Plumb the functions we care about with VM arguments. With the exception of the hack in i915_ppgtt_bind to only ever be able to do aliasing PPGTT, this most everything we want. v2: Fix purge to pick an object and unbind all vmas This was doable because of the global bound list change. v3: With the commit to actually pin/unpin pages in place, there is no longer a need to check if unbind succeeded before calling put_pages(). Make put_pages only BUG() after checking pin count. v4: Rebased on top of the new hangcheck work by Mika plumbed eb_destroy also Many checkpatch related fixes Signed-off-by: Ben Widawsky <ben at bwidawsk.net> --- drivers/gpu/drm/i915/i915_debugfs.c | 59 +++-- drivers/gpu/drm/i915/i915_dma.c | 8 +- drivers/gpu/drm/i915/i915_drv.h | 109 +++++---- drivers/gpu/drm/i915/i915_gem.c | 377 +++++++++++++++++++++-------- drivers/gpu/drm/i915/i915_gem_context.c | 11 +- drivers/gpu/drm/i915/i915_gem_evict.c | 57 +++-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 87 ++++--- drivers/gpu/drm/i915/i915_gem_gtt.c | 101 ++++---- drivers/gpu/drm/i915/i915_gem_stolen.c | 11 +- drivers/gpu/drm/i915/i915_gem_tiling.c | 19 +- drivers/gpu/drm/i915/i915_irq.c | 27 ++- drivers/gpu/drm/i915/i915_trace.h | 20 +- drivers/gpu/drm/i915/intel_display.c | 22 +- drivers/gpu/drm/i915/intel_fb.c | 6 +- drivers/gpu/drm/i915/intel_overlay.c | 16 +- drivers/gpu/drm/i915/intel_pm.c | 11 +- drivers/gpu/drm/i915/intel_ringbuffer.c | 29 ++- drivers/gpu/drm/i915/intel_sprite.c | 6 +- 18 files changed, 609 insertions(+), 367 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index aa6d63b..cf50389 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -122,10 +122,14 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) seq_printf(m, " (pinned x %d)", obj->pin_count); if (obj->fence_reg != I915_FENCE_REG_NONE) seq_printf(m, " (fence: %d)", obj->fence_reg); - if (i915_gem_obj_bound(obj)) - seq_printf(m, " (gtt offset: %08lx, size: %08lx)", - i915_gem_obj_offset(obj), - i915_gem_obj_size(obj)); + if (i915_gem_obj_bound_any(obj)) { + struct i915_vma *vma; + list_for_each_entry(vma, &obj->vma_list, vma_link) { + seq_printf(m, " (gtt offset: %08lx, size: %08lx)", + i915_gem_obj_offset(obj, vma->vm), + i915_gem_obj_size(obj, vma->vm)); + } + } if (obj->stolen) seq_printf(m, " (stolen: %08lx)", obj->stolen->start); if (obj->pin_mappable || obj->fault_mappable) { @@ -159,11 +163,11 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data) switch (list) { case ACTIVE_LIST: seq_printf(m, "Active:\n"); - head = &i915_gtt_vm->active_list; + head = ggtt_list(active_list); break; case INACTIVE_LIST: seq_printf(m, "Inactive:\n"); - head = &i915_gtt_vm->inactive_list; + head = ggtt_list(inactive_list); break; default: mutex_unlock(&dev->struct_mutex); @@ -176,7 +180,8 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data) describe_obj(m, obj); seq_printf(m, "\n"); total_obj_size += obj->base.size; - total_gtt_size += i915_gem_obj_size(obj); + /* FIXME: Add size of all VMs */ + total_gtt_size += i915_gem_ggtt_size(obj); count++; } mutex_unlock(&dev->struct_mutex); @@ -186,12 +191,13 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data) return 0; } +/* FIXME: Support multiple VM? */ #define count_objects(list, member) do { \ list_for_each_entry(obj, list, member) { \ - size += i915_gem_obj_size(obj); \ + size += i915_gem_ggtt_size(obj); \ ++count; \ if (obj->map_and_fenceable) { \ - mappable_size += i915_gem_obj_size(obj); \ + mappable_size += i915_gem_ggtt_size(obj); \ ++mappable_count; \ } \ } \ @@ -210,7 +216,7 @@ static int per_file_stats(int id, void *ptr, void *data) stats->count++; stats->total += obj->base.size; - if (i915_gem_obj_bound(obj)) { + if (i915_gem_obj_bound_any(obj)) { if (!list_empty(&obj->ring_list)) stats->active += obj->base.size; else @@ -248,12 +254,12 @@ static int i915_gem_object_info(struct seq_file *m, void* data) count, mappable_count, size, mappable_size); size = count = mappable_size = mappable_count = 0; - count_objects(&i915_gtt_vm->active_list, mm_list); + count_objects(ggtt_list(active_list), mm_list); seq_printf(m, " %u [%u] active objects, %zu [%zu] bytes\n", count, mappable_count, size, mappable_size); size = count = mappable_size = mappable_count = 0; - count_objects(&i915_gtt_vm->inactive_list, mm_list); + count_objects(ggtt_list(inactive_list), mm_list); seq_printf(m, " %u [%u] inactive objects, %zu [%zu] bytes\n", count, mappable_count, size, mappable_size); @@ -268,11 +274,11 @@ static int i915_gem_object_info(struct seq_file *m, void* data) size = count = mappable_size = mappable_count = 0; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { if (obj->fault_mappable) { - size += i915_gem_obj_size(obj); + size += i915_gem_ggtt_size(obj); ++count; } if (obj->pin_mappable) { - mappable_size += i915_gem_obj_size(obj); + mappable_size += i915_gem_ggtt_size(obj); ++mappable_count; } if (obj->madv == I915_MADV_DONTNEED) { @@ -288,8 +294,8 @@ static int i915_gem_object_info(struct seq_file *m, void* data) count, size); seq_printf(m, "%zu [%lu] gtt total\n", - i915_gtt_vm->total, - dev_priv->gtt.mappable_end - i915_gtt_vm->start); + dev_priv->gtt.base.total, + dev_priv->gtt.mappable_end - dev_priv->gtt.base.start); seq_printf(m, "\n"); list_for_each_entry_reverse(file, &dev->filelist, lhead) { @@ -334,7 +340,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void* data) describe_obj(m, obj); seq_printf(m, "\n"); total_obj_size += obj->base.size; - total_gtt_size += i915_gem_obj_size(obj); + total_gtt_size += i915_gem_ggtt_size(obj); count++; } @@ -381,13 +387,13 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data) struct drm_i915_gem_object *obj = work->old_fb_obj; if (obj) seq_printf(m, "Old framebuffer gtt_offset 0x%08lx\n", - i915_gem_obj_offset(obj)); + i915_gem_ggtt_offset(obj)); } if (work->pending_flip_obj) { struct drm_i915_gem_object *obj = work->pending_flip_obj; if (obj) seq_printf(m, "New framebuffer gtt_offset 0x%08lx\n", - i915_gem_obj_offset(obj)); + i915_gem_ggtt_offset(obj)); } } spin_unlock_irqrestore(&dev->event_lock, flags); @@ -1980,19 +1986,22 @@ i915_drop_caches_set(void *data, u64 val) i915_gem_retire_requests(dev); if (val & DROP_BOUND) { - list_for_each_entry_safe(obj, next, &i915_gtt_vm->inactive_list, + /* FIXME: Do this for all vms? */ + list_for_each_entry_safe(obj, next, ggtt_list(inactive_list), mm_list) - if (obj->pin_count == 0) { - ret = i915_gem_object_unbind(obj); - if (ret) - goto unlock; - } + if (obj->pin_count) + continue; + + ret = i915_gem_object_unbind(obj, &dev_priv->gtt.base); + if (ret) + goto unlock; } if (val & DROP_UNBOUND) { list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, global_list) if (obj->pages_pin_count == 0) { + /* FIXME: Do this for all vms? */ ret = i915_gem_object_put_pages(obj); if (ret) goto unlock; diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 24dd593..4b330e5 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1363,7 +1363,7 @@ cleanup_gem: i915_gem_cleanup_ringbuffer(dev); i915_gem_context_fini(dev); mutex_unlock(&dev->struct_mutex); - drm_mm_takedown(&i915_gtt_vm->mm); + drm_mm_takedown(&dev_priv->gtt.base.mm); cleanup_irq: drm_irq_uninstall(dev); cleanup_gem_stolen: @@ -1497,10 +1497,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) i915_dump_device_info(dev_priv); - INIT_LIST_HEAD(&dev_priv->vm_list); - INIT_LIST_HEAD(&dev_priv->gtt.base.global_link); - list_add(&dev_priv->gtt.base.global_link, &dev_priv->vm_list); - if (i915_get_bridge_dev(dev)) { ret = -EIO; goto free_priv; @@ -1758,7 +1754,7 @@ int i915_driver_unload(struct drm_device *dev) } list_del(&dev_priv->vm_list); - drm_mm_takedown(&i915_gtt_vm->mm); + drm_mm_takedown(&dev_priv->gtt.base.mm); if (dev_priv->regs != NULL) pci_iounmap(dev->pdev, dev_priv->regs); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 217695e..9042376 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -520,10 +520,6 @@ struct i915_gtt { unsigned long *mappable_end); void (*gtt_remove)(struct drm_device *dev); }; -#define i915_gtt_vm ((struct i915_address_space *) \ - list_first_entry(&dev_priv->vm_list,\ - struct i915_address_space, \ - global_link)) struct i915_hw_ppgtt { struct i915_address_space base; @@ -1362,46 +1358,6 @@ struct drm_i915_gem_object { #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base) -static inline unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o) -{ - struct i915_vma *vma; - BUG_ON(list_empty(&o->vma_list)); - vma = list_first_entry(&o->vma_list, struct i915_vma, vma_link); - return vma->node.start; -} - -static inline bool i915_gem_obj_bound(struct drm_i915_gem_object *o) -{ - return !list_empty(&o->vma_list); -} - -static inline unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o) -{ - struct i915_vma *vma; - BUG_ON(list_empty(&o->vma_list)); - vma = list_first_entry(&o->vma_list, struct i915_vma, vma_link); - return vma->node.size; -} - -static inline void i915_gem_obj_set_color(struct drm_i915_gem_object *o, - enum i915_cache_level color) -{ - struct i915_vma *vma; - BUG_ON(list_empty(&o->vma_list)); - vma = list_first_entry(&o->vma_list, struct i915_vma, vma_link); - vma->node.color = color; -} - -/* This is a temporary define to help transition us to real VMAs. If you see - * this, you're either reviewing code, or bisecting it. */ -static inline struct i915_vma * -__i915_gem_obj_to_vma(struct drm_i915_gem_object *obj) -{ - BUG_ON(!i915_gem_obj_bound(obj)); - BUG_ON(list_empty(&obj->vma_list)); - return list_first_entry(&obj->vma_list, struct i915_vma, vma_link); -} - /** * Request queue structure. * @@ -1712,15 +1668,18 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, size_t size); void i915_gem_free_object(struct drm_gem_object *obj); -struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj); +struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj, + struct i915_address_space *vm); void i915_gem_vma_destroy(struct i915_vma *vma); int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, uint32_t alignment, bool map_and_fenceable, bool nonblocking); void i915_gem_object_unpin(struct drm_i915_gem_object *obj); -int __must_check i915_gem_object_unbind(struct drm_i915_gem_object *obj); +int __must_check i915_gem_object_unbind(struct drm_i915_gem_object *obj, + struct i915_address_space *vm); int i915_gem_object_put_pages(struct drm_i915_gem_object *obj); void i915_gem_release_mmap(struct drm_i915_gem_object *obj); void i915_gem_lastclose(struct drm_device *dev); @@ -1750,6 +1709,7 @@ int __must_check i915_mutex_lock_interruptible(struct drm_device *dev); int i915_gem_object_sync(struct drm_i915_gem_object *obj, struct intel_ring_buffer *to); void i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, struct intel_ring_buffer *ring); int i915_gem_dumb_create(struct drm_file *file_priv, @@ -1856,6 +1816,7 @@ i915_gem_get_gtt_alignment(struct drm_device *dev, uint32_t size, int tiling_mode, bool fenced); int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, enum i915_cache_level cache_level); struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, @@ -1866,6 +1827,56 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev, void i915_gem_restore_fences(struct drm_device *dev); +unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o, + struct i915_address_space *vm); +bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o); +bool i915_gem_obj_bound(struct drm_i915_gem_object *o, + struct i915_address_space *vm); +unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, + struct i915_address_space *vm); +void i915_gem_obj_set_color(struct drm_i915_gem_object *o, + struct i915_address_space *vm, + enum i915_cache_level color); +struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj, + struct i915_address_space *vm); +/* Some GGTT VM helpers */ +#define ggtt_list(list_name) (&(dev_priv->gtt.base.list_name)) +#define obj_to_ggtt(obj) \ + (&((struct drm_i915_private *)(obj)->base.dev->dev_private)->gtt.base) +static inline bool is_i915_ggtt(struct i915_address_space *vm) +{ + struct i915_address_space *ggtt = + &((struct drm_i915_private *)(vm)->dev->dev_private)->gtt.base; + return vm == ggtt; +} + +static inline bool i915_gem_obj_bound_ggtt(struct drm_i915_gem_object *obj) +{ + return i915_gem_obj_bound(obj, obj_to_ggtt(obj)); +} + +static inline unsigned long +i915_gem_ggtt_offset(struct drm_i915_gem_object *obj) +{ + return i915_gem_obj_offset(obj, obj_to_ggtt(obj)); +} + +static inline unsigned long i915_gem_ggtt_size(struct drm_i915_gem_object *obj) +{ + return i915_gem_obj_size(obj, obj_to_ggtt(obj)); +} + +static inline int __must_check +i915_gem_ggtt_pin(struct drm_i915_gem_object *obj, + uint32_t alignment, + bool map_and_fenceable, + bool nonblocking) +{ + return i915_gem_object_pin(obj, obj_to_ggtt(obj), alignment, + map_and_fenceable, nonblocking); +} +#undef obj_to_ggtt + /* i915_gem_context.c */ void i915_gem_context_init(struct drm_device *dev); void i915_gem_context_fini(struct drm_device *dev); @@ -1903,6 +1914,7 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, struct drm_i915_gem_object *obj); void i915_gem_restore_gtt_mappings(struct drm_device *dev); int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj); +/* FIXME: this is never okay with full PPGTT */ void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level); void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj); @@ -1919,7 +1931,9 @@ static inline void i915_gem_chipset_flush(struct drm_device *dev) /* i915_gem_evict.c */ -int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size, +int __must_check i915_gem_evict_something(struct drm_device *dev, + struct i915_address_space *vm, + int min_size, unsigned alignment, unsigned cache_level, bool mappable, @@ -1927,6 +1941,7 @@ int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size, int i915_gem_evict_everything(struct drm_device *dev); /* i915_gem_stolen.c */ +#define I915_INVALID_OFFSET 0x1 int i915_gem_init_stolen(struct drm_device *dev); int i915_gem_stolen_setup_compression(struct drm_device *dev, int size); void i915_gem_stolen_cleanup_compression(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index bc9e089..8fe5f4e 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -38,10 +38,12 @@ static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj); static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj); -static __must_check int i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, - unsigned alignment, - bool map_and_fenceable, - bool nonblocking); +static __must_check int +i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + unsigned alignment, + bool map_and_fenceable, + bool nonblocking); static int i915_gem_phys_pwrite(struct drm_device *dev, struct drm_i915_gem_object *obj, struct drm_i915_gem_pwrite *args, @@ -135,7 +137,7 @@ int i915_mutex_lock_interruptible(struct drm_device *dev) static inline bool i915_gem_object_is_inactive(struct drm_i915_gem_object *obj) { - return i915_gem_obj_bound(obj) && !obj->active; + return i915_gem_obj_bound_any(obj) && !obj->active; } int @@ -178,10 +180,10 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, mutex_lock(&dev->struct_mutex); list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) if (obj->pin_count) - pinned += i915_gem_obj_size(obj); + pinned += i915_gem_ggtt_size(obj); mutex_unlock(&dev->struct_mutex); - args->aper_size = i915_gtt_vm->total; + args->aper_size = dev_priv->gtt.base.total; args->aper_available_size = args->aper_size - pinned; return 0; @@ -422,7 +424,7 @@ i915_gem_shmem_pread(struct drm_device *dev, * anyway again before the next pread happens. */ if (obj->cache_level == I915_CACHE_NONE) needs_clflush = 1; - if (i915_gem_obj_bound(obj)) { + if (i915_gem_obj_bound_any(obj)) { ret = i915_gem_object_set_to_gtt_domain(obj, false); if (ret) return ret; @@ -594,7 +596,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, char __user *user_data; int page_offset, page_length, ret; - ret = i915_gem_object_pin(obj, 0, true, true); + ret = i915_gem_ggtt_pin(obj, 0, true, true); if (ret) goto out; @@ -609,7 +611,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, user_data = to_user_ptr(args->data_ptr); remain = args->size; - offset = i915_gem_obj_offset(obj) + args->offset; + offset = i915_gem_ggtt_offset(obj) + args->offset; while (remain > 0) { /* Operation in this page @@ -739,7 +741,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev, * right away and we therefore have to clflush anyway. */ if (obj->cache_level == I915_CACHE_NONE) needs_clflush_after = 1; - if (i915_gem_obj_bound(obj)) { + if (i915_gem_obj_bound_any(obj)) { ret = i915_gem_object_set_to_gtt_domain(obj, true); if (ret) return ret; @@ -1347,7 +1349,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } /* Now bind it into the GTT if needed */ - ret = i915_gem_object_pin(obj, 0, true, false); + ret = i915_gem_ggtt_pin(obj, 0, true, false); if (ret) goto unlock; @@ -1361,7 +1363,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) obj->fault_mappable = true; - pfn += (i915_gem_obj_offset(obj) >> PAGE_SHIFT) + page_offset; + pfn += (i915_gem_ggtt_offset(obj) >> PAGE_SHIFT) + page_offset; /* Finally, remap it using the new GTT offset */ ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn); @@ -1667,11 +1669,11 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj) if (obj->pages == NULL) return 0; - BUG_ON(i915_gem_obj_bound(obj)); - if (obj->pages_pin_count) return -EBUSY; + BUG_ON(i915_gem_obj_bound_any(obj)); + /* ->put_pages might need to allocate memory for the bit17 swizzle * array, hence protect them from being reaped by removing them from gtt * lists early. */ @@ -1704,16 +1706,22 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target, } } - list_for_each_entry_safe(obj, next, - &i915_gtt_vm->inactive_list, - mm_list) { - if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) && - i915_gem_object_unbind(obj) == 0 && - i915_gem_object_put_pages(obj) == 0) { + list_for_each_entry_safe(obj, next, &dev_priv->mm.bound_list, + global_list) { + struct i915_vma *vma, *v; + + if (!i915_gem_object_is_purgeable(obj) && purgeable_only) + continue; + + list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link) + if (i915_gem_object_unbind(obj, vma->vm)) + break; + + if (!i915_gem_object_put_pages(obj)) count += obj->base.size >> PAGE_SHIFT; - if (count >= target) - return count; - } + + if (count >= target) + return count; } return count; @@ -1864,6 +1872,7 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj) void i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, struct intel_ring_buffer *ring) { struct drm_device *dev = obj->base.dev; @@ -1880,7 +1889,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, } /* Move from whatever list we were on to the tail of execution. */ - list_move_tail(&obj->mm_list, &i915_gtt_vm->active_list); + list_move_tail(&obj->mm_list, &vm->active_list); list_move_tail(&obj->ring_list, &ring->active_list); obj->last_read_seqno = seqno; @@ -1900,15 +1909,13 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, } static void -i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj) +i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj, + struct i915_address_space *vm) { - struct drm_device *dev = obj->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - BUG_ON(obj->base.write_domain & ~I915_GEM_GPU_DOMAINS); BUG_ON(!obj->active); - list_move_tail(&obj->mm_list, &i915_gtt_vm->inactive_list); + list_move_tail(&obj->mm_list, &vm->inactive_list); list_del_init(&obj->ring_list); obj->ring = NULL; @@ -2106,10 +2113,11 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request) spin_unlock(&file_priv->mm.lock); } -static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj) +static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj, + struct i915_address_space *vm) { - if (acthd >= i915_gem_obj_offset(obj) && - acthd < i915_gem_obj_offset(obj) + obj->base.size) + if (acthd >= i915_gem_obj_offset(obj, vm) && + acthd < i915_gem_obj_offset(obj, vm) + obj->base.size) return true; return false; @@ -2132,6 +2140,17 @@ static bool i915_head_inside_request(const u32 acthd_unmasked, return false; } +static struct i915_address_space * +request_to_vm(struct drm_i915_gem_request *request) +{ + struct drm_i915_private *dev_priv = request->ring->dev->dev_private; + struct i915_address_space *vm; + + vm = &dev_priv->gtt.base; + + return vm; +} + static bool i915_request_guilty(struct drm_i915_gem_request *request, const u32 acthd, bool *inside) { @@ -2139,9 +2158,9 @@ static bool i915_request_guilty(struct drm_i915_gem_request *request, * pointing inside the ring, matches the batch_obj address range. * However this is extremely unlikely. */ - if (request->batch_obj) { - if (i915_head_inside_object(acthd, request->batch_obj)) { + if (i915_head_inside_object(acthd, request->batch_obj, + request_to_vm(request))) { *inside = true; return true; } @@ -2161,17 +2180,21 @@ static bool i915_set_reset_status(struct intel_ring_buffer *ring, { struct i915_ctx_hang_stats *hs = NULL; bool inside, guilty, banned; + unsigned long offset = 0; /* Innocent until proven guilty */ guilty = banned = false; + if (request->batch_obj) + offset = i915_gem_obj_offset(request->batch_obj, + request_to_vm(request)); + if (ring->hangcheck.action != wait && i915_request_guilty(request, acthd, &inside)) { DRM_ERROR("%s hung %s bo (0x%lx ctx %d) at 0x%x\n", ring->name, inside ? "inside" : "flushing", - request->batch_obj ? - i915_gem_obj_offset(request->batch_obj) : 0, + offset, request->ctx ? request->ctx->id : 0, acthd); @@ -2239,13 +2262,15 @@ static bool i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv, } while (!list_empty(&ring->active_list)) { + struct i915_address_space *vm; struct drm_i915_gem_object *obj; obj = list_first_entry(&ring->active_list, struct drm_i915_gem_object, ring_list); - i915_gem_object_move_to_inactive(obj); + list_for_each_entry(vm, &dev_priv->vm_list, global_link) + i915_gem_object_move_to_inactive(obj, vm); } return ctx_banned; @@ -2267,6 +2292,7 @@ bool i915_gem_reset(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; struct intel_ring_buffer *ring; + struct i915_address_space *vm; int i; bool ctx_banned = false; @@ -2278,8 +2304,9 @@ bool i915_gem_reset(struct drm_device *dev) /* Move everything out of the GPU domains to ensure we do any * necessary invalidation upon reuse. */ - list_for_each_entry(obj, &i915_gtt_vm->inactive_list, mm_list) - obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS; + list_for_each_entry(vm, &dev_priv->vm_list, global_link) + list_for_each_entry(obj, &vm->inactive_list, mm_list) + obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS; /* The fence registers are invalidated so clear them out */ i915_gem_restore_fences(dev); @@ -2327,6 +2354,8 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) * by the ringbuffer to the flushing/inactive lists as appropriate. */ while (!list_empty(&ring->active_list)) { + struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct i915_address_space *vm; struct drm_i915_gem_object *obj; obj = list_first_entry(&ring->active_list, @@ -2336,7 +2365,8 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) if (!i915_seqno_passed(seqno, obj->last_read_seqno)) break; - i915_gem_object_move_to_inactive(obj); + list_for_each_entry(vm, &dev_priv->vm_list, global_link) + i915_gem_object_move_to_inactive(obj, vm); } if (unlikely(ring->trace_irq_seqno && @@ -2582,13 +2612,14 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj) * Unbinds an object from the GTT aperture. */ int -i915_gem_object_unbind(struct drm_i915_gem_object *obj) +i915_gem_object_unbind(struct drm_i915_gem_object *obj, + struct i915_address_space *vm) { drm_i915_private_t *dev_priv = obj->base.dev->dev_private; struct i915_vma *vma; int ret; - if (!i915_gem_obj_bound(obj)) + if (!i915_gem_obj_bound(obj, vm)) return 0; if (obj->pin_count) @@ -2611,7 +2642,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj) if (ret) return ret; - trace_i915_gem_object_unbind(obj); + trace_i915_gem_object_unbind(obj, vm); if (obj->has_global_gtt_mapping) i915_gem_gtt_unbind_object(obj); @@ -2626,7 +2657,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj) /* Avoid an unnecessary call to unbind on rebind. */ obj->map_and_fenceable = true; - vma = __i915_gem_obj_to_vma(obj); + vma = i915_gem_obj_to_vma(obj, vm); list_del(&vma->vma_link); drm_mm_remove_node(&vma->node); i915_gem_vma_destroy(vma); @@ -2676,11 +2707,11 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg, } if (obj) { - u32 size = i915_gem_obj_size(obj); + u32 size = i915_gem_ggtt_size(obj); - val = (uint64_t)((i915_gem_obj_offset(obj) + size - 4096) & + val = (uint64_t)((i915_gem_ggtt_offset(obj) + size - 4096) & 0xfffff000) << 32; - val |= i915_gem_obj_offset(obj) & 0xfffff000; + val |= i915_gem_ggtt_offset(obj) & 0xfffff000; val |= (uint64_t)((obj->stride / 128) - 1) << fence_pitch_shift; if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I965_FENCE_TILING_Y_SHIFT; @@ -2700,15 +2731,15 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg, u32 val; if (obj) { - u32 size = i915_gem_obj_size(obj); + u32 size = i915_gem_ggtt_size(obj); int pitch_val; int tile_width; - WARN((i915_gem_obj_offset(obj) & ~I915_FENCE_START_MASK) || + WARN((i915_gem_ggtt_offset(obj) & ~I915_FENCE_START_MASK) || (size & -size) != size || - (i915_gem_obj_offset(obj) & (size - 1)), + (i915_gem_ggtt_offset(obj) & (size - 1)), "object 0x%08lx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n", - i915_gem_obj_offset(obj), obj->map_and_fenceable, size); + i915_gem_ggtt_offset(obj), obj->map_and_fenceable, size); if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)) tile_width = 128; @@ -2719,7 +2750,7 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg, pitch_val = obj->stride / tile_width; pitch_val = ffs(pitch_val) - 1; - val = i915_gem_obj_offset(obj); + val = i915_gem_ggtt_offset(obj); if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I830_FENCE_TILING_Y_SHIFT; val |= I915_FENCE_SIZE_BITS(size); @@ -2744,19 +2775,19 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg, uint32_t val; if (obj) { - u32 size = i915_gem_obj_size(obj); + u32 size = i915_gem_ggtt_size(obj); uint32_t pitch_val; - WARN((i915_gem_obj_offset(obj) & ~I830_FENCE_START_MASK) || + WARN((i915_gem_ggtt_offset(obj) & ~I830_FENCE_START_MASK) || (size & -size) != size || - (i915_gem_obj_offset(obj) & (size - 1)), + (i915_gem_ggtt_offset(obj) & (size - 1)), "object 0x%08lx not 512K or pot-size 0x%08x aligned\n", - i915_gem_obj_offset(obj), size); + i915_gem_ggtt_offset(obj), size); pitch_val = obj->stride / 128; pitch_val = ffs(pitch_val) - 1; - val = i915_gem_obj_offset(obj); + val = i915_gem_ggtt_offset(obj); if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I830_FENCE_TILING_Y_SHIFT; val |= I830_FENCE_SIZE_BITS(size); @@ -3075,6 +3106,7 @@ static void i915_gem_verify_gtt(struct drm_device *dev) */ static int i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, unsigned alignment, bool map_and_fenceable, bool nonblocking) @@ -3083,14 +3115,16 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, drm_i915_private_t *dev_priv = dev->dev_private; u32 size, fence_size, fence_alignment, unfenced_alignment; bool mappable, fenceable; - size_t gtt_max = map_and_fenceable ? - dev_priv->gtt.mappable_end : dev_priv->gtt.base.total; + size_t gtt_max = + map_and_fenceable ? dev_priv->gtt.mappable_end : vm->total; struct i915_vma *vma; int ret; if (WARN_ON(!list_empty(&obj->vma_list))) return -EBUSY; + BUG_ON(!is_i915_ggtt(vm)); + fence_size = i915_gem_get_gtt_size(dev, obj->base.size, obj->tiling_mode); @@ -3129,20 +3163,23 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, i915_gem_object_pin_pages(obj); - vma = i915_gem_vma_create(obj); + /* For now we only ever use 1 vma per object */ + WARN_ON(!list_empty(&obj->vma_list)); + + vma = i915_gem_vma_create(obj, vm); if (vma == NULL) { i915_gem_object_unpin_pages(obj); return -ENOMEM; } search_free: - ret = drm_mm_insert_node_in_range_generic(&i915_gtt_vm->mm, &vma->node, + ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node, size, alignment, obj->cache_level, 0, gtt_max, DRM_MM_CREATE_DEFAULT, DRM_MM_SEARCH_DEFAULT); if (ret) { - ret = i915_gem_evict_something(dev, size, alignment, + ret = i915_gem_evict_something(dev, vm, size, alignment, obj->cache_level, map_and_fenceable, nonblocking); @@ -3170,18 +3207,25 @@ search_free: } list_move_tail(&obj->global_list, &dev_priv->mm.bound_list); - list_add_tail(&obj->mm_list, &i915_gtt_vm->inactive_list); - list_add(&vma->vma_link, &obj->vma_list); + list_add_tail(&obj->mm_list, &vm->inactive_list); + /* Keep GGTT vmas first to make debug easier */ + if (is_i915_ggtt(vm)) + list_add(&vma->vma_link, &obj->vma_list); + else + list_add_tail(&vma->vma_link, &obj->vma_list); - fenceable = i915_gem_obj_size(obj) == fence_size && - (i915_gem_obj_offset(obj) & (fence_alignment - 1)) == 0; + fenceable = + is_i915_ggtt(vm) && + i915_gem_ggtt_size(obj) == fence_size && + (i915_gem_ggtt_offset(obj) & (fence_alignment - 1)) == 0; mappable = + is_i915_ggtt(vm) && vma->node.start + obj->base.size <= dev_priv->gtt.mappable_end; obj->map_and_fenceable = mappable && fenceable; - trace_i915_gem_object_bind(obj, map_and_fenceable); + trace_i915_gem_object_bind(obj, vm, map_and_fenceable); i915_gem_verify_gtt(dev); return 0; } @@ -3279,7 +3323,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) int ret; /* Not valid to be called on unbound objects. */ - if (!i915_gem_obj_bound(obj)) + if (!i915_gem_obj_bound_any(obj)) return -EINVAL; if (obj->base.write_domain == I915_GEM_DOMAIN_GTT) @@ -3318,12 +3362,13 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) /* And bump the LRU for this access */ if (i915_gem_object_is_inactive(obj)) - list_move_tail(&obj->mm_list, &i915_gtt_vm->inactive_list); + list_move_tail(&obj->mm_list, ggtt_list(inactive_list)); return 0; } int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, enum i915_cache_level cache_level) { struct drm_device *dev = obj->base.dev; @@ -3339,16 +3384,19 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, return -EBUSY; } - if (i915_gem_obj_bound(obj)) - node = &__i915_gem_obj_to_vma(obj)->node; + if (i915_gem_obj_bound(obj, vm)) + node = &(i915_gem_obj_to_vma(obj, vm)->node); if (!i915_gem_valid_gtt_space(dev, node, cache_level)) { - ret = i915_gem_object_unbind(obj); + ret = i915_gem_object_unbind(obj, vm); if (ret) return ret; } - if (i915_gem_obj_bound(obj)) { + list_for_each_entry(vm, &dev_priv->vm_list, global_link) { + if (!i915_gem_obj_bound(obj, vm)) + continue; + ret = i915_gem_object_finish_gpu(obj); if (ret) return ret; @@ -3371,7 +3419,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, i915_ppgtt_bind_object(dev_priv->gtt.aliasing_ppgtt, obj, cache_level); - i915_gem_obj_set_color(obj, cache_level); + i915_gem_obj_set_color(obj, vm, cache_level); } if (cache_level == I915_CACHE_NONE) { @@ -3431,6 +3479,7 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct drm_i915_gem_caching *args = data; + struct drm_i915_private *dev_priv; struct drm_i915_gem_object *obj; enum i915_cache_level level; int ret; @@ -3455,8 +3504,10 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data, ret = -ENOENT; goto unlock; } + dev_priv = obj->base.dev->dev_private; - ret = i915_gem_object_set_cache_level(obj, level); + /* FIXME: Add interface for specific VM? */ + ret = i915_gem_object_set_cache_level(obj, &dev_priv->gtt.base, level); drm_gem_object_unreference(&obj->base); unlock: @@ -3474,6 +3525,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, u32 alignment, struct intel_ring_buffer *pipelined) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; u32 old_read_domains, old_write_domain; int ret; @@ -3492,7 +3544,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, * of uncaching, which would allow us to flush all the LLC-cached data * with that bit in the PTE to main memory with just one PIPE_CONTROL. */ - ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE); + ret = i915_gem_object_set_cache_level(obj, &dev_priv->gtt.base, + I915_CACHE_NONE); if (ret) return ret; @@ -3500,7 +3553,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, * (e.g. libkms for the bootup splash), we have to ensure that we * always use map_and_fenceable for all scanout buffers. */ - ret = i915_gem_object_pin(obj, alignment, true, false); + ret = i915_gem_ggtt_pin(obj, alignment, true, false); if (ret) return ret; @@ -3643,6 +3696,7 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file) int i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, uint32_t alignment, bool map_and_fenceable, bool nonblocking) @@ -3652,26 +3706,29 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj, if (WARN_ON(obj->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT)) return -EBUSY; - if (i915_gem_obj_bound(obj)) { - if ((alignment && i915_gem_obj_offset(obj) & (alignment - 1)) || + BUG_ON(map_and_fenceable && !is_i915_ggtt(vm)); + + if (i915_gem_obj_bound(obj, vm)) { + if ((alignment && + i915_gem_obj_offset(obj, vm) & (alignment - 1)) || (map_and_fenceable && !obj->map_and_fenceable)) { WARN(obj->pin_count, "bo is already pinned with incorrect alignment:" " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d," " obj->map_and_fenceable=%d\n", - i915_gem_obj_offset(obj), alignment, + i915_gem_obj_offset(obj, vm), alignment, map_and_fenceable, obj->map_and_fenceable); - ret = i915_gem_object_unbind(obj); + ret = i915_gem_object_unbind(obj, vm); if (ret) return ret; } } - if (!i915_gem_obj_bound(obj)) { + if (!i915_gem_obj_bound(obj, vm)) { struct drm_i915_private *dev_priv = obj->base.dev->dev_private; - ret = i915_gem_object_bind_to_gtt(obj, alignment, + ret = i915_gem_object_bind_to_gtt(obj, vm, alignment, map_and_fenceable, nonblocking); if (ret) @@ -3694,7 +3751,7 @@ void i915_gem_object_unpin(struct drm_i915_gem_object *obj) { BUG_ON(obj->pin_count == 0); - BUG_ON(!i915_gem_obj_bound(obj)); + BUG_ON(!i915_gem_obj_bound_any(obj)); if (--obj->pin_count == 0) obj->pin_mappable = false; @@ -3732,7 +3789,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data, } if (obj->user_pin_count == 0) { - ret = i915_gem_object_pin(obj, args->alignment, true, false); + ret = i915_gem_ggtt_pin(obj, args->alignment, true, false); if (ret) goto out; } @@ -3744,7 +3801,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data, * as the X server doesn't manage domains yet */ i915_gem_object_flush_cpu_write_domain(obj); - args->offset = i915_gem_obj_offset(obj); + args->offset = i915_gem_ggtt_offset(obj); out: drm_gem_object_unreference(&obj->base); unlock: @@ -3967,6 +4024,7 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) struct drm_i915_gem_object *obj = to_intel_bo(gem_obj); struct drm_device *dev = obj->base.dev; drm_i915_private_t *dev_priv = dev->dev_private; + struct i915_vma *vma, *next; trace_i915_gem_object_destroy(obj); @@ -3974,15 +4032,21 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) i915_gem_detach_phys_object(dev, obj); obj->pin_count = 0; - if (WARN_ON(i915_gem_object_unbind(obj) == -ERESTARTSYS)) { - bool was_interruptible; + /* NB: 0 or 1 elements */ + WARN_ON(!list_empty(&obj->vma_list) && + !list_is_singular(&obj->vma_list)); + list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) { + int ret = i915_gem_object_unbind(obj, vma->vm); + if (WARN_ON(ret == -ERESTARTSYS)) { + bool was_interruptible; - was_interruptible = dev_priv->mm.interruptible; - dev_priv->mm.interruptible = false; + was_interruptible = dev_priv->mm.interruptible; + dev_priv->mm.interruptible = false; - WARN_ON(i915_gem_object_unbind(obj)); + WARN_ON(i915_gem_object_unbind(obj, vma->vm)); - dev_priv->mm.interruptible = was_interruptible; + dev_priv->mm.interruptible = was_interruptible; + } } /* Stolen objects don't hold a ref, but do hold pin count. Fix that up @@ -4008,15 +4072,18 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) i915_gem_object_free(obj); } -struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj) +struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj, + struct i915_address_space *vm) { - struct drm_i915_private *dev_priv = obj->base.dev->dev_private; - struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL); + struct i915_vma *vma; + BUG_ON(!vm); + + vma = kzalloc(sizeof(*vma), GFP_KERNEL); if (vma == NULL) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&vma->vma_link); - vma->vm = i915_gtt_vm; + vma->vm = vm; vma->obj = obj; return vma; @@ -4256,10 +4323,10 @@ int i915_gem_init(struct drm_device *dev) */ if (HAS_HW_CONTEXTS(dev)) { i915_gem_setup_global_gtt(dev, 0, dev_priv->gtt.mappable_end, - i915_gtt_vm->total, 0); + dev_priv->gtt.base.total, 0); i915_gem_context_init(dev); if (dev_priv->hw_contexts_disabled) { - drm_mm_takedown(&i915_gtt_vm->mm); + drm_mm_takedown(&dev_priv->gtt.base.mm); goto ggtt_only; } } else @@ -4270,7 +4337,7 @@ ggtt_only: if (HAS_HW_CONTEXTS(dev)) DRM_DEBUG_DRIVER("Context setup failed %d\n", ret); i915_gem_setup_global_gtt(dev, 0, dev_priv->gtt.mappable_end, - i915_gtt_vm->total, PAGE_SIZE); + dev_priv->gtt.base.total, PAGE_SIZE); } ret = i915_gem_init_hw(dev); @@ -4321,7 +4388,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, return ret; } - BUG_ON(!list_empty(&i915_gtt_vm->active_list)); + BUG_ON(!list_empty(ggtt_list(active_list))); mutex_unlock(&dev->struct_mutex); ret = drm_irq_install(dev); @@ -4370,6 +4437,16 @@ init_ring_lists(struct intel_ring_buffer *ring) INIT_LIST_HEAD(&ring->request_list); } +static void i915_init_vm(struct drm_i915_private *dev_priv, + struct i915_address_space *vm) +{ + vm->dev = dev_priv->dev; + INIT_LIST_HEAD(&vm->active_list); + INIT_LIST_HEAD(&vm->inactive_list); + INIT_LIST_HEAD(&vm->global_link); + list_add(&vm->global_link, &dev_priv->vm_list); +} + void i915_gem_load(struct drm_device *dev) { @@ -4382,8 +4459,9 @@ i915_gem_load(struct drm_device *dev) SLAB_HWCACHE_ALIGN, NULL); - INIT_LIST_HEAD(&i915_gtt_vm->active_list); - INIT_LIST_HEAD(&i915_gtt_vm->inactive_list); + INIT_LIST_HEAD(&dev_priv->vm_list); + i915_init_vm(dev_priv, &dev_priv->gtt.base); + INIT_LIST_HEAD(&dev_priv->mm.unbound_list); INIT_LIST_HEAD(&dev_priv->mm.bound_list); INIT_LIST_HEAD(&dev_priv->mm.fence_list); @@ -4654,8 +4732,9 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) struct drm_i915_private, mm.inactive_shrinker); struct drm_device *dev = dev_priv->dev; + struct i915_address_space *vm; struct drm_i915_gem_object *obj; - int nr_to_scan = sc->nr_to_scan; + int nr_to_scan; bool unlock = true; int cnt; @@ -4669,6 +4748,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) unlock = false; } + nr_to_scan = sc->nr_to_scan; if (nr_to_scan) { nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan); if (nr_to_scan > 0) @@ -4682,11 +4762,94 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc) list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) if (obj->pages_pin_count == 0) cnt += obj->base.size >> PAGE_SHIFT; - list_for_each_entry(obj, &i915_gtt_vm->inactive_list, global_list) - if (obj->pin_count == 0 && obj->pages_pin_count == 0) - cnt += obj->base.size >> PAGE_SHIFT; + + list_for_each_entry(vm, &dev_priv->vm_list, global_link) + list_for_each_entry(obj, &vm->inactive_list, global_list) + if (obj->pin_count == 0 && obj->pages_pin_count == 0) + cnt += obj->base.size >> PAGE_SHIFT; if (unlock) mutex_unlock(&dev->struct_mutex); return cnt; } + +/* All the new VM stuff */ +unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o, + struct i915_address_space *vm) +{ + struct drm_i915_private *dev_priv = o->base.dev->dev_private; + struct i915_vma *vma; + + if (vm == &dev_priv->gtt.aliasing_ppgtt->base) + vm = &dev_priv->gtt.base; + + BUG_ON(list_empty(&o->vma_list)); + list_for_each_entry(vma, &o->vma_list, vma_link) { + if (vma->vm == vm) + return vma->node.start; + + } + WARN_ON(1); + return I915_INVALID_OFFSET; +} + +bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o) +{ + return !list_empty(&o->vma_list); +} + +bool i915_gem_obj_bound(struct drm_i915_gem_object *o, + struct i915_address_space *vm) +{ + struct i915_vma *vma; + + list_for_each_entry(vma, &o->vma_list, vma_link) { + if (vma->vm == vm) + return true; + } + return false; +} + +unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, + struct i915_address_space *vm) +{ + struct drm_i915_private *dev_priv = o->base.dev->dev_private; + struct i915_vma *vma; + + if (vm == &dev_priv->gtt.aliasing_ppgtt->base) + vm = &dev_priv->gtt.base; + BUG_ON(list_empty(&o->vma_list)); + list_for_each_entry(vma, &o->vma_list, vma_link) { + if (vma->vm == vm) + return vma->node.size; + } + + return 0; +} + +void i915_gem_obj_set_color(struct drm_i915_gem_object *o, + struct i915_address_space *vm, + enum i915_cache_level color) +{ + struct i915_vma *vma; + BUG_ON(list_empty(&o->vma_list)); + list_for_each_entry(vma, &o->vma_list, vma_link) { + if (vma->vm == vm) { + vma->node.color = color; + return; + } + } + + WARN(1, "Couldn't set color for VM %p\n", vm); +} + +struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj, + struct i915_address_space *vm) +{ + struct i915_vma *vma; + list_for_each_entry(vma, &obj->vma_list, vma_link) + if (vma->vm == vm) + return vma; + + return NULL; +} diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 75b4e27..5d5a60f 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -157,6 +157,7 @@ create_hw_context(struct drm_device *dev, if (INTEL_INFO(dev)->gen >= 7) { ret = i915_gem_object_set_cache_level(ctx->obj, + &dev_priv->gtt.base, I915_CACHE_LLC_MLC); /* Failure shouldn't ever happen this early */ if (WARN_ON(ret)) @@ -219,7 +220,7 @@ static int create_default_context(struct drm_i915_private *dev_priv) * may not be available. To avoid this we always pin the * default context. */ - ret = i915_gem_object_pin(ctx->obj, CONTEXT_ALIGN, false, false); + ret = i915_gem_ggtt_pin(ctx->obj, CONTEXT_ALIGN, false, false); if (ret) { DRM_DEBUG_DRIVER("Couldn't pin %d\n", ret); goto err_destroy; @@ -395,7 +396,7 @@ mi_set_context(struct intel_ring_buffer *ring, intel_ring_emit(ring, MI_NOOP); intel_ring_emit(ring, MI_SET_CONTEXT); - intel_ring_emit(ring, i915_gem_obj_offset(new_context->obj) | + intel_ring_emit(ring, i915_gem_ggtt_offset(new_context->obj) | MI_MM_SPACE_GTT | MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN | @@ -416,6 +417,7 @@ mi_set_context(struct intel_ring_buffer *ring, static int do_switch(struct i915_hw_context *to) { struct intel_ring_buffer *ring = to->ring; + struct drm_i915_private *dev_priv = ring->dev->dev_private; struct i915_hw_context *from = ring->last_context; u32 hw_flags = 0; int ret; @@ -425,7 +427,7 @@ static int do_switch(struct i915_hw_context *to) if (from == to) return 0; - ret = i915_gem_object_pin(to->obj, CONTEXT_ALIGN, false, false); + ret = i915_gem_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false); if (ret) return ret; @@ -462,7 +464,8 @@ static int do_switch(struct i915_hw_context *to) */ if (from != NULL) { from->obj->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION; - i915_gem_object_move_to_active(from->obj, ring); + i915_gem_object_move_to_active(from->obj, &dev_priv->gtt.base, + ring); /* As long as MI_SET_CONTEXT is serializing, ie. it flushes the * whole damn pipeline, we don't need to explicitly mark the * object dirty. The only exception is that the context must be diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 10aa4d2..7a210b8 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -32,20 +32,18 @@ #include "i915_trace.h" static bool -mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind) +mark_free(struct i915_vma *vma, struct list_head *unwind) { - struct i915_vma *vma = __i915_gem_obj_to_vma(obj); - - if (obj->pin_count) + if (vma->obj->pin_count) return false; - list_add(&obj->exec_list, unwind); + list_add(&vma->obj->exec_list, unwind); return drm_mm_scan_add_block(&vma->node); } int -i915_gem_evict_something(struct drm_device *dev, int min_size, - unsigned alignment, unsigned cache_level, +i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm, + int min_size, unsigned alignment, unsigned cache_level, bool mappable, bool nonblocking) { drm_i915_private_t *dev_priv = dev->dev_private; @@ -81,16 +79,16 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, INIT_LIST_HEAD(&unwind_list); if (mappable) - drm_mm_init_scan_with_range(&i915_gtt_vm->mm, min_size, - alignment, cache_level, 0, + drm_mm_init_scan_with_range(&vm->mm, min_size, alignment, + cache_level, 0, dev_priv->gtt.mappable_end); else - drm_mm_init_scan(&i915_gtt_vm->mm, min_size, alignment, - cache_level); + drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level); /* First see if there is a large enough contiguous idle region... */ - list_for_each_entry(obj, &i915_gtt_vm->inactive_list, mm_list) { - if (mark_free(obj, &unwind_list)) + list_for_each_entry(obj, &vm->inactive_list, mm_list) { + struct i915_vma *vma = i915_gem_obj_to_vma(obj, vm); + if (mark_free(vma, &unwind_list)) goto found; } @@ -98,8 +96,9 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, goto none; /* Now merge in the soon-to-be-expired objects... */ - list_for_each_entry(obj, &i915_gtt_vm->active_list, mm_list) { - if (mark_free(obj, &unwind_list)) + list_for_each_entry(obj, &vm->active_list, mm_list) { + struct i915_vma *vma = i915_gem_obj_to_vma(obj, vm); + if (mark_free(vma, &unwind_list)) goto found; } @@ -109,7 +108,7 @@ none: obj = list_first_entry(&unwind_list, struct drm_i915_gem_object, exec_list); - vma = __i915_gem_obj_to_vma(obj); + vma = i915_gem_obj_to_vma(obj, vm); ret = drm_mm_scan_remove_block(&vma->node); BUG_ON(ret); @@ -131,7 +130,7 @@ found: obj = list_first_entry(&unwind_list, struct drm_i915_gem_object, exec_list); - vma = __i915_gem_obj_to_vma(obj); + vma = i915_gem_obj_to_vma(obj, vm); if (drm_mm_scan_remove_block(&vma->node)) { list_move(&obj->exec_list, &eviction_list); drm_gem_object_reference(&obj->base); @@ -146,7 +145,7 @@ found: struct drm_i915_gem_object, exec_list); if (ret == 0) - ret = i915_gem_object_unbind(obj); + ret = i915_gem_object_unbind(obj, vm); list_del_init(&obj->exec_list); drm_gem_object_unreference(&obj->base); @@ -160,11 +159,17 @@ i915_gem_evict_everything(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj, *next; - bool lists_empty; + struct i915_address_space *vm; + bool lists_empty = true; int ret; - lists_empty = (list_empty(&i915_gtt_vm->inactive_list) && - list_empty(&i915_gtt_vm->active_list)); + list_for_each_entry(vm, &dev_priv->vm_list, global_link) { + lists_empty = (list_empty(&vm->inactive_list) && + list_empty(&vm->active_list)); + if (!lists_empty) + lists_empty = false; + } + if (lists_empty) return -ENOSPC; @@ -181,10 +186,12 @@ i915_gem_evict_everything(struct drm_device *dev) i915_gem_retire_requests(dev); /* Having flushed everything, unbind() should never raise an error */ - list_for_each_entry_safe(obj, next, - &i915_gtt_vm->inactive_list, mm_list) - if (obj->pin_count == 0) - WARN_ON(i915_gem_object_unbind(obj)); + list_for_each_entry(vm, &dev_priv->vm_list, global_link) { + list_for_each_entry_safe(obj, next, &vm->inactive_list, mm_list) + if (obj->pin_count == 0) + WARN_ON(i915_gem_object_unbind(obj, vm)); + } + return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 837372d..620f395 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -150,7 +150,7 @@ eb_get_object(struct eb_objects *eb, unsigned long handle) } static void -eb_destroy(struct eb_objects *eb) +eb_destroy(struct eb_objects *eb, struct i915_address_space *vm) { while (!list_empty(&eb->objects)) { struct drm_i915_gem_object *obj; @@ -174,7 +174,8 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj) static int i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, struct eb_objects *eb, - struct drm_i915_gem_relocation_entry *reloc) + struct drm_i915_gem_relocation_entry *reloc, + struct i915_address_space *vm) { struct drm_device *dev = obj->base.dev; struct drm_gem_object *target_obj; @@ -188,7 +189,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, return -ENOENT; target_i915_obj = to_intel_bo(target_obj); - target_offset = i915_gem_obj_offset(target_i915_obj); + target_offset = i915_gem_obj_offset(target_i915_obj, vm); /* Sandybridge PPGTT errata: We need a global gtt mapping for MI and * pipe_control writes because the gpu doesn't properly redirect them @@ -280,7 +281,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, return ret; /* Map the page containing the relocation we're going to perform. */ - reloc->offset += i915_gem_obj_offset(obj); + reloc->offset += i915_gem_obj_offset(obj, vm); reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, reloc->offset & PAGE_MASK); reloc_entry = (uint32_t __iomem *) @@ -297,7 +298,8 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, static int i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj, - struct eb_objects *eb) + struct eb_objects *eb, + struct i915_address_space *vm) { #define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry)) struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)]; @@ -321,7 +323,8 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj, do { u64 offset = r->presumed_offset; - ret = i915_gem_execbuffer_relocate_entry(obj, eb, r); + ret = i915_gem_execbuffer_relocate_entry(obj, eb, r, + vm); if (ret) return ret; @@ -344,13 +347,15 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj, static int i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj, struct eb_objects *eb, - struct drm_i915_gem_relocation_entry *relocs) + struct drm_i915_gem_relocation_entry *relocs, + struct i915_address_space *vm) { const struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; int i, ret; for (i = 0; i < entry->relocation_count; i++) { - ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i]); + ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i], + vm); if (ret) return ret; } @@ -359,7 +364,8 @@ i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj, } static int -i915_gem_execbuffer_relocate(struct eb_objects *eb) +i915_gem_execbuffer_relocate(struct eb_objects *eb, + struct i915_address_space *vm) { struct drm_i915_gem_object *obj; int ret = 0; @@ -373,7 +379,7 @@ i915_gem_execbuffer_relocate(struct eb_objects *eb) */ pagefault_disable(); list_for_each_entry(obj, &eb->objects, exec_list) { - ret = i915_gem_execbuffer_relocate_object(obj, eb); + ret = i915_gem_execbuffer_relocate_object(obj, eb, vm); if (ret) break; } @@ -395,6 +401,7 @@ need_reloc_mappable(struct drm_i915_gem_object *obj) static int i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, struct intel_ring_buffer *ring, + struct i915_address_space *vm, bool *need_reloc) { struct drm_i915_private *dev_priv = obj->base.dev->dev_private; @@ -409,7 +416,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, obj->tiling_mode != I915_TILING_NONE; need_mappable = need_fence || need_reloc_mappable(obj); - ret = i915_gem_object_pin(obj, entry->alignment, need_mappable, false); + ret = i915_gem_object_pin(obj, vm, entry->alignment, need_mappable, + false); if (ret) return ret; @@ -436,8 +444,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, obj->has_aliasing_ppgtt_mapping = 1; } - if (entry->offset != i915_gem_obj_offset(obj)) { - entry->offset = i915_gem_obj_offset(obj); + if (entry->offset != i915_gem_obj_offset(obj, vm)) { + entry->offset = i915_gem_obj_offset(obj, vm); *need_reloc = true; } @@ -458,7 +466,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj) { struct drm_i915_gem_exec_object2 *entry; - if (!i915_gem_obj_bound(obj)) + if (!i915_gem_obj_bound_any(obj)) return; entry = obj->exec_entry; @@ -475,6 +483,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj) static int i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, struct list_head *objects, + struct i915_address_space *vm, bool *need_relocs) { struct drm_i915_gem_object *obj; @@ -531,32 +540,35 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, unsigned long obj_offset; bool need_fence, need_mappable; - if (!i915_gem_obj_bound(obj)) + if (!i915_gem_obj_bound(obj, vm)) continue; - obj_offset = i915_gem_obj_offset(obj); + obj_offset = i915_gem_obj_offset(obj, vm); need_fence = has_fenced_gpu_access && entry->flags & EXEC_OBJECT_NEEDS_FENCE && obj->tiling_mode != I915_TILING_NONE; need_mappable = need_fence || need_reloc_mappable(obj); + BUG_ON((need_mappable || need_fence) && + !is_i915_ggtt(vm)); + if ((entry->alignment && obj_offset & (entry->alignment - 1)) || (need_mappable && !obj->map_and_fenceable)) - ret = i915_gem_object_unbind(obj); + ret = i915_gem_object_unbind(obj, vm); else - ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs); + ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs); if (ret) goto err; } /* Bind fresh objects */ list_for_each_entry(obj, objects, exec_list) { - if (i915_gem_obj_bound(obj)) + if (i915_gem_obj_bound(obj, vm)) continue; - ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs); + ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs); if (ret) goto err; } @@ -580,7 +592,8 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, struct drm_file *file, struct intel_ring_buffer *ring, struct eb_objects *eb, - struct drm_i915_gem_exec_object2 *exec) + struct drm_i915_gem_exec_object2 *exec, + struct i915_address_space *vm) { struct drm_i915_gem_relocation_entry *reloc; struct drm_i915_gem_object *obj; @@ -664,14 +677,15 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, goto err; need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; - ret = i915_gem_execbuffer_reserve(ring, &eb->objects, &need_relocs); + ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs); if (ret) goto err; list_for_each_entry(obj, &eb->objects, exec_list) { int offset = obj->exec_entry - exec; ret = i915_gem_execbuffer_relocate_object_slow(obj, eb, - reloc + reloc_offset[offset]); + reloc + reloc_offset[offset], + vm); if (ret) goto err; } @@ -770,6 +784,7 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, static void i915_gem_execbuffer_move_to_active(struct list_head *objects, + struct i915_address_space *vm, struct intel_ring_buffer *ring) { struct drm_i915_gem_object *obj; @@ -784,7 +799,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects, obj->base.read_domains = obj->base.pending_read_domains; obj->fenced_gpu_access = obj->pending_fenced_gpu_access; - i915_gem_object_move_to_active(obj, ring); + i915_gem_object_move_to_active(obj, vm, ring); if (obj->base.write_domain) { obj->dirty = 1; obj->last_write_seqno = intel_ring_get_seqno(ring); @@ -838,7 +853,8 @@ static int i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct drm_file *file, struct drm_i915_gem_execbuffer2 *args, - struct drm_i915_gem_exec_object2 *exec) + struct drm_i915_gem_exec_object2 *exec, + struct i915_address_space *vm) { drm_i915_private_t *dev_priv = dev->dev_private; struct eb_objects *eb; @@ -1001,17 +1017,17 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, /* Move the objects en-masse into the GTT, evicting if necessary. */ need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; - ret = i915_gem_execbuffer_reserve(ring, &eb->objects, &need_relocs); + ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs); if (ret) goto err; /* The objects are in their final locations, apply the relocations. */ if (need_relocs) - ret = i915_gem_execbuffer_relocate(eb); + ret = i915_gem_execbuffer_relocate(eb, vm); if (ret) { if (ret == -EFAULT) { ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring, - eb, exec); + eb, exec, vm); BUG_ON(!mutex_is_locked(&dev->struct_mutex)); } if (ret) @@ -1074,7 +1090,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto err; } - exec_start = i915_gem_obj_offset(batch_obj) + args->batch_start_offset; + exec_start = i915_gem_obj_offset(batch_obj, vm) + + args->batch_start_offset; exec_len = args->batch_len; if (cliprects) { for (i = 0; i < args->num_cliprects; i++) { @@ -1099,11 +1116,11 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags); - i915_gem_execbuffer_move_to_active(&eb->objects, ring); + i915_gem_execbuffer_move_to_active(&eb->objects, vm, ring); i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj); err: - eb_destroy(eb); + eb_destroy(eb, vm); mutex_unlock(&dev->struct_mutex); @@ -1120,6 +1137,7 @@ int i915_gem_execbuffer(struct drm_device *dev, void *data, struct drm_file *file) { + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_execbuffer *args = data; struct drm_i915_gem_execbuffer2 exec2; struct drm_i915_gem_exec_object *exec_list = NULL; @@ -1175,7 +1193,8 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, exec2.flags = I915_EXEC_RENDER; i915_execbuffer2_set_context_id(exec2, 0); - ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list); + ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list, + &dev_priv->gtt.base); if (!ret) { /* Copy the new buffer offsets back to the user's exec list. */ for (i = 0; i < args->buffer_count; i++) @@ -1201,6 +1220,7 @@ int i915_gem_execbuffer2(struct drm_device *dev, void *data, struct drm_file *file) { + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_execbuffer2 *args = data; struct drm_i915_gem_exec_object2 *exec2_list = NULL; int ret; @@ -1231,7 +1251,8 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, return -EFAULT; } - ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list); + ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list, + &dev_priv->gtt.base); if (!ret) { /* Copy the new buffer offsets back to the user's exec list. */ ret = copy_to_user(to_user_ptr(args->buffers_ptr), diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 9f686c6..8b59729 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -278,12 +278,12 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) * multiplied by page size. We allocate at the top of the GTT to avoid * fragmentation. */ - BUG_ON(!drm_mm_initialized(&i915_gtt_vm->mm)); - ret = drm_mm_insert_node_in_range_generic(&i915_gtt_vm->mm, + BUG_ON(!drm_mm_initialized(&dev_priv->gtt.base.mm)); + ret = drm_mm_insert_node_in_range_generic(&dev_priv->gtt.base.mm, &ppgtt->node, GEN6_PD_SIZE, GEN6_PD_ALIGN, 0, dev_priv->gtt.mappable_end, - i915_gtt_vm->total, + dev_priv->gtt.base.total, DRM_MM_TOPDOWN); if (ret) return ret; @@ -382,6 +382,8 @@ int i915_gem_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt) drm_mm_init(&ppgtt->base.mm, ppgtt->base.start, ppgtt->base.total); + /* i915_init_vm(dev_priv, &ppgtt->base) */ + return ret; } @@ -389,17 +391,22 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, struct drm_i915_gem_object *obj, enum i915_cache_level cache_level) { - ppgtt->base.insert_entries(&ppgtt->base, obj->pages, - i915_gem_obj_offset(obj) >> PAGE_SHIFT, - cache_level); + struct i915_address_space *vm = &ppgtt->base; + unsigned long obj_offset = i915_gem_obj_offset(obj, vm); + + vm->insert_entries(vm, obj->pages, + obj_offset >> PAGE_SHIFT, + cache_level); } void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, struct drm_i915_gem_object *obj) { - ppgtt->base.clear_range(&ppgtt->base, - i915_gem_obj_offset(obj) >> PAGE_SHIFT, - obj->base.size >> PAGE_SHIFT); + struct i915_address_space *vm = &ppgtt->base; + unsigned long obj_offset = i915_gem_obj_offset(obj, vm); + + vm->clear_range(vm, obj_offset >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT); } extern int intel_iommu_gfx_mapped; @@ -443,12 +450,12 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible) void i915_gem_restore_gtt_mappings(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; struct drm_i915_gem_object *obj; /* First fill our portion of the GTT with scratch pages */ - i915_gtt_vm->clear_range(&dev_priv->gtt.base, - i915_gtt_vm->start / PAGE_SIZE, - i915_gtt_vm->total / PAGE_SIZE); + gtt_vm->clear_range(&dev_priv->gtt.base, gtt_vm->start / PAGE_SIZE, + gtt_vm->total / PAGE_SIZE); if (dev_priv->gtt.aliasing_ppgtt) gen6_write_pdes(dev_priv->gtt.aliasing_ppgtt); @@ -570,11 +577,11 @@ void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long obj_offset = i915_gem_obj_offset(obj); + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; + uint32_t obj_offset = i915_gem_ggtt_offset(obj); - i915_gtt_vm->insert_entries(&dev_priv->gtt.base, obj->pages, - obj_offset >> PAGE_SHIFT, - cache_level); + gtt_vm->insert_entries(gtt_vm, obj->pages, obj_offset >> PAGE_SHIFT, + cache_level); obj->has_global_gtt_mapping = 1; } @@ -583,11 +590,11 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj) { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long obj_offset = i915_gem_obj_offset(obj); + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; + uint32_t obj_offset = i915_gem_obj_offset(obj, gtt_vm); - i915_gtt_vm->clear_range(&dev_priv->gtt.base, - obj_offset >> PAGE_SHIFT, - obj->base.size >> PAGE_SHIFT); + gtt_vm->clear_range(gtt_vm, obj_offset >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT); obj->has_global_gtt_mapping = 0; } @@ -665,7 +672,8 @@ void i915_gem_setup_global_gtt(struct drm_device *dev, * aperture. One page should be enough to keep any prefetching inside * of the aperture. */ - drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; struct drm_mm_node *entry; struct drm_i915_gem_object *obj; unsigned long hole_start, hole_end; @@ -675,50 +683,50 @@ void i915_gem_setup_global_gtt(struct drm_device *dev, if (WARN_ON(guard_size & ~PAGE_MASK)) guard_size = round_up(guard_size, PAGE_SIZE); - drm_mm_init(&i915_gtt_vm->mm, start, end - start - guard_size); + drm_mm_init(>t_vm->mm, start, end - start - guard_size); if (!HAS_LLC(dev)) - i915_gtt_vm->mm.color_adjust = i915_gtt_color_adjust; + gtt_vm->mm.color_adjust = i915_gtt_color_adjust; /* Mark any preallocated objects as occupied */ list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - struct i915_vma *vma = __i915_gem_obj_to_vma(obj); + struct i915_vma *vma = i915_gem_obj_to_vma(obj, gtt_vm); uintptr_t gtt_offset = (uintptr_t)vma->deferred_offset; int ret; DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n", - i915_gem_obj_offset(obj), obj->base.size); + i915_gem_ggtt_offset(obj), obj->base.size); BUG_ON((gtt_offset & I915_GTT_RESERVED) == 0); gtt_offset = gtt_offset & ~I915_GTT_RESERVED; - ret = drm_mm_create_block(&i915_gtt_vm->mm, + ret = drm_mm_create_block(>t_vm->mm, &vma->node, gtt_offset, obj->base.size); if (ret) DRM_DEBUG_KMS("Reservation failed\n"); obj->has_global_gtt_mapping = 1; - list_add(&__i915_gem_obj_to_vma(obj)->vma_link, &obj->vma_list); + list_add(&vma->vma_link, &obj->vma_list); } - i915_gtt_vm->start = start; - i915_gtt_vm->total = end - start; + gtt_vm->start = start; + gtt_vm->total = end - start; /* Clear any non-preallocated blocks */ - drm_mm_for_each_hole(entry, &i915_gtt_vm->mm, - hole_start, hole_end) { + drm_mm_for_each_hole(entry, >t_vm->mm, hole_start, hole_end) { DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n", hole_start, hole_end); - i915_gtt_vm->clear_range(i915_gtt_vm, hole_start / PAGE_SIZE, - (hole_end-hole_start) / PAGE_SIZE); + gtt_vm->clear_range(gtt_vm, hole_start / PAGE_SIZE, + (hole_end-hole_start) / PAGE_SIZE); } /* And finally clear the reserved guard page */ - i915_gtt_vm->clear_range(i915_gtt_vm, (end - guard_size) / PAGE_SIZE, - guard_size / PAGE_SIZE); + gtt_vm->clear_range(gtt_vm, (end - guard_size) / PAGE_SIZE, + guard_size / PAGE_SIZE); } static int setup_scratch_page(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; struct page *page; dma_addr_t dma_addr; @@ -736,8 +744,8 @@ static int setup_scratch_page(struct drm_device *dev) #else dma_addr = page_to_phys(page); #endif - i915_gtt_vm->scratch.page = page; - i915_gtt_vm->scratch.addr = dma_addr; + gtt_vm->scratch.page = page; + gtt_vm->scratch.addr = dma_addr; return 0; } @@ -745,12 +753,13 @@ static int setup_scratch_page(struct drm_device *dev) static void teardown_scratch_page(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; - set_pages_wb(i915_gtt_vm->scratch.page, 1); - pci_unmap_page(dev->pdev, i915_gtt_vm->scratch.addr, + set_pages_wb(gtt_vm->scratch.page, 1); + pci_unmap_page(dev->pdev, gtt_vm->scratch.addr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - put_page(i915_gtt_vm->scratch.page); - __free_page(i915_gtt_vm->scratch.page); + put_page(gtt_vm->scratch.page); + __free_page(gtt_vm->scratch.page); } static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl) @@ -774,6 +783,7 @@ static int gen6_gmch_probe(struct drm_device *dev, unsigned long *mappable_end) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; phys_addr_t gtt_bus_addr; unsigned int gtt_size; u16 snb_gmch_ctl; @@ -813,8 +823,8 @@ static int gen6_gmch_probe(struct drm_device *dev, if (ret) DRM_ERROR("Scratch setup failed\n"); - i915_gtt_vm->clear_range = gen6_ggtt_clear_range; - i915_gtt_vm->insert_entries = gen6_ggtt_insert_entries; + gtt_vm->clear_range = gen6_ggtt_clear_range; + gtt_vm->insert_entries = gen6_ggtt_insert_entries; return ret; } @@ -833,6 +843,7 @@ static int i915_gmch_probe(struct drm_device *dev, unsigned long *mappable_end) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; int ret; ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->dev->pdev, NULL); @@ -844,8 +855,8 @@ static int i915_gmch_probe(struct drm_device *dev, intel_gtt_get(gtt_total, stolen, mappable_base, mappable_end); dev_priv->gtt.do_idle_maps = needs_idle_maps(dev_priv->dev); - i915_gtt_vm->clear_range = i915_ggtt_clear_range; - i915_gtt_vm->insert_entries = i915_ggtt_insert_entries; + gtt_vm->clear_range = i915_ggtt_clear_range; + gtt_vm->insert_entries = i915_ggtt_insert_entries; return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 13d24aa..4863219 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -328,6 +328,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, u32 size) { struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_address_space *gtt_vm = &dev_priv->gtt.base; struct drm_i915_gem_object *obj; struct drm_mm_node *stolen; struct i915_vma *vma; @@ -369,7 +370,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, if (gtt_offset == -1) return obj; - vma = i915_gem_vma_create(obj); + vma = i915_gem_vma_create(obj, gtt_vm); if (!vma) { drm_gem_object_unreference(&obj->base); return NULL; @@ -380,9 +381,9 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, * setting up the GTT space. The actual reservation will occur * later. */ - if (drm_mm_initialized(&i915_gtt_vm->mm)) { - ret = drm_mm_create_block(&i915_gtt_vm->mm, &vma->node, - gtt_offset, size); + if (drm_mm_initialized(>t_vm->mm)) { + ret = drm_mm_create_block(>t_vm->mm, &vma->node, gtt_offset, + size); if (ret) { DRM_DEBUG_KMS("failed to allocate stolen GTT space\n"); i915_gem_vma_destroy(vma); @@ -396,7 +397,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, obj->has_global_gtt_mapping = 1; list_add_tail(&obj->global_list, &dev_priv->mm.bound_list); - list_add_tail(&obj->mm_list, &i915_gtt_vm->inactive_list); + list_add_tail(&obj->mm_list, >t_vm->inactive_list); return obj; } diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 2478114..25c89a0 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -268,18 +268,18 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode) return true; if (INTEL_INFO(obj->base.dev)->gen == 3) { - if (i915_gem_obj_offset(obj) & ~I915_FENCE_START_MASK) + if (i915_gem_ggtt_offset(obj) & ~I915_FENCE_START_MASK) return false; } else { - if (i915_gem_obj_offset(obj) & ~I830_FENCE_START_MASK) + if (i915_gem_ggtt_offset(obj) & ~I830_FENCE_START_MASK) return false; } size = i915_gem_get_gtt_size(obj->base.dev, obj->base.size, tiling_mode); - if (i915_gem_obj_size(obj) != size) + if (i915_gem_ggtt_size(obj) != size) return false; - if (i915_gem_obj_offset(obj) & (size - 1)) + if (i915_gem_ggtt_offset(obj) & (size - 1)) return false; return true; @@ -358,19 +358,20 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, * whilst executing a fenced command for an untiled object. */ - obj->map_and_fenceable = !i915_gem_obj_bound(obj) || - (i915_gem_obj_offset(obj) + + obj->map_and_fenceable = !i915_gem_obj_bound_ggtt(obj) || + (i915_gem_ggtt_offset(obj) + obj->base.size <= dev_priv->gtt.mappable_end && i915_gem_object_fence_ok(obj, args->tiling_mode)); /* Rebind if we need a change of alignment */ if (!obj->map_and_fenceable) { - u32 unfenced_alignment = + struct i915_address_space *ggtt = &dev_priv->gtt.base; + u32 unfenced_align = i915_gem_get_gtt_alignment(dev, obj->base.size, args->tiling_mode, false); - if (i915_gem_obj_offset(obj) & (unfenced_alignment - 1)) - ret = i915_gem_object_unbind(obj); + if (i915_gem_ggtt_offset(obj) & (unfenced_align - 1)) + ret = i915_gem_object_unbind(obj, ggtt); } if (ret == 0) { diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index c0be641..050eea3 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1512,7 +1512,8 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv, if (dst == NULL) return NULL; - reloc_offset = i915_gem_obj_offset(src); + /* FIXME: must handle per faulty VM */ + reloc_offset = i915_gem_ggtt_offset(src); for (i = 0; i < num_pages; i++) { unsigned long flags; void *d; @@ -1564,7 +1565,7 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv, reloc_offset += PAGE_SIZE; } dst->page_count = num_pages; - dst->gtt_offset = i915_gem_obj_offset(src); + dst->gtt_offset = i915_gem_ggtt_offset(src); return dst; @@ -1618,7 +1619,8 @@ static void capture_bo(struct drm_i915_error_buffer *err, err->name = obj->base.name; err->rseqno = obj->last_read_seqno; err->wseqno = obj->last_write_seqno; - err->gtt_offset = i915_gem_obj_offset(obj); + /* FIXME: plumb the actual context into here to pull the right VM */ + err->gtt_offset = i915_gem_ggtt_offset(obj); err->read_domains = obj->base.read_domains; err->write_domain = obj->base.write_domain; err->fence_reg = obj->fence_reg; @@ -1712,17 +1714,20 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv, if (HAS_BROKEN_CS_TLB(dev_priv->dev)) { u32 acthd = I915_READ(ACTHD); + if (WARN_ON(HAS_HW_CONTEXTS(dev_priv->dev))) + return NULL; + if (WARN_ON(ring->id != RCS)) return NULL; obj = ring->private; - if (acthd >= i915_gem_obj_offset(obj) && - acthd < i915_gem_obj_offset(obj) + obj->base.size) + if (acthd >= i915_gem_ggtt_offset(obj) && + acthd < i915_gem_ggtt_offset(obj) + obj->base.size) return i915_error_object_create(dev_priv, obj); } seqno = ring->get_seqno(ring, false); - list_for_each_entry(obj, &i915_gtt_vm->active_list, mm_list) { + list_for_each_entry(obj, ggtt_list(active_list), mm_list) { if (obj->ring != ring) continue; @@ -1798,7 +1803,7 @@ static void i915_gem_record_active_context(struct intel_ring_buffer *ring, return; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - if ((error->ccid & PAGE_MASK) == i915_gem_obj_offset(obj)) { + if ((error->ccid & PAGE_MASK) == i915_gem_ggtt_offset(obj)) { ering->ctx = i915_error_object_create_sized(dev_priv, obj, 1); } @@ -1857,7 +1862,7 @@ static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv, int i; i = 0; - list_for_each_entry(obj, &i915_gtt_vm->active_list, mm_list) + list_for_each_entry(obj, ggtt_list(active_list), mm_list) i++; error->active_bo_count = i; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) @@ -1877,7 +1882,7 @@ static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv, error->active_bo_count = capture_active_bo(error->active_bo, error->active_bo_count, - &i915_gtt_vm->active_list); + ggtt_list(active_list)); if (error->pinned_bo) error->pinned_bo_count = @@ -2152,10 +2157,10 @@ static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, in if (INTEL_INFO(dev)->gen >= 4) { int dspsurf = DSPSURF(intel_crtc->plane); stall_detected = I915_HI_DISPBASE(I915_READ(dspsurf)) == - i915_gem_obj_offset(obj); + i915_gem_ggtt_offset(obj); } else { int dspaddr = DSPADDR(intel_crtc->plane); - stall_detected = I915_READ(dspaddr) == (i915_gem_obj_offset(obj) + + stall_detected = I915_READ(dspaddr) == (i915_gem_ggtt_offset(obj) + crtc->y * crtc->fb->pitches[0] + crtc->x * crtc->fb->bits_per_pixel/8); } diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index e4dccb3..3f019d3 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -34,11 +34,13 @@ TRACE_EVENT(i915_gem_object_create, ); TRACE_EVENT(i915_gem_object_bind, - TP_PROTO(struct drm_i915_gem_object *obj, bool mappable), - TP_ARGS(obj, mappable), + TP_PROTO(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, bool mappable), + TP_ARGS(obj, vm, mappable), TP_STRUCT__entry( __field(struct drm_i915_gem_object *, obj) + __field(struct i915_address_space *, vm) __field(u32, offset) __field(u32, size) __field(bool, mappable) @@ -46,8 +48,8 @@ TRACE_EVENT(i915_gem_object_bind, TP_fast_assign( __entry->obj = obj; - __entry->offset = i915_gem_obj_offset(obj); - __entry->size = i915_gem_obj_size(obj); + __entry->offset = i915_gem_obj_offset(obj, vm); + __entry->size = i915_gem_obj_size(obj, vm); __entry->mappable = mappable; ), @@ -57,19 +59,21 @@ TRACE_EVENT(i915_gem_object_bind, ); TRACE_EVENT(i915_gem_object_unbind, - TP_PROTO(struct drm_i915_gem_object *obj), - TP_ARGS(obj), + TP_PROTO(struct drm_i915_gem_object *obj, + struct i915_address_space *vm), + TP_ARGS(obj, vm), TP_STRUCT__entry( __field(struct drm_i915_gem_object *, obj) + __field(struct i915_address_space *, vm) __field(u32, offset) __field(u32, size) ), TP_fast_assign( __entry->obj = obj; - __entry->offset = i915_gem_obj_offset(obj); - __entry->size = i915_gem_obj_size(obj); + __entry->offset = i915_gem_obj_offset(obj, vm); + __entry->size = i915_gem_obj_size(obj, vm); ), TP_printk("obj=%p, offset=%08x size=%x", diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 633bfbf..bd1d1bb 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1943,18 +1943,18 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb, } DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n", - i915_gem_obj_offset(obj), linear_offset, x, y, + i915_gem_ggtt_offset(obj), linear_offset, x, y, fb->pitches[0]); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); if (INTEL_INFO(dev)->gen >= 4) { I915_MODIFY_DISPBASE(DSPSURF(plane), - i915_gem_obj_offset(obj) + + i915_gem_ggtt_offset(obj) + intel_crtc->dspaddr_offset); I915_WRITE(DSPTILEOFF(plane), (y << 16) | x); I915_WRITE(DSPLINOFF(plane), linear_offset); } else I915_WRITE(DSPADDR(plane), - i915_gem_obj_offset(obj) + linear_offset); + i915_gem_ggtt_offset(obj) + linear_offset); POSTING_READ(reg); return 0; @@ -2035,11 +2035,11 @@ static int ironlake_update_plane(struct drm_crtc *crtc, linear_offset -= intel_crtc->dspaddr_offset; DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n", - i915_gem_obj_offset(obj), linear_offset, x, y, + i915_gem_ggtt_offset(obj), linear_offset, x, y, fb->pitches[0]); I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]); I915_MODIFY_DISPBASE(DSPSURF(plane), - i915_gem_obj_offset(obj)+intel_crtc->dspaddr_offset); + i915_gem_ggtt_offset(obj)+intel_crtc->dspaddr_offset); if (IS_HASWELL(dev)) { I915_WRITE(DSPOFFSET(plane), (y << 16) | x); } else { @@ -6558,7 +6558,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, goto fail_unpin; } - addr = i915_gem_obj_offset(obj); + addr = i915_gem_ggtt_offset(obj); } else { int align = IS_I830(dev) ? 16 * 1024 : 256; ret = i915_gem_attach_phys_object(dev, obj, @@ -7274,7 +7274,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev, MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); intel_ring_emit(ring, - i915_gem_obj_offset(obj) + intel_crtc->dspaddr_offset); + i915_gem_ggtt_offset(obj) + intel_crtc->dspaddr_offset); intel_ring_emit(ring, 0); /* aux display base address, unused */ intel_mark_page_flip_active(intel_crtc); @@ -7316,7 +7316,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev, MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); intel_ring_emit(ring, - i915_gem_obj_offset(obj) + intel_crtc->dspaddr_offset); + i915_gem_ggtt_offset(obj) + intel_crtc->dspaddr_offset); intel_ring_emit(ring, MI_NOOP); intel_mark_page_flip_active(intel_crtc); @@ -7356,7 +7356,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev, MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); intel_ring_emit(ring, - (i915_gem_obj_offset(obj) + intel_crtc->dspaddr_offset) | + (i915_gem_ggtt_offset(obj) + intel_crtc->dspaddr_offset) | obj->tiling_mode); /* XXX Enabling the panel-fitter across page-flip is so far @@ -7400,7 +7400,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev, MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode); intel_ring_emit(ring, - i915_gem_obj_offset(obj) + intel_crtc->dspaddr_offset); + i915_gem_ggtt_offset(obj) + intel_crtc->dspaddr_offset); /* Contrary to the suggestions in the documentation, * "Enable Panel Fitter" does not seem to be required when page @@ -7466,7 +7466,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit); intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode)); intel_ring_emit(ring, - i915_gem_obj_offset(obj) + intel_crtc->dspaddr_offset); + i915_gem_ggtt_offset(obj) + intel_crtc->dspaddr_offset); intel_ring_emit(ring, (MI_NOOP)); intel_mark_page_flip_active(intel_crtc); diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 8315a5e..1e56ab2 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -139,11 +139,11 @@ static int intelfb_create(struct drm_fb_helper *helper, info->apertures->ranges[0].base = dev->mode_config.fb_base; info->apertures->ranges[0].size = dev_priv->gtt.mappable_end; - info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_offset(obj); + info->fix.smem_start = dev->mode_config.fb_base + i915_gem_ggtt_offset(obj); info->fix.smem_len = size; info->screen_base = - ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_offset(obj), + ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_ggtt_offset(obj), size); if (!info->screen_base) { ret = -ENOSPC; @@ -168,7 +168,7 @@ static int intelfb_create(struct drm_fb_helper *helper, DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n", fb->width, fb->height, - i915_gem_obj_offset(obj), obj); + i915_gem_ggtt_offset(obj), obj); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index 41654b1..24aeb02 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -196,7 +196,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay) regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_obj->handle->vaddr; else regs = io_mapping_map_wc(dev_priv->gtt.mappable, - i915_gem_obj_offset(overlay->reg_bo)); + i915_gem_ggtt_offset(overlay->reg_bo)); return regs; } @@ -740,7 +740,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, swidth = params->src_w; swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width); sheight = params->src_h; - iowrite32(i915_gem_obj_offset(new_bo) + params->offset_Y, + iowrite32(i915_gem_ggtt_offset(new_bo) + params->offset_Y, ®s->OBUF_0Y); ostride = params->stride_Y; @@ -755,9 +755,9 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, params->src_w/uv_hscale); swidthsw |= max_t(u32, tmp_U, tmp_V) << 16; sheight |= (params->src_h/uv_vscale) << 16; - iowrite32(i915_gem_obj_offset(new_bo) + params->offset_U, + iowrite32(i915_gem_ggtt_offset(new_bo) + params->offset_U, ®s->OBUF_0U); - iowrite32(i915_gem_obj_offset(new_bo) + params->offset_V, + iowrite32(i915_gem_ggtt_offset(new_bo) + params->offset_V, ®s->OBUF_0V); ostride |= params->stride_UV << 16; } @@ -1353,12 +1353,12 @@ void intel_setup_overlay(struct drm_device *dev) } overlay->flip_addr = reg_bo->phys_obj->handle->busaddr; } else { - ret = i915_gem_object_pin(reg_bo, PAGE_SIZE, true, false); + ret = i915_gem_ggtt_pin(reg_bo, PAGE_SIZE, true, false); if (ret) { DRM_ERROR("failed to pin overlay register bo\n"); goto out_free_bo; } - overlay->flip_addr = i915_gem_obj_offset(reg_bo); + overlay->flip_addr = i915_gem_ggtt_offset(reg_bo); ret = i915_gem_object_set_to_gtt_domain(reg_bo, true); if (ret) { @@ -1437,7 +1437,7 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay) overlay->reg_bo->phys_obj->handle->vaddr; return io_mapping_map_atomic_wc(dev_priv->gtt.mappable, - i915_gem_obj_offset(overlay->reg_bo)); + i915_gem_ggtt_offset(overlay->reg_bo)); } static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay, @@ -1468,7 +1468,7 @@ intel_overlay_capture_error_state(struct drm_device *dev) if (OVERLAY_NEEDS_PHYSICAL(overlay->dev)) error->base = (__force long)overlay->reg_bo->phys_obj->handle->vaddr; else - error->base = i915_gem_obj_offset(overlay->reg_bo); + error->base = i915_gem_ggtt_offset(overlay->reg_bo); regs = intel_overlay_map_regs_atomic(overlay); if (!regs) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 9bea2e0..f8f2f1d 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -217,7 +217,8 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval) (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) | (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT)); I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y); - I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_offset(obj) | ILK_FBC_RT_VALID); + I915_WRITE(ILK_FBC_RT_BASE, + i915_gem_ggtt_offset(obj) | ILK_FBC_RT_VALID); /* enable it... */ I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); @@ -274,7 +275,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval) struct drm_i915_gem_object *obj = intel_fb->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - I915_WRITE(IVB_FBC_RT_BASE, i915_gem_obj_offset(obj)); + I915_WRITE(IVB_FBC_RT_BASE, i915_gem_ggtt_offset(obj)); I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X | IVB_DPFC_CTL_FENCE_EN | @@ -2860,7 +2861,7 @@ intel_alloc_context_page(struct drm_device *dev) return NULL; } - ret = i915_gem_object_pin(ctx, 4096, true, false); + ret = i915_gem_ggtt_pin(ctx, 4096, true, false); if (ret) { DRM_ERROR("failed to pin power context: %d\n", ret); goto err_unref; @@ -3685,7 +3686,7 @@ static void ironlake_enable_rc6(struct drm_device *dev) intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN); intel_ring_emit(ring, MI_SET_CONTEXT); - intel_ring_emit(ring, i915_gem_obj_offset(dev_priv->ips.renderctx) | + intel_ring_emit(ring, i915_gem_ggtt_offset(dev_priv->ips.renderctx) | MI_MM_SPACE_GTT | MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN | @@ -3708,7 +3709,7 @@ static void ironlake_enable_rc6(struct drm_device *dev) return; } - I915_WRITE(PWRCTXA, i915_gem_obj_offset(dev_priv->ips.pwrctx) | + I915_WRITE(PWRCTXA, i915_gem_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN); I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 64b579f..4c6cf56 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -424,14 +424,14 @@ static int init_ring_common(struct intel_ring_buffer *ring) * registers with the above sequence (the readback of the HEAD registers * also enforces ordering), otherwise the hw might lose the new ring * register values. */ - I915_WRITE_START(ring, i915_gem_obj_offset(obj)); + I915_WRITE_START(ring, i915_gem_ggtt_offset(obj)); I915_WRITE_CTL(ring, ((ring->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID); /* If the head is still not zero, the ring is dead */ if (wait_for((I915_READ_CTL(ring) & RING_VALID) != 0 && - I915_READ_START(ring) == i915_gem_obj_offset(obj) && + I915_READ_START(ring) == i915_gem_ggtt_offset(obj) && (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) { DRM_ERROR("%s initialization failed " "ctl %08x head %08x tail %08x start %08x\n", @@ -465,6 +465,7 @@ out: static int init_pipe_control(struct intel_ring_buffer *ring) { + struct drm_i915_private *dev_priv = ring->dev->dev_private; struct pipe_control *pc; struct drm_i915_gem_object *obj; int ret; @@ -483,13 +484,14 @@ init_pipe_control(struct intel_ring_buffer *ring) goto err; } - i915_gem_object_set_cache_level(obj, I915_CACHE_LLC); + i915_gem_object_set_cache_level(obj, &dev_priv->gtt.base, + I915_CACHE_LLC); - ret = i915_gem_object_pin(obj, 4096, true, false); + ret = i915_gem_ggtt_pin(obj, 4096, true, false); if (ret) goto err_unref; - pc->gtt_offset = i915_gem_obj_offset(obj); + pc->gtt_offset = i915_gem_ggtt_offset(obj); pc->cpu_page = kmap(sg_page(obj->pages->sgl)); if (pc->cpu_page == NULL) { ret = -ENOMEM; @@ -1129,7 +1131,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring, intel_ring_advance(ring); } else { struct drm_i915_gem_object *obj = ring->private; - u32 cs_offset = i915_gem_obj_offset(obj); + u32 cs_offset = i915_gem_ggtt_offset(obj); if (len > I830_BATCH_LIMIT) return -ENOSPC; @@ -1197,6 +1199,7 @@ static void cleanup_status_page(struct intel_ring_buffer *ring) static int init_status_page(struct intel_ring_buffer *ring) { struct drm_device *dev = ring->dev; + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; int ret; @@ -1207,14 +1210,15 @@ static int init_status_page(struct intel_ring_buffer *ring) goto err; } - i915_gem_object_set_cache_level(obj, I915_CACHE_LLC); + i915_gem_object_set_cache_level(obj, &dev_priv->gtt.base, + I915_CACHE_LLC); - ret = i915_gem_object_pin(obj, 4096, true, false); + ret = i915_gem_ggtt_pin(obj, 4096, true, false); if (ret != 0) { goto err_unref; } - ring->status_page.gfx_addr = i915_gem_obj_offset(obj); + ring->status_page.gfx_addr = i915_gem_ggtt_offset(obj); ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl)); if (ring->status_page.page_addr == NULL) { ret = -ENOMEM; @@ -1299,7 +1303,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, ring->obj = obj; - ret = i915_gem_object_pin(obj, PAGE_SIZE, true, false); + ret = i915_gem_ggtt_pin(obj, PAGE_SIZE, true, false); if (ret) goto err_unref; @@ -1308,7 +1312,8 @@ static int intel_init_ring_buffer(struct drm_device *dev, goto err_unpin; ring->virtual_start = - ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_offset(obj), + ioremap_wc(dev_priv->gtt.mappable_base + + i915_gem_ggtt_offset(obj), ring->size); if (ring->virtual_start == NULL) { DRM_ERROR("Failed to map ringbuffer.\n"); @@ -1821,7 +1826,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev) return -ENOMEM; } - ret = i915_gem_object_pin(obj, 0, true, false); + ret = i915_gem_ggtt_pin(obj, 0, true, false); if (ret != 0) { drm_gem_object_unreference(&obj->base); DRM_ERROR("Failed to ping batch bo\n"); diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 117a2f8..3555cca 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -133,7 +133,7 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb, I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w); I915_WRITE(SPCNTR(pipe, plane), sprctl); - I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_obj_offset(obj) + + I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_ggtt_offset(obj) + sprsurf_offset); POSTING_READ(SPSURF(pipe, plane)); } @@ -309,7 +309,7 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb, I915_WRITE(SPRSCALE(pipe), sprscale); I915_WRITE(SPRCTL(pipe), sprctl); I915_MODIFY_DISPBASE(SPRSURF(pipe), - i915_gem_obj_offset(obj) + sprsurf_offset); + i915_gem_ggtt_offset(obj) + sprsurf_offset); POSTING_READ(SPRSURF(pipe)); /* potentially re-enable LP watermarks */ @@ -480,7 +480,7 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb, I915_WRITE(DVSSCALE(pipe), dvsscale); I915_WRITE(DVSCNTR(pipe), dvscntr); I915_MODIFY_DISPBASE(DVSSURF(pipe), - i915_gem_obj_offset(obj) + dvssurf_offset); + i915_gem_ggtt_offset(obj) + dvssurf_offset); POSTING_READ(DVSSURF(pipe)); } -- 1.8.3.1