dri-devel.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: "Christian König" <ckoenig.leichtzumerken@gmail.com>
To: Lang.Yu@amd.com, thomas_os@shipmail.org
Cc: dri-devel@lists.freedesktop.org
Subject: [PATCH 2/4] drm/amdgpu: user temporary GTT as bounce buffer
Date: Tue,  1 Jun 2021 14:25:26 +0200	[thread overview]
Message-ID: <20210601122528.1643-2-christian.koenig@amd.com> (raw)
In-Reply-To: <20210601122528.1643-1-christian.koenig@amd.com>

From: Lang Yu <Lang.Yu@amd.com>

Currently, we have a limitted GTT memory size and need a bounce buffer
when doing buffer migration between VRAM and SYSTEM domain.

The problem is under GTT memory pressure we can't do buffer migration
between VRAM and SYSTEM domain. But in some cases we really need that.
Eespecially when validating a VRAM backing store BO which resides in
SYSTEM domain.

v2: still account temporary GTT allocations
v3 (chk): revert to the simpler change for now

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 19 +++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c     |  2 +-
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 6a84c9778cc0..5e6b76441449 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -121,14 +121,15 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 	struct amdgpu_gtt_node *node;
 	int r;
 
-	spin_lock(&mgr->lock);
-	if ((&tbo->mem == mem || tbo->mem.mem_type != TTM_PL_TT) &&
-	    atomic64_read(&mgr->available) < mem->num_pages) {
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) {
+		spin_lock(&mgr->lock);
+		if (atomic64_read(&mgr->available) < mem->num_pages) {
+			spin_unlock(&mgr->lock);
+			return -ENOSPC;
+		}
+		atomic64_sub(mem->num_pages, &mgr->available);
 		spin_unlock(&mgr->lock);
-		return -ENOSPC;
 	}
-	atomic64_sub(mem->num_pages, &mgr->available);
-	spin_unlock(&mgr->lock);
 
 	if (!place->lpfn) {
 		mem->mm_node = NULL;
@@ -162,7 +163,8 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 	kfree(node);
 
 err_out:
-	atomic64_add(mem->num_pages, &mgr->available);
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY))
+		atomic64_add(mem->num_pages, &mgr->available);
 
 	return r;
 }
@@ -188,7 +190,8 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 		kfree(node);
 	}
 
-	atomic64_add(mem->num_pages, &mgr->available);
+	if (!(mem->placement & TTM_PL_FLAG_TEMPORARY))
+		atomic64_add(mem->num_pages, &mgr->available);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 80437b6ba5f3..6bdff9005a47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -514,7 +514,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			hop->fpfn = 0;
 			hop->lpfn = 0;
 			hop->mem_type = TTM_PL_TT;
-			hop->flags = 0;
+			hop->flags = TTM_PL_FLAG_TEMPORARY;
 			return -EMULTIHOP;
 		}
 
-- 
2.25.1


  reply	other threads:[~2021-06-01 12:25 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-01 12:25 [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3 Christian König
2021-06-01 12:25 ` Christian König [this message]
2021-06-01 12:25 ` [PATCH 3/4] drm/amdgpu: always allow evicting to SYSTEM domain Christian König
2021-06-02  1:30   ` Yu, Lang
2021-06-01 12:25 ` [PATCH 4/4] drm/amdgpu: switch gtt_mgr to counting used pages Christian König
2021-06-07 12:36 ` [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3 Christian König
2021-06-07 12:38   ` Thomas Hellström (Intel)
2021-06-07 12:41     ` Christian König
2021-06-07 12:58       ` Yu, Lang
2021-06-07 13:01         ` Christian König
2021-06-07 14:42           ` Das, Nirmoy
2021-06-07 15:27             ` Das, Nirmoy

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=20210601122528.1643-2-christian.koenig@amd.com \
    --to=ckoenig.leichtzumerken@gmail.com \
    --cc=Lang.Yu@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=thomas_os@shipmail.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).