Merge remote-tracking branch 'airlied/drm-next' into drm-intel-next-queued

[karo-tx-linux.git] / drivers / gpu / drm / i915 / i915_gem.c

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f7e85fb1464f44613b1050e559a5e81d898b69fb..e29f9400c9d11d4b3fc4988ac3979935724b1b61 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1452,6 +1452,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 
        trace_i915_gem_object_pwrite(obj, args->offset, args->size);
 
+       ret = -ENODEV;
+       if (obj->ops->pwrite)
+               ret = obj->ops->pwrite(obj, args);
+       if (ret != -ENODEV)
+               goto err;
+
        ret = i915_gem_object_wait(obj,
                                   I915_WAIT_INTERRUPTIBLE |
                                   I915_WAIT_ALL,
@@ -1783,7 +1789,6 @@ compute_partial_view(struct drm_i915_gem_object *obj,
 
 /**
  * i915_gem_fault - fault a page into the GTT
- * @area: CPU VMA in question
  * @vmf: fault info
  *
  * The fault handler is set up by drm_gem_mmap() when a object is GTT mapped
@@ -1800,9 +1805,10 @@ compute_partial_view(struct drm_i915_gem_object *obj,
  * The current feature set supported by i915_gem_fault() and thus GTT mmaps
  * is exposed via I915_PARAM_MMAP_GTT_VERSION (see i915_gem_mmap_gtt_version).
  */
-int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf)
+int i915_gem_fault(struct vm_fault *vmf)
 {
 #define MIN_CHUNK_PAGES ((1 << 20) >> PAGE_SHIFT) /* 1 MiB */
+       struct vm_area_struct *area = vmf->vma;
        struct drm_i915_gem_object *obj = to_intel_bo(area->vm_private_data);
        struct drm_device *dev = obj->base.dev;
        struct drm_i915_private *dev_priv = to_i915(dev);
@@ -2130,6 +2136,7 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj)
         */
        shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1);
        obj->mm.madv = __I915_MADV_PURGED;
+       obj->mm.pages = ERR_PTR(-EFAULT);
 }
 
 /* Try to discard unwanted pages */
@@ -2229,7 +2236,9 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 
        __i915_gem_object_reset_page_iter(obj);
 
-       obj->ops->put_pages(obj, pages);
+       if (!IS_ERR(pages))
+               obj->ops->put_pages(obj, pages);
+
 unlock:
        mutex_unlock(&obj->mm.lock);
 }
@@ -2449,7 +2458,7 @@ int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
        if (err)
                return err;
 
-       if (unlikely(!obj->mm.pages)) {
+       if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
                err = ____i915_gem_object_get_pages(obj);
                if (err)
                        goto unlock;
@@ -2527,7 +2536,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 
        pinned = true;
        if (!atomic_inc_not_zero(&obj->mm.pages_pin_count)) {
-               if (unlikely(!obj->mm.pages)) {
+               if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
                        ret = ____i915_gem_object_get_pages(obj);
                        if (ret)
                                goto err_unlock;
@@ -2575,6 +2584,75 @@ err_unlock:
        goto out_unlock;
 }
 
+static int
+i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
+                          const struct drm_i915_gem_pwrite *arg)
+{
+       struct address_space *mapping = obj->base.filp->f_mapping;
+       char __user *user_data = u64_to_user_ptr(arg->data_ptr);
+       u64 remain, offset;
+       unsigned int pg;
+
+       /* Before we instantiate/pin the backing store for our use, we
+        * can prepopulate the shmemfs filp efficiently using a write into
+        * the pagecache. We avoid the penalty of instantiating all the
+        * pages, important if the user is just writing to a few and never
+        * uses the object on the GPU, and using a direct write into shmemfs
+        * allows it to avoid the cost of retrieving a page (either swapin
+        * or clearing-before-use) before it is overwritten.
+        */
+       if (READ_ONCE(obj->mm.pages))
+               return -ENODEV;
+
+       /* Before the pages are instantiated the object is treated as being
+        * in the CPU domain. The pages will be clflushed as required before
+        * use, and we can freely write into the pages directly. If userspace
+        * races pwrite with any other operation; corruption will ensue -
+        * that is userspace's prerogative!
+        */
+
+       remain = arg->size;
+       offset = arg->offset;
+       pg = offset_in_page(offset);
+
+       do {
+               unsigned int len, unwritten;
+               struct page *page;
+               void *data, *vaddr;
+               int err;
+
+               len = PAGE_SIZE - pg;
+               if (len > remain)
+                       len = remain;
+
+               err = pagecache_write_begin(obj->base.filp, mapping,
+                                           offset, len, 0,
+                                           &page, &data);
+               if (err < 0)
+                       return err;
+
+               vaddr = kmap(page);
+               unwritten = copy_from_user(vaddr + pg, user_data, len);
+               kunmap(page);
+
+               err = pagecache_write_end(obj->base.filp, mapping,
+                                         offset, len, len - unwritten,
+                                         page, data);
+               if (err < 0)
+                       return err;
+
+               if (unwritten)
+                       return -EFAULT;
+
+               remain -= len;
+               user_data += len;
+               offset += len;
+               pg = 0;
+       } while (remain);
+
+       return 0;
+}
+
 static bool ban_context(const struct i915_gem_context *ctx)
 {
        return (i915_gem_context_is_bannable(ctx) &&
@@ -3991,8 +4069,11 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
        .flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
                 I915_GEM_OBJECT_IS_SHRINKABLE,
+
        .get_pages = i915_gem_object_get_pages_gtt,
        .put_pages = i915_gem_object_put_pages_gtt,
+
+       .pwrite = i915_gem_object_pwrite_gtt,
 };
 
 struct drm_i915_gem_object *