AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Alex Sierra <alex.sierra@amd.com>
To: amd-gfx@lists.freedesktop.org
Cc: Alex Sierra <alex.sierra@amd.com>,
	Felix Kuehling <Felix.Kuehling@amd.com>
Subject: [PATCH 03/11] drm/amdkfd: set owner ref to svm range prefault
Date: Tue, 29 Jun 2021 13:01:58 -0500	[thread overview]
Message-ID: <20210629180206.8002-3-alex.sierra@amd.com> (raw)
In-Reply-To: <20210629180206.8002-1-alex.sierra@amd.com>

svm_range_prefault is called right before migrations to VRAM,
to make sure pages are resident in system memory before the migration.
With partial migrations, this reference is used by hmm range get pages
to avoid migrating pages that are already in the same VRAM domain.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c     | 5 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_svm.h     | 3 ++-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 8ce71c8142aa..33d4a118d05f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -519,7 +519,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 		 prange->start, prange->last, best_loc);
 
 	/* FIXME: workaround for page locking bug with invalid pages */
-	svm_range_prefault(prange, mm);
+	svm_range_prefault(prange, mm, SVM_ADEV_PGMAP_OWNER(adev));
 
 	start = prange->start << PAGE_SHIFT;
 	end = (prange->last + 1) << PAGE_SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 125099a91e18..61db2a4db917 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2705,7 +2705,8 @@ svm_range_best_prefetch_location(struct svm_range *prange)
 /* FIXME: This is a workaround for page locking bug when some pages are
  * invalid during migration to VRAM
  */
-void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm)
+void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm,
+			void *owner)
 {
 	struct hmm_range *hmm_range;
 	int r;
@@ -2716,7 +2717,7 @@ void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm)
 	r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
 				       prange->start << PAGE_SHIFT,
 				       prange->npages, &hmm_range,
-				       false, true, NULL);
+				       false, true, owner);
 	if (!r) {
 		amdgpu_hmm_range_get_pages_done(hmm_range);
 		prange->validated_once = true;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 1f88bdfdbcc2..9a7744a12dab 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -176,7 +176,8 @@ void schedule_deferred_list_work(struct svm_range_list *svms);
 void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr,
 			 unsigned long offset, unsigned long npages);
 void svm_range_free_dma_mappings(struct svm_range *prange);
-void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm);
+void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm,
+			void *owner);
 struct kfd_process_device *
 svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev);
 
-- 
2.32.0

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

  parent reply	other threads:[~2021-06-29 18:03 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-29 18:01 [PATCH 01/11] drm/amdkfd: device pgmap owner at the svm migrate init Alex Sierra
2021-06-29 18:01 ` [PATCH 02/11] drm/amdkfd: add owner ref param to get hmm pages Alex Sierra
2021-06-29 18:01 ` Alex Sierra [this message]
2021-06-29 18:01 ` [PATCH 04/11] drm/amdgpu: get owner ref in validate and map Alex Sierra
2021-06-29 18:02 ` [PATCH 05/11] drm/amdkfd: use hmm range fault to get both domain pfns Alex Sierra
2021-06-29 18:02 ` [PATCH 06/11] drm/amdkfd: classify and map mixed svm range pages in GPU Alex Sierra
2021-06-29 18:02 ` [PATCH 07/11] drm/amdkfd: skip invalid pages during migrations Alex Sierra
2021-06-29 18:02 ` [PATCH 08/11] drm/amdkfd: skip migration for pages already in VRAM Alex Sierra
2021-06-29 18:02 ` [PATCH 09/11] drm/amdkfd: add invalid pages debug at vram migration Alex Sierra
2021-06-29 18:02 ` [PATCH 10/11] drm/amdkfd: Maintain svm_bo reference in page->zone_device_data Alex Sierra
2021-06-29 18:02 ` [PATCH 11/11] drm/amdkfd: inc counter on child ranges with xnack off Alex Sierra
2021-06-29 19:00   ` Felix Kuehling
2021-06-30  4:00 ` [PATCH 01/11] drm/amdkfd: device pgmap owner at the svm migrate init Felix Kuehling
2021-06-30  4:06   ` 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=20210629180206.8002-3-alex.sierra@amd.com \
    --to=alex.sierra@amd.com \
    --cc=Felix.Kuehling@amd.com \
    --cc=amd-gfx@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