From 92664676f2e3f8588949d01edc1193896b683d00 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Mon, 11 Sep 2023 14:44:22 -0400 Subject: [PATCH] drm/amdkfd: Move dma unmapping after TLB flush [ Upstream commit 101b8104307eac734f2dfa4d3511430b0b631c73 ] Otherwise GPU may access the stale mapping and generate IOMMU IO_PAGE_FAULT. Move this to inside p->mutex to prevent multiple threads mapping and unmapping concurrently race condition. After kfd_mem_dmaunmap_attachment is removed from unmap_bo_from_gpuvm, kfd_mem_dmaunmap_attachment is called if failed to map to GPUs, and before free the mem attachment in case failed to unmap from GPUs. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 + .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 26 ++++++++++++++++--- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 22 +++++++++------- 3 files changed, 36 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index dbc842590b25..585d608c10e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -286,6 +286,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); +void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_sync_memory( struct amdgpu_device *adev, struct kgd_mem *mem, bool intr); int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 7d5fbaaba72f..3e7f4d8dc9d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -719,7 +719,7 @@ kfd_mem_dmaunmap_sg_bo(struct kgd_mem *mem, enum dma_data_direction dir; if (unlikely(!ttm->sg)) { - pr_err("SG Table of BO is UNEXPECTEDLY NULL"); + pr_debug("SG Table of BO is NULL"); return; } @@ -1226,8 +1226,6 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem, amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update); amdgpu_sync_fence(sync, bo_va->last_pt_update); - - kfd_mem_dmaunmap_attachment(mem, entry); } static int update_gpuvm_pte(struct kgd_mem *mem, @@ -1282,6 +1280,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem, update_gpuvm_pte_failed: unmap_bo_from_gpuvm(mem, entry, sync); + kfd_mem_dmaunmap_attachment(mem, entry); return ret; } @@ -1852,8 +1851,10 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( mem->va + bo_size * (1 + mem->aql_queue)); /* Remove from VM internal data structures */ - list_for_each_entry_safe(entry, tmp, &mem->attachments, list) + list_for_each_entry_safe(entry, tmp, &mem->attachments, list) { + kfd_mem_dmaunmap_attachment(mem, entry); kfd_mem_detach(entry); + } ret = unreserve_bo_and_vms(&ctx, false, false); @@ -2024,6 +2025,23 @@ out: return ret; } +void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv) +{ + struct kfd_mem_attachment *entry; + struct amdgpu_vm *vm; + + vm = drm_priv_to_vm(drm_priv); + + mutex_lock(&mem->lock); + + list_for_each_entry(entry, &mem->attachments, list) { + if (entry->bo_va->base.vm == vm) + kfd_mem_dmaunmap_attachment(mem, entry); + } + + mutex_unlock(&mem->lock); +} + int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index b0f475d51ae7..2b21ce967e76 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1400,17 +1400,21 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, goto sync_memory_failed; } } + + /* Flush TLBs after waiting for the page table updates to complete */ + for (i = 0; i < args->n_devices; i++) { + peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + if (flush_tlb) + kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); + + /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */ + amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv); + } + mutex_unlock(&p->mutex); - if (flush_tlb) { - /* Flush TLBs after waiting for the page table updates to complete */ - for (i = 0; i < args->n_devices; i++) { - peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); - } - } kfree(devices_arr); return 0;