diff options
| author | Yunxiang Li <Yunxiang.Li@amd.com> | 2024-12-19 10:14:11 -0500 |
|---|---|---|
| committer | Christian König <christian.koenig@amd.com> | 2024-12-19 16:56:28 +0100 |
| commit | 74ef9527bd87ead62deabe749a6d867af748d448 (patch) | |
| tree | e2568cbf9df5bb6843547a211bd46548307d43b6 /drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c | |
| parent | a541a6e865ecd8dfd8df6eeb134cc20e7139d329 (diff) | |
drm/amdgpu: track bo memory stats at runtime
Before, every time fdinfo is queried we try to lock all the BOs in the
VM and calculate memory usage from scratch. This works okay if the
fdinfo is rarely read and the VMs don't have a ton of BOs. If either of
these conditions is not true, we get a massive performance hit.
In this new revision, we track the BOs as they change states. This way
when the fdinfo is queried we only need to take the status lock and copy
out the usage stats with minimal impact to the runtime performance. With
this new approach however, we would no longer be able to track active
buffers.
Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241219151411.1150-6-Yunxiang.Li@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c | 18 |
1 files changed, 6 insertions, 12 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c index 7717e3e4f05b..91d638098889 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c @@ -60,7 +60,7 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) struct amdgpu_fpriv *fpriv = file->driver_priv; struct amdgpu_vm *vm = &fpriv->vm; - struct amdgpu_mem_stats stats[__AMDGPU_PL_LAST + 1] = { }; + struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM]; ktime_t usage[AMDGPU_HW_IP_NUM]; const char *pl_name[] = { [TTM_PL_VRAM] = "vram", @@ -72,15 +72,8 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) [AMDGPU_PL_DOORBELL] = "doorbell", }; unsigned int hw_ip, i; - int ret; - - ret = amdgpu_bo_reserve(vm->root.bo, false); - if (ret) - return; - - amdgpu_vm_get_memory(vm, stats, ARRAY_SIZE(stats)); - amdgpu_bo_unreserve(vm->root.bo); + amdgpu_vm_get_memory(vm, stats); amdgpu_ctx_mgr_usage(&fpriv->ctx_mgr, usage); /* @@ -97,7 +90,6 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) drm_print_memory_stats(p, &stats[i].drm, - DRM_GEM_OBJECT_ACTIVE | DRM_GEM_OBJECT_RESIDENT | DRM_GEM_OBJECT_PURGEABLE, pl_name[i]); @@ -115,9 +107,11 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) drm_printf(p, "amd-evicted-vram:\t%llu KiB\n", stats[TTM_PL_VRAM].evicted/1024UL); drm_printf(p, "amd-requested-vram:\t%llu KiB\n", - stats[TTM_PL_VRAM].requested/1024UL); + (stats[TTM_PL_VRAM].drm.shared + + stats[TTM_PL_VRAM].drm.private) / 1024UL); drm_printf(p, "amd-requested-gtt:\t%llu KiB\n", - stats[TTM_PL_TT].requested/1024UL); + (stats[TTM_PL_TT].drm.shared + + stats[TTM_PL_TT].drm.private) / 1024UL); for (hw_ip = 0; hw_ip < AMDGPU_HW_IP_NUM; ++hw_ip) { if (!usage[hw_ip]) |