From ec6abe831a843208e99a59adf108adba22166b3f Mon Sep 17 00:00:00 2001 From: Alex Sierra Date: Thu, 7 Oct 2021 12:04:09 -0500 Subject: [PATCH] drm/amdkfd: rm BO resv on validation to avoid deadlock This fix the deadlock with the BO reservations during SVM_BO evictions while allocations in VRAM are concurrently performed. More specific, while the ttm waits for the fence to be signaled (ttm_bo_wait), it already has the BO reserved. In parallel, the restore worker might be running, prefetching memory to VRAM. This also requires to reserve the BO, but blocks the mmap semaphore first. The deadlock happens when the SVM_BO eviction worker kicks in and waits for the mmap semaphore held in restore worker. Preventing signal the fence back, causing the deadlock until the ttm times out. We don't need to hold the BO reservation anymore during validation and mapping. Now the physical addresses are taken from hmm_range_fault. We also take migrate_mutex to prevent range migration while validate_and_map update GPU page table. Signed-off-by: Alex Sierra Signed-off-by: Felix Kuehling Reviewed-by: Philip Yang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 9d0f65a90002..179080329af8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1307,7 +1307,7 @@ struct svm_validate_context { struct svm_range *prange; bool intr; unsigned long bitmap[MAX_GPU_INSTANCE]; - struct ttm_validate_buffer tv[MAX_GPU_INSTANCE+1]; + struct ttm_validate_buffer tv[MAX_GPU_INSTANCE]; struct list_head validate_list; struct ww_acquire_ctx ticket; }; @@ -1334,11 +1334,6 @@ static int svm_range_reserve_bos(struct svm_validate_context *ctx) ctx->tv[gpuidx].num_shared = 4; list_add(&ctx->tv[gpuidx].head, &ctx->validate_list); } - if (ctx->prange->svm_bo && ctx->prange->ttm_res) { - ctx->tv[MAX_GPU_INSTANCE].bo = &ctx->prange->svm_bo->bo->tbo; - ctx->tv[MAX_GPU_INSTANCE].num_shared = 1; - list_add(&ctx->tv[MAX_GPU_INSTANCE].head, &ctx->validate_list); - } r = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->validate_list, ctx->intr, NULL); -- 2.34.1