diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 20:42:10 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 20:42:10 -0800 |
commit | e60e1ee60630cafef5e430c2ae364877e061d980 (patch) | |
tree | 816aeef8fe8d4a2c6a1ebbc7a350839bac8dd4c2 /drivers/gpu/drm/i915/i915_gem_shrinker.c | |
parent | 5d352e69c60e54b5f04d6e337a1d2bf0dbf3d94a (diff) | |
parent | f150891fd9878ef0d9197c4e8451ce67c3bdd014 (diff) | |
download | linux-stable-e60e1ee60630cafef5e430c2ae364877e061d980.tar.gz linux-stable-e60e1ee60630cafef5e430c2ae364877e061d980.tar.bz2 linux-stable-e60e1ee60630cafef5e430c2ae364877e061d980.zip |
Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux
Pull drm updates from Dave Airlie:
"This is the main drm pull request for v4.15.
Core:
- Atomic object lifetime fixes
- Atomic iterator improvements
- Sparse/smatch fixes
- Legacy kms ioctls to be interruptible
- EDID override improvements
- fb/gem helper cleanups
- Simple outreachy patches
- Documentation improvements
- Fix dma-buf rcu races
- DRM mode object leasing for improving VR use cases.
- vgaarb improvements for non-x86 platforms.
New driver:
- tve200: Faraday Technology TVE200 block.
This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
the StorLink SL3516 (later Cortina Systems CS3516) as well as the
Grain Media GM8180.
New bridges:
- SiI9234 support
New panels:
- S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
LT089AC19000, Innolux AT043TN24
i915:
- Remove Coffeelake from alpha support
- Cannonlake workarounds
- Infoframe refactoring for DisplayPort
- VBT updates
- DisplayPort vswing/emph/buffer translation refactoring
- CCS fixes
- Restore GPU clock boost on missed vblanks
- Scatter list updates for userptr allocations
- Gen9+ transition watermarks
- Display IPC (Isochronous Priority Control)
- Private PAT management
- GVT: improved error handling and pci config sanitizing
- Execlist refactoring
- Transparent Huge Page support
- User defined priorities support
- HuC/GuC firmware refactoring
- DP MST fixes
- eDP power sequencing fixes
- Use RCU instead of stop_machine
- PSR state tracking support
- Eviction fixes
- BDW DP aux channel timeout fixes
- LSPCON fixes
- Cannonlake PLL fixes
amdgpu:
- Per VM BO support
- Powerplay cleanups
- CI powerplay support
- PASID mgr for kfd
- SR-IOV fixes
- initial GPU reset for vega10
- Prime mmap support
- TTM updates
- Clock query interface for Raven
- Fence to handle ioctl
- UVD encode ring support on Polaris
- Transparent huge page DMA support
- Compute LRU pipe tweaks
- BO flag to allow buffers to opt out of implicit sync
- CTX priority setting API
- VRAM lost infrastructure plumbing
qxl:
- fix flicker since atomic rework
amdkfd:
- Further improvements from internal AMD tree
- Usermode events
- Drop radeon support
nouveau:
- Pascal temperature sensor support
- Improved BAR2 handling
- MMU rework to support Pascal MMU
exynos:
- Improved HDMI/mixer support
- HDMI audio interface support
tegra:
- Prep work for tegra186
- Cleanup/fixes
msm:
- Preemption support for a5xx
- Display fixes for 8x96 (snapdragon 820)
- Async cursor plane fixes
- FW loading rework
- GPU debugging improvements
vc4:
- Prep for DSI panels
- fix T-format tiling scanout
- New madvise ioctl
Rockchip:
- LVDS support
omapdrm:
- omap4 HDMI CEC support
etnaviv:
- GPU performance counters groundwork
sun4i:
- refactor driver load + TCON backend
- HDMI improvements
- A31 support
- Misc fixes
udl:
- Probe/EDID read fixes.
tilcdc:
- Misc fixes.
pl111:
- Support more variants
adv7511:
- Improve EDID handling.
- HDMI CEC support
sii8620:
- Add remote control support"
* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
drm/rockchip: analogix_dp: Use mutex rather than spinlock
drm/mode_object: fix documentation for object lookups.
drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
drm/i915: Move init_clock_gating() back to where it was
drm/i915: Prune the reservation shared fence array
drm/i915: Idle the GPU before shinking everything
drm/i915: Lock llist_del_first() vs llist_del_all()
drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
drm/i915: Disable lazy PPGTT page table optimization for vGPU
drm/i915/execlists: Remove the priority "optimisation"
drm/i915: Filter out spurious execlists context-switch interrupts
drm/amdgpu: use irq-safe lock for kiq->ring_lock
drm/amdgpu: bypass lru touch for KIQ ring submission
drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
drm/amd/powerplay: initialize a variable before using it
drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
drm/rockchip: add CONFIG_OF dependency for lvds
...
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gem_shrinker.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_gem_shrinker.c | 131 |
1 files changed, 69 insertions, 62 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 74002b2d1b6f..3770e3323fc8 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -71,25 +71,6 @@ static void shrinker_unlock(struct drm_i915_private *dev_priv, bool unlock) mutex_unlock(&dev_priv->drm.struct_mutex); } -static bool any_vma_pinned(struct drm_i915_gem_object *obj) -{ - struct i915_vma *vma; - - list_for_each_entry(vma, &obj->vma_list, obj_link) { - /* Only GGTT vma may be permanently pinned, and are always - * at the start of the list. We can stop hunting as soon - * as we see a ppGTT vma. - */ - if (!i915_vma_is_ggtt(vma)) - break; - - if (i915_vma_is_pinned(vma)) - return true; - } - - return false; -} - static bool swap_available(void) { return get_nr_swap_pages() > 0; @@ -97,9 +78,6 @@ static bool swap_available(void) static bool can_release_pages(struct drm_i915_gem_object *obj) { - if (!obj->mm.pages) - return false; - /* Consider only shrinkable ojects. */ if (!i915_gem_object_is_shrinkable(obj)) return false; @@ -115,7 +93,13 @@ static bool can_release_pages(struct drm_i915_gem_object *obj) if (atomic_read(&obj->mm.pages_pin_count) > obj->bind_count) return false; - if (any_vma_pinned(obj)) + /* If any vma are "permanently" pinned, it will prevent us from + * reclaiming the obj->mm.pages. We only allow scanout objects to claim + * a permanent pin, along with a few others like the context objects. + * To simplify the scan, and to avoid walking the list of vma under the + * object, we just check the count of its permanently pinned. + */ + if (READ_ONCE(obj->pin_global)) return false; /* We can only return physical pages to the system if we can either @@ -129,7 +113,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj) { if (i915_gem_object_unbind(obj) == 0) __i915_gem_object_put_pages(obj, I915_MM_SHRINKER); - return !READ_ONCE(obj->mm.pages); + return !i915_gem_object_has_pages(obj); } /** @@ -178,6 +162,18 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, if (!shrinker_lock(dev_priv, &unlock)) return 0; + /* + * When shrinking the active list, also consider active contexts. + * Active contexts are pinned until they are retired, and so can + * not be simply unbound to retire and unpin their pages. To shrink + * the contexts, we must wait until the gpu is idle. + * + * We don't care about errors here; if we cannot wait upon the GPU, + * we will free as much as we can and hope to get a second chance. + */ + if (flags & I915_SHRINK_ACTIVE) + i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED); + trace_i915_gem_shrink(dev_priv, target, flags); i915_gem_retire_requests(dev_priv); @@ -217,15 +213,20 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, continue; INIT_LIST_HEAD(&still_in_list); + + /* + * We serialize our access to unreferenced objects through + * the use of the struct_mutex. While the objects are not + * yet freed (due to RCU then a workqueue) we still want + * to be able to shrink their pages, so they remain on + * the unbound/bound list until actually freed. + */ + spin_lock(&dev_priv->mm.obj_lock); while (count < target && (obj = list_first_entry_or_null(phase->list, typeof(*obj), - global_link))) { - list_move_tail(&obj->global_link, &still_in_list); - if (!obj->mm.pages) { - list_del_init(&obj->global_link); - continue; - } + mm.link))) { + list_move_tail(&obj->mm.link, &still_in_list); if (flags & I915_SHRINK_PURGEABLE && obj->mm.madv != I915_MADV_DONTNEED) @@ -243,20 +244,24 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, if (!can_release_pages(obj)) continue; + spin_unlock(&dev_priv->mm.obj_lock); + if (unsafe_drop_pages(obj)) { /* May arrive from get_pages on another bo */ mutex_lock_nested(&obj->mm.lock, I915_MM_SHRINKER); - if (!obj->mm.pages) { + if (!i915_gem_object_has_pages(obj)) { __i915_gem_object_invalidate(obj); - list_del_init(&obj->global_link); count += obj->base.size >> PAGE_SHIFT; } mutex_unlock(&obj->mm.lock); - scanned += obj->base.size >> PAGE_SHIFT; } + scanned += obj->base.size >> PAGE_SHIFT; + + spin_lock(&dev_priv->mm.obj_lock); } list_splice_tail(&still_in_list, phase->list); + spin_unlock(&dev_priv->mm.obj_lock); } if (flags & I915_SHRINK_BOUND) @@ -302,28 +307,39 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv) static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { - struct drm_i915_private *dev_priv = + struct drm_i915_private *i915 = container_of(shrinker, struct drm_i915_private, mm.shrinker); struct drm_i915_gem_object *obj; - unsigned long count; - bool unlock; - - if (!shrinker_lock(dev_priv, &unlock)) - return 0; - - i915_gem_retire_requests(dev_priv); + unsigned long num_objects = 0; + unsigned long count = 0; - count = 0; - list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_link) - if (can_release_pages(obj)) + spin_lock(&i915->mm.obj_lock); + list_for_each_entry(obj, &i915->mm.unbound_list, mm.link) + if (can_release_pages(obj)) { count += obj->base.size >> PAGE_SHIFT; + num_objects++; + } - list_for_each_entry(obj, &dev_priv->mm.bound_list, global_link) { - if (!i915_gem_object_is_active(obj) && can_release_pages(obj)) + list_for_each_entry(obj, &i915->mm.bound_list, mm.link) + if (!i915_gem_object_is_active(obj) && can_release_pages(obj)) { count += obj->base.size >> PAGE_SHIFT; - } + num_objects++; + } + spin_unlock(&i915->mm.obj_lock); - shrinker_unlock(dev_priv, unlock); + /* Update our preferred vmscan batch size for the next pass. + * Our rough guess for an effective batch size is roughly 2 + * available GEM objects worth of pages. That is we don't want + * the shrinker to fire, until it is worth the cost of freeing an + * entire GEM object. + */ + if (num_objects) { + unsigned long avg = 2 * count / num_objects; + + i915->mm.shrinker.batch = + max((i915->mm.shrinker.batch + avg) >> 1, + 128ul /* default SHRINK_BATCH */); + } return count; } @@ -400,10 +416,6 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) container_of(nb, struct drm_i915_private, mm.oom_notifier); struct drm_i915_gem_object *obj; unsigned long unevictable, bound, unbound, freed_pages; - bool unlock; - - if (!shrinker_lock_uninterruptible(dev_priv, &unlock, 5000)) - return NOTIFY_DONE; freed_pages = i915_gem_shrink_all(dev_priv); @@ -412,26 +424,20 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) * being pointed to by hardware. */ unbound = bound = unevictable = 0; - list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_link) { - if (!obj->mm.pages) - continue; - + spin_lock(&dev_priv->mm.obj_lock); + list_for_each_entry(obj, &dev_priv->mm.unbound_list, mm.link) { if (!can_release_pages(obj)) unevictable += obj->base.size >> PAGE_SHIFT; else unbound += obj->base.size >> PAGE_SHIFT; } - list_for_each_entry(obj, &dev_priv->mm.bound_list, global_link) { - if (!obj->mm.pages) - continue; - + list_for_each_entry(obj, &dev_priv->mm.bound_list, mm.link) { if (!can_release_pages(obj)) unevictable += obj->base.size >> PAGE_SHIFT; else bound += obj->base.size >> PAGE_SHIFT; } - - shrinker_unlock(dev_priv, unlock); + spin_unlock(&dev_priv->mm.obj_lock); if (freed_pages || unbound || bound) pr_info("Purging GPU memory, %lu pages freed, " @@ -498,6 +504,7 @@ void i915_gem_shrinker_init(struct drm_i915_private *dev_priv) dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan; dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count; dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS; + dev_priv->mm.shrinker.batch = 4096; WARN_ON(register_shrinker(&dev_priv->mm.shrinker)); dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom; |