[PATCH] drm: stop vmgfx driver explosion

[PATCH] drm: stop vmgfx driver explosion

[Alan Cox]

From: Alan Cox <alan@linux.intel.com>

If you do a page flip with no flags set then event is NULL. If event is
NULL then the vmw_gfx driver likes to go digging into NULL and extracts
NULL->base.file_priv.

On a modern kernel with NULL mapping protection it's just another oops,
without it there are some "intriguing" possibilities.

What it should do is an open question but that for the driver owners to
sort out.

Signed-off-by: Alan Cox <alan@linux.intel.com>
---

 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 6b0078f..c50724b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1688,15 +1688,19 @@ int vmw_du_page_flip(struct drm_crtc *crtc,
 	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
 	struct drm_framebuffer *old_fb = crtc->fb;
 	struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(fb);
-	struct drm_file *file_priv = event->base.file_priv;
+	struct drm_file *file_priv ;
 	struct vmw_fence_obj *fence = NULL;
 	struct drm_clip_rect clips;
 	int ret;
 
+	if (event == NULL)
+		return -EINVAL;
+
 	/* require ScreenObject support for page flipping */
 	if (!dev_priv->sou_priv)
 		return -ENOSYS;
 
+	file_priv = event->base.file_priv;
 	if (!vmw_kms_screen_object_flippable(dev_priv, crtc))
 		return -EINVAL;
 

Re: [PATCH] drm: stop vmgfx driver explosion

[Jakob Bornecrantz]

----- Original Message -----
> From: Alan Cox <alan@linux.intel.com>
> 
> If you do a page flip with no flags set then event is NULL. If event
> is NULL then the vmw_gfx driver likes to go digging into NULL and
> extracts NULL->base.file_priv.
> 
> On a modern kernel with NULL mapping protection it's just another
> oops, without it there are some "intriguing" possibilities.
> 
> What it should do is an open question but that for the driver owners
> to sort out.
> 
> Signed-off-by: Alan Cox <alan@linux.intel.com>

Thanks Alan!

Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>

I think CC stable is in order.

Cheers, Jakob.