[PATCH 06/11] drm/amdgpu: remove GTT accounting v2
Mike Lothian
mike at fireburn.co.uk
Wed Mar 9 14:10:04 UTC 2022
Hi
This patch seems to be causing me problems
https://gitlab.freedesktop.org/drm/amd/-/issues/1927
There are 3 issues I'm experiencing, two kernel bugs and a mesa bug
Cheers
Mike
On Mon, 14 Feb 2022 at 09:34, Christian König
<ckoenig.leichtzumerken at gmail.com> wrote:
>
> This is provided by TTM now.
>
> Also switch man->size to bytes instead of pages and fix the double
> printing of size and usage in debugfs.
>
> v2: fix size checking as well
>
> Signed-off-by: Christian König <christian.koenig at amd.com>
> Tested-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 49 +++++----------------
> drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 8 ++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 2 -
> 4 files changed, 16 insertions(+), 45 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> index e0c7fbe01d93..3bcd27ae379d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> @@ -60,7 +60,7 @@ static ssize_t amdgpu_mem_info_gtt_total_show(struct device *dev,
> struct ttm_resource_manager *man;
>
> man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
> - return sysfs_emit(buf, "%llu\n", man->size * PAGE_SIZE);
> + return sysfs_emit(buf, "%llu\n", man->size);
> }
>
> /**
> @@ -77,8 +77,9 @@ static ssize_t amdgpu_mem_info_gtt_used_show(struct device *dev,
> {
> struct drm_device *ddev = dev_get_drvdata(dev);
> struct amdgpu_device *adev = drm_to_adev(ddev);
> + struct ttm_resource_manager *man = &adev->mman.gtt_mgr.manager;
>
> - return sysfs_emit(buf, "%llu\n", amdgpu_gtt_mgr_usage(&adev->mman.gtt_mgr));
> + return sysfs_emit(buf, "%llu\n", ttm_resource_manager_usage(man));
> }
>
> static DEVICE_ATTR(mem_info_gtt_total, S_IRUGO,
> @@ -130,20 +131,17 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
> struct amdgpu_gtt_node *node;
> int r;
>
> - if (!(place->flags & TTM_PL_FLAG_TEMPORARY) &&
> - atomic64_add_return(num_pages, &mgr->used) > man->size) {
> - atomic64_sub(num_pages, &mgr->used);
> - return -ENOSPC;
> - }
> -
> node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL);
> - if (!node) {
> - r = -ENOMEM;
> - goto err_out;
> - }
> + if (!node)
> + return -ENOMEM;
>
> node->tbo = tbo;
> ttm_resource_init(tbo, place, &node->base.base);
> + if (!(place->flags & TTM_PL_FLAG_TEMPORARY) &&
> + ttm_resource_manager_usage(man) > man->size) {
> + r = -ENOSPC;
> + goto err_free;
> + }
>
> if (place->lpfn) {
> spin_lock(&mgr->lock);
> @@ -169,11 +167,6 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
> err_free:
> ttm_resource_fini(man, &node->base.base);
> kfree(node);
> -
> -err_out:
> - if (!(place->flags & TTM_PL_FLAG_TEMPORARY))
> - atomic64_sub(num_pages, &mgr->used);
> -
> return r;
> }
>
> @@ -196,25 +189,10 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
> drm_mm_remove_node(&node->base.mm_nodes[0]);
> spin_unlock(&mgr->lock);
>
> - if (!(res->placement & TTM_PL_FLAG_TEMPORARY))
> - atomic64_sub(res->num_pages, &mgr->used);
> -
> ttm_resource_fini(man, res);
> kfree(node);
> }
>
> -/**
> - * amdgpu_gtt_mgr_usage - return usage of GTT domain
> - *
> - * @mgr: amdgpu_gtt_mgr pointer
> - *
> - * Return how many bytes are used in the GTT domain
> - */
> -uint64_t amdgpu_gtt_mgr_usage(struct amdgpu_gtt_mgr *mgr)
> -{
> - return atomic64_read(&mgr->used) * PAGE_SIZE;
> -}
> -
> /**
> * amdgpu_gtt_mgr_recover - re-init gart
> *
> @@ -260,9 +238,6 @@ static void amdgpu_gtt_mgr_debug(struct ttm_resource_manager *man,
> spin_lock(&mgr->lock);
> drm_mm_print(&mgr->mm, printer);
> spin_unlock(&mgr->lock);
> -
> - drm_printf(printer, "man size:%llu pages, gtt used:%llu pages\n",
> - man->size, atomic64_read(&mgr->used));
> }
>
> static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func = {
> @@ -288,14 +263,12 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
> man->use_tt = true;
> man->func = &amdgpu_gtt_mgr_func;
>
> - ttm_resource_manager_init(man, &adev->mman.bdev,
> - gtt_size >> PAGE_SHIFT);
> + ttm_resource_manager_init(man, &adev->mman.bdev, gtt_size);
>
> start = AMDGPU_GTT_MAX_TRANSFER_SIZE * AMDGPU_GTT_NUM_TRANSFER_WINDOWS;
> size = (adev->gmc.gart_size >> PAGE_SHIFT) - start;
> drm_mm_init(&mgr->mm, start, size);
> spin_lock_init(&mgr->lock);
> - atomic64_set(&mgr->used, 0);
>
> ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_TT, &mgr->manager);
> ttm_resource_manager_set_used(man, true);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index 1ebb91db2274..9ff4aced5da7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -684,7 +684,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
> ui64 = amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr);
> return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
> case AMDGPU_INFO_GTT_USAGE:
> - ui64 = amdgpu_gtt_mgr_usage(&adev->mman.gtt_mgr);
> + ui64 = ttm_resource_manager_usage(&adev->mman.gtt_mgr.manager);
> return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
> case AMDGPU_INFO_GDS_CONFIG: {
> struct drm_amdgpu_info_gds gds_info;
> @@ -716,7 +716,8 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
> case AMDGPU_INFO_MEMORY: {
> struct drm_amdgpu_memory_info mem;
> struct ttm_resource_manager *gtt_man =
> - ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
> + &adev->mman.gtt_mgr.manager;
> +
> memset(&mem, 0, sizeof(mem));
> mem.vram.total_heap_size = adev->gmc.real_vram_size;
> mem.vram.usable_heap_size = adev->gmc.real_vram_size -
> @@ -741,8 +742,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
> mem.gtt.total_heap_size *= PAGE_SIZE;
> mem.gtt.usable_heap_size = mem.gtt.total_heap_size -
> atomic64_read(&adev->gart_pin_size);
> - mem.gtt.heap_usage =
> - amdgpu_gtt_mgr_usage(&adev->mman.gtt_mgr);
> + mem.gtt.heap_usage = ttm_resource_manager_usage(gtt_man);
> mem.gtt.max_allocation = mem.gtt.usable_heap_size * 3 / 4;
>
> return copy_to_user(out, &mem,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 5661b82d84d4..514754142f69 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -451,7 +451,7 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev,
> if (domain & AMDGPU_GEM_DOMAIN_GTT) {
> man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
>
> - if (size < (man->size << PAGE_SHIFT))
> + if (size < man->size)
> return true;
> else
> goto fail;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> index f8f48be16d80..120b69ec9885 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -52,7 +52,6 @@ struct amdgpu_gtt_mgr {
> struct ttm_resource_manager manager;
> struct drm_mm mm;
> spinlock_t lock;
> - atomic64_t used;
> };
>
> struct amdgpu_preempt_mgr {
> @@ -114,7 +113,6 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev);
> void amdgpu_vram_mgr_fini(struct amdgpu_device *adev);
>
> bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem);
> -uint64_t amdgpu_gtt_mgr_usage(struct amdgpu_gtt_mgr *mgr);
> int amdgpu_gtt_mgr_recover(struct amdgpu_gtt_mgr *mgr);
>
> uint64_t amdgpu_preempt_mgr_usage(struct ttm_resource_manager *man);
> --
> 2.25.1
>
More information about the dri-devel
mailing list