drm/xe/guc: Allocate GuC data structures in system memory for initial load

GuC load will need to happen at an earlier point in probe, where local
memory is not yet available. Use system memory for GuC data structures
used for initial "hwconfig" load, and realloc at a later,
"post-hwconfig" load if needed, when local memory is available.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240219130530.1406044-1-michal.winiarski@intel.com

7 files changed, 71 insertions, 4 deletions

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 9d7ad67bd7b4..76dfaf1cd200 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1612,6 +1612,38 @@ struct xe_bo *xe_managed_bo_create_from_data(struct xe_device *xe, struct xe_til
 	return bo;
 }
 
+/**
+ * xe_managed_bo_reinit_in_vram
+ * @xe: xe device
+ * @tile: Tile where the new buffer will be created
+ * @src: Managed buffer object allocated in system memory
+ *
+ * Replace a managed src buffer object allocated in system memory with a new
+ * one allocated in vram, copying the data between them.
+ * Buffer object in VRAM is not going to have the same GGTT address, the caller
+ * is responsible for making sure that any old references to it are updated.
+ *
+ * Returns 0 for success, negative error code otherwise.
+ */
+int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, struct xe_bo **src)
+{
+	struct xe_bo *bo;
+
+	xe_assert(xe, IS_DGFX(xe));
+	xe_assert(xe, !(*src)->vmap.is_iomem);
+
+	bo = xe_managed_bo_create_from_data(xe, tile, (*src)->vmap.vaddr, (*src)->size,
+					    XE_BO_CREATE_VRAM_IF_DGFX(tile) |
+					    XE_BO_CREATE_GGTT_BIT);
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
+
+	drmm_release_action(&xe->drm, __xe_bo_unpin_map_no_vm, *src);
+	*src = bo;
+
+	return 0;
+}
+
 /*
  * XXX: This is in the VM bind data path, likely should calculate this once and
  * store, with a recalculation if the BO is moved.
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 7e49e670d91e..c59ad15961ce 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -129,6 +129,7 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile
 					   size_t size, u32 flags);
 struct xe_bo *xe_managed_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
 					     const void *data, size_t size, u32 flags);
+int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, struct xe_bo **src);
 
 int xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo,
 			      u32 bo_flags);
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 868208a39829..8c10546e387d 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -272,6 +272,34 @@ void xe_guc_comm_init_early(struct xe_guc *guc)
 		guc->notify_reg = GUC_HOST_INTERRUPT;
 }
 
+static int xe_guc_realloc_post_hwconfig(struct xe_guc *guc)
+{
+	struct xe_tile *tile = gt_to_tile(guc_to_gt(guc));
+	struct xe_device *xe = guc_to_xe(guc);
+	int ret;
+
+	if (!IS_DGFX(guc_to_xe(guc)))
+		return 0;
+
+	ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->fw.bo);
+	if (ret)
+		return ret;
+
+	ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->log.bo);
+	if (ret)
+		return ret;
+
+	ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->ads.bo);
+	if (ret)
+		return ret;
+
+	ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->ct.bo);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 int xe_guc_init(struct xe_guc *guc)
 {
 	struct xe_device *xe = guc_to_xe(guc);
@@ -331,6 +359,12 @@ out:
  */
 int xe_guc_init_post_hwconfig(struct xe_guc *guc)
 {
+	int ret;
+
+	ret = xe_guc_realloc_post_hwconfig(guc);
+	if (ret)
+		return ret;
+
 	guc_init_params_post_hwconfig(guc);
 
 	return xe_guc_ads_init_post_hwconfig(&guc->ads);
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 390e6f1bf4e1..6ad4c1a90a78 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -273,7 +273,7 @@ int xe_guc_ads_init(struct xe_guc_ads *ads)
 	ads->regset_size = calculate_regset_size(gt);
 
 	bo = xe_managed_bo_create_pin_map(xe, tile, guc_ads_size(ads) + MAX_GOLDEN_LRC_SIZE,
-					  XE_BO_CREATE_VRAM_IF_DGFX(tile) |
+					  XE_BO_CREATE_SYSTEM_BIT |
 					  XE_BO_CREATE_GGTT_BIT);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index f3d356383ced..355edd4d758a 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -155,7 +155,7 @@ int xe_guc_ct_init(struct xe_guc_ct *ct)
 	primelockdep(ct);
 
 	bo = xe_managed_bo_create_pin_map(xe, tile, guc_ct_size(),
-					  XE_BO_CREATE_VRAM_IF_DGFX(tile) |
+					  XE_BO_CREATE_SYSTEM_BIT |
 					  XE_BO_CREATE_GGTT_BIT);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/xe/xe_guc_hwconfig.c b/drivers/gpu/drm/xe/xe_guc_hwconfig.c
index 2a13a00917f8..ea49f3885c10 100644
--- a/drivers/gpu/drm/xe/xe_guc_hwconfig.c
+++ b/drivers/gpu/drm/xe/xe_guc_hwconfig.c
@@ -78,7 +78,7 @@ int xe_guc_hwconfig_init(struct xe_guc *guc)
 		return -EINVAL;
 
 	bo = xe_managed_bo_create_pin_map(xe, tile, PAGE_ALIGN(size),
-					  XE_BO_CREATE_VRAM_IF_DGFX(tile) |
+					  XE_BO_CREATE_SYSTEM_BIT |
 					  XE_BO_CREATE_GGTT_BIT);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index bcd2f4d34081..45135c3520e5 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -84,7 +84,7 @@ int xe_guc_log_init(struct xe_guc_log *log)
 	struct xe_bo *bo;
 
 	bo = xe_managed_bo_create_pin_map(xe, tile, guc_log_size(),
-					  XE_BO_CREATE_VRAM_IF_DGFX(tile) |
+					  XE_BO_CREATE_SYSTEM_BIT |
 					  XE_BO_CREATE_GGTT_BIT);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);