[Intel-gfx] [PATCH] drm/i915/gem: Prevent NULL pointer dereference on missing ctx->vm

[Colin Ian King]

On 23/01/2020 15:26, Chris Wilson wrote:
> If the ctx->vm is freed before we can acquire a local reference to it,
> we proceed to call i915_vm_put(NULL), which is invalid.
> 
> Reported-by: Colin Ian King <colin.king at canonical.com>
> Fixes: 5dbd2b7be61e ("drm/i915/gem: Convert vm idr to xarray")
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Colin Ian King <colin.king at canonical.com>
> ---
>  drivers/gpu/drm/i915/gem/i915_gem_context.c | 9 +++++----
>  1 file changed, 5 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index 5d4157e1ccf7..8873db5be123 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -1002,13 +1002,14 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
>  	if (!rcu_access_pointer(ctx->vm))
>  		return -ENODEV;
>  
> -	err = -ENODEV;
>  	rcu_read_lock();
>  	vm = context_get_vm_rcu(ctx);
> -	if (vm)
> -		err = xa_alloc(&file_priv->vm_xa, &id, vm,
> -			       xa_limit_32b, GFP_KERNEL);
>  	rcu_read_unlock();
> +	if (!vm)
> +		return -ENODEV;
> +
> +	err = xa_alloc(&file_priv->vm_xa, &id, vm,
> +		       xa_limit_32b, GFP_KERNEL);
>  	if (err)
>  		goto err_put;
>  
> 
Ah, yes, that's definitely an improvement on my fix. Thanks Chris.

Colin