All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx <intel-gfx@lists.freedesktop.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Subject: Re: [PATCH 3/5] drm/i915: fall through pwrite_gtt_slow to the shmem slow path
Date: Sat, 17 Sep 2011 21:57:05 +0100	[thread overview]
Message-ID: <d08817$1fjvni@azsmga001.ch.intel.com> (raw)
In-Reply-To: <1316285749-30130-4-git-send-email-daniel.vetter@ffwll.ch>

On Sat, 17 Sep 2011 20:55:47 +0200, Daniel Vetter <daniel.vetter@ffwll.ch> wrote:
> The gtt_pwrite slowpath grabs the userspace memory with
> get_user_pages. This will not work for non-page backed memory, like a
> gtt mmapped gem object. Hence fall throuh to the shmem paths if we hit
> -EFAULT in the gtt paths.
> 
> Now the shmem paths have exactly the same problem, but this way we
> only need to rearrange the code in one write path.
> 
> Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
> ---
>  drivers/gpu/drm/i915/i915_gem.c |   24 +++++++++++++++---------
>  1 files changed, 15 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index e0475ca..9c28d48 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -1018,18 +1018,24 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
>  
>  out_unpin:
>  		i915_gem_object_unpin(obj);
> -	} else {
> -		ret = i915_gem_object_set_to_cpu_domain(obj, 1);
> -		if (ret)
> -			goto out;
>  
> -		ret = -EFAULT;
> -		if (!i915_gem_object_needs_bit17_swizzle(obj))
> -			ret = i915_gem_shmem_pwrite_fast(dev, obj, args, file);
> -		if (ret == -EFAULT)
> -			ret = i915_gem_shmem_pwrite_slow(dev, obj, args, file);
> +		if (ret != -EFAULT)
> +			goto out;
> +		/* Fall through to the shmfs paths because the gtt paths might
> +		 * fail with non-page-backed user pointers (e.g. gtt mappings
> +		 * when moving data between textures). */
>  	}

I'd actually prefer to have an
  if (ret == -EFAULT) {
and comments here in order to mark the shmem paths as a logical unit to the
reader. Better yet would be to move the two paths (GTT/CPU) into their own
routines:

  ret = -EFAULT;
  if (can_gtt)
    ret = i915_gem_gtt_pwrite();
  /* Fallback to the slow shmem paths if we need to handle
   * GTT mapped user pointers, or otherwise can not do the upload in
   * place.
   */
  if (ret == -EFAULT)
    ret = i915_gem_cpu_pwrite();

And whilst you are here, can you incorporate this patch?
        else if (obj->gtt_space &&
+                obj->map_and_fenceable &&
                 obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
                ret = i915_gem_object_pin(obj, 0, true);
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre

  reply	other threads:[~2011-09-17 20:57 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-09-17 18:55 [PATCH 0/5] Fixup pwrite/pread with gtt mmapped user addresses Daniel Vetter
2011-09-17 18:55 ` [PATCH 1/5] io-mapping: ensure io_mapping_map_atomic _is_ atomic Daniel Vetter
2011-09-17 20:43   ` Chris Wilson
2011-09-17 18:55 ` [PATCH 2/5] drm/i915: drop KM_USER0 argument to k(un)map_atomic Daniel Vetter
2011-09-17 20:44   ` Chris Wilson
2011-09-23 16:25   ` Daniel Vetter
2011-09-17 18:55 ` [PATCH 3/5] drm/i915: fall through pwrite_gtt_slow to the shmem slow path Daniel Vetter
2011-09-17 20:57   ` Chris Wilson [this message]
2011-09-20 11:35     ` Daniel Vetter
2011-10-30  8:35       ` Chris Wilson
2011-09-17 18:55 ` [PATCH 4/5] drm/i915: rewrite shmem_pwrite_slow to use copy_from_user Daniel Vetter
2011-09-17 20:52   ` Daniel Vetter
2011-09-17 21:00   ` Chris Wilson
2011-09-18  8:44     ` Daniel Vetter
2011-09-17 18:55 ` [PATCH 5/5] drm/i915: rewrite shmem_pread_slow to use copy_to_user Daniel Vetter
2011-09-17 21:04   ` Chris Wilson
2011-09-17 23:07 ` [PATCH 0/5] Fixup pwrite/pread with gtt mmapped user addresses Ben Widawsky
2011-10-20 21:14 ` Keith Packard

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='d08817$1fjvni@azsmga001.ch.intel.com' \
    --to=chris@chris-wilson.co.uk \
    --cc=daniel.vetter@ffwll.ch \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.