Re: [PATCH 3/3] drm/amdgpu: improve VM state machine documentation

2018-09-02 Thread Zhang, Jerry (Junwei)

On 09/02/2018 02:05 AM, Christian König wrote:

Since we have a lot of FAQ on the VM state machine try to improve the
documentation by adding functions for each state move.

Signed-off-by: Christian König 
---
  drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 139 +
  1 file changed, 108 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 65977e7c94dc..ce252ead2ee4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -204,6 +204,95 @@ static unsigned amdgpu_vm_bo_size(struct amdgpu_device 
*adev, unsigned level)
return AMDGPU_GPU_PAGE_ALIGN(amdgpu_vm_num_entries(adev, level) * 8);
  }

+/**
+ * amdgpu_vm_bo_evicted - vm_bo is evicted
+ *
+ * @vm_bo: vm_bo which is evicted
+ *
+ * State for PDs/PTs and per VM BOs which are not at the location they should
+ * be.
+ */
+static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
+{
+   struct amdgpu_vm *vm = vm_bo->vm;
+   struct amdgpu_bo *bo = vm_bo->bo;
+
+   vm_bo->moved = true;
+   if (bo->tbo.type == ttm_bo_type_kernel)
+   list_move(&vm_bo->vm_status, &vm->evicted);
+   else
+   list_move_tail(&vm_bo->vm_status, &vm->evicted);
+}
+
+/**
+ * amdgpu_vm_bo_relocated - vm_bo is reloacted
+ *
+ * @vm_bo: vm_bo which is relocated
+ *
+ * State for PDs/PTs which needs to update their parent PD.
+ */
+static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
+{
+   list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
+}
+
+/**
+ * amdgpu_vm_bo_moved - vm_bo is moved
+ *
+ * @vm_bo: vm_bo which is moved
+ *
+ * State for per VM BOs which are moved, but that change is not yet reflected
+ * in the page tables.
+ */
+static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
+{
+   list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
+}
+
+/**
+ * amdgpu_vm_bo_idle - vm_bo is idle
+ *
+ * @vm_bo: vm_bo which is now idle
+ *
+ * State for PDs/PTs and per VM BOs which have gone through the state machine
+ * and are now idle.
+ */
+static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
+{
+   list_move(&vm_bo->vm_status, &vm_bo->vm->idle);
+   vm_bo->moved = false;
+}
+
+/**
+ * amdgpu_vm_bo_invalidated - vm_bo is invalidated
+ *
+ * @vm_bo: vm_bo which is now invalidated
+ *
+ * State for normal BOs which are invalidated and that change not yet reflected
+ * in the PTs.
+ */
+static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
+{
+   spin_lock(&vm_bo->vm->invalidated_lock);
+   list_move(&vm_bo->vm_status, &vm_bo->vm->idle);


Is that a typo? move to vm->invalidated?

Apart from that, it's
Reviewed-by: Junwei Zhang 

Regards,
Jerry


+   spin_unlock(&vm_bo->vm->invalidated_lock);
+}
+
+/**
+ * amdgpu_vm_bo_done - vm_bo is done
+ *
+ * @vm_bo: vm_bo which is now done
+ *
+ * State for normal BOs which are invalidated and that change has been updated
+ * in the PTs.
+ */
+static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo)
+{
+   spin_lock(&vm_bo->vm->invalidated_lock);
+   list_del_init(&vm_bo->vm_status);
+   spin_unlock(&vm_bo->vm->invalidated_lock);
+}
+
  /**
   * amdgpu_vm_bo_base_init - Adds bo to the list of bos associated with the vm
   *
@@ -232,9 +321,9 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base 
*base,

vm->bulk_moveable = false;
if (bo->tbo.type == ttm_bo_type_kernel)
-   list_move(&base->vm_status, &vm->relocated);
+   amdgpu_vm_bo_relocated(base);
else
-   list_move(&base->vm_status, &vm->idle);
+   amdgpu_vm_bo_idle(base);

if (bo->preferred_domains &
amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type))
@@ -245,8 +334,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base 
*base,
 * is currently evicted. add the bo to the evicted list to make sure it
 * is validated on next vm use to avoid fault.
 * */
-   list_move_tail(&base->vm_status, &vm->evicted);
-   base->moved = true;
+   amdgpu_vm_bo_evicted(base);
  }

  /**
@@ -342,7 +430,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, 
struct amdgpu_vm *vm,
break;

if (bo->tbo.type != ttm_bo_type_kernel) {
-   list_move(&bo_base->vm_status, &vm->moved);
+   amdgpu_vm_bo_moved(bo_base);
} else {
if (vm->use_cpu_for_update)
r = amdgpu_bo_kmap(bo, NULL);
@@ -350,7 +438,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, 
struct amdgpu_vm *vm,
r = amdgpu_ttm_alloc_gart(&bo->tbo);
if (r)
break;
-   list_move(&bo_base->vm_status, &vm->relocated);
+   amdgpu_vm_bo_reloc

[PATCH 3/3] drm/amdgpu: improve VM state machine documentation

2018-09-01 Thread Christian König
Since we have a lot of FAQ on the VM state machine try to improve the
documentation by adding functions for each state move.

Signed-off-by: Christian König 
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 139 +
 1 file changed, 108 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 65977e7c94dc..ce252ead2ee4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -204,6 +204,95 @@ static unsigned amdgpu_vm_bo_size(struct amdgpu_device 
*adev, unsigned level)
return AMDGPU_GPU_PAGE_ALIGN(amdgpu_vm_num_entries(adev, level) * 8);
 }
 
+/**
+ * amdgpu_vm_bo_evicted - vm_bo is evicted
+ *
+ * @vm_bo: vm_bo which is evicted
+ *
+ * State for PDs/PTs and per VM BOs which are not at the location they should
+ * be.
+ */
+static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
+{
+   struct amdgpu_vm *vm = vm_bo->vm;
+   struct amdgpu_bo *bo = vm_bo->bo;
+
+   vm_bo->moved = true;
+   if (bo->tbo.type == ttm_bo_type_kernel)
+   list_move(&vm_bo->vm_status, &vm->evicted);
+   else
+   list_move_tail(&vm_bo->vm_status, &vm->evicted);
+}
+
+/**
+ * amdgpu_vm_bo_relocated - vm_bo is reloacted
+ *
+ * @vm_bo: vm_bo which is relocated
+ *
+ * State for PDs/PTs which needs to update their parent PD.
+ */
+static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
+{
+   list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
+}
+
+/**
+ * amdgpu_vm_bo_moved - vm_bo is moved
+ *
+ * @vm_bo: vm_bo which is moved
+ *
+ * State for per VM BOs which are moved, but that change is not yet reflected
+ * in the page tables.
+ */
+static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
+{
+   list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
+}
+
+/**
+ * amdgpu_vm_bo_idle - vm_bo is idle
+ *
+ * @vm_bo: vm_bo which is now idle
+ *
+ * State for PDs/PTs and per VM BOs which have gone through the state machine
+ * and are now idle.
+ */
+static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
+{
+   list_move(&vm_bo->vm_status, &vm_bo->vm->idle);
+   vm_bo->moved = false;
+}
+
+/**
+ * amdgpu_vm_bo_invalidated - vm_bo is invalidated
+ *
+ * @vm_bo: vm_bo which is now invalidated
+ *
+ * State for normal BOs which are invalidated and that change not yet reflected
+ * in the PTs.
+ */
+static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
+{
+   spin_lock(&vm_bo->vm->invalidated_lock);
+   list_move(&vm_bo->vm_status, &vm_bo->vm->idle);
+   spin_unlock(&vm_bo->vm->invalidated_lock);
+}
+
+/**
+ * amdgpu_vm_bo_done - vm_bo is done
+ *
+ * @vm_bo: vm_bo which is now done
+ *
+ * State for normal BOs which are invalidated and that change has been updated
+ * in the PTs.
+ */
+static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo)
+{
+   spin_lock(&vm_bo->vm->invalidated_lock);
+   list_del_init(&vm_bo->vm_status);
+   spin_unlock(&vm_bo->vm->invalidated_lock);
+}
+
 /**
  * amdgpu_vm_bo_base_init - Adds bo to the list of bos associated with the vm
  *
@@ -232,9 +321,9 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base 
*base,
 
vm->bulk_moveable = false;
if (bo->tbo.type == ttm_bo_type_kernel)
-   list_move(&base->vm_status, &vm->relocated);
+   amdgpu_vm_bo_relocated(base);
else
-   list_move(&base->vm_status, &vm->idle);
+   amdgpu_vm_bo_idle(base);
 
if (bo->preferred_domains &
amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type))
@@ -245,8 +334,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base 
*base,
 * is currently evicted. add the bo to the evicted list to make sure it
 * is validated on next vm use to avoid fault.
 * */
-   list_move_tail(&base->vm_status, &vm->evicted);
-   base->moved = true;
+   amdgpu_vm_bo_evicted(base);
 }
 
 /**
@@ -342,7 +430,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, 
struct amdgpu_vm *vm,
break;
 
if (bo->tbo.type != ttm_bo_type_kernel) {
-   list_move(&bo_base->vm_status, &vm->moved);
+   amdgpu_vm_bo_moved(bo_base);
} else {
if (vm->use_cpu_for_update)
r = amdgpu_bo_kmap(bo, NULL);
@@ -350,7 +438,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, 
struct amdgpu_vm *vm,
r = amdgpu_ttm_alloc_gart(&bo->tbo);
if (r)
break;
-   list_move(&bo_base->vm_status, &vm->relocated);
+   amdgpu_vm_bo_relocated(bo_base);
}
}
 
@@ -1121,8 +1209,7 @@ int amdgpu_vm_update_directories(struct amdgpu_device 
*adev,
bo_base = list_fir