From: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
To: "Alex Deucher" <alexander.deucher@amd.com>,
"Christian König" <christian.koenig@amd.com>,
"David Airlie" <airlied@gmail.com>,
"Simona Vetter" <simona@ffwll.ch>,
"Felix Kuehling" <Felix.Kuehling@amd.com>
Cc: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>,
"Felix Kuehling" <felix.kuehling@amd.com>,
<amd-gfx@lists.freedesktop.org>,
<dri-devel@lists.freedesktop.org>, <linux-kernel@vger.kernel.org>
Subject: [PATCH v3 21/28] drm/amdgpu: allocate multiple move entities
Date: Fri, 21 Nov 2025 11:12:31 +0100 [thread overview]
Message-ID: <20251121101315.3585-22-pierre-eric.pelloux-prayer@amd.com> (raw)
In-Reply-To: <20251121101315.3585-1-pierre-eric.pelloux-prayer@amd.com>
No functional change for now, as we always use entity 0.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-by: Felix Kuehling <felix.kuehling@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 45 +++++++++++++++---------
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 3 +-
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 2 +-
3 files changed, 31 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index d7f041e43eca..438e8a3b7a06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -439,7 +439,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
dst.offset = 0;
r = amdgpu_ttm_copy_mem_to_mem(adev,
- &adev->mman.move_entity,
+ &adev->mman.move_entities[0],
&src, &dst,
new_mem->size,
amdgpu_bo_encrypted(abo),
@@ -452,7 +452,7 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) {
struct dma_fence *wipe_fence = NULL;
- r = amdgpu_fill_buffer(adev, &adev->mman.move_entity,
+ r = amdgpu_fill_buffer(adev, &adev->mman.move_entities[0],
abo, 0, NULL, &wipe_fence,
AMDGPU_KERNEL_JOB_ID_MOVE_BLIT);
if (r) {
@@ -2224,12 +2224,13 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
{
struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
u32 used_windows, reserved_windows;
- u32 num_clear_entities;
+ u32 num_clear_entities, num_move_entities;
uint64_t size;
int r, i, j;
num_clear_entities = adev->sdma.num_instances;
- reserved_windows = 2 + num_clear_entities;
+ num_move_entities = MIN(adev->sdma.num_instances, TTM_NUM_MOVE_FENCES);
+ reserved_windows = 2 * num_move_entities + num_clear_entities;
if (!adev->mman.initialized || amdgpu_in_reset(adev) ||
adev->mman.buffer_funcs_enabled == enable || adev->gmc.is_app_apu)
@@ -2251,20 +2252,25 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
DRM_SCHED_PRIORITY_KERNEL, &sched,
1, NULL);
if (r) {
- dev_err(adev->dev,
- "Failed setting up TTM BO eviction entity (%d)\n",
+ dev_err(adev->dev, "Failed setting up entity (%d)\n",
r);
return 0;
}
- r = drm_sched_entity_init(&adev->mman.move_entity.base,
- DRM_SCHED_PRIORITY_NORMAL, &sched,
- 1, NULL);
- if (r) {
- dev_err(adev->dev,
- "Failed setting up TTM BO move entity (%d)\n",
- r);
- goto error_free_entity;
+ adev->mman.num_move_entities = num_move_entities;
+ for (i = 0; i < num_move_entities; i++) {
+ r = drm_sched_entity_init(&adev->mman.move_entities[i].base,
+ DRM_SCHED_PRIORITY_NORMAL, &sched,
+ 1, NULL);
+ if (r) {
+ dev_err(adev->dev,
+ "Failed setting up TTM BO move entities (%d)\n",
+ r);
+ for (j = 0; j < i; j++)
+ drm_sched_entity_destroy(
+ &adev->mman.move_entities[j].base);
+ goto error_free_entity;
+ }
}
adev->mman.num_clear_entities = num_clear_entities;
@@ -2279,6 +2285,9 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
DRM_SCHED_PRIORITY_NORMAL, &sched,
1, NULL);
if (r) {
+ for (j = 0; j < num_move_entities; j++)
+ drm_sched_entity_destroy(
+ &adev->mman.move_entities[j].base);
for (j = 0; j < i; j++)
drm_sched_entity_destroy(
&adev->mman.clear_entities[j].base);
@@ -2290,15 +2299,17 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
/* Statically assign GART windows to each entity. */
used_windows = amdgpu_ttm_buffer_entity_init(&adev->mman.default_entity,
0, false, false);
- used_windows = amdgpu_ttm_buffer_entity_init(&adev->mman.move_entity,
- used_windows, true, true);
+ for (i = 0; i < num_move_entities; i++)
+ used_windows = amdgpu_ttm_buffer_entity_init(&adev->mman.move_entities[i],
+ used_windows, true, true);
for (i = 0; i < num_clear_entities; i++)
used_windows = amdgpu_ttm_buffer_entity_init(&adev->mman.clear_entities[i],
used_windows, false, true);
WARN_ON(used_windows != reserved_windows);
} else {
drm_sched_entity_destroy(&adev->mman.default_entity.base);
- drm_sched_entity_destroy(&adev->mman.move_entity.base);
+ for (i = 0; i < num_move_entities; i++)
+ drm_sched_entity_destroy(&adev->mman.move_entities[i].base);
for (i = 0; i < num_clear_entities; i++)
drm_sched_entity_destroy(&adev->mman.clear_entities[i].base);
/* Drop all the old fences since re-creating the scheduler entities
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 250ef54a5550..eabc5a1549e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -72,9 +72,10 @@ struct amdgpu_mman {
struct mutex gtt_window_lock;
struct amdgpu_ttm_buffer_entity default_entity; /* has no gart windows */
- struct amdgpu_ttm_buffer_entity move_entity;
struct amdgpu_ttm_buffer_entity *clear_entities;
u32 num_clear_entities;
+ struct amdgpu_ttm_buffer_entity move_entities[TTM_NUM_MOVE_FENCES];
+ u32 num_move_entities;
struct amdgpu_vram_mgr vram_mgr;
struct amdgpu_gtt_mgr gtt_mgr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 0cc1d2b35026..5dd65f05a1e0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -135,7 +135,7 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
u64 size;
int r;
- entity = &adev->mman.move_entity;
+ entity = &adev->mman.move_entities[0];
mutex_lock(&entity->lock);
--
2.43.0
next prev parent reply other threads:[~2025-11-21 10:18 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-21 10:12 [PATCH v3 00/28] drm/amdgpu: use all SDMA instances for TTM clears and moves Pierre-Eric Pelloux-Prayer
2025-11-21 10:12 ` [PATCH v3 01/28] drm/amdgpu: give each kernel job a unique id Pierre-Eric Pelloux-Prayer
2025-11-21 12:51 ` Christian König
2025-11-21 20:02 ` Felix Kuehling
2025-11-21 10:12 ` [PATCH v3 02/28] drm/amdgpu: use ttm_resource_manager_cleanup Pierre-Eric Pelloux-Prayer
2025-11-21 12:52 ` Christian König
2025-11-21 10:12 ` [PATCH v3 03/28] drm/amdgpu: remove direct_submit arg from amdgpu_copy_buffer Pierre-Eric Pelloux-Prayer
2025-11-21 10:12 ` [PATCH v3 04/28] drm/amdgpu: remove the ring param from ttm functions Pierre-Eric Pelloux-Prayer
2025-11-21 12:58 ` Christian König
2025-11-21 10:12 ` [PATCH v3 05/28] drm/amdgpu: introduce amdgpu_ttm_buffer_entity Pierre-Eric Pelloux-Prayer
2025-11-21 10:12 ` [PATCH v3 06/28] drm/amdgpu: add amdgpu_ttm_job_submit helper Pierre-Eric Pelloux-Prayer
2025-11-21 13:00 ` Christian König
2025-11-21 10:12 ` [PATCH v3 07/28] drm/amdgpu: fix error handling in amdgpu_copy_buffer Pierre-Eric Pelloux-Prayer
2025-11-21 13:04 ` Christian König
2025-11-21 10:12 ` [PATCH v3 08/28] drm/amdgpu: pass the entity to use to amdgpu_ttm_map_buffer Pierre-Eric Pelloux-Prayer
2025-11-21 13:05 ` Christian König
2025-11-21 10:12 ` [PATCH v3 09/28] drm/amdgpu: pass the entity to use to ttm public functions Pierre-Eric Pelloux-Prayer
2025-11-21 13:23 ` Christian König
2025-11-21 10:12 ` [PATCH v3 10/28] drm/amdgpu: add amdgpu_device argument to ttm functions that need it Pierre-Eric Pelloux-Prayer
2025-11-21 13:24 ` Christian König
2025-11-21 16:09 ` Pierre-Eric Pelloux-Prayer
2025-11-24 8:42 ` Christian König
2025-11-21 10:12 ` [PATCH v3 11/28] drm/amdgpu: statically assign gart windows to ttm entities Pierre-Eric Pelloux-Prayer
2025-11-21 13:34 ` Christian König
2025-11-21 10:12 ` [PATCH v3 12/28] drm/amdgpu: remove AMDGPU_GTT_NUM_TRANSFER_WINDOWS Pierre-Eric Pelloux-Prayer
2025-11-21 13:50 ` Christian König
2025-11-21 10:12 ` [PATCH v3 13/28] drm/amdgpu: add missing lock when using ttm entities Pierre-Eric Pelloux-Prayer
2025-11-21 13:53 ` Christian König
2025-11-21 10:12 ` [PATCH v3 14/28] drm/amdgpu: check entity lock is held in amdgpu_ttm_job_submit Pierre-Eric Pelloux-Prayer
2025-11-21 13:54 ` Christian König
2025-11-21 10:12 ` [PATCH v3 15/28] drm/amdgpu: double AMDGPU_GTT_MAX_TRANSFER_SIZE Pierre-Eric Pelloux-Prayer
2025-11-21 10:12 ` [PATCH v3 16/28] drm/amdgpu: use larger gart window when possible Pierre-Eric Pelloux-Prayer
2025-11-21 15:02 ` Christian König
2025-11-21 10:12 ` [PATCH v3 17/28] drm/amdgpu: introduce amdgpu_sdma_set_vm_pte_scheds Pierre-Eric Pelloux-Prayer
2025-11-21 15:05 ` Christian König
2025-11-21 10:12 ` [PATCH v3 18/28] drm/amdgpu: move sched status check inside amdgpu_ttm_set_buffer_funcs_status Pierre-Eric Pelloux-Prayer
2025-11-21 15:08 ` Christian König
2025-11-21 15:12 ` Pierre-Eric Pelloux-Prayer
2025-11-21 15:23 ` Christian König
2025-11-21 10:12 ` [PATCH v3 19/28] drm/ttm: rework pipelined eviction fence handling Pierre-Eric Pelloux-Prayer
2025-11-21 15:12 ` Christian König
2025-11-26 15:34 ` Maarten Lankhorst
2025-11-26 15:36 ` Christian König
2025-11-26 15:39 ` Maarten Lankhorst
2025-11-26 15:48 ` Christian König
2025-11-26 17:14 ` Maarten Lankhorst
2025-11-21 10:12 ` [PATCH v3 20/28] drm/amdgpu: allocate multiple clear entities Pierre-Eric Pelloux-Prayer
2025-11-21 15:34 ` Christian König
2025-11-21 10:12 ` Pierre-Eric Pelloux-Prayer [this message]
2025-11-21 10:12 ` [PATCH v3 22/28] drm/amdgpu: round robin through clear_entities in amdgpu_fill_buffer Pierre-Eric Pelloux-Prayer
2025-11-21 15:36 ` Christian König
2025-11-21 10:12 ` [PATCH v3 23/28] drm/amdgpu: use TTM_NUM_MOVE_FENCES when reserving fences Pierre-Eric Pelloux-Prayer
2025-11-21 15:41 ` Christian König
2025-11-21 10:12 ` [PATCH v3 24/28] drm/amdgpu: use multiple entities in amdgpu_move_blit Pierre-Eric Pelloux-Prayer
2025-11-21 10:12 ` [PATCH v3 25/28] drm/amdgpu: pass all the sdma scheds to amdgpu_mman Pierre-Eric Pelloux-Prayer
2025-11-21 15:52 ` Christian König
2025-11-21 10:12 ` [PATCH v3 26/28] drm/amdgpu: give ttm entities access to all the sdma scheds Pierre-Eric Pelloux-Prayer
2025-11-21 10:12 ` [PATCH v3 27/28] drm/amdgpu: get rid of amdgpu_ttm_clear_buffer Pierre-Eric Pelloux-Prayer
2025-11-21 15:54 ` Christian König
2025-11-21 10:12 ` [PATCH v3 28/28] drm/amdgpu: rename amdgpu_fill_buffer as amdgpu_ttm_clear_buffer Pierre-Eric Pelloux-Prayer
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=20251121101315.3585-22-pierre-eric.pelloux-prayer@amd.com \
--to=pierre-eric.pelloux-prayer@amd.com \
--cc=Felix.Kuehling@amd.com \
--cc=airlied@gmail.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=simona@ffwll.ch \
/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
all inboxes | Powered by JetHome®