diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gem.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_gem.c | 149 |
1 files changed, 71 insertions, 78 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 0b2e167..a087e1b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -31,6 +31,7 @@ #include "i915_drv.h" #include "i915_trace.h" #include "intel_drv.h" +#include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/pci.h> @@ -354,13 +355,12 @@ i915_gem_shmem_pread_fast(struct drm_device *dev, * page_offset = offset within page * page_length = bytes to copy for this page */ - page_offset = offset & (PAGE_SIZE-1); + page_offset = offset_in_page(offset); page_length = remain; if ((page_offset + remain) > PAGE_SIZE) page_length = PAGE_SIZE - page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); @@ -453,9 +453,9 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, * data_page_offset = offset with data_page_index page. * page_length = bytes to copy for this page */ - shmem_page_offset = offset & ~PAGE_MASK; + shmem_page_offset = offset_in_page(offset); data_page_index = data_ptr / PAGE_SIZE - first_data_page; - data_page_offset = data_ptr & ~PAGE_MASK; + data_page_offset = offset_in_page(data_ptr); page_length = remain; if ((shmem_page_offset + page_length) > PAGE_SIZE) @@ -463,10 +463,11 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, if ((data_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - data_page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); - if (IS_ERR(page)) - return PTR_ERR(page); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + goto out; + } if (do_bit17_swizzling) { slow_shmem_bit17_copy(page, @@ -638,8 +639,8 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, * page_offset = offset within page * page_length = bytes to copy for this page */ - page_base = (offset & ~(PAGE_SIZE-1)); - page_offset = offset & (PAGE_SIZE-1); + page_base = offset & PAGE_MASK; + page_offset = offset_in_page(offset); page_length = remain; if ((page_offset + remain) > PAGE_SIZE) page_length = PAGE_SIZE - page_offset; @@ -650,7 +651,6 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, */ if (fast_user_write(dev_priv->mm.gtt_mapping, page_base, page_offset, user_data, page_length)) - return -EFAULT; remain -= page_length; @@ -730,9 +730,9 @@ i915_gem_gtt_pwrite_slow(struct drm_device *dev, * page_length = bytes to copy for this page */ gtt_page_base = offset & PAGE_MASK; - gtt_page_offset = offset & ~PAGE_MASK; + gtt_page_offset = offset_in_page(offset); data_page_index = data_ptr / PAGE_SIZE - first_data_page; - data_page_offset = data_ptr & ~PAGE_MASK; + data_page_offset = offset_in_page(data_ptr); page_length = remain; if ((gtt_page_offset + page_length) > PAGE_SIZE) @@ -791,13 +791,12 @@ i915_gem_shmem_pwrite_fast(struct drm_device *dev, * page_offset = offset within page * page_length = bytes to copy for this page */ - page_offset = offset & (PAGE_SIZE-1); + page_offset = offset_in_page(offset); page_length = remain; if ((page_offset + remain) > PAGE_SIZE) page_length = PAGE_SIZE - page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); @@ -896,9 +895,9 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, * data_page_offset = offset with data_page_index page. * page_length = bytes to copy for this page */ - shmem_page_offset = offset & ~PAGE_MASK; + shmem_page_offset = offset_in_page(offset); data_page_index = data_ptr / PAGE_SIZE - first_data_page; - data_page_offset = data_ptr & ~PAGE_MASK; + data_page_offset = offset_in_page(data_ptr); page_length = remain; if ((shmem_page_offset + page_length) > PAGE_SIZE) @@ -906,8 +905,7 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, if ((data_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - data_page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; @@ -1218,11 +1216,11 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ret = i915_gem_object_bind_to_gtt(obj, 0, true); if (ret) goto unlock; - } - ret = i915_gem_object_set_to_gtt_domain(obj, write); - if (ret) - goto unlock; + ret = i915_gem_object_set_to_gtt_domain(obj, write); + if (ret) + goto unlock; + } if (obj->tiling_mode == I915_TILING_NONE) ret = i915_gem_object_put_fence(obj); @@ -1376,25 +1374,24 @@ i915_gem_free_mmap_offset(struct drm_i915_gem_object *obj) } static uint32_t -i915_gem_get_gtt_size(struct drm_i915_gem_object *obj) +i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode) { - struct drm_device *dev = obj->base.dev; - uint32_t size; + uint32_t gtt_size; if (INTEL_INFO(dev)->gen >= 4 || - obj->tiling_mode == I915_TILING_NONE) - return obj->base.size; + tiling_mode == I915_TILING_NONE) + return size; /* Previous chips need a power-of-two fence region when tiling */ if (INTEL_INFO(dev)->gen == 3) - size = 1024*1024; + gtt_size = 1024*1024; else - size = 512*1024; + gtt_size = 512*1024; - while (size < obj->base.size) - size <<= 1; + while (gtt_size < size) + gtt_size <<= 1; - return size; + return gtt_size; } /** @@ -1405,58 +1402,52 @@ i915_gem_get_gtt_size(struct drm_i915_gem_object *obj) * potential fence register mapping. */ static uint32_t -i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj) +i915_gem_get_gtt_alignment(struct drm_device *dev, + uint32_t size, + int tiling_mode) { - struct drm_device *dev = obj->base.dev; - /* * Minimum alignment is 4k (GTT page size), but might be greater * if a fence register is needed for the object. */ if (INTEL_INFO(dev)->gen >= 4 || - obj->tiling_mode == I915_TILING_NONE) + tiling_mode == I915_TILING_NONE) return 4096; /* * Previous chips need to be aligned to the size of the smallest * fence register that can contain the object. */ - return i915_gem_get_gtt_size(obj); + return i915_gem_get_gtt_size(dev, size, tiling_mode); } /** * i915_gem_get_unfenced_gtt_alignment - return required GTT alignment for an * unfenced object - * @obj: object to check + * @dev: the device + * @size: size of the object + * @tiling_mode: tiling mode of the object * * Return the required GTT alignment for an object, only taking into account * unfenced tiled surface requirements. */ uint32_t -i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj) +i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev, + uint32_t size, + int tiling_mode) { - struct drm_device *dev = obj->base.dev; - int tile_height; - /* * Minimum alignment is 4k (GTT page size) for sane hw. */ if (INTEL_INFO(dev)->gen >= 4 || IS_G33(dev) || - obj->tiling_mode == I915_TILING_NONE) + tiling_mode == I915_TILING_NONE) return 4096; - /* - * Older chips need unfenced tiled buffers to be aligned to the left - * edge of an even tile row (where tile rows are counted as if the bo is - * placed in a fenced gtt region). + /* Previous hardware however needs to be aligned to a power-of-two + * tile height. The simplest method for determining this is to reuse + * the power-of-tile object size. */ - if (IS_GEN2(dev) || - (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))) - tile_height = 32; - else - tile_height = 8; - - return tile_height * obj->stride * 2; + return i915_gem_get_gtt_size(dev, size, tiling_mode); } int @@ -1556,12 +1547,10 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj, inode = obj->base.filp->f_path.dentry->d_inode; mapping = inode->i_mapping; + gfpmask |= mapping_gfp_mask(mapping); + for (i = 0; i < page_count; i++) { - page = read_cache_page_gfp(mapping, i, - GFP_HIGHUSER | - __GFP_COLD | - __GFP_RECLAIMABLE | - gfpmask); + page = shmem_read_mapping_page_gfp(mapping, i, gfpmask); if (IS_ERR(page)) goto err_pages; @@ -1699,13 +1688,10 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj) /* Our goal here is to return as much of the memory as * is possible back to the system as we are called from OOM. * To do this we must instruct the shmfs to drop all of its - * backing pages, *now*. Here we mirror the actions taken - * when by shmem_delete_inode() to release the backing store. + * backing pages, *now*. */ inode = obj->base.filp->f_path.dentry->d_inode; - truncate_inode_pages(inode->i_mapping, 0); - if (inode->i_op->truncate_range) - inode->i_op->truncate_range(inode, 0, (loff_t)-1); + shmem_truncate_range(inode, 0, (loff_t)-1); obj->madv = __I915_MADV_PURGED; } @@ -2078,8 +2064,8 @@ i915_wait_request(struct intel_ring_buffer *ring, if (!ier) { DRM_ERROR("something (likely vbetool) disabled " "interrupts, re-enabling\n"); - i915_driver_irq_preinstall(ring->dev); - i915_driver_irq_postinstall(ring->dev); + ring->dev->driver->irq_preinstall(ring->dev); + ring->dev->driver->irq_postinstall(ring->dev); } trace_i915_gem_request_wait_begin(ring, seqno); @@ -2750,9 +2736,16 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, return -EINVAL; } - fence_size = i915_gem_get_gtt_size(obj); - fence_alignment = i915_gem_get_gtt_alignment(obj); - unfenced_alignment = i915_gem_get_unfenced_gtt_alignment(obj); + fence_size = i915_gem_get_gtt_size(dev, + obj->base.size, + obj->tiling_mode); + fence_alignment = i915_gem_get_gtt_alignment(dev, + obj->base.size, + obj->tiling_mode); + unfenced_alignment = + i915_gem_get_unfenced_gtt_alignment(dev, + obj->base.size, + obj->tiling_mode); if (alignment == 0) alignment = map_and_fenceable ? fence_alignment : @@ -2924,8 +2917,6 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj) */ wmb(); - i915_gem_release_mmap(obj); - old_write_domain = obj->base.write_domain; obj->base.write_domain = 0; @@ -3565,6 +3556,7 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; + struct address_space *mapping; obj = kzalloc(sizeof(*obj), GFP_KERNEL); if (obj == NULL) @@ -3575,6 +3567,9 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, return NULL; } + mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping; + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE); + i915_gem_info_add_obj(dev_priv, size); obj->base.write_domain = I915_GEM_DOMAIN_CPU; @@ -3950,8 +3945,7 @@ void i915_gem_detach_phys_object(struct drm_device *dev, page_count = obj->base.size / PAGE_SIZE; for (i = 0; i < page_count; i++) { - struct page *page = read_cache_page_gfp(mapping, i, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + struct page *page = shmem_read_mapping_page(mapping, i); if (!IS_ERR(page)) { char *dst = kmap_atomic(page); memcpy(dst, vaddr + i*PAGE_SIZE, PAGE_SIZE); @@ -4012,8 +4006,7 @@ i915_gem_attach_phys_object(struct drm_device *dev, struct page *page; char *dst, *src; - page = read_cache_page_gfp(mapping, i, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, i); if (IS_ERR(page)) return PTR_ERR(page); |