On Mon, Jun 26, 2017 at 03:39:57PM +0200, Christian König wrote:
> From: Christian König <christian.koenig at amd.com>
>
> Limit the size of the GART table for the system domain.
>
> This saves us a bunch of visible VRAM, but also limitates the maximum BO size we can swap out.
>
> Signed-off-by: Christian König <christian.koenig at amd.com>
Hmm.
On my system, GTT is 4096MiB (1048576 pages). For this, the table takes up
1048576*8 bytes = 8MiB. Reducing GTT to 256MiB (65536 pages) would reduce the
size of the table to 512 KiB. A relatively large saving, to be sure. But in the
grander scheme of things, is saving 7.5MiB (3% of visible VRAM @ 256M) worth
cutting GTT memory by a factor of 16?
John
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 8 ++++++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 6 ++++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 +++---
> 7 files changed, 26 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index ab1dad2..a511029 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -76,6 +76,7 @@
> extern int amdgpu_modeset;
> extern int amdgpu_vram_limit;
> extern int amdgpu_gart_size;
> +extern unsigned amdgpu_gart_sys_limit;
> extern int amdgpu_moverate;
> extern int amdgpu_benchmarking;
> extern int amdgpu_testing;
> @@ -602,6 +603,7 @@ struct amdgpu_mc {
> u64 mc_vram_size;
> u64 visible_vram_size;
> u64 gtt_size;
> + u64 gtt_sys_limit;
> u64 gtt_start;
> u64 gtt_end;
> u64 vram_start;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 44484bb..b6edb83 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -1122,6 +1122,12 @@ static void amdgpu_check_arguments(struct amdgpu_device *adev)
> }
> }
>
> + if (amdgpu_gart_sys_limit < 32) {
> + dev_warn(adev->dev, "gart sys limit (%d) too small\n",
> + amdgpu_gart_sys_limit);
> + amdgpu_gart_sys_limit = 32;
> + }
> +
> amdgpu_check_vm_size(adev);
>
> amdgpu_check_block_size(adev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 5a1d794..907ae5e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -75,6 +75,7 @@
>
> int amdgpu_vram_limit = 0;
> int amdgpu_gart_size = -1; /* auto */
> +unsigned amdgpu_gart_sys_limit = 256;
> int amdgpu_moverate = -1; /* auto */
> int amdgpu_benchmarking = 0;
> int amdgpu_testing = 0;
> @@ -124,6 +125,9 @@ module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
> MODULE_PARM_DESC(gartsize, "Size of PCIE/IGP gart to setup in megabytes (32, 64, etc., -1 = auto)");
> module_param_named(gartsize, amdgpu_gart_size, int, 0600);
>
> +MODULE_PARM_DESC(gartlimit, "GART limit for the system domain in megabytes (default 256)");
> +module_param_named(gartlimit, amdgpu_gart_sys_limit, int, 0600);
> +
> MODULE_PARM_DESC(moverate, "Maximum buffer migration rate in MB/s. (32, 64, etc., -1=auto, 0=1=disabled)");
> module_param_named(moverate, amdgpu_moverate, int, 0600);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> index 8877015..5c6a461 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
> @@ -70,6 +70,9 @@ void amdgpu_gart_set_defaults(struct amdgpu_device *adev)
> adev->mc.mc_vram_size);
> else
> adev->mc.gtt_size = (uint64_t)amdgpu_gart_size << 20;
> +
> + adev->mc.gtt_sys_limit = min((uint64_t)amdgpu_gart_sys_limit << 20,
> + adev->mc.gtt_size);
> }
>
> /**
> @@ -350,8 +353,9 @@ int amdgpu_gart_init(struct amdgpu_device *adev)
> if (r)
> return r;
> /* Compute table size */
> - adev->gart.num_cpu_pages = adev->mc.gtt_size / PAGE_SIZE;
> - adev->gart.num_gpu_pages = adev->mc.gtt_size / AMDGPU_GPU_PAGE_SIZE;
> + adev->gart.num_cpu_pages = adev->mc.gtt_sys_limit / PAGE_SIZE;
> + adev->gart.num_gpu_pages = adev->mc.gtt_sys_limit /
> + AMDGPU_GPU_PAGE_SIZE;
> DRM_INFO("GART: num cpu pages %u, num gpu pages %u\n",
> adev->gart.num_cpu_pages, adev->gart.num_gpu_pages);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> index 96c4493..6eac481 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
> @@ -62,7 +62,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
> /* Maximum bo size is the unpinned gtt size since we use the gtt to
> * handle vram to system pool migrations.
> */
> - max_size = adev->mc.gtt_size - adev->gart_pin_size;
> + max_size = adev->mc.gtt_sys_limit - adev->gart_pin_size;
> if (size > max_size) {
> DRM_DEBUG("Allocation size %ldMb bigger than %ldMb limit\n",
> size >> 20, max_size >> 20);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> index f7d22c4..7609229 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
> @@ -42,13 +42,14 @@ struct amdgpu_gtt_mgr {
> static int amdgpu_gtt_mgr_init(struct ttm_mem_type_manager *man,
> unsigned long p_size)
> {
> + struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
> struct amdgpu_gtt_mgr *mgr;
>
> mgr = kzalloc(sizeof(*mgr), GFP_KERNEL);
> if (!mgr)
> return -ENOMEM;
>
> - drm_mm_init(&mgr->mm, 0, p_size);
> + drm_mm_init(&mgr->mm, 0, adev->mc.gtt_sys_limit >> PAGE_SHIFT);
> spin_lock_init(&mgr->lock);
> mgr->available = p_size;
> man->priv = mgr;
> @@ -95,6 +96,7 @@ int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man,
> const struct ttm_place *place,
> struct ttm_mem_reg *mem)
> {
> + struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
> struct amdgpu_gtt_mgr *mgr = man->priv;
> struct drm_mm_node *node = mem->mm_node;
> enum drm_mm_insert_mode mode;
> @@ -112,7 +114,7 @@ int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man,
> if (place && place->lpfn)
> lpfn = place->lpfn;
> else
> - lpfn = man->size;
> + lpfn = adev->gart.num_cpu_pages;
>
> mode = DRM_MM_INSERT_BEST;
> if (place && place->flags & TTM_PL_FLAG_TOPDOWN)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index e4860ac..1e0fcb6 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -221,7 +221,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
> * allocating address space for the BO.
> */
> abo->placements[i].lpfn =
> - adev->mc.gtt_size >> PAGE_SHIFT;
> + adev->gart.num_cpu_pages;
> }
> }
> break;
> @@ -384,7 +384,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo,
> placement.num_busy_placement = 1;
> placement.busy_placement = &placements;
> placements.fpfn = 0;
> - placements.lpfn = adev->mc.gtt_size >> PAGE_SHIFT;
> + placements.lpfn = adev->gart.num_cpu_pages;
> placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
> r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
> interruptible, no_wait_gpu);
> @@ -431,7 +431,7 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo,
> placement.num_busy_placement = 1;
> placement.busy_placement = &placements;
> placements.fpfn = 0;
> - placements.lpfn = adev->mc.gtt_size >> PAGE_SHIFT;
> + placements.lpfn = adev->gart.num_cpu_pages;
> placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
> r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
> interruptible, no_wait_gpu);
> --
> 2.7.4
>
