amd-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Felix Kuehling <Felix.Kuehling@amd.com>
To: amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: Alex Sierra <alex.sierra@amd.com>
Subject: [PATCH 25/34] drm/amdkfd: add svm_bo reference for eviction fence
Date: Mon,  5 Apr 2021 21:46:20 -0400	[thread overview]
Message-ID: <20210406014629.25141-26-Felix.Kuehling@amd.com> (raw)
In-Reply-To: <20210406014629.25141-1-Felix.Kuehling@amd.com>

From: Alex Sierra <alex.sierra@amd.com>

[why]
As part of the SVM functionality, the eviction mechanism used for
SVM_BOs is different. This mechanism uses one eviction fence per prange,
instead of one fence per kfd_process.

[how]
A svm_bo reference to amdgpu_amdkfd_fence to allow differentiate between
SVM_BO or regular BO evictions. This also include modifications to set the
reference at the fence creation call.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h       | 4 +++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c | 5 +++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 6 ++++--
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 14f68c028126..beb2ef070a0c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -75,6 +75,7 @@ struct amdgpu_amdkfd_fence {
 	struct mm_struct *mm;
 	spinlock_t lock;
 	char timeline_name[TASK_COMM_LEN];
+	struct svm_range_bo *svm_bo;
 };
 
 struct amdgpu_kfd_dev {
@@ -148,7 +149,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
 					int queue_bit);
 
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
-								struct mm_struct *mm);
+				struct mm_struct *mm,
+				struct svm_range_bo *svm_bo);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm);
 struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
index 5af464933976..53559643c712 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
@@ -60,7 +60,8 @@ static atomic_t fence_seq = ATOMIC_INIT(0);
  */
 
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
-						       struct mm_struct *mm)
+				struct mm_struct *mm,
+				struct svm_range_bo *svm_bo)
 {
 	struct amdgpu_amdkfd_fence *fence;
 
@@ -73,7 +74,7 @@ struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
 	fence->mm = mm;
 	get_task_comm(fence->timeline_name, current);
 	spin_lock_init(&fence->lock);
-
+	fence->svm_bo = svm_bo;
 	dma_fence_init(&fence->base, &amdkfd_fence_ops, &fence->lock,
 		   context, atomic_inc_return(&fence_seq));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index e93850f2f3b1..9af644f256e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -970,7 +970,8 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 
 		info->eviction_fence =
 			amdgpu_amdkfd_fence_create(dma_fence_context_alloc(1),
-						   current->mm);
+						   current->mm,
+						   NULL);
 		if (!info->eviction_fence) {
 			pr_err("Failed to create eviction fence\n");
 			ret = -ENOMEM;
@@ -2188,7 +2189,8 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 	 */
 	new_fence = amdgpu_amdkfd_fence_create(
 				process_info->eviction_fence->base.context,
-				process_info->eviction_fence->mm);
+				process_info->eviction_fence->mm,
+				NULL);
 	if (!new_fence) {
 		pr_err("Failed to create eviction fence\n");
 		ret = -ENOMEM;
-- 
2.31.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  parent reply	other threads:[~2021-04-06  1:47 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-06  1:45 [PATCH 00/34] Add HMM-based SVM memory manager to KFD v4 Felix Kuehling
2021-04-06  1:45 ` [PATCH 01/34] drm/amdkfd: helper to convert gpu id and idx Felix Kuehling
2021-04-06  1:45 ` [PATCH 02/34] drm/amdkfd: add svm ioctl API Felix Kuehling
2021-04-06  1:45 ` [PATCH 03/34] drm/amdkfd: register svm range Felix Kuehling
2021-04-06  1:45 ` [PATCH 04/34] drm/amdkfd: add svm ioctl GET_ATTR op Felix Kuehling
2021-04-06  1:46 ` [PATCH 05/34] drm/amdgpu: add common HMM get pages function Felix Kuehling
2021-04-06  1:46 ` [PATCH 06/34] drm/amdkfd: support larger svm range allocation Felix Kuehling
2021-04-06  1:46 ` [PATCH 07/34] drm/amdkfd: validate svm range system memory Felix Kuehling
2021-04-06  1:46 ` [PATCH 08/34] drm/amdkfd: deregister svm range Felix Kuehling
2021-04-06  1:46 ` [PATCH 09/34] drm/amdgpu: export vm update mapping interface Felix Kuehling
2021-04-06  1:46 ` [PATCH 10/34] drm/amdkfd: map svm range to GPUs Felix Kuehling
2021-04-06  1:46 ` [PATCH 11/34] drm/amdkfd: svm range eviction and restore Felix Kuehling
2021-04-06  1:46 ` [PATCH 12/34] drm/amdgpu: Enable retry faults unconditionally on Aldebaran Felix Kuehling
2021-04-06  1:46 ` [PATCH 13/34] drm/amdkfd: add xnack enabled flag to kfd_process Felix Kuehling
2021-04-06  1:46 ` [PATCH 14/34] drm/amdkfd: add ioctl to configure and query xnack retries Felix Kuehling
2021-04-06  1:46 ` [PATCH 15/34] drm/amdkfd: register HMM device private zone Felix Kuehling
2021-04-06  1:46 ` [PATCH 16/34] drm/amdkfd: validate vram svm range from TTM Felix Kuehling
2021-04-06  1:46 ` [PATCH 17/34] drm/amdkfd: support xgmi same hive mapping Felix Kuehling
2021-04-06  1:46 ` [PATCH 18/34] drm/amdkfd: copy memory through gart table Felix Kuehling
2021-04-06  1:46 ` [PATCH 19/34] drm/amdkfd: HMM migrate ram to vram Felix Kuehling
2021-04-06  1:46 ` [PATCH 20/34] drm/amdkfd: HMM migrate vram to ram Felix Kuehling
2021-04-06  1:46 ` [PATCH 21/34] drm/amdkfd: invalidate tables on page retry fault Felix Kuehling
2021-04-06  1:46 ` [PATCH 22/34] drm/amdgpu: enable 48-bit IH timestamp counter Felix Kuehling
2021-04-06  1:46 ` [PATCH 23/34] drm/amdkfd: page table restore through svm API Felix Kuehling
2021-04-06  1:46 ` [PATCH 24/34] drm/amdkfd: SVM API call to restore page tables Felix Kuehling
2021-04-06  1:46 ` Felix Kuehling [this message]
2021-04-06  1:46 ` [PATCH 26/34] drm/amdgpu: add param bit flag to create SVM BOs Felix Kuehling
2021-04-06  1:46 ` [PATCH 27/34] drm/amdkfd: add svm_bo eviction mechanism support Felix Kuehling
2021-04-06  1:46 ` [PATCH 28/34] drm/amdgpu: svm bo enable_signal call condition Felix Kuehling
2021-04-06  1:46 ` [PATCH 29/34] drm/amdgpu: add svm_bo eviction to enable_signal cb Felix Kuehling
2021-04-06  1:46 ` [PATCH 30/34] drm/amdkfd: refine migration policy with xnack on Felix Kuehling
2021-04-06  1:46 ` [PATCH 31/34] drm/amdkfd: add svm range validate timestamp Felix Kuehling
2021-04-06  1:46 ` [PATCH 32/34] drm/amdkfd: multiple gpu migrate vram to vram Felix Kuehling
2021-04-06  1:46 ` [PATCH 33/34] drm/amdkfd: Add SVM API support capability bits Felix Kuehling
2021-04-06  1:46 ` [PATCH 34/34] drm/amdkfd: Add CONFIG_HSA_AMD_SVM Felix Kuehling
2021-04-08 15:02 ` [PATCH 00/34] Add HMM-based SVM memory manager to KFD v4 Jason Gunthorpe
2021-04-08 15:10   ` Felix Kuehling
2021-04-15  1:23 [PATCH 00/34] Add HMM-based SVM memory manager to KFD v5 Felix Kuehling
2021-04-15  1:23 ` [PATCH 25/34] drm/amdkfd: add svm_bo reference for eviction fence Felix Kuehling

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=20210406014629.25141-26-Felix.Kuehling@amd.com \
    --to=felix.kuehling@amd.com \
    --cc=alex.sierra@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=dri-devel@lists.freedesktop.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).