From: Dave Airlie Date: Wed, 1 Jun 2016 21:58:36 +0000 (+1000) Subject: Merge branch 'drm-intel-next' of git://anongit.freedesktop.org/drm-intel into drm... X-Git-Tag: v4.8-rc1~62^2~45 X-Git-Url: http://git.cascardo.info/?p=cascardo%2Flinux.git;a=commitdiff_plain;h=66fd7a66e8b9e11e49f46ea77910f935c4dee5c3;hp=-c Merge branch 'drm-intel-next' of git://anongit.freedesktop.org/drm-intel into drm-next drm-intel-next-2016-05-22: - cmd-parser support for direct reg->reg loads (Ken Graunke) - better handle DP++ smart dongles (Ville) - bxt guc fw loading support (Nick Hoathe) - remove a bunch of struct typedefs from dpll code (Ander) - tons of small work all over to avoid casting between drm_device and the i915 dev struct (Tvrtko&Chris) - untangle request retiring from other operations, also fixes reset stat corner cases (Chris) - skl atomic watermark support from Matt Roper, yay! - various wm handling bugfixes from Ville - big pile of cdclck rework for bxt/skl (Ville) - CABC (Content Adaptive Brigthness Control) for dsi panels (Jani&Deepak M) - nonblocking atomic commits for plane-only updates (Maarten Lankhorst) - bunch of PSR fixes&improvements - untangle our map/pin/sg_iter code a bit (Dave Gordon) drm-intel-next-2016-05-08: - refactor stolen quirks to share code between early quirks and i915 (Joonas) - refactor gem BO/vma funcstion (Tvrtko&Dave) - backlight over DPCD support (Yetunde Abedisi) - more dsi panel sequence support (Jani) - lots of refactoring around handling iomaps, vma, ring access and related topics culmulating in removing the duplicated request tracking in the execlist code (Chris & Tvrtko) includes a small patch for core iomapping code - hw state readout for bxt dsi (Ramalingam C) - cdclk cleanups (Ville) - dedupe chv pll code a bit (Ander) - enable semaphores on gen8+ for legacy submission, to be able to have a direct comparison against execlist on the same platform (Chris) Not meant to be used for anything else but performance tuning - lvds border bit hw state checker fix (Jani) - rpm vs. shrinker/oom-notifier fixes (Praveen Paneri) - l3 tuning (Imre) - revert mst dp audio, it's totally non-functional and crash-y (Lyude) - first official dmc for kbl (Rodrigo) - and tons of small things all over as usual * 'drm-intel-next' of git://anongit.freedesktop.org/drm-intel: (194 commits) drm/i915: Revert async unpin and nonblocking atomic commit drm/i915: Update DRIVER_DATE to 20160522 drm/i915: Inline sg_next() for the optimised SGL iterator drm/i915: Introduce & use new lightweight SGL iterators drm/i915: optimise i915_gem_object_map() for small objects drm/i915: refactor i915_gem_object_pin_map() drm/i915/psr: Implement PSR2 w/a for gen9 drm/i915/psr: Use ->get_aux_send_ctl functions drm/i915/psr: Order DP aux transactions correctly drm/i915/psr: Make idle_frames sensible again drm/i915/psr: Try to program link training times correctly drm/i915/userptr: Convert to drm_i915_private drm/i915: Allow nonblocking update of pageflips. drm/i915: Check for unpin correctness. Reapply "drm/i915: Avoid stalling on pending flips for legacy cursor updates" drm/i915: Make unpin async. drm/i915: Prepare connectors for nonblocking checks. drm/i915: Pass atomic states to fbc update functions. drm/i915: Remove reset_counter from intel_crtc. drm/i915: Remove queue_flip pointer. ... --- 66fd7a66e8b9e11e49f46ea77910f935c4dee5c3 diff --combined drivers/gpu/drm/drm_irq.c index 66e5c1e412d3,d3124b67f4a5..5a773e437e2f --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@@ -42,6 -42,10 +42,6 @@@ #include #include -/* Access macro for slots in vblank timestamp ringbuffer. */ -#define vblanktimestamp(dev, pipe, count) \ - ((dev)->vblank[pipe].time[(count) % DRM_VBLANKTIME_RBSIZE]) - /* Retry timestamp calculation up to 3 times to satisfy * drm_timestamp_precision before giving up. */ @@@ -78,15 -82,29 +78,15 @@@ static void store_vblank(struct drm_dev struct timeval *t_vblank, u32 last) { struct drm_vblank_crtc *vblank = &dev->vblank[pipe]; - u32 tslot; assert_spin_locked(&dev->vblank_time_lock); vblank->last = last; - /* All writers hold the spinlock, but readers are serialized by - * the latching of vblank->count below. - */ - tslot = vblank->count + vblank_count_inc; - vblanktimestamp(dev, pipe, tslot) = *t_vblank; - - /* - * vblank timestamp updates are protected on the write side with - * vblank_time_lock, but on the read side done locklessly using a - * sequence-lock on the vblank counter. Ensure correct ordering using - * memory barrriers. We need the barrier both before and also after the - * counter update to synchronize with the next timestamp write. - * The read-side barriers for this are in drm_vblank_count_and_time. - */ - smp_wmb(); + write_seqlock(&vblank->seqlock); + vblank->time = *t_vblank; vblank->count += vblank_count_inc; - smp_wmb(); + write_sequnlock(&vblank->seqlock); } /** @@@ -187,7 -205,7 +187,7 @@@ static void drm_update_vblank_count(str const struct timeval *t_old; u64 diff_ns; - t_old = &vblanktimestamp(dev, pipe, vblank->count); + t_old = &vblank->time; diff_ns = timeval_to_ns(&t_vblank) - timeval_to_ns(t_old); /* @@@ -221,6 -239,49 +221,6 @@@ diff = 1; } - /* - * FIMXE: Need to replace this hack with proper seqlocks. - * - * Restrict the bump of the software vblank counter to a safe maximum - * value of +1 whenever there is the possibility that concurrent readers - * of vblank timestamps could be active at the moment, as the current - * implementation of the timestamp caching and updating is not safe - * against concurrent readers for calls to store_vblank() with a bump - * of anything but +1. A bump != 1 would very likely return corrupted - * timestamps to userspace, because the same slot in the cache could - * be concurrently written by store_vblank() and read by one of those - * readers without the read-retry logic detecting the collision. - * - * Concurrent readers can exist when we are called from the - * drm_vblank_off() or drm_vblank_on() functions and other non-vblank- - * irq callers. However, all those calls to us are happening with the - * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount - * can't increase while we are executing. Therefore a zero refcount at - * this point is safe for arbitrary counter bumps if we are called - * outside vblank irq, a non-zero count is not 100% safe. Unfortunately - * we must also accept a refcount of 1, as whenever we are called from - * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and - * we must let that one pass through in order to not lose vblank counts - * during vblank irq off - which would completely defeat the whole - * point of this routine. - * - * Whenever we are called from vblank irq, we have to assume concurrent - * readers exist or can show up any time during our execution, even if - * the refcount is currently zero, as vblank irqs are usually only - * enabled due to the presence of readers, and because when we are called - * from vblank irq we can't hold the vbl_lock to protect us from sudden - * bumps in vblank refcount. Therefore also restrict bumps to +1 when - * called from vblank irq. - */ - if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 || - (flags & DRM_CALLED_FROM_VBLIRQ))) { - DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u " - "refcount %u, vblirq %u\n", pipe, diff, - atomic_read(&vblank->refcount), - (flags & DRM_CALLED_FROM_VBLIRQ) != 0); - diff = 1; - } - DRM_DEBUG_VBL("updating vblank count on crtc %u:" " current=%u, diff=%u, hw=%u hw_last=%u\n", pipe, vblank->count, diff, cur_vblank, vblank->last); @@@ -242,6 -303,37 +242,37 @@@ store_vblank(dev, pipe, diff, &t_vblank, cur_vblank); } + /** + * drm_accurate_vblank_count - retrieve the master vblank counter + * @crtc: which counter to retrieve + * + * This function is similar to @drm_crtc_vblank_count but this + * function interpolates to handle a race with vblank irq's. + * + * This is mostly useful for hardware that can obtain the scanout + * position, but doesn't have a frame counter. + */ + u32 drm_accurate_vblank_count(struct drm_crtc *crtc) + { + struct drm_device *dev = crtc->dev; + unsigned int pipe = drm_crtc_index(crtc); + u32 vblank; + unsigned long flags; + + WARN(!dev->driver->get_vblank_timestamp, + "This function requires support for accurate vblank timestamps."); + + spin_lock_irqsave(&dev->vblank_time_lock, flags); + + drm_update_vblank_count(dev, pipe, 0); + vblank = drm_vblank_count(dev, pipe); + + spin_unlock_irqrestore(&dev->vblank_time_lock, flags); + + return vblank; + } + EXPORT_SYMBOL(drm_accurate_vblank_count); + /* * Disable vblank irq's on crtc, make sure that last vblank count * of hardware and corresponding consistent software vblank counter @@@ -287,6 -379,9 +318,6 @@@ static void vblank_disable_fn(unsigned unsigned int pipe = vblank->pipe; unsigned long irqflags; - if (!dev->vblank_disable_allowed) - return; - spin_lock_irqsave(&dev->vbl_lock, irqflags); if (atomic_read(&vblank->refcount) == 0 && vblank->enabled) { DRM_DEBUG("disabling vblank on crtc %u\n", pipe); @@@ -356,7 -451,6 +387,7 @@@ int drm_vblank_init(struct drm_device * init_waitqueue_head(&vblank->queue); setup_timer(&vblank->disable_timer, vblank_disable_fn, (unsigned long)vblank); + seqlock_init(&vblank->seqlock); } DRM_INFO("Supports vblank timestamp caching Rev 2 (21.10.2013).\n"); @@@ -374,6 -468,8 +405,6 @@@ "get_vblank_timestamp == NULL\n"); } - dev->vblank_disable_allowed = false; - return 0; err: @@@ -926,19 -1022,25 +957,19 @@@ u32 drm_vblank_count_and_time(struct dr struct timeval *vblanktime) { struct drm_vblank_crtc *vblank = &dev->vblank[pipe]; - int count = DRM_TIMESTAMP_MAXRETRIES; - u32 cur_vblank; + u32 vblank_count; + unsigned int seq; if (WARN_ON(pipe >= dev->num_crtcs)) return 0; - /* - * Vblank timestamps are read lockless. To ensure consistency the vblank - * counter is rechecked and ordering is ensured using memory barriers. - * This works like a seqlock. The write-side barriers are in store_vblank. - */ do { - cur_vblank = vblank->count; - smp_rmb(); - *vblanktime = vblanktimestamp(dev, pipe, cur_vblank); - smp_rmb(); - } while (cur_vblank != vblank->count && --count > 0); + seq = read_seqbegin(&vblank->seqlock); + vblank_count = vblank->count; + *vblanktime = vblank->time; + } while (read_seqretry(&vblank->seqlock, seq)); - return cur_vblank; + return vblank_count; } EXPORT_SYMBOL(drm_vblank_count_and_time); @@@ -1514,6 -1616,7 +1545,6 @@@ void drm_vblank_post_modeset(struct drm if (vblank->inmodeset) { spin_lock_irqsave(&dev->vbl_lock, irqflags); - dev->vblank_disable_allowed = true; drm_reset_vblank_timestamp(dev, pipe); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); diff --combined drivers/gpu/drm/i915/i915_dma.c index b3198fcd0536,a8c79f6512a4..fd06bff216ff --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@@ -186,7 -186,7 +186,7 @@@ static int i915_getparam(struct drm_dev value = 1; break; case I915_PARAM_HAS_SEMAPHORES: - value = i915_semaphore_is_enabled(dev); + value = i915_semaphore_is_enabled(dev_priv); break; case I915_PARAM_HAS_PRIME_VMAP_FLUSH: value = 1; @@@ -204,7 -204,7 +204,7 @@@ value = 1; break; case I915_PARAM_CMD_PARSER_VERSION: - value = i915_cmd_parser_get_version(); + value = i915_cmd_parser_get_version(dev_priv); break; case I915_PARAM_HAS_COHERENT_PHYS_GTT: value = 1; @@@ -223,8 -223,7 +223,7 @@@ return -ENODEV; break; case I915_PARAM_HAS_GPU_RESET: - value = i915.enable_hangcheck && - intel_has_gpu_reset(dev); + value = i915.enable_hangcheck && intel_has_gpu_reset(dev_priv); break; case I915_PARAM_HAS_RESOURCE_STREAMER: value = HAS_RESOURCE_STREAMER(dev); @@@ -425,6 -424,43 +424,43 @@@ static const struct vga_switcheroo_clie .can_switch = i915_switcheroo_can_switch, }; + static void i915_gem_fini(struct drm_device *dev) + { + struct drm_i915_private *dev_priv = to_i915(dev); + + /* + * Neither the BIOS, ourselves or any other kernel + * expects the system to be in execlists mode on startup, + * so we need to reset the GPU back to legacy mode. And the only + * known way to disable logical contexts is through a GPU reset. + * + * So in order to leave the system in a known default configuration, + * always reset the GPU upon unload. Afterwards we then clean up the + * GEM state tracking, flushing off the requests and leaving the + * system in a known idle state. + * + * Note that is of the upmost importance that the GPU is idle and + * all stray writes are flushed *before* we dismantle the backing + * storage for the pinned objects. + * + * However, since we are uncertain that reseting the GPU on older + * machines is a good idea, we don't - just in case it leaves the + * machine in an unusable condition. + */ + if (HAS_HW_CONTEXTS(dev)) { + int reset = intel_gpu_reset(dev_priv, ALL_ENGINES); + WARN_ON(reset && reset != -ENODEV); + } + + mutex_lock(&dev->struct_mutex); + i915_gem_reset(dev); + i915_gem_cleanup_engines(dev); + i915_gem_context_fini(dev); + mutex_unlock(&dev->struct_mutex); + + WARN_ON(!list_empty(&to_i915(dev)->context_list)); + } + static int i915_load_modeset_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@@ -454,6 -490,9 +490,9 @@@ if (ret) goto cleanup_vga_client; + /* must happen before intel_power_domains_init_hw() on VLV/CHV */ + intel_update_rawclk(dev_priv); + intel_power_domains_init_hw(dev_priv, false); intel_csr_ucode_init(dev_priv); @@@ -476,6 -515,9 +515,6 @@@ intel_modeset_gem_init(dev); - /* Always safe in the mode setting case. */ - /* FIXME: do pre/post-mode set stuff in core KMS code */ - dev->vblank_disable_allowed = true; if (INTEL_INFO(dev)->num_pipes == 0) return 0; @@@ -503,10 -545,7 +542,7 @@@ return 0; cleanup_gem: - mutex_lock(&dev->struct_mutex); - i915_gem_cleanup_engines(dev); - i915_gem_context_fini(dev); - mutex_unlock(&dev->struct_mutex); + i915_gem_fini(dev); cleanup_irq: intel_guc_ucode_fini(dev); drm_irq_uninstall(dev); @@@ -850,7 -889,7 +886,7 @@@ static void intel_device_info_runtime_i DRM_INFO("Display disabled (module parameter)\n"); info->num_pipes = 0; } else if (info->num_pipes > 0 && - (INTEL_INFO(dev)->gen == 7 || INTEL_INFO(dev)->gen == 8) && + (IS_GEN7(dev_priv) || IS_GEN8(dev_priv)) && HAS_PCH_SPLIT(dev)) { u32 fuse_strap = I915_READ(FUSE_STRAP); u32 sfuse_strap = I915_READ(SFUSE_STRAP); @@@ -874,7 -913,7 +910,7 @@@ DRM_INFO("PipeC fused off\n"); info->num_pipes -= 1; } - } else if (info->num_pipes > 0 && INTEL_INFO(dev)->gen == 9) { + } else if (info->num_pipes > 0 && IS_GEN9(dev_priv)) { u32 dfsm = I915_READ(SKL_DFSM); u8 disabled_mask = 0; bool invalid; @@@ -915,9 -954,11 +951,11 @@@ else if (INTEL_INFO(dev)->gen >= 9) gen9_sseu_info_init(dev); - /* Snooping is broken on BXT A stepping. */ info->has_snoop = !info->has_llc; - info->has_snoop &= !IS_BXT_REVID(dev, 0, BXT_REVID_A1); + + /* Snooping is broken on BXT A stepping. */ + if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) + info->has_snoop = false; DRM_DEBUG_DRIVER("slice total: %u\n", info->slice_total); DRM_DEBUG_DRIVER("subslice total: %u\n", info->subslice_total); @@@ -930,6 -971,20 +968,20 @@@ info->has_subslice_pg ? "y" : "n"); DRM_DEBUG_DRIVER("has EU power gating: %s\n", info->has_eu_pg ? "y" : "n"); + + i915.enable_execlists = + intel_sanitize_enable_execlists(dev_priv, + i915.enable_execlists); + + /* + * i915.enable_ppgtt is read-only, so do an early pass to validate the + * user's requested state against the hardware/driver capabilities. We + * do this now so that we can print out any log messages once rather + * than every time we check intel_enable_ppgtt(). + */ + i915.enable_ppgtt = + intel_sanitize_enable_ppgtt(dev_priv, i915.enable_ppgtt); + DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915.enable_ppgtt); } static void intel_init_dpio(struct drm_i915_private *dev_priv) @@@ -1020,6 -1075,9 +1072,9 @@@ static int i915_driver_init_early(struc memcpy(device_info, info, sizeof(dev_priv->info)); device_info->device_id = dev->pdev->device; + BUG_ON(device_info->gen > sizeof(device_info->gen_mask) * BITS_PER_BYTE); + device_info->gen_mask = BIT(device_info->gen - 1); + spin_lock_init(&dev_priv->irq_lock); spin_lock_init(&dev_priv->gpu_error.lock); mutex_init(&dev_priv->backlight_lock); @@@ -1137,7 -1195,7 +1192,7 @@@ static int i915_driver_init_mmio(struc if (ret < 0) goto put_bridge; - intel_uncore_init(dev); + intel_uncore_init(dev_priv); return 0; @@@ -1155,7 -1213,7 +1210,7 @@@ static void i915_driver_cleanup_mmio(st { struct drm_device *dev = dev_priv->dev; - intel_uncore_fini(dev); + intel_uncore_fini(dev_priv); i915_mmio_cleanup(dev); pci_dev_put(dev_priv->bridge_dev); } @@@ -1206,8 -1264,15 +1261,15 @@@ static int i915_driver_init_hw(struct d pci_set_master(dev->pdev); /* overlay on gen2 is broken and can't address above 1G */ - if (IS_GEN2(dev)) - dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30)); + if (IS_GEN2(dev)) { + ret = dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30)); + if (ret) { + DRM_ERROR("failed to set DMA mask\n"); + + goto out_ggtt; + } + } + /* 965GM sometimes incorrectly writes to hardware status page (HWS) * using 32bit addressing, overwriting memory if HWS is located @@@ -1217,8 -1282,15 +1279,15 @@@ * behaviour if any general state is accessed within a page above 4GB, * which also needs to be handled carefully. */ - if (IS_BROADWATER(dev) || IS_CRESTLINE(dev)) - dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32)); + if (IS_BROADWATER(dev) || IS_CRESTLINE(dev)) { + ret = dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32)); + + if (ret) { + DRM_ERROR("failed to set DMA mask\n"); + + goto out_ggtt; + } + } aperture_size = ggtt->mappable_end; @@@ -1236,7 -1308,7 +1305,7 @@@ pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY, PM_QOS_DEFAULT_VALUE); - intel_uncore_sanitize(dev); + intel_uncore_sanitize(dev_priv); intel_opregion_setup(dev); @@@ -1300,7 -1372,7 +1369,7 @@@ static void i915_driver_register(struc * Notify a valid surface after modesetting, * when running inside a VM. */ - if (intel_vgpu_active(dev)) + if (intel_vgpu_active(dev_priv)) I915_WRITE(vgtif_reg(display_ready), VGT_DRV_DISPLAY_READY); i915_setup_sysfs(dev); @@@ -1459,10 -1531,7 +1528,7 @@@ int i915_driver_unload(struct drm_devic flush_workqueue(dev_priv->wq); intel_guc_ucode_fini(dev); - mutex_lock(&dev->struct_mutex); - i915_gem_cleanup_engines(dev); - i915_gem_context_fini(dev); - mutex_unlock(&dev->struct_mutex); + i915_gem_fini(dev); intel_fbc_cleanup_cfb(dev_priv); intel_power_domains_fini(dev_priv); @@@ -1570,15 -1639,15 +1636,15 @@@ const struct drm_ioctl_desc i915_ioctls DRM_IOCTL_DEF_DRV(I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id, 0), DRM_IOCTL_DEF_DRV(I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_RENDER_ALLOW), - DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image, DRM_MASTER|DRM_CONTROL_ALLOW), - DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs, DRM_MASTER|DRM_CONTROL_ALLOW), + DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW), + DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW), DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW), DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_RENDER_ALLOW), - DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_get_reset_stats_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_gem_context_reset_stats_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_GETPARAM, i915_gem_context_getparam_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_SETPARAM, i915_gem_context_setparam_ioctl, DRM_RENDER_ALLOW), diff --combined drivers/gpu/drm/i915/i915_drv.c index e264a90d1b0d,dba03c026151..61bf5a92040d --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@@ -35,9 -35,11 +35,9 @@@ #include "i915_trace.h" #include "intel_drv.h" -#include #include #include #include -#include #include #include @@@ -298,22 -300,26 +298,26 @@@ static const struct intel_device_info i static const struct intel_device_info intel_broadwell_d_info = { BDW_FEATURES, .gen = 8, + .is_broadwell = 1, }; static const struct intel_device_info intel_broadwell_m_info = { BDW_FEATURES, .gen = 8, .is_mobile = 1, + .is_broadwell = 1, }; static const struct intel_device_info intel_broadwell_gt3d_info = { BDW_FEATURES, .gen = 8, + .is_broadwell = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, }; static const struct intel_device_info intel_broadwell_gt3m_info = { BDW_FEATURES, .gen = 8, .is_mobile = 1, + .is_broadwell = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, }; @@@ -528,9 -534,9 +532,9 @@@ void intel_detect_pch(struct drm_devic pci_dev_put(pch); } - bool i915_semaphore_is_enabled(struct drm_device *dev) + bool i915_semaphore_is_enabled(struct drm_i915_private *dev_priv) { - if (INTEL_INFO(dev)->gen < 6) + if (INTEL_GEN(dev_priv) < 6) return false; if (i915.semaphores >= 0) @@@ -540,13 -546,9 +544,9 @@@ if (i915.enable_execlists) return false; - /* Until we get further testing... */ - if (IS_GEN8(dev)) - return false; - #ifdef CONFIG_INTEL_IOMMU /* Enable semaphores on SNB when IO remapping is off */ - if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) + if (IS_GEN6(dev_priv) && intel_iommu_gfx_mapped) return false; #endif @@@ -608,7 -610,7 +608,7 @@@ static int i915_drm_suspend(struct drm_ intel_guc_suspend(dev); - intel_suspend_gt_powersave(dev); + intel_suspend_gt_powersave(dev_priv); intel_display_suspend(dev); @@@ -628,7 -630,7 +628,7 @@@ opregion_target_state = suspend_to_idle(dev_priv) ? PCI_D1 : PCI_D3cold; intel_opregion_notify_adapter(dev, opregion_target_state); - intel_uncore_forcewake_reset(dev, false); + intel_uncore_forcewake_reset(dev_priv, false); intel_opregion_fini(dev); intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true); @@@ -775,7 -777,7 +775,7 @@@ static int i915_drm_resume(struct drm_d spin_lock_irq(&dev_priv->irq_lock); if (dev_priv->display.hpd_irq_setup) - dev_priv->display.hpd_irq_setup(dev); + dev_priv->display.hpd_irq_setup(dev_priv); spin_unlock_irq(&dev_priv->irq_lock); intel_dp_mst_resume(dev); @@@ -868,9 -870,9 +868,9 @@@ static int i915_drm_resume_early(struc DRM_ERROR("Resume prepare failed: %d, continuing anyway\n", ret); - intel_uncore_early_sanitize(dev, true); + intel_uncore_early_sanitize(dev_priv, true); - if (IS_BROXTON(dev)) { + if (IS_BROXTON(dev_priv)) { if (!dev_priv->suspended_to_idle) gen9_sanitize_dc_state(dev_priv); bxt_disable_dc9(dev_priv); @@@ -878,7 -880,7 +878,7 @@@ hsw_disable_pc8(dev_priv); } - intel_uncore_sanitize(dev); + intel_uncore_sanitize(dev_priv); if (IS_BROXTON(dev_priv) || !(dev_priv->suspended_to_idle && dev_priv->csr.dmc_payload)) @@@ -921,14 -923,14 +921,14 @@@ int i915_resume_switcheroo(struct drm_d * - re-init interrupt state * - re-init display */ - int i915_reset(struct drm_device *dev) + int i915_reset(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_device *dev = dev_priv->dev; struct i915_gpu_error *error = &dev_priv->gpu_error; unsigned reset_counter; int ret; - intel_reset_gt_powersave(dev); + intel_reset_gt_powersave(dev_priv); mutex_lock(&dev->struct_mutex); @@@ -944,7 -946,7 +944,7 @@@ i915_gem_reset(dev); - ret = intel_gpu_reset(dev, ALL_ENGINES); + ret = intel_gpu_reset(dev_priv, ALL_ENGINES); /* Also reset the gpu hangman. */ if (error->stop_rings != 0) { @@@ -999,7 -1001,7 +999,7 @@@ * of re-init after reset. */ if (INTEL_INFO(dev)->gen > 5) - intel_enable_gt_powersave(dev); + intel_enable_gt_powersave(dev_priv); return 0; @@@ -1028,7 -1030,13 +1028,7 @@@ static int i915_pci_probe(struct pci_de if (PCI_FUNC(pdev->devfn)) return -ENODEV; - /* - * apple-gmux is needed on dual GPU MacBook Pro - * to probe the panel if we're the inactive GPU. - */ - if (IS_ENABLED(CONFIG_VGA_ARB) && IS_ENABLED(CONFIG_VGA_SWITCHEROO) && - apple_gmux_present() && pdev != vga_default_device() && - !vga_switcheroo_handler_flags()) + if (vga_switcheroo_client_probe_defer(pdev)) return -EPROBE_DEFER; return drm_get_pci_dev(pdev, ent, &driver); @@@ -1107,6 -1115,49 +1107,49 @@@ static int i915_pm_resume(struct devic return i915_drm_resume(drm_dev); } + /* freeze: before creating the hibernation_image */ + static int i915_pm_freeze(struct device *dev) + { + return i915_pm_suspend(dev); + } + + static int i915_pm_freeze_late(struct device *dev) + { + int ret; + + ret = i915_pm_suspend_late(dev); + if (ret) + return ret; + + ret = i915_gem_freeze_late(dev_to_i915(dev)); + if (ret) + return ret; + + return 0; + } + + /* thaw: called after creating the hibernation image, but before turning off. */ + static int i915_pm_thaw_early(struct device *dev) + { + return i915_pm_resume_early(dev); + } + + static int i915_pm_thaw(struct device *dev) + { + return i915_pm_resume(dev); + } + + /* restore: called after loading the hibernation image. */ + static int i915_pm_restore_early(struct device *dev) + { + return i915_pm_resume_early(dev); + } + + static int i915_pm_restore(struct device *dev) + { + return i915_pm_resume(dev); + } + /* * Save all Gunit registers that may be lost after a D3 and a subsequent * S0i[R123] transition. The list of registers needing a save/restore is @@@ -1470,7 -1521,7 +1513,7 @@@ static int intel_runtime_suspend(struc struct drm_i915_private *dev_priv = dev->dev_private; int ret; - if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6(dev)))) + if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6()))) return -ENODEV; if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev))) @@@ -1509,7 -1560,7 +1552,7 @@@ intel_guc_suspend(dev); - intel_suspend_gt_powersave(dev); + intel_suspend_gt_powersave(dev_priv); intel_runtime_pm_disable_interrupts(dev_priv); ret = 0; @@@ -1531,7 -1582,7 +1574,7 @@@ return ret; } - intel_uncore_forcewake_reset(dev, false); + intel_uncore_forcewake_reset(dev_priv, false); enable_rpm_wakeref_asserts(dev_priv); WARN_ON_ONCE(atomic_read(&dev_priv->pm.wakeref_count)); @@@ -1612,7 -1663,7 +1655,7 @@@ static int intel_runtime_resume(struct * we can do is to hope that things will still work (and disable RPM). */ i915_gem_init_swizzling(dev); - gen6_update_ring_freq(dev); + gen6_update_ring_freq(dev_priv); intel_runtime_pm_enable_interrupts(dev_priv); @@@ -1624,7 -1675,7 +1667,7 @@@ if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) intel_hpd_init(dev_priv); - intel_enable_gt_powersave(dev); + intel_enable_gt_powersave(dev_priv); enable_rpm_wakeref_asserts(dev_priv); @@@ -1661,14 -1712,14 +1704,14 @@@ static const struct dev_pm_ops i915_pm_ * @restore, @restore_early : called after rebooting and restoring the * hibernation image [PMSG_RESTORE] */ - .freeze = i915_pm_suspend, - .freeze_late = i915_pm_suspend_late, - .thaw_early = i915_pm_resume_early, - .thaw = i915_pm_resume, + .freeze = i915_pm_freeze, + .freeze_late = i915_pm_freeze_late, + .thaw_early = i915_pm_thaw_early, + .thaw = i915_pm_thaw, .poweroff = i915_pm_suspend, .poweroff_late = i915_pm_poweroff_late, - .restore_early = i915_pm_resume_early, - .restore = i915_pm_resume, + .restore_early = i915_pm_restore_early, + .restore = i915_pm_restore, /* S0ix (via runtime suspend) event handlers */ .runtime_suspend = intel_runtime_suspend, diff --combined drivers/gpu/drm/i915/i915_drv.h index 5faacc6e548d,33a8d4e3ec21..b4ea941d87f3 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@@ -66,7 -66,7 +66,7 @@@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" - #define DRIVER_DATE "20160425" + #define DRIVER_DATE "20160522" #undef WARN_ON /* Many gcc seem to no see through this and fall over :( */ @@@ -324,6 -324,12 +324,12 @@@ struct i915_hotplug &dev->mode_config.plane_list, \ base.head) + #define for_each_intel_plane_mask(dev, intel_plane, plane_mask) \ + list_for_each_entry(intel_plane, &dev->mode_config.plane_list, \ + base.head) \ + for_each_if ((plane_mask) & \ + (1 << drm_plane_index(&intel_plane->base))) + #define for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) \ list_for_each_entry(intel_plane, \ &(dev)->mode_config.plane_list, \ @@@ -333,6 -339,10 +339,10 @@@ #define for_each_intel_crtc(dev, intel_crtc) \ list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) + #define for_each_intel_crtc_mask(dev, intel_crtc, crtc_mask) \ + list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) \ + for_each_if ((crtc_mask) & (1 << drm_crtc_index(&intel_crtc->base))) + #define for_each_intel_encoder(dev, intel_encoder) \ list_for_each_entry(intel_encoder, \ &(dev)->mode_config.encoder_list, \ @@@ -588,6 -598,7 +598,7 @@@ struct drm_i915_display_funcs struct intel_crtc_state *newstate); void (*initial_watermarks)(struct intel_crtc_state *cstate); void (*optimize_watermarks)(struct intel_crtc_state *cstate); + int (*compute_global_watermarks)(struct drm_atomic_state *state); void (*update_wm)(struct drm_crtc *crtc); int (*modeset_calc_cdclk)(struct drm_atomic_state *state); void (*modeset_commit_cdclk)(struct drm_atomic_state *state); @@@ -612,7 -623,7 +623,7 @@@ struct drm_i915_gem_object *obj, struct drm_i915_gem_request *req, uint32_t flags); - void (*hpd_irq_setup)(struct drm_device *dev); + void (*hpd_irq_setup)(struct drm_i915_private *dev_priv); /* clock updates for mode set */ /* cursor updates */ /* render clock increase/decrease */ @@@ -735,6 -746,7 +746,7 @@@ struct intel_csr func(is_valleyview) sep \ func(is_cherryview) sep \ func(is_haswell) sep \ + func(is_broadwell) sep \ func(is_skylake) sep \ func(is_broxton) sep \ func(is_kabylake) sep \ @@@ -757,9 -769,10 +769,10 @@@ struct intel_device_info { u32 display_mmio_offset; u16 device_id; - u8 num_pipes:3; + u8 num_pipes; u8 num_sprites[I915_MAX_PIPES]; u8 gen; + u16 gen_mask; u8 ring_mask; /* Rings supported by the HW */ DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG, SEP_SEMICOLON); /* Register offsets for the various display pipes and transcoders */ @@@ -851,6 -864,9 +864,9 @@@ struct intel_context struct i915_ctx_hang_stats hang_stats; struct i915_hw_ppgtt *ppgtt; + /* Unique identifier for this context, used by the hw for tracking */ + unsigned hw_id; + /* Legacy ring buffer submission */ struct { struct drm_i915_gem_object *rcs_state; @@@ -865,6 -881,7 +881,7 @@@ struct i915_vma *lrc_vma; u64 lrc_desc; uint32_t *lrc_reg_state; + bool initialised; } engine[I915_NUM_ENGINES]; struct list_head link; @@@ -1488,6 -1505,7 +1505,7 @@@ struct intel_vbt_data bool present; bool active_low_pwm; u8 min_brightness; /* min_brightness/255 of max */ + enum intel_backlight_type type; } backlight; /* MIPI DSI */ @@@ -1580,7 -1598,7 +1598,7 @@@ struct skl_ddb_allocation }; struct skl_wm_values { - bool dirty[I915_MAX_PIPES]; + unsigned dirty_pipes; struct skl_ddb_allocation ddb; uint32_t wm_linetime[I915_MAX_PIPES]; uint32_t plane[I915_MAX_PIPES][I915_MAX_PLANES][8]; @@@ -1838,6 -1856,13 +1856,13 @@@ struct drm_i915_private DECLARE_HASHTABLE(mm_structs, 7); struct mutex mm_lock; + /* The hw wants to have a stable context identifier for the lifetime + * of the context (for OA, PASID, faults, etc). This is limited + * in execlists to 21 bits. + */ + struct ida context_hw_ida; + #define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */ + /* Kernel Modesetting */ struct drm_crtc *plane_to_crtc_mapping[I915_MAX_PIPES]; @@@ -1950,9 -1975,6 +1975,6 @@@ */ uint16_t skl_latency[8]; - /* Committed wm config */ - struct intel_wm_config config; - /* * The skl_wm_values structure is a bit too big for stack * allocation, so we keep the staging struct where we store @@@ -1975,6 -1997,13 +1997,13 @@@ * cstate->wm.need_postvbl_update. */ struct mutex wm_mutex; + + /* + * Set during HW readout of watermarks/DDB. Some platforms + * need to know when we're still using BIOS-provided values + * (which we don't fully trust). + */ + bool distrust_bios_wm; } wm; struct i915_runtime_pm pm; @@@ -2227,9 -2256,75 +2256,75 @@@ struct drm_i915_gem_object }; #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base) - void i915_gem_track_fb(struct drm_i915_gem_object *old, - struct drm_i915_gem_object *new, - unsigned frontbuffer_bits); + /* + * Optimised SGL iterator for GEM objects + */ + static __always_inline struct sgt_iter { + struct scatterlist *sgp; + union { + unsigned long pfn; + dma_addr_t dma; + }; + unsigned int curr; + unsigned int max; + } __sgt_iter(struct scatterlist *sgl, bool dma) { + struct sgt_iter s = { .sgp = sgl }; + + if (s.sgp) { + s.max = s.curr = s.sgp->offset; + s.max += s.sgp->length; + if (dma) + s.dma = sg_dma_address(s.sgp); + else + s.pfn = page_to_pfn(sg_page(s.sgp)); + } + + return s; + } + + /** + * __sg_next - return the next scatterlist entry in a list + * @sg: The current sg entry + * + * Description: + * If the entry is the last, return NULL; otherwise, step to the next + * element in the array (@sg@+1). If that's a chain pointer, follow it; + * otherwise just return the pointer to the current element. + **/ + static inline struct scatterlist *__sg_next(struct scatterlist *sg) + { + #ifdef CONFIG_DEBUG_SG + BUG_ON(sg->sg_magic != SG_MAGIC); + #endif + return sg_is_last(sg) ? NULL : + likely(!sg_is_chain(++sg)) ? sg : + sg_chain_ptr(sg); + } + + /** + * for_each_sgt_dma - iterate over the DMA addresses of the given sg_table + * @__dmap: DMA address (output) + * @__iter: 'struct sgt_iter' (iterator state, internal) + * @__sgt: sg_table to iterate over (input) + */ + #define for_each_sgt_dma(__dmap, __iter, __sgt) \ + for ((__iter) = __sgt_iter((__sgt)->sgl, true); \ + ((__dmap) = (__iter).dma + (__iter).curr); \ + (((__iter).curr += PAGE_SIZE) < (__iter).max) || \ + ((__iter) = __sgt_iter(__sg_next((__iter).sgp), true), 0)) + + /** + * for_each_sgt_page - iterate over the pages of the given sg_table + * @__pp: page pointer (output) + * @__iter: 'struct sgt_iter' (iterator state, internal) + * @__sgt: sg_table to iterate over (input) + */ + #define for_each_sgt_page(__pp, __iter, __sgt) \ + for ((__iter) = __sgt_iter((__sgt)->sgl, false); \ + ((__pp) = (__iter).pfn == 0 ? NULL : \ + pfn_to_page((__iter).pfn + ((__iter).curr >> PAGE_SHIFT))); \ + (((__iter).curr += PAGE_SIZE) < (__iter).max) || \ + ((__iter) = __sgt_iter(__sg_next((__iter).sgp), false), 0)) /** * Request queue structure. @@@ -2278,6 -2373,9 +2373,9 @@@ struct drm_i915_gem_request /** Position in the ringbuffer of the end of the whole request */ u32 tail; + /** Preallocate space in the ringbuffer for the emitting the request */ + u32 reserved_space; + /** * Context and ring buffer related to this request * Contexts are refcounted, so when this request is associated with a @@@ -2291,6 -2389,17 +2389,17 @@@ struct intel_context *ctx; struct intel_ringbuffer *ringbuf; + /** + * Context related to the previous request. + * As the contexts are accessed by the hardware until the switch is + * completed to a new context, the hardware may still be writing + * to the context object after the breadcrumb is visible. We must + * not unpin/unbind/prune that object whilst still active and so + * we keep the previous context pinned until the following (this) + * request is retired. + */ + struct intel_context *previous_context; + /** Batch buffer related to this request if any (used for error state dump only) */ struct drm_i915_gem_object *batch_obj; @@@ -2327,6 -2436,8 +2436,8 @@@ /** Execlists no. of times this request has been sent to the ELSP */ int elsp_submitted; + /** Execlists context hardware id. */ + unsigned ctx_hw_id; }; struct drm_i915_gem_request * __must_check @@@ -2359,23 -2470,9 +2470,9 @@@ i915_gem_request_reference(struct drm_i static inline void i915_gem_request_unreference(struct drm_i915_gem_request *req) { - WARN_ON(!mutex_is_locked(&req->engine->dev->struct_mutex)); kref_put(&req->ref, i915_gem_request_free); } - static inline void - i915_gem_request_unreference__unlocked(struct drm_i915_gem_request *req) - { - struct drm_device *dev; - - if (!req) - return; - - dev = req->engine->dev; - if (kref_put_mutex(&req->ref, i915_gem_request_free, &dev->struct_mutex)) - mutex_unlock(&dev->struct_mutex); - } - static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst, struct drm_i915_gem_request *src) { @@@ -2503,9 -2600,29 +2600,29 @@@ struct drm_i915_cmd_table #define INTEL_INFO(p) (&__I915__(p)->info) #define INTEL_GEN(p) (INTEL_INFO(p)->gen) #define INTEL_DEVID(p) (INTEL_INFO(p)->device_id) - #define INTEL_REVID(p) (__I915__(p)->dev->pdev->revision) #define REVID_FOREVER 0xff + #define INTEL_REVID(p) (__I915__(p)->dev->pdev->revision) + + #define GEN_FOREVER (0) + /* + * Returns true if Gen is in inclusive range [Start, End]. + * + * Use GEN_FOREVER for unbound start and or end. + */ + #define IS_GEN(p, s, e) ({ \ + unsigned int __s = (s), __e = (e); \ + BUILD_BUG_ON(!__builtin_constant_p(s)); \ + BUILD_BUG_ON(!__builtin_constant_p(e)); \ + if ((__s) != GEN_FOREVER) \ + __s = (s) - 1; \ + if ((__e) == GEN_FOREVER) \ + __e = BITS_PER_LONG - 1; \ + else \ + __e = (e) - 1; \ + !!(INTEL_INFO(p)->gen_mask & GENMASK((__e), (__s))); \ + }) + /* * Return true if revision is in range [since,until] inclusive. * @@@ -2538,7 -2655,7 +2655,7 @@@ #define IS_VALLEYVIEW(dev) (INTEL_INFO(dev)->is_valleyview) #define IS_CHERRYVIEW(dev) (INTEL_INFO(dev)->is_cherryview) #define IS_HASWELL(dev) (INTEL_INFO(dev)->is_haswell) - #define IS_BROADWELL(dev) (!INTEL_INFO(dev)->is_cherryview && IS_GEN8(dev)) + #define IS_BROADWELL(dev) (INTEL_INFO(dev)->is_broadwell) #define IS_SKYLAKE(dev) (INTEL_INFO(dev)->is_skylake) #define IS_BROXTON(dev) (INTEL_INFO(dev)->is_broxton) #define IS_KABYLAKE(dev) (INTEL_INFO(dev)->is_kabylake) @@@ -2606,14 -2723,14 +2723,14 @@@ * have their own (e.g. HAS_PCH_SPLIT for ILK+ display, IS_foo for particular * chips, etc.). */ - #define IS_GEN2(dev) (INTEL_INFO(dev)->gen == 2) - #define IS_GEN3(dev) (INTEL_INFO(dev)->gen == 3) - #define IS_GEN4(dev) (INTEL_INFO(dev)->gen == 4) - #define IS_GEN5(dev) (INTEL_INFO(dev)->gen == 5) - #define IS_GEN6(dev) (INTEL_INFO(dev)->gen == 6) - #define IS_GEN7(dev) (INTEL_INFO(dev)->gen == 7) - #define IS_GEN8(dev) (INTEL_INFO(dev)->gen == 8) - #define IS_GEN9(dev) (INTEL_INFO(dev)->gen == 9) + #define IS_GEN2(dev) (INTEL_INFO(dev)->gen_mask & BIT(1)) + #define IS_GEN3(dev) (INTEL_INFO(dev)->gen_mask & BIT(2)) + #define IS_GEN4(dev) (INTEL_INFO(dev)->gen_mask & BIT(3)) + #define IS_GEN5(dev) (INTEL_INFO(dev)->gen_mask & BIT(4)) + #define IS_GEN6(dev) (INTEL_INFO(dev)->gen_mask & BIT(5)) + #define IS_GEN7(dev) (INTEL_INFO(dev)->gen_mask & BIT(6)) + #define IS_GEN8(dev) (INTEL_INFO(dev)->gen_mask & BIT(7)) + #define IS_GEN9(dev) (INTEL_INFO(dev)->gen_mask & BIT(8)) #define RENDER_RING (1<gen >= 6) - #define HAS_RC6p(dev) (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev)) + #define HAS_RC6p(dev) (IS_GEN6(dev) || IS_IVYBRIDGE(dev)) #define HAS_CSR(dev) (IS_GEN9(dev)) @@@ -2740,6 -2857,9 +2857,9 @@@ extern int i915_max_ioctl extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state); extern int i915_resume_switcheroo(struct drm_device *dev); + int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv, + int enable_ppgtt); + /* i915_dma.c */ void __printf(3, 4) __i915_printk(struct drm_i915_private *dev_priv, const char *level, @@@ -2760,9 -2880,9 +2880,9 @@@ extern void i915_driver_postclose(struc extern long i915_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); #endif - extern int intel_gpu_reset(struct drm_device *dev, u32 engine_mask); - extern bool intel_has_gpu_reset(struct drm_device *dev); - extern int i915_reset(struct drm_device *dev); + extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask); + extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv); + extern int i915_reset(struct drm_i915_private *dev_priv); extern int intel_guc_reset(struct drm_i915_private *dev_priv); extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine); extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv); @@@ -2772,30 -2892,33 +2892,33 @@@ extern void i915_update_gfx_val(struct int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on); /* intel_hotplug.c */ - void intel_hpd_irq_handler(struct drm_device *dev, u32 pin_mask, u32 long_mask); + void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, + u32 pin_mask, u32 long_mask); void intel_hpd_init(struct drm_i915_private *dev_priv); void intel_hpd_init_work(struct drm_i915_private *dev_priv); void intel_hpd_cancel_work(struct drm_i915_private *dev_priv); bool intel_hpd_pin_to_port(enum hpd_pin pin, enum port *port); /* i915_irq.c */ - void i915_queue_hangcheck(struct drm_device *dev); + void i915_queue_hangcheck(struct drm_i915_private *dev_priv); __printf(3, 4) - void i915_handle_error(struct drm_device *dev, u32 engine_mask, + void i915_handle_error(struct drm_i915_private *dev_priv, + u32 engine_mask, const char *fmt, ...); extern void intel_irq_init(struct drm_i915_private *dev_priv); int intel_irq_install(struct drm_i915_private *dev_priv); void intel_irq_uninstall(struct drm_i915_private *dev_priv); - extern void intel_uncore_sanitize(struct drm_device *dev); - extern void intel_uncore_early_sanitize(struct drm_device *dev, + extern void intel_uncore_sanitize(struct drm_i915_private *dev_priv); + extern void intel_uncore_early_sanitize(struct drm_i915_private *dev_priv, bool restore_forcewake); - extern void intel_uncore_init(struct drm_device *dev); + extern void intel_uncore_init(struct drm_i915_private *dev_priv); extern bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv); extern bool intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv); - extern void intel_uncore_fini(struct drm_device *dev); - extern void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore); + extern void intel_uncore_fini(struct drm_i915_private *dev_priv); + extern void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv, + bool restore); const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id); void intel_uncore_forcewake_get(struct drm_i915_private *dev_priv, enum forcewake_domains domains); @@@ -2811,9 -2934,9 +2934,9 @@@ void intel_uncore_forcewake_put__locked u64 intel_uncore_edram_size(struct drm_i915_private *dev_priv); void assert_forcewakes_inactive(struct drm_i915_private *dev_priv); - static inline bool intel_vgpu_active(struct drm_device *dev) + static inline bool intel_vgpu_active(struct drm_i915_private *dev_priv) { - return to_i915(dev)->vgpu.active; + return dev_priv->vgpu.active; } void @@@ -2909,7 -3032,7 +3032,7 @@@ int i915_gem_set_tiling(struct drm_devi struct drm_file *file_priv); int i915_gem_get_tiling(struct drm_device *dev, void *data, struct drm_file *file_priv); - int i915_gem_init_userptr(struct drm_device *dev); + void i915_gem_init_userptr(struct drm_i915_private *dev_priv); int i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file); int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, @@@ -2919,11 -3042,13 +3042,13 @@@ int i915_gem_wait_ioctl(struct drm_devi void i915_gem_load_init(struct drm_device *dev); void i915_gem_load_cleanup(struct drm_device *dev); void i915_gem_load_init_fences(struct drm_i915_private *dev_priv); + int i915_gem_freeze_late(struct drm_i915_private *dev_priv); + void *i915_gem_object_alloc(struct drm_device *dev); void i915_gem_object_free(struct drm_i915_gem_object *obj); void i915_gem_object_init(struct drm_i915_gem_object *obj, const struct drm_i915_gem_object_ops *ops); - struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, + struct drm_i915_gem_object *i915_gem_object_create(struct drm_device *dev, size_t size); struct drm_i915_gem_object *i915_gem_object_create_from_data( struct drm_device *dev, const void *data, size_t size); @@@ -3054,6 -3179,11 +3179,11 @@@ int i915_gem_dumb_create(struct drm_fil struct drm_mode_create_dumb *args); int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev, uint32_t handle, uint64_t *offset); + + void i915_gem_track_fb(struct drm_i915_gem_object *old, + struct drm_i915_gem_object *new, + unsigned frontbuffer_bits); + /** * Returns true if seq1 is later than seq2. */ @@@ -3081,13 -3211,13 +3211,13 @@@ static inline bool i915_gem_request_com req->seqno); } - int __must_check i915_gem_get_seqno(struct drm_device *dev, u32 *seqno); + int __must_check i915_gem_get_seqno(struct drm_i915_private *dev_priv, u32 *seqno); int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno); struct drm_i915_gem_request * i915_gem_find_active_request(struct intel_engine_cs *engine); - bool i915_gem_retire_requests(struct drm_device *dev); + bool i915_gem_retire_requests(struct drm_i915_private *dev_priv); void i915_gem_retire_requests_ring(struct intel_engine_cs *engine); static inline u32 i915_reset_counter(struct i915_gpu_error *error) @@@ -3147,7 -3277,6 +3277,6 @@@ bool i915_gem_clflush_object(struct drm int __must_check i915_gem_init(struct drm_device *dev); int i915_gem_init_engines(struct drm_device *dev); int __must_check i915_gem_init_hw(struct drm_device *dev); - int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice); void i915_gem_init_swizzling(struct drm_device *dev); void i915_gem_cleanup_engines(struct drm_device *dev); int __must_check i915_gpu_idle(struct drm_device *dev); @@@ -3215,8 -3344,6 +3344,6 @@@ bool i915_gem_obj_ggtt_bound_view(struc bool i915_gem_obj_bound(struct drm_i915_gem_object *o, struct i915_address_space *vm); - unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, - struct i915_address_space *vm); struct i915_vma * i915_gem_obj_to_vma(struct drm_i915_gem_object *obj, struct i915_address_space *vm); @@@ -3251,14 -3378,8 +3378,8 @@@ static inline bool i915_gem_obj_ggtt_bo return i915_gem_obj_ggtt_bound_view(obj, &i915_ggtt_view_normal); } - static inline unsigned long - i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj) - { - struct drm_i915_private *dev_priv = to_i915(obj->base.dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; - - return i915_gem_obj_size(obj, &ggtt->base); - } + unsigned long + i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj); static inline int __must_check i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj, @@@ -3272,12 -3393,6 +3393,6 @@@ alignment, flags | PIN_GLOBAL); } - static inline int - i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj) - { - return i915_vma_unbind(i915_gem_obj_to_ggtt(obj)); - } - void i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj, const struct i915_ggtt_view *view); static inline void @@@ -3301,10 -3416,10 +3416,10 @@@ void i915_gem_object_save_bit_17_swizzl /* i915_gem_context.c */ int __must_check i915_gem_context_init(struct drm_device *dev); + void i915_gem_context_lost(struct drm_i915_private *dev_priv); void i915_gem_context_fini(struct drm_device *dev); void i915_gem_context_reset(struct drm_device *dev); int i915_gem_context_open(struct drm_device *dev, struct drm_file *file); - int i915_gem_context_enable(struct drm_i915_gem_request *req); void i915_gem_context_close(struct drm_device *dev, struct drm_file *file); int i915_switch_context(struct drm_i915_gem_request *req); struct intel_context * @@@ -3335,6 -3450,8 +3450,8 @@@ int i915_gem_context_getparam_ioctl(str struct drm_file *file_priv); int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); + int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data, + struct drm_file *file); /* i915_gem_evict.c */ int __must_check i915_gem_evict_something(struct drm_device *dev, @@@ -3349,9 -3466,9 +3466,9 @@@ int __must_check i915_gem_evict_for_vma int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); /* belongs in i915_gem_gtt.h */ - static inline void i915_gem_chipset_flush(struct drm_device *dev) + static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv) { - if (INTEL_INFO(dev)->gen < 6) + if (INTEL_GEN(dev_priv) < 6) intel_gtt_chipset_flush(); } @@@ -3430,18 -3547,19 +3547,19 @@@ static inline void i915_error_state_buf { kfree(eb->buf); } - void i915_capture_error_state(struct drm_device *dev, u32 engine_mask, + void i915_capture_error_state(struct drm_i915_private *dev_priv, + u32 engine_mask, const char *error_msg); void i915_error_state_get(struct drm_device *dev, struct i915_error_state_file_priv *error_priv); void i915_error_state_put(struct i915_error_state_file_priv *error_priv); void i915_destroy_error_state(struct drm_device *dev); - void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone); + void i915_get_extra_instdone(struct drm_i915_private *dev_priv, uint32_t *instdone); const char *i915_cache_level_str(struct drm_i915_private *i915, int type); /* i915_cmd_parser.c */ - int i915_cmd_parser_get_version(void); + int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); int i915_cmd_parser_init_ring(struct intel_engine_cs *engine); void i915_cmd_parser_fini_ring(struct intel_engine_cs *engine); bool i915_needs_cmd_parser(struct intel_engine_cs *engine); @@@ -3492,7 -3610,7 +3610,7 @@@ bool intel_bios_is_port_hpd_inverted(st extern int intel_opregion_setup(struct drm_device *dev); extern void intel_opregion_init(struct drm_device *dev); extern void intel_opregion_fini(struct drm_device *dev); - extern void intel_opregion_asle_intr(struct drm_device *dev); + extern void intel_opregion_asle_intr(struct drm_i915_private *dev_priv); extern int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder, bool enable); extern int intel_opregion_notify_adapter(struct drm_device *dev, @@@ -3502,7 -3620,9 +3620,9 @@@ extern int intel_opregion_get_panel_typ static inline int intel_opregion_setup(struct drm_device *dev) { return 0; } static inline void intel_opregion_init(struct drm_device *dev) { return; } static inline void intel_opregion_fini(struct drm_device *dev) { return; } - static inline void intel_opregion_asle_intr(struct drm_device *dev) { return; } + static inline void intel_opregion_asle_intr(struct drm_i915_private *dev_priv) + { + } static inline int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder, bool enable) { @@@ -3538,26 -3658,25 +3658,25 @@@ extern int intel_modeset_vga_set_state( extern void intel_display_resume(struct drm_device *dev); extern void i915_redisable_vga(struct drm_device *dev); extern void i915_redisable_vga_power_on(struct drm_device *dev); - extern bool ironlake_set_drps(struct drm_device *dev, u8 val); + extern bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val); extern void intel_init_pch_refclk(struct drm_device *dev); - extern void intel_set_rps(struct drm_device *dev, u8 val); + extern void intel_set_rps(struct drm_i915_private *dev_priv, u8 val); extern void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable); extern void intel_detect_pch(struct drm_device *dev); - extern int intel_enable_rc6(const struct drm_device *dev); - extern bool i915_semaphore_is_enabled(struct drm_device *dev); + extern bool i915_semaphore_is_enabled(struct drm_i915_private *dev_priv); int i915_reg_read_ioctl(struct drm_device *dev, void *data, struct drm_file *file); - int i915_get_reset_stats_ioctl(struct drm_device *dev, void *data, - struct drm_file *file); /* overlay */ - extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev); + extern struct intel_overlay_error_state * + intel_overlay_capture_error_state(struct drm_i915_private *dev_priv); extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e, struct intel_overlay_error_state *error); - extern struct intel_display_error_state *intel_display_capture_error_state(struct drm_device *dev); + extern struct intel_display_error_state * + intel_display_capture_error_state(struct drm_i915_private *dev_priv); extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e, struct drm_device *dev, struct intel_display_error_state *error); @@@ -3586,6 -3705,24 +3705,24 @@@ void intel_sbi_write(struct drm_i915_pr u32 vlv_flisdsi_read(struct drm_i915_private *dev_priv, u32 reg); void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val); + /* intel_dpio_phy.c */ + void chv_set_phy_signal_level(struct intel_encoder *encoder, + u32 deemph_reg_value, u32 margin_reg_value, + bool uniq_trans_scale); + void chv_data_lane_soft_reset(struct intel_encoder *encoder, + bool reset); + void chv_phy_pre_pll_enable(struct intel_encoder *encoder); + void chv_phy_pre_encoder_enable(struct intel_encoder *encoder); + void chv_phy_release_cl2_override(struct intel_encoder *encoder); + void chv_phy_post_pll_disable(struct intel_encoder *encoder); + + void vlv_set_phy_signal_level(struct intel_encoder *encoder, + u32 demph_reg_value, u32 preemph_reg_value, + u32 uniqtranscale_reg_value, u32 tx3_demph); + void vlv_phy_pre_pll_enable(struct intel_encoder *encoder); + void vlv_phy_pre_encoder_enable(struct intel_encoder *encoder); + void vlv_phy_reset_lanes(struct intel_encoder *encoder); + int intel_gpu_freq(struct drm_i915_private *dev_priv, int val); int intel_freq_opcode(struct drm_i915_private *dev_priv, int val); @@@ -3676,6 -3813,11 +3813,6 @@@ static inline i915_reg_t i915_vgacntrl_ return VGACNTRL; } -static inline void __user *to_user_ptr(u64 address) -{ - return (void __user *)(uintptr_t)address; -} - static inline unsigned long msecs_to_jiffies_timeout(const unsigned int m) { unsigned long j = msecs_to_jiffies(m); diff --combined drivers/gpu/drm/i915/i915_gem.c index aad26851cee3,3251decf10f5..12407bc70c71 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@@ -177,7 -177,7 +177,7 @@@ i915_gem_object_get_pages_phys(struct d vaddr += PAGE_SIZE; } - i915_gem_chipset_flush(obj->base.dev); + i915_gem_chipset_flush(to_i915(obj->base.dev)); st = kmalloc(sizeof(*st), GFP_KERNEL); if (st == NULL) @@@ -319,7 -319,7 +319,7 @@@ i915_gem_phys_pwrite(struct drm_i915_ge { struct drm_device *dev = obj->base.dev; void *vaddr = obj->phys_handle->vaddr + args->offset; - char __user *user_data = to_user_ptr(args->data_ptr); + char __user *user_data = u64_to_user_ptr(args->data_ptr); int ret = 0; /* We manually control the domain here and pretend that it @@@ -347,7 -347,7 +347,7 @@@ } drm_clflush_virt_range(vaddr, args->size); - i915_gem_chipset_flush(dev); + i915_gem_chipset_flush(to_i915(dev)); out: intel_fb_obj_flush(obj, false, ORIGIN_CPU); @@@ -381,9 -381,9 +381,9 @@@ i915_gem_create(struct drm_file *file return -EINVAL; /* Allocate the new object */ - obj = i915_gem_alloc_object(dev, size); - if (obj == NULL) - return -ENOMEM; + obj = i915_gem_object_create(dev, size); + if (IS_ERR(obj)) + return PTR_ERR(obj); ret = drm_gem_handle_create(file, &obj->base, &handle); /* drop reference from allocate - handle holds it now */ @@@ -600,7 -600,7 +600,7 @@@ i915_gem_shmem_pread(struct drm_device int needs_clflush = 0; struct sg_page_iter sg_iter; - user_data = to_user_ptr(args->data_ptr); + user_data = u64_to_user_ptr(args->data_ptr); remain = args->size; obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); @@@ -687,7 -687,7 +687,7 @@@ i915_gem_pread_ioctl(struct drm_device return 0; if (!access_ok(VERIFY_WRITE, - to_user_ptr(args->data_ptr), + u64_to_user_ptr(args->data_ptr), args->size)) return -EFAULT; @@@ -695,7 -695,7 +695,7 @@@ if (ret) return ret; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -779,7 -779,7 +779,7 @@@ i915_gem_gtt_pwrite_fast(struct drm_dev if (ret) goto out_unpin; - user_data = to_user_ptr(args->data_ptr); + user_data = u64_to_user_ptr(args->data_ptr); remain = args->size; offset = i915_gem_obj_ggtt_offset(obj) + args->offset; @@@ -903,7 -903,7 +903,7 @@@ i915_gem_shmem_pwrite(struct drm_devic int needs_clflush_before = 0; struct sg_page_iter sg_iter; - user_data = to_user_ptr(args->data_ptr); + user_data = u64_to_user_ptr(args->data_ptr); remain = args->size; obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); @@@ -1006,7 -1006,7 +1006,7 @@@ out } if (needs_clflush_after) - i915_gem_chipset_flush(dev); + i915_gem_chipset_flush(to_i915(dev)); else obj->cache_dirty = true; @@@ -1032,12 -1032,12 +1032,12 @@@ i915_gem_pwrite_ioctl(struct drm_devic return 0; if (!access_ok(VERIFY_READ, - to_user_ptr(args->data_ptr), + u64_to_user_ptr(args->data_ptr), args->size)) return -EFAULT; if (likely(!i915.prefault_disable)) { - ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr), + ret = fault_in_multipages_readable(u64_to_user_ptr(args->data_ptr), args->size); if (ret) return -EFAULT; @@@ -1049,7 -1049,7 +1049,7 @@@ if (ret) goto put_rpm; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -1230,8 -1230,7 +1230,7 @@@ int __i915_wait_request(struct drm_i915 struct intel_rps_client *rps) { struct intel_engine_cs *engine = i915_gem_request_get_engine(req); - struct drm_device *dev = engine->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = req->i915; const bool irq_test_in_progress = ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_engine_flag(engine); int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; @@@ -1413,6 -1412,13 +1412,13 @@@ static void i915_gem_request_retire(str list_del_init(&request->list); i915_gem_request_remove_from_client(request); + if (request->previous_context) { + if (i915.enable_execlists) + intel_lr_context_unpin(request->previous_context, + request->engine); + } + + i915_gem_context_unreference(request->ctx); i915_gem_request_unreference(request); } @@@ -1422,7 -1428,7 +1428,7 @@@ __i915_gem_request_retire__upto(struct struct intel_engine_cs *engine = req->engine; struct drm_i915_gem_request *tmp; - lockdep_assert_held(&engine->dev->struct_mutex); + lockdep_assert_held(&engine->i915->dev->struct_mutex); if (list_empty(&req->list)) return; @@@ -1611,7 -1617,7 +1617,7 @@@ i915_gem_set_domain_ioctl(struct drm_de if (ret) return ret; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -1659,7 -1665,7 +1665,7 @@@ i915_gem_sw_finish_ioctl(struct drm_dev if (ret) return ret; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -1703,10 -1709,10 +1709,10 @@@ i915_gem_mmap_ioctl(struct drm_device * if (args->flags & ~(I915_MMAP_WC)) return -EINVAL; - if (args->flags & I915_MMAP_WC && !cpu_has_pat) + if (args->flags & I915_MMAP_WC && !boot_cpu_has(X86_FEATURE_PAT)) return -ENODEV; - obj = drm_gem_object_lookup(dev, file, args->handle); + obj = drm_gem_object_lookup(file, args->handle); if (obj == NULL) return -ENOENT; @@@ -1725,10 -1731,7 +1731,10 @@@ struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) { + drm_gem_object_unreference_unlocked(obj); + return -EINTR; + } vma = find_vma(mm, addr); if (vma) vma->vm_page_prot = @@@ -1982,7 -1985,7 +1988,7 @@@ i915_gem_get_gtt_size(struct drm_devic return size; /* Previous chips need a power-of-two fence region when tiling */ - if (INTEL_INFO(dev)->gen == 3) + if (IS_GEN3(dev)) gtt_size = 1024*1024; else gtt_size = 512*1024; @@@ -2072,7 -2075,7 +2078,7 @@@ i915_gem_mmap_gtt(struct drm_file *file if (ret) return ret; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -2162,7 -2165,8 +2168,8 @@@ i915_gem_object_invalidate(struct drm_i static void i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj) { - struct sg_page_iter sg_iter; + struct sgt_iter sgt_iter; + struct page *page; int ret; BUG_ON(obj->madv == __I915_MADV_PURGED); @@@ -2184,9 -2188,7 +2191,7 @@@ if (obj->madv == I915_MADV_DONTNEED) obj->dirty = 0; - for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) { - struct page *page = sg_page_iter_page(&sg_iter); - + for_each_sgt_page(page, sgt_iter, obj->pages) { if (obj->dirty) set_page_dirty(page); @@@ -2243,7 -2245,7 +2248,7 @@@ i915_gem_object_get_pages_gtt(struct dr struct address_space *mapping; struct sg_table *st; struct scatterlist *sg; - struct sg_page_iter sg_iter; + struct sgt_iter sgt_iter; struct page *page; unsigned long last_pfn = 0; /* suppress gcc warning */ int ret; @@@ -2340,8 -2342,8 +2345,8 @@@ err_pages: sg_mark_end(sg); - for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) - put_page(sg_page_iter_page(&sg_iter)); + for_each_sgt_page(page, sgt_iter, st) + put_page(page); sg_free_table(st); kfree(st); @@@ -2395,6 -2397,44 +2400,44 @@@ i915_gem_object_get_pages(struct drm_i9 return 0; } + /* The 'mapping' part of i915_gem_object_pin_map() below */ + static void *i915_gem_object_map(const struct drm_i915_gem_object *obj) + { + unsigned long n_pages = obj->base.size >> PAGE_SHIFT; + struct sg_table *sgt = obj->pages; + struct sgt_iter sgt_iter; + struct page *page; + struct page *stack_pages[32]; + struct page **pages = stack_pages; + unsigned long i = 0; + void *addr; + + /* A single page can always be kmapped */ + if (n_pages == 1) + return kmap(sg_page(sgt->sgl)); + + if (n_pages > ARRAY_SIZE(stack_pages)) { + /* Too big for stack -- allocate temporary array instead */ + pages = drm_malloc_gfp(n_pages, sizeof(*pages), GFP_TEMPORARY); + if (!pages) + return NULL; + } + + for_each_sgt_page(page, sgt_iter, sgt) + pages[i++] = page; + + /* Check that we have the expected number of pages */ + GEM_BUG_ON(i != n_pages); + + addr = vmap(pages, n_pages, 0, PAGE_KERNEL); + + if (pages != stack_pages) + drm_free_large(pages); + + return addr; + } + + /* get, pin, and map the pages of the object into kernel space */ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj) { int ret; @@@ -2407,29 -2447,9 +2450,9 @@@ i915_gem_object_pin_pages(obj); - if (obj->mapping == NULL) { - struct page **pages; - - pages = NULL; - if (obj->base.size == PAGE_SIZE) - obj->mapping = kmap(sg_page(obj->pages->sgl)); - else - pages = drm_malloc_gfp(obj->base.size >> PAGE_SHIFT, - sizeof(*pages), - GFP_TEMPORARY); - if (pages != NULL) { - struct sg_page_iter sg_iter; - int n; - - n = 0; - for_each_sg_page(obj->pages->sgl, &sg_iter, - obj->pages->nents, 0) - pages[n++] = sg_page_iter_page(&sg_iter); - - obj->mapping = vmap(pages, n, 0, PAGE_KERNEL); - drm_free_large(pages); - } - if (obj->mapping == NULL) { + if (!obj->mapping) { + obj->mapping = i915_gem_object_map(obj); + if (!obj->mapping) { i915_gem_object_unpin_pages(obj); return ERR_PTR(-ENOMEM); } @@@ -2502,9 -2522,8 +2525,8 @@@ i915_gem_object_retire__read(struct drm } static int - i915_gem_init_seqno(struct drm_device *dev, u32 seqno) + i915_gem_init_seqno(struct drm_i915_private *dev_priv, u32 seqno) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_engine_cs *engine; int ret; @@@ -2514,7 -2533,7 +2536,7 @@@ if (ret) return ret; } - i915_gem_retire_requests(dev); + i915_gem_retire_requests(dev_priv); /* Finally reset hw state */ for_each_engine(engine, dev_priv) @@@ -2534,7 -2553,7 +2556,7 @@@ int i915_gem_set_seqno(struct drm_devic /* HWS page needs to be set less than what we * will inject to ring */ - ret = i915_gem_init_seqno(dev, seqno - 1); + ret = i915_gem_init_seqno(dev_priv, seqno - 1); if (ret) return ret; @@@ -2550,13 -2569,11 +2572,11 @@@ } int - i915_gem_get_seqno(struct drm_device *dev, u32 *seqno) + i915_gem_get_seqno(struct drm_i915_private *dev_priv, u32 *seqno) { - struct drm_i915_private *dev_priv = dev->dev_private; - /* reserve 0 for non-seqno */ if (dev_priv->next_seqno == 0) { - int ret = i915_gem_init_seqno(dev, 0); + int ret = i915_gem_init_seqno(dev_priv, 0); if (ret) return ret; @@@ -2580,6 -2597,7 +2600,7 @@@ void __i915_add_request(struct drm_i915 struct drm_i915_private *dev_priv; struct intel_ringbuffer *ringbuf; u32 request_start; + u32 reserved_tail; int ret; if (WARN_ON(request == NULL)) @@@ -2594,9 -2612,10 +2615,10 @@@ * should already have been reserved in the ring buffer. Let the ring * know that it is time to use that space up. */ - intel_ring_reserved_space_use(ringbuf); - request_start = intel_ring_get_tail(ringbuf); + reserved_tail = request->reserved_space; + request->reserved_space = 0; + /* * Emit any outstanding flushes - execbuf can fail to emit the flush * after having emitted the batchbuffer command. Hence we need to fix @@@ -2652,15 -2671,21 +2674,21 @@@ /* Not allowed to fail! */ WARN(ret, "emit|add_request failed: %d!\n", ret); - i915_queue_hangcheck(engine->dev); + i915_queue_hangcheck(engine->i915); queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, round_jiffies_up_relative(HZ)); - intel_mark_busy(dev_priv->dev); + intel_mark_busy(dev_priv); /* Sanity check that the reserved size was large enough. */ - intel_ring_reserved_space_end(ringbuf); + ret = intel_ring_get_tail(ringbuf) - request_start; + if (ret < 0) + ret += ringbuf->size; + WARN_ONCE(ret > reserved_tail, + "Not enough space reserved (%d bytes) " + "for adding the request (%d bytes)\n", + reserved_tail, ret); } static bool i915_context_is_banned(struct drm_i915_private *dev_priv, @@@ -2712,18 -2737,6 +2740,6 @@@ void i915_gem_request_free(struct kref { struct drm_i915_gem_request *req = container_of(req_ref, typeof(*req), ref); - struct intel_context *ctx = req->ctx; - - if (req->file_priv) - i915_gem_request_remove_from_client(req); - - if (ctx) { - if (i915.enable_execlists && ctx != req->i915->kernel_context) - intel_lr_context_unpin(ctx, req->engine); - - i915_gem_context_unreference(ctx); - } - kmem_cache_free(req->i915->requests, req); } @@@ -2732,7 -2745,7 +2748,7 @@@ __i915_gem_request_alloc(struct intel_e struct intel_context *ctx, struct drm_i915_gem_request **req_out) { - struct drm_i915_private *dev_priv = to_i915(engine->dev); + struct drm_i915_private *dev_priv = engine->i915; unsigned reset_counter = i915_reset_counter(&dev_priv->gpu_error); struct drm_i915_gem_request *req; int ret; @@@ -2754,7 -2767,7 +2770,7 @@@ if (req == NULL) return -ENOMEM; - ret = i915_gem_get_seqno(engine->dev, &req->seqno); + ret = i915_gem_get_seqno(engine->i915, &req->seqno); if (ret) goto err; @@@ -2765,15 -2778,6 +2781,6 @@@ req->ctx = ctx; i915_gem_context_reference(req->ctx); - if (i915.enable_execlists) - ret = intel_logical_ring_alloc_request_extras(req); - else - ret = intel_ring_alloc_request_extras(req); - if (ret) { - i915_gem_context_unreference(req->ctx); - goto err; - } - /* * Reserve space in the ring buffer for all the commands required to * eventually emit this request. This is to guarantee that the @@@ -2781,24 -2785,20 +2788,20 @@@ * to be redone if the request is not actually submitted straight * away, e.g. because a GPU scheduler has deferred it. */ + req->reserved_space = MIN_SPACE_FOR_ADD_REQUEST; + if (i915.enable_execlists) - ret = intel_logical_ring_reserve_space(req); + ret = intel_logical_ring_alloc_request_extras(req); else - ret = intel_ring_reserve_space(req); - if (ret) { - /* - * At this point, the request is fully allocated even if not - * fully prepared. Thus it can be cleaned up using the proper - * free code. - */ - intel_ring_reserved_space_cancel(req->ringbuf); - i915_gem_request_unreference(req); - return ret; - } + ret = intel_ring_alloc_request_extras(req); + if (ret) + goto err_ctx; *req_out = req; return 0; + err_ctx: + i915_gem_context_unreference(ctx); err: kmem_cache_free(dev_priv->requests, req); return ret; @@@ -2824,7 -2824,7 +2827,7 @@@ i915_gem_request_alloc(struct intel_eng int err; if (ctx == NULL) - ctx = to_i915(engine->dev)->kernel_context; + ctx = engine->i915->kernel_context; err = __i915_gem_request_alloc(engine, ctx, &req); return err ? ERR_PTR(err) : req; } @@@ -2888,13 -2888,7 +2891,7 @@@ static void i915_gem_reset_engine_clean /* Ensure irq handler finishes or is cancelled. */ tasklet_kill(&engine->irq_tasklet); - spin_lock_bh(&engine->execlist_lock); - /* list_splice_tail_init checks for empty lists */ - list_splice_tail_init(&engine->execlist_queue, - &engine->execlist_retired_req_list); - spin_unlock_bh(&engine->execlist_lock); - - intel_execlists_retire_requests(engine); + intel_execlists_cancel_requests(engine); } /* @@@ -3005,9 -2999,8 +3002,8 @@@ i915_gem_retire_requests_ring(struct in } bool - i915_gem_retire_requests(struct drm_device *dev) + i915_gem_retire_requests(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_engine_cs *engine; bool idle = true; @@@ -3018,8 -3011,6 +3014,6 @@@ spin_lock_bh(&engine->execlist_lock); idle &= list_empty(&engine->execlist_queue); spin_unlock_bh(&engine->execlist_lock); - - intel_execlists_retire_requests(engine); } } @@@ -3042,7 -3033,7 +3036,7 @@@ i915_gem_retire_work_handler(struct wor /* Come back later if the device is busy... */ idle = false; if (mutex_trylock(&dev->struct_mutex)) { - idle = i915_gem_retire_requests(dev); + idle = i915_gem_retire_requests(dev_priv); mutex_unlock(&dev->struct_mutex); } if (!idle) @@@ -3066,7 -3057,7 +3060,7 @@@ i915_gem_idle_work_handler(struct work_ * Also locking seems to be fubar here, engine->request_list is protected * by dev->struct_mutex. */ - intel_mark_idle(dev); + intel_mark_idle(dev_priv); if (mutex_trylock(&dev->struct_mutex)) { for_each_engine(engine, dev_priv) @@@ -3096,14 -3087,8 +3090,8 @@@ i915_gem_object_flush_active(struct drm if (req == NULL) continue; - if (list_empty(&req->list)) - goto retire; - - if (i915_gem_request_completed(req, true)) { - __i915_gem_request_retire__upto(req); - retire: + if (i915_gem_request_completed(req, true)) i915_gem_object_retire__read(obj, i); - } } return 0; @@@ -3147,7 -3132,7 +3135,7 @@@ i915_gem_wait_ioctl(struct drm_device * if (ret) return ret; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->bo_handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->bo_handle)); if (&obj->base == NULL) { mutex_unlock(&dev->struct_mutex); return -ENOENT; @@@ -3185,7 -3170,7 +3173,7 @@@ ret = __i915_wait_request(req[i], true, args->timeout_ns > 0 ? &args->timeout_ns : NULL, to_rps_client(file)); - i915_gem_request_unreference__unlocked(req[i]); + i915_gem_request_unreference(req[i]); } return ret; @@@ -3211,7 -3196,7 +3199,7 @@@ __i915_gem_object_sync(struct drm_i915_ if (i915_gem_request_completed(from_req, true)) return 0; - if (!i915_semaphore_is_enabled(obj->base.dev)) { + if (!i915_semaphore_is_enabled(to_i915(obj->base.dev))) { struct drm_i915_private *i915 = to_i915(obj->base.dev); ret = __i915_wait_request(from_req, i915->mm.interruptible, @@@ -3345,6 -3330,17 +3333,17 @@@ static void i915_gem_object_finish_gtt( old_write_domain); } + static void __i915_vma_iounmap(struct i915_vma *vma) + { + GEM_BUG_ON(vma->pin_count); + + if (vma->iomap == NULL) + return; + + io_mapping_unmap(vma->iomap); + vma->iomap = NULL; + } + static int __i915_vma_unbind(struct i915_vma *vma, bool wait) { struct drm_i915_gem_object *obj = vma->obj; @@@ -3377,6 -3373,8 +3376,8 @@@ ret = i915_gem_object_put_fence(obj); if (ret) return ret; + + __i915_vma_iounmap(vma); } trace_i915_vma_unbind(vma); @@@ -3731,7 -3729,7 +3732,7 @@@ i915_gem_object_flush_cpu_write_domain( return; if (i915_gem_clflush_object(obj, obj->pin_display)) - i915_gem_chipset_flush(obj->base.dev); + i915_gem_chipset_flush(to_i915(obj->base.dev)); old_write_domain = obj->base.write_domain; obj->base.write_domain = 0; @@@ -3929,7 -3927,7 +3930,7 @@@ out obj->base.write_domain != I915_GEM_DOMAIN_CPU && cpu_write_needs_clflush(obj)) { if (i915_gem_clflush_object(obj, true)) - i915_gem_chipset_flush(obj->base.dev); + i915_gem_chipset_flush(to_i915(obj->base.dev)); } return 0; @@@ -3941,7 -3939,7 +3942,7 @@@ int i915_gem_get_caching_ioctl(struct d struct drm_i915_gem_caching *args = data; struct drm_i915_gem_object *obj; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) return -ENOENT; @@@ -4002,7 -4000,7 +4003,7 @@@ int i915_gem_set_caching_ioctl(struct d if (ret) goto rpm_put; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -4198,7 -4196,7 +4199,7 @@@ i915_gem_ring_throttle(struct drm_devic if (ret == 0) queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, 0); - i915_gem_request_unreference__unlocked(target); + i915_gem_request_unreference(target); return ret; } @@@ -4372,7 -4370,7 +4373,7 @@@ i915_gem_busy_ioctl(struct drm_device * if (ret) return ret; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -4437,7 -4435,7 +4438,7 @@@ i915_gem_madvise_ioctl(struct drm_devic if (ret) return ret; - obj = to_intel_bo(drm_gem_object_lookup(dev, file_priv, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file_priv, args->handle)); if (&obj->base == NULL) { ret = -ENOENT; goto unlock; @@@ -4499,21 -4497,21 +4500,21 @@@ static const struct drm_i915_gem_object .put_pages = i915_gem_object_put_pages_gtt, }; - struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, + struct drm_i915_gem_object *i915_gem_object_create(struct drm_device *dev, size_t size) { struct drm_i915_gem_object *obj; struct address_space *mapping; gfp_t mask; + int ret; obj = i915_gem_object_alloc(dev); if (obj == NULL) - return NULL; + return ERR_PTR(-ENOMEM); - if (drm_gem_object_init(dev, &obj->base, size) != 0) { - i915_gem_object_free(obj); - return NULL; - } + ret = drm_gem_object_init(dev, &obj->base, size); + if (ret) + goto fail; mask = GFP_HIGHUSER | __GFP_RECLAIMABLE; if (IS_CRESTLINE(dev) || IS_BROADWATER(dev)) { @@@ -4550,6 -4548,11 +4551,11 @@@ trace_i915_gem_object_create(obj); return obj; + + fail: + i915_gem_object_free(obj); + + return ERR_PTR(ret); } static bool discard_backing_storage(struct drm_i915_gem_object *obj) @@@ -4655,16 -4658,12 +4661,12 @@@ struct i915_vma *i915_gem_obj_to_vma(st struct i915_vma *i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj, const struct i915_ggtt_view *view) { - struct drm_device *dev = obj->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; struct i915_vma *vma; - BUG_ON(!view); + GEM_BUG_ON(!view); list_for_each_entry(vma, &obj->vma_list, obj_link) - if (vma->vm == &ggtt->base && - i915_ggtt_view_equal(&vma->ggtt_view, view)) + if (vma->is_ggtt && i915_ggtt_view_equal(&vma->ggtt_view, view)) return vma; return NULL; } @@@ -4706,9 -4705,10 +4708,10 @@@ i915_gem_suspend(struct drm_device *dev if (ret) goto err; - i915_gem_retire_requests(dev); + i915_gem_retire_requests(dev_priv); i915_gem_stop_engines(dev); + i915_gem_context_lost(dev_priv); mutex_unlock(&dev->struct_mutex); cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work); @@@ -4727,37 -4727,6 +4730,6 @@@ err return ret; } - int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice) - { - struct intel_engine_cs *engine = req->engine; - struct drm_device *dev = engine->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - u32 *remap_info = dev_priv->l3_parity.remap_info[slice]; - int i, ret; - - if (!HAS_L3_DPF(dev) || !remap_info) - return 0; - - ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3); - if (ret) - return ret; - - /* - * Note: We do not worry about the concurrent register cacheline hang - * here because no other code should access these registers other than - * at initialization time. - */ - for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) { - intel_ring_emit(engine, MI_LOAD_REGISTER_IMM(1)); - intel_ring_emit_reg(engine, GEN7_L3LOG(slice, i)); - intel_ring_emit(engine, remap_info[i]); - } - - intel_ring_advance(engine); - - return ret; - } - void i915_gem_init_swizzling(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@@ -4862,7 -4831,7 +4834,7 @@@ i915_gem_init_hw(struct drm_device *dev { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_engine_cs *engine; - int ret, j; + int ret; /* Double layer security blanket, see i915_gem_init() */ intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); @@@ -4928,44 -4897,6 +4900,6 @@@ * on re-initialisation */ ret = i915_gem_set_seqno(dev, dev_priv->next_seqno+0x100); - if (ret) - goto out; - - /* Now it is safe to go back round and do everything else: */ - for_each_engine(engine, dev_priv) { - struct drm_i915_gem_request *req; - - req = i915_gem_request_alloc(engine, NULL); - if (IS_ERR(req)) { - ret = PTR_ERR(req); - break; - } - - if (engine->id == RCS) { - for (j = 0; j < NUM_L3_SLICES(dev); j++) { - ret = i915_gem_l3_remap(req, j); - if (ret) - goto err_request; - } - } - - ret = i915_ppgtt_init_ring(req); - if (ret) - goto err_request; - - ret = i915_gem_context_enable(req); - if (ret) - goto err_request; - - err_request: - i915_add_request_no_flush(req); - if (ret) { - DRM_ERROR("Failed to enable %s, error=%d\n", - engine->name, ret); - i915_gem_cleanup_engines(dev); - break; - } - } out: intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); @@@ -4977,9 -4908,6 +4911,6 @@@ int i915_gem_init(struct drm_device *de struct drm_i915_private *dev_priv = dev->dev_private; int ret; - i915.enable_execlists = intel_sanitize_enable_execlists(dev, - i915.enable_execlists); - mutex_lock(&dev->struct_mutex); if (!i915.enable_execlists) { @@@ -5002,10 -4930,7 +4933,7 @@@ */ intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); - ret = i915_gem_init_userptr(dev); - if (ret) - goto out_unlock; - + i915_gem_init_userptr(dev_priv); i915_gem_init_ggtt(dev); ret = i915_gem_context_init(dev); @@@ -5042,14 -4967,6 +4970,6 @@@ i915_gem_cleanup_engines(struct drm_dev for_each_engine(engine, dev_priv) dev_priv->gt.cleanup_engine(engine); - - if (i915.enable_execlists) - /* - * Neither the BIOS, ourselves or any other kernel - * expects the system to be in execlists mode on startup, - * so we need to reset the GPU back to legacy mode. - */ - intel_gpu_reset(dev, ALL_ENGINES); } static void @@@ -5073,7 -4990,7 +4993,7 @@@ i915_gem_load_init_fences(struct drm_i9 else dev_priv->num_fence_regs = 8; - if (intel_vgpu_active(dev)) + if (intel_vgpu_active(dev_priv)) dev_priv->num_fence_regs = I915_READ(vgtif_reg(avail_rs.fence_num)); @@@ -5148,6 -5065,34 +5068,34 @@@ void i915_gem_load_cleanup(struct drm_d kmem_cache_destroy(dev_priv->objects); } + int i915_gem_freeze_late(struct drm_i915_private *dev_priv) + { + struct drm_i915_gem_object *obj; + + /* Called just before we write the hibernation image. + * + * We need to update the domain tracking to reflect that the CPU + * will be accessing all the pages to create and restore from the + * hibernation, and so upon restoration those pages will be in the + * CPU domain. + * + * To make sure the hibernation image contains the latest state, + * we update that state just before writing out the image. + */ + + list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) { + obj->base.read_domains = I915_GEM_DOMAIN_CPU; + obj->base.write_domain = I915_GEM_DOMAIN_CPU; + } + + list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { + obj->base.read_domains = I915_GEM_DOMAIN_CPU; + obj->base.write_domain = I915_GEM_DOMAIN_CPU; + } + + return 0; + } + void i915_gem_release(struct drm_device *dev, struct drm_file *file) { struct drm_i915_file_private *file_priv = file->driver_priv; @@@ -5254,13 -5199,10 +5202,10 @@@ u64 i915_gem_obj_offset(struct drm_i915 u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o, const struct i915_ggtt_view *view) { - struct drm_i915_private *dev_priv = to_i915(o->base.dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; struct i915_vma *vma; list_for_each_entry(vma, &o->vma_list, obj_link) - if (vma->vm == &ggtt->base && - i915_ggtt_view_equal(&vma->ggtt_view, view)) + if (vma->is_ggtt && i915_ggtt_view_equal(&vma->ggtt_view, view)) return vma->node.start; WARN(1, "global vma for this object not found. (view=%u)\n", view->type); @@@ -5286,12 -5228,10 +5231,10 @@@ bool i915_gem_obj_bound(struct drm_i915 bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o, const struct i915_ggtt_view *view) { - struct drm_i915_private *dev_priv = to_i915(o->base.dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; struct i915_vma *vma; list_for_each_entry(vma, &o->vma_list, obj_link) - if (vma->vm == &ggtt->base && + if (vma->is_ggtt && i915_ggtt_view_equal(&vma->ggtt_view, view) && drm_mm_node_allocated(&vma->node)) return true; @@@ -5310,23 -5250,18 +5253,18 @@@ bool i915_gem_obj_bound_any(struct drm_ return false; } - unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, - struct i915_address_space *vm) + unsigned long i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o) { - struct drm_i915_private *dev_priv = o->base.dev->dev_private; struct i915_vma *vma; - WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base); - - BUG_ON(list_empty(&o->vma_list)); + GEM_BUG_ON(list_empty(&o->vma_list)); list_for_each_entry(vma, &o->vma_list, obj_link) { if (vma->is_ggtt && - vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL) - continue; - if (vma->vm == vm) + vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) return vma->node.size; } + return 0; } @@@ -5365,8 -5300,8 +5303,8 @@@ i915_gem_object_create_from_data(struc size_t bytes; int ret; - obj = i915_gem_alloc_object(dev, round_up(size, PAGE_SIZE)); - if (IS_ERR_OR_NULL(obj)) + obj = i915_gem_object_create(dev, round_up(size, PAGE_SIZE)); + if (IS_ERR(obj)) return obj; ret = i915_gem_object_set_to_cpu_domain(obj, true); diff --combined drivers/gpu/drm/i915/i915_gem_execbuffer.c index 33df74d98269,a54a243ccaac..f315e78f38ed --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@@ -489,7 -489,7 +489,7 @@@ i915_gem_execbuffer_relocate_entry(stru ret = relocate_entry_cpu(obj, reloc, target_offset); else if (obj->map_and_fenceable) ret = relocate_entry_gtt(obj, reloc, target_offset); - else if (cpu_has_clflush) + else if (static_cpu_has(X86_FEATURE_CLFLUSH)) ret = relocate_entry_clflush(obj, reloc, target_offset); else { WARN_ONCE(1, "Impossible case in relocation handling\n"); @@@ -515,7 -515,7 +515,7 @@@ i915_gem_execbuffer_relocate_vma(struc struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; int remain, ret; - user_relocs = to_user_ptr(entry->relocs_ptr); + user_relocs = u64_to_user_ptr(entry->relocs_ptr); remain = entry->relocation_count; while (remain) { @@@ -536,7 -536,9 +536,7 @@@ return ret; if (r->presumed_offset != offset && - __copy_to_user_inatomic(&user_relocs->presumed_offset, - &r->presumed_offset, - sizeof(r->presumed_offset))) { + __put_user(r->presumed_offset, &user_relocs->presumed_offset)) { return -EFAULT; } @@@ -722,7 -724,7 +722,7 @@@ i915_gem_execbuffer_reserve(struct inte struct i915_address_space *vm; struct list_head ordered_vmas; struct list_head pinned_vmas; - bool has_fenced_gpu_access = INTEL_INFO(engine->dev)->gen < 4; + bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4; int retry; i915_gem_retire_requests_ring(engine); @@@ -867,7 -869,7 +867,7 @@@ i915_gem_execbuffer_relocate_slow(struc u64 invalid_offset = (u64)-1; int j; - user_relocs = to_user_ptr(exec[i].relocs_ptr); + user_relocs = u64_to_user_ptr(exec[i].relocs_ptr); if (copy_from_user(reloc+total, user_relocs, exec[i].relocation_count * sizeof(*reloc))) { @@@ -963,7 -965,7 +963,7 @@@ i915_gem_execbuffer_move_to_gpu(struct } if (flush_chipset) - i915_gem_chipset_flush(req->engine->dev); + i915_gem_chipset_flush(req->engine->i915); if (flush_domains & I915_GEM_DOMAIN_GTT) wmb(); @@@ -1012,7 -1014,7 +1012,7 @@@ validate_exec_list(struct drm_device *d invalid_flags |= EXEC_OBJECT_NEEDS_GTT; for (i = 0; i < count; i++) { - char __user *ptr = to_user_ptr(exec[i].relocs_ptr); + char __user *ptr = u64_to_user_ptr(exec[i].relocs_ptr); int length; /* limited by fault_in_pages_readable() */ if (exec[i].flags & invalid_flags) @@@ -1083,14 -1085,6 +1083,6 @@@ i915_gem_validate_context(struct drm_de return ERR_PTR(-EIO); } - if (i915.enable_execlists && !ctx->engine[engine->id].state) { - int ret = intel_lr_context_deferred_alloc(ctx, engine); - if (ret) { - DRM_DEBUG("Could not create LRC %u: %d\n", ctx_id, ret); - return ERR_PTR(ret); - } - } - return ctx; } @@@ -1125,7 -1119,7 +1117,7 @@@ i915_gem_execbuffer_move_to_active(stru if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) { i915_gem_request_assign(&obj->last_fenced_req, req); if (entry->flags & __EXEC_OBJECT_HAS_FENCE) { - struct drm_i915_private *dev_priv = to_i915(engine->dev); + struct drm_i915_private *dev_priv = engine->i915; list_move_tail(&dev_priv->fence_regs[obj->fence_reg].lru_list, &dev_priv->mm.fence_list); } @@@ -1695,7 -1689,7 +1687,7 @@@ i915_gem_execbuffer(struct drm_device * return -ENOMEM; } ret = copy_from_user(exec_list, - to_user_ptr(args->buffers_ptr), + u64_to_user_ptr(args->buffers_ptr), sizeof(*exec_list) * args->buffer_count); if (ret != 0) { DRM_DEBUG("copy %d exec entries failed %d\n", @@@ -1731,7 -1725,7 +1723,7 @@@ ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list); if (!ret) { struct drm_i915_gem_exec_object __user *user_exec_list = - to_user_ptr(args->buffers_ptr); + u64_to_user_ptr(args->buffers_ptr); /* Copy the new buffer offsets back to the user's exec list. */ for (i = 0; i < args->buffer_count; i++) { @@@ -1783,7 -1777,7 +1775,7 @@@ i915_gem_execbuffer2(struct drm_device return -ENOMEM; } ret = copy_from_user(exec2_list, - to_user_ptr(args->buffers_ptr), + u64_to_user_ptr(args->buffers_ptr), sizeof(*exec2_list) * args->buffer_count); if (ret != 0) { DRM_DEBUG("copy %d exec entries failed %d\n", @@@ -1796,7 -1790,7 +1788,7 @@@ if (!ret) { /* Copy the new buffer offsets back to the user's exec list. */ struct drm_i915_gem_exec_object2 __user *user_exec_list = - to_user_ptr(args->buffers_ptr); + u64_to_user_ptr(args->buffers_ptr); int i; for (i = 0; i < args->buffer_count; i++) { diff --combined drivers/gpu/drm/i915/i915_gem_tiling.c index b9bdb34032cd,2fcb4afade19..a6eb5c47a49c --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@@ -125,7 -125,7 +125,7 @@@ i915_gem_object_fence_ok(struct drm_i91 if (INTEL_INFO(obj->base.dev)->gen >= 4) return true; - if (INTEL_INFO(obj->base.dev)->gen == 3) { + if (IS_GEN3(obj->base.dev)) { if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) return false; } else { @@@ -166,7 -166,7 +166,7 @@@ i915_gem_set_tiling(struct drm_device * struct drm_i915_gem_object *obj; int ret = 0; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) return -ENOENT; @@@ -229,7 -229,7 +229,7 @@@ */ if (obj->map_and_fenceable && !i915_gem_object_fence_ok(obj, args->tiling_mode)) - ret = i915_gem_object_ggtt_unbind(obj); + ret = i915_vma_unbind(i915_gem_obj_to_ggtt(obj)); if (ret == 0) { if (obj->pages && @@@ -297,7 -297,7 +297,7 @@@ i915_gem_get_tiling(struct drm_device * struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; - obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); + obj = to_intel_bo(drm_gem_object_lookup(file, args->handle)); if (&obj->base == NULL) return -ENOENT; diff --combined drivers/gpu/drm/i915/intel_display.c index 2113f401f0ba,ae253bb57c25..3f8987b7ee48 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@@ -48,6 -48,11 +48,11 @@@ #include #include + static bool is_mmio_work(struct intel_flip_work *work) + { + return work->mmio_work.func; + } + /* Primary plane formats for gen <= 3 */ static const uint32_t i8xx_primary_formats[] = { DRM_FORMAT_C8, @@@ -117,20 -122,17 +122,17 @@@ static void ironlake_pfit_disable(struc static void ironlake_pfit_enable(struct intel_crtc *crtc); static void intel_modeset_setup_hw_state(struct drm_device *dev); static void intel_pre_disable_primary_noatomic(struct drm_crtc *crtc); + static int ilk_max_pixel_rate(struct drm_atomic_state *state); - typedef struct { - int min, max; - } intel_range_t; - - typedef struct { - int dot_limit; - int p2_slow, p2_fast; - } intel_p2_t; - - typedef struct intel_limit intel_limit_t; struct intel_limit { - intel_range_t dot, vco, n, m, m1, m2, p, p1; - intel_p2_t p2; + struct { + int min, max; + } dot, vco, n, m, m1, m2, p, p1; + + struct { + int dot_limit; + int p2_slow, p2_fast; + } p2; }; /* returns HPLL frequency in kHz */ @@@ -185,6 -187,7 +187,7 @@@ intel_pch_rawclk(struct drm_i915_privat static int intel_vlv_hrawclk(struct drm_i915_private *dev_priv) { + /* RAWCLK_FREQ_VLV register updated from power well code */ return vlv_get_cck_clock_hpll(dev_priv, "hrawclk", CCK_DISPLAY_REF_CLOCK_CONTROL); } @@@ -218,7 -221,7 +221,7 @@@ intel_g4x_hrawclk(struct drm_i915_priva } } - static void intel_update_rawclk(struct drm_i915_private *dev_priv) + void intel_update_rawclk(struct drm_i915_private *dev_priv) { if (HAS_PCH_SPLIT(dev_priv)) dev_priv->rawclk_freq = intel_pch_rawclk(dev_priv); @@@ -255,7 -258,7 +258,7 @@@ intel_fdi_link_freq(struct drm_i915_pri return 270000; } - static const intel_limit_t intel_limits_i8xx_dac = { + static const struct intel_limit intel_limits_i8xx_dac = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 908000, .max = 1512000 }, .n = { .min = 2, .max = 16 }, @@@ -268,7 -271,7 +271,7 @@@ .p2_slow = 4, .p2_fast = 2 }, }; - static const intel_limit_t intel_limits_i8xx_dvo = { + static const struct intel_limit intel_limits_i8xx_dvo = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 908000, .max = 1512000 }, .n = { .min = 2, .max = 16 }, @@@ -281,7 -284,7 +284,7 @@@ .p2_slow = 4, .p2_fast = 4 }, }; - static const intel_limit_t intel_limits_i8xx_lvds = { + static const struct intel_limit intel_limits_i8xx_lvds = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 908000, .max = 1512000 }, .n = { .min = 2, .max = 16 }, @@@ -294,7 -297,7 +297,7 @@@ .p2_slow = 14, .p2_fast = 7 }, }; - static const intel_limit_t intel_limits_i9xx_sdvo = { + static const struct intel_limit intel_limits_i9xx_sdvo = { .dot = { .min = 20000, .max = 400000 }, .vco = { .min = 1400000, .max = 2800000 }, .n = { .min = 1, .max = 6 }, @@@ -307,7 -310,7 +310,7 @@@ .p2_slow = 10, .p2_fast = 5 }, }; - static const intel_limit_t intel_limits_i9xx_lvds = { + static const struct intel_limit intel_limits_i9xx_lvds = { .dot = { .min = 20000, .max = 400000 }, .vco = { .min = 1400000, .max = 2800000 }, .n = { .min = 1, .max = 6 }, @@@ -321,7 -324,7 +324,7 @@@ }; - static const intel_limit_t intel_limits_g4x_sdvo = { + static const struct intel_limit intel_limits_g4x_sdvo = { .dot = { .min = 25000, .max = 270000 }, .vco = { .min = 1750000, .max = 3500000}, .n = { .min = 1, .max = 4 }, @@@ -336,7 -339,7 +339,7 @@@ }, }; - static const intel_limit_t intel_limits_g4x_hdmi = { + static const struct intel_limit intel_limits_g4x_hdmi = { .dot = { .min = 22000, .max = 400000 }, .vco = { .min = 1750000, .max = 3500000}, .n = { .min = 1, .max = 4 }, @@@ -349,7 -352,7 +352,7 @@@ .p2_slow = 10, .p2_fast = 5 }, }; - static const intel_limit_t intel_limits_g4x_single_channel_lvds = { + static const struct intel_limit intel_limits_g4x_single_channel_lvds = { .dot = { .min = 20000, .max = 115000 }, .vco = { .min = 1750000, .max = 3500000 }, .n = { .min = 1, .max = 3 }, @@@ -363,7 -366,7 +366,7 @@@ }, }; - static const intel_limit_t intel_limits_g4x_dual_channel_lvds = { + static const struct intel_limit intel_limits_g4x_dual_channel_lvds = { .dot = { .min = 80000, .max = 224000 }, .vco = { .min = 1750000, .max = 3500000 }, .n = { .min = 1, .max = 3 }, @@@ -377,7 -380,7 +380,7 @@@ }, }; - static const intel_limit_t intel_limits_pineview_sdvo = { + static const struct intel_limit intel_limits_pineview_sdvo = { .dot = { .min = 20000, .max = 400000}, .vco = { .min = 1700000, .max = 3500000 }, /* Pineview's Ncounter is a ring counter */ @@@ -392,7 -395,7 +395,7 @@@ .p2_slow = 10, .p2_fast = 5 }, }; - static const intel_limit_t intel_limits_pineview_lvds = { + static const struct intel_limit intel_limits_pineview_lvds = { .dot = { .min = 20000, .max = 400000 }, .vco = { .min = 1700000, .max = 3500000 }, .n = { .min = 3, .max = 6 }, @@@ -410,7 -413,7 +413,7 @@@ * We calculate clock using (register_value + 2) for N/M1/M2, so here * the range value for them is (actual_value - 2). */ - static const intel_limit_t intel_limits_ironlake_dac = { + static const struct intel_limit intel_limits_ironlake_dac = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 1760000, .max = 3510000 }, .n = { .min = 1, .max = 5 }, @@@ -423,7 -426,7 +426,7 @@@ .p2_slow = 10, .p2_fast = 5 }, }; - static const intel_limit_t intel_limits_ironlake_single_lvds = { + static const struct intel_limit intel_limits_ironlake_single_lvds = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 1760000, .max = 3510000 }, .n = { .min = 1, .max = 3 }, @@@ -436,7 -439,7 +439,7 @@@ .p2_slow = 14, .p2_fast = 14 }, }; - static const intel_limit_t intel_limits_ironlake_dual_lvds = { + static const struct intel_limit intel_limits_ironlake_dual_lvds = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 1760000, .max = 3510000 }, .n = { .min = 1, .max = 3 }, @@@ -450,7 -453,7 +453,7 @@@ }; /* LVDS 100mhz refclk limits. */ - static const intel_limit_t intel_limits_ironlake_single_lvds_100m = { + static const struct intel_limit intel_limits_ironlake_single_lvds_100m = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 1760000, .max = 3510000 }, .n = { .min = 1, .max = 2 }, @@@ -463,7 -466,7 +466,7 @@@ .p2_slow = 14, .p2_fast = 14 }, }; - static const intel_limit_t intel_limits_ironlake_dual_lvds_100m = { + static const struct intel_limit intel_limits_ironlake_dual_lvds_100m = { .dot = { .min = 25000, .max = 350000 }, .vco = { .min = 1760000, .max = 3510000 }, .n = { .min = 1, .max = 3 }, @@@ -476,7 -479,7 +479,7 @@@ .p2_slow = 7, .p2_fast = 7 }, }; - static const intel_limit_t intel_limits_vlv = { + static const struct intel_limit intel_limits_vlv = { /* * These are the data rate limits (measured in fast clocks) * since those are the strictest limits we have. The fast @@@ -492,7 -495,7 +495,7 @@@ .p2 = { .p2_slow = 2, .p2_fast = 20 }, /* slow=min, fast=max */ }; - static const intel_limit_t intel_limits_chv = { + static const struct intel_limit intel_limits_chv = { /* * These are the data rate limits (measured in fast clocks) * since those are the strictest limits we have. The fast @@@ -508,7 -511,7 +511,7 @@@ .p2 = { .p2_slow = 1, .p2_fast = 14 }, }; - static const intel_limit_t intel_limits_bxt = { + static const struct intel_limit intel_limits_bxt = { /* FIXME: find real dot limits */ .dot = { .min = 0, .max = INT_MAX }, .vco = { .min = 4800000, .max = 6700000 }, @@@ -581,7 -584,7 +584,7 @@@ static bool intel_pipe_will_have_type(c * divided-down version of it. */ /* m1 is reserved as 0 in Pineview, n is a ring counter */ - static int pnv_calc_dpll_params(int refclk, intel_clock_t *clock) + static int pnv_calc_dpll_params(int refclk, struct dpll *clock) { clock->m = clock->m2 + 2; clock->p = clock->p1 * clock->p2; @@@ -598,7 -601,7 +601,7 @@@ static uint32_t i9xx_dpll_compute_m(str return 5 * (dpll->m1 + 2) + (dpll->m2 + 2); } - static int i9xx_calc_dpll_params(int refclk, intel_clock_t *clock) + static int i9xx_calc_dpll_params(int refclk, struct dpll *clock) { clock->m = i9xx_dpll_compute_m(clock); clock->p = clock->p1 * clock->p2; @@@ -610,7 -613,7 +613,7 @@@ return clock->dot; } - static int vlv_calc_dpll_params(int refclk, intel_clock_t *clock) + static int vlv_calc_dpll_params(int refclk, struct dpll *clock) { clock->m = clock->m1 * clock->m2; clock->p = clock->p1 * clock->p2; @@@ -622,7 -625,7 +625,7 @@@ return clock->dot / 5; } - int chv_calc_dpll_params(int refclk, intel_clock_t *clock) + int chv_calc_dpll_params(int refclk, struct dpll *clock) { clock->m = clock->m1 * clock->m2; clock->p = clock->p1 * clock->p2; @@@ -642,8 -645,8 +645,8 @@@ */ static bool intel_PLL_is_valid(struct drm_device *dev, - const intel_limit_t *limit, - const intel_clock_t *clock) + const struct intel_limit *limit, + const struct dpll *clock) { if (clock->n < limit->n.min || limit->n.max < clock->n) INTELPllInvalid("n out of range\n"); @@@ -678,7 -681,7 +681,7 @@@ } static int - i9xx_select_p2_div(const intel_limit_t *limit, + i9xx_select_p2_div(const struct intel_limit *limit, const struct intel_crtc_state *crtc_state, int target) { @@@ -713,13 -716,13 +716,13 @@@ * divider from @match_clock used for LVDS downclocking. */ static bool - i9xx_find_best_dpll(const intel_limit_t *limit, + i9xx_find_best_dpll(const struct intel_limit *limit, struct intel_crtc_state *crtc_state, - int target, int refclk, intel_clock_t *match_clock, - intel_clock_t *best_clock) + int target, int refclk, struct dpll *match_clock, + struct dpll *best_clock) { struct drm_device *dev = crtc_state->base.crtc->dev; - intel_clock_t clock; + struct dpll clock; int err = target; memset(best_clock, 0, sizeof(*best_clock)); @@@ -770,13 -773,13 +773,13 @@@ * divider from @match_clock used for LVDS downclocking. */ static bool - pnv_find_best_dpll(const intel_limit_t *limit, + pnv_find_best_dpll(const struct intel_limit *limit, struct intel_crtc_state *crtc_state, - int target, int refclk, intel_clock_t *match_clock, - intel_clock_t *best_clock) + int target, int refclk, struct dpll *match_clock, + struct dpll *best_clock) { struct drm_device *dev = crtc_state->base.crtc->dev; - intel_clock_t clock; + struct dpll clock; int err = target; memset(best_clock, 0, sizeof(*best_clock)); @@@ -825,13 -828,13 +828,13 @@@ * divider from @match_clock used for LVDS downclocking. */ static bool - g4x_find_best_dpll(const intel_limit_t *limit, + g4x_find_best_dpll(const struct intel_limit *limit, struct intel_crtc_state *crtc_state, - int target, int refclk, intel_clock_t *match_clock, - intel_clock_t *best_clock) + int target, int refclk, struct dpll *match_clock, + struct dpll *best_clock) { struct drm_device *dev = crtc_state->base.crtc->dev; - intel_clock_t clock; + struct dpll clock; int max_n; bool found = false; /* approximately equals target * 0.00585 */ @@@ -877,8 -880,8 +880,8 @@@ * best configuration and error found so far. Return the calculated error. */ static bool vlv_PLL_is_optimal(struct drm_device *dev, int target_freq, - const intel_clock_t *calculated_clock, - const intel_clock_t *best_clock, + const struct dpll *calculated_clock, + const struct dpll *best_clock, unsigned int best_error_ppm, unsigned int *error_ppm) { @@@ -918,14 -921,14 +921,14 @@@ * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2. */ static bool - vlv_find_best_dpll(const intel_limit_t *limit, + vlv_find_best_dpll(const struct intel_limit *limit, struct intel_crtc_state *crtc_state, - int target, int refclk, intel_clock_t *match_clock, - intel_clock_t *best_clock) + int target, int refclk, struct dpll *match_clock, + struct dpll *best_clock) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); struct drm_device *dev = crtc->base.dev; - intel_clock_t clock; + struct dpll clock; unsigned int bestppm = 1000000; /* min update 19.2 MHz */ int max_n = min(limit->n.max, refclk / 19200); @@@ -977,15 -980,15 +980,15 @@@ * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2. */ static bool - chv_find_best_dpll(const intel_limit_t *limit, + chv_find_best_dpll(const struct intel_limit *limit, struct intel_crtc_state *crtc_state, - int target, int refclk, intel_clock_t *match_clock, - intel_clock_t *best_clock) + int target, int refclk, struct dpll *match_clock, + struct dpll *best_clock) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); struct drm_device *dev = crtc->base.dev; unsigned int best_error_ppm; - intel_clock_t clock; + struct dpll clock; uint64_t m2; int found = false; @@@ -1035,10 -1038,10 +1038,10 @@@ } bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state, int target_clock, - intel_clock_t *best_clock) + struct dpll *best_clock) { int refclk = 100000; - const intel_limit_t *limit = &intel_limits_bxt; + const struct intel_limit *limit = &intel_limits_bxt; return chv_find_best_dpll(limit, crtc_state, target_clock, refclk, NULL, best_clock); @@@ -1203,7 -1206,7 +1206,7 @@@ static void assert_fdi_tx_pll_enabled(s u32 val; /* ILK FDI PLL is always enabled */ - if (INTEL_INFO(dev_priv)->gen == 5) + if (IS_GEN5(dev_priv)) return; /* On Haswell, DDI ports are responsible for the FDI PLL setup */ @@@ -2309,7 -2312,7 +2312,7 @@@ err_pm return ret; } - static void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation) + void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation) { struct drm_i915_gem_object *obj = intel_fb_obj(fb); struct i915_ggtt_view view; @@@ -3110,17 -3113,12 +3113,12 @@@ intel_pipe_set_base_atomic(struct drm_c return -ENODEV; } - static void intel_complete_page_flips(struct drm_device *dev) + static void intel_complete_page_flips(struct drm_i915_private *dev_priv) { - struct drm_crtc *crtc; - - for_each_crtc(dev, crtc) { - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum plane plane = intel_crtc->plane; + struct intel_crtc *crtc; - intel_prepare_page_flip(dev, plane); - intel_finish_page_flip_plane(dev, plane); - } + for_each_intel_crtc(dev_priv->dev, crtc) + intel_finish_page_flip_cs(dev_priv, crtc->pipe); } static void intel_update_primary_planes(struct drm_device *dev) @@@ -3143,41 -3141,39 +3141,39 @@@ } } - void intel_prepare_reset(struct drm_device *dev) + void intel_prepare_reset(struct drm_i915_private *dev_priv) { /* no reset support for gen2 */ - if (IS_GEN2(dev)) + if (IS_GEN2(dev_priv)) return; /* reset doesn't touch the display */ - if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev)) + if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) return; - drm_modeset_lock_all(dev); + drm_modeset_lock_all(dev_priv->dev); /* * Disabling the crtcs gracefully seems nicer. Also the * g33 docs say we should at least disable all the planes. */ - intel_display_suspend(dev); + intel_display_suspend(dev_priv->dev); } - void intel_finish_reset(struct drm_device *dev) + void intel_finish_reset(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(dev); - /* * Flips in the rings will be nuked by the reset, * so complete all pending flips so that user space * will get its events and not get stuck. */ - intel_complete_page_flips(dev); + intel_complete_page_flips(dev_priv); /* no reset support for gen2 */ - if (IS_GEN2(dev)) + if (IS_GEN2(dev_priv)) return; /* reset doesn't touch the display */ - if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev)) { + if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { /* * Flips in the rings have been nuked by the reset, * so update the base address of all primary @@@ -3187,7 -3183,7 +3183,7 @@@ * FIXME: Atomic will make this obsolete since we won't schedule * CS-based flips (which might get lost in gpu resets) any more. */ - intel_update_primary_planes(dev); + intel_update_primary_planes(dev_priv->dev); return; } @@@ -3198,18 -3194,18 +3194,18 @@@ intel_runtime_pm_disable_interrupts(dev_priv); intel_runtime_pm_enable_interrupts(dev_priv); - intel_modeset_init_hw(dev); + intel_modeset_init_hw(dev_priv->dev); spin_lock_irq(&dev_priv->irq_lock); if (dev_priv->display.hpd_irq_setup) - dev_priv->display.hpd_irq_setup(dev); + dev_priv->display.hpd_irq_setup(dev_priv); spin_unlock_irq(&dev_priv->irq_lock); - intel_display_resume(dev); + intel_display_resume(dev_priv->dev); intel_hpd_init(dev_priv); - drm_modeset_unlock_all(dev); + drm_modeset_unlock_all(dev_priv->dev); } static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc) @@@ -3224,7 -3220,7 +3220,7 @@@ return false; spin_lock_irq(&dev->event_lock); - pending = to_intel_crtc(crtc)->unpin_work != NULL; + pending = to_intel_crtc(crtc)->flip_work != NULL; spin_unlock_irq(&dev->event_lock); return pending; @@@ -3803,7 -3799,7 +3799,7 @@@ bool intel_has_pending_fb_unpin(struct if (atomic_read(&crtc->unpin_work_count) == 0) continue; - if (crtc->unpin_work) + if (crtc->flip_work) intel_wait_for_vblank(dev, crtc->pipe); return true; @@@ -3815,11 -3811,9 +3811,9 @@@ static void page_flip_completed(struct intel_crtc *intel_crtc) { struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); - struct intel_unpin_work *work = intel_crtc->unpin_work; + struct intel_flip_work *work = intel_crtc->flip_work; - /* ensure that the unpin work is consistent wrt ->pending. */ - smp_rmb(); - intel_crtc->unpin_work = NULL; + intel_crtc->flip_work = NULL; if (work->event) drm_crtc_send_vblank_event(&intel_crtc->base, work->event); @@@ -3827,7 -3821,7 +3821,7 @@@ drm_crtc_vblank_put(&intel_crtc->base); wake_up_all(&dev_priv->pending_flip_queue); - queue_work(dev_priv->wq, &work->work); + queue_work(dev_priv->wq, &work->unpin_work); trace_i915_flip_complete(intel_crtc->plane, work->pending_flip_obj); @@@ -3851,9 -3845,11 +3845,11 @@@ static int intel_crtc_wait_for_pending_ if (ret == 0) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_flip_work *work; spin_lock_irq(&dev->event_lock); - if (intel_crtc->unpin_work) { + work = intel_crtc->flip_work; + if (work && !is_mmio_work(work)) { WARN_ONCE(1, "Removing stuck page flip\n"); page_flip_completed(intel_crtc); } @@@ -5328,32 -5324,33 +5324,33 @@@ static void intel_update_cdclk(struct d dev_priv->cdclk_freq); /* - * Program the gmbus_freq based on the cdclk frequency. - * BSpec erroneously claims we should aim for 4MHz, but - * in fact 1MHz is the correct frequency. + * 9:0 CMBUS [sic] CDCLK frequency (cdfreq): + * Programmng [sic] note: bit[9:2] should be programmed to the number + * of cdclk that generates 4MHz reference clock freq which is used to + * generate GMBus clock. This will vary with the cdclk freq. */ - if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { - /* - * Program the gmbus_freq based on the cdclk frequency. - * BSpec erroneously claims we should aim for 4MHz, but - * in fact 1MHz is the correct frequency. - */ + if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) I915_WRITE(GMBUSFREQ_VLV, DIV_ROUND_UP(dev_priv->cdclk_freq, 1000)); - } if (dev_priv->max_cdclk_freq == 0) intel_update_max_cdclk(dev); } - static void broxton_set_cdclk(struct drm_i915_private *dev_priv, int frequency) + /* convert from kHz to .1 fixpoint MHz with -1MHz offset */ + static int skl_cdclk_decimal(int cdclk) + { + return DIV_ROUND_CLOSEST(cdclk - 1000, 500); + } + + static void broxton_set_cdclk(struct drm_i915_private *dev_priv, int cdclk) { uint32_t divider; uint32_t ratio; - uint32_t current_freq; + uint32_t current_cdclk; int ret; /* frequency = 19.2MHz * ratio / 2 / div{1,1.5,2,4} */ - switch (frequency) { + switch (cdclk) { case 144000: divider = BXT_CDCLK_CD2X_DIV_SEL_4; ratio = BXT_DE_PLL_RATIO(60); @@@ -5383,7 -5380,7 +5380,7 @@@ divider = 0; break; default: - DRM_ERROR("unsupported CDCLK freq %d", frequency); + DRM_ERROR("unsupported CDCLK freq %d", cdclk); return; } @@@ -5396,13 -5393,13 +5393,13 @@@ if (ret) { DRM_ERROR("PCode CDCLK freq change notify failed (err %d, freq %d)\n", - ret, frequency); + ret, cdclk); return; } - current_freq = I915_READ(CDCLK_CTL) & CDCLK_FREQ_DECIMAL_MASK; + current_cdclk = I915_READ(CDCLK_CTL) & CDCLK_FREQ_DECIMAL_MASK; /* convert from .1 fixpoint MHz with -1MHz offset to kHz */ - current_freq = current_freq * 500 + 1000; + current_cdclk = current_cdclk * 500 + 1000; /* * DE PLL has to be disabled when @@@ -5410,8 -5407,8 +5407,8 @@@ * - before setting to 624MHz (PLL needs toggling) * - before setting to any frequency from 624MHz (PLL needs toggling) */ - if (frequency == 19200 || frequency == 624000 || - current_freq == 624000) { + if (cdclk == 19200 || cdclk == 624000 || + current_cdclk == 624000) { I915_WRITE(BXT_DE_PLL_ENABLE, ~BXT_DE_PLL_PLL_ENABLE); /* Timeout 200us */ if (wait_for(!(I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK), @@@ -5419,7 -5416,7 +5416,7 @@@ DRM_ERROR("timout waiting for DE PLL unlock\n"); } - if (frequency != 19200) { + if (cdclk != 19200) { uint32_t val; val = I915_READ(BXT_DE_PLL_CTL); @@@ -5432,31 -5429,29 +5429,29 @@@ if (wait_for(I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK, 1)) DRM_ERROR("timeout waiting for DE PLL lock\n"); - val = I915_READ(CDCLK_CTL); - val &= ~BXT_CDCLK_CD2X_DIV_SEL_MASK; - val |= divider; + val = divider | skl_cdclk_decimal(cdclk); + /* + * FIXME if only the cd2x divider needs changing, it could be done + * without shutting off the pipe (if only one pipe is active). + */ + val |= BXT_CDCLK_CD2X_PIPE_NONE; /* * Disable SSA Precharge when CD clock frequency < 500 MHz, * enable otherwise. */ - val &= ~BXT_CDCLK_SSA_PRECHARGE_ENABLE; - if (frequency >= 500000) + if (cdclk >= 500000) val |= BXT_CDCLK_SSA_PRECHARGE_ENABLE; - - val &= ~CDCLK_FREQ_DECIMAL_MASK; - /* convert from kHz to .1 fixpoint MHz with -1MHz offset */ - val |= (frequency - 1000) / 500; I915_WRITE(CDCLK_CTL, val); } mutex_lock(&dev_priv->rps.hw_lock); ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, - DIV_ROUND_UP(frequency, 25000)); + DIV_ROUND_UP(cdclk, 25000)); mutex_unlock(&dev_priv->rps.hw_lock); if (ret) { DRM_ERROR("PCode CDCLK freq set failed, (err %d, freq %d)\n", - ret, frequency); + ret, cdclk); return; } @@@ -5545,11 -5540,6 +5540,6 @@@ static const struct skl_cdclk_entry { .freq = 675000, .vco = 8100 }, }; - static unsigned int skl_cdclk_decimal(unsigned int freq) - { - return (freq - 1000) / 500; - } - static unsigned int skl_cdclk_get_vco(unsigned int freq) { unsigned int i; @@@ -5565,23 -5555,18 +5555,18 @@@ } static void - skl_dpll0_enable(struct drm_i915_private *dev_priv, unsigned int required_vco) + skl_dpll0_enable(struct drm_i915_private *dev_priv, int vco) { - unsigned int min_freq; + int min_cdclk; u32 val; /* select the minimum CDCLK before enabling DPLL 0 */ - val = I915_READ(CDCLK_CTL); - val &= ~CDCLK_FREQ_SEL_MASK | ~CDCLK_FREQ_DECIMAL_MASK; - val |= CDCLK_FREQ_337_308; - - if (required_vco == 8640) - min_freq = 308570; + if (vco == 8640) + min_cdclk = 308570; else - min_freq = 337500; - - val = CDCLK_FREQ_337_308 | skl_cdclk_decimal(min_freq); + min_cdclk = 337500; + val = CDCLK_FREQ_337_308 | skl_cdclk_decimal(min_cdclk); I915_WRITE(CDCLK_CTL, val); POSTING_READ(CDCLK_CTL); @@@ -5599,7 -5584,7 +5584,7 @@@ val &= ~(DPLL_CTRL1_HDMI_MODE(SKL_DPLL0) | DPLL_CTRL1_SSC(SKL_DPLL0) | DPLL_CTRL1_LINK_RATE_MASK(SKL_DPLL0)); val |= DPLL_CTRL1_OVERRIDE(SKL_DPLL0); - if (required_vco == 8640) + if (vco == 8640) val |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1080, SKL_DPLL0); else @@@ -5615,6 -5600,14 +5600,14 @@@ DRM_ERROR("DPLL0 not locked\n"); } + static void + skl_dpll0_disable(struct drm_i915_private *dev_priv) + { + I915_WRITE(LCPLL1_CTL, I915_READ(LCPLL1_CTL) & ~LCPLL_PLL_ENABLE); + if (wait_for(!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_LOCK), 1)) + DRM_ERROR("Couldn't disable DPLL0\n"); + } + static bool skl_cdclk_pcu_ready(struct drm_i915_private *dev_priv) { int ret; @@@ -5642,12 -5635,12 +5635,12 @@@ static bool skl_cdclk_wait_for_pcu_read return false; } - static void skl_set_cdclk(struct drm_i915_private *dev_priv, unsigned int freq) + static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk) { struct drm_device *dev = dev_priv->dev; u32 freq_select, pcu_ack; - DRM_DEBUG_DRIVER("Changing CDCLK to %dKHz\n", freq); + DRM_DEBUG_DRIVER("Changing CDCLK to %dKHz\n", cdclk); if (!skl_cdclk_wait_for_pcu_ready(dev_priv)) { DRM_ERROR("failed to inform PCU about cdclk change\n"); @@@ -5655,7 -5648,7 +5648,7 @@@ } /* set CDCLK_CTL */ - switch(freq) { + switch (cdclk) { case 450000: case 432000: freq_select = CDCLK_FREQ_450_432; @@@ -5678,7 -5671,7 +5671,7 @@@ break; } - I915_WRITE(CDCLK_CTL, freq_select | skl_cdclk_decimal(freq)); + I915_WRITE(CDCLK_CTL, freq_select | skl_cdclk_decimal(cdclk)); POSTING_READ(CDCLK_CTL); /* inform PCU of the change */ @@@ -5700,21 -5693,18 +5693,18 @@@ void skl_uninit_cdclk(struct drm_i915_p if (I915_READ(DBUF_CTL) & DBUF_POWER_STATE) DRM_ERROR("DBuf power disable timeout\n"); - /* disable DPLL0 */ - I915_WRITE(LCPLL1_CTL, I915_READ(LCPLL1_CTL) & ~LCPLL_PLL_ENABLE); - if (wait_for(!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_LOCK), 1)) - DRM_ERROR("Couldn't disable DPLL0\n"); + skl_dpll0_disable(dev_priv); } void skl_init_cdclk(struct drm_i915_private *dev_priv) { - unsigned int required_vco; + unsigned int vco; /* DPLL0 not enabled (happens on early BIOS versions) */ if (!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_ENABLE)) { /* enable DPLL0 */ - required_vco = skl_cdclk_get_vco(dev_priv->skl_boot_cdclk); - skl_dpll0_enable(dev_priv, required_vco); + vco = skl_cdclk_get_vco(dev_priv->skl_boot_cdclk); + skl_dpll0_enable(dev_priv, vco); } /* set CDCLK to the frequency the BIOS chose */ @@@ -5906,21 -5896,19 +5896,19 @@@ static int valleyview_calc_cdclk(struc return 200000; } - static int broxton_calc_cdclk(struct drm_i915_private *dev_priv, - int max_pixclk) + static int broxton_calc_cdclk(int max_pixclk) { /* * FIXME: - * - remove the guardband, it's not needed on BXT * - set 19.2MHz bypass frequency if there are no active pipes */ - if (max_pixclk > 576000*9/10) + if (max_pixclk > 576000) return 624000; - else if (max_pixclk > 384000*9/10) + else if (max_pixclk > 384000) return 576000; - else if (max_pixclk > 288000*9/10) + else if (max_pixclk > 288000) return 384000; - else if (max_pixclk > 144000*9/10) + else if (max_pixclk > 144000) return 288000; else return 144000; @@@ -5963,9 -5951,6 +5951,6 @@@ static int valleyview_modeset_calc_cdcl struct intel_atomic_state *intel_state = to_intel_atomic_state(state); - if (max_pixclk < 0) - return max_pixclk; - intel_state->cdclk = intel_state->dev_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk); @@@ -5977,20 -5962,15 +5962,15 @@@ static int broxton_modeset_calc_cdclk(struct drm_atomic_state *state) { - struct drm_device *dev = state->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - int max_pixclk = intel_mode_max_pixclk(dev, state); + int max_pixclk = ilk_max_pixel_rate(state); struct intel_atomic_state *intel_state = to_intel_atomic_state(state); - if (max_pixclk < 0) - return max_pixclk; - intel_state->cdclk = intel_state->dev_cdclk = - broxton_calc_cdclk(dev_priv, max_pixclk); + broxton_calc_cdclk(max_pixclk); if (!intel_state->active_crtcs) - intel_state->dev_cdclk = broxton_calc_cdclk(dev_priv, 0); + intel_state->dev_cdclk = broxton_calc_cdclk(0); return 0; } @@@ -6252,7 -6232,7 +6232,7 @@@ static void intel_crtc_disable_noatomic return; if (to_intel_plane_state(crtc->primary->state)->visible) { - WARN_ON(intel_crtc->unpin_work); + WARN_ON(intel_crtc->flip_work); intel_pre_disable_primary_noatomic(crtc); @@@ -7063,7 -7043,7 +7043,7 @@@ static uint32_t i9xx_dpll_compute_fp(st static void i9xx_update_pll_dividers(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state, - intel_clock_t *reduced_clock) + struct dpll *reduced_clock) { struct drm_device *dev = crtc->base.dev; u32 fp, fp2 = 0; @@@ -7487,7 -7467,7 +7467,7 @@@ void vlv_force_pll_off(struct drm_devic static void i9xx_compute_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state, - intel_clock_t *reduced_clock) + struct dpll *reduced_clock) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@@ -7563,7 -7543,7 +7543,7 @@@ static void i8xx_compute_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state, - intel_clock_t *reduced_clock) + struct dpll *reduced_clock) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@@ -7817,7 -7797,7 +7797,7 @@@ static int i8xx_crtc_compute_clock(stru { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - const intel_limit_t *limit; + const struct intel_limit *limit; int refclk = 48000; memset(&crtc_state->dpll_hw_state, 0, @@@ -7853,7 -7833,7 +7833,7 @@@ static int g4x_crtc_compute_clock(struc { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - const intel_limit_t *limit; + const struct intel_limit *limit; int refclk = 96000; memset(&crtc_state->dpll_hw_state, 0, @@@ -7896,7 -7876,7 +7876,7 @@@ static int pnv_crtc_compute_clock(struc { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - const intel_limit_t *limit; + const struct intel_limit *limit; int refclk = 96000; memset(&crtc_state->dpll_hw_state, 0, @@@ -7930,7 -7910,7 +7910,7 @@@ static int i9xx_crtc_compute_clock(stru { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - const intel_limit_t *limit; + const struct intel_limit *limit; int refclk = 96000; memset(&crtc_state->dpll_hw_state, 0, @@@ -7963,7 -7943,7 +7943,7 @@@ static int chv_crtc_compute_clock(struc struct intel_crtc_state *crtc_state) { int refclk = 100000; - const intel_limit_t *limit = &intel_limits_chv; + const struct intel_limit *limit = &intel_limits_chv; memset(&crtc_state->dpll_hw_state, 0, sizeof(crtc_state->dpll_hw_state)); @@@ -7984,7 -7964,7 +7964,7 @@@ static int vlv_crtc_compute_clock(struc struct intel_crtc_state *crtc_state) { int refclk = 100000; - const intel_limit_t *limit = &intel_limits_vlv; + const struct intel_limit *limit = &intel_limits_vlv; memset(&crtc_state->dpll_hw_state, 0, sizeof(crtc_state->dpll_hw_state)); @@@ -8034,7 -8014,7 +8014,7 @@@ static void vlv_crtc_clock_get(struct i struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; int pipe = pipe_config->cpu_transcoder; - intel_clock_t clock; + struct dpll clock; u32 mdiv; int refclk = 100000; @@@ -8131,7 -8111,7 +8111,7 @@@ static void chv_crtc_clock_get(struct i struct drm_i915_private *dev_priv = dev->dev_private; int pipe = pipe_config->cpu_transcoder; enum dpio_channel port = vlv_pipe_to_channel(pipe); - intel_clock_t clock; + struct dpll clock; u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2, pll_dw3; int refclk = 100000; @@@ -8794,7 -8774,7 +8774,7 @@@ static bool ironlake_needs_fb_cb_tune(s static void ironlake_compute_dpll(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state, - intel_clock_t *reduced_clock) + struct dpll *reduced_clock) { struct drm_crtc *crtc = &intel_crtc->base; struct drm_device *dev = crtc->dev; @@@ -8902,10 -8882,10 +8882,10 @@@ static int ironlake_crtc_compute_clock( { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - intel_clock_t reduced_clock; + struct dpll reduced_clock; bool has_reduced_clock = false; struct intel_shared_dpll *pll; - const intel_limit_t *limit; + const struct intel_limit *limit; int refclk = 120000; memset(&crtc_state->dpll_hw_state, 0, @@@ -9300,6 -9280,10 +9280,10 @@@ static bool ironlake_get_pipe_config(st ironlake_get_fdi_m_n_config(crtc, pipe_config); if (HAS_PCH_IBX(dev_priv)) { + /* + * The pipe->pch transcoder and pch transcoder->pll + * mapping is fixed. + */ pll_id = (enum intel_dpll_id) crtc->pipe; } else { tmp = I915_READ(PCH_DPLL_SEL); @@@ -9687,6 -9671,18 +9671,18 @@@ static void broadwell_set_cdclk(struct cdclk, dev_priv->cdclk_freq); } + static int broadwell_calc_cdclk(int max_pixclk) + { + if (max_pixclk > 540000) + return 675000; + else if (max_pixclk > 450000) + return 540000; + else if (max_pixclk > 337500) + return 450000; + else + return 337500; + } + static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->dev); @@@ -9698,14 -9694,7 +9694,7 @@@ * FIXME should also account for plane ratio * once 64bpp pixel formats are supported. */ - if (max_pixclk > 540000) - cdclk = 675000; - else if (max_pixclk > 450000) - cdclk = 540000; - else if (max_pixclk > 337500) - cdclk = 450000; - else - cdclk = 337500; + cdclk = broadwell_calc_cdclk(max_pixclk); if (cdclk > dev_priv->max_cdclk_freq) { DRM_DEBUG_KMS("requested cdclk (%d kHz) exceeds max (%d kHz)\n", @@@ -9715,7 -9704,7 +9704,7 @@@ intel_state->cdclk = intel_state->dev_cdclk = cdclk; if (!intel_state->active_crtcs) - intel_state->dev_cdclk = 337500; + intel_state->dev_cdclk = broadwell_calc_cdclk(0); return 0; } @@@ -9850,6 -9839,10 +9839,10 @@@ static bool hsw_get_transcoder_state(st enum intel_display_power_domain power_domain; u32 tmp; + /* + * The pipe->transcoder mapping is fixed with the exception of the eDP + * transcoder handled below. + */ pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; /* @@@ -10317,10 -10310,10 +10310,10 @@@ intel_framebuffer_create_for_mode(struc struct drm_i915_gem_object *obj; struct drm_mode_fb_cmd2 mode_cmd = { 0 }; - obj = i915_gem_alloc_object(dev, + obj = i915_gem_object_create(dev, intel_framebuffer_size_for_mode(mode, bpp)); - if (obj == NULL) - return ERR_PTR(-ENOMEM); + if (IS_ERR(obj)) + return ERR_CAST(obj); mode_cmd.width = mode->hdisplay; mode_cmd.height = mode->vdisplay; @@@ -10632,7 -10625,7 +10625,7 @@@ static void i9xx_crtc_clock_get(struct int pipe = pipe_config->cpu_transcoder; u32 dpll = pipe_config->dpll_hw_state.dpll; u32 fp; - intel_clock_t clock; + struct dpll clock; int port_clock; int refclk = i9xx_pll_refclk(dev, pipe_config); @@@ -10806,31 -10799,27 +10799,27 @@@ struct drm_display_mode *intel_crtc_mod return mode; } - void intel_mark_busy(struct drm_device *dev) + void intel_mark_busy(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; - if (dev_priv->mm.busy) return; intel_runtime_pm_get(dev_priv); i915_update_gfx_val(dev_priv); - if (INTEL_INFO(dev)->gen >= 6) + if (INTEL_GEN(dev_priv) >= 6) gen6_rps_busy(dev_priv); dev_priv->mm.busy = true; } - void intel_mark_idle(struct drm_device *dev) + void intel_mark_idle(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; - if (!dev_priv->mm.busy) return; dev_priv->mm.busy = false; - if (INTEL_INFO(dev)->gen >= 6) - gen6_rps_idle(dev->dev_private); + if (INTEL_GEN(dev_priv) >= 6) + gen6_rps_idle(dev_priv); intel_runtime_pm_put(dev_priv); } @@@ -10839,15 -10828,16 +10828,16 @@@ static void intel_crtc_destroy(struct d { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct drm_device *dev = crtc->dev; - struct intel_unpin_work *work; + struct intel_flip_work *work; spin_lock_irq(&dev->event_lock); - work = intel_crtc->unpin_work; - intel_crtc->unpin_work = NULL; + work = intel_crtc->flip_work; + intel_crtc->flip_work = NULL; spin_unlock_irq(&dev->event_lock); if (work) { - cancel_work_sync(&work->work); + cancel_work_sync(&work->mmio_work); + cancel_work_sync(&work->unpin_work); kfree(work); } @@@ -10858,12 -10848,15 +10848,15 @@@ static void intel_unpin_work_fn(struct work_struct *__work) { - struct intel_unpin_work *work = - container_of(__work, struct intel_unpin_work, work); + struct intel_flip_work *work = + container_of(__work, struct intel_flip_work, unpin_work); struct intel_crtc *crtc = to_intel_crtc(work->crtc); struct drm_device *dev = crtc->base.dev; struct drm_plane *primary = crtc->base.primary; + if (is_mmio_work(work)) + flush_work(&work->mmio_work); + mutex_lock(&dev->struct_mutex); intel_unpin_fb_obj(work->old_fb, primary->state->rotation); drm_gem_object_unreference(&work->pending_flip_obj->base); @@@ -10882,60 -10875,14 +10875,14 @@@ kfree(work); } - static void do_intel_finish_page_flip(struct drm_device *dev, - struct drm_crtc *crtc) - { - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_unpin_work *work; - unsigned long flags; - - /* Ignore early vblank irqs */ - if (intel_crtc == NULL) - return; - - /* - * This is called both by irq handlers and the reset code (to complete - * lost pageflips) so needs the full irqsave spinlocks. - */ - spin_lock_irqsave(&dev->event_lock, flags); - work = intel_crtc->unpin_work; - - /* Ensure we don't miss a work->pending update ... */ - smp_rmb(); - - if (work == NULL || atomic_read(&work->pending) < INTEL_FLIP_COMPLETE) { - spin_unlock_irqrestore(&dev->event_lock, flags); - return; - } - - page_flip_completed(intel_crtc); - - spin_unlock_irqrestore(&dev->event_lock, flags); - } - - void intel_finish_page_flip(struct drm_device *dev, int pipe) - { - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; - - do_intel_finish_page_flip(dev, crtc); - } - - void intel_finish_page_flip_plane(struct drm_device *dev, int plane) - { - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_crtc *crtc = dev_priv->plane_to_crtc_mapping[plane]; - - do_intel_finish_page_flip(dev, crtc); - } - /* Is 'a' after or equal to 'b'? */ static bool g4x_flip_count_after_eq(u32 a, u32 b) { return !((a - b) & 0x80000000); } - static bool page_flip_finished(struct intel_crtc *crtc) + static bool __pageflip_finished_cs(struct intel_crtc *crtc, + struct intel_flip_work *work) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@@ -10977,40 -10924,103 +10924,103 @@@ * anyway, we don't really care. */ return (I915_READ(DSPSURFLIVE(crtc->plane)) & ~0xfff) == - crtc->unpin_work->gtt_offset && + crtc->flip_work->gtt_offset && g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_G4X(crtc->pipe)), - crtc->unpin_work->flip_count); + crtc->flip_work->flip_count); } - void intel_prepare_page_flip(struct drm_device *dev, int plane) + static bool + __pageflip_finished_mmio(struct intel_crtc *crtc, + struct intel_flip_work *work) { - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = - to_intel_crtc(dev_priv->plane_to_crtc_mapping[plane]); + /* + * MMIO work completes when vblank is different from + * flip_queued_vblank. + * + * Reset counter value doesn't matter, this is handled by + * i915_wait_request finishing early, so no need to handle + * reset here. + */ + return intel_crtc_get_vblank_counter(crtc) != work->flip_queued_vblank; + } + + + static bool pageflip_finished(struct intel_crtc *crtc, + struct intel_flip_work *work) + { + if (!atomic_read(&work->pending)) + return false; + + smp_rmb(); + + if (is_mmio_work(work)) + return __pageflip_finished_mmio(crtc, work); + else + return __pageflip_finished_cs(crtc, work); + } + + void intel_finish_page_flip_cs(struct drm_i915_private *dev_priv, int pipe) + { + struct drm_device *dev = dev_priv->dev; + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_flip_work *work; unsigned long flags; + /* Ignore early vblank irqs */ + if (!crtc) + return; + + /* + * This is called both by irq handlers and the reset code (to complete + * lost pageflips) so needs the full irqsave spinlocks. + */ + spin_lock_irqsave(&dev->event_lock, flags); + work = intel_crtc->flip_work; + + if (work != NULL && + !is_mmio_work(work) && + pageflip_finished(intel_crtc, work)) + page_flip_completed(intel_crtc); + + spin_unlock_irqrestore(&dev->event_lock, flags); + } + + void intel_finish_page_flip_mmio(struct drm_i915_private *dev_priv, int pipe) + { + struct drm_device *dev = dev_priv->dev; + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_flip_work *work; + unsigned long flags; + + /* Ignore early vblank irqs */ + if (!crtc) + return; /* * This is called both by irq handlers and the reset code (to complete * lost pageflips) so needs the full irqsave spinlocks. - * - * NB: An MMIO update of the plane base pointer will also - * generate a page-flip completion irq, i.e. every modeset - * is also accompanied by a spurious intel_prepare_page_flip(). */ spin_lock_irqsave(&dev->event_lock, flags); - if (intel_crtc->unpin_work && page_flip_finished(intel_crtc)) - atomic_inc_not_zero(&intel_crtc->unpin_work->pending); + work = intel_crtc->flip_work; + + if (work != NULL && + is_mmio_work(work) && + pageflip_finished(intel_crtc, work)) + page_flip_completed(intel_crtc); + spin_unlock_irqrestore(&dev->event_lock, flags); } - static inline void intel_mark_page_flip_active(struct intel_unpin_work *work) + static inline void intel_mark_page_flip_active(struct intel_crtc *crtc, + struct intel_flip_work *work) { + work->flip_queued_vblank = intel_crtc_get_vblank_counter(crtc); + /* Ensure that the work item is consistent when activating it ... */ - smp_wmb(); - atomic_set(&work->pending, INTEL_FLIP_PENDING); - /* and that it is marked active as soon as the irq could fire. */ - smp_wmb(); + smp_mb__before_atomic(); + atomic_set(&work->pending, 1); } static int intel_gen2_queue_flip(struct drm_device *dev, @@@ -11041,10 -11051,9 +11051,9 @@@ intel_ring_emit(engine, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(engine, fb->pitches[0]); - intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset); + intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset); intel_ring_emit(engine, 0); /* aux display base address, unused */ - intel_mark_page_flip_active(intel_crtc->unpin_work); return 0; } @@@ -11073,10 -11082,9 +11082,9 @@@ static int intel_gen3_queue_flip(struc intel_ring_emit(engine, MI_DISPLAY_FLIP_I915 | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(engine, fb->pitches[0]); - intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset); + intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset); intel_ring_emit(engine, MI_NOOP); - intel_mark_page_flip_active(intel_crtc->unpin_work); return 0; } @@@ -11104,7 -11112,7 +11112,7 @@@ static int intel_gen4_queue_flip(struc intel_ring_emit(engine, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(engine, fb->pitches[0]); - intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset | + intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset | obj->tiling_mode); /* XXX Enabling the panel-fitter across page-flip is so far @@@ -11115,7 -11123,6 +11123,6 @@@ pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff; intel_ring_emit(engine, pf | pipesrc); - intel_mark_page_flip_active(intel_crtc->unpin_work); return 0; } @@@ -11139,7 -11146,7 +11146,7 @@@ static int intel_gen6_queue_flip(struc intel_ring_emit(engine, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(engine, fb->pitches[0] | obj->tiling_mode); - intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset); + intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset); /* Contrary to the suggestions in the documentation, * "Enable Panel Fitter" does not seem to be required when page @@@ -11151,7 -11158,6 +11158,6 @@@ pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff; intel_ring_emit(engine, pf | pipesrc); - intel_mark_page_flip_active(intel_crtc->unpin_work); return 0; } @@@ -11243,10 -11249,9 +11249,9 @@@ static int intel_gen7_queue_flip(struc intel_ring_emit(engine, MI_DISPLAY_FLIP_I915 | plane_bit); intel_ring_emit(engine, (fb->pitches[0] | obj->tiling_mode)); - intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset); + intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset); intel_ring_emit(engine, (MI_NOOP)); - intel_mark_page_flip_active(intel_crtc->unpin_work); return 0; } @@@ -11264,7 -11269,7 +11269,7 @@@ static bool use_mmio_flip(struct intel_ if (engine == NULL) return true; - if (INTEL_INFO(engine->dev)->gen < 5) + if (INTEL_GEN(engine->i915) < 5) return false; if (i915.use_mmio_flip < 0) @@@ -11283,7 -11288,7 +11288,7 @@@ static void skl_do_mmio_flip(struct intel_crtc *intel_crtc, unsigned int rotation, - struct intel_unpin_work *work) + struct intel_flip_work *work) { struct drm_device *dev = intel_crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@@ -11335,7 -11340,7 +11340,7 @@@ } static void ilk_do_mmio_flip(struct intel_crtc *intel_crtc, - struct intel_unpin_work *work) + struct intel_flip_work *work) { struct drm_device *dev = intel_crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@@ -11358,48 -11363,20 +11363,20 @@@ POSTING_READ(DSPSURF(intel_crtc->plane)); } - /* - * XXX: This is the temporary way to update the plane registers until we get - * around to using the usual plane update functions for MMIO flips - */ - static void intel_do_mmio_flip(struct intel_mmio_flip *mmio_flip) - { - struct intel_crtc *crtc = mmio_flip->crtc; - struct intel_unpin_work *work; - - spin_lock_irq(&crtc->base.dev->event_lock); - work = crtc->unpin_work; - spin_unlock_irq(&crtc->base.dev->event_lock); - if (work == NULL) - return; - - intel_mark_page_flip_active(work); - - intel_pipe_update_start(crtc); - - if (INTEL_INFO(mmio_flip->i915)->gen >= 9) - skl_do_mmio_flip(crtc, mmio_flip->rotation, work); - else - /* use_mmio_flip() retricts MMIO flips to ilk+ */ - ilk_do_mmio_flip(crtc, work); - - intel_pipe_update_end(crtc); - } - - static void intel_mmio_flip_work_func(struct work_struct *work) + static void intel_mmio_flip_work_func(struct work_struct *w) { - struct intel_mmio_flip *mmio_flip = - container_of(work, struct intel_mmio_flip, work); + struct intel_flip_work *work = + container_of(w, struct intel_flip_work, mmio_work); + struct intel_crtc *crtc = to_intel_crtc(work->crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_framebuffer *intel_fb = - to_intel_framebuffer(mmio_flip->crtc->base.primary->fb); + to_intel_framebuffer(crtc->base.primary->fb); struct drm_i915_gem_object *obj = intel_fb->obj; - if (mmio_flip->req) { - WARN_ON(__i915_wait_request(mmio_flip->req, + if (work->flip_queued_req) + WARN_ON(__i915_wait_request(work->flip_queued_req, false, NULL, - &mmio_flip->i915->rps.mmioflips)); - i915_gem_request_unreference__unlocked(mmio_flip->req); - } + &dev_priv->rps.mmioflips)); /* For framebuffer backed by dmabuf, wait for fence */ if (obj->base.dma_buf) @@@ -11407,29 -11384,15 +11384,15 @@@ false, false, MAX_SCHEDULE_TIMEOUT) < 0); - intel_do_mmio_flip(mmio_flip); - kfree(mmio_flip); - } - - static int intel_queue_mmio_flip(struct drm_device *dev, - struct drm_crtc *crtc, - struct drm_i915_gem_object *obj) - { - struct intel_mmio_flip *mmio_flip; - - mmio_flip = kmalloc(sizeof(*mmio_flip), GFP_KERNEL); - if (mmio_flip == NULL) - return -ENOMEM; - - mmio_flip->i915 = to_i915(dev); - mmio_flip->req = i915_gem_request_reference(obj->last_write_req); - mmio_flip->crtc = to_intel_crtc(crtc); - mmio_flip->rotation = crtc->primary->state->rotation; + intel_pipe_update_start(crtc); - INIT_WORK(&mmio_flip->work, intel_mmio_flip_work_func); - schedule_work(&mmio_flip->work); + if (INTEL_GEN(dev_priv) >= 9) + skl_do_mmio_flip(crtc, work->rotation, work); + else + /* use_mmio_flip() retricts MMIO flips to ilk+ */ + ilk_do_mmio_flip(crtc, work); - return 0; + intel_pipe_update_end(crtc, work); } static int intel_default_queue_flip(struct drm_device *dev, @@@ -11442,37 -11405,32 +11405,32 @@@ return -ENODEV; } - static bool __intel_pageflip_stall_check(struct drm_device *dev, - struct drm_crtc *crtc) + static bool __pageflip_stall_check_cs(struct drm_i915_private *dev_priv, + struct intel_crtc *intel_crtc, + struct intel_flip_work *work) { - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_unpin_work *work = intel_crtc->unpin_work; - u32 addr; - - if (atomic_read(&work->pending) >= INTEL_FLIP_COMPLETE) - return true; + u32 addr, vblank; - if (atomic_read(&work->pending) < INTEL_FLIP_PENDING) + if (!atomic_read(&work->pending)) return false; - if (!work->enable_stall_check) - return false; + smp_rmb(); + vblank = intel_crtc_get_vblank_counter(intel_crtc); if (work->flip_ready_vblank == 0) { if (work->flip_queued_req && !i915_gem_request_completed(work->flip_queued_req, true)) return false; - work->flip_ready_vblank = drm_crtc_vblank_count(crtc); + work->flip_ready_vblank = vblank; } - if (drm_crtc_vblank_count(crtc) - work->flip_ready_vblank < 3) + if (vblank - work->flip_ready_vblank < 3) return false; /* Potential stall - if we see that the flip has happened, * assume a missed interrupt. */ - if (INTEL_INFO(dev)->gen >= 4) + if (INTEL_GEN(dev_priv) >= 4) addr = I915_HI_DISPBASE(I915_READ(DSPSURF(intel_crtc->plane))); else addr = I915_READ(DSPADDR(intel_crtc->plane)); @@@ -11484,12 -11442,12 +11442,12 @@@ return addr == work->gtt_offset; } - void intel_check_page_flip(struct drm_device *dev, int pipe) + void intel_check_page_flip(struct drm_i915_private *dev_priv, int pipe) { - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_device *dev = dev_priv->dev; struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_unpin_work *work; + struct intel_flip_work *work; WARN_ON(!in_interrupt()); @@@ -11497,16 -11455,20 +11455,20 @@@ return; spin_lock(&dev->event_lock); - work = intel_crtc->unpin_work; - if (work != NULL && __intel_pageflip_stall_check(dev, crtc)) { - WARN_ONCE(1, "Kicking stuck page flip: queued at %d, now %d\n", - work->flip_queued_vblank, drm_vblank_count(dev, pipe)); + work = intel_crtc->flip_work; + + if (work != NULL && !is_mmio_work(work) && + __pageflip_stall_check_cs(dev_priv, intel_crtc, work)) { + WARN_ONCE(1, + "Kicking stuck page flip: queued at %d, now %d\n", + work->flip_queued_vblank, intel_crtc_get_vblank_counter(intel_crtc)); page_flip_completed(intel_crtc); work = NULL; } - if (work != NULL && - drm_vblank_count(dev, pipe) - work->flip_queued_vblank > 1) - intel_queue_rps_boost_for_request(dev, work->flip_queued_req); + + if (work != NULL && !is_mmio_work(work) && + intel_crtc_get_vblank_counter(intel_crtc) - work->flip_queued_vblank > 1) + intel_queue_rps_boost_for_request(work->flip_queued_req); spin_unlock(&dev->event_lock); } @@@ -11522,7 -11484,7 +11484,7 @@@ static int intel_crtc_page_flip(struct struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct drm_plane *primary = crtc->primary; enum pipe pipe = intel_crtc->pipe; - struct intel_unpin_work *work; + struct intel_flip_work *work; struct intel_engine_cs *engine; bool mmio_flip; struct drm_i915_gem_request *request = NULL; @@@ -11559,19 -11521,19 +11521,19 @@@ work->event = event; work->crtc = crtc; work->old_fb = old_fb; - INIT_WORK(&work->work, intel_unpin_work_fn); + INIT_WORK(&work->unpin_work, intel_unpin_work_fn); ret = drm_crtc_vblank_get(crtc); if (ret) goto free_work; - /* We borrow the event spin lock for protecting unpin_work */ + /* We borrow the event spin lock for protecting flip_work */ spin_lock_irq(&dev->event_lock); - if (intel_crtc->unpin_work) { + if (intel_crtc->flip_work) { /* Before declaring the flip queue wedged, check if * the hardware completed the operation behind our backs. */ - if (__intel_pageflip_stall_check(dev, crtc)) { + if (pageflip_finished(intel_crtc, intel_crtc->flip_work)) { DRM_DEBUG_DRIVER("flip queue: previous flip completed, continuing\n"); page_flip_completed(intel_crtc); } else { @@@ -11583,7 -11545,7 +11545,7 @@@ return -EBUSY; } } - intel_crtc->unpin_work = work; + intel_crtc->flip_work = work; spin_unlock_irq(&dev->event_lock); if (atomic_read(&intel_crtc->unpin_work_count) >= 2) @@@ -11638,6 -11600,11 +11600,11 @@@ */ if (!mmio_flip) { ret = i915_gem_object_sync(obj, engine, &request); + if (!ret && !request) { + request = i915_gem_request_alloc(engine, NULL); + ret = PTR_ERR_OR_ZERO(request); + } + if (ret) goto cleanup_pending; } @@@ -11649,38 -11616,28 +11616,28 @@@ work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary), obj, 0); work->gtt_offset += intel_crtc->dspaddr_offset; + work->rotation = crtc->primary->state->rotation; if (mmio_flip) { - ret = intel_queue_mmio_flip(dev, crtc, obj); - if (ret) - goto cleanup_unpin; + INIT_WORK(&work->mmio_work, intel_mmio_flip_work_func); i915_gem_request_assign(&work->flip_queued_req, obj->last_write_req); - } else { - if (!request) { - request = i915_gem_request_alloc(engine, NULL); - if (IS_ERR(request)) { - ret = PTR_ERR(request); - goto cleanup_unpin; - } - } + schedule_work(&work->mmio_work); + } else { + i915_gem_request_assign(&work->flip_queued_req, request); ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request, page_flip_flags); if (ret) goto cleanup_unpin; - i915_gem_request_assign(&work->flip_queued_req, request); - } + intel_mark_page_flip_active(intel_crtc, work); - if (request) i915_add_request_no_flush(request); + } - work->flip_queued_vblank = drm_crtc_vblank_count(crtc); - work->enable_stall_check = true; - - i915_gem_track_fb(intel_fb_obj(work->old_fb), obj, + i915_gem_track_fb(intel_fb_obj(old_fb), obj, to_intel_plane(primary)->frontbuffer_bit); mutex_unlock(&dev->struct_mutex); @@@ -11706,7 -11663,7 +11663,7 @@@ cleanup drm_framebuffer_unreference(work->old_fb); spin_lock_irq(&dev->event_lock); - intel_crtc->unpin_work = NULL; + intel_crtc->flip_work = NULL; spin_unlock_irq(&dev->event_lock); drm_crtc_vblank_put(crtc); @@@ -11834,6 -11791,11 +11791,11 @@@ int intel_plane_atomic_calc_changes(str * Visibility is calculated as if the crtc was on, but * after scaler setup everything depends on it being off * when the crtc isn't active. + * + * FIXME this is wrong for watermarks. Watermarks should also + * be computed as if the pipe would be active. Perhaps move + * per-plane wm computation to the .check_plane() hook, and + * only combine the results from all planes in the current place? */ if (!is_crtc_enabled) to_intel_plane_state(plane_state)->visible = visible = false; @@@ -12007,7 -11969,7 +11969,7 @@@ static int intel_crtc_atomic_check(stru } } else if (dev_priv->display.compute_intermediate_wm) { if (HAS_PCH_SPLIT(dev_priv) && INTEL_GEN(dev_priv) < 9) - pipe_config->wm.intermediate = pipe_config->wm.optimal.ilk; + pipe_config->wm.ilk.intermediate = pipe_config->wm.ilk.optimal; } if (INTEL_INFO(dev)->gen >= 9) { @@@ -12926,7 -12888,7 +12888,7 @@@ verify_crtc_state(struct drm_crtc *crtc bool active; old_state = old_crtc_state->state; - __drm_atomic_helper_crtc_destroy_state(crtc, old_crtc_state); + __drm_atomic_helper_crtc_destroy_state(old_crtc_state); pipe_config = to_intel_crtc_state(old_crtc_state); memset(pipe_config, 0, sizeof(*pipe_config)); pipe_config->base.crtc = crtc; @@@ -13280,6 -13242,9 +13242,9 @@@ static int intel_modeset_checks(struct intel_state->active_crtcs |= 1 << i; else intel_state->active_crtcs &= ~(1 << i); + + if (crtc_state->active != crtc->state->active) + intel_state->active_pipe_changes |= drm_crtc_mask(crtc); } /* @@@ -13316,38 -13281,16 +13281,16 @@@ * phase. The code here should be run after the per-crtc and per-plane 'check' * handlers to ensure that all derived state has been updated. */ - static void calc_watermark_data(struct drm_atomic_state *state) + static int calc_watermark_data(struct drm_atomic_state *state) { struct drm_device *dev = state->dev; - struct intel_atomic_state *intel_state = to_intel_atomic_state(state); - struct drm_crtc *crtc; - struct drm_crtc_state *cstate; - struct drm_plane *plane; - struct drm_plane_state *pstate; - - /* - * Calculate watermark configuration details now that derived - * plane/crtc state is all properly updated. - */ - drm_for_each_crtc(crtc, dev) { - cstate = drm_atomic_get_existing_crtc_state(state, crtc) ?: - crtc->state; - - if (cstate->active) - intel_state->wm_config.num_pipes_active++; - } - drm_for_each_legacy_plane(plane, dev) { - pstate = drm_atomic_get_existing_plane_state(state, plane) ?: - plane->state; + struct drm_i915_private *dev_priv = to_i915(dev); - if (!to_intel_plane_state(pstate)->visible) - continue; + /* Is there platform-specific watermark information to calculate? */ + if (dev_priv->display.compute_global_watermarks) + return dev_priv->display.compute_global_watermarks(state); - intel_state->wm_config.sprites_enabled = true; - if (pstate->crtc_w != pstate->src_w >> 16 || - pstate->crtc_h != pstate->src_h >> 16) - intel_state->wm_config.sprites_scaled = true; - } + return 0; } /** @@@ -13377,14 -13320,13 +13320,13 @@@ static int intel_atomic_check(struct dr if (crtc_state->mode.private_flags != crtc->state->mode.private_flags) crtc_state->mode_changed = true; - if (!crtc_state->enable) { - if (needs_modeset(crtc_state)) - any_ms = true; + if (!needs_modeset(crtc_state)) continue; - } - if (!needs_modeset(crtc_state)) + if (!crtc_state->enable) { + any_ms = true; continue; + } /* FIXME: For only active_changed we shouldn't need to do any * state recomputation at all. */ @@@ -13394,8 -13336,11 +13336,11 @@@ return ret; ret = intel_modeset_pipe_config(crtc, pipe_config); - if (ret) + if (ret) { + intel_dump_pipe_config(to_intel_crtc(crtc), + pipe_config, "[failed]"); return ret; + } if (i915.fastboot && intel_pipe_config_compare(dev, @@@ -13405,13 -13350,12 +13350,12 @@@ to_intel_crtc_state(crtc_state)->update_pipe = true; } - if (needs_modeset(crtc_state)) { + if (needs_modeset(crtc_state)) any_ms = true; - ret = drm_atomic_add_affected_planes(state, crtc); - if (ret) - return ret; - } + ret = drm_atomic_add_affected_planes(state, crtc); + if (ret) + return ret; intel_dump_pipe_config(to_intel_crtc(crtc), pipe_config, needs_modeset(crtc_state) ? @@@ -13431,9 -13375,7 +13375,7 @@@ return ret; intel_fbc_choose_crtc(dev_priv, state); - calc_watermark_data(state); - - return 0; + return calc_watermark_data(state); } static int intel_atomic_prepare_commit(struct drm_device *dev, @@@ -13495,6 -13437,16 +13437,16 @@@ return ret; } + u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc) + { + struct drm_device *dev = crtc->base.dev; + + if (!dev->max_vblank_count) + return drm_accurate_vblank_count(&crtc->base); + + return dev->driver->get_vblank_counter(dev, crtc->pipe); + } + static void intel_atomic_wait_for_vblanks(struct drm_device *dev, struct drm_i915_private *dev_priv, unsigned crtc_mask) @@@ -13597,7 -13549,8 +13549,8 @@@ static int intel_atomic_commit(struct d } drm_atomic_helper_swap_state(dev, state); - dev_priv->wm.config = intel_state->wm_config; + dev_priv->wm.distrust_bios_wm = false; + dev_priv->wm.skl_results = intel_state->wm_results; intel_shared_dpll_commit(state); if (intel_state->modeset) { @@@ -14006,7 -13959,7 +13959,7 @@@ static void intel_finish_crtc_commit(st { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - intel_pipe_update_end(intel_crtc); + intel_pipe_update_end(intel_crtc, NULL); } /** @@@ -14885,7 -14838,8 +14838,7 @@@ intel_user_framebuffer_create(struct dr struct drm_i915_gem_object *obj; struct drm_mode_fb_cmd2 mode_cmd = *user_mode_cmd; - obj = to_intel_bo(drm_gem_object_lookup(dev, filp, - mode_cmd.handles[0])); + obj = to_intel_bo(drm_gem_object_lookup(filp, mode_cmd.handles[0])); if (&obj->base == NULL) return ERR_PTR(-ENOENT); @@@ -15050,12 -15004,13 +15003,13 @@@ void intel_init_display_hooks(struct dr dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train; } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { dev_priv->display.fdi_link_train = hsw_fdi_link_train; - if (IS_BROADWELL(dev_priv)) { - dev_priv->display.modeset_commit_cdclk = - broadwell_modeset_commit_cdclk; - dev_priv->display.modeset_calc_cdclk = - broadwell_modeset_calc_cdclk; - } + } + + if (IS_BROADWELL(dev_priv)) { + dev_priv->display.modeset_commit_cdclk = + broadwell_modeset_commit_cdclk; + dev_priv->display.modeset_calc_cdclk = + broadwell_modeset_calc_cdclk; } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { dev_priv->display.modeset_commit_cdclk = valleyview_modeset_commit_cdclk; @@@ -15293,7 -15248,7 +15247,7 @@@ void intel_modeset_init_hw(struct drm_d dev_priv->atomic_cdclk_freq = dev_priv->cdclk_freq; intel_init_clock_gating(dev); - intel_enable_gt_powersave(dev); + intel_enable_gt_powersave(dev_priv); } /* @@@ -15363,7 -15318,6 +15317,6 @@@ retry } /* Write calculated watermark values back */ - to_i915(dev)->wm.config = to_intel_atomic_state(state)->wm_config; for_each_crtc_in_state(state, crtc, cstate, i) { struct intel_crtc_state *cs = to_intel_crtc_state(cstate); @@@ -15461,7 -15415,6 +15414,6 @@@ void intel_modeset_init(struct drm_devi } intel_update_czclk(dev_priv); - intel_update_rawclk(dev_priv); intel_update_cdclk(dev); intel_shared_dpll_init(dev); @@@ -15762,7 -15715,7 +15714,7 @@@ static void intel_modeset_readout_hw_st struct intel_crtc_state *crtc_state = crtc->config; int pixclk = 0; - __drm_atomic_helper_crtc_destroy_state(&crtc->base, &crtc_state->base); + __drm_atomic_helper_crtc_destroy_state(&crtc_state->base); memset(crtc_state, 0, sizeof(*crtc_state)); crtc_state->base.crtc = &crtc->base; @@@ -16025,15 -15978,16 +15977,16 @@@ retry void intel_modeset_gem_init(struct drm_device *dev) { + struct drm_i915_private *dev_priv = to_i915(dev); struct drm_crtc *c; struct drm_i915_gem_object *obj; int ret; - intel_init_gt_powersave(dev); + intel_init_gt_powersave(dev_priv); intel_modeset_init_hw(dev); - intel_setup_overlay(dev); + intel_setup_overlay(dev_priv); /* * Make sure any fbs we allocated at startup are properly @@@ -16076,7 -16030,7 +16029,7 @@@ void intel_modeset_cleanup(struct drm_d struct drm_i915_private *dev_priv = dev->dev_private; struct intel_connector *connector; - intel_disable_gt_powersave(dev); + intel_disable_gt_powersave(dev_priv); intel_backlight_unregister(dev); @@@ -16106,9 -16060,9 +16059,9 @@@ drm_mode_config_cleanup(dev); - intel_cleanup_overlay(dev); + intel_cleanup_overlay(dev_priv); - intel_cleanup_gt_powersave(dev); + intel_cleanup_gt_powersave(dev_priv); intel_teardown_gmbus(dev); } @@@ -16204,9 -16158,8 +16157,8 @@@ struct intel_display_error_state }; struct intel_display_error_state * - intel_display_capture_error_state(struct drm_device *dev) + intel_display_capture_error_state(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_display_error_state *error; int transcoders[] = { TRANSCODER_A, @@@ -16216,14 -16169,14 +16168,14 @@@ }; int i; - if (INTEL_INFO(dev)->num_pipes == 0) + if (INTEL_INFO(dev_priv)->num_pipes == 0) return NULL; error = kzalloc(sizeof(*error), GFP_ATOMIC); if (error == NULL) return NULL; - if (IS_HASWELL(dev) || IS_BROADWELL(dev)) + if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) error->power_well_driver = I915_READ(HSW_PWR_WELL_DRIVER); for_each_pipe(dev_priv, i) { @@@ -16239,25 -16192,25 +16191,25 @@@ error->plane[i].control = I915_READ(DSPCNTR(i)); error->plane[i].stride = I915_READ(DSPSTRIDE(i)); - if (INTEL_INFO(dev)->gen <= 3) { + if (INTEL_GEN(dev_priv) <= 3) { error->plane[i].size = I915_READ(DSPSIZE(i)); error->plane[i].pos = I915_READ(DSPPOS(i)); } - if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) + if (INTEL_GEN(dev_priv) <= 7 && !IS_HASWELL(dev_priv)) error->plane[i].addr = I915_READ(DSPADDR(i)); - if (INTEL_INFO(dev)->gen >= 4) { + if (INTEL_GEN(dev_priv) >= 4) { error->plane[i].surface = I915_READ(DSPSURF(i)); error->plane[i].tile_offset = I915_READ(DSPTILEOFF(i)); } error->pipe[i].source = I915_READ(PIPESRC(i)); - if (HAS_GMCH_DISPLAY(dev)) + if (HAS_GMCH_DISPLAY(dev_priv)) error->pipe[i].stat = I915_READ(PIPESTAT(i)); } /* Note: this does not include DSI transcoders. */ - error->num_transcoders = INTEL_INFO(dev)->num_pipes; + error->num_transcoders = INTEL_INFO(dev_priv)->num_pipes; if (HAS_DDI(dev_priv)) error->num_transcoders++; /* Account for eDP. */ diff --combined drivers/gpu/drm/i915/intel_fbdev.c index ab8d09a81f14,5a101a28063b..99e27530e264 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@@ -150,10 -150,10 +150,10 @@@ static int intelfb_alloc(struct drm_fb_ if (size * 2 < ggtt->stolen_usable_size) obj = i915_gem_object_create_stolen(dev, size); if (obj == NULL) - obj = i915_gem_alloc_object(dev, size); - if (!obj) { + obj = i915_gem_object_create(dev, size); + if (IS_ERR(obj)) { DRM_ERROR("failed to allocate framebuffer\n"); - ret = -ENOMEM; + ret = PTR_ERR(obj); goto out; } @@@ -186,9 -186,11 +186,11 @@@ static int intelfb_create(struct drm_fb struct i915_ggtt *ggtt = &dev_priv->ggtt; struct fb_info *info; struct drm_framebuffer *fb; + struct i915_vma *vma; struct drm_i915_gem_object *obj; - int size, ret; bool prealloc = false; + void *vaddr; + int ret; if (intel_fb && (sizes->fb_width > intel_fb->base.width || @@@ -214,7 -216,6 +216,6 @@@ } obj = intel_fb->obj; - size = obj->base.size; mutex_lock(&dev->struct_mutex); @@@ -244,22 -245,23 +245,23 @@@ info->flags = FBINFO_DEFAULT | FBINFO_CAN_FORCE_OUTPUT; info->fbops = &intelfb_ops; + vma = i915_gem_obj_to_ggtt(obj); + /* setup aperture base/size for vesafb takeover */ info->apertures->ranges[0].base = dev->mode_config.fb_base; info->apertures->ranges[0].size = ggtt->mappable_end; - info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_ggtt_offset(obj); - info->fix.smem_len = size; + info->fix.smem_start = dev->mode_config.fb_base + vma->node.start; + info->fix.smem_len = vma->node.size; - info->screen_base = - ioremap_wc(ggtt->mappable_base + i915_gem_obj_ggtt_offset(obj), - size); - if (!info->screen_base) { + vaddr = i915_vma_pin_iomap(vma); + if (IS_ERR(vaddr)) { DRM_ERROR("Failed to remap framebuffer into virtual memory\n"); - ret = -ENOSPC; + ret = PTR_ERR(vaddr); goto out_destroy_fbi; } - info->screen_size = size; + info->screen_base = vaddr; + info->screen_size = vma->node.size; /* This driver doesn't need a VT switch to restore the mode on resume */ info->skip_vt_switch = true; @@@ -287,7 -289,7 +289,7 @@@ out_destroy_fbi: drm_fb_helper_release_fbi(helper); out_unpin: - i915_gem_object_ggtt_unpin(obj); + intel_unpin_fb_obj(&ifbdev->fb->base, BIT(DRM_ROTATE_0)); out_unlock: mutex_unlock(&dev->struct_mutex); return ret; @@@ -368,12 -370,12 +370,12 @@@ static bool intel_fb_initial_config(str uint64_t conn_configured = 0, mask; int pass = 0; - save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool), + save_enabled = kcalloc(fb_helper->connector_count, sizeof(bool), GFP_KERNEL); if (!save_enabled) return false; - memcpy(save_enabled, enabled, dev->mode_config.num_connector); + memcpy(save_enabled, enabled, fb_helper->connector_count); mask = (1 << fb_helper->connector_count) - 1; retry: for (i = 0; i < fb_helper->connector_count; i++) { @@@ -520,7 -522,7 +522,7 @@@ if (fallback) { bail: DRM_DEBUG_KMS("Not using firmware configuration\n"); - memcpy(enabled, save_enabled, dev->mode_config.num_connector); + memcpy(enabled, save_enabled, fb_helper->connector_count); kfree(save_enabled); return false; } @@@ -551,6 -553,11 +553,11 @@@ static void intel_fbdev_destroy(struct if (ifbdev->fb) { drm_framebuffer_unregister_private(&ifbdev->fb->base); + + mutex_lock(&dev->struct_mutex); + intel_unpin_fb_obj(&ifbdev->fb->base, BIT(DRM_ROTATE_0)); + mutex_unlock(&dev->struct_mutex); + drm_framebuffer_remove(&ifbdev->fb->base); } } diff --combined drivers/gpu/drm/i915/intel_overlay.c index bd38e49f7334,b9b042cc619f..eb93f90bb74d --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@@ -168,7 -168,7 +168,7 @@@ struct overlay_registers }; struct intel_overlay { - struct drm_device *dev; + struct drm_i915_private *i915; struct intel_crtc *crtc; struct drm_i915_gem_object *vid_bo; struct drm_i915_gem_object *old_vid_bo; @@@ -190,15 -190,15 +190,15 @@@ static struct overlay_registers __iomem * intel_overlay_map_regs(struct intel_overlay *overlay) { - struct drm_i915_private *dev_priv = to_i915(overlay->dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; + struct drm_i915_private *dev_priv = overlay->i915; struct overlay_registers __iomem *regs; - if (OVERLAY_NEEDS_PHYSICAL(overlay->dev)) + if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_handle->vaddr; else - regs = io_mapping_map_wc(ggtt->mappable, - i915_gem_obj_ggtt_offset(overlay->reg_bo)); + regs = io_mapping_map_wc(dev_priv->ggtt.mappable, + overlay->flip_addr, + PAGE_SIZE); return regs; } @@@ -206,7 -206,7 +206,7 @@@ static void intel_overlay_unmap_regs(struct intel_overlay *overlay, struct overlay_registers __iomem *regs) { - if (!OVERLAY_NEEDS_PHYSICAL(overlay->dev)) + if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) io_mapping_unmap(regs); } @@@ -232,14 -232,13 +232,13 @@@ static int intel_overlay_do_wait_reques /* overlay needs to be disable in OCMD reg */ static int intel_overlay_on(struct intel_overlay *overlay) { - struct drm_device *dev = overlay->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = overlay->i915; struct intel_engine_cs *engine = &dev_priv->engine[RCS]; struct drm_i915_gem_request *req; int ret; WARN_ON(overlay->active); - WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE)); + WARN_ON(IS_I830(dev_priv) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE)); req = i915_gem_request_alloc(engine, NULL); if (IS_ERR(req)) @@@ -266,8 -265,7 +265,7 @@@ static int intel_overlay_continue(struct intel_overlay *overlay, bool load_polyphase_filter) { - struct drm_device *dev = overlay->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = overlay->i915; struct intel_engine_cs *engine = &dev_priv->engine[RCS]; struct drm_i915_gem_request *req; u32 flip_addr = overlay->flip_addr; @@@ -335,8 -333,7 +333,7 @@@ static void intel_overlay_off_tail(stru /* overlay needs to be disabled in OCMD reg */ static int intel_overlay_off(struct intel_overlay *overlay) { - struct drm_device *dev = overlay->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = overlay->i915; struct intel_engine_cs *engine = &dev_priv->engine[RCS]; struct drm_i915_gem_request *req; u32 flip_addr = overlay->flip_addr; @@@ -365,7 -362,7 +362,7 @@@ intel_ring_emit(engine, flip_addr); intel_ring_emit(engine, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP); /* turn overlay off */ - if (IS_I830(dev)) { + if (IS_I830(dev_priv)) { /* Workaround: Don't disable the overlay fully, since otherwise * it dies on the next OVERLAY_ON cmd. */ intel_ring_emit(engine, MI_NOOP); @@@ -408,12 -405,11 +405,11 @@@ static int intel_overlay_recover_from_i */ static int intel_overlay_release_old_vid(struct intel_overlay *overlay) { - struct drm_device *dev = overlay->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = overlay->i915; struct intel_engine_cs *engine = &dev_priv->engine[RCS]; int ret; - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); + lockdep_assert_held(&dev_priv->dev->struct_mutex); /* Only wait if there is actually an old frame to release to * guarantee forward progress. @@@ -537,10 -533,10 +533,10 @@@ static int uv_vsubsampling(u32 format } } - static u32 calc_swidthsw(struct drm_device *dev, u32 offset, u32 width) + static u32 calc_swidthsw(struct drm_i915_private *dev_priv, u32 offset, u32 width) { u32 mask, shift, ret; - if (IS_GEN2(dev)) { + if (IS_GEN2(dev_priv)) { mask = 0x1f; shift = 5; } else { @@@ -548,7 -544,7 +544,7 @@@ shift = 6; } ret = ((offset + width + mask) >> shift) - (offset >> shift); - if (!IS_GEN2(dev)) + if (!IS_GEN2(dev_priv)) ret <<= 1; ret -= 1; return ret << 2; @@@ -741,12 -737,12 +737,12 @@@ static int intel_overlay_do_put_image(s int ret, tmp_width; struct overlay_registers __iomem *regs; bool scale_changed = false; - struct drm_device *dev = overlay->dev; + struct drm_i915_private *dev_priv = overlay->i915; u32 swidth, swidthsw, sheight, ostride; enum pipe pipe = overlay->crtc->pipe; - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); + lockdep_assert_held(&dev_priv->dev->struct_mutex); + WARN_ON(!drm_modeset_is_locked(&dev_priv->dev->mode_config.connection_mutex)); ret = intel_overlay_release_old_vid(overlay); if (ret != 0) @@@ -769,7 -765,7 +765,7 @@@ goto out_unpin; } oconfig = OCONF_CC_OUT_8BIT; - if (IS_GEN4(overlay->dev)) + if (IS_GEN4(dev_priv)) oconfig |= OCONF_CSC_MODE_BT709; oconfig |= pipe == 0 ? OCONF_PIPE_A : OCONF_PIPE_B; @@@ -796,7 -792,7 +792,7 @@@ tmp_width = params->src_w; swidth = params->src_w; - swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width); + swidthsw = calc_swidthsw(dev_priv, params->offset_Y, tmp_width); sheight = params->src_h; iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, ®s->OBUF_0Y); ostride = params->stride_Y; @@@ -806,9 -802,9 +802,9 @@@ int uv_vscale = uv_vsubsampling(params->format); u32 tmp_U, tmp_V; swidth |= (params->src_w/uv_hscale) << 16; - tmp_U = calc_swidthsw(overlay->dev, params->offset_U, + tmp_U = calc_swidthsw(dev_priv, params->offset_U, params->src_w/uv_hscale); - tmp_V = calc_swidthsw(overlay->dev, params->offset_V, + tmp_V = calc_swidthsw(dev_priv, params->offset_V, params->src_w/uv_hscale); swidthsw |= max_t(u32, tmp_U, tmp_V) << 16; sheight |= (params->src_h/uv_vscale) << 16; @@@ -840,8 -836,7 +836,7 @@@ overlay->old_vid_bo = overlay->vid_bo; overlay->vid_bo = new_bo; - intel_frontbuffer_flip(dev, - INTEL_FRONTBUFFER_OVERLAY(pipe)); + intel_frontbuffer_flip(dev_priv->dev, INTEL_FRONTBUFFER_OVERLAY(pipe)); return 0; @@@ -852,12 -847,12 +847,12 @@@ out_unpin int intel_overlay_switch_off(struct intel_overlay *overlay) { + struct drm_i915_private *dev_priv = overlay->i915; struct overlay_registers __iomem *regs; - struct drm_device *dev = overlay->dev; int ret; - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); + lockdep_assert_held(&dev_priv->dev->struct_mutex); + WARN_ON(!drm_modeset_is_locked(&dev_priv->dev->mode_config.connection_mutex)); ret = intel_overlay_recover_from_interrupt(overlay); if (ret != 0) @@@ -897,15 -892,14 +892,14 @@@ static int check_overlay_possible_on_cr static void update_pfit_vscale_ratio(struct intel_overlay *overlay) { - struct drm_device *dev = overlay->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = overlay->i915; u32 pfit_control = I915_READ(PFIT_CONTROL); u32 ratio; /* XXX: This is not the same logic as in the xorg driver, but more in * line with the intel documentation for the i965 */ - if (INTEL_INFO(dev)->gen >= 4) { + if (INTEL_GEN(dev_priv) >= 4) { /* on i965 use the PGM reg to read out the autoscaler values */ ratio = I915_READ(PFIT_PGM_RATIOS) >> PFIT_VERT_SCALE_SHIFT_965; } else { @@@ -948,7 -942,7 +942,7 @@@ static int check_overlay_scaling(struc return 0; } - static int check_overlay_src(struct drm_device *dev, + static int check_overlay_src(struct drm_i915_private *dev_priv, struct drm_intel_overlay_put_image *rec, struct drm_i915_gem_object *new_bo) { @@@ -959,7 -953,7 +953,7 @@@ u32 tmp; /* check src dimensions */ - if (IS_845G(dev) || IS_I830(dev)) { + if (IS_845G(dev_priv) || IS_I830(dev_priv)) { if (rec->src_height > IMAGE_MAX_HEIGHT_LEGACY || rec->src_width > IMAGE_MAX_WIDTH_LEGACY) return -EINVAL; @@@ -1011,14 -1005,14 +1005,14 @@@ return -EINVAL; /* stride checking */ - if (IS_I830(dev) || IS_845G(dev)) + if (IS_I830(dev_priv) || IS_845G(dev_priv)) stride_mask = 255; else stride_mask = 63; if (rec->stride_Y & stride_mask || rec->stride_UV & stride_mask) return -EINVAL; - if (IS_GEN4(dev) && rec->stride_Y < 512) + if (IS_GEN4(dev_priv) && rec->stride_Y < 512) return -EINVAL; tmp = (rec->flags & I915_OVERLAY_TYPE_MASK) == I915_OVERLAY_YUV_PLANAR ? @@@ -1063,13 -1057,13 +1057,13 @@@ * Return the pipe currently connected to the panel fitter, * or -1 if the panel fitter is not present or not in use */ - static int intel_panel_fitter_pipe(struct drm_device *dev) + static int intel_panel_fitter_pipe(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; u32 pfit_control; /* i830 doesn't have a panel fitter */ - if (INTEL_INFO(dev)->gen <= 3 && (IS_I830(dev) || !IS_MOBILE(dev))) + if (INTEL_GEN(dev_priv) <= 3 && + (IS_I830(dev_priv) || !IS_MOBILE(dev_priv))) return -1; pfit_control = I915_READ(PFIT_CONTROL); @@@ -1079,15 -1073,15 +1073,15 @@@ return -1; /* 965 can place panel fitter on either pipe */ - if (IS_GEN4(dev)) + if (IS_GEN4(dev_priv)) return (pfit_control >> 29) & 0x3; /* older chips can only use pipe 1 */ return 1; } - int intel_overlay_put_image(struct drm_device *dev, void *data, - struct drm_file *file_priv) + int intel_overlay_put_image_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) { struct drm_intel_overlay_put_image *put_image_rec = data; struct drm_i915_private *dev_priv = dev->dev_private; @@@ -1127,7 -1121,7 +1121,7 @@@ } crtc = to_intel_crtc(drmmode_crtc); - new_bo = to_intel_bo(drm_gem_object_lookup(dev, file_priv, + new_bo = to_intel_bo(drm_gem_object_lookup(file_priv, put_image_rec->bo_handle)); if (&new_bo->base == NULL) { ret = -ENOENT; @@@ -1162,7 -1156,7 +1156,7 @@@ /* line too wide, i.e. one-line-mode */ if (mode->hdisplay > 1024 && - intel_panel_fitter_pipe(dev) == crtc->pipe) { + intel_panel_fitter_pipe(dev_priv) == crtc->pipe) { overlay->pfit_active = true; update_pfit_vscale_ratio(overlay); } else @@@ -1196,7 -1190,7 +1190,7 @@@ goto out_unlock; } - ret = check_overlay_src(dev, put_image_rec, new_bo); + ret = check_overlay_src(dev_priv, put_image_rec, new_bo); if (ret != 0) goto out_unlock; params->format = put_image_rec->flags & ~I915_OVERLAY_FLAGS_MASK; @@@ -1284,8 -1278,8 +1278,8 @@@ static int check_gamma(struct drm_intel return 0; } - int intel_overlay_attrs(struct drm_device *dev, void *data, - struct drm_file *file_priv) + int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) { struct drm_intel_overlay_attrs *attrs = data; struct drm_i915_private *dev_priv = dev->dev_private; @@@ -1309,7 -1303,7 +1303,7 @@@ attrs->contrast = overlay->contrast; attrs->saturation = overlay->saturation; - if (!IS_GEN2(dev)) { + if (!IS_GEN2(dev_priv)) { attrs->gamma0 = I915_READ(OGAMC0); attrs->gamma1 = I915_READ(OGAMC1); attrs->gamma2 = I915_READ(OGAMC2); @@@ -1341,7 -1335,7 +1335,7 @@@ intel_overlay_unmap_regs(overlay, regs); if (attrs->flags & I915_OVERLAY_UPDATE_GAMMA) { - if (IS_GEN2(dev)) + if (IS_GEN2(dev_priv)) goto out_unlock; if (overlay->active) { @@@ -1371,37 -1365,36 +1365,36 @@@ out_unlock return ret; } - void intel_setup_overlay(struct drm_device *dev) + void intel_setup_overlay(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_overlay *overlay; struct drm_i915_gem_object *reg_bo; struct overlay_registers __iomem *regs; int ret; - if (!HAS_OVERLAY(dev)) + if (!HAS_OVERLAY(dev_priv)) return; overlay = kzalloc(sizeof(*overlay), GFP_KERNEL); if (!overlay) return; - mutex_lock(&dev->struct_mutex); + mutex_lock(&dev_priv->dev->struct_mutex); if (WARN_ON(dev_priv->overlay)) goto out_free; - overlay->dev = dev; + overlay->i915 = dev_priv; reg_bo = NULL; - if (!OVERLAY_NEEDS_PHYSICAL(dev)) - reg_bo = i915_gem_object_create_stolen(dev, PAGE_SIZE); - if (reg_bo == NULL) - reg_bo = i915_gem_alloc_object(dev, PAGE_SIZE); + if (!OVERLAY_NEEDS_PHYSICAL(dev_priv)) + reg_bo = i915_gem_object_create_stolen(dev_priv->dev, PAGE_SIZE); if (reg_bo == NULL) + reg_bo = i915_gem_object_create(dev_priv->dev, PAGE_SIZE); + if (IS_ERR(reg_bo)) goto out_free; overlay->reg_bo = reg_bo; - if (OVERLAY_NEEDS_PHYSICAL(dev)) { + if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) { ret = i915_gem_object_attach_phys(reg_bo, PAGE_SIZE); if (ret) { DRM_ERROR("failed to attach phys overlay regs\n"); @@@ -1441,25 -1434,23 +1434,23 @@@ intel_overlay_unmap_regs(overlay, regs); dev_priv->overlay = overlay; - mutex_unlock(&dev->struct_mutex); + mutex_unlock(&dev_priv->dev->struct_mutex); DRM_INFO("initialized overlay support\n"); return; out_unpin_bo: - if (!OVERLAY_NEEDS_PHYSICAL(dev)) + if (!OVERLAY_NEEDS_PHYSICAL(dev_priv)) i915_gem_object_ggtt_unpin(reg_bo); out_free_bo: drm_gem_object_unreference(®_bo->base); out_free: - mutex_unlock(&dev->struct_mutex); + mutex_unlock(&dev_priv->dev->struct_mutex); kfree(overlay); return; } - void intel_cleanup_overlay(struct drm_device *dev) + void intel_cleanup_overlay(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; - if (!dev_priv->overlay) return; @@@ -1482,18 -1473,17 +1473,17 @@@ struct intel_overlay_error_state static struct overlay_registers __iomem * intel_overlay_map_regs_atomic(struct intel_overlay *overlay) { - struct drm_i915_private *dev_priv = to_i915(overlay->dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; + struct drm_i915_private *dev_priv = overlay->i915; struct overlay_registers __iomem *regs; - if (OVERLAY_NEEDS_PHYSICAL(overlay->dev)) + if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) /* Cast to make sparse happy, but it's wc memory anyway, so * equivalent to the wc io mapping on X86. */ regs = (struct overlay_registers __iomem *) overlay->reg_bo->phys_handle->vaddr; else - regs = io_mapping_map_atomic_wc(ggtt->mappable, - i915_gem_obj_ggtt_offset(overlay->reg_bo)); + regs = io_mapping_map_atomic_wc(dev_priv->ggtt.mappable, + overlay->flip_addr); return regs; } @@@ -1501,15 -1491,13 +1491,13 @@@ static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay, struct overlay_registers __iomem *regs) { - if (!OVERLAY_NEEDS_PHYSICAL(overlay->dev)) + if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) io_mapping_unmap_atomic(regs); } - struct intel_overlay_error_state * - intel_overlay_capture_error_state(struct drm_device *dev) + intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_overlay *overlay = dev_priv->overlay; struct intel_overlay_error_state *error; struct overlay_registers __iomem *regs; @@@ -1523,10 -1511,7 +1511,7 @@@ error->dovsta = I915_READ(DOVSTA); error->isr = I915_READ(ISR); - if (OVERLAY_NEEDS_PHYSICAL(overlay->dev)) - error->base = (__force long)overlay->reg_bo->phys_handle->vaddr; - else - error->base = i915_gem_obj_ggtt_offset(overlay->reg_bo); + error->base = overlay->flip_addr; regs = intel_overlay_map_regs_atomic(overlay); if (!regs) diff --combined drivers/gpu/drm/i915/intel_panel.c index 8357d571553a,efaee7a7f933..f0b1602c3258 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@@ -1638,12 -1638,6 +1638,12 @@@ static int pwm_setup_backlight(struct i return -ENODEV; } + /* + * FIXME: pwm_apply_args() should be removed when switching to + * the atomic PWM API. + */ + pwm_apply_args(panel->backlight.pwm); + retval = pwm_config(panel->backlight.pwm, CRC_PMIC_PWM_PERIOD_NS, CRC_PMIC_PWM_PERIOD_NS); if (retval < 0) { @@@ -1724,6 -1718,14 +1724,14 @@@ intel_panel_init_backlight_funcs(struc container_of(panel, struct intel_connector, panel); struct drm_i915_private *dev_priv = to_i915(connector->base.dev); + if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP && + intel_dp_aux_init_backlight_funcs(connector) == 0) + return; + + if (connector->base.connector_type == DRM_MODE_CONNECTOR_DSI && + intel_dsi_dcs_init_backlight_funcs(connector) == 0) + return; + if (IS_BROXTON(dev_priv)) { panel->backlight.setup = bxt_setup_backlight; panel->backlight.enable = bxt_enable_backlight; diff --combined include/drm/drmP.h index af8b71b2e5bd,ed890384b938..c5d29505f937 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@@ -52,7 -52,6 +52,7 @@@ #include #include #include +#include #include #include #include @@@ -393,6 -392,11 +393,6 @@@ struct drm_master void *driver_priv; }; -/* Size of ringbuffer for vblank timestamps. Just double-buffer - * in initial implementation. - */ -#define DRM_VBLANKTIME_RBSIZE 2 - /* Flags and return codes for get_vblank_timestamp() driver function. */ #define DRM_CALLED_FROM_VBLIRQ 1 #define DRM_VBLANKTIME_SCANOUTPOS_METHOD (1 << 0) @@@ -721,10 -725,10 +721,10 @@@ struct drm_vblank_crtc wait_queue_head_t queue; /**< VBLANK wait queue */ struct timer_list disable_timer; /* delayed disable timer */ - /* vblank counter, protected by dev->vblank_time_lock for writes */ - u32 count; - /* vblank timestamps, protected by dev->vblank_time_lock for writes */ - struct timeval time[DRM_VBLANKTIME_RBSIZE]; + seqlock_t seqlock; /* protects vblank count and time */ + + u32 count; /* vblank counter */ + struct timeval time; /* vblank timestamp */ atomic_t refcount; /* number of users of vblank interruptsper crtc */ u32 last; /* protected by dev->vbl_lock, used */ @@@ -810,6 -814,14 +810,6 @@@ struct drm_device bool irq_enabled; int irq; - /* - * At load time, disabling the vblank interrupt won't be allowed since - * old clients may not call the modeset ioctl and therefore misbehave. - * Once the modeset ioctl *has* been called though, we can safely - * disable them when unused. - */ - bool vblank_disable_allowed; - /* * If true, vblank interrupt will be disabled immediately when the * refcount drops to zero, as opposed to via the vblank disable @@@ -990,6 -1002,7 +990,7 @@@ extern void drm_crtc_vblank_off(struct extern void drm_crtc_vblank_reset(struct drm_crtc *crtc); extern void drm_crtc_vblank_on(struct drm_crtc *crtc); extern void drm_vblank_cleanup(struct drm_device *dev); + extern u32 drm_accurate_vblank_count(struct drm_crtc *crtc); extern u32 drm_vblank_no_hw_counter(struct drm_device *dev, unsigned int pipe); extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,