diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gem')
28 files changed, 594 insertions, 209 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c index b3b398fe689c..385ffc575b48 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c @@ -8,6 +8,7 @@ #include "display/intel_frontbuffer.h" +#include "i915_config.h" #include "i915_drv.h" #include "i915_gem_clflush.h" #include "i915_sw_fence_work.h" diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 7f2831efc798..6d639ca24dfb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -257,7 +257,7 @@ static int proto_context_set_protected(struct drm_i915_private *i915, if (!protected) { pc->uses_protected_content = false; - } else if (!intel_pxp_is_enabled(&to_gt(i915)->pxp)) { + } else if (!intel_pxp_is_enabled(i915->pxp)) { ret = -ENODEV; } else if ((pc->user_flags & BIT(UCONTEXT_RECOVERABLE)) || !(pc->user_flags & BIT(UCONTEXT_BANNABLE))) { @@ -271,8 +271,8 @@ static int proto_context_set_protected(struct drm_i915_private *i915, */ pc->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); - if (!intel_pxp_is_active(&to_gt(i915)->pxp)) - ret = intel_pxp_start(&to_gt(i915)->pxp); + if (!intel_pxp_is_active(i915->pxp)) + ret = intel_pxp_start(i915->pxp); } return ret; @@ -1096,16 +1096,15 @@ static struct i915_gem_engines *alloc_engines(unsigned int count) static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx, struct intel_sseu rcs_sseu) { - const struct intel_gt *gt = to_gt(ctx->i915); + const unsigned int max = I915_NUM_ENGINES; struct intel_engine_cs *engine; struct i915_gem_engines *e, *err; - enum intel_engine_id id; - e = alloc_engines(I915_NUM_ENGINES); + e = alloc_engines(max); if (!e) return ERR_PTR(-ENOMEM); - for_each_engine(engine, gt, id) { + for_each_uabi_engine(engine, ctx->i915) { struct intel_context *ce; struct intel_sseu sseu = {}; int ret; @@ -1113,7 +1112,7 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx, if (engine->legacy_idx == INVALID_ENGINE) continue; - GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES); + GEM_BUG_ON(engine->legacy_idx >= max); GEM_BUG_ON(e->engines[engine->legacy_idx]); ce = intel_context_create(engine); @@ -1688,6 +1687,10 @@ void i915_gem_init__contexts(struct drm_i915_private *i915) init_contexts(&i915->gem.contexts); } +/* + * Note that this implicitly consumes the ctx reference, by placing + * the ctx in the context_xa. + */ static void gem_context_register(struct i915_gem_context *ctx, struct drm_i915_file_private *fpriv, u32 id) @@ -1703,10 +1706,6 @@ static void gem_context_register(struct i915_gem_context *ctx, snprintf(ctx->name, sizeof(ctx->name), "%s[%d]", current->comm, pid_nr(ctx->pid)); - /* And finally expose ourselves to userspace via the idr */ - old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL); - WARN_ON(old); - spin_lock(&ctx->client->ctx_lock); list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list); spin_unlock(&ctx->client->ctx_lock); @@ -1714,6 +1713,10 @@ static void gem_context_register(struct i915_gem_context *ctx, spin_lock(&i915->gem.contexts.lock); list_add_tail(&ctx->link, &i915->gem.contexts.list); spin_unlock(&i915->gem.contexts.lock); + + /* And finally expose ourselves to userspace via the idr */ + old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL); + WARN_ON(old); } int i915_gem_context_open(struct drm_i915_private *i915, @@ -1857,11 +1860,19 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv, vm = ctx->vm; GEM_BUG_ON(!vm); + /* + * Get a reference for the allocated handle. Once the handle is + * visible in the vm_xa table, userspace could try to close it + * from under our feet, so we need to hold the extra reference + * first. + */ + i915_vm_get(vm); + err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL); - if (err) + if (err) { + i915_vm_put(vm); return err; - - i915_vm_get(vm); + } GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */ args->value = id; @@ -2199,14 +2210,22 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv, if (IS_ERR(ctx)) return ctx; + /* + * One for the xarray and one for the caller. We need to grab + * the reference *prior* to making the ctx visble to userspace + * in gem_context_register(), as at any point after that + * userspace can try to race us with another thread destroying + * the context under our feet. + */ + i915_gem_context_get(ctx); + gem_context_register(ctx, file_priv, id); old = xa_erase(&file_priv->proto_context_xa, id); GEM_BUG_ON(old != pc); proto_context_close(file_priv->dev_priv, pc); - /* One for the xarray and one for the caller */ - return i915_gem_context_get(ctx); + return ctx; } struct i915_gem_context * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 33673fe7ee0a..e76c9703680e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -5,6 +5,7 @@ #include <drm/drm_fourcc.h> +#include "display/intel_display.h" #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" @@ -384,7 +385,7 @@ static int ext_set_protected(struct i915_user_extension __user *base, void *data if (ext.flags) return -EINVAL; - if (!intel_pxp_is_enabled(&to_gt(ext_data->i915)->pxp)) + if (!intel_pxp_is_enabled(ext_data->i915->pxp)) return -ENODEV; ext_data->flags |= I915_BO_PROTECTED; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index d44a152ce680..497de40b8e68 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -4,6 +4,7 @@ * Copyright © 2014-2016 Intel Corporation */ +#include "display/intel_display.h" #include "display/intel_frontbuffer.h" #include "gt/intel_gt.h" @@ -17,6 +18,8 @@ #include "i915_gem_object.h" #include "i915_vma.h" +#define VTD_GUARD (168u * I915_GTT_PAGE_SIZE) /* 168 or tile-row PTE padding */ + static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = to_i915(obj->base.dev); @@ -424,6 +427,17 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, if (ret) return ERR_PTR(ret); + /* VT-d may overfetch before/after the vma, so pad with scratch */ + if (intel_scanout_needs_vtd_wa(i915)) { + unsigned int guard = VTD_GUARD; + + if (i915_gem_object_is_tiled(obj)) + guard = max(guard, + i915_gem_object_get_tile_row_size(obj)); + + flags |= PIN_OFFSET_GUARD | guard; + } + /* * As the user may map the buffer once pinned in the display plane * (e.g. libkms for the bootup splash), we have to ensure that we @@ -444,7 +458,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, if (IS_ERR(vma)) return vma; - vma->display_alignment = max_t(u64, vma->display_alignment, alignment); + vma->display_alignment = max(vma->display_alignment, alignment); i915_vma_mark_scanout(vma); i915_gem_object_flush_if_display_locked(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index f266b68cf012..9dce2957b4e5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -379,22 +379,25 @@ eb_vma_misplaced(const struct drm_i915_gem_exec_object2 *entry, const struct i915_vma *vma, unsigned int flags) { - if (vma->node.size < entry->pad_to_size) + const u64 start = i915_vma_offset(vma); + const u64 size = i915_vma_size(vma); + + if (size < entry->pad_to_size) return true; - if (entry->alignment && !IS_ALIGNED(vma->node.start, entry->alignment)) + if (entry->alignment && !IS_ALIGNED(start, entry->alignment)) return true; if (flags & EXEC_OBJECT_PINNED && - vma->node.start != entry->offset) + start != entry->offset) return true; if (flags & __EXEC_OBJECT_NEEDS_BIAS && - vma->node.start < BATCH_OFFSET_BIAS) + start < BATCH_OFFSET_BIAS) return true; if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) && - (vma->node.start + vma->node.size + 4095) >> 32) + (start + size + 4095) >> 32) return true; if (flags & __EXEC_OBJECT_NEEDS_MAP && @@ -440,7 +443,7 @@ eb_pin_vma(struct i915_execbuffer *eb, int err; if (vma->node.size) - pin_flags = vma->node.start; + pin_flags = __i915_vma_offset(vma); else pin_flags = entry->offset & PIN_OFFSET_MASK; @@ -663,8 +666,8 @@ static int eb_reserve_vma(struct i915_execbuffer *eb, if (err) return err; - if (entry->offset != vma->node.start) { - entry->offset = vma->node.start | UPDATE; + if (entry->offset != i915_vma_offset(vma)) { + entry->offset = i915_vma_offset(vma) | UPDATE; eb->args->flags |= __EXEC_HAS_RELOC; } @@ -906,7 +909,7 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) */ if (i915_gem_context_uses_protected_content(eb->gem_context) && i915_gem_object_is_protected(obj)) { - err = intel_pxp_key_check(&vm->gt->pxp, obj, true); + err = intel_pxp_key_check(eb->i915->pxp, obj, true); if (err) { i915_gem_object_put(obj); return ERR_PTR(err); @@ -1021,8 +1024,8 @@ static int eb_validate_vmas(struct i915_execbuffer *eb) return err; if (!err) { - if (entry->offset != vma->node.start) { - entry->offset = vma->node.start | UPDATE; + if (entry->offset != i915_vma_offset(vma)) { + entry->offset = i915_vma_offset(vma) | UPDATE; eb->args->flags |= __EXEC_HAS_RELOC; } } else { @@ -1103,7 +1106,7 @@ static inline u64 relocation_target(const struct drm_i915_gem_relocation_entry *reloc, const struct i915_vma *target) { - return gen8_canonical_addr((int)reloc->delta + target->node.start); + return gen8_canonical_addr((int)reloc->delta + i915_vma_offset(target)); } static void reloc_cache_init(struct reloc_cache *cache, @@ -1312,7 +1315,7 @@ static void *reloc_iomap(struct i915_vma *batch, if (err) /* no inactive aperture space, use cpu reloc */ return NULL; } else { - cache->node.start = vma->node.start; + cache->node.start = i915_ggtt_offset(vma); cache->node.mm = (void *)vma; } } @@ -1475,7 +1478,7 @@ eb_relocate_entry(struct i915_execbuffer *eb, * more work needs to be done. */ if (!DBG_FORCE_RELOC && - gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset) + gen8_canonical_addr(i915_vma_offset(target->vma)) == reloc->presumed_offset) return 0; /* Check that the relocation address is valid... */ @@ -2405,7 +2408,7 @@ static int eb_request_submit(struct i915_execbuffer *eb, } err = rq->context->engine->emit_bb_start(rq, - batch->node.start + + i915_vma_offset(batch) + eb->batch_start_offset, batch_len, eb->batch_flags); @@ -2416,7 +2419,7 @@ static int eb_request_submit(struct i915_execbuffer *eb, GEM_BUG_ON(intel_context_is_parallel(rq->context)); GEM_BUG_ON(eb->batch_start_offset); err = rq->context->engine->emit_bb_start(rq, - eb->trampoline->node.start + + i915_vma_offset(eb->trampoline) + batch_len, 0, 0); if (err) return err; @@ -3483,6 +3486,13 @@ err_request: eb.composite_fence : &eb.requests[0]->fence); + if (unlikely(eb.gem_context->syncobj)) { + drm_syncobj_replace_fence(eb.gem_context->syncobj, + eb.composite_fence ? + eb.composite_fence : + &eb.requests[0]->fence); + } + if (out_fence) { if (err == 0) { fd_install(out_fence_fd, out_fence->file); @@ -3494,13 +3504,6 @@ err_request: } } - if (unlikely(eb.gem_context->syncobj)) { - drm_syncobj_replace_fence(eb.gem_context->syncobj, - eb.composite_fence ? - eb.composite_fence : - &eb.requests[0]->fence); - } - if (!out_fence && eb.composite_fence) dma_fence_put(eb.composite_fence); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index f66bcefc09ec..6bc26b4b06b8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -35,11 +35,15 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct sg_table *st; struct scatterlist *sg; - unsigned int npages; + unsigned int npages; /* restricted by sg_alloc_table */ int max_order = MAX_ORDER; unsigned int max_segment; gfp_t gfp; + if (overflows_type(obj->base.size >> PAGE_SHIFT, npages)) + return -E2BIG; + + npages = obj->base.size >> PAGE_SHIFT; max_segment = i915_sg_segment_size(i915->drm.dev) >> PAGE_SHIFT; max_order = min(max_order, get_order(max_segment)); @@ -55,7 +59,6 @@ create_st: if (!st) return -ENOMEM; - npages = obj->base.size / PAGE_SIZE; if (sg_alloc_table(st, npages, GFP_KERNEL)) { kfree(st); return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index c7c252d4d366..d3c1dee16af2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -395,7 +395,7 @@ retry: /* Finally, remap it using the new GTT offset */ ret = remap_io_mapping(area, area->vm_start + (vma->gtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT, + (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT, min_t(u64, vma->size, area->vm_end - area->vm_start), &ggtt->iomap); if (ret) @@ -979,7 +979,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) i915_gem_object_put(obj); return -EINVAL; } - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } anon = mmap_singleton(to_i915(dev)); @@ -988,7 +988,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) return PTR_ERR(anon); } - vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO; + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO); /* * We keep the ref on mmo->obj, not vm_file, but we require diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 1a0886b8aaa1..e6d4efde4fc5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -427,10 +427,11 @@ void __i915_gem_object_invalidate_frontbuffer(struct drm_i915_gem_object *obj, static void i915_gem_object_read_from_page_kmap(struct drm_i915_gem_object *obj, u64 offset, void *dst, int size) { + pgoff_t idx = offset >> PAGE_SHIFT; void *src_map; void *src_ptr; - src_map = kmap_atomic(i915_gem_object_get_page(obj, offset >> PAGE_SHIFT)); + src_map = kmap_atomic(i915_gem_object_get_page(obj, idx)); src_ptr = src_map + offset_in_page(offset); if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ)) @@ -443,9 +444,10 @@ i915_gem_object_read_from_page_kmap(struct drm_i915_gem_object *obj, u64 offset, static void i915_gem_object_read_from_page_iomap(struct drm_i915_gem_object *obj, u64 offset, void *dst, int size) { + pgoff_t idx = offset >> PAGE_SHIFT; + dma_addr_t dma = i915_gem_object_get_dma_address(obj, idx); void __iomem *src_map; void __iomem *src_ptr; - dma_addr_t dma = i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT); src_map = io_mapping_map_wc(&obj->mm.region->iomap, dma - obj->mm.region->region.start, @@ -484,6 +486,7 @@ static bool object_has_mappable_iomem(struct drm_i915_gem_object *obj) */ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, void *dst, int size) { + GEM_BUG_ON(overflows_type(offset >> PAGE_SHIFT, pgoff_t)); GEM_BUG_ON(offset >= obj->base.size); GEM_BUG_ON(offset_in_page(offset) > PAGE_SIZE - size); GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 3db53769864c..f9a8acbba715 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -20,26 +20,10 @@ enum intel_region_id; -/* - * XXX: There is a prevalence of the assumption that we fit the - * object's page count inside a 32bit _signed_ variable. Let's document - * this and catch if we ever need to fix it. In the meantime, if you do - * spot such a local variable, please consider fixing! - * - * Aside from our own locals (for which we have no excuse!): - * - sg_table embeds unsigned int for num_pages - * - get_user_pages*() mixed ints with longs - */ -#define GEM_CHECK_SIZE_OVERFLOW(sz) \ - GEM_WARN_ON((sz) >> PAGE_SHIFT > INT_MAX) - static inline bool i915_gem_object_size_2big(u64 size) { struct drm_i915_gem_object *obj; - if (GEM_CHECK_SIZE_OVERFLOW(size)) - return true; - if (overflows_type(size, obj->base.size)) return true; @@ -363,44 +347,289 @@ i915_gem_object_get_tile_row_size(const struct drm_i915_gem_object *obj) int i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, unsigned int tiling, unsigned int stride); +/** + * __i915_gem_object_page_iter_get_sg - helper to find the target scatterlist + * pointer and the target page position using pgoff_t n input argument and + * i915_gem_object_page_iter + * @obj: i915 GEM buffer object + * @iter: i915 GEM buffer object page iterator + * @n: page offset + * @offset: searched physical offset, + * it will be used for returning physical page offset value + * + * Context: Takes and releases the mutex lock of the i915_gem_object_page_iter. + * Takes and releases the RCU lock to search the radix_tree of + * i915_gem_object_page_iter. + * + * Returns: + * The target scatterlist pointer and the target page position. + * + * Recommended to use wrapper macro: i915_gem_object_page_iter_get_sg() + */ struct scatterlist * -__i915_gem_object_get_sg(struct drm_i915_gem_object *obj, - struct i915_gem_object_page_iter *iter, - unsigned int n, - unsigned int *offset, bool dma); +__i915_gem_object_page_iter_get_sg(struct drm_i915_gem_object *obj, + struct i915_gem_object_page_iter *iter, + pgoff_t n, + unsigned int *offset); +/** + * i915_gem_object_page_iter_get_sg - wrapper macro for + * __i915_gem_object_page_iter_get_sg() + * @obj: i915 GEM buffer object + * @it: i915 GEM buffer object page iterator + * @n: page offset + * @offset: searched physical offset, + * it will be used for returning physical page offset value + * + * Context: Takes and releases the mutex lock of the i915_gem_object_page_iter. + * Takes and releases the RCU lock to search the radix_tree of + * i915_gem_object_page_iter. + * + * Returns: + * The target scatterlist pointer and the target page position. + * + * In order to avoid the truncation of the input parameter, it checks the page + * offset n's type from the input parameter before calling + * __i915_gem_object_page_iter_get_sg(). + */ +#define i915_gem_object_page_iter_get_sg(obj, it, n, offset) ({ \ + static_assert(castable_to_type(n, pgoff_t)); \ + __i915_gem_object_page_iter_get_sg(obj, it, n, offset); \ +}) + +/** + * __i915_gem_object_get_sg - helper to find the target scatterlist + * pointer and the target page position using pgoff_t n input argument and + * drm_i915_gem_object. It uses an internal shmem scatterlist lookup function. + * @obj: i915 GEM buffer object + * @n: page offset + * @offset: searched physical offset, + * it will be used for returning physical page offset value + * + * It uses drm_i915_gem_object's internal shmem scatterlist lookup function as + * i915_gem_object_page_iter and calls __i915_gem_object_page_iter_get_sg(). + * + * Returns: + * The target scatterlist pointer and the target page position. + * + * Recommended to use wrapper macro: i915_gem_object_get_sg() + * See also __i915_gem_object_page_iter_get_sg() + */ static inline struct scatterlist * -i915_gem_object_get_sg(struct drm_i915_gem_object *obj, - unsigned int n, - unsigned int *offset) +__i915_gem_object_get_sg(struct drm_i915_gem_object *obj, pgoff_t n, + unsigned int *offset) { - return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset, false); + return __i915_gem_object_page_iter_get_sg(obj, &obj->mm.get_page, n, offset); } +/** + * i915_gem_object_get_sg - wrapper macro for __i915_gem_object_get_sg() + * @obj: i915 GEM buffer object + * @n: page offset + * @offset: searched physical offset, + * it will be used for returning physical page offset value + * + * Returns: + * The target scatterlist pointer and the target page position. + * + * In order to avoid the truncation of the input parameter, it checks the page + * offset n's type from the input parameter before calling + * __i915_gem_object_get_sg(). + * See also __i915_gem_object_page_iter_get_sg() + */ +#define i915_gem_object_get_sg(obj, n, offset) ({ \ + static_assert(castable_to_type(n, pgoff_t)); \ + __i915_gem_object_get_sg(obj, n, offset); \ +}) + +/** + * __i915_gem_object_get_sg_dma - helper to find the target scatterlist + * pointer and the target page position using pgoff_t n input argument and + * drm_i915_gem_object. It uses an internal DMA mapped scatterlist lookup function + * @obj: i915 GEM buffer object + * @n: page offset + * @offset: searched physical offset, + * it will be used for returning physical page offset value + * + * It uses drm_i915_gem_object's internal DMA mapped scatterlist lookup function + * as i915_gem_object_page_iter and calls __i915_gem_object_page_iter_get_sg(). + * + * Returns: + * The target scatterlist pointer and the target page position. + * + * Recommended to use wrapper macro: i915_gem_object_get_sg_dma() + * See also __i915_gem_object_page_iter_get_sg() + */ static inline struct scatterlist * -i915_gem_object_get_sg_dma(struct drm_i915_gem_object *obj, - unsigned int n, - unsigned int *offset) +__i915_gem_object_get_sg_dma(struct drm_i915_gem_object *obj, pgoff_t n, + unsigned int *offset) { - return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset, true); + return __i915_gem_object_page_iter_get_sg(obj, &obj->mm.get_dma_page, n, offset); } +/** + * i915_gem_object_get_sg_dma - wrapper macro for __i915_gem_object_get_sg_dma() + * @obj: i915 GEM buffer object + * @n: page offset + * @offset: searched physical offset, + * it will be used for returning physical page offset value + * + * Returns: + * The target scatterlist pointer and the target page position. + * + * In order to avoid the truncation of the input parameter, it checks the page + * offset n's type from the input parameter before calling + * __i915_gem_object_get_sg_dma(). + * See also __i915_gem_object_page_iter_get_sg() + */ +#define i915_gem_object_get_sg_dma(obj, n, offset) ({ \ + static_assert(castable_to_type(n, pgoff_t)); \ + __i915_gem_object_get_sg_dma(obj, n, offset); \ +}) + +/** + * __i915_gem_object_get_page - helper to find the target page with a page offset + * @obj: i915 GEM buffer object + * @n: page offset + * + * It uses drm_i915_gem_object's internal shmem scatterlist lookup function as + * i915_gem_object_page_iter and calls __i915_gem_object_page_iter_get_sg() + * internally. + * + * Returns: + * The target page pointer. + * + * Recommended to use wrapper macro: i915_gem_object_get_page() + * See also __i915_gem_object_page_iter_get_sg() + */ struct page * -i915_gem_object_get_page(struct drm_i915_gem_object *obj, - unsigned int n); +__i915_gem_object_get_page(struct drm_i915_gem_object *obj, pgoff_t n); +/** + * i915_gem_object_get_page - wrapper macro for __i915_gem_object_get_page + * @obj: i915 GEM buffer object + * @n: page offset + * + * Returns: + * The target page pointer. + * + * In order to avoid the truncation of the input parameter, it checks the page + * offset n's type from the input parameter before calling + * __i915_gem_object_get_page(). + * See also __i915_gem_object_page_iter_get_sg() + */ +#define i915_gem_object_get_page(obj, n) ({ \ + static_assert(castable_to_type(n, pgoff_t)); \ + __i915_gem_object_get_page(obj, n); \ +}) + +/** + * __i915_gem_object_get_dirty_page - helper to find the target page with a page + * offset + * @obj: i915 GEM buffer object + * @n: page offset + * + * It works like i915_gem_object_get_page(), but it marks the returned page dirty. + * + * Returns: + * The target page pointer. + * + * Recommended to use wrapper macro: i915_gem_object_get_dirty_page() + * See also __i915_gem_object_page_iter_get_sg() and __i915_gem_object_get_page() + */ struct page * -i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, - unsigned int n); +__i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, pgoff_t n); + +/** + * i915_gem_object_get_dirty_page - wrapper macro for __i915_gem_object_get_dirty_page + * @obj: i915 GEM buffer object + * @n: page offset + * + * Returns: + * The target page pointer. + * + * In order to avoid the truncation of the input parameter, it checks the page + * offset n's type from the input parameter before calling + * __i915_gem_object_get_dirty_page(). + * See also __i915_gem_object_page_iter_get_sg() and __i915_gem_object_get_page() + */ +#define i915_gem_object_get_dirty_page(obj, n) ({ \ + static_assert(castable_to_type(n, pgoff_t)); \ + __i915_gem_object_get_dirty_page(obj, n); \ +}) +/** + * __i915_gem_object_get_dma_address_len - helper to get bus addresses of + * targeted DMA mapped scatterlist from i915 GEM buffer object and it's length + * @obj: i915 GEM buffer object + * @n: page offset + * @len: DMA mapped scatterlist's DMA bus addresses length to return + * + * Returns: + * Bus addresses of targeted DMA mapped scatterlist + * + * Recommended to use wrapper macro: i915_gem_object_get_dma_address_len() + * See also __i915_gem_object_page_iter_get_sg() and __i915_gem_object_get_sg_dma() + */ dma_addr_t -i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, - unsigned long n, - unsigned int *len); +__i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, pgoff_t n, + unsigned int *len); + +/** + * i915_gem_object_get_dma_address_len - wrapper macro for + * __i915_gem_object_get_dma_address_len + * @obj: i915 GEM buffer object + * @n: page offset + * @len: DMA mapped scatterlist's DMA bus addresses length to return + * + * Returns: + * Bus addresses of targeted DMA mapped scatterlist + * + * In order to avoid the truncation of the input parameter, it checks the page + * offset n's type from the input parameter before calling + * __i915_gem_object_get_dma_address_len(). + * See also __i915_gem_object_page_iter_get_sg() and + * __i915_gem_object_get_dma_address_len() + */ +#define i915_gem_object_get_dma_address_len(obj, n, len) ({ \ + static_assert(castable_to_type(n, pgoff_t)); \ + __i915_gem_object_get_dma_address_len(obj, n, len); \ +}) +/** + * __i915_gem_object_get_dma_address - helper to get bus addresses of + * targeted DMA mapped scatterlist from i915 GEM buffer object + * @obj: i915 GEM buffer object + * @n: page offset + * + * Returns: + * Bus addresses of targeted DMA mapped scatterlis + * + * Recommended to use wrapper macro: i915_gem_object_get_dma_address() + * See also __i915_gem_object_page_iter_get_sg() and __i915_gem_object_get_sg_dma() + */ dma_addr_t -i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, - unsigned long n); +__i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, pgoff_t n); + +/** + * i915_gem_object_get_dma_address - wrapper macro for + * __i915_gem_object_get_dma_address + * @obj: i915 GEM buffer object + * @n: page offset + * + * Returns: + * Bus addresses of targeted DMA mapped scatterlist + * + * In order to avoid the truncation of the input parameter, it checks the page + * offset n's type from the input parameter before calling + * __i915_gem_object_get_dma_address(). + * See also __i915_gem_object_page_iter_get_sg() and + * __i915_gem_object_get_dma_address() + */ +#define i915_gem_object_get_dma_address(obj, n) ({ \ + static_assert(castable_to_type(n, pgoff_t)); \ + __i915_gem_object_get_dma_address(obj, n); \ +}) void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, struct sg_table *pages); 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 ab4c2f90a564..19c9bdd8f905 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -10,7 +10,7 @@ #include <linux/mmu_notifier.h> #include <drm/drm_gem.h> -#include <drm/ttm/ttm_bo_api.h> +#include <drm/ttm/ttm_bo.h> #include <uapi/drm/i915_drm.h> #include "i915_active.h" diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 05a27723ebb8..ecd86130b74f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -521,14 +521,16 @@ void __i915_gem_object_release_map(struct drm_i915_gem_object *obj) } struct scatterlist * -__i915_gem_object_get_sg(struct drm_i915_gem_object *obj, - struct i915_gem_object_page_iter *iter, - unsigned int n, - unsigned int *offset, - bool dma) +__i915_gem_object_page_iter_get_sg(struct drm_i915_gem_object *obj, + struct i915_gem_object_page_iter *iter, + pgoff_t n, + unsigned int *offset) + { - struct scatterlist *sg; + const bool dma = iter == &obj->mm.get_dma_page || + iter == &obj->ttm.get_io_page; unsigned int idx, count; + struct scatterlist *sg; might_sleep(); GEM_BUG_ON(n >= obj->base.size >> PAGE_SHIFT); @@ -636,7 +638,7 @@ lookup: } struct page * -i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n) +__i915_gem_object_get_page(struct drm_i915_gem_object *obj, pgoff_t n) { struct scatterlist *sg; unsigned int offset; @@ -649,8 +651,7 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n) /* Like i915_gem_object_get_page(), but mark the returned page dirty */ struct page * -i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, - unsigned int n) +__i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, pgoff_t n) { struct page *page; @@ -662,9 +663,8 @@ i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, } dma_addr_t -i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, - unsigned long n, - unsigned int *len) +__i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, + pgoff_t n, unsigned int *len) { struct scatterlist *sg; unsigned int offset; @@ -678,8 +678,7 @@ i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, } dma_addr_t -i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, - unsigned long n) +__i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, pgoff_t n) { return i915_gem_object_get_dma_address_len(obj, n, NULL); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 68453572275b..76efe98eaa14 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -28,6 +28,10 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) void *dst; int i; + /* Contiguous chunk, with a single scatterlist element */ + if (overflows_type(obj->base.size, sg->length)) + return -E2BIG; + if (GEM_WARN_ON(i915_gem_object_needs_bit17_swizzle(obj))) return -EINVAL; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 9c759df700ca..37d1efcd3ca6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -60,7 +60,7 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, struct address_space *mapping, unsigned int max_segment) { - const unsigned long page_count = size / PAGE_SIZE; + unsigned int page_count; /* restricted by sg_alloc_table */ unsigned long i; struct scatterlist *sg; struct page *page; @@ -68,6 +68,10 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, gfp_t noreclaim; int ret; + if (overflows_type(size / PAGE_SIZE, page_count)) + return -E2BIG; + + page_count = size / PAGE_SIZE; /* * If there's no chance of allocating enough pages for the whole * object, bail early. @@ -193,7 +197,6 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct intel_memory_region *mem = obj->mm.region; struct address_space *mapping = obj->base.filp->f_mapping; - const unsigned long page_count = obj->base.size / PAGE_SIZE; unsigned int max_segment = i915_sg_segment_size(i915->drm.dev); struct sg_table *st; struct sgt_iter sgt_iter; @@ -235,8 +238,8 @@ rebuild_st: goto rebuild_st; } else { dev_warn(i915->drm.dev, - "Failed to DMA remap %lu pages\n", - page_count); + "Failed to DMA remap %zu pages\n", + obj->base.size >> PAGE_SHIFT); goto err_pages; } } @@ -538,6 +541,20 @@ static int __create_shmem(struct drm_i915_private *i915, drm_gem_private_object_init(&i915->drm, obj, size); + /* XXX: The __shmem_file_setup() function returns -EINVAL if size is + * greater than MAX_LFS_FILESIZE. + * To handle the same error as other code that returns -E2BIG when + * the size is too large, we add a code that returns -E2BIG when the + * size is larger than the size that can be handled. + * If BITS_PER_LONG is 32, size > MAX_LFS_FILESIZE is always false, + * so we only needs to check when BITS_PER_LONG is 64. + * If BITS_PER_LONG is 32, E2BIG checks are processed when + * i915_gem_object_size_2big() is called before init_object() callback + * is called. + */ + if (BITS_PER_LONG == 64 && size > MAX_LFS_FILESIZE) + return -E2BIG; + if (i915->mm.gemfs) filp = shmem_file_setup_with_mnt(i915->mm.gemfs, "i915", size, flags); @@ -579,7 +596,7 @@ static int shmem_object_init(struct intel_memory_region *mem, mapping_set_gfp_mask(mapping, mask); GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM)); - i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, 0); + i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, flags); obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE; obj->write_domain = I915_GEM_DOMAIN_CPU; obj->read_domains = I915_GEM_DOMAIN_CPU; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 8dc5c8874d8a..b1672e054b21 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -400,7 +400,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr mutex_lock(&to_gt(i915)->ggtt->vm.mutex); list_for_each_entry_safe(vma, next, &to_gt(i915)->ggtt->vm.bound_list, vm_link) { - unsigned long count = vma->node.size >> PAGE_SHIFT; + unsigned long count = i915_vma_size(vma) >> PAGE_SHIFT; struct drm_i915_gem_object *obj = vma->obj; if (!vma->iomap || i915_vma_is_active(vma)) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index bc9521078807..90a967374b1a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -110,9 +110,7 @@ static int adjust_stolen(struct drm_i915_private *i915, else ggtt_start &= PGTBL_ADDRESS_LO_MASK; - ggtt_res = - (struct resource) DEFINE_RES_MEM(ggtt_start, - ggtt_total_entries(ggtt) * 4); + ggtt_res = DEFINE_RES_MEM(ggtt_start, ggtt_total_entries(ggtt) * 4); if (ggtt_res.start >= stolen[0].start && ggtt_res.start < stolen[0].end) stolen[0].end = ggtt_res.start; @@ -211,7 +209,7 @@ static void g4x_get_stolen_reserved(struct drm_i915_private *i915, IS_GM45(i915) ? CTG_STOLEN_RESERVED : ELK_STOLEN_RESERVED); - resource_size_t stolen_top = i915->dsm.end + 1; + resource_size_t stolen_top = i915->dsm.stolen.end + 1; drm_dbg(&i915->drm, "%s_STOLEN_RESERVED = %08x\n", IS_GM45(i915) ? "CTG" : "ELK", reg_val); @@ -276,7 +274,7 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *i915, resource_size_t *size) { u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED); - resource_size_t stolen_top = i915->dsm.end + 1; + resource_size_t stolen_top = i915->dsm.stolen.end + 1; drm_dbg(&i915->drm, "GEN6_STOLEN_RESERVED = %08x\n", reg_val); @@ -365,7 +363,7 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *i915, resource_size_t *size) { u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED); - resource_size_t stolen_top = i915->dsm.end + 1; + resource_size_t stolen_top = i915->dsm.stolen.end + 1; drm_dbg(&i915->drm, "GEN6_STOLEN_RESERVED = %08x\n", reg_val); @@ -414,7 +412,7 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915, } /* - * Initialize i915->dsm_reserved to contain the reserved space within the Data + * Initialize i915->dsm.reserved to contain the reserved space within the Data * Stolen Memory. This is a range on the top of DSM that is reserved, not to * be used by driver, so must be excluded from the region passed to the * allocator later. In the spec this is also called as WOPCM. @@ -430,7 +428,7 @@ static int init_reserved_stolen(struct drm_i915_private *i915) resource_size_t reserved_size; int ret = 0; - stolen_top = i915->dsm.end + 1; + stolen_top = i915->dsm.stolen.end + 1; reserved_base = stolen_top; reserved_size = 0; @@ -471,13 +469,12 @@ static int init_reserved_stolen(struct drm_i915_private *i915) goto bail_out; } - i915->dsm_reserved = - (struct resource)DEFINE_RES_MEM(reserved_base, reserved_size); + i915->dsm.reserved = DEFINE_RES_MEM(reserved_base, reserved_size); - if (!resource_contains(&i915->dsm, &i915->dsm_reserved)) { + if (!resource_contains(&i915->dsm.stolen, &i915->dsm.reserved)) { drm_err(&i915->drm, "Stolen reserved area %pR outside stolen memory %pR\n", - &i915->dsm_reserved, &i915->dsm); + &i915->dsm.reserved, &i915->dsm.stolen); ret = -EINVAL; goto bail_out; } @@ -485,8 +482,7 @@ static int init_reserved_stolen(struct drm_i915_private *i915) return 0; bail_out: - i915->dsm_reserved = - (struct resource)DEFINE_RES_MEM(reserved_base, 0); + i915->dsm.reserved = DEFINE_RES_MEM(reserved_base, 0); return ret; } @@ -517,27 +513,27 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) if (request_smem_stolen(i915, &mem->region)) return -ENOSPC; - i915->dsm = mem->region; + i915->dsm.stolen = mem->region; if (init_reserved_stolen(i915)) return -ENOSPC; /* Exclude the reserved region from driver use */ - mem->region.end = i915->dsm_reserved.start - 1; + mem->region.end = i915->dsm.reserved.start - 1; mem->io_size = min(mem->io_size, resource_size(&mem->region)); - i915->stolen_usable_size = resource_size(&mem->region); + i915->dsm.usable_size = resource_size(&mem->region); drm_dbg(&i915->drm, "Memory reserved for graphics device: %lluK, usable: %lluK\n", - (u64)resource_size(&i915->dsm) >> 10, - (u64)i915->stolen_usable_size >> 10); + (u64)resource_size(&i915->dsm.stolen) >> 10, + (u64)i915->dsm.usable_size >> 10); - if (i915->stolen_usable_size == 0) + if (i915->dsm.usable_size == 0) return -ENOSPC; /* Basic memrange allocator for stolen space. */ - drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size); + drm_mm_init(&i915->mm.stolen, 0, i915->dsm.usable_size); return 0; } @@ -587,7 +583,7 @@ i915_pages_create_for_stolen(struct drm_device *dev, struct sg_table *st; struct scatterlist *sg; - GEM_BUG_ON(range_overflows(offset, size, resource_size(&i915->dsm))); + GEM_BUG_ON(range_overflows(offset, size, resource_size(&i915->dsm.stolen))); /* We hide that we have no struct page backing our stolen object * by wrapping the contiguous physical allocation with a fake @@ -607,7 +603,7 @@ i915_pages_create_for_stolen(struct drm_device *dev, sg->offset = 0; sg->length = size; - sg_dma_address(sg) = (dma_addr_t)i915->dsm.start + offset; + sg_dma_address(sg) = (dma_addr_t)i915->dsm.stolen.start + offset; sg_dma_len(sg) = size; return st; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index fd42b89b7162..a049ca0b7980 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -168,11 +168,11 @@ static bool i915_vma_fence_prepare(struct i915_vma *vma, return true; size = i915_gem_fence_size(i915, vma->size, tiling_mode, stride); - if (vma->node.size < size) + if (i915_vma_size(vma) < size) return false; alignment = i915_gem_fence_alignment(i915, vma->size, tiling_mode, stride); - if (!IS_ALIGNED(vma->node.start, alignment)) + if (!IS_ALIGNED(i915_ggtt_offset(vma), alignment)) return false; return true; @@ -305,10 +305,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, spin_unlock(&obj->vma.lock); obj->tiling_and_stride = tiling | stride; - i915_gem_object_unlock(obj); - - /* Force the fence to be reacquired for GTT access */ - i915_gem_object_release_mmap_gtt(obj); /* Try to preallocate memory required to save swizzling on put-pages */ if (i915_gem_object_needs_bit17_swizzle(obj)) { @@ -321,6 +317,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, obj->bit_17 = NULL; } + i915_gem_object_unlock(obj); + + /* Force the fence to be reacquired for GTT access */ + i915_gem_object_release_mmap_gtt(obj); + return 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 1e50fb0d6bfc..7420276827a5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -5,8 +5,8 @@ #include <linux/shmem_fs.h> -#include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_tt.h> #include <drm/drm_buddy.h> #include "i915_drv.h" @@ -140,13 +140,16 @@ i915_ttm_place_from_region(const struct intel_memory_region *mr, if (flags & I915_BO_ALLOC_CONTIGUOUS) place->flags |= TTM_PL_FLAG_CONTIGUOUS; if (offset != I915_BO_INVALID_OFFSET) { + WARN_ON(overflows_type(offset >> PAGE_SHIFT, place->fpfn)); place->fpfn = offset >> PAGE_SHIFT; + WARN_ON(overflows_type(place->fpfn + (size >> PAGE_SHIFT), place->lpfn)); place->lpfn = place->fpfn + (size >> PAGE_SHIFT); } else if (mr->io_size && mr->io_size < mr->total) { if (flags & I915_BO_ALLOC_GPU_ONLY) { place->flags |= TTM_PL_FLAG_TOPDOWN; } else { place->fpfn = 0; + WARN_ON(overflows_type(mr->io_size >> PAGE_SHIFT, place->lpfn)); place->lpfn = mr->io_size >> PAGE_SHIFT; } } @@ -271,8 +274,6 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, { struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915), bdev); - struct ttm_resource_manager *man = - ttm_manager_type(bo->bdev, bo->resource->mem_type); struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); unsigned long ccs_pages = 0; enum ttm_caching caching; @@ -286,8 +287,8 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, if (!i915_tt) return NULL; - if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && - man->use_tt) + if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && (!bo->resource || + ttm_manager_type(bo->bdev, bo->resource->mem_type)->use_tt)) page_flags |= TTM_TT_FLAG_ZERO_ALLOC; caching = i915_ttm_select_tt_caching(obj); @@ -599,13 +600,16 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, static int i915_ttm_truncate(struct drm_i915_gem_object *obj) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); - int err; + long err; WARN_ON_ONCE(obj->mm.madv == I915_MADV_WILLNEED); - err = ttm_bo_wait(bo, true, false); - if (err) + err = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, + true, 15 * HZ); + if (err < 0) return err; + if (err == 0) + return -EBUSY; err = i915_ttm_move_notify(bo); if (err) @@ -689,7 +693,7 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo, GEM_WARN_ON(bo->ttm); base = obj->mm.region->iomap.base - obj->mm.region->region.start; - sg = __i915_gem_object_get_sg(obj, &obj->ttm.get_io_page, page_offset, &ofs, true); + sg = i915_gem_object_page_iter_get_sg(obj, &obj->ttm.get_io_page, page_offset, &ofs); return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs; } @@ -832,6 +836,10 @@ static int i915_ttm_get_pages(struct drm_i915_gem_object *obj) struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS]; struct ttm_placement placement; + /* restricted by sg_alloc_table */ + if (overflows_type(obj->base.size >> PAGE_SHIFT, unsigned int)) + return -E2BIG; + GEM_BUG_ON(obj->mm.n_placements > I915_TTM_MAX_PLACEMENTS); /* Move to the requested placement. */ @@ -1048,7 +1056,26 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - if (!i915_ttm_resource_mappable(bo->resource)) { + /* + * This must be swapped out with shmem ttm_tt (pipeline-gutting). + * Calling ttm_bo_validate() here with TTM_PL_SYSTEM should only go as + * far as far doing a ttm_bo_move_null(), which should skip all the + * other junk. + */ + if (!bo->resource) { + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = true, /* should be idle already */ + }; + + GEM_BUG_ON(!bo->ttm || !(bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED)); + + ret = ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx); + if (ret) { + dma_resv_unlock(bo->base.resv); + return VM_FAULT_SIGBUS; + } + } else if (!i915_ttm_resource_mappable(bo->resource)) { int err = -ENODEV; int i; @@ -1302,6 +1329,17 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, ret = ttm_bo_init_reserved(&i915->bdev, i915_gem_to_ttm(obj), bo_type, &i915_sys_placement, page_size >> PAGE_SHIFT, &ctx, NULL, NULL, i915_ttm_bo_destroy); + + /* + * XXX: The ttm_bo_init_reserved() functions returns -ENOSPC if the size + * is too big to add vma. The direct function that returns -ENOSPC is + * drm_mm_insert_node_in_range(). To handle the same error as other code + * that returns -E2BIG when the size is too large, it converts -ENOSPC to + * -E2BIG. + */ + if (size >> PAGE_SHIFT > INT_MAX && ret == -ENOSPC) + ret = -E2BIG; + if (ret) return i915_ttm_err_to_gem(ret); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c index f59f812dc6d2..76dd9e5e1a8b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -3,7 +3,7 @@ * Copyright © 2021 Intel Corporation */ -#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_tt.h> #include "i915_deps.h" #include "i915_drv.h" @@ -103,7 +103,27 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) { struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); unsigned int cache_level; + unsigned int mem_flags; unsigned int i; + int mem_type; + + /* + * We might have been purged (or swapped out) if the resource is NULL, + * in which case the SYSTEM placement is the closest match to describe + * the current domain. If the object is ever used in this state then we + * will require moving it again. + */ + if (!bo->resource) { + mem_flags = I915_BO_FLAG_STRUCT_PAGE; + mem_type = I915_PL_SYSTEM; + cache_level = I915_CACHE_NONE; + } else { + mem_flags = i915_ttm_cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM : + I915_BO_FLAG_STRUCT_PAGE; + mem_type = bo->resource->mem_type; + cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource, + bo->ttm); + } /* * If object was moved to an allowable region, update the object @@ -111,11 +131,11 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) * in an allowable region, it's evicted and we don't update the * object region. */ - if (intel_region_to_ttm_type(obj->mm.region) != bo->resource->mem_type) { + if (intel_region_to_ttm_type(obj->mm.region) != mem_type) { for (i = 0; i < obj->mm.n_placements; ++i) { struct intel_memory_region *mr = obj->mm.placements[i]; - if (intel_region_to_ttm_type(mr) == bo->resource->mem_type && + if (intel_region_to_ttm_type(mr) == mem_type && mr != obj->mm.region) { i915_gem_object_release_memory_region(obj); i915_gem_object_init_memory_region(obj, mr); @@ -125,12 +145,8 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj) } obj->mem_flags &= ~(I915_BO_FLAG_STRUCT_PAGE | I915_BO_FLAG_IOMEM); + obj->mem_flags |= mem_flags; - obj->mem_flags |= i915_ttm_cpu_maps_iomem(bo->resource) ? I915_BO_FLAG_IOMEM : - I915_BO_FLAG_STRUCT_PAGE; - - cache_level = i915_ttm_cache_level(to_i915(bo->base.dev), bo->resource, - bo->ttm); i915_gem_object_set_cache_coherency(obj, cache_level); } @@ -565,6 +581,32 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, return 0; } + if (!bo->resource) { + if (dst_mem->mem_type != TTM_PL_SYSTEM) { + hop->mem_type = TTM_PL_SYSTEM; + hop->flags = TTM_PL_FLAG_TEMPORARY; + return -EMULTIHOP; + } + + /* + * This is only reached when first creating the object, or if + * the object was purged or swapped out (pipeline-gutting). For + * the former we can safely skip all of the below since we are + * only using a dummy SYSTEM placement here. And with the latter + * we will always re-enter here with bo->resource set correctly + * (as per the above), since this is part of a multi-hop + * sequence, where at the end we can do the move for real. + * + * The special case here is when the dst_mem is TTM_PL_SYSTEM, + * which doens't require any kind of move, so it should be safe + * to skip all the below and call ttm_bo_move_null() here, where + * the caller in __i915_ttm_get_pages() will take care of the + * rest, since we should have a valid ttm_tt. + */ + ttm_bo_move_null(bo, dst_mem); + return 0; + } + ret = i915_ttm_move_notify(bo); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 9348b1804d53..1d3ebdf4069b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -128,12 +128,16 @@ static void i915_gem_object_userptr_drop_ref(struct drm_i915_gem_object *obj) static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) { - const unsigned long num_pages = obj->base.size >> PAGE_SHIFT; unsigned int max_segment = i915_sg_segment_size(obj->base.dev->dev); struct sg_table *st; struct page **pvec; + unsigned int num_pages; /* limited by sg_alloc_table_from_pages_segment */ int ret; + if (overflows_type(obj->base.size >> PAGE_SHIFT, num_pages)) + return -E2BIG; + + num_pages = obj->base.size >> PAGE_SHIFT; st = kmalloc(sizeof(*st), GFP_KERNEL); if (!st) return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c index cbd9b624a788..bac957755068 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c @@ -29,11 +29,15 @@ static int huge_get_pages(struct drm_i915_gem_object *obj) { #define GFP (GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL) const unsigned long nreal = obj->scratch / PAGE_SIZE; - const unsigned long npages = obj->base.size / PAGE_SIZE; + unsigned int npages; /* restricted by sg_alloc_table */ struct scatterlist *sg, *src, *end; struct sg_table *pages; unsigned long n; + if (overflows_type(obj->base.size / PAGE_SIZE, npages)) + return -E2BIG; + + npages = obj->base.size / PAGE_SIZE; pages = kmalloc(sizeof(*pages), GFP); if (!pages) return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index beaf27e09e8a..defece0bcb81 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -84,6 +84,10 @@ static int get_huge_pages(struct drm_i915_gem_object *obj) unsigned int sg_page_sizes; u64 rem; + /* restricted by sg_alloc_table */ + if (overflows_type(obj->base.size >> PAGE_SHIFT, unsigned int)) + return -E2BIG; + st = kmalloc(sizeof(*st), GFP); if (!st) return -ENOMEM; @@ -212,6 +216,10 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) struct scatterlist *sg; u64 rem; + /* restricted by sg_alloc_table */ + if (overflows_type(obj->base.size >> PAGE_SHIFT, unsigned int)) + return -E2BIG; + st = kmalloc(sizeof(*st), GFP); if (!st) return -ENOMEM; @@ -400,7 +408,7 @@ static int igt_check_page_sizes(struct i915_vma *vma) * Maintaining alignment is required to utilise huge pages in the ppGGT. */ if (i915_gem_object_is_lmem(obj) && - IS_ALIGNED(vma->node.start, SZ_2M) && + IS_ALIGNED(i915_vma_offset(vma), SZ_2M) && vma->page_sizes.sg & SZ_2M && vma->resource->page_sizes_gtt < SZ_2M) { pr_err("gtt pages mismatch for LMEM, expected 2M GTT pages, sg(%u), gtt(%u)\n", @@ -1847,7 +1855,7 @@ static int igt_shrink_thp(void *arg) I915_SHRINK_ACTIVE); i915_vma_unpin(vma); if (err) - goto out_put; + goto out_wf; /* * Now that the pages are *unpinned* shrinking should invoke @@ -1863,19 +1871,19 @@ static int igt_shrink_thp(void *arg) pr_err("unexpected pages mismatch, should_swap=%s\n", str_yes_no(should_swap)); err = -EINVAL; - goto out_put; + goto out_wf; } if (should_swap == (obj->mm.page_sizes.sg || obj->mm.page_sizes.phys)) { pr_err("unexpected residual page-size bits, should_swap=%s\n", str_yes_no(should_swap)); err = -EINVAL; - goto out_put; + goto out_wf; } err = i915_vma_pin(vma, 0, 0, flags); if (err) - goto out_put; + goto out_wf; while (n--) { err = cpu_check(obj, n, 0xdeadbeaf); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index 692a16914ca0..3bb1f7f0110e 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -194,12 +194,12 @@ static int prepare_blit(const struct tiled_blits *t, *cs++ = src_4t | dst_4t | BLT_DEPTH_32 | dst_pitch; *cs++ = 0; *cs++ = t->height << 16 | t->width; - *cs++ = lower_32_bits(dst->vma->node.start); - *cs++ = upper_32_bits(dst->vma->node.start); + *cs++ = lower_32_bits(i915_vma_offset(dst->vma)); + *cs++ = upper_32_bits(i915_vma_offset(dst->vma)); *cs++ = 0; *cs++ = src_pitch; - *cs++ = lower_32_bits(src->vma->node.start); - *cs++ = upper_32_bits(src->vma->node.start); + *cs++ = lower_32_bits(i915_vma_offset(src->vma)); + *cs++ = upper_32_bits(i915_vma_offset(src->vma)); } else { if (ver >= 6) { *cs++ = MI_LOAD_REGISTER_IMM(1); @@ -240,14 +240,14 @@ static int prepare_blit(const struct tiled_blits *t, *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | dst_pitch; *cs++ = 0; *cs++ = t->height << 16 | t->width; - *cs++ = lower_32_bits(dst->vma->node.start); + *cs++ = lower_32_bits(i915_vma_offset(dst->vma)); if (use_64b_reloc) - *cs++ = upper_32_bits(dst->vma->node.start); + *cs++ = upper_32_bits(i915_vma_offset(dst->vma)); *cs++ = 0; *cs++ = src_pitch; - *cs++ = lower_32_bits(src->vma->node.start); + *cs++ = lower_32_bits(i915_vma_offset(src->vma)); if (use_64b_reloc) - *cs++ = upper_32_bits(src->vma->node.start); + *cs++ = upper_32_bits(i915_vma_offset(src->vma)); } *cs++ = MI_BATCH_BUFFER_END; @@ -462,7 +462,7 @@ static int pin_buffer(struct i915_vma *vma, u64 addr) { int err; - if (drm_mm_node_allocated(&vma->node) && vma->node.start != addr) { + if (drm_mm_node_allocated(&vma->node) && i915_vma_offset(vma) != addr) { err = i915_vma_unbind_unlocked(vma); if (err) return err; @@ -472,6 +472,7 @@ static int pin_buffer(struct i915_vma *vma, u64 addr) if (err) return err; + GEM_BUG_ON(i915_vma_offset(vma) != addr); return 0; } @@ -518,8 +519,8 @@ tiled_blit(struct tiled_blits *t, err = igt_vma_move_to_active_unlocked(dst->vma, rq, 0); if (!err) err = rq->engine->emit_bb_start(rq, - t->batch->node.start, - t->batch->node.size, + i915_vma_offset(t->batch), + i915_vma_size(t->batch), 0); i915_request_get(rq); i915_request_add(rq); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c index c228fe4aba50..3bef1beec7cb 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c @@ -222,7 +222,7 @@ static int gpu_set(struct context *ctx, unsigned long offset, u32 v) } if (GRAPHICS_VER(ctx->engine->i915) >= 8) { - *cs++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22; + *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; *cs++ = lower_32_bits(i915_ggtt_offset(vma) + offset); *cs++ = upper_32_bits(i915_ggtt_offset(vma) + offset); *cs++ = v; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index a0ff51d71d07..a81fa6a20f5a 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -469,7 +469,8 @@ static int gpu_fill(struct intel_context *ce, static int cpu_fill(struct drm_i915_gem_object *obj, u32 value) { const bool has_llc = HAS_LLC(to_i915(obj->base.dev)); - unsigned int n, m, need_flush; + unsigned int need_flush; + unsigned long n, m; int err; i915_gem_object_lock(obj, NULL); @@ -499,7 +500,8 @@ out: static noinline int cpu_check(struct drm_i915_gem_object *obj, unsigned int idx, unsigned int max) { - unsigned int n, m, needs_flush; + unsigned int needs_flush; + unsigned long n; int err; i915_gem_object_lock(obj, NULL); @@ -508,7 +510,7 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj, goto out_unlock; for (n = 0; n < real_page_count(obj); n++) { - u32 *map; + u32 *map, m; map = kmap_atomic(i915_gem_object_get_page(obj, n)); if (needs_flush & CLFLUSH_BEFORE) @@ -516,7 +518,7 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj, for (m = 0; m < max; m++) { if (map[m] != m) { - pr_err("%pS: Invalid value at object %d page %d/%ld, offset %d/%d: found %x expected %x\n", + pr_err("%pS: Invalid value at object %d page %ld/%ld, offset %d/%d: found %x expected %x\n", __builtin_return_address(0), idx, n, real_page_count(obj), m, max, map[m], m); @@ -527,7 +529,7 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj, for (; m < DW_PER_PAGE; m++) { if (map[m] != STACK_MAGIC) { - pr_err("%pS: Invalid value at object %d page %d, offset %d: found %x expected %x (uninitialised)\n", + pr_err("%pS: Invalid value at object %d page %ld, offset %d: found %x expected %x (uninitialised)\n", __builtin_return_address(0), idx, n, m, map[m], STACK_MAGIC); err = -EINVAL; @@ -914,8 +916,8 @@ static int rpcs_query_batch(struct drm_i915_gem_object *rpcs, *cmd++ = MI_STORE_REGISTER_MEM_GEN8; *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE(engine->mmio_base)); - *cmd++ = lower_32_bits(vma->node.start); - *cmd++ = upper_32_bits(vma->node.start); + *cmd++ = lower_32_bits(i915_vma_offset(vma)); + *cmd++ = upper_32_bits(i915_vma_offset(vma)); *cmd = MI_BATCH_BUFFER_END; __i915_gem_object_flush_map(rpcs, 0, 64); @@ -999,7 +1001,8 @@ retry: } err = rq->engine->emit_bb_start(rq, - batch->node.start, batch->node.size, + i915_vma_offset(batch), + i915_vma_size(batch), 0); if (err) goto skip_request; @@ -1548,9 +1551,7 @@ static int write_to_scratch(struct i915_gem_context *ctx, goto err_unpin; } - i915_vma_lock(vma); - err = i915_vma_move_to_active(vma, rq, 0); - i915_vma_unlock(vma); + err = igt_vma_move_to_active_unlocked(vma, rq, 0); if (err) goto skip_request; @@ -1560,7 +1561,8 @@ static int write_to_scratch(struct i915_gem_context *ctx, goto skip_request; } - err = engine->emit_bb_start(rq, vma->node.start, vma->node.size, 0); + err = engine->emit_bb_start(rq, i915_vma_offset(vma), + i915_vma_size(vma), 0); if (err) goto skip_request; @@ -1665,7 +1667,7 @@ static int read_from_scratch(struct i915_gem_context *ctx, *cmd++ = offset; *cmd++ = MI_STORE_REGISTER_MEM | MI_USE_GGTT; *cmd++ = reg; - *cmd++ = vma->node.start + result; + *cmd++ = i915_vma_offset(vma) + result; *cmd = MI_BATCH_BUFFER_END; i915_gem_object_flush_map(obj); @@ -1682,9 +1684,7 @@ static int read_from_scratch(struct i915_gem_context *ctx, goto err_unpin; } - i915_vma_lock(vma); - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); - i915_vma_unlock(vma); + err = igt_vma_move_to_active_unlocked(vma, rq, EXEC_OBJECT_WRITE); if (err) goto skip_request; @@ -1694,7 +1694,8 @@ static int read_from_scratch(struct i915_gem_context *ctx, goto skip_request; } - err = engine->emit_bb_start(rq, vma->node.start, vma->node.size, flags); + err = engine->emit_bb_start(rq, i915_vma_offset(vma), + i915_vma_size(vma), flags); if (err) goto skip_request; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 3f658d5717d8..56279908ed30 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -97,11 +97,11 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_gtt_view view; struct i915_vma *vma; + unsigned long offset; unsigned long page; u32 __iomem *io; struct page *p; unsigned int n; - u64 offset; u32 *cpu; int err; @@ -158,7 +158,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, cpu = kmap(p) + offset_in_page(offset); drm_clflush_virt_range(cpu, sizeof(*cpu)); if (*cpu != (u32)page) { - pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%llu + %u [0x%llx]) of 0x%x, found 0x%x\n", + pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%lu + %u [0x%lx]) of 0x%x, found 0x%x\n", page, n, view.partial.offset, view.partial.size, @@ -214,10 +214,10 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj, for_each_prime_number_from(page, 1, npages) { struct i915_gtt_view view = compute_partial_view(obj, page, MIN_CHUNK_PAGES); + unsigned long offset; u32 __iomem *io; struct page *p; unsigned int n; - u64 offset; u32 *cpu; GEM_BUG_ON(view.partial.size > nreal); @@ -254,7 +254,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj, cpu = kmap(p) + offset_in_page(offset); drm_clflush_virt_range(cpu, sizeof(*cpu)); if (*cpu != (u32)page) { - pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%llu + %u [0x%llx]) of 0x%x, found 0x%x\n", + pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%lu + %u [0x%lx]) of 0x%x, found 0x%x\n", page, n, view.partial.offset, view.partial.size, @@ -1609,7 +1609,7 @@ retry: err = i915_vma_move_to_active(vma, rq, 0); - err = engine->emit_bb_start(rq, vma->node.start, 0, 0); + err = engine->emit_bb_start(rq, i915_vma_offset(vma), 0, 0); i915_request_get(rq); i915_request_add(rq); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c index bdf5bb40ccf1..19e374f68ff7 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c @@ -33,10 +33,10 @@ out: static int igt_gem_huge(void *arg) { - const unsigned int nreal = 509; /* just to be awkward */ + const unsigned long nreal = 509; /* just to be awkward */ struct drm_i915_private *i915 = arg; struct drm_i915_gem_object *obj; - unsigned int n; + unsigned long n; int err; /* Basic sanitycheck of our huge fake object allocation */ @@ -49,7 +49,7 @@ static int igt_gem_huge(void *arg) err = i915_gem_object_pin_pages_unlocked(obj); if (err) { - pr_err("Failed to allocate %u pages (%lu total), err=%d\n", + pr_err("Failed to allocate %lu pages (%lu total), err=%d\n", nreal, obj->base.size / PAGE_SIZE, err); goto out; } @@ -57,7 +57,7 @@ static int igt_gem_huge(void *arg) for (n = 0; n < obj->base.size / PAGE_SIZE; n++) { if (i915_gem_object_get_page(obj, n) != i915_gem_object_get_page(obj, n % nreal)) { - pr_err("Page lookup mismatch at index %u [%u]\n", + pr_err("Page lookup mismatch at index %lu [%lu]\n", n, n % nreal); err = -EINVAL; goto out_unpin; diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c index 374b10ac430e..20a232a140b0 100644 --- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c +++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c @@ -62,8 +62,8 @@ igt_emit_store_dw(struct i915_vma *vma, goto err; } - GEM_BUG_ON(offset + (count - 1) * PAGE_SIZE > vma->node.size); - offset += vma->node.start; + GEM_BUG_ON(offset + (count - 1) * PAGE_SIZE > i915_vma_size(vma)); + offset += i915_vma_offset(vma); for (n = 0; n < count; n++) { if (ver >= 8) { @@ -130,15 +130,11 @@ int igt_gpu_fill_dw(struct intel_context *ce, goto err_batch; } - i915_vma_lock(batch); - err = i915_vma_move_to_active(batch, rq, 0); - i915_vma_unlock(batch); + err = igt_vma_move_to_active_unlocked(batch, rq, 0); if (err) goto skip_request; - i915_vma_lock(vma); - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); - i915_vma_unlock(vma); + err = igt_vma_move_to_active_unlocked(vma, rq, EXEC_OBJECT_WRITE); if (err) goto skip_request; @@ -147,7 +143,8 @@ int igt_gpu_fill_dw(struct intel_context *ce, flags |= I915_DISPATCH_SECURE; err = rq->engine->emit_bb_start(rq, - batch->node.start, batch->node.size, + i915_vma_offset(batch), + i915_vma_size(batch), flags); skip_request: diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h index 1379fbc14431..71a3ca8a8865 100644 --- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h +++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h @@ -38,7 +38,7 @@ igt_vma_move_to_active_unlocked(struct i915_vma *vma, struct i915_request *rq, int err; i915_vma_lock(vma); - err = _i915_vma_move_to_active(vma, rq, &rq->fence, flags); + err = i915_vma_move_to_active(vma, rq, flags); i915_vma_unlock(vma); return err; } |