aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c66
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h11
3 files changed, 57 insertions, 23 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index fd3902983195..b62bbe71662d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1259,6 +1259,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
union drm_amdgpu_cs *cs = data;
struct amdgpu_cs_parser parser = {};
bool reserved_buffers = false;
+ struct amdgpu_fpriv *fpriv;
int i, r;
if (!adev->accel_working)
@@ -1303,6 +1304,8 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
r = amdgpu_cs_submit(&parser, cs);
+ fpriv = filp->driver_priv;
+ amdgpu_vm_move_to_lru_tail(adev, &fpriv->vm);
out:
amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d12bffa5f70c..7b0fdf5c79f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -268,6 +268,47 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
}
/**
+ * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU
+ *
+ * @adev: amdgpu device pointer
+ * @vm: vm providing the BOs
+ *
+ * Move all BOs to the end of LRU and remember their positions to put them
+ * together.
+ */
+void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
+ struct amdgpu_vm *vm)
+{
+ struct ttm_bo_global *glob = adev->mman.bdev.glob;
+ struct amdgpu_vm_bo_base *bo_base;
+
+ if (vm->bulk_moveable) {
+ spin_lock(&glob->lru_lock);
+ ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
+ spin_unlock(&glob->lru_lock);
+ return;
+ }
+
+ memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
+
+ spin_lock(&glob->lru_lock);
+ list_for_each_entry(bo_base, &vm->idle, vm_status) {
+ struct amdgpu_bo *bo = bo_base->bo;
+
+ if (!bo->parent)
+ continue;
+
+ ttm_bo_move_to_lru_tail(&bo->tbo, &vm->lru_bulk_move);
+ if (bo->shadow)
+ ttm_bo_move_to_lru_tail(&bo->shadow->tbo,
+ &vm->lru_bulk_move);
+ }
+ spin_unlock(&glob->lru_lock);
+
+ vm->bulk_moveable = true;
+}
+
+/**
* amdgpu_vm_validate_pt_bos - validate the page table BOs
*
* @adev: amdgpu device pointer
@@ -284,10 +325,11 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
int (*validate)(void *p, struct amdgpu_bo *bo),
void *param)
{
- struct ttm_bo_global *glob = adev->mman.bdev.glob;
struct amdgpu_vm_bo_base *bo_base, *tmp;
int r = 0;
+ vm->bulk_moveable &= list_empty(&vm->evicted);
+
list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
struct amdgpu_bo *bo = bo_base->bo;
@@ -295,14 +337,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
if (r)
break;
- if (bo->parent) {
- spin_lock(&glob->lru_lock);
- ttm_bo_move_to_lru_tail(&bo->tbo, NULL);
- if (bo->shadow)
- ttm_bo_move_to_lru_tail(&bo->shadow->tbo, NULL);
- spin_unlock(&glob->lru_lock);
- }
-
if (bo->tbo.type != ttm_bo_type_kernel) {
spin_lock(&vm->moved_lock);
list_move(&bo_base->vm_status, &vm->moved);
@@ -312,19 +346,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
}
}
- spin_lock(&glob->lru_lock);
- list_for_each_entry(bo_base, &vm->idle, vm_status) {
- struct amdgpu_bo *bo = bo_base->bo;
-
- if (!bo->parent)
- continue;
-
- ttm_bo_move_to_lru_tail(&bo->tbo, NULL);
- if (bo->shadow)
- ttm_bo_move_to_lru_tail(&bo->shadow->tbo, NULL);
- }
- spin_unlock(&glob->lru_lock);
-
return r;
}
@@ -2590,6 +2611,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
return r;
vm->pte_support_ats = false;
+ vm->bulk_moveable = true;
if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE) {
vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 1162c2bf3138..14bafe771c9b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -29,6 +29,7 @@
#include <linux/rbtree.h>
#include <drm/gpu_scheduler.h>
#include <drm/drm_file.h>
+#include <drm/ttm/ttm_bo_driver.h>
#include "amdgpu_sync.h"
#include "amdgpu_ring.h"
@@ -247,6 +248,11 @@ struct amdgpu_vm {
/* Some basic info about the task */
struct amdgpu_task_info task_info;
+
+ /* Store positions of group of BOs */
+ struct ttm_lru_bulk_move lru_bulk_move;
+ /* mark whether can do the bulk move */
+ bool bulk_moveable;
};
struct amdgpu_vm_manager {
@@ -354,8 +360,11 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
- struct amdgpu_task_info *task_info);
+ struct amdgpu_task_info *task_info);
void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
+void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
+ struct amdgpu_vm *vm);
+
#endif