[PATCH AUTOSEL 6.6 10/19] drm/amdkfd: Add VRAM accounting for SVM migration

From: Sasha Levin
Date: Tue May 07 2024 - 19:07:10 EST


From: Mukul Joshi <mukul.joshi@xxxxxxx>

[ Upstream commit 1e214f7faaf5d842754cd5cfcd76308bfedab3b5 ]

Do VRAM accounting when doing migrations to vram to make sure
there is enough available VRAM and migrating to VRAM doesn't evict
other possible non-unified memory BOs. If migrating to VRAM fails,
driver can fall back to using system memory seamlessly.

Signed-off-by: Mukul Joshi <mukul.joshi@xxxxxxx>
Reviewed-by: Felix Kuehling <felix.kuehling@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 16 +++++++++++++++-
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 659313648b200..3263b5fa182d2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -516,10 +516,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
start = prange->start << PAGE_SHIFT;
end = (prange->last + 1) << PAGE_SHIFT;

+ r = amdgpu_amdkfd_reserve_mem_limit(node->adev,
+ prange->npages * PAGE_SIZE,
+ KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+ node->xcp ? node->xcp->id : 0);
+ if (r) {
+ dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r);
+ return -ENOSPC;
+ }
+
r = svm_range_vram_node_new(node, prange, true);
if (r) {
dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r);
- return r;
+ goto out;
}
ttm_res_offset = prange->offset << PAGE_SHIFT;

@@ -549,6 +558,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
svm_range_vram_node_free(prange);
}

+out:
+ amdgpu_amdkfd_unreserve_mem_limit(node->adev,
+ prange->npages * PAGE_SIZE,
+ KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+ node->xcp ? node->xcp->id : 0);
return r < 0 ? r : 0;
}

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 87e9ca65e58e0..ce76d45549984 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3416,7 +3416,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
r = svm_migrate_to_vram(prange, best_loc, mm, KFD_MIGRATE_TRIGGER_PREFETCH);
*migrated = !r;

- return r;
+ return 0;
}

int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
--
2.43.0