All of lore.kernel.org
 help / color / mirror / Atom feed
From: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
To: <dri-devel@lists.freedesktop.org>,
	<intel-gfx@lists.freedesktop.org>,
	<amd-gfx@lists.freedesktop.org>
Cc: Arunpravin <Arunpravin.PaneerSelvam@amd.com>,
	matthew.auld@intel.com, tzimmermann@suse.de,
	alexander.deucher@amd.com, christian.koenig@amd.com
Subject: [PATCH v7 3/6] drm: implement top-down allocation method
Date: Sun, 9 Jan 2022 19:49:48 +0530	[thread overview]
Message-ID: <20220109141951.134432-3-Arunpravin.PaneerSelvam@amd.com> (raw)
In-Reply-To: <20220109141951.134432-1-Arunpravin.PaneerSelvam@amd.com>

Implemented a function which walk through the order list,
compares the offset and returns the maximum offset block,
this method is unpredictable in obtaining the high range
address blocks which depends on allocation and deallocation.
for instance, if driver requests address at a low specific
range, allocator traverses from the root block and splits
the larger blocks until it reaches the specific block and
in the process of splitting, lower orders in the freelist
are occupied with low range address blocks and for the
subsequent TOPDOWN memory request we may return the low
range blocks.To overcome this issue, we may go with the
below approach.

The other approach, sorting each order list entries in
ascending order and compares the last entry of each
order list in the freelist and return the max block.
This creates sorting overhead on every drm_buddy_free()
request and split up of larger blocks for a single page
request.

v2:
  - Fix alignment issues(Matthew Auld)
  - Remove unnecessary list_empty check(Matthew Auld)
  - merged the below patch to see the feature in action
     - add top-down alloc support to i915 driver

Signed-off-by: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
---
 drivers/gpu/drm/drm_buddy.c                   | 36 ++++++++++++++++---
 drivers/gpu/drm/i915/i915_ttm_buddy_manager.c |  3 ++
 include/drm/drm_buddy.h                       |  1 +
 3 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index cd914d104b1a..11356c2bb7aa 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -369,6 +369,26 @@ alloc_range_bias(struct drm_buddy *mm,
 	return ERR_PTR(err);
 }
 
+static struct drm_buddy_block *
+get_maxblock(struct list_head *head)
+{
+	struct drm_buddy_block *max_block = NULL, *node;
+
+	max_block = list_first_entry_or_null(head,
+					     struct drm_buddy_block,
+					     link);
+	if (!max_block)
+		return NULL;
+
+	list_for_each_entry(node, head, link) {
+		if (drm_buddy_block_offset(node) >
+		    drm_buddy_block_offset(max_block))
+			max_block = node;
+	}
+
+	return max_block;
+}
+
 static struct drm_buddy_block *
 alloc_from_freelist(struct drm_buddy *mm,
 		    unsigned int order,
@@ -379,11 +399,17 @@ alloc_from_freelist(struct drm_buddy *mm,
 	int err;
 
 	for (i = order; i <= mm->max_order; ++i) {
-		block = list_first_entry_or_null(&mm->free_list[i],
-						 struct drm_buddy_block,
-						 link);
-		if (block)
-			break;
+		if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
+			block = get_maxblock(&mm->free_list[i]);
+			if (block)
+				break;
+		} else {
+			block = list_first_entry_or_null(&mm->free_list[i],
+							 struct drm_buddy_block,
+							 link);
+			if (block)
+				break;
+		}
 	}
 
 	if (!block)
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
index 143657a706ae..ae9201246bb5 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -53,6 +53,9 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
 	INIT_LIST_HEAD(&bman_res->blocks);
 	bman_res->mm = mm;
 
+	if (place->flags & TTM_PL_FLAG_TOPDOWN)
+		bman_res->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+
 	if (place->fpfn || lpfn != man->size)
 		bman_res->flags |= DRM_BUDDY_RANGE_ALLOCATION;
 
diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h
index 865664b90a8a..424fc443115e 100644
--- a/include/drm/drm_buddy.h
+++ b/include/drm/drm_buddy.h
@@ -28,6 +28,7 @@
 })
 
 #define DRM_BUDDY_RANGE_ALLOCATION (1 << 0)
+#define DRM_BUDDY_TOPDOWN_ALLOCATION (1 << 1)
 
 struct drm_buddy_block {
 #define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
-- 
2.25.1


WARNING: multiple messages have this Message-ID (diff)
From: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
To: <dri-devel@lists.freedesktop.org>,
	<intel-gfx@lists.freedesktop.org>,
	<amd-gfx@lists.freedesktop.org>
Cc: Arunpravin <Arunpravin.PaneerSelvam@amd.com>,
	matthew.auld@intel.com, tzimmermann@suse.de,
	alexander.deucher@amd.com, christian.koenig@amd.com
Subject: [Intel-gfx] [PATCH v7 3/6] drm: implement top-down allocation method
Date: Sun, 9 Jan 2022 19:49:48 +0530	[thread overview]
Message-ID: <20220109141951.134432-3-Arunpravin.PaneerSelvam@amd.com> (raw)
In-Reply-To: <20220109141951.134432-1-Arunpravin.PaneerSelvam@amd.com>

Implemented a function which walk through the order list,
compares the offset and returns the maximum offset block,
this method is unpredictable in obtaining the high range
address blocks which depends on allocation and deallocation.
for instance, if driver requests address at a low specific
range, allocator traverses from the root block and splits
the larger blocks until it reaches the specific block and
in the process of splitting, lower orders in the freelist
are occupied with low range address blocks and for the
subsequent TOPDOWN memory request we may return the low
range blocks.To overcome this issue, we may go with the
below approach.

The other approach, sorting each order list entries in
ascending order and compares the last entry of each
order list in the freelist and return the max block.
This creates sorting overhead on every drm_buddy_free()
request and split up of larger blocks for a single page
request.

v2:
  - Fix alignment issues(Matthew Auld)
  - Remove unnecessary list_empty check(Matthew Auld)
  - merged the below patch to see the feature in action
     - add top-down alloc support to i915 driver

Signed-off-by: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
---
 drivers/gpu/drm/drm_buddy.c                   | 36 ++++++++++++++++---
 drivers/gpu/drm/i915/i915_ttm_buddy_manager.c |  3 ++
 include/drm/drm_buddy.h                       |  1 +
 3 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index cd914d104b1a..11356c2bb7aa 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -369,6 +369,26 @@ alloc_range_bias(struct drm_buddy *mm,
 	return ERR_PTR(err);
 }
 
+static struct drm_buddy_block *
+get_maxblock(struct list_head *head)
+{
+	struct drm_buddy_block *max_block = NULL, *node;
+
+	max_block = list_first_entry_or_null(head,
+					     struct drm_buddy_block,
+					     link);
+	if (!max_block)
+		return NULL;
+
+	list_for_each_entry(node, head, link) {
+		if (drm_buddy_block_offset(node) >
+		    drm_buddy_block_offset(max_block))
+			max_block = node;
+	}
+
+	return max_block;
+}
+
 static struct drm_buddy_block *
 alloc_from_freelist(struct drm_buddy *mm,
 		    unsigned int order,
@@ -379,11 +399,17 @@ alloc_from_freelist(struct drm_buddy *mm,
 	int err;
 
 	for (i = order; i <= mm->max_order; ++i) {
-		block = list_first_entry_or_null(&mm->free_list[i],
-						 struct drm_buddy_block,
-						 link);
-		if (block)
-			break;
+		if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
+			block = get_maxblock(&mm->free_list[i]);
+			if (block)
+				break;
+		} else {
+			block = list_first_entry_or_null(&mm->free_list[i],
+							 struct drm_buddy_block,
+							 link);
+			if (block)
+				break;
+		}
 	}
 
 	if (!block)
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
index 143657a706ae..ae9201246bb5 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -53,6 +53,9 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
 	INIT_LIST_HEAD(&bman_res->blocks);
 	bman_res->mm = mm;
 
+	if (place->flags & TTM_PL_FLAG_TOPDOWN)
+		bman_res->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+
 	if (place->fpfn || lpfn != man->size)
 		bman_res->flags |= DRM_BUDDY_RANGE_ALLOCATION;
 
diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h
index 865664b90a8a..424fc443115e 100644
--- a/include/drm/drm_buddy.h
+++ b/include/drm/drm_buddy.h
@@ -28,6 +28,7 @@
 })
 
 #define DRM_BUDDY_RANGE_ALLOCATION (1 << 0)
+#define DRM_BUDDY_TOPDOWN_ALLOCATION (1 << 1)
 
 struct drm_buddy_block {
 #define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
-- 
2.25.1


WARNING: multiple messages have this Message-ID (diff)
From: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
To: <dri-devel@lists.freedesktop.org>,
	<intel-gfx@lists.freedesktop.org>,
	<amd-gfx@lists.freedesktop.org>
Cc: daniel@ffwll.ch, Arunpravin <Arunpravin.PaneerSelvam@amd.com>,
	jani.nikula@linux.intel.com, matthew.auld@intel.com,
	tzimmermann@suse.de, alexander.deucher@amd.com,
	christian.koenig@amd.com
Subject: [PATCH v7 3/6] drm: implement top-down allocation method
Date: Sun, 9 Jan 2022 19:49:48 +0530	[thread overview]
Message-ID: <20220109141951.134432-3-Arunpravin.PaneerSelvam@amd.com> (raw)
In-Reply-To: <20220109141951.134432-1-Arunpravin.PaneerSelvam@amd.com>

Implemented a function which walk through the order list,
compares the offset and returns the maximum offset block,
this method is unpredictable in obtaining the high range
address blocks which depends on allocation and deallocation.
for instance, if driver requests address at a low specific
range, allocator traverses from the root block and splits
the larger blocks until it reaches the specific block and
in the process of splitting, lower orders in the freelist
are occupied with low range address blocks and for the
subsequent TOPDOWN memory request we may return the low
range blocks.To overcome this issue, we may go with the
below approach.

The other approach, sorting each order list entries in
ascending order and compares the last entry of each
order list in the freelist and return the max block.
This creates sorting overhead on every drm_buddy_free()
request and split up of larger blocks for a single page
request.

v2:
  - Fix alignment issues(Matthew Auld)
  - Remove unnecessary list_empty check(Matthew Auld)
  - merged the below patch to see the feature in action
     - add top-down alloc support to i915 driver

Signed-off-by: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
---
 drivers/gpu/drm/drm_buddy.c                   | 36 ++++++++++++++++---
 drivers/gpu/drm/i915/i915_ttm_buddy_manager.c |  3 ++
 include/drm/drm_buddy.h                       |  1 +
 3 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index cd914d104b1a..11356c2bb7aa 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -369,6 +369,26 @@ alloc_range_bias(struct drm_buddy *mm,
 	return ERR_PTR(err);
 }
 
+static struct drm_buddy_block *
+get_maxblock(struct list_head *head)
+{
+	struct drm_buddy_block *max_block = NULL, *node;
+
+	max_block = list_first_entry_or_null(head,
+					     struct drm_buddy_block,
+					     link);
+	if (!max_block)
+		return NULL;
+
+	list_for_each_entry(node, head, link) {
+		if (drm_buddy_block_offset(node) >
+		    drm_buddy_block_offset(max_block))
+			max_block = node;
+	}
+
+	return max_block;
+}
+
 static struct drm_buddy_block *
 alloc_from_freelist(struct drm_buddy *mm,
 		    unsigned int order,
@@ -379,11 +399,17 @@ alloc_from_freelist(struct drm_buddy *mm,
 	int err;
 
 	for (i = order; i <= mm->max_order; ++i) {
-		block = list_first_entry_or_null(&mm->free_list[i],
-						 struct drm_buddy_block,
-						 link);
-		if (block)
-			break;
+		if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
+			block = get_maxblock(&mm->free_list[i]);
+			if (block)
+				break;
+		} else {
+			block = list_first_entry_or_null(&mm->free_list[i],
+							 struct drm_buddy_block,
+							 link);
+			if (block)
+				break;
+		}
 	}
 
 	if (!block)
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
index 143657a706ae..ae9201246bb5 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -53,6 +53,9 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
 	INIT_LIST_HEAD(&bman_res->blocks);
 	bman_res->mm = mm;
 
+	if (place->flags & TTM_PL_FLAG_TOPDOWN)
+		bman_res->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+
 	if (place->fpfn || lpfn != man->size)
 		bman_res->flags |= DRM_BUDDY_RANGE_ALLOCATION;
 
diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h
index 865664b90a8a..424fc443115e 100644
--- a/include/drm/drm_buddy.h
+++ b/include/drm/drm_buddy.h
@@ -28,6 +28,7 @@
 })
 
 #define DRM_BUDDY_RANGE_ALLOCATION (1 << 0)
+#define DRM_BUDDY_TOPDOWN_ALLOCATION (1 << 1)
 
 struct drm_buddy_block {
 #define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
-- 
2.25.1


  parent reply	other threads:[~2022-01-09 14:20 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-09 14:19 [PATCH v7 1/6] drm: move the buddy allocator from i915 into common drm Arunpravin
2022-01-09 14:19 ` Arunpravin
2022-01-09 14:19 ` [Intel-gfx] " Arunpravin
2022-01-09 14:19 ` [PATCH v7 2/6] drm: improve drm_buddy_alloc function Arunpravin
2022-01-09 14:19   ` Arunpravin
2022-01-09 14:19   ` [Intel-gfx] " Arunpravin
2022-01-09 14:19 ` Arunpravin [this message]
2022-01-09 14:19   ` [PATCH v7 3/6] drm: implement top-down allocation method Arunpravin
2022-01-09 14:19   ` [Intel-gfx] " Arunpravin
2022-01-09 14:19 ` [PATCH v7 4/6] drm: implement a method to free unused pages Arunpravin
2022-01-09 14:19   ` Arunpravin
2022-01-09 14:19   ` [Intel-gfx] " Arunpravin
2022-01-09 14:19 ` [PATCH v7 5/6] drm/amdgpu: move vram inline functions into a header Arunpravin
2022-01-09 14:19   ` Arunpravin
2022-01-09 14:19   ` [Intel-gfx] " Arunpravin
2022-01-09 14:19 ` [PATCH v7 6/6] drm/amdgpu: add drm buddy support to amdgpu Arunpravin
2022-01-09 14:19   ` Arunpravin
2022-01-09 14:19   ` [Intel-gfx] " Arunpravin
2022-01-10  9:58   ` kernel test robot
2022-01-10  9:58     ` kernel test robot
2022-01-09 14:43 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [v7,1/6] drm: move the buddy allocator from i915 into common drm Patchwork
2022-01-09 14:46 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2022-01-09 15:02 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2022-01-09 16:22 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2022-01-10  8:03 ` [PATCH v7 1/6] " Christian König
2022-01-10  8:03   ` Christian König
2022-01-10  8:03   ` [Intel-gfx] " Christian König
2022-01-11 20:12   ` Arunpravin
2022-01-11 20:12     ` Arunpravin
2022-01-11 20:12     ` [Intel-gfx] " Arunpravin
2022-01-10  9:58 ` kernel test robot

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=20220109141951.134432-3-Arunpravin.PaneerSelvam@amd.com \
    --to=arunpravin.paneerselvam@amd.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=matthew.auld@intel.com \
    --cc=tzimmermann@suse.de \
    /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.