Merge tag 'drm-xe-fixes-2024-11-14' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes
Driver Changes:
- Fix unlock on exec ioctl error path (Matthew Brost)
- Fix hibernation on LNL due to ggtt getting lost
(Matthew Brost / Matthew Auld)
- Fix missing runtime PM in OA release (Ashutosh)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/5ntcf2ssmmvo5dsf2mdcee4guwwmpbm3xrlufgt2pdfmznzjo3@62ygo3bxkock
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index e5f51fd..2a093540 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -886,8 +886,8 @@ int xe_bo_evict_pinned(struct xe_bo *bo)
if (WARN_ON(!xe_bo_is_pinned(bo)))
return -EINVAL;
- if (WARN_ON(!xe_bo_is_vram(bo)))
- return -EINVAL;
+ if (!xe_bo_is_vram(bo))
+ return 0;
ret = ttm_bo_mem_space(&bo->ttm, &placement, &new_mem, &ctx);
if (ret)
@@ -937,6 +937,7 @@ int xe_bo_restore_pinned(struct xe_bo *bo)
.interruptible = false,
};
struct ttm_resource *new_mem;
+ struct ttm_place *place = &bo->placements[0];
int ret;
xe_bo_assert_held(bo);
@@ -947,9 +948,15 @@ int xe_bo_restore_pinned(struct xe_bo *bo)
if (WARN_ON(!xe_bo_is_pinned(bo)))
return -EINVAL;
- if (WARN_ON(xe_bo_is_vram(bo) || !bo->ttm.ttm))
+ if (WARN_ON(xe_bo_is_vram(bo)))
return -EINVAL;
+ if (WARN_ON(!bo->ttm.ttm && !xe_bo_is_stolen(bo)))
+ return -EINVAL;
+
+ if (!mem_type_is_vram(place->mem_type))
+ return 0;
+
ret = ttm_bo_mem_space(&bo->ttm, &bo->placement, &new_mem, &ctx);
if (ret)
return ret;
@@ -1719,6 +1726,7 @@ int xe_bo_pin_external(struct xe_bo *bo)
int xe_bo_pin(struct xe_bo *bo)
{
+ struct ttm_place *place = &bo->placements[0];
struct xe_device *xe = xe_bo_device(bo);
int err;
@@ -1749,21 +1757,21 @@ int xe_bo_pin(struct xe_bo *bo)
*/
if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
bo->flags & XE_BO_FLAG_INTERNAL_TEST)) {
- struct ttm_place *place = &(bo->placements[0]);
-
if (mem_type_is_vram(place->mem_type)) {
xe_assert(xe, place->flags & TTM_PL_FLAG_CONTIGUOUS);
place->fpfn = (xe_bo_addr(bo, 0, PAGE_SIZE) -
vram_region_gpu_offset(bo->ttm.resource)) >> PAGE_SHIFT;
place->lpfn = place->fpfn + (bo->size >> PAGE_SHIFT);
-
- spin_lock(&xe->pinned.lock);
- list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present);
- spin_unlock(&xe->pinned.lock);
}
}
+ if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) {
+ spin_lock(&xe->pinned.lock);
+ list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present);
+ spin_unlock(&xe->pinned.lock);
+ }
+
ttm_bo_pin(&bo->ttm);
/*
@@ -1809,23 +1817,18 @@ void xe_bo_unpin_external(struct xe_bo *bo)
void xe_bo_unpin(struct xe_bo *bo)
{
+ struct ttm_place *place = &bo->placements[0];
struct xe_device *xe = xe_bo_device(bo);
xe_assert(xe, !bo->ttm.base.import_attach);
xe_assert(xe, xe_bo_is_pinned(bo));
- if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
- bo->flags & XE_BO_FLAG_INTERNAL_TEST)) {
- struct ttm_place *place = &(bo->placements[0]);
-
- if (mem_type_is_vram(place->mem_type)) {
- spin_lock(&xe->pinned.lock);
- xe_assert(xe, !list_empty(&bo->pinned_link));
- list_del_init(&bo->pinned_link);
- spin_unlock(&xe->pinned.lock);
- }
+ if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) {
+ spin_lock(&xe->pinned.lock);
+ xe_assert(xe, !list_empty(&bo->pinned_link));
+ list_del_init(&bo->pinned_link);
+ spin_unlock(&xe->pinned.lock);
}
-
ttm_bo_unpin(&bo->ttm);
}
diff --git a/drivers/gpu/drm/xe/xe_bo_evict.c b/drivers/gpu/drm/xe/xe_bo_evict.c
index 541b490..8fb2be0 100644
--- a/drivers/gpu/drm/xe/xe_bo_evict.c
+++ b/drivers/gpu/drm/xe/xe_bo_evict.c
@@ -34,14 +34,22 @@ int xe_bo_evict_all(struct xe_device *xe)
u8 id;
int ret;
- if (!IS_DGFX(xe))
- return 0;
-
/* User memory */
- for (mem_type = XE_PL_VRAM0; mem_type <= XE_PL_VRAM1; ++mem_type) {
+ for (mem_type = XE_PL_TT; mem_type <= XE_PL_VRAM1; ++mem_type) {
struct ttm_resource_manager *man =
ttm_manager_type(bdev, mem_type);
+ /*
+ * On igpu platforms with flat CCS we need to ensure we save and restore any CCS
+ * state since this state lives inside graphics stolen memory which doesn't survive
+ * hibernation.
+ *
+ * This can be further improved by only evicting objects that we know have actually
+ * used a compression enabled PAT index.
+ */
+ if (mem_type == XE_PL_TT && (IS_DGFX(xe) || !xe_device_has_flat_ccs(xe)))
+ continue;
+
if (man) {
ret = ttm_resource_manager_evict_all(bdev, man);
if (ret)
@@ -125,9 +133,6 @@ int xe_bo_restore_kernel(struct xe_device *xe)
struct xe_bo *bo;
int ret;
- if (!IS_DGFX(xe))
- return 0;
-
spin_lock(&xe->pinned.lock);
for (;;) {
bo = list_first_entry_or_null(&xe->pinned.evicted,
@@ -159,7 +164,6 @@ int xe_bo_restore_kernel(struct xe_device *xe)
* should setup the iosys map.
*/
xe_assert(xe, !iosys_map_is_null(&bo->vmap));
- xe_assert(xe, xe_bo_is_vram(bo));
xe_bo_put(bo);
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 756b492..31cca93 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -203,14 +203,14 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
write_locked = false;
}
if (err)
- goto err_syncs;
+ goto err_hw_exec_mode;
if (write_locked) {
err = xe_vm_userptr_pin(vm);
downgrade_write(&vm->lock);
write_locked = false;
if (err)
- goto err_hw_exec_mode;
+ goto err_unlock_list;
}
if (!args->num_batch_buffer) {
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 2804f14f..78823f5 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1206,9 +1206,11 @@ static int xe_oa_release(struct inode *inode, struct file *file)
struct xe_oa_stream *stream = file->private_data;
struct xe_gt *gt = stream->gt;
+ xe_pm_runtime_get(gt_to_xe(gt));
mutex_lock(>->oa.gt_lock);
xe_oa_destroy_locked(stream);
mutex_unlock(>->oa.gt_lock);
+ xe_pm_runtime_put(gt_to_xe(gt));
/* Release the reference the OA stream kept on the driver */
drm_dev_put(>_to_xe(gt)->drm);
