Re: [PATCH] drm: Take mmap_sem up front to avoid lock order violations.

[Peter Zijlstra <peterz@infradead.org>]

On Wed, 2009-02-18 at 11:38 -0500, krh@bitplanet.net wrote:
> From: Kristian Høgsberg <krh@redhat.com>
> 
> A number of GEM operations (and legacy drm ones) want to copy data to
> or from userspace while holding the struct_mutex lock.  However, the
> fault handler calls us with the mmap_sem held and thus enforces the
> opposite locking order.  This patch downs the mmap_sem up front for
> those operations that access userspace data under the struct_mutex
> lock to ensure the locking order is consistent.
> 
> Signed-off-by: Kristian Høgsberg <krh@redhat.com>
> ---
> 
> Here's a different and simpler attempt to fix the locking order
> problem.  We can just down_read() the mmap_sem pre-emptively up-front,
> and the locking order is respected.  It's simpler than the
> mutex_trylock() game, avoids introducing a new mutex.
> 

Hell no!

for one, mmap_sem is not a recursive lock, so a pagefault will utterly
fail with this in place.

Secondly, holding mmap_sem for no good reason just sucks.

>  drivers/gpu/drm/i915/i915_dma.c |    6 +++++-
>  drivers/gpu/drm/i915/i915_gem.c |   20 +++++++++++++-------
>  2 files changed, 18 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
> index 81f1cff..d8b58d9 100644
> --- a/drivers/gpu/drm/i915/i915_dma.c
> +++ b/drivers/gpu/drm/i915/i915_dma.c
> @@ -642,9 +642,11 @@ static int i915_batchbuffer(struct drm_device *dev, void *data,
>  						       sizeof(struct drm_clip_rect)))
>  		return -EFAULT;
>  
> +	down_read(&current->mm->mmap_sem);
>  	mutex_lock(&dev->struct_mutex);
>  	ret = i915_dispatch_batchbuffer(dev, batch);
>  	mutex_unlock(&dev->struct_mutex);
> +	up_read(&current->mm->mmap_sem);
>  
>  	if (sarea_priv)
>  		sarea_priv->last_dispatch = READ_BREADCRUMB(dev_priv);
> @@ -674,14 +676,16 @@ static int i915_cmdbuffer(struct drm_device *dev, void *data,
>  		return -EFAULT;
>  	}
>  
> +	down_read(&current->mm->mmap_sem);
>  	mutex_lock(&dev->struct_mutex);
>  	ret = i915_dispatch_cmdbuffer(dev, cmdbuf);
>  	mutex_unlock(&dev->struct_mutex);
> +	up_read(&current->mm->mmap_sem);
> +
>  	if (ret) {
>  		DRM_ERROR("i915_dispatch_cmdbuffer failed\n");
>  		return ret;
>  	}
> -
>  	if (sarea_priv)
>  		sarea_priv->last_dispatch = READ_BREADCRUMB(dev_priv);
>  	return 0;
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index d9cd42f..3dd8b6e 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -171,6 +171,7 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
>  		return -EINVAL;
>  	}
>  
> +	down_read(&current->mm->mmap_sem);
>  	mutex_lock(&dev->struct_mutex);
>  
>  	ret = i915_gem_object_set_cpu_read_domain_range(obj, args->offset,
> @@ -196,6 +197,7 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
>  
>  	drm_gem_object_unreference(obj);
>  	mutex_unlock(&dev->struct_mutex);
> +	up_read(&current->mm->mmap_sem);
>  
>  	return 0;
>  }
> @@ -264,7 +266,7 @@ i915_gem_gtt_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
>  	if (!access_ok(VERIFY_READ, user_data, remain))
>  		return -EFAULT;
>  
> -
> +	down_read(&current->mm->mmap_sem);
>  	mutex_lock(&dev->struct_mutex);
>  	ret = i915_gem_object_pin(obj, 0);
>  	if (ret) {
> @@ -315,6 +317,7 @@ i915_gem_gtt_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
>  fail:
>  	i915_gem_object_unpin(obj);
>  	mutex_unlock(&dev->struct_mutex);
> +	up_read(&current->mm->mmap_sem);
>  
>  	return ret;
>  }
> @@ -328,6 +331,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
>  	loff_t offset;
>  	ssize_t written;
>  
> +	down_read(&current->mm->mmap_sem);
>  	mutex_lock(&dev->struct_mutex);
>  
>  	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
> @@ -350,6 +354,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
>  	}
>  
>  	mutex_unlock(&dev->struct_mutex);
> +	up_read(&current->mm->mmap_sem);
>  
>  	return 0;
>  }
> @@ -2473,22 +2478,21 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
>  		goto pre_mutex_err;
>  	}
>  
> +	down_read(&current->mm->mmap_sem);
>  	mutex_lock(&dev->struct_mutex);
>  
>  	i915_verify_inactive(dev, __FILE__, __LINE__);
>  
>  	if (dev_priv->mm.wedged) {
>  		DRM_ERROR("Execbuf while wedged\n");
> -		mutex_unlock(&dev->struct_mutex);
>  		ret = -EIO;
> -		goto pre_mutex_err;
> +		goto mutex_err;
>  	}
>  
>  	if (dev_priv->mm.suspended) {
>  		DRM_ERROR("Execbuf while VT-switched.\n");
> -		mutex_unlock(&dev->struct_mutex);
>  		ret = -EBUSY;
> -		goto pre_mutex_err;
> +		goto mutex_err;
>  	}
>  
>  	/* Look up object handles */
> @@ -2641,8 +2645,6 @@ err:
>  	for (i = 0; i < args->buffer_count; i++)
>  		drm_gem_object_unreference(object_list[i]);
>  
> -	mutex_unlock(&dev->struct_mutex);
> -
>  	if (!ret) {
>  		/* Copy the new buffer offsets back to the user's exec list. */
>  		ret = copy_to_user((struct drm_i915_relocation_entry __user *)
> @@ -2655,6 +2657,10 @@ err:
>  				  args->buffer_count, ret);
>  	}
>  
> +mutex_err:
> +	mutex_unlock(&dev->struct_mutex);
> +	up_read(&current->mm->mmap_sem);
> +
>  pre_mutex_err:
>  	drm_free(object_list, sizeof(*object_list) * args->buffer_count,
>  		 DRM_MEM_DRIVER);