Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   xinhui pan <xinhui.pan@amd.com>
To:     <amd-gfx@lists.freedesktop.org>
CC:     <daniel@ffwll.ch>, <matthew.auld@intel.com>,
        <christian.koenig@amd.com>, <dri-devel@lists.freedesktop.org>,
        <linux-kernel@vger.kernel.org>, xinhui pan <xinhui.pan@amd.com>
Subject: [PATCH v3] drm: Optimise for continuous memory allocation
Date:   Mon, 28 Nov 2022 14:34:19 +0800
Message-ID: <20221128063419.101586-1-xinhui.pan@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 28 Nov 2022 06:35:29.0626
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: b0abce57-5989-49a9-a663-08dad10abdd7
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: DM6NAM11FT085.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: CY5PR12MB6599
X-Spam-Status: No, score=-2.1 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE,
        RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_PASS autolearn=ham
        autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Currently drm-buddy does not have full knowledge of continuous memory.

Lets consider scenario below.
order 1:    L		    R
order 0: LL	LR	RL	RR
for order 1 allocation, it can offer L or R or LR+RL.

For now, we only implement L or R case for continuous memory allocation.
So this patch aims to implement the LR+RL case.

Signed-off-by: xinhui pan <xinhui.pan@amd.com>
---
change from v2:
search continuous block in nearby root if needed

change from v1:
implement top-down continuous allocation
---
 drivers/gpu/drm/drm_buddy.c | 78 +++++++++++++++++++++++++++++++++----
 1 file changed, 71 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 11bb59399471..ff58eb3136d2 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -386,6 +386,58 @@ alloc_range_bias(struct drm_buddy *mm,
 	return ERR_PTR(err);
 }
 
+static struct drm_buddy_block *
+find_continuous_blocks(struct drm_buddy *mm,
+		       int order,
+		       unsigned long flags,
+		       struct drm_buddy_block **rn)
+{
+	struct list_head *head = &mm->free_list[order];
+	struct drm_buddy_block *node, *parent, *free_node, *max_node = NULL;
+	int i;
+
+	list_for_each_entry(free_node, head, link) {
+		if (max_node) {
+			if (!(flags & DRM_BUDDY_TOPDOWN_ALLOCATION))
+				break;
+
+			if (drm_buddy_block_offset(free_node) <
+			    drm_buddy_block_offset(max_node))
+				continue;
+		}
+
+		parent = free_node;
+		do {
+			node = parent;
+			parent = parent->parent;
+		} while (parent && parent->right == node);
+
+		if (!parent) {
+			for (i = 0; i < mm->n_roots - 1; i++)
+				if (mm->roots[i] == node)
+					break;
+			if (i == mm->n_roots - 1)
+				continue;
+			node = mm->roots[i + 1];
+		} else {
+			node = parent->right;
+		}
+
+		while (drm_buddy_block_is_split(node))
+			node = node->left;
+
+		if (drm_buddy_block_is_free(node) &&
+		    drm_buddy_block_order(node) == order) {
+			*rn = node;
+			max_node = free_node;
+			BUG_ON(drm_buddy_block_offset(node) !=
+				drm_buddy_block_offset(max_node) +
+				drm_buddy_block_size(mm, max_node));
+		}
+	}
+	return max_node;
+}
+
 static struct drm_buddy_block *
 get_maxblock(struct list_head *head)
 {
@@ -637,7 +689,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
 			   struct list_head *blocks,
 			   unsigned long flags)
 {
-	struct drm_buddy_block *block = NULL;
+	struct drm_buddy_block *block = NULL, *rblock = NULL;
 	unsigned int min_order, order;
 	unsigned long pages;
 	LIST_HEAD(allocated);
@@ -689,17 +741,29 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
 				break;
 
 			if (order-- == min_order) {
+				if (!(flags & DRM_BUDDY_RANGE_ALLOCATION) &&
+				    min_order != 0 && pages == BIT(order + 1)) {
+					block = find_continuous_blocks(mm,
+								       order,
+								       flags,
+								       &rblock);
+					if (block)
+						break;
+				}
 				err = -ENOSPC;
 				goto err_free;
 			}
 		} while (1);
 
-		mark_allocated(block);
-		mm->avail -= drm_buddy_block_size(mm, block);
-		kmemleak_update_trace(block);
-		list_add_tail(&block->link, &allocated);
-
-		pages -= BIT(order);
+		do {
+			mark_allocated(block);
+			mm->avail -= drm_buddy_block_size(mm, block);
+			kmemleak_update_trace(block);
+			list_add_tail(&block->link, &allocated);
+			pages -= BIT(order);
+			block = rblock;
+			rblock = NULL;
+		} while (block);
 
 		if (!pages)
 			break;
-- 
2.34.1