From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, dri-devel@lists.freedesktop.org
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 30/34] drm: Optimise power-of-two alignments in drm_mm_scan_add_block()
Date: Tue, 13 Dec 2016 17:55:37 +0200 [thread overview]
Message-ID: <1481644537.3639.43.camel@linux.intel.com> (raw)
In-Reply-To: <20161212115350.780-31-chris@chris-wilson.co.uk>
On ma, 2016-12-12 at 11:53 +0000, Chris Wilson wrote:
> For power-of-two alignments, we can avoid the 64bit divide and do a
> simple bitwise add instead.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
> drivers/gpu/drm/drm_mm.c | 9 ++++++++-
> include/drm/drm_mm.h | 1 +
> 2 files changed, 9 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
> index eec0a46f5b38..7245483f1111 100644
> --- a/drivers/gpu/drm/drm_mm.c
> +++ b/drivers/gpu/drm/drm_mm.c
> @@ -741,8 +741,12 @@ void drm_mm_scan_init_with_range(struct drm_mm_scan *scan,
>
> scan->mm = mm;
>
> + if (alignment <= 1)
> + alignment = 0;
> +
> scan->color = color;
> scan->alignment = alignment;
> + scan->alignment_mask = is_power_of_2(alignment) ? alignment - 1 : 0;
One would assume alignment_mask to be the bit-opposite, really.
reminder_mask should describe it better.
And sprinkle a likely() for the POT case, because I think that's
something to expect.
With above comments;
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Regards, Joonas
--
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2016-12-13 15:55 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-12 11:53 struct drm_mm fixes Chris Wilson
2016-12-12 11:53 ` [PATCH 01/34] drm/i915: Use the MRU stack search after evicting Chris Wilson
2016-12-13 9:29 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 02/34] drm/i915: Simplify i915_gtt_color_adjust() Chris Wilson
2016-12-13 9:32 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 03/34] drm: Add drm_mm_for_each_node_safe() Chris Wilson
2016-12-13 9:35 ` Joonas Lahtinen
2016-12-14 11:39 ` Chris Wilson
2016-12-14 12:03 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 04/34] drm: Add some kselftests for the DRM range manager (struct drm_mm) Chris Wilson
2016-12-13 9:58 ` Joonas Lahtinen
2016-12-13 10:21 ` Chris Wilson
2016-12-13 15:03 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 05/34] drm: kselftest for drm_mm_init() Chris Wilson
2016-12-13 10:16 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 06/34] drm: Add a simple linear congruent generator PRNG Chris Wilson
2016-12-13 10:44 ` Joonas Lahtinen
2016-12-13 15:16 ` David Herrmann
2016-12-13 15:18 ` David Herrmann
2016-12-13 15:40 ` Chris Wilson
2016-12-13 16:21 ` David Herrmann
2016-12-13 15:26 ` Chris Wilson
2016-12-13 19:39 ` Laurent Pinchart
2016-12-13 20:50 ` Chris Wilson
2016-12-12 11:53 ` [PATCH 07/34] drm: Add a simple prime number generator Chris Wilson
2016-12-12 11:53 ` [PATCH 08/34] drm: kselftest for drm_mm_reserve_node() Chris Wilson
2016-12-14 9:55 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 09/34] drm: kselftest for drm_mm_insert_node() Chris Wilson
2016-12-14 12:26 ` Joonas Lahtinen
2016-12-14 12:51 ` Chris Wilson
2016-12-12 11:53 ` [PATCH 10/34] drm: kselftest for drm_mm_replace_node() Chris Wilson
2016-12-14 12:01 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 11/34] drm: kselftest for drm_mm_insert_node_in_range() Chris Wilson
2016-12-15 8:43 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 12/34] drm: kselftest for drm_mm and alignment Chris Wilson
2016-12-15 8:59 ` Joonas Lahtinen
2016-12-15 9:21 ` Chris Wilson
2016-12-12 11:53 ` [PATCH 13/34] drm: kselftest for drm_mm and eviction Chris Wilson
2016-12-15 9:29 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 14/34] drm: kselftest for drm_mm and range restricted eviction Chris Wilson
2016-12-15 9:50 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 15/34] drm: kselftest for drm_mm and top-down allocation Chris Wilson
2016-12-14 11:33 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 16/34] drm: kselftest for drm_mm and top-down alignment Chris Wilson
2016-12-14 11:51 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 17/34] drm: kselftest for drm_mm and color adjustment Chris Wilson
2016-12-15 11:04 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 18/34] drm: kselftest for drm_mm and color eviction Chris Wilson
2016-12-12 11:53 ` [PATCH 19/34] drm: kselftest for drm_mm and restricted " Chris Wilson
2016-12-12 11:53 ` [PATCH 20/34] drm/i915: Build DRM range manager selftests for CI Chris Wilson
2016-12-15 12:31 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 21/34] drm: Promote drm_mm alignment to u64 Chris Wilson
2016-12-12 12:39 ` Christian König
2016-12-12 11:53 ` [PATCH 22/34] drm: Constify the drm_mm API Chris Wilson
2016-12-12 11:53 ` [PATCH 23/34] drm: Simplify drm_mm_clean() Chris Wilson
2016-12-13 12:30 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 24/34] drm: Compile time enabling for asserts in drm_mm Chris Wilson
2016-12-13 15:04 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 25/34] drm: Extract struct drm_mm_scan from struct drm_mm Chris Wilson
2016-12-13 15:17 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 26/34] drm: Rename prev_node to hole in drm_mm_scan_add_block() Chris Wilson
2016-12-13 15:23 ` Joonas Lahtinen
2016-12-13 22:28 ` Chris Wilson
2016-12-12 11:53 ` [PATCH 27/34] drm: Unconditionally do the range check " Chris Wilson
2016-12-13 15:28 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 28/34] drm: Fix application of color vs range restriction when scanning drm_mm Chris Wilson
2016-12-12 14:57 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 29/34] drm: Compute tight evictions for drm_mm_scan Chris Wilson
2016-12-13 15:48 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 30/34] drm: Optimise power-of-two alignments in drm_mm_scan_add_block() Chris Wilson
2016-12-13 15:55 ` Joonas Lahtinen [this message]
2016-12-12 11:53 ` [PATCH 31/34] drm: Simplify drm_mm scan-list manipulation Chris Wilson
2016-12-14 8:27 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 32/34] drm: Apply tight eviction scanning to color_adjust Chris Wilson
2016-12-13 16:03 ` Joonas Lahtinen
2016-12-12 11:53 ` [PATCH 33/34] drm: Fix drm_mm search and insertion Chris Wilson
2016-12-15 12:28 ` Joonas Lahtinen
2016-12-15 12:57 ` Chris Wilson
2016-12-12 11:53 ` [PATCH 34/34] drm: kselftest for drm_mm and bottom-up allocation Chris Wilson
2016-12-14 9:10 ` Joonas Lahtinen
2016-12-12 12:15 ` ✓ Fi.CI.BAT: success for series starting with [01/34] drm/i915: Use the MRU stack search after evicting Patchwork
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=1481644537.3639.43.camel@linux.intel.com \
--to=joonas.lahtinen@linux.intel.com \
--cc=chris@chris-wilson.co.uk \
--cc=dri-devel@lists.freedesktop.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).