We are currently sharing the VM reservation locks across a number of gem objects with page-table memory. Since TTM will individiualize the reservation locks when freeing objects, including accessing the shared locks, make sure that the shared locks are not freed until that is done. For PPGTT we add an additional refcount, for GGTT we take additional measures to make sure objects sharing the GGTT reservation lock are freed at GGTT takedown

Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Reviewed-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com --- v2: Try harder to make sure objects sharing the GGTT reservation lock are freed at GGTT takedown. v3: Use a pointer to the vm to indicate that an object shares a reservation object from that vm, rather than a pointer to the reservation object itself. --- drivers/gpu/drm/i915/gem/i915_gem_object.c | 3 ++ .../gpu/drm/i915/gem/i915_gem_object_types.h | 4 ++ drivers/gpu/drm/i915/gt/intel_ggtt.c | 19 ++++++-- drivers/gpu/drm/i915/gt/intel_gtt.c | 45 +++++++++++++++---- drivers/gpu/drm/i915/gt/intel_gtt.h | 28 +++++++++++- drivers/gpu/drm/i915/gt/intel_ppgtt.c | 2 +- drivers/gpu/drm/i915/i915_drv.c | 5 +++ 7 files changed, 93 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 28144410df86..2be6109d0093 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -252,6 +252,9 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, if (obj->mm.n_placements > 1) kfree(obj->mm.placements);

+ if (obj->shares_resv_from) + i915_vm_resv_put(obj->shares_resv_from); + /* But keep the pointer alive for RCU-protected lookups */ call_rcu(&obj->rcu, __i915_gem_free_object_rcu); cond_resched(); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 0727d0c76aa0..0415f99b6b95 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -149,6 +149,10 @@ struct drm_i915_gem_object { * when i915_gem_ww_ctx_backoff() or i915_gem_ww_ctx_fini() are called. */ struct list_head obj_link; + /** + * @shared_resv_from: The object shares the resv from this vm. + */ + struct i915_address_space *shares_resv_from;

union { struct rcu_head rcu; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 35069ca5d7de..10c23a749a95 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -746,7 +746,6 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)

mutex_unlock(&ggtt->vm.mutex); i915_address_space_fini(&ggtt->vm); - dma_resv_fini(&ggtt->vm.resv);

arch_phys_wc_del(ggtt->mtrr);

@@ -768,6 +767,19 @@ void i915_ggtt_driver_release(struct drm_i915_private *i915) ggtt_cleanup_hw(ggtt); }

+/** + * i915_ggtt_driver_late_release - Cleanup of GGTT that needs to be done after + * all free objects have been drained. + * @i915: i915 device + */ +void i915_ggtt_driver_late_release(struct drm_i915_private *i915) +{ + struct i915_ggtt *ggtt = &i915->ggtt; + + GEM_WARN_ON(kref_read(&ggtt->vm.resv_ref) != 1); + dma_resv_fini(&ggtt->vm._resv); +} + static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl) { snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT; @@ -829,6 +841,7 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) return -ENOMEM; }

+ kref_init(&ggtt->vm.resv_ref); ret = setup_scratch_page(&ggtt->vm); if (ret) { drm_err(&i915->drm, "Scratch setup failed\n"); @@ -1135,7 +1148,7 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt) ggtt->vm.gt = gt; ggtt->vm.i915 = i915; ggtt->vm.dma = i915->drm.dev; - dma_resv_init(&ggtt->vm.resv); + dma_resv_init(&ggtt->vm._resv);

if (INTEL_GEN(i915) <= 5) ret = i915_gmch_probe(ggtt); @@ -1144,7 +1157,7 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt) else ret = gen8_gmch_probe(ggtt); if (ret) { - dma_resv_fini(&ggtt->vm.resv); + dma_resv_fini(&ggtt->vm._resv); return ret; }

diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 9b98f9d9faa3..94849567143d 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -22,8 +22,11 @@ struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz) * object underneath, with the idea that one object_lock() will lock * them all at once. */ - if (!IS_ERR(obj)) - obj->base.resv = &vm->resv; + if (!IS_ERR(obj)) { + obj->base.resv = i915_vm_resv_get(vm); + obj->shares_resv_from = vm; + } + return obj; }

@@ -40,8 +43,11 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz) * object underneath, with the idea that one object_lock() will lock * them all at once. */ - if (!IS_ERR(obj)) - obj->base.resv = &vm->resv; + if (!IS_ERR(obj)) { + obj->base.resv = i915_vm_resv_get(vm); + obj->shares_resv_from = vm; + } + return obj; }

@@ -102,7 +108,7 @@ void __i915_vm_close(struct i915_address_space *vm) int i915_vm_lock_objects(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww) { - if (vm->scratch[0]->base.resv == &vm->resv) { + if (vm->scratch[0]->base.resv == &vm->_resv) { return i915_gem_object_lock(vm->scratch[0], ww); } else { struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); @@ -118,6 +124,22 @@ void i915_address_space_fini(struct i915_address_space *vm) mutex_destroy(&vm->mutex); }

+/** + * i915_vm_resv_release - Final struct i915_address_space destructor + * @kref: Pointer to the &i915_address_space.resv_ref member. + * + * This function is called when the last lock sharer no longer shares the + * &i915_address_space._resv lock. + */ +void i915_vm_resv_release(struct kref *kref) +{ + struct i915_address_space *vm = + container_of(kref, typeof(*vm), resv_ref); + + dma_resv_fini(&vm->_resv); + kfree(vm); +} + static void __i915_vm_release(struct work_struct *work) { struct i915_address_space *vm = @@ -125,9 +147,8 @@ static void __i915_vm_release(struct work_struct *work)

vm->cleanup(vm); i915_address_space_fini(vm); - dma_resv_fini(&vm->resv);

- kfree(vm); + i915_vm_resv_put(vm); }

void i915_vm_release(struct kref *kref) @@ -144,6 +165,14 @@ void i915_vm_release(struct kref *kref) void i915_address_space_init(struct i915_address_space *vm, int subclass) { kref_init(&vm->ref); + + /* + * Special case for GGTT that has already done an early + * kref_init here. + */ + if (!kref_read(&vm->resv_ref)) + kref_init(&vm->resv_ref); + INIT_RCU_WORK(&vm->rcu, __i915_vm_release); atomic_set(&vm->open, 1);

@@ -170,7 +199,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) might_alloc(GFP_KERNEL); mutex_release(&vm->mutex.dep_map, _THIS_IP_); } - dma_resv_init(&vm->resv); + dma_resv_init(&vm->_resv);

GEM_BUG_ON(!vm->total); drm_mm_init(&vm->mm, 0, vm->total); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 50a98ce39f74..edea95b97c36 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -245,7 +245,9 @@ struct i915_address_space { atomic_t open;

struct mutex mutex; /* protects vma and our lists */ - struct dma_resv resv; /* reservation lock for all pd objects, and buffer pool */ + + struct kref resv_ref; /* kref to keep the reservation lock alive. */ + struct dma_resv _resv; /* reservation lock for all pd objects, and buffer pool */ #define VM_CLASS_GGTT 0 #define VM_CLASS_PPGTT 1 #define VM_CLASS_DPT 2 @@ -405,13 +407,36 @@ i915_vm_get(struct i915_address_space *vm) return vm; }

+/** + * i915_vm_resv_get - Obtain a reference on the vm's reservation lock + * @vm: The vm whose reservation lock we want to share. + * + * Return: A pointer to the vm's reservation lock. + */ +static inline struct dma_resv *i915_vm_resv_get(struct i915_address_space *vm) +{ + kref_get(&vm->resv_ref); + return &vm->_resv; +} + void i915_vm_release(struct kref *kref);

+void i915_vm_resv_release(struct kref *kref); + static inline void i915_vm_put(struct i915_address_space *vm) { kref_put(&vm->ref, i915_vm_release); }

+/** + * i915_vm_resv_put - Release a reference on the vm's reservation lock + * @resv: Pointer to a reservation lock obtained from i915_vm_resv_get() + */ +static inline void i915_vm_resv_put(struct i915_address_space *vm) +{ + kref_put(&vm->resv_ref, i915_vm_resv_release); +} + static inline struct i915_address_space * i915_vm_open(struct i915_address_space *vm) { @@ -507,6 +532,7 @@ void i915_ggtt_enable_guc(struct i915_ggtt *ggtt); void i915_ggtt_disable_guc(struct i915_ggtt *ggtt); int i915_init_ggtt(struct drm_i915_private *i915); void i915_ggtt_driver_release(struct drm_i915_private *i915); +void i915_ggtt_driver_late_release(struct drm_i915_private *i915);

static inline bool i915_ggtt_has_aperture(const struct i915_ggtt *ggtt) { diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 4e3d80c2295c..aee3a8929245 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -307,7 +307,7 @@ void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt) ppgtt->vm.dma = i915->drm.dev; ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size);

- dma_resv_init(&ppgtt->vm.resv); + dma_resv_init(&ppgtt->vm._resv); i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);

ppgtt->vm.vma_ops.bind_vma = ppgtt_bind_vma; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 2f06bb7b3ed2..d82a99e128cf 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -631,6 +631,8 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) intel_memory_regions_driver_release(dev_priv); err_ggtt: i915_ggtt_driver_release(dev_priv); + i915_gem_drain_freed_objects(dev_priv); + i915_ggtt_driver_late_release(dev_priv); err_perf: i915_perf_fini(dev_priv); return ret; @@ -880,6 +882,8 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i915_driver_hw_remove(i915); intel_memory_regions_driver_release(i915); i915_ggtt_driver_release(i915); + i915_gem_drain_freed_objects(i915); + i915_ggtt_driver_late_release(i915); out_cleanup_mmio: i915_driver_mmio_release(i915); out_runtime_pm_put: @@ -936,6 +940,7 @@ static void i915_driver_release(struct drm_device *dev) intel_memory_regions_driver_release(dev_priv); i915_ggtt_driver_release(dev_priv); i915_gem_drain_freed_objects(dev_priv); + i915_ggtt_driver_late_release(dev_priv);

i915_driver_mmio_release(dev_priv);

Temporarily remove the buddy allocator and related selftests and hook up the TTM range manager for i915 regions.

Also modify the mock region selftests somewhat to account for a fragmenting manager.

Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com #v2 --- v2: - Fix an error unwind in lmem_get_pages() (Reported by Matthew Auld) - Break out and modify usage of i915_sg_dma_sizes() (Reported by Mattew Auld) - Break out TTM changes to a separate patch (Reported by Christian König) v3: - Fix the same error unwind in mock_region_get_pages() (Reported by Matthew Auld) - Don't rely on new TTM functionality, but create a mock TTM device, (Reported by Christian König) v4: - Use mock_gem_device rather than creating a separate ttm_device per region. --- drivers/gpu/drm/i915/Kconfig | 1 + drivers/gpu/drm/i915/Makefile | 2 +- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 59 +- .../gpu/drm/i915/gem/i915_gem_object_types.h | 6 +- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 3 +- drivers/gpu/drm/i915/gem/i915_gem_region.c | 120 --- drivers/gpu/drm/i915/gem/i915_gem_region.h | 4 - drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 4 +- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 10 +- drivers/gpu/drm/i915/gem/i915_gem_stolen.h | 9 +- drivers/gpu/drm/i915/gt/intel_gt.c | 2 - drivers/gpu/drm/i915/gt/intel_region_lmem.c | 27 +- drivers/gpu/drm/i915/i915_buddy.c | 435 ---------- drivers/gpu/drm/i915/i915_buddy.h | 131 --- drivers/gpu/drm/i915/i915_drv.c | 8 + drivers/gpu/drm/i915/i915_drv.h | 8 +- drivers/gpu/drm/i915/i915_gem.c | 1 + drivers/gpu/drm/i915/i915_globals.c | 1 - drivers/gpu/drm/i915/i915_globals.h | 1 - drivers/gpu/drm/i915/i915_scatterlist.c | 70 ++ drivers/gpu/drm/i915/i915_scatterlist.h | 4 + drivers/gpu/drm/i915/intel_memory_region.c | 180 ++-- drivers/gpu/drm/i915/intel_memory_region.h | 44 +- drivers/gpu/drm/i915/intel_region_ttm.c | 220 +++++ drivers/gpu/drm/i915/intel_region_ttm.h | 32 + drivers/gpu/drm/i915/selftests/i915_buddy.c | 789 ------------------ .../drm/i915/selftests/i915_mock_selftests.h | 1 - .../drm/i915/selftests/intel_memory_region.c | 133 +-- .../gpu/drm/i915/selftests/mock_gem_device.c | 10 + drivers/gpu/drm/i915/selftests/mock_region.c | 70 +- 30 files changed, 631 insertions(+), 1754 deletions(-) delete mode 100644 drivers/gpu/drm/i915/i915_buddy.c delete mode 100644 drivers/gpu/drm/i915/i915_buddy.h create mode 100644 drivers/gpu/drm/i915/intel_region_ttm.c create mode 100644 drivers/gpu/drm/i915/intel_region_ttm.h delete mode 100644 drivers/gpu/drm/i915/selftests/i915_buddy.c

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 93f4d059fc89..61ff5c178714 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -27,6 +27,7 @@ config DRM_I915 select SND_HDA_I915 if SND_HDA_CORE select CEC_CORE if CEC_NOTIFIER select VMAP_PFN + select DRM_TTM help Choose this option if you have a system that has "Intel Graphics Media Accelerator" or "HD Graphics" integrated graphics, diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 6947495bf34b..4f22cac1c49b 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -50,6 +50,7 @@ i915-y += i915_drv.o \ intel_memory_region.o \ intel_pch.o \ intel_pm.o \ + intel_region_ttm.o \ intel_runtime_pm.o \ intel_sideband.o \ intel_step.o \ @@ -160,7 +161,6 @@ gem-y += \ i915-y += \ $(gem-y) \ i915_active.o \ - i915_buddy.o \ i915_cmd_parser.o \ i915_gem_evict.o \ i915_gem_gtt.o \ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index f44bdd08f7cb..3b4aa28a076d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -4,16 +4,71 @@ */

#include "intel_memory_region.h" +#include "intel_region_ttm.h" #include "gem/i915_gem_region.h" #include "gem/i915_gem_lmem.h" #include "i915_drv.h"

+static void lmem_put_pages(struct drm_i915_gem_object *obj, + struct sg_table *pages) +{ + intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node); + obj->mm.dirty = false; + sg_free_table(pages); + kfree(pages); +} + +static int lmem_get_pages(struct drm_i915_gem_object *obj) +{ + unsigned int flags; + struct sg_table *pages; + + flags = I915_ALLOC_MIN_PAGE_SIZE; + if (obj->flags & I915_BO_ALLOC_CONTIGUOUS) + flags |= I915_ALLOC_CONTIGUOUS; + + obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region, + obj->base.size, + flags); + if (IS_ERR(obj->mm.st_mm_node)) + return PTR_ERR(obj->mm.st_mm_node); + + /* Range manager is always contigous */ + if (obj->mm.region->is_range_manager) + obj->flags |= I915_BO_ALLOC_CONTIGUOUS; + pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node); + if (IS_ERR(pages)) { + intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node); + return PTR_ERR(pages); + } + + __i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl)); + + if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) { + void __iomem *vaddr = + i915_gem_object_lmem_io_map(obj, 0, obj->base.size); + + if (!vaddr) { + struct sg_table *pages = + __i915_gem_object_unset_pages(obj); + + if (!IS_ERR_OR_NULL(pages)) + lmem_put_pages(obj, pages); + } + + memset_io(vaddr, 0, obj->base.size); + io_mapping_unmap(vaddr); + } + + return 0; +} + const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = { .name = "i915_gem_object_lmem", .flags = I915_GEM_OBJECT_HAS_IOMEM,

- .get_pages = i915_gem_object_get_pages_buddy, - .put_pages = i915_gem_object_put_pages_buddy, + .get_pages = lmem_get_pages, + .put_pages = lmem_put_pages, .release = i915_gem_object_release_memory_region, };

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 0415f99b6b95..f5b46d11e6e6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -235,10 +235,12 @@ struct drm_i915_gem_object { * Memory region for this object. */ struct intel_memory_region *region; + /** - * List of memory region blocks allocated for this object. + * Memory manager node allocated for this object. */ - struct list_head blocks; + void *st_mm_node; + /** * Element within memory_region->objects or region->purgeable * if the object is marked as DONTNEED. Access is protected by diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 7361971c177d..6444e097016d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -475,7 +475,8 @@ __i915_gem_object_get_sg(struct drm_i915_gem_object *obj,

might_sleep(); GEM_BUG_ON(n >= obj->base.size >> PAGE_SHIFT); - GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); + if (!i915_gem_object_has_pinned_pages(obj)) + assert_object_held(obj);

/* As we iterate forward through the sg, we record each entry in a * radixtree for quick repeated (backwards) lookups. If we have seen diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index ce8fcfc54079..f25e6646c5b7 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -8,129 +8,9 @@ #include "i915_drv.h" #include "i915_trace.h"

-void -i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj, - struct sg_table *pages) -{ - __intel_memory_region_put_pages_buddy(obj->mm.region, &obj->mm.blocks); - - obj->mm.dirty = false; - sg_free_table(pages); - kfree(pages); -} - -int -i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj) -{ - const u64 max_segment = i915_sg_segment_size(); - struct intel_memory_region *mem = obj->mm.region; - struct list_head *blocks = &obj->mm.blocks; - resource_size_t size = obj->base.size; - resource_size_t prev_end; - struct i915_buddy_block *block; - unsigned int flags; - struct sg_table *st; - struct scatterlist *sg; - unsigned int sg_page_sizes; - int ret; - - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) - return -ENOMEM; - - if (sg_alloc_table(st, size >> PAGE_SHIFT, GFP_KERNEL)) { - kfree(st); - return -ENOMEM; - } - - flags = I915_ALLOC_MIN_PAGE_SIZE; - if (obj->flags & I915_BO_ALLOC_CONTIGUOUS) - flags |= I915_ALLOC_CONTIGUOUS; - - ret = __intel_memory_region_get_pages_buddy(mem, size, flags, blocks); - if (ret) - goto err_free_sg; - - GEM_BUG_ON(list_empty(blocks)); - - sg = st->sgl; - st->nents = 0; - sg_page_sizes = 0; - prev_end = (resource_size_t)-1; - - list_for_each_entry(block, blocks, link) { - u64 block_size, offset; - - block_size = min_t(u64, size, - i915_buddy_block_size(&mem->mm, block)); - offset = i915_buddy_block_offset(block); - - while (block_size) { - u64 len; - - if (offset != prev_end || sg->length >= max_segment) { - if (st->nents) { - sg_page_sizes |= sg->length; - sg = __sg_next(sg); - } - - sg_dma_address(sg) = mem->region.start + offset; - sg_dma_len(sg) = 0; - sg->length = 0; - st->nents++; - } - - len = min(block_size, max_segment - sg->length); - sg->length += len; - sg_dma_len(sg) += len; - - offset += len; - block_size -= len; - - prev_end = offset; - } - } - - sg_page_sizes |= sg->length; - sg_mark_end(sg); - i915_sg_trim(st); - - /* Intended for kernel internal use only */ - if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) { - struct scatterlist *sg; - unsigned long i; - - for_each_sg(st->sgl, sg, st->nents, i) { - unsigned int length; - void __iomem *vaddr; - dma_addr_t daddr; - - daddr = sg_dma_address(sg); - daddr -= mem->region.start; - length = sg_dma_len(sg); - - vaddr = io_mapping_map_wc(&mem->iomap, daddr, length); - memset64((void __force *)vaddr, 0, length / sizeof(u64)); - io_mapping_unmap(vaddr); - } - - wmb(); - } - - __i915_gem_object_set_pages(obj, st, sg_page_sizes); - - return 0; - -err_free_sg: - sg_free_table(st); - kfree(st); - return ret; -} - void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj, struct intel_memory_region *mem) { - INIT_LIST_HEAD(&obj->mm.blocks); obj->mm.region = intel_memory_region_get(mem);

if (obj->base.size <= mem->min_page_size) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.h b/drivers/gpu/drm/i915/gem/i915_gem_region.h index ebddc86d78f7..84fcb3297400 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.h @@ -12,10 +12,6 @@ struct intel_memory_region; struct drm_i915_gem_object; struct sg_table;

-int i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj); -void i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj, - struct sg_table *pages); - void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj, struct intel_memory_region *mem); void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index a9bfa66c8da1..5d16c4462fda 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -628,11 +628,13 @@ static const struct intel_memory_region_ops shmem_region_ops = { .init_object = shmem_object_init, };

-struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915) +struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915, + u16 type, u16 instance) { return intel_memory_region_create(i915, 0, totalram_pages() << PAGE_SHIFT, PAGE_SIZE, 0, + type, instance, &shmem_region_ops); }

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index b5553fc3ac4d..092d7a21de82 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -772,7 +772,8 @@ static const struct intel_memory_region_ops i915_region_stolen_lmem_ops = { };

struct intel_memory_region * -i915_gem_stolen_lmem_setup(struct drm_i915_private *i915) +i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, + u16 instance) { struct intel_uncore *uncore = &i915->uncore; struct pci_dev *pdev = to_pci_dev(i915->drm.dev); @@ -790,6 +791,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915)

mem = intel_memory_region_create(i915, lmem_base, lmem_size, I915_GTT_PAGE_SIZE_4K, io_start, + type, instance, &i915_region_stolen_lmem_ops); if (IS_ERR(mem)) return mem; @@ -811,14 +813,15 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915) }

struct intel_memory_region* -i915_gem_stolen_smem_setup(struct drm_i915_private *i915) +i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type, + u16 instance) { struct intel_memory_region *mem;

mem = intel_memory_region_create(i915, intel_graphics_stolen_res.start, resource_size(&intel_graphics_stolen_res), - PAGE_SIZE, 0, + PAGE_SIZE, 0, type, instance, &i915_region_stolen_smem_ops); if (IS_ERR(mem)) return mem; @@ -826,7 +829,6 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915) intel_memory_region_set_name(mem, "stolen-system");

mem->private = true; - return mem; }

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h index 2bec6c367b9c..ccdf7befc571 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h @@ -21,8 +21,13 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, u64 end); void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv, struct drm_mm_node *node); -struct intel_memory_region *i915_gem_stolen_smem_setup(struct drm_i915_private *i915); -struct intel_memory_region *i915_gem_stolen_lmem_setup(struct drm_i915_private *i915); +struct intel_memory_region * +i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type, + u16 instance); +struct intel_memory_region * +i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, + u16 instance); + struct drm_i915_gem_object * i915_gem_object_create_stolen(struct drm_i915_private *dev_priv, resource_size_t size); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 8d77dcbad059..3f88ecdee031 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -68,8 +68,6 @@ int intel_gt_probe_lmem(struct intel_gt *gt) id = INTEL_REGION_LMEM;

mem->id = id; - mem->type = INTEL_MEMORY_LOCAL; - mem->instance = 0;

intel_memory_region_set_name(mem, "local%u", mem->instance);

diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index 73fceb0c25fc..f7366b054f8e 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -5,6 +5,8 @@

#include "i915_drv.h" #include "intel_memory_region.h" +#include "intel_region_lmem.h" +#include "intel_region_ttm.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" #include "intel_region_lmem.h" @@ -66,9 +68,9 @@ static void release_fake_lmem_bar(struct intel_memory_region *mem) static void region_lmem_release(struct intel_memory_region *mem) { - release_fake_lmem_bar(mem); + intel_region_ttm_fini(mem); io_mapping_fini(&mem->iomap); - intel_memory_region_release_buddy(mem); + release_fake_lmem_bar(mem); }

static int @@ -83,12 +85,21 @@ region_lmem_init(struct intel_memory_region *mem)

if (!io_mapping_init_wc(&mem->iomap, mem->io_start, - resource_size(&mem->region))) - return -EIO; + resource_size(&mem->region))) { + ret = -EIO; + goto out_no_io; + }

- ret = intel_memory_region_init_buddy(mem); + ret = intel_region_ttm_init(mem); if (ret) - io_mapping_fini(&mem->iomap); + goto out_no_buddy; + + return 0; + +out_no_buddy: + io_mapping_fini(&mem->iomap); +out_no_io: + release_fake_lmem_bar(mem);

return ret; } @@ -127,6 +138,8 @@ intel_gt_setup_fake_lmem(struct intel_gt *gt) mappable_end, PAGE_SIZE, io_start, + INTEL_MEMORY_LOCAL, + 0, &intel_region_lmem_ops); if (!IS_ERR(mem)) { drm_info(&i915->drm, "Intel graphics fake LMEM: %pR\n", @@ -198,6 +211,8 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) lmem_size, I915_GTT_PAGE_SIZE_4K, io_start, + INTEL_MEMORY_LOCAL, + 0, &intel_region_lmem_ops); if (IS_ERR(mem)) return mem; diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c deleted file mode 100644 index 3a2f6eecb2fc..000000000000 --- a/drivers/gpu/drm/i915/i915_buddy.c +++ /dev/null @@ -1,435 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2019 Intel Corporation - */ - -#include <linux/kmemleak.h> -#include <linux/slab.h> - -#include "i915_buddy.h" - -#include "i915_gem.h" -#include "i915_globals.h" -#include "i915_utils.h" - -static struct i915_global_block { - struct i915_global base; - struct kmem_cache *slab_blocks; -} global; - -static void i915_global_buddy_shrink(void) -{ - kmem_cache_shrink(global.slab_blocks); -} - -static void i915_global_buddy_exit(void) -{ - kmem_cache_destroy(global.slab_blocks); -} - -static struct i915_global_block global = { { - .shrink = i915_global_buddy_shrink, - .exit = i915_global_buddy_exit, -} }; - -int __init i915_global_buddy_init(void) -{ - global.slab_blocks = KMEM_CACHE(i915_buddy_block, SLAB_HWCACHE_ALIGN); - if (!global.slab_blocks) - return -ENOMEM; - - i915_global_register(&global.base); - return 0; -} - -static struct i915_buddy_block *i915_block_alloc(struct i915_buddy_block *parent, - unsigned int order, - u64 offset) -{ - struct i915_buddy_block *block; - - GEM_BUG_ON(order > I915_BUDDY_MAX_ORDER); - - block = kmem_cache_zalloc(global.slab_blocks, GFP_KERNEL); - if (!block) - return NULL; - - block->header = offset; - block->header |= order; - block->parent = parent; - - GEM_BUG_ON(block->header & I915_BUDDY_HEADER_UNUSED); - return block; -} - -static void i915_block_free(struct i915_buddy_block *block) -{ - kmem_cache_free(global.slab_blocks, block); -} - -static void mark_allocated(struct i915_buddy_block *block) -{ - block->header &= ~I915_BUDDY_HEADER_STATE; - block->header |= I915_BUDDY_ALLOCATED; - - list_del(&block->link); -} - -static void mark_free(struct i915_buddy_mm *mm, - struct i915_buddy_block *block) -{ - block->header &= ~I915_BUDDY_HEADER_STATE; - block->header |= I915_BUDDY_FREE; - - list_add(&block->link, - &mm->free_list[i915_buddy_block_order(block)]); -} - -static void mark_split(struct i915_buddy_block *block) -{ - block->header &= ~I915_BUDDY_HEADER_STATE; - block->header |= I915_BUDDY_SPLIT; - - list_del(&block->link); -} - -int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size) -{ - unsigned int i; - u64 offset; - - if (size < chunk_size) - return -EINVAL; - - if (chunk_size < PAGE_SIZE) - return -EINVAL; - - if (!is_power_of_2(chunk_size)) - return -EINVAL; - - size = round_down(size, chunk_size); - - mm->size = size; - mm->chunk_size = chunk_size; - mm->max_order = ilog2(size) - ilog2(chunk_size); - - GEM_BUG_ON(mm->max_order > I915_BUDDY_MAX_ORDER); - - mm->free_list = kmalloc_array(mm->max_order + 1, - sizeof(struct list_head), - GFP_KERNEL); - if (!mm->free_list) - return -ENOMEM; - - for (i = 0; i <= mm->max_order; ++i) - INIT_LIST_HEAD(&mm->free_list[i]); - - mm->n_roots = hweight64(size); - - mm->roots = kmalloc_array(mm->n_roots, - sizeof(struct i915_buddy_block *), - GFP_KERNEL); - if (!mm->roots) - goto out_free_list; - - offset = 0; - i = 0; - - /* - * Split into power-of-two blocks, in case we are given a size that is - * not itself a power-of-two. - */ - do { - struct i915_buddy_block *root; - unsigned int order; - u64 root_size; - - root_size = rounddown_pow_of_two(size); - order = ilog2(root_size) - ilog2(chunk_size); - - root = i915_block_alloc(NULL, order, offset); - if (!root) - goto out_free_roots; - - mark_free(mm, root); - - GEM_BUG_ON(i > mm->max_order); - GEM_BUG_ON(i915_buddy_block_size(mm, root) < chunk_size); - - mm->roots[i] = root; - - offset += root_size; - size -= root_size; - i++; - } while (size); - - return 0; - -out_free_roots: - while (i--) - i915_block_free(mm->roots[i]); - kfree(mm->roots); -out_free_list: - kfree(mm->free_list); - return -ENOMEM; -} - -void i915_buddy_fini(struct i915_buddy_mm *mm) -{ - int i; - - for (i = 0; i < mm->n_roots; ++i) { - GEM_WARN_ON(!i915_buddy_block_is_free(mm->roots[i])); - i915_block_free(mm->roots[i]); - } - - kfree(mm->roots); - kfree(mm->free_list); -} - -static int split_block(struct i915_buddy_mm *mm, - struct i915_buddy_block *block) -{ - unsigned int block_order = i915_buddy_block_order(block) - 1; - u64 offset = i915_buddy_block_offset(block); - - GEM_BUG_ON(!i915_buddy_block_is_free(block)); - GEM_BUG_ON(!i915_buddy_block_order(block)); - - block->left = i915_block_alloc(block, block_order, offset); - if (!block->left) - return -ENOMEM; - - block->right = i915_block_alloc(block, block_order, - offset + (mm->chunk_size << block_order)); - if (!block->right) { - i915_block_free(block->left); - return -ENOMEM; - } - - mark_free(mm, block->left); - mark_free(mm, block->right); - - mark_split(block); - - return 0; -} - -static struct i915_buddy_block * -get_buddy(struct i915_buddy_block *block) -{ - struct i915_buddy_block *parent; - - parent = block->parent; - if (!parent) - return NULL; - - if (parent->left == block) - return parent->right; - - return parent->left; -} - -static void __i915_buddy_free(struct i915_buddy_mm *mm, - struct i915_buddy_block *block) -{ - struct i915_buddy_block *parent; - - while ((parent = block->parent)) { - struct i915_buddy_block *buddy; - - buddy = get_buddy(block); - - if (!i915_buddy_block_is_free(buddy)) - break; - - list_del(&buddy->link); - - i915_block_free(block); - i915_block_free(buddy); - - block = parent; - } - - mark_free(mm, block); -} - -void i915_buddy_free(struct i915_buddy_mm *mm, - struct i915_buddy_block *block) -{ - GEM_BUG_ON(!i915_buddy_block_is_allocated(block)); - __i915_buddy_free(mm, block); -} - -void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects) -{ - struct i915_buddy_block *block, *on; - - list_for_each_entry_safe(block, on, objects, link) { - i915_buddy_free(mm, block); - cond_resched(); - } - INIT_LIST_HEAD(objects); -} - -/* - * Allocate power-of-two block. The order value here translates to: - * - * 0 = 2^0 * mm->chunk_size - * 1 = 2^1 * mm->chunk_size - * 2 = 2^2 * mm->chunk_size - * ... - */ -struct i915_buddy_block * -i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order) -{ - struct i915_buddy_block *block = NULL; - unsigned int i; - int err; - - for (i = order; i <= mm->max_order; ++i) { - block = list_first_entry_or_null(&mm->free_list[i], - struct i915_buddy_block, - link); - if (block) - break; - } - - if (!block) - return ERR_PTR(-ENOSPC); - - GEM_BUG_ON(!i915_buddy_block_is_free(block)); - - while (i != order) { - err = split_block(mm, block); - if (unlikely(err)) - goto out_free; - - /* Go low */ - block = block->left; - i--; - } - - mark_allocated(block); - kmemleak_update_trace(block); - return block; - -out_free: - if (i != order) - __i915_buddy_free(mm, block); - return ERR_PTR(err); -} - -static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2) -{ - return s1 <= e2 && e1 >= s2; -} - -static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2) -{ - return s1 <= s2 && e1 >= e2; -} - -/* - * Allocate range. Note that it's safe to chain together multiple alloc_ranges - * with the same blocks list. - * - * Intended for pre-allocating portions of the address space, for example to - * reserve a block for the initial framebuffer or similar, hence the expectation - * here is that i915_buddy_alloc() is still the main vehicle for - * allocations, so if that's not the case then the drm_mm range allocator is - * probably a much better fit, and so you should probably go use that instead. - */ -int i915_buddy_alloc_range(struct i915_buddy_mm *mm, - struct list_head *blocks, - u64 start, u64 size) -{ - struct i915_buddy_block *block; - struct i915_buddy_block *buddy; - LIST_HEAD(allocated); - LIST_HEAD(dfs); - u64 end; - int err; - int i; - - if (size < mm->chunk_size) - return -EINVAL; - - if (!IS_ALIGNED(size | start, mm->chunk_size)) - return -EINVAL; - - if (range_overflows(start, size, mm->size)) - return -EINVAL; - - for (i = 0; i < mm->n_roots; ++i) - list_add_tail(&mm->roots[i]->tmp_link, &dfs); - - end = start + size - 1; - - do { - u64 block_start; - u64 block_end; - - block = list_first_entry_or_null(&dfs, - struct i915_buddy_block, - tmp_link); - if (!block) - break; - - list_del(&block->tmp_link); - - block_start = i915_buddy_block_offset(block); - block_end = block_start + i915_buddy_block_size(mm, block) - 1; - - if (!overlaps(start, end, block_start, block_end)) - continue; - - if (i915_buddy_block_is_allocated(block)) { - err = -ENOSPC; - goto err_free; - } - - if (contains(start, end, block_start, block_end)) { - if (!i915_buddy_block_is_free(block)) { - err = -ENOSPC; - goto err_free; - } - - mark_allocated(block); - list_add_tail(&block->link, &allocated); - continue; - } - - if (!i915_buddy_block_is_split(block)) { - err = split_block(mm, block); - if (unlikely(err)) - goto err_undo; - } - - list_add(&block->right->tmp_link, &dfs); - list_add(&block->left->tmp_link, &dfs); - } while (1); - - list_splice_tail(&allocated, blocks); - return 0; - -err_undo: - /* - * We really don't want to leave around a bunch of split blocks, since - * bigger is better, so make sure we merge everything back before we - * free the allocated blocks. - */ - buddy = get_buddy(block); - if (buddy && - (i915_buddy_block_is_free(block) && - i915_buddy_block_is_free(buddy))) - __i915_buddy_free(mm, block); - -err_free: - i915_buddy_free_list(mm, &allocated); - return err; -} - -#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) -#include "selftests/i915_buddy.c" -#endif diff --git a/drivers/gpu/drm/i915/i915_buddy.h b/drivers/gpu/drm/i915/i915_buddy.h deleted file mode 100644 index 9ce5200f4001..000000000000 --- a/drivers/gpu/drm/i915/i915_buddy.h +++ /dev/null @@ -1,131 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2019 Intel Corporation - */ - -#ifndef __I915_BUDDY_H__ -#define __I915_BUDDY_H__ - -#include <linux/bitops.h> -#include <linux/list.h> - -struct i915_buddy_block { -#define I915_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12) -#define I915_BUDDY_HEADER_STATE GENMASK_ULL(11, 10) -#define I915_BUDDY_ALLOCATED (1 << 10) -#define I915_BUDDY_FREE (2 << 10) -#define I915_BUDDY_SPLIT (3 << 10) -/* Free to be used, if needed in the future */ -#define I915_BUDDY_HEADER_UNUSED GENMASK_ULL(9, 6) -#define I915_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0) - u64 header; - - struct i915_buddy_block *left; - struct i915_buddy_block *right; - struct i915_buddy_block *parent; - - void *private; /* owned by creator */ - - /* - * While the block is allocated by the user through i915_buddy_alloc*, - * the user has ownership of the link, for example to maintain within - * a list, if so desired. As soon as the block is freed with - * i915_buddy_free* ownership is given back to the mm. - */ - struct list_head link; - struct list_head tmp_link; -}; - -/* Order-zero must be at least PAGE_SIZE */ -#define I915_BUDDY_MAX_ORDER (63 - PAGE_SHIFT) - -/* - * Binary Buddy System. - * - * Locking should be handled by the user, a simple mutex around - * i915_buddy_alloc* and i915_buddy_free* should suffice. - */ -struct i915_buddy_mm { - /* Maintain a free list for each order. */ - struct list_head *free_list; - - /* - * Maintain explicit binary tree(s) to track the allocation of the - * address space. This gives us a simple way of finding a buddy block - * and performing the potentially recursive merge step when freeing a - * block. Nodes are either allocated or free, in which case they will - * also exist on the respective free list. - */ - struct i915_buddy_block **roots; - - /* - * Anything from here is public, and remains static for the lifetime of - * the mm. Everything above is considered do-not-touch. - */ - unsigned int n_roots; - unsigned int max_order; - - /* Must be at least PAGE_SIZE */ - u64 chunk_size; - u64 size; -}; - -static inline u64 -i915_buddy_block_offset(struct i915_buddy_block *block) -{ - return block->header & I915_BUDDY_HEADER_OFFSET; -} - -static inline unsigned int -i915_buddy_block_order(struct i915_buddy_block *block) -{ - return block->header & I915_BUDDY_HEADER_ORDER; -} - -static inline unsigned int -i915_buddy_block_state(struct i915_buddy_block *block) -{ - return block->header & I915_BUDDY_HEADER_STATE; -} - -static inline bool -i915_buddy_block_is_allocated(struct i915_buddy_block *block) -{ - return i915_buddy_block_state(block) == I915_BUDDY_ALLOCATED; -} - -static inline bool -i915_buddy_block_is_free(struct i915_buddy_block *block) -{ - return i915_buddy_block_state(block) == I915_BUDDY_FREE; -} - -static inline bool -i915_buddy_block_is_split(struct i915_buddy_block *block) -{ - return i915_buddy_block_state(block) == I915_BUDDY_SPLIT; -} - -static inline u64 -i915_buddy_block_size(struct i915_buddy_mm *mm, - struct i915_buddy_block *block) -{ - return mm->chunk_size << i915_buddy_block_order(block); -} - -int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size); - -void i915_buddy_fini(struct i915_buddy_mm *mm); - -struct i915_buddy_block * -i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order); - -int i915_buddy_alloc_range(struct i915_buddy_mm *mm, - struct list_head *blocks, - u64 start, u64 size); - -void i915_buddy_free(struct i915_buddy_mm *mm, struct i915_buddy_block *block); - -void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects); - -#endif diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index d82a99e128cf..30c349137be2 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -84,6 +84,7 @@ #include "intel_gvt.h" #include "intel_memory_region.h" #include "intel_pm.h" +#include "intel_region_ttm.h" #include "intel_sideband.h" #include "vlv_suspend.h"

@@ -335,6 +336,10 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) if (ret < 0) goto err_workqueues;

+ ret = intel_region_ttm_device_init(dev_priv); + if (ret) + goto err_ttm; + intel_wopcm_init_early(&dev_priv->wopcm);

intel_gt_init_early(&dev_priv->gt, dev_priv); @@ -359,6 +364,8 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) err_gem: i915_gem_cleanup_early(dev_priv); intel_gt_driver_late_release(&dev_priv->gt); + intel_region_ttm_device_fini(dev_priv); +err_ttm: vlv_suspend_cleanup(dev_priv); err_workqueues: i915_workqueues_cleanup(dev_priv); @@ -376,6 +383,7 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv) intel_power_domains_cleanup(dev_priv); i915_gem_cleanup_early(dev_priv); intel_gt_driver_late_release(&dev_priv->gt); + intel_region_ttm_device_fini(dev_priv); vlv_suspend_cleanup(dev_priv); i915_workqueues_cleanup(dev_priv);

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 0f6d27da69ac..524aaeb0e842 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -59,6 +59,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_connector.h> #include <drm/i915_mei_hdcp_interface.h> +#include <drm/ttm/ttm_device.h>

#include "i915_params.h" #include "i915_reg.h" @@ -778,6 +779,7 @@ struct intel_cdclk_config {

struct i915_selftest_stash { atomic_t counter; + struct ida mock_region_instances; };

struct drm_i915_private { @@ -1170,6 +1172,9 @@ struct drm_i915_private { /* Mutex to protect the above hdcp component related values. */ struct mutex hdcp_comp_mutex;

+ /* The TTM device structure. */ + struct ttm_device bdev; + I915_SELFTEST_DECLARE(struct i915_selftest_stash selftest;)

/* @@ -1763,7 +1768,8 @@ void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv); void i915_gem_init_early(struct drm_i915_private *dev_priv); void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);

-struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915); +struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915, + u16 type, u16 instance);

static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915) { diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index cffd7f4f87dc..0993d706f067 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1108,6 +1108,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv) }

i915_gem_drain_freed_objects(dev_priv); + return ret; }

diff --git a/drivers/gpu/drm/i915/i915_globals.c b/drivers/gpu/drm/i915/i915_globals.c index 3aa213684293..77f1911c463b 100644 --- a/drivers/gpu/drm/i915/i915_globals.c +++ b/drivers/gpu/drm/i915/i915_globals.c @@ -87,7 +87,6 @@ static void __i915_globals_cleanup(void)

static __initconst int (* const initfn[])(void) = { i915_global_active_init, - i915_global_buddy_init, i915_global_context_init, i915_global_gem_context_init, i915_global_objects_init, diff --git a/drivers/gpu/drm/i915/i915_globals.h b/drivers/gpu/drm/i915/i915_globals.h index b2f5cd9b9b1a..2d199f411a4a 100644 --- a/drivers/gpu/drm/i915/i915_globals.h +++ b/drivers/gpu/drm/i915/i915_globals.h @@ -27,7 +27,6 @@ void i915_globals_exit(void);

/* constructors */ int i915_global_active_init(void); -int i915_global_buddy_init(void); int i915_global_context_init(void); int i915_global_gem_context_init(void); int i915_global_objects_init(void); diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c index cc6b3846a8c7..69e9e6c3135e 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.c +++ b/drivers/gpu/drm/i915/i915_scatterlist.c @@ -6,6 +6,10 @@

#include "i915_scatterlist.h"

+#include <drm/drm_mm.h> + +#include <linux/slab.h> + bool i915_sg_trim(struct sg_table *orig_st) { struct sg_table new_st; @@ -34,6 +38,72 @@ bool i915_sg_trim(struct sg_table *orig_st) return true; }

+/** + * i915_sg_from_mm_node - Create an sg_table from a struct drm_mm_node + * @node: The drm_mm_node. + * @region_start: An offset to add to the dma addresses of the sg list. + * + * Create a struct sg_table, initializing it from a struct drm_mm_node, + * taking a maximum segment length into account, splitting into segments + * if necessary. + * + * Return: A pointer to a kmalloced struct sg_table on success, negative + * error code cast to an error pointer on failure. + */ +struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node, + u64 region_start) +{ + const u64 max_segment = SZ_1G; /* Do we have a limit on this? */ + u64 segment_pages = max_segment >> PAGE_SHIFT; + u64 block_size, offset, prev_end; + struct sg_table *st; + struct scatterlist *sg; + + st = kmalloc(sizeof(*st), GFP_KERNEL); + if (!st) + return ERR_PTR(-ENOMEM); + + if (sg_alloc_table(st, DIV_ROUND_UP(node->size, segment_pages), + GFP_KERNEL)) { + kfree(st); + return ERR_PTR(-ENOMEM); + } + + sg = st->sgl; + st->nents = 0; + prev_end = (resource_size_t)-1; + block_size = node->size << PAGE_SHIFT; + offset = node->start << PAGE_SHIFT; + + while (block_size) { + u64 len; + + if (offset != prev_end || sg->length >= max_segment) { + if (st->nents) + sg = __sg_next(sg); + + sg_dma_address(sg) = region_start + offset; + sg_dma_len(sg) = 0; + sg->length = 0; + st->nents++; + } + + len = min(block_size, max_segment - sg->length); + sg->length += len; + sg_dma_len(sg) += len; + + offset += len; + block_size -= len; + + prev_end = offset; + } + + sg_mark_end(sg); + i915_sg_trim(st); + + return st; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/scatterlist.c" #endif diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h index b96baad66a3a..5acca45ea981 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.h +++ b/drivers/gpu/drm/i915/i915_scatterlist.h @@ -13,6 +13,8 @@

#include "i915_gem.h"

+struct drm_mm_node; + /* * Optimised SGL iterator for GEM objects */ @@ -141,4 +143,6 @@ static inline unsigned int i915_sg_segment_size(void)

bool i915_sg_trim(struct sg_table *orig_st);

+struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node, + u64 region_start); #endif diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index d98e8b81d322..4092cc987679 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -28,6 +28,11 @@ static const struct { }, };

+struct intel_region_reserve { + struct list_head link; + void *node; +}; + struct intel_memory_region * intel_memory_region_lookup(struct drm_i915_private *i915, u16 class, u16 instance) @@ -58,146 +63,61 @@ intel_memory_region_by_type(struct drm_i915_private *i915, return NULL; }

-static u64 -intel_memory_region_free_pages(struct intel_memory_region *mem, - struct list_head *blocks) +/** + * intel_memory_region_unreserve - Unreserve all previously reserved + * ranges + * @mem: The region containing the reserved ranges. + */ +void intel_memory_region_unreserve(struct intel_memory_region *mem) { - struct i915_buddy_block *block, *on; - u64 size = 0; + struct intel_region_reserve *reserve, *next;

- list_for_each_entry_safe(block, on, blocks, link) { - size += i915_buddy_block_size(&mem->mm, block); - i915_buddy_free(&mem->mm, block); - } - INIT_LIST_HEAD(blocks); + if (!mem->priv_ops || !mem->priv_ops->free) + return;

- return size; -} - -void -__intel_memory_region_put_pages_buddy(struct intel_memory_region *mem, - struct list_head *blocks) -{ mutex_lock(&mem->mm_lock); - mem->avail += intel_memory_region_free_pages(mem, blocks); - mutex_unlock(&mem->mm_lock); -} - -void -__intel_memory_region_put_block_buddy(struct i915_buddy_block *block) -{ - struct list_head blocks; - - INIT_LIST_HEAD(&blocks); - list_add(&block->link, &blocks); - __intel_memory_region_put_pages_buddy(block->private, &blocks); -} - -int -__intel_memory_region_get_pages_buddy(struct intel_memory_region *mem, - resource_size_t size, - unsigned int flags, - struct list_head *blocks) -{ - unsigned int min_order = 0; - unsigned long n_pages; - - GEM_BUG_ON(!IS_ALIGNED(size, mem->mm.chunk_size)); - GEM_BUG_ON(!list_empty(blocks)); - - if (flags & I915_ALLOC_MIN_PAGE_SIZE) { - min_order = ilog2(mem->min_page_size) - - ilog2(mem->mm.chunk_size); - } - - if (flags & I915_ALLOC_CONTIGUOUS) { - size = roundup_pow_of_two(size); - min_order = ilog2(size) - ilog2(mem->mm.chunk_size); + list_for_each_entry_safe(reserve, next, &mem->reserved, link) { + list_del(&reserve->link); + mem->priv_ops->free(mem, reserve->node); + kfree(reserve); } - - if (size > mem->mm.size) - return -E2BIG; - - n_pages = size >> ilog2(mem->mm.chunk_size); - - mutex_lock(&mem->mm_lock); - - do { - struct i915_buddy_block *block; - unsigned int order; - - order = fls(n_pages) - 1; - GEM_BUG_ON(order > mem->mm.max_order); - GEM_BUG_ON(order < min_order); - - do { - block = i915_buddy_alloc(&mem->mm, order); - if (!IS_ERR(block)) - break; - - if (order-- == min_order) - goto err_free_blocks; - } while (1); - - n_pages -= BIT(order); - - block->private = mem; - list_add_tail(&block->link, blocks); - - if (!n_pages) - break; - } while (1); - - mem->avail -= size; mutex_unlock(&mem->mm_lock); - return 0; - -err_free_blocks: - intel_memory_region_free_pages(mem, blocks); - mutex_unlock(&mem->mm_lock); - return -ENXIO; }

-struct i915_buddy_block * -__intel_memory_region_get_block_buddy(struct intel_memory_region *mem, - resource_size_t size, - unsigned int flags) +/** + * intel_memory_region_reserve - Reserve a memory range + * @mem: The region for which we want to reserve a range. + * @offset: Start of the range to reserve. + * @size: The size of the range to reserve. + * + * Return: 0 on success, negative error code on failure. + */ +int intel_memory_region_reserve(struct intel_memory_region *mem, + resource_size_t offset, + resource_size_t size) { - struct i915_buddy_block *block; - LIST_HEAD(blocks); int ret; + struct intel_region_reserve *reserve;

- ret = __intel_memory_region_get_pages_buddy(mem, size, flags, &blocks); - if (ret) - return ERR_PTR(ret); + if (!mem->priv_ops || !mem->priv_ops->reserve) + return -EINVAL;

- block = list_first_entry(&blocks, typeof(*block), link); - list_del_init(&block->link); - return block; -} + reserve = kzalloc(sizeof(*reserve), GFP_KERNEL); + if (!reserve) + return -ENOMEM;

-int intel_memory_region_init_buddy(struct intel_memory_region *mem) -{ - return i915_buddy_init(&mem->mm, resource_size(&mem->region), - PAGE_SIZE); -} - -void intel_memory_region_release_buddy(struct intel_memory_region *mem) -{ - i915_buddy_free_list(&mem->mm, &mem->reserved); - i915_buddy_fini(&mem->mm); -} - -int intel_memory_region_reserve(struct intel_memory_region *mem, - u64 offset, u64 size) -{ - int ret; + reserve->node = mem->priv_ops->reserve(mem, offset, size); + if (IS_ERR(reserve->node)) { + ret = PTR_ERR(reserve->node); + kfree(reserve); + return ret; + }

mutex_lock(&mem->mm_lock); - ret = i915_buddy_alloc_range(&mem->mm, &mem->reserved, offset, size); + list_add_tail(&reserve->link, &mem->reserved); mutex_unlock(&mem->mm_lock);

- return ret; + return 0; }

struct intel_memory_region * @@ -206,6 +126,8 @@ intel_memory_region_create(struct drm_i915_private *i915, resource_size_t size, resource_size_t min_page_size, resource_size_t io_start, + u16 type, + u16 instance, const struct intel_memory_region_ops *ops) { struct intel_memory_region *mem; @@ -222,6 +144,8 @@ intel_memory_region_create(struct drm_i915_private *i915, mem->ops = ops; mem->total = size; mem->avail = mem->total; + mem->type = type; + mem->instance = instance;

mutex_init(&mem->objects.lock); INIT_LIST_HEAD(&mem->objects.list); @@ -259,6 +183,7 @@ static void __intel_memory_region_destroy(struct kref *kref) struct intel_memory_region *mem = container_of(kref, typeof(*mem), kref);

+ intel_memory_region_unreserve(mem); if (mem->ops->release) mem->ops->release(mem);

@@ -296,15 +221,15 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915) instance = intel_region_map[i].instance; switch (type) { case INTEL_MEMORY_SYSTEM: - mem = i915_gem_shmem_setup(i915); + mem = i915_gem_shmem_setup(i915, type, instance); break; case INTEL_MEMORY_STOLEN_LOCAL: - mem = i915_gem_stolen_lmem_setup(i915); + mem = i915_gem_stolen_lmem_setup(i915, type, instance); if (!IS_ERR(mem)) i915->mm.stolen_region = mem; break; case INTEL_MEMORY_STOLEN_SYSTEM: - mem = i915_gem_stolen_smem_setup(i915); + mem = i915_gem_stolen_smem_setup(i915, type, instance); if (!IS_ERR(mem)) i915->mm.stolen_region = mem; break; @@ -321,9 +246,6 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915) }

mem->id = i; - mem->type = type; - mem->instance = instance; - i915->mm.regions[i] = mem; }

diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index d24ce5a0b30b..e69cde13daf2 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -13,8 +13,6 @@ #include <drm/drm_mm.h> #include <drm/i915_drm.h>

-#include "i915_buddy.h" - struct drm_i915_private; struct drm_i915_gem_object; struct intel_memory_region; @@ -25,6 +23,7 @@ enum intel_memory_type { INTEL_MEMORY_LOCAL = I915_MEMORY_CLASS_DEVICE, INTEL_MEMORY_STOLEN_SYSTEM, INTEL_MEMORY_STOLEN_LOCAL, + INTEL_MEMORY_MOCK, };

enum intel_region_id { @@ -59,10 +58,19 @@ struct intel_memory_region_ops { unsigned int flags); };

+struct intel_memory_region_private_ops { + void *(*reserve)(struct intel_memory_region *mem, + resource_size_t offset, + resource_size_t size); + void (*free)(struct intel_memory_region *mem, + void *node); +}; + struct intel_memory_region { struct drm_i915_private *i915;

const struct intel_memory_region_ops *ops; + const struct intel_memory_region_private_ops *priv_ops;

struct io_mapping iomap; struct resource region; @@ -70,7 +78,6 @@ struct intel_memory_region { /* For fake LMEM */ struct drm_mm_node fake_mappable;

- struct i915_buddy_mm mm; struct mutex mm_lock;

struct kref kref; @@ -95,36 +102,26 @@ struct intel_memory_region { struct list_head list; struct list_head purgeable; } objects; + + size_t chunk_size; + unsigned int max_order; + bool is_range_manager; + + void *region_private; };

struct intel_memory_region * intel_memory_region_lookup(struct drm_i915_private *i915, u16 class, u16 instance);

-int intel_memory_region_init_buddy(struct intel_memory_region *mem); -void intel_memory_region_release_buddy(struct intel_memory_region *mem); - -int __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem, - resource_size_t size, - unsigned int flags, - struct list_head *blocks); -struct i915_buddy_block * -__intel_memory_region_get_block_buddy(struct intel_memory_region *mem, - resource_size_t size, - unsigned int flags); -void __intel_memory_region_put_pages_buddy(struct intel_memory_region *mem, - struct list_head *blocks); -void __intel_memory_region_put_block_buddy(struct i915_buddy_block *block); - -int intel_memory_region_reserve(struct intel_memory_region *mem, - u64 offset, u64 size); - struct intel_memory_region * intel_memory_region_create(struct drm_i915_private *i915, resource_size_t start, resource_size_t size, resource_size_t min_page_size, resource_size_t io_start, + u16 type, + u16 instance, const struct intel_memory_region_ops *ops);

struct intel_memory_region * @@ -141,4 +138,9 @@ __printf(2, 3) void intel_memory_region_set_name(struct intel_memory_region *mem, const char *fmt, ...);

+void intel_memory_region_unreserve(struct intel_memory_region *mem); + +int intel_memory_region_reserve(struct intel_memory_region *mem, + resource_size_t offset, + resource_size_t size); #endif diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c new file mode 100644 index 000000000000..c8ac118c21f6 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_region_ttm.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ +#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_device.h> + +#include "i915_drv.h" +#include "i915_scatterlist.h" + +#include "intel_region_ttm.h" + +/** + * DOC: TTM support structure + * + * The code in this file deals with setting up memory managers for TTM + * LMEM and MOCK regions and converting the output from + * the managers to struct sg_table, Basically providing the mapping from + * i915 GEM regions to TTM memory types and resource managers. + */ + +/* A Zero-initialized driver for now. We don't have a TTM backend yet. */ +static struct ttm_device_funcs i915_ttm_bo_driver; + +/** + * intel_region_ttm_device_init - Initialize a TTM device + * @dev_priv: Pointer to an i915 device private structure. + * + * Return: 0 on success, negative error code on failure. + */ +int intel_region_ttm_device_init(struct drm_i915_private *dev_priv) +{ + struct drm_device *drm = &dev_priv->drm; + + return ttm_device_init(&dev_priv->bdev, &i915_ttm_bo_driver, + drm->dev, drm->anon_inode->i_mapping, + drm->vma_offset_manager, false, false); +} + +/** + * intel_region_ttm_device_fini - Finalize a TTM device + * @dev_priv: Pointer to an i915 device private structure. + */ +void intel_region_ttm_device_fini(struct drm_i915_private *dev_priv) +{ + ttm_device_fini(&dev_priv->bdev); +} + +/* + * Map the i915 memory regions to TTM memory types. We use the + * driver-private types for now, reserving TTM_PL_VRAM for stolen + * memory and TTM_PL_TT for GGTT use if decided to implement this. + */ +static int intel_region_to_ttm_type(struct intel_memory_region *mem) +{ + int type; + + GEM_BUG_ON(mem->type != INTEL_MEMORY_LOCAL && + mem->type != INTEL_MEMORY_MOCK); + + type = mem->instance + TTM_PL_PRIV; + GEM_BUG_ON(type >= TTM_NUM_MEM_TYPES); + + return type; +} + +static void *intel_region_ttm_node_reserve(struct intel_memory_region *mem, + resource_size_t offset, + resource_size_t size) +{ + struct ttm_resource_manager *man = mem->region_private; + struct ttm_place place = {}; + struct ttm_resource res = {}; + struct ttm_buffer_object mock_bo = {}; + int ret; + + /* + * Having to use a mock_bo is unfortunate but stems from some + * drivers having private managers that insist to know what the + * allocate memory is intended for, using it to send private + * data to the manager. Also recently the bo has been used to send + * alignment info to the manager. Assume that apart from the latter, + * none of the managers we use will ever access the buffer object + * members, hoping we can pass the alignment info in the + * struct ttm_place in the future. + */ + + place.fpfn = offset >> PAGE_SHIFT; + place.lpfn = place.fpfn + (size >> PAGE_SHIFT); + res.num_pages = size >> PAGE_SHIFT; + ret = man->func->alloc(man, &mock_bo, &place, &res); + if (ret == -ENOSPC) + ret = -ENXIO; + + return ret ? ERR_PTR(ret) : res.mm_node; +} + +/** + * intel_region_ttm_node_free - Free a node allocated from a resource manager + * @mem: The region the node was allocated from. + * @node: The opaque node representing an allocation. + */ +void intel_region_ttm_node_free(struct intel_memory_region *mem, + void *node) +{ + struct ttm_resource_manager *man = mem->region_private; + struct ttm_resource res = {}; + + res.mm_node = node; + man->func->free(man, &res); +} + +static const struct intel_memory_region_private_ops priv_ops = { + .reserve = intel_region_ttm_node_reserve, + .free = intel_region_ttm_node_free, +}; + +int intel_region_ttm_init(struct intel_memory_region *mem) +{ + struct ttm_device *bdev = &mem->i915->bdev; + int mem_type = intel_region_to_ttm_type(mem); + int ret; + + ret = ttm_range_man_init(bdev, mem_type, false, + resource_size(&mem->region) >> PAGE_SHIFT); + if (ret) + return ret; + + mem->chunk_size = PAGE_SIZE; + mem->max_order = + get_order(rounddown_pow_of_two(resource_size(&mem->region))); + mem->is_range_manager = true; + mem->priv_ops = &priv_ops; + mem->region_private = ttm_manager_type(bdev, mem_type); + + return 0; +} + +/** + * intel_region_ttm_fini - Finalize a TTM region. + * @mem: The memory region + * + * This functions takes down the TTM resource manager associated with the + * memory region, and if it was registered with the TTM device, + * removes that registration. + */ +void intel_region_ttm_fini(struct intel_memory_region *mem) +{ + int ret; + + ret = ttm_range_man_fini(&mem->i915->bdev, + intel_region_to_ttm_type(mem)); + GEM_WARN_ON(ret); + mem->region_private = NULL; +} + +/** + * intel_region_ttm_node_to_st - Convert an opaque TTM resource manager node + * to an sg_table. + * @mem: The memory region. + * @node: The resource manager node obtained from the TTM resource manager. + * + * The gem backends typically use sg-tables for operations on the underlying + * io_memory. So provide a way for the backends to translate the + * nodes they are handed from TTM to sg-tables. + * + * Return: A malloced sg_table on success, an error pointer on failure. + */ +struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem, + void *node) +{ + return i915_sg_from_mm_node(node, mem->region.start); +} + +/** + * intel_region_ttm_node_alloc - Allocate memory resources from a region + * @mem: The memory region, + * @size: The requested size in bytes + * @flags: Allocation flags + * + * This functionality is provided only for callers that need to allocate + * memory from standalone TTM range managers, without the TTM eviction + * functionality. Don't use if you are not completely sure that's the + * case. The returned opaque node can be converted to an sg_table using + * intel_region_ttm_node_to_st(), and can be freed using + * intel_region_ttm_node_free(). + * + * Return: A valid pointer on success, an error pointer on failure. + */ +void *intel_region_ttm_node_alloc(struct intel_memory_region *mem, + resource_size_t size, + unsigned int flags) +{ + struct ttm_resource_manager *man = mem->region_private; + struct ttm_place place = {}; + struct ttm_resource res = {}; + struct ttm_buffer_object mock_bo = {}; + int ret; + + /* + * We ignore the flags for now since we're using the range + * manager and contigous and min page size would be fulfilled + * by default if size is min page size aligned. + */ + res.num_pages = size >> PAGE_SHIFT; + + if (mem->is_range_manager) { + if (size >= SZ_1G) + mock_bo.page_alignment = SZ_1G >> PAGE_SHIFT; + else if (size >= SZ_2M) + mock_bo.page_alignment = SZ_2M >> PAGE_SHIFT; + else if (size >= SZ_64K) + mock_bo.page_alignment = SZ_64K >> PAGE_SHIFT; + } + + ret = man->func->alloc(man, &mock_bo, &place, &res); + if (ret == -ENOSPC) + ret = -ENXIO; + return ret ? ERR_PTR(ret) : res.mm_node; +} diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h new file mode 100644 index 000000000000..1c82c6c3429d --- /dev/null +++ b/drivers/gpu/drm/i915/intel_region_ttm.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ +#ifndef _INTEL_REGION_TTM_H_ +#define _INTEL_REGION_TTM_H_ + +#include <linux/types.h> + +#include "i915_selftest.h" + +struct drm_i915_private; +struct intel_memory_region; + +int intel_region_ttm_device_init(struct drm_i915_private *dev_priv); + +void intel_region_ttm_device_fini(struct drm_i915_private *dev_priv); + +int intel_region_ttm_init(struct intel_memory_region *mem); + +void intel_region_ttm_fini(struct intel_memory_region *mem); + +struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem, + void *node); + +void *intel_region_ttm_node_alloc(struct intel_memory_region *mem, + resource_size_t size, + unsigned int flags); + +void intel_region_ttm_node_free(struct intel_memory_region *mem, + void *node); +#endif /* _INTEL_REGION_TTM_H_ */ diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c deleted file mode 100644 index f0f5c4df8dbc..000000000000 --- a/drivers/gpu/drm/i915/selftests/i915_buddy.c +++ /dev/null @@ -1,789 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2019 Intel Corporation - */ - -#include <linux/prime_numbers.h> - -#include "../i915_selftest.h" -#include "i915_random.h" - -static void __igt_dump_block(struct i915_buddy_mm *mm, - struct i915_buddy_block *block, - bool buddy) -{ - pr_err("block info: header=%llx, state=%u, order=%d, offset=%llx size=%llx root=%s buddy=%s\n", - block->header, - i915_buddy_block_state(block), - i915_buddy_block_order(block), - i915_buddy_block_offset(block), - i915_buddy_block_size(mm, block), - yesno(!block->parent), - yesno(buddy)); -} - -static void igt_dump_block(struct i915_buddy_mm *mm, - struct i915_buddy_block *block) -{ - struct i915_buddy_block *buddy; - - __igt_dump_block(mm, block, false); - - buddy = get_buddy(block); - if (buddy) - __igt_dump_block(mm, buddy, true); -} - -static int igt_check_block(struct i915_buddy_mm *mm, - struct i915_buddy_block *block) -{ - struct i915_buddy_block *buddy; - unsigned int block_state; - u64 block_size; - u64 offset; - int err = 0; - - block_state = i915_buddy_block_state(block); - - if (block_state != I915_BUDDY_ALLOCATED && - block_state != I915_BUDDY_FREE && - block_state != I915_BUDDY_SPLIT) { - pr_err("block state mismatch\n"); - err = -EINVAL; - } - - block_size = i915_buddy_block_size(mm, block); - offset = i915_buddy_block_offset(block); - - if (block_size < mm->chunk_size) { - pr_err("block size smaller than min size\n"); - err = -EINVAL; - } - - if (!is_power_of_2(block_size)) { - pr_err("block size not power of two\n"); - err = -EINVAL; - } - - if (!IS_ALIGNED(block_size, mm->chunk_size)) { - pr_err("block size not aligned to min size\n"); - err = -EINVAL; - } - - if (!IS_ALIGNED(offset, mm->chunk_size)) { - pr_err("block offset not aligned to min size\n"); - err = -EINVAL; - } - - if (!IS_ALIGNED(offset, block_size)) { - pr_err("block offset not aligned to block size\n"); - err = -EINVAL; - } - - buddy = get_buddy(block); - - if (!buddy && block->parent) { - pr_err("buddy has gone fishing\n"); - err = -EINVAL; - } - - if (buddy) { - if (i915_buddy_block_offset(buddy) != (offset ^ block_size)) { - pr_err("buddy has wrong offset\n"); - err = -EINVAL; - } - - if (i915_buddy_block_size(mm, buddy) != block_size) { - pr_err("buddy size mismatch\n"); - err = -EINVAL; - } - - if (i915_buddy_block_state(buddy) == block_state && - block_state == I915_BUDDY_FREE) { - pr_err("block and its buddy are free\n"); - err = -EINVAL; - } - } - - return err; -} - -static int igt_check_blocks(struct i915_buddy_mm *mm, - struct list_head *blocks, - u64 expected_size, - bool is_contiguous) -{ - struct i915_buddy_block *block; - struct i915_buddy_block *prev; - u64 total; - int err = 0; - - block = NULL; - prev = NULL; - total = 0; - - list_for_each_entry(block, blocks, link) { - err = igt_check_block(mm, block); - - if (!i915_buddy_block_is_allocated(block)) { - pr_err("block not allocated\n"), - err = -EINVAL; - } - - if (is_contiguous && prev) { - u64 prev_block_size; - u64 prev_offset; - u64 offset; - - prev_offset = i915_buddy_block_offset(prev); - prev_block_size = i915_buddy_block_size(mm, prev); - offset = i915_buddy_block_offset(block); - - if (offset != (prev_offset + prev_block_size)) { - pr_err("block offset mismatch\n"); - err = -EINVAL; - } - } - - if (err) - break; - - total += i915_buddy_block_size(mm, block); - prev = block; - } - - if (!err) { - if (total != expected_size) { - pr_err("size mismatch, expected=%llx, found=%llx\n", - expected_size, total); - err = -EINVAL; - } - return err; - } - - if (prev) { - pr_err("prev block, dump:\n"); - igt_dump_block(mm, prev); - } - - if (block) { - pr_err("bad block, dump:\n"); - igt_dump_block(mm, block); - } - - return err; -} - -static int igt_check_mm(struct i915_buddy_mm *mm) -{ - struct i915_buddy_block *root; - struct i915_buddy_block *prev; - unsigned int i; - u64 total; - int err = 0; - - if (!mm->n_roots) { - pr_err("n_roots is zero\n"); - return -EINVAL; - } - - if (mm->n_roots != hweight64(mm->size)) { - pr_err("n_roots mismatch, n_roots=%u, expected=%lu\n", - mm->n_roots, hweight64(mm->size)); - return -EINVAL; - } - - root = NULL; - prev = NULL; - total = 0; - - for (i = 0; i < mm->n_roots; ++i) { - struct i915_buddy_block *block; - unsigned int order; - - root = mm->roots[i]; - if (!root) { - pr_err("root(%u) is NULL\n", i); - err = -EINVAL; - break; - } - - err = igt_check_block(mm, root); - - if (!i915_buddy_block_is_free(root)) { - pr_err("root not free\n"); - err = -EINVAL; - } - - order = i915_buddy_block_order(root); - - if (!i) { - if (order != mm->max_order) { - pr_err("max order root missing\n"); - err = -EINVAL; - } - } - - if (prev) { - u64 prev_block_size; - u64 prev_offset; - u64 offset; - - prev_offset = i915_buddy_block_offset(prev); - prev_block_size = i915_buddy_block_size(mm, prev); - offset = i915_buddy_block_offset(root); - - if (offset != (prev_offset + prev_block_size)) { - pr_err("root offset mismatch\n"); - err = -EINVAL; - } - } - - block = list_first_entry_or_null(&mm->free_list[order], - struct i915_buddy_block, - link); - if (block != root) { - pr_err("root mismatch at order=%u\n", order); - err = -EINVAL; - } - - if (err) - break; - - prev = root; - total += i915_buddy_block_size(mm, root); - } - - if (!err) { - if (total != mm->size) { - pr_err("expected mm size=%llx, found=%llx\n", mm->size, - total); - err = -EINVAL; - } - return err; - } - - if (prev) { - pr_err("prev root(%u), dump:\n", i - 1); - igt_dump_block(mm, prev); - } - - if (root) { - pr_err("bad root(%u), dump:\n", i); - igt_dump_block(mm, root); - } - - return err; -} - -static void igt_mm_config(u64 *size, u64 *chunk_size) -{ - I915_RND_STATE(prng); - u32 s, ms; - - /* Nothing fancy, just try to get an interesting bit pattern */ - - prandom_seed_state(&prng, i915_selftest.random_seed); - - /* Let size be a random number of pages up to 8 GB (2M pages) */ - s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng); - /* Let the chunk size be a random power of 2 less than size */ - ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng)); - /* Round size down to the chunk size */ - s &= -ms; - - /* Convert from pages to bytes */ - *chunk_size = (u64)ms << 12; - *size = (u64)s << 12; -} - -static int igt_buddy_alloc_smoke(void *arg) -{ - struct i915_buddy_mm mm; - IGT_TIMEOUT(end_time); - I915_RND_STATE(prng); - u64 chunk_size; - u64 mm_size; - int *order; - int err, i; - - igt_mm_config(&mm_size, &chunk_size); - - pr_info("buddy_init with size=%llx, chunk_size=%llx\n", mm_size, chunk_size); - - err = i915_buddy_init(&mm, mm_size, chunk_size); - if (err) { - pr_err("buddy_init failed(%d)\n", err); - return err; - } - - order = i915_random_order(mm.max_order + 1, &prng); - if (!order) - goto out_fini; - - for (i = 0; i <= mm.max_order; ++i) { - struct i915_buddy_block *block; - int max_order = order[i]; - bool timeout = false; - LIST_HEAD(blocks); - int order; - u64 total; - - err = igt_check_mm(&mm); - if (err) { - pr_err("pre-mm check failed, abort\n"); - break; - } - - pr_info("filling from max_order=%u\n", max_order); - - order = max_order; - total = 0; - - do { -retry: - block = i915_buddy_alloc(&mm, order); - if (IS_ERR(block)) { - err = PTR_ERR(block); - if (err == -ENOMEM) { - pr_info("buddy_alloc hit -ENOMEM with order=%d\n", - order); - } else { - if (order--) { - err = 0; - goto retry; - } - - pr_err("buddy_alloc with order=%d failed(%d)\n", - order, err); - } - - break; - } - - list_add_tail(&block->link, &blocks); - - if (i915_buddy_block_order(block) != order) { - pr_err("buddy_alloc order mismatch\n"); - err = -EINVAL; - break; - } - - total += i915_buddy_block_size(&mm, block); - - if (__igt_timeout(end_time, NULL)) { - timeout = true; - break; - } - } while (total < mm.size); - - if (!err) - err = igt_check_blocks(&mm, &blocks, total, false); - - i915_buddy_free_list(&mm, &blocks); - - if (!err) { - err = igt_check_mm(&mm); - if (err) - pr_err("post-mm check failed\n"); - } - - if (err || timeout) - break; - - cond_resched(); - } - - if (err == -ENOMEM) - err = 0; - - kfree(order); -out_fini: - i915_buddy_fini(&mm); - - return err; -} - -static int igt_buddy_alloc_pessimistic(void *arg) -{ - const unsigned int max_order = 16; - struct i915_buddy_block *block, *bn; - struct i915_buddy_mm mm; - unsigned int order; - LIST_HEAD(blocks); - int err; - - /* - * Create a pot-sized mm, then allocate one of each possible - * order within. This should leave the mm with exactly one - * page left. - */ - - err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE); - if (err) { - pr_err("buddy_init failed(%d)\n", err); - return err; - } - GEM_BUG_ON(mm.max_order != max_order); - - for (order = 0; order < max_order; order++) { - block = i915_buddy_alloc(&mm, order); - if (IS_ERR(block)) { - pr_info("buddy_alloc hit -ENOMEM with order=%d\n", - order); - err = PTR_ERR(block); - goto err; - } - - list_add_tail(&block->link, &blocks); - } - - /* And now the last remaining block available */ - block = i915_buddy_alloc(&mm, 0); - if (IS_ERR(block)) { - pr_info("buddy_alloc hit -ENOMEM on final alloc\n"); - err = PTR_ERR(block); - goto err; - } - list_add_tail(&block->link, &blocks); - - /* Should be completely full! */ - for (order = max_order; order--; ) { - block = i915_buddy_alloc(&mm, order); - if (!IS_ERR(block)) { - pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!", - order); - list_add_tail(&block->link, &blocks); - err = -EINVAL; - goto err; - } - } - - block = list_last_entry(&blocks, typeof(*block), link); - list_del(&block->link); - i915_buddy_free(&mm, block); - - /* As we free in increasing size, we make available larger blocks */ - order = 1; - list_for_each_entry_safe(block, bn, &blocks, link) { - list_del(&block->link); - i915_buddy_free(&mm, block); - - block = i915_buddy_alloc(&mm, order); - if (IS_ERR(block)) { - pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n", - order); - err = PTR_ERR(block); - goto err; - } - i915_buddy_free(&mm, block); - order++; - } - - /* To confirm, now the whole mm should be available */ - block = i915_buddy_alloc(&mm, max_order); - if (IS_ERR(block)) { - pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n", - max_order); - err = PTR_ERR(block); - goto err; - } - i915_buddy_free(&mm, block); - -err: - i915_buddy_free_list(&mm, &blocks); - i915_buddy_fini(&mm); - return err; -} - -static int igt_buddy_alloc_optimistic(void *arg) -{ - const int max_order = 16; - struct i915_buddy_block *block; - struct i915_buddy_mm mm; - LIST_HEAD(blocks); - int order; - int err; - - /* - * Create a mm with one block of each order available, and - * try to allocate them all. - */ - - err = i915_buddy_init(&mm, - PAGE_SIZE * ((1 << (max_order + 1)) - 1), - PAGE_SIZE); - if (err) { - pr_err("buddy_init failed(%d)\n", err); - return err; - } - GEM_BUG_ON(mm.max_order != max_order); - - for (order = 0; order <= max_order; order++) { - block = i915_buddy_alloc(&mm, order); - if (IS_ERR(block)) { - pr_info("buddy_alloc hit -ENOMEM with order=%d\n", - order); - err = PTR_ERR(block); - goto err; - } - - list_add_tail(&block->link, &blocks); - } - - /* Should be completely full! */ - block = i915_buddy_alloc(&mm, 0); - if (!IS_ERR(block)) { - pr_info("buddy_alloc unexpectedly succeeded, it should be full!"); - list_add_tail(&block->link, &blocks); - err = -EINVAL; - goto err; - } - -err: - i915_buddy_free_list(&mm, &blocks); - i915_buddy_fini(&mm); - return err; -} - -static int igt_buddy_alloc_pathological(void *arg) -{ - const int max_order = 16; - struct i915_buddy_block *block; - struct i915_buddy_mm mm; - LIST_HEAD(blocks); - LIST_HEAD(holes); - int order, top; - int err; - - /* - * Create a pot-sized mm, then allocate one of each possible - * order within. This should leave the mm with exactly one - * page left. Free the largest block, then whittle down again. - * Eventually we will have a fully 50% fragmented mm. - */ - - err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE); - if (err) { - pr_err("buddy_init failed(%d)\n", err); - return err; - } - GEM_BUG_ON(mm.max_order != max_order); - - for (top = max_order; top; top--) { - /* Make room by freeing the largest allocated block */ - block = list_first_entry_or_null(&blocks, typeof(*block), link); - if (block) { - list_del(&block->link); - i915_buddy_free(&mm, block); - } - - for (order = top; order--; ) { - block = i915_buddy_alloc(&mm, order); - if (IS_ERR(block)) { - pr_info("buddy_alloc hit -ENOMEM with order=%d, top=%d\n", - order, top); - err = PTR_ERR(block); - goto err; - } - list_add_tail(&block->link, &blocks); - } - - /* There should be one final page for this sub-allocation */ - block = i915_buddy_alloc(&mm, 0); - if (IS_ERR(block)) { - pr_info("buddy_alloc hit -ENOMEM for hole\n"); - err = PTR_ERR(block); - goto err; - } - list_add_tail(&block->link, &holes); - - block = i915_buddy_alloc(&mm, top); - if (!IS_ERR(block)) { - pr_info("buddy_alloc unexpectedly succeeded at top-order %d/%d, it should be full!", - top, max_order); - list_add_tail(&block->link, &blocks); - err = -EINVAL; - goto err; - } - } - - i915_buddy_free_list(&mm, &holes); - - /* Nothing larger than blocks of chunk_size now available */ - for (order = 1; order <= max_order; order++) { - block = i915_buddy_alloc(&mm, order); - if (!IS_ERR(block)) { - pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!", - order); - list_add_tail(&block->link, &blocks); - err = -EINVAL; - goto err; - } - } - -err: - list_splice_tail(&holes, &blocks); - i915_buddy_free_list(&mm, &blocks); - i915_buddy_fini(&mm); - return err; -} - -static int igt_buddy_alloc_range(void *arg) -{ - struct i915_buddy_mm mm; - unsigned long page_num; - LIST_HEAD(blocks); - u64 chunk_size; - u64 offset; - u64 size; - u64 rem; - int err; - - igt_mm_config(&size, &chunk_size); - - pr_info("buddy_init with size=%llx, chunk_size=%llx\n", size, chunk_size); - - err = i915_buddy_init(&mm, size, chunk_size); - if (err) { - pr_err("buddy_init failed(%d)\n", err); - return err; - } - - err = igt_check_mm(&mm); - if (err) { - pr_err("pre-mm check failed, abort, abort, abort!\n"); - goto err_fini; - } - - rem = mm.size; - offset = 0; - - for_each_prime_number_from(page_num, 1, ULONG_MAX - 1) { - struct i915_buddy_block *block; - LIST_HEAD(tmp); - - size = min(page_num * mm.chunk_size, rem); - - err = i915_buddy_alloc_range(&mm, &tmp, offset, size); - if (err) { - if (err == -ENOMEM) { - pr_info("alloc_range hit -ENOMEM with size=%llx\n", - size); - } else { - pr_err("alloc_range with offset=%llx, size=%llx failed(%d)\n", - offset, size, err); - } - - break; - } - - block = list_first_entry_or_null(&tmp, - struct i915_buddy_block, - link); - if (!block) { - pr_err("alloc_range has no blocks\n"); - err = -EINVAL; - break; - } - - if (i915_buddy_block_offset(block) != offset) { - pr_err("alloc_range start offset mismatch, found=%llx, expected=%llx\n", - i915_buddy_block_offset(block), offset); - err = -EINVAL; - } - - if (!err) - err = igt_check_blocks(&mm, &tmp, size, true); - - list_splice_tail(&tmp, &blocks); - - if (err) - break; - - offset += size; - - rem -= size; - if (!rem) - break; - - cond_resched(); - } - - if (err == -ENOMEM) - err = 0; - - i915_buddy_free_list(&mm, &blocks); - - if (!err) { - err = igt_check_mm(&mm); - if (err) - pr_err("post-mm check failed\n"); - } - -err_fini: - i915_buddy_fini(&mm); - - return err; -} - -static int igt_buddy_alloc_limit(void *arg) -{ - struct i915_buddy_block *block; - struct i915_buddy_mm mm; - const u64 size = U64_MAX; - int err; - - err = i915_buddy_init(&mm, size, PAGE_SIZE); - if (err) - return err; - - if (mm.max_order != I915_BUDDY_MAX_ORDER) { - pr_err("mm.max_order(%d) != %d\n", - mm.max_order, I915_BUDDY_MAX_ORDER); - err = -EINVAL; - goto out_fini; - } - - block = i915_buddy_alloc(&mm, mm.max_order); - if (IS_ERR(block)) { - err = PTR_ERR(block); - goto out_fini; - } - - if (i915_buddy_block_order(block) != mm.max_order) { - pr_err("block order(%d) != %d\n", - i915_buddy_block_order(block), mm.max_order); - err = -EINVAL; - goto out_free; - } - - if (i915_buddy_block_size(&mm, block) != - BIT_ULL(mm.max_order) * PAGE_SIZE) { - pr_err("block size(%llu) != %llu\n", - i915_buddy_block_size(&mm, block), - BIT_ULL(mm.max_order) * PAGE_SIZE); - err = -EINVAL; - goto out_free; - } - -out_free: - i915_buddy_free(&mm, block); -out_fini: - i915_buddy_fini(&mm); - return err; -} - -int i915_buddy_mock_selftests(void) -{ - static const struct i915_subtest tests[] = { - SUBTEST(igt_buddy_alloc_pessimistic), - SUBTEST(igt_buddy_alloc_optimistic), - SUBTEST(igt_buddy_alloc_pathological), - SUBTEST(igt_buddy_alloc_smoke), - SUBTEST(igt_buddy_alloc_range), - SUBTEST(igt_buddy_alloc_limit), - }; - - return i915_subtests(tests, NULL); -} diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h index 3db34d3eea58..34e5caf38093 100644 --- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h +++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h @@ -33,5 +33,4 @@ selftest(evict, i915_gem_evict_mock_selftests) selftest(gtt, i915_gem_gtt_mock_selftests) selftest(hugepages, i915_gem_huge_page_mock_selftests) selftest(contexts, i915_gem_context_mock_selftests) -selftest(buddy, i915_buddy_mock_selftests) selftest(memory_region, intel_memory_region_mock_selftests) diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index f85fd8cbfbf5..c85d516b85cd 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -57,9 +57,10 @@ static int igt_mock_fill(void *arg) LIST_HEAD(objects); int err = 0;

- page_size = mem->mm.chunk_size; - max_pages = div64_u64(total, page_size); + page_size = mem->chunk_size; rem = total; +retry: + max_pages = div64_u64(rem, page_size);

for_each_prime_number_from(page_num, 1, max_pages) { resource_size_t size = page_num * page_size; @@ -85,6 +86,11 @@ static int igt_mock_fill(void *arg) err = 0; if (err == -ENXIO) { if (page_num * page_size <= rem) { + if (mem->is_range_manager && max_pages > 1) { + max_pages >>= 1; + goto retry; + } + pr_err("%s failed, space still left in region\n", __func__); err = -EINVAL; @@ -199,12 +205,18 @@ static int igt_mock_reserve(void *arg) do { u32 size = i915_prandom_u32_max_state(cur_avail, &prng);

+retry: size = max_t(u32, round_up(size, PAGE_SIZE), PAGE_SIZE); obj = igt_object_create(mem, &objects, size, 0); if (IS_ERR(obj)) { - if (PTR_ERR(obj) == -ENXIO) + if (PTR_ERR(obj) == -ENXIO) { + if (mem->is_range_manager && + size > mem->chunk_size) { + size >>= 1; + goto retry; + } break; - + } err = PTR_ERR(obj); goto out_close; } @@ -220,7 +232,7 @@ static int igt_mock_reserve(void *arg) out_close: kfree(order); close_objects(mem, &objects); - i915_buddy_free_list(&mem->mm, &mem->reserved); + intel_memory_region_unreserve(mem); return err; }

@@ -240,7 +252,7 @@ static int igt_mock_contiguous(void *arg) total = resource_size(&mem->region);

/* Min size */ - obj = igt_object_create(mem, &objects, mem->mm.chunk_size, + obj = igt_object_create(mem, &objects, mem->chunk_size, I915_BO_ALLOC_CONTIGUOUS); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -321,14 +333,16 @@ static int igt_mock_contiguous(void *arg) min = target; target = total >> 1;

- /* Make sure we can still allocate all the fragmented space */ - obj = igt_object_create(mem, &objects, target, 0); - if (IS_ERR(obj)) { - err = PTR_ERR(obj); - goto err_close_objects; - } + if (!mem->is_range_manager) { + /* Make sure we can still allocate all the fragmented space */ + obj = igt_object_create(mem, &objects, target, 0); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto err_close_objects; + }

- igt_object_release(obj); + igt_object_release(obj); + }

/* * Even though we have enough free space, we don't have a big enough @@ -348,7 +362,7 @@ static int igt_mock_contiguous(void *arg) }

target >>= 1; - } while (target >= mem->mm.chunk_size); + } while (target >= mem->chunk_size);

err_close_objects: list_splice_tail(&holes, &objects); @@ -368,7 +382,7 @@ static int igt_mock_splintered_region(void *arg)

/* * Sanity check we can still allocate everything even if the - * mm.max_order != mm.size. i.e our starting address space size is not a + * max_order != mm.size. i.e our starting address space size is not a * power-of-two. */

@@ -377,17 +391,10 @@ static int igt_mock_splintered_region(void *arg) if (IS_ERR(mem)) return PTR_ERR(mem);

- if (mem->mm.size != size) { - pr_err("%s size mismatch(%llu != %llu)\n", - __func__, mem->mm.size, size); - err = -EINVAL; - goto out_put; - } - expected_order = get_order(rounddown_pow_of_two(size)); - if (mem->mm.max_order != expected_order) { + if (mem->max_order != expected_order) { pr_err("%s order mismatch(%u != %u)\n", - __func__, mem->mm.max_order, expected_order); + __func__, mem->max_order, expected_order); err = -EINVAL; goto out_put; } @@ -408,12 +415,15 @@ static int igt_mock_splintered_region(void *arg) * sure that does indeed hold true. */

- obj = igt_object_create(mem, &objects, size, I915_BO_ALLOC_CONTIGUOUS); - if (!IS_ERR(obj)) { - pr_err("%s too large contiguous allocation was not rejected\n", - __func__); - err = -EINVAL; - goto out_close; + if (!mem->is_range_manager) { + obj = igt_object_create(mem, &objects, size, + I915_BO_ALLOC_CONTIGUOUS); + if (!IS_ERR(obj)) { + pr_err("%s too large contiguous allocation was not rejected\n", + __func__); + err = -EINVAL; + goto out_close; + } }

obj = igt_object_create(mem, &objects, rounddown_pow_of_two(size), @@ -432,68 +442,6 @@ static int igt_mock_splintered_region(void *arg) return err; }

-#ifndef SZ_8G -#define SZ_8G BIT_ULL(33) -#endif - -static int igt_mock_max_segment(void *arg) -{ - const unsigned int max_segment = i915_sg_segment_size(); - struct intel_memory_region *mem = arg; - struct drm_i915_private *i915 = mem->i915; - struct drm_i915_gem_object *obj; - struct i915_buddy_block *block; - struct scatterlist *sg; - LIST_HEAD(objects); - u64 size; - int err = 0; - - /* - * While we may create very large contiguous blocks, we may need - * to break those down for consumption elsewhere. In particular, - * dma-mapping with scatterlist elements have an implicit limit of - * UINT_MAX on each element. - */ - - size = SZ_8G; - mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0); - if (IS_ERR(mem)) - return PTR_ERR(mem); - - obj = igt_object_create(mem, &objects, size, 0); - if (IS_ERR(obj)) { - err = PTR_ERR(obj); - goto out_put; - } - - size = 0; - list_for_each_entry(block, &obj->mm.blocks, link) { - if (i915_buddy_block_size(&mem->mm, block) > size) - size = i915_buddy_block_size(&mem->mm, block); - } - if (size < max_segment) { - pr_err("%s: Failed to create a huge contiguous block [> %u], largest block %lld\n", - __func__, max_segment, size); - err = -EINVAL; - goto out_close; - } - - for (sg = obj->mm.pages->sgl; sg; sg = sg_next(sg)) { - if (sg->length > max_segment) { - pr_err("%s: Created an oversized scatterlist entry, %u > %u\n", - __func__, sg->length, max_segment); - err = -EINVAL; - goto out_close; - } - } - -out_close: - close_objects(mem, &objects); -out_put: - intel_memory_region_put(mem); - return err; -} - static int igt_gpu_write_dw(struct intel_context *ce, struct i915_vma *vma, u32 dword, @@ -1098,7 +1046,6 @@ int intel_memory_region_mock_selftests(void) SUBTEST(igt_mock_fill), SUBTEST(igt_mock_contiguous), SUBTEST(igt_mock_splintered_region), - SUBTEST(igt_mock_max_segment), }; struct intel_memory_region *mem; struct drm_i915_private *i915; diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index cf40004bc92a..d189c4bd4bef 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -32,6 +32,7 @@ #include "gt/intel_gt_requests.h" #include "gt/mock_engine.h" #include "intel_memory_region.h" +#include "intel_region_ttm.h"

#include "mock_request.h" #include "mock_gem_device.h" @@ -70,6 +71,7 @@ static void mock_device_release(struct drm_device *dev) mock_fini_ggtt(&i915->ggtt); destroy_workqueue(i915->wq);

+ intel_region_ttm_device_fini(i915); intel_gt_driver_late_release(&i915->gt); intel_memory_regions_driver_release(i915);

@@ -116,6 +118,7 @@ struct drm_i915_private *mock_gem_device(void) #endif struct drm_i915_private *i915; struct pci_dev *pdev; + int ret;

pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); if (!pdev) @@ -178,6 +181,10 @@ struct drm_i915_private *mock_gem_device(void) atomic_inc(&i915->gt.wakeref.count); /* disable; no hw support */ i915->gt.awake = -ENODEV;

+ ret = intel_region_ttm_device_init(i915); + if (ret) + goto err_ttm; + i915->wq = alloc_ordered_workqueue("mock", 0); if (!i915->wq) goto err_drv; @@ -201,6 +208,7 @@ struct drm_i915_private *mock_gem_device(void) intel_engines_driver_register(i915);

i915->do_release = true; + ida_init(&i915->selftest.mock_region_instances);

return i915;

@@ -209,6 +217,8 @@ struct drm_i915_private *mock_gem_device(void) err_unlock: destroy_workqueue(i915->wq); err_drv: + intel_region_ttm_device_fini(i915); +err_ttm: intel_gt_driver_late_release(&i915->gt); intel_memory_regions_driver_release(i915); drm_mode_config_cleanup(&i915->drm); diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index 5d2d010a1e22..eafc5a04975c 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -1,17 +1,56 @@ // SPDX-License-Identifier: MIT /* - * Copyright © 2019 Intel Corporation + * Copyright © 2019-2021 Intel Corporation */

+#include <linux/scatterlist.h> + +#include <drm/ttm/ttm_placement.h> + #include "gem/i915_gem_region.h" #include "intel_memory_region.h" +#include "intel_region_ttm.h"

#include "mock_region.h"

+static void mock_region_put_pages(struct drm_i915_gem_object *obj, + struct sg_table *pages) +{ + intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node); + sg_free_table(pages); + kfree(pages); +} + +static int mock_region_get_pages(struct drm_i915_gem_object *obj) +{ + unsigned int flags; + struct sg_table *pages; + + flags = I915_ALLOC_MIN_PAGE_SIZE; + if (obj->flags & I915_BO_ALLOC_CONTIGUOUS) + flags |= I915_ALLOC_CONTIGUOUS; + + obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region, + obj->base.size, + flags); + if (IS_ERR(obj->mm.st_mm_node)) + return PTR_ERR(obj->mm.st_mm_node); + + pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node); + if (IS_ERR(pages)) { + intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node); + return PTR_ERR(pages); + } + + __i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl)); + + return 0; +} + static const struct drm_i915_gem_object_ops mock_region_obj_ops = { .name = "mock-region", - .get_pages = i915_gem_object_get_pages_buddy, - .put_pages = i915_gem_object_put_pages_buddy, + .get_pages = mock_region_get_pages, + .put_pages = mock_region_put_pages, .release = i915_gem_object_release_memory_region, };

@@ -23,7 +62,7 @@ static int mock_object_init(struct intel_memory_region *mem, static struct lock_class_key lock_class; struct drm_i915_private *i915 = mem->i915;

- if (size > mem->mm.size) + if (size > resource_size(&mem->region)) return -E2BIG;

drm_gem_private_object_init(&i915->drm, &obj->base, size); @@ -38,9 +77,18 @@ static int mock_object_init(struct intel_memory_region *mem, return 0; }

+static void mock_region_fini(struct intel_memory_region *mem) +{ + struct drm_i915_private *i915 = mem->i915; + int instance = mem->instance; + + intel_region_ttm_fini(mem); + ida_free(&i915->selftest.mock_region_instances, instance); +} + static const struct intel_memory_region_ops mock_region_ops = { - .init = intel_memory_region_init_buddy, - .release = intel_memory_region_release_buddy, + .init = intel_region_ttm_init, + .release = mock_region_fini, .init_object = mock_object_init, };

@@ -51,6 +99,14 @@ mock_region_create(struct drm_i915_private *i915, resource_size_t min_page_size, resource_size_t io_start) { + int instance = ida_alloc_max(&i915->selftest.mock_region_instances, + TTM_NUM_MEM_TYPES - TTM_PL_PRIV - 1, + GFP_KERNEL); + + if (instance < 0) + return ERR_PTR(instance); + return intel_memory_region_create(i915, start, size, min_page_size, - io_start, &mock_region_ops); + io_start, INTEL_MEMORY_MOCK, instance, + &mock_region_ops); }

The internal ttm_bo_util memcpy uses ioremap functionality, and while it probably might be possible to use it for copying in- and out of sglist represented io memory, using io_mem_reserve() / io_mem_free() callbacks, that would cause problems with fault(). Instead, implement a method mapping page-by-page using kmap_local() semantics. As an additional benefit we then avoid the occasional global TLB flushes of ioremap() and consuming ioremap space, elimination of a critical point of failure and with a slight change of semantics we could also push the memcpy out async for testing and async driver development purposes.

A special linear iomem iterator is introduced internally to mimic the old ioremap behaviour for code-paths that can't immediately be ported over. This adds to the code size and should be considered a temporary solution.

Looking at the code we have a lot of checks for iomap tagged pointers. Ideally we should extend the core memremap functions to also accept uncached memory and kmap_local functionality. Then we could strip a lot of code.

Cc: Christian König christian.koenig@amd.com Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Reviewed-by: Christian König christian.koenig@amd.com --- v3: - Split up in various TTM files and addressed review comments by Christian König. Tested and fixed legacy iomap memcpy path on i915. v4: - Fix an uninitialized variable Reported by: kernel test robot lkp@intel.com Reported by: Dan Carpenter dan.carpenter@oracle.com - Minor change to the ttm_move_memcpy() interface. - Gracefully handle lack of memremap() support on memcpy (Reported by Matthew Auld) - Minor style fix (Reported by Matthew Auld) v8: - Change num_pages from pgoff_t to uint32_t (Suggested by Christian König) v9: - Fix a NULL pointer deref in ttm_kmap_iter_tt_init if tt is NULL. --- drivers/gpu/drm/ttm/ttm_bo_util.c | 280 ++++++++++------------------- drivers/gpu/drm/ttm/ttm_module.c | 35 ++++ drivers/gpu/drm/ttm/ttm_resource.c | 193 ++++++++++++++++++++ drivers/gpu/drm/ttm/ttm_tt.c | 45 +++++ include/drm/ttm/ttm_bo_driver.h | 28 +++ include/drm/ttm/ttm_caching.h | 2 + include/drm/ttm/ttm_kmap_iter.h | 61 +++++++ include/drm/ttm/ttm_resource.h | 61 +++++++ include/drm/ttm/ttm_tt.h | 16 ++ 9 files changed, 539 insertions(+), 182 deletions(-) create mode 100644 include/drm/ttm/ttm_kmap_iter.h

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index ae8b61460724..a800998a12b0 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -72,190 +72,126 @@ void ttm_mem_io_free(struct ttm_device *bdev, mem->bus.addr = NULL; }

-static int ttm_resource_ioremap(struct ttm_device *bdev, - struct ttm_resource *mem, - void **virtual) +/** + * ttm_move_memcpy - Helper to perform a memcpy ttm move operation. + * @bo: The struct ttm_buffer_object. + * @new_mem: The struct ttm_resource we're moving to (copy destination). + * @new_iter: A struct ttm_kmap_iter representing the destination resource. + * @src_iter: A struct ttm_kmap_iter representing the source resource. + * + * This function is intended to be able to move out async under a + * dma-fence if desired. + */ +void ttm_move_memcpy(struct ttm_buffer_object *bo, + u32 num_pages, + struct ttm_kmap_iter *dst_iter, + struct ttm_kmap_iter *src_iter) { - int ret; - void *addr; - - *virtual = NULL; - ret = ttm_mem_io_reserve(bdev, mem); - if (ret || !mem->bus.is_iomem) - return ret; + const struct ttm_kmap_iter_ops *dst_ops = dst_iter->ops; + const struct ttm_kmap_iter_ops *src_ops = src_iter->ops; + struct ttm_tt *ttm = bo->ttm; + struct dma_buf_map src_map, dst_map; + pgoff_t i;

- if (mem->bus.addr) { - addr = mem->bus.addr; - } else { - size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT; + /* Single TTM move. NOP */ + if (dst_ops->maps_tt && src_ops->maps_tt) + return;

- if (mem->bus.caching == ttm_write_combined) - addr = ioremap_wc(mem->bus.offset, bus_size); -#ifdef CONFIG_X86 - else if (mem->bus.caching == ttm_cached) - addr = ioremap_cache(mem->bus.offset, bus_size); -#endif - else - addr = ioremap(mem->bus.offset, bus_size); - if (!addr) { - ttm_mem_io_free(bdev, mem); - return -ENOMEM; + /* Don't move nonexistent data. Clear destination instead. */ + if (src_ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm))) { + if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)) + return; + + for (i = 0; i < num_pages; ++i) { + dst_ops->map_local(dst_iter, &dst_map, i); + if (dst_map.is_iomem) + memset_io(dst_map.vaddr_iomem, 0, PAGE_SIZE); + else + memset(dst_map.vaddr, 0, PAGE_SIZE); + if (dst_ops->unmap_local) + dst_ops->unmap_local(dst_iter, &dst_map); } + return; } - *virtual = addr; - return 0; -} - -static void ttm_resource_iounmap(struct ttm_device *bdev, - struct ttm_resource *mem, - void *virtual) -{ - if (virtual && mem->bus.addr == NULL) - iounmap(virtual); - ttm_mem_io_free(bdev, mem); -} - -static int ttm_copy_io_page(void *dst, void *src, unsigned long page) -{ - uint32_t *dstP = - (uint32_t *) ((unsigned long)dst + (page << PAGE_SHIFT)); - uint32_t *srcP = - (uint32_t *) ((unsigned long)src + (page << PAGE_SHIFT)); - - int i; - for (i = 0; i < PAGE_SIZE / sizeof(uint32_t); ++i) - iowrite32(ioread32(srcP++), dstP++); - return 0; -} - -static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src, - unsigned long page, - pgprot_t prot) -{ - struct page *d = ttm->pages[page]; - void *dst; - - if (!d) - return -ENOMEM; - - src = (void *)((unsigned long)src + (page << PAGE_SHIFT)); - dst = kmap_atomic_prot(d, prot); - if (!dst) - return -ENOMEM; - - memcpy_fromio(dst, src, PAGE_SIZE); - - kunmap_atomic(dst); - - return 0; -} - -static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst, - unsigned long page, - pgprot_t prot) -{ - struct page *s = ttm->pages[page]; - void *src;

- if (!s) - return -ENOMEM; - - dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT)); - src = kmap_atomic_prot(s, prot); - if (!src) - return -ENOMEM; - - memcpy_toio(dst, src, PAGE_SIZE); - - kunmap_atomic(src); + for (i = 0; i < num_pages; ++i) { + dst_ops->map_local(dst_iter, &dst_map, i); + src_ops->map_local(src_iter, &src_map, i); + + if (!src_map.is_iomem && !dst_map.is_iomem) { + memcpy(dst_map.vaddr, src_map.vaddr, PAGE_SIZE); + } else if (!src_map.is_iomem) { + dma_buf_map_memcpy_to(&dst_map, src_map.vaddr, + PAGE_SIZE); + } else if (!dst_map.is_iomem) { + memcpy_fromio(dst_map.vaddr, src_map.vaddr_iomem, + PAGE_SIZE); + } else { + int j; + u32 __iomem *src = src_map.vaddr_iomem; + u32 __iomem *dst = dst_map.vaddr_iomem;

- return 0; + for (j = 0; j < (PAGE_SIZE / sizeof(u32)); ++j) + iowrite32(ioread32(src++), dst++); + } + if (src_ops->unmap_local) + src_ops->unmap_local(src_iter, &src_map); + if (dst_ops->unmap_local) + dst_ops->unmap_local(dst_iter, &dst_map); + } } +EXPORT_SYMBOL(ttm_move_memcpy);

int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - struct ttm_resource *new_mem) + struct ttm_resource *dst_mem) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type); + struct ttm_resource_manager *dst_man = + ttm_manager_type(bo->bdev, dst_mem->mem_type); struct ttm_tt *ttm = bo->ttm; - struct ttm_resource *old_mem = &bo->mem; - struct ttm_resource old_copy = *old_mem; - void *old_iomap; - void *new_iomap; - int ret; - unsigned long i; - - ret = ttm_bo_wait_ctx(bo, ctx); - if (ret) - return ret; - - ret = ttm_resource_ioremap(bdev, old_mem, &old_iomap); - if (ret) - return ret; - ret = ttm_resource_ioremap(bdev, new_mem, &new_iomap); - if (ret) - goto out; - - /* - * Single TTM move. NOP. - */ - if (old_iomap == NULL && new_iomap == NULL) - goto out2; - - /* - * Don't move nonexistent data. Clear destination instead. - */ - if (old_iomap == NULL && - (ttm == NULL || (!ttm_tt_is_populated(ttm) && - !(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)))) { - memset_io(new_iomap, 0, new_mem->num_pages*PAGE_SIZE); - goto out2; - } + struct ttm_resource *src_mem = &bo->mem; + struct ttm_resource_manager *src_man = + ttm_manager_type(bdev, src_mem->mem_type); + struct ttm_resource src_copy = *src_mem; + union { + struct ttm_kmap_iter_tt tt; + struct ttm_kmap_iter_linear_io io; + } _dst_iter, _src_iter; + struct ttm_kmap_iter *dst_iter, *src_iter; + int ret = 0;

- /* - * TTM might be null for moves within the same region. - */ - if (ttm) { + if (ttm && ((ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) || + dst_man->use_tt)) { ret = ttm_tt_populate(bdev, ttm, ctx); if (ret) - goto out1; + return ret; }

- for (i = 0; i < new_mem->num_pages; ++i) { - if (old_iomap == NULL) { - pgprot_t prot = ttm_io_prot(bo, old_mem, PAGE_KERNEL); - ret = ttm_copy_ttm_io_page(ttm, new_iomap, i, - prot); - } else if (new_iomap == NULL) { - pgprot_t prot = ttm_io_prot(bo, new_mem, PAGE_KERNEL); - ret = ttm_copy_io_ttm_page(ttm, old_iomap, i, - prot); - } else { - ret = ttm_copy_io_page(new_iomap, old_iomap, i); - } - if (ret) - goto out1; + dst_iter = ttm_kmap_iter_linear_io_init(&_dst_iter.io, bdev, dst_mem); + if (PTR_ERR(dst_iter) == -EINVAL && dst_man->use_tt) + dst_iter = ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm); + if (IS_ERR(dst_iter)) + return PTR_ERR(dst_iter); + + src_iter = ttm_kmap_iter_linear_io_init(&_src_iter.io, bdev, src_mem); + if (PTR_ERR(src_iter) == -EINVAL && src_man->use_tt) + src_iter = ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm); + if (IS_ERR(src_iter)) { + ret = PTR_ERR(src_iter); + goto out_src_iter; } - mb(); -out2: - old_copy = *old_mem;

- ttm_bo_assign_mem(bo, new_mem); - - if (!man->use_tt) - ttm_bo_tt_destroy(bo); + ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter); + src_copy = *src_mem; + ttm_bo_move_sync_cleanup(bo, dst_mem);

-out1: - ttm_resource_iounmap(bdev, old_mem, new_iomap); -out: - ttm_resource_iounmap(bdev, &old_copy, old_iomap); + if (!src_iter->ops->maps_tt) + ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, &src_copy); +out_src_iter: + if (!dst_iter->ops->maps_tt) + ttm_kmap_iter_linear_io_fini(&_dst_iter.io, bdev, dst_mem);

- /* - * On error, keep the mm node! - */ - if (!ret) - ttm_resource_free(bo, &old_copy); return ret; } EXPORT_SYMBOL(ttm_bo_move_memcpy); @@ -336,27 +272,7 @@ pgprot_t ttm_io_prot(struct ttm_buffer_object *bo, struct ttm_resource *res, man = ttm_manager_type(bo->bdev, res->mem_type); caching = man->use_tt ? bo->ttm->caching : res->bus.caching;

- /* Cached mappings need no adjustment */ - if (caching == ttm_cached) - return tmp; - -#if defined(__i386__) || defined(__x86_64__) - if (caching == ttm_write_combined) - tmp = pgprot_writecombine(tmp); - else if (boot_cpu_data.x86 > 3) - tmp = pgprot_noncached(tmp); -#endif -#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \ - defined(__powerpc__) || defined(__mips__) - if (caching == ttm_write_combined) - tmp = pgprot_writecombine(tmp); - else - tmp = pgprot_noncached(tmp); -#endif -#if defined(__sparc__) - tmp = pgprot_noncached(tmp); -#endif - return tmp; + return ttm_prot_from_caching(caching, tmp); } EXPORT_SYMBOL(ttm_io_prot);

diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c index 56b0efdba1a9..997c458f68a9 100644 --- a/drivers/gpu/drm/ttm/ttm_module.c +++ b/drivers/gpu/drm/ttm/ttm_module.c @@ -31,12 +31,47 @@ */ #include <linux/module.h> #include <linux/device.h> +#include <linux/pgtable.h> #include <linux/sched.h> #include <linux/debugfs.h> #include <drm/drm_sysfs.h> +#include <drm/ttm/ttm_caching.h>

#include "ttm_module.h"

+/** + * ttm_prot_from_caching - Modify the page protection according to the + * ttm cacing mode + * @caching: The ttm caching mode + * @tmp: The original page protection + * + * Return: The modified page protection + */ +pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp) +{ + /* Cached mappings need no adjustment */ + if (caching == ttm_cached) + return tmp; + +#if defined(__i386__) || defined(__x86_64__) + if (caching == ttm_write_combined) + tmp = pgprot_writecombine(tmp); + else if (boot_cpu_data.x86 > 3) + tmp = pgprot_noncached(tmp); +#endif +#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \ + defined(__powerpc__) || defined(__mips__) + if (caching == ttm_write_combined) + tmp = pgprot_writecombine(tmp); + else + tmp = pgprot_noncached(tmp); +#endif +#if defined(__sparc__) + tmp = pgprot_noncached(tmp); +#endif + return tmp; +} + struct dentry *ttm_debugfs_root;

static int __init ttm_init(void) diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index 59e2b7157e41..931bcd1a9b9b 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -22,6 +22,10 @@ * Authors: Christian König */

+#include <linux/dma-buf-map.h> +#include <linux/io-mapping.h> +#include <linux/scatterlist.h> + #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_bo_driver.h>

@@ -147,3 +151,192 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man, man->func->debug(man, p); } EXPORT_SYMBOL(ttm_resource_manager_debug); + +static void ttm_kmap_iter_iomap_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_iomap *iter_io = + container_of(iter, typeof(*iter_io), base); + void __iomem *addr; + +retry: + while (i >= iter_io->cache.end) { + iter_io->cache.sg = iter_io->cache.sg ? + sg_next(iter_io->cache.sg) : iter_io->st->sgl; + iter_io->cache.i = iter_io->cache.end; + iter_io->cache.end += sg_dma_len(iter_io->cache.sg) >> + PAGE_SHIFT; + iter_io->cache.offs = sg_dma_address(iter_io->cache.sg) - + iter_io->start; + } + + if (i < iter_io->cache.i) { + iter_io->cache.end = 0; + iter_io->cache.sg = NULL; + goto retry; + } + + addr = io_mapping_map_local_wc(iter_io->iomap, iter_io->cache.offs + + (((resource_size_t)i - iter_io->cache.i) + << PAGE_SHIFT)); + dma_buf_map_set_vaddr_iomem(dmap, addr); +} + +static void ttm_kmap_iter_iomap_unmap_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *map) +{ + io_mapping_unmap_local(map->vaddr_iomem); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_io_ops = { + .map_local = ttm_kmap_iter_iomap_map_local, + .unmap_local = ttm_kmap_iter_iomap_unmap_local, + .maps_tt = false, +}; + +/** + * ttm_kmap_iter_iomap_init - Initialize a struct ttm_kmap_iter_iomap + * @iter_io: The struct ttm_kmap_iter_iomap to initialize. + * @iomap: The struct io_mapping representing the underlying linear io_memory. + * @st: sg_table into @iomap, representing the memory of the struct + * ttm_resource. + * @start: Offset that needs to be subtracted from @st to make + * sg_dma_address(st->sgl) - @start == 0 for @iomap start. + * + * Return: Pointer to the embedded struct ttm_kmap_iter. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, + struct io_mapping *iomap, + struct sg_table *st, + resource_size_t start) +{ + iter_io->base.ops = &ttm_kmap_iter_io_ops; + iter_io->iomap = iomap; + iter_io->st = st; + iter_io->start = start; + memset(&iter_io->cache, 0, sizeof(iter_io->cache)); + + return &iter_io->base; +} +EXPORT_SYMBOL(ttm_kmap_iter_iomap_init); + +/** + * DOC: Linear io iterator + * + * This code should die in the not too near future. Best would be if we could + * make io-mapping use memremap for all io memory, and have memremap + * implement a kmap_local functionality. We could then strip a huge amount of + * code. These linear io iterators are implemented to mimic old functionality, + * and they don't use kmap_local semantics at all internally. Rather ioremap or + * friends, and at least on 32-bit they add global TLB flushes and points + * of failure. + */ + +static void ttm_kmap_iter_linear_io_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_linear_io *iter_io = + container_of(iter, typeof(*iter_io), base); + + *dmap = iter_io->dmap; + dma_buf_map_incr(dmap, i * PAGE_SIZE); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_linear_io_ops = { + .map_local = ttm_kmap_iter_linear_io_map_local, + .maps_tt = false, +}; + +/** + * ttm_kmap_iter_linear_io_init - Initialize an iterator for linear io memory + * @iter_io: The iterator to initialize + * @bdev: The TTM device + * @mem: The ttm resource representing the iomap. + * + * This function is for internal TTM use only. It sets up a memcpy kmap iterator + * pointing at a linear chunk of io memory. + * + * Return: A pointer to the embedded struct ttm_kmap_iter or error pointer on + * failure. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem) +{ + int ret; + + ret = ttm_mem_io_reserve(bdev, mem); + if (ret) + goto out_err; + if (!mem->bus.is_iomem) { + ret = -EINVAL; + goto out_io_free; + } + + if (mem->bus.addr) { + dma_buf_map_set_vaddr(&iter_io->dmap, mem->bus.addr); + iter_io->needs_unmap = false; + } else { + size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT; + + iter_io->needs_unmap = true; + memset(&iter_io->dmap, 0, sizeof(iter_io->dmap)); + if (mem->bus.caching == ttm_write_combined) + dma_buf_map_set_vaddr_iomem(&iter_io->dmap, + ioremap_wc(mem->bus.offset, + bus_size)); + else if (mem->bus.caching == ttm_cached) + dma_buf_map_set_vaddr(&iter_io->dmap, + memremap(mem->bus.offset, bus_size, + MEMREMAP_WB | + MEMREMAP_WT | + MEMREMAP_WC)); + + /* If uncached requested or if mapping cached or wc failed */ + if (dma_buf_map_is_null(&iter_io->dmap)) + dma_buf_map_set_vaddr_iomem(&iter_io->dmap, + ioremap(mem->bus.offset, + bus_size)); + + if (dma_buf_map_is_null(&iter_io->dmap)) { + ret = -ENOMEM; + goto out_io_free; + } + } + + iter_io->base.ops = &ttm_kmap_iter_linear_io_ops; + return &iter_io->base; + +out_io_free: + ttm_mem_io_free(bdev, mem); +out_err: + return ERR_PTR(ret); +} + +/** + * ttm_kmap_iter_linear_io_fini - Clean up an iterator for linear io memory + * @iter_io: The iterator to initialize + * @bdev: The TTM device + * @mem: The ttm resource representing the iomap. + * + * This function is for internal TTM use only. It cleans up a memcpy kmap + * iterator initialized by ttm_kmap_iter_linear_io_init. + */ +void +ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem) +{ + if (iter_io->needs_unmap && dma_buf_map_is_set(&iter_io->dmap)) { + if (iter_io->dmap.is_iomem) + iounmap(iter_io->dmap.vaddr_iomem); + else + memunmap(iter_io->dmap.vaddr); + } + + ttm_mem_io_free(bdev, mem); +} diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 539e0232cb3b..5a014c4d4b6f 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -433,3 +433,48 @@ void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages) if (!ttm_dma32_pages_limit) ttm_dma32_pages_limit = num_dma32_pages; } + +static void ttm_kmap_iter_tt_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_tt *iter_tt = + container_of(iter, typeof(*iter_tt), base); + + dma_buf_map_set_vaddr(dmap, kmap_local_page_prot(iter_tt->tt->pages[i], + iter_tt->prot)); +} + +static void ttm_kmap_iter_tt_unmap_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *map) +{ + kunmap_local(map->vaddr); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_tt_ops = { + .map_local = ttm_kmap_iter_tt_map_local, + .unmap_local = ttm_kmap_iter_tt_unmap_local, + .maps_tt = true, +}; + +/** + * ttm_kmap_iter_tt_init - Initialize a struct ttm_kmap_iter_tt + * @iter_tt: The struct ttm_kmap_iter_tt to initialize. + * @tt: Struct ttm_tt holding page pointers of the struct ttm_resource. + * + * Return: Pointer to the embedded struct ttm_kmap_iter. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, + struct ttm_tt *tt) +{ + iter_tt->base.ops = &ttm_kmap_iter_tt_ops; + iter_tt->tt = tt; + if (tt) + iter_tt->prot = ttm_prot_from_caching(tt->caching, PAGE_KERNEL); + else + iter_tt->prot = PAGE_KERNEL; + + return &iter_tt->base; +} +EXPORT_SYMBOL(ttm_kmap_iter_tt_init); diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index dbccac957f8f..72511992261a 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -40,6 +40,7 @@ #include <drm/ttm/ttm_device.h>

#include "ttm_bo_api.h" +#include "ttm_kmap_iter.h" #include "ttm_placement.h" #include "ttm_tt.h" #include "ttm_pool.h" @@ -272,6 +273,23 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, bool pipeline, struct ttm_resource *new_mem);

+/** + * ttm_bo_move_accel_cleanup. + * + * @bo: A pointer to a struct ttm_buffer_object. + * @new_mem: struct ttm_resource indicating where to move. + * + * Special case of ttm_bo_move_accel_cleanup where the bo is guaranteed + * by the caller to be idle. Typically used after memcpy buffer moves. + */ +static inline void ttm_bo_move_sync_cleanup(struct ttm_buffer_object *bo, + struct ttm_resource *new_mem) +{ + int ret = ttm_bo_move_accel_cleanup(bo, NULL, true, false, new_mem); + + WARN_ON(ret); +} + /** * ttm_bo_pipeline_gutting. * @@ -332,4 +350,14 @@ int ttm_range_man_init(struct ttm_device *bdev, int ttm_range_man_fini(struct ttm_device *bdev, unsigned type);

+void ttm_move_memcpy(struct ttm_buffer_object *bo, + u32 num_pages, + struct ttm_kmap_iter *dst_iter, + struct ttm_kmap_iter *src_iter); + +struct ttm_kmap_iter * +ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, + struct io_mapping *iomap, + struct sg_table *st, + resource_size_t start); #endif diff --git a/include/drm/ttm/ttm_caching.h b/include/drm/ttm/ttm_caching.h index a0b4a49fa432..3c9dd65f5aaf 100644 --- a/include/drm/ttm/ttm_caching.h +++ b/include/drm/ttm/ttm_caching.h @@ -33,4 +33,6 @@ enum ttm_caching { ttm_cached };

+pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp); + #endif diff --git a/include/drm/ttm/ttm_kmap_iter.h b/include/drm/ttm/ttm_kmap_iter.h new file mode 100644 index 000000000000..8bb00fd39d6c --- /dev/null +++ b/include/drm/ttm/ttm_kmap_iter.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ +#ifndef __TTM_KMAP_ITER_H__ +#define __TTM_KMAP_ITER_H__ + +#include <linux/types.h> + +struct ttm_kmap_iter; +struct dma_buf_map; + +/** + * struct ttm_kmap_iter_ops - Ops structure for a struct + * ttm_kmap_iter. + * @maps_tt: Whether the iterator maps TT memory directly, as opposed + * mapping a TT through an aperture. Both these modes have + * struct ttm_resource_manager::use_tt set, but the latter typically + * returns is_iomem == true from ttm_mem_io_reserve. + */ +struct ttm_kmap_iter_ops { + /** + * kmap_local() - Map a PAGE_SIZE part of the resource using + * kmap_local semantics. + * @res_iter: Pointer to the struct ttm_kmap_iter representing + * the resource. + * @dmap: The struct dma_buf_map holding the virtual address after + * the operation. + * @i: The location within the resource to map. PAGE_SIZE granularity. + */ + void (*map_local)(struct ttm_kmap_iter *res_iter, + struct dma_buf_map *dmap, pgoff_t i); + /** + * unmap_local() - Unmap a PAGE_SIZE part of the resource previously + * mapped using kmap_local. + * @res_iter: Pointer to the struct ttm_kmap_iter representing + * the resource. + * @dmap: The struct dma_buf_map holding the virtual address after + * the operation. + */ + void (*unmap_local)(struct ttm_kmap_iter *res_iter, + struct dma_buf_map *dmap); + bool maps_tt; +}; + +/** + * struct ttm_kmap_iter - Iterator for kmap_local type operations on a + * resource. + * @ops: Pointer to the operations struct. + * + * This struct is intended to be embedded in a resource-specific specialization + * implementing operations for the resource. + * + * Nothing stops us from extending the operations to vmap, vmap_pfn etc, + * replacing some or parts of the ttm_bo_util. cpu-map functionality. + */ +struct ttm_kmap_iter { + const struct ttm_kmap_iter_ops *ops; +}; + +#endif /* __TTM_KMAP_ITER_H__ */ diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 890b9d369519..b8dc0bdb0da5 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -27,9 +27,11 @@

#include <linux/types.h> #include <linux/mutex.h> +#include <linux/dma-buf-map.h> #include <linux/dma-fence.h> #include <drm/drm_print.h> #include <drm/ttm/ttm_caching.h> +#include <drm/ttm/ttm_kmap_iter.h>

#define TTM_MAX_BO_PRIORITY 4U

@@ -38,6 +40,10 @@ struct ttm_resource_manager; struct ttm_resource; struct ttm_place; struct ttm_buffer_object; +struct dma_buf_map; +struct io_mapping; +struct sg_table; +struct scatterlist;

struct ttm_resource_manager_func { /** @@ -176,6 +182,45 @@ struct ttm_resource { struct ttm_bus_placement bus; };

+/** + * struct ttm_kmap_iter_iomap - Specialization for a struct io_mapping + + * struct sg_table backed struct ttm_resource. + * @base: Embedded struct ttm_kmap_iter providing the usage interface. + * @iomap: struct io_mapping representing the underlying linear io_memory. + * @st: sg_table into @iomap, representing the memory of the struct ttm_resource. + * @start: Offset that needs to be subtracted from @st to make + * sg_dma_address(st->sgl) - @start == 0 for @iomap start. + * @cache: Scatterlist traversal cache for fast lookups. + * @cache.sg: Pointer to the currently cached scatterlist segment. + * @cache.i: First index of @sg. PAGE_SIZE granularity. + * @cache.end: Last index + 1 of @sg. PAGE_SIZE granularity. + * @cache.offs: First offset into @iomap of @sg. PAGE_SIZE granularity. + */ +struct ttm_kmap_iter_iomap { + struct ttm_kmap_iter base; + struct io_mapping *iomap; + struct sg_table *st; + resource_size_t start; + struct { + struct scatterlist *sg; + pgoff_t i; + pgoff_t end; + pgoff_t offs; + } cache; +}; + +/** + * struct ttm_kmap_iter_linear_io - Iterator specialization for linear io + * @base: The base iterator + * @dmap: Points to the starting address of the region + * @needs_unmap: Whether we need to unmap on fini + */ +struct ttm_kmap_iter_linear_io { + struct ttm_kmap_iter base; + struct dma_buf_map dmap; + bool needs_unmap; +}; + /** * ttm_resource_manager_set_used * @@ -237,4 +282,20 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev, void ttm_resource_manager_debug(struct ttm_resource_manager *man, struct drm_printer *p);

+struct ttm_kmap_iter * +ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, + struct io_mapping *iomap, + struct sg_table *st, + resource_size_t start); + +struct ttm_kmap_iter_linear_io; + +struct ttm_kmap_iter * +ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem); + +void ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem); #endif diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 134d09ef7766..3102059db726 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -29,6 +29,7 @@

#include <linux/types.h> #include <drm/ttm/ttm_caching.h> +#include <drm/ttm/ttm_kmap_iter.h>

struct ttm_bo_device; struct ttm_tt; @@ -69,6 +70,18 @@ struct ttm_tt { enum ttm_caching caching; };

+/** + * struct ttm_kmap_iter_tt - Specialization of a mappig iterator for a tt. + * @base: Embedded struct ttm_kmap_iter providing the usage interface + * @tt: Cached struct ttm_tt. + * @prot: Cached page protection for mapping. + */ +struct ttm_kmap_iter_tt { + struct ttm_kmap_iter base; + struct ttm_tt *tt; + pgprot_t prot; +}; + static inline bool ttm_tt_is_populated(struct ttm_tt *tt) { return tt->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED; @@ -159,6 +172,9 @@ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm);

void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages);

+struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, + struct ttm_tt *tt); + #if IS_ENABLED(CONFIG_AGP) #include <linux/agp_backend.h>

Use fast wc memcpy for reading out of wc memory for TTM bo moves.

Cc: Dave Airlie airlied@gmail.com Cc: Christian König christian.koenig@amd.com Cc: Daniel Vetter daniel.vetter@ffwll.ch Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Reviewed-by: Christian König christian.koenig@amd.com #v4 -- v4: - Clarify when we try drm_memcpy_from_wc_dbm (Reported by Matthew Auld) - Be paranoid about when drm_memcpy_from_wc_dbm may fail (Reported by Matthew Auld) v5: - Rebase on change to drm_memcpy_from_wc (Suggested by Daniel Vetter) --- drivers/gpu/drm/ttm/ttm_bo_util.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index a800998a12b0..30bafac416a5 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -31,6 +31,7 @@

#include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/drm_cache.h> #include <drm/drm_vma_manager.h> #include <linux/dma-buf-map.h> #include <linux/io.h> @@ -118,22 +119,8 @@ void ttm_move_memcpy(struct ttm_buffer_object *bo, dst_ops->map_local(dst_iter, &dst_map, i); src_ops->map_local(src_iter, &src_map, i);

- if (!src_map.is_iomem && !dst_map.is_iomem) { - memcpy(dst_map.vaddr, src_map.vaddr, PAGE_SIZE); - } else if (!src_map.is_iomem) { - dma_buf_map_memcpy_to(&dst_map, src_map.vaddr, - PAGE_SIZE); - } else if (!dst_map.is_iomem) { - memcpy_fromio(dst_map.vaddr, src_map.vaddr_iomem, - PAGE_SIZE); - } else { - int j; - u32 __iomem *src = src_map.vaddr_iomem; - u32 __iomem *dst = dst_map.vaddr_iomem; - - for (j = 0; j < (PAGE_SIZE / sizeof(u32)); ++j) - iowrite32(ioread32(src++), dst++); - } + drm_memcpy_from_wc(&dst_map, &src_map, PAGE_SIZE); + if (src_ops->unmap_local) src_ops->unmap_local(src_iter, &src_map); if (dst_ops->unmap_local)

We are calling the eviction_valuable driver callback at eviction time to determine whether we actually can evict a buffer object. The upcoming i915 TTM backend needs the same functionality for swapout, and that might actually be beneficial to other drivers as well.

Add an eviction_valuable call also in the swapout path. Try to keep the current behaviour for all drivers by returning true if the buffer object is already in the TTM_PL_SYSTEM placement. We change behaviour for the case where a buffer object is in a TT backed placement when swapped out, in which case the drivers normal eviction_valuable path is run.

Reviewed-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Cc: Christian König christian.koenig@amd.com Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Acked-by: Christian König christian.koenig@amd.com --- v3: - Don't export ttm_tt_unpopulate - Fix confusion reading the locked pointer instead of the value pointed to in ttm_bo_evict_swapout_allowable (Reported by Maarten Lankhorst) v5: - Use memset() rather than = {} (Suggested by Christian König) - Remove check for ttm_tt_is_populated in the swapout code in the hope it will be fixed elsewhere (Suggested by Christian König) v7: - Re-add the check for ttm_tt_is_populated in the swapout code. --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 +++ drivers/gpu/drm/ttm/ttm_bo.c | 46 ++++++++++++++++--------- 2 files changed, 34 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 80437b6ba5f3..5116065748a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1328,6 +1328,10 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, struct dma_fence *f; int i;

+ /* Swapout? */ + if (bo->mem.mem_type == TTM_PL_SYSTEM) + return true; + if (bo->type == ttm_bo_type_kernel && !amdgpu_vm_evictable(ttm_to_amdgpu_bo(bo))) return false; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index be0406466460..98c41bf6a07d 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -536,6 +536,10 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place) { + dma_resv_assert_held(bo->base.resv); + if (bo->mem.mem_type == TTM_PL_SYSTEM) + return true; + /* Don't evict this BO if it's outside of the * requested placement range */ @@ -558,7 +562,9 @@ EXPORT_SYMBOL(ttm_bo_eviction_valuable); * b. Otherwise, trylock it. */ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, - struct ttm_operation_ctx *ctx, bool *locked, bool *busy) + struct ttm_operation_ctx *ctx, + const struct ttm_place *place, + bool *locked, bool *busy) { bool ret = false;

@@ -576,6 +582,14 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, *busy = !ret; }

+ if (ret && place && !bo->bdev->funcs->eviction_valuable(bo, place)) { + ret = false; + if (*locked) { + dma_resv_unlock(bo->base.resv); + *locked = false; + } + } + return ret; }

@@ -630,20 +644,14 @@ int ttm_mem_evict_first(struct ttm_device *bdev, list_for_each_entry(bo, &man->lru[i], lru) { bool busy;

- if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked, - &busy)) { + if (!ttm_bo_evict_swapout_allowable(bo, ctx, place, + &locked, &busy)) { if (busy && !busy_bo && ticket != dma_resv_locking_ctx(bo->base.resv)) busy_bo = bo; continue; }

- if (place && !bdev->funcs->eviction_valuable(bo, - place)) { - if (locked) - dma_resv_unlock(bo->base.resv); - continue; - } if (!ttm_bo_get_unless_zero(bo)) { if (locked) dma_resv_unlock(bo->base.resv); @@ -1140,10 +1148,19 @@ EXPORT_SYMBOL(ttm_bo_wait); int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, gfp_t gfp_flags) { + struct ttm_place place; bool locked; int ret;

- if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked, NULL)) + /* + * While the bo may already reside in SYSTEM placement, set + * SYSTEM as new placement to cover also the move further below. + * The driver may use the fact that we're moving from SYSTEM + * as an indication that we're about to swap out. + */ + memset(&place, 0, sizeof(place)); + place.mem_type = TTM_PL_SYSTEM; + if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL)) return -EBUSY;

if (!ttm_bo_get_unless_zero(bo)) { @@ -1168,13 +1185,9 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, if (bo->mem.mem_type != TTM_PL_SYSTEM) { struct ttm_operation_ctx ctx = { false, false }; struct ttm_resource evict_mem; - struct ttm_place place, hop; + struct ttm_place hop;

- memset(&place, 0, sizeof(place)); memset(&hop, 0, sizeof(hop)); - - place.mem_type = TTM_PL_SYSTEM; - ret = ttm_resource_alloc(bo, &place, &evict_mem); if (unlikely(ret)) goto out; @@ -1202,7 +1215,8 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, if (bo->bdev->funcs->swap_notify) bo->bdev->funcs->swap_notify(bo);

- ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); + if (ttm_tt_is_populated(bo->ttm)) + ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); out:

/*

Since objects can be migrated or evicted when not pinned or locked, update the checks for lmem residency or future residency so that the value returned is not immediately stale.

Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com --- v2: Simplify i915_gem_object_migratable() (Reported by Mattew Auld) --- drivers/gpu/drm/i915/display/intel_display.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 42 +++++++++++++++++++- drivers/gpu/drm/i915/gem/i915_gem_object.c | 18 +++++++++ drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 ++ 4 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index caf0414e0b50..f947295d7e53 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -11756,7 +11756,7 @@ intel_user_framebuffer_create(struct drm_device *dev,

/* object is backed with LMEM for discrete */ i915 = to_i915(obj->base.dev); - if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj)) { + if (HAS_LMEM(i915) && !i915_gem_object_validates_to_lmem(obj)) { /* object is "remote", not in local memory */ i915_gem_object_put(obj); return ERR_PTR(-EREMOTE); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index 2b8cd15de1d9..d539dffa1554 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -23,10 +23,50 @@ i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, return io_mapping_map_wc(&obj->mm.region->iomap, offset, size); }

+/** + * i915_gem_object_validates_to_lmem - Whether the object is resident in + * lmem when pages are present. + * @obj: The object to check. + * + * Migratable objects residency may change from under us if the object is + * not pinned or locked. This function is intended to be used to check whether + * the object can only reside in lmem when pages are present. + * + * Return: Whether the object is always resident in lmem when pages are + * present. + */ +bool i915_gem_object_validates_to_lmem(struct drm_i915_gem_object *obj) +{ + struct intel_memory_region *mr = READ_ONCE(obj->mm.region); + + return !i915_gem_object_migratable(obj) && + mr && (mr->type == INTEL_MEMORY_LOCAL || + mr->type == INTEL_MEMORY_STOLEN_LOCAL); +} + +/** + * i915_gem_object_is_lmem - Whether the object is resident in + * lmem + * @obj: The object to check. + * + * Even if an object is allowed to migrate and change memory region, + * this function checks whether it will always be present in lmem when + * valid *or* if that's not the case, whether it's currently resident in lmem. + * For migratable and evictable objects, the latter only makes sense when + * the object is locked. + * + * Return: Whether the object migratable but resident in lmem, or not + * migratable and will be present in lmem when valid. + */ bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) { - struct intel_memory_region *mr = obj->mm.region; + struct intel_memory_region *mr = READ_ONCE(obj->mm.region);

+#ifdef CONFIG_LOCKDEP + if (i915_gem_object_migratable(obj) && + i915_gem_object_evictable(obj)) + assert_object_held(obj); +#endif return mr && (mr->type == INTEL_MEMORY_LOCAL || mr->type == INTEL_MEMORY_STOLEN_LOCAL); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 16eac5ea9238..cf18c430d51f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -457,6 +457,24 @@ bool i915_gem_object_evictable(struct drm_i915_gem_object *obj) 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; +} + void i915_gem_init__objects(struct drm_i915_private *i915) { INIT_WORK(&i915->mm.free_work, __i915_gem_free_work); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index ae5930e307d5..a3ad8cf4eefd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -596,6 +596,10 @@ void __i915_gem_free_object(struct drm_i915_gem_object *obj);

bool i915_gem_object_evictable(struct drm_i915_gem_object *obj);

+bool i915_gem_object_migratable(struct drm_i915_gem_object *obj); + +bool i915_gem_object_validates_to_lmem(struct drm_i915_gem_object *obj); + #ifdef CONFIG_MMU_NOTIFIER static inline bool i915_gem_object_is_userptr(struct drm_i915_gem_object *obj)

From: Maarten Lankhorst maarten.lankhorst@linux.intel.com

This allows drivers to distinguish between different types of vma_node's. The readonly flag was unused and is thus removed.

This is a temporary solution, until i915 is converted completely to use ttm for bo's.

Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Thomas Hellström thomas.hellstrom@linux.intel.com Acked-by: Daniel Vetter daniel@ffwll.ch #irc --- drivers/gpu/drm/drm_gem.c | 9 --------- include/drm/drm_vma_manager.h | 2 +- 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 9989425e9875..e710e79069f6 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1149,15 +1149,6 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) return -EACCES; }

- if (node->readonly) { - if (vma->vm_flags & VM_WRITE) { - drm_gem_object_put(obj); - return -EINVAL; - } - - vma->vm_flags &= ~VM_MAYWRITE; - } - ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT, vma);

diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 76ac5e97a559..4f8c35206f7c 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -53,7 +53,7 @@ struct drm_vma_offset_node { rwlock_t vm_lock; struct drm_mm_node vm_node; struct rb_root vm_files; - bool readonly:1; + void *driver_private; };

struct drm_vma_offset_manager {