte_range(vm, pdp, start, length, + scratch_pte); + } + } +} + +static void +gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm, + struct i915_page_directory_pointer *pdp, + struct sg_page_iter *sg_iter, + uint64_t start, + enum i915_cache_level cache_level) { struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); gen8_pte_t *pt_vaddr; - unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK; - unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK; - unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK; - struct sg_page_iter sg_iter; + unsigned pdpe = gen8_pdpe_index(start); + unsigned pde = gen8_pde_index(start); + unsigned pte = gen8_pte_index(start); pt_vaddr = NULL; - for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) { - if (WARN_ON(pdpe >= GEN8_LEGACY_PDPES)) - break; - + while (__sg_page_iter_next(sg_iter)) { if (pt_vaddr == NULL) { - struct i915_page_directory *pd = ppgtt->pdp.page_directory[pdpe]; + struct i915_page_directory *pd = pdp->page_directory[pdpe]; struct i915_page_table *pt = pd->page_table[pde]; pt_vaddr = kmap_px(pt); } pt_vaddr[pte] = - gen8_pte_encode(sg_page_iter_dma_address(&sg_iter), + gen8_pte_encode(sg_page_iter_dma_address(sg_iter), cache_level, true); if (++pte == GEN8_PTES) { kunmap_px(ppgtt, pt_vaddr); pt_vaddr = NULL; if (++pde == I915_PDES) { - pdpe++; + if (++pdpe == I915_PDPES_PER_PDP(vm->dev)) + break; pde = 0; } pte = 0; @@ -661,6 +816,33 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, kunmap_px(ppgtt, pt_vaddr); } +static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, + struct sg_table *pages, + uint64_t start, + enum i915_cache_level cache_level, + u32 unused) +{ + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + struct sg_page_iter sg_iter; + + __sg_page_iter_start(&sg_iter, pages->sgl, sg_nents(pages->sgl), 0); + + if (!USES_FULL_48BIT_PPGTT(vm->dev)) { + gen8_ppgtt_insert_pte_entries(vm, &ppgtt->pdp, &sg_iter, start, + cache_level); + } else { + struct i915_page_directory_pointer *pdp; + uint64_t templ4, pml4e; + uint64_t length = (uint64_t)pages->orig_nents << PAGE_SHIFT; + + gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, templ4, pml4e) { + gen8_ppgtt_insert_pte_entries(vm, pdp, &sg_iter, + start, cache_level); + } + } +} + static void gen8_free_page_tables(struct drm_device *dev, struct i915_page_directory *pd) { @@ -699,8 +881,55 @@ static int gen8_init_scratch(struct i915_address_space *vm) return PTR_ERR(vm->scratch_pd); } + if (USES_FULL_48BIT_PPGTT(dev)) { + vm->scratch_pdp = alloc_pdp(dev); + if (IS_ERR(vm->scratch_pdp)) { + free_pd(dev, vm->scratch_pd); + free_pt(dev, vm->scratch_pt); + free_scratch_page(dev, vm->scratch_page); + return PTR_ERR(vm->scratch_pdp); + } + } + gen8_initialize_pt(vm, vm->scratch_pt); gen8_initialize_pd(vm, vm->scratch_pd); + if (USES_FULL_48BIT_PPGTT(dev)) + gen8_initialize_pdp(vm, vm->scratch_pdp); + + return 0; +} + +static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create) +{ + enum vgt_g2v_type msg; + struct drm_device *dev = ppgtt->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + unsigned int offset = vgtif_reg(pdp0_lo); + int i; + + if (USES_FULL_48BIT_PPGTT(dev)) { + u64 daddr = px_dma(&ppgtt->pml4); + + I915_WRITE(offset, lower_32_bits(daddr)); + I915_WRITE(offset + 4, upper_32_bits(daddr)); + + msg = (create ? VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE : + VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY); + } else { + for (i = 0; i < GEN8_LEGACY_PDPES; i++) { + u64 daddr = i915_page_dir_dma_addr(ppgtt, i); + + I915_WRITE(offset, lower_32_bits(daddr)); + I915_WRITE(offset + 4, upper_32_bits(daddr)); + + offset += 8; + } + + msg = (create ? VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE : + VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY); + } + + I915_WRITE(vgtif_reg(g2v_notify), msg); return 0; } @@ -709,35 +938,65 @@ static void gen8_free_scratch(struct i915_address_space *vm) { struct drm_device *dev = vm->dev; + if (USES_FULL_48BIT_PPGTT(dev)) + free_pdp(dev, vm->scratch_pdp); free_pd(dev, vm->scratch_pd); free_pt(dev, vm->scratch_pt); free_scratch_page(dev, vm->scratch_page); } -static void gen8_ppgtt_cleanup(struct i915_address_space *vm) +static void gen8_ppgtt_cleanup_3lvl(struct drm_device *dev, + struct i915_page_directory_pointer *pdp) +{ + int i; + + for_each_set_bit(i, pdp->used_pdpes, I915_PDPES_PER_PDP(dev)) { + if (WARN_ON(!pdp->page_directory[i])) + continue; + + gen8_free_page_tables(dev, pdp->page_directory[i]); + free_pd(dev, pdp->page_directory[i]); + } + + free_pdp(dev, pdp); +} + +static void gen8_ppgtt_cleanup_4lvl(struct i915_hw_ppgtt *ppgtt) { - struct i915_hw_ppgtt *ppgtt = - container_of(vm, struct i915_hw_ppgtt, base); int i; - for_each_set_bit(i, ppgtt->pdp.used_pdpes, GEN8_LEGACY_PDPES) { - if (WARN_ON(!ppgtt->pdp.page_directory[i])) + for_each_set_bit(i, ppgtt->pml4.used_pml4es, GEN8_PML4ES_PER_PML4) { + if (WARN_ON(!ppgtt->pml4.pdps[i])) continue; - gen8_free_page_tables(ppgtt->base.dev, - ppgtt->pdp.page_directory[i]); - free_pd(ppgtt->base.dev, ppgtt->pdp.page_directory[i]); + gen8_ppgtt_cleanup_3lvl(ppgtt->base.dev, ppgtt->pml4.pdps[i]); } + cleanup_px(ppgtt->base.dev, &ppgtt->pml4); +} + +static void gen8_ppgtt_cleanup(struct i915_address_space *vm) +{ + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + + if (intel_vgpu_active(vm->dev)) + gen8_ppgtt_notify_vgt(ppgtt, false); + + if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) + gen8_ppgtt_cleanup_3lvl(ppgtt->base.dev, &ppgtt->pdp); + else + gen8_ppgtt_cleanup_4lvl(ppgtt); + gen8_free_scratch(vm); } /** * gen8_ppgtt_alloc_pagetabs() - Allocate page tables for VA range. - * @ppgtt: Master ppgtt structure. - * @pd: Page directory for this address range. + * @vm: Master vm structure. + * @pd: Page directory for this address range. * @start: Starting virtual address to begin allocations. - * @length Size of the allocations. + * @length: Size of the allocations. * @new_pts: Bitmap set by function with new allocations. Likely used by the * caller to free on error. * @@ -750,22 +1009,22 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm) * * Return: 0 if success; negative error code otherwise. */ -static int gen8_ppgtt_alloc_pagetabs(struct i915_hw_ppgtt *ppgtt, +static int gen8_ppgtt_alloc_pagetabs(struct i915_address_space *vm, struct i915_page_directory *pd, uint64_t start, uint64_t length, unsigned long *new_pts) { - struct drm_device *dev = ppgtt->base.dev; + struct drm_device *dev = vm->dev; struct i915_page_table *pt; uint64_t temp; uint32_t pde; gen8_for_each_pde(pt, pd, start, length, temp, pde) { /* Don't reallocate page tables */ - if (pt) { + if (test_bit(pde, pd->used_pdes)) { /* Scratch is never allocated this way */ - WARN_ON(pt == ppgtt->base.scratch_pt); + WARN_ON(pt == vm->scratch_pt); continue; } @@ -773,9 +1032,10 @@ static int gen8_ppgtt_alloc_pagetabs(struct i915_hw_ppgtt *ppgtt, if (IS_ERR(pt)) goto unwind_out; - gen8_initialize_pt(&ppgtt->base, pt); + gen8_initialize_pt(vm, pt); pd->page_table[pde] = pt; __set_bit(pde, new_pts); + trace_i915_page_table_entry_alloc(vm, pde, start, GEN8_PDE_SHIFT); } return 0; @@ -789,11 +1049,11 @@ unwind_out: /** * gen8_ppgtt_alloc_page_directories() - Allocate page directories for VA range. - * @ppgtt: Master ppgtt structure. + * @vm: Master vm structure. * @pdp: Page directory pointer for this address range. * @start: Starting virtual address to begin allocations. - * @length Size of the allocations. - * @new_pds Bitmap set by function with new allocations. Likely used by the + * @length: Size of the allocations. + * @new_pds: Bitmap set by function with new allocations. Likely used by the * caller to free on error. * * Allocate the required number of page directories starting at the pde index of @@ -810,48 +1070,102 @@ unwind_out: * * Return: 0 if success; negative error code otherwise. */ -static int gen8_ppgtt_alloc_page_directories(struct i915_hw_ppgtt *ppgtt, - struct i915_page_directory_pointer *pdp, - uint64_t start, - uint64_t length, - unsigned long *new_pds) +static int +gen8_ppgtt_alloc_page_directories(struct i915_address_space *vm, + struct i915_page_directory_pointer *pdp, + uint64_t start, + uint64_t length, + unsigned long *new_pds) { - struct drm_device *dev = ppgtt->base.dev; + struct drm_device *dev = vm->dev; struct i915_page_directory *pd; uint64_t temp; uint32_t pdpe; + uint32_t pdpes = I915_PDPES_PER_PDP(dev); - WARN_ON(!bitmap_empty(new_pds, GEN8_LEGACY_PDPES)); + WARN_ON(!bitmap_empty(new_pds, pdpes)); gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) { - if (pd) + if (test_bit(pdpe, pdp->used_pdpes)) continue; pd = alloc_pd(dev); if (IS_ERR(pd)) goto unwind_out; - gen8_initialize_pd(&ppgtt->base, pd); + gen8_initialize_pd(vm, pd); pdp->page_directory[pdpe] = pd; __set_bit(pdpe, new_pds); + trace_i915_page_directory_entry_alloc(vm, pdpe, start, GEN8_PDPE_SHIFT); } return 0; unwind_out: - for_each_set_bit(pdpe, new_pds, GEN8_LEGACY_PDPES) + for_each_set_bit(pdpe, new_pds, pdpes) free_pd(dev, pdp->page_directory[pdpe]); return -ENOMEM; } -static void -free_gen8_temp_bitmaps(unsigned long *new_pds, unsigned long **new_pts) +/** + * gen8_ppgtt_alloc_page_dirpointers() - Allocate pdps for VA range. + * @vm: Master vm structure. + * @pml4: Page map level 4 for this address range. + * @start: Starting virtual address to begin allocations. + * @length: Size of the allocations. + * @new_pdps: Bitmap set by function with new allocations. Likely used by the + * caller to free on error. + * + * Allocate the required number of page directory pointers. Extremely similar to + * gen8_ppgtt_alloc_page_directories() and gen8_ppgtt_alloc_pagetabs(). + * The main difference is here we are limited by the pml4 boundary (instead of + * the page directory pointer). + * + * Return: 0 if success; negative error code otherwise. + */ +static int +gen8_ppgtt_alloc_page_dirpointers(struct i915_address_space *vm, + struct i915_pml4 *pml4, + uint64_t start, + uint64_t length, + unsigned long *new_pdps) { - int i; + struct drm_device *dev = vm->dev; + struct i915_page_directory_pointer *pdp; + uint64_t temp; + uint32_t pml4e; + + WARN_ON(!bitmap_empty(new_pdps, GEN8_PML4ES_PER_PML4)); + + gen8_for_each_pml4e(pdp, pml4, start, length, temp, pml4e) { + if (!test_bit(pml4e, pml4->used_pml4es)) { + pdp = alloc_pdp(dev); + if (IS_ERR(pdp)) + goto unwind_out; + + gen8_initialize_pdp(vm, pdp); + pml4->pdps[pml4e] = pdp; + __set_bit(pml4e, new_pdps); + trace_i915_page_directory_pointer_entry_alloc(vm, + pml4e, + start, + GEN8_PML4E_SHIFT); + } + } + + return 0; + +unwind_out: + for_each_set_bit(pml4e, new_pdps, GEN8_PML4ES_PER_PML4) + free_pdp(dev, pml4->pdps[pml4e]); + + return -ENOMEM; +} - for (i = 0; i < GEN8_LEGACY_PDPES; i++) - kfree(new_pts[i]); +static void +free_gen8_temp_bitmaps(unsigned long *new_pds, unsigned long *new_pts) +{ kfree(new_pts); kfree(new_pds); } @@ -861,28 +1175,20 @@ free_gen8_temp_bitmaps(unsigned long *new_pds, unsigned long **new_pts) */ static int __must_check alloc_gen8_temp_bitmaps(unsigned long **new_pds, - unsigned long ***new_pts) + unsigned long **new_pts, + uint32_t pdpes) { - int i; unsigned long *pds; - unsigned long **pts; + unsigned long *pts; - pds = kcalloc(BITS_TO_LONGS(GEN8_LEGACY_PDPES), sizeof(unsigned long), GFP_KERNEL); + pds = kcalloc(BITS_TO_LONGS(pdpes), sizeof(unsigned long), GFP_TEMPORARY); if (!pds) return -ENOMEM; - pts = kcalloc(GEN8_LEGACY_PDPES, sizeof(unsigned long *), GFP_KERNEL); - if (!pts) { - kfree(pds); - return -ENOMEM; - } - - for (i = 0; i < GEN8_LEGACY_PDPES; i++) { - pts[i] = kcalloc(BITS_TO_LONGS(I915_PDES), - sizeof(unsigned long), GFP_KERNEL); - if (!pts[i]) - goto err_out; - } + pts = kcalloc(pdpes, BITS_TO_LONGS(I915_PDES) * sizeof(unsigned long), + GFP_TEMPORARY); + if (!pts) + goto err_out; *new_pds = pds; *new_pts = pts; @@ -904,18 +1210,21 @@ static void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt) ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.dev)->ring_mask; } -static int gen8_alloc_va_range(struct i915_address_space *vm, - uint64_t start, - uint64_t length) +static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm, + struct i915_page_directory_pointer *pdp, + uint64_t start, + uint64_t length) { struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); - unsigned long *new_page_dirs, **new_page_tables; + unsigned long *new_page_dirs, *new_page_tables; + struct drm_device *dev = vm->dev; struct i915_page_directory *pd; const uint64_t orig_start = start; const uint64_t orig_length = length; uint64_t temp; uint32_t pdpe; + uint32_t pdpes = I915_PDPES_PER_PDP(dev); int ret; /* Wrap is never okay since we can only represent 48b, and we don't @@ -924,25 +1233,25 @@ static int gen8_alloc_va_range(struct i915_address_space *vm, if (WARN_ON(start + length < start)) return -ENODEV; - if (WARN_ON(start + length > ppgtt->base.total)) + if (WARN_ON(start + length > vm->total)) return -ENODEV; - ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables); + ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables, pdpes); if (ret) return ret; /* Do the allocations first so we can easily bail out */ - ret = gen8_ppgtt_alloc_page_directories(ppgtt, &ppgtt->pdp, start, length, - new_page_dirs); + ret = gen8_ppgtt_alloc_page_directories(vm, pdp, start, length, + new_page_dirs); if (ret) { free_gen8_temp_bitmaps(new_page_dirs, new_page_tables); return ret; } /* For every page directory referenced, allocate page tables */ - gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) { - ret = gen8_ppgtt_alloc_pagetabs(ppgtt, pd, start, length, - new_page_tables[pdpe]); + gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) { + ret = gen8_ppgtt_alloc_pagetabs(vm, pd, start, length, + new_page_tables + pdpe * BITS_TO_LONGS(I915_PDES)); if (ret) goto err_out; } @@ -952,10 +1261,10 @@ static int gen8_alloc_va_range(struct i915_address_space *vm, /* Allocations have completed successfully, so set the bitmaps, and do * the mappings. */ - gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) { + gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) { gen8_pde_t *const page_directory = kmap_px(pd); struct i915_page_table *pt; - uint64_t pd_len = gen8_clamp_pd(start, length); + uint64_t pd_len = length; uint64_t pd_start = start; uint32_t pde; @@ -979,14 +1288,18 @@ static int gen8_alloc_va_range(struct i915_address_space *vm, /* Map the PDE to the page table */ page_directory[pde] = gen8_pde_encode(px_dma(pt), I915_CACHE_LLC); + trace_i915_page_table_entry_map(&ppgtt->base, pde, pt, + gen8_pte_index(start), + gen8_pte_count(start, length), + GEN8_PTES); /* NB: We haven't yet mapped ptes to pages. At this * point we're still relying on insert_entries() */ } kunmap_px(ppgtt, page_directory); - - __set_bit(pdpe, ppgtt->pdp.used_pdpes); + __set_bit(pdpe, pdp->used_pdpes); + gen8_setup_page_directory(ppgtt, pdp, pd, pdpe); } free_gen8_temp_bitmaps(new_page_dirs, new_page_tables); @@ -995,18 +1308,191 @@ static int gen8_alloc_va_range(struct i915_address_space *vm, err_out: while (pdpe--) { - for_each_set_bit(temp, new_page_tables[pdpe], I915_PDES) - free_pt(vm->dev, ppgtt->pdp.page_directory[pdpe]->page_table[temp]); + for_each_set_bit(temp, new_page_tables + pdpe * + BITS_TO_LONGS(I915_PDES), I915_PDES) + free_pt(dev, pdp->page_directory[pdpe]->page_table[temp]); } - for_each_set_bit(pdpe, new_page_dirs, GEN8_LEGACY_PDPES) - free_pd(vm->dev, ppgtt->pdp.page_directory[pdpe]); + for_each_set_bit(pdpe, new_page_dirs, pdpes) + free_pd(dev, pdp->page_directory[pdpe]); free_gen8_temp_bitmaps(new_page_dirs, new_page_tables); mark_tlbs_dirty(ppgtt); return ret; } +static int gen8_alloc_va_range_4lvl(struct i915_address_space *vm, + struct i915_pml4 *pml4, + uint64_t start, + uint64_t length) +{ + DECLARE_BITMAP(new_pdps, GEN8_PML4ES_PER_PML4); + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + struct i915_page_directory_pointer *pdp; + uint64_t temp, pml4e; + int ret = 0; + + /* Do the pml4 allocations first, so we don't need to track the newly + * allocated tables below the pdp */ + bitmap_zero(new_pdps, GEN8_PML4ES_PER_PML4); + + /* The pagedirectory and pagetable allocations are done in the shared 3 + * and 4 level code. Just allocate the pdps. + */ + ret = gen8_ppgtt_alloc_page_dirpointers(vm, pml4, start, length, + new_pdps); + if (ret) + return ret; + + WARN(bitmap_weight(new_pdps, GEN8_PML4ES_PER_PML4) > 2, + "The allocation has spanned more than 512GB. " + "It is highly likely this is incorrect."); + + gen8_for_each_pml4e(pdp, pml4, start, length, temp, pml4e) { + WARN_ON(!pdp); + + ret = gen8_alloc_va_range_3lvl(vm, pdp, start, length); + if (ret) + goto err_out; + + gen8_setup_page_directory_pointer(ppgtt, pml4, pdp, pml4e); + } + + bitmap_or(pml4->used_pml4es, new_pdps, pml4->used_pml4es, + GEN8_PML4ES_PER_PML4); + + return 0; + +err_out: + for_each_set_bit(pml4e, new_pdps, GEN8_PML4ES_PER_PML4) + gen8_ppgtt_cleanup_3lvl(vm->dev, pml4->pdps[pml4e]); + + return ret; +} + +static int gen8_alloc_va_range(struct i915_address_space *vm, + uint64_t start, uint64_t length) +{ + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + + if (USES_FULL_48BIT_PPGTT(vm->dev)) + return gen8_alloc_va_range_4lvl(vm, &ppgtt->pml4, start, length); + else + return gen8_alloc_va_range_3lvl(vm, &ppgtt->pdp, start, length); +} + +static void gen8_dump_pdp(struct i915_page_directory_pointer *pdp, + uint64_t start, uint64_t length, + gen8_pte_t scratch_pte, + struct seq_file *m) +{ + struct i915_page_directory *pd; + uint64_t temp; + uint32_t pdpe; + + gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) { + struct i915_page_table *pt; + uint64_t pd_len = length; + uint64_t pd_start = start; + uint32_t pde; + + if (!test_bit(pdpe, pdp->used_pdpes)) + continue; + + seq_printf(m, "\tPDPE #%d\n", pdpe); + gen8_for_each_pde(pt, pd, pd_start, pd_len, temp, pde) { + uint32_t pte; + gen8_pte_t *pt_vaddr; + + if (!test_bit(pde, pd->used_pdes)) + continue; + + pt_vaddr = kmap_px(pt); + for (pte = 0; pte < GEN8_PTES; pte += 4) { + uint64_t va = + (pdpe << GEN8_PDPE_SHIFT) | + (pde << GEN8_PDE_SHIFT) | + (pte << GEN8_PTE_SHIFT); + int i; + bool found = false; + + for (i = 0; i < 4; i++) + if (pt_vaddr[pte + i] != scratch_pte) + found = true; + if (!found) + continue; + + seq_printf(m, "\t\t0x%llx [%03d,%03d,%04d]: =", va, pdpe, pde, pte); + for (i = 0; i < 4; i++) { + if (pt_vaddr[pte + i] != scratch_pte) + seq_printf(m, " %llx", pt_vaddr[pte + i]); + else + seq_puts(m, " SCRATCH "); + } + seq_puts(m, "\n"); + } + /* don't use kunmap_px, it could trigger + * an unnecessary flush. + */ + kunmap_atomic(pt_vaddr); + } + } +} + +static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) +{ + struct i915_address_space *vm = &ppgtt->base; + uint64_t start = ppgtt->base.start; + uint64_t length = ppgtt->base.total; + gen8_pte_t scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page), + I915_CACHE_LLC, true); + + if (!USES_FULL_48BIT_PPGTT(vm->dev)) { + gen8_dump_pdp(&ppgtt->pdp, start, length, scratch_pte, m); + } else { + uint64_t templ4, pml4e; + struct i915_pml4 *pml4 = &ppgtt->pml4; + struct i915_page_directory_pointer *pdp; + + gen8_for_each_pml4e(pdp, pml4, start, length, templ4, pml4e) { + if (!test_bit(pml4e, pml4->used_pml4es)) + continue; + + seq_printf(m, " PML4E #%llu\n", pml4e); + gen8_dump_pdp(pdp, start, length, scratch_pte, m); + } + } +} + +static int gen8_preallocate_top_level_pdps(struct i915_hw_ppgtt *ppgtt) +{ + unsigned long *new_page_dirs, *new_page_tables; + uint32_t pdpes = I915_PDPES_PER_PDP(dev); + int ret; + + /* We allocate temp bitmap for page tables for no gain + * but as this is for init only, lets keep the things simple + */ + ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables, pdpes); + if (ret) + return ret; + + /* Allocate for all pdps regardless of how the ppgtt + * was defined. + */ + ret = gen8_ppgtt_alloc_page_directories(&ppgtt->base, &ppgtt->pdp, + 0, 1ULL << 32, + new_page_dirs); + if (!ret) + *ppgtt->pdp.used_pdpes = *new_page_dirs; + + free_gen8_temp_bitmaps(new_page_dirs, new_page_tables); + + return ret; +} + /* * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers * with a net effect resembling a 2-level page table in normal x86 terms. Each @@ -1023,24 +1509,49 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) return ret; ppgtt->base.start = 0; - ppgtt->base.total = 1ULL << 32; - if (IS_ENABLED(CONFIG_X86_32)) - /* While we have a proliferation of size_t variables - * we cannot represent the full ppgtt size on 32bit, - * so limit it to the same size as the GGTT (currently - * 2GiB). - */ - ppgtt->base.total = to_i915(ppgtt->base.dev)->gtt.base.total; ppgtt->base.cleanup = gen8_ppgtt_cleanup; ppgtt->base.allocate_va_range = gen8_alloc_va_range; ppgtt->base.insert_entries = gen8_ppgtt_insert_entries; ppgtt->base.clear_range = gen8_ppgtt_clear_range; ppgtt->base.unbind_vma = ppgtt_unbind_vma; ppgtt->base.bind_vma = ppgtt_bind_vma; + ppgtt->debug_dump = gen8_dump_ppgtt; + + if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) { + ret = setup_px(ppgtt->base.dev, &ppgtt->pml4); + if (ret) + goto free_scratch; + + gen8_initialize_pml4(&ppgtt->base, &ppgtt->pml4); + + ppgtt->base.total = 1ULL << 48; + ppgtt->switch_mm = gen8_48b_mm_switch; + } else { + ret = __pdp_init(ppgtt->base.dev, &ppgtt->pdp); + if (ret) + goto free_scratch; + + ppgtt->base.total = 1ULL << 32; + ppgtt->switch_mm = gen8_legacy_mm_switch; + trace_i915_page_directory_pointer_entry_alloc(&ppgtt->base, + 0, 0, + GEN8_PML4E_SHIFT); + + if (intel_vgpu_active(ppgtt->base.dev)) { + ret = gen8_preallocate_top_level_pdps(ppgtt); + if (ret) + goto free_scratch; + } + } - ppgtt->switch_mm = gen8_mm_switch; + if (intel_vgpu_active(ppgtt->base.dev)) + gen8_ppgtt_notify_vgt(ppgtt, true); return 0; + +free_scratch: + gen8_free_scratch(&ppgtt->base); + return ret; } static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) @@ -1228,8 +1739,9 @@ static void gen8_ppgtt_enable(struct drm_device *dev) int j; for_each_ring(ring, dev_priv, j) { + u32 four_level = USES_FULL_48BIT_PPGTT(dev) ? GEN8_GFX_PPGTT_48B : 0; I915_WRITE(RING_MODE_GEN7(ring), - _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)); + _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE | four_level)); } } @@ -1609,6 +2121,16 @@ static int __hw_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt) return gen8_ppgtt_init(ppgtt); } +static void i915_address_space_init(struct i915_address_space *vm, + struct drm_i915_private *dev_priv) +{ + drm_mm_init(&vm->mm, vm->start, vm->total); + vm->dev = dev_priv->dev; + INIT_LIST_HEAD(&vm->active_list); + INIT_LIST_HEAD(&vm->inactive_list); + list_add_tail(&vm->global_link, &dev_priv->vm_list); +} + int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -1617,9 +2139,7 @@ int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt) ret = __hw_ppgtt_init(dev, ppgtt); if (ret == 0) { kref_init(&ppgtt->ref); - drm_mm_init(&ppgtt->base.mm, ppgtt->base.start, - ppgtt->base.total); - i915_init_vm(dev_priv, &ppgtt->base); + i915_address_space_init(&ppgtt->base, dev_priv); } return ret; @@ -2013,7 +2533,6 @@ static int ggtt_bind_vma(struct i915_vma *vma, * the bound flag ourselves. */ vma->bound |= GLOBAL_BIND; - } if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) { @@ -2084,9 +2603,9 @@ static void i915_gtt_color_adjust(struct drm_mm_node *node, } static int i915_gem_setup_global_gtt(struct drm_device *dev, - unsigned long start, - unsigned long mappable_end, - unsigned long end) + u64 start, + u64 mappable_end, + u64 end) { /* Let GEM Manage all of the aperture. * @@ -2106,11 +2625,13 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev, BUG_ON(mappable_end > end); - /* Subtract the guard page ... */ - drm_mm_init(&ggtt_vm->mm, start, end - start - PAGE_SIZE); + ggtt_vm->start = start; - dev_priv->gtt.base.start = start; - dev_priv->gtt.base.total = end - start; + /* Subtract the guard page before address space initialization to + * shrink the range used by drm_mm */ + ggtt_vm->total = end - start - PAGE_SIZE; + i915_address_space_init(ggtt_vm, dev_priv); + ggtt_vm->total += PAGE_SIZE; if (intel_vgpu_active(dev)) { ret = intel_vgt_balloon(dev); @@ -2119,13 +2640,13 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev, } if (!HAS_LLC(dev)) - dev_priv->gtt.base.mm.color_adjust = i915_gtt_color_adjust; + ggtt_vm->mm.color_adjust = i915_gtt_color_adjust; /* Mark any preallocated objects as occupied */ list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { struct i915_vma *vma = i915_gem_obj_to_vma(obj, ggtt_vm); - DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n", + DRM_DEBUG_KMS("reserving preallocated space: %llx + %zx\n", i915_gem_obj_ggtt_offset(obj), obj->base.size); WARN_ON(i915_gem_obj_ggtt_bound(obj)); @@ -2135,6 +2656,7 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev, return ret; } vma->bound |= GLOBAL_BIND; + list_add_tail(&vma->mm_list, &ggtt_vm->inactive_list); } /* Clear any non-preallocated blocks */ @@ -2367,8 +2889,8 @@ static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv) /* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b * write would work. */ - I915_WRITE(GEN8_PRIVATE_PAT, pat); - I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32); + I915_WRITE(GEN8_PRIVATE_PAT_LO, pat); + I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32); } static void chv_setup_private_ppat(struct drm_i915_private *dev_priv) @@ -2402,8 +2924,8 @@ static void chv_setup_private_ppat(struct drm_i915_private *dev_priv) GEN8_PPAT(6, CHV_PPAT_SNOOP) | GEN8_PPAT(7, CHV_PPAT_SNOOP); - I915_WRITE(GEN8_PRIVATE_PAT, pat); - I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32); + I915_WRITE(GEN8_PRIVATE_PAT_LO, pat); + I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32); } static int gen8_gmch_probe(struct drm_device *dev, @@ -2722,15 +3244,18 @@ i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj, } -static void -rotate_pages(dma_addr_t *in, unsigned int width, unsigned int height, - struct sg_table *st) +static struct scatterlist * +rotate_pages(dma_addr_t *in, unsigned int offset, + unsigned int width, unsigned int height, + struct sg_table *st, struct scatterlist *sg) { unsigned int column, row; unsigned int src_idx; - struct scatterlist *sg = st->sgl; - st->nents = 0; + if (!sg) { + st->nents = 0; + sg = st->sgl; + } for (column = 0; column < width; column++) { src_idx = width * (height - 1) + column; @@ -2741,12 +3266,14 @@ rotate_pages(dma_addr_t *in, unsigned int width, unsigned int height, * The only thing we need are DMA addresses. */ sg_set_page(sg, NULL, PAGE_SIZE, 0); - sg_dma_address(sg) = in[src_idx]; + sg_dma_address(sg) = in[offset + src_idx]; sg_dma_len(sg) = PAGE_SIZE; sg = sg_next(sg); src_idx -= width; } } + + return sg; } static struct sg_table * @@ -2755,10 +3282,13 @@ intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view, { struct intel_rotation_info *rot_info = &ggtt_view->rotation_info; unsigned int size_pages = rot_info->size >> PAGE_SHIFT; + unsigned int size_pages_uv; struct sg_page_iter sg_iter; unsigned long i; dma_addr_t *page_addr_list; struct sg_table *st; + unsigned int uv_start_page; + struct scatterlist *sg; int ret = -ENOMEM; /* Allocate a temporary list of source pages for random access. */ @@ -2767,12 +3297,18 @@ intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view, if (!page_addr_list) return ERR_PTR(ret); + /* Account for UV plane with NV12. */ + if (rot_info->pixel_format == DRM_FORMAT_NV12) + size_pages_uv = rot_info->size_uv >> PAGE_SHIFT; + else + size_pages_uv = 0; + /* Allocate target SG list. */ st = kmalloc(sizeof(*st), GFP_KERNEL); if (!st) goto err_st_alloc; - ret = sg_alloc_table(st, size_pages, GFP_KERNEL); + ret = sg_alloc_table(st, size_pages + size_pages_uv, GFP_KERNEL); if (ret) goto err_sg_alloc; @@ -2784,15 +3320,32 @@ intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view, } /* Rotate the pages. */ - rotate_pages(page_addr_list, + sg = rotate_pages(page_addr_list, 0, rot_info->width_pages, rot_info->height_pages, - st); + st, NULL); + + /* Append the UV plane if NV12. */ + if (rot_info->pixel_format == DRM_FORMAT_NV12) { + uv_start_page = size_pages; + + /* Check for tile-row un-alignment. */ + if (offset_in_page(rot_info->uv_offset)) + uv_start_page--; + + rot_info->uv_start_page = uv_start_page; + + rotate_pages(page_addr_list, uv_start_page, + rot_info->width_pages_uv, + rot_info->height_pages_uv, + st, sg); + } DRM_DEBUG_KMS( - "Created rotated page mapping for object size %zu (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages).\n", + "Created rotated page mapping for object size %zu (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages (%u plane 0)).\n", obj->base.size, rot_info->pitch, rot_info->height, rot_info->pixel_format, rot_info->width_pages, - rot_info->height_pages, size_pages); + rot_info->height_pages, size_pages + size_pages_uv, + size_pages); drm_free_large(page_addr_list); @@ -2804,10 +3357,11 @@ err_st_alloc: drm_free_large(page_addr_list); DRM_DEBUG_KMS( - "Failed to create rotated mapping for object size %zu! (%d) (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages)\n", + "Failed to create rotated mapping for object size %zu! (%d) (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %u pages (%u plane 0))\n", obj->base.size, ret, rot_info->pitch, rot_info->height, rot_info->pixel_format, rot_info->width_pages, - rot_info->height_pages, size_pages); + rot_info->height_pages, size_pages + size_pages_uv, + size_pages); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index e1cfa29..a216397 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -39,6 +39,8 @@ struct drm_i915_file_private; typedef uint32_t gen6_pte_t; typedef uint64_t gen8_pte_t; typedef uint64_t gen8_pde_t; +typedef uint64_t gen8_ppgtt_pdpe_t; +typedef uint64_t gen8_ppgtt_pml4e_t; #define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT) @@ -88,9 +90,18 @@ typedef uint64_t gen8_pde_t; * PDPE | PDE | PTE | offset * The difference as compared to normal x86 3 level page table is the PDPEs are * programmed via register. + * + * GEN8 48b legacy style address is defined as a 4 level page table: + * 47:39 | 38:30 | 29:21 | 20:12 | 11:0 + * PML4E | PDPE | PDE | PTE | offset */ +#define GEN8_PML4ES_PER_PML4 512 +#define GEN8_PML4E_SHIFT 39 +#define GEN8_PML4E_MASK (GEN8_PML4ES_PER_PML4 - 1) #define GEN8_PDPE_SHIFT 30 -#define GEN8_PDPE_MASK 0x3 +/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page + * tables */ +#define GEN8_PDPE_MASK 0x1ff #define GEN8_PDE_SHIFT 21 #define GEN8_PDE_MASK 0x1ff #define GEN8_PTE_SHIFT 12 @@ -98,6 +109,9 @@ typedef uint64_t gen8_pde_t; #define GEN8_LEGACY_PDPES 4 #define GEN8_PTES I915_PTES(sizeof(gen8_pte_t)) +#define I915_PDPES_PER_PDP(dev) (USES_FULL_48BIT_PPGTT(dev) ?\ + GEN8_PML4ES_PER_PML4 : GEN8_LEGACY_PDPES) + #define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD) #define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */ #define PPAT_CACHED_INDEX _PAGE_PAT /* WB LLCeLLC */ @@ -124,10 +138,14 @@ enum i915_ggtt_view_type { struct intel_rotation_info { unsigned int height; unsigned int pitch; + unsigned int uv_offset; uint32_t pixel_format; uint64_t fb_modifier; unsigned int width_pages, height_pages; uint64_t size; + unsigned int width_pages_uv, height_pages_uv; + uint64_t size_uv; + unsigned int uv_start_page; }; struct i915_ggtt_view { @@ -135,7 +153,7 @@ struct i915_ggtt_view { union { struct { - unsigned long offset; + u64 offset; unsigned int size; } partial; } params; @@ -241,9 +259,17 @@ struct i915_page_directory { }; struct i915_page_directory_pointer { - /* struct page *page; */ - DECLARE_BITMAP(used_pdpes, GEN8_LEGACY_PDPES); - struct i915_page_directory *page_directory[GEN8_LEGACY_PDPES]; + struct i915_page_dma base; + + unsigned long *used_pdpes; + struct i915_page_directory **page_directory; +}; + +struct i915_pml4 { + struct i915_page_dma base; + + DECLARE_BITMAP(used_pml4es, GEN8_PML4ES_PER_PML4); + struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4]; }; struct i915_address_space { @@ -256,6 +282,7 @@ struct i915_address_space { struct i915_page_scratch *scratch_page; struct i915_page_table *scratch_pt; struct i915_page_directory *scratch_pd; + struct i915_page_directory_pointer *scratch_pdp; /* GEN8+ & 48b PPGTT */ /** * List of objects currently involved in rendering. @@ -318,6 +345,7 @@ struct i915_gtt { struct i915_address_space base; size_t stolen_size; /* Total size of stolen memory */ + size_t stolen_usable_size; /* Total size minus BIOS reserved */ u64 mappable_end; /* End offset that we can CPU map */ struct io_mapping *mappable; /* Mapping to our CPU mappable region */ phys_addr_t mappable_base; /* PA of our GMADR */ @@ -341,8 +369,9 @@ struct i915_hw_ppgtt { struct drm_mm_node node; unsigned long pd_dirty_rings; union { - struct i915_page_directory_pointer pdp; - struct i915_page_directory pd; + struct i915_pml4 pml4; /* GEN8+ & 48b PPGTT */ + struct i915_page_directory_pointer pdp; /* GEN8+ */ + struct i915_page_directory pd; /* GEN6-7 */ }; struct drm_i915_file_private *file_priv; @@ -365,7 +394,8 @@ struct i915_hw_ppgtt { */ #define gen6_for_each_pde(pt, pd, start, length, temp, iter) \ for (iter = gen6_pde_index(start); \ - pt = (pd)->page_table[iter], length > 0 && iter < I915_PDES; \ + length > 0 && iter < I915_PDES ? \ + (pt = (pd)->page_table[iter]), 1 : 0; \ iter++, \ temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT) - start, \ temp = min_t(unsigned, temp, length), \ @@ -430,30 +460,30 @@ static inline uint32_t gen6_pde_index(uint32_t addr) */ #define gen8_for_each_pde(pt, pd, start, length, temp, iter) \ for (iter = gen8_pde_index(start); \ - pt = (pd)->page_table[iter], length > 0 && iter < I915_PDES; \ + length > 0 && iter < I915_PDES ? \ + (pt = (pd)->page_table[iter]), 1 : 0; \ iter++, \ temp = ALIGN(start+1, 1 << GEN8_PDE_SHIFT) - start, \ temp = min(temp, length), \ start += temp, length -= temp) -#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \ - for (iter = gen8_pdpe_index(start); \ - pd = (pdp)->page_directory[iter], length > 0 && iter < GEN8_LEGACY_PDPES; \ +#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \ + for (iter = gen8_pdpe_index(start); \ + length > 0 && (iter < I915_PDPES_PER_PDP(dev)) ? \ + (pd = (pdp)->page_directory[iter]), 1 : 0; \ iter++, \ temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT) - start, \ temp = min(temp, length), \ start += temp, length -= temp) -/* Clamp length to the next page_directory boundary */ -static inline uint64_t gen8_clamp_pd(uint64_t start, uint64_t length) -{ - uint64_t next_pd = ALIGN(start + 1, 1 << GEN8_PDPE_SHIFT); - - if (next_pd > (start + length)) - return length; - - return next_pd - start; -} +#define gen8_for_each_pml4e(pdp, pml4, start, length, temp, iter) \ + for (iter = gen8_pml4e_index(start); \ + length > 0 && iter < GEN8_PML4ES_PER_PML4 ? \ + (pdp = (pml4)->pdps[iter]), 1 : 0; \ + iter++, \ + temp = ALIGN(start+1, 1ULL << GEN8_PML4E_SHIFT) - start, \ + temp = min(temp, length), \ + start += temp, length -= temp) static inline uint32_t gen8_pte_index(uint64_t address) { @@ -472,8 +502,7 @@ static inline uint32_t gen8_pdpe_index(uint64_t address) static inline uint32_t gen8_pml4e_index(uint64_t address) { - WARN_ON(1); /* For 64B */ - return 0; + return (address >> GEN8_PML4E_SHIFT) & GEN8_PML4E_MASK; } static inline size_t gen8_pte_count(uint64_t address, uint64_t length) diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index f6ecbda..f7df54a 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -73,7 +73,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, - long target, unsigned flags) + unsigned long target, unsigned flags) { const struct { struct list_head *list; @@ -85,6 +85,9 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, }, *phase; unsigned long count = 0; + trace_i915_gem_shrink(dev_priv, target, flags); + i915_gem_retire_requests(dev_priv->dev); + /* * As we may completely rewrite the (un)bound list whilst unbinding * (due to retiring requests) we have to strictly process only @@ -123,6 +126,9 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, obj->madv != I915_MADV_DONTNEED) continue; + if ((flags & I915_SHRINK_ACTIVE) == 0 && obj->active) + continue; + drm_gem_object_reference(&obj->base); /* For the unbound phase, this should be a no-op! */ @@ -139,11 +145,13 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, list_splice(&still_in_list, phase->list); } + i915_gem_retire_requests(dev_priv->dev); + return count; } /** - * i915_gem_shrink - Shrink buffer object caches completely + * i915_gem_shrink_all - Shrink buffer object caches completely * @dev_priv: i915 device * * This is a simple wraper around i915_gem_shrink() to aggressively shrink all @@ -158,9 +166,10 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, */ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv) { - i915_gem_evict_everything(dev_priv->dev); - return i915_gem_shrink(dev_priv, LONG_MAX, - I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); + return i915_gem_shrink(dev_priv, -1UL, + I915_SHRINK_BOUND | + I915_SHRINK_UNBOUND | + I915_SHRINK_ACTIVE); } static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock) @@ -213,7 +222,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) count += obj->base.size >> PAGE_SHIFT; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - if (obj->pages_pin_count == num_vma_bound(obj)) + if (!obj->active && obj->pages_pin_count == num_vma_bound(obj)) count += obj->base.size >> PAGE_SHIFT; } diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index f361c4a..cdacf3f 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -30,6 +30,9 @@ #include <drm/i915_drm.h> #include "i915_drv.h" +#define KB(x) ((x) * 1024) +#define MB(x) (KB(x) * 1024) + /* * The BIOS typically reserves some of the system's memory for the exclusive * use of the integrated graphics. This memory is no longer available for @@ -42,23 +45,38 @@ * for is a boon. */ -int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv, - struct drm_mm_node *node, u64 size, - unsigned alignment) +int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, + struct drm_mm_node *node, u64 size, + unsigned alignment, u64 start, u64 end) { int ret; if (!drm_mm_initialized(&dev_priv->mm.stolen)) return -ENODEV; + /* See the comment at the drm_mm_init() call for more about this check. + * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */ + if (INTEL_INFO(dev_priv)->gen == 8 && start < 4096) + start = 4096; + mutex_lock(&dev_priv->mm.stolen_lock); - ret = drm_mm_insert_node(&dev_priv->mm.stolen, node, size, alignment, - DRM_MM_SEARCH_DEFAULT); + ret = drm_mm_insert_node_in_range(&dev_priv->mm.stolen, node, size, + alignment, start, end, + DRM_MM_SEARCH_DEFAULT); mutex_unlock(&dev_priv->mm.stolen_lock); return ret; } +int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv, + struct drm_mm_node *node, u64 size, + unsigned alignment) +{ + return i915_gem_stolen_insert_node_in_range(dev_priv, node, size, + alignment, 0, + dev_priv->gtt.stolen_usable_size); +} + void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv, struct drm_mm_node *node) { @@ -76,24 +94,91 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev) /* Almost universally we can find the Graphics Base of Stolen Memory * at offset 0x5c in the igfx configuration space. On a few (desktop) * machines this is also mirrored in the bridge device at different - * locations, or in the MCHBAR. On gen2, the layout is again slightly - * different with the Graphics Segment immediately following Top of - * Memory (or Top of Usable DRAM). Note it appears that TOUD is only - * reported by 865g, so we just use the top of memory as determined - * by the e820 probe. + * locations, or in the MCHBAR. + * + * On 865 we just check the TOUD register. + * + * On 830/845/85x the stolen memory base isn't available in any + * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size. * - * XXX However gen2 requires an unavailable symbol. */ base = 0; if (INTEL_INFO(dev)->gen >= 3) { /* Read Graphics Base of Stolen Memory directly */ pci_read_config_dword(dev->pdev, 0x5c, &base); base &= ~((1<<20) - 1); - } else { /* GEN2 */ -#if 0 - /* Stolen is immediately above Top of Memory */ - base = max_low_pfn_mapped << PAGE_SHIFT; -#endif + } else if (IS_I865G(dev)) { + u16 toud = 0; + + /* + * FIXME is the graphics stolen memory region + * always at TOUD? Ie. is it always the last + * one to be allocated by the BIOS? + */ + pci_bus_read_config_word(dev->pdev->bus, PCI_DEVFN(0, 0), + I865_TOUD, &toud); + + base = toud << 16; + } else if (IS_I85X(dev)) { + u32 tseg_size = 0; + u32 tom; + u8 tmp; + + pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0), + I85X_ESMRAMC, &tmp); + + if (tmp & TSEG_ENABLE) + tseg_size = MB(1); + + pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 1), + I85X_DRB3, &tmp); + tom = tmp * MB(32); + + base = tom - tseg_size - dev_priv->gtt.stolen_size; + } else if (IS_845G(dev)) { + u32 tseg_size = 0; + u32 tom; + u8 tmp; + + pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0), + I845_ESMRAMC, &tmp); + + if (tmp & TSEG_ENABLE) { + switch (tmp & I845_TSEG_SIZE_MASK) { + case I845_TSEG_SIZE_512K: + tseg_size = KB(512); + break; + case I845_TSEG_SIZE_1M: + tseg_size = MB(1); + break; + } + } + + pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0), + I830_DRB3, &tmp); + tom = tmp * MB(32); + + base = tom - tseg_size - dev_priv->gtt.stolen_size; + } else if (IS_I830(dev)) { + u32 tseg_size = 0; + u32 tom; + u8 tmp; + + pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0), + I830_ESMRAMC, &tmp); + + if (tmp & TSEG_ENABLE) { + if (tmp & I830_TSEG_SIZE_1M) + tseg_size = MB(1); + else + tseg_size = KB(512); + } + + pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0), + I830_DRB3, &tmp); + tom = tmp * MB(32); + + base = tom - tseg_size - dev_priv->gtt.stolen_size; } if (base == 0) @@ -186,6 +271,29 @@ void i915_gem_cleanup_stolen(struct drm_device *dev) drm_mm_takedown(&dev_priv->mm.stolen); } +static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv, + unsigned long *base, unsigned long *size) +{ + uint32_t reg_val = I915_READ(IS_GM45(dev_priv) ? + CTG_STOLEN_RESERVED : + ELK_STOLEN_RESERVED); + unsigned long stolen_top = dev_priv->mm.stolen_base + + dev_priv->gtt.stolen_size; + + *base = (reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK) << 16; + + WARN_ON((reg_val & G4X_STOLEN_RESERVED_ADDR1_MASK) < *base); + + /* On these platforms, the register doesn't have a size field, so the + * size is the distance between the base and the top of the stolen + * memory. We also have the genuine case where base is zero and there's + * nothing reserved. */ + if (*base == 0) + *size = 0; + else + *size = stolen_top - *base; +} + static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv, unsigned long *base, unsigned long *size) { @@ -281,7 +389,7 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv, int i915_gem_init_stolen(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long reserved_total, reserved_base, reserved_size; + unsigned long reserved_total, reserved_base = 0, reserved_size; unsigned long stolen_top; mutex_init(&dev_priv->mm.stolen_lock); @@ -305,7 +413,12 @@ int i915_gem_init_stolen(struct drm_device *dev) switch (INTEL_INFO(dev_priv)->gen) { case 2: case 3: + break; case 4: + if (IS_G4X(dev)) + g4x_get_stolen_reserved(dev_priv, &reserved_base, + &reserved_size); + break; case 5: /* Assume the gen6 maximum for the older platforms. */ reserved_size = 1024 * 1024; @@ -352,9 +465,21 @@ int i915_gem_init_stolen(struct drm_device *dev) dev_priv->gtt.stolen_size >> 10, (dev_priv->gtt.stolen_size - reserved_total) >> 10); - /* Basic memrange allocator for stolen space */ - drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_size - - reserved_total); + dev_priv->gtt.stolen_usable_size = dev_priv->gtt.stolen_size - + reserved_total; + + /* + * Basic memrange allocator for stolen space. + * + * TODO: Notice that some platforms require us to not use the first page + * of the stolen memory but their BIOSes may still put the framebuffer + * on the first page. So we don't reserve this page for now because of + * that. Our current solution is to just prevent new nodes from being + * inserted on the first page - see the check we have at + * i915_gem_stolen_insert_node_in_range(). We may want to fix the fbcon + * problem later. + */ + drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_usable_size); return 0; } @@ -544,7 +669,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, vma = i915_gem_obj_lookup_or_create_vma(obj, ggtt); if (IS_ERR(vma)) { ret = PTR_ERR(vma); - goto err_out; + goto err; } /* To simplify the initialisation sequence between KMS and GTT, @@ -558,23 +683,19 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, ret = drm_mm_reserve_node(&ggtt->mm, &vma->node); if (ret) { DRM_DEBUG_KMS("failed to allocate stolen GTT space\n"); - goto err_vma; + goto err; } - } - vma->bound |= GLOBAL_BIND; + vma->bound |= GLOBAL_BIND; + list_add_tail(&vma->mm_list, &ggtt->inactive_list); + } list_add_tail(&obj->global_list, &dev_priv->mm.bound_list); - list_add_tail(&vma->mm_list, &ggtt->inactive_list); i915_gem_object_pin_pages(obj); return obj; -err_vma: - i915_gem_vma_destroy(vma); -err_out: - i915_gem_stolen_remove_node(dev_priv, stolen); - kfree(stolen); +err: drm_gem_object_unreference(&obj->base); return NULL; } diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 8fd431b..1b3b451 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -50,7 +50,6 @@ struct i915_mmu_notifier { struct mmu_notifier mn; struct rb_root objects; struct list_head linear; - unsigned long serial; bool has_linear; }; @@ -59,13 +58,16 @@ struct i915_mmu_object { struct interval_tree_node it; struct list_head link; struct drm_i915_gem_object *obj; + struct work_struct work; + bool active; bool is_linear; }; -static unsigned long cancel_userptr(struct drm_i915_gem_object *obj) +static void __cancel_userptr__worker(struct work_struct *work) { + struct i915_mmu_object *mo = container_of(work, typeof(*mo), work); + struct drm_i915_gem_object *obj = mo->obj; struct drm_device *dev = obj->base.dev; - unsigned long end; mutex_lock(&dev->struct_mutex); /* Cancel any active worker and force us to re-evaluate gup */ @@ -88,45 +90,28 @@ static unsigned long cancel_userptr(struct drm_i915_gem_object *obj) dev_priv->mm.interruptible = was_interruptible; } - end = obj->userptr.ptr + obj->base.size; - drm_gem_object_unreference(&obj->base); mutex_unlock(&dev->struct_mutex); - - return end; } -static void *invalidate_range__linear(struct i915_mmu_notifier *mn, - struct mm_struct *mm, - unsigned long start, - unsigned long end) +static unsigned long cancel_userptr(struct i915_mmu_object *mo) { - struct i915_mmu_object *mo; - unsigned long serial; - -restart: - serial = mn->serial; - list_for_each_entry(mo, &mn->linear, link) { - struct drm_i915_gem_object *obj; - - if (mo->it.last < start || mo->it.start > end) - continue; - - obj = mo->obj; - - if (!kref_get_unless_zero(&obj->base.refcount)) - continue; - - spin_unlock(&mn->lock); - - cancel_userptr(obj); - - spin_lock(&mn->lock); - if (serial != mn->serial) - goto restart; + unsigned long end = mo->obj->userptr.ptr + mo->obj->base.size; + + /* The mmu_object is released late when destroying the + * GEM object so it is entirely possible to gain a + * reference on an object in the process of being freed + * since our serialisation is via the spinlock and not + * the struct_mutex - and consequently use it after it + * is freed and then double free it. + */ + if (mo->active && kref_get_unless_zero(&mo->obj->base.refcount)) { + schedule_work(&mo->work); + /* only schedule one work packet to avoid the refleak */ + mo->active = false; } - return NULL; + return end; } static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn, @@ -134,46 +119,32 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn, unsigned long start, unsigned long end) { - struct i915_mmu_notifier *mn = container_of(_mn, struct i915_mmu_notifier, mn); - struct interval_tree_node *it = NULL; - unsigned long next = start; - unsigned long serial = 0; - - end--; /* interval ranges are inclusive, but invalidate range is exclusive */ - while (next < end) { - struct drm_i915_gem_object *obj = NULL; - - spin_lock(&mn->lock); - if (mn->has_linear) - it = invalidate_range__linear(mn, mm, start, end); - else if (serial == mn->serial) - it = interval_tree_iter_next(it, next, end); - else - it = interval_tree_iter_first(&mn->objects, start, end); - if (it != NULL) { - obj = container_of(it, struct i915_mmu_object, it)->obj; - - /* The mmu_object is released late when destroying the - * GEM object so it is entirely possible to gain a - * reference on an object in the process of being freed - * since our serialisation is via the spinlock and not - * the struct_mutex - and consequently use it after it - * is freed and then double free it. - */ - if (!kref_get_unless_zero(&obj->base.refcount)) { - spin_unlock(&mn->lock); - serial = 0; + struct i915_mmu_notifier *mn = + container_of(_mn, struct i915_mmu_notifier, mn); + struct i915_mmu_object *mo; + + /* interval ranges are inclusive, but invalidate range is exclusive */ + end--; + + spin_lock(&mn->lock); + if (mn->has_linear) { + list_for_each_entry(mo, &mn->linear, link) { + if (mo->it.last < start || mo->it.start > end) continue; - } - serial = mn->serial; + cancel_userptr(mo); } - spin_unlock(&mn->lock); - if (obj == NULL) - return; + } else { + struct interval_tree_node *it; - next = cancel_userptr(obj); + it = interval_tree_iter_first(&mn->objects, start, end); + while (it) { + mo = container_of(it, struct i915_mmu_object, it); + start = cancel_userptr(mo); + it = interval_tree_iter_next(it, start, end); + } } + spin_unlock(&mn->lock); } static const struct mmu_notifier_ops i915_gem_userptr_notifier = { @@ -193,7 +164,6 @@ i915_mmu_notifier_create(struct mm_struct *mm) spin_lock_init(&mn->lock); mn->mn.ops = &i915_gem_userptr_notifier; mn->objects = RB_ROOT; - mn->serial = 1; INIT_LIST_HEAD(&mn->linear); mn->has_linear = false; @@ -207,12 +177,6 @@ i915_mmu_notifier_create(struct mm_struct *mm) return mn; } -static void __i915_mmu_notifier_update_serial(struct i915_mmu_notifier *mn) -{ - if (++mn->serial == 0) - mn->serial = 1; -} - static int i915_mmu_notifier_add(struct drm_device *dev, struct i915_mmu_notifier *mn, @@ -259,10 +223,9 @@ i915_mmu_notifier_add(struct drm_device *dev, } else interval_tree_insert(&mo->it, &mn->objects); - if (ret == 0) { + if (ret == 0) list_add(&mo->link, &mn->linear); - __i915_mmu_notifier_update_serial(mn); - } + spin_unlock(&mn->lock); mutex_unlock(&dev->struct_mutex); @@ -290,7 +253,6 @@ i915_mmu_notifier_del(struct i915_mmu_notifier *mn, mn->has_linear = i915_mmu_notifier_has_linear(mn); else interval_tree_remove(&mo->it, &mn->objects); - __i915_mmu_notifier_update_serial(mn); spin_unlock(&mn->lock); } @@ -357,6 +319,7 @@ i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj, mo->it.start = obj->userptr.ptr; mo->it.last = mo->it.start + obj->base.size - 1; mo->obj = obj; + INIT_WORK(&mo->work, __cancel_userptr__worker); ret = i915_mmu_notifier_add(obj->base.dev, mn, mo); if (ret) { @@ -565,31 +528,65 @@ __i915_gem_userptr_set_pages(struct drm_i915_gem_object *obj, return ret; } +static int +__i915_gem_userptr_set_active(struct drm_i915_gem_object *obj, + bool value) +{ + int ret = 0; + + /* During mm_invalidate_range we need to cancel any userptr that + * overlaps the range being invalidated. Doing so requires the + * struct_mutex, and that risks recursion. In order to cause + * recursion, the user must alias the userptr address space with + * a GTT mmapping (possible with a MAP_FIXED) - then when we have + * to invalidate that mmaping, mm_invalidate_range is called with + * the userptr address *and* the struct_mutex held. To prevent that + * we set a flag under the i915_mmu_notifier spinlock to indicate + * whether this object is valid. + */ +#if defined(CONFIG_MMU_NOTIFIER) + if (obj->userptr.mmu_object == NULL) + return 0; + + spin_lock(&obj->userptr.mmu_object->mn->lock); + /* In order to serialise get_pages with an outstanding + * cancel_userptr, we must drop the struct_mutex and try again. + */ + if (!value || !work_pending(&obj->userptr.mmu_object->work)) + obj->userptr.mmu_object->active = value; + else + ret = -EAGAIN; + spin_unlock(&obj->userptr.mmu_object->mn->lock); +#endif + + return ret; +} + static void __i915_gem_userptr_get_pages_worker(struct work_struct *_work) { struct get_pages_work *work = container_of(_work, typeof(*work), work); struct drm_i915_gem_object *obj = work->obj; struct drm_device *dev = obj->base.dev; - const int num_pages = obj->base.size >> PAGE_SHIFT; + const int npages = obj->base.size >> PAGE_SHIFT; struct page **pvec; int pinned, ret; ret = -ENOMEM; pinned = 0; - pvec = kmalloc(num_pages*sizeof(struct page *), + pvec = kmalloc(npages*sizeof(struct page *), GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); if (pvec == NULL) - pvec = drm_malloc_ab(num_pages, sizeof(struct page *)); + pvec = drm_malloc_ab(npages, sizeof(struct page *)); if (pvec != NULL) { struct mm_struct *mm = obj->userptr.mm->mm; down_read(&mm->mmap_sem); - while (pinned < num_pages) { + while (pinned < npages) { ret = get_user_pages(work->task, mm, obj->userptr.ptr + pinned * PAGE_SIZE, - num_pages - pinned, + npages - pinned, !obj->userptr.read_only, 0, pvec + pinned, NULL); if (ret < 0) @@ -601,20 +598,22 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) } mutex_lock(&dev->struct_mutex); - if (obj->userptr.work != &work->work) { - ret = 0; - } else if (pinned == num_pages) { - ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages); - if (ret == 0) { - list_add_tail(&obj->global_list, &to_i915(dev)->mm.unbound_list); - obj->get_page.sg = obj->pages->sgl; - obj->get_page.last = 0; - - pinned = 0; + if (obj->userptr.work == &work->work) { + if (pinned == npages) { + ret = __i915_gem_userptr_set_pages(obj, pvec, npages); + if (ret == 0) { + list_add_tail(&obj->global_list, + &to_i915(dev)->mm.unbound_list); + obj->get_page.sg = obj->pages->sgl; + obj->get_page.last = 0; + pinned = 0; + } } + obj->userptr.work = ERR_PTR(ret); + if (ret) + __i915_gem_userptr_set_active(obj, false); } - obj->userptr.work = ERR_PTR(ret); obj->userptr.workers--; drm_gem_object_unreference(&obj->base); mutex_unlock(&dev->struct_mutex); @@ -627,11 +626,60 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) } static int +__i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj, + bool *active) +{ + struct get_pages_work *work; + + /* Spawn a worker so that we can acquire the + * user pages without holding our mutex. Access + * to the user pages requires mmap_sem, and we have + * a strict lock ordering of mmap_sem, struct_mutex - + * we already hold struct_mutex here and so cannot + * call gup without encountering a lock inversion. + * + * Userspace will keep on repeating the operation + * (thanks to EAGAIN) until either we hit the fast + * path or the worker completes. If the worker is + * cancelled or superseded, the task is still run + * but the results ignored. (This leads to + * complications that we may have a stray object + * refcount that we need to be wary of when + * checking for existing objects during creation.) + * If the worker encounters an error, it reports + * that error back to this function through + * obj->userptr.work = ERR_PTR. + */ + if (obj->userptr.workers >= I915_GEM_USERPTR_MAX_WORKERS) + return -EAGAIN; + + work = kmalloc(sizeof(*work), GFP_KERNEL); + if (work == NULL) + return -ENOMEM; + + obj->userptr.work = &work->work; + obj->userptr.workers++; + + work->obj = obj; + drm_gem_object_reference(&obj->base); + + work->task = current; + get_task_struct(work->task); + + INIT_WORK(&work->work, __i915_gem_userptr_get_pages_worker); + schedule_work(&work->work); + + *active = true; + return -EAGAIN; +} + +static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) { const int num_pages = obj->base.size >> PAGE_SHIFT; struct page **pvec; int pinned, ret; + bool active; /* If userspace should engineer that these pages are replaced in * the vma between us binding this page into the GTT and completion @@ -649,6 +697,20 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) * to the vma (discard or cloning) which should prevent the more * egregious cases from causing harm. */ + if (IS_ERR(obj->userptr.work)) { + /* active flag will have been dropped already by the worker */ + ret = PTR_ERR(obj->userptr.work); + obj->userptr.work = NULL; + return ret; + } + if (obj->userptr.work) + /* active flag should still be held for the pending work */ + return -EAGAIN; + + /* Let the mmu-notifier know that we have begun and need cancellation */ + ret = __i915_gem_userptr_set_active(obj, true); + if (ret) + return ret; pvec = NULL; pinned = 0; @@ -657,73 +719,27 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); if (pvec == NULL) { pvec = drm_malloc_ab(num_pages, sizeof(struct page *)); - if (pvec == NULL) + if (pvec == NULL) { + __i915_gem_userptr_set_active(obj, false); return -ENOMEM; + } } pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages, !obj->userptr.read_only, pvec); } - if (pinned < num_pages) { - if (pinned < 0) { - ret = pinned; - pinned = 0; - } else { - /* Spawn a worker so that we can acquire the - * user pages without holding our mutex. Access - * to the user pages requires mmap_sem, and we have - * a strict lock ordering of mmap_sem, struct_mutex - - * we already hold struct_mutex here and so cannot - * call gup without encountering a lock inversion. - * - * Userspace will keep on repeating the operation - * (thanks to EAGAIN) until either we hit the fast - * path or the worker completes. If the worker is - * cancelled or superseded, the task is still run - * but the results ignored. (This leads to - * complications that we may have a stray object - * refcount that we need to be wary of when - * checking for existing objects during creation.) - * If the worker encounters an error, it reports - * that error back to this function through - * obj->userptr.work = ERR_PTR. - */ - ret = -EAGAIN; - if (obj->userptr.work == NULL && - obj->userptr.workers < I915_GEM_USERPTR_MAX_WORKERS) { - struct get_pages_work *work; - - work = kmalloc(sizeof(*work), GFP_KERNEL); - if (work != NULL) { - obj->userptr.work = &work->work; - obj->userptr.workers++; - - work->obj = obj; - drm_gem_object_reference(&obj->base); - - work->task = current; - get_task_struct(work->task); - - INIT_WORK(&work->work, __i915_gem_userptr_get_pages_worker); - schedule_work(&work->work); - } else - ret = -ENOMEM; - } else { - if (IS_ERR(obj->userptr.work)) { - ret = PTR_ERR(obj->userptr.work); - obj->userptr.work = NULL; - } - } - } - } else { + + active = false; + if (pinned < 0) + ret = pinned, pinned = 0; + else if (pinned < num_pages) + ret = __i915_gem_userptr_get_pages_schedule(obj, &active); + else ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages); - if (ret == 0) { - obj->userptr.work = NULL; - pinned = 0; - } + if (ret) { + __i915_gem_userptr_set_active(obj, active); + release_pages(pvec, pinned, 0); } - - release_pages(pvec, pinned, 0); drm_free_large(pvec); return ret; } @@ -734,6 +750,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj) struct sg_page_iter sg_iter; BUG_ON(obj->userptr.work != NULL); + __i915_gem_userptr_set_active(obj, false); if (obj->madv != I915_MADV_WILLNEED) obj->dirty = 0; @@ -813,7 +830,6 @@ static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = { int i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { - struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_userptr *args = data; struct drm_i915_gem_object *obj; int ret; @@ -826,9 +842,6 @@ i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file if (offset_in_page(args->user_ptr | args->user_size)) return -EINVAL; - if (args->user_size > dev_priv->gtt.base.total) - return -E2BIG; - if (!access_ok(args->flags & I915_USERPTR_READ_ONLY ? VERIFY_READ : VERIFY_WRITE, (char __user *)(unsigned long)args->user_ptr, args->user_size)) return -EFAULT; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 41d0739..2f04e4f 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -30,11 +30,6 @@ #include <generated/utsrelease.h> #include "i915_drv.h" -static const char *yesno(int v) -{ - return v ? "yes" : "no"; -} - static const char *ring_str(int ring) { switch (ring) { @@ -197,8 +192,9 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m, err_printf(m, " %s [%d]:\n", name, count); while (count--) { - err_printf(m, " %08x %8u %02x %02x [ ", - err->gtt_offset, + err_printf(m, " %08x_%08x %8u %02x %02x [ ", + upper_32_bits(err->gtt_offset), + lower_32_bits(err->gtt_offset), err->size, err->read_domains, err->write_domain); @@ -427,15 +423,17 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, err_printf(m, " (submitted by %s [%d])", error->ring[i].comm, error->ring[i].pid); - err_printf(m, " --- gtt_offset = 0x%08x\n", - obj->gtt_offset); + err_printf(m, " --- gtt_offset = 0x%08x %08x\n", + upper_32_bits(obj->gtt_offset), + lower_32_bits(obj->gtt_offset)); print_error_obj(m, obj); } obj = error->ring[i].wa_batchbuffer; if (obj) { err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n", - dev_priv->ring[i].name, obj->gtt_offset); + dev_priv->ring[i].name, + lower_32_bits(obj->gtt_offset)); print_error_obj(m, obj); } @@ -454,22 +452,28 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, if ((obj = error->ring[i].ringbuffer)) { err_printf(m, "%s --- ringbuffer = 0x%08x\n", dev_priv->ring[i].name, - obj->gtt_offset); + lower_32_bits(obj->gtt_offset)); print_error_obj(m, obj); } if ((obj = error->ring[i].hws_page)) { - err_printf(m, "%s --- HW Status = 0x%08x\n", - dev_priv->ring[i].name, - obj->gtt_offset); + u64 hws_offset = obj->gtt_offset; + u32 *hws_page = &obj->pages[0][0]; + + if (i915.enable_execlists) { + hws_offset += LRC_PPHWSP_PN * PAGE_SIZE; + hws_page = &obj->pages[LRC_PPHWSP_PN][0]; + } + err_printf(m, "%s --- HW Status = 0x%08llx\n", + dev_priv->ring[i].name, hws_offset); offset = 0; for (elt = 0; elt < PAGE_SIZE/16; elt += 4) { err_printf(m, "[%04x] %08x %08x %08x %08x\n", offset, - obj->pages[0][elt], - obj->pages[0][elt+1], - obj->pages[0][elt+2], - obj->pages[0][elt+3]); + hws_page[elt], + hws_page[elt+1], + hws_page[elt+2], + hws_page[elt+3]); offset += 16; } } @@ -477,13 +481,14 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, if ((obj = error->ring[i].ctx)) { err_printf(m, "%s --- HW Context = 0x%08x\n", dev_priv->ring[i].name, - obj->gtt_offset); + lower_32_bits(obj->gtt_offset)); print_error_obj(m, obj); } } if ((obj = error->semaphore_obj)) { - err_printf(m, "Semaphore page = 0x%08x\n", obj->gtt_offset); + err_printf(m, "Semaphore page = 0x%08x\n", + lower_32_bits(obj->gtt_offset)); for (elt = 0; elt < PAGE_SIZE/16; elt += 4) { err_printf(m, "[%04x] %08x %08x %08x %08x\n", elt * 4, @@ -591,7 +596,7 @@ i915_error_object_create(struct drm_i915_private *dev_priv, int num_pages; bool use_ggtt; int i = 0; - u32 reloc_offset; + u64 reloc_offset; if (src == NULL || src->pages == NULL) return NULL; @@ -787,20 +792,15 @@ static void i915_gem_record_fences(struct drm_device *dev, int i; if (IS_GEN3(dev) || IS_GEN2(dev)) { - for (i = 0; i < 8; i++) - error->fence[i] = I915_READ(FENCE_REG_830_0 + (i * 4)); - if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) - for (i = 0; i < 8; i++) - error->fence[i+8] = I915_READ(FENCE_REG_945_8 + - (i * 4)); - } else if (IS_GEN5(dev) || IS_GEN4(dev)) - for (i = 0; i < 16; i++) - error->fence[i] = I915_READ64(FENCE_REG_965_0 + - (i * 8)); - else if (INTEL_INFO(dev)->gen >= 6) for (i = 0; i < dev_priv->num_fence_regs; i++) - error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + - (i * 8)); + error->fence[i] = I915_READ(FENCE_REG(i)); + } else if (IS_GEN5(dev) || IS_GEN4(dev)) { + for (i = 0; i < dev_priv->num_fence_regs; i++) + error->fence[i] = I915_READ64(FENCE_REG_965_LO(i)); + } else if (INTEL_INFO(dev)->gen >= 6) { + for (i = 0; i < dev_priv->num_fence_regs; i++) + error->fence[i] = I915_READ64(FENCE_REG_GEN6_LO(i)); + } } @@ -886,7 +886,7 @@ static void i915_record_ring_state(struct drm_device *dev, ering->faddr = I915_READ(DMA_FADD_I8XX); ering->ipeir = I915_READ(IPEIR); ering->ipehr = I915_READ(IPEHR); - ering->instdone = I915_READ(INSTDONE); + ering->instdone = I915_READ(GEN2_INSTDONE); } ering->waiting = waitqueue_active(&ring->irq_queue); @@ -1388,12 +1388,12 @@ void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone) memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG); if (IS_GEN2(dev) || IS_GEN3(dev)) - instdone[0] = I915_READ(INSTDONE); + instdone[0] = I915_READ(GEN2_INSTDONE); else if (IS_GEN4(dev) || IS_GEN5(dev) || IS_GEN6(dev)) { - instdone[0] = I915_READ(INSTDONE_I965); - instdone[1] = I915_READ(INSTDONE1); + instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE)); + instdone[1] = I915_READ(GEN4_INSTDONE1); } else if (INTEL_INFO(dev)->gen >= 7) { - instdone[0] = I915_READ(GEN7_INSTDONE_1); + instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE)); instdone[1] = I915_READ(GEN7_SC_INSTDONE); instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE); instdone[3] = I915_READ(GEN7_ROW_INSTDONE); diff --git a/drivers/gpu/drm/i915/i915_guc_reg.h b/drivers/gpu/drm/i915/i915_guc_reg.h index ccdc6c8..c4cb1c0 100644 --- a/drivers/gpu/drm/i915/i915_guc_reg.h +++ b/drivers/gpu/drm/i915/i915_guc_reg.h @@ -37,14 +37,11 @@ #define GS_UKERNEL_READY (0xF0 << GS_UKERNEL_SHIFT) #define GS_MIA_SHIFT 16 #define GS_MIA_MASK (0x07 << GS_MIA_SHIFT) - -#define GUC_WOPCM_SIZE 0xc050 -#define GUC_WOPCM_SIZE_VALUE (0x80 << 12) /* 512KB */ -#define GUC_WOPCM_OFFSET 0x80000 /* 512KB */ +#define GS_MIA_CORE_STATE (1 << GS_MIA_SHIFT) #define SOFT_SCRATCH(n) (0xc180 + ((n) * 4)) -#define UOS_RSA_SCRATCH_0 0xc200 +#define UOS_RSA_SCRATCH(i) (0xc200 + (i) * 4) #define DMA_ADDR_0_LOW 0xc300 #define DMA_ADDR_0_HIGH 0xc304 #define DMA_ADDR_1_LOW 0xc308 @@ -56,10 +53,19 @@ #define UOS_MOVE (1<<4) #define START_DMA (1<<0) #define DMA_GUC_WOPCM_OFFSET 0xc340 +#define GUC_WOPCM_OFFSET_VALUE 0x80000 /* 512KB */ +#define GUC_MAX_IDLE_COUNT 0xC3E4 + +#define GUC_WOPCM_SIZE 0xc050 +#define GUC_WOPCM_SIZE_VALUE (0x80 << 12) /* 512KB */ + +/* GuC addresses below GUC_WOPCM_TOP don't map through the GTT */ +#define GUC_WOPCM_TOP (GUC_WOPCM_SIZE_VALUE) #define GEN8_GT_PM_CONFIG 0x138140 +#define GEN9LP_GT_PM_CONFIG 0x138140 #define GEN9_GT_PM_CONFIG 0x13816c -#define GEN8_GT_DOORBELL_ENABLE (1<<0) +#define GT_DOORBELL_ENABLE (1<<0) #define GEN8_GTCR 0x4274 #define GEN8_GTCR_INVALIDATE (1<<0) @@ -80,7 +86,8 @@ GUC_ENABLE_READ_CACHE_LOGIC | \ GUC_ENABLE_MIA_CACHING | \ GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA | \ - GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA) + GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA | \ + GUC_ENABLE_MIA_CLOCK_GATING) #define HOST2GUC_INTERRUPT 0xc4c8 #define HOST2GUC_TRIGGER (1<<0) diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c new file mode 100644 index 0000000..036b42b --- /dev/null +++ b/drivers/gpu/drm/i915/i915_guc_submission.c @@ -0,0 +1,975 @@ +/* + * Copyright © 2014 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ +#include <linux/firmware.h> +#include <linux/circ_buf.h> +#include "i915_drv.h" +#include "intel_guc.h" + +/** + * DOC: GuC Client + * + * i915_guc_client: + * We use the term client to avoid confusion with contexts. A i915_guc_client is + * equivalent to GuC object guc_context_desc. This context descriptor is + * allocated from a pool of 1024 entries. Kernel driver will allocate doorbell + * and workqueue for it. Also the process descriptor (guc_process_desc), which + * is mapped to client space. So the client can write Work Item then ring the + * doorbell. + * + * To simplify the implementation, we allocate one gem object that contains all + * pages for doorbell, process descriptor and workqueue. + * + * The Scratch registers: + * There are 16 MMIO-based registers start from 0xC180. The kernel driver writes + * a value to the action register (SOFT_SCRATCH_0) along with any data. It then + * triggers an interrupt on the GuC via another register write (0xC4C8). + * Firmware writes a success/fail code back to the action register after + * processes the request. The kernel driver polls waiting for this update and + * then proceeds. + * See host2guc_action() + * + * Doorbells: + * Doorbells are interrupts to uKernel. A doorbell is a single cache line (QW) + * mapped into process space. + * + * Work Items: + * There are several types of work items that the host may place into a + * workqueue, each with its own requirements and limitations. Currently only + * WQ_TYPE_INORDER is needed to support legacy submission via GuC, which + * represents in-order queue. The kernel driver packs ring tail pointer and an + * ELSP context descriptor dword into Work Item. + * See guc_add_workqueue_item() + * + */ + +/* + * Read GuC command/status register (SOFT_SCRATCH_0) + * Return true if it contains a response rather than a command + */ +static inline bool host2guc_action_response(struct drm_i915_private *dev_priv, + u32 *status) +{ + u32 val = I915_READ(SOFT_SCRATCH(0)); + *status = val; + return GUC2HOST_IS_RESPONSE(val); +} + +static int host2guc_action(struct intel_guc *guc, u32 *data, u32 len) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + u32 status; + int i; + int ret; + + if (WARN_ON(len < 1 || len > 15)) + return -EINVAL; + + intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + spin_lock(&dev_priv->guc.host2guc_lock); + + dev_priv->guc.action_count += 1; + dev_priv->guc.action_cmd = data[0]; + + for (i = 0; i < len; i++) + I915_WRITE(SOFT_SCRATCH(i), data[i]); + + POSTING_READ(SOFT_SCRATCH(i - 1)); + + I915_WRITE(HOST2GUC_INTERRUPT, HOST2GUC_TRIGGER); + + /* No HOST2GUC command should take longer than 10ms */ + ret = wait_for_atomic(host2guc_action_response(dev_priv, &status), 10); + if (status != GUC2HOST_STATUS_SUCCESS) { + /* + * Either the GuC explicitly returned an error (which + * we convert to -EIO here) or no response at all was + * received within the timeout limit (-ETIMEDOUT) + */ + if (ret != -ETIMEDOUT) + ret = -EIO; + + DRM_ERROR("GUC: host2guc action 0x%X failed. ret=%d " + "status=0x%08X response=0x%08X\n", + data[0], ret, status, + I915_READ(SOFT_SCRATCH(15))); + + dev_priv->guc.action_fail += 1; + dev_priv->guc.action_err = ret; + } + dev_priv->guc.action_status = status; + + spin_unlock(&dev_priv->guc.host2guc_lock); + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + + return ret; +} + +/* + * Tell the GuC to allocate or deallocate a specific doorbell + */ + +static int host2guc_allocate_doorbell(struct intel_guc *guc, + struct i915_guc_client *client) +{ + u32 data[2]; + + data[0] = HOST2GUC_ACTION_ALLOCATE_DOORBELL; + data[1] = client->ctx_index; + + return host2guc_action(guc, data, 2); +} + +static int host2guc_release_doorbell(struct intel_guc *guc, + struct i915_guc_client *client) +{ + u32 data[2]; + + data[0] = HOST2GUC_ACTION_DEALLOCATE_DOORBELL; + data[1] = client->ctx_index; + + return host2guc_action(guc, data, 2); +} + +static int host2guc_sample_forcewake(struct intel_guc *guc, + struct i915_guc_client *client) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct drm_device *dev = dev_priv->dev; + u32 data[2]; + + data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE; + /* WaRsDisableCoarsePowerGating:skl,bxt */ + if (!intel_enable_rc6(dev_priv->dev) || + (IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) || + (IS_SKL_GT3(dev) && (INTEL_REVID(dev) <= SKL_REVID_E0)) || + (IS_SKL_GT4(dev) && (INTEL_REVID(dev) <= SKL_REVID_E0))) + data[1] = 0; + else + /* bit 0 and 1 are for Render and Media domain separately */ + data[1] = GUC_FORCEWAKE_RENDER | GUC_FORCEWAKE_MEDIA; + + return host2guc_action(guc, data, ARRAY_SIZE(data)); +} + +/* + * Initialise, update, or clear doorbell data shared with the GuC + * + * These functions modify shared data and so need access to the mapped + * client object which contains the page being used for the doorbell + */ + +static void guc_init_doorbell(struct intel_guc *guc, + struct i915_guc_client *client) +{ + struct guc_doorbell_info *doorbell; + void *base; + + base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0)); + doorbell = base + client->doorbell_offset; + + doorbell->db_status = 1; + doorbell->cookie = 0; + + kunmap_atomic(base); +} + +static int guc_ring_doorbell(struct i915_guc_client *gc) +{ + struct guc_process_desc *desc; + union guc_doorbell_qw db_cmp, db_exc, db_ret; + union guc_doorbell_qw *db; + void *base; + int attempt = 2, ret = -EAGAIN; + + base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0)); + desc = base + gc->proc_desc_offset; + + /* Update the tail so it is visible to GuC */ + desc->tail = gc->wq_tail; + + /* current cookie */ + db_cmp.db_status = GUC_DOORBELL_ENABLED; + db_cmp.cookie = gc->cookie; + + /* cookie to be updated */ + db_exc.db_status = GUC_DOORBELL_ENABLED; + db_exc.cookie = gc->cookie + 1; + if (db_exc.cookie == 0) + db_exc.cookie = 1; + + /* pointer of current doorbell cacheline */ + db = base + gc->doorbell_offset; + + while (attempt--) { + /* lets ring the doorbell */ + db_ret.value_qw = atomic64_cmpxchg((atomic64_t *)db, + db_cmp.value_qw, db_exc.value_qw); + + /* if the exchange was successfully executed */ + if (db_ret.value_qw == db_cmp.value_qw) { + /* db was successfully rung */ + gc->cookie = db_exc.cookie; + ret = 0; + break; + } + + /* XXX: doorbell was lost and need to acquire it again */ + if (db_ret.db_status == GUC_DOORBELL_DISABLED) + break; + + DRM_ERROR("Cookie mismatch. Expected %d, returned %d\n", + db_cmp.cookie, db_ret.cookie); + + /* update the cookie to newly read cookie from GuC */ + db_cmp.cookie = db_ret.cookie; + db_exc.cookie = db_ret.cookie + 1; + if (db_exc.cookie == 0) + db_exc.cookie = 1; + } + + kunmap_atomic(base); + return ret; +} + +static void guc_disable_doorbell(struct intel_guc *guc, + struct i915_guc_client *client) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct guc_doorbell_info *doorbell; + void *base; + int drbreg = GEN8_DRBREGL(client->doorbell_id); + int value; + + base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0)); + doorbell = base + client->doorbell_offset; + + doorbell->db_status = 0; + + kunmap_atomic(base); + + I915_WRITE(drbreg, I915_READ(drbreg) & ~GEN8_DRB_VALID); + + value = I915_READ(drbreg); + WARN_ON((value & GEN8_DRB_VALID) != 0); + + I915_WRITE(GEN8_DRBREGU(client->doorbell_id), 0); + I915_WRITE(drbreg, 0); + + /* XXX: wait for any interrupts */ + /* XXX: wait for workqueue to drain */ +} + +/* + * Select, assign and relase doorbell cachelines + * + * These functions track which doorbell cachelines are in use. + * The data they manipulate is protected by the host2guc lock. + */ + +static uint32_t select_doorbell_cacheline(struct intel_guc *guc) +{ + const uint32_t cacheline_size = cache_line_size(); + uint32_t offset; + + spin_lock(&guc->host2guc_lock); + + /* Doorbell uses a single cache line within a page */ + offset = offset_in_page(guc->db_cacheline); + + /* Moving to next cache line to reduce contention */ + guc->db_cacheline += cacheline_size; + + spin_unlock(&guc->host2guc_lock); + + DRM_DEBUG_DRIVER("selected doorbell cacheline 0x%x, next 0x%x, linesize %u\n", + offset, guc->db_cacheline, cacheline_size); + + return offset; +} + +static uint16_t assign_doorbell(struct intel_guc *guc, uint32_t priority) +{ + /* + * The bitmap is split into two halves; the first half is used for + * normal priority contexts, the second half for high-priority ones. + * Note that logically higher priorities are numerically less than + * normal ones, so the test below means "is it high-priority?" + */ + const bool hi_pri = (priority <= GUC_CTX_PRIORITY_HIGH); + const uint16_t half = GUC_MAX_DOORBELLS / 2; + const uint16_t start = hi_pri ? half : 0; + const uint16_t end = start + half; + uint16_t id; + + spin_lock(&guc->host2guc_lock); + id = find_next_zero_bit(guc->doorbell_bitmap, end, start); + if (id == end) + id = GUC_INVALID_DOORBELL_ID; + else + bitmap_set(guc->doorbell_bitmap, id, 1); + spin_unlock(&guc->host2guc_lock); + + DRM_DEBUG_DRIVER("assigned %s priority doorbell id 0x%x\n", + hi_pri ? "high" : "normal", id); + + return id; +} + +static void release_doorbell(struct intel_guc *guc, uint16_t id) +{ + spin_lock(&guc->host2guc_lock); + bitmap_clear(guc->doorbell_bitmap, id, 1); + spin_unlock(&guc->host2guc_lock); +} + +/* + * Initialise the process descriptor shared with the GuC firmware. + */ +static void guc_init_proc_desc(struct intel_guc *guc, + struct i915_guc_client *client) +{ + struct guc_process_desc *desc; + void *base; + + base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0)); + desc = base + client->proc_desc_offset; + + memset(desc, 0, sizeof(*desc)); + + /* + * XXX: pDoorbell and WQVBaseAddress are pointers in process address + * space for ring3 clients (set them as in mmap_ioctl) or kernel + * space for kernel clients (map on demand instead? May make debug + * easier to have it mapped). + */ + desc->wq_base_addr = 0; + desc->db_base_addr = 0; + + desc->context_id = client->ctx_index; + desc->wq_size_bytes = client->wq_size; + desc->wq_status = WQ_STATUS_ACTIVE; + desc->priority = client->priority; + + kunmap_atomic(base); +} + +/* + * Initialise/clear the context descriptor shared with the GuC firmware. + * + * This descriptor tells the GuC where (in GGTT space) to find the important + * data structures relating to this client (doorbell, process descriptor, + * write queue, etc). + */ + +static void guc_init_ctx_desc(struct intel_guc *guc, + struct i915_guc_client *client) +{ + struct intel_context *ctx = client->owner; + struct guc_context_desc desc; + struct sg_table *sg; + int i; + + memset(&desc, 0, sizeof(desc)); + + desc.attribute = GUC_CTX_DESC_ATTR_ACTIVE | GUC_CTX_DESC_ATTR_KERNEL; + desc.context_id = client->ctx_index; + desc.priority = client->priority; + desc.db_id = client->doorbell_id; + + for (i = 0; i < I915_NUM_RINGS; i++) { + struct guc_execlist_context *lrc = &desc.lrc[i]; + struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf; + struct intel_engine_cs *ring; + struct drm_i915_gem_object *obj; + uint64_t ctx_desc; + + /* TODO: We have a design issue to be solved here. Only when we + * receive the first batch, we know which engine is used by the + * user. But here GuC expects the lrc and ring to be pinned. It + * is not an issue for default context, which is the only one + * for now who owns a GuC client. But for future owner of GuC + * client, need to make sure lrc is pinned prior to enter here. + */ + obj = ctx->engine[i].state; + if (!obj) + break; /* XXX: continue? */ + + ring = ringbuf->ring; + ctx_desc = intel_lr_context_descriptor(ctx, ring); + lrc->context_desc = (u32)ctx_desc; + + /* The state page is after PPHWSP */ + lrc->ring_lcra = i915_gem_obj_ggtt_offset(obj) + + LRC_STATE_PN * PAGE_SIZE; + lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) | + (ring->id << GUC_ELC_ENGINE_OFFSET); + + obj = ringbuf->obj; + + lrc->ring_begin = i915_gem_obj_ggtt_offset(obj); + lrc->ring_end = lrc->ring_begin + obj->base.size - 1; + lrc->ring_next_free_location = lrc->ring_begin; + lrc->ring_current_tail_pointer_value = 0; + + desc.engines_used |= (1 << ring->id); + } + + WARN_ON(desc.engines_used == 0); + + /* + * The CPU address is only needed at certain points, so kmap_atomic on + * demand instead of storing it in the ctx descriptor. + * XXX: May make debug easier to have it mapped + */ + desc.db_trigger_cpu = 0; + desc.db_trigger_uk = client->doorbell_offset + + i915_gem_obj_ggtt_offset(client->client_obj); + desc.db_trigger_phy = client->doorbell_offset + + sg_dma_address(client->client_obj->pages->sgl); + + desc.process_desc = client->proc_desc_offset + + i915_gem_obj_ggtt_offset(client->client_obj); + + desc.wq_addr = client->wq_offset + + i915_gem_obj_ggtt_offset(client->client_obj); + + desc.wq_size = client->wq_size; + + /* + * XXX: Take LRCs from an existing intel_context if this is not an + * IsKMDCreatedContext client + */ + desc.desc_private = (uintptr_t)client; + + /* Pool context is pinned already */ + sg = guc->ctx_pool_obj->pages; + sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc), + sizeof(desc) * client->ctx_index); +} + +static void guc_fini_ctx_desc(struct intel_guc *guc, + struct i915_guc_client *client) +{ + struct guc_context_desc desc; + struct sg_table *sg; + + memset(&desc, 0, sizeof(desc)); + + sg = guc->ctx_pool_obj->pages; + sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc), + sizeof(desc) * client->ctx_index); +} + +/* Get valid workqueue item and return it back to offset */ +static int guc_get_workqueue_space(struct i915_guc_client *gc, u32 *offset) +{ + struct guc_process_desc *desc; + void *base; + u32 size = sizeof(struct guc_wq_item); + int ret = 0, timeout_counter = 200; + + base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0)); + desc = base + gc->proc_desc_offset; + + while (timeout_counter-- > 0) { + ret = wait_for_atomic(CIRC_SPACE(gc->wq_tail, desc->head, + gc->wq_size) >= size, 1); + + if (!ret) { + *offset = gc->wq_tail; + + /* advance the tail for next workqueue item */ + gc->wq_tail += size; + gc->wq_tail &= gc->wq_size - 1; + + /* this will break the loop */ + timeout_counter = 0; + } + }; + + kunmap_atomic(base); + + return ret; +} + +static int guc_add_workqueue_item(struct i915_guc_client *gc, + struct drm_i915_gem_request *rq) +{ + enum intel_ring_id ring_id = rq->ring->id; + struct guc_wq_item *wqi; + void *base; + u32 tail, wq_len, wq_off = 0; + int ret; + + ret = guc_get_workqueue_space(gc, &wq_off); + if (ret) + return ret; + + /* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we + * should not have the case where structure wqi is across page, neither + * wrapped to the beginning. This simplifies the implementation below. + * + * XXX: if not the case, we need save data to a temp wqi and copy it to + * workqueue buffer dw by dw. + */ + WARN_ON(sizeof(struct guc_wq_item) != 16); + WARN_ON(wq_off & 3); + + /* wq starts from the page after doorbell / process_desc */ + base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, + (wq_off + GUC_DB_SIZE) >> PAGE_SHIFT)); + wq_off &= PAGE_SIZE - 1; + wqi = (struct guc_wq_item *)((char *)base + wq_off); + + /* len does not include the header */ + wq_len = sizeof(struct guc_wq_item) / sizeof(u32) - 1; + wqi->header = WQ_TYPE_INORDER | + (wq_len << WQ_LEN_SHIFT) | + (ring_id << WQ_TARGET_SHIFT) | + WQ_NO_WCFLUSH_WAIT; + + /* The GuC wants only the low-order word of the context descriptor */ + wqi->context_desc = (u32)intel_lr_context_descriptor(rq->ctx, rq->ring); + + /* The GuC firmware wants the tail index in QWords, not bytes */ + tail = rq->ringbuf->tail >> 3; + wqi->ring_tail = tail << WQ_RING_TAIL_SHIFT; + wqi->fence_id = 0; /*XXX: what fence to be here */ + + kunmap_atomic(base); + + return 0; +} + +#define CTX_RING_BUFFER_START 0x08 + +/* Update the ringbuffer pointer in a saved context image */ +static void lr_context_update(struct drm_i915_gem_request *rq) +{ + enum intel_ring_id ring_id = rq->ring->id; + struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring_id].state; + struct drm_i915_gem_object *rb_obj = rq->ringbuf->obj; + struct page *page; + uint32_t *reg_state; + + BUG_ON(!ctx_obj); + WARN_ON(!i915_gem_obj_is_pinned(ctx_obj)); + WARN_ON(!i915_gem_obj_is_pinned(rb_obj)); + + page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN); + reg_state = kmap_atomic(page); + + reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj); + + kunmap_atomic(reg_state); +} + +/** + * i915_guc_submit() - Submit commands through GuC + * @client: the guc client where commands will go through + * @ctx: LRC where commands come from + * @ring: HW engine that will excute the commands + * + * Return: 0 if succeed + */ +int i915_guc_submit(struct i915_guc_client *client, + struct drm_i915_gem_request *rq) +{ + struct intel_guc *guc = client->guc; + enum intel_ring_id ring_id = rq->ring->id; + unsigned long flags; + int q_ret, b_ret; + + /* Need this because of the deferred pin ctx and ring */ + /* Shall we move this right after ring is pinned? */ + lr_context_update(rq); + + spin_lock_irqsave(&client->wq_lock, flags); + + q_ret = guc_add_workqueue_item(client, rq); + if (q_ret == 0) + b_ret = guc_ring_doorbell(client); + + client->submissions[ring_id] += 1; + if (q_ret) { + client->q_fail += 1; + client->retcode = q_ret; + } else if (b_ret) { + client->b_fail += 1; + client->retcode = q_ret = b_ret; + } else { + client->retcode = 0; + } + spin_unlock_irqrestore(&client->wq_lock, flags); + + spin_lock(&guc->host2guc_lock); + guc->submissions[ring_id] += 1; + guc->last_seqno[ring_id] = rq->seqno; + spin_unlock(&guc->host2guc_lock); + + return q_ret; +} + +/* + * Everything below here is concerned with setup & teardown, and is + * therefore not part of the somewhat time-critical batch-submission + * path of i915_guc_submit() above. + */ + +/** + * gem_allocate_guc_obj() - Allocate gem object for GuC usage + * @dev: drm device + * @size: size of object + * + * This is a wrapper to create a gem obj. In order to use it inside GuC, the + * object needs to be pinned lifetime. Also we must pin it to gtt space other + * than [0, GUC_WOPCM_TOP) because this range is reserved inside GuC. + * + * Return: A drm_i915_gem_object if successful, otherwise NULL. + */ +static struct drm_i915_gem_object *gem_allocate_guc_obj(struct drm_device *dev, + u32 size) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_object *obj; + + obj = i915_gem_alloc_object(dev, size); + if (!obj) + return NULL; + + if (i915_gem_object_get_pages(obj)) { + drm_gem_object_unreference(&obj->base); + return NULL; + } + + if (i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, + PIN_OFFSET_BIAS | GUC_WOPCM_TOP)) { + drm_gem_object_unreference(&obj->base); + return NULL; + } + + /* Invalidate GuC TLB to let GuC take the latest updates to GTT. */ + I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE); + + return obj; +} + +/** + * gem_release_guc_obj() - Release gem object allocated for GuC usage + * @obj: gem obj to be released + */ +static void gem_release_guc_obj(struct drm_i915_gem_object *obj) +{ + if (!obj) + return; + + if (i915_gem_obj_is_pinned(obj)) + i915_gem_object_ggtt_unpin(obj); + + drm_gem_object_unreference(&obj->base); +} + +static void guc_client_free(struct drm_device *dev, + struct i915_guc_client *client) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc *guc = &dev_priv->guc; + + if (!client) + return; + + if (client->doorbell_id != GUC_INVALID_DOORBELL_ID) { + /* + * First disable the doorbell, then tell the GuC we've + * finished with it, finally deallocate it in our bitmap + */ + guc_disable_doorbell(guc, client); + host2guc_release_doorbell(guc, client); + release_doorbell(guc, client->doorbell_id); + } + + /* + * XXX: wait for any outstanding submissions before freeing memory. + * Be sure to drop any locks + */ + + gem_release_guc_obj(client->client_obj); + + if (client->ctx_index != GUC_INVALID_CTX_ID) { + guc_fini_ctx_desc(guc, client); + ida_simple_remove(&guc->ctx_ids, client->ctx_index); + } + + kfree(client); +} + +/** + * guc_client_alloc() - Allocate an i915_guc_client + * @dev: drm device + * @priority: four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW + * The kernel client to replace ExecList submission is created with + * NORMAL priority. Priority of a client for scheduler can be HIGH, + * while a preemption context can use CRITICAL. + * @ctx the context to own the client (we use the default render context) + * + * Return: An i915_guc_client object if success. + */ +static struct i915_guc_client *guc_client_alloc(struct drm_device *dev, + uint32_t priority, + struct intel_context *ctx) +{ + struct i915_guc_client *client; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc *guc = &dev_priv->guc; + struct drm_i915_gem_object *obj; + + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (!client) + return NULL; + + client->doorbell_id = GUC_INVALID_DOORBELL_ID; + client->priority = priority; + client->owner = ctx; + client->guc = guc; + + client->ctx_index = (uint32_t)ida_simple_get(&guc->ctx_ids, 0, + GUC_MAX_GPU_CONTEXTS, GFP_KERNEL); + if (client->ctx_index >= GUC_MAX_GPU_CONTEXTS) { + client->ctx_index = GUC_INVALID_CTX_ID; + goto err; + } + + /* The first page is doorbell/proc_desc. Two followed pages are wq. */ + obj = gem_allocate_guc_obj(dev, GUC_DB_SIZE + GUC_WQ_SIZE); + if (!obj) + goto err; + + client->client_obj = obj; + client->wq_offset = GUC_DB_SIZE; + client->wq_size = GUC_WQ_SIZE; + spin_lock_init(&client->wq_lock); + + client->doorbell_offset = select_doorbell_cacheline(guc); + + /* + * Since the doorbell only requires a single cacheline, we can save + * space by putting the application process descriptor in the same + * page. Use the half of the page that doesn't include the doorbell. + */ + if (client->doorbell_offset >= (GUC_DB_SIZE / 2)) + client->proc_desc_offset = 0; + else + client->proc_desc_offset = (GUC_DB_SIZE / 2); + + client->doorbell_id = assign_doorbell(guc, client->priority); + if (client->doorbell_id == GUC_INVALID_DOORBELL_ID) + /* XXX: evict a doorbell instead */ + goto err; + + guc_init_proc_desc(guc, client); + guc_init_ctx_desc(guc, client); + guc_init_doorbell(guc, client); + + /* XXX: Any cache flushes needed? General domain mgmt calls? */ + + if (host2guc_allocate_doorbell(guc, client)) + goto err; + + DRM_DEBUG_DRIVER("new priority %u client %p: ctx_index %u db_id %u\n", + priority, client, client->ctx_index, client->doorbell_id); + + return client; + +err: + DRM_ERROR("FAILED to create priority %u GuC client!\n", priority); + + guc_client_free(dev, client); + return NULL; +} + +static void guc_create_log(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct drm_i915_gem_object *obj; + unsigned long offset; + uint32_t size, flags; + + if (i915.guc_log_level < GUC_LOG_VERBOSITY_MIN) + return; + + if (i915.guc_log_level > GUC_LOG_VERBOSITY_MAX) + i915.guc_log_level = GUC_LOG_VERBOSITY_MAX; + + /* The first page is to save log buffer state. Allocate one + * extra page for others in case for overlap */ + size = (1 + GUC_LOG_DPC_PAGES + 1 + + GUC_LOG_ISR_PAGES + 1 + + GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT; + + obj = guc->log_obj; + if (!obj) { + obj = gem_allocate_guc_obj(dev_priv->dev, size); + if (!obj) { + /* logging will be off */ + i915.guc_log_level = -1; + return; + } + + guc->log_obj = obj; + } + + /* each allocated unit is a page */ + flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL | + (GUC_LOG_DPC_PAGES << GUC_LOG_DPC_SHIFT) | + (GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) | + (GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT); + + offset = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT; /* in pages */ + guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags; +} + +/* + * Set up the memory resources to be shared with the GuC. At this point, + * we require just one object that can be mapped through the GGTT. + */ +int i915_guc_submission_init(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + const size_t ctxsize = sizeof(struct guc_context_desc); + const size_t poolsize = GUC_MAX_GPU_CONTEXTS * ctxsize; + const size_t gemsize = round_up(poolsize, PAGE_SIZE); + struct intel_guc *guc = &dev_priv->guc; + + if (!i915.enable_guc_submission) + return 0; /* not enabled */ + + if (guc->ctx_pool_obj) + return 0; /* already allocated */ + + guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv->dev, gemsize); + if (!guc->ctx_pool_obj) + return -ENOMEM; + + spin_lock_init(&dev_priv->guc.host2guc_lock); + + ida_init(&guc->ctx_ids); + + guc_create_log(guc); + + return 0; +} + +int i915_guc_submission_enable(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc *guc = &dev_priv->guc; + struct intel_context *ctx = dev_priv->ring[RCS].default_context; + struct i915_guc_client *client; + + /* client for execbuf submission */ + client = guc_client_alloc(dev, GUC_CTX_PRIORITY_KMD_NORMAL, ctx); + if (!client) { + DRM_ERROR("Failed to create execbuf guc_client\n"); + return -ENOMEM; + } + + guc->execbuf_client = client; + + host2guc_sample_forcewake(guc, client); + + return 0; +} + +void i915_guc_submission_disable(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc *guc = &dev_priv->guc; + + guc_client_free(dev, guc->execbuf_client); + guc->execbuf_client = NULL; +} + +void i915_guc_submission_fini(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc *guc = &dev_priv->guc; + + gem_release_guc_obj(dev_priv->guc.log_obj); + guc->log_obj = NULL; + + if (guc->ctx_pool_obj) + ida_destroy(&guc->ctx_ids); + gem_release_guc_obj(guc->ctx_pool_obj); + guc->ctx_pool_obj = NULL; +} + +/** + * intel_guc_suspend() - notify GuC entering suspend state + * @dev: drm device + */ +int intel_guc_suspend(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc *guc = &dev_priv->guc; + struct intel_context *ctx; + u32 data[3]; + + if (!i915.enable_guc_submission) + return 0; + + ctx = dev_priv->ring[RCS].default_context; + + data[0] = HOST2GUC_ACTION_ENTER_S_STATE; + /* any value greater than GUC_POWER_D0 */ + data[1] = GUC_POWER_D1; + /* first page is shared data with GuC */ + data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state); + + return host2guc_action(guc, data, ARRAY_SIZE(data)); +} + + +/** + * intel_guc_resume() - notify GuC resuming from suspend state + * @dev: drm device + */ +int intel_guc_resume(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc *guc = &dev_priv->guc; + struct intel_context *ctx; + u32 data[3]; + + if (!i915.enable_guc_submission) + return 0; + + ctx = dev_priv->ring[RCS].default_context; + + data[0] = HOST2GUC_ACTION_EXIT_S_STATE; + data[1] = GUC_POWER_D0; + /* first page is shared data with GuC */ + data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state); + + return host2guc_action(guc, data, ARRAY_SIZE(data)); +} diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index bc732eb..4fb8a2f 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -45,6 +45,18 @@ * and related files, but that will be described in separate chapters. */ +static const u32 hpd_ilk[HPD_NUM_PINS] = { + [HPD_PORT_A] = DE_DP_A_HOTPLUG, +}; + +static const u32 hpd_ivb[HPD_NUM_PINS] = { + [HPD_PORT_A] = DE_DP_A_HOTPLUG_IVB, +}; + +static const u32 hpd_bdw[HPD_NUM_PINS] = { + [HPD_PORT_A] = GEN8_PORT_DP_A_HOTPLUG, +}; + static const u32 hpd_ibx[HPD_NUM_PINS] = { [HPD_CRT] = SDE_CRT_HOTPLUG, [HPD_SDVO_B] = SDE_SDVOB_HOTPLUG, @@ -62,6 +74,7 @@ static const u32 hpd_cpt[HPD_NUM_PINS] = { }; static const u32 hpd_spt[HPD_NUM_PINS] = { + [HPD_PORT_A] = SDE_PORTA_HOTPLUG_SPT, [HPD_PORT_B] = SDE_PORTB_HOTPLUG_CPT, [HPD_PORT_C] = SDE_PORTC_HOTPLUG_CPT, [HPD_PORT_D] = SDE_PORTD_HOTPLUG_CPT, @@ -97,6 +110,7 @@ static const u32 hpd_status_i915[HPD_NUM_PINS] = { /* BXT hpd list */ static const u32 hpd_bxt[HPD_NUM_PINS] = { + [HPD_PORT_A] = BXT_DE_PORT_HP_DDIA, [HPD_PORT_B] = BXT_DE_PORT_HP_DDIB, [HPD_PORT_C] = BXT_DE_PORT_HP_DDIC }; @@ -154,36 +168,85 @@ static const u32 hpd_bxt[HPD_NUM_PINS] = { static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir); /* For display hotplug interrupt */ -void -ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask) +static inline void +i915_hotplug_interrupt_update_locked(struct drm_i915_private *dev_priv, + uint32_t mask, + uint32_t bits) { + uint32_t val; + assert_spin_locked(&dev_priv->irq_lock); + WARN_ON(bits & ~mask); - if (WARN_ON(!intel_irqs_enabled(dev_priv))) - return; + val = I915_READ(PORT_HOTPLUG_EN); + val &= ~mask; + val |= bits; + I915_WRITE(PORT_HOTPLUG_EN, val); +} - if ((dev_priv->irq_mask & mask) != 0) { - dev_priv->irq_mask &= ~mask; - I915_WRITE(DEIMR, dev_priv->irq_mask); - POSTING_READ(DEIMR); - } +/** + * i915_hotplug_interrupt_update - update hotplug interrupt enable + * @dev_priv: driver private + * @mask: bits to update + * @bits: bits to enable + * NOTE: the HPD enable bits are modified both inside and outside + * of an interrupt context. To avoid that read-modify-write cycles + * interfer, these bits are protected by a spinlock. Since this + * function is usually not called from a context where the lock is + * held already, this function acquires the lock itself. A non-locking + * version is also available. + */ +void i915_hotplug_interrupt_update(struct drm_i915_private *dev_priv, + uint32_t mask, + uint32_t bits) +{ + spin_lock_irq(&dev_priv->irq_lock); + i915_hotplug_interrupt_update_locked(dev_priv, mask, bits); + spin_unlock_irq(&dev_priv->irq_lock); } -void -ironlake_disable_display_irq(struct drm_i915_private *dev_priv, u32 mask) +/** + * ilk_update_display_irq - update DEIMR + * @dev_priv: driver private + * @interrupt_mask: mask of interrupt bits to update + * @enabled_irq_mask: mask of interrupt bits to enable + */ +static void ilk_update_display_irq(struct drm_i915_private *dev_priv, + uint32_t interrupt_mask, + uint32_t enabled_irq_mask) { + uint32_t new_val; + assert_spin_locked(&dev_priv->irq_lock); + WARN_ON(enabled_irq_mask & ~interrupt_mask); + if (WARN_ON(!intel_irqs_enabled(dev_priv))) return; - if ((dev_priv->irq_mask & mask) != mask) { - dev_priv->irq_mask |= mask; + new_val = dev_priv->irq_mask; + new_val &= ~interrupt_mask; + new_val |= (~enabled_irq_mask & interrupt_mask); + + if (new_val != dev_priv->irq_mask) { + dev_priv->irq_mask = new_val; I915_WRITE(DEIMR, dev_priv->irq_mask); POSTING_READ(DEIMR); } } +void +ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask) +{ + ilk_update_display_irq(dev_priv, mask, mask); +} + +void +ironlake_disable_display_irq(struct drm_i915_private *dev_priv, u32 mask) +{ + ilk_update_display_irq(dev_priv, mask, 0); +} + /** * ilk_update_gt_irq - update GTIMR * @dev_priv: driver private @@ -351,6 +414,38 @@ void gen6_disable_rps_interrupts(struct drm_device *dev) } /** + * bdw_update_port_irq - update DE port interrupt + * @dev_priv: driver private + * @interrupt_mask: mask of interrupt bits to update + * @enabled_irq_mask: mask of interrupt bits to enable + */ +static void bdw_update_port_irq(struct drm_i915_private *dev_priv, + uint32_t interrupt_mask, + uint32_t enabled_irq_mask) +{ + uint32_t new_val; + uint32_t old_val; + + assert_spin_locked(&dev_priv->irq_lock); + + WARN_ON(enabled_irq_mask & ~interrupt_mask); + + if (WARN_ON(!intel_irqs_enabled(dev_priv))) + return; + + old_val = I915_READ(GEN8_DE_PORT_IMR); + + new_val = old_val; + new_val &= ~interrupt_mask; + new_val |= (~enabled_irq_mask & interrupt_mask); + + if (new_val != old_val) { + I915_WRITE(GEN8_DE_PORT_IMR, new_val); + POSTING_READ(GEN8_DE_PORT_IMR); + } +} + +/** * ibx_display_interrupt_update - update SDEIMR * @dev_priv: driver private * @interrupt_mask: mask of interrupt bits to update @@ -486,6 +581,7 @@ i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe, /** * i915_enable_asle_pipestat - enable ASLE pipestat for OpRegion + * @dev: drm device */ static void i915_enable_asle_pipestat(struct drm_device *dev) { @@ -902,12 +998,16 @@ static bool vlv_c0_above(struct drm_i915_private *dev_priv, int threshold) { u64 time, c0; + unsigned int mul = 100; if (old->cz_clock == 0) return false; + if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) + mul <<= 8; + time = now->cz_clock - old->cz_clock; - time *= threshold * dev_priv->mem_freq; + time *= threshold * dev_priv->czclk_freq; /* Workload can be split between render + media, e.g. SwapBuffers * being blitted in X after being rendered in mesa. To account for @@ -915,7 +1015,7 @@ static bool vlv_c0_above(struct drm_i915_private *dev_priv, */ c0 = now->render_c0 - old->render_c0; c0 += now->media_c0 - old->media_c0; - c0 *= 100 * VLV_CZ_CLOCK_TO_MILLI_SEC * 4 / 1000; + c0 *= mul * VLV_CZ_CLOCK_TO_MILLI_SEC; return c0 >= time; } @@ -1263,7 +1363,31 @@ static bool bxt_port_hotplug_long_detect(enum port port, u32 val) { switch (port) { case PORT_A: - return val & BXT_PORTA_HOTPLUG_LONG_DETECT; + return val & PORTA_HOTPLUG_LONG_DETECT; + case PORT_B: + return val & PORTB_HOTPLUG_LONG_DETECT; + case PORT_C: + return val & PORTC_HOTPLUG_LONG_DETECT; + default: + return false; + } +} + +static bool spt_port_hotplug2_long_detect(enum port port, u32 val) +{ + switch (port) { + case PORT_E: + return val & PORTE_HOTPLUG_LONG_DETECT; + default: + return false; + } +} + +static bool spt_port_hotplug_long_detect(enum port port, u32 val) +{ + switch (port) { + case PORT_A: + return val & PORTA_HOTPLUG_LONG_DETECT; case PORT_B: return val & PORTB_HOTPLUG_LONG_DETECT; case PORT_C: @@ -1275,6 +1399,16 @@ static bool bxt_port_hotplug_long_detect(enum port port, u32 val) } } +static bool ilk_port_hotplug_long_detect(enum port port, u32 val) +{ + switch (port) { + case PORT_A: + return val & DIGITAL_PORTA_HOTPLUG_LONG_DETECT; + default: + return false; + } +} + static bool pch_port_hotplug_long_detect(enum port port, u32 val) { switch (port) { @@ -1284,8 +1418,6 @@ static bool pch_port_hotplug_long_detect(enum port port, u32 val) return val & PORTC_HOTPLUG_LONG_DETECT; case PORT_D: return val & PORTD_HOTPLUG_LONG_DETECT; - case PORT_E: - return val & PORTE_HOTPLUG_LONG_DETECT; default: return false; } @@ -1305,7 +1437,13 @@ static bool i9xx_port_hotplug_long_detect(enum port port, u32 val) } } -/* Get a bit mask of pins that have triggered, and which ones may be long. */ +/* + * Get a bit mask of pins that have triggered, and which ones may be long. + * This can be called multiple times with the same masks to accumulate + * hotplug detection results from several registers. + * + * Note that the caller is expected to zero out the masks initially. + */ static void intel_get_hpd_pins(u32 *pin_mask, u32 *long_mask, u32 hotplug_trigger, u32 dig_hotplug_reg, const u32 hpd[HPD_NUM_PINS], @@ -1314,9 +1452,6 @@ static void intel_get_hpd_pins(u32 *pin_mask, u32 *long_mask, enum port port; int i; - *pin_mask = 0; - *long_mask = 0; - for_each_hpd_pin(i) { if ((hpd[i] & hotplug_trigger) == 0) continue; @@ -1557,7 +1692,7 @@ static void i9xx_hpd_irq_handler(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT); - u32 pin_mask, long_mask; + u32 pin_mask = 0, long_mask = 0; if (!hotplug_status) return; @@ -1572,20 +1707,25 @@ static void i9xx_hpd_irq_handler(struct drm_device *dev) if (IS_G4X(dev) || IS_VALLEYVIEW(dev)) { u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X; - intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, - hotplug_trigger, hpd_status_g4x, - i9xx_port_hotplug_long_detect); - intel_hpd_irq_handler(dev, pin_mask, long_mask); + if (hotplug_trigger) { + intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, + hotplug_trigger, hpd_status_g4x, + i9xx_port_hotplug_long_detect); + + intel_hpd_irq_handler(dev, pin_mask, long_mask); + } if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X) dp_aux_irq_handler(dev); } else { u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915; - intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, - hotplug_trigger, hpd_status_i915, - i9xx_port_hotplug_long_detect); - intel_hpd_irq_handler(dev, pin_mask, long_mask); + if (hotplug_trigger) { + intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, + hotplug_trigger, hpd_status_i915, + i9xx_port_hotplug_long_detect); + intel_hpd_irq_handler(dev, pin_mask, long_mask); + } } } @@ -1679,23 +1819,30 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg) return ret; } +static void ibx_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger, + const u32 hpd[HPD_NUM_PINS]) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0; + + dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG); + I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg); + + intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, + dig_hotplug_reg, hpd, + pch_port_hotplug_long_detect); + + intel_hpd_irq_handler(dev, pin_mask, long_mask); +} + static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir) { struct drm_i915_private *dev_priv = dev->dev_private; int pipe; u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK; - if (hotplug_trigger) { - u32 dig_hotplug_reg, pin_mask, long_mask; - - dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG); - I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg); - - intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, - dig_hotplug_reg, hpd_ibx, - pch_port_hotplug_long_detect); - intel_hpd_irq_handler(dev, pin_mask, long_mask); - } + if (hotplug_trigger) + ibx_hpd_irq_handler(dev, hotplug_trigger, hpd_ibx); if (pch_iir & SDE_AUDIO_POWER_MASK) { int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK) >> @@ -1786,38 +1933,10 @@ static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir) { struct drm_i915_private *dev_priv = dev->dev_private; int pipe; - u32 hotplug_trigger; - - if (HAS_PCH_SPT(dev)) - hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT; - else - hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT; - - if (hotplug_trigger) { - u32 dig_hotplug_reg, pin_mask, long_mask; + u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT; - dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG); - I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg); - - if (HAS_PCH_SPT(dev)) { - intel_get_hpd_pins(&pin_mask, &long_mask, - hotplug_trigger, - dig_hotplug_reg, hpd_spt, - pch_port_hotplug_long_detect); - - /* detect PORTE HP event */ - dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG2); - if (pch_port_hotplug_long_detect(PORT_E, - dig_hotplug_reg)) - long_mask |= 1 << HPD_PORT_E; - } else - intel_get_hpd_pins(&pin_mask, &long_mask, - hotplug_trigger, - dig_hotplug_reg, hpd_cpt, - pch_port_hotplug_long_detect); - - intel_hpd_irq_handler(dev, pin_mask, long_mask); - } + if (hotplug_trigger) + ibx_hpd_irq_handler(dev, hotplug_trigger, hpd_cpt); if (pch_iir & SDE_AUDIO_POWER_MASK_CPT) { int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK_CPT) >> @@ -1848,10 +1967,67 @@ static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir) cpt_serr_int_handler(dev); } +static void spt_irq_handler(struct drm_device *dev, u32 pch_iir) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT & + ~SDE_PORTE_HOTPLUG_SPT; + u32 hotplug2_trigger = pch_iir & SDE_PORTE_HOTPLUG_SPT; + u32 pin_mask = 0, long_mask = 0; + + if (hotplug_trigger) { + u32 dig_hotplug_reg; + + dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG); + I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg); + + intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, + dig_hotplug_reg, hpd_spt, + spt_port_hotplug_long_detect); + } + + if (hotplug2_trigger) { + u32 dig_hotplug_reg; + + dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG2); + I915_WRITE(PCH_PORT_HOTPLUG2, dig_hotplug_reg); + + intel_get_hpd_pins(&pin_mask, &long_mask, hotplug2_trigger, + dig_hotplug_reg, hpd_spt, + spt_port_hotplug2_long_detect); + } + + if (pin_mask) + intel_hpd_irq_handler(dev, pin_mask, long_mask); + + if (pch_iir & SDE_GMBUS_CPT) + gmbus_irq_handler(dev); +} + +static void ilk_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger, + const u32 hpd[HPD_NUM_PINS]) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0; + + dig_hotplug_reg = I915_READ(DIGITAL_PORT_HOTPLUG_CNTRL); + I915_WRITE(DIGITAL_PORT_HOTPLUG_CNTRL, dig_hotplug_reg); + + intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, + dig_hotplug_reg, hpd, + ilk_port_hotplug_long_detect); + + intel_hpd_irq_handler(dev, pin_mask, long_mask); +} + static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir) { struct drm_i915_private *dev_priv = dev->dev_private; enum pipe pipe; + u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG; + + if (hotplug_trigger) + ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_ilk); if (de_iir & DE_AUX_CHANNEL_A) dp_aux_irq_handler(dev); @@ -1901,6 +2077,10 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir) { struct drm_i915_private *dev_priv = dev->dev_private; enum pipe pipe; + u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG_IVB; + + if (hotplug_trigger) + ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_ivb); if (de_iir & DE_ERR_INT_IVB) ivb_err_int_handler(dev); @@ -2013,27 +2193,19 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg) return ret; } -static void bxt_hpd_handler(struct drm_device *dev, uint32_t iir_status) +static void bxt_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger, + const u32 hpd[HPD_NUM_PINS]) { - struct drm_i915_private *dev_priv = dev->dev_private; - u32 hp_control, hp_trigger; - u32 pin_mask, long_mask; + struct drm_i915_private *dev_priv = to_i915(dev); + u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0; - /* Get the status */ - hp_trigger = iir_status & BXT_DE_PORT_HOTPLUG_MASK; - hp_control = I915_READ(BXT_HOTPLUG_CTL); + dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG); + I915_WRITE(PCH_PORT_HOTPLUG, dig_hotplug_reg); - /* Hotplug not enabled ? */ - if (!(hp_control & BXT_HOTPLUG_CTL_MASK)) { - DRM_ERROR("Interrupt when HPD disabled\n"); - return; - } - - /* Clear sticky bits in hpd status */ - I915_WRITE(BXT_HOTPLUG_CTL, hp_control); + intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger, + dig_hotplug_reg, hpd, + bxt_port_hotplug_long_detect); - intel_get_hpd_pins(&pin_mask, &long_mask, hp_trigger, hp_control, - hpd_bxt, bxt_port_hotplug_long_detect); intel_hpd_irq_handler(dev, pin_mask, long_mask); } @@ -2050,7 +2222,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) if (!intel_irqs_enabled(dev_priv)) return IRQ_NONE; - if (IS_GEN9(dev)) + if (INTEL_INFO(dev_priv)->gen >= 9) aux_mask |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | GEN9_AUX_CHANNEL_D; @@ -2083,6 +2255,12 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) tmp = I915_READ(GEN8_DE_PORT_IIR); if (tmp) { bool found = false; + u32 hotplug_trigger = 0; + + if (IS_BROXTON(dev_priv)) + hotplug_trigger = tmp & BXT_DE_PORT_HOTPLUG_MASK; + else if (IS_BROADWELL(dev_priv)) + hotplug_trigger = tmp & GEN8_PORT_DP_A_HOTPLUG; I915_WRITE(GEN8_DE_PORT_IIR, tmp); ret = IRQ_HANDLED; @@ -2092,8 +2270,11 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) found = true; } - if (IS_BROXTON(dev) && tmp & BXT_DE_PORT_HOTPLUG_MASK) { - bxt_hpd_handler(dev, tmp); + if (hotplug_trigger) { + if (IS_BROXTON(dev)) + bxt_hpd_irq_handler(dev, hotplug_trigger, hpd_bxt); + else + ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_bdw); found = true; } @@ -2124,7 +2305,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) intel_pipe_handle_vblank(dev, pipe)) intel_check_page_flip(dev, pipe); - if (IS_GEN9(dev)) + if (INTEL_INFO(dev_priv)->gen >= 9) flip_done = pipe_iir & GEN9_PIPE_PLANE1_FLIP_DONE; else flip_done = pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE; @@ -2142,7 +2323,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) pipe); - if (IS_GEN9(dev)) + if (INTEL_INFO(dev_priv)->gen >= 9) fault_errors = pipe_iir & GEN9_DE_PIPE_IRQ_FAULT_ERRORS; else fault_errors = pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS; @@ -2166,7 +2347,11 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) if (pch_iir) { I915_WRITE(SDEIIR, pch_iir); ret = IRQ_HANDLED; - cpt_irq_handler(dev, pch_iir); + + if (HAS_PCH_SPT(dev_priv)) + spt_irq_handler(dev, pch_iir); + else + cpt_irq_handler(dev, pch_iir); } else DRM_ERROR("The master control interrupt lied (SDE)!\n"); @@ -2208,6 +2393,7 @@ static void i915_error_wake_up(struct drm_i915_private *dev_priv, /** * i915_reset_and_wakeup - do process context error handling work + * @dev: drm device * * Fire an error uevent so userspace can see that a hang or error * was detected. @@ -2385,7 +2571,7 @@ static void i915_report_and_clear_eir(struct drm_device *dev) * i915_handle_error - handle a gpu error * @dev: drm device * - * Do some basic checking of regsiter state at error time and + * Do some basic checking of register state at error time and * dump it to the syslog. Also call i915_capture_error_state() to make * sure we get a record and make it available in debugfs. Fire a uevent * so userspace knows something bad happened (should trigger collection @@ -2598,6 +2784,26 @@ semaphore_waits_for(struct intel_engine_cs *ring, u32 *seqno) u64 offset = 0; int i, backwards; + /* + * This function does not support execlist mode - any attempt to + * proceed further into this function will result in a kernel panic + * when dereferencing ring->buffer, which is not set up in execlist + * mode. + * + * The correct way of doing it would be to derive the currently + * executing ring buffer from the current context, which is derived + * from the currently running request. Unfortunately, to get the + * current request we would have to grab the struct_mutex before doing + * anything else, which would be ill-advised since some other thread + * might have grabbed it already and managed to hang itself, causing + * the hang checker to deadlock. + * + * Therefore, this function does not support execlist mode in its + * current form. Just return NULL and move on. + */ + if (ring->buffer == NULL) + return NULL; + ipehr = I915_READ(RING_IPEHR(ring->mmio_base)); if (!ipehr_is_semaphore_wait(ring->dev, ipehr)) return NULL; @@ -2932,7 +3138,7 @@ static void vlv_display_irq_reset(struct drm_i915_private *dev_priv) { enum pipe pipe; - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xFFFFFFFF, 0); I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); for_each_pipe(dev_priv, pipe) @@ -3026,86 +3232,124 @@ static void cherryview_irq_preinstall(struct drm_device *dev) vlv_display_irq_reset(dev_priv); } +static u32 intel_hpd_enabled_irqs(struct drm_device *dev, + const u32 hpd[HPD_NUM_PINS]) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_encoder *encoder; + u32 enabled_irqs = 0; + + for_each_intel_encoder(dev, encoder) + if (dev_priv->hotplug.stats[encoder->hpd_pin].state == HPD_ENABLED) + enabled_irqs |= hpd[encoder->hpd_pin]; + + return enabled_irqs; +} + static void ibx_hpd_irq_setup(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *intel_encoder; - u32 hotplug_irqs, hotplug, enabled_irqs = 0; + u32 hotplug_irqs, hotplug, enabled_irqs; if (HAS_PCH_IBX(dev)) { hotplug_irqs = SDE_HOTPLUG_MASK; - for_each_intel_encoder(dev, intel_encoder) - if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED) - enabled_irqs |= hpd_ibx[intel_encoder->hpd_pin]; - } else if (HAS_PCH_SPT(dev)) { - hotplug_irqs = SDE_HOTPLUG_MASK_SPT; - for_each_intel_encoder(dev, intel_encoder) - if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED) - enabled_irqs |= hpd_spt[intel_encoder->hpd_pin]; + enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ibx); } else { hotplug_irqs = SDE_HOTPLUG_MASK_CPT; - for_each_intel_encoder(dev, intel_encoder) - if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED) - enabled_irqs |= hpd_cpt[intel_encoder->hpd_pin]; + enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_cpt); } ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); /* * Enable digital hotplug on the PCH, and configure the DP short pulse - * duration to 2ms (which is the minimum in the Display Port spec) - * - * This register is the same on all known PCH chips. + * duration to 2ms (which is the minimum in the Display Port spec). + * The pulse duration bits are reserved on LPT+. */ hotplug = I915_READ(PCH_PORT_HOTPLUG); hotplug &= ~(PORTD_PULSE_DURATION_MASK|PORTC_PULSE_DURATION_MASK|PORTB_PULSE_DURATION_MASK); hotplug |= PORTD_HOTPLUG_ENABLE | PORTD_PULSE_DURATION_2ms; hotplug |= PORTC_HOTPLUG_ENABLE | PORTC_PULSE_DURATION_2ms; hotplug |= PORTB_HOTPLUG_ENABLE | PORTB_PULSE_DURATION_2ms; + /* + * When CPU and PCH are on the same package, port A + * HPD must be enabled in both north and south. + */ + if (HAS_PCH_LPT_LP(dev)) + hotplug |= PORTA_HOTPLUG_ENABLE; I915_WRITE(PCH_PORT_HOTPLUG, hotplug); +} - /* enable SPT PORTE hot plug */ - if (HAS_PCH_SPT(dev)) { - hotplug = I915_READ(PCH_PORT_HOTPLUG2); - hotplug |= PORTE_HOTPLUG_ENABLE; - I915_WRITE(PCH_PORT_HOTPLUG2, hotplug); - } +static void spt_hpd_irq_setup(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 hotplug_irqs, hotplug, enabled_irqs; + + hotplug_irqs = SDE_HOTPLUG_MASK_SPT; + enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_spt); + + ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); + + /* Enable digital hotplug on the PCH */ + hotplug = I915_READ(PCH_PORT_HOTPLUG); + hotplug |= PORTD_HOTPLUG_ENABLE | PORTC_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | PORTA_HOTPLUG_ENABLE; + I915_WRITE(PCH_PORT_HOTPLUG, hotplug); + + hotplug = I915_READ(PCH_PORT_HOTPLUG2); + hotplug |= PORTE_HOTPLUG_ENABLE; + I915_WRITE(PCH_PORT_HOTPLUG2, hotplug); } -static void bxt_hpd_irq_setup(struct drm_device *dev) +static void ilk_hpd_irq_setup(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *intel_encoder; - u32 hotplug_port = 0; - u32 hotplug_ctrl; - - /* Now, enable HPD */ - for_each_intel_encoder(dev, intel_encoder) { - if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state - == HPD_ENABLED) - hotplug_port |= hpd_bxt[intel_encoder->hpd_pin]; + u32 hotplug_irqs, hotplug, enabled_irqs; + + if (INTEL_INFO(dev)->gen >= 8) { + hotplug_irqs = GEN8_PORT_DP_A_HOTPLUG; + enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_bdw); + + bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); + } else if (INTEL_INFO(dev)->gen >= 7) { + hotplug_irqs = DE_DP_A_HOTPLUG_IVB; + enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ivb); + + ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs); + } else { + hotplug_irqs = DE_DP_A_HOTPLUG; + enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ilk); + + ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs); } - /* Mask all HPD control bits */ - hotplug_ctrl = I915_READ(BXT_HOTPLUG_CTL) & ~BXT_HOTPLUG_CTL_MASK; + /* + * Enable digital hotplug on the CPU, and configure the DP short pulse + * duration to 2ms (which is the minimum in the Display Port spec) + * The pulse duration bits are reserved on HSW+. + */ + hotplug = I915_READ(DIGITAL_PORT_HOTPLUG_CNTRL); + hotplug &= ~DIGITAL_PORTA_PULSE_DURATION_MASK; + hotplug |= DIGITAL_PORTA_HOTPLUG_ENABLE | DIGITAL_PORTA_PULSE_DURATION_2ms; + I915_WRITE(DIGITAL_PORT_HOTPLUG_CNTRL, hotplug); - /* Enable requested port in hotplug control */ - /* TODO: implement (short) HPD support on port A */ - WARN_ON_ONCE(hotplug_port & BXT_DE_PORT_HP_DDIA); - if (hotplug_port & BXT_DE_PORT_HP_DDIB) - hotplug_ctrl |= BXT_DDIB_HPD_ENABLE; - if (hotplug_port & BXT_DE_PORT_HP_DDIC) - hotplug_ctrl |= BXT_DDIC_HPD_ENABLE; - I915_WRITE(BXT_HOTPLUG_CTL, hotplug_ctrl); + ibx_hpd_irq_setup(dev); +} - /* Unmask DDI hotplug in IMR */ - hotplug_ctrl = I915_READ(GEN8_DE_PORT_IMR) & ~hotplug_port; - I915_WRITE(GEN8_DE_PORT_IMR, hotplug_ctrl); +static void bxt_hpd_irq_setup(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 hotplug_irqs, hotplug, enabled_irqs; + + enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_bxt); + hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK; - /* Enable DDI hotplug in IER */ - hotplug_ctrl = I915_READ(GEN8_DE_PORT_IER) | hotplug_port; - I915_WRITE(GEN8_DE_PORT_IER, hotplug_ctrl); - POSTING_READ(GEN8_DE_PORT_IER); + bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); + + hotplug = I915_READ(PCH_PORT_HOTPLUG); + hotplug |= PORTC_HOTPLUG_ENABLE | PORTB_HOTPLUG_ENABLE | + PORTA_HOTPLUG_ENABLE; + I915_WRITE(PCH_PORT_HOTPLUG, hotplug); } static void ibx_irq_postinstall(struct drm_device *dev) @@ -3173,15 +3417,17 @@ static int ironlake_irq_postinstall(struct drm_device *dev) DE_PLANEB_FLIP_DONE_IVB | DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB); extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB | - DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB); + DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB | + DE_DP_A_HOTPLUG_IVB); } else { display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT | DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE | DE_AUX_CHANNEL_A | DE_PIPEB_CRC_DONE | DE_PIPEA_CRC_DONE | DE_POISON); - extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT | - DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN; + extra_mask = (DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT | + DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN | + DE_DP_A_HOTPLUG); } dev_priv->irq_mask = ~display_mask; @@ -3308,7 +3554,7 @@ static void vlv_display_irq_postinstall(struct drm_i915_private *dev_priv) { dev_priv->irq_mask = ~0; - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); POSTING_READ(PORT_HOTPLUG_EN); I915_WRITE(VLV_IIR, 0xffffffff); @@ -3377,24 +3623,31 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) { uint32_t de_pipe_masked = GEN8_PIPE_CDCLK_CRC_DONE; uint32_t de_pipe_enables; - int pipe; - u32 de_port_en = GEN8_AUX_CHANNEL_A; + u32 de_port_masked = GEN8_AUX_CHANNEL_A; + u32 de_port_enables; + enum pipe pipe; - if (IS_GEN9(dev_priv)) { + if (INTEL_INFO(dev_priv)->gen >= 9) { de_pipe_masked |= GEN9_PIPE_PLANE1_FLIP_DONE | GEN9_DE_PIPE_IRQ_FAULT_ERRORS; - de_port_en |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | - GEN9_AUX_CHANNEL_D; - + de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | + GEN9_AUX_CHANNEL_D; if (IS_BROXTON(dev_priv)) - de_port_en |= BXT_DE_PORT_GMBUS; - } else + de_port_masked |= BXT_DE_PORT_GMBUS; + } else { de_pipe_masked |= GEN8_PIPE_PRIMARY_FLIP_DONE | GEN8_DE_PIPE_IRQ_FAULT_ERRORS; + } de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN; + de_port_enables = de_port_masked; + if (IS_BROXTON(dev_priv)) + de_port_enables |= BXT_DE_PORT_HOTPLUG_MASK; + else if (IS_BROADWELL(dev_priv)) + de_port_enables |= GEN8_PORT_DP_A_HOTPLUG; + dev_priv->de_irq_mask[PIPE_A] = ~de_pipe_masked; dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked; dev_priv->de_irq_mask[PIPE_C] = ~de_pipe_masked; @@ -3406,7 +3659,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) dev_priv->de_irq_mask[pipe], de_pipe_enables); - GEN5_IRQ_INIT(GEN8_DE_PORT_, ~de_port_en, de_port_en); + GEN5_IRQ_INIT(GEN8_DE_PORT_, ~de_port_masked, de_port_enables); } static int gen8_irq_postinstall(struct drm_device *dev) @@ -3675,7 +3928,7 @@ static void i915_irq_preinstall(struct drm_device * dev) int pipe; if (I915_HAS_HOTPLUG(dev)) { - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); } @@ -3709,7 +3962,7 @@ static int i915_irq_postinstall(struct drm_device *dev) I915_USER_INTERRUPT; if (I915_HAS_HOTPLUG(dev)) { - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); POSTING_READ(PORT_HOTPLUG_EN); /* Enable in IER... */ @@ -3871,7 +4124,7 @@ static void i915_irq_uninstall(struct drm_device * dev) int pipe; if (I915_HAS_HOTPLUG(dev)) { - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); } @@ -3892,7 +4145,7 @@ static void i965_irq_preinstall(struct drm_device * dev) struct drm_i915_private *dev_priv = dev->dev_private; int pipe; - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); I915_WRITE(HWSTAM, 0xeffe); @@ -3953,7 +4206,7 @@ static int i965_irq_postinstall(struct drm_device *dev) I915_WRITE(IER, enable_mask); POSTING_READ(IER); - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); POSTING_READ(PORT_HOTPLUG_EN); i915_enable_asle_pipestat(dev); @@ -3964,29 +4217,26 @@ static int i965_irq_postinstall(struct drm_device *dev) static void i915_hpd_irq_setup(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *intel_encoder; u32 hotplug_en; assert_spin_locked(&dev_priv->irq_lock); - hotplug_en = I915_READ(PORT_HOTPLUG_EN); - hotplug_en &= ~HOTPLUG_INT_EN_MASK; /* Note HDMI and DP share hotplug bits */ /* enable bits are the same for all generations */ - for_each_intel_encoder(dev, intel_encoder) - if (dev_priv->hotplug.stats[intel_encoder->hpd_pin].state == HPD_ENABLED) - hotplug_en |= hpd_mask_i915[intel_encoder->hpd_pin]; + hotplug_en = intel_hpd_enabled_irqs(dev, hpd_mask_i915); /* Programming the CRT detection parameters tends to generate a spurious hotplug event about three seconds later. So just do it once. */ if (IS_G4X(dev)) hotplug_en |= CRT_HOTPLUG_ACTIVATION_PERIOD_64; - hotplug_en &= ~CRT_HOTPLUG_VOLTAGE_COMPARE_MASK; hotplug_en |= CRT_HOTPLUG_VOLTAGE_COMPARE_50; /* Ignore TV since it's buggy */ - I915_WRITE(PORT_HOTPLUG_EN, hotplug_en); + i915_hotplug_interrupt_update_locked(dev_priv, + (HOTPLUG_INT_EN_MASK + | CRT_HOTPLUG_VOLTAGE_COMPARE_MASK), + hotplug_en); } static irqreturn_t i965_irq_handler(int irq, void *arg) @@ -4099,7 +4349,7 @@ static void i965_irq_uninstall(struct drm_device * dev) if (!dev_priv) return; - I915_WRITE(PORT_HOTPLUG_EN, 0); + i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0); I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); I915_WRITE(HWSTAM, 0xffffffff); @@ -4187,10 +4437,12 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev->driver->irq_uninstall = gen8_irq_uninstall; dev->driver->enable_vblank = gen8_enable_vblank; dev->driver->disable_vblank = gen8_disable_vblank; - if (HAS_PCH_SPLIT(dev)) - dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup; - else + if (IS_BROXTON(dev)) dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup; + else if (HAS_PCH_SPT(dev)) + dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup; + else + dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup; } else if (HAS_PCH_SPLIT(dev)) { dev->driver->irq_handler = ironlake_irq_handler; dev->driver->irq_preinstall = ironlake_irq_reset; @@ -4198,7 +4450,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev->driver->irq_uninstall = ironlake_irq_uninstall; dev->driver->enable_vblank = ironlake_enable_vblank; dev->driver->disable_vblank = ironlake_disable_vblank; - dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup; + dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup; } else { if (INTEL_INFO(dev_priv)->gen == 2) { dev->driver->irq_preinstall = i8xx_irq_preinstall; diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 5ae4b0a..ca9b8f6 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -40,7 +40,6 @@ struct i915_params i915 __read_mostly = { .preliminary_hw_support = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT), .disable_power_well = 1, .enable_ips = 1, - .fastboot = 0, .prefault_disable = 0, .load_detect_test = 0, .reset = true, @@ -51,6 +50,7 @@ struct i915_params i915 __read_mostly = { .use_mmio_flip = 0, .mmio_debug = 0, .verbose_state_checks = 1, + .nuclear_pageflip = 0, .edp_vswing = 0, .enable_guc_submission = false, .guc_log_level = -1, @@ -61,7 +61,7 @@ MODULE_PARM_DESC(modeset, "Use kernel modesetting [KMS] (0=disable, " "1=on, -1=force vga console preference [default])"); -module_param_named(panel_ignore_lid, i915.panel_ignore_lid, int, 0600); +module_param_named_unsafe(panel_ignore_lid, i915.panel_ignore_lid, int, 0600); MODULE_PARM_DESC(panel_ignore_lid, "Override lid status (0=autodetect, 1=autodetect disabled [default], " "-1=force lid closed, -2=force lid open)"); @@ -84,17 +84,17 @@ MODULE_PARM_DESC(enable_fbc, "Enable frame buffer compression for power savings " "(default: -1 (use per-chip default))"); -module_param_named(lvds_channel_mode, i915.lvds_channel_mode, int, 0600); +module_param_named_unsafe(lvds_channel_mode, i915.lvds_channel_mode, int, 0600); MODULE_PARM_DESC(lvds_channel_mode, "Specify LVDS channel mode " "(0=probe BIOS [default], 1=single-channel, 2=dual-channel)"); -module_param_named(lvds_use_ssc, i915.panel_use_ssc, int, 0600); +module_param_named_unsafe(lvds_use_ssc, i915.panel_use_ssc, int, 0600); MODULE_PARM_DESC(lvds_use_ssc, "Use Spread Spectrum Clock with panels [LVDS/eDP] " "(default: auto from VBT)"); -module_param_named(vbt_sdvo_panel_type, i915.vbt_sdvo_panel_type, int, 0600); +module_param_named_unsafe(vbt_sdvo_panel_type, i915.vbt_sdvo_panel_type, int, 0600); MODULE_PARM_DESC(vbt_sdvo_panel_type, "Override/Ignore selection of SDVO panel mode in the VBT " "(-2=ignore, -1=auto [default], index in VBT BIOS table)"); @@ -102,7 +102,7 @@ MODULE_PARM_DESC(vbt_sdvo_panel_type, module_param_named_unsafe(reset, i915.reset, bool, 0600); MODULE_PARM_DESC(reset, "Attempt GPU resets (default: true)"); -module_param_named(enable_hangcheck, i915.enable_hangcheck, bool, 0644); +module_param_named_unsafe(enable_hangcheck, i915.enable_hangcheck, bool, 0644); MODULE_PARM_DESC(enable_hangcheck, "Periodically check GPU activity for detecting hangs. " "WARNING: Disabling this can cause system wide hangs. " @@ -113,29 +113,25 @@ MODULE_PARM_DESC(enable_ppgtt, "Override PPGTT usage. " "(-1=auto [default], 0=disabled, 1=aliasing, 2=full)"); -module_param_named(enable_execlists, i915.enable_execlists, int, 0400); +module_param_named_unsafe(enable_execlists, i915.enable_execlists, int, 0400); MODULE_PARM_DESC(enable_execlists, "Override execlists usage. " "(-1=auto [default], 0=disabled, 1=enabled)"); -module_param_named(enable_psr, i915.enable_psr, int, 0600); +module_param_named_unsafe(enable_psr, i915.enable_psr, int, 0600); MODULE_PARM_DESC(enable_psr, "Enable PSR (default: false)"); -module_param_named(preliminary_hw_support, i915.preliminary_hw_support, int, 0600); +module_param_named_unsafe(preliminary_hw_support, i915.preliminary_hw_support, int, 0600); MODULE_PARM_DESC(preliminary_hw_support, "Enable preliminary hardware support."); -module_param_named(disable_power_well, i915.disable_power_well, int, 0600); +module_param_named_unsafe(disable_power_well, i915.disable_power_well, int, 0600); MODULE_PARM_DESC(disable_power_well, "Disable the power well when possible (default: true)"); -module_param_named(enable_ips, i915.enable_ips, int, 0600); +module_param_named_unsafe(enable_ips, i915.enable_ips, int, 0600); MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)"); -module_param_named(fastboot, i915.fastboot, bool, 0600); -MODULE_PARM_DESC(fastboot, - "Try to skip unnecessary mode sets at boot time (default: false)"); - module_param_named_unsafe(prefault_disable, i915.prefault_disable, bool, 0600); MODULE_PARM_DESC(prefault_disable, "Disable page prefaulting for pread/pwrite/reloc (default:false). " @@ -146,7 +142,7 @@ MODULE_PARM_DESC(load_detect_test, "Force-enable the VGA load detect code for testing (default:false). " "For developers only."); -module_param_named(invert_brightness, i915.invert_brightness, int, 0600); +module_param_named_unsafe(invert_brightness, i915.invert_brightness, int, 0600); MODULE_PARM_DESC(invert_brightness, "Invert backlight brightness " "(-1 force normal, 0 machine defaults, 1 force inversion), please " @@ -157,14 +153,14 @@ MODULE_PARM_DESC(invert_brightness, module_param_named(disable_display, i915.disable_display, bool, 0600); MODULE_PARM_DESC(disable_display, "Disable display (default: false)"); -module_param_named(disable_vtd_wa, i915.disable_vtd_wa, bool, 0600); +module_param_named_unsafe(disable_vtd_wa, i915.disable_vtd_wa, bool, 0600); MODULE_PARM_DESC(disable_vtd_wa, "Disable all VT-d workarounds (default: false)"); -module_param_named(enable_cmd_parser, i915.enable_cmd_parser, int, 0600); +module_param_named_unsafe(enable_cmd_parser, i915.enable_cmd_parser, int, 0600); MODULE_PARM_DESC(enable_cmd_parser, "Enable command parsing (1=enabled [default], 0=disabled)"); -module_param_named(use_mmio_flip, i915.use_mmio_flip, int, 0600); +module_param_named_unsafe(use_mmio_flip, i915.use_mmio_flip, int, 0600); MODULE_PARM_DESC(use_mmio_flip, "use MMIO flips (-1=never, 0=driver discretion [default], 1=always)"); @@ -177,6 +173,10 @@ module_param_named(verbose_state_checks, i915.verbose_state_checks, bool, 0600); MODULE_PARM_DESC(verbose_state_checks, "Enable verbose logs (ie. WARN_ON()) in case of unexpected hw state conditions."); +module_param_named_unsafe(nuclear_pageflip, i915.nuclear_pageflip, bool, 0600); +MODULE_PARM_DESC(nuclear_pageflip, + "Force atomic modeset functionality; asynchronous mode is not yet supported. (default: false)."); + /* WA to get away with the default setting in VBT for early platforms.Will be removed */ module_param_named_unsafe(edp_vswing, i915.edp_vswing, int, 0400); MODULE_PARM_DESC(edp_vswing, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 83a0888..6be853d 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -105,7 +105,7 @@ #define GRDOM_RESET_STATUS (1<<1) #define GRDOM_RESET_ENABLE (1<<0) -#define ILK_GDSR 0x2ca4 /* MCHBAR offset */ +#define ILK_GDSR (MCHBAR_MIRROR_BASE + 0x2ca4) #define ILK_GRDOM_FULL (0<<1) #define ILK_GRDOM_RENDER (1<<1) #define ILK_GRDOM_MEDIA (3<<1) @@ -352,8 +352,8 @@ */ #define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*(x)-1) #define MI_LRI_FORCE_POSTED (1<<12) -#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*(x)-1) -#define MI_STORE_REGISTER_MEM_GEN8(x) MI_INSTR(0x24, 3*(x)-1) +#define MI_STORE_REGISTER_MEM MI_INSTR(0x24, 1) +#define MI_STORE_REGISTER_MEM_GEN8 MI_INSTR(0x24, 2) #define MI_SRM_LRM_GLOBAL_GTT (1<<22) #define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */ #define MI_FLUSH_DW_STORE_INDEX (1<<21) @@ -364,8 +364,8 @@ #define MI_INVALIDATE_BSD (1<<7) #define MI_FLUSH_DW_USE_GTT (1<<2) #define MI_FLUSH_DW_USE_PPGTT (0<<2) -#define MI_LOAD_REGISTER_MEM(x) MI_INSTR(0x29, 2*(x)-1) -#define MI_LOAD_REGISTER_MEM_GEN8(x) MI_INSTR(0x29, 3*(x)-1) +#define MI_LOAD_REGISTER_MEM MI_INSTR(0x29, 1) +#define MI_LOAD_REGISTER_MEM_GEN8 MI_INSTR(0x29, 2) #define MI_BATCH_BUFFER MI_INSTR(0x30, 1) #define MI_BATCH_NON_SECURE (1) /* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */ @@ -536,6 +536,10 @@ #define GEN7_3DPRIM_START_INSTANCE 0x243C #define GEN7_3DPRIM_BASE_VERTEX 0x2440 +#define GEN7_GPGPU_DISPATCHDIMX 0x2500 +#define GEN7_GPGPU_DISPATCHDIMY 0x2504 +#define GEN7_GPGPU_DISPATCHDIMZ 0x2508 + #define OACONTROL 0x2360 #define _GEN7_PIPEA_DE_LOAD_SL 0x70068 @@ -728,12 +732,13 @@ enum skl_disp_power_wells { #define DSI_PLL_N1_DIV_MASK (3 << 16) #define DSI_PLL_M1_DIV_SHIFT 0 #define DSI_PLL_M1_DIV_MASK (0x1ff << 0) +#define CCK_CZ_CLOCK_CONTROL 0x62 #define CCK_DISPLAY_CLOCK_CONTROL 0x6b -#define DISPLAY_TRUNK_FORCE_ON (1 << 17) -#define DISPLAY_TRUNK_FORCE_OFF (1 << 16) -#define DISPLAY_FREQUENCY_STATUS (0x1f << 8) -#define DISPLAY_FREQUENCY_STATUS_SHIFT 8 -#define DISPLAY_FREQUENCY_VALUES (0x1f << 0) +#define CCK_TRUNK_FORCE_ON (1 << 17) +#define CCK_TRUNK_FORCE_OFF (1 << 16) +#define CCK_FREQUENCY_STATUS (0x1f << 8) +#define CCK_FREQUENCY_STATUS_SHIFT 8 +#define CCK_FREQUENCY_VALUES (0x1f << 0) /** * DOC: DPIO @@ -1099,6 +1104,12 @@ enum skl_disp_power_wells { #define DPIO_CHV_INT_LOCK_THRESHOLD_SEL_COARSE 1 /* 1: coarse & 0 : fine */ #define CHV_PLL_DW9(ch) _PIPE(ch, _CHV_PLL_DW9_CH0, _CHV_PLL_DW9_CH1) +#define _CHV_CMN_DW0_CH0 0x8100 +#define DPIO_ALLDL_POWERDOWN_SHIFT_CH0 19 +#define DPIO_ANYDL_POWERDOWN_SHIFT_CH0 18 +#define DPIO_ALLDL_POWERDOWN (1 << 1) +#define DPIO_ANYDL_POWERDOWN (1 << 0) + #define _CHV_CMN_DW5_CH0 0x8114 #define CHV_BUFRIGHTENA1_DISABLE (0 << 20) #define CHV_BUFRIGHTENA1_NORMAL (1 << 20) @@ -1135,10 +1146,23 @@ enum skl_disp_power_wells { #define _CHV_CMN_DW19_CH0 0x814c #define _CHV_CMN_DW6_CH1 0x8098 +#define DPIO_ALLDL_POWERDOWN_SHIFT_CH1 30 /* CL2 DW6 only */ +#define DPIO_ANYDL_POWERDOWN_SHIFT_CH1 29 /* CL2 DW6 only */ +#define DPIO_DYNPWRDOWNEN_CH1 (1 << 28) /* CL2 DW6 only */ #define CHV_CMN_USEDCLKCHANNEL (1 << 13) + #define CHV_CMN_DW19(ch) _PIPE(ch, _CHV_CMN_DW19_CH0, _CHV_CMN_DW6_CH1) +#define CHV_CMN_DW28 0x8170 +#define DPIO_CL1POWERDOWNEN (1 << 23) +#define DPIO_DYNPWRDOWNEN_CH0 (1 << 22) +#define DPIO_SUS_CLK_CONFIG_ON (0 << 0) +#define DPIO_SUS_CLK_CONFIG_CLKREQ (1 << 0) +#define DPIO_SUS_CLK_CONFIG_GATE (2 << 0) +#define DPIO_SUS_CLK_CONFIG_GATE_CLKREQ (3 << 0) + #define CHV_CMN_DW30 0x8178 +#define DPIO_CL2_LDOFUSE_PWRENB (1 << 6) #define DPIO_LRC_BYPASS (1 << 3) #define _TXLANE(ch, lane, offset) ((ch ? 0x2400 : 0) + \ @@ -1376,7 +1400,8 @@ enum skl_disp_power_wells { #define BXT_PORT_TX_DW3_LN0(port) _PORT3(port, _PORT_TX_DW3_LN0_A, \ _PORT_TX_DW3_LN0_B, \ _PORT_TX_DW3_LN0_C) -#define UNIQE_TRANGE_EN_METHOD (1 << 27) +#define SCALE_DCOMP_METHOD (1 << 26) +#define UNIQUE_TRANGE_EN_METHOD (1 << 27) #define _PORT_TX_DW4_LN0_A 0x162510 #define _PORT_TX_DW4_LN0_B 0x6C510 @@ -1417,9 +1442,15 @@ enum skl_disp_power_wells { /* * Fence registers + * [0-7] @ 0x2000 gen2,gen3 + * [8-15] @ 0x3000 945,g33,pnv + * + * [0-15] @ 0x3000 gen4,gen5 + * + * [0-15] @ 0x100000 gen6,vlv,chv + * [0-31] @ 0x100000 gen7+ */ -#define FENCE_REG_830_0 0x2000 -#define FENCE_REG_945_8 0x3000 +#define FENCE_REG(i) (0x2000 + (((i) & 8) << 9) + ((i) & 7) * 4) #define I830_FENCE_START_MASK 0x07f80000 #define I830_FENCE_TILING_Y_SHIFT 12 #define I830_FENCE_SIZE_BITS(size) ((ffs((size) >> 19) - 1) << 8) @@ -1432,14 +1463,16 @@ enum skl_disp_power_wells { #define I915_FENCE_START_MASK 0x0ff00000 #define I915_FENCE_SIZE_BITS(size) ((ffs((size) >> 20) - 1) << 8) -#define FENCE_REG_965_0 0x03000 +#define FENCE_REG_965_LO(i) (0x03000 + (i) * 8) +#define FENCE_REG_965_HI(i) (0x03000 + (i) * 8 + 4) #define I965_FENCE_PITCH_SHIFT 2 #define I965_FENCE_TILING_Y_SHIFT 1 #define I965_FENCE_REG_VALID (1<<0) #define I965_FENCE_MAX_PITCH_VAL 0x0400 -#define FENCE_REG_SANDYBRIDGE_0 0x100000 -#define SANDYBRIDGE_FENCE_PITCH_SHIFT 32 +#define FENCE_REG_GEN6_LO(i) (0x100000 + (i) * 8) +#define FENCE_REG_GEN6_HI(i) (0x100000 + (i) * 8 + 4) +#define GEN6_FENCE_PITCH_SHIFT 32 #define GEN7_FENCE_MAX_PITCH_VAL 0x0800 @@ -1508,7 +1541,7 @@ enum skl_disp_power_wells { #define GEN7_GFX_PEND_TLB0 0x4034 #define GEN7_GFX_PEND_TLB1 0x4038 /* L3, CVS, ZTLB, RCC, CASC LRA min, max values */ -#define GEN7_LRA_LIMITS_BASE 0x403C +#define GEN7_LRA_LIMITS(i) (0x403C + (i) * 4) #define GEN7_LRA_LIMITS_REG_NUM 13 #define GEN7_MEDIA_MAX_REQ_COUNT 0x4070 #define GEN7_GFX_MAX_REQ_COUNT 0x4074 @@ -1523,7 +1556,8 @@ enum skl_disp_power_wells { #define RING_FAULT_FAULT_TYPE(x) ((x >> 1) & 0x3) #define RING_FAULT_VALID (1<<0) #define DONE_REG 0x40b0 -#define GEN8_PRIVATE_PAT 0x40e0 +#define GEN8_PRIVATE_PAT_LO 0x40e0 +#define GEN8_PRIVATE_PAT_HI (0x40e0 + 4) #define BSD_HWS_PGA_GEN7 (0x04180) #define BLT_HWS_PGA_GEN7 (0x04280) #define VEBOX_HWS_PGA_GEN7 (0x04380) @@ -1563,14 +1597,17 @@ enum skl_disp_power_wells { #endif #define IPEIR_I965 0x02064 #define IPEHR_I965 0x02068 -#define INSTDONE_I965 0x0206c -#define GEN7_INSTDONE_1 0x0206c #define GEN7_SC_INSTDONE 0x07100 #define GEN7_SAMPLER_INSTDONE 0x0e160 #define GEN7_ROW_INSTDONE 0x0e164 #define I915_NUM_INSTDONE_REG 4 #define RING_IPEIR(base) ((base)+0x64) #define RING_IPEHR(base) ((base)+0x68) +/* + * On GEN4, only the render ring INSTDONE exists and has a different + * layout than the GEN7+ version. + * The GEN2 counterpart of this register is GEN2_INSTDONE. + */ #define RING_INSTDONE(base) ((base)+0x6c) #define RING_INSTPS(base) ((base)+0x70) #define RING_DMA_FADD(base) ((base)+0x78) @@ -1578,7 +1615,7 @@ enum skl_disp_power_wells { #define RING_INSTPM(base) ((base)+0xc0) #define RING_MI_MODE(base) ((base)+0x9c) #define INSTPS 0x02070 /* 965+ only */ -#define INSTDONE1 0x0207c /* 965+ only */ +#define GEN4_INSTDONE1 0x0207c /* 965+ only, aka INSTDONE_2 on SNB */ #define ACTHD_I965 0x02074 #define HWS_PGA 0x02080 #define HWS_ADDRESS_MASK 0xfffff000 @@ -1587,7 +1624,7 @@ enum skl_disp_power_wells { #define PWRCTX_EN (1<<0) #define IPEIR 0x02088 #define IPEHR 0x0208c -#define INSTDONE 0x02090 +#define GEN2_INSTDONE 0x02090 #define NOPID 0x02094 #define HWSTAM 0x02098 #define DMA_FADD_I8XX 0x020d0 @@ -1674,11 +1711,18 @@ enum skl_disp_power_wells { #define GFX_MODE_GEN7 0x0229c #define RING_MODE_GEN7(ring) ((ring)->mmio_base+0x29c) #define GFX_RUN_LIST_ENABLE (1<<15) +#define GFX_INTERRUPT_STEERING (1<<14) #define GFX_TLB_INVALIDATE_EXPLICIT (1<<13) #define GFX_SURFACE_FAULT_ENABLE (1<<12) #define GFX_REPLAY_MODE (1<<11) #define GFX_PSMI_GRANULARITY (1<<10) #define GFX_PPGTT_ENABLE (1<<9) +#define GEN8_GFX_PPGTT_48B (1<<7) + +#define GFX_FORWARD_VBLANK_MASK (3<<5) +#define GFX_FORWARD_VBLANK_NEVER (0<<5) +#define GFX_FORWARD_VBLANK_ALWAYS (1<<5) +#define GFX_FORWARD_VBLANK_COND (2<<5) #define VLV_DISPLAY_BASE 0x180000 #define VLV_MIPI_BASE VLV_DISPLAY_BASE @@ -1850,12 +1894,27 @@ enum skl_disp_power_wells { #define CHV_FGT_EU_DIS_SS1_R1_MASK (0xf << CHV_FGT_EU_DIS_SS1_R1_SHIFT) #define GEN8_FUSE2 0x9120 +#define GEN8_F2_SS_DIS_SHIFT 21 +#define GEN8_F2_SS_DIS_MASK (0x7 << GEN8_F2_SS_DIS_SHIFT) #define GEN8_F2_S_ENA_SHIFT 25 #define GEN8_F2_S_ENA_MASK (0x7 << GEN8_F2_S_ENA_SHIFT) #define GEN9_F2_SS_DIS_SHIFT 20 #define GEN9_F2_SS_DIS_MASK (0xf << GEN9_F2_SS_DIS_SHIFT) +#define GEN8_EU_DISABLE0 0x9134 +#define GEN8_EU_DIS0_S0_MASK 0xffffff +#define GEN8_EU_DIS0_S1_SHIFT 24 +#define GEN8_EU_DIS0_S1_MASK (0xff << GEN8_EU_DIS0_S1_SHIFT) + +#define GEN8_EU_DISABLE1 0x9138 +#define GEN8_EU_DIS1_S1_MASK 0xffff +#define GEN8_EU_DIS1_S2_SHIFT 16 +#define GEN8_EU_DIS1_S2_MASK (0xffff << GEN8_EU_DIS1_S2_SHIFT) + +#define GEN8_EU_DISABLE2 0x913c +#define GEN8_EU_DIS2_S2_MASK 0xff + #define GEN9_EU_DISABLE(slice) (0x9134 + (slice)*0x4) #define GEN6_BSD_SLEEP_PSMI_CONTROL 0x12050 @@ -1985,7 +2044,7 @@ enum skl_disp_power_wells { #define FBC_CTL_CPU_FENCE (1<<1) #define FBC_CTL_PLANE(plane) ((plane)<<0) #define FBC_FENCE_OFF 0x03218 /* BSpec typo has 321Bh */ -#define FBC_TAG 0x03300 +#define FBC_TAG(i) (0x03300 + (i) * 4) #define FBC_STATUS2 0x43214 #define FBC_COMPRESSION_MASK 0x7ff @@ -2185,16 +2244,20 @@ enum skl_disp_power_wells { #define DPIO_PHY_STATUS (VLV_DISPLAY_BASE + 0x6240) #define DPLL_PORTD_READY_MASK (0xf) #define DISPLAY_PHY_CONTROL (VLV_DISPLAY_BASE + 0x60100) +#define PHY_CH_POWER_DOWN_OVRD_EN(phy, ch) (1 << (2*(phy)+(ch)+27)) #define PHY_LDO_DELAY_0NS 0x0 #define PHY_LDO_DELAY_200NS 0x1 #define PHY_LDO_DELAY_600NS 0x2 #define PHY_LDO_SEQ_DELAY(delay, phy) ((delay) << (2*(phy)+23)) +#define PHY_CH_POWER_DOWN_OVRD(mask, phy, ch) ((mask) << (8*(phy)+4*(ch)+11)) #define PHY_CH_SU_PSR 0x1 #define PHY_CH_DEEP_PSR 0x7 #define PHY_CH_POWER_MODE(mode, phy, ch) ((mode) << (6*(phy)+3*(ch)+2)) #define PHY_COM_LANE_RESET_DEASSERT(phy) (1 << (phy)) #define DISPLAY_PHY_STATUS (VLV_DISPLAY_BASE + 0x60104) #define PHY_POWERGOOD(phy) (((phy) == DPIO_PHY0) ? (1<<31) : (1<<30)) +#define PHY_STATUS_CMN_LDO(phy, ch) (1 << (6-(6*(phy)+3*(ch)))) +#define PHY_STATUS_SPLINE_LDO(phy, ch, spline) (1 << (8-(6*(phy)+3*(ch)+(spline)))) /* * The i830 generation, in LVDS mode, defines P1 as the bit number set within @@ -2445,8 +2508,8 @@ enum skl_disp_power_wells { #define PALETTE_A_OFFSET 0xa000 #define PALETTE_B_OFFSET 0xa800 #define CHV_PALETTE_C_OFFSET 0xc000 -#define PALETTE(pipe) (dev_priv->info.palette_offsets[pipe] + \ - dev_priv->info.display_mmio_offset) +#define PALETTE(pipe, i) (dev_priv->info.palette_offsets[pipe] + \ + dev_priv->info.display_mmio_offset + (i) * 4) /* MCH MMIO space */ @@ -2464,6 +2527,11 @@ enum skl_disp_power_wells { #define MCHBAR_MIRROR_BASE_SNB 0x140000 +#define CTG_STOLEN_RESERVED (MCHBAR_MIRROR_BASE + 0x34) +#define ELK_STOLEN_RESERVED (MCHBAR_MIRROR_BASE + 0x48) +#define G4X_STOLEN_RESERVED_ADDR1_MASK (0xFFFF << 16) +#define G4X_STOLEN_RESERVED_ADDR2_MASK (0xFFF << 4) + /* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */ #define DCLK (MCHBAR_MIRROR_BASE_SNB + 0x5e04) @@ -2544,7 +2612,7 @@ enum skl_disp_power_wells { #define TSFS_INTR_MASK 0x000000ff #define CRSTANDVID 0x11100 -#define PXVFREQ_BASE 0x11110 /* P[0-15]VIDFREQ (0x1114c) (Ironlake) */ +#define PXVFREQ(i) (0x11110 + (i) * 4) /* P[0-15]VIDFREQ (0x1114c) (Ironlake) */ #define PXVFREQ_PX_MASK 0x7f000000 #define PXVFREQ_PX_SHIFT 24 #define VIDFREQ_BASE 0x11110 @@ -2728,8 +2796,8 @@ enum skl_disp_power_wells { #define CSIEW0 0x11250 #define CSIEW1 0x11254 #define CSIEW2 0x11258 -#define PEW 0x1125c -#define DEW 0x11270 +#define PEW(i) (0x1125c + (i) * 4) /* 5 registers */ +#define DEW(i) (0x11270 + (i) * 4) /* 3 registers */ #define MCHAFE 0x112c0 #define CSIEC 0x112e0 #define DMIEC 0x112e4 @@ -2753,8 +2821,8 @@ enum skl_disp_power_wells { #define EG5 0x11624 #define EG6 0x11628 #define EG7 0x1162c -#define PXW 0x11664 -#define PXWL 0x11680 +#define PXW(i) (0x11664 + (i) * 4) /* 4 registers */ +#define PXWL(i) (0x11680 + (i) * 4) /* 8 registers */ #define LCFUSE02 0x116c0 #define LCFUSE_HIV_MASK 0x000000ff #define CSIPLL0 0x12c10 @@ -2772,8 +2840,11 @@ enum skl_disp_power_wells { #define INTERVAL_1_28_US(us) (((us) * 100) >> 7) #define INTERVAL_1_33_US(us) (((us) * 3) >> 2) +#define INTERVAL_0_833_US(us) (((us) * 6) / 5) #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \ - INTERVAL_1_33_US(us) : \ + (IS_BROXTON(dev_priv) ? \ + INTERVAL_0_833_US(us) : \ + INTERVAL_1_33_US(us)) : \ INTERVAL_1_28_US(us)) /* @@ -3229,7 +3300,9 @@ enum skl_disp_power_wells { #define GEN3_SDVOC 0x61160 #define GEN4_HDMIB GEN3_SDVOB #define GEN4_HDMIC GEN3_SDVOC -#define CHV_HDMID 0x6116C +#define VLV_HDMIB (VLV_DISPLAY_BASE + GEN4_HDMIB) +#define VLV_HDMIC (VLV_DISPLAY_BASE + GEN4_HDMIC) +#define CHV_HDMID (VLV_DISPLAY_BASE + 0x6116C) #define PCH_SDVOB 0xe1140 #define PCH_HDMIB PCH_SDVOB #define PCH_HDMIC 0xe1150 @@ -3561,17 +3634,29 @@ enum skl_disp_power_wells { #define UTIL_PIN_CTL 0x48400 #define UTIL_PIN_ENABLE (1 << 31) +#define UTIL_PIN_PIPE(x) ((x) << 29) +#define UTIL_PIN_PIPE_MASK (3 << 29) +#define UTIL_PIN_MODE_PWM (1 << 24) +#define UTIL_PIN_MODE_MASK (0xf << 24) +#define UTIL_PIN_POLARITY (1 << 22) + /* BXT backlight register definition. */ -#define BXT_BLC_PWM_CTL1 0xC8250 +#define _BXT_BLC_PWM_CTL1 0xC8250 #define BXT_BLC_PWM_ENABLE (1 << 31) #define BXT_BLC_PWM_POLARITY (1 << 29) -#define BXT_BLC_PWM_FREQ1 0xC8254 -#define BXT_BLC_PWM_DUTY1 0xC8258 +#define _BXT_BLC_PWM_FREQ1 0xC8254 +#define _BXT_BLC_PWM_DUTY1 0xC8258 -#define BXT_BLC_PWM_CTL2 0xC8350 -#define BXT_BLC_PWM_FREQ2 0xC8354 -#define BXT_BLC_PWM_DUTY2 0xC8358 +#define _BXT_BLC_PWM_CTL2 0xC8350 +#define _BXT_BLC_PWM_FREQ2 0xC8354 +#define _BXT_BLC_PWM_DUTY2 0xC8358 +#define BXT_BLC_PWM_CTL(controller) _PIPE(controller, \ + _BXT_BLC_PWM_CTL1, _BXT_BLC_PWM_CTL2) +#define BXT_BLC_PWM_FREQ(controller) _PIPE(controller, \ + _BXT_BLC_PWM_FREQ1, _BXT_BLC_PWM_FREQ2) +#define BXT_BLC_PWM_DUTY(controller) _PIPE(controller, \ + _BXT_BLC_PWM_DUTY1, _BXT_BLC_PWM_DUTY2) #define PCH_GTC_CTL 0xe7000 #define PCH_GTC_ENABLE (1 << 31) @@ -4047,14 +4132,10 @@ enum skl_disp_power_wells { # define TV_CC_DATA_1_MASK 0x0000007f # define TV_CC_DATA_1_SHIFT 0 -#define TV_H_LUMA_0 0x68100 -#define TV_H_LUMA_59 0x681ec -#define TV_H_CHROMA_0 0x68200 -#define TV_H_CHROMA_59 0x682ec -#define TV_V_LUMA_0 0x68300 -#define TV_V_LUMA_42 0x683a8 -#define TV_V_CHROMA_0 0x68400 -#define TV_V_CHROMA_42 0x684a8 +#define TV_H_LUMA(i) (0x68100 + (i) * 4) /* 60 registers */ +#define TV_H_CHROMA(i) (0x68200 + (i) * 4) /* 60 registers */ +#define TV_V_LUMA(i) (0x68300 + (i) * 4) /* 43 registers */ +#define TV_V_CHROMA(i) (0x68400 + (i) * 4) /* 43 registers */ /* Display Port */ #define DP_A 0x64000 /* eDP */ @@ -4062,6 +4143,10 @@ enum skl_disp_power_wells { #define DP_C 0x64200 #define DP_D 0x64300 +#define VLV_DP_B (VLV_DISPLAY_BASE + DP_B) +#define VLV_DP_C (VLV_DISPLAY_BASE + DP_C) +#define CHV_DP_D (VLV_DISPLAY_BASE + DP_D) + #define DP_PORT_EN (1 << 31) #define DP_PIPEB_SELECT (1 << 30) #define DP_PIPE_MASK (1 << 30) @@ -4107,6 +4192,7 @@ enum skl_disp_power_wells { /* How many wires to use. I guess 3 was too hard */ #define DP_PORT_WIDTH(width) (((width) - 1) << 19) #define DP_PORT_WIDTH_MASK (7 << 19) +#define DP_PORT_WIDTH_SHIFT 19 /* Mystic DPCD version 1.1 special mode */ #define DP_ENHANCED_FRAMING (1 << 18) @@ -4617,6 +4703,7 @@ enum skl_disp_power_wells { #define CBR1_VLV (VLV_DISPLAY_BASE + 0x70400) #define CBR_PND_DEADLINE_DISABLE (1<<31) +#define CBR_PWM_CLOCK_MUX_SELECT (1<<30) /* FIFO watermark sizes etc */ #define G4X_FIFO_LINE_SIZE 64 @@ -5363,15 +5450,17 @@ enum skl_disp_power_wells { #define CPU_VGACNTRL 0x41000 -#define DIGITAL_PORT_HOTPLUG_CNTRL 0x44030 -#define DIGITAL_PORTA_HOTPLUG_ENABLE (1 << 4) -#define DIGITAL_PORTA_SHORT_PULSE_2MS (0 << 2) -#define DIGITAL_PORTA_SHORT_PULSE_4_5MS (1 << 2) -#define DIGITAL_PORTA_SHORT_PULSE_6MS (2 << 2) -#define DIGITAL_PORTA_SHORT_PULSE_100MS (3 << 2) -#define DIGITAL_PORTA_NO_DETECT (0 << 0) -#define DIGITAL_PORTA_LONG_PULSE_DETECT_MASK (1 << 1) -#define DIGITAL_PORTA_SHORT_PULSE_DETECT_MASK (1 << 0) +#define DIGITAL_PORT_HOTPLUG_CNTRL 0x44030 +#define DIGITAL_PORTA_HOTPLUG_ENABLE (1 << 4) +#define DIGITAL_PORTA_PULSE_DURATION_2ms (0 << 2) /* pre-HSW */ +#define DIGITAL_PORTA_PULSE_DURATION_4_5ms (1 << 2) /* pre-HSW */ +#define DIGITAL_PORTA_PULSE_DURATION_6ms (2 << 2) /* pre-HSW */ +#define DIGITAL_PORTA_PULSE_DURATION_100ms (3 << 2) /* pre-HSW */ +#define DIGITAL_PORTA_PULSE_DURATION_MASK (3 << 2) /* pre-HSW */ +#define DIGITAL_PORTA_HOTPLUG_STATUS_MASK (3 << 0) +#define DIGITAL_PORTA_HOTPLUG_NO_DETECT (0 << 0) +#define DIGITAL_PORTA_HOTPLUG_SHORT_DETECT (1 << 0) +#define DIGITAL_PORTA_HOTPLUG_LONG_DETECT (2 << 0) /* refresh rate hardware control */ #define RR_HW_CTL 0x45300 @@ -5596,7 +5685,7 @@ enum skl_disp_power_wells { /* legacy palette */ #define _LGC_PALETTE_A 0x4a000 #define _LGC_PALETTE_B 0x4a800 -#define LGC_PALETTE(pipe) _PIPE(pipe, _LGC_PALETTE_A, _LGC_PALETTE_B) +#define LGC_PALETTE(pipe, i) (_PIPE(pipe, _LGC_PALETTE_A, _LGC_PALETTE_B) + (i) * 4) #define _GAMMA_MODE_A 0x4a480 #define _GAMMA_MODE_B 0x4ac80 @@ -5693,11 +5782,12 @@ enum skl_disp_power_wells { #define GEN8_GT_IIR(which) (0x44308 + (0x10 * (which))) #define GEN8_GT_IER(which) (0x4430c + (0x10 * (which))) -#define GEN8_BCS_IRQ_SHIFT 16 #define GEN8_RCS_IRQ_SHIFT 0 -#define GEN8_VCS2_IRQ_SHIFT 16 +#define GEN8_BCS_IRQ_SHIFT 16 #define GEN8_VCS1_IRQ_SHIFT 0 +#define GEN8_VCS2_IRQ_SHIFT 16 #define GEN8_VECS_IRQ_SHIFT 0 +#define GEN8_WD_IRQ_SHIFT 16 #define GEN8_DE_PIPE_ISR(pipe) (0x44400 + (0x10 * (pipe))) #define GEN8_DE_PIPE_IMR(pipe) (0x44404 + (0x10 * (pipe))) @@ -5763,21 +5853,6 @@ enum skl_disp_power_wells { #define GEN8_PCU_IIR 0x444e8 #define GEN8_PCU_IER 0x444ec -/* BXT hotplug control */ -#define BXT_HOTPLUG_CTL 0xC4030 -#define BXT_DDIA_HPD_ENABLE (1 << 28) -#define BXT_DDIA_HPD_STATUS (3 << 24) -#define BXT_DDIC_HPD_ENABLE (1 << 12) -#define BXT_DDIC_HPD_STATUS (3 << 8) -#define BXT_DDIB_HPD_ENABLE (1 << 4) -#define BXT_DDIB_HPD_STATUS (3 << 0) -#define BXT_HOTPLUG_CTL_MASK (BXT_DDIA_HPD_ENABLE | \ - BXT_DDIB_HPD_ENABLE | \ - BXT_DDIC_HPD_ENABLE) -#define BXT_HPD_STATUS_MASK (BXT_DDIA_HPD_STATUS | \ - BXT_DDIB_HPD_STATUS | \ - BXT_DDIC_HPD_STATUS) - #define ILK_DISPLAY_CHICKEN2 0x42004 /* Required on all Ironlake and Sandybridge according to the B-Spec. */ #define ILK_ELPIN_409_SELECT (1 << 25) @@ -5950,6 +6025,7 @@ enum skl_disp_power_wells { #define SDE_AUXB_CPT (1 << 25) #define SDE_AUX_MASK_CPT (7 << 25) #define SDE_PORTE_HOTPLUG_SPT (1 << 25) +#define SDE_PORTA_HOTPLUG_SPT (1 << 24) #define SDE_PORTD_HOTPLUG_CPT (1 << 23) #define SDE_PORTC_HOTPLUG_CPT (1 << 22) #define SDE_PORTB_HOTPLUG_CPT (1 << 21) @@ -5963,7 +6039,8 @@ enum skl_disp_power_wells { #define SDE_HOTPLUG_MASK_SPT (SDE_PORTE_HOTPLUG_SPT | \ SDE_PORTD_HOTPLUG_CPT | \ SDE_PORTC_HOTPLUG_CPT | \ - SDE_PORTB_HOTPLUG_CPT) + SDE_PORTB_HOTPLUG_CPT | \ + SDE_PORTA_HOTPLUG_SPT) #define SDE_GMBUS_CPT (1 << 17) #define SDE_ERROR_CPT (1 << 16) #define SDE_AUDIO_CP_REQ_C_CPT (1 << 10) @@ -5998,46 +6075,46 @@ enum skl_disp_power_wells { #define SERR_INT_TRANS_FIFO_UNDERRUN(pipe) (1<<(pipe*3)) /* digital port hotplug */ -#define PCH_PORT_HOTPLUG 0xc4030 /* SHOTPLUG_CTL */ -#define BXT_PORTA_HOTPLUG_ENABLE (1 << 28) -#define BXT_PORTA_HOTPLUG_STATUS_MASK (0x3 << 24) -#define BXT_PORTA_HOTPLUG_NO_DETECT (0 << 24) -#define BXT_PORTA_HOTPLUG_SHORT_DETECT (1 << 24) -#define BXT_PORTA_HOTPLUG_LONG_DETECT (2 << 24) -#define PORTD_HOTPLUG_ENABLE (1 << 20) -#define PORTD_PULSE_DURATION_2ms (0) -#define PORTD_PULSE_DURATION_4_5ms (1 << 18) -#define PORTD_PULSE_DURATION_6ms (2 << 18) -#define PORTD_PULSE_DURATION_100ms (3 << 18) -#define PORTD_PULSE_DURATION_MASK (3 << 18) -#define PORTD_HOTPLUG_STATUS_MASK (0x3 << 16) +#define PCH_PORT_HOTPLUG 0xc4030 /* SHOTPLUG_CTL */ +#define PORTA_HOTPLUG_ENABLE (1 << 28) /* LPT:LP+ & BXT */ +#define PORTA_HOTPLUG_STATUS_MASK (3 << 24) /* SPT+ & BXT */ +#define PORTA_HOTPLUG_NO_DETECT (0 << 24) /* SPT+ & BXT */ +#define PORTA_HOTPLUG_SHORT_DETECT (1 << 24) /* SPT+ & BXT */ +#define PORTA_HOTPLUG_LONG_DETECT (2 << 24) /* SPT+ & BXT */ +#define PORTD_HOTPLUG_ENABLE (1 << 20) +#define PORTD_PULSE_DURATION_2ms (0 << 18) /* pre-LPT */ +#define PORTD_PULSE_DURATION_4_5ms (1 << 18) /* pre-LPT */ +#define PORTD_PULSE_DURATION_6ms (2 << 18) /* pre-LPT */ +#define PORTD_PULSE_DURATION_100ms (3 << 18) /* pre-LPT */ +#define PORTD_PULSE_DURATION_MASK (3 << 18) /* pre-LPT */ +#define PORTD_HOTPLUG_STATUS_MASK (3 << 16) #define PORTD_HOTPLUG_NO_DETECT (0 << 16) #define PORTD_HOTPLUG_SHORT_DETECT (1 << 16) #define PORTD_HOTPLUG_LONG_DETECT (2 << 16) -#define PORTC_HOTPLUG_ENABLE (1 << 12) -#define PORTC_PULSE_DURATION_2ms (0) -#define PORTC_PULSE_DURATION_4_5ms (1 << 10) -#define PORTC_PULSE_DURATION_6ms (2 << 10) -#define PORTC_PULSE_DURATION_100ms (3 << 10) -#define PORTC_PULSE_DURATION_MASK (3 << 10) -#define PORTC_HOTPLUG_STATUS_MASK (0x3 << 8) +#define PORTC_HOTPLUG_ENABLE (1 << 12) +#define PORTC_PULSE_DURATION_2ms (0 << 10) /* pre-LPT */ +#define PORTC_PULSE_DURATION_4_5ms (1 << 10) /* pre-LPT */ +#define PORTC_PULSE_DURATION_6ms (2 << 10) /* pre-LPT */ +#define PORTC_PULSE_DURATION_100ms (3 << 10) /* pre-LPT */ +#define PORTC_PULSE_DURATION_MASK (3 << 10) /* pre-LPT */ +#define PORTC_HOTPLUG_STATUS_MASK (3 << 8) #define PORTC_HOTPLUG_NO_DETECT (0 << 8) #define PORTC_HOTPLUG_SHORT_DETECT (1 << 8) #define PORTC_HOTPLUG_LONG_DETECT (2 << 8) -#define PORTB_HOTPLUG_ENABLE (1 << 4) -#define PORTB_PULSE_DURATION_2ms (0) -#define PORTB_PULSE_DURATION_4_5ms (1 << 2) -#define PORTB_PULSE_DURATION_6ms (2 << 2) -#define PORTB_PULSE_DURATION_100ms (3 << 2) -#define PORTB_PULSE_DURATION_MASK (3 << 2) -#define PORTB_HOTPLUG_STATUS_MASK (0x3 << 0) +#define PORTB_HOTPLUG_ENABLE (1 << 4) +#define PORTB_PULSE_DURATION_2ms (0 << 2) /* pre-LPT */ +#define PORTB_PULSE_DURATION_4_5ms (1 << 2) /* pre-LPT */ +#define PORTB_PULSE_DURATION_6ms (2 << 2) /* pre-LPT */ +#define PORTB_PULSE_DURATION_100ms (3 << 2) /* pre-LPT */ +#define PORTB_PULSE_DURATION_MASK (3 << 2) /* pre-LPT */ +#define PORTB_HOTPLUG_STATUS_MASK (3 << 0) #define PORTB_HOTPLUG_NO_DETECT (0 << 0) #define PORTB_HOTPLUG_SHORT_DETECT (1 << 0) #define PORTB_HOTPLUG_LONG_DETECT (2 << 0) -#define PCH_PORT_HOTPLUG2 0xc403C /* SHOTPLUG_CTL2 */ -#define PORTE_HOTPLUG_ENABLE (1 << 4) -#define PORTE_HOTPLUG_STATUS_MASK (0x3 << 0) +#define PCH_PORT_HOTPLUG2 0xc403C /* SHOTPLUG_CTL2 SPT+ */ +#define PORTE_HOTPLUG_ENABLE (1 << 4) +#define PORTE_HOTPLUG_STATUS_MASK (3 << 0) #define PORTE_HOTPLUG_NO_DETECT (0 << 0) #define PORTE_HOTPLUG_SHORT_DETECT (1 << 0) #define PORTE_HOTPLUG_LONG_DETECT (2 << 0) @@ -6304,9 +6381,11 @@ enum skl_disp_power_wells { #define FDI_PHASE_SYNC_OVR(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_OVR - ((pipe) * 2))) #define FDI_PHASE_SYNC_EN(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_EN - ((pipe) * 2))) #define FDI_BC_BIFURCATION_SELECT (1 << 12) +#define SPT_PWM_GRANULARITY (1<<0) #define SOUTH_CHICKEN2 0xc2004 #define FDI_MPHY_IOSFSB_RESET_STATUS (1<<13) #define FDI_MPHY_IOSFSB_RESET_CTL (1<<12) +#define LPT_PWM_GRANULARITY (1<<5) #define DPLS_EDP_PPS_FIX_DIS (1<<0) #define _FDI_RXA_CHICKEN 0xc200c @@ -6784,7 +6863,7 @@ enum skl_disp_power_wells { GEN6_PM_RP_DOWN_THRESHOLD | \ GEN6_PM_RP_DOWN_TIMEOUT) -#define GEN7_GT_SCRATCH_BASE 0x4F100 +#define GEN7_GT_SCRATCH(i) (0x4F100 + (i) * 4) #define GEN7_GT_SCRATCH_REG_NUM 8 #define VLV_GTLC_SURVIVABILITY_REG 0x130098 @@ -6843,6 +6922,9 @@ enum skl_disp_power_wells { #define GEN6_RC6 3 #define GEN6_RC7 4 +#define GEN8_GT_SLICE_INFO 0x138064 +#define GEN8_LSLICESTAT_MASK 0x7 + #define CHV_POWER_SS0_SIG1 0xa720 #define CHV_POWER_SS1_SIG1 0xa728 #define CHV_SS_PG_ENABLE (1<<1) @@ -6870,7 +6952,10 @@ enum skl_disp_power_wells { #define GEN9_PGCTL_SSB_EU311_ACK (1 << 14) #define GEN7_MISCCPCTL (0x9424) -#define GEN7_DOP_CLOCK_GATE_ENABLE (1<<0) +#define GEN7_DOP_CLOCK_GATE_ENABLE (1<<0) +#define GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE (1<<2) +#define GEN8_DOP_CLOCK_GATE_GUC_ENABLE (1<<4) +#define GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE (1<<6) #define GEN8_GARBCNTL 0xB004 #define GEN9_GAPS_TSV_CREDIT_DISABLE (1<<7) @@ -6916,6 +7001,9 @@ enum skl_disp_power_wells { #define HSW_ROW_CHICKEN3 0xe49c #define HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE (1 << 6) +#define HALF_SLICE_CHICKEN2 0xe180 +#define GEN8_ST_PO_DISABLE (1<<13) + #define HALF_SLICE_CHICKEN3 0xe184 #define HSW_SAMPLE_C_PERFORMANCE (1<<9) #define GEN8_CENTROID_PIXEL_OPT_DIS (1<<8) @@ -7159,12 +7247,15 @@ enum skl_disp_power_wells { #define DDI_BUF_IS_IDLE (1<<7) #define DDI_A_4_LANES (1<<4) #define DDI_PORT_WIDTH(width) (((width) - 1) << 1) +#define DDI_PORT_WIDTH_MASK (7 << 1) +#define DDI_PORT_WIDTH_SHIFT 1 #define DDI_INIT_DISPLAY_DETECTED (1<<0) /* DDI Buffer Translations */ #define DDI_BUF_TRANS_A 0x64E00 #define DDI_BUF_TRANS_B 0x64E60 -#define DDI_BUF_TRANS(port) _PORT(port, DDI_BUF_TRANS_A, DDI_BUF_TRANS_B) +#define DDI_BUF_TRANS_LO(port, i) (_PORT(port, DDI_BUF_TRANS_A, DDI_BUF_TRANS_B) + (i) * 8) +#define DDI_BUF_TRANS_HI(port, i) (_PORT(port, DDI_BUF_TRANS_A, DDI_BUF_TRANS_B) + (i) * 8 + 4) /* Sideband Interface (SBI) is programmed indirectly, via * SBI_ADDR, which contains the register offset; and SBI_DATA, @@ -7369,8 +7460,8 @@ enum skl_disp_power_wells { #define DPLL_CFGCR2_PDIV_7 (4<<2) #define DPLL_CFGCR2_CENTRAL_FREQ_MASK (3) -#define GET_CFG_CR1_REG(id) (DPLL1_CFGCR1 + (id - SKL_DPLL1) * 8) -#define GET_CFG_CR2_REG(id) (DPLL1_CFGCR2 + (id - SKL_DPLL1) * 8) +#define DPLL_CFGCR1(id) (DPLL1_CFGCR1 + ((id) - SKL_DPLL1) * 8) +#define DPLL_CFGCR2(id) (DPLL1_CFGCR2 + ((id) - SKL_DPLL1) * 8) /* BXT display engine PLL */ #define BXT_DE_PLL_CTL 0x6d000 @@ -7475,9 +7566,116 @@ enum skl_disp_power_wells { #define _MIPI_PORT(port, a, c) _PORT3(port, a, 0, c) /* ports A and C only */ +/* BXT MIPI clock controls */ +#define BXT_MAX_VAR_OUTPUT_KHZ 39500 + +#define BXT_MIPI_CLOCK_CTL 0x46090 +#define BXT_MIPI1_DIV_SHIFT 26 +#define BXT_MIPI2_DIV_SHIFT 10 +#define BXT_MIPI_DIV_SHIFT(port) \ + _MIPI_PORT(port, BXT_MIPI1_DIV_SHIFT, \ + BXT_MIPI2_DIV_SHIFT) +/* Var clock divider to generate TX source. Result must be < 39.5 M */ +#define BXT_MIPI1_ESCLK_VAR_DIV_MASK (0x3F << 26) +#define BXT_MIPI2_ESCLK_VAR_DIV_MASK (0x3F << 10) +#define BXT_MIPI_ESCLK_VAR_DIV_MASK(port) \ + _MIPI_PORT(port, BXT_MIPI1_ESCLK_VAR_DIV_MASK, \ + BXT_MIPI2_ESCLK_VAR_DIV_MASK) + +#define BXT_MIPI_ESCLK_VAR_DIV(port, val) \ + (val << BXT_MIPI_DIV_SHIFT(port)) +/* TX control divider to select actual TX clock output from (8x/var) */ +#define BXT_MIPI1_TX_ESCLK_SHIFT 21 +#define BXT_MIPI2_TX_ESCLK_SHIFT 5 +#define BXT_MIPI_TX_ESCLK_SHIFT(port) \ + _MIPI_PORT(port, BXT_MIPI1_TX_ESCLK_SHIFT, \ + BXT_MIPI2_TX_ESCLK_SHIFT) +#define BXT_MIPI1_TX_ESCLK_FIXDIV_MASK (3 << 21) +#define BXT_MIPI2_TX_ESCLK_FIXDIV_MASK (3 << 5) +#define BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port) \ + _MIPI_PORT(port, BXT_MIPI1_TX_ESCLK_FIXDIV_MASK, \ + BXT_MIPI2_TX_ESCLK_FIXDIV_MASK) +#define BXT_MIPI_TX_ESCLK_8XDIV_BY2(port) \ + (0x0 << BXT_MIPI_TX_ESCLK_SHIFT(port)) +#define BXT_MIPI_TX_ESCLK_8XDIV_BY4(port) \ + (0x1 << BXT_MIPI_TX_ESCLK_SHIFT(port)) +#define BXT_MIPI_TX_ESCLK_8XDIV_BY8(port) \ + (0x2 << BXT_MIPI_TX_ESCLK_SHIFT(port)) +/* RX control divider to select actual RX clock output from 8x*/ +#define BXT_MIPI1_RX_ESCLK_SHIFT 19 +#define BXT_MIPI2_RX_ESCLK_SHIFT 3 +#define BXT_MIPI_RX_ESCLK_SHIFT(port) \ + _MIPI_PORT(port, BXT_MIPI1_RX_ESCLK_SHIFT, \ + BXT_MIPI2_RX_ESCLK_SHIFT) +#define BXT_MIPI1_RX_ESCLK_FIXDIV_MASK (3 << 19) +#define BXT_MIPI2_RX_ESCLK_FIXDIV_MASK (3 << 3) +#define BXT_MIPI_RX_ESCLK_FIXDIV_MASK(port) \ + (3 << BXT_MIPI_RX_ESCLK_SHIFT(port)) +#define BXT_MIPI_RX_ESCLK_8X_BY2(port) \ + (1 << BXT_MIPI_RX_ESCLK_SHIFT(port)) +#define BXT_MIPI_RX_ESCLK_8X_BY3(port) \ + (2 << BXT_MIPI_RX_ESCLK_SHIFT(port)) +#define BXT_MIPI_RX_ESCLK_8X_BY4(port) \ + (3 << BXT_MIPI_RX_ESCLK_SHIFT(port)) +/* BXT-A WA: Always prog DPHY dividers to 00 */ +#define BXT_MIPI1_DPHY_DIV_SHIFT 16 +#define BXT_MIPI2_DPHY_DIV_SHIFT 0 +#define BXT_MIPI_DPHY_DIV_SHIFT(port) \ + _MIPI_PORT(port, BXT_MIPI1_DPHY_DIV_SHIFT, \ + BXT_MIPI2_DPHY_DIV_SHIFT) +#define BXT_MIPI_1_DPHY_DIVIDER_MASK (3 << 16) +#define BXT_MIPI_2_DPHY_DIVIDER_MASK (3 << 0) +#define BXT_MIPI_DPHY_DIVIDER_MASK(port) \ + (3 << BXT_MIPI_DPHY_DIV_SHIFT(port)) + +/* BXT MIPI mode configure */ +#define _BXT_MIPIA_TRANS_HACTIVE 0x6B0F8 +#define _BXT_MIPIC_TRANS_HACTIVE 0x6B8F8 +#define BXT_MIPI_TRANS_HACTIVE(tc) _MIPI_PORT(tc, \ + _BXT_MIPIA_TRANS_HACTIVE, _BXT_MIPIC_TRANS_HACTIVE) + +#define _BXT_MIPIA_TRANS_VACTIVE 0x6B0FC +#define _BXT_MIPIC_TRANS_VACTIVE 0x6B8FC +#define BXT_MIPI_TRANS_VACTIVE(tc) _MIPI_PORT(tc, \ + _BXT_MIPIA_TRANS_VACTIVE, _BXT_MIPIC_TRANS_VACTIVE) + +#define _BXT_MIPIA_TRANS_VTOTAL 0x6B100 +#define _BXT_MIPIC_TRANS_VTOTAL 0x6B900 +#define BXT_MIPI_TRANS_VTOTAL(tc) _MIPI_PORT(tc, \ + _BXT_MIPIA_TRANS_VTOTAL, _BXT_MIPIC_TRANS_VTOTAL) + +#define BXT_DSI_PLL_CTL 0x161000 +#define BXT_DSI_PLL_PVD_RATIO_SHIFT 16 +#define BXT_DSI_PLL_PVD_RATIO_MASK (3 << BXT_DSI_PLL_PVD_RATIO_SHIFT) +#define BXT_DSI_PLL_PVD_RATIO_1 (1 << BXT_DSI_PLL_PVD_RATIO_SHIFT) +#define BXT_DSIC_16X_BY2 (1 << 10) +#define BXT_DSIC_16X_BY3 (2 << 10) +#define BXT_DSIC_16X_BY4 (3 << 10) +#define BXT_DSIA_16X_BY2 (1 << 8) +#define BXT_DSIA_16X_BY3 (2 << 8) +#define BXT_DSIA_16X_BY4 (3 << 8) +#define BXT_DSI_FREQ_SEL_SHIFT 8 +#define BXT_DSI_FREQ_SEL_MASK (0xF << BXT_DSI_FREQ_SEL_SHIFT) + +#define BXT_DSI_PLL_RATIO_MAX 0x7D +#define BXT_DSI_PLL_RATIO_MIN 0x22 +#define BXT_DSI_PLL_RATIO_MASK 0xFF +#define BXT_REF_CLOCK_KHZ 19500 + +#define BXT_DSI_PLL_ENABLE 0x46080 +#define BXT_DSI_PLL_DO_ENABLE (1 << 31) +#define BXT_DSI_PLL_LOCKED (1 << 30) + #define _MIPIA_PORT_CTRL (VLV_DISPLAY_BASE + 0x61190) #define _MIPIC_PORT_CTRL (VLV_DISPLAY_BASE + 0x61700) #define MIPI_PORT_CTRL(port) _MIPI_PORT(port, _MIPIA_PORT_CTRL, _MIPIC_PORT_CTRL) + + /* BXT port control */ +#define _BXT_MIPIA_PORT_CTRL 0x6B0C0 +#define _BXT_MIPIC_PORT_CTRL 0x6B8C0 +#define BXT_MIPI_PORT_CTRL(tc) _MIPI_PORT(tc, _BXT_MIPIA_PORT_CTRL, \ + _BXT_MIPIC_PORT_CTRL) + #define DPI_ENABLE (1 << 31) /* A + C */ #define MIPIA_MIPI4DPHY_DELAY_COUNT_SHIFT 27 #define MIPIA_MIPI4DPHY_DELAY_COUNT_MASK (0xf << 27) @@ -7888,6 +8086,11 @@ enum skl_disp_power_wells { #define READ_REQUEST_PRIORITY_HIGH (3 << 3) #define RGB_FLIP_TO_BGR (1 << 2) +#define BXT_PIPE_SELECT_MASK (7 << 7) +#define BXT_PIPE_SELECT_C (2 << 7) +#define BXT_PIPE_SELECT_B (1 << 7) +#define BXT_PIPE_SELECT_A (0 << 7) + #define _MIPIA_DATA_ADDRESS (dev_priv->mipi_mmio_base + 0xb108) #define _MIPIC_DATA_ADDRESS (dev_priv->mipi_mmio_base + 0xb908) #define MIPI_DATA_ADDRESS(port) _MIPI_PORT(port, _MIPIA_DATA_ADDRESS, \ diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 55bd04c..50ce9ce 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -39,7 +39,7 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg) { struct drm_i915_private *dev_priv = dev->dev_private; u64 raw_time; /* 32b value may overflow during fixed point math */ - u64 units = 128ULL, div = 100000ULL, bias = 100ULL; + u64 units = 128ULL, div = 100000ULL; u32 ret; if (!intel_enable_rc6(dev)) @@ -49,41 +49,19 @@ static u32 calc_residency(struct drm_device *dev, const u32 reg) /* On VLV and CHV, residency time is in CZ units rather than 1.28us */ if (IS_VALLEYVIEW(dev)) { - u32 clk_reg, czcount_30ns; - - if (IS_CHERRYVIEW(dev)) - clk_reg = CHV_CLK_CTL1; - else - clk_reg = VLV_CLK_CTL2; - - czcount_30ns = I915_READ(clk_reg) >> CLK_CTL2_CZCOUNT_30NS_SHIFT; - - if (!czcount_30ns) { - WARN(!czcount_30ns, "bogus CZ count value"); - ret = 0; - goto out; - } - - if (IS_CHERRYVIEW(dev) && czcount_30ns == 1) { - /* Special case for 320Mhz */ - div = 10000000ULL; - units = 3125ULL; - } else { - czcount_30ns += 1; - div = 1000000ULL; - units = DIV_ROUND_UP_ULL(30ULL * bias, czcount_30ns); - } + units = 1; + div = dev_priv->czclk_freq; if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH) units <<= 8; - - div = div * bias; + } else if (IS_BROXTON(dev)) { + units = 1; + div = 1200; /* 833.33ns */ } raw_time = I915_READ(reg) * units; ret = DIV_ROUND_UP_ULL(raw_time, div); -out: intel_runtime_pm_put(dev_priv); return ret; } diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 2f34c47..04fe849 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -17,8 +17,8 @@ /* pipe updates */ TRACE_EVENT(i915_pipe_update_start, - TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max), - TP_ARGS(crtc, min, max), + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), TP_STRUCT__entry( __field(enum pipe, pipe) @@ -33,8 +33,8 @@ TRACE_EVENT(i915_pipe_update_start, __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, crtc->pipe); __entry->scanline = intel_get_crtc_scanline(crtc); - __entry->min = min; - __entry->max = max; + __entry->min = crtc->debug.min_vbl; + __entry->max = crtc->debug.max_vbl; ), TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u", @@ -43,8 +43,8 @@ TRACE_EVENT(i915_pipe_update_start, ); TRACE_EVENT(i915_pipe_update_vblank_evaded, - TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max, u32 frame), - TP_ARGS(crtc, min, max, frame), + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), TP_STRUCT__entry( __field(enum pipe, pipe) @@ -56,10 +56,10 @@ TRACE_EVENT(i915_pipe_update_vblank_evaded, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = frame; - __entry->scanline = intel_get_crtc_scanline(crtc); - __entry->min = min; - __entry->max = max; + __entry->frame = crtc->debug.start_vbl_count; + __entry->scanline = crtc->debug.scanline_start; + __entry->min = crtc->debug.min_vbl; + __entry->max = crtc->debug.max_vbl; ), TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u", @@ -68,8 +68,8 @@ TRACE_EVENT(i915_pipe_update_vblank_evaded, ); TRACE_EVENT(i915_pipe_update_end, - TP_PROTO(struct intel_crtc *crtc, u32 frame), - TP_ARGS(crtc, frame), + TP_PROTO(struct intel_crtc *crtc, u32 frame, int scanline_end), + TP_ARGS(crtc, frame, scanline_end), TP_STRUCT__entry( __field(enum pipe, pipe) @@ -80,7 +80,7 @@ TRACE_EVENT(i915_pipe_update_end, TP_fast_assign( __entry->pipe = crtc->pipe; __entry->frame = frame; - __entry->scanline = intel_get_crtc_scanline(crtc); + __entry->scanline = scanline_end; ), TP_printk("pipe %c, frame=%u, scanline=%u", @@ -107,6 +107,26 @@ TRACE_EVENT(i915_gem_object_create, TP_printk("obj=%p, size=%u", __entry->obj, __entry->size) ); +TRACE_EVENT(i915_gem_shrink, + TP_PROTO(struct drm_i915_private *i915, unsigned long target, unsigned flags), + TP_ARGS(i915, target, flags), + + TP_STRUCT__entry( + __field(int, dev) + __field(unsigned long, target) + __field(unsigned, flags) + ), + + TP_fast_assign( + __entry->dev = i915->dev->primary->index; + __entry->target = target; + __entry->flags = flags; + ), + + TP_printk("dev=%d, target=%lu, flags=%x", + __entry->dev, __entry->target, __entry->flags) +); + TRACE_EVENT(i915_vma_bind, TP_PROTO(struct i915_vma *vma, unsigned flags), TP_ARGS(vma, flags), @@ -186,33 +206,49 @@ DEFINE_EVENT(i915_va, i915_va_alloc, TP_ARGS(vm, start, length, name) ); -DECLARE_EVENT_CLASS(i915_page_table_entry, - TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift), - TP_ARGS(vm, pde, start, pde_shift), +DECLARE_EVENT_CLASS(i915_px_entry, + TP_PROTO(struct i915_address_space *vm, u32 px, u64 start, u64 px_shift), + TP_ARGS(vm, px, start, px_shift), TP_STRUCT__entry( __field(struct i915_address_space *, vm) - __field(u32, pde) + __field(u32, px) __field(u64, start) __field(u64, end) ), TP_fast_assign( __entry->vm = vm; - __entry->pde = pde; + __entry->px = px; __entry->start = start; - __entry->end = ((start + (1ULL << pde_shift)) & ~((1ULL << pde_shift)-1)) - 1; + __entry->end = ((start + (1ULL << px_shift)) & ~((1ULL << px_shift)-1)) - 1; ), TP_printk("vm=%p, pde=%d (0x%llx-0x%llx)", - __entry->vm, __entry->pde, __entry->start, __entry->end) + __entry->vm, __entry->px, __entry->start, __entry->end) ); -DEFINE_EVENT(i915_page_table_entry, i915_page_table_entry_alloc, +DEFINE_EVENT(i915_px_entry, i915_page_table_entry_alloc, TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift), TP_ARGS(vm, pde, start, pde_shift) ); +DEFINE_EVENT_PRINT(i915_px_entry, i915_page_directory_entry_alloc, + TP_PROTO(struct i915_address_space *vm, u32 pdpe, u64 start, u64 pdpe_shift), + TP_ARGS(vm, pdpe, start, pdpe_shift), + + TP_printk("vm=%p, pdpe=%d (0x%llx-0x%llx)", + __entry->vm, __entry->px, __entry->start, __entry->end) +); + +DEFINE_EVENT_PRINT(i915_px_entry, i915_page_directory_pointer_entry_alloc, + TP_PROTO(struct i915_address_space *vm, u32 pml4e, u64 start, u64 pml4e_shift), + TP_ARGS(vm, pml4e, start, pml4e_shift), + + TP_printk("vm=%p, pml4e=%d (0x%llx-0x%llx)", + __entry->vm, __entry->px, __entry->start, __entry->end) +); + /* Avoid extra math because we only support two sizes. The format is defined by * bitmap_scnprintf. Each 32 bits is 8 HEX digits followed by comma */ #define TRACE_PT_SIZE(bits) \ diff --git a/drivers/gpu/drm/i915/i915_vgpu.h b/drivers/gpu/drm/i915/i915_vgpu.h index 97a88b5..21c97f4 100644 --- a/drivers/gpu/drm/i915/i915_vgpu.h +++ b/drivers/gpu/drm/i915/i915_vgpu.h @@ -40,6 +40,19 @@ #define INTEL_VGT_IF_VERSION \ INTEL_VGT_IF_VERSION_ENCODE(VGT_VERSION_MAJOR, VGT_VERSION_MINOR) +/* + * notifications from guest to vgpu device model + */ +enum vgt_g2v_type { + VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE = 2, + VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY, + VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE, + VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY, + VGT_G2V_EXECLIST_CONTEXT_CREATE, + VGT_G2V_EXECLIST_CONTEXT_DESTROY, + VGT_G2V_MAX, +}; + struct vgt_if { uint64_t magic; /* VGT_MAGIC */ uint16_t version_major; @@ -70,11 +83,28 @@ struct vgt_if { uint32_t rsv3[0x200 - 24]; /* pad to half page */ /* * The bottom half page is for response from Gfx driver to hypervisor. - * Set to reserved fields temporarily by now. */ uint32_t rsv4; uint32_t display_ready; /* ready for display owner switch */ - uint32_t rsv5[0x200 - 2]; /* pad to one page */ + + uint32_t rsv5[4]; + + uint32_t g2v_notify; + uint32_t rsv6[7]; + + uint32_t pdp0_lo; + uint32_t pdp0_hi; + uint32_t pdp1_lo; + uint32_t pdp1_hi; + uint32_t pdp2_lo; + uint32_t pdp2_hi; + uint32_t pdp3_lo; + uint32_t pdp3_hi; + + uint32_t execlist_context_descriptor_lo; + uint32_t execlist_context_descriptor_hi; + + uint32_t rsv7[0x200 - 24]; /* pad to one page */ } __packed; #define vgtif_reg(x) \ diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c index d96eee1..8b13b9d 100644 --- a/drivers/gpu/drm/i915/intel_acpi.c +++ b/drivers/gpu/drm/i915/intel_acpi.c @@ -146,7 +146,7 @@ static bool intel_dsm_detect(void) if (vga_count == 2 && has_dsm) { acpi_get_name(intel_dsm_priv.dhandle, ACPI_FULL_PATHNAME, &buffer); - DRM_DEBUG_DRIVER("VGA switcheroo: detected DSM switching method %s handle\n", + DRM_DEBUG_DRIVER("vga_switcheroo: detected DSM switching method %s handle\n", acpi_method_name); return true; } diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c index e2531cf..05b1203 100644 --- a/drivers/gpu/drm/i915/intel_atomic.c +++ b/drivers/gpu/drm/i915/intel_atomic.c @@ -85,21 +85,16 @@ intel_connector_atomic_get_property(struct drm_connector *connector, struct drm_crtc_state * intel_crtc_duplicate_state(struct drm_crtc *crtc) { - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_crtc_state *crtc_state; - if (WARN_ON(!intel_crtc->config)) - crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL); - else - crtc_state = kmemdup(intel_crtc->config, - sizeof(*intel_crtc->config), GFP_KERNEL); - + crtc_state = kmemdup(crtc->state, sizeof(*crtc_state), GFP_KERNEL); if (!crtc_state) return NULL; __drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->base); - crtc_state->base.crtc = crtc; + crtc_state->update_pipe = false; + crtc_state->disable_lp_wm = false; return &crtc_state->base; } @@ -149,9 +144,6 @@ int intel_atomic_setup_scalers(struct drm_device *dev, int i, j; num_scalers_need = hweight32(scaler_state->scaler_users); - DRM_DEBUG_KMS("crtc_state = %p need = %d avail = %d scaler_users = 0x%x\n", - crtc_state, num_scalers_need, intel_crtc->num_scalers, - scaler_state->scaler_users); /* * High level flow: diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c index f1ab8e4..a119806 100644 --- a/drivers/gpu/drm/i915/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/intel_atomic_plane.c @@ -76,11 +76,7 @@ intel_plane_duplicate_state(struct drm_plane *plane) struct drm_plane_state *state; struct intel_plane_state *intel_state; - if (WARN_ON(!plane->state)) - intel_state = intel_create_plane_state(plane); - else - intel_state = kmemdup(plane->state, sizeof(*intel_state), - GFP_KERNEL); + intel_state = kmemdup(plane->state, sizeof(*intel_state), GFP_KERNEL); if (!intel_state) return NULL; diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index e35997e..56c2f54 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -50,6 +50,11 @@ * co-operation between the graphics and audio drivers is handled via audio * related registers. (The notable exception is the power management, not * covered here.) + * + * The struct i915_audio_component is used to interact between the graphics + * and audio drivers. The struct i915_audio_component_ops *ops in it is + * defined in graphics driver and called in audio driver. The + * struct i915_audio_component_audio_ops *audio_ops is called from i915 driver. */ static const struct { @@ -68,18 +73,44 @@ static const struct { { 148500, AUD_CONFIG_PIXEL_CLOCK_HDMI_148500 }, }; +/* HDMI N/CTS table */ +#define TMDS_297M 297000 +#define TMDS_296M DIV_ROUND_UP(297000 * 1000, 1001) +static const struct { + int sample_rate; + int clock; + int n; + int cts; +} aud_ncts[] = { + { 44100, TMDS_296M, 4459, 234375 }, + { 44100, TMDS_297M, 4704, 247500 }, + { 48000, TMDS_296M, 5824, 281250 }, + { 48000, TMDS_297M, 5120, 247500 }, + { 32000, TMDS_296M, 5824, 421875 }, + { 32000, TMDS_297M, 3072, 222750 }, + { 88200, TMDS_296M, 8918, 234375 }, + { 88200, TMDS_297M, 9408, 247500 }, + { 96000, TMDS_296M, 11648, 281250 }, + { 96000, TMDS_297M, 10240, 247500 }, + { 176400, TMDS_296M, 17836, 234375 }, + { 176400, TMDS_297M, 18816, 247500 }, + { 192000, TMDS_296M, 23296, 281250 }, + { 192000, TMDS_297M, 20480, 247500 }, +}; + /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ -static u32 audio_config_hdmi_pixel_clock(struct drm_display_mode *mode) +static u32 audio_config_hdmi_pixel_clock(const struct drm_display_mode *adjusted_mode) { int i; for (i = 0; i < ARRAY_SIZE(hdmi_audio_clock); i++) { - if (mode->clock == hdmi_audio_clock[i].clock) + if (adjusted_mode->crtc_clock == hdmi_audio_clock[i].clock) break; } if (i == ARRAY_SIZE(hdmi_audio_clock)) { - DRM_DEBUG_KMS("HDMI audio pixel clock setting for %d not found, falling back to defaults\n", mode->clock); + DRM_DEBUG_KMS("HDMI audio pixel clock setting for %d not found, falling back to defaults\n", + adjusted_mode->crtc_clock); i = 1; } @@ -90,6 +121,45 @@ static u32 audio_config_hdmi_pixel_clock(struct drm_display_mode *mode) return hdmi_audio_clock[i].config; } +static int audio_config_get_n(const struct drm_display_mode *mode, int rate) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(aud_ncts); i++) { + if ((rate == aud_ncts[i].sample_rate) && + (mode->clock == aud_ncts[i].clock)) { + return aud_ncts[i].n; + } + } + return 0; +} + +static uint32_t audio_config_setup_n_reg(int n, uint32_t val) +{ + int n_low, n_up; + uint32_t tmp = val; + + n_low = n & 0xfff; + n_up = (n >> 12) & 0xff; + tmp &= ~(AUD_CONFIG_UPPER_N_MASK | AUD_CONFIG_LOWER_N_MASK); + tmp |= ((n_up << AUD_CONFIG_UPPER_N_SHIFT) | + (n_low << AUD_CONFIG_LOWER_N_SHIFT) | + AUD_CONFIG_N_PROG_ENABLE); + return tmp; +} + +/* check whether N/CTS/M need be set manually */ +static bool audio_rate_need_prog(struct intel_crtc *crtc, + const struct drm_display_mode *mode) +{ + if (((mode->clock == TMDS_297M) || + (mode->clock == TMDS_296M)) && + intel_pipe_has_type(crtc, INTEL_OUTPUT_HDMI)) + return true; + else + return false; +} + static bool intel_eld_uptodate(struct drm_connector *connector, int reg_eldv, uint32_t bits_eldv, int reg_elda, uint32_t bits_elda, @@ -138,7 +208,7 @@ static void g4x_audio_codec_disable(struct intel_encoder *encoder) static void g4x_audio_codec_enable(struct drm_connector *connector, struct intel_encoder *encoder, - struct drm_display_mode *mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = connector->dev->dev_private; uint8_t *eld = connector->eld; @@ -184,6 +254,8 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder) DRM_DEBUG_KMS("Disable audio codec on pipe %c\n", pipe_name(pipe)); + mutex_lock(&dev_priv->av_mutex); + /* Disable timestamps */ tmp = I915_READ(HSW_AUD_CFG(pipe)); tmp &= ~AUD_CONFIG_N_VALUE_INDEX; @@ -199,22 +271,31 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder) tmp &= ~AUDIO_ELD_VALID(pipe); tmp &= ~AUDIO_OUTPUT_ENABLE(pipe); I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); + + mutex_unlock(&dev_priv->av_mutex); } static void hsw_audio_codec_enable(struct drm_connector *connector, struct intel_encoder *encoder, - struct drm_display_mode *mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = connector->dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); enum pipe pipe = intel_crtc->pipe; + struct i915_audio_component *acomp = dev_priv->audio_component; const uint8_t *eld = connector->eld; + struct intel_digital_port *intel_dig_port = + enc_to_dig_port(&encoder->base); + enum port port = intel_dig_port->port; uint32_t tmp; int len, i; + int n, rate; DRM_DEBUG_KMS("Enable audio codec on pipe %c, %u bytes ELD\n", pipe_name(pipe), drm_eld_size(eld)); + mutex_lock(&dev_priv->av_mutex); + /* Enable audio presence detect, invalidate ELD */ tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); tmp |= AUDIO_OUTPUT_ENABLE(pipe); @@ -246,13 +327,32 @@ static void hsw_audio_codec_enable(struct drm_connector *connector, /* Enable timestamps */ tmp = I915_READ(HSW_AUD_CFG(pipe)); tmp &= ~AUD_CONFIG_N_VALUE_INDEX; - tmp &= ~AUD_CONFIG_N_PROG_ENABLE; tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT)) tmp |= AUD_CONFIG_N_VALUE_INDEX; else - tmp |= audio_config_hdmi_pixel_clock(mode); + tmp |= audio_config_hdmi_pixel_clock(adjusted_mode); + + tmp &= ~AUD_CONFIG_N_PROG_ENABLE; + if (audio_rate_need_prog(intel_crtc, adjusted_mode)) { + if (!acomp) + rate = 0; + else if (port >= PORT_A && port <= PORT_E) + rate = acomp->aud_sample_rate[port]; + else { + DRM_ERROR("invalid port: %d\n", port); + rate = 0; + } + n = audio_config_get_n(adjusted_mode, rate); + if (n != 0) + tmp = audio_config_setup_n_reg(n, tmp); + else + DRM_DEBUG_KMS("no suitable N value is found\n"); + } + I915_WRITE(HSW_AUD_CFG(pipe), tmp); + + mutex_unlock(&dev_priv->av_mutex); } static void ilk_audio_codec_disable(struct intel_encoder *encoder) @@ -304,7 +404,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder) static void ilk_audio_codec_enable(struct drm_connector *connector, struct intel_encoder *encoder, - struct drm_display_mode *mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = connector->dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); @@ -381,7 +481,7 @@ static void ilk_audio_codec_enable(struct drm_connector *connector, if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT)) tmp |= AUD_CONFIG_N_VALUE_INDEX; else - tmp |= audio_config_hdmi_pixel_clock(mode); + tmp |= audio_config_hdmi_pixel_clock(adjusted_mode); I915_WRITE(aud_config, tmp); } @@ -396,7 +496,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; struct intel_crtc *crtc = to_intel_crtc(encoder->crtc); - struct drm_display_mode *mode = &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; struct drm_connector *connector; struct drm_device *dev = encoder->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -419,10 +519,11 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) connector->eld[5] |= (1 << 2); - connector->eld[6] = drm_av_sync_delay(connector, mode) / 2; + connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; if (dev_priv->display.audio_codec_enable) - dev_priv->display.audio_codec_enable(connector, intel_encoder, mode); + dev_priv->display.audio_codec_enable(connector, intel_encoder, + adjusted_mode); if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, (int) port); @@ -527,12 +628,91 @@ static int i915_audio_component_get_cdclk_freq(struct device *dev) return ret; } +static int i915_audio_component_sync_audio_rate(struct device *dev, + int port, int rate) +{ + struct drm_i915_private *dev_priv = dev_to_i915(dev); + struct drm_device *drm_dev = dev_priv->dev; + struct intel_encoder *intel_encoder; + struct intel_digital_port *intel_dig_port; + struct intel_crtc *crtc; + struct drm_display_mode *mode; + struct i915_audio_component *acomp = dev_priv->audio_component; + enum pipe pipe = -1; + u32 tmp; + int n; + + /* HSW, BDW SKL need this fix */ + if (!IS_SKYLAKE(dev_priv) && + !IS_BROADWELL(dev_priv) && + !IS_HASWELL(dev_priv)) + return 0; + + mutex_lock(&dev_priv->av_mutex); + /* 1. get the pipe */ + for_each_intel_encoder(drm_dev, intel_encoder) { + if (intel_encoder->type != INTEL_OUTPUT_HDMI) + continue; + intel_dig_port = enc_to_dig_port(&intel_encoder->base); + if (port == intel_dig_port->port) { + crtc = to_intel_crtc(intel_encoder->base.crtc); + if (!crtc) { + DRM_DEBUG_KMS("%s: crtc is NULL\n", __func__); + continue; + } + pipe = crtc->pipe; + break; + } + } + + if (pipe == INVALID_PIPE) { + DRM_DEBUG_KMS("no pipe for the port %c\n", port_name(port)); + mutex_unlock(&dev_priv->av_mutex); + return -ENODEV; + } + DRM_DEBUG_KMS("pipe %c connects port %c\n", + pipe_name(pipe), port_name(port)); + mode = &crtc->config->base.adjusted_mode; + + /* port must be valid now, otherwise the pipe will be invalid */ + acomp->aud_sample_rate[port] = rate; + + /* 2. check whether to set the N/CTS/M manually or not */ + if (!audio_rate_need_prog(crtc, mode)) { + tmp = I915_READ(HSW_AUD_CFG(pipe)); + tmp &= ~AUD_CONFIG_N_PROG_ENABLE; + I915_WRITE(HSW_AUD_CFG(pipe), tmp); + mutex_unlock(&dev_priv->av_mutex); + return 0; + } + + n = audio_config_get_n(mode, rate); + if (n == 0) { + DRM_DEBUG_KMS("Using automatic mode for N value on port %c\n", + port_name(port)); + tmp = I915_READ(HSW_AUD_CFG(pipe)); + tmp &= ~AUD_CONFIG_N_PROG_ENABLE; + I915_WRITE(HSW_AUD_CFG(pipe), tmp); + mutex_unlock(&dev_priv->av_mutex); + return 0; + } + + /* 3. set the N/CTS/M */ + tmp = I915_READ(HSW_AUD_CFG(pipe)); + tmp = audio_config_setup_n_reg(n, tmp); + I915_WRITE(HSW_AUD_CFG(pipe), tmp); + + mutex_unlock(&dev_priv->av_mutex); + return 0; +} + static const struct i915_audio_component_ops i915_audio_component_ops = { .owner = THIS_MODULE, .get_power = i915_audio_component_get_power, .put_power = i915_audio_component_put_power, .codec_wake_override = i915_audio_component_codec_wake_override, .get_cdclk_freq = i915_audio_component_get_cdclk_freq, + .sync_audio_rate = i915_audio_component_sync_audio_rate, }; static int i915_audio_component_bind(struct device *i915_dev, @@ -540,6 +720,7 @@ static int i915_audio_component_bind(struct device *i915_dev, { struct i915_audio_component *acomp = data; struct drm_i915_private *dev_priv = dev_to_i915(i915_dev); + int i; if (WARN_ON(acomp->ops || acomp->dev)) return -EEXIST; @@ -547,6 +728,9 @@ static int i915_audio_component_bind(struct device *i915_dev, drm_modeset_lock_all(dev_priv->dev); acomp->ops = &i915_audio_component_ops; acomp->dev = i915_dev; + BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS); + for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++) + acomp->aud_sample_rate[i] = 0; dev_priv->audio_component = acomp; drm_modeset_unlock_all(dev_priv->dev); diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index c19e669..68421c2 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1350,21 +1350,3 @@ intel_parse_bios(struct drm_device *dev) return 0; } - -/* Ensure that vital registers have been initialised, even if the BIOS - * is absent or just failing to do its job. - */ -void intel_setup_bios(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - /* Set the Panel Power On/Off timings if uninitialized. */ - if (!HAS_PCH_SPLIT(dev) && - I915_READ(PP_ON_DELAYS) == 0 && I915_READ(PP_OFF_DELAYS) == 0) { - /* Set T2 to 40ms and T5 to 200ms */ - I915_WRITE(PP_ON_DELAYS, 0x019007d0); - - /* Set T3 to 35ms and Tx to 200ms */ - I915_WRITE(PP_OFF_DELAYS, 0x015e07d0); - } -} diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h index 46cd5c7..7ec8c9a 100644 --- a/drivers/gpu/drm/i915/intel_bios.h +++ b/drivers/gpu/drm/i915/intel_bios.h @@ -588,7 +588,6 @@ struct bdb_psr { struct psr_table psr_table[16]; } __packed; -void intel_setup_bios(struct drm_device *dev); int intel_parse_bios(struct drm_device *dev); /* @@ -742,7 +741,6 @@ int intel_parse_bios(struct drm_device *dev); */ #define DEVICE_TYPE_eDP_BITS \ (DEVICE_TYPE_INTERNAL_CONNECTOR | \ - DEVICE_TYPE_NOT_HDMI_OUTPUT | \ DEVICE_TYPE_MIPI_OUTPUT | \ DEVICE_TYPE_COMPOSITE_OUTPUT | \ DEVICE_TYPE_DUAL_CHANNEL | \ @@ -750,7 +748,6 @@ int intel_parse_bios(struct drm_device *dev); DEVICE_TYPE_TMDS_DVI_SIGNALING | \ DEVICE_TYPE_VIDEO_SIGNALING | \ DEVICE_TYPE_DISPLAYPORT_OUTPUT | \ - DEVICE_TYPE_DIGITAL_OUTPUT | \ DEVICE_TYPE_ANALOG_OUTPUT) /* define the DVO port for HDMI output type */ diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index af5e43b..b84aaa0 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -158,7 +158,7 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crt *crt = intel_encoder_to_crt(encoder); struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; u32 adpa; if (INTEL_INFO(dev)->gen >= 5) @@ -376,7 +376,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct drm_i915_private *dev_priv = dev->dev_private; - u32 hotplug_en, orig, stat; + u32 stat; bool ret = false; int i, tries = 0; @@ -395,12 +395,12 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector) tries = 2; else tries = 1; - hotplug_en = orig = I915_READ(PORT_HOTPLUG_EN); - hotplug_en |= CRT_HOTPLUG_FORCE_DETECT; for (i = 0; i < tries ; i++) { /* turn on the FORCE_DETECT */ - I915_WRITE(PORT_HOTPLUG_EN, hotplug_en); + i915_hotplug_interrupt_update(dev_priv, + CRT_HOTPLUG_FORCE_DETECT, + CRT_HOTPLUG_FORCE_DETECT); /* wait for FORCE_DETECT to go off */ if (wait_for((I915_READ(PORT_HOTPLUG_EN) & CRT_HOTPLUG_FORCE_DETECT) == 0, @@ -415,8 +415,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector) /* clear the interrupt we just generated, if any */ I915_WRITE(PORT_HOTPLUG_STAT, CRT_HOTPLUG_INT_STATUS); - /* and put the bits back */ - I915_WRITE(PORT_HOTPLUG_EN, orig); + i915_hotplug_interrupt_update(dev_priv, CRT_HOTPLUG_FORCE_DETECT, 0); return ret; } @@ -891,7 +890,7 @@ void intel_crt_init(struct drm_device *dev) u32 fdi_config = FDI_RX_POLARITY_REVERSED_LPT | FDI_RX_LINK_REVERSAL_OVERRIDE; - dev_priv->fdi_rx_config = I915_READ(_FDI_RXA_CTL) & fdi_config; + dev_priv->fdi_rx_config = I915_READ(FDI_RX_CTL(PIPE_A)) & fdi_config; } intel_crt_reset(connector); diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index d0f1b8d..9e530a7 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -42,13 +42,15 @@ */ #define I915_CSR_SKL "i915/skl_dmc_ver1.bin" +#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" MODULE_FIRMWARE(I915_CSR_SKL); +MODULE_FIRMWARE(I915_CSR_BXT); /* * SKL CSR registers for DC5 and DC6 */ -#define CSR_PROGRAM_BASE 0x80000 +#define CSR_PROGRAM(i) (0x80000 + (i) * 4) #define CSR_SSP_BASE_ADDR_GEN9 0x00002FC0 #define CSR_HTP_ADDR_SKL 0x00500034 #define CSR_SSP_BASE 0x8F074 @@ -181,11 +183,19 @@ static const struct stepping_info skl_stepping_info[] = { {'G', '0'}, {'H', '0'}, {'I', '0'} }; +static struct stepping_info bxt_stepping_info[] = { + {'A', '0'}, {'A', '1'}, {'A', '2'}, + {'B', '0'}, {'B', '1'}, {'B', '2'} +}; + static char intel_get_stepping(struct drm_device *dev) { if (IS_SKYLAKE(dev) && (dev->pdev->revision < ARRAY_SIZE(skl_stepping_info))) return skl_stepping_info[dev->pdev->revision].stepping; + else if (IS_BROXTON(dev) && (dev->pdev->revision < + ARRAY_SIZE(bxt_stepping_info))) + return bxt_stepping_info[dev->pdev->revision].stepping; else return -ENODATA; } @@ -195,6 +205,9 @@ static char intel_get_substepping(struct drm_device *dev) if (IS_SKYLAKE(dev) && (dev->pdev->revision < ARRAY_SIZE(skl_stepping_info))) return skl_stepping_info[dev->pdev->revision].substepping; + else if (IS_BROXTON(dev) && (dev->pdev->revision < + ARRAY_SIZE(bxt_stepping_info))) + return bxt_stepping_info[dev->pdev->revision].substepping; else return -ENODATA; } @@ -252,11 +265,19 @@ void intel_csr_load_program(struct drm_device *dev) return; } + /* + * FIXME: Firmware gets lost on S3/S4, but not when entering system + * standby or suspend-to-idle (which is just like forced runtime pm). + * Unfortunately the ACPI subsystem doesn't yet give us a way to + * differentiate this, hence figure it out with this hack. + */ + if (I915_READ(CSR_PROGRAM(0))) + return; + mutex_lock(&dev_priv->csr_lock); fw_size = dev_priv->csr.dmc_fw_size; for (i = 0; i < fw_size; i++) - I915_WRITE(CSR_PROGRAM_BASE + i * 4, - payload[i]); + I915_WRITE(CSR_PROGRAM(i), payload[i]); for (i = 0; i < dev_priv->csr.mmio_count; i++) { I915_WRITE(dev_priv->csr.mmioaddr[i], @@ -409,6 +430,8 @@ void intel_csr_ucode_init(struct drm_device *dev) if (IS_SKYLAKE(dev)) csr->fw_path = I915_CSR_SKL; + else if (IS_BROXTON(dev_priv)) + csr->fw_path = I915_CSR_BXT; else { DRM_ERROR("Unexpected: no known CSR firmware for platform\n"); intel_csr_load_status_set(dev_priv, FW_FAILED); @@ -454,10 +477,10 @@ void intel_csr_ucode_fini(struct drm_device *dev) void assert_csr_loaded(struct drm_i915_private *dev_priv) { - WARN(intel_csr_load_status_get(dev_priv) != FW_LOADED, - "CSR is not loaded.\n"); - WARN(!I915_READ(CSR_PROGRAM_BASE), - "CSR program storage start is NULL\n"); - WARN(!I915_READ(CSR_SSP_BASE), "CSR SSP Base Not fine\n"); - WARN(!I915_READ(CSR_HTP_SKL), "CSR HTP Not fine\n"); + WARN_ONCE(intel_csr_load_status_get(dev_priv) != FW_LOADED, + "CSR is not loaded.\n"); + WARN_ONCE(!I915_READ(CSR_PROGRAM(0)), + "CSR program storage start is NULL\n"); + WARN_ONCE(!I915_READ(CSR_SSP_BASE), "CSR SSP Base Not fine\n"); + WARN_ONCE(!I915_READ(CSR_HTP_SKL), "CSR HTP Not fine\n"); } diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 61575f6..b25e99a 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -256,9 +256,6 @@ struct bxt_ddi_buf_trans { bool default_index; /* true if the entry represents default value */ }; -/* BSpec does not define separate vswing/pre-emphasis values for eDP. - * Using DP values for eDP as well. - */ static const struct bxt_ddi_buf_trans bxt_ddi_translations_dp[] = { /* Idx NT mV diff db */ { 52, 0x9A, 0, 128, true }, /* 0: 400 0 */ @@ -273,6 +270,20 @@ static const struct bxt_ddi_buf_trans bxt_ddi_translations_dp[] = { { 154, 0x9A, 1, 128, false }, /* 9: 1200 0 */ }; +static const struct bxt_ddi_buf_trans bxt_ddi_translations_edp[] = { + /* Idx NT mV diff db */ + { 26, 0, 0, 128, false }, /* 0: 200 0 */ + { 38, 0, 0, 112, false }, /* 1: 200 1.5 */ + { 48, 0, 0, 96, false }, /* 2: 200 4 */ + { 54, 0, 0, 69, false }, /* 3: 200 6 */ + { 32, 0, 0, 128, false }, /* 4: 250 0 */ + { 48, 0, 0, 104, false }, /* 5: 250 1.5 */ + { 54, 0, 0, 85, false }, /* 6: 250 4 */ + { 43, 0, 0, 128, false }, /* 7: 300 0 */ + { 54, 0, 0, 101, false }, /* 8: 300 1.5 */ + { 48, 0, 0, 128, false }, /* 9: 300 0 */ +}; + /* BSpec has 2 recommended values - entries 0 and 8. * Using the entry with higher vswing. */ @@ -298,21 +309,26 @@ static void ddi_get_encoder_port(struct intel_encoder *intel_encoder, enum port *port) { struct drm_encoder *encoder = &intel_encoder->base; - int type = intel_encoder->type; - if (type == INTEL_OUTPUT_DP_MST) { + switch (intel_encoder->type) { + case INTEL_OUTPUT_DP_MST: *dig_port = enc_to_mst(encoder)->primary; *port = (*dig_port)->port; - } else if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP || - type == INTEL_OUTPUT_HDMI || type == INTEL_OUTPUT_UNKNOWN) { + break; + case INTEL_OUTPUT_DISPLAYPORT: + case INTEL_OUTPUT_EDP: + case INTEL_OUTPUT_HDMI: + case INTEL_OUTPUT_UNKNOWN: *dig_port = enc_to_dig_port(encoder); *port = (*dig_port)->port; - } else if (type == INTEL_OUTPUT_ANALOG) { + break; + case INTEL_OUTPUT_ANALOG: *dig_port = NULL; *port = PORT_E; - } else { - DRM_ERROR("Invalid DDI encoder type %d\n", type); - BUG(); + break; + default: + WARN(1, "Invalid DDI encoder type %d\n", intel_encoder->type); + break; } } @@ -414,7 +430,6 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, bool supports_hdmi) { struct drm_i915_private *dev_priv = dev->dev_private; - u32 reg; u32 iboost_bit = 0; int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry, size; @@ -505,11 +520,11 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, BUG(); } - for (i = 0, reg = DDI_BUF_TRANS(port); i < size; i++) { - I915_WRITE(reg, ddi_translations[i].trans1 | iboost_bit); - reg += 4; - I915_WRITE(reg, ddi_translations[i].trans2); - reg += 4; + for (i = 0; i < size; i++) { + I915_WRITE(DDI_BUF_TRANS_LO(port, i), + ddi_translations[i].trans1 | iboost_bit); + I915_WRITE(DDI_BUF_TRANS_HI(port, i), + ddi_translations[i].trans2); } if (!supports_hdmi) @@ -521,10 +536,10 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, hdmi_level = hdmi_default_entry; /* Entry 9 is for HDMI: */ - I915_WRITE(reg, ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit); - reg += 4; - I915_WRITE(reg, ddi_translations_hdmi[hdmi_level].trans2); - reg += 4; + I915_WRITE(DDI_BUF_TRANS_LO(port, i), + ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit); + I915_WRITE(DDI_BUF_TRANS_HI(port, i), + ddi_translations_hdmi[hdmi_level].trans2); } /* Program DDI buffers translations for DP. By default, program ports A-D in DP @@ -543,8 +558,10 @@ void intel_prepare_ddi(struct drm_device *dev) enum port port; bool supports_hdmi; - ddi_get_encoder_port(intel_encoder, &intel_dig_port, &port); + if (intel_encoder->type == INTEL_OUTPUT_DSI) + continue; + ddi_get_encoder_port(intel_encoder, &intel_dig_port, &port); if (visited[port]) continue; @@ -593,7 +610,7 @@ void hsw_fdi_link_train(struct drm_crtc *crtc) * * WaFDIAutoLinkSetTimingOverrride:hsw */ - I915_WRITE(_FDI_RXA_MISC, FDI_RX_PWRDN_LANE1_VAL(2) | + I915_WRITE(FDI_RX_MISC(PIPE_A), FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2) | FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90); @@ -601,13 +618,13 @@ void hsw_fdi_link_train(struct drm_crtc *crtc) rx_ctl_val = dev_priv->fdi_rx_config | FDI_RX_ENHANCE_FRAME_ENABLE | FDI_RX_PLL_ENABLE | FDI_DP_PORT_WIDTH(intel_crtc->config->fdi_lanes); - I915_WRITE(_FDI_RXA_CTL, rx_ctl_val); - POSTING_READ(_FDI_RXA_CTL); + I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val); + POSTING_READ(FDI_RX_CTL(PIPE_A)); udelay(220); /* Switch from Rawclk to PCDclk */ rx_ctl_val |= FDI_PCDCLK; - I915_WRITE(_FDI_RXA_CTL, rx_ctl_val); + I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val); /* Configure Port Clock Select */ I915_WRITE(PORT_CLK_SEL(PORT_E), intel_crtc->config->ddi_pll_sel); @@ -636,21 +653,21 @@ void hsw_fdi_link_train(struct drm_crtc *crtc) udelay(600); /* Program PCH FDI Receiver TU */ - I915_WRITE(_FDI_RXA_TUSIZE1, TU_SIZE(64)); + I915_WRITE(FDI_RX_TUSIZE1(PIPE_A), TU_SIZE(64)); /* Enable PCH FDI Receiver with auto-training */ rx_ctl_val |= FDI_RX_ENABLE | FDI_LINK_TRAIN_AUTO; - I915_WRITE(_FDI_RXA_CTL, rx_ctl_val); - POSTING_READ(_FDI_RXA_CTL); + I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val); + POSTING_READ(FDI_RX_CTL(PIPE_A)); /* Wait for FDI receiver lane calibration */ udelay(30); /* Unset FDI_RX_MISC pwrdn lanes */ - temp = I915_READ(_FDI_RXA_MISC); + temp = I915_READ(FDI_RX_MISC(PIPE_A)); temp &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK); - I915_WRITE(_FDI_RXA_MISC, temp); - POSTING_READ(_FDI_RXA_MISC); + I915_WRITE(FDI_RX_MISC(PIPE_A), temp); + POSTING_READ(FDI_RX_MISC(PIPE_A)); /* Wait for FDI auto training time */ udelay(5); @@ -684,15 +701,15 @@ void hsw_fdi_link_train(struct drm_crtc *crtc) intel_wait_ddi_buf_idle(dev_priv, PORT_E); rx_ctl_val &= ~FDI_RX_ENABLE; - I915_WRITE(_FDI_RXA_CTL, rx_ctl_val); - POSTING_READ(_FDI_RXA_CTL); + I915_WRITE(FDI_RX_CTL(PIPE_A), rx_ctl_val); + POSTING_READ(FDI_RX_CTL(PIPE_A)); /* Reset FDI_RX_MISC pwrdn lanes */ - temp = I915_READ(_FDI_RXA_MISC); + temp = I915_READ(FDI_RX_MISC(PIPE_A)); temp &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK); temp |= FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2); - I915_WRITE(_FDI_RXA_MISC, temp); - POSTING_READ(_FDI_RXA_MISC); + I915_WRITE(FDI_RX_MISC(PIPE_A), temp); + POSTING_READ(FDI_RX_MISC(PIPE_A)); } DRM_ERROR("FDI link training failed!\n"); @@ -707,7 +724,6 @@ void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder) intel_dp->DP = intel_dig_port->saved_port_bits | DDI_BUF_CTL_ENABLE | DDI_BUF_TRANS_SELECT(0); intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count); - } static struct intel_encoder * @@ -955,8 +971,8 @@ static int skl_calc_wrpll_link(struct drm_i915_private *dev_priv, uint32_t cfgcr1_val, cfgcr2_val; uint32_t p0, p1, p2, dco_freq; - cfgcr1_reg = GET_CFG_CR1_REG(dpll); - cfgcr2_reg = GET_CFG_CR2_REG(dpll); + cfgcr1_reg = DPLL_CFGCR1(dpll); + cfgcr2_reg = DPLL_CFGCR2(dpll); cfgcr1_val = I915_READ(cfgcr1_reg); cfgcr2_val = I915_READ(cfgcr2_reg); @@ -1242,9 +1258,10 @@ hsw_ddi_calculate_wrpll(int clock /* in Hz */, static bool hsw_ddi_pll_select(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state, - struct intel_encoder *intel_encoder, - int clock) + struct intel_encoder *intel_encoder) { + int clock = crtc_state->port_clock; + if (intel_encoder->type == INTEL_OUTPUT_HDMI) { struct intel_shared_dpll *pll; uint32_t val; @@ -1523,11 +1540,11 @@ skip_remaining_dividers: static bool skl_ddi_pll_select(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state, - struct intel_encoder *intel_encoder, - int clock) + struct intel_encoder *intel_encoder) { struct intel_shared_dpll *pll; uint32_t ctrl1, cfgcr1, cfgcr2; + int clock = crtc_state->port_clock; /* * See comment in intel_dpll_hw_state to understand why we always use 0 @@ -1615,14 +1632,14 @@ static const struct bxt_clk_div bxt_dp_clk_val[] = { static bool bxt_ddi_pll_select(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state, - struct intel_encoder *intel_encoder, - int clock) + struct intel_encoder *intel_encoder) { struct intel_shared_dpll *pll; struct bxt_clk_div clk_div = {0}; int vco = 0; uint32_t prop_coef, int_coef, gain_ctl, targ_cnt; uint32_t lanestagger; + int clock = crtc_state->port_clock; if (intel_encoder->type == INTEL_OUTPUT_HDMI) { intel_clock_t best_clock; @@ -1750,17 +1767,16 @@ bool intel_ddi_pll_select(struct intel_crtc *intel_crtc, struct drm_device *dev = intel_crtc->base.dev; struct intel_encoder *intel_encoder = intel_ddi_get_crtc_new_encoder(crtc_state); - int clock = crtc_state->port_clock; if (IS_SKYLAKE(dev)) return skl_ddi_pll_select(intel_crtc, crtc_state, - intel_encoder, clock); + intel_encoder); else if (IS_BROXTON(dev)) return bxt_ddi_pll_select(intel_crtc, crtc_state, - intel_encoder, clock); + intel_encoder); else return hsw_ddi_pll_select(intel_crtc, crtc_state, - intel_encoder, clock); + intel_encoder); } void intel_ddi_set_pipe_settings(struct drm_crtc *crtc) @@ -1893,7 +1909,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc) } else temp |= TRANS_DDI_MODE_SELECT_DP_SST; - temp |= DDI_PORT_WIDTH(intel_dp->lane_count); + temp |= DDI_PORT_WIDTH(intel_crtc->config->lane_count); } else if (type == INTEL_OUTPUT_DP_MST) { struct intel_dp *intel_dp = &enc_to_mst(encoder)->primary->dp; @@ -1902,7 +1918,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc) } else temp |= TRANS_DDI_MODE_SELECT_DP_SST; - temp |= DDI_PORT_WIDTH(intel_dp->lane_count); + temp |= DDI_PORT_WIDTH(intel_crtc->config->lane_count); } else { WARN(1, "Invalid encoder type %d for pipe %c\n", intel_encoder->type, pipe_name(pipe)); @@ -2029,7 +2045,8 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc) { struct drm_crtc *crtc = &intel_crtc->base; - struct drm_i915_private *dev_priv = crtc->dev->dev_private; + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc); enum port port = intel_ddi_get_encoder_port(intel_encoder); enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder; @@ -2114,7 +2131,11 @@ static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level, u32 n_entries, i; uint32_t val; - if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { + if (type == INTEL_OUTPUT_EDP && dev_priv->edp_low_vswing) { + n_entries = ARRAY_SIZE(bxt_ddi_translations_edp); + ddi_translations = bxt_ddi_translations_edp; + } else if (type == INTEL_OUTPUT_DISPLAYPORT + || type == INTEL_OUTPUT_EDP) { n_entries = ARRAY_SIZE(bxt_ddi_translations_dp); ddi_translations = bxt_ddi_translations_dp; } else if (type == INTEL_OUTPUT_HDMI) { @@ -2152,9 +2173,13 @@ static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level, I915_WRITE(BXT_PORT_TX_DW2_GRP(port), val); val = I915_READ(BXT_PORT_TX_DW3_LN0(port)); - val &= ~UNIQE_TRANGE_EN_METHOD; + val &= ~SCALE_DCOMP_METHOD; if (ddi_translations[level].enable) - val |= UNIQE_TRANGE_EN_METHOD; + val |= SCALE_DCOMP_METHOD; + + if ((val & UNIQUE_TRANGE_EN_METHOD) && !(val & SCALE_DCOMP_METHOD)) + DRM_ERROR("Disabled scaling while ouniqetrangenmethod was set"); + I915_WRITE(BXT_PORT_TX_DW3_GRP(port), val); val = I915_READ(BXT_PORT_TX_DW4_LN0(port)); @@ -2289,11 +2314,12 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder) if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + intel_dp_set_link_params(intel_dp, crtc->config); + intel_ddi_init_dp_buf_reg(intel_encoder); intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); intel_dp_start_link_train(intel_dp); - intel_dp_complete_link_train(intel_dp); if (port != PORT_A || INTEL_INFO(dev)->gen >= 9) intel_dp_stop_link_train(intel_dp); } else if (type == INTEL_OUTPUT_HDMI) { @@ -2480,20 +2506,20 @@ static const struct skl_dpll_regs skl_dpll_regs[3] = { { /* DPLL 1 */ .ctl = LCPLL2_CTL, - .cfgcr1 = DPLL1_CFGCR1, - .cfgcr2 = DPLL1_CFGCR2, + .cfgcr1 = DPLL_CFGCR1(SKL_DPLL1), + .cfgcr2 = DPLL_CFGCR2(SKL_DPLL1), }, { /* DPLL 2 */ .ctl = WRPLL_CTL1, - .cfgcr1 = DPLL2_CFGCR1, - .cfgcr2 = DPLL2_CFGCR2, + .cfgcr1 = DPLL_CFGCR1(SKL_DPLL2), + .cfgcr2 = DPLL_CFGCR2(SKL_DPLL2), }, { /* DPLL 3 */ .ctl = WRPLL_CTL2, - .cfgcr1 = DPLL3_CFGCR1, - .cfgcr2 = DPLL3_CFGCR2, + .cfgcr1 = DPLL_CFGCR1(SKL_DPLL3), + .cfgcr2 = DPLL_CFGCR2(SKL_DPLL3), }, }; @@ -2881,7 +2907,7 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, * here just read out lanes 0/1 and output a note if lanes 2/3 differ. */ hw_state->pcsdw12 = I915_READ(BXT_PORT_PCS_DW12_LN01(port)); - if (I915_READ(BXT_PORT_PCS_DW12_LN23(port) != hw_state->pcsdw12)) + if (I915_READ(BXT_PORT_PCS_DW12_LN23(port)) != hw_state->pcsdw12) DRM_DEBUG_DRIVER("lane stagger config different for lane 01 (%08x) and 23 (%08x)\n", hw_state->pcsdw12, I915_READ(BXT_PORT_PCS_DW12_LN23(port))); @@ -2999,22 +3025,22 @@ void intel_ddi_fdi_disable(struct drm_crtc *crtc) intel_ddi_post_disable(intel_encoder); - val = I915_READ(_FDI_RXA_CTL); + val = I915_READ(FDI_RX_CTL(PIPE_A)); val &= ~FDI_RX_ENABLE; - I915_WRITE(_FDI_RXA_CTL, val); + I915_WRITE(FDI_RX_CTL(PIPE_A), val); - val = I915_READ(_FDI_RXA_MISC); + val = I915_READ(FDI_RX_MISC(PIPE_A)); val &= ~(FDI_RX_PWRDN_LANE1_MASK | FDI_RX_PWRDN_LANE0_MASK); val |= FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2); - I915_WRITE(_FDI_RXA_MISC, val); + I915_WRITE(FDI_RX_MISC(PIPE_A), val); - val = I915_READ(_FDI_RXA_CTL); + val = I915_READ(FDI_RX_CTL(PIPE_A)); val &= ~FDI_PCDCLK; - I915_WRITE(_FDI_RXA_CTL, val); + I915_WRITE(FDI_RX_CTL(PIPE_A), val); - val = I915_READ(_FDI_RXA_CTL); + val = I915_READ(FDI_RX_CTL(PIPE_A)); val &= ~FDI_RX_PLL_ENABLE; - I915_WRITE(_FDI_RXA_CTL, val); + I915_WRITE(FDI_RX_CTL(PIPE_A), val); } void intel_ddi_get_config(struct intel_encoder *encoder, @@ -3069,6 +3095,8 @@ void intel_ddi_get_config(struct intel_encoder *encoder, case TRANS_DDI_MODE_SELECT_DP_SST: case TRANS_DDI_MODE_SELECT_DP_MST: pipe_config->has_dp_encoder = true; + pipe_config->lane_count = + ((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1; intel_dp_get_m_n(intel_crtc, pipe_config); break; default: @@ -3215,7 +3243,15 @@ void intel_ddi_init(struct drm_device *dev, enum port port) goto err; intel_dig_port->hpd_pulse = intel_dp_hpd_pulse; - dev_priv->hotplug.irq_port[port] = intel_dig_port; + /* + * On BXT A0/A1, sw needs to activate DDIA HPD logic and + * interrupts to check the external panel connection. + */ + if (IS_BROXTON(dev_priv) && (INTEL_REVID(dev) < BXT_REVID_B0) + && port == PORT_B) + dev_priv->hotplug.irq_port[PORT_A] = intel_dig_port; + else + dev_priv->hotplug.irq_port[port] = intel_dig_port; } /* In theory we don't need the encoder->type check, but leave it just in diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 0379f14..cddb0c6 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -72,6 +72,10 @@ static const uint32_t skl_primary_formats[] = { DRM_FORMAT_ABGR8888, DRM_FORMAT_XRGB2101010, DRM_FORMAT_XBGR2101010, + DRM_FORMAT_YUYV, + DRM_FORMAT_YVYU, + DRM_FORMAT_UYVY, + DRM_FORMAT_VYUY, }; /* Cursor formats */ @@ -108,6 +112,9 @@ static void skl_init_scalers(struct drm_device *dev, struct intel_crtc *intel_cr struct intel_crtc_state *crtc_state); static int i9xx_get_refclk(const struct intel_crtc_state *crtc_state, int num_connectors); +static void skylake_pfit_enable(struct intel_crtc *crtc); +static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force); +static void ironlake_pfit_enable(struct intel_crtc *crtc); static void intel_modeset_setup_hw_state(struct drm_device *dev); typedef struct { @@ -125,6 +132,42 @@ struct intel_limit { intel_p2_t p2; }; +/* returns HPLL frequency in kHz */ +static int valleyview_get_vco(struct drm_i915_private *dev_priv) +{ + int hpll_freq, vco_freq[] = { 800, 1600, 2000, 2400 }; + + /* Obtain SKU information */ + mutex_lock(&dev_priv->sb_lock); + hpll_freq = vlv_cck_read(dev_priv, CCK_FUSE_REG) & + CCK_FUSE_HPLL_FREQ_MASK; + mutex_unlock(&dev_priv->sb_lock); + + return vco_freq[hpll_freq] * 1000; +} + +static int vlv_get_cck_clock_hpll(struct drm_i915_private *dev_priv, + const char *name, u32 reg) +{ + u32 val; + int divider; + + if (dev_priv->hpll_freq == 0) + dev_priv->hpll_freq = valleyview_get_vco(dev_priv); + + mutex_lock(&dev_priv->sb_lock); + val = vlv_cck_read(dev_priv, reg); + mutex_unlock(&dev_priv->sb_lock); + + divider = val & CCK_FREQUENCY_VALUES; + + WARN((val & CCK_FREQUENCY_STATUS) != + (divider << CCK_FREQUENCY_STATUS_SHIFT), + "%s change in progress\n", name); + + return DIV_ROUND_CLOSEST(dev_priv->hpll_freq << 1, divider + 1); +} + int intel_pch_rawclk(struct drm_device *dev) { @@ -135,6 +178,50 @@ intel_pch_rawclk(struct drm_device *dev) return I915_READ(PCH_RAWCLK_FREQ) & RAWCLK_FREQ_MASK; } +/* hrawclock is 1/4 the FSB frequency */ +int intel_hrawclk(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t clkcfg; + + /* There is no CLKCFG reg in Valleyview. VLV hrawclk is 200 MHz */ + if (IS_VALLEYVIEW(dev)) + return 200; + + clkcfg = I915_READ(CLKCFG); + switch (clkcfg & CLKCFG_FSB_MASK) { + case CLKCFG_FSB_400: + return 100; + case CLKCFG_FSB_533: + return 133; + case CLKCFG_FSB_667: + return 166; + case CLKCFG_FSB_800: + return 200; + case CLKCFG_FSB_1067: + return 266; + case CLKCFG_FSB_1333: + return 333; + /* these two are just a guess; one of them might be right */ + case CLKCFG_FSB_1600: + case CLKCFG_FSB_1600_ALT: + return 400; + default: + return 133; + } +} + +static void intel_update_czclk(struct drm_i915_private *dev_priv) +{ + if (!IS_VALLEYVIEW(dev_priv)) + return; + + dev_priv->czclk_freq = vlv_get_cck_clock_hpll(dev_priv, "czclk", + CCK_CZ_CLOCK_CONTROL); + + DRM_DEBUG_DRIVER("CZ clock rate: %d kHz\n", dev_priv->czclk_freq); +} + static inline u32 /* units of 100MHz */ intel_fdi_link_freq(struct drm_device *dev) { @@ -1061,54 +1148,6 @@ static void intel_wait_for_pipe_off(struct intel_crtc *crtc) } } -/* - * ibx_digital_port_connected - is the specified port connected? - * @dev_priv: i915 private structure - * @port: the port to test - * - * Returns true if @port is connected, false otherwise. - */ -bool ibx_digital_port_connected(struct drm_i915_private *dev_priv, - struct intel_digital_port *port) -{ - u32 bit; - - if (HAS_PCH_IBX(dev_priv->dev)) { - switch (port->port) { - case PORT_B: - bit = SDE_PORTB_HOTPLUG; - break; - case PORT_C: - bit = SDE_PORTC_HOTPLUG; - break; - case PORT_D: - bit = SDE_PORTD_HOTPLUG; - break; - default: - return true; - } - } else { - switch (port->port) { - case PORT_B: - bit = SDE_PORTB_HOTPLUG_CPT; - break; - case PORT_C: - bit = SDE_PORTC_HOTPLUG_CPT; - break; - case PORT_D: - bit = SDE_PORTD_HOTPLUG_CPT; - break; - case PORT_E: - bit = SDE_PORTE_HOTPLUG_SPT; - break; - default: - return true; - } - } - - return I915_READ(SDEISR) & bit; -} - static const char *state_string(bool enabled) { return enabled ? "on" : "off"; @@ -1303,7 +1342,7 @@ static void assert_cursor(struct drm_i915_private *dev_priv, bool cur_state; if (IS_845G(dev) || IS_I865G(dev)) - cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE; + cur_state = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE; else cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; @@ -1585,26 +1624,6 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv, assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMID); } -static void intel_init_dpio(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - if (!IS_VALLEYVIEW(dev)) - return; - - /* - * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C), - * CHV x1 PHY (DP/HDMI D) - * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C) - */ - if (IS_CHERRYVIEW(dev)) { - DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2; - DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO; - } else { - DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO; - } -} - static void vlv_enable_pll(struct intel_crtc *crtc, const struct intel_crtc_state *pipe_config) { @@ -1831,17 +1850,6 @@ static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) val &= ~DPIO_DCLKP_EN; vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), val); - /* disable left/right clock distribution */ - if (pipe != PIPE_B) { - val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0); - val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK); - vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val); - } else { - val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1); - val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK); - vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val); - } - mutex_unlock(&dev_priv->sb_lock); } @@ -2042,9 +2050,9 @@ static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv, assert_fdi_rx_enabled(dev_priv, TRANSCODER_A); /* Workaround: set timing override bit. */ - val = I915_READ(_TRANSA_CHICKEN2); + val = I915_READ(TRANS_CHICKEN2(PIPE_A)); val |= TRANS_CHICKEN2_TIMING_OVERRIDE; - I915_WRITE(_TRANSA_CHICKEN2, val); + I915_WRITE(TRANS_CHICKEN2(PIPE_A), val); val = TRANS_ENABLE; pipeconf_val = I915_READ(PIPECONF(cpu_transcoder)); @@ -2102,9 +2110,9 @@ static void lpt_disable_pch_transcoder(struct drm_i915_private *dev_priv) DRM_ERROR("Failed to disable PCH transcoder\n"); /* Workaround: clear timing override bit. */ - val = I915_READ(_TRANSA_CHICKEN2); + val = I915_READ(TRANS_CHICKEN2(PIPE_A)); val &= ~TRANS_CHICKEN2_TIMING_OVERRIDE; - I915_WRITE(_TRANSA_CHICKEN2, val); + I915_WRITE(TRANS_CHICKEN2(PIPE_A), val); } /** @@ -2229,7 +2237,7 @@ static bool need_vtd_wa(struct drm_device *dev) unsigned int intel_tile_height(struct drm_device *dev, uint32_t pixel_format, - uint64_t fb_format_modifier) + uint64_t fb_format_modifier, unsigned int plane) { unsigned int tile_height; uint32_t pixel_bytes; @@ -2245,7 +2253,7 @@ intel_tile_height(struct drm_device *dev, uint32_t pixel_format, tile_height = 32; break; case I915_FORMAT_MOD_Yf_TILED: - pixel_bytes = drm_format_plane_cpp(pixel_format, 0); + pixel_bytes = drm_format_plane_cpp(pixel_format, plane); switch (pixel_bytes) { default: case 1: @@ -2279,7 +2287,7 @@ intel_fb_align_height(struct drm_device *dev, unsigned int height, uint32_t pixel_format, uint64_t fb_format_modifier) { return ALIGN(height, intel_tile_height(dev, pixel_format, - fb_format_modifier)); + fb_format_modifier, 0)); } static int @@ -2302,15 +2310,27 @@ intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb, info->height = fb->height; info->pixel_format = fb->pixel_format; info->pitch = fb->pitches[0]; + info->uv_offset = fb->offsets[1]; info->fb_modifier = fb->modifier[0]; tile_height = intel_tile_height(fb->dev, fb->pixel_format, - fb->modifier[0]); + fb->modifier[0], 0); tile_pitch = PAGE_SIZE / tile_height; info->width_pages = DIV_ROUND_UP(fb->pitches[0], tile_pitch); info->height_pages = DIV_ROUND_UP(fb->height, tile_height); info->size = info->width_pages * info->height_pages * PAGE_SIZE; + if (info->pixel_format == DRM_FORMAT_NV12) { + tile_height = intel_tile_height(fb->dev, fb->pixel_format, + fb->modifier[0], 1); + tile_pitch = PAGE_SIZE / tile_height; + info->width_pages_uv = DIV_ROUND_UP(fb->pitches[0], tile_pitch); + info->height_pages_uv = DIV_ROUND_UP(fb->height / 2, + tile_height); + info->size_uv = info->width_pages_uv * info->height_pages_uv * + PAGE_SIZE; + } + return 0; } @@ -2525,6 +2545,7 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc, struct intel_initial_plane_config *plane_config) { struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); struct drm_i915_gem_object *obj = NULL; struct drm_mode_fb_cmd2 mode_cmd = { 0 }; struct drm_framebuffer *fb = &plane_config->fb->base; @@ -2537,6 +2558,12 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc, if (plane_config->size == 0) return false; + /* If the FB is too big, just don't use it since fbdev is not very + * important and we should probably use that space with FBC or other + * features. */ + if (size_aligned * 2 > dev_priv->gtt.stolen_usable_size) + return false; + obj = i915_gem_object_create_stolen_for_preallocated(dev, base_aligned, base_aligned, @@ -2769,6 +2796,9 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc, (intel_crtc->config->pipe_src_w - 1) * pixel_size; } + intel_crtc->adjusted_x = x; + intel_crtc->adjusted_y = y; + I915_WRITE(reg, dspcntr); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); @@ -2869,6 +2899,9 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc, } } + intel_crtc->adjusted_x = x; + intel_crtc->adjusted_y = y; + I915_WRITE(reg, dspcntr); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); @@ -2918,14 +2951,29 @@ u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier, } unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane, - struct drm_i915_gem_object *obj) + struct drm_i915_gem_object *obj, + unsigned int plane) { const struct i915_ggtt_view *view = &i915_ggtt_view_normal; + struct i915_vma *vma; + unsigned char *offset; if (intel_rotation_90_or_270(intel_plane->base.state->rotation)) view = &i915_ggtt_view_rotated; - return i915_gem_obj_ggtt_offset_view(obj, view); + vma = i915_gem_obj_to_ggtt_view(obj, view); + if (WARN(!vma, "ggtt vma for display object not found! (view=%u)\n", + view->type)) + return -1; + + offset = (unsigned char *)vma->node.start; + + if (plane == 1) { + offset += vma->ggtt_view.rotation_info.uv_start_page * + PAGE_SIZE; + } + + return (unsigned long)offset; } static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id) @@ -2936,8 +2984,6 @@ static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id) I915_WRITE(SKL_PS_CTRL(intel_crtc->pipe, id), 0); I915_WRITE(SKL_PS_WIN_POS(intel_crtc->pipe, id), 0); I915_WRITE(SKL_PS_WIN_SZ(intel_crtc->pipe, id), 0); - DRM_DEBUG_KMS("CRTC:%d Disabled scaler id %u.%u\n", - intel_crtc->base.base.id, intel_crtc->pipe, id); } /* @@ -3083,34 +3129,26 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc, obj = intel_fb_obj(fb); stride_div = intel_fb_stride_alignment(dev, fb->modifier[0], fb->pixel_format); - surf_addr = intel_plane_obj_offset(to_intel_plane(plane), obj); + surf_addr = intel_plane_obj_offset(to_intel_plane(plane), obj, 0); - /* - * FIXME: intel_plane_state->src, dst aren't set when transitional - * update_plane helpers are called from legacy paths. - * Once full atomic crtc is available, below check can be avoided. - */ - if (drm_rect_width(&plane_state->src)) { - scaler_id = plane_state->scaler_id; - src_x = plane_state->src.x1 >> 16; - src_y = plane_state->src.y1 >> 16; - src_w = drm_rect_width(&plane_state->src) >> 16; - src_h = drm_rect_height(&plane_state->src) >> 16; - dst_x = plane_state->dst.x1; - dst_y = plane_state->dst.y1; - dst_w = drm_rect_width(&plane_state->dst); - dst_h = drm_rect_height(&plane_state->dst); - - WARN_ON(x != src_x || y != src_y); - } else { - src_w = intel_crtc->config->pipe_src_w; - src_h = intel_crtc->config->pipe_src_h; - } + WARN_ON(drm_rect_width(&plane_state->src) == 0); + + scaler_id = plane_state->scaler_id; + src_x = plane_state->src.x1 >> 16; + src_y = plane_state->src.y1 >> 16; + src_w = drm_rect_width(&plane_state->src) >> 16; + src_h = drm_rect_height(&plane_state->src) >> 16; + dst_x = plane_state->dst.x1; + dst_y = plane_state->dst.y1; + dst_w = drm_rect_width(&plane_state->dst); + dst_h = drm_rect_height(&plane_state->dst); + + WARN_ON(x != src_x || y != src_y); if (intel_rotation_90_or_270(rotation)) { /* stride = Surface height in tiles */ tile_height = intel_tile_height(dev, fb->pixel_format, - fb->modifier[0]); + fb->modifier[0], 0); stride = DIV_ROUND_UP(fb->height, tile_height); x_offset = stride * tile_height - y - src_h; y_offset = x; @@ -3123,6 +3161,9 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc, } plane_offset = y_offset << 16 | x_offset; + intel_crtc->adjusted_x = x_offset; + intel_crtc->adjusted_y = y_offset; + I915_WRITE(PLANE_CTL(pipe, 0), plane_ctl); I915_WRITE(PLANE_OFFSET(pipe, 0), plane_offset); I915_WRITE(PLANE_SIZE(pipe, 0), plane_size); @@ -3179,24 +3220,20 @@ static void intel_complete_page_flips(struct drm_device *dev) static void intel_update_primary_planes(struct drm_device *dev) { - struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc *crtc; for_each_crtc(dev, crtc) { - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_plane *plane = to_intel_plane(crtc->primary); + struct intel_plane_state *plane_state; - drm_modeset_lock(&crtc->mutex, NULL); - /* - * FIXME: Once we have proper support for primary planes (and - * disabling them without disabling the entire crtc) allow again - * a NULL crtc->primary->fb. - */ - if (intel_crtc->active && crtc->primary->fb) - dev_priv->display.update_primary_plane(crtc, - crtc->primary->fb, - crtc->x, - crtc->y); - drm_modeset_unlock(&crtc->mutex); + drm_modeset_lock_crtc(crtc, &plane->base); + + plane_state = to_intel_plane_state(plane->base.state); + + if (plane_state->base.fb) + plane->commit_plane(&plane->base, plane_state); + + drm_modeset_unlock_crtc(crtc); } } @@ -3240,6 +3277,9 @@ void intel_finish_reset(struct drm_device *dev) * so update the base address of all primary * planes to the the last fb to make sure we're * showing the correct fb after a reset. + * + * FIXME: Atomic will make this obsolete since we won't schedule + * CS-based flips (which might get lost in gpu resets) any more. */ intel_update_primary_planes(dev); return; @@ -3310,14 +3350,23 @@ static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc) return pending; } -static void intel_update_pipe_size(struct intel_crtc *crtc) +static void intel_update_pipe_config(struct intel_crtc *crtc, + struct intel_crtc_state *old_crtc_state) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - const struct drm_display_mode *adjusted_mode; + struct intel_crtc_state *pipe_config = + to_intel_crtc_state(crtc->base.state); - if (!i915.fastboot) - return; + /* drm_atomic_helper_update_legacy_modeset_state might not be called. */ + crtc->base.mode = crtc->base.state->mode; + + DRM_DEBUG_KMS("Updating pipe size %ix%i -> %ix%i\n", + old_crtc_state->pipe_src_w, old_crtc_state->pipe_src_h, + pipe_config->pipe_src_w, pipe_config->pipe_src_h); + + if (HAS_DDI(dev)) + intel_set_pipe_csc(&crtc->base); /* * Update pipe size and adjust fitter if needed: the reason for this is @@ -3326,27 +3375,24 @@ static void intel_update_pipe_size(struct intel_crtc *crtc) * fastboot case, we'll flip, but if we don't update the pipesrc and * pfit state, we'll end up with a big fb scanned out into the wrong * sized surface. - * - * To fix this properly, we need to hoist the checks up into - * compute_mode_changes (or above), check the actual pfit state and - * whether the platform allows pfit disable with pipe active, and only - * then update the pipesrc and pfit state, even on the flip path. */ - adjusted_mode = &crtc->config->base.adjusted_mode; - I915_WRITE(PIPESRC(crtc->pipe), - ((adjusted_mode->crtc_hdisplay - 1) << 16) | - (adjusted_mode->crtc_vdisplay - 1)); - if (!crtc->config->pch_pfit.enabled && - (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) || - intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) { - I915_WRITE(PF_CTL(crtc->pipe), 0); - I915_WRITE(PF_WIN_POS(crtc->pipe), 0); - I915_WRITE(PF_WIN_SZ(crtc->pipe), 0); + ((pipe_config->pipe_src_w - 1) << 16) | + (pipe_config->pipe_src_h - 1)); + + /* on skylake this is done by detaching scalers */ + if (INTEL_INFO(dev)->gen >= 9) { + skl_detach_scalers(crtc); + + if (pipe_config->pch_pfit.enabled) + skylake_pfit_enable(crtc); + } else if (HAS_PCH_SPLIT(dev)) { + if (pipe_config->pch_pfit.enabled) + ironlake_pfit_enable(crtc); + else if (old_crtc_state->pch_pfit.enabled) + ironlake_pfit_disable(crtc, true); } - crtc->config->pipe_src_w = adjusted_mode->crtc_hdisplay; - crtc->config->pipe_src_h = adjusted_mode->crtc_vdisplay; } static void intel_fdi_normal_train(struct drm_crtc *crtc) @@ -4392,8 +4438,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, int skl_update_scaler_crtc(struct intel_crtc_state *state) { struct intel_crtc *intel_crtc = to_intel_crtc(state->base.crtc); - struct drm_display_mode *adjusted_mode = - &state->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &state->base.adjusted_mode; DRM_DEBUG_KMS("Updating scaler for [CRTC:%i] scaler_user index %u.%u\n", intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX); @@ -4401,7 +4446,7 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state) return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX, &state->scaler_state.scaler_id, DRM_ROTATE_0, state->pipe_src_w, state->pipe_src_h, - adjusted_mode->hdisplay, adjusted_mode->vdisplay); + adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay); } /** @@ -4594,7 +4639,6 @@ static void intel_crtc_load_lut(struct drm_crtc *crtc) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum pipe pipe = intel_crtc->pipe; - int palreg = PALETTE(pipe); int i; bool reenable_ips = false; @@ -4609,10 +4653,6 @@ static void intel_crtc_load_lut(struct drm_crtc *crtc) assert_pll_enabled(dev_priv, pipe); } - /* use legacy palette for Ironlake */ - if (!HAS_GMCH_DISPLAY(dev)) - palreg = LGC_PALETTE(pipe); - /* Workaround : Do not read or write the pipe palette/gamma data while * GAMMA_MODE is configured for split gamma and IPS_CTL has IPS enabled. */ @@ -4624,7 +4664,14 @@ static void intel_crtc_load_lut(struct drm_crtc *crtc) } for (i = 0; i < 256; i++) { - I915_WRITE(palreg + 4 * i, + u32 palreg; + + if (HAS_GMCH_DISPLAY(dev)) + palreg = PALETTE(pipe, i); + else + palreg = LGC_PALETTE(pipe, i); + + I915_WRITE(palreg, (intel_crtc->lut_r[i] << 16) | (intel_crtc->lut_g[i] << 8) | intel_crtc->lut_b[i]); @@ -4757,7 +4804,6 @@ static void intel_post_plane_update(struct intel_crtc *crtc) struct intel_crtc_atomic_commit *atomic = &crtc->atomic; struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_plane *plane; if (atomic->wait_vblank) intel_wait_for_vblank(dev, crtc->pipe); @@ -4776,10 +4822,6 @@ static void intel_post_plane_update(struct intel_crtc *crtc) if (atomic->post_enable_primary) intel_post_enable_primary(&crtc->base); - drm_for_each_plane_mask(plane, dev, atomic->update_sprite_watermarks) - intel_update_sprite_watermarks(plane, &crtc->base, - 0, 0, 0, false, false); - memset(atomic, 0, sizeof(*atomic)); } @@ -4922,6 +4964,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) int pipe = intel_crtc->pipe, hsw_workaround_pipe; struct intel_crtc_state *pipe_config = to_intel_crtc_state(crtc->state); + bool is_dsi = intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DSI); if (WARN_ON(intel_crtc->active)) return; @@ -4951,9 +4994,12 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) intel_crtc->active = true; intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); - for_each_encoder_on_crtc(dev, crtc, encoder) + for_each_encoder_on_crtc(dev, crtc, encoder) { + if (encoder->pre_pll_enable) + encoder->pre_pll_enable(encoder); if (encoder->pre_enable) encoder->pre_enable(encoder); + } if (intel_crtc->config->has_pch_encoder) { intel_set_pch_fifo_underrun_reporting(dev_priv, TRANSCODER_A, @@ -4961,14 +5007,13 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) dev_priv->display.fdi_link_train(crtc); } - intel_ddi_enable_pipe_clock(intel_crtc); + if (!is_dsi) + intel_ddi_enable_pipe_clock(intel_crtc); - if (INTEL_INFO(dev)->gen == 9) + if (INTEL_INFO(dev)->gen >= 9) skylake_pfit_enable(intel_crtc); - else if (INTEL_INFO(dev)->gen < 9) - ironlake_pfit_enable(intel_crtc); else - MISSING_CASE(INTEL_INFO(dev)->gen); + ironlake_pfit_enable(intel_crtc); /* * On ILK+ LUT must be loaded before the pipe is running but with @@ -4977,7 +5022,8 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) intel_crtc_load_lut(crtc); intel_ddi_set_pipe_settings(crtc); - intel_ddi_enable_transcoder_func(crtc); + if (!is_dsi) + intel_ddi_enable_transcoder_func(crtc); intel_update_watermarks(crtc); intel_enable_pipe(intel_crtc); @@ -4985,7 +5031,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) if (intel_crtc->config->has_pch_encoder) lpt_pch_enable(crtc); - if (intel_crtc->config->dp_encoder_is_mst) + if (intel_crtc->config->dp_encoder_is_mst && !is_dsi) intel_ddi_set_vc_payload_alloc(crtc, true); assert_vblank_disabled(crtc); @@ -5005,7 +5051,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) } } -static void ironlake_pfit_disable(struct intel_crtc *crtc) +static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -5013,7 +5059,7 @@ static void ironlake_pfit_disable(struct intel_crtc *crtc) /* To avoid upsetting the power well on haswell only disable the pfit if * it's in use. The hw state code will make sure we get this right. */ - if (crtc->config->pch_pfit.enabled) { + if (force || crtc->config->pch_pfit.enabled) { I915_WRITE(PF_CTL(pipe), 0); I915_WRITE(PF_WIN_POS(pipe), 0); I915_WRITE(PF_WIN_SZ(pipe), 0); @@ -5040,7 +5086,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) intel_disable_pipe(intel_crtc); - ironlake_pfit_disable(intel_crtc); + ironlake_pfit_disable(intel_crtc, false); if (intel_crtc->config->has_pch_encoder) ironlake_fdi_disable(crtc); @@ -5069,9 +5115,6 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) ironlake_fdi_pll_disable(intel_crtc); } - - intel_crtc->active = false; - intel_update_watermarks(crtc); } static void haswell_crtc_disable(struct drm_crtc *crtc) @@ -5081,6 +5124,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder; + bool is_dsi = intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DSI); for_each_encoder_on_crtc(dev, crtc, encoder) { intel_opregion_notify_encoder(encoder, false); @@ -5098,16 +5142,16 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) if (intel_crtc->config->dp_encoder_is_mst) intel_ddi_set_vc_payload_alloc(crtc, false); - intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder); + if (!is_dsi) + intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder); - if (INTEL_INFO(dev)->gen == 9) + if (INTEL_INFO(dev)->gen >= 9) skylake_scaler_disable(intel_crtc); - else if (INTEL_INFO(dev)->gen < 9) - ironlake_pfit_disable(intel_crtc); else - MISSING_CASE(INTEL_INFO(dev)->gen); + ironlake_pfit_disable(intel_crtc, false); - intel_ddi_disable_pipe_clock(intel_crtc); + if (!is_dsi) + intel_ddi_disable_pipe_clock(intel_crtc); if (intel_crtc->config->has_pch_encoder) { lpt_disable_pch_transcoder(dev_priv); @@ -5117,9 +5161,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->post_disable) encoder->post_disable(encoder); - - intel_crtc->active = false; - intel_update_watermarks(crtc); } static void i9xx_pfit_enable(struct intel_crtc *crtc) @@ -5277,6 +5318,21 @@ static void modeset_update_crtc_power_domains(struct drm_atomic_state *state) modeset_put_power_domains(dev_priv, put_domains[i]); } +static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) +{ + int max_cdclk_freq = dev_priv->max_cdclk_freq; + + if (INTEL_INFO(dev_priv)->gen >= 9 || + IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) + return max_cdclk_freq; + else if (IS_CHERRYVIEW(dev_priv)) + return max_cdclk_freq*95/100; + else if (INTEL_INFO(dev_priv)->gen < 4) + return 2*max_cdclk_freq*90/100; + else + return max_cdclk_freq*90/100; +} + static void intel_update_max_cdclk(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -5316,8 +5372,13 @@ static void intel_update_max_cdclk(struct drm_device *dev) dev_priv->max_cdclk_freq = dev_priv->cdclk_freq; } + dev_priv->max_dotclk_freq = intel_compute_max_dotclk(dev_priv); + DRM_DEBUG_DRIVER("Max CD clock rate: %d kHz\n", dev_priv->max_cdclk_freq); + + DRM_DEBUG_DRIVER("Max dotclock rate: %d kHz\n", + dev_priv->max_dotclk_freq); } static void intel_update_cdclk(struct drm_device *dev) @@ -5693,10 +5754,16 @@ void skl_uninit_cdclk(struct drm_i915_private *dev_priv) if (I915_READ(DBUF_CTL) & DBUF_POWER_STATE) DRM_ERROR("DBuf power disable timeout\n"); - /* disable DPLL0 */ - I915_WRITE(LCPLL1_CTL, I915_READ(LCPLL1_CTL) & ~LCPLL_PLL_ENABLE); - if (wait_for(!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_LOCK), 1)) - DRM_ERROR("Couldn't disable DPLL0\n"); + /* + * DMC assumes ownership of LCPLL and will get confused if we touch it. + */ + if (dev_priv->csr.dmc_payload) { + /* disable DPLL0 */ + I915_WRITE(LCPLL1_CTL, I915_READ(LCPLL1_CTL) & + ~LCPLL_PLL_ENABLE); + if (wait_for(!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_LOCK), 1)) + DRM_ERROR("Couldn't disable DPLL0\n"); + } intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); } @@ -5733,20 +5800,6 @@ void skl_init_cdclk(struct drm_i915_private *dev_priv) DRM_ERROR("DBuf power enable timeout\n"); } -/* returns HPLL frequency in kHz */ -static int valleyview_get_vco(struct drm_i915_private *dev_priv) -{ - int hpll_freq, vco_freq[] = { 800, 1600, 2000, 2400 }; - - /* Obtain SKU information */ - mutex_lock(&dev_priv->sb_lock); - hpll_freq = vlv_cck_read(dev_priv, CCK_FUSE_REG) & - CCK_FUSE_HPLL_FREQ_MASK; - mutex_unlock(&dev_priv->sb_lock); - - return vco_freq[hpll_freq] * 1000; -} - /* Adjust CDclk dividers to allow high res or save power if possible */ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk) { @@ -5784,12 +5837,12 @@ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk) /* adjust cdclk divider */ val = vlv_cck_read(dev_priv, CCK_DISPLAY_CLOCK_CONTROL); - val &= ~DISPLAY_FREQUENCY_VALUES; + val &= ~CCK_FREQUENCY_VALUES; val |= divider; vlv_cck_write(dev_priv, CCK_DISPLAY_CLOCK_CONTROL, val); if (wait_for((vlv_cck_read(dev_priv, CCK_DISPLAY_CLOCK_CONTROL) & - DISPLAY_FREQUENCY_STATUS) == (divider << DISPLAY_FREQUENCY_STATUS_SHIFT), + CCK_FREQUENCY_STATUS) == (divider << CCK_FREQUENCY_STATUS_SHIFT), 50)) DRM_ERROR("timed out waiting for CDclk change\n"); } @@ -5967,7 +6020,7 @@ static void vlv_program_pfi_credits(struct drm_i915_private *dev_priv) else default_credits = PFI_CREDIT(8); - if (DIV_ROUND_CLOSEST(dev_priv->cdclk_freq, 1000) >= dev_priv->rps.cz_freq) { + if (dev_priv->cdclk_freq >= dev_priv->czclk_freq) { /* CHV suggested value is 31 or 63 */ if (IS_CHERRYVIEW(dev_priv)) credits = PFI_CREDIT_63; @@ -6035,13 +6088,6 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc) is_dsi = intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DSI); - if (!is_dsi) { - if (IS_CHERRYVIEW(dev)) - chv_prepare_pll(intel_crtc, intel_crtc->config); - else - vlv_prepare_pll(intel_crtc, intel_crtc->config); - } - if (intel_crtc->config->has_dp_encoder) intel_dp_set_m_n(intel_crtc, M1_N1); @@ -6065,10 +6111,13 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc) encoder->pre_pll_enable(encoder); if (!is_dsi) { - if (IS_CHERRYVIEW(dev)) + if (IS_CHERRYVIEW(dev)) { + chv_prepare_pll(intel_crtc, intel_crtc->config); chv_enable_pll(intel_crtc, intel_crtc->config); - else + } else { + vlv_prepare_pll(intel_crtc, intel_crtc->config); vlv_enable_pll(intel_crtc, intel_crtc->config); + } } for_each_encoder_on_crtc(dev, crtc, encoder) @@ -6196,11 +6245,12 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc) i9xx_disable_pll(intel_crtc); } + for_each_encoder_on_crtc(dev, crtc, encoder) + if (encoder->post_pll_disable) + encoder->post_pll_disable(encoder); + if (!IS_GEN2(dev)) intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); - - intel_crtc->active = false; - intel_update_watermarks(crtc); } static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) @@ -6220,6 +6270,8 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) intel_crtc_disable_planes(crtc, crtc->state->plane_mask); dev_priv->display.crtc_disable(crtc); + intel_crtc->active = false; + intel_update_watermarks(crtc); intel_disable_shared_dpll(intel_crtc); domains = intel_crtc->enabled_power_domains; @@ -6456,7 +6508,7 @@ static int ironlake_fdi_compute_config(struct intel_crtc *intel_crtc, struct intel_crtc_state *pipe_config) { struct drm_device *dev = intel_crtc->base.dev; - struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; int lane, link_bw, fdi_dotclock, ret; bool needs_recompute = false; @@ -6535,7 +6587,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; /* FIXME should check pixel clock limits on all platforms */ if (INTEL_INFO(dev)->gen < 4) { @@ -6572,7 +6624,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc, * WaPruneModeWithIncorrectHsyncOffset:ctg,elk,ilk,snb,ivb,vlv,hsw. */ if ((INTEL_INFO(dev)->gen > 4 || IS_G4X(dev)) && - adjusted_mode->hsync_start == adjusted_mode->hdisplay) + adjusted_mode->crtc_hsync_start == adjusted_mode->crtc_hdisplay) return -EINVAL; if (HAS_IPS(dev)) @@ -6699,24 +6751,8 @@ static int haswell_get_display_clock_speed(struct drm_device *dev) static int valleyview_get_display_clock_speed(struct drm_device *dev) { - struct drm_i915_private *dev_priv = dev->dev_private; - u32 val; - int divider; - - if (dev_priv->hpll_freq == 0) - dev_priv->hpll_freq = valleyview_get_vco(dev_priv); - - mutex_lock(&dev_priv->sb_lock); - val = vlv_cck_read(dev_priv, CCK_DISPLAY_CLOCK_CONTROL); - mutex_unlock(&dev_priv->sb_lock); - - divider = val & DISPLAY_FREQUENCY_VALUES; - - WARN((val & DISPLAY_FREQUENCY_STATUS) != - (divider << DISPLAY_FREQUENCY_STATUS_SHIFT), - "cdclk change in progress\n"); - - return DIV_ROUND_CLOSEST(dev_priv->hpll_freq << 1, divider + 1); + return vlv_get_cck_clock_hpll(to_i915(dev), "cdclk", + CCK_DISPLAY_CLOCK_CONTROL); } static int ilk_get_display_clock_speed(struct drm_device *dev) @@ -7377,8 +7413,7 @@ static void chv_prepare_pll(struct intel_crtc *crtc, 1 << DPIO_CHV_N_DIV_SHIFT); /* M2 fraction division */ - if (bestm2_frac) - vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac); + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac); /* M2 fraction division enable */ dpio_val = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW3(port)); @@ -7604,8 +7639,7 @@ static void intel_set_pipe_timings(struct intel_crtc *intel_crtc) struct drm_i915_private *dev_priv = dev->dev_private; enum pipe pipe = intel_crtc->pipe; enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder; - struct drm_display_mode *adjusted_mode = - &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; uint32_t crtc_vtotal, crtc_vblank_end; int vsyncshift = 0; @@ -8119,6 +8153,14 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, else i9xx_crtc_clock_get(crtc, pipe_config); + /* + * Normally the dotclock is filled in by the encoder .get_config() + * but in case the pipe is enabled w/o any ports we need a sane + * default. + */ + pipe_config->base.adjusted_mode.crtc_clock = + pipe_config->port_clock / pipe_config->pixel_multiplier; + return true; } @@ -8380,8 +8422,7 @@ static void lpt_enable_clkout_dp(struct drm_device *dev, bool with_spread, if (WARN(with_fdi && !with_spread, "FDI requires downspread\n")) with_spread = true; - if (WARN(dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE && - with_fdi, "LP PCH doesn't have FDI\n")) + if (WARN(HAS_PCH_LPT_LP(dev) && with_fdi, "LP PCH doesn't have FDI\n")) with_fdi = false; mutex_lock(&dev_priv->sb_lock); @@ -8404,8 +8445,7 @@ static void lpt_enable_clkout_dp(struct drm_device *dev, bool with_spread, } } - reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ? - SBI_GEN0 : SBI_DBUFF0; + reg = HAS_PCH_LPT_LP(dev) ? SBI_GEN0 : SBI_DBUFF0; tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); tmp |= SBI_GEN0_CFG_BUFFENABLE_DISABLE; intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); @@ -8421,8 +8461,7 @@ static void lpt_disable_clkout_dp(struct drm_device *dev) mutex_lock(&dev_priv->sb_lock); - reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ? - SBI_GEN0 : SBI_DBUFF0; + reg = HAS_PCH_LPT_LP(dev) ? SBI_GEN0 : SBI_DBUFF0; tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK); tmp &= ~SBI_GEN0_CFG_BUFFENABLE_DISABLE; intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK); @@ -9434,7 +9473,7 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv) DRM_DEBUG_KMS("Enabling package C8+\n"); - if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) { + if (HAS_PCH_LPT_LP(dev)) { val = I915_READ(SOUTH_DSPCLK_GATE_D); val &= ~PCH_LP_PARTITION_LEVEL_DISABLE; I915_WRITE(SOUTH_DSPCLK_GATE_D, val); @@ -9454,7 +9493,7 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) hsw_restore_lcpll(dev_priv); lpt_init_pch_refclk(dev); - if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) { + if (HAS_PCH_LPT_LP(dev)) { val = I915_READ(SOUTH_DSPCLK_GATE_D); val |= PCH_LP_PARTITION_LEVEL_DISABLE; I915_WRITE(SOUTH_DSPCLK_GATE_D, val); @@ -9804,12 +9843,10 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, } if (intel_display_power_is_enabled(dev_priv, pfit_domain)) { - if (INTEL_INFO(dev)->gen == 9) + if (INTEL_INFO(dev)->gen >= 9) skylake_get_pfit_config(crtc, pipe_config); - else if (INTEL_INFO(dev)->gen < 9) - ironlake_get_pfit_config(crtc, pipe_config); else - MISSING_CASE(INTEL_INFO(dev)->gen); + ironlake_get_pfit_config(crtc, pipe_config); } if (IS_HASWELL(dev)) @@ -9866,13 +9903,13 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base) /* On these chipsets we can only modify the base/size/stride * whilst the cursor is disabled. */ - I915_WRITE(_CURACNTR, 0); - POSTING_READ(_CURACNTR); + I915_WRITE(CURCNTR(PIPE_A), 0); + POSTING_READ(CURCNTR(PIPE_A)); intel_crtc->cursor_cntl = 0; } if (intel_crtc->cursor_base != base) { - I915_WRITE(_CURABASE, base); + I915_WRITE(CURBASE(PIPE_A), base); intel_crtc->cursor_base = base; } @@ -9882,8 +9919,8 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base) } if (intel_crtc->cursor_cntl != cntl) { - I915_WRITE(_CURACNTR, cntl); - POSTING_READ(_CURACNTR); + I915_WRITE(CURCNTR(PIPE_A), cntl); + POSTING_READ(CURCNTR(PIPE_A)); intel_crtc->cursor_cntl = cntl; } } @@ -9943,8 +9980,9 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - int x = crtc->cursor_x; - int y = crtc->cursor_y; + struct drm_plane_state *cursor_state = crtc->cursor->state; + int x = cursor_state->crtc_x; + int y = cursor_state->crtc_y; u32 base = 0, pos = 0; if (on) @@ -9957,7 +9995,7 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, base = 0; if (x < 0) { - if (x + intel_crtc->base.cursor->state->crtc_w <= 0) + if (x + cursor_state->crtc_w <= 0) base = 0; pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; @@ -9966,7 +10004,7 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, pos |= x << CURSOR_X_SHIFT; if (y < 0) { - if (y + intel_crtc->base.cursor->state->crtc_h <= 0) + if (y + cursor_state->crtc_h <= 0) base = 0; pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; @@ -9982,8 +10020,8 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, /* ILK+ do this automagically */ if (HAS_GMCH_DISPLAY(dev) && crtc->cursor->state->rotation == BIT(DRM_ROTATE_180)) { - base += (intel_crtc->base.cursor->state->crtc_h * - intel_crtc->base.cursor->state->crtc_w - 1) * 4; + base += (cursor_state->crtc_h * + cursor_state->crtc_w - 1) * 4; } if (IS_845G(dev) || IS_I865G(dev)) @@ -11034,10 +11072,10 @@ static int intel_gen7_queue_flip(struct drm_device *dev, DERRMR_PIPEB_PRI_FLIP_DONE | DERRMR_PIPEC_PRI_FLIP_DONE)); if (IS_GEN8(dev)) - intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8(1) | + intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT); else - intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) | + intel_ring_emit(ring, MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT); intel_ring_emit(ring, DERRMR); intel_ring_emit(ring, ring->scratch.gtt_offset + 256); @@ -11161,11 +11199,10 @@ static void ilk_do_mmio_flip(struct intel_crtc *intel_crtc) static void intel_do_mmio_flip(struct intel_crtc *intel_crtc) { struct drm_device *dev = intel_crtc->base.dev; - u32 start_vbl_count; intel_mark_page_flip_active(intel_crtc); - intel_pipe_update_start(intel_crtc, &start_vbl_count); + intel_pipe_update_start(intel_crtc); if (INTEL_INFO(dev)->gen >= 9) skl_do_mmio_flip(intel_crtc); @@ -11173,7 +11210,7 @@ static void intel_do_mmio_flip(struct intel_crtc *intel_crtc) /* use_mmio_flip() retricts MMIO flips to ilk+ */ ilk_do_mmio_flip(intel_crtc); - intel_pipe_update_end(intel_crtc, start_vbl_count); + intel_pipe_update_end(intel_crtc); } static void intel_mmio_flip_work_func(struct work_struct *work) @@ -11237,6 +11274,9 @@ static bool __intel_pageflip_stall_check(struct drm_device *dev, if (atomic_read(&work->pending) >= INTEL_FLIP_COMPLETE) return true; + if (atomic_read(&work->pending) < INTEL_FLIP_PENDING) + return false; + if (!work->enable_stall_check) return false; @@ -11417,8 +11457,9 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, if (ret) goto cleanup_pending; - work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary), obj) - + intel_crtc->dspaddr_offset; + work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary), + obj, 0); + work->gtt_offset += intel_crtc->dspaddr_offset; if (mmio_flip) { ret = intel_queue_mmio_flip(dev, crtc, fb, obj, ring, @@ -11536,18 +11577,32 @@ retry: static bool intel_wm_need_update(struct drm_plane *plane, struct drm_plane_state *state) { - /* Update watermarks on tiling changes. */ + struct intel_plane_state *new = to_intel_plane_state(state); + struct intel_plane_state *cur = to_intel_plane_state(plane->state); + + /* Update watermarks on tiling or size changes. */ if (!plane->state->fb || !state->fb || plane->state->fb->modifier[0] != state->fb->modifier[0] || - plane->state->rotation != state->rotation) - return true; - - if (plane->state->crtc_w != state->crtc_w) + plane->state->rotation != state->rotation || + drm_rect_width(&new->src) != drm_rect_width(&cur->src) || + drm_rect_height(&new->src) != drm_rect_height(&cur->src) || + drm_rect_width(&new->dst) != drm_rect_width(&cur->dst) || + drm_rect_height(&new->dst) != drm_rect_height(&cur->dst)) return true; return false; } +static bool needs_scaling(struct intel_plane_state *state) +{ + int src_w = drm_rect_width(&state->src) >> 16; + int src_h = drm_rect_height(&state->src) >> 16; + int dst_w = drm_rect_width(&state->dst); + int dst_h = drm_rect_height(&state->dst); + + return (src_w != dst_w || src_h != dst_h); +} + int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, struct drm_plane_state *plane_state) { @@ -11563,7 +11618,6 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, bool mode_changed = needs_modeset(crtc_state); bool was_crtc_enabled = crtc->state->active; bool is_crtc_enabled = crtc_state->active; - bool turn_off, turn_on, visible, was_visible; struct drm_framebuffer *fb = plane_state->fb; @@ -11627,7 +11681,7 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, intel_crtc->atomic.update_wm_pre = true; } - if (visible) + if (visible || was_visible) intel_crtc->atomic.fb_bits |= to_intel_plane(plane)->frontbuffer_bit; @@ -11681,11 +11735,23 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, case DRM_PLANE_TYPE_CURSOR: break; case DRM_PLANE_TYPE_OVERLAY: - if (turn_off && !mode_changed) { + /* + * WaCxSRDisabledForSpriteScaling:ivb + * + * cstate->update_wm was already set above, so this flag will + * take effect when we commit and program watermarks. + */ + if (IS_IVYBRIDGE(dev) && + needs_scaling(to_intel_plane_state(plane_state)) && + !needs_scaling(old_plane_state)) { + to_intel_crtc_state(crtc_state)->disable_lp_wm = true; + } else if (turn_off && !mode_changed) { intel_crtc->atomic.wait_vblank = true; intel_crtc->atomic.update_sprite_watermarks |= 1 << i; } + + break; } return 0; } @@ -11900,14 +11966,16 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc, pipe_config->fdi_m_n.gmch_m, pipe_config->fdi_m_n.gmch_n, pipe_config->fdi_m_n.link_m, pipe_config->fdi_m_n.link_n, pipe_config->fdi_m_n.tu); - DRM_DEBUG_KMS("dp: %i, gmch_m: %u, gmch_n: %u, link_m: %u, link_n: %u, tu: %u\n", + DRM_DEBUG_KMS("dp: %i, lanes: %i, gmch_m: %u, gmch_n: %u, link_m: %u, link_n: %u, tu: %u\n", pipe_config->has_dp_encoder, + pipe_config->lane_count, pipe_config->dp_m_n.gmch_m, pipe_config->dp_m_n.gmch_n, pipe_config->dp_m_n.link_m, pipe_config->dp_m_n.link_n, pipe_config->dp_m_n.tu); - DRM_DEBUG_KMS("dp: %i, gmch_m2: %u, gmch_n2: %u, link_m2: %u, link_n2: %u, tu2: %u\n", + DRM_DEBUG_KMS("dp: %i, lanes: %i, gmch_m2: %u, gmch_n2: %u, link_m2: %u, link_n2: %u, tu2: %u\n", pipe_config->has_dp_encoder, + pipe_config->lane_count, pipe_config->dp_m2_n2.gmch_m, pipe_config->dp_m2_n2.gmch_n, pipe_config->dp_m2_n2.link_m, @@ -12119,10 +12187,6 @@ intel_modeset_pipe_config(struct drm_crtc *crtc, (DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC))) pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_NVSYNC; - /* Compute a starting value for pipe_config->pipe_bpp taking the source - * plane pixel format and any sink constraints into account. Returns the - * source plane bpp so that dithering can be selected on mismatches - * after encoders and crtc also have had their say. */ base_bpp = compute_baseline_pipe_bpp(to_intel_crtc(crtc), pipe_config); if (base_bpp < 0) @@ -12191,7 +12255,7 @@ encoder_retry: /* Dithering seems to not pass-through bits correctly when it should, so * only enable it on 6bpc panels. */ pipe_config->dither = pipe_config->pipe_bpp == 6*3; - DRM_DEBUG_KMS("plane bpp: %i, pipe bpp: %i, dithering: %i\n", + DRM_DEBUG_KMS("hw max bpp: %i, pipe bpp: %i, dithering: %i\n", base_bpp, pipe_config->pipe_bpp, pipe_config->dither); fail: @@ -12241,7 +12305,6 @@ static bool intel_fuzzy_clock_check(int clock1, int clock2) base.head) \ if (mask & (1 <<(intel_crtc)->pipe)) - static bool intel_compare_m_n(unsigned int m, unsigned int n, unsigned int m2, unsigned int n2, @@ -12414,6 +12477,7 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_M_N(fdi_m_n); PIPE_CONF_CHECK_I(has_dp_encoder); + PIPE_CONF_CHECK_I(lane_count); if (INTEL_INFO(dev)->gen < 8) { PIPE_CONF_CHECK_M_N(dp_m_n); @@ -12461,22 +12525,24 @@ intel_pipe_config_compare(struct drm_device *dev, DRM_MODE_FLAG_NVSYNC); } - PIPE_CONF_CHECK_I(pipe_src_w); - PIPE_CONF_CHECK_I(pipe_src_h); - - PIPE_CONF_CHECK_I(gmch_pfit.control); + PIPE_CONF_CHECK_X(gmch_pfit.control); /* pfit ratios are autocomputed by the hw on gen4+ */ if (INTEL_INFO(dev)->gen < 4) PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios); - PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits); + PIPE_CONF_CHECK_X(gmch_pfit.lvds_border_bits); - PIPE_CONF_CHECK_I(pch_pfit.enabled); - if (current_config->pch_pfit.enabled) { - PIPE_CONF_CHECK_I(pch_pfit.pos); - PIPE_CONF_CHECK_I(pch_pfit.size); - } + if (!adjust) { + PIPE_CONF_CHECK_I(pipe_src_w); + PIPE_CONF_CHECK_I(pipe_src_h); - PIPE_CONF_CHECK_I(scaler_state.scaler_id); + PIPE_CONF_CHECK_I(pch_pfit.enabled); + if (current_config->pch_pfit.enabled) { + PIPE_CONF_CHECK_X(pch_pfit.pos); + PIPE_CONF_CHECK_X(pch_pfit.size); + } + + PIPE_CONF_CHECK_I(scaler_state.scaler_id); + } /* BDW+ don't expose a synchronous way to read the state */ if (IS_HASWELL(dev)) @@ -12549,8 +12615,8 @@ static void check_wm_state(struct drm_device *dev) } /* cursor */ - hw_entry = &hw_ddb.cursor[pipe]; - sw_entry = &sw_ddb->cursor[pipe]; + hw_entry = &hw_ddb.plane[pipe][PLANE_CURSOR]; + sw_entry = &sw_ddb->plane[pipe][PLANE_CURSOR]; if (skl_ddb_entry_equal(hw_entry, sw_entry)) continue; @@ -12638,7 +12704,8 @@ check_crtc_state(struct drm_device *dev, struct drm_atomic_state *old_state) struct intel_crtc_state *pipe_config, *sw_config; bool active; - if (!needs_modeset(crtc->state)) + if (!needs_modeset(crtc->state) && + !to_intel_crtc_state(crtc->state)->update_pipe) continue; __drm_atomic_helper_crtc_destroy_state(crtc, old_crtc_state); @@ -12792,11 +12859,11 @@ static void update_scanline_offset(struct intel_crtc *crtc) * one to the value. */ if (IS_GEN2(dev)) { - const struct drm_display_mode *mode = &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; int vtotal; - vtotal = mode->crtc_vtotal; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vtotal = adjusted_mode->crtc_vtotal; + if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) vtotal /= 2; crtc->scanline_offset = vtotal - 1; @@ -12934,7 +13001,6 @@ static int intel_modeset_all_pipes(struct drm_atomic_state *state) return ret; } - static int intel_modeset_checks(struct drm_atomic_state *state) { struct drm_device *dev = state->dev; @@ -13020,11 +13086,11 @@ static int intel_atomic_check(struct drm_device *dev, if (ret) return ret; - if (i915.fastboot && - intel_pipe_config_compare(state->dev, + if (intel_pipe_config_compare(state->dev, to_intel_crtc_state(crtc->state), pipe_config, true)) { crtc_state->mode_changed = false; + to_intel_crtc_state(crtc_state)->update_pipe = true; } if (needs_modeset(crtc_state)) { @@ -13122,16 +13188,30 @@ static int intel_atomic_commit(struct drm_device *dev, for_each_crtc_in_state(state, crtc, crtc_state, i) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); bool modeset = needs_modeset(crtc->state); + bool update_pipe = !modeset && + to_intel_crtc_state(crtc->state)->update_pipe; + unsigned long put_domains = 0; if (modeset && crtc->state->active) { update_scanline_offset(to_intel_crtc(crtc)); dev_priv->display.crtc_enable(crtc); } + if (update_pipe) { + put_domains = modeset_get_crtc_power_domains(crtc); + + /* make sure intel_modeset_check_state runs */ + any_ms = true; + } + if (!modeset) intel_pre_plane_update(intel_crtc); drm_atomic_helper_commit_planes_on_crtc(crtc_state); + + if (put_domains) + modeset_put_power_domains(dev_priv, put_domains); + intel_post_plane_update(intel_crtc); } @@ -13287,8 +13367,6 @@ static void intel_shared_dpll_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - intel_update_cdclk(dev); - if (HAS_DDI(dev)) intel_ddi_pll_init(dev); else if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev)) @@ -13447,11 +13525,9 @@ intel_commit_primary_plane(struct drm_plane *plane, if (!crtc->state->active) return; - if (state->visible) - /* FIXME: kill this fastboot hack */ - intel_update_pipe_size(intel_crtc); - - dev_priv->display.update_primary_plane(crtc, fb, crtc->x, crtc->y); + dev_priv->display.update_primary_plane(crtc, fb, + state->src.x1 >> 16, + state->src.y1 >> 16); } static void @@ -13469,15 +13545,23 @@ static void intel_begin_crtc_commit(struct drm_crtc *crtc, { struct drm_device *dev = crtc->dev; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc_state *old_intel_state = + to_intel_crtc_state(old_crtc_state); + bool modeset = needs_modeset(crtc->state); if (intel_crtc->atomic.update_wm_pre) intel_update_watermarks(crtc); /* Perform vblank evasion around commit operation */ if (crtc->state->active) - intel_pipe_update_start(intel_crtc, &intel_crtc->start_vbl_count); + intel_pipe_update_start(intel_crtc); + + if (modeset) + return; - if (!needs_modeset(crtc->state) && INTEL_INFO(dev)->gen >= 9) + if (to_intel_crtc_state(crtc->state)->update_pipe) + intel_update_pipe_config(intel_crtc, old_intel_state); + else if (INTEL_INFO(dev)->gen >= 9) skl_detach_scalers(intel_crtc); } @@ -13487,7 +13571,7 @@ static void intel_finish_crtc_commit(struct drm_crtc *crtc, struct intel_crtc *intel_crtc = to_intel_crtc(crtc); if (crtc->state->active) - intel_pipe_update_end(intel_crtc, intel_crtc->start_vbl_count); + intel_pipe_update_end(intel_crtc); } /** @@ -13656,10 +13740,6 @@ intel_commit_cursor_plane(struct drm_plane *plane, crtc = crtc ? crtc : plane->crtc; intel_crtc = to_intel_crtc(crtc); - plane->fb = state->base.fb; - crtc->cursor_x = state->base.crtc_x; - crtc->cursor_y = state->base.crtc_y; - if (intel_crtc->cursor_bo == obj) goto update; @@ -13945,7 +14025,7 @@ static void intel_setup_outputs(struct drm_device *dev) * On SKL pre-D0 the strap isn't connected, so we assume * it's there. */ - found = I915_READ(DDI_BUF_CTL_A) & DDI_INIT_DISPLAY_DETECTED; + found = I915_READ(DDI_BUF_CTL(PORT_A)) & DDI_INIT_DISPLAY_DETECTED; /* WaIgnoreDDIAStrap: skl */ if (found || IS_SKYLAKE(dev)) intel_ddi_init(dev, PORT_A); @@ -14006,29 +14086,26 @@ static void intel_setup_outputs(struct drm_device *dev) * eDP ports. Consult the VBT as well as DP_DETECTED to * detect eDP ports. */ - if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIB) & SDVO_DETECTED && + if (I915_READ(VLV_HDMIB) & SDVO_DETECTED && !intel_dp_is_edp(dev, PORT_B)) - intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIB, - PORT_B); - if (I915_READ(VLV_DISPLAY_BASE + DP_B) & DP_DETECTED || + intel_hdmi_init(dev, VLV_HDMIB, PORT_B); + if (I915_READ(VLV_DP_B) & DP_DETECTED || intel_dp_is_edp(dev, PORT_B)) - intel_dp_init(dev, VLV_DISPLAY_BASE + DP_B, PORT_B); + intel_dp_init(dev, VLV_DP_B, PORT_B); - if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIC) & SDVO_DETECTED && + if (I915_READ(VLV_HDMIC) & SDVO_DETECTED && !intel_dp_is_edp(dev, PORT_C)) - intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIC, - PORT_C); - if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED || + intel_hdmi_init(dev, VLV_HDMIC, PORT_C); + if (I915_READ(VLV_DP_C) & DP_DETECTED || intel_dp_is_edp(dev, PORT_C)) - intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C); + intel_dp_init(dev, VLV_DP_C, PORT_C); if (IS_CHERRYVIEW(dev)) { - if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED) - intel_hdmi_init(dev, VLV_DISPLAY_BASE + CHV_HDMID, - PORT_D); /* eDP not supported on port D, so don't check VBT */ - if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED) - intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D); + if (I915_READ(CHV_HDMID) & SDVO_DETECTED) + intel_hdmi_init(dev, CHV_HDMID, PORT_D); + if (I915_READ(CHV_DP_D) & DP_DETECTED) + intel_dp_init(dev, CHV_DP_D, PORT_D); } intel_dsi_init(dev); @@ -14519,8 +14596,6 @@ static void intel_init_display(struct drm_device *dev) dev_priv->display.queue_flip = intel_default_queue_flip; } - intel_panel_init_backlight_funcs(dev); - mutex_init(&dev_priv->pps_mutex); } @@ -14798,7 +14873,8 @@ void intel_modeset_init(struct drm_device *dev) } } - intel_init_dpio(dev); + intel_update_czclk(dev_priv); + intel_update_cdclk(dev); intel_shared_dpll_init(dev); @@ -14881,13 +14957,22 @@ intel_check_plane_mapping(struct intel_crtc *crtc) return true; } +static bool intel_crtc_has_encoders(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct intel_encoder *encoder; + + for_each_encoder_on_crtc(dev, &crtc->base, encoder) + return true; + + return false; +} + static void intel_sanitize_crtc(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *encoder; u32 reg; - bool enable; /* Clear any frame start delays used for debugging left by the BIOS */ reg = PIPECONF(crtc->config->cpu_transcoder); @@ -14896,9 +14981,17 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) /* restore vblank interrupts to correct state */ drm_crtc_vblank_reset(&crtc->base); if (crtc->active) { - drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode); - update_scanline_offset(crtc); + struct intel_plane *plane; + drm_crtc_vblank_on(&crtc->base); + + /* Disable everything but the primary plane */ + for_each_intel_plane_on_crtc(dev, crtc, plane) { + if (plane->base.type == DRM_PLANE_TYPE_PRIMARY) + continue; + + plane->disable_plane(&plane->base, &crtc->base); + } } /* We need to sanitize the plane -> pipe mapping first because this will @@ -14931,16 +15024,11 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) /* Adjust the state of the output pipe according to whether we * have active connectors/encoders. */ - enable = false; - for_each_encoder_on_crtc(dev, &crtc->base, encoder) { - enable = true; - break; - } - - if (!enable) + if (!intel_crtc_has_encoders(crtc)) intel_crtc_disable_noatomic(&crtc->base); if (crtc->active != crtc->base.state->active) { + struct intel_encoder *encoder; /* This can happen either due to bugs in the get_hw_state * functions or because of calls to intel_crtc_disable_noatomic, @@ -15066,38 +15154,25 @@ void i915_redisable_vga(struct drm_device *dev) i915_redisable_vga_power_on(dev); } -static bool primary_get_hw_state(struct intel_crtc *crtc) +static bool primary_get_hw_state(struct intel_plane *plane) { - struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - return !!(I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE); + return I915_READ(DSPCNTR(plane->plane)) & DISPLAY_PLANE_ENABLE; } -static void readout_plane_state(struct intel_crtc *crtc, - struct intel_crtc_state *crtc_state) +/* FIXME read out full plane state for all planes */ +static void readout_plane_state(struct intel_crtc *crtc) { - struct intel_plane *p; - struct intel_plane_state *plane_state; - bool active = crtc_state->base.active; - - for_each_intel_plane(crtc->base.dev, p) { - if (crtc->pipe != p->pipe) - continue; - - plane_state = to_intel_plane_state(p->base.state); + struct drm_plane *primary = crtc->base.primary; + struct intel_plane_state *plane_state = + to_intel_plane_state(primary->state); - if (p->base.type == DRM_PLANE_TYPE_PRIMARY) { - plane_state->visible = primary_get_hw_state(crtc); - if (plane_state->visible) - crtc->base.state->plane_mask |= - 1 << drm_plane_index(&p->base); - } else { - if (active) - p->disable_plane(&p->base, &crtc->base); + plane_state->visible = + primary_get_hw_state(to_intel_plane(primary)); - plane_state->visible = false; - } - } + if (plane_state->visible) + crtc->base.state->plane_mask |= 1 << drm_plane_index(primary); } static void intel_modeset_readout_hw_state(struct drm_device *dev) @@ -15120,34 +15195,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) crtc->base.state->active = crtc->active; crtc->base.enabled = crtc->active; - memset(&crtc->base.mode, 0, sizeof(crtc->base.mode)); - if (crtc->base.state->active) { - intel_mode_from_pipe_config(&crtc->base.mode, crtc->config); - intel_mode_from_pipe_config(&crtc->base.state->adjusted_mode, crtc->config); - WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode)); - - /* - * The initial mode needs to be set in order to keep - * the atomic core happy. It wants a valid mode if the - * crtc's enabled, so we do the above call. - * - * At this point some state updated by the connectors - * in their ->detect() callback has not run yet, so - * no recalculation can be done yet. - * - * Even if we could do a recalculation and modeset - * right now it would cause a double modeset if - * fbdev or userspace chooses a different initial mode. - * - * If that happens, someone indicated they wanted a - * mode change, which means it's safe to do a full - * recalculation. - */ - crtc->base.state->mode.private_flags = I915_MODE_FLAG_INHERITED; - } - - crtc->base.hwmode = crtc->config->base.adjusted_mode; - readout_plane_state(crtc, to_intel_crtc_state(crtc->base.state)); + readout_plane_state(crtc); DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n", crtc->base.base.id, @@ -15206,6 +15254,39 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) connector->base.name, connector->base.encoder ? "enabled" : "disabled"); } + + for_each_intel_crtc(dev, crtc) { + crtc->base.hwmode = crtc->config->base.adjusted_mode; + + memset(&crtc->base.mode, 0, sizeof(crtc->base.mode)); + if (crtc->base.state->active) { + intel_mode_from_pipe_config(&crtc->base.mode, crtc->config); + intel_mode_from_pipe_config(&crtc->base.state->adjusted_mode, crtc->config); + WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode)); + + /* + * The initial mode needs to be set in order to keep + * the atomic core happy. It wants a valid mode if the + * crtc's enabled, so we do the above call. + * + * At this point some state updated by the connectors + * in their ->detect() callback has not run yet, so + * no recalculation can be done yet. + * + * Even if we could do a recalculation and modeset + * right now it would cause a double modeset if + * fbdev or userspace chooses a different initial mode. + * + * If that happens, someone indicated they wanted a + * mode change, which means it's safe to do a full + * recalculation. + */ + crtc->base.state->mode.private_flags = I915_MODE_FLAG_INHERITED; + + drm_calc_timestamping_constants(&crtc->base, &crtc->base.hwmode); + update_scanline_offset(crtc); + } + } } /* Scan out the current hw modeset state, diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 7bb96d5..18bcfbe 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -130,6 +130,11 @@ static void vlv_init_panel_power_sequencer(struct intel_dp *intel_dp); static void vlv_steal_power_sequencer(struct drm_device *dev, enum pipe pipe); +static unsigned int intel_dp_unused_lane_mask(int lane_count) +{ + return ~((1 << lane_count) - 1) & 0xf; +} + static int intel_dp_max_link_bw(struct intel_dp *intel_dp) { @@ -253,40 +258,6 @@ static void intel_dp_unpack_aux(uint32_t src, uint8_t *dst, int dst_bytes) dst[i] = src >> ((3-i) * 8); } -/* hrawclock is 1/4 the FSB frequency */ -static int -intel_hrawclk(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t clkcfg; - - /* There is no CLKCFG reg in Valleyview. VLV hrawclk is 200 MHz */ - if (IS_VALLEYVIEW(dev)) - return 200; - - clkcfg = I915_READ(CLKCFG); - switch (clkcfg & CLKCFG_FSB_MASK) { - case CLKCFG_FSB_400: - return 100; - case CLKCFG_FSB_533: - return 133; - case CLKCFG_FSB_667: - return 166; - case CLKCFG_FSB_800: - return 200; - case CLKCFG_FSB_1067: - return 266; - case CLKCFG_FSB_1333: - return 333; - /* these two are just a guess; one of them might be right */ - case CLKCFG_FSB_1600: - case CLKCFG_FSB_1600_ALT: - return 400; - default: - return 133; - } -} - static void intel_dp_init_panel_power_sequencer(struct drm_device *dev, struct intel_dp *intel_dp); @@ -333,7 +304,9 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp) struct drm_device *dev = intel_dig_port->base.base.dev; struct drm_i915_private *dev_priv = dev->dev_private; enum pipe pipe = intel_dp->pps_pipe; - bool pll_enabled; + bool pll_enabled, release_cl_override = false; + enum dpio_phy phy = DPIO_PHY(pipe); + enum dpio_channel ch = vlv_pipe_to_channel(pipe); uint32_t DP; if (WARN(I915_READ(intel_dp->output_reg) & DP_PORT_EN, @@ -363,9 +336,13 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp) * The DPLL for the pipe must be enabled for this to work. * So enable temporarily it if it's not already enabled. */ - if (!pll_enabled) + if (!pll_enabled) { + release_cl_override = IS_CHERRYVIEW(dev) && + !chv_phy_powergate_ch(dev_priv, phy, ch, true); + vlv_force_pll_on(dev, pipe, IS_CHERRYVIEW(dev) ? &chv_dpll[0].dpll : &vlv_dpll[0].dpll); + } /* * Similar magic as in intel_dp_enable_port(). @@ -382,8 +359,12 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp) I915_WRITE(intel_dp->output_reg, DP & ~DP_PORT_EN); POSTING_READ(intel_dp->output_reg); - if (!pll_enabled) + if (!pll_enabled) { vlv_force_pll_off(dev, pipe); + + if (release_cl_override) + chv_phy_powergate_ch(dev_priv, phy, ch, false); + } } static enum pipe @@ -1384,6 +1365,19 @@ int intel_dp_rate_select(struct intel_dp *intel_dp, int rate) return rate_to_index(rate, intel_dp->sink_rates); } +static void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock, + uint8_t *link_bw, uint8_t *rate_select) +{ + if (intel_dp->num_sink_rates) { + *link_bw = 0; + *rate_select = + intel_dp_rate_select(intel_dp, port_clock); + } else { + *link_bw = drm_dp_link_rate_to_bw_code(port_clock); + *rate_select = 0; + } +} + bool intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) @@ -1405,6 +1399,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, int link_avail, link_clock; int common_rates[DP_MAX_SUPPORTED_RATES] = {}; int common_len; + uint8_t link_bw, rate_select; common_len = intel_dp_common_rates(intel_dp, common_rates); @@ -1500,32 +1495,23 @@ found: * CEA-861-E - 5.1 Default Encoding Parameters * VESA DisplayPort Ver.1.2a - 5.1.1.1 Video Colorimetry */ - if (bpp != 18 && drm_match_cea_mode(adjusted_mode) > 1) - intel_dp->color_range = DP_COLOR_RANGE_16_235; - else - intel_dp->color_range = 0; - } - - if (intel_dp->color_range) - pipe_config->limited_color_range = true; - - intel_dp->lane_count = lane_count; - - if (intel_dp->num_sink_rates) { - intel_dp->link_bw = 0; - intel_dp->rate_select = - intel_dp_rate_select(intel_dp, common_rates[clock]); + pipe_config->limited_color_range = + bpp != 18 && drm_match_cea_mode(adjusted_mode) > 1; } else { - intel_dp->link_bw = - drm_dp_link_rate_to_bw_code(common_rates[clock]); - intel_dp->rate_select = 0; + pipe_config->limited_color_range = + intel_dp->limited_color_range; } + pipe_config->lane_count = lane_count; + pipe_config->pipe_bpp = bpp; pipe_config->port_clock = common_rates[clock]; - DRM_DEBUG_KMS("DP link bw %02x lane count %d clock %d bpp %d\n", - intel_dp->link_bw, intel_dp->lane_count, + intel_dp_compute_rate(intel_dp, pipe_config->port_clock, + &link_bw, &rate_select); + + DRM_DEBUG_KMS("DP link bw %02x rate select %02x lane count %d clock %d bpp %d\n", + link_bw, rate_select, pipe_config->lane_count, pipe_config->port_clock, bpp); DRM_DEBUG_KMS("DP link bw required %i available %i\n", mode_rate, link_avail); @@ -1587,6 +1573,13 @@ static void ironlake_set_pll_cpu_edp(struct intel_dp *intel_dp) udelay(500); } +void intel_dp_set_link_params(struct intel_dp *intel_dp, + const struct intel_crtc_state *pipe_config) +{ + intel_dp->link_rate = pipe_config->port_clock; + intel_dp->lane_count = pipe_config->lane_count; +} + static void intel_dp_prepare(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; @@ -1594,7 +1587,9 @@ static void intel_dp_prepare(struct intel_encoder *encoder) struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); enum port port = dp_to_dig_port(intel_dp)->port; struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; + + intel_dp_set_link_params(intel_dp, crtc->config); /* * There are four kinds of DP registers: @@ -1620,7 +1615,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder) /* Handle DP bits in common between all three register formats */ intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0; - intel_dp->DP |= DP_PORT_WIDTH(intel_dp->lane_count); + intel_dp->DP |= DP_PORT_WIDTH(crtc->config->lane_count); if (crtc->config->has_audio) intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE; @@ -1650,8 +1645,9 @@ static void intel_dp_prepare(struct intel_encoder *encoder) trans_dp &= ~TRANS_DP_ENH_FRAMING; I915_WRITE(TRANS_DP_CTL(crtc->pipe), trans_dp); } else { - if (!HAS_PCH_SPLIT(dev) && !IS_VALLEYVIEW(dev)) - intel_dp->DP |= intel_dp->color_range; + if (!HAS_PCH_SPLIT(dev) && !IS_VALLEYVIEW(dev) && + crtc->config->limited_color_range) + intel_dp->DP |= DP_COLOR_RANGE_16_235; if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) intel_dp->DP |= DP_SYNC_HS_HIGH; @@ -2291,13 +2287,14 @@ static void intel_dp_get_config(struct intel_encoder *encoder, pipe_config->has_audio = tmp & DP_AUDIO_OUTPUT_ENABLE && port != PORT_A; if (HAS_PCH_CPT(dev) && port != PORT_A) { - tmp = I915_READ(TRANS_DP_CTL(crtc->pipe)); - if (tmp & TRANS_DP_HSYNC_ACTIVE_HIGH) + u32 trans_dp = I915_READ(TRANS_DP_CTL(crtc->pipe)); + + if (trans_dp & TRANS_DP_HSYNC_ACTIVE_HIGH) flags |= DRM_MODE_FLAG_PHSYNC; else flags |= DRM_MODE_FLAG_NHSYNC; - if (tmp & TRANS_DP_VSYNC_ACTIVE_HIGH) + if (trans_dp & TRANS_DP_VSYNC_ACTIVE_HIGH) flags |= DRM_MODE_FLAG_PVSYNC; else flags |= DRM_MODE_FLAG_NVSYNC; @@ -2321,6 +2318,9 @@ static void intel_dp_get_config(struct intel_encoder *encoder, pipe_config->has_dp_encoder = true; + pipe_config->lane_count = + ((tmp & DP_PORT_WIDTH_MASK) >> DP_PORT_WIDTH_SHIFT) + 1; + intel_dp_get_m_n(crtc, pipe_config); if (port == PORT_A) { @@ -2400,38 +2400,62 @@ static void vlv_post_disable_dp(struct intel_encoder *encoder) intel_dp_link_down(intel_dp); } -static void chv_post_disable_dp(struct intel_encoder *encoder) +static void chv_data_lane_soft_reset(struct intel_encoder *encoder, + bool reset) { - struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); - struct intel_digital_port *dport = dp_to_dig_port(intel_dp); - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = - to_intel_crtc(encoder->base.crtc); - enum dpio_channel ch = vlv_dport_to_channel(dport); - enum pipe pipe = intel_crtc->pipe; - u32 val; + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base)); + struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); + enum pipe pipe = crtc->pipe; + uint32_t val; - intel_dp_link_down(intel_dp); + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + if (reset) + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + else + val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); - mutex_lock(&dev_priv->sb_lock); + if (crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + if (reset) + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + else + val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + } - /* Propagate soft reset to data lane reset */ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); val |= CHV_PCS_REQ_SOFTRESET_EN; + if (reset) + val &= ~DPIO_PCS_CLK_SOFT_RESET; + else + val |= DPIO_PCS_CLK_SOFT_RESET; vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); - val |= CHV_PCS_REQ_SOFTRESET_EN; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + if (crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + if (reset) + val &= ~DPIO_PCS_CLK_SOFT_RESET; + else + val |= DPIO_PCS_CLK_SOFT_RESET; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + } +} - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); - val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); +static void chv_post_disable_dp(struct intel_encoder *encoder) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + intel_dp_link_down(intel_dp); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); - val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + mutex_lock(&dev_priv->sb_lock); + + /* Assert data lane reset */ + chv_data_lane_soft_reset(encoder, true); mutex_unlock(&dev_priv->sb_lock); } @@ -2551,7 +2575,6 @@ static void intel_enable_dp(struct intel_encoder *encoder) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); uint32_t dp_reg = I915_READ(intel_dp->output_reg); - unsigned int lane_mask = 0x0; if (WARN_ON(dp_reg & DP_PORT_EN)) return; @@ -2569,13 +2592,18 @@ static void intel_enable_dp(struct intel_encoder *encoder) pps_unlock(intel_dp); - if (IS_VALLEYVIEW(dev)) + if (IS_VALLEYVIEW(dev)) { + unsigned int lane_mask = 0x0; + + if (IS_CHERRYVIEW(dev)) + lane_mask = intel_dp_unused_lane_mask(crtc->config->lane_count); + vlv_wait_port_ready(dev_priv, dp_to_dig_port(intel_dp), lane_mask); + } intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); intel_dp_start_link_train(intel_dp); - intel_dp_complete_link_train(intel_dp); intel_dp_stop_link_train(intel_dp); if (crtc->config->has_audio) { @@ -2798,31 +2826,19 @@ static void chv_pre_enable_dp(struct intel_encoder *encoder) val &= ~DPIO_LANEDESKEW_STRAP_OVRD; vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch)); - val &= ~DPIO_LANEDESKEW_STRAP_OVRD; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val); - - /* Deassert soft data lane reset*/ - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); - val |= CHV_PCS_REQ_SOFTRESET_EN; - vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); - val |= CHV_PCS_REQ_SOFTRESET_EN; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); - val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); - val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + if (intel_crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch)); + val &= ~DPIO_LANEDESKEW_STRAP_OVRD; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val); + } /* Program Tx lane latency optimal setting*/ - for (i = 0; i < 4; i++) { + for (i = 0; i < intel_crtc->config->lane_count; i++) { /* Set the upar bit */ - data = (i == 1) ? 0x0 : 0x1; + if (intel_crtc->config->lane_count == 1) + data = 0x0; + else + data = (i == 1) ? 0x0 : 0x1; vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i), data << DPIO_UPAR_SHIFT); } @@ -2843,9 +2859,11 @@ static void chv_pre_enable_dp(struct intel_encoder *encoder) val |= DPIO_TX2_STAGGER_MASK(0x1f); vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch)); - val |= DPIO_TX2_STAGGER_MASK(0x1f); - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val); + if (intel_crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch)); + val |= DPIO_TX2_STAGGER_MASK(0x1f); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val); + } vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW12(ch), DPIO_LANESTAGGER_STRAP(stagger) | @@ -2854,16 +2872,27 @@ static void chv_pre_enable_dp(struct intel_encoder *encoder) DPIO_TX1_STAGGER_MULT(6) | DPIO_TX2_STAGGER_MULT(0)); - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW12(ch), - DPIO_LANESTAGGER_STRAP(stagger) | - DPIO_LANESTAGGER_STRAP_OVRD | - DPIO_TX1_STAGGER_MASK(0x1f) | - DPIO_TX1_STAGGER_MULT(7) | - DPIO_TX2_STAGGER_MULT(5)); + if (intel_crtc->config->lane_count > 2) { + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW12(ch), + DPIO_LANESTAGGER_STRAP(stagger) | + DPIO_LANESTAGGER_STRAP_OVRD | + DPIO_TX1_STAGGER_MASK(0x1f) | + DPIO_TX1_STAGGER_MULT(7) | + DPIO_TX2_STAGGER_MULT(5)); + } + + /* Deassert data lane reset */ + chv_data_lane_soft_reset(encoder, false); mutex_unlock(&dev_priv->sb_lock); intel_enable_dp(encoder); + + /* Second common lane will stay alive on its own now */ + if (dport->release_cl2_override) { + chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, false); + dport->release_cl2_override = false; + } } static void chv_dp_pre_pll_enable(struct intel_encoder *encoder) @@ -2875,12 +2904,27 @@ static void chv_dp_pre_pll_enable(struct intel_encoder *encoder) to_intel_crtc(encoder->base.crtc); enum dpio_channel ch = vlv_dport_to_channel(dport); enum pipe pipe = intel_crtc->pipe; + unsigned int lane_mask = + intel_dp_unused_lane_mask(intel_crtc->config->lane_count); u32 val; intel_dp_prepare(encoder); + /* + * Must trick the second common lane into life. + * Otherwise we can't even access the PLL. + */ + if (ch == DPIO_CH0 && pipe == PIPE_B) + dport->release_cl2_override = + !chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, true); + + chv_phy_powergate_lanes(encoder, true, lane_mask); + mutex_lock(&dev_priv->sb_lock); + /* Assert data lane reset */ + chv_data_lane_soft_reset(encoder, true); + /* program left/right clock distribution */ if (pipe != PIPE_B) { val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0); @@ -2909,13 +2953,15 @@ static void chv_dp_pre_pll_enable(struct intel_encoder *encoder) val |= CHV_PCS_USEDCLKCHANNEL; vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch)); - val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE; - if (pipe != PIPE_B) - val &= ~CHV_PCS_USEDCLKCHANNEL; - else - val |= CHV_PCS_USEDCLKCHANNEL; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val); + if (intel_crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch)); + val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE; + if (pipe != PIPE_B) + val &= ~CHV_PCS_USEDCLKCHANNEL; + else + val |= CHV_PCS_USEDCLKCHANNEL; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val); + } /* * This a a bit weird since generally CL @@ -2932,6 +2978,39 @@ static void chv_dp_pre_pll_enable(struct intel_encoder *encoder) mutex_unlock(&dev_priv->sb_lock); } +static void chv_dp_post_pll_disable(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum pipe pipe = to_intel_crtc(encoder->base.crtc)->pipe; + u32 val; + + mutex_lock(&dev_priv->sb_lock); + + /* disable left/right clock distribution */ + if (pipe != PIPE_B) { + val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0); + val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK); + vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val); + } else { + val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1); + val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK); + vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val); + } + + mutex_unlock(&dev_priv->sb_lock); + + /* + * Leave the power down bit cleared for at least one + * lane so that chv_powergate_phy_ch() will power + * on something when the channel is otherwise unused. + * When the port is off and the override is removed + * the lanes power down anyway, so otherwise it doesn't + * really matter what the state of power down bits is + * after this. + */ + chv_phy_powergate_lanes(encoder, false, 0x0); +} + /* * Native read with retry for link status and receiver capability reads for * cases where the sink may still be asleep. @@ -3168,6 +3247,12 @@ static uint32_t vlv_signal_levels(struct intel_dp *intel_dp) return 0; } +static bool chv_need_uniq_trans_scale(uint8_t train_set) +{ + return (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) == DP_TRAIN_PRE_EMPH_LEVEL_0 && + (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) == DP_TRAIN_VOLTAGE_SWING_LEVEL_3; +} + static uint32_t chv_signal_levels(struct intel_dp *intel_dp) { struct drm_device *dev = intel_dp_to_dev(intel_dp); @@ -3259,24 +3344,28 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp) val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5; vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); - val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); - val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK); - val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + if (intel_crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK); + val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + } val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW9(ch)); val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK); val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000; vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW9(ch), val); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW9(ch)); - val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK); - val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW9(ch), val); + if (intel_crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW9(ch)); + val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK); + val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW9(ch), val); + } /* Program swing deemph */ - for (i = 0; i < 4; i++) { + for (i = 0; i < intel_crtc->config->lane_count; i++) { val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i)); val &= ~DPIO_SWING_DEEMPH9P5_MASK; val |= deemph_reg_value << DPIO_SWING_DEEMPH9P5_SHIFT; @@ -3284,43 +3373,36 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp) } /* Program swing margin */ - for (i = 0; i < 4; i++) { + for (i = 0; i < intel_crtc->config->lane_count; i++) { val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~DPIO_SWING_MARGIN000_MASK; val |= margin_reg_value << DPIO_SWING_MARGIN000_SHIFT; + + /* + * Supposedly this value shouldn't matter when unique transition + * scale is disabled, but in fact it does matter. Let's just + * always program the same value and hope it's OK. + */ + val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT); + val |= 0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); } - /* Disable unique transition scale */ - for (i = 0; i < 4; i++) { + /* + * The document said it needs to set bit 27 for ch0 and bit 26 + * for ch1. Might be a typo in the doc. + * For now, for this unique transition scale selection, set bit + * 27 for ch0 and ch1. + */ + for (i = 0; i < intel_crtc->config->lane_count; i++) { val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); - val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN; - vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); - } - - if (((train_set & DP_TRAIN_PRE_EMPHASIS_MASK) - == DP_TRAIN_PRE_EMPH_LEVEL_0) && - ((train_set & DP_TRAIN_VOLTAGE_SWING_MASK) - == DP_TRAIN_VOLTAGE_SWING_LEVEL_3)) { - - /* - * The document said it needs to set bit 27 for ch0 and bit 26 - * for ch1. Might be a typo in the doc. - * For now, for this unique transition scale selection, set bit - * 27 for ch0 and ch1. - */ - for (i = 0; i < 4; i++) { - val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); + if (chv_need_uniq_trans_scale(train_set)) val |= DPIO_TX_UNIQ_TRANS_SCALE_EN; - vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); - } - - for (i = 0; i < 4; i++) { - val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); - val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT); - val |= (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT); - vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); - } + else + val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); } /* Start swing calculation */ @@ -3328,14 +3410,11 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp) val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); - val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); - - /* LRC Bypass */ - val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30); - val |= DPIO_LRC_BYPASS; - vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val); + if (intel_crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + } mutex_unlock(&dev_priv->sb_lock); @@ -3521,8 +3600,8 @@ intel_dp_set_link_train(struct intel_dp *intel_dp, uint8_t dp_train_pat) { struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = intel_dig_port->base.base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = + to_i915(intel_dig_port->base.base.dev); uint8_t buf[sizeof(intel_dp->train_set) + 1]; int ret, len; @@ -3563,8 +3642,8 @@ intel_dp_update_link_train(struct intel_dp *intel_dp, uint32_t *DP, const uint8_t link_status[DP_LINK_STATUS_SIZE]) { struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = intel_dig_port->base.base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = + to_i915(intel_dig_port->base.base.dev); int ret; intel_get_adjust_train(intel_dp, link_status); @@ -3611,8 +3690,8 @@ static void intel_dp_set_idle_link_train(struct intel_dp *intel_dp) } /* Enable corresponding port and start training pattern 1 */ -void -intel_dp_start_link_train(struct intel_dp *intel_dp) +static void +intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp) { struct drm_encoder *encoder = &dp_to_dig_port(intel_dp)->base.base; struct drm_device *dev = encoder->dev; @@ -3621,19 +3700,23 @@ intel_dp_start_link_train(struct intel_dp *intel_dp) int voltage_tries, loop_tries; uint32_t DP = intel_dp->DP; uint8_t link_config[2]; + uint8_t link_bw, rate_select; if (HAS_DDI(dev)) intel_ddi_prepare_link_retrain(encoder); + intel_dp_compute_rate(intel_dp, intel_dp->link_rate, + &link_bw, &rate_select); + /* Write the link configuration data */ - link_config[0] = intel_dp->link_bw; + link_config[0] = link_bw; link_config[1] = intel_dp->lane_count; if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2); if (intel_dp->num_sink_rates) drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET, - &intel_dp->rate_select, 1); + &rate_select, 1); link_config[0] = 0; link_config[1] = DP_SET_ANSI_8B10B; @@ -3721,17 +3804,30 @@ intel_dp_start_link_train(struct intel_dp *intel_dp) intel_dp->DP = DP; } -void -intel_dp_complete_link_train(struct intel_dp *intel_dp) +static void +intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) { + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_device *dev = dig_port->base.base.dev; bool channel_eq = false; int tries, cr_tries; uint32_t DP = intel_dp->DP; uint32_t training_pattern = DP_TRAINING_PATTERN_2; - /* Training Pattern 3 for HBR2 ot 1.2 devices that support it*/ - if (intel_dp->link_bw == DP_LINK_BW_5_4 || intel_dp->use_tps3) + /* + * Training Pattern 3 for HBR2 or 1.2 devices that support it. + * + * Intel platforms that support HBR2 also support TPS3. TPS3 support is + * also mandatory for downstream devices that support HBR2. + * + * Due to WaDisableHBR2 SKL < B0 is the only exception where TPS3 is + * supported but still not enabled. + */ + if (intel_dp_source_supports_hbr2(dev) && + drm_dp_tps3_supported(intel_dp->dpcd)) training_pattern = DP_TRAINING_PATTERN_3; + else if (intel_dp->link_rate == 540000) + DRM_ERROR("5.4 Gbps link rate without HBR2/TPS3 support\n"); /* channel equalization */ if (!intel_dp_set_link_train(intel_dp, &DP, @@ -3759,9 +3855,10 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp) } /* Make sure clock is still ok */ - if (!drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) { + if (!drm_dp_clock_recovery_ok(link_status, + intel_dp->lane_count)) { intel_dp->train_set_valid = false; - intel_dp_start_link_train(intel_dp); + intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, &DP, training_pattern | DP_LINK_SCRAMBLING_DISABLE); @@ -3769,7 +3866,8 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp) continue; } - if (drm_dp_channel_eq_ok(link_status, intel_dp->lane_count)) { + if (drm_dp_channel_eq_ok(link_status, + intel_dp->lane_count)) { channel_eq = true; break; } @@ -3777,7 +3875,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp) /* Try 5 times, then try clock recovery if that fails */ if (tries > 5) { intel_dp->train_set_valid = false; - intel_dp_start_link_train(intel_dp); + intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, &DP, training_pattern | DP_LINK_SCRAMBLING_DISABLE); @@ -3810,6 +3908,13 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp) DP_TRAINING_PATTERN_DISABLE); } +void +intel_dp_start_link_train(struct intel_dp *intel_dp) +{ + intel_dp_link_training_clock_recovery(intel_dp); + intel_dp_link_training_channel_equalization(intel_dp); +} + static void intel_dp_link_down(struct intel_dp *intel_dp) { @@ -3910,19 +4015,9 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) } } - /* Training Pattern 3 support, Intel platforms that support HBR2 alone - * have support for TP3 hence that check is used along with dpcd check - * to ensure TP3 can be enabled. - * SKL < B0: due it's WaDisableHBR2 is the only exception where TP3 is - * supported but still not enabled. - */ - if (intel_dp->dpcd[DP_DPCD_REV] >= 0x12 && - intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED && - intel_dp_source_supports_hbr2(dev)) { - intel_dp->use_tps3 = true; - DRM_DEBUG_KMS("Displayport TPS3 supported\n"); - } else - intel_dp->use_tps3 = false; + DRM_DEBUG_KMS("Display Port TPS3 support: source %s, sink %s\n", + yesno(intel_dp_source_supports_hbr2(dev)), + yesno(drm_dp_tps3_supported(intel_dp->dpcd))); /* Intermediate frequency support */ if (is_edp(intel_dp) && @@ -4008,22 +4103,30 @@ intel_dp_probe_mst(struct intel_dp *intel_dp) return intel_dp->is_mst; } -static void intel_dp_sink_crc_stop(struct intel_dp *intel_dp) +static int intel_dp_sink_crc_stop(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct intel_crtc *intel_crtc = to_intel_crtc(dig_port->base.base.crtc); u8 buf; + int ret = 0; if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) { DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n"); - return; + ret = -EIO; + goto out; } if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK, - buf & ~DP_TEST_SINK_START) < 0) + buf & ~DP_TEST_SINK_START) < 0) { DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n"); + ret = -EIO; + goto out; + } + intel_dp->sink_crc.started = false; + out: hsw_enable_ips(intel_crtc); + return ret; } static int intel_dp_sink_crc_start(struct intel_dp *intel_dp) @@ -4031,6 +4134,13 @@ static int intel_dp_sink_crc_start(struct intel_dp *intel_dp) struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct intel_crtc *intel_crtc = to_intel_crtc(dig_port->base.base.crtc); u8 buf; + int ret; + + if (intel_dp->sink_crc.started) { + ret = intel_dp_sink_crc_stop(intel_dp); + if (ret) + return ret; + } if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0) return -EIO; @@ -4038,6 +4148,8 @@ static int intel_dp_sink_crc_start(struct intel_dp *intel_dp) if (!(buf & DP_TEST_CRC_SUPPORTED)) return -ENOTTY; + intel_dp->sink_crc.last_count = buf & DP_TEST_COUNT_MASK; + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) return -EIO; @@ -4049,6 +4161,7 @@ static int intel_dp_sink_crc_start(struct intel_dp *intel_dp) return -EIO; } + intel_dp->sink_crc.started = true; return 0; } @@ -4058,38 +4171,55 @@ int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc) struct drm_device *dev = dig_port->base.base.dev; struct intel_crtc *intel_crtc = to_intel_crtc(dig_port->base.base.crtc); u8 buf; - int test_crc_count; + int count, ret; int attempts = 6; - int ret; + bool old_equal_new; ret = intel_dp_sink_crc_start(intel_dp); if (ret) return ret; - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0) { - ret = -EIO; - goto stop; - } - - test_crc_count = buf & DP_TEST_COUNT_MASK; - do { + intel_wait_for_vblank(dev, intel_crtc->pipe); + if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0) { ret = -EIO; goto stop; } - intel_wait_for_vblank(dev, intel_crtc->pipe); - } while (--attempts && (buf & DP_TEST_COUNT_MASK) == test_crc_count); + count = buf & DP_TEST_COUNT_MASK; + + /* + * Count might be reset during the loop. In this case + * last known count needs to be reset as well. + */ + if (count == 0) + intel_dp->sink_crc.last_count = 0; + + if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) { + ret = -EIO; + goto stop; + } + + old_equal_new = (count == intel_dp->sink_crc.last_count && + !memcmp(intel_dp->sink_crc.last_crc, crc, + 6 * sizeof(u8))); + + } while (--attempts && (count == 0 || old_equal_new)); + + intel_dp->sink_crc.last_count = buf & DP_TEST_COUNT_MASK; + memcpy(intel_dp->sink_crc.last_crc, crc, 6 * sizeof(u8)); if (attempts == 0) { - DRM_DEBUG_KMS("Panel is unable to calculate CRC after 6 vblanks\n"); - ret = -ETIMEDOUT; - goto stop; + if (old_equal_new) { + DRM_DEBUG_KMS("Unreliable Sink CRC counter: Current returned CRC is identical to the previous one\n"); + } else { + DRM_ERROR("Panel is unable to calculate any CRC after 6 vblanks\n"); + ret = -ETIMEDOUT; + goto stop; + } } - if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) - ret = -EIO; stop: intel_dp_sink_crc_stop(intel_dp); return ret; @@ -4249,10 +4379,10 @@ go_again: if (bret == true) { /* check link status - esi[10] = 0x200c */ - if (intel_dp->active_mst_links && !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) { + if (intel_dp->active_mst_links && + !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) { DRM_DEBUG_KMS("channel EQ not ok, retraining\n"); intel_dp_start_link_train(intel_dp); - intel_dp_complete_link_train(intel_dp); intel_dp_stop_link_train(intel_dp); } @@ -4343,7 +4473,6 @@ intel_dp_check_link_status(struct intel_dp *intel_dp) DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n", intel_encoder->base.name); intel_dp_start_link_train(intel_dp); - intel_dp_complete_link_train(intel_dp); intel_dp_stop_link_train(intel_dp); } } @@ -4411,58 +4540,164 @@ edp_detect(struct intel_dp *intel_dp) return status; } -static enum drm_connector_status -ironlake_dp_detect(struct intel_dp *intel_dp) +static bool ibx_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) { - struct drm_device *dev = intel_dp_to_dev(intel_dp); - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + u32 bit; - if (!ibx_digital_port_connected(dev_priv, intel_dig_port)) - return connector_status_disconnected; + switch (port->port) { + case PORT_A: + return true; + case PORT_B: + bit = SDE_PORTB_HOTPLUG; + break; + case PORT_C: + bit = SDE_PORTC_HOTPLUG; + break; + case PORT_D: + bit = SDE_PORTD_HOTPLUG; + break; + default: + MISSING_CASE(port->port); + return false; + } - return intel_dp_detect_dpcd(intel_dp); + return I915_READ(SDEISR) & bit; +} + +static bool cpt_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) +{ + u32 bit; + + switch (port->port) { + case PORT_A: + return true; + case PORT_B: + bit = SDE_PORTB_HOTPLUG_CPT; + break; + case PORT_C: + bit = SDE_PORTC_HOTPLUG_CPT; + break; + case PORT_D: + bit = SDE_PORTD_HOTPLUG_CPT; + break; + case PORT_E: + bit = SDE_PORTE_HOTPLUG_SPT; + break; + default: + MISSING_CASE(port->port); + return false; + } + + return I915_READ(SDEISR) & bit; } -static int g4x_digital_port_connected(struct drm_device *dev, +static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) +{ + u32 bit; + + switch (port->port) { + case PORT_B: + bit = PORTB_HOTPLUG_LIVE_STATUS_G4X; + break; + case PORT_C: + bit = PORTC_HOTPLUG_LIVE_STATUS_G4X; + break; + case PORT_D: + bit = PORTD_HOTPLUG_LIVE_STATUS_G4X; + break; + default: + MISSING_CASE(port->port); + return false; + } + + return I915_READ(PORT_HOTPLUG_STAT) & bit; +} + +static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) +{ + u32 bit; + + switch (port->port) { + case PORT_B: + bit = PORTB_HOTPLUG_LIVE_STATUS_VLV; + break; + case PORT_C: + bit = PORTC_HOTPLUG_LIVE_STATUS_VLV; + break; + case PORT_D: + bit = PORTD_HOTPLUG_LIVE_STATUS_VLV; + break; + default: + MISSING_CASE(port->port); + return false; + } + + return I915_READ(PORT_HOTPLUG_STAT) & bit; +} + +static bool bxt_digital_port_connected(struct drm_i915_private *dev_priv, struct intel_digital_port *intel_dig_port) { - struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t bit; + struct intel_encoder *intel_encoder = &intel_dig_port->base; + enum port port; + u32 bit; - if (IS_VALLEYVIEW(dev)) { - switch (intel_dig_port->port) { - case PORT_B: - bit = PORTB_HOTPLUG_LIVE_STATUS_VLV; - break; - case PORT_C: - bit = PORTC_HOTPLUG_LIVE_STATUS_VLV; - break; - case PORT_D: - bit = PORTD_HOTPLUG_LIVE_STATUS_VLV; - break; - default: - return -EINVAL; - } - } else { - switch (intel_dig_port->port) { - case PORT_B: - bit = PORTB_HOTPLUG_LIVE_STATUS_G4X; - break; - case PORT_C: - bit = PORTC_HOTPLUG_LIVE_STATUS_G4X; - break; - case PORT_D: - bit = PORTD_HOTPLUG_LIVE_STATUS_G4X; - break; - default: - return -EINVAL; - } + intel_hpd_pin_to_port(intel_encoder->hpd_pin, &port); + switch (port) { + case PORT_A: + bit = BXT_DE_PORT_HP_DDIA; + break; + case PORT_B: + bit = BXT_DE_PORT_HP_DDIB; + break; + case PORT_C: + bit = BXT_DE_PORT_HP_DDIC; + break; + default: + MISSING_CASE(port); + return false; } - if ((I915_READ(PORT_HOTPLUG_STAT) & bit) == 0) - return 0; - return 1; + return I915_READ(GEN8_DE_PORT_ISR) & bit; +} + +/* + * intel_digital_port_connected - is the specified port connected? + * @dev_priv: i915 private structure + * @port: the port to test + * + * Return %true if @port is connected, %false otherwise. + */ +bool intel_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) +{ + if (HAS_PCH_IBX(dev_priv)) + return ibx_digital_port_connected(dev_priv, port); + if (HAS_PCH_SPLIT(dev_priv)) + return cpt_digital_port_connected(dev_priv, port); + else if (IS_BROXTON(dev_priv)) + return bxt_digital_port_connected(dev_priv, port); + else if (IS_VALLEYVIEW(dev_priv)) + return vlv_digital_port_connected(dev_priv, port); + else + return g4x_digital_port_connected(dev_priv, port); +} + +static enum drm_connector_status +ironlake_dp_detect(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + + if (!intel_digital_port_connected(dev_priv, intel_dig_port)) + return connector_status_disconnected; + + return intel_dp_detect_dpcd(intel_dp); } static enum drm_connector_status @@ -4470,7 +4705,6 @@ g4x_dp_detect(struct intel_dp *intel_dp) { struct drm_device *dev = intel_dp_to_dev(intel_dp); struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - int ret; /* Can't disconnect eDP, but you can close the lid... */ if (is_edp(intel_dp)) { @@ -4482,10 +4716,7 @@ g4x_dp_detect(struct intel_dp *intel_dp) return status; } - ret = g4x_digital_port_connected(dev, intel_dig_port); - if (ret == -EINVAL) - return connector_status_unknown; - else if (ret == 0) + if (!intel_digital_port_connected(dev->dev_private, intel_dig_port)) return connector_status_disconnected; return intel_dp_detect_dpcd(intel_dp); @@ -4729,7 +4960,7 @@ intel_dp_set_property(struct drm_connector *connector, if (property == dev_priv->broadcast_rgb_property) { bool old_auto = intel_dp->color_range_auto; - uint32_t old_range = intel_dp->color_range; + bool old_range = intel_dp->limited_color_range; switch (val) { case INTEL_BROADCAST_RGB_AUTO: @@ -4737,18 +4968,18 @@ intel_dp_set_property(struct drm_connector *connector, break; case INTEL_BROADCAST_RGB_FULL: intel_dp->color_range_auto = false; - intel_dp->color_range = 0; + intel_dp->limited_color_range = false; break; case INTEL_BROADCAST_RGB_LIMITED: intel_dp->color_range_auto = false; - intel_dp->color_range = DP_COLOR_RANGE_16_235; + intel_dp->limited_color_range = true; break; default: return -EINVAL; } if (old_auto == intel_dp->color_range_auto && - old_range == intel_dp->color_range) + old_range == intel_dp->limited_color_range) return 0; goto done; @@ -4948,13 +5179,8 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) /* indicate that we need to restart link training */ intel_dp->train_set_valid = false; - if (HAS_PCH_SPLIT(dev)) { - if (!ibx_digital_port_connected(dev_priv, intel_dig_port)) - goto mst_fail; - } else { - if (g4x_digital_port_connected(dev, intel_dig_port) != 1) - goto mst_fail; - } + if (!intel_digital_port_connected(dev_priv, intel_dig_port)) + goto mst_fail; if (!intel_dp_get_dpcd(intel_dp)) { goto mst_fail; @@ -5029,6 +5255,13 @@ bool intel_dp_is_edp(struct drm_device *dev, enum port port) [PORT_E] = DVO_PORT_DPE, }; + /* + * eDP not supported on g4x. so bail out early just + * for a bit extra safety in case the VBT is bonkers. + */ + if (INTEL_INFO(dev)->gen < 5) + return false; + if (port == PORT_A) return true; @@ -5766,7 +5999,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, } intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode); - intel_connector->panel.backlight_power = intel_edp_backlight_power; + intel_connector->panel.backlight.power = intel_edp_backlight_power; intel_panel_setup_backlight(connector, pipe); return true; @@ -5854,6 +6087,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, break; case PORT_B: intel_encoder->hpd_pin = HPD_PORT_B; + if (IS_BROXTON(dev_priv) && (INTEL_REVID(dev) < BXT_REVID_B0)) + intel_encoder->hpd_pin = HPD_PORT_A; break; case PORT_C: intel_encoder->hpd_pin = HPD_PORT_C; @@ -5933,10 +6168,8 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) return; intel_connector = intel_connector_alloc(); - if (!intel_connector) { - kfree(intel_dig_port); - return; - } + if (!intel_connector) + goto err_connector_alloc; intel_encoder = &intel_dig_port->base; encoder = &intel_encoder->base; @@ -5954,6 +6187,7 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) intel_encoder->pre_enable = chv_pre_enable_dp; intel_encoder->enable = vlv_enable_dp; intel_encoder->post_disable = chv_post_disable_dp; + intel_encoder->post_pll_disable = chv_dp_post_pll_disable; } else if (IS_VALLEYVIEW(dev)) { intel_encoder->pre_pll_enable = vlv_dp_pre_pll_enable; intel_encoder->pre_enable = vlv_pre_enable_dp; @@ -5983,11 +6217,18 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) intel_dig_port->hpd_pulse = intel_dp_hpd_pulse; dev_priv->hotplug.irq_port[port] = intel_dig_port; - if (!intel_dp_init_connector(intel_dig_port, intel_connector)) { - drm_encoder_cleanup(encoder); - kfree(intel_dig_port); - kfree(intel_connector); - } + if (!intel_dp_init_connector(intel_dig_port, intel_connector)) + goto err_init_connector; + + return; + +err_init_connector: + drm_encoder_cleanup(encoder); + kfree(intel_connector); +err_connector_alloc: + kfree(intel_dig_port); + + return; } void intel_dp_mst_suspend(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 3e4be5a..0639275 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -39,8 +39,8 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, struct intel_dp *intel_dp = &intel_dig_port->dp; struct drm_atomic_state *state; int bpp, i; - int lane_count, slots, rate; - struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + int lane_count, slots; + const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; struct drm_connector *drm_connector; struct intel_connector *connector, *found = NULL; struct drm_connector_state *connector_state; @@ -56,20 +56,11 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, */ lane_count = drm_dp_max_lane_count(intel_dp->dpcd); - rate = intel_dp_max_link_rate(intel_dp); - if (intel_dp->num_sink_rates) { - intel_dp->link_bw = 0; - intel_dp->rate_select = intel_dp_rate_select(intel_dp, rate); - } else { - intel_dp->link_bw = drm_dp_link_rate_to_bw_code(rate); - intel_dp->rate_select = 0; - } - - intel_dp->lane_count = lane_count; + pipe_config->lane_count = lane_count; pipe_config->pipe_bpp = 24; - pipe_config->port_clock = rate; + pipe_config->port_clock = intel_dp_max_link_rate(intel_dp); state = pipe_config->base.state; @@ -87,7 +78,7 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, return false; } - mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->clock, bpp); + mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp); pipe_config->pbn = mst_pbn; slots = drm_dp_find_vcpi_slots(&intel_dp->mst_mgr, mst_pbn); @@ -184,6 +175,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder) if (intel_dp->active_mst_links == 0) { enum port port = intel_ddi_get_encoder_port(encoder); + intel_dp_set_link_params(intel_dp, intel_crtc->config); + /* FIXME: add support for SKL */ if (INTEL_INFO(dev)->gen < 9) I915_WRITE(PORT_CLK_SEL(port), @@ -195,7 +188,6 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder) intel_dp_start_link_train(intel_dp); - intel_dp_complete_link_train(intel_dp); intel_dp_stop_link_train(intel_dp); } @@ -286,6 +278,10 @@ static void intel_dp_mst_enc_get_config(struct intel_encoder *encoder, break; } pipe_config->base.adjusted_mode.flags |= flags; + + pipe_config->lane_count = + ((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1; + intel_dp_get_m_n(crtc, pipe_config); intel_ddi_clock_get(&intel_dig_port->base, pipe_config); @@ -462,11 +458,17 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); drm_mode_connector_set_path_property(connector, pathprop); + return connector; +} + +static void intel_dp_register_mst_connector(struct drm_connector *connector) +{ + struct intel_connector *intel_connector = to_intel_connector(connector); + struct drm_device *dev = connector->dev; drm_modeset_lock_all(dev); intel_connector_add_to_fbdev(intel_connector); drm_modeset_unlock_all(dev); drm_connector_register(&intel_connector->base); - return connector; } static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, @@ -512,6 +514,7 @@ static void intel_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) static struct drm_dp_mst_topology_cbs mst_cbs = { .add_connector = intel_dp_add_mst_connector, + .register_connector = intel_dp_register_mst_connector, .destroy_connector = intel_dp_destroy_mst_connector, .hotplug = intel_dp_mst_hotplug, }; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 354432f..91b6b40 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -142,6 +142,7 @@ struct intel_encoder { void (*mode_set)(struct intel_encoder *intel_encoder); void (*disable)(struct intel_encoder *); void (*post_disable)(struct intel_encoder *); + void (*post_pll_disable)(struct intel_encoder *); /* Read out the current hw state of this connector, returning true if * the encoder is active. If the encoder is enabled it also set the pipe * it is connected to in the pipe parameter. */ @@ -178,12 +179,22 @@ struct intel_panel { bool active_low_pwm; /* PWM chip */ + bool util_pin_active_low; /* bxt+ */ + u8 controller; /* bxt+ only */ struct pwm_device *pwm; struct backlight_device *device; - } backlight; - void (*backlight_power)(struct intel_connector *, bool enable); + /* Connector and platform specific backlight functions */ + int (*setup)(struct intel_connector *connector, enum pipe pipe); + uint32_t (*get)(struct intel_connector *connector); + void (*set)(struct intel_connector *connector, uint32_t level); + void (*disable)(struct intel_connector *connector); + void (*enable)(struct intel_connector *connector); + uint32_t (*hz_to_pwm)(struct intel_connector *connector, + uint32_t hz); + void (*power)(struct intel_connector *, bool enable); + } backlight; }; struct intel_connector { @@ -337,6 +348,8 @@ struct intel_crtc_state { #define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */ unsigned long quirks; + bool update_pipe; + /* Pipe source size (ie. panel fitter input size) * All planes will be positioned inside this space, * and get clipped at the edges. */ @@ -423,6 +436,8 @@ struct intel_crtc_state { /* Used by SDVO (and if we ever fix it, HDMI). */ unsigned pixel_multiplier; + uint8_t lane_count; + /* Panel fitter controls for gen2-gen4 + VLV */ struct { u32 control; @@ -453,6 +468,9 @@ struct intel_crtc_state { /* w/a for waiting 2 vblanks during crtc enable */ enum pipe hsw_workaround_pipe; + + /* IVB sprite scaling w/a (WaCxSRDisabledForSpriteScaling:ivb) */ + bool disable_lp_wm; }; struct vlv_wm_state { @@ -532,6 +550,8 @@ struct intel_crtc { * gen4+ this only adjusts up to a tile, offsets within a tile are * handled in the hw itself (with the TILEOFF register). */ unsigned long dspaddr_offset; + int adjusted_x; + int adjusted_y; struct drm_i915_gem_object *cursor_bo; uint32_t cursor_addr; @@ -560,7 +580,13 @@ struct intel_crtc { int scanline_offset; - unsigned start_vbl_count; + struct { + unsigned start_vbl_count; + ktime_t start_vbl_time; + int min_vbl, max_vbl; + int scanline_start; + } debug; + struct intel_crtc_atomic_commit atomic; /* scalers available on this crtc */ @@ -657,19 +683,20 @@ struct cxsr_latency { struct intel_hdmi { u32 hdmi_reg; int ddc_bus; - uint32_t color_range; + bool limited_color_range; bool color_range_auto; bool has_hdmi_sink; bool has_audio; enum hdmi_force_audio force_audio; bool rgb_quant_range_selectable; enum hdmi_picture_aspect aspect_ratio; + struct intel_connector *attached_connector; void (*write_infoframe)(struct drm_encoder *encoder, enum hdmi_infoframe_type type, const void *frame, ssize_t len); void (*set_infoframes)(struct drm_encoder *encoder, bool enable, - struct drm_display_mode *adjusted_mode); + const struct drm_display_mode *adjusted_mode); bool (*infoframe_enabled)(struct drm_encoder *encoder); }; @@ -696,23 +723,29 @@ enum link_m_n_set { M2_N2 }; +struct sink_crc { + bool started; + u8 last_crc[6]; + int last_count; +}; + struct intel_dp { uint32_t output_reg; uint32_t aux_ch_ctl_reg; uint32_t DP; + int link_rate; + uint8_t lane_count; bool has_audio; enum hdmi_force_audio force_audio; - uint32_t color_range; + bool limited_color_range; bool color_range_auto; - uint8_t link_bw; - uint8_t rate_select; - uint8_t lane_count; uint8_t dpcd[DP_RECEIVER_CAP_SIZE]; uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE]; uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS]; /* sink rates as reported by DP_SUPPORTED_LINK_RATES */ uint8_t num_sink_rates; int sink_rates[DP_MAX_SUPPORTED_RATES]; + struct sink_crc sink_crc; struct drm_dp_aux aux; uint8_t train_set[4]; int panel_power_up_delay; @@ -735,7 +768,6 @@ struct intel_dp { enum pipe pps_pipe; struct edp_power_seq pps_delays; - bool use_tps3; bool can_mst; /* this port supports mst */ bool is_mst; int active_mst_links; @@ -770,6 +802,7 @@ struct intel_digital_port { struct intel_dp dp; struct intel_hdmi hdmi; enum irqreturn (*hpd_pulse)(struct intel_digital_port *, bool); + bool release_cl2_override; }; struct intel_dp_mst_encoder { @@ -779,7 +812,7 @@ struct intel_dp_mst_encoder { void *port; /* store this opaque as its illegal to dereference it */ }; -static inline int +static inline enum dpio_channel vlv_dport_to_channel(struct intel_digital_port *dport) { switch (dport->port) { @@ -793,7 +826,21 @@ vlv_dport_to_channel(struct intel_digital_port *dport) } } -static inline int +static inline enum dpio_phy +vlv_dport_to_phy(struct intel_digital_port *dport) +{ + switch (dport->port) { + case PORT_B: + case PORT_C: + return DPIO_PHY0; + case PORT_D: + return DPIO_PHY1; + default: + BUG(); + } +} + +static inline enum dpio_channel vlv_pipe_to_channel(enum pipe pipe) { switch (pipe) { @@ -987,6 +1034,7 @@ void i915_audio_component_cleanup(struct drm_i915_private *dev_priv); extern const struct drm_plane_funcs intel_plane_funcs; bool intel_has_pending_fb_unpin(struct drm_device *dev); int intel_pch_rawclk(struct drm_device *dev); +int intel_hrawclk(struct drm_device *dev); void intel_mark_busy(struct drm_device *dev); void intel_mark_idle(struct drm_device *dev); void intel_crtc_restore_mode(struct drm_crtc *crtc); @@ -995,8 +1043,6 @@ void intel_encoder_destroy(struct drm_encoder *encoder); int intel_connector_init(struct intel_connector *); struct intel_connector *intel_connector_alloc(void); bool intel_connector_get_hw_state(struct intel_connector *connector); -bool ibx_digital_port_connected(struct drm_i915_private *dev_priv, - struct intel_digital_port *port); void intel_connector_attach_encoder(struct intel_connector *connector, struct intel_encoder *encoder); struct drm_encoder *intel_best_encoder(struct drm_connector *connector); @@ -1054,7 +1100,7 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, unsigned int intel_tile_height(struct drm_device *dev, uint32_t pixel_format, - uint64_t fb_format_modifier); + uint64_t fb_format_modifier, unsigned int plane); static inline bool intel_rotation_90_or_270(unsigned int rotation) @@ -1135,7 +1181,9 @@ int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state); int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane, - struct drm_i915_gem_object *obj); + struct drm_i915_gem_object *obj, + unsigned int plane); + u32 skl_plane_ctl_format(uint32_t pixel_format); u32 skl_plane_ctl_tiling(uint64_t fb_modifier); u32 skl_plane_ctl_rotation(unsigned int rotation); @@ -1153,8 +1201,9 @@ void assert_csr_loaded(struct drm_i915_private *dev_priv); void intel_dp_init(struct drm_device *dev, int output_reg, enum port port); bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port, struct intel_connector *intel_connector); +void intel_dp_set_link_params(struct intel_dp *intel_dp, + const struct intel_crtc_state *pipe_config); void intel_dp_start_link_train(struct intel_dp *intel_dp); -void intel_dp_complete_link_train(struct intel_dp *intel_dp); void intel_dp_stop_link_train(struct intel_dp *intel_dp); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); void intel_dp_encoder_destroy(struct drm_encoder *encoder); @@ -1183,6 +1232,8 @@ void intel_edp_drrs_disable(struct intel_dp *intel_dp); void intel_edp_drrs_invalidate(struct drm_device *dev, unsigned frontbuffer_bits); void intel_edp_drrs_flush(struct drm_device *dev, unsigned frontbuffer_bits); +bool intel_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port); void hsw_dp_set_ddi_pll_sel(struct intel_crtc_state *pipe_config); /* intel_dp_mst.c */ @@ -1261,6 +1312,7 @@ int intel_connector_update_modes(struct drm_connector *connector, int intel_ddc_get_modes(struct drm_connector *c, struct i2c_adapter *adapter); void intel_attach_force_audio_property(struct drm_connector *connector); void intel_attach_broadcast_rgb_property(struct drm_connector *connector); +void intel_attach_aspect_ratio_property(struct drm_connector *connector); /* intel_overlay.c */ @@ -1293,7 +1345,6 @@ int intel_panel_setup_backlight(struct drm_connector *connector, enum pipe pipe) void intel_panel_enable_backlight(struct intel_connector *connector); void intel_panel_disable_backlight(struct intel_connector *connector); void intel_panel_destroy_backlight(struct drm_connector *connector); -void intel_panel_init_backlight_funcs(struct drm_device *dev); enum drm_connector_status intel_panel_detect(struct drm_device *dev); extern struct drm_display_mode *intel_find_panel_downclock( struct drm_device *dev, @@ -1337,17 +1388,17 @@ void intel_runtime_pm_put(struct drm_i915_private *dev_priv); void intel_display_set_init_power(struct drm_i915_private *dev, bool enable); +void chv_phy_powergate_lanes(struct intel_encoder *encoder, + bool override, unsigned int mask); +bool chv_phy_powergate_ch(struct drm_i915_private *dev_priv, enum dpio_phy phy, + enum dpio_channel ch, bool override); + + /* intel_pm.c */ void intel_init_clock_gating(struct drm_device *dev); void intel_suspend_hw(struct drm_device *dev); int ilk_wm_max_level(const struct drm_device *dev); void intel_update_watermarks(struct drm_crtc *crtc); -void intel_update_sprite_watermarks(struct drm_plane *plane, - struct drm_crtc *crtc, - uint32_t sprite_width, - uint32_t sprite_height, - int pixel_size, - bool enabled, bool scaled); void intel_init_pm(struct drm_device *dev); void intel_pm_setup(struct drm_device *dev); void intel_gpu_ips_init(struct drm_i915_private *dev_priv); @@ -1382,9 +1433,8 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob); int intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane); int intel_sprite_set_colorkey(struct drm_device *dev, void *data, struct drm_file *file_priv); -void intel_pipe_update_start(struct intel_crtc *crtc, - uint32_t *start_vbl_count); -void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count); +void intel_pipe_update_start(struct intel_crtc *crtc); +void intel_pipe_update_end(struct intel_crtc *crtc); /* intel_tv.c */ void intel_tv_init(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 32a6c71..170ae6f 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -282,58 +282,46 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder, return true; } -static void intel_dsi_port_enable(struct intel_encoder *encoder) +static void bxt_dsi_device_ready(struct intel_encoder *encoder) { - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); enum port port; - u32 temp; + u32 val; - if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) { - temp = I915_READ(VLV_CHICKEN_3); - temp &= ~PIXEL_OVERLAP_CNT_MASK | - intel_dsi->pixel_overlap << - PIXEL_OVERLAP_CNT_SHIFT; - I915_WRITE(VLV_CHICKEN_3, temp); - } + DRM_DEBUG_KMS("\n"); + /* Exit Low power state in 4 steps*/ for_each_dsi_port(port, intel_dsi->ports) { - temp = I915_READ(MIPI_PORT_CTRL(port)); - temp &= ~LANE_CONFIGURATION_MASK; - temp &= ~DUAL_LINK_MODE_MASK; - if (intel_dsi->ports == ((1 << PORT_A) | (1 << PORT_C))) { - temp |= (intel_dsi->dual_link - 1) - << DUAL_LINK_MODE_SHIFT; - temp |= intel_crtc->pipe ? - LANE_CONFIGURATION_DUAL_LINK_B : - LANE_CONFIGURATION_DUAL_LINK_A; - } - /* assert ip_tg_enable signal */ - I915_WRITE(MIPI_PORT_CTRL(port), temp | DPI_ENABLE); - POSTING_READ(MIPI_PORT_CTRL(port)); - } -} + /* 1. Enable MIPI PHY transparent latch */ + val = I915_READ(BXT_MIPI_PORT_CTRL(port)); + I915_WRITE(BXT_MIPI_PORT_CTRL(port), val | LP_OUTPUT_HOLD); + usleep_range(2000, 2500); -static void intel_dsi_port_disable(struct intel_encoder *encoder) -{ - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); - enum port port; - u32 temp; + /* 2. Enter ULPS */ + val = I915_READ(MIPI_DEVICE_READY(port)); + val &= ~ULPS_STATE_MASK; + val |= (ULPS_STATE_ENTER | DEVICE_READY); + I915_WRITE(MIPI_DEVICE_READY(port), val); + usleep_range(2, 3); + + /* 3. Exit ULPS */ + val = I915_READ(MIPI_DEVICE_READY(port)); + val &= ~ULPS_STATE_MASK; + val |= (ULPS_STATE_EXIT | DEVICE_READY); + I915_WRITE(MIPI_DEVICE_READY(port), val); + usleep_range(1000, 1500); - for_each_dsi_port(port, intel_dsi->ports) { - /* de-assert ip_tg_enable signal */ - temp = I915_READ(MIPI_PORT_CTRL(port)); - I915_WRITE(MIPI_PORT_CTRL(port), temp & ~DPI_ENABLE); - POSTING_READ(MIPI_PORT_CTRL(port)); + /* Clear ULPS and set device ready */ + val = I915_READ(MIPI_DEVICE_READY(port)); + val &= ~ULPS_STATE_MASK; + val |= DEVICE_READY; + I915_WRITE(MIPI_DEVICE_READY(port), val); } } -static void intel_dsi_device_ready(struct intel_encoder *encoder) +static void vlv_dsi_device_ready(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); @@ -372,6 +360,75 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder) } } +static void intel_dsi_device_ready(struct intel_encoder *encoder) +{ + struct drm_device *dev = encoder->base.dev; + + if (IS_VALLEYVIEW(dev)) + vlv_dsi_device_ready(encoder); + else if (IS_BROXTON(dev)) + bxt_dsi_device_ready(encoder); +} + +static void intel_dsi_port_enable(struct intel_encoder *encoder) +{ + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + enum port port; + u32 temp; + u32 port_ctrl; + + if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) { + temp = I915_READ(VLV_CHICKEN_3); + temp &= ~PIXEL_OVERLAP_CNT_MASK | + intel_dsi->pixel_overlap << + PIXEL_OVERLAP_CNT_SHIFT; + I915_WRITE(VLV_CHICKEN_3, temp); + } + + for_each_dsi_port(port, intel_dsi->ports) { + port_ctrl = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) : + MIPI_PORT_CTRL(port); + + temp = I915_READ(port_ctrl); + + temp &= ~LANE_CONFIGURATION_MASK; + temp &= ~DUAL_LINK_MODE_MASK; + + if (intel_dsi->ports == ((1 << PORT_A) | (1 << PORT_C))) { + temp |= (intel_dsi->dual_link - 1) + << DUAL_LINK_MODE_SHIFT; + temp |= intel_crtc->pipe ? + LANE_CONFIGURATION_DUAL_LINK_B : + LANE_CONFIGURATION_DUAL_LINK_A; + } + /* assert ip_tg_enable signal */ + I915_WRITE(port_ctrl, temp | DPI_ENABLE); + POSTING_READ(port_ctrl); + } +} + +static void intel_dsi_port_disable(struct intel_encoder *encoder) +{ + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + enum port port; + u32 temp; + u32 port_ctrl; + + for_each_dsi_port(port, intel_dsi->ports) { + /* de-assert ip_tg_enable signal */ + port_ctrl = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) : + MIPI_PORT_CTRL(port); + temp = I915_READ(port_ctrl); + I915_WRITE(port_ctrl, temp & ~DPI_ENABLE); + POSTING_READ(port_ctrl); + } +} + static void intel_dsi_enable(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; @@ -419,19 +476,24 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder) msleep(intel_dsi->panel_on_delay); - /* Disable DPOunit clock gating, can stall pipe - * and we need DPLL REFA always enabled */ - tmp = I915_READ(DPLL(pipe)); - tmp |= DPLL_REF_CLK_ENABLE_VLV; - I915_WRITE(DPLL(pipe), tmp); - - /* update the hw state for DPLL */ - intel_crtc->config->dpll_hw_state.dpll = DPLL_INTEGRATED_REF_CLK_VLV | - DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS; - - tmp = I915_READ(DSPCLK_GATE_D); - tmp |= DPOUNIT_CLOCK_GATE_DISABLE; - I915_WRITE(DSPCLK_GATE_D, tmp); + if (IS_VALLEYVIEW(dev)) { + /* + * Disable DPOunit clock gating, can stall pipe + * and we need DPLL REFA always enabled + */ + tmp = I915_READ(DPLL(pipe)); + tmp |= DPLL_REF_CLK_ENABLE_VLV; + I915_WRITE(DPLL(pipe), tmp); + + /* update the hw state for DPLL */ + intel_crtc->config->dpll_hw_state.dpll = + DPLL_INTEGRATED_REF_CLK_VLV | + DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS; + + tmp = I915_READ(DSPCLK_GATE_D); + tmp |= DPOUNIT_CLOCK_GATE_DISABLE; + I915_WRITE(DSPCLK_GATE_D, tmp); + } /* put device in ready state */ intel_dsi_device_ready(encoder); @@ -495,12 +557,7 @@ static void intel_dsi_disable(struct intel_encoder *encoder) /* Panel commands can be sent when clock is in LP11 */ I915_WRITE(MIPI_DEVICE_READY(port), 0x0); - temp = I915_READ(MIPI_CTRL(port)); - temp &= ~ESCAPE_CLOCK_DIVIDER_MASK; - I915_WRITE(MIPI_CTRL(port), temp | - intel_dsi->escape_clk_div << - ESCAPE_CLOCK_DIVIDER_SHIFT); - + intel_dsi_reset_clocks(encoder, port); I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP); temp = I915_READ(MIPI_DSI_FUNC_PRG(port)); @@ -519,10 +576,12 @@ static void intel_dsi_disable(struct intel_encoder *encoder) static void intel_dsi_clear_device_ready(struct intel_encoder *encoder) { + struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); enum port port; u32 val; + u32 port_ctrl = 0; DRM_DEBUG_KMS("\n"); for_each_dsi_port(port, intel_dsi->ports) { @@ -539,25 +598,29 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder) ULPS_STATE_ENTER); usleep_range(2000, 2500); + if (IS_BROXTON(dev)) + port_ctrl = BXT_MIPI_PORT_CTRL(port); + else if (IS_VALLEYVIEW(dev)) + /* Common bit for both MIPI Port A & MIPI Port C */ + port_ctrl = MIPI_PORT_CTRL(PORT_A); + /* Wait till Clock lanes are in LP-00 state for MIPI Port A * only. MIPI Port C has no similar bit for checking */ - if (wait_for(((I915_READ(MIPI_PORT_CTRL(PORT_A)) & AFE_LATCHOUT) - == 0x00000), 30)) + if (wait_for(((I915_READ(port_ctrl) & AFE_LATCHOUT) + == 0x00000), 30)) DRM_ERROR("DSI LP not going Low\n"); - /* Disable MIPI PHY transparent latch - * Common bit for both MIPI Port A & MIPI Port C - */ - val = I915_READ(MIPI_PORT_CTRL(PORT_A)); - I915_WRITE(MIPI_PORT_CTRL(PORT_A), val & ~LP_OUTPUT_HOLD); + /* Disable MIPI PHY transparent latch */ + val = I915_READ(port_ctrl); + I915_WRITE(port_ctrl, val & ~LP_OUTPUT_HOLD); usleep_range(1000, 1500); I915_WRITE(MIPI_DEVICE_READY(port), 0x00); usleep_range(2000, 2500); } - vlv_disable_dsi_pll(encoder); + intel_disable_dsi_pll(encoder); } static void intel_dsi_post_disable(struct intel_encoder *encoder) @@ -593,7 +656,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); struct drm_device *dev = encoder->base.dev; enum intel_display_power_domain power_domain; - u32 dpi_enabled, func; + u32 dpi_enabled, func, ctrl_reg; enum port port; DRM_DEBUG_KMS("\n"); @@ -605,8 +668,9 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, /* XXX: this only works for one DSI output */ for_each_dsi_port(port, intel_dsi->ports) { func = I915_READ(MIPI_DSI_FUNC_PRG(port)); - dpi_enabled = I915_READ(MIPI_PORT_CTRL(port)) & - DPI_ENABLE; + ctrl_reg = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) : + MIPI_PORT_CTRL(port); + dpi_enabled = I915_READ(ctrl_reg) & DPI_ENABLE; /* Due to some hardware limitations on BYT, MIPI Port C DPI * Enable bit does not get set. To check whether DSI Port C @@ -631,7 +695,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, static void intel_dsi_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { - u32 pclk; + u32 pclk = 0; DRM_DEBUG_KMS("\n"); /* @@ -640,7 +704,11 @@ static void intel_dsi_get_config(struct intel_encoder *encoder, */ pipe_config->dpll_hw_state.dpll_md = 0; - pclk = vlv_get_dsi_pclk(encoder, pipe_config->pipe_bpp); + if (IS_BROXTON(encoder->base.dev)) + pclk = bxt_get_dsi_pclk(encoder, pipe_config->pipe_bpp); + else if (IS_VALLEYVIEW(encoder->base.dev)) + pclk = vlv_get_dsi_pclk(encoder, pipe_config->pipe_bpp); + if (!pclk) return; @@ -654,6 +722,7 @@ intel_dsi_mode_valid(struct drm_connector *connector, { struct intel_connector *intel_connector = to_intel_connector(connector); struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode; + int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; DRM_DEBUG_KMS("\n"); @@ -667,6 +736,8 @@ intel_dsi_mode_valid(struct drm_connector *connector, return MODE_PANEL; if (mode->vdisplay > fixed_mode->vdisplay) return MODE_PANEL; + if (fixed_mode->clock > max_dotclk) + return MODE_CLOCK_HIGH; } return MODE_OK; @@ -695,7 +766,7 @@ static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count, } static void set_dsi_timings(struct drm_encoder *encoder, - const struct drm_display_mode *mode) + const struct drm_display_mode *adjusted_mode) { struct drm_device *dev = encoder->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -707,10 +778,10 @@ static void set_dsi_timings(struct drm_encoder *encoder, u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp; - hactive = mode->hdisplay; - hfp = mode->hsync_start - mode->hdisplay; - hsync = mode->hsync_end - mode->hsync_start; - hbp = mode->htotal - mode->hsync_end; + hactive = adjusted_mode->crtc_hdisplay; + hfp = adjusted_mode->crtc_hsync_start - adjusted_mode->crtc_hdisplay; + hsync = adjusted_mode->crtc_hsync_end - adjusted_mode->crtc_hsync_start; + hbp = adjusted_mode->crtc_htotal - adjusted_mode->crtc_hsync_end; if (intel_dsi->dual_link) { hactive /= 2; @@ -721,9 +792,9 @@ static void set_dsi_timings(struct drm_encoder *encoder, hbp /= 2; } - vfp = mode->vsync_start - mode->vdisplay; - vsync = mode->vsync_end - mode->vsync_start; - vbp = mode->vtotal - mode->vsync_end; + vfp = adjusted_mode->crtc_vsync_start - adjusted_mode->crtc_vdisplay; + vsync = adjusted_mode->crtc_vsync_end - adjusted_mode->crtc_vsync_start; + vbp = adjusted_mode->crtc_vtotal - adjusted_mode->crtc_vsync_end; /* horizontal values are in terms of high speed byte clock */ hactive = txbyteclkhs(hactive, bpp, lane_count, @@ -734,6 +805,21 @@ static void set_dsi_timings(struct drm_encoder *encoder, hbp = txbyteclkhs(hbp, bpp, lane_count, intel_dsi->burst_mode_ratio); for_each_dsi_port(port, intel_dsi->ports) { + if (IS_BROXTON(dev)) { + /* + * Program hdisplay and vdisplay on MIPI transcoder. + * This is different from calculated hactive and + * vactive, as they are calculated per channel basis, + * whereas these values should be based on resolution. + */ + I915_WRITE(BXT_MIPI_TRANS_HACTIVE(port), + adjusted_mode->crtc_hdisplay); + I915_WRITE(BXT_MIPI_TRANS_VACTIVE(port), + adjusted_mode->crtc_vdisplay); + I915_WRITE(BXT_MIPI_TRANS_VTOTAL(port), + adjusted_mode->crtc_vtotal); + } + I915_WRITE(MIPI_HACTIVE_AREA_COUNT(port), hactive); I915_WRITE(MIPI_HFP_COUNT(port), hfp); @@ -756,8 +842,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); - struct drm_display_mode *adjusted_mode = - &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; enum port port; unsigned int bpp = intel_crtc->config->pipe_bpp; u32 val, tmp; @@ -765,7 +850,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder) DRM_DEBUG_KMS("pipe %c\n", pipe_name(intel_crtc->pipe)); - mode_hdisplay = adjusted_mode->hdisplay; + mode_hdisplay = adjusted_mode->crtc_hdisplay; if (intel_dsi->dual_link) { mode_hdisplay /= 2; @@ -774,16 +859,39 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder) } for_each_dsi_port(port, intel_dsi->ports) { - /* escape clock divider, 20MHz, shared for A and C. - * device ready must be off when doing this! txclkesc? */ - tmp = I915_READ(MIPI_CTRL(PORT_A)); - tmp &= ~ESCAPE_CLOCK_DIVIDER_MASK; - I915_WRITE(MIPI_CTRL(PORT_A), tmp | ESCAPE_CLOCK_DIVIDER_1); - - /* read request priority is per pipe */ - tmp = I915_READ(MIPI_CTRL(port)); - tmp &= ~READ_REQUEST_PRIORITY_MASK; - I915_WRITE(MIPI_CTRL(port), tmp | READ_REQUEST_PRIORITY_HIGH); + if (IS_VALLEYVIEW(dev)) { + /* + * escape clock divider, 20MHz, shared for A and C. + * device ready must be off when doing this! txclkesc? + */ + tmp = I915_READ(MIPI_CTRL(PORT_A)); + tmp &= ~ESCAPE_CLOCK_DIVIDER_MASK; + I915_WRITE(MIPI_CTRL(PORT_A), tmp | + ESCAPE_CLOCK_DIVIDER_1); + + /* read request priority is per pipe */ + tmp = I915_READ(MIPI_CTRL(port)); + tmp &= ~READ_REQUEST_PRIORITY_MASK; + I915_WRITE(MIPI_CTRL(port), tmp | + READ_REQUEST_PRIORITY_HIGH); + } else if (IS_BROXTON(dev)) { + /* + * FIXME: + * BXT can connect any PIPE to any MIPI port. + * Select the pipe based on the MIPI port read from + * VBT for now. Pick PIPE A for MIPI port A and C + * for port C. + */ + tmp = I915_READ(MIPI_CTRL(port)); + tmp &= ~BXT_PIPE_SELECT_MASK; + + if (port == PORT_A) + tmp |= BXT_PIPE_SELECT_A; + else if (port == PORT_C) + tmp |= BXT_PIPE_SELECT_C; + + I915_WRITE(MIPI_CTRL(port), tmp); + } /* XXX: why here, why like this? handling in irq handler?! */ I915_WRITE(MIPI_INTR_STAT(port), 0xffffffff); @@ -792,7 +900,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder) I915_WRITE(MIPI_DPHY_PARAM(port), intel_dsi->dphy_reg); I915_WRITE(MIPI_DPI_RESOLUTION(port), - adjusted_mode->vdisplay << VERTICAL_ADDRESS_SHIFT | + adjusted_mode->crtc_vdisplay << VERTICAL_ADDRESS_SHIFT | mode_hdisplay << HORIZONTAL_ADDRESS_SHIFT); } @@ -838,15 +946,15 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder) if (is_vid_mode(intel_dsi) && intel_dsi->video_mode_format == VIDEO_MODE_BURST) { I915_WRITE(MIPI_HS_TX_TIMEOUT(port), - txbyteclkhs(adjusted_mode->htotal, bpp, - intel_dsi->lane_count, - intel_dsi->burst_mode_ratio) + 1); + txbyteclkhs(adjusted_mode->crtc_htotal, bpp, + intel_dsi->lane_count, + intel_dsi->burst_mode_ratio) + 1); } else { I915_WRITE(MIPI_HS_TX_TIMEOUT(port), - txbyteclkhs(adjusted_mode->vtotal * - adjusted_mode->htotal, - bpp, intel_dsi->lane_count, - intel_dsi->burst_mode_ratio) + 1); + txbyteclkhs(adjusted_mode->crtc_vtotal * + adjusted_mode->crtc_htotal, + bpp, intel_dsi->lane_count, + intel_dsi->burst_mode_ratio) + 1); } I915_WRITE(MIPI_LP_RX_TIMEOUT(port), intel_dsi->lp_rx_timeout); I915_WRITE(MIPI_TURN_AROUND_TIMEOUT(port), @@ -860,6 +968,17 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder) I915_WRITE(MIPI_INIT_COUNT(port), txclkesc(intel_dsi->escape_clk_div, 100)); + if (IS_BROXTON(dev) && (!intel_dsi->dual_link)) { + /* + * BXT spec says write MIPI_INIT_COUNT for + * both the ports, even if only one is + * getting used. So write the other port + * if not in dual link mode. + */ + I915_WRITE(MIPI_INIT_COUNT(port == + PORT_A ? PORT_C : PORT_A), + intel_dsi->init_count); + } /* recovery disables */ I915_WRITE(MIPI_EOT_DISABLE(port), tmp); @@ -911,8 +1030,8 @@ static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder) DRM_DEBUG_KMS("\n"); intel_dsi_prepare(encoder); + intel_enable_dsi_pll(encoder); - vlv_enable_dsi_pll(encoder); } static enum drm_connector_status diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h index 42a6859..e6cb252 100644 --- a/drivers/gpu/drm/i915/intel_dsi.h +++ b/drivers/gpu/drm/i915/intel_dsi.h @@ -124,9 +124,12 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder) return container_of(encoder, struct intel_dsi, base.base); } -extern void vlv_enable_dsi_pll(struct intel_encoder *encoder); -extern void vlv_disable_dsi_pll(struct intel_encoder *encoder); +extern void intel_enable_dsi_pll(struct intel_encoder *encoder); +extern void intel_disable_dsi_pll(struct intel_encoder *encoder); extern u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp); +extern u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp); +extern void intel_dsi_reset_clocks(struct intel_encoder *encoder, + enum port port); struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id); diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c index c6a8975..cb3cf39 100644 --- a/drivers/gpu/drm/i915/intel_dsi_pll.c +++ b/drivers/gpu/drm/i915/intel_dsi_pll.c @@ -246,7 +246,7 @@ static void vlv_configure_dsi_pll(struct intel_encoder *encoder) vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, dsi_mnp.dsi_pll_ctrl); } -void vlv_enable_dsi_pll(struct intel_encoder *encoder) +static void vlv_enable_dsi_pll(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; u32 tmp; @@ -276,7 +276,7 @@ void vlv_enable_dsi_pll(struct intel_encoder *encoder) DRM_DEBUG_KMS("DSI PLL locked\n"); } -void vlv_disable_dsi_pll(struct intel_encoder *encoder) +static void vlv_disable_dsi_pll(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; u32 tmp; @@ -293,6 +293,26 @@ void vlv_disable_dsi_pll(struct intel_encoder *encoder) mutex_unlock(&dev_priv->sb_lock); } +static void bxt_disable_dsi_pll(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; + u32 val; + + DRM_DEBUG_KMS("\n"); + + val = I915_READ(BXT_DSI_PLL_ENABLE); + val &= ~BXT_DSI_PLL_DO_ENABLE; + I915_WRITE(BXT_DSI_PLL_ENABLE, val); + + /* + * PLL lock should deassert within 200us. + * Wait up to 1ms before timing out. + */ + if (wait_for((I915_READ(BXT_DSI_PLL_ENABLE) + & BXT_DSI_PLL_LOCKED) == 0, 1)) + DRM_ERROR("Timeout waiting for PLL lock deassertion\n"); +} + static void assert_bpp_mismatch(int pixel_format, int pipe_bpp) { int bpp = dsi_pixel_format_bpp(pixel_format); @@ -363,3 +383,222 @@ u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp) return pclk; } + +u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp) +{ + u32 pclk; + u32 dsi_clk; + u32 dsi_ratio; + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; + + /* Divide by zero */ + if (!pipe_bpp) { + DRM_ERROR("Invalid BPP(0)\n"); + return 0; + } + + dsi_ratio = I915_READ(BXT_DSI_PLL_CTL) & + BXT_DSI_PLL_RATIO_MASK; + + /* Invalid DSI ratio ? */ + if (dsi_ratio < BXT_DSI_PLL_RATIO_MIN || + dsi_ratio > BXT_DSI_PLL_RATIO_MAX) { + DRM_ERROR("Invalid DSI pll ratio(%u) programmed\n", dsi_ratio); + return 0; + } + + dsi_clk = (dsi_ratio * BXT_REF_CLOCK_KHZ) / 2; + + /* pixel_format and pipe_bpp should agree */ + assert_bpp_mismatch(intel_dsi->pixel_format, pipe_bpp); + + pclk = DIV_ROUND_CLOSEST(dsi_clk * intel_dsi->lane_count, pipe_bpp); + + DRM_DEBUG_DRIVER("Calculated pclk=%u\n", pclk); + return pclk; +} + +static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port) +{ + u32 temp; + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + + temp = I915_READ(MIPI_CTRL(port)); + temp &= ~ESCAPE_CLOCK_DIVIDER_MASK; + I915_WRITE(MIPI_CTRL(port), temp | + intel_dsi->escape_clk_div << + ESCAPE_CLOCK_DIVIDER_SHIFT); +} + +/* Program BXT Mipi clocks and dividers */ +static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port) +{ + u32 tmp; + u32 divider; + u32 dsi_rate; + u32 pll_ratio; + struct drm_i915_private *dev_priv = dev->dev_private; + + /* Clear old configurations */ + tmp = I915_READ(BXT_MIPI_CLOCK_CTL); + tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port)); + tmp &= ~(BXT_MIPI_RX_ESCLK_FIXDIV_MASK(port)); + tmp &= ~(BXT_MIPI_ESCLK_VAR_DIV_MASK(port)); + tmp &= ~(BXT_MIPI_DPHY_DIVIDER_MASK(port)); + + /* Get the current DSI rate(actual) */ + pll_ratio = I915_READ(BXT_DSI_PLL_CTL) & + BXT_DSI_PLL_RATIO_MASK; + dsi_rate = (BXT_REF_CLOCK_KHZ * pll_ratio) / 2; + + /* Max possible output of clock is 39.5 MHz, program value -1 */ + divider = (dsi_rate / BXT_MAX_VAR_OUTPUT_KHZ) - 1; + tmp |= BXT_MIPI_ESCLK_VAR_DIV(port, divider); + + /* + * Tx escape clock must be as close to 20MHz possible, but should + * not exceed it. Hence select divide by 2 + */ + tmp |= BXT_MIPI_TX_ESCLK_8XDIV_BY2(port); + + tmp |= BXT_MIPI_RX_ESCLK_8X_BY3(port); + + I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp); +} + +static bool bxt_configure_dsi_pll(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u8 dsi_ratio; + u32 dsi_clk; + u32 val; + + dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format, + intel_dsi->lane_count); + + /* + * From clock diagram, to get PLL ratio divider, divide double of DSI + * link rate (i.e., 2*8x=16x frequency value) by ref clock. Make sure to + * round 'up' the result + */ + dsi_ratio = DIV_ROUND_UP(dsi_clk * 2, BXT_REF_CLOCK_KHZ); + if (dsi_ratio < BXT_DSI_PLL_RATIO_MIN || + dsi_ratio > BXT_DSI_PLL_RATIO_MAX) { + DRM_ERROR("Cant get a suitable ratio from DSI PLL ratios\n"); + return false; + } + + /* + * Program DSI ratio and Select MIPIC and MIPIA PLL output as 8x + * Spec says both have to be programmed, even if one is not getting + * used. Configure MIPI_CLOCK_CTL dividers in modeset + */ + val = I915_READ(BXT_DSI_PLL_CTL); + val &= ~BXT_DSI_PLL_PVD_RATIO_MASK; + val &= ~BXT_DSI_FREQ_SEL_MASK; + val &= ~BXT_DSI_PLL_RATIO_MASK; + val |= (dsi_ratio | BXT_DSIA_16X_BY2 | BXT_DSIC_16X_BY2); + + /* As per recommendation from hardware team, + * Prog PVD ratio =1 if dsi ratio <= 50 + */ + if (dsi_ratio <= 50) { + val &= ~BXT_DSI_PLL_PVD_RATIO_MASK; + val |= BXT_DSI_PLL_PVD_RATIO_1; + } + + I915_WRITE(BXT_DSI_PLL_CTL, val); + POSTING_READ(BXT_DSI_PLL_CTL); + + return true; +} + +static void bxt_enable_dsi_pll(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + enum port port; + u32 val; + + DRM_DEBUG_KMS("\n"); + + val = I915_READ(BXT_DSI_PLL_ENABLE); + + if (val & BXT_DSI_PLL_DO_ENABLE) { + WARN(1, "DSI PLL already enabled. Disabling it.\n"); + val &= ~BXT_DSI_PLL_DO_ENABLE; + I915_WRITE(BXT_DSI_PLL_ENABLE, val); + } + + /* Configure PLL vales */ + if (!bxt_configure_dsi_pll(encoder)) { + DRM_ERROR("Configure DSI PLL failed, abort PLL enable\n"); + return; + } + + /* Program TX, RX, Dphy clocks */ + for_each_dsi_port(port, intel_dsi->ports) + bxt_dsi_program_clocks(encoder->base.dev, port); + + /* Enable DSI PLL */ + val = I915_READ(BXT_DSI_PLL_ENABLE); + val |= BXT_DSI_PLL_DO_ENABLE; + I915_WRITE(BXT_DSI_PLL_ENABLE, val); + + /* Timeout and fail if PLL not locked */ + if (wait_for(I915_READ(BXT_DSI_PLL_ENABLE) & BXT_DSI_PLL_LOCKED, 1)) { + DRM_ERROR("Timed out waiting for DSI PLL to lock\n"); + return; + } + + DRM_DEBUG_KMS("DSI PLL locked\n"); +} + +void intel_enable_dsi_pll(struct intel_encoder *encoder) +{ + struct drm_device *dev = encoder->base.dev; + + if (IS_VALLEYVIEW(dev)) + vlv_enable_dsi_pll(encoder); + else if (IS_BROXTON(dev)) + bxt_enable_dsi_pll(encoder); +} + +void intel_disable_dsi_pll(struct intel_encoder *encoder) +{ + struct drm_device *dev = encoder->base.dev; + + if (IS_VALLEYVIEW(dev)) + vlv_disable_dsi_pll(encoder); + else if (IS_BROXTON(dev)) + bxt_disable_dsi_pll(encoder); +} + +static void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port) +{ + u32 tmp; + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + /* Clear old configurations */ + tmp = I915_READ(BXT_MIPI_CLOCK_CTL); + tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port)); + tmp &= ~(BXT_MIPI_RX_ESCLK_FIXDIV_MASK(port)); + tmp &= ~(BXT_MIPI_ESCLK_VAR_DIV_MASK(port)); + tmp &= ~(BXT_MIPI_DPHY_DIVIDER_MASK(port)); + I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp); + I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP); +} + +void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port) +{ + struct drm_device *dev = encoder->base.dev; + + if (IS_BROXTON(dev)) + bxt_dsi_reset_clocks(encoder, port); + else if (IS_VALLEYVIEW(dev)) + vlv_dsi_reset_clocks(encoder, port); +} diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index dc532bb..8492053 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -97,7 +97,8 @@ struct intel_dvo { struct intel_dvo_device dev; - struct drm_display_mode *panel_fixed_mode; + struct intel_connector *attached_connector; + bool panel_wants_dither; }; @@ -201,19 +202,28 @@ intel_dvo_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct intel_dvo *intel_dvo = intel_attached_dvo(connector); + const struct drm_display_mode *fixed_mode = + to_intel_connector(connector)->panel.fixed_mode; + int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + int target_clock = mode->clock; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; /* XXX: Validate clock range */ - if (intel_dvo->panel_fixed_mode) { - if (mode->hdisplay > intel_dvo->panel_fixed_mode->hdisplay) + if (fixed_mode) { + if (mode->hdisplay > fixed_mode->hdisplay) return MODE_PANEL; - if (mode->vdisplay > intel_dvo->panel_fixed_mode->vdisplay) + if (mode->vdisplay > fixed_mode->vdisplay) return MODE_PANEL; + + target_clock = fixed_mode->clock; } + if (target_clock > max_dotclk) + return MODE_CLOCK_HIGH; + return intel_dvo->dev.dev_ops->mode_valid(&intel_dvo->dev, mode); } @@ -221,6 +231,8 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { struct intel_dvo *intel_dvo = enc_to_dvo(encoder); + const struct drm_display_mode *fixed_mode = + intel_dvo->attached_connector->panel.fixed_mode; struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; /* If we have timings from the BIOS for the panel, put them in @@ -228,21 +240,8 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder, * with the panel scaling set up to source from the H/VDisplay * of the original mode. */ - if (intel_dvo->panel_fixed_mode != NULL) { -#define C(x) adjusted_mode->x = intel_dvo->panel_fixed_mode->x - C(hdisplay); - C(hsync_start); - C(hsync_end); - C(htotal); - C(vdisplay); - C(vsync_start); - C(vsync_end); - C(vtotal); - C(clock); -#undef C - - drm_mode_set_crtcinfo(adjusted_mode, 0); - } + if (fixed_mode) + intel_fixed_panel_mode(fixed_mode, adjusted_mode); return true; } @@ -252,7 +251,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder) struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; struct intel_dvo *intel_dvo = enc_to_dvo(encoder); int pipe = crtc->pipe; u32 dvo_val; @@ -286,11 +285,11 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder) dvo_val |= DVO_VSYNC_ACTIVE_HIGH; /*I915_WRITE(DVOB_SRCDIM, - (adjusted_mode->hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) | - (adjusted_mode->VDisplay << DVO_SRCDIM_VERTICAL_SHIFT));*/ + (adjusted_mode->crtc_hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) | + (adjusted_mode->crtc_vdisplay << DVO_SRCDIM_VERTICAL_SHIFT));*/ I915_WRITE(dvo_srcdim_reg, - (adjusted_mode->hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) | - (adjusted_mode->vdisplay << DVO_SRCDIM_VERTICAL_SHIFT)); + (adjusted_mode->crtc_hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) | + (adjusted_mode->crtc_vdisplay << DVO_SRCDIM_VERTICAL_SHIFT)); /*I915_WRITE(DVOB, dvo_val);*/ I915_WRITE(dvo_reg, dvo_val); } @@ -311,8 +310,9 @@ intel_dvo_detect(struct drm_connector *connector, bool force) static int intel_dvo_get_modes(struct drm_connector *connector) { - struct intel_dvo *intel_dvo = intel_attached_dvo(connector); struct drm_i915_private *dev_priv = connector->dev->dev_private; + const struct drm_display_mode *fixed_mode = + to_intel_connector(connector)->panel.fixed_mode; /* We should probably have an i2c driver get_modes function for those * devices which will have a fixed set of modes determined by the chip @@ -324,9 +324,9 @@ static int intel_dvo_get_modes(struct drm_connector *connector) if (!list_empty(&connector->probed_modes)) return 1; - if (intel_dvo->panel_fixed_mode != NULL) { + if (fixed_mode) { struct drm_display_mode *mode; - mode = drm_mode_duplicate(connector->dev, intel_dvo->panel_fixed_mode); + mode = drm_mode_duplicate(connector->dev, fixed_mode); if (mode) { drm_mode_probed_add(connector, mode); return 1; @@ -339,6 +339,7 @@ static int intel_dvo_get_modes(struct drm_connector *connector) static void intel_dvo_destroy(struct drm_connector *connector) { drm_connector_cleanup(connector); + intel_panel_fini(&to_intel_connector(connector)->panel); kfree(connector); } @@ -365,8 +366,6 @@ static void intel_dvo_enc_destroy(struct drm_encoder *encoder) if (intel_dvo->dev.dev_ops->destroy) intel_dvo->dev.dev_ops->destroy(&intel_dvo->dev); - kfree(intel_dvo->panel_fixed_mode); - intel_encoder_destroy(encoder); } @@ -431,6 +430,8 @@ void intel_dvo_init(struct drm_device *dev) return; } + intel_dvo->attached_connector = intel_connector; + intel_encoder = &intel_dvo->base; drm_encoder_init(dev, &intel_encoder->base, &intel_dvo_enc_funcs, encoder_type); @@ -535,8 +536,9 @@ void intel_dvo_init(struct drm_device *dev) * headers, likely), so for now, just get the current * mode being output through DVO. */ - intel_dvo->panel_fixed_mode = - intel_dvo_get_current_mode(connector); + intel_panel_init(&intel_connector->panel, + intel_dvo_get_current_mode(connector), + NULL); intel_dvo->panel_wants_dither = true; } diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 1f97fb5..cf47352 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -41,6 +41,24 @@ #include "intel_drv.h" #include "i915_drv.h" +static inline bool fbc_supported(struct drm_i915_private *dev_priv) +{ + return dev_priv->fbc.enable_fbc != NULL; +} + +/* + * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the + * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's + * origin so the x and y offsets can actually fit the registers. As a + * consequence, the fence doesn't really start exactly at the display plane + * address we program because it starts at the real start of the buffer, so we + * have to take this into consideration here. + */ +static unsigned int get_crtc_fence_y_offset(struct intel_crtc *crtc) +{ + return crtc->base.y - crtc->adjusted_y; +} + static void i8xx_fbc_disable(struct drm_i915_private *dev_priv) { u32 fbc_ctl; @@ -88,7 +106,7 @@ static void i8xx_fbc_enable(struct intel_crtc *crtc) /* Clear old tags */ for (i = 0; i < (FBC_LL_SIZE / 32) + 1; i++) - I915_WRITE(FBC_TAG + (i * 4), 0); + I915_WRITE(FBC_TAG(i), 0); if (IS_GEN4(dev_priv)) { u32 fbc_ctl2; @@ -97,7 +115,7 @@ static void i8xx_fbc_enable(struct intel_crtc *crtc) fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE; fbc_ctl2 |= FBC_CTL_PLANE(crtc->plane); I915_WRITE(FBC_CONTROL2, fbc_ctl2); - I915_WRITE(FBC_FENCE_OFF, crtc->base.y); + I915_WRITE(FBC_FENCE_OFF, get_crtc_fence_y_offset(crtc)); } /* enable it... */ @@ -135,7 +153,7 @@ static void g4x_fbc_enable(struct intel_crtc *crtc) dpfc_ctl |= DPFC_CTL_LIMIT_1X; dpfc_ctl |= DPFC_CTL_FENCE_EN | obj->fence_reg; - I915_WRITE(DPFC_FENCE_YOFF, crtc->base.y); + I915_WRITE(DPFC_FENCE_YOFF, get_crtc_fence_y_offset(crtc)); /* enable it... */ I915_WRITE(DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); @@ -177,6 +195,7 @@ static void ilk_fbc_enable(struct intel_crtc *crtc) struct drm_i915_gem_object *obj = intel_fb_obj(fb); u32 dpfc_ctl; int threshold = dev_priv->fbc.threshold; + unsigned int y_offset; dev_priv->fbc.enabled = true; @@ -200,7 +219,8 @@ static void ilk_fbc_enable(struct intel_crtc *crtc) if (IS_GEN5(dev_priv)) dpfc_ctl |= obj->fence_reg; - I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->base.y); + y_offset = get_crtc_fence_y_offset(crtc); + I915_WRITE(ILK_DPFC_FENCE_YOFF, y_offset); I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID); /* enable it... */ I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); @@ -208,7 +228,7 @@ static void ilk_fbc_enable(struct intel_crtc *crtc) if (IS_GEN6(dev_priv)) { I915_WRITE(SNB_DPFC_CTL_SA, SNB_CPU_FENCE_ENABLE | obj->fence_reg); - I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->base.y); + I915_WRITE(DPFC_CPU_FENCE_OFFSET, y_offset); } intel_fbc_nuke(dev_priv); @@ -272,23 +292,23 @@ static void gen7_fbc_enable(struct intel_crtc *crtc) if (dev_priv->fbc.false_color) dpfc_ctl |= FBC_CTL_FALSE_COLOR; - I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); - if (IS_IVYBRIDGE(dev_priv)) { /* WaFbcAsynchFlipDisableFbcQueue:ivb */ I915_WRITE(ILK_DISPLAY_CHICKEN1, I915_READ(ILK_DISPLAY_CHICKEN1) | ILK_FBCQ_DIS); - } else { + } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */ I915_WRITE(CHICKEN_PIPESL_1(crtc->pipe), I915_READ(CHICKEN_PIPESL_1(crtc->pipe)) | HSW_FBCQ_DIS); } + I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); + I915_WRITE(SNB_DPFC_CTL_SA, SNB_CPU_FENCE_ENABLE | obj->fence_reg); - I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->base.y); + I915_WRITE(DPFC_CPU_FENCE_OFFSET, get_crtc_fence_y_offset(crtc)); intel_fbc_nuke(dev_priv); @@ -308,6 +328,18 @@ bool intel_fbc_enabled(struct drm_i915_private *dev_priv) return dev_priv->fbc.enabled; } +static void intel_fbc_enable(struct intel_crtc *crtc, + const struct drm_framebuffer *fb) +{ + struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + + dev_priv->fbc.enable_fbc(crtc); + + dev_priv->fbc.crtc = crtc; + dev_priv->fbc.fb_id = fb->base.id; + dev_priv->fbc.y = crtc->base.y; +} + static void intel_fbc_work_fn(struct work_struct *__work) { struct intel_fbc_work *work = @@ -321,13 +353,8 @@ static void intel_fbc_work_fn(struct work_struct *__work) /* Double check that we haven't switched fb without cancelling * the prior work. */ - if (crtc_fb == work->fb) { - dev_priv->fbc.enable_fbc(work->crtc); - - dev_priv->fbc.crtc = work->crtc; - dev_priv->fbc.fb_id = crtc_fb->base.id; - dev_priv->fbc.y = work->crtc->base.y; - } + if (crtc_fb == work->fb) + intel_fbc_enable(work->crtc, work->fb); dev_priv->fbc.fbc_work = NULL; } @@ -361,7 +388,7 @@ static void intel_fbc_cancel_work(struct drm_i915_private *dev_priv) dev_priv->fbc.fbc_work = NULL; } -static void intel_fbc_enable(struct intel_crtc *crtc) +static void intel_fbc_schedule_enable(struct intel_crtc *crtc) { struct intel_fbc_work *work; struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; @@ -373,7 +400,7 @@ static void intel_fbc_enable(struct intel_crtc *crtc) work = kzalloc(sizeof(*work), GFP_KERNEL); if (work == NULL) { DRM_ERROR("Failed to allocate FBC work structure\n"); - dev_priv->fbc.enable_fbc(crtc); + intel_fbc_enable(crtc, crtc->base.primary->fb); return; } @@ -417,7 +444,7 @@ static void __intel_fbc_disable(struct drm_i915_private *dev_priv) */ void intel_fbc_disable(struct drm_i915_private *dev_priv) { - if (!dev_priv->fbc.enable_fbc) + if (!fbc_supported(dev_priv)) return; mutex_lock(&dev_priv->fbc.lock); @@ -435,7 +462,7 @@ void intel_fbc_disable_crtc(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; - if (!dev_priv->fbc.enable_fbc) + if (!fbc_supported(dev_priv)) return; mutex_lock(&dev_priv->fbc.lock); @@ -473,6 +500,12 @@ const char *intel_no_fbc_reason_str(enum no_fbc_reason reason) return "rotation unsupported"; case FBC_IN_DBG_MASTER: return "Kernel debugger is active"; + case FBC_BAD_STRIDE: + return "framebuffer stride not supported"; + case FBC_PIXEL_RATE: + return "pixel rate is too big"; + case FBC_PIXEL_FORMAT: + return "pixel format is invalid"; default: MISSING_CASE(reason); return "unknown reason"; @@ -542,6 +575,16 @@ static int find_compression_threshold(struct drm_i915_private *dev_priv, { int compression_threshold = 1; int ret; + u64 end; + + /* The FBC hardware for BDW/SKL doesn't have access to the stolen + * reserved range size, so it always assumes the maximum (8mb) is used. + * If we enable FBC using a CFB on that memory range we'll get FIFO + * underruns, even if that range is not reserved by the BIOS. */ + if (IS_BROADWELL(dev_priv) || IS_SKYLAKE(dev_priv)) + end = dev_priv->gtt.stolen_size - 8 * 1024 * 1024; + else + end = dev_priv->gtt.stolen_usable_size; /* HACK: This code depends on what we will do in *_enable_fbc. If that * code changes, this code needs to change as well. @@ -551,7 +594,8 @@ static int find_compression_threshold(struct drm_i915_private *dev_priv, */ /* Try to over-allocate to reduce reallocations and fragmentation. */ - ret = i915_gem_stolen_insert_node(dev_priv, node, size <<= 1, 4096); + ret = i915_gem_stolen_insert_node_in_range(dev_priv, node, size <<= 1, + 4096, 0, end); if (ret == 0) return compression_threshold; @@ -561,7 +605,8 @@ again: (fb_cpp == 2 && compression_threshold == 2)) return 0; - ret = i915_gem_stolen_insert_node(dev_priv, node, size >>= 1, 4096); + ret = i915_gem_stolen_insert_node_in_range(dev_priv, node, size >>= 1, + 4096, 0, end); if (ret && INTEL_INFO(dev_priv)->gen <= 4) { return 0; } else if (ret) { @@ -613,8 +658,9 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, int size, dev_priv->fbc.uncompressed_size = size; - DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n", - size); + DRM_DEBUG_KMS("reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n", + dev_priv->fbc.compressed_fb.size, + dev_priv->fbc.threshold); return 0; @@ -644,7 +690,7 @@ static void __intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv) void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv) { - if (!dev_priv->fbc.enable_fbc) + if (!fbc_supported(dev_priv)) return; mutex_lock(&dev_priv->fbc.lock); @@ -652,16 +698,134 @@ void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv) mutex_unlock(&dev_priv->fbc.lock); } -static int intel_fbc_setup_cfb(struct drm_i915_private *dev_priv, int size, - int fb_cpp) +/* + * For SKL+, the plane source size used by the hardware is based on the value we + * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value + * we wrote to PIPESRC. + */ +static void intel_fbc_get_plane_source_size(struct intel_crtc *crtc, + int *width, int *height) { + struct intel_plane_state *plane_state = + to_intel_plane_state(crtc->base.primary->state); + int w, h; + + if (intel_rotation_90_or_270(plane_state->base.rotation)) { + w = drm_rect_height(&plane_state->src) >> 16; + h = drm_rect_width(&plane_state->src) >> 16; + } else { + w = drm_rect_width(&plane_state->src) >> 16; + h = drm_rect_height(&plane_state->src) >> 16; + } + + if (width) + *width = w; + if (height) + *height = h; +} + +static int intel_fbc_calculate_cfb_size(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + struct drm_framebuffer *fb = crtc->base.primary->fb; + int lines; + + intel_fbc_get_plane_source_size(crtc, NULL, &lines); + if (INTEL_INFO(dev_priv)->gen >= 7) + lines = min(lines, 2048); + + return lines * fb->pitches[0]; +} + +static int intel_fbc_setup_cfb(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + struct drm_framebuffer *fb = crtc->base.primary->fb; + int size, cpp; + + size = intel_fbc_calculate_cfb_size(crtc); + cpp = drm_format_plane_cpp(fb->pixel_format, 0); + if (size <= dev_priv->fbc.uncompressed_size) return 0; /* Release any current block */ __intel_fbc_cleanup_cfb(dev_priv); - return intel_fbc_alloc_cfb(dev_priv, size, fb_cpp); + return intel_fbc_alloc_cfb(dev_priv, size, cpp); +} + +static bool stride_is_valid(struct drm_i915_private *dev_priv, + unsigned int stride) +{ + /* These should have been caught earlier. */ + WARN_ON(stride < 512); + WARN_ON((stride & (64 - 1)) != 0); + + /* Below are the additional FBC restrictions. */ + + if (IS_GEN2(dev_priv) || IS_GEN3(dev_priv)) + return stride == 4096 || stride == 8192; + + if (IS_GEN4(dev_priv) && !IS_G4X(dev_priv) && stride < 2048) + return false; + + if (stride > 16384) + return false; + + return true; +} + +static bool pixel_format_is_valid(struct drm_framebuffer *fb) +{ + struct drm_device *dev = fb->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + switch (fb->pixel_format) { + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_XBGR8888: + return true; + case DRM_FORMAT_XRGB1555: + case DRM_FORMAT_RGB565: + /* 16bpp not supported on gen2 */ + if (IS_GEN2(dev)) + return false; + /* WaFbcOnly1to1Ratio:ctg */ + if (IS_G4X(dev_priv)) + return false; + return true; + default: + return false; + } +} + +/* + * For some reason, the hardware tracking starts looking at whatever we + * programmed as the display plane base address register. It does not look at + * the X and Y offset registers. That's why we look at the crtc->adjusted{x,y} + * variables instead of just looking at the pipe/plane size. + */ +static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + unsigned int effective_w, effective_h, max_w, max_h; + + if (INTEL_INFO(dev_priv)->gen >= 8 || IS_HASWELL(dev_priv)) { + max_w = 4096; + max_h = 4096; + } else if (IS_G4X(dev_priv) || INTEL_INFO(dev_priv)->gen >= 5) { + max_w = 4096; + max_h = 2048; + } else { + max_w = 2048; + max_h = 1536; + } + + intel_fbc_get_plane_source_size(crtc, &effective_w, &effective_h); + effective_w += crtc->adjusted_x; + effective_h += crtc->adjusted_y; + + return effective_w <= max_w && effective_h <= max_h; } /** @@ -690,7 +854,6 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv) struct drm_framebuffer *fb; struct drm_i915_gem_object *obj; const struct drm_display_mode *adjusted_mode; - unsigned int max_width, max_height; WARN_ON(!mutex_is_locked(&dev_priv->fbc.lock)); @@ -739,21 +902,11 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv) goto out_disable; } - if (INTEL_INFO(dev_priv)->gen >= 8 || IS_HASWELL(dev_priv)) { - max_width = 4096; - max_height = 4096; - } else if (IS_G4X(dev_priv) || INTEL_INFO(dev_priv)->gen >= 5) { - max_width = 4096; - max_height = 2048; - } else { - max_width = 2048; - max_height = 1536; - } - if (intel_crtc->config->pipe_src_w > max_width || - intel_crtc->config->pipe_src_h > max_height) { + if (!intel_fbc_hw_tracking_covers_screen(intel_crtc)) { set_no_fbc_reason(dev_priv, FBC_MODE_TOO_LARGE); goto out_disable; } + if ((INTEL_INFO(dev_priv)->gen < 4 || HAS_DDI(dev_priv)) && intel_crtc->plane != PLANE_A) { set_no_fbc_reason(dev_priv, FBC_BAD_PLANE); @@ -774,14 +927,31 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv) goto out_disable; } + if (!stride_is_valid(dev_priv, fb->pitches[0])) { + set_no_fbc_reason(dev_priv, FBC_BAD_STRIDE); + goto out_disable; + } + + if (!pixel_format_is_valid(fb)) { + set_no_fbc_reason(dev_priv, FBC_PIXEL_FORMAT); + goto out_disable; + } + /* If the kernel debugger is active, always disable compression */ if (in_dbg_master()) { set_no_fbc_reason(dev_priv, FBC_IN_DBG_MASTER); goto out_disable; } - if (intel_fbc_setup_cfb(dev_priv, obj->base.size, - drm_format_plane_cpp(fb->pixel_format, 0))) { + /* WaFbcExceedCdClockThreshold:hsw,bdw */ + if ((IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) && + ilk_pipe_pixel_rate(intel_crtc->config) >= + dev_priv->cdclk_freq * 95 / 100) { + set_no_fbc_reason(dev_priv, FBC_PIXEL_RATE); + goto out_disable; + } + + if (intel_fbc_setup_cfb(intel_crtc)) { set_no_fbc_reason(dev_priv, FBC_STOLEN_TOO_SMALL); goto out_disable; } @@ -824,7 +994,7 @@ static void __intel_fbc_update(struct drm_i915_private *dev_priv) __intel_fbc_disable(dev_priv); } - intel_fbc_enable(intel_crtc); + intel_fbc_schedule_enable(intel_crtc); dev_priv->fbc.no_fbc_reason = FBC_OK; return; @@ -845,7 +1015,7 @@ out_disable: */ void intel_fbc_update(struct drm_i915_private *dev_priv) { - if (!dev_priv->fbc.enable_fbc) + if (!fbc_supported(dev_priv)) return; mutex_lock(&dev_priv->fbc.lock); @@ -859,7 +1029,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv, { unsigned int fbc_bits; - if (!dev_priv->fbc.enable_fbc) + if (!fbc_supported(dev_priv)) return; if (origin == ORIGIN_GTT) @@ -886,7 +1056,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv, void intel_fbc_flush(struct drm_i915_private *dev_priv, unsigned int frontbuffer_bits, enum fb_op_origin origin) { - if (!dev_priv->fbc.enable_fbc) + if (!fbc_supported(dev_priv)) return; if (origin == ORIGIN_GTT) diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index ab2b856..4fd5fdf 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -121,8 +121,9 @@ static int intelfb_alloc(struct drm_fb_helper *helper, container_of(helper, struct intel_fbdev, helper); struct drm_framebuffer *fb; struct drm_device *dev = helper->dev; + struct drm_i915_private *dev_priv = to_i915(dev); struct drm_mode_fb_cmd2 mode_cmd = {}; - struct drm_i915_gem_object *obj; + struct drm_i915_gem_object *obj = NULL; int size, ret; /* we don't do packed 24bpp */ @@ -139,7 +140,12 @@ static int intelfb_alloc(struct drm_fb_helper *helper, size = mode_cmd.pitches[0] * mode_cmd.height; size = PAGE_ALIGN(size); - obj = i915_gem_object_create_stolen(dev, size); + + /* If the FB is too big, just don't use it since fbdev is not very + * important and we should probably use that space with FBC or other + * features. */ + if (size * 2 < dev_priv->gtt.stolen_usable_size) + obj = i915_gem_object_create_stolen(dev, size); if (obj == NULL) obj = i915_gem_alloc_object(dev, size); if (!obj) { @@ -263,7 +269,7 @@ static int intelfb_create(struct drm_fb_helper *helper, /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */ - DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n", + DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08llx, bo %p\n", fb->width, fb->height, i915_gem_obj_ggtt_offset(obj), obj); @@ -541,16 +547,13 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, struct intel_crtc *intel_crtc; unsigned int max_size = 0; - if (!i915.fastboot) - return false; - /* Find the largest fb */ for_each_crtc(dev, crtc) { struct drm_i915_gem_object *obj = intel_fb_obj(crtc->primary->state->fb); intel_crtc = to_intel_crtc(crtc); - if (!intel_crtc->active || !obj) { + if (!crtc->state->active || !obj) { DRM_DEBUG_KMS("pipe %c not active or no fb, skipping\n", pipe_name(intel_crtc->pipe)); continue; @@ -575,7 +578,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, intel_crtc = to_intel_crtc(crtc); - if (!intel_crtc->active) { + if (!crtc->state->active) { DRM_DEBUG_KMS("pipe %c not active, skipping\n", pipe_name(intel_crtc->pipe)); continue; @@ -638,7 +641,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, for_each_crtc(dev, crtc) { intel_crtc = to_intel_crtc(crtc); - if (!intel_crtc->active) + if (!crtc->state->active) continue; WARN(!crtc->primary->fb, diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h new file mode 100644 index 0000000..081d5f6 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_guc.h @@ -0,0 +1,124 @@ +/* + * Copyright © 2014 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ +#ifndef _INTEL_GUC_H_ +#define _INTEL_GUC_H_ + +#include "intel_guc_fwif.h" +#include "i915_guc_reg.h" + +struct i915_guc_client { + struct drm_i915_gem_object *client_obj; + struct intel_context *owner; + struct intel_guc *guc; + uint32_t priority; + uint32_t ctx_index; + + uint32_t proc_desc_offset; + uint32_t doorbell_offset; + uint32_t cookie; + uint16_t doorbell_id; + uint16_t padding; /* Maintain alignment */ + + uint32_t wq_offset; + uint32_t wq_size; + + spinlock_t wq_lock; /* Protects all data below */ + uint32_t wq_tail; + + /* GuC submission statistics & status */ + uint64_t submissions[I915_NUM_RINGS]; + uint32_t q_fail; + uint32_t b_fail; + int retcode; +}; + +enum intel_guc_fw_status { + GUC_FIRMWARE_FAIL = -1, + GUC_FIRMWARE_NONE = 0, + GUC_FIRMWARE_PENDING, + GUC_FIRMWARE_SUCCESS +}; + +/* + * This structure encapsulates all the data needed during the process + * of fetching, caching, and loading the firmware image into the GuC. + */ +struct intel_guc_fw { + struct drm_device * guc_dev; + const char * guc_fw_path; + size_t guc_fw_size; + struct drm_i915_gem_object * guc_fw_obj; + enum intel_guc_fw_status guc_fw_fetch_status; + enum intel_guc_fw_status guc_fw_load_status; + + uint16_t guc_fw_major_wanted; + uint16_t guc_fw_minor_wanted; + uint16_t guc_fw_major_found; + uint16_t guc_fw_minor_found; +}; + +struct intel_guc { + struct intel_guc_fw guc_fw; + + uint32_t log_flags; + struct drm_i915_gem_object *log_obj; + + struct drm_i915_gem_object *ctx_pool_obj; + struct ida ctx_ids; + + struct i915_guc_client *execbuf_client; + + spinlock_t host2guc_lock; /* Protects all data below */ + + DECLARE_BITMAP(doorbell_bitmap, GUC_MAX_DOORBELLS); + uint32_t db_cacheline; /* Cyclic counter mod pagesize */ + + /* Action status & statistics */ + uint64_t action_count; /* Total commands issued */ + uint32_t action_cmd; /* Last command word */ + uint32_t action_status; /* Last return status */ + uint32_t action_fail; /* Total number of failures */ + int32_t action_err; /* Last error code */ + + uint64_t submissions[I915_NUM_RINGS]; + uint32_t last_seqno[I915_NUM_RINGS]; +}; + +/* intel_guc_loader.c */ +extern void intel_guc_ucode_init(struct drm_device *dev); +extern int intel_guc_ucode_load(struct drm_device *dev); +extern void intel_guc_ucode_fini(struct drm_device *dev); +extern const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status); +extern int intel_guc_suspend(struct drm_device *dev); +extern int intel_guc_resume(struct drm_device *dev); + +/* i915_guc_submission.c */ +int i915_guc_submission_init(struct drm_device *dev); +int i915_guc_submission_enable(struct drm_device *dev); +int i915_guc_submit(struct i915_guc_client *client, + struct drm_i915_gem_request *rq); +void i915_guc_submission_disable(struct drm_device *dev); +void i915_guc_submission_fini(struct drm_device *dev); + +#endif diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h index 18d7f20..593d2f5 100644 --- a/drivers/gpu/drm/i915/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/intel_guc_fwif.h @@ -32,17 +32,16 @@ * EDITING THIS FILE IS THEREFORE NOT RECOMMENDED - YOUR CHANGES MAY BE LOST. */ -#define GFXCORE_FAMILY_GEN8 11 #define GFXCORE_FAMILY_GEN9 12 -#define GFXCORE_FAMILY_FORCE_ULONG 0x7fffffff +#define GFXCORE_FAMILY_UNKNOWN 0x7fffffff -#define GUC_CTX_PRIORITY_CRITICAL 0 +#define GUC_CTX_PRIORITY_KMD_HIGH 0 #define GUC_CTX_PRIORITY_HIGH 1 -#define GUC_CTX_PRIORITY_NORMAL 2 -#define GUC_CTX_PRIORITY_LOW 3 +#define GUC_CTX_PRIORITY_KMD_NORMAL 2 +#define GUC_CTX_PRIORITY_NORMAL 3 #define GUC_MAX_GPU_CONTEXTS 1024 -#define GUC_INVALID_CTX_ID (GUC_MAX_GPU_CONTEXTS + 1) +#define GUC_INVALID_CTX_ID GUC_MAX_GPU_CONTEXTS /* Work queue item header definitions */ #define WQ_STATUS_ACTIVE 1 @@ -76,6 +75,7 @@ #define GUC_CTX_DESC_ATTR_RESET (1 << 4) #define GUC_CTX_DESC_ATTR_WQLOCKED (1 << 5) #define GUC_CTX_DESC_ATTR_PCH (1 << 6) +#define GUC_CTX_DESC_ATTR_TERMINATED (1 << 7) /* The guc control data is 10 DWORDs */ #define GUC_CTL_CTXINFO 0 @@ -108,6 +108,7 @@ #define GUC_CTL_DISABLE_SCHEDULER (1 << 4) #define GUC_CTL_PREEMPTION_LOG (1 << 5) #define GUC_CTL_ENABLE_SLPC (1 << 7) +#define GUC_CTL_RESET_ON_PREMPT_FAILURE (1 << 8) #define GUC_CTL_DEBUG 8 #define GUC_LOG_VERBOSITY_SHIFT 0 #define GUC_LOG_VERBOSITY_LOW (0 << GUC_LOG_VERBOSITY_SHIFT) @@ -117,8 +118,9 @@ /* Verbosity range-check limits, without the shift */ #define GUC_LOG_VERBOSITY_MIN 0 #define GUC_LOG_VERBOSITY_MAX 3 +#define GUC_CTL_RSRVD 9 -#define GUC_CTL_MAX_DWORDS (GUC_CTL_DEBUG + 1) +#define GUC_CTL_MAX_DWORDS (GUC_CTL_RSRVD + 1) struct guc_doorbell_info { u32 db_status; @@ -208,18 +210,31 @@ struct guc_context_desc { u32 engine_presence; - u32 reserved0[1]; + u8 engine_suspended; + + u8 reserved0[3]; u64 reserved1[1]; u64 desc_private; } __packed; +#define GUC_FORCEWAKE_RENDER (1 << 0) +#define GUC_FORCEWAKE_MEDIA (1 << 1) + +#define GUC_POWER_UNSPECIFIED 0 +#define GUC_POWER_D0 1 +#define GUC_POWER_D1 2 +#define GUC_POWER_D2 3 +#define GUC_POWER_D3 4 + /* This Action will be programmed in C180 - SOFT_SCRATCH_O_REG */ enum host2guc_action { HOST2GUC_ACTION_DEFAULT = 0x0, HOST2GUC_ACTION_SAMPLE_FORCEWAKE = 0x6, HOST2GUC_ACTION_ALLOCATE_DOORBELL = 0x10, HOST2GUC_ACTION_DEALLOCATE_DOORBELL = 0x20, + HOST2GUC_ACTION_ENTER_S_STATE = 0x501, + HOST2GUC_ACTION_EXIT_S_STATE = 0x502, HOST2GUC_ACTION_SLPC_REQUEST = 0x3003, HOST2GUC_ACTION_LIMIT }; diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c new file mode 100644 index 0000000..a17b6a5 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_guc_loader.c @@ -0,0 +1,606 @@ +/* + * Copyright © 2014 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + * Authors: + * Vinit Azad <vinit.azad@intel.com> + * Ben Widawsky <ben@bwidawsk.net> + * Dave Gordon <david.s.gordon@intel.com> + * Alex Dai <yu.dai@intel.com> + */ +#include <linux/firmware.h> +#include "i915_drv.h" +#include "intel_guc.h" + +/** + * DOC: GuC + * + * intel_guc: + * Top level structure of guc. It handles firmware loading and manages client + * pool and doorbells. intel_guc owns a i915_guc_client to replace the legacy + * ExecList submission. + * + * Firmware versioning: + * The firmware build process will generate a version header file with major and + * minor version defined. The versions are built into CSS header of firmware. + * i915 kernel driver set the minimal firmware version required per platform. + * The firmware installation package will install (symbolic link) proper version + * of firmware. + * + * GuC address space: + * GuC does not allow any gfx GGTT address that falls into range [0, WOPCM_TOP), + * which is reserved for Boot ROM, SRAM and WOPCM. Currently this top address is + * 512K. In order to exclude 0-512K address space from GGTT, all gfx objects + * used by GuC is pinned with PIN_OFFSET_BIAS along with size of WOPCM. + * + * Firmware log: + * Firmware log is enabled by setting i915.guc_log_level to non-negative level. + * Log data is printed out via reading debugfs i915_guc_log_dump. Reading from + * i915_guc_load_status will print out firmware loading status and scratch + * registers value. + * + */ + +#define I915_SKL_GUC_UCODE "i915/skl_guc_ver4.bin" +MODULE_FIRMWARE(I915_SKL_GUC_UCODE); + +/* User-friendly representation of an enum */ +const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status) +{ + switch (status) { + case GUC_FIRMWARE_FAIL: + return "FAIL"; + case GUC_FIRMWARE_NONE: + return "NONE"; + case GUC_FIRMWARE_PENDING: + return "PENDING"; + case GUC_FIRMWARE_SUCCESS: + return "SUCCESS"; + default: + return "UNKNOWN!"; + } +}; + +static void direct_interrupts_to_host(struct drm_i915_private *dev_priv) +{ + struct intel_engine_cs *ring; + int i, irqs; + + /* tell all command streamers NOT to forward interrupts and vblank to GuC */ + irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER); + irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING); + for_each_ring(ring, dev_priv, i) + I915_WRITE(RING_MODE_GEN7(ring), irqs); + + /* route all GT interrupts to the host */ + I915_WRITE(GUC_BCS_RCS_IER, 0); + I915_WRITE(GUC_VCS2_VCS1_IER, 0); + I915_WRITE(GUC_WD_VECS_IER, 0); +} + +static void direct_interrupts_to_guc(struct drm_i915_private *dev_priv) +{ + struct intel_engine_cs *ring; + int i, irqs; + + /* tell all command streamers to forward interrupts and vblank to GuC */ + irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_ALWAYS); + irqs |= _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING); + for_each_ring(ring, dev_priv, i) + I915_WRITE(RING_MODE_GEN7(ring), irqs); + + /* route USER_INTERRUPT to Host, all others are sent to GuC. */ + irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT | + GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT; + /* These three registers have the same bit definitions */ + I915_WRITE(GUC_BCS_RCS_IER, ~irqs); + I915_WRITE(GUC_VCS2_VCS1_IER, ~irqs); + I915_WRITE(GUC_WD_VECS_IER, ~irqs); +} + +static u32 get_gttype(struct drm_i915_private *dev_priv) +{ + /* XXX: GT type based on PCI device ID? field seems unused by fw */ + return 0; +} + +static u32 get_core_family(struct drm_i915_private *dev_priv) +{ + switch (INTEL_INFO(dev_priv)->gen) { + case 9: + return GFXCORE_FAMILY_GEN9; + + default: + DRM_ERROR("GUC: unsupported core family\n"); + return GFXCORE_FAMILY_UNKNOWN; + } +} + +static void set_guc_init_params(struct drm_i915_private *dev_priv) +{ + struct intel_guc *guc = &dev_priv->guc; + u32 params[GUC_CTL_MAX_DWORDS]; + int i; + + memset(¶ms, 0, sizeof(params)); + + params[GUC_CTL_DEVICE_INFO] |= + (get_gttype(dev_priv) << GUC_CTL_GTTYPE_SHIFT) | + (get_core_family(dev_priv) << GUC_CTL_COREFAMILY_SHIFT); + + /* + * GuC ARAT increment is 10 ns. GuC default scheduler quantum is one + * second. This ARAR is calculated by: + * Scheduler-Quantum-in-ns / ARAT-increment-in-ns = 1000000000 / 10 + */ + params[GUC_CTL_ARAT_HIGH] = 0; + params[GUC_CTL_ARAT_LOW] = 100000000; + + params[GUC_CTL_WA] |= GUC_CTL_WA_UK_BY_DRIVER; + + params[GUC_CTL_FEATURE] |= GUC_CTL_DISABLE_SCHEDULER | + GUC_CTL_VCS2_ENABLED; + + if (i915.guc_log_level >= 0) { + params[GUC_CTL_LOG_PARAMS] = guc->log_flags; + params[GUC_CTL_DEBUG] = + i915.guc_log_level << GUC_LOG_VERBOSITY_SHIFT; + } + + /* If GuC submission is enabled, set up additional parameters here */ + if (i915.enable_guc_submission) { + u32 pgs = i915_gem_obj_ggtt_offset(dev_priv->guc.ctx_pool_obj); + u32 ctx_in_16 = GUC_MAX_GPU_CONTEXTS / 16; + + pgs >>= PAGE_SHIFT; + params[GUC_CTL_CTXINFO] = (pgs << GUC_CTL_BASE_ADDR_SHIFT) | + (ctx_in_16 << GUC_CTL_CTXNUM_IN16_SHIFT); + + params[GUC_CTL_FEATURE] |= GUC_CTL_KERNEL_SUBMISSIONS; + + /* Unmask this bit to enable the GuC's internal scheduler */ + params[GUC_CTL_FEATURE] &= ~GUC_CTL_DISABLE_SCHEDULER; + } + + I915_WRITE(SOFT_SCRATCH(0), 0); + + for (i = 0; i < GUC_CTL_MAX_DWORDS; i++) + I915_WRITE(SOFT_SCRATCH(1 + i), params[i]); +} + +/* + * Read the GuC status register (GUC_STATUS) and store it in the + * specified location; then return a boolean indicating whether + * the value matches either of two values representing completion + * of the GuC boot process. + * + * This is used for polling the GuC status in a wait_for_atomic() + * loop below. + */ +static inline bool guc_ucode_response(struct drm_i915_private *dev_priv, + u32 *status) +{ + u32 val = I915_READ(GUC_STATUS); + u32 uk_val = val & GS_UKERNEL_MASK; + *status = val; + return (uk_val == GS_UKERNEL_READY || + ((val & GS_MIA_CORE_STATE) && uk_val == GS_UKERNEL_LAPIC_DONE)); +} + +/* + * Transfer the firmware image to RAM for execution by the microcontroller. + * + * GuC Firmware layout: + * +-------------------------------+ ---- + * | CSS header | 128B + * | contains major/minor version | + * +-------------------------------+ ---- + * | uCode | + * +-------------------------------+ ---- + * | RSA signature | 256B + * +-------------------------------+ ---- + * + * Architecturally, the DMA engine is bidirectional, and can potentially even + * transfer between GTT locations. This functionality is left out of the API + * for now as there is no need for it. + * + * Note that GuC needs the CSS header plus uKernel code to be copied by the + * DMA engine in one operation, whereas the RSA signature is loaded via MMIO. + */ + +#define UOS_CSS_HEADER_OFFSET 0 +#define UOS_VER_MINOR_OFFSET 0x44 +#define UOS_VER_MAJOR_OFFSET 0x46 +#define UOS_CSS_HEADER_SIZE 0x80 +#define UOS_RSA_SIG_SIZE 0x100 + +static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv) +{ + struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw; + struct drm_i915_gem_object *fw_obj = guc_fw->guc_fw_obj; + unsigned long offset; + struct sg_table *sg = fw_obj->pages; + u32 status, ucode_size, rsa[UOS_RSA_SIG_SIZE / sizeof(u32)]; + int i, ret = 0; + + /* uCode size, also is where RSA signature starts */ + offset = ucode_size = guc_fw->guc_fw_size - UOS_RSA_SIG_SIZE; + I915_WRITE(DMA_COPY_SIZE, ucode_size); + + /* Copy RSA signature from the fw image to HW for verification */ + sg_pcopy_to_buffer(sg->sgl, sg->nents, rsa, UOS_RSA_SIG_SIZE, offset); + for (i = 0; i < UOS_RSA_SIG_SIZE / sizeof(u32); i++) + I915_WRITE(UOS_RSA_SCRATCH(i), rsa[i]); + + /* Set the source address for the new blob */ + offset = i915_gem_obj_ggtt_offset(fw_obj); + I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset)); + I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF); + + /* + * Set the DMA destination. Current uCode expects the code to be + * loaded at 8k; locations below this are used for the stack. + */ + I915_WRITE(DMA_ADDR_1_LOW, 0x2000); + I915_WRITE(DMA_ADDR_1_HIGH, DMA_ADDRESS_SPACE_WOPCM); + + /* Finally start the DMA */ + I915_WRITE(DMA_CTRL, _MASKED_BIT_ENABLE(UOS_MOVE | START_DMA)); + + /* + * Spin-wait for the DMA to complete & the GuC to start up. + * NB: Docs recommend not using the interrupt for completion. + * Measurements indicate this should take no more than 20ms, so a + * timeout here indicates that the GuC has failed and is unusable. + * (Higher levels of the driver will attempt to fall back to + * execlist mode if this happens.) + */ + ret = wait_for_atomic(guc_ucode_response(dev_priv, &status), 100); + + DRM_DEBUG_DRIVER("DMA status 0x%x, GuC status 0x%x\n", + I915_READ(DMA_CTRL), status); + + if ((status & GS_BOOTROM_MASK) == GS_BOOTROM_RSA_FAILED) { + DRM_ERROR("GuC firmware signature verification failed\n"); + ret = -ENOEXEC; + } + + DRM_DEBUG_DRIVER("returning %d\n", ret); + + return ret; +} + +/* + * Load the GuC firmware blob into the MinuteIA. + */ +static int guc_ucode_xfer(struct drm_i915_private *dev_priv) +{ + struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw; + struct drm_device *dev = dev_priv->dev; + int ret; + + ret = i915_gem_object_set_to_gtt_domain(guc_fw->guc_fw_obj, false); + if (ret) { + DRM_DEBUG_DRIVER("set-domain failed %d\n", ret); + return ret; + } + + ret = i915_gem_obj_ggtt_pin(guc_fw->guc_fw_obj, 0, 0); + if (ret) { + DRM_DEBUG_DRIVER("pin failed %d\n", ret); + return ret; + } + + /* Invalidate GuC TLB to let GuC take the latest updates to GTT. */ + I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE); + + intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + + /* init WOPCM */ + I915_WRITE(GUC_WOPCM_SIZE, GUC_WOPCM_SIZE_VALUE); + I915_WRITE(DMA_GUC_WOPCM_OFFSET, GUC_WOPCM_OFFSET_VALUE); + + /* Enable MIA caching. GuC clock gating is disabled. */ + I915_WRITE(GUC_SHIM_CONTROL, GUC_SHIM_CONTROL_VALUE); + + /* WaDisableMinuteIaClockGating:skl,bxt */ + if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) || + (IS_BROXTON(dev) && INTEL_REVID(dev) == BXT_REVID_A0)) { + I915_WRITE(GUC_SHIM_CONTROL, (I915_READ(GUC_SHIM_CONTROL) & + ~GUC_ENABLE_MIA_CLOCK_GATING)); + } + + /* WaC6DisallowByGfxPause*/ + I915_WRITE(GEN6_GFXPAUSE, 0x30FFF); + + if (IS_BROXTON(dev)) + I915_WRITE(GEN9LP_GT_PM_CONFIG, GT_DOORBELL_ENABLE); + else + I915_WRITE(GEN9_GT_PM_CONFIG, GT_DOORBELL_ENABLE); + + if (IS_GEN9(dev)) { + /* DOP Clock Gating Enable for GuC clocks */ + I915_WRITE(GEN7_MISCCPCTL, (GEN8_DOP_CLOCK_GATE_GUC_ENABLE | + I915_READ(GEN7_MISCCPCTL))); + + /* allows for 5us before GT can go to RC6 */ + I915_WRITE(GUC_ARAT_C6DIS, 0x1FF); + } + + set_guc_init_params(dev_priv); + + ret = guc_ucode_xfer_dma(dev_priv); + + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + + /* + * We keep the object pages for reuse during resume. But we can unpin it + * now that DMA has completed, so it doesn't continue to take up space. + */ + i915_gem_object_ggtt_unpin(guc_fw->guc_fw_obj); + + return ret; +} + +/** + * intel_guc_ucode_load() - load GuC uCode into the device + * @dev: drm device + * + * Called from gem_init_hw() during driver loading and also after a GPU reset. + * + * The firmware image should have already been fetched into memory by the + * earlier call to intel_guc_ucode_init(), so here we need only check that + * is succeeded, and then transfer the image to the h/w. + * + * Return: non-zero code on error + */ +int intel_guc_ucode_load(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw; + int err = 0; + + DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n", + intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status), + intel_guc_fw_status_repr(guc_fw->guc_fw_load_status)); + + direct_interrupts_to_host(dev_priv); + + if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_NONE) + return 0; + + if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_SUCCESS && + guc_fw->guc_fw_load_status == GUC_FIRMWARE_FAIL) + return -ENOEXEC; + + guc_fw->guc_fw_load_status = GUC_FIRMWARE_PENDING; + + DRM_DEBUG_DRIVER("GuC fw fetch status %s\n", + intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status)); + + switch (guc_fw->guc_fw_fetch_status) { + case GUC_FIRMWARE_FAIL: + /* something went wrong :( */ + err = -EIO; + goto fail; + + case GUC_FIRMWARE_NONE: + case GUC_FIRMWARE_PENDING: + default: + /* "can't happen" */ + WARN_ONCE(1, "GuC fw %s invalid guc_fw_fetch_status %s [%d]\n", + guc_fw->guc_fw_path, + intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status), + guc_fw->guc_fw_fetch_status); + err = -ENXIO; + goto fail; + + case GUC_FIRMWARE_SUCCESS: + break; + } + + err = i915_guc_submission_init(dev); + if (err) + goto fail; + + err = guc_ucode_xfer(dev_priv); + if (err) + goto fail; + + guc_fw->guc_fw_load_status = GUC_FIRMWARE_SUCCESS; + + DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n", + intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status), + intel_guc_fw_status_repr(guc_fw->guc_fw_load_status)); + + if (i915.enable_guc_submission) { + /* The execbuf_client will be recreated. Release it first. */ + i915_guc_submission_disable(dev); + + err = i915_guc_submission_enable(dev); + if (err) + goto fail; + direct_interrupts_to_guc(dev_priv); + } + + return 0; + +fail: + if (guc_fw->guc_fw_load_status == GUC_FIRMWARE_PENDING) + guc_fw->guc_fw_load_status = GUC_FIRMWARE_FAIL; + + direct_interrupts_to_host(dev_priv); + i915_guc_submission_disable(dev); + + return err; +} + +static void guc_fw_fetch(struct drm_device *dev, struct intel_guc_fw *guc_fw) +{ + struct drm_i915_gem_object *obj; + const struct firmware *fw; + const u8 *css_header; + const size_t minsize = UOS_CSS_HEADER_SIZE + UOS_RSA_SIG_SIZE; + const size_t maxsize = GUC_WOPCM_SIZE_VALUE + UOS_RSA_SIG_SIZE + - 0x8000; /* 32k reserved (8K stack + 24k context) */ + int err; + + DRM_DEBUG_DRIVER("before requesting firmware: GuC fw fetch status %s\n", + intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status)); + + err = request_firmware(&fw, guc_fw->guc_fw_path, &dev->pdev->dev); + if (err) + goto fail; + if (!fw) + goto fail; + + DRM_DEBUG_DRIVER("fetch GuC fw from %s succeeded, fw %p\n", + guc_fw->guc_fw_path, fw); + DRM_DEBUG_DRIVER("firmware file size %zu (minimum %zu, maximum %zu)\n", + fw->size, minsize, maxsize); + + /* Check the size of the blob befoe examining buffer contents */ + if (fw->size < minsize || fw->size > maxsize) + goto fail; + + /* + * The GuC firmware image has the version number embedded at a well-known + * offset within the firmware blob; note that major / minor version are + * TWO bytes each (i.e. u16), although all pointers and offsets are defined + * in terms of bytes (u8). + */ + css_header = fw->data + UOS_CSS_HEADER_OFFSET; + guc_fw->guc_fw_major_found = *(u16 *)(css_header + UOS_VER_MAJOR_OFFSET); + guc_fw->guc_fw_minor_found = *(u16 *)(css_header + UOS_VER_MINOR_OFFSET); + + if (guc_fw->guc_fw_major_found != guc_fw->guc_fw_major_wanted || + guc_fw->guc_fw_minor_found < guc_fw->guc_fw_minor_wanted) { + DRM_ERROR("GuC firmware version %d.%d, required %d.%d\n", + guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found, + guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted); + err = -ENOEXEC; + goto fail; + } + + DRM_DEBUG_DRIVER("firmware version %d.%d OK (minimum %d.%d)\n", + guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found, + guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted); + + obj = i915_gem_object_create_from_data(dev, fw->data, fw->size); + if (IS_ERR_OR_NULL(obj)) { + err = obj ? PTR_ERR(obj) : -ENOMEM; + goto fail; + } + + guc_fw->guc_fw_obj = obj; + guc_fw->guc_fw_size = fw->size; + + DRM_DEBUG_DRIVER("GuC fw fetch status SUCCESS, obj %p\n", + guc_fw->guc_fw_obj); + + release_firmware(fw); + guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_SUCCESS; + return; + +fail: + DRM_DEBUG_DRIVER("GuC fw fetch status FAIL; err %d, fw %p, obj %p\n", + err, fw, guc_fw->guc_fw_obj); + DRM_ERROR("Failed to fetch GuC firmware from %s (error %d)\n", + guc_fw->guc_fw_path, err); + + obj = guc_fw->guc_fw_obj; + if (obj) + drm_gem_object_unreference(&obj->base); + guc_fw->guc_fw_obj = NULL; + + release_firmware(fw); /* OK even if fw is NULL */ + guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL; +} + +/** + * intel_guc_ucode_init() - define parameters and fetch firmware + * @dev: drm device + * + * Called early during driver load, but after GEM is initialised. + * The device struct_mutex must be held by the caller, as we're + * going to allocate a GEM object to hold the firmware image. + * + * The firmware will be transferred to the GuC's memory later, + * when intel_guc_ucode_load() is called. + */ +void intel_guc_ucode_init(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw; + const char *fw_path; + + if (!HAS_GUC_SCHED(dev)) + i915.enable_guc_submission = false; + + if (!HAS_GUC_UCODE(dev)) { + fw_path = NULL; + } else if (IS_SKYLAKE(dev)) { + fw_path = I915_SKL_GUC_UCODE; + guc_fw->guc_fw_major_wanted = 4; + guc_fw->guc_fw_minor_wanted = 3; + } else { + i915.enable_guc_submission = false; + fw_path = ""; /* unknown device */ + } + + guc_fw->guc_dev = dev; + guc_fw->guc_fw_path = fw_path; + guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE; + guc_fw->guc_fw_load_status = GUC_FIRMWARE_NONE; + + if (fw_path == NULL) + return; + + if (*fw_path == '\0') { + DRM_ERROR("No GuC firmware known for this platform\n"); + guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL; + return; + } + + guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_PENDING; + DRM_DEBUG_DRIVER("GuC firmware pending, path %s\n", fw_path); + guc_fw_fetch(dev, guc_fw); + /* status must now be FAIL or SUCCESS */ +} + +/** + * intel_guc_ucode_fini() - clean up all allocated resources + * @dev: drm device + */ +void intel_guc_ucode_fini(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw; + + direct_interrupts_to_host(dev_priv); + i915_guc_submission_fini(dev); + + if (guc_fw->guc_fw_obj) + drm_gem_object_unreference(&guc_fw->guc_fw_obj->base); + guc_fw->guc_fw_obj = NULL; + + guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE; +} diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index dcd336b..3b28ed3 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -447,16 +447,13 @@ static void intel_write_infoframe(struct drm_encoder *encoder, } static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *adjusted_mode) { struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); union hdmi_infoframe frame; int ret; - /* Set user selected PAR to incoming mode's member */ - adjusted_mode->picture_aspect_ratio = intel_hdmi->aspect_ratio; - ret = drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, adjusted_mode); if (ret < 0) { @@ -494,7 +491,7 @@ static void intel_hdmi_set_spd_infoframe(struct drm_encoder *encoder) static void intel_hdmi_set_hdmi_infoframe(struct drm_encoder *encoder, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *adjusted_mode) { union hdmi_infoframe frame; int ret; @@ -509,7 +506,7 @@ intel_hdmi_set_hdmi_infoframe(struct drm_encoder *encoder, static void g4x_set_infoframes(struct drm_encoder *encoder, bool enable, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); @@ -661,7 +658,7 @@ static bool intel_hdmi_set_gcp_infoframe(struct drm_encoder *encoder) static void ibx_set_infoframes(struct drm_encoder *encoder, bool enable, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); @@ -713,7 +710,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder, static void cpt_set_infoframes(struct drm_encoder *encoder, bool enable, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); @@ -755,7 +752,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder, static void vlv_set_infoframes(struct drm_encoder *encoder, bool enable, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); @@ -807,7 +804,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder, static void hsw_set_infoframes(struct drm_encoder *encoder, bool enable, - struct drm_display_mode *adjusted_mode) + const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); @@ -844,12 +841,12 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); - struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; u32 hdmi_val; hdmi_val = SDVO_ENCODING_HDMI; - if (!HAS_PCH_SPLIT(dev)) - hdmi_val |= intel_hdmi->color_range; + if (!HAS_PCH_SPLIT(dev) && crtc->config->limited_color_range) + hdmi_val |= HDMI_COLOR_RANGE_16_235; if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) hdmi_val |= SDVO_VSYNC_ACTIVE_HIGH; if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) @@ -1260,11 +1257,12 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, if (intel_hdmi->color_range_auto) { /* See CEA-861-E - 5.1 Default Encoding Parameters */ - if (pipe_config->has_hdmi_sink && - drm_match_cea_mode(adjusted_mode) > 1) - intel_hdmi->color_range = HDMI_COLOR_RANGE_16_235; - else - intel_hdmi->color_range = 0; + pipe_config->limited_color_range = + pipe_config->has_hdmi_sink && + drm_match_cea_mode(adjusted_mode) > 1; + } else { + pipe_config->limited_color_range = + intel_hdmi->limited_color_range; } if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) { @@ -1273,9 +1271,6 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, clock_12bpc *= 2; } - if (intel_hdmi->color_range) - pipe_config->limited_color_range = true; - if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev)) pipe_config->has_pch_encoder = true; @@ -1314,6 +1309,9 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, return false; } + /* Set user selected PAR to incoming mode's member */ + adjusted_mode->picture_aspect_ratio = intel_hdmi->aspect_ratio; + return true; } @@ -1331,22 +1329,23 @@ intel_hdmi_unset_edid(struct drm_connector *connector) } static bool -intel_hdmi_set_edid(struct drm_connector *connector) +intel_hdmi_set_edid(struct drm_connector *connector, bool force) { struct drm_i915_private *dev_priv = to_i915(connector->dev); struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); struct intel_encoder *intel_encoder = &hdmi_to_dig_port(intel_hdmi)->base; enum intel_display_power_domain power_domain; - struct edid *edid; + struct edid *edid = NULL; bool connected = false; power_domain = intel_display_port_power_domain(intel_encoder); intel_display_power_get(dev_priv, power_domain); - edid = drm_get_edid(connector, - intel_gmbus_get_adapter(dev_priv, - intel_hdmi->ddc_bus)); + if (force) + edid = drm_get_edid(connector, + intel_gmbus_get_adapter(dev_priv, + intel_hdmi->ddc_bus)); intel_display_power_put(dev_priv, power_domain); @@ -1374,13 +1373,26 @@ static enum drm_connector_status intel_hdmi_detect(struct drm_connector *connector, bool force) { enum drm_connector_status status; + struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); + struct drm_i915_private *dev_priv = to_i915(connector->dev); + bool live_status = false; + unsigned int retry = 3; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); + while (!live_status && --retry) { + live_status = intel_digital_port_connected(dev_priv, + hdmi_to_dig_port(intel_hdmi)); + mdelay(10); + } + + if (!live_status) + DRM_DEBUG_KMS("Live status not up!"); + intel_hdmi_unset_edid(connector); - if (intel_hdmi_set_edid(connector)) { + if (intel_hdmi_set_edid(connector, live_status)) { struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI; @@ -1404,7 +1416,7 @@ intel_hdmi_force(struct drm_connector *connector) if (connector->status != connector_status_connected) return; - intel_hdmi_set_edid(connector); + intel_hdmi_set_edid(connector, true); hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI; } @@ -1470,7 +1482,7 @@ intel_hdmi_set_property(struct drm_connector *connector, if (property == dev_priv->broadcast_rgb_property) { bool old_auto = intel_hdmi->color_range_auto; - uint32_t old_range = intel_hdmi->color_range; + bool old_range = intel_hdmi->limited_color_range; switch (val) { case INTEL_BROADCAST_RGB_AUTO: @@ -1478,18 +1490,18 @@ intel_hdmi_set_property(struct drm_connector *connector, break; case INTEL_BROADCAST_RGB_FULL: intel_hdmi->color_range_auto = false; - intel_hdmi->color_range = 0; + intel_hdmi->limited_color_range = false; break; case INTEL_BROADCAST_RGB_LIMITED: intel_hdmi->color_range_auto = false; - intel_hdmi->color_range = HDMI_COLOR_RANGE_16_235; + intel_hdmi->limited_color_range = true; break; default: return -EINVAL; } if (old_auto == intel_hdmi->color_range_auto && - old_range == intel_hdmi->color_range) + old_range == intel_hdmi->limited_color_range) return 0; goto done; @@ -1525,8 +1537,7 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder) { struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); - struct drm_display_mode *adjusted_mode = - &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; intel_hdmi_prepare(encoder); @@ -1543,8 +1554,7 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); - struct drm_display_mode *adjusted_mode = - &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; enum dpio_channel port = vlv_dport_to_channel(dport); int pipe = intel_crtc->pipe; u32 val; @@ -1617,6 +1627,50 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder) mutex_unlock(&dev_priv->sb_lock); } +static void chv_data_lane_soft_reset(struct intel_encoder *encoder, + bool reset) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base)); + struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); + enum pipe pipe = crtc->pipe; + uint32_t val; + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + if (reset) + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + else + val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + if (crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + if (reset) + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + else + val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + } + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + if (reset) + val &= ~DPIO_PCS_CLK_SOFT_RESET; + else + val |= DPIO_PCS_CLK_SOFT_RESET; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + if (crtc->config->lane_count > 2) { + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + if (reset) + val &= ~DPIO_PCS_CLK_SOFT_RESET; + else + val |= DPIO_PCS_CLK_SOFT_RESET; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + } +} + static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder) { struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); @@ -1630,8 +1684,21 @@ static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder) intel_hdmi_prepare(encoder); + /* + * Must trick the second common lane into life. + * Otherwise we can't even access the PLL. + */ + if (ch == DPIO_CH0 && pipe == PIPE_B) + dport->release_cl2_override = + !chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, true); + + chv_phy_powergate_lanes(encoder, true, 0x0); + mutex_lock(&dev_priv->sb_lock); + /* Assert data lane reset */ + chv_data_lane_soft_reset(encoder, true); + /* program left/right clock distribution */ if (pipe != PIPE_B) { val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0); @@ -1683,6 +1750,39 @@ static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder) mutex_unlock(&dev_priv->sb_lock); } +static void chv_hdmi_post_pll_disable(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum pipe pipe = to_intel_crtc(encoder->base.crtc)->pipe; + u32 val; + + mutex_lock(&dev_priv->sb_lock); + + /* disable left/right clock distribution */ + if (pipe != PIPE_B) { + val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0); + val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK); + vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val); + } else { + val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1); + val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK); + vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val); + } + + mutex_unlock(&dev_priv->sb_lock); + + /* + * Leave the power down bit cleared for at least one + * lane so that chv_powergate_phy_ch() will power + * on something when the channel is otherwise unused. + * When the port is off and the override is removed + * the lanes power down anyway, so otherwise it doesn't + * really matter what the state of power down bits is + * after this. + */ + chv_phy_powergate_lanes(encoder, false, 0x0); +} + static void vlv_hdmi_post_disable(struct intel_encoder *encoder) { struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); @@ -1701,33 +1801,13 @@ static void vlv_hdmi_post_disable(struct intel_encoder *encoder) static void chv_hdmi_post_disable(struct intel_encoder *encoder) { - struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = - to_intel_crtc(encoder->base.crtc); - enum dpio_channel ch = vlv_dport_to_channel(dport); - enum pipe pipe = intel_crtc->pipe; - u32 val; mutex_lock(&dev_priv->sb_lock); - /* Propagate soft reset to data lane reset */ - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); - val |= CHV_PCS_REQ_SOFTRESET_EN; - vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); - val |= CHV_PCS_REQ_SOFTRESET_EN; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); - val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); - val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + /* Assert data lane reset */ + chv_data_lane_soft_reset(encoder, true); mutex_unlock(&dev_priv->sb_lock); } @@ -1740,8 +1820,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); - struct drm_display_mode *adjusted_mode = - &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; enum dpio_channel ch = vlv_dport_to_channel(dport); int pipe = intel_crtc->pipe; int data, i, stagger; @@ -1758,23 +1837,6 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder) val &= ~DPIO_LANEDESKEW_STRAP_OVRD; vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val); - /* Deassert soft data lane reset*/ - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); - val |= CHV_PCS_REQ_SOFTRESET_EN; - vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); - val |= CHV_PCS_REQ_SOFTRESET_EN; - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); - val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); - - val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); - val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); - vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); - /* Program Tx latency optimal setting */ for (i = 0; i < 4; i++) { /* Set the upar bit */ @@ -1817,6 +1879,9 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder) DPIO_TX1_STAGGER_MULT(7) | DPIO_TX2_STAGGER_MULT(5)); + /* Deassert data lane reset */ + chv_data_lane_soft_reset(encoder, false); + /* Clear calc init */ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); @@ -1851,31 +1916,33 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder) for (i = 0; i < 4; i++) { val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~DPIO_SWING_MARGIN000_MASK; val |= 102 << DPIO_SWING_MARGIN000_SHIFT; + + /* + * Supposedly this value shouldn't matter when unique transition + * scale is disabled, but in fact it does matter. Let's just + * always program the same value and hope it's OK. + */ + val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT); + val |= 0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); } - /* Disable unique transition scale */ + /* + * The document said it needs to set bit 27 for ch0 and bit 26 + * for ch1. Might be a typo in the doc. + * For now, for this unique transition scale selection, set bit + * 27 for ch0 and ch1. + */ for (i = 0; i < 4; i++) { val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN; vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); } - /* Additional steps for 1200mV-0dB */ -#if 0 - val = vlv_dpio_read(dev_priv, pipe, VLV_TX_DW3(ch)); - if (ch) - val |= DPIO_TX_UNIQ_TRANS_SCALE_CH1; - else - val |= DPIO_TX_UNIQ_TRANS_SCALE_CH0; - vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(ch), val); - - vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(ch), - vlv_dpio_read(dev_priv, pipe, VLV_TX_DW2(ch)) | - (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT)); -#endif /* Start swing calculation */ val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; @@ -1885,11 +1952,6 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder) val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); - /* LRC Bypass */ - val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30); - val |= DPIO_LRC_BYPASS; - vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val); - mutex_unlock(&dev_priv->sb_lock); intel_hdmi->set_infoframes(&encoder->base, @@ -1899,6 +1961,12 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder) g4x_enable_hdmi(encoder); vlv_wait_port_ready(dev_priv, dport, 0x0); + + /* Second common lane will stay alive on its own now */ + if (dport->release_cl2_override) { + chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, false); + dport->release_cl2_override = false; + } } static void intel_hdmi_destroy(struct drm_connector *connector) @@ -1931,15 +1999,6 @@ static const struct drm_encoder_funcs intel_hdmi_enc_funcs = { }; static void -intel_attach_aspect_ratio_property(struct drm_connector *connector) -{ - if (!drm_mode_create_aspect_ratio_property(connector->dev)) - drm_object_attach_property(&connector->base, - connector->dev->mode_config.aspect_ratio_property, - DRM_MODE_PICTURE_ASPECT_NONE); -} - -static void intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *connector) { intel_attach_force_audio_property(connector); @@ -1974,7 +2033,14 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, intel_hdmi->ddc_bus = GMBUS_PIN_1_BXT; else intel_hdmi->ddc_bus = GMBUS_PIN_DPB; - intel_encoder->hpd_pin = HPD_PORT_B; + /* + * On BXT A0/A1, sw needs to activate DDIA HPD logic and + * interrupts to check the external panel connection. + */ + if (IS_BROXTON(dev_priv) && (INTEL_REVID(dev) < BXT_REVID_B0)) + intel_encoder->hpd_pin = HPD_PORT_A; + else + intel_encoder->hpd_pin = HPD_PORT_B; break; case PORT_C: if (IS_BROXTON(dev_priv)) @@ -2051,6 +2117,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, intel_connector_attach_encoder(intel_connector, intel_encoder); drm_connector_register(connector); + intel_hdmi->attached_connector = intel_connector; /* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written * 0xd. Failure to do so will result in spurious interrupts being @@ -2097,6 +2164,7 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port) intel_encoder->pre_enable = chv_hdmi_pre_enable; intel_encoder->enable = vlv_enable_hdmi; intel_encoder->post_disable = chv_hdmi_post_disable; + intel_encoder->post_pll_disable = chv_hdmi_post_pll_disable; } else if (IS_VALLEYVIEW(dev)) { intel_encoder->pre_pll_enable = vlv_hdmi_pre_pll_enable; intel_encoder->pre_enable = vlv_hdmi_pre_enable; diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c index 53c0173..b177857 100644 --- a/drivers/gpu/drm/i915/intel_hotplug.c +++ b/drivers/gpu/drm/i915/intel_hotplug.c @@ -180,7 +180,7 @@ static void intel_hpd_irq_storm_disable(struct drm_i915_private *dev_priv) /* Enable polling and queue hotplug re-enabling. */ if (hpd_disabled) { - drm_kms_helper_poll_enable(dev); + drm_kms_helper_poll_enable_locked(dev); mod_delayed_work(system_wq, &dev_priv->hotplug.reenable_work, msecs_to_jiffies(HPD_STORM_REENABLE_DELAY)); } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 72e0edd..efb704b 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -196,13 +196,21 @@ reg_state[CTX_PDP ## n ## _LDW+1] = lower_32_bits(_addr); \ } +#define ASSIGN_CTX_PML4(ppgtt, reg_state) { \ + reg_state[CTX_PDP0_UDW + 1] = upper_32_bits(px_dma(&ppgtt->pml4)); \ + reg_state[CTX_PDP0_LDW + 1] = lower_32_bits(px_dma(&ppgtt->pml4)); \ +} + enum { ADVANCED_CONTEXT = 0, - LEGACY_CONTEXT, + LEGACY_32B_CONTEXT, ADVANCED_AD_CONTEXT, LEGACY_64B_CONTEXT }; -#define GEN8_CTX_MODE_SHIFT 3 +#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3 +#define GEN8_CTX_ADDRESSING_MODE(dev) (USES_FULL_48BIT_PPGTT(dev) ?\ + LEGACY_64B_CONTEXT :\ + LEGACY_32B_CONTEXT) enum { FAULT_AND_HANG = 0, FAULT_AND_HALT, /* Debug only */ @@ -213,6 +221,9 @@ enum { #define CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT 0x17 static int intel_lr_context_pin(struct drm_i915_gem_request *rq); +static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring, + struct drm_i915_gem_object *default_ctx_obj); + /** * intel_sanitize_enable_execlists() - sanitize i915.enable_execlists @@ -228,6 +239,12 @@ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists { WARN_ON(i915.enable_ppgtt == -1); + /* On platforms with execlist available, vGPU will only + * support execlist mode, no ring buffer mode. + */ + if (HAS_LOGICAL_RING_CONTEXTS(dev) && intel_vgpu_active(dev)) + return 1; + if (INTEL_INFO(dev)->gen >= 9) return 1; @@ -255,25 +272,35 @@ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists */ u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj) { - u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj); + u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj) + + LRC_PPHWSP_PN * PAGE_SIZE; /* LRCA is required to be 4K aligned so the more significant 20 bits * are globally unique */ return lrca >> 12; } -static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_request *rq) +static bool disable_lite_restore_wa(struct intel_engine_cs *ring) { - struct intel_engine_cs *ring = rq->ring; struct drm_device *dev = ring->dev; - struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state; + + return ((IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) || + (IS_BROXTON(dev) && INTEL_REVID(dev) == BXT_REVID_A0)) && + (ring->id == VCS || ring->id == VCS2); +} + +uint64_t intel_lr_context_descriptor(struct intel_context *ctx, + struct intel_engine_cs *ring) +{ + struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state; uint64_t desc; - uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj); + uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj) + + LRC_PPHWSP_PN * PAGE_SIZE; WARN_ON(lrca & 0xFFFFFFFF00000FFFULL); desc = GEN8_CTX_VALID; - desc |= LEGACY_CONTEXT << GEN8_CTX_MODE_SHIFT; + desc |= GEN8_CTX_ADDRESSING_MODE(dev) << GEN8_CTX_ADDRESSING_MODE_SHIFT; if (IS_GEN8(ctx_obj->base.dev)) desc |= GEN8_CTX_L3LLC_COHERENT; desc |= GEN8_CTX_PRIVILEGE; @@ -285,10 +312,8 @@ static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_request *rq) /* desc |= GEN8_CTX_FORCE_RESTORE; */ /* WaEnableForceRestoreInCtxtDescForVCS:skl */ - if (IS_GEN9(dev) && - INTEL_REVID(dev) <= SKL_REVID_B0 && - (ring->id == BCS || ring->id == VCS || - ring->id == VECS || ring->id == VCS2)) + /* WaEnableForceRestoreInCtxtDescForVCS:bxt */ + if (disable_lite_restore_wa(ring)) desc |= GEN8_CTX_FORCE_RESTORE; return desc; @@ -304,13 +329,13 @@ static void execlists_elsp_write(struct drm_i915_gem_request *rq0, uint64_t desc[2]; if (rq1) { - desc[1] = execlists_ctx_descriptor(rq1); + desc[1] = intel_lr_context_descriptor(rq1->ctx, rq1->ring); rq1->elsp_submitted++; } else { desc[1] = 0; } - desc[0] = execlists_ctx_descriptor(rq0); + desc[0] = intel_lr_context_descriptor(rq0->ctx, rq0->ring); rq0->elsp_submitted++; /* You must always write both descriptors in the order below. */ @@ -324,7 +349,7 @@ static void execlists_elsp_write(struct drm_i915_gem_request *rq0, I915_WRITE_FW(RING_ELSP(ring), lower_32_bits(desc[0])); /* ELSP is a wo register, use another nearby reg for posting */ - POSTING_READ_FW(RING_EXECLIST_STATUS(ring)); + POSTING_READ_FW(RING_EXECLIST_STATUS_LO(ring)); intel_uncore_forcewake_put__locked(dev_priv, FORCEWAKE_ALL); spin_unlock(&dev_priv->uncore.lock); } @@ -342,16 +367,18 @@ static int execlists_update_context(struct drm_i915_gem_request *rq) WARN_ON(!i915_gem_obj_is_pinned(ctx_obj)); WARN_ON(!i915_gem_obj_is_pinned(rb_obj)); - page = i915_gem_object_get_page(ctx_obj, 1); + page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN); reg_state = kmap_atomic(page); reg_state[CTX_RING_TAIL+1] = rq->tail; reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj); - /* True PPGTT with dynamic page allocation: update PDP registers and - * point the unallocated PDPs to the scratch page - */ - if (ppgtt) { + if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) { + /* True 32b PPGTT with dynamic page allocation: update PDP + * registers and point the unallocated PDPs to scratch page. + * PML4 is allocated during ppgtt init, so this is not needed + * in 48-bit mode. + */ ASSIGN_CTX_PDP(ppgtt, reg_state, 3); ASSIGN_CTX_PDP(ppgtt, reg_state, 2); ASSIGN_CTX_PDP(ppgtt, reg_state, 1); @@ -477,25 +504,23 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring) u32 status_pointer; u8 read_pointer; u8 write_pointer; - u32 status; + u32 status = 0; u32 status_id; u32 submit_contexts = 0; status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring)); read_pointer = ring->next_context_status_buffer; - write_pointer = status_pointer & 0x07; + write_pointer = status_pointer & GEN8_CSB_PTR_MASK; if (read_pointer > write_pointer) - write_pointer += 6; + write_pointer += GEN8_CSB_ENTRIES; spin_lock(&ring->execlist_lock); while (read_pointer < write_pointer) { read_pointer++; - status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + - (read_pointer % 6) * 8); - status_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + - (read_pointer % 6) * 8 + 4); + status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, read_pointer % GEN8_CSB_ENTRIES)); + status_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, read_pointer % GEN8_CSB_ENTRIES)); if (status & GEN8_CTX_STATUS_IDLE_ACTIVE) continue; @@ -515,16 +540,24 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring) } } - if (submit_contexts != 0) + if (disable_lite_restore_wa(ring)) { + /* Prevent a ctx to preempt itself */ + if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) && + (submit_contexts != 0)) + execlists_context_unqueue(ring); + } else if (submit_contexts != 0) { execlists_context_unqueue(ring); + } spin_unlock(&ring->execlist_lock); WARN(submit_contexts > 2, "More than two context complete events?\n"); - ring->next_context_status_buffer = write_pointer % 6; + ring->next_context_status_buffer = write_pointer % GEN8_CSB_ENTRIES; I915_WRITE(RING_CONTEXT_STATUS_PTR(ring), - _MASKED_FIELD(0x07 << 8, ((u32)ring->next_context_status_buffer & 0x07) << 8)); + _MASKED_FIELD(GEN8_CSB_PTR_MASK << 8, + ((u32)ring->next_context_status_buffer & + GEN8_CSB_PTR_MASK) << 8)); } static int execlists_context_queue(struct drm_i915_gem_request *request) @@ -538,8 +571,6 @@ static int execlists_context_queue(struct drm_i915_gem_request *request) i915_gem_request_reference(request); - request->tail = request->ringbuf->tail; - spin_lock_irq(&ring->execlist_lock); list_for_each_entry(cursor, &ring->execlist_queue, execlist_link) @@ -692,13 +723,19 @@ static void intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request) { struct intel_engine_cs *ring = request->ring; + struct drm_i915_private *dev_priv = request->i915; intel_logical_ring_advance(request->ringbuf); + request->tail = request->ringbuf->tail; + if (intel_ring_stopped(ring)) return; - execlists_context_queue(request); + if (dev_priv->guc.execbuf_client) + i915_guc_submit(dev_priv->guc.execbuf_client, request); + else + execlists_context_queue(request); } static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf) @@ -765,8 +802,7 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes) /** * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands * - * @request: The request to start some new work for - * @ctx: Logical ring context whose ringbuffer is being prepared. + * @req: The request to start some new work for * @num_dwords: number of DWORDs that we plan to write to the ringbuffer. * * The ringbuffer might not be ready to accept the commands right away (maybe it needs to @@ -868,21 +904,6 @@ int intel_execlists_submission(struct i915_execbuffer_params *params, return -EINVAL; } - if (args->num_cliprects != 0) { - DRM_DEBUG("clip rectangles are only valid on pre-gen5\n"); - return -EINVAL; - } else { - if (args->DR4 == 0xffffffff) { - DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); - args->DR4 = 0; - } - - if (args->DR1 || args->DR4 || args->cliprects_ptr) { - DRM_DEBUG("0 cliprects but dirt in cliprects fields\n"); - return -EINVAL; - } - } - if (args->flags & I915_EXEC_GEN7_SOL_RESET) { DRM_DEBUG("sol reset is gen7 only\n"); return -EINVAL; @@ -986,34 +1007,54 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req) return 0; } +static int intel_lr_context_do_pin(struct intel_engine_cs *ring, + struct drm_i915_gem_object *ctx_obj, + struct intel_ringbuffer *ringbuf) +{ + struct drm_device *dev = ring->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int ret = 0; + + WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex)); + ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, + PIN_OFFSET_BIAS | GUC_WOPCM_TOP); + if (ret) + return ret; + + ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf); + if (ret) + goto unpin_ctx_obj; + + ctx_obj->dirty = true; + + /* Invalidate GuC TLB. */ + if (i915.enable_guc_submission) + I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE); + + return ret; + +unpin_ctx_obj: + i915_gem_object_ggtt_unpin(ctx_obj); + + return ret; +} + static int intel_lr_context_pin(struct drm_i915_gem_request *rq) { + int ret = 0; struct intel_engine_cs *ring = rq->ring; struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state; struct intel_ringbuffer *ringbuf = rq->ringbuf; - int ret = 0; - WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex)); if (rq->ctx->engine[ring->id].pin_count++ == 0) { - ret = i915_gem_obj_ggtt_pin(ctx_obj, - GEN8_LR_CONTEXT_ALIGN, 0); + ret = intel_lr_context_do_pin(ring, ctx_obj, ringbuf); if (ret) goto reset_pin_count; - - ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf); - if (ret) - goto unpin_ctx_obj; - - ctx_obj->dirty = true; } - return ret; -unpin_ctx_obj: - i915_gem_object_ggtt_unpin(ctx_obj); reset_pin_count: rq->ctx->engine[ring->id].pin_count = 0; - return ret; } @@ -1111,7 +1152,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *ring, if (IS_SKYLAKE(ring->dev) && INTEL_REVID(ring->dev) <= SKL_REVID_E0) l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; - wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8(1) | + wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT)); wa_ctx_emit(batch, index, GEN8_L3SQCREG4); wa_ctx_emit(batch, index, ring->scratch.gtt_offset + 256); @@ -1129,7 +1170,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *ring, wa_ctx_emit(batch, index, 0); wa_ctx_emit(batch, index, 0); - wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8(1) | + wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT)); wa_ctx_emit(batch, index, GEN8_L3SQCREG4); wa_ctx_emit(batch, index, ring->scratch.gtt_offset + 256); @@ -1198,9 +1239,10 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring, /* WaFlushCoherentL3CacheLinesAtContextSwitch:bdw */ if (IS_BROADWELL(ring->dev)) { - index = gen8_emit_flush_coherentl3_wa(ring, batch, index); - if (index < 0) - return index; + int rc = gen8_emit_flush_coherentl3_wa(ring, batch, index); + if (rc < 0) + return rc; + index = rc; } /* WaClearSlmSpaceAtContextSwitch:bdw,chv */ @@ -1422,6 +1464,10 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; + u8 next_context_status_buffer_hw; + + lrc_setup_hardware_status_page(ring, + ring->default_context->engine[ring->id].state); I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask)); I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff); @@ -1436,7 +1482,29 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring) _MASKED_BIT_DISABLE(GFX_REPLAY_MODE) | _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)); POSTING_READ(RING_MODE_GEN7(ring)); - ring->next_context_status_buffer = 0; + + /* + * Instead of resetting the Context Status Buffer (CSB) read pointer to + * zero, we need to read the write pointer from hardware and use its + * value because "this register is power context save restored". + * Effectively, these states have been observed: + * + * | Suspend-to-idle (freeze) | Suspend-to-RAM (mem) | + * BDW | CSB regs not reset | CSB regs reset | + * CHT | CSB regs not reset | CSB regs not reset | + */ + next_context_status_buffer_hw = (I915_READ(RING_CONTEXT_STATUS_PTR(ring)) + & GEN8_CSB_PTR_MASK); + + /* + * When the CSB registers are reset (also after power-up / gpu reset), + * CSB write pointer is set to all 1's, which is not valid, use '5' in + * this special case, so the first element read is CSB[0]. + */ + if (next_context_status_buffer_hw == GEN8_CSB_PTR_MASK) + next_context_status_buffer_hw = (GEN8_CSB_ENTRIES - 1); + + ring->next_context_status_buffer = next_context_status_buffer_hw; DRM_DEBUG_DRIVER("Execlists enabled for %s\n", ring->name); memset(&ring->hangcheck, 0, sizeof(ring->hangcheck)); @@ -1517,12 +1585,16 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req, * Ideally, we should set Force PD Restore in ctx descriptor, * but we can't. Force Restore would be a second option, but * it is unsafe in case of lite-restore (because the ctx is - * not idle). */ + * not idle). PML4 is allocated during ppgtt init so this is + * not needed in 48-bit.*/ if (req->ctx->ppgtt && (intel_ring_flag(req->ring) & req->ctx->ppgtt->pd_dirty_rings)) { - ret = intel_logical_ring_emit_pdps(req); - if (ret) - return ret; + if (!USES_FULL_48BIT_PPGTT(req->i915) && + !intel_vgpu_active(req->i915->dev)) { + ret = intel_logical_ring_emit_pdps(req); + if (ret) + return ret; + } req->ctx->ppgtt->pd_dirty_rings &= ~intel_ring_flag(req->ring); } @@ -1688,6 +1760,34 @@ static void gen8_set_seqno(struct intel_engine_cs *ring, u32 seqno) intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno); } +static u32 bxt_a_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency) +{ + + /* + * On BXT A steppings there is a HW coherency issue whereby the + * MI_STORE_DATA_IMM storing the completed request's seqno + * occasionally doesn't invalidate the CPU cache. Work around this by + * clflushing the corresponding cacheline whenever the caller wants + * the coherency to be guaranteed. Note that this cacheline is known + * to be clean at this point, since we only write it in + * bxt_a_set_seqno(), where we also do a clflush after the write. So + * this clflush in practice becomes an invalidate operation. + */ + + if (!lazy_coherency) + intel_flush_status_page(ring, I915_GEM_HWS_INDEX); + + return intel_read_status_page(ring, I915_GEM_HWS_INDEX); +} + +static void bxt_a_set_seqno(struct intel_engine_cs *ring, u32 seqno) +{ + intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno); + + /* See bxt_a_get_seqno() explaining the reason for the clflush. */ + intel_flush_status_page(ring, I915_GEM_HWS_INDEX); +} + static int gen8_emit_request(struct drm_i915_gem_request *request) { struct intel_ringbuffer *ringbuf = request->ringbuf; @@ -1830,7 +1930,21 @@ static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *rin if (ret) return ret; - ret = intel_lr_context_deferred_create(ring->default_context, ring); + ret = intel_lr_context_deferred_alloc(ring->default_context, ring); + if (ret) + return ret; + + /* As this is the default context, always pin it */ + ret = intel_lr_context_do_pin( + ring, + ring->default_context->engine[ring->id].state, + ring->default_context->engine[ring->id].ringbuf); + if (ret) { + DRM_ERROR( + "Failed to pin and map ringbuffer %s: %d\n", + ring->name, ret); + return ret; + } return ret; } @@ -1857,8 +1971,13 @@ static int logical_render_ring_init(struct drm_device *dev) ring->init_hw = gen8_init_render_ring; ring->init_context = gen8_init_rcs_context; ring->cleanup = intel_fini_pipe_control; - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; + if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) { + ring->get_seqno = bxt_a_get_seqno; + ring->set_seqno = bxt_a_set_seqno; + } else { + ring->get_seqno = gen8_get_seqno; + ring->set_seqno = gen8_set_seqno; + } ring->emit_request = gen8_emit_request; ring->emit_flush = gen8_emit_flush_render; ring->irq_get = gen8_logical_ring_get_irq; @@ -1904,8 +2023,13 @@ static int logical_bsd_ring_init(struct drm_device *dev) GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT; ring->init_hw = gen8_init_common_ring; - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; + if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) { + ring->get_seqno = bxt_a_get_seqno; + ring->set_seqno = bxt_a_set_seqno; + } else { + ring->get_seqno = gen8_get_seqno; + ring->set_seqno = gen8_set_seqno; + } ring->emit_request = gen8_emit_request; ring->emit_flush = gen8_emit_flush; ring->irq_get = gen8_logical_ring_get_irq; @@ -1954,8 +2078,13 @@ static int logical_blt_ring_init(struct drm_device *dev) GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT; ring->init_hw = gen8_init_common_ring; - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; + if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) { + ring->get_seqno = bxt_a_get_seqno; + ring->set_seqno = bxt_a_set_seqno; + } else { + ring->get_seqno = gen8_get_seqno; + ring->set_seqno = gen8_set_seqno; + } ring->emit_request = gen8_emit_request; ring->emit_flush = gen8_emit_flush; ring->irq_get = gen8_logical_ring_get_irq; @@ -1979,8 +2108,13 @@ static int logical_vebox_ring_init(struct drm_device *dev) GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT; ring->init_hw = gen8_init_common_ring; - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; + if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0) { + ring->get_seqno = bxt_a_get_seqno; + ring->set_seqno = bxt_a_set_seqno; + } else { + ring->get_seqno = gen8_get_seqno; + ring->set_seqno = gen8_set_seqno; + } ring->emit_request = gen8_emit_request; ring->emit_flush = gen8_emit_flush; ring->irq_get = gen8_logical_ring_get_irq; @@ -2033,14 +2167,8 @@ int intel_logical_rings_init(struct drm_device *dev) goto cleanup_vebox_ring; } - ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000)); - if (ret) - goto cleanup_bsd2_ring; - return 0; -cleanup_bsd2_ring: - intel_logical_ring_cleanup(&dev_priv->ring[VCS2]); cleanup_vebox_ring: intel_logical_ring_cleanup(&dev_priv->ring[VECS]); cleanup_blt_ring: @@ -2126,7 +2254,7 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o /* The second page of the context object contains some fields which must * be set up prior to the first execution. */ - page = i915_gem_object_get_page(ctx_obj, 1); + page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN); reg_state = kmap_atomic(page); /* A context is actually a big batch buffer with several MI_LOAD_REGISTER_IMM @@ -2203,13 +2331,24 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0); reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0); - /* With dynamic page allocation, PDPs may not be allocated at this point, - * Point the unallocated PDPs to the scratch page - */ - ASSIGN_CTX_PDP(ppgtt, reg_state, 3); - ASSIGN_CTX_PDP(ppgtt, reg_state, 2); - ASSIGN_CTX_PDP(ppgtt, reg_state, 1); - ASSIGN_CTX_PDP(ppgtt, reg_state, 0); + if (USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) { + /* 64b PPGTT (48bit canonical) + * PDP0_DESCRIPTOR contains the base address to PML4 and + * other PDP Descriptors are ignored. + */ + ASSIGN_CTX_PML4(ppgtt, reg_state); + } else { + /* 32b PPGTT + * PDP*_DESCRIPTOR contains the base address of space supported. + * With dynamic page allocation, PDPs may not be allocated at + * this point. Point the unallocated PDPs to the scratch page + */ + ASSIGN_CTX_PDP(ppgtt, reg_state, 3); + ASSIGN_CTX_PDP(ppgtt, reg_state, 2); + ASSIGN_CTX_PDP(ppgtt, reg_state, 1); + ASSIGN_CTX_PDP(ppgtt, reg_state, 0); + } + if (ring->id == RCS) { reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1); reg_state[CTX_R_PWR_CLK_STATE] = GEN8_R_PWR_CLK_STATE; @@ -2250,8 +2389,7 @@ void intel_lr_context_free(struct intel_context *ctx) i915_gem_object_ggtt_unpin(ctx_obj); } WARN_ON(ctx->engine[ring->id].pin_count); - intel_destroy_ringbuffer_obj(ringbuf); - kfree(ringbuf); + intel_ringbuffer_free(ringbuf); drm_gem_object_unreference(&ctx_obj->base); } } @@ -2285,12 +2423,13 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring, struct drm_i915_gem_object *default_ctx_obj) { struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct page *page; - /* The status page is offset 0 from the default context object - * in LRC mode. */ - ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(default_ctx_obj); - ring->status_page.page_addr = - kmap(sg_page(default_ctx_obj->pages->sgl)); + /* The HWSP is part of the default context object in LRC mode. */ + ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(default_ctx_obj) + + LRC_PPHWSP_PN * PAGE_SIZE; + page = i915_gem_object_get_page(default_ctx_obj, LRC_PPHWSP_PN); + ring->status_page.page_addr = kmap(page); ring->status_page.obj = default_ctx_obj; I915_WRITE(RING_HWS_PGA(ring->mmio_base), @@ -2299,7 +2438,7 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring, } /** - * intel_lr_context_deferred_create() - create the LRC specific bits of a context + * intel_lr_context_deferred_alloc() - create the LRC specific bits of a context * @ctx: LR context to create. * @ring: engine to be used with the context. * @@ -2311,10 +2450,10 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring, * * Return: non-zero on error. */ -int intel_lr_context_deferred_create(struct intel_context *ctx, + +int intel_lr_context_deferred_alloc(struct intel_context *ctx, struct intel_engine_cs *ring) { - const bool is_global_default_ctx = (ctx == ring->default_context); struct drm_device *dev = ring->dev; struct drm_i915_gem_object *ctx_obj; uint32_t context_size; @@ -2326,107 +2465,58 @@ int intel_lr_context_deferred_create(struct intel_context *ctx, context_size = round_up(get_lr_context_size(ring), 4096); + /* One extra page as the sharing data between driver and GuC */ + context_size += PAGE_SIZE * LRC_PPHWSP_PN; + ctx_obj = i915_gem_alloc_object(dev, context_size); if (!ctx_obj) { DRM_DEBUG_DRIVER("Alloc LRC backing obj failed.\n"); return -ENOMEM; } - if (is_global_default_ctx) { - ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, 0); - if (ret) { - DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n", - ret); - drm_gem_object_unreference(&ctx_obj->base); - return ret; - } - } - - ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL); - if (!ringbuf) { - DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n", - ring->name); - ret = -ENOMEM; - goto error_unpin_ctx; - } - - ringbuf->ring = ring; - - ringbuf->size = 32 * PAGE_SIZE; - ringbuf->effective_size = ringbuf->size; - ringbuf->head = 0; - ringbuf->tail = 0; - ringbuf->last_retired_head = -1; - intel_ring_update_space(ringbuf); - - if (ringbuf->obj == NULL) { - ret = intel_alloc_ringbuffer_obj(dev, ringbuf); - if (ret) { - DRM_DEBUG_DRIVER( - "Failed to allocate ringbuffer obj %s: %d\n", - ring->name, ret); - goto error_free_rbuf; - } - - if (is_global_default_ctx) { - ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf); - if (ret) { - DRM_ERROR( - "Failed to pin and map ringbuffer %s: %d\n", - ring->name, ret); - goto error_destroy_rbuf; - } - } - + ringbuf = intel_engine_create_ringbuffer(ring, 4 * PAGE_SIZE); + if (IS_ERR(ringbuf)) { + ret = PTR_ERR(ringbuf); + goto error_deref_obj; } ret = populate_lr_context(ctx, ctx_obj, ring, ringbuf); if (ret) { DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret); - goto error; + goto error_ringbuf; } ctx->engine[ring->id].ringbuf = ringbuf; ctx->engine[ring->id].state = ctx_obj; - if (ctx == ring->default_context) - lrc_setup_hardware_status_page(ring, ctx_obj); - else if (ring->id == RCS && !ctx->rcs_initialized) { - if (ring->init_context) { - struct drm_i915_gem_request *req; + if (ctx != ring->default_context && ring->init_context) { + struct drm_i915_gem_request *req; - ret = i915_gem_request_alloc(ring, ctx, &req); - if (ret) - return ret; - - ret = ring->init_context(req); - if (ret) { - DRM_ERROR("ring init context: %d\n", ret); - i915_gem_request_cancel(req); - ctx->engine[ring->id].ringbuf = NULL; - ctx->engine[ring->id].state = NULL; - goto error; - } - - i915_add_request_no_flush(req); + ret = i915_gem_request_alloc(ring, + ctx, &req); + if (ret) { + DRM_ERROR("ring create req: %d\n", + ret); + goto error_ringbuf; } - ctx->rcs_initialized = true; + ret = ring->init_context(req); + if (ret) { + DRM_ERROR("ring init context: %d\n", + ret); + i915_gem_request_cancel(req); + goto error_ringbuf; + } + i915_add_request_no_flush(req); } - return 0; -error: - if (is_global_default_ctx) - intel_unpin_ringbuffer_obj(ringbuf); -error_destroy_rbuf: - intel_destroy_ringbuffer_obj(ringbuf); -error_free_rbuf: - kfree(ringbuf); -error_unpin_ctx: - if (is_global_default_ctx) - i915_gem_object_ggtt_unpin(ctx_obj); +error_ringbuf: + intel_ringbuffer_free(ringbuf); +error_deref_obj: drm_gem_object_unreference(&ctx_obj->base); + ctx->engine[ring->id].ringbuf = NULL; + ctx->engine[ring->id].state = NULL; return ret; } @@ -2452,7 +2542,7 @@ void intel_lr_context_reset(struct drm_device *dev, WARN(1, "Failed get_pages for context obj\n"); continue; } - page = i915_gem_object_get_page(ctx_obj, 1); + page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN); reg_state = kmap_atomic(page); reg_state[CTX_RING_HEAD+1] = 0; diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index 64f89f99..4e60d54 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -25,15 +25,19 @@ #define _INTEL_LRC_H_ #define GEN8_LR_CONTEXT_ALIGN 4096 +#define GEN8_CSB_ENTRIES 6 +#define GEN8_CSB_PTR_MASK 0x07 /* Execlists regs */ #define RING_ELSP(ring) ((ring)->mmio_base+0x230) -#define RING_EXECLIST_STATUS(ring) ((ring)->mmio_base+0x234) +#define RING_EXECLIST_STATUS_LO(ring) ((ring)->mmio_base+0x234) +#define RING_EXECLIST_STATUS_HI(ring) ((ring)->mmio_base+0x234 + 4) #define RING_CONTEXT_CONTROL(ring) ((ring)->mmio_base+0x244) #define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH (1 << 3) #define CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT (1 << 0) #define CTX_CTRL_RS_CTX_ENABLE (1 << 1) -#define RING_CONTEXT_STATUS_BUF(ring) ((ring)->mmio_base+0x370) +#define RING_CONTEXT_STATUS_BUF_LO(ring, i) ((ring)->mmio_base+0x370 + (i) * 8) +#define RING_CONTEXT_STATUS_BUF_HI(ring, i) ((ring)->mmio_base+0x370 + (i) * 8 + 4) #define RING_CONTEXT_STATUS_PTR(ring) ((ring)->mmio_base+0x3a0) /* Logical Rings */ @@ -68,12 +72,20 @@ static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf, } /* Logical Ring Contexts */ + +/* One extra page is added before LRC for GuC as shared data */ +#define LRC_GUCSHR_PN (0) +#define LRC_PPHWSP_PN (LRC_GUCSHR_PN + 1) +#define LRC_STATE_PN (LRC_PPHWSP_PN + 1) + void intel_lr_context_free(struct intel_context *ctx); -int intel_lr_context_deferred_create(struct intel_context *ctx, - struct intel_engine_cs *ring); +int intel_lr_context_deferred_alloc(struct intel_context *ctx, + struct intel_engine_cs *ring); void intel_lr_context_unpin(struct drm_i915_gem_request *req); void intel_lr_context_reset(struct drm_device *dev, struct intel_context *ctx); +uint64_t intel_lr_context_descriptor(struct intel_context *ctx, + struct intel_engine_cs *ring); /* Execlists */ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists); diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 881b5d1..5e70acf 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -139,8 +139,7 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder) struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - const struct drm_display_mode *adjusted_mode = - &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; int pipe = crtc->pipe; u32 temp; @@ -289,11 +288,14 @@ intel_lvds_mode_valid(struct drm_connector *connector, { struct intel_connector *intel_connector = to_intel_connector(connector); struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode; + int max_pixclk = to_i915(connector->dev)->max_dotclk_freq; if (mode->hdisplay > fixed_mode->hdisplay) return MODE_PANEL; if (mode->vdisplay > fixed_mode->vdisplay) return MODE_PANEL; + if (fixed_mode->clock > max_pixclk) + return MODE_CLOCK_HIGH; return MODE_OK; } @@ -952,7 +954,7 @@ void intel_lvds_init(struct drm_device *dev) if (HAS_PCH_SPLIT(dev)) { I915_WRITE(PCH_PP_CONTROL, I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS); - } else { + } else if (INTEL_INFO(dev_priv)->gen < 5) { I915_WRITE(PP_CONTROL, I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); } @@ -982,6 +984,18 @@ void intel_lvds_init(struct drm_device *dev) DRM_DEBUG_KMS("LVDS is not present in VBT, but enabled anyway\n"); } + /* Set the Panel Power On/Off timings if uninitialized. */ + if (INTEL_INFO(dev_priv)->gen < 5 && + I915_READ(PP_ON_DELAYS) == 0 && I915_READ(PP_OFF_DELAYS) == 0) { + /* Set T2 to 40ms and T5 to 200ms */ + I915_WRITE(PP_ON_DELAYS, 0x019007d0); + + /* Set T3 to 35ms and Tx to 200ms */ + I915_WRITE(PP_OFF_DELAYS, 0x015e07d0); + + DRM_DEBUG_KMS("Panel power timings uninitialized, setting defaults\n"); + } + lvds_encoder = kzalloc(sizeof(*lvds_encoder), GFP_KERNEL); if (!lvds_encoder) return; diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index 0e860f3..38a4c8c 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -126,3 +126,12 @@ intel_attach_broadcast_rgb_property(struct drm_connector *connector) drm_object_attach_property(&connector->base, prop, 0); } + +void +intel_attach_aspect_ratio_property(struct drm_connector *connector) +{ + if (!drm_mode_create_aspect_ratio_property(connector->dev)) + drm_object_attach_property(&connector->base, + connector->dev->mode_config.aspect_ratio_property, + DRM_MODE_PICTURE_ASPECT_NONE); +} diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index cb1c657..b706b4e 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -341,8 +341,12 @@ int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder, if (!HAS_DDI(dev)) return 0; - port = intel_ddi_get_encoder_port(intel_encoder); - if (port == PORT_E) { + if (intel_encoder->type == INTEL_OUTPUT_DSI) + port = 0; + else + port = intel_ddi_get_encoder_port(intel_encoder); + + if (port == PORT_E) { port = 0; } else { parm |= 1 << port; @@ -363,6 +367,7 @@ int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder, type = DISPLAY_TYPE_EXTERNAL_FLAT_PANEL; break; case INTEL_OUTPUT_EDP: + case INTEL_OUTPUT_DSI: type = DISPLAY_TYPE_INTERNAL_FLAT_PANEL; break; default: diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index e2ab3f6..f30c996 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -105,59 +105,55 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc, struct intel_crtc_state *pipe_config, int fitting_mode) { - struct drm_display_mode *adjusted_mode; - int x, y, width, height; - - adjusted_mode = &pipe_config->base.adjusted_mode; - - x = y = width = height = 0; + const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + int x = 0, y = 0, width = 0, height = 0; /* Native modes don't need fitting */ - if (adjusted_mode->hdisplay == pipe_config->pipe_src_w && - adjusted_mode->vdisplay == pipe_config->pipe_src_h) + if (adjusted_mode->crtc_hdisplay == pipe_config->pipe_src_w && + adjusted_mode->crtc_vdisplay == pipe_config->pipe_src_h) goto done; switch (fitting_mode) { case DRM_MODE_SCALE_CENTER: width = pipe_config->pipe_src_w; height = pipe_config->pipe_src_h; - x = (adjusted_mode->hdisplay - width + 1)/2; - y = (adjusted_mode->vdisplay - height + 1)/2; + x = (adjusted_mode->crtc_hdisplay - width + 1)/2; + y = (adjusted_mode->crtc_vdisplay - height + 1)/2; break; case DRM_MODE_SCALE_ASPECT: /* Scale but preserve the aspect ratio */ { - u32 scaled_width = adjusted_mode->hdisplay + u32 scaled_width = adjusted_mode->crtc_hdisplay * pipe_config->pipe_src_h; u32 scaled_height = pipe_config->pipe_src_w - * adjusted_mode->vdisplay; + * adjusted_mode->crtc_vdisplay; if (scaled_width > scaled_height) { /* pillar */ width = scaled_height / pipe_config->pipe_src_h; if (width & 1) width++; - x = (adjusted_mode->hdisplay - width + 1) / 2; + x = (adjusted_mode->crtc_hdisplay - width + 1) / 2; y = 0; - height = adjusted_mode->vdisplay; + height = adjusted_mode->crtc_vdisplay; } else if (scaled_width < scaled_height) { /* letter */ height = scaled_width / pipe_config->pipe_src_w; if (height & 1) height++; - y = (adjusted_mode->vdisplay - height + 1) / 2; + y = (adjusted_mode->crtc_vdisplay - height + 1) / 2; x = 0; - width = adjusted_mode->hdisplay; + width = adjusted_mode->crtc_hdisplay; } else { x = y = 0; - width = adjusted_mode->hdisplay; - height = adjusted_mode->vdisplay; + width = adjusted_mode->crtc_hdisplay; + height = adjusted_mode->crtc_vdisplay; } } break; case DRM_MODE_SCALE_FULLSCREEN: x = y = 0; - width = adjusted_mode->hdisplay; - height = adjusted_mode->vdisplay; + width = adjusted_mode->crtc_hdisplay; + height = adjusted_mode->crtc_vdisplay; break; default: @@ -172,46 +168,46 @@ done: } static void -centre_horizontally(struct drm_display_mode *mode, +centre_horizontally(struct drm_display_mode *adjusted_mode, int width) { u32 border, sync_pos, blank_width, sync_width; /* keep the hsync and hblank widths constant */ - sync_width = mode->crtc_hsync_end - mode->crtc_hsync_start; - blank_width = mode->crtc_hblank_end - mode->crtc_hblank_start; + sync_width = adjusted_mode->crtc_hsync_end - adjusted_mode->crtc_hsync_start; + blank_width = adjusted_mode->crtc_hblank_end - adjusted_mode->crtc_hblank_start; sync_pos = (blank_width - sync_width + 1) / 2; - border = (mode->hdisplay - width + 1) / 2; + border = (adjusted_mode->crtc_hdisplay - width + 1) / 2; border += border & 1; /* make the border even */ - mode->crtc_hdisplay = width; - mode->crtc_hblank_start = width + border; - mode->crtc_hblank_end = mode->crtc_hblank_start + blank_width; + adjusted_mode->crtc_hdisplay = width; + adjusted_mode->crtc_hblank_start = width + border; + adjusted_mode->crtc_hblank_end = adjusted_mode->crtc_hblank_start + blank_width; - mode->crtc_hsync_start = mode->crtc_hblank_start + sync_pos; - mode->crtc_hsync_end = mode->crtc_hsync_start + sync_width; + adjusted_mode->crtc_hsync_start = adjusted_mode->crtc_hblank_start + sync_pos; + adjusted_mode->crtc_hsync_end = adjusted_mode->crtc_hsync_start + sync_width; } static void -centre_vertically(struct drm_display_mode *mode, +centre_vertically(struct drm_display_mode *adjusted_mode, int height) { u32 border, sync_pos, blank_width, sync_width; /* keep the vsync and vblank widths constant */ - sync_width = mode->crtc_vsync_end - mode->crtc_vsync_start; - blank_width = mode->crtc_vblank_end - mode->crtc_vblank_start; + sync_width = adjusted_mode->crtc_vsync_end - adjusted_mode->crtc_vsync_start; + blank_width = adjusted_mode->crtc_vblank_end - adjusted_mode->crtc_vblank_start; sync_pos = (blank_width - sync_width + 1) / 2; - border = (mode->vdisplay - height + 1) / 2; + border = (adjusted_mode->crtc_vdisplay - height + 1) / 2; - mode->crtc_vdisplay = height; - mode->crtc_vblank_start = height + border; - mode->crtc_vblank_end = mode->crtc_vblank_start + blank_width; + adjusted_mode->crtc_vdisplay = height; + adjusted_mode->crtc_vblank_start = height + border; + adjusted_mode->crtc_vblank_end = adjusted_mode->crtc_vblank_start + blank_width; - mode->crtc_vsync_start = mode->crtc_vblank_start + sync_pos; - mode->crtc_vsync_end = mode->crtc_vsync_start + sync_width; + adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vblank_start + sync_pos; + adjusted_mode->crtc_vsync_end = adjusted_mode->crtc_vsync_start + sync_width; } static inline u32 panel_fitter_scaling(u32 source, u32 target) @@ -230,11 +226,11 @@ static inline u32 panel_fitter_scaling(u32 source, u32 target) static void i965_scale_aspect(struct intel_crtc_state *pipe_config, u32 *pfit_control) { - struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; - u32 scaled_width = adjusted_mode->hdisplay * + const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + u32 scaled_width = adjusted_mode->crtc_hdisplay * pipe_config->pipe_src_h; u32 scaled_height = pipe_config->pipe_src_w * - adjusted_mode->vdisplay; + adjusted_mode->crtc_vdisplay; /* 965+ is easy, it does everything in hw */ if (scaled_width > scaled_height) @@ -243,7 +239,7 @@ static void i965_scale_aspect(struct intel_crtc_state *pipe_config, else if (scaled_width < scaled_height) *pfit_control |= PFIT_ENABLE | PFIT_SCALING_LETTER; - else if (adjusted_mode->hdisplay != pipe_config->pipe_src_w) + else if (adjusted_mode->crtc_hdisplay != pipe_config->pipe_src_w) *pfit_control |= PFIT_ENABLE | PFIT_SCALING_AUTO; } @@ -252,10 +248,10 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config, u32 *border) { struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; - u32 scaled_width = adjusted_mode->hdisplay * + u32 scaled_width = adjusted_mode->crtc_hdisplay * pipe_config->pipe_src_h; u32 scaled_height = pipe_config->pipe_src_w * - adjusted_mode->vdisplay; + adjusted_mode->crtc_vdisplay; u32 bits; /* @@ -269,9 +265,9 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config, pipe_config->pipe_src_h); *border = LVDS_BORDER_ENABLE; - if (pipe_config->pipe_src_h != adjusted_mode->vdisplay) { + if (pipe_config->pipe_src_h != adjusted_mode->crtc_vdisplay) { bits = panel_fitter_scaling(pipe_config->pipe_src_h, - adjusted_mode->vdisplay); + adjusted_mode->crtc_vdisplay); *pfit_pgm_ratios |= (bits << PFIT_HORIZ_SCALE_SHIFT | bits << PFIT_VERT_SCALE_SHIFT); @@ -285,9 +281,9 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config, pipe_config->pipe_src_w); *border = LVDS_BORDER_ENABLE; - if (pipe_config->pipe_src_w != adjusted_mode->hdisplay) { + if (pipe_config->pipe_src_w != adjusted_mode->crtc_hdisplay) { bits = panel_fitter_scaling(pipe_config->pipe_src_w, - adjusted_mode->hdisplay); + adjusted_mode->crtc_hdisplay); *pfit_pgm_ratios |= (bits << PFIT_HORIZ_SCALE_SHIFT | bits << PFIT_VERT_SCALE_SHIFT); @@ -310,13 +306,11 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc, { struct drm_device *dev = intel_crtc->base.dev; u32 pfit_control = 0, pfit_pgm_ratios = 0, border = 0; - struct drm_display_mode *adjusted_mode; - - adjusted_mode = &pipe_config->base.adjusted_mode; + struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; /* Native modes don't need fitting */ - if (adjusted_mode->hdisplay == pipe_config->pipe_src_w && - adjusted_mode->vdisplay == pipe_config->pipe_src_h) + if (adjusted_mode->crtc_hdisplay == pipe_config->pipe_src_w && + adjusted_mode->crtc_vdisplay == pipe_config->pipe_src_h) goto out; switch (fitting_mode) { @@ -342,8 +336,8 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc, * Full scaling, even if it changes the aspect ratio. * Fortunately this is all done for us in hw. */ - if (pipe_config->pipe_src_h != adjusted_mode->vdisplay || - pipe_config->pipe_src_w != adjusted_mode->hdisplay) { + if (pipe_config->pipe_src_h != adjusted_mode->crtc_vdisplay || + pipe_config->pipe_src_w != adjusted_mode->crtc_hdisplay) { pfit_control |= PFIT_ENABLE; if (INTEL_INFO(dev)->gen >= 4) pfit_control |= PFIT_SCALING_AUTO; @@ -484,7 +478,7 @@ static u32 intel_panel_compute_brightness(struct intel_connector *connector, return val; } -static u32 bdw_get_backlight(struct intel_connector *connector) +static u32 lpt_get_backlight(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -542,9 +536,10 @@ static u32 vlv_get_backlight(struct intel_connector *connector) static u32 bxt_get_backlight(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; + struct intel_panel *panel = &connector->panel; struct drm_i915_private *dev_priv = dev->dev_private; - return I915_READ(BXT_BLC_PWM_DUTY1); + return I915_READ(BXT_BLC_PWM_DUTY(panel->backlight.controller)); } static u32 pwm_get_backlight(struct intel_connector *connector) @@ -566,7 +561,7 @@ static u32 intel_panel_get_backlight(struct intel_connector *connector) mutex_lock(&dev_priv->backlight_lock); if (panel->backlight.enabled) { - val = dev_priv->display.get_backlight(connector); + val = panel->backlight.get(connector); val = intel_panel_compute_brightness(connector, val); } @@ -576,7 +571,7 @@ static u32 intel_panel_get_backlight(struct intel_connector *connector) return val; } -static void bdw_set_backlight(struct intel_connector *connector, u32 level) +static void lpt_set_backlight(struct intel_connector *connector, u32 level) { struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -640,8 +635,9 @@ static void bxt_set_backlight(struct intel_connector *connector, u32 level) { struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_panel *panel = &connector->panel; - I915_WRITE(BXT_BLC_PWM_DUTY1, level); + I915_WRITE(BXT_BLC_PWM_DUTY(panel->backlight.controller), level); } static void pwm_set_backlight(struct intel_connector *connector, u32 level) @@ -655,13 +651,12 @@ static void pwm_set_backlight(struct intel_connector *connector, u32 level) static void intel_panel_actually_set_backlight(struct intel_connector *connector, u32 level) { - struct drm_device *dev = connector->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_panel *panel = &connector->panel; DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level); level = intel_panel_compute_brightness(connector, level); - dev_priv->display.set_backlight(connector, level); + panel->backlight.set(connector, level); } /* set backlight brightness to level in range [0..max], scaling wrt hw min */ @@ -729,6 +724,18 @@ void intel_panel_set_backlight_acpi(struct intel_connector *connector, mutex_unlock(&dev_priv->backlight_lock); } +static void lpt_disable_backlight(struct intel_connector *connector) +{ + struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 tmp; + + intel_panel_actually_set_backlight(connector, 0); + + tmp = I915_READ(BLC_PWM_PCH_CTL1); + I915_WRITE(BLC_PWM_PCH_CTL1, tmp & ~BLM_PCH_PWM_ENABLE); +} + static void pch_disable_backlight(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; @@ -781,12 +788,20 @@ static void bxt_disable_backlight(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - u32 tmp; + struct intel_panel *panel = &connector->panel; + u32 tmp, val; intel_panel_actually_set_backlight(connector, 0); - tmp = I915_READ(BXT_BLC_PWM_CTL1); - I915_WRITE(BXT_BLC_PWM_CTL1, tmp & ~BXT_BLC_PWM_ENABLE); + tmp = I915_READ(BXT_BLC_PWM_CTL(panel->backlight.controller)); + I915_WRITE(BXT_BLC_PWM_CTL(panel->backlight.controller), + tmp & ~BXT_BLC_PWM_ENABLE); + + if (panel->backlight.controller == 1) { + val = I915_READ(UTIL_PIN_CTL); + val &= ~UTIL_PIN_ENABLE; + I915_WRITE(UTIL_PIN_CTL, val); + } } static void pwm_disable_backlight(struct intel_connector *connector) @@ -809,7 +824,7 @@ void intel_panel_disable_backlight(struct intel_connector *connector) return; /* - * Do not disable backlight on the vgaswitcheroo path. When switching + * Do not disable backlight on the vga_switcheroo path. When switching * away from i915, the other client may depend on i915 to handle the * backlight. This will leave the backlight on unnecessarily when * another client is not activated. @@ -824,12 +839,12 @@ void intel_panel_disable_backlight(struct intel_connector *connector) if (panel->backlight.device) panel->backlight.device->props.power = FB_BLANK_POWERDOWN; panel->backlight.enabled = false; - dev_priv->display.disable_backlight(connector); + panel->backlight.disable(connector); mutex_unlock(&dev_priv->backlight_lock); } -static void bdw_enable_backlight(struct intel_connector *connector) +static void lpt_enable_backlight(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1018,16 +1033,38 @@ static void bxt_enable_backlight(struct intel_connector *connector) struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_panel *panel = &connector->panel; - u32 pwm_ctl; + enum pipe pipe = intel_get_pipe_from_connector(connector); + u32 pwm_ctl, val; + + /* To use 2nd set of backlight registers, utility pin has to be + * enabled with PWM mode. + * The field should only be changed when the utility pin is disabled + */ + if (panel->backlight.controller == 1) { + val = I915_READ(UTIL_PIN_CTL); + if (val & UTIL_PIN_ENABLE) { + DRM_DEBUG_KMS("util pin already enabled\n"); + val &= ~UTIL_PIN_ENABLE; + I915_WRITE(UTIL_PIN_CTL, val); + } - pwm_ctl = I915_READ(BXT_BLC_PWM_CTL1); + val = 0; + if (panel->backlight.util_pin_active_low) + val |= UTIL_PIN_POLARITY; + I915_WRITE(UTIL_PIN_CTL, val | UTIL_PIN_PIPE(pipe) | + UTIL_PIN_MODE_PWM | UTIL_PIN_ENABLE); + } + + pwm_ctl = I915_READ(BXT_BLC_PWM_CTL(panel->backlight.controller)); if (pwm_ctl & BXT_BLC_PWM_ENABLE) { DRM_DEBUG_KMS("backlight already enabled\n"); pwm_ctl &= ~BXT_BLC_PWM_ENABLE; - I915_WRITE(BXT_BLC_PWM_CTL1, pwm_ctl); + I915_WRITE(BXT_BLC_PWM_CTL(panel->backlight.controller), + pwm_ctl); } - I915_WRITE(BXT_BLC_PWM_FREQ1, panel->backlight.max); + I915_WRITE(BXT_BLC_PWM_FREQ(panel->backlight.controller), + panel->backlight.max); intel_panel_actually_set_backlight(connector, panel->backlight.level); @@ -1035,9 +1072,10 @@ static void bxt_enable_backlight(struct intel_connector *connector) if (panel->backlight.active_low_pwm) pwm_ctl |= BXT_BLC_PWM_POLARITY; - I915_WRITE(BXT_BLC_PWM_CTL1, pwm_ctl); - POSTING_READ(BXT_BLC_PWM_CTL1); - I915_WRITE(BXT_BLC_PWM_CTL1, pwm_ctl | BXT_BLC_PWM_ENABLE); + I915_WRITE(BXT_BLC_PWM_CTL(panel->backlight.controller), pwm_ctl); + POSTING_READ(BXT_BLC_PWM_CTL(panel->backlight.controller)); + I915_WRITE(BXT_BLC_PWM_CTL(panel->backlight.controller), + pwm_ctl | BXT_BLC_PWM_ENABLE); } static void pwm_enable_backlight(struct intel_connector *connector) @@ -1073,7 +1111,7 @@ void intel_panel_enable_backlight(struct intel_connector *connector) panel->backlight.device->props.max_brightness); } - dev_priv->display.enable_backlight(connector); + panel->backlight.enable(connector); panel->backlight.enabled = true; if (panel->backlight.device) panel->backlight.device->props.power = FB_BLANK_UNBLANK; @@ -1101,10 +1139,10 @@ static int intel_backlight_device_update_status(struct backlight_device *bd) * callback needs to take this into account. */ if (panel->backlight.enabled) { - if (panel->backlight_power) { + if (panel->backlight.power) { bool enable = bd->props.power == FB_BLANK_UNBLANK && bd->props.brightness != 0; - panel->backlight_power(connector, enable); + panel->backlight.power(connector, enable); } } else { bd->props.power = FB_BLANK_POWERDOWN; @@ -1212,10 +1250,150 @@ static void intel_backlight_device_unregister(struct intel_connector *connector) #endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */ /* - * Note: The setup hooks can't assume pipe is set! + * SPT: This value represents the period of the PWM stream in clock periods + * multiplied by 16 (default increment) or 128 (alternate increment selected in + * SCHICKEN_1 bit 0). PWM clock is 24 MHz. + */ +static u32 spt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) +{ + struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 mul, clock; + + if (I915_READ(SOUTH_CHICKEN1) & SPT_PWM_GRANULARITY) + mul = 128; + else + mul = 16; + + clock = MHz(24); + + return clock / (pwm_freq_hz * mul); +} + +/* + * LPT: This value represents the period of the PWM stream in clock periods + * multiplied by 128 (default increment) or 16 (alternate increment, selected in + * LPT SOUTH_CHICKEN2 register bit 5). + */ +static u32 lpt_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) +{ + struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 mul, clock; + + if (I915_READ(SOUTH_CHICKEN2) & LPT_PWM_GRANULARITY) + mul = 16; + else + mul = 128; + + if (dev_priv->pch_id == INTEL_PCH_LPT_DEVICE_ID_TYPE) + clock = MHz(135); /* LPT:H */ + else + clock = MHz(24); /* LPT:LP */ + + return clock / (pwm_freq_hz * mul); +} + +/* + * ILK/SNB/IVB: This value represents the period of the PWM stream in PCH + * display raw clocks multiplied by 128. + */ +static u32 pch_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) +{ + struct drm_device *dev = connector->base.dev; + int clock = MHz(intel_pch_rawclk(dev)); + + return clock / (pwm_freq_hz * 128); +} + +/* + * Gen2: This field determines the number of time base events (display core + * clock frequency/32) in total for a complete cycle of modulated backlight + * control. * - * XXX: Query mode clock or hardware clock and program PWM modulation frequency - * appropriately when it's 0. Use VBT and/or sane defaults. + * Gen3: A time base event equals the display core clock ([DevPNV] HRAW clock) + * divided by 32. + */ +static u32 i9xx_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) +{ + struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int clock; + + if (IS_PINEVIEW(dev)) + clock = intel_hrawclk(dev); + else + clock = 1000 * dev_priv->display.get_display_clock_speed(dev); + + return clock / (pwm_freq_hz * 32); +} + +/* + * Gen4: This value represents the period of the PWM stream in display core + * clocks multiplied by 128. + */ +static u32 i965_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) +{ + struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int clock = 1000 * dev_priv->display.get_display_clock_speed(dev); + + return clock / (pwm_freq_hz * 128); +} + +/* + * VLV: This value represents the period of the PWM stream in display core + * clocks ([DevCTG] 200MHz HRAW clocks) multiplied by 128 or 25MHz S0IX clocks + * multiplied by 16. CHV uses a 19.2MHz S0IX clock. + */ +static u32 vlv_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) +{ + struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int clock; + + if ((I915_READ(CBR1_VLV) & CBR_PWM_CLOCK_MUX_SELECT) == 0) { + if (IS_CHERRYVIEW(dev)) + return KHz(19200) / (pwm_freq_hz * 16); + else + return MHz(25) / (pwm_freq_hz * 16); + } else { + clock = intel_hrawclk(dev); + return MHz(clock) / (pwm_freq_hz * 128); + } +} + +static u32 get_backlight_max_vbt(struct intel_connector *connector) +{ + struct drm_device *dev = connector->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_panel *panel = &connector->panel; + u16 pwm_freq_hz = dev_priv->vbt.backlight.pwm_freq_hz; + u32 pwm; + + if (!pwm_freq_hz) { + DRM_DEBUG_KMS("backlight frequency not specified in VBT\n"); + return 0; + } + + if (!panel->backlight.hz_to_pwm) { + DRM_DEBUG_KMS("backlight frequency setting from VBT currently not supported on this platform\n"); + return 0; + } + + pwm = panel->backlight.hz_to_pwm(connector, pwm_freq_hz); + if (!pwm) { + DRM_DEBUG_KMS("backlight frequency conversion failed\n"); + return 0; + } + + DRM_DEBUG_KMS("backlight frequency %u Hz from VBT\n", pwm_freq_hz); + + return pwm; +} + +/* + * Note: The setup hooks can't assume pipe is set! */ static u32 get_backlight_min_vbt(struct intel_connector *connector) { @@ -1243,7 +1421,7 @@ static u32 get_backlight_min_vbt(struct intel_connector *connector) return scale(min, 0, 255, 0, panel->backlight.max); } -static int bdw_setup_backlight(struct intel_connector *connector, enum pipe unused) +static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unused) { struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1255,12 +1433,16 @@ static int bdw_setup_backlight(struct intel_connector *connector, enum pipe unus pch_ctl2 = I915_READ(BLC_PWM_PCH_CTL2); panel->backlight.max = pch_ctl2 >> 16; + + if (!panel->backlight.max) + panel->backlight.max = get_backlight_max_vbt(connector); + if (!panel->backlight.max) return -ENODEV; panel->backlight.min = get_backlight_min_vbt(connector); - val = bdw_get_backlight(connector); + val = lpt_get_backlight(connector); panel->backlight.level = intel_panel_compute_brightness(connector, val); panel->backlight.enabled = (pch_ctl1 & BLM_PCH_PWM_ENABLE) && @@ -1281,6 +1463,10 @@ static int pch_setup_backlight(struct intel_connector *connector, enum pipe unus pch_ctl2 = I915_READ(BLC_PWM_PCH_CTL2); panel->backlight.max = pch_ctl2 >> 16; + + if (!panel->backlight.max) + panel->backlight.max = get_backlight_max_vbt(connector); + if (!panel->backlight.max) return -ENODEV; @@ -1312,12 +1498,18 @@ static int i9xx_setup_backlight(struct intel_connector *connector, enum pipe unu panel->backlight.active_low_pwm = ctl & BLM_POLARITY_PNV; panel->backlight.max = ctl >> 17; - if (panel->backlight.combination_mode) - panel->backlight.max *= 0xff; + + if (!panel->backlight.max) { + panel->backlight.max = get_backlight_max_vbt(connector); + panel->backlight.max >>= 1; + } if (!panel->backlight.max) return -ENODEV; + if (panel->backlight.combination_mode) + panel->backlight.max *= 0xff; + panel->backlight.min = get_backlight_min_vbt(connector); val = i9xx_get_backlight(connector); @@ -1341,12 +1533,16 @@ static int i965_setup_backlight(struct intel_connector *connector, enum pipe unu ctl = I915_READ(BLC_PWM_CTL); panel->backlight.max = ctl >> 16; - if (panel->backlight.combination_mode) - panel->backlight.max *= 0xff; + + if (!panel->backlight.max) + panel->backlight.max = get_backlight_max_vbt(connector); if (!panel->backlight.max) return -ENODEV; + if (panel->backlight.combination_mode) + panel->backlight.max *= 0xff; + panel->backlight.min = get_backlight_min_vbt(connector); val = i9xx_get_backlight(connector); @@ -1363,21 +1559,8 @@ static int vlv_setup_backlight(struct intel_connector *connector, enum pipe pipe struct drm_device *dev = connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_panel *panel = &connector->panel; - enum pipe p; u32 ctl, ctl2, val; - for_each_pipe(dev_priv, p) { - u32 cur_val = I915_READ(VLV_BLC_PWM_CTL(p)); - - /* Skip if the modulation freq is already set */ - if (cur_val & ~BACKLIGHT_DUTY_CYCLE_MASK) - continue; - - cur_val &= BACKLIGHT_DUTY_CYCLE_MASK; - I915_WRITE(VLV_BLC_PWM_CTL(p), (0xf42 << 16) | - cur_val); - } - if (WARN_ON(pipe != PIPE_A && pipe != PIPE_B)) return -ENODEV; @@ -1386,6 +1569,10 @@ static int vlv_setup_backlight(struct intel_connector *connector, enum pipe pipe ctl = I915_READ(VLV_BLC_PWM_CTL(pipe)); panel->backlight.max = ctl >> 16; + + if (!panel->backlight.max) + panel->backlight.max = get_backlight_max_vbt(connector); + if (!panel->backlight.max) return -ENODEV; @@ -1408,10 +1595,32 @@ bxt_setup_backlight(struct intel_connector *connector, enum pipe unused) struct intel_panel *panel = &connector->panel; u32 pwm_ctl, val; - pwm_ctl = I915_READ(BXT_BLC_PWM_CTL1); + /* + * For BXT hard coding the Backlight controller to 0. + * TODO : Read the controller value from VBT and generalize + */ + panel->backlight.controller = 0; + + pwm_ctl = I915_READ(BXT_BLC_PWM_CTL(panel->backlight.controller)); + + /* Keeping the check if controller 1 is to be programmed. + * This will come into affect once the VBT parsing + * is fixed for controller selection, and controller 1 is used + * for a prticular display configuration. + */ + if (panel->backlight.controller == 1) { + val = I915_READ(UTIL_PIN_CTL); + panel->backlight.util_pin_active_low = + val & UTIL_PIN_POLARITY; + } + panel->backlight.active_low_pwm = pwm_ctl & BXT_BLC_PWM_POLARITY; + panel->backlight.max = + I915_READ(BXT_BLC_PWM_FREQ(panel->backlight.controller)); + + if (!panel->backlight.max) + panel->backlight.max = get_backlight_max_vbt(connector); - panel->backlight.max = I915_READ(BXT_BLC_PWM_FREQ1); if (!panel->backlight.max) return -ENODEV; @@ -1475,9 +1684,13 @@ int intel_panel_setup_backlight(struct drm_connector *connector, enum pipe pipe) } } + /* ensure intel_panel has been initialized first */ + if (WARN_ON(!panel->backlight.setup)) + return -ENODEV; + /* set level and max in panel struct */ mutex_lock(&dev_priv->backlight_lock); - ret = dev_priv->display.setup_backlight(intel_connector, pipe); + ret = panel->backlight.setup(intel_connector, pipe); mutex_unlock(&dev_priv->backlight_lock); if (ret) { @@ -1509,54 +1722,66 @@ void intel_panel_destroy_backlight(struct drm_connector *connector) } /* Set up chip specific backlight functions */ -void intel_panel_init_backlight_funcs(struct drm_device *dev) +static void +intel_panel_init_backlight_funcs(struct intel_panel *panel) { + struct intel_connector *intel_connector = + container_of(panel, struct intel_connector, panel); + struct drm_device *dev = intel_connector->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; if (IS_BROXTON(dev)) { - dev_priv->display.setup_backlight = bxt_setup_backlight; - dev_priv->display.enable_backlight = bxt_enable_backlight; - dev_priv->display.disable_backlight = bxt_disable_backlight; - dev_priv->display.set_backlight = bxt_set_backlight; - dev_priv->display.get_backlight = bxt_get_backlight; - } else if (IS_BROADWELL(dev) || IS_SKYLAKE(dev)) { - dev_priv->display.setup_backlight = bdw_setup_backlight; - dev_priv->display.enable_backlight = bdw_enable_backlight; - dev_priv->display.disable_backlight = pch_disable_backlight; - dev_priv->display.set_backlight = bdw_set_backlight; - dev_priv->display.get_backlight = bdw_get_backlight; + panel->backlight.setup = bxt_setup_backlight; + panel->backlight.enable = bxt_enable_backlight; + panel->backlight.disable = bxt_disable_backlight; + panel->backlight.set = bxt_set_backlight; + panel->backlight.get = bxt_get_backlight; + } else if (HAS_PCH_LPT(dev) || HAS_PCH_SPT(dev)) { + panel->backlight.setup = lpt_setup_backlight; + panel->backlight.enable = lpt_enable_backlight; + panel->backlight.disable = lpt_disable_backlight; + panel->backlight.set = lpt_set_backlight; + panel->backlight.get = lpt_get_backlight; + if (HAS_PCH_LPT(dev)) + panel->backlight.hz_to_pwm = lpt_hz_to_pwm; + else + panel->backlight.hz_to_pwm = spt_hz_to_pwm; } else if (HAS_PCH_SPLIT(dev)) { - dev_priv->display.setup_backlight = pch_setup_backlight; - dev_priv->display.enable_backlight = pch_enable_backlight; - dev_priv->display.disable_backlight = pch_disable_backlight; - dev_priv->display.set_backlight = pch_set_backlight; - dev_priv->display.get_backlight = pch_get_backlight; + panel->backlight.setup = pch_setup_backlight; + panel->backlight.enable = pch_enable_backlight; + panel->backlight.disable = pch_disable_backlight; + panel->backlight.set = pch_set_backlight; + panel->backlight.get = pch_get_backlight; + panel->backlight.hz_to_pwm = pch_hz_to_pwm; } else if (IS_VALLEYVIEW(dev)) { if (dev_priv->vbt.has_mipi) { - dev_priv->display.setup_backlight = pwm_setup_backlight; - dev_priv->display.enable_backlight = pwm_enable_backlight; - dev_priv->display.disable_backlight = pwm_disable_backlight; - dev_priv->display.set_backlight = pwm_set_backlight; - dev_priv->display.get_backlight = pwm_get_backlight; + panel->backlight.setup = pwm_setup_backlight; + panel->backlight.enable = pwm_enable_backlight; + panel->backlight.disable = pwm_disable_backlight; + panel->backlight.set = pwm_set_backlight; + panel->backlight.get = pwm_get_backlight; } else { - dev_priv->display.setup_backlight = vlv_setup_backlight; - dev_priv->display.enable_backlight = vlv_enable_backlight; - dev_priv->display.disable_backlight = vlv_disable_backlight; - dev_priv->display.set_backlight = vlv_set_backlight; - dev_priv->display.get_backlight = vlv_get_backlight; + panel->backlight.setup = vlv_setup_backlight; + panel->backlight.enable = vlv_enable_backlight; + panel->backlight.disable = vlv_disable_backlight; + panel->backlight.set = vlv_set_backlight; + panel->backlight.get = vlv_get_backlight; + panel->backlight.hz_to_pwm = vlv_hz_to_pwm; } } else if (IS_GEN4(dev)) { - dev_priv->display.setup_backlight = i965_setup_backlight; - dev_priv->display.enable_backlight = i965_enable_backlight; - dev_priv->display.disable_backlight = i965_disable_backlight; - dev_priv->display.set_backlight = i9xx_set_backlight; - dev_priv->display.get_backlight = i9xx_get_backlight; + panel->backlight.setup = i965_setup_backlight; + panel->backlight.enable = i965_enable_backlight; + panel->backlight.disable = i965_disable_backlight; + panel->backlight.set = i9xx_set_backlight; + panel->backlight.get = i9xx_get_backlight; + panel->backlight.hz_to_pwm = i965_hz_to_pwm; } else { - dev_priv->display.setup_backlight = i9xx_setup_backlight; - dev_priv->display.enable_backlight = i9xx_enable_backlight; - dev_priv->display.disable_backlight = i9xx_disable_backlight; - dev_priv->display.set_backlight = i9xx_set_backlight; - dev_priv->display.get_backlight = i9xx_get_backlight; + panel->backlight.setup = i9xx_setup_backlight; + panel->backlight.enable = i9xx_enable_backlight; + panel->backlight.disable = i9xx_disable_backlight; + panel->backlight.set = i9xx_set_backlight; + panel->backlight.get = i9xx_get_backlight; + panel->backlight.hz_to_pwm = i9xx_hz_to_pwm; } } @@ -1564,6 +1789,8 @@ int intel_panel_init(struct intel_panel *panel, struct drm_display_mode *fixed_mode, struct drm_display_mode *downclock_mode) { + intel_panel_init_backlight_funcs(panel); + panel->fixed_mode = fixed_mode; panel->downclock_mode = downclock_mode; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index ddbb7ed..d031d74 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -71,20 +71,6 @@ static void skl_init_clock_gating(struct drm_device *dev) gen9_init_clock_gating(dev); - if (INTEL_REVID(dev) <= SKL_REVID_B0) { - /* - * WaDisableSDEUnitClockGating:skl - * WaSetGAPSunitClckGateDisable:skl - */ - I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | - GEN8_GAPSUNIT_CLOCK_GATE_DISABLE | - GEN8_SDEUNIT_CLOCK_GATE_DISABLE); - - /* WaDisableVFUnitClockGating:skl */ - I915_WRITE(GEN6_UCGCTL2, I915_READ(GEN6_UCGCTL2) | - GEN6_VFUNIT_CLOCK_GATE_DISABLE); - } - if (INTEL_REVID(dev) <= SKL_REVID_D0) { /* WaDisableHDCInvalidation:skl */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | @@ -116,18 +102,27 @@ static void bxt_init_clock_gating(struct drm_device *dev) gen9_init_clock_gating(dev); + /* WaDisableSDEUnitClockGating:bxt */ + I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | + GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + /* * FIXME: - * GEN8_SDEUNIT_CLOCK_GATE_DISABLE applies on A0 only. * GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ applies on 3x6 GT SKUs only. */ - /* WaDisableSDEUnitClockGating:bxt */ I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | - GEN8_SDEUNIT_CLOCK_GATE_DISABLE | GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ); - /* FIXME: apply on A0 only */ - I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF); + /* WaStoreMultiplePTEenable:bxt */ + /* This is a requirement according to Hardware specification */ + if (INTEL_REVID(dev) == BXT_REVID_A0) + I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF); + + /* WaSetClckGatingDisableMedia:bxt */ + if (INTEL_REVID(dev) == BXT_REVID_A0) { + I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) & + ~GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE)); + } } static void i915_pineview_get_mem_freq(struct drm_device *dev) @@ -691,12 +686,9 @@ static void pineview_update_wm(struct drm_crtc *unused_crtc) crtc = single_enabled_crtc(dev); if (crtc) { - const struct drm_display_mode *adjusted_mode; + const struct drm_display_mode *adjusted_mode = &to_intel_crtc(crtc)->config->base.adjusted_mode; int pixel_size = crtc->primary->state->fb->bits_per_pixel / 8; - int clock; - - adjusted_mode = &to_intel_crtc(crtc)->config->base.adjusted_mode; - clock = adjusted_mode->crtc_clock; + int clock = adjusted_mode->crtc_clock; /* Display SR */ wm = intel_calculate_wm(clock, &pineview_display_wm, @@ -1490,8 +1482,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc) if (crtc) { /* self-refresh has much higher latency */ static const int sr_latency_ns = 12000; - const struct drm_display_mode *adjusted_mode = - &to_intel_crtc(crtc)->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &to_intel_crtc(crtc)->config->base.adjusted_mode; int clock = adjusted_mode->crtc_clock; int htotal = adjusted_mode->crtc_htotal; int hdisplay = to_intel_crtc(crtc)->config->pipe_src_w; @@ -1638,8 +1629,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc) if (HAS_FW_BLC(dev) && enabled) { /* self-refresh has much higher latency */ static const int sr_latency_ns = 6000; - const struct drm_display_mode *adjusted_mode = - &to_intel_crtc(enabled)->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &to_intel_crtc(enabled)->config->base.adjusted_mode; int clock = adjusted_mode->crtc_clock; int htotal = adjusted_mode->crtc_htotal; int hdisplay = to_intel_crtc(enabled)->config->pipe_src_w; @@ -1775,23 +1765,6 @@ static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels, return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2; } -struct skl_pipe_wm_parameters { - bool active; - uint32_t pipe_htotal; - uint32_t pixel_rate; /* in KHz */ - struct intel_plane_wm_parameters plane[I915_MAX_PLANES]; - struct intel_plane_wm_parameters cursor; -}; - -struct ilk_pipe_wm_parameters { - bool active; - uint32_t pipe_htotal; - uint32_t pixel_rate; - struct intel_plane_wm_parameters pri; - struct intel_plane_wm_parameters spr; - struct intel_plane_wm_parameters cur; -}; - struct ilk_wm_maximums { uint16_t pri; uint16_t spr; @@ -1810,26 +1783,26 @@ struct intel_wm_config { * For both WM_PIPE and WM_LP. * mem_value must be in 0.1us units. */ -static uint32_t ilk_compute_pri_wm(const struct ilk_pipe_wm_parameters *params, +static uint32_t ilk_compute_pri_wm(const struct intel_crtc_state *cstate, + const struct intel_plane_state *pstate, uint32_t mem_value, bool is_lp) { + int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; uint32_t method1, method2; - if (!params->active || !params->pri.enabled) + if (!cstate->base.active || !pstate->visible) return 0; - method1 = ilk_wm_method1(params->pixel_rate, - params->pri.bytes_per_pixel, - mem_value); + method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), bpp, mem_value); if (!is_lp) return method1; - method2 = ilk_wm_method2(params->pixel_rate, - params->pipe_htotal, - params->pri.horiz_pixels, - params->pri.bytes_per_pixel, + method2 = ilk_wm_method2(ilk_pipe_pixel_rate(cstate), + cstate->base.adjusted_mode.crtc_htotal, + drm_rect_width(&pstate->dst), + bpp, mem_value); return min(method1, method2); @@ -1839,21 +1812,21 @@ static uint32_t ilk_compute_pri_wm(const struct ilk_pipe_wm_parameters *params, * For both WM_PIPE and WM_LP. * mem_value must be in 0.1us units. */ -static uint32_t ilk_compute_spr_wm(const struct ilk_pipe_wm_parameters *params, +static uint32_t ilk_compute_spr_wm(const struct intel_crtc_state *cstate, + const struct intel_plane_state *pstate, uint32_t mem_value) { + int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; uint32_t method1, method2; - if (!params->active || !params->spr.enabled) + if (!cstate->base.active || !pstate->visible) return 0; - method1 = ilk_wm_method1(params->pixel_rate, - params->spr.bytes_per_pixel, - mem_value); - method2 = ilk_wm_method2(params->pixel_rate, - params->pipe_htotal, - params->spr.horiz_pixels, - params->spr.bytes_per_pixel, + method1 = ilk_wm_method1(ilk_pipe_pixel_rate(cstate), bpp, mem_value); + method2 = ilk_wm_method2(ilk_pipe_pixel_rate(cstate), + cstate->base.adjusted_mode.crtc_htotal, + drm_rect_width(&pstate->dst), + bpp, mem_value); return min(method1, method2); } @@ -1862,29 +1835,33 @@ static uint32_t ilk_compute_spr_wm(const struct ilk_pipe_wm_parameters *params, * For both WM_PIPE and WM_LP. * mem_value must be in 0.1us units. */ -static uint32_t ilk_compute_cur_wm(const struct ilk_pipe_wm_parameters *params, +static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate, + const struct intel_plane_state *pstate, uint32_t mem_value) { - if (!params->active || !params->cur.enabled) + int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + + if (!cstate->base.active || !pstate->visible) return 0; - return ilk_wm_method2(params->pixel_rate, - params->pipe_htotal, - params->cur.horiz_pixels, - params->cur.bytes_per_pixel, + return ilk_wm_method2(ilk_pipe_pixel_rate(cstate), + cstate->base.adjusted_mode.crtc_htotal, + drm_rect_width(&pstate->dst), + bpp, mem_value); } /* Only for WM_LP. */ -static uint32_t ilk_compute_fbc_wm(const struct ilk_pipe_wm_parameters *params, +static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate, + const struct intel_plane_state *pstate, uint32_t pri_val) { - if (!params->active || !params->pri.enabled) + int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + + if (!cstate->base.active || !pstate->visible) return 0; - return ilk_wm_fbc(pri_val, - params->pri.horiz_pixels, - params->pri.bytes_per_pixel); + return ilk_wm_fbc(pri_val, drm_rect_width(&pstate->dst), bpp); } static unsigned int ilk_display_fifo_size(const struct drm_device *dev) @@ -2049,10 +2026,12 @@ static bool ilk_validate_wm_level(int level, } static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, + const struct intel_crtc *intel_crtc, int level, - const struct ilk_pipe_wm_parameters *p, + struct intel_crtc_state *cstate, struct intel_wm_level *result) { + struct intel_plane *intel_plane; uint16_t pri_latency = dev_priv->wm.pri_latency[level]; uint16_t spr_latency = dev_priv->wm.spr_latency[level]; uint16_t cur_latency = dev_priv->wm.cur_latency[level]; @@ -2064,10 +2043,29 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, cur_latency *= 5; } - result->pri_val = ilk_compute_pri_wm(p, pri_latency, level); - result->spr_val = ilk_compute_spr_wm(p, spr_latency); - result->cur_val = ilk_compute_cur_wm(p, cur_latency); - result->fbc_val = ilk_compute_fbc_wm(p, result->pri_val); + for_each_intel_plane_on_crtc(dev_priv->dev, intel_crtc, intel_plane) { + struct intel_plane_state *pstate = + to_intel_plane_state(intel_plane->base.state); + + switch (intel_plane->base.type) { + case DRM_PLANE_TYPE_PRIMARY: + result->pri_val = ilk_compute_pri_wm(cstate, pstate, + pri_latency, + level); + result->fbc_val = ilk_compute_fbc_wm(cstate, pstate, + result->pri_val); + break; + case DRM_PLANE_TYPE_OVERLAY: + result->spr_val = ilk_compute_spr_wm(cstate, pstate, + spr_latency); + break; + case DRM_PLANE_TYPE_CURSOR: + result->cur_val = ilk_compute_cur_wm(cstate, pstate, + cur_latency); + break; + } + } + result->enable = true; } @@ -2076,7 +2074,7 @@ hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_display_mode *mode = &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; u32 linetime, ips_linetime; if (!intel_crtc->active) @@ -2085,9 +2083,9 @@ hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc) /* The WM are computed with base on how long it takes to fill a single * row at the given clock rate, multiplied by 8. * */ - linetime = DIV_ROUND_CLOSEST(mode->crtc_htotal * 1000 * 8, - mode->crtc_clock); - ips_linetime = DIV_ROUND_CLOSEST(mode->crtc_htotal * 1000 * 8, + linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8, + adjusted_mode->crtc_clock); + ips_linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8, dev_priv->cdclk_freq); return PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) | @@ -2326,48 +2324,6 @@ static void skl_setup_wm_latency(struct drm_device *dev) intel_print_wm_latency(dev, "Gen9 Plane", dev_priv->wm.skl_latency); } -static void ilk_compute_wm_parameters(struct drm_crtc *crtc, - struct ilk_pipe_wm_parameters *p) -{ - struct drm_device *dev = crtc->dev; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum pipe pipe = intel_crtc->pipe; - struct drm_plane *plane; - - if (!intel_crtc->active) - return; - - p->active = true; - p->pipe_htotal = intel_crtc->config->base.adjusted_mode.crtc_htotal; - p->pixel_rate = ilk_pipe_pixel_rate(intel_crtc->config); - - if (crtc->primary->state->fb) - p->pri.bytes_per_pixel = - crtc->primary->state->fb->bits_per_pixel / 8; - else - p->pri.bytes_per_pixel = 4; - - p->cur.bytes_per_pixel = 4; - /* - * TODO: for now, assume primary and cursor planes are always enabled. - * Setting them to false makes the screen flicker. - */ - p->pri.enabled = true; - p->cur.enabled = true; - - p->pri.horiz_pixels = intel_crtc->config->pipe_src_w; - p->cur.horiz_pixels = intel_crtc->base.cursor->state->crtc_w; - - drm_for_each_legacy_plane(plane, dev) { - struct intel_plane *intel_plane = to_intel_plane(plane); - - if (intel_plane->pipe == pipe) { - p->spr = intel_plane->wm; - break; - } - } -} - static void ilk_compute_wm_config(struct drm_device *dev, struct intel_wm_config *config) { @@ -2387,34 +2343,47 @@ static void ilk_compute_wm_config(struct drm_device *dev, } /* Compute new watermarks for the pipe */ -static bool intel_compute_pipe_wm(struct drm_crtc *crtc, - const struct ilk_pipe_wm_parameters *params, +static bool intel_compute_pipe_wm(struct intel_crtc_state *cstate, struct intel_pipe_wm *pipe_wm) { + struct drm_crtc *crtc = cstate->base.crtc; struct drm_device *dev = crtc->dev; const struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_plane *intel_plane; + struct intel_plane_state *sprstate = NULL; int level, max_level = ilk_wm_max_level(dev); /* LP0 watermark maximums depend on this pipe alone */ struct intel_wm_config config = { .num_pipes_active = 1, - .sprites_enabled = params->spr.enabled, - .sprites_scaled = params->spr.scaled, }; struct ilk_wm_maximums max; - pipe_wm->pipe_enabled = params->active; - pipe_wm->sprites_enabled = params->spr.enabled; - pipe_wm->sprites_scaled = params->spr.scaled; + for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { + if (intel_plane->base.type == DRM_PLANE_TYPE_OVERLAY) { + sprstate = to_intel_plane_state(intel_plane->base.state); + break; + } + } + + config.sprites_enabled = sprstate->visible; + config.sprites_scaled = sprstate->visible && + (drm_rect_width(&sprstate->dst) != drm_rect_width(&sprstate->src) >> 16 || + drm_rect_height(&sprstate->dst) != drm_rect_height(&sprstate->src) >> 16); + + pipe_wm->pipe_enabled = cstate->base.active; + pipe_wm->sprites_enabled = sprstate->visible; + pipe_wm->sprites_scaled = config.sprites_scaled; /* ILK/SNB: LP2+ watermarks only w/o sprites */ - if (INTEL_INFO(dev)->gen <= 6 && params->spr.enabled) + if (INTEL_INFO(dev)->gen <= 6 && sprstate->visible) max_level = 1; /* ILK/SNB/IVB: LP1+ watermarks only w/o scaling */ - if (params->spr.scaled) + if (config.sprites_scaled) max_level = 0; - ilk_compute_wm_level(dev_priv, 0, params, &pipe_wm->wm[0]); + ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate, &pipe_wm->wm[0]); if (IS_HASWELL(dev) || IS_BROADWELL(dev)) pipe_wm->linetime = hsw_compute_linetime_wm(dev, crtc); @@ -2431,7 +2400,7 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc, for (level = 1; level <= max_level; level++) { struct intel_wm_level wm = {}; - ilk_compute_wm_level(dev_priv, level, params, &wm); + ilk_compute_wm_level(dev_priv, intel_crtc, level, cstate, &wm); /* * Disable any watermark level that exceeds the @@ -2836,18 +2805,40 @@ static bool ilk_disable_lp_wm(struct drm_device *dev) #define SKL_DDB_SIZE 896 /* in blocks */ #define BXT_DDB_SIZE 512 +/* + * Return the index of a plane in the SKL DDB and wm result arrays. Primary + * plane is always in slot 0, cursor is always in slot I915_MAX_PLANES-1, and + * other universal planes are in indices 1..n. Note that this may leave unused + * indices between the top "sprite" plane and the cursor. + */ +static int +skl_wm_plane_id(const struct intel_plane *plane) +{ + switch (plane->base.type) { + case DRM_PLANE_TYPE_PRIMARY: + return 0; + case DRM_PLANE_TYPE_CURSOR: + return PLANE_CURSOR; + case DRM_PLANE_TYPE_OVERLAY: + return plane->plane + 1; + default: + MISSING_CASE(plane->base.type); + return plane->plane; + } +} + static void skl_ddb_get_pipe_allocation_limits(struct drm_device *dev, - struct drm_crtc *for_crtc, + const struct intel_crtc_state *cstate, const struct intel_wm_config *config, - const struct skl_pipe_wm_parameters *params, struct skl_ddb_entry *alloc /* out */) { + struct drm_crtc *for_crtc = cstate->base.crtc; struct drm_crtc *crtc; unsigned int pipe_size, ddb_size; int nth_active_pipe; - if (!params->active) { + if (!cstate->base.active) { alloc->start = 0; alloc->end = 0; return; @@ -2907,24 +2898,35 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, } val = I915_READ(CUR_BUF_CFG(pipe)); - skl_ddb_entry_init_from_hw(&ddb->cursor[pipe], val); + skl_ddb_entry_init_from_hw(&ddb->plane[pipe][PLANE_CURSOR], + val); } } static unsigned int -skl_plane_relative_data_rate(const struct intel_plane_wm_parameters *p, int y) +skl_plane_relative_data_rate(const struct intel_crtc_state *cstate, + const struct drm_plane_state *pstate, + int y) { + struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); + struct drm_framebuffer *fb = pstate->fb; /* for planar format */ - if (p->y_bytes_per_pixel) { + if (fb->pixel_format == DRM_FORMAT_NV12) { if (y) /* y-plane data rate */ - return p->horiz_pixels * p->vert_pixels * p->y_bytes_per_pixel; + return intel_crtc->config->pipe_src_w * + intel_crtc->config->pipe_src_h * + drm_format_plane_cpp(fb->pixel_format, 0); else /* uv-plane data rate */ - return (p->horiz_pixels/2) * (p->vert_pixels/2) * p->bytes_per_pixel; + return (intel_crtc->config->pipe_src_w/2) * + (intel_crtc->config->pipe_src_h/2) * + drm_format_plane_cpp(fb->pixel_format, 1); } /* for packed formats */ - return p->horiz_pixels * p->vert_pixels * p->bytes_per_pixel; + return intel_crtc->config->pipe_src_w * + intel_crtc->config->pipe_src_h * + drm_format_plane_cpp(fb->pixel_format, 0); } /* @@ -2933,72 +2935,81 @@ skl_plane_relative_data_rate(const struct intel_plane_wm_parameters *p, int y) * 3 * 4096 * 8192 * 4 < 2^32 */ static unsigned int -skl_get_total_relative_data_rate(struct intel_crtc *intel_crtc, - const struct skl_pipe_wm_parameters *params) +skl_get_total_relative_data_rate(const struct intel_crtc_state *cstate) { + struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); + struct drm_device *dev = intel_crtc->base.dev; + const struct intel_plane *intel_plane; unsigned int total_data_rate = 0; - int plane; - for (plane = 0; plane < intel_num_planes(intel_crtc); plane++) { - const struct intel_plane_wm_parameters *p; + for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { + const struct drm_plane_state *pstate = intel_plane->base.state; - p = ¶ms->plane[plane]; - if (!p->enabled) + if (pstate->fb == NULL) continue; - total_data_rate += skl_plane_relative_data_rate(p, 0); /* packed/uv */ - if (p->y_bytes_per_pixel) { - total_data_rate += skl_plane_relative_data_rate(p, 1); /* y-plane */ - } + /* packed/uv */ + total_data_rate += skl_plane_relative_data_rate(cstate, + pstate, + 0); + + if (pstate->fb->pixel_format == DRM_FORMAT_NV12) + /* y-plane */ + total_data_rate += skl_plane_relative_data_rate(cstate, + pstate, + 1); } return total_data_rate; } static void -skl_allocate_pipe_ddb(struct drm_crtc *crtc, +skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, const struct intel_wm_config *config, - const struct skl_pipe_wm_parameters *params, struct skl_ddb_allocation *ddb /* out */) { + struct drm_crtc *crtc = cstate->base.crtc; struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_plane *intel_plane; enum pipe pipe = intel_crtc->pipe; struct skl_ddb_entry *alloc = &ddb->pipe[pipe]; uint16_t alloc_size, start, cursor_blocks; uint16_t minimum[I915_MAX_PLANES]; uint16_t y_minimum[I915_MAX_PLANES]; unsigned int total_data_rate; - int plane; - skl_ddb_get_pipe_allocation_limits(dev, crtc, config, params, alloc); + skl_ddb_get_pipe_allocation_limits(dev, cstate, config, alloc); alloc_size = skl_ddb_entry_size(alloc); if (alloc_size == 0) { memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe])); - memset(&ddb->cursor[pipe], 0, sizeof(ddb->cursor[pipe])); + memset(&ddb->plane[pipe][PLANE_CURSOR], 0, + sizeof(ddb->plane[pipe][PLANE_CURSOR])); return; } cursor_blocks = skl_cursor_allocation(config); - ddb->cursor[pipe].start = alloc->end - cursor_blocks; - ddb->cursor[pipe].end = alloc->end; + ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - cursor_blocks; + ddb->plane[pipe][PLANE_CURSOR].end = alloc->end; alloc_size -= cursor_blocks; alloc->end -= cursor_blocks; /* 1. Allocate the mininum required blocks for each active plane */ - for_each_plane(dev_priv, pipe, plane) { - const struct intel_plane_wm_parameters *p; + for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { + struct drm_plane *plane = &intel_plane->base; + struct drm_framebuffer *fb = plane->fb; + int id = skl_wm_plane_id(intel_plane); - p = ¶ms->plane[plane]; - if (!p->enabled) + if (fb == NULL) + continue; + if (plane->type == DRM_PLANE_TYPE_CURSOR) continue; - minimum[plane] = 8; - alloc_size -= minimum[plane]; - y_minimum[plane] = p->y_bytes_per_pixel ? 8 : 0; - alloc_size -= y_minimum[plane]; + minimum[id] = 8; + alloc_size -= minimum[id]; + y_minimum[id] = (fb->pixel_format == DRM_FORMAT_NV12) ? 8 : 0; + alloc_size -= y_minimum[id]; } /* @@ -3007,45 +3018,50 @@ skl_allocate_pipe_ddb(struct drm_crtc *crtc, * * FIXME: we may not allocate every single block here. */ - total_data_rate = skl_get_total_relative_data_rate(intel_crtc, params); + total_data_rate = skl_get_total_relative_data_rate(cstate); start = alloc->start; - for (plane = 0; plane < intel_num_planes(intel_crtc); plane++) { - const struct intel_plane_wm_parameters *p; + for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { + struct drm_plane *plane = &intel_plane->base; + struct drm_plane_state *pstate = intel_plane->base.state; unsigned int data_rate, y_data_rate; uint16_t plane_blocks, y_plane_blocks = 0; + int id = skl_wm_plane_id(intel_plane); - p = ¶ms->plane[plane]; - if (!p->enabled) + if (pstate->fb == NULL) + continue; + if (plane->type == DRM_PLANE_TYPE_CURSOR) continue; - data_rate = skl_plane_relative_data_rate(p, 0); + data_rate = skl_plane_relative_data_rate(cstate, pstate, 0); /* * allocation for (packed formats) or (uv-plane part of planar format): * promote the expression to 64 bits to avoid overflowing, the * result is < available as data_rate / total_data_rate < 1 */ - plane_blocks = minimum[plane]; + plane_blocks = minimum[id]; plane_blocks += div_u64((uint64_t)alloc_size * data_rate, total_data_rate); - ddb->plane[pipe][plane].start = start; - ddb->plane[pipe][plane].end = start + plane_blocks; + ddb->plane[pipe][id].start = start; + ddb->plane[pipe][id].end = start + plane_blocks; start += plane_blocks; /* * allocation for y_plane part of planar format: */ - if (p->y_bytes_per_pixel) { - y_data_rate = skl_plane_relative_data_rate(p, 1); - y_plane_blocks = y_minimum[plane]; + if (pstate->fb->pixel_format == DRM_FORMAT_NV12) { + y_data_rate = skl_plane_relative_data_rate(cstate, + pstate, + 1); + y_plane_blocks = y_minimum[id]; y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate, total_data_rate); - ddb->y_plane[pipe][plane].start = start; - ddb->y_plane[pipe][plane].end = start + y_plane_blocks; + ddb->y_plane[pipe][id].start = start; + ddb->y_plane[pipe][id].end = start + y_plane_blocks; start += y_plane_blocks; } @@ -3121,8 +3137,8 @@ static bool skl_ddb_allocation_changed(const struct skl_ddb_allocation *new_ddb, sizeof(new_ddb->plane[pipe]))) return true; - if (memcmp(&new_ddb->cursor[pipe], &cur_ddb->cursor[pipe], - sizeof(new_ddb->cursor[pipe]))) + if (memcmp(&new_ddb->plane[pipe][PLANE_CURSOR], &cur_ddb->plane[pipe][PLANE_CURSOR], + sizeof(new_ddb->plane[pipe][PLANE_CURSOR]))) return true; return false; @@ -3132,86 +3148,21 @@ static void skl_compute_wm_global_parameters(struct drm_device *dev, struct intel_wm_config *config) { struct drm_crtc *crtc; - struct drm_plane *plane; list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) config->num_pipes_active += to_intel_crtc(crtc)->active; - - /* FIXME: I don't think we need those two global parameters on SKL */ - list_for_each_entry(plane, &dev->mode_config.plane_list, head) { - struct intel_plane *intel_plane = to_intel_plane(plane); - - config->sprites_enabled |= intel_plane->wm.enabled; - config->sprites_scaled |= intel_plane->wm.scaled; - } -} - -static void skl_compute_wm_pipe_parameters(struct drm_crtc *crtc, - struct skl_pipe_wm_parameters *p) -{ - struct drm_device *dev = crtc->dev; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum pipe pipe = intel_crtc->pipe; - struct drm_plane *plane; - struct drm_framebuffer *fb; - int i = 1; /* Index for sprite planes start */ - - p->active = intel_crtc->active; - if (p->active) { - p->pipe_htotal = intel_crtc->config->base.adjusted_mode.crtc_htotal; - p->pixel_rate = skl_pipe_pixel_rate(intel_crtc->config); - - fb = crtc->primary->state->fb; - /* For planar: Bpp is for uv plane, y_Bpp is for y plane */ - if (fb) { - p->plane[0].enabled = true; - p->plane[0].bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ? - drm_format_plane_cpp(fb->pixel_format, 1) : fb->bits_per_pixel / 8; - p->plane[0].y_bytes_per_pixel = fb->pixel_format == DRM_FORMAT_NV12 ? - drm_format_plane_cpp(fb->pixel_format, 0) : 0; - p->plane[0].tiling = fb->modifier[0]; - } else { - p->plane[0].enabled = false; - p->plane[0].bytes_per_pixel = 0; - p->plane[0].y_bytes_per_pixel = 0; - p->plane[0].tiling = DRM_FORMAT_MOD_NONE; - } - p->plane[0].horiz_pixels = intel_crtc->config->pipe_src_w; - p->plane[0].vert_pixels = intel_crtc->config->pipe_src_h; - p->plane[0].rotation = crtc->primary->state->rotation; - - fb = crtc->cursor->state->fb; - p->cursor.y_bytes_per_pixel = 0; - if (fb) { - p->cursor.enabled = true; - p->cursor.bytes_per_pixel = fb->bits_per_pixel / 8; - p->cursor.horiz_pixels = crtc->cursor->state->crtc_w; - p->cursor.vert_pixels = crtc->cursor->state->crtc_h; - } else { - p->cursor.enabled = false; - p->cursor.bytes_per_pixel = 0; - p->cursor.horiz_pixels = 64; - p->cursor.vert_pixels = 64; - } - } - - list_for_each_entry(plane, &dev->mode_config.plane_list, head) { - struct intel_plane *intel_plane = to_intel_plane(plane); - - if (intel_plane->pipe == pipe && - plane->type == DRM_PLANE_TYPE_OVERLAY) - p->plane[i++] = intel_plane->wm; - } } static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv, - struct skl_pipe_wm_parameters *p, - struct intel_plane_wm_parameters *p_params, + struct intel_crtc_state *cstate, + struct intel_plane *intel_plane, uint16_t ddb_allocation, int level, uint16_t *out_blocks, /* out */ uint8_t *out_lines /* out */) { + struct drm_plane *plane = &intel_plane->base; + struct drm_framebuffer *fb = plane->state->fb; uint32_t latency = dev_priv->wm.skl_latency[level]; uint32_t method1, method2; uint32_t plane_bytes_per_line, plane_blocks_per_line; @@ -3219,31 +3170,35 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv, uint32_t selected_result; uint8_t bytes_per_pixel; - if (latency == 0 || !p->active || !p_params->enabled) + if (latency == 0 || !cstate->base.active || !fb) return false; - bytes_per_pixel = p_params->y_bytes_per_pixel ? - p_params->y_bytes_per_pixel : - p_params->bytes_per_pixel; - method1 = skl_wm_method1(p->pixel_rate, + bytes_per_pixel = (fb->pixel_format == DRM_FORMAT_NV12) ? + drm_format_plane_cpp(DRM_FORMAT_NV12, 0) : + drm_format_plane_cpp(DRM_FORMAT_NV12, 1); + method1 = skl_wm_method1(skl_pipe_pixel_rate(cstate), bytes_per_pixel, latency); - method2 = skl_wm_method2(p->pixel_rate, - p->pipe_htotal, - p_params->horiz_pixels, + method2 = skl_wm_method2(skl_pipe_pixel_rate(cstate), + cstate->base.adjusted_mode.crtc_htotal, + cstate->pipe_src_w, bytes_per_pixel, - p_params->tiling, + fb->modifier[0], latency); - plane_bytes_per_line = p_params->horiz_pixels * bytes_per_pixel; + plane_bytes_per_line = cstate->pipe_src_w * bytes_per_pixel; plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512); - if (p_params->tiling == I915_FORMAT_MOD_Y_TILED || - p_params->tiling == I915_FORMAT_MOD_Yf_TILED) { + if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED || + fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) { uint32_t min_scanlines = 4; uint32_t y_tile_minimum; - if (intel_rotation_90_or_270(p_params->rotation)) { - switch (p_params->bytes_per_pixel) { + if (intel_rotation_90_or_270(plane->state->rotation)) { + int bpp = (fb->pixel_format == DRM_FORMAT_NV12) ? + drm_format_plane_cpp(fb->pixel_format, 1) : + drm_format_plane_cpp(fb->pixel_format, 0); + + switch (bpp) { case 1: min_scanlines = 16; break; @@ -3267,8 +3222,8 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv, res_lines = DIV_ROUND_UP(selected_result, plane_blocks_per_line); if (level >= 1 && level <= 7) { - if (p_params->tiling == I915_FORMAT_MOD_Y_TILED || - p_params->tiling == I915_FORMAT_MOD_Yf_TILED) + if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED || + fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) res_lines += 4; else res_blocks++; @@ -3285,83 +3240,80 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv, static void skl_compute_wm_level(const struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb, - struct skl_pipe_wm_parameters *p, - enum pipe pipe, + struct intel_crtc_state *cstate, int level, - int num_planes, struct skl_wm_level *result) { + struct drm_device *dev = dev_priv->dev; + struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc); + struct intel_plane *intel_plane; uint16_t ddb_blocks; - int i; + enum pipe pipe = intel_crtc->pipe; + + for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { + int i = skl_wm_plane_id(intel_plane); - for (i = 0; i < num_planes; i++) { ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][i]); result->plane_en[i] = skl_compute_plane_wm(dev_priv, - p, &p->plane[i], + cstate, + intel_plane, ddb_blocks, level, &result->plane_res_b[i], &result->plane_res_l[i]); } - - ddb_blocks = skl_ddb_entry_size(&ddb->cursor[pipe]); - result->cursor_en = skl_compute_plane_wm(dev_priv, p, &p->cursor, - ddb_blocks, level, - &result->cursor_res_b, - &result->cursor_res_l); } static uint32_t -skl_compute_linetime_wm(struct drm_crtc *crtc, struct skl_pipe_wm_parameters *p) +skl_compute_linetime_wm(struct intel_crtc_state *cstate) { - if (!to_intel_crtc(crtc)->active) + if (!cstate->base.active) return 0; - if (WARN_ON(p->pixel_rate == 0)) + if (WARN_ON(skl_pipe_pixel_rate(cstate) == 0)) return 0; - return DIV_ROUND_UP(8 * p->pipe_htotal * 1000, p->pixel_rate); + return DIV_ROUND_UP(8 * cstate->base.adjusted_mode.crtc_htotal * 1000, + skl_pipe_pixel_rate(cstate)); } -static void skl_compute_transition_wm(struct drm_crtc *crtc, - struct skl_pipe_wm_parameters *params, +static void skl_compute_transition_wm(struct intel_crtc_state *cstate, struct skl_wm_level *trans_wm /* out */) { + struct drm_crtc *crtc = cstate->base.crtc; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int i; + struct intel_plane *intel_plane; - if (!params->active) + if (!cstate->base.active) return; /* Until we know more, just disable transition WMs */ - for (i = 0; i < intel_num_planes(intel_crtc); i++) + for_each_intel_plane_on_crtc(crtc->dev, intel_crtc, intel_plane) { + int i = skl_wm_plane_id(intel_plane); + trans_wm->plane_en[i] = false; - trans_wm->cursor_en = false; + } } -static void skl_compute_pipe_wm(struct drm_crtc *crtc, +static void skl_compute_pipe_wm(struct intel_crtc_state *cstate, struct skl_ddb_allocation *ddb, - struct skl_pipe_wm_parameters *params, struct skl_pipe_wm *pipe_wm) { - struct drm_device *dev = crtc->dev; + struct drm_device *dev = cstate->base.crtc->dev; const struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int level, max_level = ilk_wm_max_level(dev); for (level = 0; level <= max_level; level++) { - skl_compute_wm_level(dev_priv, ddb, params, intel_crtc->pipe, - level, intel_num_planes(intel_crtc), - &pipe_wm->wm[level]); + skl_compute_wm_level(dev_priv, ddb, cstate, + level, &pipe_wm->wm[level]); } - pipe_wm->linetime = skl_compute_linetime_wm(crtc, params); + pipe_wm->linetime = skl_compute_linetime_wm(cstate); - skl_compute_transition_wm(crtc, params, &pipe_wm->trans_wm); + skl_compute_transition_wm(cstate, &pipe_wm->trans_wm); } static void skl_compute_wm_results(struct drm_device *dev, - struct skl_pipe_wm_parameters *p, struct skl_pipe_wm *p_wm, struct skl_wm_values *r, struct intel_crtc *intel_crtc) @@ -3386,13 +3338,13 @@ static void skl_compute_wm_results(struct drm_device *dev, temp = 0; - temp |= p_wm->wm[level].cursor_res_l << PLANE_WM_LINES_SHIFT; - temp |= p_wm->wm[level].cursor_res_b; + temp |= p_wm->wm[level].plane_res_l[PLANE_CURSOR] << PLANE_WM_LINES_SHIFT; + temp |= p_wm->wm[level].plane_res_b[PLANE_CURSOR]; - if (p_wm->wm[level].cursor_en) + if (p_wm->wm[level].plane_en[PLANE_CURSOR]) temp |= PLANE_WM_EN; - r->cursor[pipe][level] = temp; + r->plane[pipe][PLANE_CURSOR][level] = temp; } @@ -3408,12 +3360,12 @@ static void skl_compute_wm_results(struct drm_device *dev, } temp = 0; - temp |= p_wm->trans_wm.cursor_res_l << PLANE_WM_LINES_SHIFT; - temp |= p_wm->trans_wm.cursor_res_b; - if (p_wm->trans_wm.cursor_en) + temp |= p_wm->trans_wm.plane_res_l[PLANE_CURSOR] << PLANE_WM_LINES_SHIFT; + temp |= p_wm->trans_wm.plane_res_b[PLANE_CURSOR]; + if (p_wm->trans_wm.plane_en[PLANE_CURSOR]) temp |= PLANE_WM_EN; - r->cursor_trans[pipe] = temp; + r->plane_trans[pipe][PLANE_CURSOR] = temp; r->wm_linetime[pipe] = p_wm->linetime; } @@ -3447,12 +3399,13 @@ static void skl_write_wm_values(struct drm_i915_private *dev_priv, I915_WRITE(PLANE_WM(pipe, i, level), new->plane[pipe][i][level]); I915_WRITE(CUR_WM(pipe, level), - new->cursor[pipe][level]); + new->plane[pipe][PLANE_CURSOR][level]); } for (i = 0; i < intel_num_planes(crtc); i++) I915_WRITE(PLANE_WM_TRANS(pipe, i), new->plane_trans[pipe][i]); - I915_WRITE(CUR_WM_TRANS(pipe), new->cursor_trans[pipe]); + I915_WRITE(CUR_WM_TRANS(pipe), + new->plane_trans[pipe][PLANE_CURSOR]); for (i = 0; i < intel_num_planes(crtc); i++) { skl_ddb_entry_write(dev_priv, @@ -3464,7 +3417,7 @@ static void skl_write_wm_values(struct drm_i915_private *dev_priv, } skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe), - &new->ddb.cursor[pipe]); + &new->ddb.plane[pipe][PLANE_CURSOR]); } } @@ -3604,16 +3557,15 @@ static void skl_flush_wm_values(struct drm_i915_private *dev_priv, } static bool skl_update_pipe_wm(struct drm_crtc *crtc, - struct skl_pipe_wm_parameters *params, struct intel_wm_config *config, struct skl_ddb_allocation *ddb, /* out */ struct skl_pipe_wm *pipe_wm /* out */) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); - skl_compute_wm_pipe_parameters(crtc, params); - skl_allocate_pipe_ddb(crtc, config, params, ddb); - skl_compute_pipe_wm(crtc, ddb, params, pipe_wm); + skl_allocate_pipe_ddb(cstate, config, ddb); + skl_compute_pipe_wm(cstate, ddb, pipe_wm); if (!memcmp(&intel_crtc->wm.skl_active, pipe_wm, sizeof(*pipe_wm))) return false; @@ -3646,7 +3598,6 @@ static void skl_update_other_pipe_wm(struct drm_device *dev, */ list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { - struct skl_pipe_wm_parameters params = {}; struct skl_pipe_wm pipe_wm = {}; bool wm_changed; @@ -3656,8 +3607,7 @@ static void skl_update_other_pipe_wm(struct drm_device *dev, if (!intel_crtc->active) continue; - wm_changed = skl_update_pipe_wm(&intel_crtc->base, - ¶ms, config, + wm_changed = skl_update_pipe_wm(&intel_crtc->base, config, &r->ddb, &pipe_wm); /* @@ -3667,30 +3617,52 @@ static void skl_update_other_pipe_wm(struct drm_device *dev, */ WARN_ON(!wm_changed); - skl_compute_wm_results(dev, ¶ms, &pipe_wm, r, intel_crtc); + skl_compute_wm_results(dev, &pipe_wm, r, intel_crtc); r->dirty[intel_crtc->pipe] = true; } } +static void skl_clear_wm(struct skl_wm_values *watermarks, enum pipe pipe) +{ + watermarks->wm_linetime[pipe] = 0; + memset(watermarks->plane[pipe], 0, + sizeof(uint32_t) * 8 * I915_MAX_PLANES); + memset(watermarks->plane_trans[pipe], + 0, sizeof(uint32_t) * I915_MAX_PLANES); + watermarks->plane_trans[pipe][PLANE_CURSOR] = 0; + + /* Clear ddb entries for pipe */ + memset(&watermarks->ddb.pipe[pipe], 0, sizeof(struct skl_ddb_entry)); + memset(&watermarks->ddb.plane[pipe], 0, + sizeof(struct skl_ddb_entry) * I915_MAX_PLANES); + memset(&watermarks->ddb.y_plane[pipe], 0, + sizeof(struct skl_ddb_entry) * I915_MAX_PLANES); + memset(&watermarks->ddb.plane[pipe][PLANE_CURSOR], 0, + sizeof(struct skl_ddb_entry)); + +} + static void skl_update_wm(struct drm_crtc *crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct skl_pipe_wm_parameters params = {}; struct skl_wm_values *results = &dev_priv->wm.skl_results; struct skl_pipe_wm pipe_wm = {}; struct intel_wm_config config = {}; - memset(results, 0, sizeof(*results)); + + /* Clear all dirty flags */ + memset(results->dirty, 0, sizeof(bool) * I915_MAX_PIPES); + + skl_clear_wm(results, intel_crtc->pipe); skl_compute_wm_global_parameters(dev, &config); - if (!skl_update_pipe_wm(crtc, ¶ms, &config, - &results->ddb, &pipe_wm)) + if (!skl_update_pipe_wm(crtc, &config, &results->ddb, &pipe_wm)) return; - skl_compute_wm_results(dev, ¶ms, &pipe_wm, results, intel_crtc); + skl_compute_wm_results(dev, &pipe_wm, results, intel_crtc); results->dirty[intel_crtc->pipe] = true; skl_update_other_pipe_wm(dev, crtc, &config, results); @@ -3701,55 +3673,34 @@ static void skl_update_wm(struct drm_crtc *crtc) dev_priv->wm.skl_hw = *results; } -static void -skl_update_sprite_wm(struct drm_plane *plane, struct drm_crtc *crtc, - uint32_t sprite_width, uint32_t sprite_height, - int pixel_size, bool enabled, bool scaled) -{ - struct intel_plane *intel_plane = to_intel_plane(plane); - struct drm_framebuffer *fb = plane->state->fb; - - intel_plane->wm.enabled = enabled; - intel_plane->wm.scaled = scaled; - intel_plane->wm.horiz_pixels = sprite_width; - intel_plane->wm.vert_pixels = sprite_height; - intel_plane->wm.tiling = DRM_FORMAT_MOD_NONE; - - /* For planar: Bpp is for UV plane, y_Bpp is for Y plane */ - intel_plane->wm.bytes_per_pixel = - (fb && fb->pixel_format == DRM_FORMAT_NV12) ? - drm_format_plane_cpp(plane->state->fb->pixel_format, 1) : pixel_size; - intel_plane->wm.y_bytes_per_pixel = - (fb && fb->pixel_format == DRM_FORMAT_NV12) ? - drm_format_plane_cpp(plane->state->fb->pixel_format, 0) : 0; - - /* - * Framebuffer can be NULL on plane disable, but it does not - * matter for watermarks if we assume no tiling in that case. - */ - if (fb) - intel_plane->wm.tiling = fb->modifier[0]; - intel_plane->wm.rotation = plane->state->rotation; - - skl_update_wm(crtc); -} - static void ilk_update_wm(struct drm_crtc *crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct ilk_wm_maximums max; - struct ilk_pipe_wm_parameters params = {}; struct ilk_wm_values results = {}; enum intel_ddb_partitioning partitioning; struct intel_pipe_wm pipe_wm = {}; struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct intel_wm_config config = {}; - ilk_compute_wm_parameters(crtc, ¶ms); + WARN_ON(cstate->base.active != intel_crtc->active); + + /* + * IVB workaround: must disable low power watermarks for at least + * one frame before enabling scaling. LP watermarks can be re-enabled + * when scaling is disabled. + * + * WaCxSRDisabledForSpriteScaling:ivb + */ + if (cstate->disable_lp_wm) { + ilk_disable_lp_wm(dev); + intel_wait_for_vblank(dev, intel_crtc->pipe); + } - intel_compute_pipe_wm(crtc, ¶ms, &pipe_wm); + intel_compute_pipe_wm(cstate, &pipe_wm); if (!memcmp(&intel_crtc->wm.active, &pipe_wm, sizeof(pipe_wm))) return; @@ -3780,34 +3731,6 @@ static void ilk_update_wm(struct drm_crtc *crtc) ilk_write_wm_values(dev_priv, &results); } -static void -ilk_update_sprite_wm(struct drm_plane *plane, - struct drm_crtc *crtc, - uint32_t sprite_width, uint32_t sprite_height, - int pixel_size, bool enabled, bool scaled) -{ - struct drm_device *dev = plane->dev; - struct intel_plane *intel_plane = to_intel_plane(plane); - - intel_plane->wm.enabled = enabled; - intel_plane->wm.scaled = scaled; - intel_plane->wm.horiz_pixels = sprite_width; - intel_plane->wm.vert_pixels = sprite_width; - intel_plane->wm.bytes_per_pixel = pixel_size; - - /* - * IVB workaround: must disable low power watermarks for at least - * one frame before enabling scaling. LP watermarks can be re-enabled - * when scaling is disabled. - * - * WaCxSRDisabledForSpriteScaling:ivb - */ - if (IS_IVYBRIDGE(dev) && scaled && ilk_disable_lp_wm(dev)) - intel_wait_for_vblank(dev, intel_plane->pipe); - - ilk_update_wm(crtc); -} - static void skl_pipe_wm_active_state(uint32_t val, struct skl_pipe_wm *active, bool is_transwm, @@ -3826,10 +3749,10 @@ static void skl_pipe_wm_active_state(uint32_t val, (val >> PLANE_WM_LINES_SHIFT) & PLANE_WM_LINES_MASK; } else { - active->wm[level].cursor_en = is_enabled; - active->wm[level].cursor_res_b = + active->wm[level].plane_en[PLANE_CURSOR] = is_enabled; + active->wm[level].plane_res_b[PLANE_CURSOR] = val & PLANE_WM_BLOCKS_MASK; - active->wm[level].cursor_res_l = + active->wm[level].plane_res_l[PLANE_CURSOR] = (val >> PLANE_WM_LINES_SHIFT) & PLANE_WM_LINES_MASK; } @@ -3842,10 +3765,10 @@ static void skl_pipe_wm_active_state(uint32_t val, (val >> PLANE_WM_LINES_SHIFT) & PLANE_WM_LINES_MASK; } else { - active->trans_wm.cursor_en = is_enabled; - active->trans_wm.cursor_res_b = + active->trans_wm.plane_en[PLANE_CURSOR] = is_enabled; + active->trans_wm.plane_res_b[PLANE_CURSOR] = val & PLANE_WM_BLOCKS_MASK; - active->trans_wm.cursor_res_l = + active->trans_wm.plane_res_l[PLANE_CURSOR] = (val >> PLANE_WM_LINES_SHIFT) & PLANE_WM_LINES_MASK; } @@ -3871,12 +3794,12 @@ static void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc) for (i = 0; i < intel_num_planes(intel_crtc); i++) hw->plane[pipe][i][level] = I915_READ(PLANE_WM(pipe, i, level)); - hw->cursor[pipe][level] = I915_READ(CUR_WM(pipe, level)); + hw->plane[pipe][PLANE_CURSOR][level] = I915_READ(CUR_WM(pipe, level)); } for (i = 0; i < intel_num_planes(intel_crtc); i++) hw->plane_trans[pipe][i] = I915_READ(PLANE_WM_TRANS(pipe, i)); - hw->cursor_trans[pipe] = I915_READ(CUR_WM_TRANS(pipe)); + hw->plane_trans[pipe][PLANE_CURSOR] = I915_READ(CUR_WM_TRANS(pipe)); if (!intel_crtc->active) return; @@ -3891,7 +3814,7 @@ static void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc) skl_pipe_wm_active_state(temp, active, false, false, i, level); } - temp = hw->cursor[pipe][level]; + temp = hw->plane[pipe][PLANE_CURSOR][level]; skl_pipe_wm_active_state(temp, active, false, true, i, level); } @@ -3900,7 +3823,7 @@ static void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc) skl_pipe_wm_active_state(temp, active, true, false, i, 0); } - temp = hw->cursor_trans[pipe]; + temp = hw->plane_trans[pipe][PLANE_CURSOR]; skl_pipe_wm_active_state(temp, active, true, true, i, 0); } @@ -4185,21 +4108,6 @@ void intel_update_watermarks(struct drm_crtc *crtc) dev_priv->display.update_wm(crtc); } -void intel_update_sprite_watermarks(struct drm_plane *plane, - struct drm_crtc *crtc, - uint32_t sprite_width, - uint32_t sprite_height, - int pixel_size, - bool enabled, bool scaled) -{ - struct drm_i915_private *dev_priv = plane->dev->dev_private; - - if (dev_priv->display.update_sprite_wm) - dev_priv->display.update_sprite_wm(plane, crtc, - sprite_width, sprite_height, - pixel_size, enabled, scaled); -} - /** * Lock protecting IPS related data structures */ @@ -4261,7 +4169,7 @@ static void ironlake_enable_drps(struct drm_device *dev) fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >> MEMMODE_FSTART_SHIFT; - vstart = (I915_READ(PXVFREQ_BASE + (fstart * 4)) & PXVFREQ_PX_MASK) >> + vstart = (I915_READ(PXVFREQ(fstart)) & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT; dev_priv->ips.fmax = fmax; /* IPS callback will increase this */ @@ -4292,10 +4200,10 @@ static void ironlake_enable_drps(struct drm_device *dev) ironlake_set_drps(dev, fstart); - dev_priv->ips.last_count1 = I915_READ(0x112e4) + I915_READ(0x112e8) + - I915_READ(0x112e0); + dev_priv->ips.last_count1 = I915_READ(DMIEC) + + I915_READ(DDREC) + I915_READ(CSIEC); dev_priv->ips.last_time1 = jiffies_to_msecs(jiffies); - dev_priv->ips.last_count2 = I915_READ(0x112f4); + dev_priv->ips.last_count2 = I915_READ(GFXEC); dev_priv->ips.last_time2 = ktime_get_raw_ns(); spin_unlock_irq(&mchdev_lock); @@ -4466,6 +4374,10 @@ static void gen6_set_rps(struct drm_device *dev, u8 val) { struct drm_i915_private *dev_priv = dev->dev_private; + /* WaGsvDisableTurbo: Workaround to disable turbo on BXT A* */ + if (IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) + return; + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); WARN_ON(val > dev_priv->rps.max_freq); WARN_ON(val < dev_priv->rps.min_freq); @@ -4786,6 +4698,12 @@ static void gen9_enable_rps(struct drm_device *dev) gen6_init_rps_frequencies(dev); + /* WaGsvDisableTurbo: Workaround to disable turbo on BXT A* */ + if (IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) { + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + return; + } + /* Program defaults and thresholds for RPS*/ I915_WRITE(GEN6_RC_VIDEO_FREQ, GEN9_FREQUENCY(dev_priv->rps.rp1_freq)); @@ -4823,13 +4741,22 @@ static void gen9_enable_rc6(struct drm_device *dev) I915_WRITE(GEN6_RC_CONTROL, 0); /* 2b: Program RC6 thresholds.*/ - I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16); + + /* WaRsDoubleRc6WrlWithCoarsePowerGating: Doubling WRL only when CPG is enabled */ + if (IS_SKYLAKE(dev) && !((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && + (INTEL_REVID(dev) <= SKL_REVID_E0))) + I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16); + else + I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16); I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */ I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */ for_each_ring(ring, dev_priv, unused) I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10); + + if (HAS_GUC_UCODE(dev)) + I915_WRITE(GUC_MAX_IDLE_COUNT, 0xA); + I915_WRITE(GEN6_RC_SLEEP, 0); - I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */ /* 2c: Program Coarse Power Gating Policies. */ I915_WRITE(GEN9_MEDIA_PG_IDLE_HYSTERESIS, 25); @@ -4840,17 +4767,30 @@ static void gen9_enable_rc6(struct drm_device *dev) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; DRM_INFO("RC6 %s\n", (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off"); - I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE | - GEN6_RC_CTL_EI_MODE(1) | - rc6_mask); + /* WaRsUseTimeoutMode */ + if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_D0) || + (IS_BROXTON(dev) && INTEL_REVID(dev) <= BXT_REVID_A0)) { + I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us */ + I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE | + GEN7_RC_CTL_TO_MODE | + rc6_mask); + } else { + I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */ + I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE | + GEN6_RC_CTL_EI_MODE(1) | + rc6_mask); + } /* * 3b: Enable Coarse Power Gating only when RC6 is enabled. - * WaDisableRenderPowerGating:skl,bxt - Render PG need to be disabled with RC6. + * WaRsDisableCoarsePowerGating:skl,bxt - Render/Media PG need to be disabled with RC6. */ - I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? - GEN9_MEDIA_PG_ENABLE : 0); - + if ((IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) || + ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && (INTEL_REVID(dev) <= SKL_REVID_E0))) + I915_WRITE(GEN9_PG_ENABLE, 0); + else + I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? + (GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE) : 0); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); @@ -5148,32 +5088,27 @@ static int cherryview_rps_max_freq(struct drm_i915_private *dev_priv) struct drm_device *dev = dev_priv->dev; u32 val, rp0; - if (dev->pdev->revision >= 0x20) { - val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE); + val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE); - switch (INTEL_INFO(dev)->eu_total) { - case 8: - /* (2 * 4) config */ - rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT); - break; - case 12: - /* (2 * 6) config */ - rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS6EU_FUSE_SHIFT); - break; - case 16: - /* (2 * 8) config */ - default: - /* Setting (2 * 8) Min RP0 for any other combination */ - rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS8EU_FUSE_SHIFT); - break; - } - rp0 = (rp0 & FB_GFX_FREQ_FUSE_MASK); - } else { - /* For pre-production hardware */ - val = vlv_punit_read(dev_priv, PUNIT_GPU_STATUS_REG); - rp0 = (val >> PUNIT_GPU_STATUS_MAX_FREQ_SHIFT) & - PUNIT_GPU_STATUS_MAX_FREQ_MASK; + switch (INTEL_INFO(dev)->eu_total) { + case 8: + /* (2 * 4) config */ + rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT); + break; + case 12: + /* (2 * 6) config */ + rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS6EU_FUSE_SHIFT); + break; + case 16: + /* (2 * 8) config */ + default: + /* Setting (2 * 8) Min RP0 for any other combination */ + rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS8EU_FUSE_SHIFT); + break; } + + rp0 = (rp0 & FB_GFX_FREQ_FUSE_MASK); + return rp0; } @@ -5189,18 +5124,11 @@ static int cherryview_rps_rpe_freq(struct drm_i915_private *dev_priv) static int cherryview_rps_guar_freq(struct drm_i915_private *dev_priv) { - struct drm_device *dev = dev_priv->dev; u32 val, rp1; - if (dev->pdev->revision >= 0x20) { - val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE); - rp1 = (val & FB_GFX_FREQ_FUSE_MASK); - } else { - /* For pre-production hardware */ - val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS); - rp1 = ((val >> PUNIT_GPU_STATUS_MAX_FREQ_SHIFT) & - PUNIT_GPU_STATUS_MAX_FREQ_MASK); - } + val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE); + rp1 = (val & FB_GFX_FREQ_FUSE_MASK); + return rp1; } @@ -5415,25 +5343,10 @@ static void cherryview_init_gt_powersave(struct drm_device *dev) mutex_unlock(&dev_priv->sb_lock); switch ((val >> 2) & 0x7) { - case 0: - case 1: - dev_priv->rps.cz_freq = 200; - dev_priv->mem_freq = 1600; - break; - case 2: - dev_priv->rps.cz_freq = 267; - dev_priv->mem_freq = 1600; - break; case 3: - dev_priv->rps.cz_freq = 333; dev_priv->mem_freq = 2000; break; - case 4: - dev_priv->rps.cz_freq = 320; - dev_priv->mem_freq = 1600; - break; - case 5: - dev_priv->rps.cz_freq = 400; + default: dev_priv->mem_freq = 1600; break; } @@ -5565,7 +5478,7 @@ static void cherryview_enable_rps(struct drm_device *dev) /* RPS code assumes GPLL is used */ WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n"); - DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & GPLLENABLE ? "yes" : "no"); + DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE)); DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val); dev_priv->rps.cur_freq = (val >> 8) & 0xff; @@ -5655,7 +5568,7 @@ static void valleyview_enable_rps(struct drm_device *dev) /* RPS code assumes GPLL is used */ WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n"); - DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & GPLLENABLE ? "yes" : "no"); + DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE)); DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val); dev_priv->rps.cur_freq = (val >> 8) & 0xff; @@ -5864,7 +5777,7 @@ static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv) assert_spin_locked(&mchdev_lock); - pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->rps.cur_freq * 4)); + pxvid = I915_READ(PXVFREQ(dev_priv->rps.cur_freq)); pxvid = (pxvid >> 24) & 0x7f; ext_v = pvid_to_extvid(dev_priv, pxvid); @@ -6107,13 +6020,13 @@ static void intel_init_emon(struct drm_device *dev) I915_WRITE(CSIEW2, 0x04000004); for (i = 0; i < 5; i++) - I915_WRITE(PEW + (i * 4), 0); + I915_WRITE(PEW(i), 0); for (i = 0; i < 3; i++) - I915_WRITE(DEW + (i * 4), 0); + I915_WRITE(DEW(i), 0); /* Program P-state weights to account for frequency power adjustment */ for (i = 0; i < 16; i++) { - u32 pxvidfreq = I915_READ(PXVFREQ_BASE + (i * 4)); + u32 pxvidfreq = I915_READ(PXVFREQ(i)); unsigned long freq = intel_pxfreq(pxvidfreq); unsigned long vid = (pxvidfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT; @@ -6134,7 +6047,7 @@ static void intel_init_emon(struct drm_device *dev) for (i = 0; i < 4; i++) { u32 val = (pxw[i*4] << 24) | (pxw[(i*4)+1] << 16) | (pxw[(i*4)+2] << 8) | (pxw[(i*4)+3]); - I915_WRITE(PXW + (i * 4), val); + I915_WRITE(PXW(i), val); } /* Adjust magic regs to magic values (more experimental results) */ @@ -6150,7 +6063,7 @@ static void intel_init_emon(struct drm_device *dev) I915_WRITE(EG7, 0); for (i = 0; i < 8; i++) - I915_WRITE(PXWL + (i * 4), 0); + I915_WRITE(PXWL(i), 0); /* Enable PMON + select events */ I915_WRITE(ECR, 0x80000019); @@ -6604,14 +6517,14 @@ static void lpt_init_clock_gating(struct drm_device *dev) * TODO: this bit should only be enabled when really needed, then * disabled when not needed anymore in order to save power. */ - if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) + if (HAS_PCH_LPT_LP(dev)) I915_WRITE(SOUTH_DSPCLK_GATE_D, I915_READ(SOUTH_DSPCLK_GATE_D) | PCH_LP_PARTITION_LEVEL_DISABLE); /* WADPOClockGatingDisable:hsw */ - I915_WRITE(_TRANSA_CHICKEN1, - I915_READ(_TRANSA_CHICKEN1) | + I915_WRITE(TRANS_CHICKEN1(PIPE_A), + I915_READ(TRANS_CHICKEN1(PIPE_A)) | TRANS_CHICKEN1_DP0UNIT_GC_DISABLE); } @@ -6619,7 +6532,7 @@ static void lpt_suspend_hw(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) { + if (HAS_PCH_LPT_LP(dev)) { uint32_t val = I915_READ(SOUTH_DSPCLK_GATE_D); val &= ~PCH_LP_PARTITION_LEVEL_DISABLE; @@ -7109,7 +7022,6 @@ void intel_init_pm(struct drm_device *dev) dev_priv->display.init_clock_gating = skl_init_clock_gating; dev_priv->display.update_wm = skl_update_wm; - dev_priv->display.update_sprite_wm = skl_update_sprite_wm; } else if (HAS_PCH_SPLIT(dev)) { ilk_setup_wm_latency(dev); @@ -7118,7 +7030,6 @@ void intel_init_pm(struct drm_device *dev) (!IS_GEN5(dev) && dev_priv->wm.pri_latency[0] && dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { dev_priv->display.update_wm = ilk_update_wm; - dev_priv->display.update_sprite_wm = ilk_update_sprite_wm; } else { DRM_DEBUG_KMS("Failed to read display plane latency. " "Disable CxSR\n"); @@ -7260,7 +7171,7 @@ static int vlv_gpu_freq_div(unsigned int czclk_freq) static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val) { - int div, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->mem_freq, 4); + int div, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000); div = vlv_gpu_freq_div(czclk_freq); if (div < 0) @@ -7271,7 +7182,7 @@ static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val) static int byt_freq_opcode(struct drm_i915_private *dev_priv, int val) { - int mul, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->mem_freq, 4); + int mul, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000); mul = vlv_gpu_freq_div(czclk_freq); if (mul < 0) @@ -7282,7 +7193,7 @@ static int byt_freq_opcode(struct drm_i915_private *dev_priv, int val) static int chv_gpu_freq(struct drm_i915_private *dev_priv, int val) { - int div, czclk_freq = dev_priv->rps.cz_freq; + int div, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000); div = vlv_gpu_freq_div(czclk_freq) / 2; if (div < 0) @@ -7293,7 +7204,7 @@ static int chv_gpu_freq(struct drm_i915_private *dev_priv, int val) static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val) { - int mul, czclk_freq = dev_priv->rps.cz_freq; + int mul, czclk_freq = DIV_ROUND_CLOSEST(dev_priv->czclk_freq, 1000); mul = vlv_gpu_freq_div(czclk_freq) / 2; if (mul < 0) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 6e6b8db..654ae99 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -717,7 +717,7 @@ static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req) struct drm_i915_private *dev_priv = dev->dev_private; struct i915_workarounds *w = &dev_priv->workarounds; - if (WARN_ON_ONCE(w->count == 0)) + if (w->count == 0) return 0; ring->gpu_caches_dirty = true; @@ -800,42 +800,29 @@ static int wa_add(struct drm_i915_private *dev_priv, #define WA_WRITE(addr, val) WA_REG(addr, 0xffffffff, val) -static int bdw_init_workarounds(struct intel_engine_cs *ring) +static int gen8_init_workarounds(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING); - /* WaDisableAsyncFlipPerfMode:bdw */ + /* WaDisableAsyncFlipPerfMode:bdw,chv */ WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE); - /* WaDisablePartialInstShootdown:bdw */ - /* WaDisableThreadStallDopClockGating:bdw (pre-production) */ + /* WaDisablePartialInstShootdown:bdw,chv */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, - PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE | - STALL_DOP_GATING_DISABLE); - - /* WaDisableDopClockGating:bdw */ - WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, - DOP_CLOCK_GATING_DISABLE); - - WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, - GEN8_SAMPLER_POWER_BYPASS_DIS); + PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); /* Use Force Non-Coherent whenever executing a 3D context. This is a * workaround for for a possible hang in the unlikely event a TLB * invalidation occurs during a PSD flush. */ + /* WaForceEnableNonCoherent:bdw,chv */ + /* WaHdcDisableFetchWhenMasked:bdw,chv */ WA_SET_BIT_MASKED(HDC_CHICKEN0, - /* WaForceEnableNonCoherent:bdw */ - HDC_FORCE_NON_COHERENT | - /* WaForceContextSaveRestoreNonCoherent:bdw */ - HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | - /* WaHdcDisableFetchWhenMasked:bdw */ HDC_DONOT_FETCH_MEM_WHEN_MASKED | - /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */ - (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0)); + HDC_FORCE_NON_COHERENT); /* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0: * "The Hierarchical Z RAW Stall Optimization allows non-overlapping @@ -843,13 +830,12 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring) * stalling waiting for the earlier ones to write to Hierarchical Z * buffer." * - * This optimization is off by default for Broadwell; turn it on. + * This optimization is off by default for BDW and CHV; turn it on. */ WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE); - /* Wa4x4STCOptimizationDisable:bdw */ - WA_SET_BIT_MASKED(CACHE_MODE_1, - GEN8_4x4_STC_OPTIMIZATION_DISABLE); + /* Wa4x4STCOptimizationDisable:bdw,chv */ + WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE); /* * BSpec recommends 8x4 when MSAA is used, @@ -866,56 +852,51 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring) return 0; } -static int chv_init_workarounds(struct intel_engine_cs *ring) +static int bdw_init_workarounds(struct intel_engine_cs *ring) { + int ret; struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; - WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING); + ret = gen8_init_workarounds(ring); + if (ret) + return ret; - /* WaDisableAsyncFlipPerfMode:chv */ - WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE); + /* WaDisableThreadStallDopClockGating:bdw (pre-production) */ + WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); - /* WaDisablePartialInstShootdown:chv */ - /* WaDisableThreadStallDopClockGating:chv */ - WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, - PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE | - STALL_DOP_GATING_DISABLE); + /* WaDisableDopClockGating:bdw */ + WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, + DOP_CLOCK_GATING_DISABLE); + + WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, + GEN8_SAMPLER_POWER_BYPASS_DIS); - /* Use Force Non-Coherent whenever executing a 3D context. This is a - * workaround for a possible hang in the unlikely event a TLB - * invalidation occurs during a PSD flush. - */ - /* WaForceEnableNonCoherent:chv */ - /* WaHdcDisableFetchWhenMasked:chv */ WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FORCE_NON_COHERENT | - HDC_DONOT_FETCH_MEM_WHEN_MASKED); + /* WaForceContextSaveRestoreNonCoherent:bdw */ + HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | + /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */ + (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0)); - /* According to the CACHE_MODE_0 default value documentation, some - * CHV platforms disable this optimization by default. Turn it on. - */ - WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE); + return 0; +} + +static int chv_init_workarounds(struct intel_engine_cs *ring) +{ + int ret; + struct drm_device *dev = ring->dev; + struct drm_i915_private *dev_priv = dev->dev_private; - /* Wa4x4STCOptimizationDisable:chv */ - WA_SET_BIT_MASKED(CACHE_MODE_1, - GEN8_4x4_STC_OPTIMIZATION_DISABLE); + ret = gen8_init_workarounds(ring); + if (ret) + return ret; + + /* WaDisableThreadStallDopClockGating:chv */ + WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); /* Improve HiZ throughput on CHV. */ WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X); - /* - * BSpec recommends 8x4 when MSAA is used, - * however in practice 16x4 seems fastest. - * - * Note that PS/WM thread counts depend on the WIZ hashing - * disable bit, which we don't touch here, but it's good - * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM). - */ - WA_SET_FIELD_MASKED(GEN7_GT_MODE, - GEN6_WIZ_HASHING_MASK, - GEN6_WIZ_HASHING_16x4); - return 0; } @@ -961,10 +942,9 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring) } /* Wa4x4STCOptimizationDisable:skl,bxt */ - WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE); - /* WaDisablePartialResolveInVc:skl,bxt */ - WA_SET_BIT_MASKED(CACHE_MODE_1, GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE); + WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE | + GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE)); /* WaCcsTlbPrefetchDisable:skl,bxt */ WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5, @@ -983,6 +963,16 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring) tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE; WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp); + /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */ + if (IS_SKYLAKE(dev) || + (IS_BROXTON(dev) && INTEL_REVID(dev) <= BXT_REVID_B0)) { + WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, + GEN8_SAMPLER_POWER_BYPASS_DIS); + } + + /* WaDisableSTUnitPowerOptimization:skl,bxt */ + WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); + return 0; } @@ -1031,10 +1021,13 @@ static int skl_tune_iz_hashing(struct intel_engine_cs *ring) static int skl_init_workarounds(struct intel_engine_cs *ring) { + int ret; struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; - gen9_init_workarounds(ring); + ret = gen9_init_workarounds(ring); + if (ret) + return ret; /* WaDisablePowerCompilerClockGating:skl */ if (INTEL_REVID(dev) == SKL_REVID_B0) @@ -1071,10 +1064,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring) static int bxt_init_workarounds(struct intel_engine_cs *ring) { + int ret; struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; - gen9_init_workarounds(ring); + ret = gen9_init_workarounds(ring); + if (ret) + return ret; /* WaDisableThreadStallDopClockGating:bxt */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, @@ -1996,14 +1992,14 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev, return 0; } -void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf) +static void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf) { drm_gem_object_unreference(&ringbuf->obj->base); ringbuf->obj = NULL; } -int intel_alloc_ringbuffer_obj(struct drm_device *dev, - struct intel_ringbuffer *ringbuf) +static int intel_alloc_ringbuffer_obj(struct drm_device *dev, + struct intel_ringbuffer *ringbuf) { struct drm_i915_gem_object *obj; @@ -2023,6 +2019,48 @@ int intel_alloc_ringbuffer_obj(struct drm_device *dev, return 0; } +struct intel_ringbuffer * +intel_engine_create_ringbuffer(struct intel_engine_cs *engine, int size) +{ + struct intel_ringbuffer *ring; + int ret; + + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (ring == NULL) + return ERR_PTR(-ENOMEM); + + ring->ring = engine; + + ring->size = size; + /* Workaround an erratum on the i830 which causes a hang if + * the TAIL pointer points to within the last 2 cachelines + * of the buffer. + */ + ring->effective_size = size; + if (IS_I830(engine->dev) || IS_845G(engine->dev)) + ring->effective_size -= 2 * CACHELINE_BYTES; + + ring->last_retired_head = -1; + intel_ring_update_space(ring); + + ret = intel_alloc_ringbuffer_obj(engine->dev, ring); + if (ret) { + DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", + engine->name, ret); + kfree(ring); + return ERR_PTR(ret); + } + + return ring; +} + +void +intel_ringbuffer_free(struct intel_ringbuffer *ring) +{ + intel_destroy_ringbuffer_obj(ring); + kfree(ring); +} + static int intel_init_ring_buffer(struct drm_device *dev, struct intel_engine_cs *ring) { @@ -2031,22 +2069,20 @@ static int intel_init_ring_buffer(struct drm_device *dev, WARN_ON(ring->buffer); - ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL); - if (!ringbuf) - return -ENOMEM; - ring->buffer = ringbuf; - ring->dev = dev; INIT_LIST_HEAD(&ring->active_list); INIT_LIST_HEAD(&ring->request_list); INIT_LIST_HEAD(&ring->execlist_queue); i915_gem_batch_pool_init(dev, &ring->batch_pool); - ringbuf->size = 32 * PAGE_SIZE; - ringbuf->ring = ring; memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno)); init_waitqueue_head(&ring->irq_queue); + ringbuf = intel_engine_create_ringbuffer(ring, 32 * PAGE_SIZE); + if (IS_ERR(ringbuf)) + return PTR_ERR(ringbuf); + ring->buffer = ringbuf; + if (I915_NEED_GFX_HWS(dev)) { ret = init_status_page(ring); if (ret) @@ -2058,15 +2094,6 @@ static int intel_init_ring_buffer(struct drm_device *dev, goto error; } - WARN_ON(ringbuf->obj); - - ret = intel_alloc_ringbuffer_obj(dev, ringbuf); - if (ret) { - DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", - ring->name, ret); - goto error; - } - ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf); if (ret) { DRM_ERROR("Failed to pin and map ringbuffer %s: %d\n", @@ -2075,14 +2102,6 @@ static int intel_init_ring_buffer(struct drm_device *dev, goto error; } - /* Workaround an erratum on the i830 which causes a hang if - * the TAIL pointer points to within the last 2 cachelines - * of the buffer. - */ - ringbuf->effective_size = ringbuf->size; - if (IS_I830(dev) || IS_845G(dev)) - ringbuf->effective_size -= 2 * CACHELINE_BYTES; - ret = i915_cmd_parser_init_ring(ring); if (ret) goto error; @@ -2090,7 +2109,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, return 0; error: - kfree(ringbuf); + intel_ringbuffer_free(ringbuf); ring->buffer = NULL; return ret; } @@ -2098,19 +2117,18 @@ error: void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv; - struct intel_ringbuffer *ringbuf; if (!intel_ring_initialized(ring)) return; dev_priv = to_i915(ring->dev); - ringbuf = ring->buffer; intel_stop_ring_buffer(ring); WARN_ON(!IS_GEN2(ring->dev) && (I915_READ_MODE(ring) & MODE_IDLE) == 0); - intel_unpin_ringbuffer_obj(ringbuf); - intel_destroy_ringbuffer_obj(ringbuf); + intel_unpin_ringbuffer_obj(ring->buffer); + intel_ringbuffer_free(ring->buffer); + ring->buffer = NULL; if (ring->cleanup) ring->cleanup(ring); @@ -2119,9 +2137,6 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) i915_cmd_parser_fini_ring(ring); i915_gem_batch_pool_fini(&ring->batch_pool); - - kfree(ringbuf); - ring->buffer = NULL; } static int ring_wait_for_space(struct intel_engine_cs *ring, int n) @@ -2608,6 +2623,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev) GEN8_RING_SEMAPHORE_INIT; } } else if (INTEL_INFO(dev)->gen >= 6) { + ring->init_context = intel_rcs_ctx_init; ring->add_request = gen6_add_request; ring->flush = gen7_render_ring_flush; if (INTEL_INFO(dev)->gen == 6) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 2e85fda..49fa41d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -377,6 +377,13 @@ intel_ring_sync_index(struct intel_engine_cs *ring, return idx; } +static inline void +intel_flush_status_page(struct intel_engine_cs *ring, int reg) +{ + drm_clflush_virt_range(&ring->status_page.page_addr[reg], + sizeof(uint32_t)); +} + static inline u32 intel_read_status_page(struct intel_engine_cs *ring, int reg) @@ -413,12 +420,12 @@ intel_write_status_page(struct intel_engine_cs *ring, #define I915_GEM_HWS_SCRATCH_INDEX 0x40 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT) -void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf); +struct intel_ringbuffer * +intel_engine_create_ringbuffer(struct intel_engine_cs *engine, int size); int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev, struct intel_ringbuffer *ringbuf); -void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf); -int intel_alloc_ringbuffer_obj(struct drm_device *dev, - struct intel_ringbuffer *ringbuf); +void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf); +void intel_ringbuffer_free(struct intel_ringbuffer *ring); void intel_stop_ring_buffer(struct intel_engine_cs *ring); void intel_cleanup_ring_buffer(struct intel_engine_cs *ring); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index af7fdb3..ec010ee 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -246,7 +246,8 @@ static void skl_power_well_post_enable(struct drm_i915_private *dev_priv, } if (power_well->data == SKL_DISP_PW_1) { - intel_prepare_ddi(dev); + if (!dev_priv->power_domains.initializing) + intel_prepare_ddi(dev); gen8_irq_power_well_post_enable(dev_priv, 1 << PIPE_A); } } @@ -463,14 +464,14 @@ static void assert_can_enable_dc5(struct drm_i915_private *dev_priv) bool pg2_enabled = intel_display_power_well_is_enabled(dev_priv, SKL_DISP_PW_2); - WARN(!IS_SKYLAKE(dev), "Platform doesn't support DC5.\n"); - WARN(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n"); - WARN(pg2_enabled, "PG2 not disabled to enable DC5.\n"); + WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC5.\n"); + WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n"); + WARN_ONCE(pg2_enabled, "PG2 not disabled to enable DC5.\n"); - WARN((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC5), - "DC5 already programmed to be enabled.\n"); - WARN(dev_priv->pm.suspended, - "DC5 cannot be enabled, if platform is runtime-suspended.\n"); + WARN_ONCE((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC5), + "DC5 already programmed to be enabled.\n"); + WARN_ONCE(dev_priv->pm.suspended, + "DC5 cannot be enabled, if platform is runtime-suspended.\n"); assert_csr_loaded(dev_priv); } @@ -486,8 +487,8 @@ static void assert_can_disable_dc5(struct drm_i915_private *dev_priv) if (dev_priv->power_domains.initializing) return; - WARN(!pg2_enabled, "PG2 not enabled to disable DC5.\n"); - WARN(dev_priv->pm.suspended, + WARN_ONCE(!pg2_enabled, "PG2 not enabled to disable DC5.\n"); + WARN_ONCE(dev_priv->pm.suspended, "Disabling of DC5 while platform is runtime-suspended should never happen.\n"); } @@ -526,12 +527,12 @@ static void assert_can_enable_dc6(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; - WARN(!IS_SKYLAKE(dev), "Platform doesn't support DC6.\n"); - WARN(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n"); - WARN(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE, - "Backlight is not disabled.\n"); - WARN((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6), - "DC6 already programmed to be enabled.\n"); + WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC6.\n"); + WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n"); + WARN_ONCE(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE, + "Backlight is not disabled.\n"); + WARN_ONCE((I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6), + "DC6 already programmed to be enabled.\n"); assert_csr_loaded(dev_priv); } @@ -546,8 +547,8 @@ static void assert_can_disable_dc6(struct drm_i915_private *dev_priv) return; assert_csr_loaded(dev_priv); - WARN(!(I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6), - "DC6 already programmed to be disabled.\n"); + WARN_ONCE(!(I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC6), + "DC6 already programmed to be disabled.\n"); } static void skl_enable_dc6(struct drm_i915_private *dev_priv) @@ -656,9 +657,15 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv, } } else { if (enable_requested) { - I915_WRITE(HSW_PWR_WELL_DRIVER, tmp & ~req_mask); - POSTING_READ(HSW_PWR_WELL_DRIVER); - DRM_DEBUG_KMS("Disabling %s\n", power_well->name); + if (IS_SKYLAKE(dev) && + (power_well->data == SKL_DISP_PW_1) && + (intel_csr_load_status_get(dev_priv) == FW_LOADED)) + DRM_DEBUG_KMS("Not Disabling PW1, dmc will handle\n"); + else { + I915_WRITE(HSW_PWR_WELL_DRIVER, tmp & ~req_mask); + POSTING_READ(HSW_PWR_WELL_DRIVER); + DRM_DEBUG_KMS("Disabling %s\n", power_well->name); + } if ((GEN9_ENABLE_DC5(dev) || SKL_ENABLE_DC6(dev)) && power_well->data == SKL_DISP_PW_2) { @@ -670,7 +677,7 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv, wait_for((state = intel_csr_load_status_get(dev_priv)) != FW_UNINITIALIZED, 1000); if (state != FW_LOADED) - DRM_ERROR("CSR firmware not ready (%d)\n", + DRM_DEBUG("CSR firmware not ready (%d)\n", state); else if (SKL_ENABLE_DC6(dev)) @@ -855,6 +862,25 @@ static bool vlv_power_well_enabled(struct drm_i915_private *dev_priv, static void vlv_display_power_well_init(struct drm_i915_private *dev_priv) { + enum pipe pipe; + + /* + * Enable the CRI clock source so we can get at the + * display and the reference clock for VGA + * hotplug / manual detection. Supposedly DSI also + * needs the ref clock up and running. + * + * CHV DPLL B/C have some issues if VGA mode is enabled. + */ + for_each_pipe(dev_priv->dev, pipe) { + u32 val = I915_READ(DPLL(pipe)); + + val |= DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS; + if (pipe != PIPE_A) + val |= DPLL_INTEGRATED_CRI_CLK_VLV; + + I915_WRITE(DPLL(pipe), val); + } spin_lock_irq(&dev_priv->irq_lock); valleyview_enable_display_irqs(dev_priv); @@ -906,13 +932,7 @@ static void vlv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv, { WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC); - /* - * Enable the CRI clock source so we can get at the - * display and the reference clock for VGA - * hotplug / manual detection. - */ - I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | DPLL_VGA_MODE_DIS | - DPLL_REF_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV); + /* since ref/cri clock was enabled */ udelay(1); /* >10ns for cmnreset, >0ns for sidereset */ vlv_set_power_well(dev_priv, power_well, true); @@ -947,30 +967,149 @@ static void vlv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv, vlv_set_power_well(dev_priv, power_well, false); } +#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1) + +static struct i915_power_well *lookup_power_well(struct drm_i915_private *dev_priv, + int power_well_id) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_well *power_well; + int i; + + for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) { + if (power_well->data == power_well_id) + return power_well; + } + + return NULL; +} + +#define BITS_SET(val, bits) (((val) & (bits)) == (bits)) + +static void assert_chv_phy_status(struct drm_i915_private *dev_priv) +{ + struct i915_power_well *cmn_bc = + lookup_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_BC); + struct i915_power_well *cmn_d = + lookup_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_D); + u32 phy_control = dev_priv->chv_phy_control; + u32 phy_status = 0; + u32 phy_status_mask = 0xffffffff; + u32 tmp; + + /* + * The BIOS can leave the PHY is some weird state + * where it doesn't fully power down some parts. + * Disable the asserts until the PHY has been fully + * reset (ie. the power well has been disabled at + * least once). + */ + if (!dev_priv->chv_phy_assert[DPIO_PHY0]) + phy_status_mask &= ~(PHY_STATUS_CMN_LDO(DPIO_PHY0, DPIO_CH0) | + PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 0) | + PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 1) | + PHY_STATUS_CMN_LDO(DPIO_PHY0, DPIO_CH1) | + PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 0) | + PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 1)); + + if (!dev_priv->chv_phy_assert[DPIO_PHY1]) + phy_status_mask &= ~(PHY_STATUS_CMN_LDO(DPIO_PHY1, DPIO_CH0) | + PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 0) | + PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 1)); + + if (cmn_bc->ops->is_enabled(dev_priv, cmn_bc)) { + phy_status |= PHY_POWERGOOD(DPIO_PHY0); + + /* this assumes override is only used to enable lanes */ + if ((phy_control & PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH0)) == 0) + phy_control |= PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH0); + + if ((phy_control & PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH1)) == 0) + phy_control |= PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH1); + + /* CL1 is on whenever anything is on in either channel */ + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH0) | + PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH1))) + phy_status |= PHY_STATUS_CMN_LDO(DPIO_PHY0, DPIO_CH0); + + /* + * The DPLLB check accounts for the pipe B + port A usage + * with CL2 powered up but all the lanes in the second channel + * powered down. + */ + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY0, DPIO_CH1)) && + (I915_READ(DPLL(PIPE_B)) & DPLL_VCO_ENABLE) == 0) + phy_status |= PHY_STATUS_CMN_LDO(DPIO_PHY0, DPIO_CH1); + + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0x3, DPIO_PHY0, DPIO_CH0))) + phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 0); + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0xc, DPIO_PHY0, DPIO_CH0))) + phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 1); + + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0x3, DPIO_PHY0, DPIO_CH1))) + phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 0); + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0xc, DPIO_PHY0, DPIO_CH1))) + phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 1); + } + + if (cmn_d->ops->is_enabled(dev_priv, cmn_d)) { + phy_status |= PHY_POWERGOOD(DPIO_PHY1); + + /* this assumes override is only used to enable lanes */ + if ((phy_control & PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY1, DPIO_CH0)) == 0) + phy_control |= PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY1, DPIO_CH0); + + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0xf, DPIO_PHY1, DPIO_CH0))) + phy_status |= PHY_STATUS_CMN_LDO(DPIO_PHY1, DPIO_CH0); + + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0x3, DPIO_PHY1, DPIO_CH0))) + phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 0); + if (BITS_SET(phy_control, + PHY_CH_POWER_DOWN_OVRD(0xc, DPIO_PHY1, DPIO_CH0))) + phy_status |= PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 1); + } + + phy_status &= phy_status_mask; + + /* + * The PHY may be busy with some initial calibration and whatnot, + * so the power state can take a while to actually change. + */ + if (wait_for((tmp = I915_READ(DISPLAY_PHY_STATUS) & phy_status_mask) == phy_status, 10)) + WARN(phy_status != tmp, + "Unexpected PHY_STATUS 0x%08x, expected 0x%08x (PHY_CONTROL=0x%08x)\n", + tmp, phy_status, dev_priv->chv_phy_control); +} + +#undef BITS_SET + static void chv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { enum dpio_phy phy; + enum pipe pipe; + uint32_t tmp; WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC && power_well->data != PUNIT_POWER_WELL_DPIO_CMN_D); - /* - * Enable the CRI clock source so we can get at the - * display and the reference clock for VGA - * hotplug / manual detection. - */ if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) { + pipe = PIPE_A; phy = DPIO_PHY0; - I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | DPLL_VGA_MODE_DIS | - DPLL_REF_CLK_ENABLE_VLV); - I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) | DPLL_VGA_MODE_DIS | - DPLL_REF_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV); } else { + pipe = PIPE_C; phy = DPIO_PHY1; - I915_WRITE(DPLL(PIPE_C), I915_READ(DPLL(PIPE_C)) | DPLL_VGA_MODE_DIS | - DPLL_REF_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV); } + + /* since ref/cri clock was enabled */ udelay(1); /* >10ns for cmnreset, >0ns for sidereset */ vlv_set_power_well(dev_priv, power_well, true); @@ -978,8 +1117,38 @@ static void chv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv, if (wait_for(I915_READ(DISPLAY_PHY_STATUS) & PHY_POWERGOOD(phy), 1)) DRM_ERROR("Display PHY %d is not power up\n", phy); + mutex_lock(&dev_priv->sb_lock); + + /* Enable dynamic power down */ + tmp = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW28); + tmp |= DPIO_DYNPWRDOWNEN_CH0 | DPIO_CL1POWERDOWNEN | + DPIO_SUS_CLK_CONFIG_GATE_CLKREQ; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW28, tmp); + + if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) { + tmp = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW6_CH1); + tmp |= DPIO_DYNPWRDOWNEN_CH1; + vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW6_CH1, tmp); + } else { + /* + * Force the non-existing CL2 off. BXT does this + * too, so maybe it saves some power even though + * CL2 doesn't exist? + */ + tmp = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30); + tmp |= DPIO_CL2_LDOFUSE_PWRENB; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, tmp); + } + + mutex_unlock(&dev_priv->sb_lock); + dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(phy); I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control); + + DRM_DEBUG_KMS("Enabled DPIO PHY%d (PHY_CONTROL=0x%08x)\n", + phy, dev_priv->chv_phy_control); + + assert_chv_phy_status(dev_priv); } static void chv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv, @@ -1003,6 +1172,137 @@ static void chv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv, I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control); vlv_set_power_well(dev_priv, power_well, false); + + DRM_DEBUG_KMS("Disabled DPIO PHY%d (PHY_CONTROL=0x%08x)\n", + phy, dev_priv->chv_phy_control); + + /* PHY is fully reset now, so we can enable the PHY state asserts */ + dev_priv->chv_phy_assert[phy] = true; + + assert_chv_phy_status(dev_priv); +} + +static void assert_chv_phy_powergate(struct drm_i915_private *dev_priv, enum dpio_phy phy, + enum dpio_channel ch, bool override, unsigned int mask) +{ + enum pipe pipe = phy == DPIO_PHY0 ? PIPE_A : PIPE_C; + u32 reg, val, expected, actual; + + /* + * The BIOS can leave the PHY is some weird state + * where it doesn't fully power down some parts. + * Disable the asserts until the PHY has been fully + * reset (ie. the power well has been disabled at + * least once). + */ + if (!dev_priv->chv_phy_assert[phy]) + return; + + if (ch == DPIO_CH0) + reg = _CHV_CMN_DW0_CH0; + else + reg = _CHV_CMN_DW6_CH1; + + mutex_lock(&dev_priv->sb_lock); + val = vlv_dpio_read(dev_priv, pipe, reg); + mutex_unlock(&dev_priv->sb_lock); + + /* + * This assumes !override is only used when the port is disabled. + * All lanes should power down even without the override when + * the port is disabled. + */ + if (!override || mask == 0xf) { + expected = DPIO_ALLDL_POWERDOWN | DPIO_ANYDL_POWERDOWN; + /* + * If CH1 common lane is not active anymore + * (eg. for pipe B DPLL) the entire channel will + * shut down, which causes the common lane registers + * to read as 0. That means we can't actually check + * the lane power down status bits, but as the entire + * register reads as 0 it's a good indication that the + * channel is indeed entirely powered down. + */ + if (ch == DPIO_CH1 && val == 0) + expected = 0; + } else if (mask != 0x0) { + expected = DPIO_ANYDL_POWERDOWN; + } else { + expected = 0; + } + + if (ch == DPIO_CH0) + actual = val >> DPIO_ANYDL_POWERDOWN_SHIFT_CH0; + else + actual = val >> DPIO_ANYDL_POWERDOWN_SHIFT_CH1; + actual &= DPIO_ALLDL_POWERDOWN | DPIO_ANYDL_POWERDOWN; + + WARN(actual != expected, + "Unexpected DPIO lane power down: all %d, any %d. Expected: all %d, any %d. (0x%x = 0x%08x)\n", + !!(actual & DPIO_ALLDL_POWERDOWN), !!(actual & DPIO_ANYDL_POWERDOWN), + !!(expected & DPIO_ALLDL_POWERDOWN), !!(expected & DPIO_ANYDL_POWERDOWN), + reg, val); +} + +bool chv_phy_powergate_ch(struct drm_i915_private *dev_priv, enum dpio_phy phy, + enum dpio_channel ch, bool override) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + bool was_override; + + mutex_lock(&power_domains->lock); + + was_override = dev_priv->chv_phy_control & PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + + if (override == was_override) + goto out; + + if (override) + dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + else + dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + + I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control); + + DRM_DEBUG_KMS("Power gating DPIO PHY%d CH%d (DPIO_PHY_CONTROL=0x%08x)\n", + phy, ch, dev_priv->chv_phy_control); + + assert_chv_phy_status(dev_priv); + +out: + mutex_unlock(&power_domains->lock); + + return was_override; +} + +void chv_phy_powergate_lanes(struct intel_encoder *encoder, + bool override, unsigned int mask) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct i915_power_domains *power_domains = &dev_priv->power_domains; + enum dpio_phy phy = vlv_dport_to_phy(enc_to_dig_port(&encoder->base)); + enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base)); + + mutex_lock(&power_domains->lock); + + dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD(0xf, phy, ch); + dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD(mask, phy, ch); + + if (override) + dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + else + dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + + I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control); + + DRM_DEBUG_KMS("Power gating DPIO PHY%d CH%d lanes 0x%x (PHY_CONTROL=0x%08x)\n", + phy, ch, mask, dev_priv->chv_phy_control); + + assert_chv_phy_status(dev_priv); + + assert_chv_phy_powergate(dev_priv, phy, ch, override, mask); + + mutex_unlock(&power_domains->lock); } static bool chv_pipe_power_well_enabled(struct drm_i915_private *dev_priv, @@ -1166,8 +1466,6 @@ void intel_display_power_put(struct drm_i915_private *dev_priv, intel_runtime_pm_put(dev_priv); } -#define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1) - #define HSW_ALWAYS_ON_POWER_DOMAINS ( \ BIT(POWER_DOMAIN_PIPE_A) | \ BIT(POWER_DOMAIN_TRANSCODER_EDP) | \ @@ -1429,21 +1727,6 @@ static struct i915_power_well chv_power_wells[] = { }, }; -static struct i915_power_well *lookup_power_well(struct drm_i915_private *dev_priv, - int power_well_id) -{ - struct i915_power_domains *power_domains = &dev_priv->power_domains; - struct i915_power_well *power_well; - int i; - - for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) { - if (power_well->data == power_well_id) - return power_well; - } - - return NULL; -} - bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv, int power_well_id) { @@ -1582,7 +1865,6 @@ static void intel_runtime_pm_disable(struct drm_i915_private *dev_priv) /* Make sure we're not suspended first. */ pm_runtime_get_sync(device); - pm_runtime_disable(device); } /** @@ -1629,19 +1911,80 @@ static void chv_phy_control_init(struct drm_i915_private *dev_priv) * DISPLAY_PHY_CONTROL can get corrupted if read. As a * workaround never ever read DISPLAY_PHY_CONTROL, and * instead maintain a shadow copy ourselves. Use the actual - * power well state to reconstruct the expected initial - * value. + * power well state and lane status to reconstruct the + * expected initial value. */ dev_priv->chv_phy_control = PHY_LDO_SEQ_DELAY(PHY_LDO_DELAY_600NS, DPIO_PHY0) | PHY_LDO_SEQ_DELAY(PHY_LDO_DELAY_600NS, DPIO_PHY1) | - PHY_CH_POWER_MODE(PHY_CH_SU_PSR, DPIO_PHY0, DPIO_CH0) | - PHY_CH_POWER_MODE(PHY_CH_SU_PSR, DPIO_PHY0, DPIO_CH1) | - PHY_CH_POWER_MODE(PHY_CH_SU_PSR, DPIO_PHY1, DPIO_CH0); - if (cmn_bc->ops->is_enabled(dev_priv, cmn_bc)) + PHY_CH_POWER_MODE(PHY_CH_DEEP_PSR, DPIO_PHY0, DPIO_CH0) | + PHY_CH_POWER_MODE(PHY_CH_DEEP_PSR, DPIO_PHY0, DPIO_CH1) | + PHY_CH_POWER_MODE(PHY_CH_DEEP_PSR, DPIO_PHY1, DPIO_CH0); + + /* + * If all lanes are disabled we leave the override disabled + * with all power down bits cleared to match the state we + * would use after disabling the port. Otherwise enable the + * override and set the lane powerdown bits accding to the + * current lane status. + */ + if (cmn_bc->ops->is_enabled(dev_priv, cmn_bc)) { + uint32_t status = I915_READ(DPLL(PIPE_A)); + unsigned int mask; + + mask = status & DPLL_PORTB_READY_MASK; + if (mask == 0xf) + mask = 0x0; + else + dev_priv->chv_phy_control |= + PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH0); + + dev_priv->chv_phy_control |= + PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY0, DPIO_CH0); + + mask = (status & DPLL_PORTC_READY_MASK) >> 4; + if (mask == 0xf) + mask = 0x0; + else + dev_priv->chv_phy_control |= + PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH1); + + dev_priv->chv_phy_control |= + PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY0, DPIO_CH1); + dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY0); - if (cmn_d->ops->is_enabled(dev_priv, cmn_d)) + + dev_priv->chv_phy_assert[DPIO_PHY0] = false; + } else { + dev_priv->chv_phy_assert[DPIO_PHY0] = true; + } + + if (cmn_d->ops->is_enabled(dev_priv, cmn_d)) { + uint32_t status = I915_READ(DPIO_PHY_STATUS); + unsigned int mask; + + mask = status & DPLL_PORTD_READY_MASK; + + if (mask == 0xf) + mask = 0x0; + else + dev_priv->chv_phy_control |= + PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY1, DPIO_CH0); + + dev_priv->chv_phy_control |= + PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY1, DPIO_CH0); + dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY1); + + dev_priv->chv_phy_assert[DPIO_PHY1] = false; + } else { + dev_priv->chv_phy_assert[DPIO_PHY1] = true; + } + + I915_WRITE(DISPLAY_PHY_CONTROL, dev_priv->chv_phy_control); + + DRM_DEBUG_KMS("Initial PHY_CONTROL=0x%08x\n", + dev_priv->chv_phy_control); } static void vlv_cmnlane_wa(struct drm_i915_private *dev_priv) @@ -1687,7 +2030,9 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv) power_domains->initializing = true; if (IS_CHERRYVIEW(dev)) { + mutex_lock(&power_domains->lock); chv_phy_control_init(dev_priv); + mutex_unlock(&power_domains->lock); } else if (IS_VALLEYVIEW(dev)) { mutex_lock(&power_domains->lock); vlv_cmnlane_wa(dev_priv); @@ -1819,8 +2164,6 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv) if (!HAS_RUNTIME_PM(dev)) return; - pm_runtime_set_active(device); - /* * RPM depends on RC6 to save restore the GT HW context, so make RC6 a * requirement. diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index c98098e..c42b636 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -53,7 +53,7 @@ #define IS_DIGITAL(c) (c->output_flag & (SDVO_TMDS_MASK | SDVO_LVDS_MASK)) -static const char *tv_format_names[] = { +static const char * const tv_format_names[] = { "NTSC_M" , "NTSC_J" , "NTSC_443", "PAL_B" , "PAL_D" , "PAL_G" , "PAL_H" , "PAL_I" , "PAL_M" , @@ -63,7 +63,7 @@ static const char *tv_format_names[] = { "SECAM_60" }; -#define TV_FORMAT_NUM (sizeof(tv_format_names) / sizeof(*tv_format_names)) +#define TV_FORMAT_NUM ARRAY_SIZE(tv_format_names) struct intel_sdvo { struct intel_encoder base; @@ -107,6 +107,11 @@ struct intel_sdvo { bool color_range_auto; /** + * HDMI user specified aspect ratio + */ + enum hdmi_picture_aspect aspect_ratio; + + /** * This is set if we're going to treat the device as TV-out. * * While we have these nice friendly flags for output types that ought @@ -452,7 +457,7 @@ static void intel_sdvo_debug_write(struct intel_sdvo *intel_sdvo, u8 cmd, DRM_DEBUG_KMS("%s: W: %02X %s\n", SDVO_NAME(intel_sdvo), cmd, buffer); } -static const char *cmd_status_names[] = { +static const char * const cmd_status_names[] = { "Power on", "Success", "Not supported", @@ -603,11 +608,11 @@ log_fail: return false; } -static int intel_sdvo_get_pixel_multiplier(struct drm_display_mode *mode) +static int intel_sdvo_get_pixel_multiplier(const struct drm_display_mode *adjusted_mode) { - if (mode->clock >= 100000) + if (adjusted_mode->crtc_clock >= 100000) return 1; - else if (mode->clock >= 50000) + else if (adjusted_mode->crtc_clock >= 50000) return 2; else return 4; @@ -1181,6 +1186,10 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, if (intel_sdvo->is_tv) i9xx_adjust_sdvo_tv_clock(pipe_config); + /* Set user selected PAR to incoming mode's member */ + if (intel_sdvo->is_hdmi) + adjusted_mode->picture_aspect_ratio = intel_sdvo->aspect_ratio; + return true; } @@ -1189,8 +1198,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder) struct drm_device *dev = intel_encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc = to_intel_crtc(intel_encoder->base.crtc); - struct drm_display_mode *adjusted_mode = - &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; struct drm_display_mode *mode = &crtc->config->base.mode; struct intel_sdvo *intel_sdvo = to_sdvo(intel_encoder); u32 sdvox; @@ -2044,6 +2052,23 @@ intel_sdvo_set_property(struct drm_connector *connector, goto done; } + if (property == connector->dev->mode_config.aspect_ratio_property) { + switch (val) { + case DRM_MODE_PICTURE_ASPECT_NONE: + intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_NONE; + break; + case DRM_MODE_PICTURE_ASPECT_4_3: + intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_4_3; + break; + case DRM_MODE_PICTURE_ASPECT_16_9: + intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_16_9; + break; + default: + return -EINVAL; + } + goto done; + } + #define CHECK_PROPERTY(name, NAME) \ if (intel_sdvo_connector->name == property) { \ if (intel_sdvo_connector->cur_##name == temp_value) return 0; \ @@ -2222,7 +2247,7 @@ intel_sdvo_guess_ddc_bus(struct intel_sdvo *sdvo) */ static void intel_sdvo_select_ddc_bus(struct drm_i915_private *dev_priv, - struct intel_sdvo *sdvo, u32 reg) + struct intel_sdvo *sdvo) { struct sdvo_device_mapping *mapping; @@ -2239,7 +2264,7 @@ intel_sdvo_select_ddc_bus(struct drm_i915_private *dev_priv, static void intel_sdvo_select_i2c_bus(struct drm_i915_private *dev_priv, - struct intel_sdvo *sdvo, u32 reg) + struct intel_sdvo *sdvo) { struct sdvo_device_mapping *mapping; u8 pin; @@ -2383,6 +2408,8 @@ intel_sdvo_add_hdmi_properties(struct intel_sdvo *intel_sdvo, intel_attach_broadcast_rgb_property(&connector->base.base); intel_sdvo->color_range_auto = true; } + intel_attach_aspect_ratio_property(&connector->base.base); + intel_sdvo->aspect_ratio = HDMI_PICTURE_ASPECT_NONE; } static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void) @@ -2925,7 +2952,7 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob) intel_sdvo->sdvo_reg = sdvo_reg; intel_sdvo->is_sdvob = is_sdvob; intel_sdvo->slave_addr = intel_sdvo_get_slave_addr(dev, intel_sdvo) >> 1; - intel_sdvo_select_i2c_bus(dev_priv, intel_sdvo, sdvo_reg); + intel_sdvo_select_i2c_bus(dev_priv, intel_sdvo); if (!intel_sdvo_init_ddc_proxy(intel_sdvo, dev)) goto err_i2c_bus; @@ -2987,7 +3014,7 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob) */ intel_sdvo->base.cloneable = 0; - intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo, sdvo_reg); + intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo); /* Set the input timing to the screen. Assume always input 0. */ if (!intel_sdvo_set_target_input(intel_sdvo)) diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 9d8af2f..dd2d568 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -53,13 +53,15 @@ format_is_yuv(uint32_t format) } } -static int usecs_to_scanlines(const struct drm_display_mode *mode, int usecs) +static int usecs_to_scanlines(const struct drm_display_mode *adjusted_mode, + int usecs) { /* paranoia */ - if (!mode->crtc_htotal) + if (!adjusted_mode->crtc_htotal) return 1; - return DIV_ROUND_UP(usecs * mode->crtc_clock, 1000 * mode->crtc_htotal); + return DIV_ROUND_UP(usecs * adjusted_mode->crtc_clock, + 1000 * adjusted_mode->crtc_htotal); } /** @@ -76,26 +78,25 @@ static int usecs_to_scanlines(const struct drm_display_mode *mode, int usecs) * avoid random delays. The value written to @start_vbl_count should be * supplied to intel_pipe_update_end() for error checking. */ -void intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count) +void intel_pipe_update_start(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; - const struct drm_display_mode *mode = &crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; enum pipe pipe = crtc->pipe; long timeout = msecs_to_jiffies_timeout(1); int scanline, min, max, vblank_start; wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base); DEFINE_WAIT(wait); - vblank_start = mode->crtc_vblank_start; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vblank_start = adjusted_mode->crtc_vblank_start; + if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) vblank_start = DIV_ROUND_UP(vblank_start, 2); /* FIXME needs to be calibrated sensibly */ - min = vblank_start - usecs_to_scanlines(mode, 100); + min = vblank_start - usecs_to_scanlines(adjusted_mode, 100); max = vblank_start - 1; local_irq_disable(); - *start_vbl_count = 0; if (min <= 0 || max <= 0) return; @@ -103,7 +104,9 @@ void intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count) if (WARN_ON(drm_crtc_vblank_get(&crtc->base))) return; - trace_i915_pipe_update_start(crtc, min, max); + crtc->debug.min_vbl = min; + crtc->debug.max_vbl = max; + trace_i915_pipe_update_start(crtc); for (;;) { /* @@ -134,9 +137,12 @@ void intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count) drm_crtc_vblank_put(&crtc->base); - *start_vbl_count = dev->driver->get_vblank_counter(dev, pipe); + crtc->debug.scanline_start = scanline; + crtc->debug.start_vbl_time = ktime_get(); + crtc->debug.start_vbl_count = + dev->driver->get_vblank_counter(dev, pipe); - trace_i915_pipe_update_vblank_evaded(crtc, min, max, *start_vbl_count); + trace_i915_pipe_update_vblank_evaded(crtc); } /** @@ -148,19 +154,27 @@ void intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count) * re-enables interrupts and verifies the update was actually completed * before a vblank using the value of @start_vbl_count. */ -void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count) +void intel_pipe_update_end(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; enum pipe pipe = crtc->pipe; + int scanline_end = intel_get_crtc_scanline(crtc); u32 end_vbl_count = dev->driver->get_vblank_counter(dev, pipe); + ktime_t end_vbl_time = ktime_get(); - trace_i915_pipe_update_end(crtc, end_vbl_count); + trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end); local_irq_enable(); - if (start_vbl_count && start_vbl_count != end_vbl_count) - DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u)\n", - pipe_name(pipe), start_vbl_count, end_vbl_count); + if (crtc->debug.start_vbl_count && + crtc->debug.start_vbl_count != end_vbl_count) { + DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u) time %lld us, min %d, max %d, scanline start %d, end %d\n", + pipe_name(pipe), crtc->debug.start_vbl_count, + end_vbl_count, + ktime_us_delta(end_vbl_time, crtc->debug.start_vbl_time), + crtc->debug.min_vbl, crtc->debug.max_vbl, + crtc->debug.scanline_start, scanline_end); + } } static void @@ -178,7 +192,6 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, const int pipe = intel_plane->pipe; const int plane = intel_plane->plane + 1; u32 plane_ctl, stride_div, stride; - int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); const struct drm_intel_sprite_colorkey *key = &to_intel_plane_state(drm_plane->state)->ckey; unsigned long surf_addr; @@ -197,10 +210,6 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, rotation = drm_plane->state->rotation; plane_ctl |= skl_plane_ctl_rotation(rotation); - intel_update_sprite_watermarks(drm_plane, crtc, src_w, src_h, - pixel_size, true, - src_w != crtc_w || src_h != crtc_h); - stride_div = intel_fb_stride_alignment(dev, fb->modifier[0], fb->pixel_format); @@ -223,12 +232,12 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, else if (key->flags & I915_SET_COLORKEY_SOURCE) plane_ctl |= PLANE_CTL_KEY_ENABLE_SOURCE; - surf_addr = intel_plane_obj_offset(intel_plane, obj); + surf_addr = intel_plane_obj_offset(intel_plane, obj, 0); if (intel_rotation_90_or_270(rotation)) { /* stride: Surface height in tiles */ tile_height = intel_tile_height(dev, fb->pixel_format, - fb->modifier[0]); + fb->modifier[0], 0); stride = DIV_ROUND_UP(fb->height, tile_height); plane_size = (src_w << 16) | src_h; x_offset = stride * tile_height - y - (src_h + 1); @@ -282,8 +291,6 @@ skl_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc) I915_WRITE(PLANE_SURF(pipe, plane), 0); POSTING_READ(PLANE_SURF(pipe, plane)); - - intel_update_sprite_watermarks(dplane, crtc, 0, 0, 0, false, false); } static void @@ -526,10 +533,6 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, if (IS_HASWELL(dev) || IS_BROADWELL(dev)) sprctl |= SPRITE_PIPE_CSC_ENABLE; - intel_update_sprite_watermarks(plane, crtc, src_w, src_h, pixel_size, - true, - src_w != crtc_w || src_h != crtc_h); - /* Sizes are 0 based */ src_w--; src_h--; @@ -663,10 +666,6 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, if (IS_GEN6(dev)) dvscntr |= DVS_TRICKLE_FEED_DISABLE; /* must disable */ - intel_update_sprite_watermarks(plane, crtc, src_w, src_h, - pixel_size, true, - src_w != crtc_w || src_h != crtc_h); - /* Sizes are 0 based */ src_w--; src_h--; @@ -923,8 +922,6 @@ intel_commit_sprite_plane(struct drm_plane *plane, crtc = crtc ? crtc : plane->crtc; - plane->fb = fb; - if (!crtc->state->active) return; @@ -1121,7 +1118,7 @@ intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane) intel_plane->pipe = pipe; intel_plane->plane = plane; - intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER_SPRITE(pipe); + intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER_SPRITE(pipe, plane); intel_plane->check_plane = intel_check_sprite_plane; intel_plane->commit_plane = intel_commit_sprite_plane; possible_crtcs = (1 << pipe); diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 590ceab..6bea789 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1138,13 +1138,13 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder) j = 0; for (i = 0; i < 60; i++) - I915_WRITE(TV_H_LUMA_0 + (i<<2), tv_mode->filter_table[j++]); + I915_WRITE(TV_H_LUMA(i), tv_mode->filter_table[j++]); for (i = 0; i < 60; i++) - I915_WRITE(TV_H_CHROMA_0 + (i<<2), tv_mode->filter_table[j++]); + I915_WRITE(TV_H_CHROMA(i), tv_mode->filter_table[j++]); for (i = 0; i < 43; i++) - I915_WRITE(TV_V_LUMA_0 + (i<<2), tv_mode->filter_table[j++]); + I915_WRITE(TV_V_LUMA(i), tv_mode->filter_table[j++]); for (i = 0; i < 43; i++) - I915_WRITE(TV_V_CHROMA_0 + (i<<2), tv_mode->filter_table[j++]); + I915_WRITE(TV_V_CHROMA(i), tv_mode->filter_table[j++]); I915_WRITE(TV_DAC, I915_READ(TV_DAC) & TV_DAC_SAVE); I915_WRITE(TV_CTL, tv_ctl); } @@ -1291,7 +1291,7 @@ static void intel_tv_find_better_format(struct drm_connector *connector) return; - for (i = 0; i < sizeof(tv_modes) / sizeof(*tv_modes); i++) { + for (i = 0; i < ARRAY_SIZE(tv_modes); i++) { tv_mode = tv_modes + i; if ((intel_tv->type == DRM_MODE_CONNECTOR_Component) == diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 9d3c2e4..b43c6d0 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -27,7 +27,7 @@ #include <linux/pm_runtime.h> -#define FORCEWAKE_ACK_TIMEOUT_MS 2 +#define FORCEWAKE_ACK_TIMEOUT_MS 50 #define __raw_i915_read8(dev_priv__, reg__) readb((dev_priv__)->regs + (reg__)) #define __raw_i915_write8(dev_priv__, reg__, val__) writeb(val__, (dev_priv__)->regs + (reg__)) @@ -52,8 +52,7 @@ static const char * const forcewake_domain_names[] = { const char * intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id) { - BUILD_BUG_ON((sizeof(forcewake_domain_names)/sizeof(const char *)) != - FW_DOMAIN_ID_COUNT); + BUILD_BUG_ON(ARRAY_SIZE(forcewake_domain_names) != FW_DOMAIN_ID_COUNT); if (id >= 0 && id < FW_DOMAIN_ID_COUNT) return forcewake_domain_names[id]; @@ -770,6 +769,7 @@ static u##x \ gen9_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \ enum forcewake_domains fw_engine; \ GEN6_READ_HEADER(x); \ + hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \ if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg))) \ fw_engine = 0; \ else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg)) \ @@ -783,6 +783,7 @@ gen9_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \ if (fw_engine) \ __force_wake_get(dev_priv, fw_engine); \ val = __raw_i915_read##x(dev_priv, reg); \ + hsw_unclaimed_reg_debug(dev_priv, reg, true, false); \ GEN6_READ_FOOTER; \ } @@ -983,6 +984,7 @@ gen9_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, \ bool trace) { \ enum forcewake_domains fw_engine; \ GEN6_WRITE_HEADER; \ + hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \ if (!SKL_NEEDS_FORCE_WAKE((dev_priv), (reg)) || \ is_gen9_shadowed(dev_priv, reg)) \ fw_engine = 0; \ @@ -997,6 +999,8 @@ gen9_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, \ if (fw_engine) \ __force_wake_get(dev_priv, fw_engine); \ __raw_i915_write##x(dev_priv, reg, val); \ + hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \ + hsw_unclaimed_reg_detect(dev_priv); \ GEN6_WRITE_FOOTER; \ } @@ -1198,8 +1202,6 @@ void intel_uncore_init(struct drm_device *dev) switch (INTEL_INFO(dev)->gen) { default: - MISSING_CASE(INTEL_INFO(dev)->gen); - return; case 9: ASSIGN_WRITE_MMIO_VFUNCS(gen9); ASSIGN_READ_MMIO_VFUNCS(gen9); @@ -1427,21 +1429,21 @@ static int ironlake_do_reset(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; int ret; - I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, + I915_WRITE(ILK_GDSR, ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE); - ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & + ret = wait_for((I915_READ(ILK_GDSR) & ILK_GRDOM_RESET_ENABLE) == 0, 500); if (ret) return ret; - I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, + I915_WRITE(ILK_GDSR, ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE); - ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & + ret = wait_for((I915_READ(ILK_GDSR) & ILK_GRDOM_RESET_ENABLE) == 0, 500); if (ret) return ret; - I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, 0); + I915_WRITE(ILK_GDSR, 0); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 886079d..614b32e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -472,9 +472,13 @@ nouveau_display_create(struct drm_device *dev) if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) { dev->mode_config.max_width = 4096; dev->mode_config.max_height = 4096; - } else { + } else + if (drm->device.info.family < NV_DEVICE_INFO_V0_FERMI) { dev->mode_config.max_width = 8192; dev->mode_config.max_height = 8192; + } else { + dev->mode_config.max_width = 16384; + dev->mode_config.max_height = 16384; } dev->mode_config.preferred_depth = 24; diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 2791701..59f27e7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -178,8 +178,30 @@ nouveau_fbcon_sync(struct fb_info *info) return 0; } +static int +nouveau_fbcon_open(struct fb_info *info, int user) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->dev); + int ret = pm_runtime_get_sync(drm->dev->dev); + if (ret < 0 && ret != -EACCES) + return ret; + return 0; +} + +static int +nouveau_fbcon_release(struct fb_info *info, int user) +{ + struct nouveau_fbdev *fbcon = info->par; + struct nouveau_drm *drm = nouveau_drm(fbcon->dev); + pm_runtime_put(drm->dev->dev); + return 0; +} + static struct fb_ops nouveau_fbcon_ops = { .owner = THIS_MODULE, + .fb_open = nouveau_fbcon_open, + .fb_release = nouveau_fbcon_release, .fb_check_var = drm_fb_helper_check_var, .fb_set_par = drm_fb_helper_set_par, .fb_fillrect = nouveau_fbcon_fillrect, @@ -195,6 +217,8 @@ static struct fb_ops nouveau_fbcon_ops = { static struct fb_ops nouveau_fbcon_sw_ops = { .owner = THIS_MODULE, + .fb_open = nouveau_fbcon_open, + .fb_release = nouveau_fbcon_release, .fb_check_var = drm_fb_helper_check_var, .fb_set_par = drm_fb_helper_set_par, .fb_fillrect = drm_fb_helper_cfb_fillrect, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c index 65af314..a7d69ce 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c @@ -267,6 +267,12 @@ init_i2c(struct nvbios_init *init, int index) index = NVKM_I2C_BUS_PRI; if (init->outp && init->outp->i2c_upper_default) index = NVKM_I2C_BUS_SEC; + } else + if (index == 0x80) { + index = NVKM_I2C_BUS_PRI; + } else + if (index == 0x81) { + index = NVKM_I2C_BUS_SEC; } bus = nvkm_i2c_bus_find(i2c, index); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h index e0ec2a6..212800e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h @@ -8,7 +8,10 @@ struct nvbios_source { void *(*init)(struct nvkm_bios *, const char *); void (*fini)(void *); u32 (*read)(void *, u32 offset, u32 length, struct nvkm_bios *); + u32 (*size)(void *); bool rw; + bool ignore_checksum; + bool no_pcir; }; int nvbios_extend(struct nvkm_bios *, u32 length); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c index 792f017..b2557e8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c @@ -45,7 +45,7 @@ shadow_fetch(struct nvkm_bios *bios, struct shadow *mthd, u32 upto) u32 read = mthd->func->read(data, start, limit - start, bios); bios->size = start + read; } - return bios->size >= limit; + return bios->size >= upto; } static int @@ -55,14 +55,22 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd) struct nvbios_image image; int score = 1; - if (!shadow_fetch(bios, mthd, offset + 0x1000)) { - nvkm_debug(subdev, "%08x: header fetch failed\n", offset); - return 0; - } + if (mthd->func->no_pcir) { + image.base = 0; + image.type = 0; + image.size = mthd->func->size(mthd->data); + image.last = 1; + } else { + if (!shadow_fetch(bios, mthd, offset + 0x1000)) { + nvkm_debug(subdev, "%08x: header fetch failed\n", + offset); + return 0; + } - if (!nvbios_image(bios, idx, &image)) { - nvkm_debug(subdev, "image %d invalid\n", idx); - return 0; + if (!nvbios_image(bios, idx, &image)) { + nvkm_debug(subdev, "image %d invalid\n", idx); + return 0; + } } nvkm_debug(subdev, "%08x: type %02x, %d bytes\n", image.base, image.type, image.size); @@ -74,7 +82,8 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd) switch (image.type) { case 0x00: - if (nvbios_checksum(&bios->data[image.base], image.size)) { + if (!mthd->func->ignore_checksum && + nvbios_checksum(&bios->data[image.base], image.size)) { nvkm_debug(subdev, "%08x: checksum failed\n", image.base); if (mthd->func->rw) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c index bd60d7d..4bf486b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c @@ -21,6 +21,7 @@ * */ #include "priv.h" + #include <core/pci.h> #if defined(__powerpc__) @@ -33,17 +34,26 @@ static u32 of_read(void *data, u32 offset, u32 length, struct nvkm_bios *bios) { struct priv *priv = data; - if (offset + length <= priv->size) { + if (offset < priv->size) { + length = min_t(u32, length, priv->size - offset); memcpy_fromio(bios->data + offset, priv->data + offset, length); return length; } return 0; } +static u32 +of_size(void *data) +{ + struct priv *priv = data; + return priv->size; +} + static void * of_init(struct nvkm_bios *bios, const char *name) { - struct pci_dev *pdev = bios->subdev.device->func->pci(bios->subdev.device)->pdev; + struct nvkm_device *device = bios->subdev.device; + struct pci_dev *pdev = device->func->pci(device)->pdev; struct device_node *dn; struct priv *priv; if (!(dn = pci_device_to_OF_node(pdev))) @@ -62,7 +72,10 @@ nvbios_of = { .init = of_init, .fini = (void(*)(void *))kfree, .read = of_read, + .size = of_size, .rw = false, + .ignore_checksum = true, + .no_pcir = true, }; #else const struct nvbios_source diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c index 814cb51..385a90f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/agp.c @@ -35,6 +35,8 @@ static const struct nvkm_device_agp_quirk nvkm_device_agp_quirks[] = { /* VIA Apollo PRO133x / GeForce FX 5600 Ultra - fdo#20341 */ { PCI_VENDOR_ID_VIA, 0x0691, PCI_VENDOR_ID_NVIDIA, 0x0311, 2 }, + /* SiS 761 does not support AGP cards, use PCI mode */ + { PCI_VENDOR_ID_SI, 0x0761, PCI_ANY_ID, PCI_ANY_ID, 0 }, {}, }; @@ -137,8 +139,10 @@ nvkm_agp_ctor(struct nvkm_pci *pci) while (quirk->hostbridge_vendor) { if (info.device->vendor == quirk->hostbridge_vendor && info.device->device == quirk->hostbridge_device && - pci->pdev->vendor == quirk->chip_vendor && - pci->pdev->device == quirk->chip_device) { + (quirk->chip_vendor == (u16)PCI_ANY_ID || + pci->pdev->vendor == quirk->chip_vendor) && + (quirk->chip_device == (u16)PCI_ANY_ID || + pci->pdev->device == quirk->chip_device)) { nvkm_info(subdev, "forcing default agp mode to %dX, " "use NvAGP=<mode> to override\n", quirk->mode); diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index dd845f8..183aea1 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -244,6 +244,10 @@ static int qxl_crtc_page_flip(struct drm_crtc *crtc, ret = qxl_bo_reserve(bo, false); if (ret) return ret; + ret = qxl_bo_pin(bo, bo->type, NULL); + qxl_bo_unreserve(bo); + if (ret) + return ret; qxl_draw_dirty_fb(qdev, qfb_src, bo, 0, 0, &norect, one_clip_rect, inc); @@ -257,7 +261,11 @@ static int qxl_crtc_page_flip(struct drm_crtc *crtc, } drm_vblank_put(dev, qcrtc->index); - qxl_bo_unreserve(bo); + ret = qxl_bo_reserve(bo, false); + if (!ret) { + qxl_bo_unpin(bo); + qxl_bo_unreserve(bo); + } return 0; } @@ -618,7 +626,7 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc, adjusted_mode->hdisplay, adjusted_mode->vdisplay); - if (qcrtc->index == 0) + if (bo->is_primary == false) recreate_primary = true; if (bo->surf.stride * bo->surf.height > qdev->vram_size) { diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c index 41c422f..c4a5526 100644 --- a/drivers/gpu/drm/qxl/qxl_fb.c +++ b/drivers/gpu/drm/qxl/qxl_fb.c @@ -144,14 +144,17 @@ static void qxl_dirty_update(struct qxl_fbdev *qfbdev, spin_lock_irqsave(&qfbdev->dirty.lock, flags); - if (qfbdev->dirty.y1 < y) - y = qfbdev->dirty.y1; - if (qfbdev->dirty.y2 > y2) - y2 = qfbdev->dirty.y2; - if (qfbdev->dirty.x1 < x) - x = qfbdev->dirty.x1; - if (qfbdev->dirty.x2 > x2) - x2 = qfbdev->dirty.x2; + if ((qfbdev->dirty.y2 - qfbdev->dirty.y1) && + (qfbdev->dirty.x2 - qfbdev->dirty.x1)) { + if (qfbdev->dirty.y1 < y) + y = qfbdev->dirty.y1; + if (qfbdev->dirty.y2 > y2) + y2 = qfbdev->dirty.y2; + if (qfbdev->dirty.x1 < x) + x = qfbdev->dirty.x1; + if (qfbdev->dirty.x2 > x2) + x2 = qfbdev->dirty.x2; + } qfbdev->dirty.x1 = x; qfbdev->dirty.x2 = x2; diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index b66ec33..4efa8e2 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -307,7 +307,7 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev, idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release); if (idr_ret < 0) return idr_ret; - bo = qxl_bo_ref(to_qxl_bo(entry->tv.bo)); + bo = to_qxl_bo(entry->tv.bo); (*release)->release_offset = create_rel->release_offset + 64; @@ -316,8 +316,6 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev, info = qxl_release_map(qdev, *release); info->id = idr_ret; qxl_release_unmap(qdev, *release, info); - - qxl_bo_unref(&bo); return 0; } diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index c387259..65adb9c 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -1624,8 +1624,9 @@ radeon_atom_encoder_dpms_avivo(struct drm_encoder *encoder, int mode) } else atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { - args.ucAction = ATOM_LCD_BLON; - atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; + + atombios_set_backlight_level(radeon_encoder, dig->backlight_level); } break; case DRM_MODE_DPMS_STANDBY: @@ -1706,8 +1707,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0); } if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) - atombios_dig_transmitter_setup(encoder, - ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0); + atombios_set_backlight_level(radeon_encoder, dig->backlight_level); if (ext_encoder) atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE); break; diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index c9e0fbb..46f87d4 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -34,6 +34,8 @@ #define MAX(a,b) (((a)>(b))?(a):(b)) #define MIN(a,b) (((a)<(b))?(a):(b)) +#define REG_SAFE_BM_SIZE ARRAY_SIZE(evergreen_reg_safe_bm) + int r600_dma_cs_next_reloc(struct radeon_cs_parser *p, struct radeon_bo_list **cs_reloc); struct evergreen_cs_track { @@ -84,6 +86,7 @@ struct evergreen_cs_track { u32 htile_surface; struct radeon_bo *htile_bo; unsigned long indirect_draw_buffer_size; + const unsigned *reg_safe_bm; }; static u32 evergreen_cs_get_aray_mode(u32 tiling_flags) @@ -444,7 +447,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i * command stream. */ if (!surf.mode) { - volatile u32 *ib = p->ib.ptr; + uint32_t *ib = p->ib.ptr; unsigned long tmp, nby, bsize, size, min = 0; /* find the height the ddx wants */ @@ -1083,41 +1086,18 @@ static int evergreen_cs_parse_packet0(struct radeon_cs_parser *p, } /** - * evergreen_cs_check_reg() - check if register is authorized or not + * evergreen_cs_handle_reg() - process registers that need special handling. * @parser: parser structure holding parsing context * @reg: register we are testing * @idx: index into the cs buffer - * - * This function will test against evergreen_reg_safe_bm and return 0 - * if register is safe. If register is not flag as safe this function - * will test it against a list of register needind special handling. */ -static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) +static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) { struct evergreen_cs_track *track = (struct evergreen_cs_track *)p->track; struct radeon_bo_list *reloc; - u32 last_reg; - u32 m, i, tmp, *ib; + u32 tmp, *ib; int r; - if (p->rdev->family >= CHIP_CAYMAN) - last_reg = ARRAY_SIZE(cayman_reg_safe_bm); - else - last_reg = ARRAY_SIZE(evergreen_reg_safe_bm); - - i = (reg >> 7); - if (i >= last_reg) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); - return -EINVAL; - } - m = 1 << ((reg >> 2) & 31); - if (p->rdev->family >= CHIP_CAYMAN) { - if (!(cayman_reg_safe_bm[i] & m)) - return 0; - } else { - if (!(evergreen_reg_safe_bm[i] & m)) - return 0; - } ib = p->ib.ptr; switch (reg) { /* force following reg to 0 in an attempt to disable out buffer @@ -1764,29 +1744,27 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) return 0; } -static bool evergreen_is_safe_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) +/** + * evergreen_is_safe_reg() - check if register is authorized or not + * @parser: parser structure holding parsing context + * @reg: register we are testing + * + * This function will test against reg_safe_bm and return true + * if register is safe or false otherwise. + */ +static inline bool evergreen_is_safe_reg(struct radeon_cs_parser *p, u32 reg) { - u32 last_reg, m, i; - - if (p->rdev->family >= CHIP_CAYMAN) - last_reg = ARRAY_SIZE(cayman_reg_safe_bm); - else - last_reg = ARRAY_SIZE(evergreen_reg_safe_bm); + struct evergreen_cs_track *track = p->track; + u32 m, i; i = (reg >> 7); - if (i >= last_reg) { - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); + if (unlikely(i >= REG_SAFE_BM_SIZE)) { return false; } m = 1 << ((reg >> 2) & 31); - if (p->rdev->family >= CHIP_CAYMAN) { - if (!(cayman_reg_safe_bm[i] & m)) - return true; - } else { - if (!(evergreen_reg_safe_bm[i] & m)) - return true; - } - dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx); + if (!(track->reg_safe_bm[i] & m)) + return true; + return false; } @@ -1795,7 +1773,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, { struct radeon_bo_list *reloc; struct evergreen_cs_track *track; - volatile u32 *ib; + uint32_t *ib; unsigned idx; unsigned i; unsigned start_reg, end_reg, reg; @@ -2321,9 +2299,10 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n"); return -EINVAL; } - for (i = 0; i < pkt->count; i++) { - reg = start_reg + (4 * i); - r = evergreen_cs_check_reg(p, reg, idx+1+i); + for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) { + if (evergreen_is_safe_reg(p, reg)) + continue; + r = evergreen_cs_handle_reg(p, reg, idx); if (r) return r; } @@ -2337,9 +2316,10 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n"); return -EINVAL; } - for (i = 0; i < pkt->count; i++) { - reg = start_reg + (4 * i); - r = evergreen_cs_check_reg(p, reg, idx+1+i); + for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) { + if (evergreen_is_safe_reg(p, reg)) + continue; + r = evergreen_cs_handle_reg(p, reg, idx); if (r) return r; } @@ -2594,8 +2574,11 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, } else { /* SRC is a reg. */ reg = radeon_get_ib_value(p, idx+1) << 2; - if (!evergreen_is_safe_reg(p, reg, idx+1)) + if (!evergreen_is_safe_reg(p, reg)) { + dev_warn(p->dev, "forbidden register 0x%08x at %d\n", + reg, idx + 1); return -EINVAL; + } } if (idx_value & 0x2) { u64 offset; @@ -2618,8 +2601,11 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p, } else { /* DST is a reg. */ reg = radeon_get_ib_value(p, idx+3) << 2; - if (!evergreen_is_safe_reg(p, reg, idx+3)) + if (!evergreen_is_safe_reg(p, reg)) { + dev_warn(p->dev, "forbidden register 0x%08x at %d\n", + reg, idx + 3); return -EINVAL; + } } break; case PACKET3_NOP: @@ -2644,11 +2630,15 @@ int evergreen_cs_parse(struct radeon_cs_parser *p) if (track == NULL) return -ENOMEM; evergreen_cs_track_init(track); - if (p->rdev->family >= CHIP_CAYMAN) + if (p->rdev->family >= CHIP_CAYMAN) { tmp = p->rdev->config.cayman.tile_config; - else + track->reg_safe_bm = cayman_reg_safe_bm; + } else { tmp = p->rdev->config.evergreen.tile_config; - + track->reg_safe_bm = evergreen_reg_safe_bm; + } + BUILD_BUG_ON(ARRAY_SIZE(cayman_reg_safe_bm) != REG_SAFE_BM_SIZE); + BUILD_BUG_ON(ARRAY_SIZE(evergreen_reg_safe_bm) != REG_SAFE_BM_SIZE); switch (tmp & 0xf) { case 0: track->npipes = 1; @@ -2757,7 +2747,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) struct radeon_cs_chunk *ib_chunk = p->chunk_ib; struct radeon_bo_list *src_reloc, *dst_reloc, *dst2_reloc; u32 header, cmd, count, sub_cmd; - volatile u32 *ib = p->ib.ptr; + uint32_t *ib = p->ib.ptr; u32 idx; u64 src_offset, dst_offset, dst2_offset; int r; diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c index 77e9d07..59acd0e 100644 --- a/drivers/gpu/drm/radeon/radeon_acpi.c +++ b/drivers/gpu/drm/radeon/radeon_acpi.c @@ -25,7 +25,6 @@ #include <linux/acpi.h> #include <linux/slab.h> #include <linux/power_supply.h> -#include <linux/vga_switcheroo.h> #include <acpi/video.h> #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index f2421bc..1d4d452 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -31,7 +31,6 @@ #include <drm/drm_crtc_helper.h> #include <drm/radeon_drm.h> #include <linux/vgaarb.h> -#include <linux/vga_switcheroo.h> #include "radeon_reg.h" #include "radeon.h" #include "radeon_asic.h" diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 8bc7d0b..a771b9f 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -535,7 +535,7 @@ static bool radeon_atpx_detect(void) if (has_atpx && vga_count == 2) { acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer); - printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n", + printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); radeon_atpx_priv.atpx_detected = true; return true; diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index d27e4cc..21b6732 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -30,7 +30,6 @@ #include "radeon.h" #include "atom.h" -#include <linux/vga_switcheroo.h> #include <linux/slab.h> #include <linux/acpi.h> /* diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index f3f562f..c566993 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1197,7 +1197,7 @@ static void radeon_check_arguments(struct radeon_device *rdev) * radeon_switcheroo_set_state - set switcheroo state * * @pdev: pci dev pointer - * @state: vga switcheroo state + * @state: vga_switcheroo state * * Callback for the switcheroo driver. Suspends or resumes the * the asics before or after it is powered up using ACPI methods. diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index a58635c..a8d9927 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1634,18 +1634,8 @@ int radeon_modeset_init(struct radeon_device *rdev) radeon_fbdev_init(rdev); drm_kms_helper_poll_init(rdev->ddev); - if (rdev->pm.dpm_enabled) { - /* do dpm late init */ - ret = radeon_pm_late_init(rdev); - if (ret) { - rdev->pm.dpm_enabled = false; - DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); - } - /* set the dpm state for PX since there won't be - * a modeset to call this. - */ - radeon_pm_compute_clocks(rdev); - } + /* do pm late init */ + ret = radeon_pm_late_init(rdev); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c index 5e09c06..6cddae4 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_mst.c +++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c @@ -265,7 +265,6 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol { struct radeon_connector *master = container_of(mgr, struct radeon_connector, mst_mgr); struct drm_device *dev = master->base.dev; - struct radeon_device *rdev = dev->dev_private; struct radeon_connector *radeon_connector; struct drm_connector *connector; @@ -286,12 +285,19 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0); drm_mode_connector_set_path_property(connector, pathprop); + return connector; +} + +static void radeon_dp_register_mst_connector(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + struct radeon_device *rdev = dev->dev_private; + drm_modeset_lock_all(dev); radeon_fb_add_connector(rdev, connector); drm_modeset_unlock_all(dev); drm_connector_register(connector); - return connector; } static void radeon_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, @@ -324,6 +330,7 @@ static void radeon_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) struct drm_dp_mst_topology_cbs mst_cbs = { .add_connector = radeon_dp_add_mst_connector, + .register_connector = radeon_dp_register_mst_connector, .destroy_connector = radeon_dp_destroy_mst_connector, .hotplug = radeon_dp_mst_hotplug, }; diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c index 7214858..26da2f4 100644 --- a/drivers/gpu/drm/radeon/radeon_fb.c +++ b/drivers/gpu/drm/radeon/radeon_fb.c @@ -48,40 +48,10 @@ struct radeon_fbdev { struct radeon_device *rdev; }; -/** - * radeon_fb_helper_set_par - Hide cursor on CRTCs used by fbdev. - * - * @info: fbdev info - * - * This function hides the cursor on all CRTCs used by fbdev. - */ -static int radeon_fb_helper_set_par(struct fb_info *info) -{ - int ret; - - ret = drm_fb_helper_set_par(info); - - /* XXX: with universal plane support fbdev will automatically disable - * all non-primary planes (including the cursor) - */ - if (ret == 0) { - struct drm_fb_helper *fb_helper = info->par; - int i; - - for (i = 0; i < fb_helper->crtc_count; i++) { - struct drm_crtc *crtc = fb_helper->crtc_info[i].mode_set.crtc; - - radeon_crtc_cursor_set2(crtc, NULL, 0, 0, 0, 0, 0); - } - } - - return ret; -} - static struct fb_ops radeonfb_ops = { .owner = THIS_MODULE, .fb_check_var = drm_fb_helper_check_var, - .fb_set_par = radeon_fb_helper_set_par, + .fb_set_par = drm_fb_helper_set_par, .fb_fillrect = drm_fb_helper_cfb_fillrect, .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, @@ -427,3 +397,19 @@ void radeon_fb_remove_connector(struct radeon_device *rdev, struct drm_connector { drm_fb_helper_remove_one_connector(&rdev->mode_info.rfbdev->helper, connector); } + +void radeon_fbdev_restore_mode(struct radeon_device *rdev) +{ + struct radeon_fbdev *rfbdev = rdev->mode_info.rfbdev; + struct drm_fb_helper *fb_helper; + int ret; + + if (!rfbdev) + return; + + fb_helper = &rfbdev->helper; + + ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); + if (ret) + DRM_DEBUG("failed to restore crtc mode\n"); +} diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 4e2780f..5f687c9 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -598,14 +598,17 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file * Outdated mess for old drm with Xorg being in charge (void function now). */ /** - * radeon_driver_firstopen_kms - drm callback for last close + * radeon_driver_lastclose_kms - drm callback for last close * * @dev: drm dev pointer * - * Switch vga switcheroo state after last close (all asics). + * Switch vga_switcheroo state after last close (all asics). */ void radeon_driver_lastclose_kms(struct drm_device *dev) { + struct radeon_device *rdev = dev->dev_private; + + radeon_fbdev_restore_mode(rdev); vga_switcheroo_process_delayed_switch(); } diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index de18f06..830e171 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -980,6 +980,7 @@ int radeon_fbdev_init(struct radeon_device *rdev); void radeon_fbdev_fini(struct radeon_device *rdev); void radeon_fbdev_set_suspend(struct radeon_device *rdev, int state); bool radeon_fbdev_robj_is_fb(struct radeon_device *rdev, struct radeon_bo *robj); +void radeon_fbdev_restore_mode(struct radeon_device *rdev); void radeon_fb_output_poll_changed(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 10f4c12..bcdc508 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1326,14 +1326,6 @@ static int radeon_pm_init_old(struct radeon_device *rdev) INIT_DELAYED_WORK(&rdev->pm.dynpm_idle_work, radeon_dynpm_idle_work_handler); if (rdev->pm.num_power_states > 1) { - /* where's the best place to put these? */ - ret = device_create_file(rdev->dev, &dev_attr_power_profile); - if (ret) - DRM_ERROR("failed to create device file for power profile\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_method); - if (ret) - DRM_ERROR("failed to create device file for power method\n"); - if (radeon_debugfs_pm_init(rdev)) { DRM_ERROR("Failed to register debugfs file for PM!\n"); } @@ -1391,20 +1383,6 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev) goto dpm_failed; rdev->pm.dpm_enabled = true; - ret = device_create_file(rdev->dev, &dev_attr_power_dpm_state); - if (ret) - DRM_ERROR("failed to create device file for dpm state\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_dpm_force_performance_level); - if (ret) - DRM_ERROR("failed to create device file for dpm state\n"); - /* XXX: these are noops for dpm but are here for backwards compat */ - ret = device_create_file(rdev->dev, &dev_attr_power_profile); - if (ret) - DRM_ERROR("failed to create device file for power profile\n"); - ret = device_create_file(rdev->dev, &dev_attr_power_method); - if (ret) - DRM_ERROR("failed to create device file for power method\n"); - if (radeon_debugfs_pm_init(rdev)) { DRM_ERROR("Failed to register debugfs file for dpm!\n"); } @@ -1545,9 +1523,44 @@ int radeon_pm_late_init(struct radeon_device *rdev) int ret = 0; if (rdev->pm.pm_method == PM_METHOD_DPM) { - mutex_lock(&rdev->pm.mutex); - ret = radeon_dpm_late_enable(rdev); - mutex_unlock(&rdev->pm.mutex); + if (rdev->pm.dpm_enabled) { + ret = device_create_file(rdev->dev, &dev_attr_power_dpm_state); + if (ret) + DRM_ERROR("failed to create device file for dpm state\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_dpm_force_performance_level); + if (ret) + DRM_ERROR("failed to create device file for dpm state\n"); + /* XXX: these are noops for dpm but are here for backwards compat */ + ret = device_create_file(rdev->dev, &dev_attr_power_profile); + if (ret) + DRM_ERROR("failed to create device file for power profile\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_method); + if (ret) + DRM_ERROR("failed to create device file for power method\n"); + + mutex_lock(&rdev->pm.mutex); + ret = radeon_dpm_late_enable(rdev); + mutex_unlock(&rdev->pm.mutex); + if (ret) { + rdev->pm.dpm_enabled = false; + DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n"); + } else { + /* set the dpm state for PX since there won't be + * a modeset to call this. + */ + radeon_pm_compute_clocks(rdev); + } + } + } else { + if (rdev->pm.num_power_states > 1) { + /* where's the best place to put these? */ + ret = device_create_file(rdev->dev, &dev_attr_power_profile); + if (ret) + DRM_ERROR("failed to create device file for power profile\n"); + ret = device_create_file(rdev->dev, &dev_attr_power_method); + if (ret) + DRM_ERROR("failed to create device file for power method\n"); + } } return ret; } diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index e9115d3..e72bf46 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2928,6 +2928,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, { 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig index 11485a4..d4e0a39 100644 --- a/drivers/gpu/drm/rcar-du/Kconfig +++ b/drivers/gpu/drm/rcar-du/Kconfig @@ -1,6 +1,6 @@ config DRM_RCAR_DU tristate "DRM Support for R-Car Display Unit" - depends on DRM && ARM && HAVE_DMA_ATTRS + depends on DRM && ARM && HAVE_DMA_ATTRS && OF depends on ARCH_SHMOBILE || COMPILE_TEST select DRM_KMS_HELPER select DRM_KMS_CMA_HELPER diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index feddda0..bebcc97 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -93,7 +93,7 @@ static const struct rcar_du_device_info rcar_du_r8a7791_info = { * (currently unsupported) TCON output. */ [RCAR_DU_OUTPUT_DPAD0] = { - .possible_crtcs = BIT(1), + .possible_crtcs = BIT(1) | BIT(0), .encoder_type = DRM_MODE_ENCODER_NONE, .port = 0, }, @@ -106,15 +106,6 @@ static const struct rcar_du_device_info rcar_du_r8a7791_info = { .num_lvds = 1, }; -static const struct platform_device_id rcar_du_id_table[] = { - { "rcar-du-r8a7779", (kernel_ulong_t)&rcar_du_r8a7779_info }, - { "rcar-du-r8a7790", (kernel_ulong_t)&rcar_du_r8a7790_info }, - { "rcar-du-r8a7791", (kernel_ulong_t)&rcar_du_r8a7791_info }, - { } -}; - -MODULE_DEVICE_TABLE(platform, rcar_du_id_table); - static const struct of_device_id rcar_du_of_table[] = { { .compatible = "renesas,du-r8a7779", .data = &rcar_du_r8a7779_info }, { .compatible = "renesas,du-r8a7790", .data = &rcar_du_r8a7790_info }, @@ -167,8 +158,7 @@ static int rcar_du_load(struct drm_device *dev, unsigned long flags) init_waitqueue_head(&rcdu->commit.wait); rcdu->dev = &pdev->dev; - rcdu->info = np ? of_match_device(rcar_du_of_table, rcdu->dev)->data - : (void *)platform_get_device_id(pdev)->driver_data; + rcdu->info = of_match_device(rcar_du_of_table, rcdu->dev)->data; rcdu->ddev = dev; dev->dev_private = rcdu; @@ -340,7 +330,6 @@ static struct platform_driver rcar_du_platform_driver = { .pm = &rcar_du_pm_ops, .of_match_table = rcar_du_of_table, }, - .id_table = rcar_du_id_table, }; module_platform_driver(rcar_du_platform_driver); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c index c669864..ffa5837 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c @@ -273,29 +273,6 @@ static const struct drm_plane_helper_funcs rcar_du_plane_helper_funcs = { .atomic_update = rcar_du_plane_atomic_update, }; -static void rcar_du_plane_reset(struct drm_plane *plane) -{ - struct rcar_du_plane_state *state; - - if (plane->state && plane->state->fb) - drm_framebuffer_unreference(plane->state->fb); - - kfree(plane->state); - plane->state = NULL; - - state = kzalloc(sizeof(*state), GFP_KERNEL); - if (state == NULL) - return; - - state->hwindex = -1; - state->alpha = 255; - state->colorkey = RCAR_DU_COLORKEY_NONE; - state->zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1; - - plane->state = &state->state; - plane->state->plane = plane; -} - static struct drm_plane_state * rcar_du_plane_atomic_duplicate_state(struct drm_plane *plane) { @@ -322,6 +299,28 @@ static void rcar_du_plane_atomic_destroy_state(struct drm_plane *plane, kfree(to_rcar_plane_state(state)); } +static void rcar_du_plane_reset(struct drm_plane *plane) +{ + struct rcar_du_plane_state *state; + + if (plane->state) { + rcar_du_plane_atomic_destroy_state(plane, plane->state); + plane->state = NULL; + } + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (state == NULL) + return; + + state->hwindex = -1; + state->alpha = 255; + state->colorkey = RCAR_DU_COLORKEY_NONE; + state->zpos = plane->type == DRM_PLANE_TYPE_PRIMARY ? 0 : 1; + + plane->state = &state->state; + plane->state->plane = plane; +} + static int rcar_du_plane_atomic_set_property(struct drm_plane *plane, struct drm_plane_state *state, struct drm_property *property, diff --git a/drivers/gpu/drm/sis/sis_drv.h b/drivers/gpu/drm/sis/sis_drv.h index 16f972b..328f8a7 100644 --- a/drivers/gpu/drm/sis/sis_drv.h +++ b/drivers/gpu/drm/sis/sis_drv.h @@ -67,6 +67,10 @@ typedef struct drm_sis_private { struct idr object_idr; } drm_sis_private_t; +struct sis_file_private { + struct list_head obj_list; +}; + extern int sis_idle(struct drm_device *dev); extern void sis_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv); diff --git a/drivers/gpu/drm/via/via_drv.h b/drivers/gpu/drm/via/via_drv.h index 644093f..286a785 100644 --- a/drivers/gpu/drm/via/via_drv.h +++ b/drivers/gpu/drm/via/via_drv.h @@ -102,6 +102,10 @@ typedef struct drm_via_private { uint32_t dma_diff; } drm_via_private_t; +struct via_file_private { + struct list_head obj_list; +}; + enum via_family { VIA_OTHER = 0, /* Baseline */ VIA_PRO_GROUP_A, /* Another video engine and DMA commands */ diff --git a/drivers/gpu/drm/virtio/Makefile b/drivers/gpu/drm/virtio/Makefile index 2ee1602..3fb8eac 100644 --- a/drivers/gpu/drm/virtio/Makefile +++ b/drivers/gpu/drm/virtio/Makefile @@ -6,6 +6,7 @@ ccflags-y := -Iinclude/drm virtio-gpu-y := virtgpu_drv.o virtgpu_kms.o virtgpu_drm_bus.o virtgpu_gem.o \ virtgpu_fb.o virtgpu_display.o virtgpu_vq.o virtgpu_ttm.o \ - virtgpu_fence.o virtgpu_object.o virtgpu_debugfs.o virtgpu_plane.o + virtgpu_fence.o virtgpu_object.o virtgpu_debugfs.o virtgpu_plane.o \ + virtgpu_ioctl.o virtgpu_prime.o obj-$(CONFIG_DRM_VIRTIO_GPU) += virtio-gpu.o diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 4e160ef..f545913 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -90,6 +90,14 @@ static int virtio_gpu_crtc_cursor_set(struct drm_crtc *crtc, cpu_to_le32(64), cpu_to_le32(64), 0, 0, &fence); + ret = virtio_gpu_object_reserve(qobj, false); + if (!ret) { + reservation_object_add_excl_fence(qobj->tbo.resv, + &fence->f); + fence_put(&fence->f); + virtio_gpu_object_unreserve(qobj); + virtio_gpu_object_wait(qobj, false); + } output->cursor.hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_UPDATE_CURSOR); output->cursor.resource_id = cpu_to_le32(qobj->hw_res_handle); @@ -117,6 +125,51 @@ static int virtio_gpu_crtc_cursor_move(struct drm_crtc *crtc, return 0; } +static int virtio_gpu_page_flip(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_pending_vblank_event *event, + uint32_t flags) +{ + struct virtio_gpu_device *vgdev = crtc->dev->dev_private; + struct virtio_gpu_output *output = + container_of(crtc, struct virtio_gpu_output, crtc); + struct drm_plane *plane = crtc->primary; + struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_object *bo; + unsigned long irqflags; + uint32_t handle; + + plane->fb = fb; + vgfb = to_virtio_gpu_framebuffer(plane->fb); + bo = gem_to_virtio_gpu_obj(vgfb->obj); + handle = bo->hw_res_handle; + + DRM_DEBUG("handle 0x%x%s, crtc %dx%d\n", handle, + bo->dumb ? ", dumb" : "", + crtc->mode.hdisplay, crtc->mode.vdisplay); + if (bo->dumb) { + virtio_gpu_cmd_transfer_to_host_2d + (vgdev, handle, 0, + cpu_to_le32(crtc->mode.hdisplay), + cpu_to_le32(crtc->mode.vdisplay), + 0, 0, NULL); + } + virtio_gpu_cmd_set_scanout(vgdev, output->index, handle, + crtc->mode.hdisplay, + crtc->mode.vdisplay, 0, 0); + virtio_gpu_cmd_resource_flush(vgdev, handle, 0, 0, + crtc->mode.hdisplay, + crtc->mode.vdisplay); + + if (event) { + spin_lock_irqsave(&crtc->dev->event_lock, irqflags); + drm_send_vblank_event(crtc->dev, -1, event); + spin_unlock_irqrestore(&crtc->dev->event_lock, irqflags); + } + + return 0; +} + static const struct drm_crtc_funcs virtio_gpu_crtc_funcs = { .cursor_set2 = virtio_gpu_crtc_cursor_set, .cursor_move = virtio_gpu_crtc_cursor_move, @@ -124,9 +177,7 @@ static const struct drm_crtc_funcs virtio_gpu_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .destroy = drm_crtc_cleanup, -#if 0 /* not (yet) working without vblank support according to docs */ - .page_flip = drm_atomic_helper_page_flip, -#endif + .page_flip = virtio_gpu_page_flip, .reset = drm_atomic_helper_crtc_reset, .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 7d9610a..b40ed60 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -73,6 +73,14 @@ static struct virtio_device_id id_table[] = { }; static unsigned int features[] = { +#ifdef __LITTLE_ENDIAN + /* + * Gallium command stream send by virgl is native endian. + * Because of that we only support little endian guests on + * little endian hosts. + */ + VIRTIO_GPU_F_VIRGL, +#endif }; static struct virtio_driver virtio_gpu_driver = { .feature_table = features, @@ -110,10 +118,12 @@ static const struct file_operations virtio_gpu_driver_fops = { static struct drm_driver driver = { - .driver_features = DRIVER_MODESET | DRIVER_GEM, + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME | DRIVER_RENDER, .set_busid = drm_virtio_set_busid, .load = virtio_gpu_driver_load, .unload = virtio_gpu_driver_unload, + .open = virtio_gpu_driver_open, + .postclose = virtio_gpu_driver_postclose, .dumb_create = virtio_gpu_mode_dumb_create, .dumb_map_offset = virtio_gpu_mode_dumb_mmap, @@ -123,10 +133,26 @@ static struct drm_driver driver = { .debugfs_init = virtio_gpu_debugfs_init, .debugfs_cleanup = virtio_gpu_debugfs_takedown, #endif + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_export = drm_gem_prime_export, + .gem_prime_import = drm_gem_prime_import, + .gem_prime_pin = virtgpu_gem_prime_pin, + .gem_prime_unpin = virtgpu_gem_prime_unpin, + .gem_prime_get_sg_table = virtgpu_gem_prime_get_sg_table, + .gem_prime_import_sg_table = virtgpu_gem_prime_import_sg_table, + .gem_prime_vmap = virtgpu_gem_prime_vmap, + .gem_prime_vunmap = virtgpu_gem_prime_vunmap, + .gem_prime_mmap = virtgpu_gem_prime_mmap, .gem_free_object = virtio_gpu_gem_free_object, + .gem_open_object = virtio_gpu_gem_object_open, + .gem_close_object = virtio_gpu_gem_object_close, .fops = &virtio_gpu_driver_fops, + .ioctls = virtio_gpu_ioctls, + .num_ioctls = DRM_VIRTIO_NUM_IOCTLS, + .name = DRIVER_NAME, .desc = DRIVER_DESC, .date = DRIVER_DATE, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 6d4db2db..79f0abe 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -146,6 +146,21 @@ struct virtio_gpu_queue { struct work_struct dequeue_work; }; +struct virtio_gpu_drv_capset { + uint32_t id; + uint32_t max_version; + uint32_t max_size; +}; + +struct virtio_gpu_drv_cap_cache { + struct list_head head; + void *caps_cache; + uint32_t id; + uint32_t version; + uint32_t size; + atomic_t is_valid; +}; + struct virtio_gpu_device { struct device *dev; struct drm_device *ddev; @@ -179,7 +194,13 @@ struct virtio_gpu_device { struct idr ctx_id_idr; spinlock_t ctx_id_idr_lock; + bool has_virgl_3d; + struct work_struct config_changed_work; + + struct virtio_gpu_drv_capset *capsets; + uint32_t num_capsets; + struct list_head cap_cache; }; struct virtio_gpu_fpriv { @@ -193,6 +214,8 @@ extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; /* virtio_kms.c */ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags); int virtio_gpu_driver_unload(struct drm_device *dev); +int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file); +void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file); /* virtio_gem.c */ void virtio_gpu_gem_free_object(struct drm_gem_object *gem_obj); @@ -203,6 +226,10 @@ int virtio_gpu_gem_create(struct drm_file *file, uint64_t size, struct drm_gem_object **obj_p, uint32_t *handle_p); +int virtio_gpu_gem_object_open(struct drm_gem_object *obj, + struct drm_file *file); +void virtio_gpu_gem_object_close(struct drm_gem_object *obj, + struct drm_file *file); struct virtio_gpu_object *virtio_gpu_alloc_object(struct drm_device *dev, size_t size, bool kernel, bool pinned); @@ -260,10 +287,43 @@ void virtio_gpu_cursor_ping(struct virtio_gpu_device *vgdev, int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev); void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev, uint32_t resource_id); +int virtio_gpu_cmd_get_capset_info(struct virtio_gpu_device *vgdev, int idx); +int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev, + int idx, int version, + struct virtio_gpu_drv_cap_cache **cache_p); +void virtio_gpu_cmd_context_create(struct virtio_gpu_device *vgdev, uint32_t id, + uint32_t nlen, const char *name); +void virtio_gpu_cmd_context_destroy(struct virtio_gpu_device *vgdev, + uint32_t id); +void virtio_gpu_cmd_context_attach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id); +void virtio_gpu_cmd_context_detach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id); +void virtio_gpu_cmd_submit(struct virtio_gpu_device *vgdev, + void *data, uint32_t data_size, + uint32_t ctx_id, struct virtio_gpu_fence **fence); +void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence); +void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence); +void +virtio_gpu_cmd_resource_create_3d(struct virtio_gpu_device *vgdev, + struct virtio_gpu_resource_create_3d *rc_3d, + struct virtio_gpu_fence **fence); void virtio_gpu_ctrl_ack(struct virtqueue *vq); void virtio_gpu_cursor_ack(struct virtqueue *vq); +void virtio_gpu_fence_ack(struct virtqueue *vq); void virtio_gpu_dequeue_ctrl_func(struct work_struct *work); void virtio_gpu_dequeue_cursor_func(struct work_struct *work); +void virtio_gpu_dequeue_fence_func(struct work_struct *work); /* virtio_gpu_display.c */ int virtio_gpu_framebuffer_init(struct drm_device *dev, @@ -299,6 +359,18 @@ int virtio_gpu_object_get_sg_table(struct virtio_gpu_device *qdev, void virtio_gpu_object_free_sg_table(struct virtio_gpu_object *bo); int virtio_gpu_object_wait(struct virtio_gpu_object *bo, bool no_wait); +/* virtgpu_prime.c */ +int virtgpu_gem_prime_pin(struct drm_gem_object *obj); +void virtgpu_gem_prime_unpin(struct drm_gem_object *obj); +struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj); +struct drm_gem_object *virtgpu_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *sgt); +void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj); +void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); +int virtgpu_gem_prime_mmap(struct drm_gem_object *obj, + struct vm_area_struct *vma); + static inline struct virtio_gpu_object* virtio_gpu_object_ref(struct virtio_gpu_object *bo) { diff --git a/drivers/gpu/drm/virtio/virtgpu_fence.c b/drivers/gpu/drm/virtio/virtgpu_fence.c index 1da6326..793ad9f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_fence.c +++ b/drivers/gpu/drm/virtio/virtgpu_fence.c @@ -81,7 +81,7 @@ int virtio_gpu_fence_emit(struct virtio_gpu_device *vgdev, struct virtio_gpu_fence_driver *drv = &vgdev->fence_drv; unsigned long irq_flags; - *fence = kmalloc(sizeof(struct virtio_gpu_fence), GFP_KERNEL); + *fence = kmalloc(sizeof(struct virtio_gpu_fence), GFP_ATOMIC); if ((*fence) == NULL) return -ENOMEM; diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index cfa0d27..1feb7ce 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -138,3 +138,44 @@ int virtio_gpu_mode_dumb_mmap(struct drm_file *file_priv, drm_gem_object_unreference_unlocked(gobj); return 0; } + +int virtio_gpu_gem_object_open(struct drm_gem_object *obj, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = obj->dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct virtio_gpu_object *qobj = gem_to_virtio_gpu_obj(obj); + int r; + + if (!vgdev->has_virgl_3d) + return 0; + + r = virtio_gpu_object_reserve(qobj, false); + if (r) + return r; + + virtio_gpu_cmd_context_attach_resource(vgdev, vfpriv->ctx_id, + qobj->hw_res_handle); + virtio_gpu_object_unreserve(qobj); + return 0; +} + +void virtio_gpu_gem_object_close(struct drm_gem_object *obj, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = obj->dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct virtio_gpu_object *qobj = gem_to_virtio_gpu_obj(obj); + int r; + + if (!vgdev->has_virgl_3d) + return; + + r = virtio_gpu_object_reserve(qobj, false); + if (r) + return; + + virtio_gpu_cmd_context_detach_resource(vgdev, vfpriv->ctx_id, + qobj->hw_res_handle); + virtio_gpu_object_unreserve(qobj); +} diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c new file mode 100644 index 0000000..b4de18e --- /dev/null +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -0,0 +1,573 @@ +/* + * Copyright (C) 2015 Red Hat, Inc. + * All Rights Reserved. + * + * Authors: + * Dave Airlie + * Alon Levy + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include <drm/drmP.h> +#include "virtgpu_drv.h" +#include <drm/virtgpu_drm.h> +#include "ttm/ttm_execbuf_util.h" + +static void convert_to_hw_box(struct virtio_gpu_box *dst, + const struct drm_virtgpu_3d_box *src) +{ + dst->x = cpu_to_le32(src->x); + dst->y = cpu_to_le32(src->y); + dst->z = cpu_to_le32(src->z); + dst->w = cpu_to_le32(src->w); + dst->h = cpu_to_le32(src->h); + dst->d = cpu_to_le32(src->d); +} + +static int virtio_gpu_map_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_map *virtio_gpu_map = data; + + return virtio_gpu_mode_dumb_mmap(file_priv, vgdev->ddev, + virtio_gpu_map->handle, + &virtio_gpu_map->offset); +} + +static int virtio_gpu_object_list_validate(struct ww_acquire_ctx *ticket, + struct list_head *head) +{ + struct ttm_validate_buffer *buf; + struct ttm_buffer_object *bo; + struct virtio_gpu_object *qobj; + int ret; + + ret = ttm_eu_reserve_buffers(ticket, head, true, NULL); + if (ret != 0) + return ret; + + list_for_each_entry(buf, head, head) { + bo = buf->bo; + qobj = container_of(bo, struct virtio_gpu_object, tbo); + ret = ttm_bo_validate(bo, &qobj->placement, false, false); + if (ret) { + ttm_eu_backoff_reservation(ticket, head); + return ret; + } + } + return 0; +} + +static void virtio_gpu_unref_list(struct list_head *head) +{ + struct ttm_validate_buffer *buf; + struct ttm_buffer_object *bo; + struct virtio_gpu_object *qobj; + list_for_each_entry(buf, head, head) { + bo = buf->bo; + qobj = container_of(bo, struct virtio_gpu_object, tbo); + + drm_gem_object_unreference_unlocked(&qobj->gem_base); + } +} + +static int virtio_gpu_execbuffer(struct drm_device *dev, + struct drm_virtgpu_execbuffer *exbuf, + struct drm_file *drm_file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv; + struct drm_gem_object *gobj; + struct virtio_gpu_fence *fence; + struct virtio_gpu_object *qobj; + int ret; + uint32_t *bo_handles = NULL; + void __user *user_bo_handles = NULL; + struct list_head validate_list; + struct ttm_validate_buffer *buflist = NULL; + int i; + struct ww_acquire_ctx ticket; + void *buf; + + if (vgdev->has_virgl_3d == false) + return -ENOSYS; + + INIT_LIST_HEAD(&validate_list); + if (exbuf->num_bo_handles) { + + bo_handles = drm_malloc_ab(exbuf->num_bo_handles, + sizeof(uint32_t)); + buflist = drm_calloc_large(exbuf->num_bo_handles, + sizeof(struct ttm_validate_buffer)); + if (!bo_handles || !buflist) { + drm_free_large(bo_handles); + drm_free_large(buflist); + return -ENOMEM; + } + + user_bo_handles = (void __user *)(uintptr_t)exbuf->bo_handles; + if (copy_from_user(bo_handles, user_bo_handles, + exbuf->num_bo_handles * sizeof(uint32_t))) { + ret = -EFAULT; + drm_free_large(bo_handles); + drm_free_large(buflist); + return ret; + } + + for (i = 0; i < exbuf->num_bo_handles; i++) { + gobj = drm_gem_object_lookup(dev, + drm_file, bo_handles[i]); + if (!gobj) { + drm_free_large(bo_handles); + drm_free_large(buflist); + return -ENOENT; + } + + qobj = gem_to_virtio_gpu_obj(gobj); + buflist[i].bo = &qobj->tbo; + + list_add(&buflist[i].head, &validate_list); + } + drm_free_large(bo_handles); + } + + ret = virtio_gpu_object_list_validate(&ticket, &validate_list); + if (ret) + goto out_free; + + buf = kmalloc(exbuf->size, GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto out_unresv; + } + if (copy_from_user(buf, (void __user *)(uintptr_t)exbuf->command, + exbuf->size)) { + kfree(buf); + ret = -EFAULT; + goto out_unresv; + } + virtio_gpu_cmd_submit(vgdev, buf, exbuf->size, + vfpriv->ctx_id, &fence); + + ttm_eu_fence_buffer_objects(&ticket, &validate_list, &fence->f); + + /* fence the command bo */ + virtio_gpu_unref_list(&validate_list); + drm_free_large(buflist); + fence_put(&fence->f); + return 0; + +out_unresv: + ttm_eu_backoff_reservation(&ticket, &validate_list); +out_free: + virtio_gpu_unref_list(&validate_list); + drm_free_large(buflist); + return ret; +} + +/* + * Usage of execbuffer: + * Relocations need to take into account the full VIRTIO_GPUDrawable size. + * However, the command as passed from user space must *not* contain the initial + * VIRTIO_GPUReleaseInfo struct (first XXX bytes) + */ +static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct drm_virtgpu_execbuffer *execbuffer = data; + return virtio_gpu_execbuffer(dev, execbuffer, file_priv); +} + + +static int virtio_gpu_getparam_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_getparam *param = data; + int value; + + switch (param->param) { + case VIRTGPU_PARAM_3D_FEATURES: + value = vgdev->has_virgl_3d == true ? 1 : 0; + break; + default: + return -EINVAL; + } + if (copy_to_user((void __user *)(unsigned long)param->value, + &value, sizeof(int))) { + return -EFAULT; + } + return 0; +} + +static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_resource_create *rc = data; + int ret; + uint32_t res_id; + struct virtio_gpu_object *qobj; + struct drm_gem_object *obj; + uint32_t handle = 0; + uint32_t size; + struct list_head validate_list; + struct ttm_validate_buffer mainbuf; + struct virtio_gpu_fence *fence = NULL; + struct ww_acquire_ctx ticket; + struct virtio_gpu_resource_create_3d rc_3d; + + if (vgdev->has_virgl_3d == false) { + if (rc->depth > 1) + return -EINVAL; + if (rc->nr_samples > 1) + return -EINVAL; + if (rc->last_level > 1) + return -EINVAL; + if (rc->target != 2) + return -EINVAL; + if (rc->array_size > 1) + return -EINVAL; + } + + INIT_LIST_HEAD(&validate_list); + memset(&mainbuf, 0, sizeof(struct ttm_validate_buffer)); + + virtio_gpu_resource_id_get(vgdev, &res_id); + + size = rc->size; + + /* allocate a single page size object */ + if (size == 0) + size = PAGE_SIZE; + + qobj = virtio_gpu_alloc_object(dev, size, false, false); + if (IS_ERR(qobj)) { + ret = PTR_ERR(qobj); + goto fail_id; + } + obj = &qobj->gem_base; + + if (!vgdev->has_virgl_3d) { + virtio_gpu_cmd_create_resource(vgdev, res_id, rc->format, + rc->width, rc->height); + + ret = virtio_gpu_object_attach(vgdev, qobj, res_id, NULL); + } else { + /* use a gem reference since unref list undoes them */ + drm_gem_object_reference(&qobj->gem_base); + mainbuf.bo = &qobj->tbo; + list_add(&mainbuf.head, &validate_list); + + ret = virtio_gpu_object_list_validate(&ticket, &validate_list); + if (ret) { + DRM_DEBUG("failed to validate\n"); + goto fail_unref; + } + + rc_3d.resource_id = cpu_to_le32(res_id); + rc_3d.target = cpu_to_le32(rc->target); + rc_3d.format = cpu_to_le32(rc->format); + rc_3d.bind = cpu_to_le32(rc->bind); + rc_3d.width = cpu_to_le32(rc->width); + rc_3d.height = cpu_to_le32(rc->height); + rc_3d.depth = cpu_to_le32(rc->depth); + rc_3d.array_size = cpu_to_le32(rc->array_size); + rc_3d.last_level = cpu_to_le32(rc->last_level); + rc_3d.nr_samples = cpu_to_le32(rc->nr_samples); + rc_3d.flags = cpu_to_le32(rc->flags); + + virtio_gpu_cmd_resource_create_3d(vgdev, &rc_3d, NULL); + ret = virtio_gpu_object_attach(vgdev, qobj, res_id, &fence); + if (ret) { + ttm_eu_backoff_reservation(&ticket, &validate_list); + goto fail_unref; + } + ttm_eu_fence_buffer_objects(&ticket, &validate_list, &fence->f); + } + + qobj->hw_res_handle = res_id; + + ret = drm_gem_handle_create(file_priv, obj, &handle); + if (ret) { + + drm_gem_object_release(obj); + if (vgdev->has_virgl_3d) { + virtio_gpu_unref_list(&validate_list); + fence_put(&fence->f); + } + return ret; + } + drm_gem_object_unreference_unlocked(obj); + + rc->res_handle = res_id; /* similiar to a VM address */ + rc->bo_handle = handle; + + if (vgdev->has_virgl_3d) { + virtio_gpu_unref_list(&validate_list); + fence_put(&fence->f); + } + return 0; +fail_unref: + if (vgdev->has_virgl_3d) { + virtio_gpu_unref_list(&validate_list); + fence_put(&fence->f); + } +//fail_obj: +// drm_gem_object_handle_unreference_unlocked(obj); +fail_id: + virtio_gpu_resource_id_put(vgdev, res_id); + return ret; +} + +static int virtio_gpu_resource_info_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct drm_virtgpu_resource_info *ri = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + + gobj = drm_gem_object_lookup(dev, file_priv, ri->bo_handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + ri->size = qobj->gem_base.size; + ri->res_handle = qobj->hw_res_handle; + drm_gem_object_unreference_unlocked(gobj); + return 0; +} + +static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev, + void *data, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct drm_virtgpu_3d_transfer_from_host *args = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + struct virtio_gpu_fence *fence; + int ret; + u32 offset = args->offset; + struct virtio_gpu_box box; + + if (vgdev->has_virgl_3d == false) + return -ENOSYS; + + gobj = drm_gem_object_lookup(dev, file, args->bo_handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + ret = virtio_gpu_object_reserve(qobj, false); + if (ret) + goto out; + + ret = ttm_bo_validate(&qobj->tbo, &qobj->placement, + true, false); + if (unlikely(ret)) + goto out_unres; + + convert_to_hw_box(&box, &args->box); + virtio_gpu_cmd_transfer_from_host_3d + (vgdev, qobj->hw_res_handle, + vfpriv->ctx_id, offset, args->level, + &box, &fence); + reservation_object_add_excl_fence(qobj->tbo.resv, + &fence->f); + + fence_put(&fence->f); +out_unres: + virtio_gpu_object_unreserve(qobj); +out: + drm_gem_object_unreference_unlocked(gobj); + return ret; +} + +static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct drm_virtgpu_3d_transfer_to_host *args = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + struct virtio_gpu_fence *fence; + struct virtio_gpu_box box; + int ret; + u32 offset = args->offset; + + gobj = drm_gem_object_lookup(dev, file, args->bo_handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + ret = virtio_gpu_object_reserve(qobj, false); + if (ret) + goto out; + + ret = ttm_bo_validate(&qobj->tbo, &qobj->placement, + true, false); + if (unlikely(ret)) + goto out_unres; + + convert_to_hw_box(&box, &args->box); + if (!vgdev->has_virgl_3d) { + virtio_gpu_cmd_transfer_to_host_2d + (vgdev, qobj->hw_res_handle, offset, + box.w, box.h, box.x, box.y, NULL); + } else { + virtio_gpu_cmd_transfer_to_host_3d + (vgdev, qobj->hw_res_handle, + vfpriv ? vfpriv->ctx_id : 0, offset, + args->level, &box, &fence); + reservation_object_add_excl_fence(qobj->tbo.resv, + &fence->f); + fence_put(&fence->f); + } + +out_unres: + virtio_gpu_object_unreserve(qobj); +out: + drm_gem_object_unreference_unlocked(gobj); + return ret; +} + +static int virtio_gpu_wait_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct drm_virtgpu_3d_wait *args = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + int ret; + bool nowait = false; + + gobj = drm_gem_object_lookup(dev, file, args->handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + if (args->flags & VIRTGPU_WAIT_NOWAIT) + nowait = true; + ret = virtio_gpu_object_wait(qobj, nowait); + + drm_gem_object_unreference_unlocked(gobj); + return ret; +} + +static int virtio_gpu_get_caps_ioctl(struct drm_device *dev, + void *data, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_get_caps *args = data; + int size; + int i; + int found_valid = -1; + int ret; + struct virtio_gpu_drv_cap_cache *cache_ent; + void *ptr; + if (vgdev->num_capsets == 0) + return -ENOSYS; + + spin_lock(&vgdev->display_info_lock); + for (i = 0; i < vgdev->num_capsets; i++) { + if (vgdev->capsets[i].id == args->cap_set_id) { + if (vgdev->capsets[i].max_version >= args->cap_set_ver) { + found_valid = i; + break; + } + } + } + + if (found_valid == -1) { + spin_unlock(&vgdev->display_info_lock); + return -EINVAL; + } + + size = vgdev->capsets[found_valid].max_size; + if (args->size > size) { + spin_unlock(&vgdev->display_info_lock); + return -EINVAL; + } + + list_for_each_entry(cache_ent, &vgdev->cap_cache, head) { + if (cache_ent->id == args->cap_set_id && + cache_ent->version == args->cap_set_ver) { + ptr = cache_ent->caps_cache; + spin_unlock(&vgdev->display_info_lock); + goto copy_exit; + } + } + spin_unlock(&vgdev->display_info_lock); + + /* not in cache - need to talk to hw */ + virtio_gpu_cmd_get_capset(vgdev, found_valid, args->cap_set_ver, + &cache_ent); + + ret = wait_event_timeout(vgdev->resp_wq, + atomic_read(&cache_ent->is_valid), 5 * HZ); + + ptr = cache_ent->caps_cache; + +copy_exit: + if (copy_to_user((void __user *)(unsigned long)args->addr, ptr, size)) + return -EFAULT; + + return 0; +} + +struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS] = { + DRM_IOCTL_DEF_DRV(VIRTGPU_MAP, virtio_gpu_map_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + + DRM_IOCTL_DEF_DRV(VIRTGPU_EXECBUFFER, virtio_gpu_execbuffer_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + + DRM_IOCTL_DEF_DRV(VIRTGPU_GETPARAM, virtio_gpu_getparam_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + + DRM_IOCTL_DEF_DRV(VIRTGPU_RESOURCE_CREATE, + virtio_gpu_resource_create_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + + DRM_IOCTL_DEF_DRV(VIRTGPU_RESOURCE_INFO, virtio_gpu_resource_info_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + + /* make transfer async to the main ring? - no sure, can we + thread these in the underlying GL */ + DRM_IOCTL_DEF_DRV(VIRTGPU_TRANSFER_FROM_HOST, + virtio_gpu_transfer_from_host_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(VIRTGPU_TRANSFER_TO_HOST, + virtio_gpu_transfer_to_host_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + + DRM_IOCTL_DEF_DRV(VIRTGPU_WAIT, virtio_gpu_wait_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), + + DRM_IOCTL_DEF_DRV(VIRTGPU_GET_CAPS, virtio_gpu_get_caps_ioctl, + DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW), +}; diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 782766c..06496a1 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -52,6 +52,41 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work) events_clear, &events_clear); } +static void virtio_gpu_ctx_id_get(struct virtio_gpu_device *vgdev, + uint32_t *resid) +{ + int handle; + + idr_preload(GFP_KERNEL); + spin_lock(&vgdev->ctx_id_idr_lock); + handle = idr_alloc(&vgdev->ctx_id_idr, NULL, 1, 0, 0); + spin_unlock(&vgdev->ctx_id_idr_lock); + idr_preload_end(); + *resid = handle; +} + +static void virtio_gpu_ctx_id_put(struct virtio_gpu_device *vgdev, uint32_t id) +{ + spin_lock(&vgdev->ctx_id_idr_lock); + idr_remove(&vgdev->ctx_id_idr, id); + spin_unlock(&vgdev->ctx_id_idr_lock); +} + +static void virtio_gpu_context_create(struct virtio_gpu_device *vgdev, + uint32_t nlen, const char *name, + uint32_t *ctx_id) +{ + virtio_gpu_ctx_id_get(vgdev, ctx_id); + virtio_gpu_cmd_context_create(vgdev, *ctx_id, nlen, name); +} + +static void virtio_gpu_context_destroy(struct virtio_gpu_device *vgdev, + uint32_t ctx_id) +{ + virtio_gpu_cmd_context_destroy(vgdev, ctx_id); + virtio_gpu_ctx_id_put(vgdev, ctx_id); +} + static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq, void (*work_func)(struct work_struct *work)) { @@ -60,6 +95,36 @@ static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq, INIT_WORK(&vgvq->dequeue_work, work_func); } +static void virtio_gpu_get_capsets(struct virtio_gpu_device *vgdev, + int num_capsets) +{ + int i, ret; + + vgdev->capsets = kcalloc(num_capsets, + sizeof(struct virtio_gpu_drv_capset), + GFP_KERNEL); + if (!vgdev->capsets) { + DRM_ERROR("failed to allocate cap sets\n"); + return; + } + for (i = 0; i < num_capsets; i++) { + virtio_gpu_cmd_get_capset_info(vgdev, i); + ret = wait_event_timeout(vgdev->resp_wq, + vgdev->capsets[i].id > 0, 5 * HZ); + if (ret == 0) { + DRM_ERROR("timed out waiting for cap set %d\n", i); + kfree(vgdev->capsets); + vgdev->capsets = NULL; + return; + } + DRM_INFO("cap set %d: id %d, max-version %d, max-size %d\n", + i, vgdev->capsets[i].id, + vgdev->capsets[i].max_version, + vgdev->capsets[i].max_size); + } + vgdev->num_capsets = num_capsets; +} + int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) { static vq_callback_t *callbacks[] = { @@ -70,7 +135,7 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) struct virtio_gpu_device *vgdev; /* this will expand later */ struct virtqueue *vqs[2]; - u32 num_scanouts; + u32 num_scanouts, num_capsets; int ret; if (!virtio_has_feature(dev->virtdev, VIRTIO_F_VERSION_1)) @@ -96,9 +161,15 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) spin_lock_init(&vgdev->fence_drv.lock); INIT_LIST_HEAD(&vgdev->fence_drv.fences); + INIT_LIST_HEAD(&vgdev->cap_cache); INIT_WORK(&vgdev->config_changed_work, virtio_gpu_config_changed_work_func); + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_VIRGL)) + vgdev->has_virgl_3d = true; + DRM_INFO("virgl 3d acceleration %s\n", + vgdev->has_virgl_3d ? "enabled" : "not available"); + ret = vgdev->vdev->config->find_vqs(vgdev->vdev, 2, vqs, callbacks, names); if (ret) { @@ -129,6 +200,11 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) ret = -EINVAL; goto err_scanouts; } + DRM_INFO("number of scanouts: %d\n", num_scanouts); + + virtio_cread(vgdev->vdev, struct virtio_gpu_config, + num_capsets, &num_capsets); + DRM_INFO("number of cap sets: %d\n", num_capsets); ret = virtio_gpu_modeset_init(vgdev); if (ret) @@ -137,6 +213,8 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) virtio_device_ready(vgdev->vdev); vgdev->vqs_ready = true; + if (num_capsets) + virtio_gpu_get_capsets(vgdev, num_capsets); virtio_gpu_cmd_get_display_info(vgdev); wait_event_timeout(vgdev->resp_wq, !vgdev->display_info_pending, 5 * HZ); @@ -157,6 +235,16 @@ err_vqs: return ret; } +static void virtio_gpu_cleanup_cap_cache(struct virtio_gpu_device *vgdev) +{ + struct virtio_gpu_drv_cap_cache *cache_ent, *tmp; + + list_for_each_entry_safe(cache_ent, tmp, &vgdev->cap_cache, head) { + kfree(cache_ent->caps_cache); + kfree(cache_ent); + } +} + int virtio_gpu_driver_unload(struct drm_device *dev) { struct virtio_gpu_device *vgdev = dev->dev_private; @@ -170,6 +258,49 @@ int virtio_gpu_driver_unload(struct drm_device *dev) virtio_gpu_modeset_fini(vgdev); virtio_gpu_ttm_fini(vgdev); virtio_gpu_free_vbufs(vgdev); + virtio_gpu_cleanup_cap_cache(vgdev); + kfree(vgdev->capsets); kfree(vgdev); return 0; } + +int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv; + uint32_t id; + char dbgname[64], tmpname[TASK_COMM_LEN]; + + /* can't create contexts without 3d renderer */ + if (!vgdev->has_virgl_3d) + return 0; + + get_task_comm(tmpname, current); + snprintf(dbgname, sizeof(dbgname), "%s", tmpname); + dbgname[63] = 0; + /* allocate a virt GPU context for this opener */ + vfpriv = kzalloc(sizeof(*vfpriv), GFP_KERNEL); + if (!vfpriv) + return -ENOMEM; + + virtio_gpu_context_create(vgdev, strlen(dbgname), dbgname, &id); + + vfpriv->ctx_id = id; + file->driver_priv = vfpriv; + return 0; +} + +void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv; + + if (!vgdev->has_virgl_3d) + return; + + vfpriv = file->driver_priv; + + virtio_gpu_context_destroy(vgdev, vfpriv->ctx_id); + kfree(vfpriv); + file->driver_priv = NULL; +} diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 2c624c7..f300eba 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -82,24 +82,19 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev, size = roundup(size, PAGE_SIZE); ret = drm_gem_object_init(vgdev->ddev, &bo->gem_base, size); if (ret != 0) - goto err_gem_init; + return ret; bo->dumb = false; virtio_gpu_init_ttm_placement(bo, pinned); ret = ttm_bo_init(&vgdev->mman.bdev, &bo->tbo, size, type, &bo->placement, 0, !kernel, NULL, acc_size, NULL, NULL, &virtio_gpu_ttm_bo_destroy); + /* ttm_bo_init failure will call the destroy */ if (ret != 0) - goto err_ttm_init; + return ret; *bo_ptr = bo; return 0; - -err_ttm_init: - drm_gem_object_release(&bo->gem_base); -err_gem_init: - kfree(bo); - return ret; } int virtio_gpu_object_kmap(struct virtio_gpu_object *bo, void **ptr) diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c new file mode 100644 index 0000000..385e0eb --- /dev/null +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -0,0 +1,71 @@ +/* + * Copyright 2014 Canonical + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Andreas Pokorny + */ + +#include "virtgpu_drv.h" + +/* Empty Implementations as there should not be any other driver for a virtual + * device that might share buffers with virtgpu */ + +int virtgpu_gem_prime_pin(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); + return -ENODEV; +} + +void virtgpu_gem_prime_unpin(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); +} + + +struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); + return ERR_PTR(-ENODEV); +} + +struct drm_gem_object *virtgpu_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *table) +{ + WARN_ONCE(1, "not implemented"); + return ERR_PTR(-ENODEV); +} + +void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj) +{ + WARN_ONCE(1, "not implemented"); + return ERR_PTR(-ENODEV); +} + +void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) +{ + WARN_ONCE(1, "not implemented"); +} + +int virtgpu_gem_prime_mmap(struct drm_gem_object *obj, + struct vm_area_struct *area) +{ + return -ENODEV; +} diff --git a/drivers/gpu/drm/virtio/virtgpu_ttm.c b/drivers/gpu/drm/virtio/virtgpu_ttm.c index b092d7b..9fd924c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ttm.c +++ b/drivers/gpu/drm/virtio/virtgpu_ttm.c @@ -32,6 +32,7 @@ #include <ttm/ttm_module.h> #include <drm/drmP.h> #include <drm/drm.h> +#include <drm/virtgpu_drm.h> #include "virtgpu_drv.h" #include <linux/delay.h> diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 1698669f..5a0f8a7 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -293,8 +293,8 @@ void virtio_gpu_dequeue_cursor_func(struct work_struct *work) wake_up(&vgdev->cursorq.ack_queue); } -static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev, - struct virtio_gpu_vbuffer *vbuf) +static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev, + struct virtio_gpu_vbuffer *vbuf) { struct virtqueue *vq = vgdev->ctrlq.vq; struct scatterlist *sgs[3], vcmd, vout, vresp; @@ -320,7 +320,6 @@ static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev, incnt++; } - spin_lock(&vgdev->ctrlq.qlock); retry: ret = virtqueue_add_sgs(vq, sgs, outcnt, incnt, vbuf, GFP_ATOMIC); if (ret == -ENOSPC) { @@ -331,13 +330,55 @@ retry: } else { virtqueue_kick(vq); } - spin_unlock(&vgdev->ctrlq.qlock); if (!ret) ret = vq->num_free; return ret; } +static int virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev, + struct virtio_gpu_vbuffer *vbuf) +{ + int rc; + + spin_lock(&vgdev->ctrlq.qlock); + rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf); + spin_unlock(&vgdev->ctrlq.qlock); + return rc; +} + +static int virtio_gpu_queue_fenced_ctrl_buffer(struct virtio_gpu_device *vgdev, + struct virtio_gpu_vbuffer *vbuf, + struct virtio_gpu_ctrl_hdr *hdr, + struct virtio_gpu_fence **fence) +{ + struct virtqueue *vq = vgdev->ctrlq.vq; + int rc; + +again: + spin_lock(&vgdev->ctrlq.qlock); + + /* + * Make sure we have enouth space in the virtqueue. If not + * wait here until we have. + * + * Without that virtio_gpu_queue_ctrl_buffer_nolock might have + * to wait for free space, which can result in fence ids being + * submitted out-of-order. + */ + if (vq->num_free < 3) { + spin_unlock(&vgdev->ctrlq.qlock); + wait_event(vgdev->ctrlq.ack_queue, vq->num_free >= 3); + goto again; + } + + if (fence) + virtio_gpu_fence_emit(vgdev, hdr, fence); + rc = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf); + spin_unlock(&vgdev->ctrlq.qlock); + return rc; +} + static int virtio_gpu_queue_cursor(struct virtio_gpu_device *vgdev, struct virtio_gpu_vbuffer *vbuf) { @@ -490,9 +531,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, cmd_p->r.x = x; cmd_p->r.y = y; - if (fence) - virtio_gpu_fence_emit(vgdev, &cmd_p->hdr, fence); - virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); } static void @@ -515,9 +554,7 @@ virtio_gpu_cmd_resource_attach_backing(struct virtio_gpu_device *vgdev, vbuf->data_buf = ents; vbuf->data_size = sizeof(*ents) * nents; - if (fence) - virtio_gpu_fence_emit(vgdev, &cmd_p->hdr, fence); - virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); } static void virtio_gpu_cmd_get_display_info_cb(struct virtio_gpu_device *vgdev, @@ -549,6 +586,47 @@ static void virtio_gpu_cmd_get_display_info_cb(struct virtio_gpu_device *vgdev, drm_kms_helper_hotplug_event(vgdev->ddev); } +static void virtio_gpu_cmd_get_capset_info_cb(struct virtio_gpu_device *vgdev, + struct virtio_gpu_vbuffer *vbuf) +{ + struct virtio_gpu_get_capset_info *cmd = + (struct virtio_gpu_get_capset_info *)vbuf->buf; + struct virtio_gpu_resp_capset_info *resp = + (struct virtio_gpu_resp_capset_info *)vbuf->resp_buf; + int i = le32_to_cpu(cmd->capset_index); + + spin_lock(&vgdev->display_info_lock); + vgdev->capsets[i].id = le32_to_cpu(resp->capset_id); + vgdev->capsets[i].max_version = le32_to_cpu(resp->capset_max_version); + vgdev->capsets[i].max_size = le32_to_cpu(resp->capset_max_size); + spin_unlock(&vgdev->display_info_lock); + wake_up(&vgdev->resp_wq); +} + +static void virtio_gpu_cmd_capset_cb(struct virtio_gpu_device *vgdev, + struct virtio_gpu_vbuffer *vbuf) +{ + struct virtio_gpu_get_capset *cmd = + (struct virtio_gpu_get_capset *)vbuf->buf; + struct virtio_gpu_resp_capset *resp = + (struct virtio_gpu_resp_capset *)vbuf->resp_buf; + struct virtio_gpu_drv_cap_cache *cache_ent; + + spin_lock(&vgdev->display_info_lock); + list_for_each_entry(cache_ent, &vgdev->cap_cache, head) { + if (cache_ent->version == le32_to_cpu(cmd->capset_version) && + cache_ent->id == le32_to_cpu(cmd->capset_id)) { + memcpy(cache_ent->caps_cache, resp->capset_data, + cache_ent->size); + atomic_set(&cache_ent->is_valid, 1); + break; + } + } + spin_unlock(&vgdev->display_info_lock); + wake_up(&vgdev->resp_wq); +} + + int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev) { struct virtio_gpu_ctrl_hdr *cmd_p; @@ -572,6 +650,230 @@ int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev) return 0; } +int virtio_gpu_cmd_get_capset_info(struct virtio_gpu_device *vgdev, int idx) +{ + struct virtio_gpu_get_capset_info *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + void *resp_buf; + + resp_buf = kzalloc(sizeof(struct virtio_gpu_resp_capset_info), + GFP_KERNEL); + if (!resp_buf) + return -ENOMEM; + + cmd_p = virtio_gpu_alloc_cmd_resp + (vgdev, &virtio_gpu_cmd_get_capset_info_cb, &vbuf, + sizeof(*cmd_p), sizeof(struct virtio_gpu_resp_capset_info), + resp_buf); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_GET_CAPSET_INFO); + cmd_p->capset_index = cpu_to_le32(idx); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + return 0; +} + +int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev, + int idx, int version, + struct virtio_gpu_drv_cap_cache **cache_p) +{ + struct virtio_gpu_get_capset *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + int max_size = vgdev->capsets[idx].max_size; + struct virtio_gpu_drv_cap_cache *cache_ent; + void *resp_buf; + + if (idx > vgdev->num_capsets) + return -EINVAL; + + if (version > vgdev->capsets[idx].max_version) + return -EINVAL; + + cache_ent = kzalloc(sizeof(*cache_ent), GFP_KERNEL); + if (!cache_ent) + return -ENOMEM; + + cache_ent->caps_cache = kmalloc(max_size, GFP_KERNEL); + if (!cache_ent->caps_cache) { + kfree(cache_ent); + return -ENOMEM; + } + + resp_buf = kzalloc(sizeof(struct virtio_gpu_resp_capset) + max_size, + GFP_KERNEL); + if (!resp_buf) { + kfree(cache_ent->caps_cache); + kfree(cache_ent); + return -ENOMEM; + } + + cache_ent->version = version; + cache_ent->id = vgdev->capsets[idx].id; + atomic_set(&cache_ent->is_valid, 0); + cache_ent->size = max_size; + spin_lock(&vgdev->display_info_lock); + list_add_tail(&cache_ent->head, &vgdev->cap_cache); + spin_unlock(&vgdev->display_info_lock); + + cmd_p = virtio_gpu_alloc_cmd_resp + (vgdev, &virtio_gpu_cmd_capset_cb, &vbuf, sizeof(*cmd_p), + sizeof(struct virtio_gpu_resp_capset) + max_size, + resp_buf); + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_GET_CAPSET); + cmd_p->capset_id = cpu_to_le32(vgdev->capsets[idx].id); + cmd_p->capset_version = cpu_to_le32(version); + *cache_p = cache_ent; + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + + return 0; +} + +void virtio_gpu_cmd_context_create(struct virtio_gpu_device *vgdev, uint32_t id, + uint32_t nlen, const char *name) +{ + struct virtio_gpu_ctx_create *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_CREATE); + cmd_p->hdr.ctx_id = cpu_to_le32(id); + cmd_p->nlen = cpu_to_le32(nlen); + strncpy(cmd_p->debug_name, name, sizeof(cmd_p->debug_name)-1); + cmd_p->debug_name[sizeof(cmd_p->debug_name)-1] = 0; + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); +} + +void virtio_gpu_cmd_context_destroy(struct virtio_gpu_device *vgdev, + uint32_t id) +{ + struct virtio_gpu_ctx_destroy *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_DESTROY); + cmd_p->hdr.ctx_id = cpu_to_le32(id); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); +} + +void virtio_gpu_cmd_context_attach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id) +{ + struct virtio_gpu_ctx_resource *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_ATTACH_RESOURCE); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + +} + +void virtio_gpu_cmd_context_detach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id) +{ + struct virtio_gpu_ctx_resource *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_DETACH_RESOURCE); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); +} + +void +virtio_gpu_cmd_resource_create_3d(struct virtio_gpu_device *vgdev, + struct virtio_gpu_resource_create_3d *rc_3d, + struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_resource_create_3d *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + *cmd_p = *rc_3d; + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_RESOURCE_CREATE_3D); + cmd_p->hdr.flags = 0; + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + +void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_transfer_host_3d *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_TO_HOST_3D); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + cmd_p->box = *box; + cmd_p->offset = cpu_to_le64(offset); + cmd_p->level = cpu_to_le32(level); + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + +void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_transfer_host_3d *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_FROM_HOST_3D); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + cmd_p->box = *box; + cmd_p->offset = cpu_to_le64(offset); + cmd_p->level = cpu_to_le32(level); + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + +void virtio_gpu_cmd_submit(struct virtio_gpu_device *vgdev, + void *data, uint32_t data_size, + uint32_t ctx_id, struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_cmd_submit *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + vbuf->data_buf = data; + vbuf->data_size = data_size; + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_SUBMIT_3D); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->size = cpu_to_le32(data_size); + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *obj, uint32_t resource_id, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 5ae8f92..8a76821 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -681,6 +681,14 @@ static bool vmw_cmdbuf_try_alloc(struct vmw_cmdbuf_man *man, 0, 0, DRM_MM_SEARCH_DEFAULT, DRM_MM_CREATE_DEFAULT); + if (ret) { + (void) vmw_cmdbuf_man_process(man); + ret = drm_mm_insert_node_generic(&man->mm, info->node, + info->page_size, 0, 0, + DRM_MM_SEARCH_DEFAULT, + DRM_MM_CREATE_DEFAULT); + } + spin_unlock_bh(&man->lock); info->done = !ret; diff --git a/drivers/gpu/ipu-v3/ipu-dc.c b/drivers/gpu/ipu-v3/ipu-dc.c index 9ef2e1f..d3ad534 100644 --- a/drivers/gpu/ipu-v3/ipu-dc.c +++ b/drivers/gpu/ipu-v3/ipu-dc.c @@ -183,12 +183,19 @@ int ipu_dc_init_sync(struct ipu_dc *dc, struct ipu_di *di, bool interlaced, } if (interlaced) { - dc_link_event(dc, DC_EVT_NL, 0, 3); - dc_link_event(dc, DC_EVT_EOL, 0, 2); - dc_link_event(dc, DC_EVT_NEW_DATA, 0, 1); + int addr; + + if (dc->di) + addr = 1; + else + addr = 0; + + dc_link_event(dc, DC_EVT_NL, addr, 3); + dc_link_event(dc, DC_EVT_EOL, addr, 2); + dc_link_event(dc, DC_EVT_NEW_DATA, addr, 1); /* Init template microcode */ - dc_write_tmpl(dc, 0, WROD(0), 0, map, SYNC_WAVE, 0, 8, 1); + dc_write_tmpl(dc, addr, WROD(0), 0, map, SYNC_WAVE, 0, 6, 1); } else { if (dc->di) { dc_link_event(dc, DC_EVT_NL, 2, 3); diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c index 2970c6b..359268e 100644 --- a/drivers/gpu/ipu-v3/ipu-di.c +++ b/drivers/gpu/ipu-v3/ipu-di.c @@ -71,6 +71,10 @@ enum di_sync_wave { DI_SYNC_HSYNC = 3, DI_SYNC_VSYNC = 4, DI_SYNC_DE = 6, + + DI_SYNC_CNT1 = 2, /* counter >= 2 only */ + DI_SYNC_CNT4 = 5, /* counter >= 5 only */ + DI_SYNC_CNT5 = 6, /* counter >= 6 only */ }; #define SYNC_WAVE 0 @@ -211,66 +215,59 @@ static void ipu_di_sync_config_interlaced(struct ipu_di *di, sig->mode.hback_porch + sig->mode.hfront_porch; u32 v_total = sig->mode.vactive + sig->mode.vsync_len + sig->mode.vback_porch + sig->mode.vfront_porch; - u32 reg; struct di_sync_config cfg[] = { { - .run_count = h_total / 2 - 1, - .run_src = DI_SYNC_CLK, + /* 1: internal VSYNC for each frame */ + .run_count = v_total * 2 - 1, + .run_src = 3, /* == counter 7 */ }, { - .run_count = h_total - 11, + /* PIN2: HSYNC waveform */ + .run_count = h_total - 1, .run_src = DI_SYNC_CLK, - .cnt_down = 4, + .cnt_polarity_gen_en = 1, + .cnt_polarity_trigger_src = DI_SYNC_CLK, + .cnt_down = sig->mode.hsync_len * 2, }, { - .run_count = v_total * 2 - 1, - .run_src = DI_SYNC_INT_HSYNC, - .offset_count = 1, - .offset_src = DI_SYNC_INT_HSYNC, - .cnt_down = 4, + /* PIN3: VSYNC waveform */ + .run_count = v_total - 1, + .run_src = 4, /* == counter 7 */ + .cnt_polarity_gen_en = 1, + .cnt_polarity_trigger_src = 4, /* == counter 7 */ + .cnt_down = sig->mode.vsync_len * 2, + .cnt_clr_src = DI_SYNC_CNT1, }, { - .run_count = v_total / 2 - 1, + /* 4: Field */ + .run_count = v_total / 2, .run_src = DI_SYNC_HSYNC, - .offset_count = sig->mode.vback_porch, - .offset_src = DI_SYNC_HSYNC, + .offset_count = h_total / 2, + .offset_src = DI_SYNC_CLK, .repeat_count = 2, - .cnt_clr_src = DI_SYNC_VSYNC, - }, { - .run_src = DI_SYNC_HSYNC, - .repeat_count = sig->mode.vactive / 2, - .cnt_clr_src = 4, - }, { - .run_count = v_total - 1, - .run_src = DI_SYNC_HSYNC, + .cnt_clr_src = DI_SYNC_CNT1, }, { - .run_count = v_total / 2 - 1, + /* 5: Active lines */ .run_src = DI_SYNC_HSYNC, - .offset_count = 9, + .offset_count = (sig->mode.vsync_len + + sig->mode.vback_porch) / 2, .offset_src = DI_SYNC_HSYNC, - .repeat_count = 2, - .cnt_clr_src = DI_SYNC_VSYNC, + .repeat_count = sig->mode.vactive / 2, + .cnt_clr_src = DI_SYNC_CNT4, }, { + /* 6: Active pixel, referenced by DC */ .run_src = DI_SYNC_CLK, - .offset_count = sig->mode.hback_porch, + .offset_count = sig->mode.hsync_len + + sig->mode.hback_porch, .offset_src = DI_SYNC_CLK, .repeat_count = sig->mode.hactive, - .cnt_clr_src = 5, + .cnt_clr_src = DI_SYNC_CNT5, }, { - .run_count = v_total - 1, - .run_src = DI_SYNC_INT_HSYNC, - .offset_count = v_total / 2, - .offset_src = DI_SYNC_INT_HSYNC, - .cnt_clr_src = DI_SYNC_HSYNC, - .cnt_down = 4, + /* 7: Half line HSYNC */ + .run_count = h_total / 2 - 1, + .run_src = DI_SYNC_CLK, } }; ipu_di_sync_config(di, cfg, 0, ARRAY_SIZE(cfg)); - /* set gentime select and tag sel */ - reg = ipu_di_read(di, DI_SW_GEN1(9)); - reg &= 0x1FFFFFFF; - reg |= (3 - 1) << 29 | 0x00008000; - ipu_di_write(di, reg, DI_SW_GEN1(9)); - ipu_di_write(di, v_total / 2 - 1, DI_SCR_CONF); } @@ -543,6 +540,29 @@ int ipu_di_adjust_videomode(struct ipu_di *di, struct videomode *mode) } EXPORT_SYMBOL_GPL(ipu_di_adjust_videomode); +static u32 ipu_di_gen_polarity(int pin) +{ + switch (pin) { + case 1: + return DI_GEN_POLARITY_1; + case 2: + return DI_GEN_POLARITY_2; + case 3: + return DI_GEN_POLARITY_3; + case 4: + return DI_GEN_POLARITY_4; + case 5: + return DI_GEN_POLARITY_5; + case 6: + return DI_GEN_POLARITY_6; + case 7: + return DI_GEN_POLARITY_7; + case 8: + return DI_GEN_POLARITY_8; + } + return 0; +} + int ipu_di_init_sync_panel(struct ipu_di *di, struct ipu_di_signal_cfg *sig) { u32 reg; @@ -582,15 +602,8 @@ int ipu_di_init_sync_panel(struct ipu_di *di, struct ipu_di_signal_cfg *sig) /* set y_sel = 1 */ di_gen |= 0x10000000; - di_gen |= DI_GEN_POLARITY_5; - di_gen |= DI_GEN_POLARITY_8; - - vsync_cnt = 7; - if (sig->mode.flags & DISPLAY_FLAGS_HSYNC_HIGH) - di_gen |= DI_GEN_POLARITY_3; - if (sig->mode.flags & DISPLAY_FLAGS_VSYNC_HIGH) - di_gen |= DI_GEN_POLARITY_2; + vsync_cnt = 3; } else { ipu_di_sync_config_noninterlaced(di, sig, div); @@ -602,25 +615,13 @@ int ipu_di_init_sync_panel(struct ipu_di *di, struct ipu_di_signal_cfg *sig) */ if (!(sig->hsync_pin == 2 && sig->vsync_pin == 3)) vsync_cnt = 6; - - if (sig->mode.flags & DISPLAY_FLAGS_HSYNC_HIGH) { - if (sig->hsync_pin == 2) - di_gen |= DI_GEN_POLARITY_2; - else if (sig->hsync_pin == 4) - di_gen |= DI_GEN_POLARITY_4; - else if (sig->hsync_pin == 7) - di_gen |= DI_GEN_POLARITY_7; - } - if (sig->mode.flags & DISPLAY_FLAGS_VSYNC_HIGH) { - if (sig->vsync_pin == 3) - di_gen |= DI_GEN_POLARITY_3; - else if (sig->vsync_pin == 6) - di_gen |= DI_GEN_POLARITY_6; - else if (sig->vsync_pin == 8) - di_gen |= DI_GEN_POLARITY_8; - } } + if (sig->mode.flags & DISPLAY_FLAGS_HSYNC_HIGH) + di_gen |= ipu_di_gen_polarity(sig->hsync_pin); + if (sig->mode.flags & DISPLAY_FLAGS_VSYNC_HIGH) + di_gen |= ipu_di_gen_polarity(sig->vsync_pin); + if (sig->clk_pol) di_gen |= DI_GEN_POLARITY_DISP_CLK; |
