diff options
Diffstat (limited to 'drivers/gpu/drm')
96 files changed, 1340 insertions, 643 deletions
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 02e52d543e4..b6b7d70f283 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -177,7 +177,7 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast, static inline void ast_open_key(struct ast_private *ast) { - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xA1, 0xFF, 0x04); + ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x80, 0xA8); } #define AST_VIDMEM_SIZE_8M 0x00800000 diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c index 09da3393c52..d5902e21d4a 100644 --- a/drivers/gpu/drm/ast/ast_ttm.c +++ b/drivers/gpu/drm/ast/ast_ttm.c @@ -348,6 +348,7 @@ int ast_bo_create(struct drm_device *dev, int size, int align, astbo->gem.driver_private = NULL; astbo->bo.bdev = &ast->ttm.bdev; + astbo->bo.bdev->dev_mapping = dev->dev_mapping; ast_ttm_placement(astbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM); diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index 60685b21cc3..379a47ea99f 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -273,8 +273,8 @@ static int cirrus_crtc_mode_set(struct drm_crtc *crtc, sr07 |= 0x11; break; case 16: - sr07 |= 0xc1; - hdr = 0xc0; + sr07 |= 0x17; + hdr = 0xc1; break; case 24: sr07 |= 0x15; diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c index 2ed8cfc740c..c18faff8265 100644 --- a/drivers/gpu/drm/cirrus/cirrus_ttm.c +++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c @@ -353,6 +353,7 @@ int cirrus_bo_create(struct drm_device *dev, int size, int align, cirrusbo->gem.driver_private = NULL; cirrusbo->bo.bdev = &cirrus->ttm.bdev; + cirrusbo->bo.bdev->dev_mapping = dev->dev_mapping; cirrus_ttm_placement(cirrusbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index e7e92429d10..8759d699bd8 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2501,10 +2501,22 @@ int drm_mode_getfb(struct drm_device *dev, r->depth = fb->depth; r->bpp = fb->bits_per_pixel; r->pitch = fb->pitches[0]; - if (fb->funcs->create_handle) - ret = fb->funcs->create_handle(fb, file_priv, &r->handle); - else + if (fb->funcs->create_handle) { + if (file_priv->is_master || capable(CAP_SYS_ADMIN)) { + ret = fb->funcs->create_handle(fb, file_priv, + &r->handle); + } else { + /* GET_FB() is an unprivileged ioctl so we must not + * return a buffer-handle to non-master processes! For + * backwards-compatibility reasons, we cannot make + * GET_FB() privileged, so just return an invalid handle + * for non-masters. */ + r->handle = 0; + ret = 0; + } + } else { ret = -ENODEV; + } drm_framebuffer_unreference(fb); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 9cc247f5550..2ab782cb38a 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -406,9 +406,16 @@ long drm_ioctl(struct file *filp, cmd = ioctl->cmd_drv; } else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE)) { + u32 drv_size; + ioctl = &drm_ioctls[nr]; - cmd = ioctl->cmd; + + drv_size = _IOC_SIZE(ioctl->cmd); usize = asize = _IOC_SIZE(cmd); + if (drv_size > asize) + asize = drv_size; + + cmd = ioctl->cmd; } else goto err_i1; diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 9e62bbedb5a..83f0ba5859c 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -68,6 +68,8 @@ #define EDID_QUIRK_DETAILED_SYNC_PP (1 << 6) /* Force reduced-blanking timings for detailed modes */ #define EDID_QUIRK_FORCE_REDUCED_BLANKING (1 << 7) +/* Force 8bpc */ +#define EDID_QUIRK_FORCE_8BPC (1 << 8) struct detailed_mode_closure { struct drm_connector *connector; @@ -125,6 +127,12 @@ static struct edid_quirk { /* ViewSonic VA2026w */ { "VSC", 5020, EDID_QUIRK_FORCE_REDUCED_BLANKING }, + + /* Medion MD 30217 PG */ + { "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 }, + + /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */ + { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC }, }; /* @@ -2952,6 +2960,9 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) drm_add_display_info(edid, &connector->display_info); + if (quirks & EDID_QUIRK_FORCE_8BPC) + connector->display_info.bpc = 8; + return num_modes; } EXPORT_SYMBOL(drm_add_edid_modes); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index cf919e36e8a..239ef30f4a6 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -453,25 +453,21 @@ drm_gem_flink_ioctl(struct drm_device *dev, void *data, spin_lock(&dev->object_name_lock); if (!obj->name) { ret = idr_alloc(&dev->object_name_idr, obj, 1, 0, GFP_NOWAIT); - obj->name = ret; - args->name = (uint64_t) obj->name; - spin_unlock(&dev->object_name_lock); - idr_preload_end(); - if (ret < 0) goto err; - ret = 0; + + obj->name = ret; /* Allocate a reference for the name table. */ drm_gem_object_reference(obj); - } else { - args->name = (uint64_t) obj->name; - spin_unlock(&dev->object_name_lock); - idr_preload_end(); - ret = 0; } + args->name = (uint64_t) obj->name; + ret = 0; + err: + spin_unlock(&dev->object_name_lock); + idr_preload_end(); drm_gem_object_unreference_unlocked(obj); return ret; } diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 8bcce7866d3..f92da0a32f0 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -708,7 +708,10 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc, /* Subtract time delta from raw timestamp to get final * vblank_time timestamp for end of vblank. */ - etime = ktime_sub_ns(etime, delta_ns); + if (delta_ns < 0) + etime = ktime_add_ns(etime, -delta_ns); + else + etime = ktime_sub_ns(etime, delta_ns); *vblank_time = ktime_to_timeval(etime); DRM_DEBUG("crtc %d : v %d p(%d,%d)@ %ld.%ld -> %ld.%ld [e %d us, %d rep]\n", diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 3b315ba85a3..ccfc63665e7 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -84,6 +84,14 @@ void i915_update_dri1_breadcrumb(struct drm_device *dev) drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_master_private *master_priv; + /* + * The dri breadcrumb update races against the drm master disappearing. + * Instead of trying to fix this (this is by far not the only ums issue) + * just don't do the update in kms mode. + */ + if (drm_core_check_feature(dev, DRIVER_MODESET)) + return; + if (dev->primary->master) { master_priv = dev->primary->master->driver_priv; if (master_priv->sarea_priv) @@ -1511,6 +1519,14 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) dev_priv->dev = dev; dev_priv->info = info; + spin_lock_init(&dev_priv->irq_lock); + spin_lock_init(&dev_priv->gpu_error.lock); + spin_lock_init(&dev_priv->rps.lock); + spin_lock_init(&dev_priv->gt_lock); + mutex_init(&dev_priv->dpio_lock); + mutex_init(&dev_priv->rps.hw_lock); + mutex_init(&dev_priv->modeset_restore_lock); + i915_dump_device_info(dev_priv); if (i915_get_bridge_dev(dev)) { @@ -1601,6 +1617,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) intel_detect_pch(dev); intel_irq_init(dev); + intel_pm_init(dev); + intel_gt_sanitize(dev); intel_gt_init(dev); /* Try to make sure MCHBAR is enabled before poking at it */ @@ -1626,14 +1644,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) if (!IS_I945G(dev) && !IS_I945GM(dev)) pci_enable_msi(dev->pdev); - spin_lock_init(&dev_priv->irq_lock); - spin_lock_init(&dev_priv->gpu_error.lock); - spin_lock_init(&dev_priv->rps.lock); - mutex_init(&dev_priv->dpio_lock); - - mutex_init(&dev_priv->rps.hw_lock); - mutex_init(&dev_priv->modeset_restore_lock); - dev_priv->num_plane = 1; if (IS_VALLEYVIEW(dev)) dev_priv->num_plane = 2; @@ -1677,6 +1687,7 @@ out_gem_unload: intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); + pm_qos_remove_request(&dev_priv->pm_qos); destroy_workqueue(dev_priv->wq); out_mtrrfree: if (dev_priv->mm.gtt_mtrr >= 0) { @@ -1845,8 +1856,10 @@ void i915_driver_lastclose(struct drm_device * dev) void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv) { + mutex_lock(&dev->struct_mutex); i915_gem_context_close(dev, file_priv); i915_gem_release(dev, file_priv); + mutex_unlock(&dev->struct_mutex); } void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index a2e4953b8e8..bc6cd3117ac 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -685,7 +685,7 @@ static int i915_drm_thaw(struct drm_device *dev) { int error = 0; - intel_gt_reset(dev); + intel_gt_sanitize(dev); if (drm_core_check_feature(dev, DRIVER_MODESET)) { mutex_lock(&dev->struct_mutex); @@ -711,7 +711,7 @@ int i915_resume(struct drm_device *dev) pci_set_master(dev->pdev); - intel_gt_reset(dev); + intel_gt_sanitize(dev); /* * Platforms with opregion should have sane BIOS, older ones (gen3 and @@ -1247,21 +1247,21 @@ hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg) #define __i915_read(x, y) \ u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \ + unsigned long irqflags; \ u##x val = 0; \ + spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \ if (IS_GEN5(dev_priv->dev)) \ ilk_dummy_write(dev_priv); \ if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \ - unsigned long irqflags; \ - spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \ if (dev_priv->forcewake_count == 0) \ dev_priv->gt.force_wake_get(dev_priv); \ val = read##y(dev_priv->regs + reg); \ if (dev_priv->forcewake_count == 0) \ dev_priv->gt.force_wake_put(dev_priv); \ - spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \ } else { \ val = read##y(dev_priv->regs + reg); \ } \ + spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \ trace_i915_reg_rw(false, reg, val, sizeof(val)); \ return val; \ } @@ -1274,8 +1274,10 @@ __i915_read(64, q) #define __i915_write(x, y) \ void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \ + unsigned long irqflags; \ u32 __fifo_ret = 0; \ trace_i915_reg_rw(true, reg, val, sizeof(val)); \ + spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \ if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \ __fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \ } \ @@ -1287,6 +1289,7 @@ void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \ gen6_gt_check_fifodbg(dev_priv); \ } \ hsw_unclaimed_reg_check(dev_priv, reg); \ + spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \ } __i915_write(8, b) __i915_write(16, w) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9669a0b8b44..47d8b68c500 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -491,6 +491,7 @@ enum intel_sbi_destination { #define QUIRK_PIPEA_FORCE (1<<0) #define QUIRK_LVDS_SSC_DISABLE (1<<1) #define QUIRK_INVERT_BRIGHTNESS (1<<2) +#define QUIRK_NO_PCH_PWM_ENABLE (1<<3) struct intel_fbdev; struct intel_fbc_work; @@ -1474,9 +1475,10 @@ void i915_hangcheck_elapsed(unsigned long data); void i915_handle_error(struct drm_device *dev, bool wedged); extern void intel_irq_init(struct drm_device *dev); +extern void intel_pm_init(struct drm_device *dev); extern void intel_hpd_init(struct drm_device *dev); extern void intel_gt_init(struct drm_device *dev); -extern void intel_gt_reset(struct drm_device *dev); +extern void intel_gt_sanitize(struct drm_device *dev); void i915_error_state_free(struct kref *error_ref); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 9e35dafc580..0a30088178b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1160,7 +1160,8 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj, /* Manually manage the write flush as we may have not yet * retired the buffer. */ - if (obj->last_write_seqno && + if (ret == 0 && + obj->last_write_seqno && i915_seqno_passed(seqno, obj->last_write_seqno)) { obj->last_write_seqno = 0; obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS; @@ -1880,6 +1881,10 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, u32 seqno = intel_ring_get_seqno(ring); BUG_ON(ring == NULL); + if (obj->ring != ring && obj->last_write_seqno) { + /* Keep the seqno relative to the current ring */ + obj->last_write_seqno = seqno; + } obj->ring = ring; /* Add a reference if we're newly entering the active list. */ @@ -2133,7 +2138,17 @@ void i915_gem_restore_fences(struct drm_device *dev) for (i = 0; i < dev_priv->num_fence_regs; i++) { struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i]; - i915_gem_write_fence(dev, i, reg->obj); + + /* + * Commit delayed tiling changes if we have an object still + * attached to the fence, otherwise just clear the fence. + */ + if (reg->obj) { + i915_gem_object_update_fence(reg->obj, reg, + reg->obj->tiling_mode); + } else { + i915_gem_write_fence(dev, i, NULL); + } } } @@ -2533,7 +2548,6 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, drm_i915_private_t *dev_priv = dev->dev_private; int fence_reg; int fence_pitch_shift; - uint64_t val; if (INTEL_INFO(dev)->gen >= 6) { fence_reg = FENCE_REG_SANDYBRIDGE_0; @@ -2543,8 +2557,23 @@ static void i965_write_fence_reg(struct drm_device *dev, int 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 + * precede the update with write to turn off the fence register, + * and only enable the fence as the last step. + * + * 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); + if (obj) { u32 size = obj->gtt_space->size; + uint64_t val; val = (uint64_t)((obj->gtt_offset + size - 4096) & 0xfffff000) << 32; @@ -2553,12 +2582,16 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I965_FENCE_TILING_Y_SHIFT; val |= I965_FENCE_REG_VALID; - } else - val = 0; - fence_reg += reg * 8; - I915_WRITE64(fence_reg, val); - POSTING_READ(fence_reg); + I915_WRITE(fence_reg + 4, val >> 32); + POSTING_READ(fence_reg + 4); + + I915_WRITE(fence_reg + 0, val); + POSTING_READ(fence_reg); + } else { + I915_WRITE(fence_reg + 4, 0); + POSTING_READ(fence_reg + 4); + } } static void i915_write_fence_reg(struct drm_device *dev, int reg, @@ -2653,6 +2686,10 @@ static void i915_gem_write_fence(struct drm_device *dev, int reg, if (i915_gem_object_needs_mb(dev_priv->fence_regs[reg].obj)) mb(); + WARN(obj && (!obj->stride || !obj->tiling_mode), + "bogus fence setup with stride: 0x%x, tiling mode: %i\n", + obj->stride, obj->tiling_mode); + switch (INTEL_INFO(dev)->gen) { case 7: case 6: @@ -2712,6 +2749,7 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj, fence->obj = NULL; list_del_init(&fence->lru_list); } + obj->fence_dirty = false; } static int @@ -2841,7 +2879,6 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj) return 0; i915_gem_object_update_fence(obj, reg, enable); - obj->fence_dirty = false; return 0; } @@ -4456,7 +4493,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list) if (obj->pages_pin_count == 0) cnt += obj->base.size >> PAGE_SHIFT; - list_for_each_entry(obj, &dev_priv->mm.inactive_list, gtt_list) + list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list) if (obj->pin_count == 0 && obj->pages_pin_count == 0) cnt += obj->base.size >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index a1e8ecb6adf..b10b1b1b487 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -113,7 +113,7 @@ static int get_context_size(struct drm_device *dev) case 7: reg = I915_READ(GEN7_CXT_SIZE); if (IS_HASWELL(dev)) - ret = HSW_CXT_TOTAL_SIZE(reg) * 64; + ret = HSW_CXT_TOTAL_SIZE; else ret = GEN7_CXT_TOTAL_SIZE(reg) * 64; break; @@ -291,10 +291,8 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file) { struct drm_i915_file_private *file_priv = file->driver_priv; - mutex_lock(&dev->struct_mutex); idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL); idr_destroy(&file_priv->context_idr); - mutex_unlock(&dev->struct_mutex); } static struct i915_hw_context * diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 130d1db27e2..fa2d15b1673 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -222,7 +222,7 @@ i915_pages_create_for_stolen(struct drm_device *dev, } sg = st->sgl; - sg->offset = offset; + sg->offset = 0; sg->length = size; sg_dma_address(sg) = (dma_addr_t)dev_priv->mm.stolen_base + offset; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 0aa2ef0d2ae..c8d16a622f3 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -70,15 +70,6 @@ static const u32 hpd_status_gen4[] = { [HPD_PORT_D] = PORTD_HOTPLUG_INT_STATUS }; -static const u32 hpd_status_i965[] = { - [HPD_CRT] = CRT_HOTPLUG_INT_STATUS, - [HPD_SDVO_B] = SDVOB_HOTPLUG_INT_STATUS_I965, - [HPD_SDVO_C] = SDVOC_HOTPLUG_INT_STATUS_I965, - [HPD_PORT_B] = PORTB_HOTPLUG_INT_STATUS, - [HPD_PORT_C] = PORTC_HOTPLUG_INT_STATUS, - [HPD_PORT_D] = PORTD_HOTPLUG_INT_STATUS -}; - static const u32 hpd_status_i915[] = { /* i915 and valleyview are the same */ [HPD_CRT] = CRT_HOTPLUG_INT_STATUS, [HPD_SDVO_B] = SDVOB_HOTPLUG_INT_STATUS_I915, @@ -1018,6 +1009,34 @@ done: return ret; } +static void i915_error_wake_up(struct drm_i915_private *dev_priv, + bool reset_completed) +{ + struct intel_ring_buffer *ring; + int i; + + /* + * Notify all waiters for GPU completion events that reset state has + * been changed, and that they need to restart their wait after + * checking for potential errors (and bail out to drop locks if there is + * a gpu reset pending so that i915_error_work_func can acquire them). + */ + + /* Wake up __wait_seqno, potentially holding dev->struct_mutex. */ + for_each_ring(ring, dev_priv, i) + wake_up_all(&ring->irq_queue); + + /* Wake up intel_crtc_wait_for_pending_flips, holding crtc->mutex. */ + wake_up_all(&dev_priv->pending_flip_queue); + + /* + * Signal tasks blocked in i915_gem_wait_for_error that the pending + * reset state is cleared. + */ + if (reset_completed) + wake_up_all(&dev_priv->gpu_error.reset_queue); +} + /** * i915_error_work_func - do process context error handling work * @work: work struct @@ -1032,11 +1051,10 @@ static void i915_error_work_func(struct work_struct *work) drm_i915_private_t *dev_priv = container_of(error, drm_i915_private_t, gpu_error); struct drm_device *dev = dev_priv->dev; - struct intel_ring_buffer *ring; char *error_event[] = { "ERROR=1", NULL }; char *reset_event[] = { "RESET=1", NULL }; char *reset_done_event[] = { "ERROR=0", NULL }; - int i, ret; + int ret; kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event); @@ -1055,8 +1073,16 @@ static void i915_error_work_func(struct work_struct *work) kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, reset_event); + /* + * All state reset _must_ be completed before we update the + * reset counter, for otherwise waiters might miss the reset + * pending state and not properly drop locks, resulting in + * deadlocks with the reset work. + */ ret = i915_reset(dev); + intel_display_handle_reset(dev); + if (ret == 0) { /* * After all the gem state is reset, increment the reset @@ -1077,12 +1103,11 @@ static void i915_error_work_func(struct work_struct *work) atomic_set(&error->reset_counter, I915_WEDGED); } - for_each_ring(ring, dev_priv, i) - wake_up_all(&ring->irq_queue); - - intel_display_handle_reset(dev); - - wake_up_all(&dev_priv->gpu_error.reset_queue); + /* + * Note: The wake_up also serves as a memory barrier so that + * waiters see the update value of the reset counter atomic_t. + */ + i915_error_wake_up(dev_priv, true); } } @@ -1718,8 +1743,6 @@ static void i915_report_and_clear_eir(struct drm_device *dev) void i915_handle_error(struct drm_device *dev, bool wedged) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; - int i; i915_capture_error_state(dev); i915_report_and_clear_eir(dev); @@ -1729,14 +1752,28 @@ void i915_handle_error(struct drm_device *dev, bool wedged) &dev_priv->gpu_error.reset_counter); /* - * Wakeup waiting processes so that the reset work item - * doesn't deadlock trying to grab various locks. + * Wakeup waiting processes so that the reset work function + * i915_error_work_func doesn't deadlock trying to grab various + * locks. By bumping the reset counter first, the woken + * processes will see a reset in progress and back off, + * releasing their locks and then wait for the reset completion. + * We must do this for _all_ gpu waiters that might hold locks + * that the reset work needs to acquire. + * + * Note: The wake_up serves as the required memory barrier to + * ensure that the waiters see the updated value of the reset + * counter atomic_t. */ - for_each_ring(ring, dev_priv, i) - wake_up_all(&ring->irq_queue); + i915_error_wake_up(dev_priv, false); } - queue_work(dev_priv->wq, &dev_priv->gpu_error.work); + /* + * Our reset work can grab modeset locks (since it needs to reset the + * state of outstanding pagelips). Hence it must not be run on our own + * dev-priv->wq work queue for otherwise the flush_work in the pageflip + * code will deadlock. + */ + schedule_work(&dev_priv->gpu_error.work); } static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, int pipe) @@ -2952,13 +2989,13 @@ static irqreturn_t i965_irq_handler(int irq, void *arg) u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT); u32 hotplug_trigger = hotplug_status & (IS_G4X(dev) ? HOTPLUG_INT_STATUS_G4X : - HOTPLUG_INT_STATUS_I965); + HOTPLUG_INT_STATUS_I915); DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x\n", hotplug_status); if (hotplug_trigger) { if (hotplug_irq_storm_detect(dev, hotplug_trigger, - IS_G4X(dev) ? hpd_status_gen4 : hpd_status_i965)) + IS_G4X(dev) ? hpd_status_gen4 : hpd_status_i915)) i915_hpd_irq_setup(dev); queue_work(dev_priv->wq, &dev_priv->hotplug_work); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2d6b62e42da..2d90f96c19d 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -617,6 +617,8 @@ will not assert AGPBUSY# and will only be delivered when out of C3. */ #define INSTPM_FORCE_ORDERING (1<<7) /* GEN6+ */ +#define INSTPM_TLB_INVALIDATE (1<<9) +#define INSTPM_SYNC_FLUSH (1<<5) #define ACTHD 0x020c8 #define FW_BLC 0x020d8 #define FW_BLC2 0x020dc @@ -1535,14 +1537,13 @@ GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \ GEN7_CXT_GT1_SIZE(ctx_reg) + \ GEN7_CXT_VFSTATE_SIZE(ctx_reg)) -#define HSW_CXT_POWER_SIZE(ctx_reg) ((ctx_reg >> 26) & 0x3f) -#define HSW_CXT_RING_SIZE(ctx_reg) ((ctx_reg >> 23) & 0x7) -#define HSW_CXT_RENDER_SIZE(ctx_reg) ((ctx_reg >> 15) & 0xff) -#define HSW_CXT_TOTAL_SIZE(ctx_reg) (HSW_CXT_POWER_SIZE(ctx_reg) + \ - HSW_CXT_RING_SIZE(ctx_reg) + \ - HSW_CXT_RENDER_SIZE(ctx_reg) + \ - GEN7_CXT_VFSTATE_SIZE(ctx_reg)) - +/* Haswell does have the CXT_SIZE register however it does not appear to be + * valid. Now, docs explain in dwords what is in the context object. The full + * size is 70720 bytes, however, the power context and execlist context will + * never be saved (power context is stored elsewhere, and execlists don't work + * on HSW) - so the final size is 66944 bytes, which rounds to 17 pages. + */ +#define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE) /* * Overlay regs @@ -1674,10 +1675,20 @@ #define CRT_HOTPLUG_DETECT_VOLTAGE_475MV (1 << 2) #define PORT_HOTPLUG_STAT (dev_priv->info->display_mmio_offset + 0x61114) -/* HDMI/DP bits are gen4+ */ -#define PORTB_HOTPLUG_LIVE_STATUS (1 << 29) -#define PORTC_HOTPLUG_LIVE_STATUS (1 << 28) -#define PORTD_HOTPLUG_LIVE_STATUS (1 << 27) +/* + * HDMI/DP bits are gen4+ + * + * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused. + * Please check the detailed lore in the commit message for for experimental + * evidence. + */ +#define PORTD_HOTPLUG_LIVE_STATUS_G4X (1 << 29) +#define PORTC_HOTPLUG_LIVE_STATUS_G4X (1 << 28) +#define PORTB_HOTPLUG_LIVE_STATUS_G4X (1 << 27) +/* VLV DP/HDMI bits again match Bspec */ +#define PORTD_HOTPLUG_LIVE_STATUS_VLV (1 << 27) +#define PORTC_HOTPLUG_LIVE_STATUS_VLV (1 << 28) +#define PORTB_HOTPLUG_LIVE_STATUS_VLV (1 << 29) #define PORTD_HOTPLUG_INT_STATUS (3 << 21) #define PORTC_HOTPLUG_INT_STATUS (3 << 19) #define PORTB_HOTPLUG_INT_STATUS (3 << 17) @@ -1691,6 +1702,12 @@ /* SDVO is different across gen3/4 */ #define SDVOC_HOTPLUG_INT_STATUS_G4X (1 << 3) #define SDVOB_HOTPLUG_INT_STATUS_G4X (1 << 2) +/* + * Bspec seems to be seriously misleaded about the SDVO hpd bits on i965g/gm, + * since reality corrobates that they're the same as on gen3. But keep these + * bits here (and the comment!) to help any other lost wanderers back onto the + * right tracks. + */ #define SDVOC_HOTPLUG_INT_STATUS_I965 (3 << 4) #define SDVOB_HOTPLUG_INT_STATUS_I965 (3 << 2) #define SDVOC_HOTPLUG_INT_STATUS_I915 (1 << 7) @@ -1702,13 +1719,6 @@ PORTC_HOTPLUG_INT_STATUS | \ PORTD_HOTPLUG_INT_STATUS) -#define HOTPLUG_INT_STATUS_I965 (CRT_HOTPLUG_INT_STATUS | \ - SDVOB_HOTPLUG_INT_STATUS_I965 | \ - SDVOC_HOTPLUG_INT_STATUS_I965 | \ - PORTB_HOTPLUG_INT_STATUS | \ - PORTC_HOTPLUG_INT_STATUS | \ - PORTD_HOTPLUG_INT_STATUS) - #define HOTPLUG_INT_STATUS_I915 (CRT_HOTPLUG_INT_STATUS | \ SDVOB_HOTPLUG_INT_STATUS_I915 | \ SDVOC_HOTPLUG_INT_STATUS_I915 | \ @@ -4246,7 +4256,7 @@ #define EDP_LINK_TRAIN_600MV_0DB_IVB (0x30 <<22) #define EDP_LINK_TRAIN_600MV_3_5DB_IVB (0x36 <<22) #define EDP_LINK_TRAIN_800MV_0DB_IVB (0x38 <<22) -#define EDP_LINK_TRAIN_800MV_3_5DB_IVB (0x33 <<22) +#define EDP_LINK_TRAIN_800MV_3_5DB_IVB (0x3e <<22) /* legacy values */ #define EDP_LINK_TRAIN_500MV_0DB_IVB (0x00 <<22) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index fb961bb8190..7ce38344e48 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -684,7 +684,7 @@ static void intel_ddi_mode_set(struct drm_encoder *encoder, struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); - intel_dp->DP = intel_dig_port->port_reversal | + intel_dp->DP = intel_dig_port->saved_port_bits | DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW; switch (intel_dp->lane_count) { case 1: @@ -1193,12 +1193,18 @@ void intel_ddi_setup_hw_pll_state(struct drm_device *dev) enum pipe pipe; struct intel_crtc *intel_crtc; + dev_priv->ddi_plls.spll_refcount = 0; + dev_priv->ddi_plls.wrpll1_refcount = 0; + dev_priv->ddi_plls.wrpll2_refcount = 0; + for_each_pipe(pipe) { intel_crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]); - if (!intel_crtc->active) + if (!intel_crtc->active) { + intel_crtc->ddi_pll_sel = PORT_CLK_SEL_NONE; continue; + } intel_crtc->ddi_pll_sel = intel_ddi_get_crtc_pll(dev_priv, pipe); @@ -1324,7 +1330,8 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder) * enabling the port. */ I915_WRITE(DDI_BUF_CTL(port), - intel_dig_port->port_reversal | DDI_BUF_CTL_ENABLE); + intel_dig_port->saved_port_bits | + DDI_BUF_CTL_ENABLE); } else if (type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); @@ -1543,8 +1550,9 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->get_hw_state = intel_ddi_get_hw_state; intel_dig_port->port = port; - intel_dig_port->port_reversal = I915_READ(DDI_BUF_CTL(port)) & - DDI_BUF_PORT_REVERSAL; + intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & + (DDI_BUF_PORT_REVERSAL | + DDI_A_4_LANES); if (hdmi_connector) intel_dig_port->hdmi.hdmi_reg = DDI_BUF_CTL(port); intel_dig_port->dp.output_reg = DDI_BUF_CTL(port); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 56746dcac40..54ae96f7bec 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -3946,8 +3946,6 @@ static void intel_connector_check_state(struct intel_connector *connector) * consider. */ void intel_connector_dpms(struct drm_connector *connector, int mode) { - struct intel_encoder *encoder = intel_attached_encoder(connector); - /* All the simple cases only support two dpms states. */ if (mode != DRM_MODE_DPMS_ON) mode = DRM_MODE_DPMS_OFF; @@ -3958,10 +3956,8 @@ void intel_connector_dpms(struct drm_connector *connector, int mode) connector->dpms = mode; /* Only need to change hw state when actually enabled */ - if (encoder->base.crtc) - intel_encoder_dpms(encoder, mode); - else - WARN_ON(encoder->connectors_active != false); + if (connector->encoder) + intel_encoder_dpms(to_intel_encoder(connector->encoder), mode); intel_modeset_check_state(connector->dev); } @@ -4333,7 +4329,8 @@ static void vlv_update_pll(struct intel_crtc *crtc) static void i9xx_update_pll(struct intel_crtc *crtc, intel_clock_t *reduced_clock, - int num_connectors) + int num_connectors, + bool needs_tv_clock) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -4391,7 +4388,7 @@ static void i9xx_update_pll(struct intel_crtc *crtc, if (INTEL_INFO(dev)->gen >= 4) dpll |= (6 << PLL_LOAD_PULSE_PHASE_SHIFT); - if (is_sdvo && intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_TVOUT)) + if (is_sdvo && needs_tv_clock) dpll |= PLL_REF_INPUT_TVCLKINBC; else if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_TVOUT)) /* XXX: just matching BIOS for now */ @@ -4563,6 +4560,10 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc) pipeconf = I915_READ(PIPECONF(intel_crtc->pipe)); + if (dev_priv->quirks & QUIRK_PIPEA_FORCE && + I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE) + pipeconf |= PIPECONF_ENABLE; + if (intel_crtc->pipe == 0 && INTEL_INFO(dev)->gen < 4) { /* Enable pixel doubling when the dot clock is > 90% of the (display) * core speed. @@ -4716,7 +4717,8 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, else i9xx_update_pll(intel_crtc, has_reduced_clock ? &reduced_clock : NULL, - num_connectors); + num_connectors, + is_sdvo && is_tv); /* Set up the display plane register */ dspcntr = DISPPLANE_GAMMA_ENABLE; @@ -5223,7 +5225,7 @@ static void intel_set_pipe_csc(struct drm_crtc *crtc) uint16_t postoff = 0; if (intel_crtc->config.limited_color_range) - postoff = (16 * (1 << 13) / 255) & 0x1fff; + postoff = (16 * (1 << 12) / 255) & 0x1fff; I915_WRITE(PIPE_CSC_POSTOFF_HI(pipe), postoff); I915_WRITE(PIPE_CSC_POSTOFF_ME(pipe), postoff); @@ -6260,7 +6262,9 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) intel_crtc->cursor_visible = visible; } /* and commit changes on next vblank */ + POSTING_READ(CURCNTR(pipe)); I915_WRITE(CURBASE(pipe), base); + POSTING_READ(CURBASE(pipe)); } static void ivb_update_cursor(struct drm_crtc *crtc, u32 base) @@ -6287,7 +6291,9 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base) intel_crtc->cursor_visible = visible; } /* and commit changes on next vblank */ + POSTING_READ(CURCNTR_IVB(pipe)); I915_WRITE(CURBASE_IVB(pipe), base); + POSTING_READ(CURBASE_IVB(pipe)); } /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */ @@ -8146,15 +8152,20 @@ static void intel_set_config_restore_state(struct drm_device *dev, } static bool -is_crtc_connector_off(struct drm_crtc *crtc, struct drm_connector *connectors, - int num_connectors) +is_crtc_connector_off(struct drm_mode_set *set) { int i; - for (i = 0; i < num_connectors; i++) - if (connectors[i].encoder && - connectors[i].encoder->crtc == crtc && - connectors[i].dpms != DRM_MODE_DPMS_ON) + if (set->num_connectors == 0) + return false; + + if (WARN_ON(set->connectors == NULL)) + return false; + + for (i = 0; i < set->num_connectors; i++) + if (set->connectors[i]->encoder && + set->connectors[i]->encoder->crtc == set->crtc && + set->connectors[i]->dpms != DRM_MODE_DPMS_ON) return true; return false; @@ -8167,10 +8178,8 @@ intel_set_config_compute_mode_changes(struct drm_mode_set *set, /* We should be able to check here if the fb has the same properties * and then just flip_or_move it */ - if (set->connectors != NULL && - is_crtc_connector_off(set->crtc, *set->connectors, - set->num_connectors)) { - config->mode_changed = true; + if (is_crtc_connector_off(set)) { + config->mode_changed = true; } else if (set->crtc->fb != set->fb) { /* If we have no fb then treat it as a full mode set */ if (set->crtc->fb == NULL) { @@ -8914,6 +8923,17 @@ static void quirk_invert_brightness(struct drm_device *dev) DRM_INFO("applying inverted panel brightness quirk\n"); } +/* + * Some machines (Dell XPS13) suffer broken backlight controls if + * BLM_PCH_PWM_ENABLE is set. + */ +static void quirk_no_pcm_pwm_enable(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + dev_priv->quirks |= QUIRK_NO_PCH_PWM_ENABLE; + DRM_INFO("applying no-PCH_PWM_ENABLE quirk\n"); +} + struct intel_quirk { int device; int subsystem_vendor; @@ -8983,6 +9003,11 @@ static struct intel_quirk intel_quirks[] = { /* Acer Aspire 4736Z */ { 0x2a42, 0x1025, 0x0260, quirk_invert_brightness }, + + /* Dell XPS13 HD Sandy Bridge */ + { 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable }, + /* Dell XPS13 HD and XPS13 FHD Ivy Bridge */ + { 0x0166, 0x1028, 0x058b, quirk_no_pcm_pwm_enable }, }; static void intel_init_quirks(struct drm_device *dev) @@ -9431,7 +9456,9 @@ void intel_modeset_gem_init(struct drm_device *dev) intel_setup_overlay(dev); + mutex_lock(&dev->mode_config.mutex); intel_modeset_setup_hw_state(dev, false); + mutex_unlock(&dev->mode_config.mutex); } void intel_modeset_cleanup(struct drm_device *dev) @@ -9505,14 +9532,15 @@ void intel_connector_attach_encoder(struct intel_connector *connector, int intel_modeset_vga_set_state(struct drm_device *dev, bool state) { struct drm_i915_private *dev_priv = dev->dev_private; + unsigned reg = INTEL_INFO(dev)->gen >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL; u16 gmch_ctrl; - pci_read_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, &gmch_ctrl); + pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl); if (state) gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE; else gmch_ctrl |= INTEL_GMCH_VGA_DISABLE; - pci_write_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, gmch_ctrl); + pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl); return 0; } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 70789b1b564..cfd327c292e 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -604,7 +604,18 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode, DRM_DEBUG_KMS("aux_ch native nack\n"); return -EREMOTEIO; case AUX_NATIVE_REPLY_DEFER: - udelay(100); + /* + * For now, just give more slack to branch devices. We + * could check the DPCD for I2C bit rate capabilities, + * and if available, adjust the interval. We could also + * be more careful with DP-to-Legacy adapters where a + * long legacy cable may force very low I2C bit rates. + */ + if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & + DP_DWN_STRM_PORT_PRESENT) + usleep_range(500, 600); + else + usleep_range(300, 400); continue; default: DRM_ERROR("aux_ch invalid native reply 0x%02x\n", @@ -2266,18 +2277,34 @@ g4x_dp_detect(struct intel_dp *intel_dp) return status; } - switch (intel_dig_port->port) { - case PORT_B: - bit = PORTB_HOTPLUG_LIVE_STATUS; - break; - case PORT_C: - bit = PORTC_HOTPLUG_LIVE_STATUS; - break; - case PORT_D: - bit = PORTD_HOTPLUG_LIVE_STATUS; - break; - default: - return connector_status_unknown; + 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 connector_status_unknown; + } + } 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 connector_status_unknown; + } } if ((I915_READ(PORT_HOTPLUG_STAT) & bit) == 0) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 624a9e6b8d7..7cd55843e73 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -426,7 +426,7 @@ struct intel_dp { struct intel_digital_port { struct intel_encoder base; enum port port; - u32 port_reversal; + u32 saved_port_bits; struct intel_dp dp; struct intel_hdmi hdmi; }; diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 29412cc89c7..f77d42f7442 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -869,6 +869,30 @@ static const struct dmi_system_id intel_no_lvds[] = { DMI_MATCH(DMI_PRODUCT_NAME, "ESPRIMO Q900"), }, }, + { + .callback = intel_no_lvds_dmi_callback, + .ident = "Intel D410PT", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel"), + DMI_MATCH(DMI_BOARD_NAME, "D410PT"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, + .ident = "Intel D425KT", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "D425KT"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, + .ident = "Intel D510MO", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "D510MO"), + }, + }, { } /* terminating entry */ }; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index eb5e6e95f3c..33cb87f7983 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -354,7 +354,8 @@ void intel_panel_enable_backlight(struct drm_device *dev, POSTING_READ(reg); I915_WRITE(reg, tmp | BLM_PWM_ENABLE); - if (HAS_PCH_SPLIT(dev)) { + if (HAS_PCH_SPLIT(dev) && + !(dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)) { tmp = I915_READ(BLC_PWM_PCH_CTL1); tmp |= BLM_PCH_PWM_ENABLE; tmp &= ~BLM_PCH_OVERRIDE_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index aa01128ff19..94ad6bc0826 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4486,7 +4486,7 @@ static void vlv_force_wake_put(struct drm_i915_private *dev_priv) gen6_gt_check_fifodbg(dev_priv); } -void intel_gt_reset(struct drm_device *dev) +void intel_gt_sanitize(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -4497,26 +4497,61 @@ void intel_gt_reset(struct drm_device *dev) if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) __gen6_gt_force_wake_mt_reset(dev_priv); } + + /* BIOS often leaves RC6 enabled, but disable it for hw init */ + if (INTEL_INFO(dev)->gen >= 6) + intel_disable_gt_powersave(dev); } void intel_gt_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - spin_lock_init(&dev_priv->gt_lock); - - intel_gt_reset(dev); - if (IS_VALLEYVIEW(dev)) { dev_priv->gt.force_wake_get = vlv_force_wake_get; dev_priv->gt.force_wake_put = vlv_force_wake_put; - } else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) { + } else if (IS_HASWELL(dev)) { dev_priv->gt.force_wake_get = __gen6_gt_force_wake_mt_get; dev_priv->gt.force_wake_put = __gen6_gt_force_wake_mt_put; + } else if (IS_IVYBRIDGE(dev)) { + u32 ecobus; + + /* IVB configs may use multi-threaded forcewake */ + + /* A small trick here - if the bios hasn't configured + * MT forcewake, and if the device is in RC6, then + * force_wake_mt_get will not wake the device and the + * ECOBUS read will return zero. Which will be + * (correctly) interpreted by the test below as MT + * forcewake being disabled. + */ + mutex_lock(&dev->struct_mutex); + __gen6_gt_force_wake_mt_get(dev_priv); + ecobus = I915_READ_NOTRACE(ECOBUS); + __gen6_gt_force_wake_mt_put(dev_priv); + mutex_unlock(&dev->struct_mutex); + + if (ecobus & FORCEWAKE_MT_ENABLE) { + dev_priv->gt.force_wake_get = + __gen6_gt_force_wake_mt_get; + dev_priv->gt.force_wake_put = + __gen6_gt_force_wake_mt_put; + } else { + DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n"); + DRM_INFO("when using vblank-synced partial screen updates.\n"); + dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get; + dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put; + } } else if (IS_GEN6(dev)) { dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get; dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put; } +} + +void intel_pm_init(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work, intel_gen6_powersave_work); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 1d5d613eb6b..629527d205d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -490,9 +490,6 @@ cleanup_pipe_control(struct intel_ring_buffer *ring) struct pipe_control *pc = ring->private; struct drm_i915_gem_object *obj; - if (!ring->private) - return; - obj = pc->obj; kunmap(sg_page(obj->pages->sgl)); @@ -500,7 +497,6 @@ cleanup_pipe_control(struct intel_ring_buffer *ring) drm_gem_object_unreference(&obj->base); kfree(pc); - ring->private = NULL; } static int init_render_ring(struct intel_ring_buffer *ring) @@ -571,7 +567,10 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring) if (HAS_BROKEN_CS_TLB(dev)) drm_gem_object_unreference(to_gem_object(ring->private)); - cleanup_pipe_control(ring); + if (INTEL_INFO(dev)->gen >= 5) + cleanup_pipe_control(ring); + + ring->private = NULL; } static void @@ -908,6 +907,18 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring) I915_WRITE(mmio, (u32)ring->status_page.gfx_addr); POSTING_READ(mmio); + + /* Flush the TLB for this page */ + if (INTEL_INFO(dev)->gen >= 6) { + u32 reg = RING_INSTPM(ring->mmio_base); + I915_WRITE(reg, + _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE | + INSTPM_SYNC_FLUSH)); + if (wait_for((I915_READ(reg) & INSTPM_SYNC_FLUSH) == 0, + 1000)) + DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n", + ring->name); + } } static int @@ -1448,8 +1459,8 @@ intel_ring_alloc_seqno(struct intel_ring_buffer *ring) return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_request); } -static int __intel_ring_begin(struct intel_ring_buffer *ring, - int bytes) +static int __intel_ring_prepare(struct intel_ring_buffer *ring, + int bytes) { int ret; @@ -1465,7 +1476,6 @@ static int __intel_ring_begin(struct intel_ring_buffer *ring, return ret; } - ring->space -= bytes; return 0; } @@ -1480,12 +1490,17 @@ int intel_ring_begin(struct intel_ring_buffer *ring, if (ret) return ret; + ret = __intel_ring_prepare(ring, num_dwords * sizeof(uint32_t)); + if (ret) + return ret; + /* Preallocate the olr before touching the ring */ ret = intel_ring_alloc_seqno(ring); if (ret) return ret; - return __intel_ring_begin(ring, num_dwords * sizeof(uint32_t)); + ring->space -= num_dwords * sizeof(uint32_t); + return 0; } void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno) diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index b945bc54207..a202d8d08c5 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -921,6 +921,14 @@ intel_tv_compute_config(struct intel_encoder *encoder, DRM_DEBUG_KMS("forcing bpc to 8 for TV\n"); pipe_config->pipe_bpp = 8*3; + /* TV has it's own notion of sync and other mode flags, so clear them. */ + pipe_config->adjusted_mode.flags = 0; + + /* + * FIXME: We don't check whether the input mode is actually what we want + * or whether userspace is doing something stupid. + */ + return true; } diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index bf29b2f4d68..988911afcc8 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -198,7 +198,8 @@ struct mga_device { struct ttm_bo_device bdev; } ttm; - u32 reg_1e24; /* SE model number */ + /* SE model number stored in reg 0x1e24 */ + u32 unique_rev_id; }; diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c index 99059237da3..dafe049fb1a 100644 --- a/drivers/gpu/drm/mgag200/mgag200_main.c +++ b/drivers/gpu/drm/mgag200/mgag200_main.c @@ -176,7 +176,7 @@ static int mgag200_device_init(struct drm_device *dev, /* stash G200 SE model number for later use */ if (IS_G200_SE(mdev)) - mdev->reg_1e24 = RREG32(0x1e24); + mdev->unique_rev_id = RREG32(0x1e24); ret = mga_vram_init(mdev); if (ret) diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index ee66badc8bb..f6341e8622e 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -1008,7 +1008,7 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc, if (IS_G200_SE(mdev)) { - if (mdev->reg_1e24 >= 0x02) { + if (mdev->unique_rev_id >= 0x02) { u8 hi_pri_lvl; u32 bpp; u32 mb; @@ -1038,7 +1038,7 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc, WREG8(MGAREG_CRTCEXT_DATA, hi_pri_lvl); } else { WREG8(MGAREG_CRTCEXT_INDEX, 0x06); - if (mdev->reg_1e24 >= 0x01) + if (mdev->unique_rev_id >= 0x01) WREG8(MGAREG_CRTCEXT_DATA, 0x03); else WREG8(MGAREG_CRTCEXT_DATA, 0x04); @@ -1410,6 +1410,32 @@ static int mga_vga_get_modes(struct drm_connector *connector) return ret; } +static uint32_t mga_vga_calculate_mode_bandwidth(struct drm_display_mode *mode, + int bits_per_pixel) +{ + uint32_t total_area, divisor; + int64_t active_area, pixels_per_second, bandwidth; + uint64_t bytes_per_pixel = (bits_per_pixel + 7) / 8; + + divisor = 1024; + + if (!mode->htotal || !mode->vtotal || !mode->clock) + return 0; + + active_area = mode->hdisplay * mode->vdisplay; + total_area = mode->htotal * mode->vtotal; + + pixels_per_second = active_area * mode->clock * 1000; + do_div(pixels_per_second, total_area); + + bandwidth = pixels_per_second * bytes_per_pixel * 100; + do_div(bandwidth, divisor); + + return (uint32_t)(bandwidth); +} + +#define MODE_BANDWIDTH MODE_BAD + static int mga_vga_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { @@ -1421,7 +1447,45 @@ static int mga_vga_mode_valid(struct drm_connector *connector, int bpp = 32; int i = 0; - /* FIXME: Add bandwidth and g200se limitations */ + if (IS_G200_SE(mdev)) { + if (mdev->unique_rev_id == 0x01) { + if (mode->hdisplay > 1600) + return MODE_VIRTUAL_X; + if (mode->vdisplay > 1200) + return MODE_VIRTUAL_Y; + if (mga_vga_calculate_mode_bandwidth(mode, bpp) + > (24400 * 1024)) + return MODE_BANDWIDTH; + } else if (mdev->unique_rev_id >= 0x02) { + if (mode->hdisplay > 1920) + return MODE_VIRTUAL_X; + if (mode->vdisplay > 1200) + return MODE_VIRTUAL_Y; + if (mga_vga_calculate_mode_bandwidth(mode, bpp) + > (30100 * 1024)) + return MODE_BANDWIDTH; + } + } else if (mdev->type == G200_WB) { + if (mode->hdisplay > 1280) + return MODE_VIRTUAL_X; + if (mode->vdisplay > 1024) + return MODE_VIRTUAL_Y; + if (mga_vga_calculate_mode_bandwidth(mode, + bpp > (31877 * 1024))) + return MODE_BANDWIDTH; + } else if (mdev->type == G200_EV && + (mga_vga_calculate_mode_bandwidth(mode, bpp) + > (32700 * 1024))) { + return MODE_BANDWIDTH; + } else if (mdev->type == G200_EH && + (mga_vga_calculate_mode_bandwidth(mode, bpp) + > (37500 * 1024))) { + return MODE_BANDWIDTH; + } else if (mdev->type == G200_ER && + (mga_vga_calculate_mode_bandwidth(mode, + bpp) > (55000 * 1024))) { + return MODE_BANDWIDTH; + } if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 || mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 || diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c index 401c9891d3a..d2cb32f3c05 100644 --- a/drivers/gpu/drm/mgag200/mgag200_ttm.c +++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c @@ -347,6 +347,7 @@ int mgag200_bo_create(struct drm_device *dev, int size, int align, mgabo->gem.driver_private = NULL; mgabo->bo.bdev = &mdev->ttm.bdev; + mgabo->bo.bdev->dev_mapping = dev->dev_mapping; mgag200_ttm_placement(mgabo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM); diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c index f02fd9f443f..a66b27c0fca 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c @@ -49,18 +49,23 @@ int nv50_dac_sense(struct nv50_disp_priv *priv, int or, u32 loadval) { const u32 doff = (or * 0x800); - int load = -EINVAL; + nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80150000); nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000); + nv_wr32(priv, 0x61a00c + doff, 0x00100000 | loadval); mdelay(9); udelay(500); - nv_wr32(priv, 0x61a00c + doff, 0x80000000); - load = (nv_rd32(priv, 0x61a00c + doff) & 0x38000000) >> 27; - nv_wr32(priv, 0x61a00c + doff, 0x00000000); + loadval = nv_mask(priv, 0x61a00c + doff, 0xffffffff, 0x00000000); + nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80550000); nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000); - return load; + + nv_debug(priv, "DAC%d sense: 0x%08x\n", or, loadval); + if (!(loadval & 0x80000000)) + return -ETIMEDOUT; + + return (loadval & 0x38000000) >> 27; } int diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c index 373dbcc523b..a19e7d79b84 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c @@ -36,6 +36,8 @@ nva3_hda_eld(struct nv50_disp_priv *priv, int or, u8 *data, u32 size) if (data && data[0]) { for (i = 0; i < size; i++) nv_wr32(priv, 0x61c440 + soff, (i << 8) | data[i]); + for (; i < 0x60; i++) + nv_wr32(priv, 0x61c440 + soff, (i << 8)); nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000003); } else if (data) { diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c index dc57e24fc1d..717639386ce 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c @@ -41,6 +41,8 @@ nvd0_hda_eld(struct nv50_disp_priv *priv, int or, u8 *data, u32 size) if (data && data[0]) { for (i = 0; i < size; i++) nv_wr32(priv, 0x10ec00 + soff, (i << 8) | data[i]); + for (; i < 0x60; i++) + nv_wr32(priv, 0x10ec00 + soff, (i << 8)); nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000003); } else if (data) { diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c index f065fc248ad..db8c6fd4627 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c @@ -55,6 +55,10 @@ nva3_hdmi_ctrl(struct nv50_disp_priv *priv, int head, int or, u32 data) nv_wr32(priv, 0x61c510 + soff, 0x00000000); nv_mask(priv, 0x61c500 + soff, 0x00000001, 0x00000001); + nv_mask(priv, 0x61c5d0 + soff, 0x00070001, 0x00010001); /* SPARE, HW_CTS */ + nv_mask(priv, 0x61c568 + soff, 0x00010101, 0x00000000); /* ACR_CTRL, ?? */ + nv_mask(priv, 0x61c578 + soff, 0x80000000, 0x80000000); /* ACR_0441_ENABLE */ + /* ??? */ nv_mask(priv, 0x61733c, 0x00100000, 0x00100000); /* RESETF */ nv_mask(priv, 0x61733c, 0x10000000, 0x10000000); /* LOOKUP_EN */ diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c index 6a38402fa56..5680d3eb11c 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c @@ -1107,6 +1107,7 @@ nv50_disp_intr_unk20_2(struct nv50_disp_priv *priv, int head) u32 pclk = nv_rd32(priv, 0x610ad0 + (head * 0x540)) & 0x3fffff; u32 hval, hreg = 0x614200 + (head * 0x800); u32 oval, oreg; + u32 mask; u32 conf = exec_clkcmp(priv, head, 0xff, pclk, &outp); if (conf != ~0) { if (outp.location == 0 && outp.type == DCB_OUTPUT_DP) { @@ -1133,6 +1134,7 @@ nv50_disp_intr_unk20_2(struct nv50_disp_priv *priv, int head) oreg = 0x614280 + (ffs(outp.or) - 1) * 0x800; oval = 0x00000000; hval = 0x00000000; + mask = 0xffffffff; } else if (!outp.location) { if (outp.type == DCB_OUTPUT_DP) @@ -1140,14 +1142,16 @@ nv50_disp_intr_unk20_2(struct nv50_disp_priv *priv, int head) oreg = 0x614300 + (ffs(outp.or) - 1) * 0x800; oval = (conf & 0x0100) ? 0x00000101 : 0x00000000; hval = 0x00000000; + mask = 0x00000707; } else { oreg = 0x614380 + (ffs(outp.or) - 1) * 0x800; oval = 0x00000001; hval = 0x00000001; + mask = 0x00000707; } nv_mask(priv, hreg, 0x0000000f, hval); - nv_mask(priv, oreg, 0x00000707, oval); + nv_mask(priv, oreg, mask, oval); } } diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c index ab1e918469a..526b7524289 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c @@ -47,14 +47,8 @@ int nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size) { struct nv50_disp_priv *priv = (void *)object->engine; - struct nouveau_bios *bios = nouveau_bios(priv); - const u16 type = (mthd & NV50_DISP_SOR_MTHD_TYPE) >> 12; const u8 head = (mthd & NV50_DISP_SOR_MTHD_HEAD) >> 3; - const u8 link = (mthd & NV50_DISP_SOR_MTHD_LINK) >> 2; const u8 or = (mthd & NV50_DISP_SOR_MTHD_OR); - const u16 mask = (0x0100 << head) | (0x0040 << link) | (0x0001 << or); - struct dcb_output outp; - u8 ver, hdr; u32 data; int ret = -EINVAL; @@ -62,8 +56,6 @@ nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size) return -EINVAL; data = *(u32 *)args; - if (type && !dcb_outp_match(bios, type, mask, &ver, &hdr, &outp)) - return -ENODEV; switch (mthd & ~0x3f) { case NV50_DISP_SOR_PWR: diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h index d5502267c30..9d2cd200625 100644 --- a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h +++ b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h @@ -20,8 +20,8 @@ nouveau_mc(void *obj) return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_MC]; } -#define nouveau_mc_create(p,e,o,d) \ - nouveau_mc_create_((p), (e), (o), sizeof(**d), (void **)d) +#define nouveau_mc_create(p,e,o,m,d) \ + nouveau_mc_create_((p), (e), (o), (m), sizeof(**d), (void **)d) #define nouveau_mc_destroy(p) ({ \ struct nouveau_mc *pmc = (p); _nouveau_mc_dtor(nv_object(pmc)); \ }) @@ -33,7 +33,8 @@ nouveau_mc(void *obj) }) int nouveau_mc_create_(struct nouveau_object *, struct nouveau_object *, - struct nouveau_oclass *, int, void **); + struct nouveau_oclass *, const struct nouveau_mc_intr *, + int, void **); void _nouveau_mc_dtor(struct nouveau_object *); int _nouveau_mc_init(struct nouveau_object *); int _nouveau_mc_fini(struct nouveau_object *, bool); diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c index c434d398d16..c7bf974ed4a 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c @@ -366,13 +366,13 @@ static u16 init_script(struct nouveau_bios *bios, int index) { struct nvbios_init init = { .bios = bios }; - u16 data; + u16 bmp_ver = bmp_version(bios), data; - if (bmp_version(bios) && bmp_version(bios) < 0x0510) { - if (index > 1) + if (bmp_ver && bmp_ver < 0x0510) { + if (index > 1 || bmp_ver < 0x0100) return 0x0000; - data = bios->bmp_offset + (bios->version.major < 2 ? 14 : 18); + data = bios->bmp_offset + (bmp_ver < 0x0200 ? 14 : 18); return nv_ro16(bios, data + (index * 2)); } @@ -580,8 +580,22 @@ static void init_reserved(struct nvbios_init *init) { u8 opcode = nv_ro08(init->bios, init->offset); - trace("RESERVED\t0x%02x\n", opcode); - init->offset += 1; + u8 length, i; + + switch (opcode) { + case 0xaa: + length = 4; + break; + default: + length = 1; + break; + } + + trace("RESERVED 0x%02x\t", opcode); + for (i = 1; i < length; i++) + cont(" 0x%02x", nv_ro08(init->bios, init->offset + i)); + cont("\n"); + init->offset += length; } /** @@ -1281,7 +1295,11 @@ init_jump(struct nvbios_init *init) u16 offset = nv_ro16(bios, init->offset + 1); trace("JUMP\t0x%04x\n", offset); - init->offset = offset; + + if (init_exec(init)) + init->offset = offset; + else + init->offset += 3; } /** @@ -2136,6 +2154,7 @@ static struct nvbios_init_opcode { [0x99] = { init_zm_auxch }, [0x9a] = { init_i2c_long_if }, [0xa9] = { init_gpio_ne }, + [0xaa] = { init_reserved }, }; #define init_opcode_nr (sizeof(init_opcode) / sizeof(init_opcode[0])) diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c index 1c0330b8c9a..ec9cd6f10f9 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c @@ -80,7 +80,9 @@ _nouveau_mc_dtor(struct nouveau_object *object) int nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine, - struct nouveau_oclass *oclass, int length, void **pobject) + struct nouveau_oclass *oclass, + const struct nouveau_mc_intr *intr_map, + int length, void **pobject) { struct nouveau_device *device = nv_device(parent); struct nouveau_mc *pmc; @@ -92,6 +94,8 @@ nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine, if (ret) return ret; + pmc->intr_map = intr_map; + ret = request_irq(device->pdev->irq, nouveau_mc_intr, IRQF_SHARED, "nouveau", pmc); if (ret < 0) diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c index 8c769715227..64aa4edb0d9 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c @@ -50,12 +50,11 @@ nv04_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine, struct nv04_mc_priv *priv; int ret; - ret = nouveau_mc_create(parent, engine, oclass, &priv); + ret = nouveau_mc_create(parent, engine, oclass, nv04_mc_intr, &priv); *pobject = nv_object(priv); if (ret) return ret; - priv->base.intr_map = nv04_mc_intr; return 0; } diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c index 51919371810..d9891782bf2 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c @@ -36,12 +36,11 @@ nv44_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine, struct nv44_mc_priv *priv; int ret; - ret = nouveau_mc_create(parent, engine, oclass, &priv); + ret = nouveau_mc_create(parent, engine, oclass, nv04_mc_intr, &priv); *pobject = nv_object(priv); if (ret) return ret; - priv->base.intr_map = nv04_mc_intr; return 0; } diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c index d796924f993..732d8100344 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c @@ -52,12 +52,11 @@ nv50_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine, struct nv50_mc_priv *priv; int ret; - ret = nouveau_mc_create(parent, engine, oclass, &priv); + ret = nouveau_mc_create(parent, engine, oclass, nv50_mc_intr, &priv); *pobject = nv_object(priv); if (ret) return ret; - priv->base.intr_map = nv50_mc_intr; return 0; } diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c index e82fd21b504..0d57b4d3e00 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c @@ -54,12 +54,11 @@ nv98_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine, struct nv98_mc_priv *priv; int ret; - ret = nouveau_mc_create(parent, engine, oclass, &priv); + ret = nouveau_mc_create(parent, engine, oclass, nv98_mc_intr, &priv); *pobject = nv_object(priv); if (ret) return ret; - priv->base.intr_map = nv98_mc_intr; return 0; } diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c index 737bd4b682e..4c97cd2e7b5 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c @@ -56,12 +56,11 @@ nvc0_mc_ctor(struct nouveau_object *parent, struct nouveau_object *engine, struct nvc0_mc_priv *priv; int ret; - ret = nouveau_mc_create(parent, engine, oclass, &priv); + ret = nouveau_mc_create(parent, engine, oclass, nvc0_mc_intr, &priv); *pobject = nv_object(priv); if (ret) return ret; - priv->base.intr_map = nvc0_mc_intr; return 0; } diff --git a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c index 77c67fc970e..e66fb77131b 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c +++ b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c @@ -362,7 +362,7 @@ nouveau_vm_create(struct nouveau_vmmgr *vmm, u64 offset, u64 length, vm->fpde = offset >> (vmm->pgt_bits + 12); vm->lpde = (offset + length - 1) >> (vmm->pgt_bits + 12); - vm->pgt = kcalloc(vm->lpde - vm->fpde + 1, sizeof(*vm->pgt), GFP_KERNEL); + vm->pgt = vzalloc((vm->lpde - vm->fpde + 1) * sizeof(*vm->pgt)); if (!vm->pgt) { kfree(vm); return -ENOMEM; @@ -371,7 +371,7 @@ nouveau_vm_create(struct nouveau_vmmgr *vmm, u64 offset, u64 length, ret = nouveau_mm_init(&vm->mm, mm_offset >> 12, mm_length >> 12, block >> 12); if (ret) { - kfree(vm->pgt); + vfree(vm->pgt); kfree(vm); return ret; } @@ -446,7 +446,7 @@ nouveau_vm_del(struct nouveau_vm *vm) } nouveau_mm_fini(&vm->mm); - kfree(vm->pgt); + vfree(vm->pgt); kfree(vm); } diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 7ff10711a4d..5a5f021d586 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -788,25 +788,25 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo, struct ttm_mem_reg *old_mem, struct ttm_mem_reg *new_mem) { struct nouveau_mem *node = old_mem->mm_node; - struct nouveau_bo *nvbo = nouveau_bo(bo); u64 length = (new_mem->num_pages << PAGE_SHIFT); u64 src_offset = node->vma[0].offset; u64 dst_offset = node->vma[1].offset; + int src_tiled = !!node->memtype; + int dst_tiled = !!((struct nouveau_mem *)new_mem->mm_node)->memtype; int ret; while (length) { u32 amount, stride, height; + ret = RING_SPACE(chan, 18 + 6 * (src_tiled + dst_tiled)); + if (ret) + return ret; + amount = min(length, (u64)(4 * 1024 * 1024)); stride = 16 * 4; height = amount / stride; - if (old_mem->mem_type == TTM_PL_VRAM && - nouveau_bo_tile_layout(nvbo)) { - ret = RING_SPACE(chan, 8); - if (ret) - return ret; - + if (src_tiled) { BEGIN_NV04(chan, NvSubCopy, 0x0200, 7); OUT_RING (chan, 0); OUT_RING (chan, 0); @@ -816,19 +816,10 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo, OUT_RING (chan, 0); OUT_RING (chan, 0); } else { - ret = RING_SPACE(chan, 2); - if (ret) - return ret; - BEGIN_NV04(chan, NvSubCopy, 0x0200, 1); OUT_RING (chan, 1); } - if (new_mem->mem_type == TTM_PL_VRAM && - nouveau_bo_tile_layout(nvbo)) { - ret = RING_SPACE(chan, 8); - if (ret) - return ret; - + if (dst_tiled) { BEGIN_NV04(chan, NvSubCopy, 0x021c, 7); OUT_RING (chan, 0); OUT_RING (chan, 0); @@ -838,18 +829,10 @@ nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo, OUT_RING (chan, 0); OUT_RING (chan, 0); } else { - ret = RING_SPACE(chan, 2); - if (ret) - return ret; - BEGIN_NV04(chan, NvSubCopy, 0x021c, 1); OUT_RING (chan, 1); } - ret = RING_SPACE(chan, 14); - if (ret) - return ret; - BEGIN_NV04(chan, NvSubCopy, 0x0238, 2); OUT_RING (chan, upper_32_bits(src_offset)); OUT_RING (chan, upper_32_bits(dst_offset)); diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index b4b4d0c1f4a..5bccf31cc97 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -287,7 +287,8 @@ validate_fini_list(struct list_head *list, struct nouveau_fence *fence) list_for_each_safe(entry, tmp, list) { nvbo = list_entry(entry, struct nouveau_bo, entry); - nouveau_bo_fence(nvbo, fence); + if (likely(fence)) + nouveau_bo_fence(nvbo, fence); if (unlikely(nvbo->validate_mapped)) { ttm_bo_kunmap(&nvbo->kmap); diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c index 8e47a9bae8c..22aa9963ea6 100644 --- a/drivers/gpu/drm/nouveau/nv17_fence.c +++ b/drivers/gpu/drm/nouveau/nv17_fence.c @@ -76,7 +76,7 @@ nv17_fence_context_new(struct nouveau_channel *chan) struct ttm_mem_reg *mem = &priv->bo->bo.mem; struct nouveau_object *object; u32 start = mem->start * PAGE_SIZE; - u32 limit = mem->start + mem->size - 1; + u32 limit = start + mem->size - 1; int ret = 0; fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL); diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c index f9701e567db..0ee36384003 100644 --- a/drivers/gpu/drm/nouveau/nv50_fence.c +++ b/drivers/gpu/drm/nouveau/nv50_fence.c @@ -39,6 +39,8 @@ nv50_fence_context_new(struct nouveau_channel *chan) struct nv10_fence_chan *fctx; struct ttm_mem_reg *mem = &priv->bo->bo.mem; struct nouveau_object *object; + u32 start = mem->start * PAGE_SIZE; + u32 limit = start + mem->size - 1; int ret, i; fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL); @@ -51,26 +53,28 @@ nv50_fence_context_new(struct nouveau_channel *chan) fctx->base.sync = nv17_fence_sync; ret = nouveau_object_new(nv_object(chan->cli), chan->handle, - NvSema, 0x0002, + NvSema, 0x003d, &(struct nv_dma_class) { .flags = NV_DMA_TARGET_VRAM | NV_DMA_ACCESS_RDWR, - .start = mem->start * PAGE_SIZE, - .limit = mem->size - 1, + .start = start, + .limit = limit, }, sizeof(struct nv_dma_class), &object); /* dma objects for display sync channel semaphore blocks */ for (i = 0; !ret && i < dev->mode_config.num_crtc; i++) { struct nouveau_bo *bo = nv50_display_crtc_sema(dev, i); + u32 start = bo->bo.mem.start * PAGE_SIZE; + u32 limit = start + bo->bo.mem.size - 1; ret = nouveau_object_new(nv_object(chan->cli), chan->handle, NvEvoSema0 + i, 0x003d, &(struct nv_dma_class) { .flags = NV_DMA_TARGET_VRAM | NV_DMA_ACCESS_RDWR, - .start = bo->bo.offset, - .limit = bo->bo.offset + 0xfff, + .start = start, + .limit = limit, }, sizeof(struct nv_dma_class), &object); } diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c index b3c51275df5..7002de79e5d 100644 --- a/drivers/gpu/drm/qxl/qxl_fb.c +++ b/drivers/gpu/drm/qxl/qxl_fb.c @@ -91,7 +91,7 @@ static void qxl_fb_dirty_flush(struct fb_info *info) u32 x1, x2, y1, y2; /* TODO: hard coding 32 bpp */ - int stride = qfbdev->qfb.base.pitches[0] * 4; + int stride = qfbdev->qfb.base.pitches[0]; x1 = qfbdev->dirty.x1; x2 = qfbdev->dirty.x2; diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c index fb441a790f3..15da7ef344a 100644 --- a/drivers/gpu/drm/radeon/atom.c +++ b/drivers/gpu/drm/radeon/atom.c @@ -1222,12 +1222,17 @@ int atom_execute_table(struct atom_context *ctx, int index, uint32_t * params) int r; mutex_lock(&ctx->mutex); + /* reset data block */ + ctx->data_block = 0; /* reset reg block */ ctx->reg_block = 0; /* reset fb window */ ctx->fb_base = 0; /* reset io mode */ ctx->io_mode = ATOM_IO_MM; + /* reset divmul */ + ctx->divmul[0] = 0; + ctx->divmul[1] = 0; r = atom_execute_table_locked(ctx, index, params); mutex_unlock(&ctx->mutex); return r; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index d5df8fd1021..50684dc6ffd 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -938,11 +938,14 @@ static bool atombios_crtc_prepare_pll(struct drm_crtc *crtc, struct drm_display_ radeon_atombios_get_ppll_ss_info(rdev, &radeon_crtc->ss, ATOM_DP_SS_ID1); - } else + } else { radeon_crtc->ss_enabled = radeon_atombios_get_ppll_ss_info(rdev, &radeon_crtc->ss, ATOM_DP_SS_ID1); + } + /* disable spread spectrum on DCE3 DP */ + radeon_crtc->ss_enabled = false; } break; case ATOM_ENCODER_MODE_LVDS: @@ -1176,7 +1179,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, if ((rdev->family == CHIP_TAHITI) || (rdev->family == CHIP_PITCAIRN)) fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16); - else if (rdev->family == CHIP_VERDE) + else if ((rdev->family == CHIP_VERDE) || + (rdev->family == CHIP_OLAND) || + (rdev->family == CHIP_HAINAN)) /* for completeness. HAINAN has no display hw */ fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P4_8x16); switch (radeon_crtc->crtc_id) { @@ -1683,7 +1688,7 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc) if (pll != ATOM_PPLL_INVALID) return pll; } - } else { + } else if (!ASIC_IS_DCE41(rdev)) { /* Don't share PLLs on DCE4.1 chips */ /* use the same PPLL for all monitors with the same clock */ pll = radeon_get_shared_nondp_ppll(crtc); if (pll != ATOM_PPLL_INVALID) diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 064023bed48..16023986d30 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -44,6 +44,41 @@ static char *pre_emph_names[] = { }; /***** radeon AUX functions *****/ + +/* Atom needs data in little endian format + * so swap as appropriate when copying data to + * or from atom. Note that atom operates on + * dw units. + */ +void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le) +{ +#ifdef __BIG_ENDIAN + u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */ + u32 *dst32, *src32; + int i; + + memcpy(src_tmp, src, num_bytes); + src32 = (u32 *)src_tmp; + dst32 = (u32 *)dst_tmp; + if (to_le) { + for (i = 0; i < ((num_bytes + 3) / 4); i++) + dst32[i] = cpu_to_le32(src32[i]); + memcpy(dst, dst_tmp, num_bytes); + } else { + u8 dws = num_bytes & ~3; + for (i = 0; i < ((num_bytes + 3) / 4); i++) + dst32[i] = le32_to_cpu(src32[i]); + memcpy(dst, dst_tmp, dws); + if (num_bytes % 4) { + for (i = 0; i < (num_bytes % 4); i++) + dst[dws+i] = dst_tmp[dws+i]; + } + } +#else + memcpy(dst, src, num_bytes); +#endif +} + union aux_channel_transaction { PROCESS_AUX_CHANNEL_TRANSACTION_PS_ALLOCATION v1; PROCESS_AUX_CHANNEL_TRANSACTION_PARAMETERS_V2 v2; @@ -65,10 +100,10 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan, base = (unsigned char *)(rdev->mode_info.atom_context->scratch + 1); - memcpy(base, send, send_bytes); + radeon_atom_copy_swap(base, send, send_bytes, true); - args.v1.lpAuxRequest = 0 + 4; - args.v1.lpDataOut = 16 + 4; + args.v1.lpAuxRequest = cpu_to_le16((u16)(0 + 4)); + args.v1.lpDataOut = cpu_to_le16((u16)(16 + 4)); args.v1.ucDataOutLen = 0; args.v1.ucChannelID = chan->rec.i2c_id; args.v1.ucDelay = delay / 10; @@ -102,7 +137,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan, recv_bytes = recv_size; if (recv && recv_size) - memcpy(recv, base + 16, recv_bytes); + radeon_atom_copy_swap(recv, base + 16, recv_bytes, false); return recv_bytes; } diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 8406c8251fb..4c81e9faa63 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -186,6 +186,13 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder, u8 backlight_level; char bl_name[16]; + /* Mac laptops with multiple GPUs use the gmux driver for backlight + * so don't register a backlight device + */ + if ((rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) && + (rdev->pdev->device == 0x6741)) + return; + if (!radeon_encoder->enc_priv) return; @@ -1629,8 +1636,12 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0); atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0); atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); - /* some early dce3.2 boards have a bug in their transmitter control table */ - if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730)) + /* some dce3.x boards have a bug in their transmitter control table. + * ACTION_ENABLE_OUTPUT can probably be dropped since ACTION_ENABLE + * does the same thing and more. + */ + if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) && + (rdev->family != CHIP_RS780) && (rdev->family != CHIP_RS880)) atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0); } if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) { diff --git a/drivers/gpu/drm/radeon/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c index 082338df708..2ca389d1925 100644 --- a/drivers/gpu/drm/radeon/atombios_i2c.c +++ b/drivers/gpu/drm/radeon/atombios_i2c.c @@ -27,6 +27,8 @@ #include "radeon.h" #include "atom.h" +extern void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le); + #define TARGET_HW_I2C_CLOCK 50 /* these are a limitation of ProcessI2cChannelTransaction not the hw */ @@ -77,7 +79,7 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan, } if (!(flags & HW_I2C_WRITE)) - memcpy(buf, base, num); + radeon_atom_copy_swap(buf, base, num, false); return 0; } diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 0f89ce3d02b..93e26339051 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -1718,7 +1718,8 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev, struct drm_display_mode *mode, struct drm_display_mode *other_mode) { - u32 tmp; + u32 tmp, buffer_alloc, i; + u32 pipe_offset = radeon_crtc->crtc_id * 0x20; /* * Line Buffer Setup * There are 3 line buffers, each one shared by 2 display controllers. @@ -1741,18 +1742,34 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev, * non-linked crtcs for maximum line buffer allocation. */ if (radeon_crtc->base.enabled && mode) { - if (other_mode) + if (other_mode) { tmp = 0; /* 1/2 */ - else + buffer_alloc = 1; + } else { tmp = 2; /* whole */ - } else + buffer_alloc = 2; + } + } else { tmp = 0; + buffer_alloc = 0; + } /* second controller of the pair uses second half of the lb */ if (radeon_crtc->crtc_id % 2) tmp += 4; WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset, tmp); + if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) { + WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset, + DMIF_BUFFERS_ALLOCATED(buffer_alloc)); + for (i = 0; i < rdev->usec_timeout; i++) { + if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) & + DMIF_BUFFERS_ALLOCATED_COMPLETED) + break; + udelay(1); + } + } + if (radeon_crtc->base.enabled && mode) { switch (tmp) { case 0: @@ -2973,7 +2990,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev) rdev->config.evergreen.sx_max_export_size = 256; rdev->config.evergreen.sx_max_export_pos_size = 64; rdev->config.evergreen.sx_max_export_smx_size = 192; - rdev->config.evergreen.max_hw_contexts = 8; + rdev->config.evergreen.max_hw_contexts = 4; rdev->config.evergreen.sq_num_cf_insts = 2; rdev->config.evergreen.sc_prim_fifo_size = 0x40; @@ -3775,8 +3792,8 @@ void evergreen_disable_interrupt_state(struct radeon_device *rdev) WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); } - /* only one DAC on DCE6 */ - if (!ASIC_IS_DCE6(rdev)) + /* only one DAC on DCE5 */ + if (!ASIC_IS_DCE5(rdev)) WREG32(DACA_AUTODETECT_INT_CONTROL, 0); WREG32(DACB_AUTODETECT_INT_CONTROL, 0); @@ -4681,6 +4698,8 @@ static int evergreen_startup(struct radeon_device *rdev) /* enable pcie gen2 link */ evergreen_pcie_gen2_enable(rdev); + evergreen_mc_program(rdev); + if (ASIC_IS_DCE5(rdev)) { if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw || !rdev->mc_fw) { r = ni_init_microcode(rdev); @@ -4708,7 +4727,6 @@ static int evergreen_startup(struct radeon_device *rdev) if (r) return r; - evergreen_mc_program(rdev); if (rdev->flags & RADEON_IS_AGP) { evergreen_agp_enable(rdev); } else { @@ -4854,10 +4872,10 @@ int evergreen_resume(struct radeon_device *rdev) int evergreen_suspend(struct radeon_device *rdev) { r600_audio_fini(rdev); + r600_uvd_stop(rdev); radeon_uvd_suspend(rdev); r700_cp_stop(rdev); r600_dma_stop(rdev); - r600_uvd_rbc_stop(rdev); evergreen_irq_suspend(rdev); radeon_wb_disable(rdev); evergreen_pcie_gart_disable(rdev); @@ -4988,6 +5006,7 @@ void evergreen_fini(struct radeon_device *rdev) radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); evergreen_pcie_gart_fini(rdev); + r600_uvd_stop(rdev); radeon_uvd_fini(rdev); r600_vram_scratch_fini(rdev); radeon_gem_fini(rdev); diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index eb8ac315f92..c7cac07f139 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -967,7 +967,10 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p) if (track->cb_dirty) { tmp = track->cb_target_mask; for (i = 0; i < 8; i++) { - if ((tmp >> (i * 4)) & 0xF) { + u32 format = G_028C70_FORMAT(track->cb_color_info[i]); + + if (format != V_028C70_COLOR_INVALID && + (tmp >> (i * 4)) & 0xF) { /* at least one component is enabled */ if (track->cb_color_bo[i] == NULL) { dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n", diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index ed7c8a76809..067cc1fc48e 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -128,14 +128,7 @@ static void evergreen_hdmi_update_avi_infoframe(struct drm_encoder *encoder, struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; uint32_t offset = dig->afmt->offset; uint8_t *frame = buffer + 3; - - /* Our header values (type, version, length) should be alright, Intel - * is using the same. Checksum function also seems to be OK, it works - * fine for audio infoframe. However calculated value is always lower - * by 2 in comparison to fglrx. It breaks displaying anything in case - * of TVs that strictly check the checksum. Hack it manually here to - * workaround this issue. */ - frame[0x0] += 2; + uint8_t *header = buffer; WREG32(AFMT_AVI_INFO0 + offset, frame[0x0] | (frame[0x1] << 8) | (frame[0x2] << 16) | (frame[0x3] << 24)); @@ -144,7 +137,7 @@ static void evergreen_hdmi_update_avi_infoframe(struct drm_encoder *encoder, WREG32(AFMT_AVI_INFO2 + offset, frame[0x8] | (frame[0x9] << 8) | (frame[0xA] << 16) | (frame[0xB] << 24)); WREG32(AFMT_AVI_INFO3 + offset, - frame[0xC] | (frame[0xD] << 8)); + frame[0xC] | (frame[0xD] << 8) | (header[1] << 24)); } static void evergreen_audio_set_dto(struct drm_encoder *encoder, u32 clock) @@ -164,9 +157,9 @@ static void evergreen_audio_set_dto(struct drm_encoder *encoder, u32 clock) * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ + WREG32(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL(radeon_crtc->crtc_id)); WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100); WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100); - WREG32(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL(radeon_crtc->crtc_id)); } @@ -184,6 +177,9 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode uint32_t offset; ssize_t err; + if (!dig || !dig->afmt) + return; + /* Silent, r600_hdmi_enable will raise WARN for us */ if (!dig->afmt->enabled) return; @@ -223,8 +219,7 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode /* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */ WREG32(HDMI_ACR_PACKET_CONTROL + offset, - HDMI_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */ - HDMI_ACR_SOURCE); /* select SW CTS value */ + HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */ evergreen_hdmi_update_ACR(encoder, mode->clock); @@ -287,6 +282,9 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; + if (!dig || !dig->afmt) + return; + /* Silent, r600_hdmi_enable will raise WARN for us */ if (enable && dig->afmt->enabled) return; diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 75c05631146..150e3186bec 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -810,6 +810,10 @@ # define LATENCY_LOW_WATERMARK(x) ((x) << 0) # define LATENCY_HIGH_WATERMARK(x) ((x) << 16) +#define PIPE0_DMIF_BUFFER_CONTROL 0x0ca0 +# define DMIF_BUFFERS_ALLOCATED(x) ((x) << 0) +# define DMIF_BUFFERS_ALLOCATED_COMPLETED (1 << 4) + #define IH_RB_CNTL 0x3e00 # define IH_RB_ENABLE (1 << 0) # define IH_IB_SIZE(x) ((x) << 1) /* log2 */ @@ -1100,7 +1104,7 @@ * 6. COMMAND [29:22] | BYTE_COUNT [20:0] */ # define PACKET3_CP_DMA_DST_SEL(x) ((x) << 20) - /* 0 - SRC_ADDR + /* 0 - DST_ADDR * 1 - GDS */ # define PACKET3_CP_DMA_ENGINE(x) ((x) << 27) @@ -1115,7 +1119,7 @@ # define PACKET3_CP_DMA_CP_SYNC (1 << 31) /* COMMAND */ # define PACKET3_CP_DMA_DIS_WC (1 << 21) -# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23) +# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22) /* 0 - none * 1 - 8 in 16 * 2 - 8 in 32 diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 84583302b08..451d7886644 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -753,6 +753,10 @@ static void cayman_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x999C)) { rdev->config.cayman.max_simds_per_se = 6; rdev->config.cayman.max_backends_per_se = 2; + rdev->config.cayman.max_hw_contexts = 8; + rdev->config.cayman.sx_max_export_size = 256; + rdev->config.cayman.sx_max_export_pos_size = 64; + rdev->config.cayman.sx_max_export_smx_size = 192; } else if ((rdev->pdev->device == 0x9903) || (rdev->pdev->device == 0x9904) || (rdev->pdev->device == 0x990A) || @@ -763,6 +767,10 @@ static void cayman_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x999D)) { rdev->config.cayman.max_simds_per_se = 4; rdev->config.cayman.max_backends_per_se = 2; + rdev->config.cayman.max_hw_contexts = 8; + rdev->config.cayman.sx_max_export_size = 256; + rdev->config.cayman.sx_max_export_pos_size = 64; + rdev->config.cayman.sx_max_export_smx_size = 192; } else if ((rdev->pdev->device == 0x9919) || (rdev->pdev->device == 0x9990) || (rdev->pdev->device == 0x9991) || @@ -773,9 +781,17 @@ static void cayman_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x99A0)) { rdev->config.cayman.max_simds_per_se = 3; rdev->config.cayman.max_backends_per_se = 1; + rdev->config.cayman.max_hw_contexts = 4; + rdev->config.cayman.sx_max_export_size = 128; + rdev->config.cayman.sx_max_export_pos_size = 32; + rdev->config.cayman.sx_max_export_smx_size = 96; } else { rdev->config.cayman.max_simds_per_se = 2; rdev->config.cayman.max_backends_per_se = 1; + rdev->config.cayman.max_hw_contexts = 4; + rdev->config.cayman.sx_max_export_size = 128; + rdev->config.cayman.sx_max_export_pos_size = 32; + rdev->config.cayman.sx_max_export_smx_size = 96; } rdev->config.cayman.max_texture_channel_caches = 2; rdev->config.cayman.max_gprs = 256; @@ -783,10 +799,6 @@ static void cayman_gpu_init(struct radeon_device *rdev) rdev->config.cayman.max_gs_threads = 32; rdev->config.cayman.max_stack_entries = 512; rdev->config.cayman.sx_num_of_sets = 8; - rdev->config.cayman.sx_max_export_size = 256; - rdev->config.cayman.sx_max_export_pos_size = 64; - rdev->config.cayman.sx_max_export_smx_size = 192; - rdev->config.cayman.max_hw_contexts = 8; rdev->config.cayman.sq_num_cf_insts = 2; rdev->config.cayman.sc_prim_fifo_size = 0x40; @@ -1166,13 +1178,12 @@ void cayman_fence_ring_emit(struct radeon_device *rdev, { struct radeon_ring *ring = &rdev->ring[fence->ring]; u64 addr = rdev->fence_drv[fence->ring].gpu_addr; + u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA | + PACKET3_SH_ACTION_ENA; /* flush read cache over gart for this vmid */ - radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1)); - radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2); - radeon_ring_write(ring, 0); radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3)); - radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA); + radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl); radeon_ring_write(ring, 0xFFFFFFFF); radeon_ring_write(ring, 0); radeon_ring_write(ring, 10); /* poll interval */ @@ -1188,6 +1199,8 @@ void cayman_fence_ring_emit(struct radeon_device *rdev, void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) { struct radeon_ring *ring = &rdev->ring[ib->ring]; + u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA | + PACKET3_SH_ACTION_ENA; /* set to DX10/11 mode */ radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0)); @@ -1212,14 +1225,11 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) (ib->vm ? (ib->vm->id << 24) : 0)); /* flush read cache over gart for this vmid */ - radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1)); - radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2); - radeon_ring_write(ring, ib->vm ? ib->vm->id : 0); radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3)); - radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA); + radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl); radeon_ring_write(ring, 0xFFFFFFFF); radeon_ring_write(ring, 0); - radeon_ring_write(ring, 10); /* poll interval */ + radeon_ring_write(ring, ((ib->vm ? ib->vm->id : 0) << 24) | 10); /* poll interval */ } void cayman_uvd_semaphore_emit(struct radeon_device *rdev, @@ -1929,6 +1939,8 @@ static int cayman_startup(struct radeon_device *rdev) /* enable pcie gen2 link */ evergreen_pcie_gen2_enable(rdev); + evergreen_mc_program(rdev); + if (rdev->flags & RADEON_IS_IGP) { if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) { r = ni_init_microcode(rdev); @@ -1957,7 +1969,6 @@ static int cayman_startup(struct radeon_device *rdev) if (r) return r; - evergreen_mc_program(rdev); r = cayman_pcie_gart_enable(rdev); if (r) return r; @@ -2133,7 +2144,7 @@ int cayman_suspend(struct radeon_device *rdev) radeon_vm_manager_fini(rdev); cayman_cp_enable(rdev, false); cayman_dma_stop(rdev); - r600_uvd_rbc_stop(rdev); + r600_uvd_stop(rdev); radeon_uvd_suspend(rdev); evergreen_irq_suspend(rdev); radeon_wb_disable(rdev); @@ -2265,6 +2276,7 @@ void cayman_fini(struct radeon_device *rdev) radeon_vm_manager_fini(rdev); radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); + r600_uvd_stop(rdev); radeon_uvd_fini(rdev); cayman_pcie_gart_fini(rdev); r600_vram_scratch_fini(rdev); diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h index e226faf16fe..e49f7b45603 100644 --- a/drivers/gpu/drm/radeon/nid.h +++ b/drivers/gpu/drm/radeon/nid.h @@ -573,6 +573,7 @@ # define PACKET3_DB_ACTION_ENA (1 << 26) # define PACKET3_SH_ACTION_ENA (1 << 27) # define PACKET3_SX_ACTION_ENA (1 << 28) +# define PACKET3_ENGINE_ME (1 << 31) #define PACKET3_ME_INITIALIZE 0x44 #define PACKET3_ME_INITIALIZE_DEVICE_ID(x) ((x) << 16) #define PACKET3_COND_WRITE 0x45 diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index d0314ecbd7c..46470dd7c71 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -2935,9 +2935,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data) seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp); seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw); seq_printf(m, "%u dwords in ring\n", count); - for (j = 0; j <= count; j++) { - i = (rdp + j) & ring->ptr_mask; - seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]); + if (ring->ready) { + for (j = 0; j <= count; j++) { + i = (rdp + j) & ring->ptr_mask; + seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]); + } } return 0; } diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 6948eb88c2b..4cf21ec1abe 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -2675,12 +2675,29 @@ int r600_uvd_rbc_start(struct radeon_device *rdev) return 0; } -void r600_uvd_rbc_stop(struct radeon_device *rdev) +void r600_uvd_stop(struct radeon_device *rdev) { struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX]; /* force RBC into idle state */ WREG32(UVD_RBC_RB_CNTL, 0x11010101); + + /* Stall UMC and register bus before resetting VCPU */ + WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8)); + WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3)); + mdelay(1); + + /* put VCPU into reset */ + WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET); + mdelay(5); + + /* disable VCPU clock */ + WREG32(UVD_VCPU_CNTL, 0x0); + + /* Unstall UMC and register bus */ + WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8)); + WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3)); + ring->ready = false; } @@ -2700,6 +2717,11 @@ int r600_uvd_init(struct radeon_device *rdev) /* disable interupt */ WREG32_P(UVD_MASTINT_EN, 0, ~(1 << 1)); + /* Stall UMC and register bus before resetting VCPU */ + WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8)); + WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3)); + mdelay(1); + /* put LMI, VCPU, RBC etc... into reset */ WREG32(UVD_SOFT_RESET, LMI_SOFT_RESET | VCPU_SOFT_RESET | LBSI_SOFT_RESET | RBC_SOFT_RESET | CSM_SOFT_RESET | @@ -2729,10 +2751,6 @@ int r600_uvd_init(struct radeon_device *rdev) WREG32(UVD_MPC_SET_ALU, 0); WREG32(UVD_MPC_SET_MUX, 0x88); - /* Stall UMC */ - WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8)); - WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3)); - /* take all subblocks out of reset, except VCPU */ WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET); mdelay(5); @@ -2939,14 +2957,17 @@ void r600_fence_ring_emit(struct radeon_device *rdev, struct radeon_fence *fence) { struct radeon_ring *ring = &rdev->ring[fence->ring]; + u32 cp_coher_cntl = PACKET3_TC_ACTION_ENA | PACKET3_VC_ACTION_ENA | + PACKET3_SH_ACTION_ENA; + + if (rdev->family >= CHIP_RV770) + cp_coher_cntl |= PACKET3_FULL_CACHE_ENA; if (rdev->wb.use_event) { u64 addr = rdev->fence_drv[fence->ring].gpu_addr; /* flush read cache over gart */ radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3)); - radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | - PACKET3_VC_ACTION_ENA | - PACKET3_SH_ACTION_ENA); + radeon_ring_write(ring, cp_coher_cntl); radeon_ring_write(ring, 0xFFFFFFFF); radeon_ring_write(ring, 0); radeon_ring_write(ring, 10); /* poll interval */ @@ -2960,9 +2981,7 @@ void r600_fence_ring_emit(struct radeon_device *rdev, } else { /* flush read cache over gart */ radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3)); - radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | - PACKET3_VC_ACTION_ENA | - PACKET3_SH_ACTION_ENA); + radeon_ring_write(ring, cp_coher_cntl); radeon_ring_write(ring, 0xFFFFFFFF); radeon_ring_write(ring, 0); radeon_ring_write(ring, 10); /* poll interval */ @@ -2986,7 +3005,7 @@ void r600_uvd_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence) { struct radeon_ring *ring = &rdev->ring[fence->ring]; - uint32_t addr = rdev->fence_drv[fence->ring].gpu_addr; + uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr; radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0)); radeon_ring_write(ring, fence->seq); @@ -3206,6 +3225,8 @@ static int r600_startup(struct radeon_device *rdev) /* enable pcie gen2 link */ r600_pcie_gen2_enable(rdev); + r600_mc_program(rdev); + if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) { r = r600_init_microcode(rdev); if (r) { @@ -3218,7 +3239,6 @@ static int r600_startup(struct radeon_device *rdev) if (r) return r; - r600_mc_program(rdev); if (rdev->flags & RADEON_IS_AGP) { r600_agp_enable(rdev); } else { @@ -4489,6 +4509,10 @@ restart_ih: break; } break; + case 124: /* UVD */ + DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data); + radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX); + break; case 176: /* CP_INT in ring buffer */ case 177: /* CP_INT in IB1 */ case 178: /* CP_INT in IB2 */ diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 01a3ec83f28..745e66eacd4 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -749,7 +749,10 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) } for (i = 0; i < 8; i++) { - if ((tmp >> (i * 4)) & 0xF) { + u32 format = G_0280A0_FORMAT(track->cb_color_info[i]); + + if (format != V_0280A0_COLOR_INVALID && + (tmp >> (i * 4)) & 0xF) { /* at least one component is enabled */ if (track->cb_color_bo[i] == NULL) { dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n", diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c index 456750a0daa..5df71165904 100644 --- a/drivers/gpu/drm/radeon/r600_hdmi.c +++ b/drivers/gpu/drm/radeon/r600_hdmi.c @@ -24,6 +24,7 @@ * Authors: Christian König */ #include <linux/hdmi.h> +#include <linux/gcd.h> #include <drm/drmP.h> #include <drm/radeon_drm.h> #include "radeon.h" @@ -57,28 +58,57 @@ enum r600_hdmi_iec_status_bits { static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = { /* 32kHz 44.1kHz 48kHz */ /* Clock N CTS N CTS N CTS */ - { 25174, 4576, 28125, 7007, 31250, 6864, 28125 }, /* 25,20/1.001 MHz */ + { 25175, 4096, 25175, 28224, 125875, 6144, 25175 }, /* 25,20/1.001 MHz */ { 25200, 4096, 25200, 6272, 28000, 6144, 25200 }, /* 25.20 MHz */ { 27000, 4096, 27000, 6272, 30000, 6144, 27000 }, /* 27.00 MHz */ { 27027, 4096, 27027, 6272, 30030, 6144, 27027 }, /* 27.00*1.001 MHz */ { 54000, 4096, 54000, 6272, 60000, 6144, 54000 }, /* 54.00 MHz */ { 54054, 4096, 54054, 6272, 60060, 6144, 54054 }, /* 54.00*1.001 MHz */ - { 74175, 11648, 210937, 17836, 234375, 11648, 140625 }, /* 74.25/1.001 MHz */ + { 74176, 4096, 74176, 5733, 75335, 6144, 74176 }, /* 74.25/1.001 MHz */ { 74250, 4096, 74250, 6272, 82500, 6144, 74250 }, /* 74.25 MHz */ - { 148351, 11648, 421875, 8918, 234375, 5824, 140625 }, /* 148.50/1.001 MHz */ + { 148352, 4096, 148352, 5733, 150670, 6144, 148352 }, /* 148.50/1.001 MHz */ { 148500, 4096, 148500, 6272, 165000, 6144, 148500 }, /* 148.50 MHz */ - { 0, 4096, 0, 6272, 0, 6144, 0 } /* Other */ }; + /* - * calculate CTS value if it's not found in the table + * calculate CTS and N values if they are not found in the table */ -static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq) +static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int *N, int freq) { - if (*CTS == 0) - *CTS = clock * N / (128 * freq) * 1000; - DRM_DEBUG("Using ACR timing N=%d CTS=%d for frequency %d\n", - N, *CTS, freq); + int n, cts; + unsigned long div, mul; + + /* Safe, but overly large values */ + n = 128 * freq; + cts = clock * 1000; + + /* Smallest valid fraction */ + div = gcd(n, cts); + + n /= div; + cts /= div; + + /* + * The optimal N is 128*freq/1000. Calculate the closest larger + * value that doesn't truncate any bits. + */ + mul = ((128*freq/1000) + (n-1))/n; + + n *= mul; + cts *= mul; + + /* Check that we are in spec (not always possible) */ + if (n < (128*freq/1500)) + printk(KERN_WARNING "Calculated ACR N value is too small. You may experience audio problems.\n"); + if (n > (128*freq/300)) + printk(KERN_WARNING "Calculated ACR N value is too large. You may experience audio problems.\n"); + + *N = n; + *CTS = cts; + + DRM_DEBUG("Calculated ACR timing N=%d CTS=%d for frequency %d\n", + *N, *CTS, freq); } struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock) @@ -86,15 +116,16 @@ struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock) struct radeon_hdmi_acr res; u8 i; - for (i = 0; r600_hdmi_predefined_acr[i].clock != clock && - r600_hdmi_predefined_acr[i].clock != 0; i++) - ; - res = r600_hdmi_predefined_acr[i]; + /* Precalculated values for common clocks */ + for (i = 0; i < ARRAY_SIZE(r600_hdmi_predefined_acr); i++) { + if (r600_hdmi_predefined_acr[i].clock == clock) + return r600_hdmi_predefined_acr[i]; + } - /* In case some CTS are missing */ - r600_hdmi_calc_cts(clock, &res.cts_32khz, res.n_32khz, 32000); - r600_hdmi_calc_cts(clock, &res.cts_44_1khz, res.n_44_1khz, 44100); - r600_hdmi_calc_cts(clock, &res.cts_48khz, res.n_48khz, 48000); + /* And odd clocks get manually calculated */ + r600_hdmi_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000); + r600_hdmi_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100); + r600_hdmi_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000); return res; } @@ -133,14 +164,7 @@ static void r600_hdmi_update_avi_infoframe(struct drm_encoder *encoder, struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; uint32_t offset = dig->afmt->offset; uint8_t *frame = buffer + 3; - - /* Our header values (type, version, length) should be alright, Intel - * is using the same. Checksum function also seems to be OK, it works - * fine for audio infoframe. However calculated value is always lower - * by 2 in comparison to fglrx. It breaks displaying anything in case - * of TVs that strictly check the checksum. Hack it manually here to - * workaround this issue. */ - frame[0x0] += 2; + uint8_t *header = buffer; WREG32(HDMI0_AVI_INFO0 + offset, frame[0x0] | (frame[0x1] << 8) | (frame[0x2] << 16) | (frame[0x3] << 24)); @@ -149,7 +173,7 @@ static void r600_hdmi_update_avi_infoframe(struct drm_encoder *encoder, WREG32(HDMI0_AVI_INFO2 + offset, frame[0x8] | (frame[0x9] << 8) | (frame[0xA] << 16) | (frame[0xB] << 24)); WREG32(HDMI0_AVI_INFO3 + offset, - frame[0xC] | (frame[0xD] << 8)); + frame[0xC] | (frame[0xD] << 8) | (header[1] << 24)); } /* @@ -245,17 +269,29 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock) * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ - if (ASIC_IS_DCE3(rdev)) { + if (ASIC_IS_DCE32(rdev)) { + if (dig->dig_encoder == 0) { + WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100); + WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100); + WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */ + } else { + WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100); + WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100); + WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */ + } + } else { /* according to the reg specs, this should DCE3.2 only, but in - * practice it seems to cover DCE3.0 as well. + * practice it seems to cover DCE2.0/3.0/3.1 as well. */ - WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100); - WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100); - WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */ - } else { - /* according to the reg specs, this should be DCE2.0 and DCE3.0 */ - WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) | - AUDIO_DTO_MODULE(clock / 10)); + if (dig->dig_encoder == 0) { + WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100); + WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100); + WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */ + } else { + WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100); + WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100); + WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */ + } } } @@ -273,6 +309,9 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod uint32_t offset; ssize_t err; + if (!dig || !dig->afmt) + return; + /* Silent, r600_hdmi_enable will raise WARN for us */ if (!dig->afmt->enabled) return; @@ -301,8 +340,8 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod } WREG32(HDMI0_ACR_PACKET_CONTROL + offset, - HDMI0_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */ - HDMI0_ACR_SOURCE); /* select SW CTS value */ + HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */ + HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */ WREG32(HDMI0_VBI_PACKET_CONTROL + offset, HDMI0_NULL_SEND | /* send null packets when required */ @@ -455,6 +494,9 @@ void r600_hdmi_enable(struct drm_encoder *encoder, bool enable) struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; u32 hdmi = HDMI0_ERROR_ACK; + if (!dig || !dig->afmt) + return; + /* Silent, r600_hdmi_enable will raise WARN for us */ if (enable && dig->afmt->enabled) return; diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h index 79df558f8c4..eb28716e87f 100644 --- a/drivers/gpu/drm/radeon/r600d.h +++ b/drivers/gpu/drm/radeon/r600d.h @@ -1259,7 +1259,7 @@ */ # define PACKET3_CP_DMA_CP_SYNC (1 << 31) /* COMMAND */ -# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23) +# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22) /* 0 - none * 1 - 8 in 16 * 2 - 8 in 32 @@ -1283,6 +1283,7 @@ # define PACKET3_CP_DMA_CMD_DAIC (1 << 29) #define PACKET3_SURFACE_SYNC 0x43 # define PACKET3_CB0_DEST_BASE_ENA (1 << 6) +# define PACKET3_FULL_CACHE_ENA (1 << 20) /* r7xx+ only */ # define PACKET3_TC_ACTION_ENA (1 << 23) # define PACKET3_VC_ACTION_ENA (1 << 24) # define PACKET3_CB_ACTION_ENA (1 << 25) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 142ce6cc69f..d4ff48ce1d8 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -408,6 +408,7 @@ struct radeon_sa_manager { uint64_t gpu_addr; void *cpu_ptr; uint32_t domain; + uint32_t align; }; struct radeon_sa_bo; @@ -1144,6 +1145,7 @@ struct radeon_uvd { struct radeon_bo *vcpu_bo; void *cpu_addr; uint64_t gpu_addr; + void *saved_bo; atomic_t handles[RADEON_MAX_UVD_HANDLES]; struct drm_file *filp[RADEON_MAX_UVD_HANDLES]; struct delayed_work idle_work; @@ -1762,7 +1764,7 @@ void r100_io_wreg(struct radeon_device *rdev, u32 reg, u32 v); WREG32(reg, tmp_); \ } while (0) #define WREG32_AND(reg, and) WREG32_P(reg, 0, and) -#define WREG32_OR(reg, or) WREG32_P(reg, or, ~or) +#define WREG32_OR(reg, or) WREG32_P(reg, or, ~(or)) #define WREG32_PLL_P(reg, val, mask) \ do { \ uint32_t tmp_ = RREG32_PLL(reg); \ diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index a2802b47ee9..de36c472242 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -986,8 +986,8 @@ static struct radeon_asic r600_asic = { .blit_ring_index = RADEON_RING_TYPE_GFX_INDEX, .dma = &r600_copy_dma, .dma_ring_index = R600_RING_TYPE_DMA_INDEX, - .copy = &r600_copy_dma, - .copy_ring_index = R600_RING_TYPE_DMA_INDEX, + .copy = &r600_copy_blit, + .copy_ring_index = RADEON_RING_TYPE_GFX_INDEX, }, .surface = { .set_reg = r600_set_surface_reg, @@ -1074,8 +1074,8 @@ static struct radeon_asic rs780_asic = { .blit_ring_index = RADEON_RING_TYPE_GFX_INDEX, .dma = &r600_copy_dma, .dma_ring_index = R600_RING_TYPE_DMA_INDEX, - .copy = &r600_copy_dma, - .copy_ring_index = R600_RING_TYPE_DMA_INDEX, + .copy = &r600_copy_blit, + .copy_ring_index = RADEON_RING_TYPE_GFX_INDEX, }, .surface = { .set_reg = r600_set_surface_reg, diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index a72759ede75..34223fc3d82 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -399,7 +399,7 @@ uint64_t r600_get_gpu_clock_counter(struct radeon_device *rdev); /* uvd */ int r600_uvd_init(struct radeon_device *rdev); int r600_uvd_rbc_start(struct radeon_device *rdev); -void r600_uvd_rbc_stop(struct radeon_device *rdev); +void r600_uvd_stop(struct radeon_device *rdev); int r600_uvd_ib_test(struct radeon_device *rdev, struct radeon_ring *ring); void r600_uvd_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence); diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index dea6f63c972..efb06e34aed 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -715,13 +715,16 @@ bool radeon_get_atom_connector_info_from_object_table(struct drm_device *dev) (ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT *) (ctx->bios + data_offset + le16_to_cpu(router_obj->asObjects[k].usSrcDstTableOffset)); + u8 *num_dst_objs = (u8 *) + ((u8 *)router_src_dst_table + 1 + + (router_src_dst_table->ucNumberOfSrc * 2)); + u16 *dst_objs = (u16 *)(num_dst_objs + 1); int enum_id; router.router_id = router_obj_id; - for (enum_id = 0; enum_id < router_src_dst_table->ucNumberOfDst; - enum_id++) { + for (enum_id = 0; enum_id < (*num_dst_objs); enum_id++) { if (le16_to_cpu(path->usConnObjectId) == - le16_to_cpu(router_src_dst_table->usDstObjectID[enum_id])) + le16_to_cpu(dst_objs[enum_id])) break; } @@ -1651,7 +1654,9 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct kfree(edid); } } - record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD); + record += fake_edid_record->ucFakeEDIDLength ? + fake_edid_record->ucFakeEDIDLength + 2 : + sizeof(ATOM_FAKE_EDID_PATCH_RECORD); break; case LCD_PANEL_RESOLUTION_RECORD_TYPE: panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; @@ -2921,6 +2926,10 @@ void radeon_atom_initialize_bios_scratch_regs(struct drm_device *dev) /* tell the bios not to handle mode switching */ bios_6_scratch |= ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH; + /* clear the vbios dpms state */ + if (ASIC_IS_DCE4(rdev)) + bios_2_scratch &= ~ATOM_S2_DEVICE_DPMS_STATE; + if (rdev->family >= CHIP_R600) { WREG32(R600_BIOS_2_SCRATCH, bios_2_scratch); WREG32(R600_BIOS_6_SCRATCH, bios_6_scratch); diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 78edadc9e86..68ce3605601 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -147,7 +147,7 @@ static uint16_t combios_get_table_offset(struct drm_device *dev, enum radeon_combios_table_offset table) { struct radeon_device *rdev = dev->dev_private; - int rev; + int rev, size; uint16_t offset = 0, check_offset; if (!rdev->bios) @@ -156,174 +156,106 @@ static uint16_t combios_get_table_offset(struct drm_device *dev, switch (table) { /* absolute offset tables */ case COMBIOS_ASIC_INIT_1_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0xc); - if (check_offset) - offset = check_offset; + check_offset = 0xc; break; case COMBIOS_BIOS_SUPPORT_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x14); - if (check_offset) - offset = check_offset; + check_offset = 0x14; break; case COMBIOS_DAC_PROGRAMMING_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x2a); - if (check_offset) - offset = check_offset; + check_offset = 0x2a; break; case COMBIOS_MAX_COLOR_DEPTH_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x2c); - if (check_offset) - offset = check_offset; + check_offset = 0x2c; break; case COMBIOS_CRTC_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x2e); - if (check_offset) - offset = check_offset; + check_offset = 0x2e; break; case COMBIOS_PLL_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x30); - if (check_offset) - offset = check_offset; + check_offset = 0x30; break; case COMBIOS_TV_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x32); - if (check_offset) - offset = check_offset; + check_offset = 0x32; break; case COMBIOS_DFP_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x34); - if (check_offset) - offset = check_offset; + check_offset = 0x34; break; case COMBIOS_HW_CONFIG_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x36); - if (check_offset) - offset = check_offset; + check_offset = 0x36; break; case COMBIOS_MULTIMEDIA_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x38); - if (check_offset) - offset = check_offset; + check_offset = 0x38; break; case COMBIOS_TV_STD_PATCH_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x3e); - if (check_offset) - offset = check_offset; + check_offset = 0x3e; break; case COMBIOS_LCD_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x40); - if (check_offset) - offset = check_offset; + check_offset = 0x40; break; case COMBIOS_MOBILE_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x42); - if (check_offset) - offset = check_offset; + check_offset = 0x42; break; case COMBIOS_PLL_INIT_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x46); - if (check_offset) - offset = check_offset; + check_offset = 0x46; break; case COMBIOS_MEM_CONFIG_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x48); - if (check_offset) - offset = check_offset; + check_offset = 0x48; break; case COMBIOS_SAVE_MASK_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x4a); - if (check_offset) - offset = check_offset; + check_offset = 0x4a; break; case COMBIOS_HARDCODED_EDID_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x4c); - if (check_offset) - offset = check_offset; + check_offset = 0x4c; break; case COMBIOS_ASIC_INIT_2_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x4e); - if (check_offset) - offset = check_offset; + check_offset = 0x4e; break; case COMBIOS_CONNECTOR_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x50); - if (check_offset) - offset = check_offset; + check_offset = 0x50; break; case COMBIOS_DYN_CLK_1_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x52); - if (check_offset) - offset = check_offset; + check_offset = 0x52; break; case COMBIOS_RESERVED_MEM_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x54); - if (check_offset) - offset = check_offset; + check_offset = 0x54; break; case COMBIOS_EXT_TMDS_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x58); - if (check_offset) - offset = check_offset; + check_offset = 0x58; break; case COMBIOS_MEM_CLK_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x5a); - if (check_offset) - offset = check_offset; + check_offset = 0x5a; break; case COMBIOS_EXT_DAC_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x5c); - if (check_offset) - offset = check_offset; + check_offset = 0x5c; break; case COMBIOS_MISC_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x5e); - if (check_offset) - offset = check_offset; + check_offset = 0x5e; break; case COMBIOS_CRT_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x60); - if (check_offset) - offset = check_offset; + check_offset = 0x60; break; case COMBIOS_INTEGRATED_SYSTEM_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x62); - if (check_offset) - offset = check_offset; + check_offset = 0x62; break; case COMBIOS_COMPONENT_VIDEO_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x64); - if (check_offset) - offset = check_offset; + check_offset = 0x64; break; case COMBIOS_FAN_SPEED_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x66); - if (check_offset) - offset = check_offset; + check_offset = 0x66; break; case COMBIOS_OVERDRIVE_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x68); - if (check_offset) - offset = check_offset; + check_offset = 0x68; break; case COMBIOS_OEM_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x6a); - if (check_offset) - offset = check_offset; + check_offset = 0x6a; break; case COMBIOS_DYN_CLK_2_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x6c); - if (check_offset) - offset = check_offset; + check_offset = 0x6c; break; case COMBIOS_POWER_CONNECTOR_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x6e); - if (check_offset) - offset = check_offset; + check_offset = 0x6e; break; case COMBIOS_I2C_INFO_TABLE: - check_offset = RBIOS16(rdev->bios_header_start + 0x70); - if (check_offset) - offset = check_offset; + check_offset = 0x70; break; /* relative offset tables */ case COMBIOS_ASIC_INIT_3_TABLE: /* offset from misc info */ @@ -439,11 +371,16 @@ static uint16_t combios_get_table_offset(struct drm_device *dev, } break; default: + check_offset = 0; break; } - return offset; + size = RBIOS8(rdev->bios_header_start + 0x6); + /* check absolute offset tables */ + if (table < COMBIOS_ASIC_INIT_3_TABLE && check_offset && check_offset < size) + offset = RBIOS16(rdev->bios_header_start + check_offset); + return offset; } bool radeon_combios_check_hardcoded_edid(struct radeon_device *rdev) @@ -965,16 +902,22 @@ struct radeon_encoder_primary_dac *radeon_combios_get_primary_dac_info(struct dac = RBIOS8(dac_info + 0x3) & 0xf; p_dac->ps2_pdac_adj = (bg << 8) | (dac); } - /* if the values are all zeros, use the table */ - if (p_dac->ps2_pdac_adj) + /* if the values are zeros, use the table */ + if ((dac == 0) || (bg == 0)) + found = 0; + else found = 1; } /* quirks */ + /* Radeon 7000 (RV100) */ + if (((dev->pdev->device == 0x5159) && + (dev->pdev->subsystem_vendor == 0x174B) && + (dev->pdev->subsystem_device == 0x7c28)) || /* Radeon 9100 (R200) */ - if ((dev->pdev->device == 0x514D) && + ((dev->pdev->device == 0x514D) && (dev->pdev->subsystem_vendor == 0x174B) && - (dev->pdev->subsystem_device == 0x7149)) { + (dev->pdev->subsystem_device == 0x7149))) { /* vbios value is bad, use the default */ found = 0; } diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 2399f25ec03..5a87c9fc78d 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1489,6 +1489,24 @@ static const struct drm_connector_funcs radeon_dp_connector_funcs = { .force = radeon_dvi_force, }; +static const struct drm_connector_funcs radeon_edp_connector_funcs = { + .dpms = drm_helper_connector_dpms, + .detect = radeon_dp_detect, + .fill_modes = drm_helper_probe_single_connector_modes, + .set_property = radeon_lvds_set_property, + .destroy = radeon_dp_connector_destroy, + .force = radeon_dvi_force, +}; + +static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = { + .dpms = drm_helper_connector_dpms, + .detect = radeon_dp_detect, + .fill_modes = drm_helper_probe_single_connector_modes, + .set_property = radeon_lvds_set_property, + .destroy = radeon_dp_connector_destroy, + .force = radeon_dvi_force, +}; + void radeon_add_atom_connector(struct drm_device *dev, uint32_t connector_id, @@ -1580,8 +1598,6 @@ radeon_add_atom_connector(struct drm_device *dev, goto failed; radeon_dig_connector->igp_lane_info = igp_lane_info; radeon_connector->con_priv = radeon_dig_connector; - drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type); - drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs); if (i2c_bus->valid) { /* add DP i2c bus */ if (connector_type == DRM_MODE_CONNECTOR_eDP) @@ -1598,6 +1614,10 @@ radeon_add_atom_connector(struct drm_device *dev, case DRM_MODE_CONNECTOR_VGA: case DRM_MODE_CONNECTOR_DVIA: default: + drm_connector_init(dev, &radeon_connector->base, + &radeon_dp_connector_funcs, connector_type); + drm_connector_helper_add(&radeon_connector->base, + &radeon_dp_connector_helper_funcs); connector->interlace_allowed = true; connector->doublescan_allowed = true; radeon_connector->dac_load_detect = true; @@ -1610,6 +1630,10 @@ radeon_add_atom_connector(struct drm_device *dev, case DRM_MODE_CONNECTOR_HDMIA: case DRM_MODE_CONNECTOR_HDMIB: case DRM_MODE_CONNECTOR_DisplayPort: + drm_connector_init(dev, &radeon_connector->base, + &radeon_dp_connector_funcs, connector_type); + drm_connector_helper_add(&radeon_connector->base, + &radeon_dp_connector_helper_funcs); drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.underscan_property, UNDERSCAN_OFF); @@ -1634,6 +1658,10 @@ radeon_add_atom_connector(struct drm_device *dev, break; case DRM_MODE_CONNECTOR_LVDS: case DRM_MODE_CONNECTOR_eDP: + drm_connector_init(dev, &radeon_connector->base, + &radeon_lvds_bridge_connector_funcs, connector_type); + drm_connector_helper_add(&radeon_connector->base, + &radeon_dp_connector_helper_funcs); drm_object_attach_property(&radeon_connector->base.base, dev->mode_config.scaling_mode_property, DRM_MODE_SCALE_FULLSCREEN); @@ -1797,7 +1825,7 @@ radeon_add_atom_connector(struct drm_device *dev, goto failed; radeon_dig_connector->igp_lane_info = igp_lane_info; radeon_connector->con_priv = radeon_dig_connector; - drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type); + drm_connector_init(dev, &radeon_connector->base, &radeon_edp_connector_funcs, connector_type); drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs); if (i2c_bus->valid) { /* add DP i2c bus */ diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 7e265a58141..fe36f1d9496 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -80,9 +80,11 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) p->relocs[i].lobj.bo = p->relocs[i].robj; p->relocs[i].lobj.written = !!r->write_domain; - /* the first reloc of an UVD job is the - msg and that must be in VRAM */ - if (p->ring == R600_RING_TYPE_UVD_INDEX && i == 0) { + /* the first reloc of an UVD job is the msg and that must be in + VRAM, also but everything into VRAM on AGP cards to avoid + image corruptions */ + if (p->ring == R600_RING_TYPE_UVD_INDEX && + (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) { /* TODO: is this still needed for NI+ ? */ p->relocs[i].lobj.domain = RADEON_GEM_DOMAIN_VRAM; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index b0dc0b6cb4e..8df1525f71d 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1196,13 +1196,22 @@ int radeon_device_init(struct radeon_device *rdev, return r; } if ((radeon_testing & 1)) { - radeon_test_moves(rdev); + if (rdev->accel_working) + radeon_test_moves(rdev); + else + DRM_INFO("radeon: acceleration disabled, skipping move tests\n"); } if ((radeon_testing & 2)) { - radeon_test_syncing(rdev); + if (rdev->accel_working) + radeon_test_syncing(rdev); + else + DRM_INFO("radeon: acceleration disabled, skipping sync tests\n"); } if (radeon_benchmarking) { - radeon_benchmark(rdev, radeon_benchmarking); + if (rdev->accel_working) + radeon_benchmark(rdev, radeon_benchmarking); + else + DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n"); } return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index 43ec4a401f0..2915a1c5693 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -467,6 +467,7 @@ int radeon_vm_manager_init(struct radeon_device *rdev) size *= 2; r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager, RADEON_GPU_PAGE_ALIGN(size), + RADEON_GPU_PAGE_SIZE, RADEON_GEM_DOMAIN_VRAM); if (r) { dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n", @@ -1156,6 +1157,8 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev, return -ENOMEM; r = radeon_ib_get(rdev, ridx, &ib, NULL, ndw * 4); + if (r) + return r; ib.length_dw = 0; r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset); diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c index fc60b74ee30..e24ca6ab96d 100644 --- a/drivers/gpu/drm/radeon/radeon_i2c.c +++ b/drivers/gpu/drm/radeon/radeon_i2c.c @@ -1020,6 +1020,9 @@ void radeon_i2c_destroy(struct radeon_i2c_chan *i2c) /* Add the default buses */ void radeon_i2c_init(struct radeon_device *rdev) { + if (radeon_hw_i2c) + DRM_INFO("hw_i2c forced on, you may experience display detection problems!\n"); + if (rdev->is_atom_bios) radeon_atombios_i2c_init(rdev); else diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index 5a99d433fc3..1fe12ab5c5e 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -241,9 +241,6 @@ int radeon_irq_kms_init(struct radeon_device *rdev) { int r = 0; - INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func); - INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi); - spin_lock_init(&rdev->irq.lock); r = drm_vblank_init(rdev->ddev, rdev->num_crtc); if (r) { @@ -265,6 +262,10 @@ int radeon_irq_kms_init(struct radeon_device *rdev) rdev->irq.installed = false; return r; } + + INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func); + INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi); + DRM_INFO("radeon: irq initialized.\n"); return 0; } @@ -284,8 +285,8 @@ void radeon_irq_kms_fini(struct radeon_device *rdev) rdev->irq.installed = false; if (rdev->msi_enabled) pci_disable_msi(rdev->pdev); + flush_work(&rdev->hotplug_work); } - flush_work(&rdev->hotplug_work); } /** diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 4f2d4f4c1da..7e292d89920 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -414,6 +414,9 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) value = rdev->config.si.tile_mode_array; value_size = sizeof(uint32_t)*32; break; + case RADEON_INFO_SI_CP_DMA_COMPUTE: + *value = 1; + break; default: DRM_DEBUG_KMS("Invalid request %d\n", info->request); return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c index 7cb178a34a0..bc73021d359 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c @@ -422,6 +422,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc, /* Pin framebuffer & get tilling informations */ obj = radeon_fb->obj; rbo = gem_to_radeon_bo(obj); +retry: r = radeon_bo_reserve(rbo, false); if (unlikely(r != 0)) return r; @@ -430,6 +431,33 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc, &base); if (unlikely(r != 0)) { radeon_bo_unreserve(rbo); + + /* On old GPU like RN50 with little vram pining can fails because + * current fb is taking all space needed. So instead of unpining + * the old buffer after pining the new one, first unpin old one + * and then retry pining new one. + * + * As only master can set mode only master can pin and it is + * unlikely the master client will race with itself especialy + * on those old gpu with single crtc. + * + * We don't shutdown the display controller because new buffer + * will end up in same spot. + */ + if (!atomic && fb && fb != crtc->fb) { + struct radeon_bo *old_rbo; + unsigned long nsize, osize; + + old_rbo = gem_to_radeon_bo(to_radeon_framebuffer(fb)->obj); + osize = radeon_bo_size(old_rbo); + nsize = radeon_bo_size(rbo); + if (nsize <= osize && !radeon_bo_reserve(old_rbo, false)) { + radeon_bo_unpin(old_rbo); + radeon_bo_unreserve(old_rbo); + fb = NULL; + goto retry; + } + } return -EINVAL; } radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL); diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index e2cb80a96b5..29438239460 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -158,7 +158,7 @@ static inline void * radeon_sa_bo_cpu_addr(struct radeon_sa_bo *sa_bo) extern int radeon_sa_bo_manager_init(struct radeon_device *rdev, struct radeon_sa_manager *sa_manager, - unsigned size, u32 domain); + unsigned size, u32 align, u32 domain); extern void radeon_sa_bo_manager_fini(struct radeon_device *rdev, struct radeon_sa_manager *sa_manager); extern int radeon_sa_bo_manager_start(struct radeon_device *rdev, diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 788c64cb4b4..469ba710b52 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -561,8 +561,10 @@ void radeon_pm_resume(struct radeon_device *rdev) rdev->pm.current_clock_mode_index = 0; rdev->pm.current_sclk = rdev->pm.default_sclk; rdev->pm.current_mclk = rdev->pm.default_mclk; - rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage; - rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci; + if (rdev->pm.power_state) { + rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage; + rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci; + } if (rdev->pm.pm_method == PM_METHOD_DYNPM && rdev->pm.dynpm_state == DYNPM_STATE_SUSPENDED) { rdev->pm.dynpm_state = DYNPM_STATE_ACTIVE; diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 82434018cbe..6e0f4809bda 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -224,6 +224,7 @@ int radeon_ib_pool_init(struct radeon_device *rdev) } r = radeon_sa_bo_manager_init(rdev, &rdev->ring_tmp_bo, RADEON_IB_POOL_SIZE*64*1024, + RADEON_GPU_PAGE_SIZE, RADEON_GEM_DOMAIN_GTT); if (r) { return r; @@ -822,9 +823,11 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data) * packet that is the root issue */ i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask; - for (j = 0; j <= (count + 32); j++) { - seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]); - i = (i + 1) & ring->ptr_mask; + if (ring->ready) { + for (j = 0; j <= (count + 32); j++) { + seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]); + i = (i + 1) & ring->ptr_mask; + } } return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c index 0abe5a9431b..f0bac68254b 100644 --- a/drivers/gpu/drm/radeon/radeon_sa.c +++ b/drivers/gpu/drm/radeon/radeon_sa.c @@ -49,7 +49,7 @@ static void radeon_sa_bo_try_free(struct radeon_sa_manager *sa_manager); int radeon_sa_bo_manager_init(struct radeon_device *rdev, struct radeon_sa_manager *sa_manager, - unsigned size, u32 domain) + unsigned size, u32 align, u32 domain) { int i, r; @@ -57,13 +57,14 @@ int radeon_sa_bo_manager_init(struct radeon_device *rdev, sa_manager->bo = NULL; sa_manager->size = size; sa_manager->domain = domain; + sa_manager->align = align; sa_manager->hole = &sa_manager->olist; INIT_LIST_HEAD(&sa_manager->olist); for (i = 0; i < RADEON_NUM_RINGS; ++i) { INIT_LIST_HEAD(&sa_manager->flist[i]); } - r = radeon_bo_create(rdev, size, RADEON_GPU_PAGE_SIZE, true, + r = radeon_bo_create(rdev, size, align, true, domain, NULL, &sa_manager->bo); if (r) { dev_err(rdev->dev, "(%d) failed to allocate bo for manager\n", r); @@ -317,7 +318,7 @@ int radeon_sa_bo_new(struct radeon_device *rdev, unsigned tries[RADEON_NUM_RINGS]; int i, r; - BUG_ON(align > RADEON_GPU_PAGE_SIZE); + BUG_ON(align > sa_manager->align); BUG_ON(size > sa_manager->size); *sa_bo = kmalloc(sizeof(struct radeon_sa_bo), GFP_KERNEL); diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c index bbed4af8d0b..f9ebf2bf8b5 100644 --- a/drivers/gpu/drm/radeon/radeon_test.c +++ b/drivers/gpu/drm/radeon/radeon_test.c @@ -37,8 +37,8 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag) struct radeon_bo **gtt_obj = NULL; struct radeon_fence *fence = NULL; uint64_t gtt_addr, vram_addr; - unsigned i, n, size; - int r, ring; + unsigned n, size; + int i, r, ring; switch (flag) { case RADEON_TEST_COPY_DMA: diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index cad735dd02c..21d2d5280fc 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -123,16 +123,29 @@ int radeon_uvd_init(struct radeon_device *rdev) return r; } - r = radeon_uvd_resume(rdev); - if (r) + r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false); + if (r) { + radeon_bo_unref(&rdev->uvd.vcpu_bo); + dev_err(rdev->dev, "(%d) failed to reserve UVD bo\n", r); return r; + } - memset(rdev->uvd.cpu_addr, 0, bo_size); - memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size); + r = radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_VRAM, + &rdev->uvd.gpu_addr); + if (r) { + radeon_bo_unreserve(rdev->uvd.vcpu_bo); + radeon_bo_unref(&rdev->uvd.vcpu_bo); + dev_err(rdev->dev, "(%d) UVD bo pin failed\n", r); + return r; + } - r = radeon_uvd_suspend(rdev); - if (r) + r = radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr); + if (r) { + dev_err(rdev->dev, "(%d) UVD map failed\n", r); return r; + } + + radeon_bo_unreserve(rdev->uvd.vcpu_bo); for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { atomic_set(&rdev->uvd.handles[i], 0); @@ -144,70 +157,73 @@ int radeon_uvd_init(struct radeon_device *rdev) void radeon_uvd_fini(struct radeon_device *rdev) { - radeon_uvd_suspend(rdev); - radeon_bo_unref(&rdev->uvd.vcpu_bo); -} - -int radeon_uvd_suspend(struct radeon_device *rdev) -{ int r; if (rdev->uvd.vcpu_bo == NULL) - return 0; + return; r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false); if (!r) { radeon_bo_kunmap(rdev->uvd.vcpu_bo); radeon_bo_unpin(rdev->uvd.vcpu_bo); - rdev->uvd.cpu_addr = NULL; - if (!radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_CPU, NULL)) { - radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr); - } radeon_bo_unreserve(rdev->uvd.vcpu_bo); - - if (rdev->uvd.cpu_addr) { - radeon_fence_driver_start_ring(rdev, R600_RING_TYPE_UVD_INDEX); - } else { - rdev->fence_drv[R600_RING_TYPE_UVD_INDEX].cpu_addr = NULL; - } } - return r; + + radeon_bo_unref(&rdev->uvd.vcpu_bo); + + release_firmware(rdev->uvd_fw); +} + +int radeon_uvd_suspend(struct radeon_device *rdev) +{ + unsigned size; + void *ptr; + int i; + + if (rdev->uvd.vcpu_bo == NULL) + return 0; + + for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) + if (atomic_read(&rdev->uvd.handles[i])) + break; + + if (i == RADEON_MAX_UVD_HANDLES) + return 0; + + size = radeon_bo_size(rdev->uvd.vcpu_bo); + size -= rdev->uvd_fw->size; + + ptr = rdev->uvd.cpu_addr; + ptr += rdev->uvd_fw->size; + + rdev->uvd.saved_bo = kmalloc(size, GFP_KERNEL); + memcpy(rdev->uvd.saved_bo, ptr, size); + + return 0; } int radeon_uvd_resume(struct radeon_device *rdev) { - int r; + unsigned size; + void *ptr; if (rdev->uvd.vcpu_bo == NULL) return -EINVAL; - r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false); - if (r) { - radeon_bo_unref(&rdev->uvd.vcpu_bo); - dev_err(rdev->dev, "(%d) failed to reserve UVD bo\n", r); - return r; - } - - /* Have been pin in cpu unmap unpin */ - radeon_bo_kunmap(rdev->uvd.vcpu_bo); - radeon_bo_unpin(rdev->uvd.vcpu_bo); + memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size); - r = radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_VRAM, - &rdev->uvd.gpu_addr); - if (r) { - radeon_bo_unreserve(rdev->uvd.vcpu_bo); - radeon_bo_unref(&rdev->uvd.vcpu_bo); - dev_err(rdev->dev, "(%d) UVD bo pin failed\n", r); - return r; - } + size = radeon_bo_size(rdev->uvd.vcpu_bo); + size -= rdev->uvd_fw->size; - r = radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr); - if (r) { - dev_err(rdev->dev, "(%d) UVD map failed\n", r); - return r; - } + ptr = rdev->uvd.cpu_addr; + ptr += rdev->uvd_fw->size; - radeon_bo_unreserve(rdev->uvd.vcpu_bo); + if (rdev->uvd.saved_bo != NULL) { + memcpy(ptr, rdev->uvd.saved_bo, size); + kfree(rdev->uvd.saved_bo); + rdev->uvd.saved_bo = NULL; + } else + memset(ptr, 0, size); return 0; } @@ -222,10 +238,12 @@ void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp) { int i, r; for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) { - if (rdev->uvd.filp[i] == filp) { - uint32_t handle = atomic_read(&rdev->uvd.handles[i]); + uint32_t handle = atomic_read(&rdev->uvd.handles[i]); + if (handle != 0 && rdev->uvd.filp[i] == filp) { struct radeon_fence *fence; + radeon_uvd_note_usage(rdev); + r = radeon_uvd_get_destroy_msg(rdev, R600_RING_TYPE_UVD_INDEX, handle, &fence); if (r) { @@ -343,6 +361,14 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; } + if (bo->tbo.sync_obj) { + r = radeon_fence_wait(bo->tbo.sync_obj, false); + if (r) { + DRM_ERROR("Failed waiting for UVD message (%d)!\n", r); + return r; + } + } + r = radeon_bo_kmap(bo, &ptr); if (r) return r; @@ -434,7 +460,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p, return -EINVAL; } - if ((start >> 28) != (end >> 28)) { + if ((start >> 28) != ((end - 1) >> 28)) { DRM_ERROR("reloc %LX-%LX crossing 256MB boundary!\n", start, end); return -EINVAL; diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c index 233a9b9fa1f..b8074a8ec75 100644 --- a/drivers/gpu/drm/radeon/rs400.c +++ b/drivers/gpu/drm/radeon/rs400.c @@ -174,10 +174,13 @@ int rs400_gart_enable(struct radeon_device *rdev) /* FIXME: according to doc we should set HIDE_MMCFG_BAR=0, * AGPMODE30=0 & AGP30ENHANCED=0 in NB_CNTL */ if ((rdev->family == CHIP_RS690) || (rdev->family == CHIP_RS740)) { - WREG32_MC(RS480_MC_MISC_CNTL, - (RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN)); + tmp = RREG32_MC(RS480_MC_MISC_CNTL); + tmp |= RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN; + WREG32_MC(RS480_MC_MISC_CNTL, tmp); } else { - WREG32_MC(RS480_MC_MISC_CNTL, RS480_GART_INDEX_REG_EN); + tmp = RREG32_MC(RS480_MC_MISC_CNTL); + tmp |= RS480_GART_INDEX_REG_EN; + WREG32_MC(RS480_MC_MISC_CNTL, tmp); } /* Enable gart */ WREG32_MC(RS480_AGP_ADDRESS_SPACE_SIZE, (RS480_GART_EN | size_reg)); diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 55880d5962c..ea28ecbd5c7 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -162,6 +162,16 @@ static void rs690_mc_init(struct radeon_device *rdev) base = RREG32_MC(R_000100_MCCFG_FB_LOCATION); base = G_000100_MC_FB_START(base) << 16; rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev); + /* Some boards seem to be configured for 128MB of sideport memory, + * but really only have 64MB. Just skip the sideport and use + * UMA memory. + */ + if (rdev->mc.igp_sideport_enabled && + (rdev->mc.real_vram_size == (384 * 1024 * 1024))) { + base += 128 * 1024 * 1024; + rdev->mc.real_vram_size -= 128 * 1024 * 1024; + rdev->mc.mc_vram_size = rdev->mc.real_vram_size; + } /* Use K8 direct mapping for fast fb access. */ rdev->fastfb_working = false; diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index 4a62ad2e539..f5e92cfcc14 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -744,10 +744,10 @@ static void rv770_init_golden_registers(struct radeon_device *rdev) (const u32)ARRAY_SIZE(r7xx_golden_dyn_gpr_registers)); radeon_program_register_sequence(rdev, rv730_golden_registers, - (const u32)ARRAY_SIZE(rv770_golden_registers)); + (const u32)ARRAY_SIZE(rv730_golden_registers)); radeon_program_register_sequence(rdev, rv730_mgcg_init, - (const u32)ARRAY_SIZE(rv770_mgcg_init)); + (const u32)ARRAY_SIZE(rv730_mgcg_init)); break; case CHIP_RV710: radeon_program_register_sequence(rdev, @@ -758,18 +758,18 @@ static void rv770_init_golden_registers(struct radeon_device *rdev) (const u32)ARRAY_SIZE(r7xx_golden_dyn_gpr_registers)); radeon_program_register_sequence(rdev, rv710_golden_registers, - (const u32)ARRAY_SIZE(rv770_golden_registers)); + (const u32)ARRAY_SIZE(rv710_golden_registers)); radeon_program_register_sequence(rdev, rv710_mgcg_init, - (const u32)ARRAY_SIZE(rv770_mgcg_init)); + (const u32)ARRAY_SIZE(rv710_mgcg_init)); break; case CHIP_RV740: radeon_program_register_sequence(rdev, rv740_golden_registers, - (const u32)ARRAY_SIZE(rv770_golden_registers)); + (const u32)ARRAY_SIZE(rv740_golden_registers)); radeon_program_register_sequence(rdev, rv740_mgcg_init, - (const u32)ARRAY_SIZE(rv770_mgcg_init)); + (const u32)ARRAY_SIZE(rv740_mgcg_init)); break; default: break; @@ -1829,6 +1829,8 @@ static int rv770_startup(struct radeon_device *rdev) /* enable pcie gen2 link */ rv770_pcie_gen2_enable(rdev); + rv770_mc_program(rdev); + if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) { r = r600_init_microcode(rdev); if (r) { @@ -1841,7 +1843,6 @@ static int rv770_startup(struct radeon_device *rdev) if (r) return r; - rv770_mc_program(rdev); if (rdev->flags & RADEON_IS_AGP) { rv770_agp_enable(rdev); } else { @@ -1983,6 +1984,7 @@ int rv770_resume(struct radeon_device *rdev) int rv770_suspend(struct radeon_device *rdev) { r600_audio_fini(rdev); + r600_uvd_stop(rdev); radeon_uvd_suspend(rdev); r700_cp_stop(rdev); r600_dma_stop(rdev); @@ -2098,6 +2100,7 @@ void rv770_fini(struct radeon_device *rdev) radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); rv770_pcie_gart_fini(rdev); + r600_uvd_stop(rdev); radeon_uvd_fini(rdev); r600_vram_scratch_fini(rdev); radeon_gem_fini(rdev); diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index a1b0da6b580..03add5d5542 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -1467,7 +1467,8 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev, struct drm_display_mode *mode, struct drm_display_mode *other_mode) { - u32 tmp; + u32 tmp, buffer_alloc, i; + u32 pipe_offset = radeon_crtc->crtc_id * 0x20; /* * Line Buffer Setup * There are 3 line buffers, each one shared by 2 display controllers. @@ -1482,16 +1483,30 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev, * non-linked crtcs for maximum line buffer allocation. */ if (radeon_crtc->base.enabled && mode) { - if (other_mode) + if (other_mode) { tmp = 0; /* 1/2 */ - else + buffer_alloc = 1; + } else { tmp = 2; /* whole */ - } else + buffer_alloc = 2; + } + } else { tmp = 0; + buffer_alloc = 0; + } WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset, DC_LB_MEMORY_CONFIG(tmp)); + WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset, + DMIF_BUFFERS_ALLOCATED(buffer_alloc)); + for (i = 0; i < rdev->usec_timeout; i++) { + if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) & + DMIF_BUFFERS_ALLOCATED_COMPLETED) + break; + udelay(1); + } + if (radeon_crtc->base.enabled && mode) { switch (tmp) { case 0: @@ -3600,8 +3615,15 @@ static int si_mc_init(struct radeon_device *rdev) rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); /* size in MB on si */ - rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL; - rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL; + tmp = RREG32(CONFIG_MEMSIZE); + /* some boards may have garbage in the upper 16 bits */ + if (tmp & 0xffff0000) { + DRM_INFO("Probable bad vram size: 0x%08x\n", tmp); + if (tmp & 0xffff) + tmp &= 0xffff; + } + rdev->mc.mc_vram_size = tmp * 1024ULL * 1024ULL; + rdev->mc.real_vram_size = rdev->mc.mc_vram_size; rdev->mc.visible_vram_size = rdev->mc.aper_size; si_vram_gtt_location(rdev, &rdev->mc); radeon_update_bandwidth_info(rdev); @@ -3796,13 +3818,64 @@ static int si_vm_packet3_ce_check(struct radeon_device *rdev, return 0; } +static int si_vm_packet3_cp_dma_check(u32 *ib, u32 idx) +{ + u32 start_reg, reg, i; + u32 command = ib[idx + 4]; + u32 info = ib[idx + 1]; + u32 idx_value = ib[idx]; + if (command & PACKET3_CP_DMA_CMD_SAS) { + /* src address space is register */ + if (((info & 0x60000000) >> 29) == 0) { + start_reg = idx_value << 2; + if (command & PACKET3_CP_DMA_CMD_SAIC) { + reg = start_reg; + if (!si_vm_reg_valid(reg)) { + DRM_ERROR("CP DMA Bad SRC register\n"); + return -EINVAL; + } + } else { + for (i = 0; i < (command & 0x1fffff); i++) { + reg = start_reg + (4 * i); + if (!si_vm_reg_valid(reg)) { + DRM_ERROR("CP DMA Bad SRC register\n"); + return -EINVAL; + } + } + } + } + } + if (command & PACKET3_CP_DMA_CMD_DAS) { + /* dst address space is register */ + if (((info & 0x00300000) >> 20) == 0) { + start_reg = ib[idx + 2]; + if (command & PACKET3_CP_DMA_CMD_DAIC) { + reg = start_reg; + if (!si_vm_reg_valid(reg)) { + DRM_ERROR("CP DMA Bad DST register\n"); + return -EINVAL; + } + } else { + for (i = 0; i < (command & 0x1fffff); i++) { + reg = start_reg + (4 * i); + if (!si_vm_reg_valid(reg)) { + DRM_ERROR("CP DMA Bad DST register\n"); + return -EINVAL; + } + } + } + } + } + return 0; +} + static int si_vm_packet3_gfx_check(struct radeon_device *rdev, u32 *ib, struct radeon_cs_packet *pkt) { + int r; u32 idx = pkt->idx + 1; u32 idx_value = ib[idx]; u32 start_reg, end_reg, reg, i; - u32 command, info; switch (pkt->opcode) { case PACKET3_NOP: @@ -3903,50 +3976,9 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev, } break; case PACKET3_CP_DMA: - command = ib[idx + 4]; - info = ib[idx + 1]; - if (command & PACKET3_CP_DMA_CMD_SAS) { - /* src address space is register */ - if (((info & 0x60000000) >> 29) == 0) { - start_reg = idx_value << 2; - if (command & PACKET3_CP_DMA_CMD_SAIC) { - reg = start_reg; - if (!si_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad SRC register\n"); - return -EINVAL; - } - } else { - for (i = 0; i < (command & 0x1fffff); i++) { - reg = start_reg + (4 * i); - if (!si_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad SRC register\n"); - return -EINVAL; - } - } - } - } - } - if (command & PACKET3_CP_DMA_CMD_DAS) { - /* dst address space is register */ - if (((info & 0x00300000) >> 20) == 0) { - start_reg = ib[idx + 2]; - if (command & PACKET3_CP_DMA_CMD_DAIC) { - reg = start_reg; - if (!si_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad DST register\n"); - return -EINVAL; - } - } else { - for (i = 0; i < (command & 0x1fffff); i++) { - reg = start_reg + (4 * i); - if (!si_vm_reg_valid(reg)) { - DRM_ERROR("CP DMA Bad DST register\n"); - return -EINVAL; - } - } - } - } - } + r = si_vm_packet3_cp_dma_check(ib, idx); + if (r) + return r; break; default: DRM_ERROR("Invalid GFX packet3: 0x%x\n", pkt->opcode); @@ -3958,6 +3990,7 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev, static int si_vm_packet3_compute_check(struct radeon_device *rdev, u32 *ib, struct radeon_cs_packet *pkt) { + int r; u32 idx = pkt->idx + 1; u32 idx_value = ib[idx]; u32 start_reg, reg, i; @@ -4030,6 +4063,11 @@ static int si_vm_packet3_compute_check(struct radeon_device *rdev, return -EINVAL; } break; + case PACKET3_CP_DMA: + r = si_vm_packet3_cp_dma_check(ib, idx); + if (r) + return r; + break; default: DRM_ERROR("Invalid Compute packet3: 0x%x\n", pkt->opcode); return -EINVAL; @@ -4481,7 +4519,7 @@ static void si_disable_interrupt_state(struct radeon_device *rdev) } if (!ASIC_IS_NODCE(rdev)) { - WREG32(DACA_AUTODETECT_INT_CONTROL, 0); + WREG32(DAC_AUTODETECT_INT_CONTROL, 0); tmp = RREG32(DC_HPD1_INT_CONTROL) & DC_HPDx_INT_POLARITY; WREG32(DC_HPD1_INT_CONTROL, tmp); @@ -5121,6 +5159,10 @@ restart_ih: break; } break; + case 124: /* UVD */ + DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data); + radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX); + break; case 146: case 147: dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data); @@ -5270,6 +5312,8 @@ static int si_startup(struct radeon_device *rdev) struct radeon_ring *ring; int r; + si_mc_program(rdev); + if (!rdev->me_fw || !rdev->pfp_fw || !rdev->ce_fw || !rdev->rlc_fw || !rdev->mc_fw) { r = si_init_microcode(rdev); @@ -5289,7 +5333,6 @@ static int si_startup(struct radeon_device *rdev) if (r) return r; - si_mc_program(rdev); r = si_pcie_gart_enable(rdev); if (r) return r; @@ -5473,7 +5516,7 @@ int si_suspend(struct radeon_device *rdev) si_cp_enable(rdev, false); cayman_dma_stop(rdev); if (rdev->has_uvd) { - r600_uvd_rbc_stop(rdev); + r600_uvd_stop(rdev); radeon_uvd_suspend(rdev); } si_irq_suspend(rdev); @@ -5613,8 +5656,10 @@ void si_fini(struct radeon_device *rdev) radeon_vm_manager_fini(rdev); radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); - if (rdev->has_uvd) + if (rdev->has_uvd) { + r600_uvd_stop(rdev); radeon_uvd_fini(rdev); + } si_pcie_gart_fini(rdev); r600_vram_scratch_fini(rdev); radeon_gem_fini(rdev); diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h index 8f2d7d4f9b2..9652ed9ec63 100644 --- a/drivers/gpu/drm/radeon/sid.h +++ b/drivers/gpu/drm/radeon/sid.h @@ -97,6 +97,10 @@ #define DMIF_ADDR_CALC 0xC00 +#define PIPE0_DMIF_BUFFER_CONTROL 0x0ca0 +# define DMIF_BUFFERS_ALLOCATED(x) ((x) << 0) +# define DMIF_BUFFERS_ALLOCATED_COMPLETED (1 << 4) + #define SRBM_STATUS 0xE50 #define GRBM_RQ_PENDING (1 << 5) #define VMC_BUSY (1 << 8) @@ -243,7 +247,7 @@ #define NOOFGROUPS_SHIFT 12 #define NOOFGROUPS_MASK 0x00001000 -#define MC_SEQ_TRAIN_WAKEUP_CNTL 0x2808 +#define MC_SEQ_TRAIN_WAKEUP_CNTL 0x28e8 #define TRAIN_DONE_D0 (1 << 30) #define TRAIN_DONE_D1 (1 << 31) @@ -390,7 +394,7 @@ # define GRPH_PFLIP_INT_MASK (1 << 0) # define GRPH_PFLIP_INT_TYPE (1 << 8) -#define DACA_AUTODETECT_INT_CONTROL 0x66c8 +#define DAC_AUTODETECT_INT_CONTROL 0x67c8 #define DC_HPD1_INT_STATUS 0x601c #define DC_HPD2_INT_STATUS 0x6028 @@ -924,7 +928,7 @@ * 6. COMMAND [30:21] | BYTE_COUNT [20:0] */ # define PACKET3_CP_DMA_DST_SEL(x) ((x) << 20) - /* 0 - SRC_ADDR + /* 0 - DST_ADDR * 1 - GDS */ # define PACKET3_CP_DMA_ENGINE(x) ((x) << 27) @@ -939,7 +943,7 @@ # define PACKET3_CP_DMA_CP_SYNC (1 << 31) /* COMMAND */ # define PACKET3_CP_DMA_DIS_WC (1 << 21) -# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23) +# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22) /* 0 - none * 1 - 8 in 16 * 2 - 8 in 32 diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 9b07b7d44a5..8697abd7b17 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1153,24 +1153,32 @@ out_unlock: return ret; } -static int ttm_bo_mem_compat(struct ttm_placement *placement, - struct ttm_mem_reg *mem) +static bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags) { int i; if (mem->mm_node && placement->lpfn != 0 && (mem->start < placement->fpfn || mem->start + mem->num_pages > placement->lpfn)) - return -1; + return false; for (i = 0; i < placement->num_placement; i++) { - if ((placement->placement[i] & mem->placement & - TTM_PL_MASK_CACHING) && - (placement->placement[i] & mem->placement & - TTM_PL_MASK_MEM)) - return i; + *new_flags = placement->placement[i]; + if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) && + (*new_flags & mem->placement & TTM_PL_MASK_MEM)) + return true; + } + + for (i = 0; i < placement->num_busy_placement; i++) { + *new_flags = placement->busy_placement[i]; + if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) && + (*new_flags & mem->placement & TTM_PL_MASK_MEM)) + return true; } - return -1; + + return false; } int ttm_bo_validate(struct ttm_buffer_object *bo, @@ -1179,6 +1187,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, bool no_wait_gpu) { int ret; + uint32_t new_flags; BUG_ON(!ttm_bo_is_reserved(bo)); /* Check that range is valid */ @@ -1189,8 +1198,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, /* * Check whether we need to move buffer. */ - ret = ttm_bo_mem_compat(placement, &bo->mem); - if (ret < 0) { + if (!ttm_bo_mem_compat(placement, &bo->mem, &new_flags)) { ret = ttm_bo_move_buffer(bo, placement, interruptible, no_wait_gpu); if (ret) @@ -1200,7 +1208,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, * Use the access and other non-mapping-related flag bits from * the compatible memory placement flags to the active flags */ - ttm_flag_masked(&bo->mem.placement, placement->placement[ret], + ttm_flag_masked(&bo->mem.placement, new_flags, ~TTM_PL_MASK_MEMTYPE); } /* diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index af894584dd9..b7f757158df 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -342,19 +342,25 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, if (ret) goto out; + /* + * Single TTM move. NOP. + */ if (old_iomap == NULL && new_iomap == NULL) goto out2; + + /* + * Move nonexistent data. NOP. + */ if (old_iomap == NULL && ttm == NULL) goto out2; - if (ttm->state == tt_unpopulated) { + /* + * TTM might be null for moves within the same region. + */ + if (ttm && ttm->state == tt_unpopulated) { ret = ttm->bdev->driver->ttm_tt_populate(ttm); - if (ret) { - /* if we fail here don't nuke the mm node - * as the bo still owns it */ - old_copy.mm_node = NULL; + if (ret) goto out1; - } } add = 0; @@ -380,11 +386,8 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, prot); } else ret = ttm_copy_io_page(new_iomap, old_iomap, page); - if (ret) { - /* failing here, means keep old copy as-is */ - old_copy.mm_node = NULL; + if (ret) goto out1; - } } mb(); out2: @@ -402,7 +405,12 @@ out1: ttm_mem_reg_iounmap(bdev, old_mem, new_iomap); out: ttm_mem_reg_iounmap(bdev, &old_copy, old_iomap); - ttm_bo_mem_put(bo, &old_copy); + + /* + * On error, keep the mm node! + */ + if (!ret) + ttm_bo_mem_put(bo, &old_copy); return ret; } EXPORT_SYMBOL(ttm_bo_move_memcpy); diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 5e93a52d4f2..210d5036516 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -170,7 +170,7 @@ void ttm_tt_destroy(struct ttm_tt *ttm) ttm_tt_unbind(ttm); } - if (likely(ttm->pages != NULL)) { + if (ttm->state == tt_unbound) { ttm->bdev->driver->ttm_tt_unpopulate(ttm); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 07dfd823cc3..6c44c69a5ba 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -740,9 +740,17 @@ static void vmw_postclose(struct drm_device *dev, struct vmw_fpriv *vmw_fp; vmw_fp = vmw_fpriv(file_priv); - ttm_object_file_release(&vmw_fp->tfile); - if (vmw_fp->locked_master) + + if (vmw_fp->locked_master) { + struct vmw_master *vmaster = + vmw_master(vmw_fp->locked_master); + + ttm_lock_set_kill(&vmaster->lock, true, SIGTERM); + ttm_vt_unlock(&vmaster->lock); drm_master_put(&vmw_fp->locked_master); + } + + ttm_object_file_release(&vmw_fp->tfile); kfree(vmw_fp); } @@ -942,14 +950,13 @@ static void vmw_master_drop(struct drm_device *dev, vmw_fp->locked_master = drm_master_get(file_priv->master); ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile); - vmw_execbuf_release_pinned_bo(dev_priv); - if (unlikely((ret != 0))) { DRM_ERROR("Unable to lock TTM at VT switch.\n"); drm_master_put(&vmw_fp->locked_master); } - ttm_lock_set_kill(&vmaster->lock, true, SIGTERM); + ttm_lock_set_kill(&vmaster->lock, false, SIGTERM); + vmw_execbuf_release_pinned_bo(dev_priv); if (!dev_priv->enable_fb) { ret = ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c index 3751730764a..1a0bf07fe54 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c @@ -29,7 +29,9 @@ #include <drm/drmP.h> #include <drm/ttm/ttm_bo_driver.h> -#define VMW_PPN_SIZE sizeof(unsigned long) +#define VMW_PPN_SIZE (sizeof(unsigned long)) +/* A future safe maximum remap size. */ +#define VMW_PPN_PER_REMAP ((31 * 1024) / VMW_PPN_SIZE) static int vmw_gmr2_bind(struct vmw_private *dev_priv, struct page *pages[], @@ -38,43 +40,61 @@ static int vmw_gmr2_bind(struct vmw_private *dev_priv, { SVGAFifoCmdDefineGMR2 define_cmd; SVGAFifoCmdRemapGMR2 remap_cmd; - uint32_t define_size = sizeof(define_cmd) + 4; - uint32_t remap_size = VMW_PPN_SIZE * num_pages + sizeof(remap_cmd) + 4; uint32_t *cmd; uint32_t *cmd_orig; + uint32_t define_size = sizeof(define_cmd) + sizeof(*cmd); + uint32_t remap_num = num_pages / VMW_PPN_PER_REMAP + ((num_pages % VMW_PPN_PER_REMAP) > 0); + uint32_t remap_size = VMW_PPN_SIZE * num_pages + (sizeof(remap_cmd) + sizeof(*cmd)) * remap_num; + uint32_t remap_pos = 0; + uint32_t cmd_size = define_size + remap_size; uint32_t i; - cmd_orig = cmd = vmw_fifo_reserve(dev_priv, define_size + remap_size); + cmd_orig = cmd = vmw_fifo_reserve(dev_priv, cmd_size); if (unlikely(cmd == NULL)) return -ENOMEM; define_cmd.gmrId = gmr_id; define_cmd.numPages = num_pages; + *cmd++ = SVGA_CMD_DEFINE_GMR2; + memcpy(cmd, &define_cmd, sizeof(define_cmd)); + cmd += sizeof(define_cmd) / sizeof(*cmd); + + /* + * Need to split the command if there are too many + * pages that goes into the gmr. + */ + remap_cmd.gmrId = gmr_id; remap_cmd.flags = (VMW_PPN_SIZE > sizeof(*cmd)) ? SVGA_REMAP_GMR2_PPN64 : SVGA_REMAP_GMR2_PPN32; - remap_cmd.offsetPages = 0; - remap_cmd.numPages = num_pages; - *cmd++ = SVGA_CMD_DEFINE_GMR2; - memcpy(cmd, &define_cmd, sizeof(define_cmd)); - cmd += sizeof(define_cmd) / sizeof(uint32); + while (num_pages > 0) { + unsigned long nr = min(num_pages, (unsigned long)VMW_PPN_PER_REMAP); + + remap_cmd.offsetPages = remap_pos; + remap_cmd.numPages = nr; - *cmd++ = SVGA_CMD_REMAP_GMR2; - memcpy(cmd, &remap_cmd, sizeof(remap_cmd)); - cmd += sizeof(remap_cmd) / sizeof(uint32); + *cmd++ = SVGA_CMD_REMAP_GMR2; + memcpy(cmd, &remap_cmd, sizeof(remap_cmd)); + cmd += sizeof(remap_cmd) / sizeof(*cmd); - for (i = 0; i < num_pages; ++i) { - if (VMW_PPN_SIZE <= 4) - *cmd = page_to_pfn(*pages++); - else - *((uint64_t *)cmd) = page_to_pfn(*pages++); + for (i = 0; i < nr; ++i) { + if (VMW_PPN_SIZE <= 4) + *cmd = page_to_pfn(*pages++); + else + *((uint64_t *)cmd) = page_to_pfn(*pages++); - cmd += VMW_PPN_SIZE / sizeof(*cmd); + cmd += VMW_PPN_SIZE / sizeof(*cmd); + } + + num_pages -= nr; + remap_pos += nr; } - vmw_fifo_commit(dev_priv, define_size + remap_size); + BUG_ON(cmd != cmd_orig + cmd_size / sizeof(*cmd)); + + vmw_fifo_commit(dev_priv, cmd_size); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index bc784254e78..407d7f9fe8a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -970,7 +970,7 @@ void vmw_resource_unreserve(struct vmw_resource *res, if (new_backup) res->backup_offset = new_backup_offset; - if (!res->func->may_evict) + if (!res->func->may_evict || res->id == -1) return; write_lock(&dev_priv->resource_lock); |