diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-01 21:26:46 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-01 21:26:46 +0300 |
commit | 477f70cd2a67904e04c2c2b9bd0fa2e95222f2f6 (patch) | |
tree | 1897dd1de49e1ea24897163533e2d8ead5dad0ad /drivers/gpu/drm/i915/gem/i915_gem_object.c | |
parent | 835d31d319d9c8c4eb6cac074643360ba0ecab10 (diff) | |
parent | 8f0284f190e6a0aa09015090568c03f18288231a (diff) | |
download | linux-477f70cd2a67904e04c2c2b9bd0fa2e95222f2f6.tar.xz |
Merge tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie:
"Highlights:
- i915 has seen a lot of refactoring and uAPI cleanups due to a
change in the upstream direction going forward
This has all been audited with known userspace, but there may be
some pitfalls that were missed.
- i915 now uses common TTM to enable discrete memory on DG1/2 GPUs
- i915 enables Jasper and Elkhart Lake by default and has preliminary
XeHP/DG2 support
- amdgpu adds support for Cyan Skillfish
- lots of implicit fencing rules documented and fixed up in drivers
- msm now uses the core scheduler
- the irq midlayer has been removed for non-legacy drivers
- the sysfb code now works on more than x86.
Otherwise the usual smattering of stuff everywhere, panels, bridges,
refactorings.
Detailed summary:
core:
- extract i915 eDP backlight into core
- DP aux bus support
- drm_device.irq_enabled removed
- port drivers to native irq interfaces
- export gem shadow plane handling for vgem
- print proper driver name in framebuffer registration
- driver fixes for implicit fencing rules
- ARM fixed rate compression modifier added
- updated fb damage handling
- rmfb ioctl logging/docs
- drop drm_gem_object_put_locked
- define DRM_FORMAT_MAX_PLANES
- add gem fb vmap/vunmap helpers
- add lockdep_assert(once) helpers
- mark drm irq midlayer as legacy
- use offset adjusted bo mapping conversion
vgaarb:
- cleanups
fbdev:
- extend efifb handling to all arches
- div by 0 fixes for multiple drivers
udmabuf:
- add hugepage mapping support
dma-buf:
- non-dynamic exporter fixups
- document implicit fencing rules
amdgpu:
- Initial Cyan Skillfish support
- switch virtual DCE over to vkms based atomic
- VCN/JPEG power down fixes
- NAVI PCIE link handling fixes
- AMD HDMI freesync fixes
- Yellow Carp + Beige Goby fixes
- Clockgating/S0ix/SMU/EEPROM fixes
- embed hw fence in job
- rework dma-resv handling
- ensure eviction to system ram
amdkfd:
- uapi: SVM address range query added
- sysfs leak fix
- GPUVM TLB optimizations
- vmfault/migration counters
i915:
- Enable JSL and EHL by default
- preliminary XeHP/DG2 support
- remove all CNL support (never shipped)
- move to TTM for discrete memory support
- allow mixed object mmap handling
- GEM uAPI spring cleaning
- add I915_MMAP_OBJECT_FIXED
- reinstate ADL-P mmap ioctls
- drop a bunch of unused by userspace features
- disable and remove GPU relocations
- revert some i915 misfeatures
- major refactoring of GuC for Gen11+
- execbuffer object locking separate step
- reject caching/set-domain on discrete
- Enable pipe DMC loading on XE-LPD and ADL-P
- add PSF GV point support
- Refactor and fix DDI buffer translations
- Clean up FBC CFB allocation code
- Finish INTEL_GEN() and friends macro conversions
nouveau:
- add eDP backlight support
- implicit fence fix
msm:
- a680/7c3 support
- drm/scheduler conversion
panfrost:
- rework GPU reset
virtio:
- fix fencing for planes
ast:
- add detect support
bochs:
- move to tiny GPU driver
vc4:
- use hotplug irqs
- HDMI codec support
vmwgfx:
- use internal vmware device headers
ingenic:
- demidlayering irq
rcar-du:
- shutdown fixes
- convert to bridge connector helpers
zynqmp-dsub:
- misc fixes
mgag200:
- convert PLL handling to atomic
mediatek:
- MT8133 AAL support
- gem mmap object support
- MT8167 support
etnaviv:
- NXP Layerscape LS1028A SoC support
- GEM mmap cleanups
tegra:
- new user API
exynos:
- missing unlock fix
- build warning fix
- use refcount_t"
* tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm: (1318 commits)
drm/amd/display: Move AllowDRAMSelfRefreshOrDRAMClockChangeInVblank to bounding box
drm/amd/display: Remove duplicate dml init
drm/amd/display: Update bounding box states (v2)
drm/amd/display: Update number of DCN3 clock states
drm/amdgpu: disable GFX CGCG in aldebaran
drm/amdgpu: Clear RAS interrupt status on aldebaran
drm/amdgpu: Add support for RAS XGMI err query
drm/amdkfd: Account for SH/SE count when setting up cu masks.
drm/amdgpu: rename amdgpu_bo_get_preferred_pin_domain
drm/amdgpu: drop redundant cancel_delayed_work_sync call
drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend
drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend
drm/amdkfd: map SVM range with correct access permission
drm/amdkfd: check access permisson to restore retry fault
drm/amdgpu: Update RAS XGMI Error Query
drm/amdgpu: Add driver infrastructure for MCA RAS
drm/amd/display: Add Logging for HDMI color depth information
drm/amd/amdgpu: consolidate PSP TA init shared buf functions
drm/amd/amdgpu: add name field back to ras_common_if
drm/amdgpu: Fix build with missing pm_suspend_target_state module export
...
Diffstat (limited to 'drivers/gpu/drm/i915/gem/i915_gem_object.c')
-rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_object.c | 350 |
1 files changed, 289 insertions, 61 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 5706d471692d..6fb9afb65034 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -30,14 +30,10 @@ #include "i915_gem_context.h" #include "i915_gem_mman.h" #include "i915_gem_object.h" -#include "i915_globals.h" #include "i915_memcpy.h" #include "i915_trace.h" -static struct i915_global_object { - struct i915_global base; - struct kmem_cache *slab_objects; -} global; +static struct kmem_cache *slab_objects; static const struct drm_gem_object_funcs i915_gem_object_funcs; @@ -45,7 +41,7 @@ struct drm_i915_gem_object *i915_gem_object_alloc(void) { struct drm_i915_gem_object *obj; - obj = kmem_cache_zalloc(global.slab_objects, GFP_KERNEL); + obj = kmem_cache_zalloc(slab_objects, GFP_KERNEL); if (!obj) return NULL; obj->base.funcs = &i915_gem_object_funcs; @@ -55,7 +51,7 @@ struct drm_i915_gem_object *i915_gem_object_alloc(void) void i915_gem_object_free(struct drm_i915_gem_object *obj) { - return kmem_cache_free(global.slab_objects, obj); + return kmem_cache_free(slab_objects, obj); } void i915_gem_object_init(struct drm_i915_gem_object *obj, @@ -172,7 +168,7 @@ static void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *f } } -static void __i915_gem_free_object_rcu(struct rcu_head *head) +void __i915_gem_free_object_rcu(struct rcu_head *head) { struct drm_i915_gem_object *obj = container_of(head, typeof(*obj), rcu); @@ -208,59 +204,69 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) } } -static void __i915_gem_free_objects(struct drm_i915_private *i915, - struct llist_node *freed) +void __i915_gem_free_object(struct drm_i915_gem_object *obj) { - struct drm_i915_gem_object *obj, *on; + trace_i915_gem_object_destroy(obj); - llist_for_each_entry_safe(obj, on, freed, freed) { - trace_i915_gem_object_destroy(obj); + if (!list_empty(&obj->vma.list)) { + struct i915_vma *vma; + + /* + * Note that the vma keeps an object reference while + * it is active, so it *should* not sleep while we + * destroy it. Our debug code errs insits it *might*. + * For the moment, play along. + */ + spin_lock(&obj->vma.lock); + while ((vma = list_first_entry_or_null(&obj->vma.list, + struct i915_vma, + obj_link))) { + GEM_BUG_ON(vma->obj != obj); + spin_unlock(&obj->vma.lock); - if (!list_empty(&obj->vma.list)) { - struct i915_vma *vma; + __i915_vma_put(vma); - /* - * Note that the vma keeps an object reference while - * it is active, so it *should* not sleep while we - * destroy it. Our debug code errs insits it *might*. - * For the moment, play along. - */ spin_lock(&obj->vma.lock); - while ((vma = list_first_entry_or_null(&obj->vma.list, - struct i915_vma, - obj_link))) { - GEM_BUG_ON(vma->obj != obj); - spin_unlock(&obj->vma.lock); + } + spin_unlock(&obj->vma.lock); + } - __i915_vma_put(vma); + __i915_gem_object_free_mmaps(obj); - spin_lock(&obj->vma.lock); - } - spin_unlock(&obj->vma.lock); - } + GEM_BUG_ON(!list_empty(&obj->lut_list)); - __i915_gem_object_free_mmaps(obj); + atomic_set(&obj->mm.pages_pin_count, 0); + __i915_gem_object_put_pages(obj); + GEM_BUG_ON(i915_gem_object_has_pages(obj)); + bitmap_free(obj->bit_17); - GEM_BUG_ON(!list_empty(&obj->lut_list)); + if (obj->base.import_attach) + drm_prime_gem_destroy(&obj->base, NULL); - atomic_set(&obj->mm.pages_pin_count, 0); - __i915_gem_object_put_pages(obj); - GEM_BUG_ON(i915_gem_object_has_pages(obj)); - bitmap_free(obj->bit_17); + drm_gem_free_mmap_offset(&obj->base); - if (obj->base.import_attach) - drm_prime_gem_destroy(&obj->base, NULL); + if (obj->ops->release) + obj->ops->release(obj); - drm_gem_free_mmap_offset(&obj->base); + if (obj->mm.n_placements > 1) + kfree(obj->mm.placements); - if (obj->ops->release) - obj->ops->release(obj); + if (obj->shares_resv_from) + i915_vm_resv_put(obj->shares_resv_from); +} - if (obj->mm.n_placements > 1) - kfree(obj->mm.placements); +static void __i915_gem_free_objects(struct drm_i915_private *i915, + struct llist_node *freed) +{ + struct drm_i915_gem_object *obj, *on; - if (obj->shares_resv_from) - i915_vm_resv_put(obj->shares_resv_from); + llist_for_each_entry_safe(obj, on, freed, freed) { + might_sleep(); + if (obj->ops->delayed_free) { + obj->ops->delayed_free(obj); + continue; + } + __i915_gem_free_object(obj); /* But keep the pointer alive for RCU-protected lookups */ call_rcu(&obj->rcu, __i915_gem_free_object_rcu); @@ -318,6 +324,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj) * worker and performing frees directly from subsequent allocations for * crude but effective memory throttling. */ + if (llist_add(&obj->freed, &i915->mm.free_list)) queue_work(i915->wq, &i915->mm.free_work); } @@ -410,34 +417,254 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, return 0; } -void i915_gem_init__objects(struct drm_i915_private *i915) +/** + * i915_gem_object_evictable - Whether object is likely evictable after unbind. + * @obj: The object to check + * + * This function checks whether the object is likely unvictable after unbind. + * If the object is not locked when checking, the result is only advisory. + * If the object is locked when checking, and the function returns true, + * then an eviction should indeed be possible. But since unlocked vma + * unpinning and unbinding is currently possible, the object can actually + * become evictable even if this function returns false. + * + * Return: true if the object may be evictable. False otherwise. + */ +bool i915_gem_object_evictable(struct drm_i915_gem_object *obj) { - INIT_WORK(&i915->mm.free_work, __i915_gem_free_work); + struct i915_vma *vma; + int pin_count = atomic_read(&obj->mm.pages_pin_count); + + if (!pin_count) + return true; + + spin_lock(&obj->vma.lock); + list_for_each_entry(vma, &obj->vma.list, obj_link) { + if (i915_vma_is_pinned(vma)) { + spin_unlock(&obj->vma.lock); + return false; + } + if (atomic_read(&vma->pages_count)) + pin_count--; + } + spin_unlock(&obj->vma.lock); + GEM_WARN_ON(pin_count < 0); + + return pin_count == 0; +} + +/** + * i915_gem_object_migratable - Whether the object is migratable out of the + * current region. + * @obj: Pointer to the object. + * + * Return: Whether the object is allowed to be resident in other + * regions than the current while pages are present. + */ +bool i915_gem_object_migratable(struct drm_i915_gem_object *obj) +{ + struct intel_memory_region *mr = READ_ONCE(obj->mm.region); + + if (!mr) + return false; + + return obj->mm.n_placements > 1; } -static void i915_global_objects_shrink(void) +/** + * i915_gem_object_has_struct_page - Whether the object is page-backed + * @obj: The object to query. + * + * This function should only be called while the object is locked or pinned, + * otherwise the page backing may change under the caller. + * + * Return: True if page-backed, false otherwise. + */ +bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj) { - kmem_cache_shrink(global.slab_objects); +#ifdef CONFIG_LOCKDEP + if (IS_DGFX(to_i915(obj->base.dev)) && + i915_gem_object_evictable((void __force *)obj)) + assert_object_held_shared(obj); +#endif + return obj->mem_flags & I915_BO_FLAG_STRUCT_PAGE; } -static void i915_global_objects_exit(void) +/** + * i915_gem_object_has_iomem - Whether the object is iomem-backed + * @obj: The object to query. + * + * This function should only be called while the object is locked or pinned, + * otherwise the iomem backing may change under the caller. + * + * Return: True if iomem-backed, false otherwise. + */ +bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj) { - kmem_cache_destroy(global.slab_objects); +#ifdef CONFIG_LOCKDEP + if (IS_DGFX(to_i915(obj->base.dev)) && + i915_gem_object_evictable((void __force *)obj)) + assert_object_held_shared(obj); +#endif + return obj->mem_flags & I915_BO_FLAG_IOMEM; } -static struct i915_global_object global = { { - .shrink = i915_global_objects_shrink, - .exit = i915_global_objects_exit, -} }; +/** + * i915_gem_object_can_migrate - Whether an object likely can be migrated + * + * @obj: The object to migrate + * @id: The region intended to migrate to + * + * Check whether the object backend supports migration to the + * given region. Note that pinning may affect the ability to migrate as + * returned by this function. + * + * This function is primarily intended as a helper for checking the + * possibility to migrate objects and might be slightly less permissive + * than i915_gem_object_migrate() when it comes to objects with the + * I915_BO_ALLOC_USER flag set. + * + * Return: true if migration is possible, false otherwise. + */ +bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj, + enum intel_region_id id) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + unsigned int num_allowed = obj->mm.n_placements; + struct intel_memory_region *mr; + unsigned int i; + + GEM_BUG_ON(id >= INTEL_REGION_UNKNOWN); + GEM_BUG_ON(obj->mm.madv != I915_MADV_WILLNEED); + + mr = i915->mm.regions[id]; + if (!mr) + return false; + + if (obj->mm.region == mr) + return true; + + if (!i915_gem_object_evictable(obj)) + return false; + + if (!obj->ops->migrate) + return false; + + if (!(obj->flags & I915_BO_ALLOC_USER)) + return true; + + if (num_allowed == 0) + return false; + + for (i = 0; i < num_allowed; ++i) { + if (mr == obj->mm.placements[i]) + return true; + } + + return false; +} + +/** + * i915_gem_object_migrate - Migrate an object to the desired region id + * @obj: The object to migrate. + * @ww: An optional struct i915_gem_ww_ctx. If NULL, the backend may + * not be successful in evicting other objects to make room for this object. + * @id: The region id to migrate to. + * + * Attempt to migrate the object to the desired memory region. The + * object backend must support migration and the object may not be + * pinned, (explicitly pinned pages or pinned vmas). The object must + * be locked. + * On successful completion, the object will have pages pointing to + * memory in the new region, but an async migration task may not have + * completed yet, and to accomplish that, i915_gem_object_wait_migration() + * must be called. + * + * Note: the @ww parameter is not used yet, but included to make sure + * callers put some effort into obtaining a valid ww ctx if one is + * available. + * + * Return: 0 on success. Negative error code on failure. In particular may + * return -ENXIO on lack of region space, -EDEADLK for deadlock avoidance + * if @ww is set, -EINTR or -ERESTARTSYS if signal pending, and + * -EBUSY if the object is pinned. + */ +int i915_gem_object_migrate(struct drm_i915_gem_object *obj, + struct i915_gem_ww_ctx *ww, + enum intel_region_id id) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct intel_memory_region *mr; + + GEM_BUG_ON(id >= INTEL_REGION_UNKNOWN); + GEM_BUG_ON(obj->mm.madv != I915_MADV_WILLNEED); + assert_object_held(obj); + + mr = i915->mm.regions[id]; + GEM_BUG_ON(!mr); + + if (!i915_gem_object_can_migrate(obj, id)) + return -EINVAL; + + if (!obj->ops->migrate) { + if (GEM_WARN_ON(obj->mm.region != mr)) + return -EINVAL; + return 0; + } + + return obj->ops->migrate(obj, mr); +} + +/** + * i915_gem_object_placement_possible - Check whether the object can be + * placed at certain memory type + * @obj: Pointer to the object + * @type: The memory type to check + * + * Return: True if the object can be placed in @type. False otherwise. + */ +bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj, + enum intel_memory_type type) +{ + unsigned int i; + + if (!obj->mm.n_placements) { + switch (type) { + case INTEL_MEMORY_LOCAL: + return i915_gem_object_has_iomem(obj); + case INTEL_MEMORY_SYSTEM: + return i915_gem_object_has_pages(obj); + default: + /* Ignore stolen for now */ + GEM_BUG_ON(1); + return false; + } + } + + for (i = 0; i < obj->mm.n_placements; i++) { + if (obj->mm.placements[i]->type == type) + return true; + } + + return false; +} + +void i915_gem_init__objects(struct drm_i915_private *i915) +{ + INIT_WORK(&i915->mm.free_work, __i915_gem_free_work); +} + +void i915_objects_module_exit(void) +{ + kmem_cache_destroy(slab_objects); +} -int __init i915_global_objects_init(void) +int __init i915_objects_module_init(void) { - global.slab_objects = - KMEM_CACHE(drm_i915_gem_object, SLAB_HWCACHE_ALIGN); - if (!global.slab_objects) + slab_objects = KMEM_CACHE(drm_i915_gem_object, SLAB_HWCACHE_ALIGN); + if (!slab_objects) return -ENOMEM; - i915_global_register(&global.base); return 0; } @@ -450,6 +677,7 @@ static const struct drm_gem_object_funcs i915_gem_object_funcs = { #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/huge_gem_object.c" #include "selftests/huge_pages.c" +#include "selftests/i915_gem_migrate.c" #include "selftests/i915_gem_object.c" #include "selftests/i915_gem_coherency.c" #endif |