Re: [PATCH 3/5] drm/i915: Add cpu fault handler for mmap_offset

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Quoting Abdiel Janulgue (2019-08-26 13:21:00)
> Fault handler to handle missing pages for shmem-backed objects. Handle also
> logic needed to refault pages depending on fault handler usage.
> 
> Signed-off-by: Abdiel Janulgue <abdiel.janulgue@xxxxxxxxxxxxxxx>
> Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
> Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
> ---
>  drivers/gpu/drm/i915/gem/i915_gem_domain.c |   2 +-
>  drivers/gpu/drm/i915/gem/i915_gem_mman.c   | 189 ++++++++++++++++-----
>  drivers/gpu/drm/i915/gem/i915_gem_object.h |   2 +-
>  drivers/gpu/drm/i915/i915_gem.c            |   2 +-
>  4 files changed, 149 insertions(+), 46 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
> index 9c58e8fac1d9..517e73c3aa31 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
> @@ -254,7 +254,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
>                         }
>  
>                         if (obj->userfault_count)
> -                               __i915_gem_object_release_mmap(obj);
> +                               __i915_gem_object_release_mmap_gtt(obj);
>  
>                         /*
>                          * As we no longer need a fence for GTT access,
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
> index 87690aa64814..d0a653a9a4cc 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
> @@ -5,6 +5,7 @@
>   */
>  
>  #include <linux/mman.h>
> +#include <linux/pfn_t.h>
>  #include <linux/sizes.h>
>  
>  #include "gt/intel_gt.h"
> @@ -199,6 +200,45 @@ compute_partial_view(const struct drm_i915_gem_object *obj,
>         return view;
>  }
>  
> +static vm_fault_t i915_error_to_vmf_fault(int err, struct intel_gt *gt)
> +{
> +       switch (err) {
> +       case -EIO:
> +               /*
> +                * We eat errors when the gpu is terminally wedged to avoid
> +                * userspace unduly crashing (gl has no provisions for mmaps to
> +                * fail). But any other -EIO isn't ours (e.g. swap in failure)
> +                * and so needs to be reported.
> +                */
> +               if (!intel_gt_is_wedged(gt))
> +                       return VM_FAULT_SIGBUS;
> +               /* else, fall through */
> +       case -EAGAIN:
> +               /*
> +                * EAGAIN means the gpu is hung and we'll wait for the error
> +                * handler to reset everything when re-faulting in
> +                * i915_mutex_lock_interruptible.
> +                */

These errors don't exist anymore and should not be cargo-culted onto
paths that could not possibly generate them.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx




[Index of Archives]     [AMD Graphics]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux