The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
To: tomba@kernel.org, airlied@linux.ie, daniel@ffwll.ch
Cc: dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org,
	linux-omap@vger.kernel.org, merlijn@wizzup.org, tony@atomide.com,
	Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Subject: [PATCH 3/3] drm: omapdrm: Do no allocate non-scanout GEMs through DMM/TILER
Date: Wed, 19 Jan 2022 12:23:11 +0200	[thread overview]
Message-ID: <1642587791-13222-4-git-send-email-ivo.g.dimitrov.75@gmail.com> (raw)
In-Reply-To: <1642587791-13222-1-git-send-email-ivo.g.dimitrov.75@gmail.com>

On devices with DMM, all allocations are done through either DMM or TILER.
DMM/TILER being a limited resource means that such allocations will start
to fail before actual free memory is exhausted. What is even worse is that
with time DMM/TILER space gets fragmented to the point that even if we have
enough free DMM/TILER space and free memory, allocation fails because there
is no big enough free block in DMM/TILER space.

Such failures can be easily observed with OMAP xorg DDX, for example -
starting few GUI applications (so buffers for their windows are allocated)
and then rotating landscape<->portrait while closing and opening new
windows soon results in allocation failures.

Fix that by mapping buffers through DMM/TILER only when really needed,
like, for scanout buffers.

Signed-off-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
---
 drivers/gpu/drm/omapdrm/omap_gem.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 41c1a6d..cf57179 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -821,10 +821,12 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 			if (ret)
 				goto fail;
 
-			if (priv->has_dmm) {
-				ret = omap_gem_pin_tiler(obj);
-				if (ret)
-					goto fail;
+			if (omap_obj->flags & OMAP_BO_SCANOUT) {
+				if (priv->has_dmm) {
+					ret = omap_gem_pin_tiler(obj);
+					if (ret)
+						goto fail;
+				}
 			}
 		} else {
 			refcount_inc(&omap_obj->pin_cnt);
@@ -861,6 +863,8 @@ static void omap_gem_unpin_locked(struct drm_gem_object *obj)
 			kfree(omap_obj->sgt);
 			omap_obj->sgt = NULL;
 		}
+		if (!(omap_obj->flags & OMAP_BO_SCANOUT))
+			return;
 		if (priv->has_dmm) {
 			ret = tiler_unpin(omap_obj->block);
 			if (ret) {
-- 
1.9.1


  parent reply	other threads:[~2022-01-19 10:24 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-19 10:23 [PATCH 0/3] drm: omapdrm: Fix excessive GEM buffers DMM/CMA usage Ivaylo Dimitrov
2022-01-19 10:23 ` [PATCH 1/3] drm: omapdrm: simplify omap_gem_pin Ivaylo Dimitrov
2022-01-19 10:23 ` [PATCH 2/3] drm: omapdrm: Support exporting of non-contiguous GEM BOs Ivaylo Dimitrov
2022-01-19 10:23 ` Ivaylo Dimitrov [this message]
2022-02-17 12:46   ` [PATCH 3/3] drm: omapdrm: Do no allocate non-scanout GEMs through DMM/TILER Tomi Valkeinen
2022-02-17 15:29     ` Ivaylo Dimitrov
2022-08-12  4:35       ` Yongqin Liu
2022-08-13  6:58         ` Ivaylo Dimitrov
2022-08-14 14:27           ` Yongqin Liu
2022-08-15  6:23             ` Ivaylo Dimitrov
2022-08-17  4:52               ` Yongqin Liu
2022-08-18 10:23                 ` Ivaylo Dimitrov
2022-08-29  2:51                   ` Yongqin Liu
2022-08-29 13:24                     ` Ivaylo Dimitrov
2022-08-29 14:36                       ` Andrew Davis
2022-08-30 15:08                         ` Yongqin Liu
2022-08-30 18:08                           ` Ivaylo Dimitrov
2022-08-30 18:23                             ` Tomi Valkeinen
2022-09-02 14:13                               ` Ivaylo Dimitrov
2022-10-30 22:08   ` H. Nikolaus Schaller
2022-10-31  7:05     ` Ivaylo Dimitrov
2022-10-31  7:44       ` H. Nikolaus Schaller
2022-10-31  7:57         ` H. Nikolaus Schaller
2022-10-31  9:58           ` Ivaylo Dimitrov
2022-10-31 10:07             ` H. Nikolaus Schaller
2022-10-31 10:13       ` Tony Lindgren
2022-10-31 10:30         ` Ivaylo Dimitrov
2022-10-31 11:14         ` Ivaylo Dimitrov
2022-02-14  7:08 ` [PATCH 0/3] drm: omapdrm: Fix excessive GEM buffers DMM/CMA usage Ivaylo Dimitrov
2022-02-16  8:10 ` Thomas Zimmermann
2022-02-17 13:03 ` Tomi Valkeinen
2022-02-17 16:21   ` Ivaylo Dimitrov
2022-03-08  8:51     ` Tomi Valkeinen
2022-03-28  9:46 ` Tomi Valkeinen
2022-03-28 15:30   ` Ivaylo Dimitrov

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=1642587791-13222-4-git-send-email-ivo.g.dimitrov.75@gmail.com \
    --to=ivo.g.dimitrov.75@gmail.com \
    --cc=airlied@linux.ie \
    --cc=daniel@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-omap@vger.kernel.org \
    --cc=merlijn@wizzup.org \
    --cc=tomba@kernel.org \
    --cc=tony@atomide.com \
    /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