drm/xe: Move GGTT from GT to tile

The GGTT exists at the tile level.  When a tile contains multiple GTs,
they share the same GGTT.

v2:
 - Include some changes that were mis-squashed into the VRAM patch.
   (Gustavo)

Cc: Gustavo Sousa <gustavo.sousa@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Acked-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20230601215244.678611-9-matthew.d.roper@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

13 files changed, 125 insertions, 47 deletions

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index a685e39d6b44..c914d02d8a8c 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -101,6 +101,7 @@ xe-y += xe_bb.o \
 	xe_sched_job.o \
 	xe_step.o \
 	xe_sync.o \
+	xe_tile.o \
 	xe_trace.o \
 	xe_ttm_sys_mgr.o \
 	xe_ttm_stolen_mgr.o \
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index e766f8955718..915d4c4b15c4 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -964,7 +964,7 @@ static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo)
 	WARN_ON(!list_empty(&bo->vmas));
 
 	if (bo->ggtt_node.size)
-		xe_ggtt_remove_bo(bo->gt->mem.ggtt, bo);
+		xe_ggtt_remove_bo(gt_to_tile(bo->gt)->mem.ggtt, bo);
 
 	if (bo->vm && xe_bo_is_user(bo))
 		xe_vm_put(bo->vm);
@@ -1242,9 +1242,9 @@ xe_bo_create_locked_range(struct xe_device *xe,
 
 		if (flags & XE_BO_CREATE_STOLEN_BIT &&
 		    flags & XE_BO_FIXED_PLACEMENT_BIT) {
-			err = xe_ggtt_insert_bo_at(gt->mem.ggtt, bo, start);
+			err = xe_ggtt_insert_bo_at(gt_to_tile(gt)->mem.ggtt, bo, start);
 		} else {
-			err = xe_ggtt_insert_bo(gt->mem.ggtt, bo);
+			err = xe_ggtt_insert_bo(gt_to_tile(gt)->mem.ggtt, bo);
 		}
 		if (err)
 			goto err_unlock_put_bo;
diff --git a/drivers/gpu/drm/xe/xe_bo_evict.c b/drivers/gpu/drm/xe/xe_bo_evict.c
index 6642c5f52009..a72963c54bf3 100644
--- a/drivers/gpu/drm/xe/xe_bo_evict.c
+++ b/drivers/gpu/drm/xe/xe_bo_evict.c
@@ -149,9 +149,11 @@ int xe_bo_restore_kernel(struct xe_device *xe)
 		}
 
 		if (bo->flags & XE_BO_CREATE_GGTT_BIT) {
-			mutex_lock(&bo->gt->mem.ggtt->lock);
-			xe_ggtt_map_bo(bo->gt->mem.ggtt, bo);
-			mutex_unlock(&bo->gt->mem.ggtt->lock);
+			struct xe_tile *tile = gt_to_tile(bo->gt);
+
+			mutex_lock(&tile->mem.ggtt->lock);
+			xe_ggtt_map_bo(tile->mem.ggtt, bo);
+			mutex_unlock(&tile->mem.ggtt->lock);
 		}
 
 		/*
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 2c65eb84e6e9..0657842d8db2 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -27,6 +27,7 @@
 #include "xe_pcode.h"
 #include "xe_pm.h"
 #include "xe_query.h"
+#include "xe_tile.h"
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_ttm_sys_mgr.h"
 #include "xe_vm.h"
@@ -237,14 +238,19 @@ static void xe_device_sanitize(struct drm_device *drm, void *arg)
 
 int xe_device_probe(struct xe_device *xe)
 {
+	struct xe_tile *tile;
 	struct xe_gt *gt;
 	int err;
 	u8 id;
 
 	xe->info.mem_region_mask = 1;
 
-	for_each_gt(gt, xe, id) {
-		err = xe_gt_alloc(xe, gt);
+	for_each_tile(tile, xe, id) {
+		err = xe_tile_alloc(tile);
+		if (err)
+			return err;
+
+		err = xe_gt_alloc(xe, &tile->primary_gt);
 		if (err)
 			return err;
 	}
@@ -275,8 +281,12 @@ int xe_device_probe(struct xe_device *xe)
 
 	xe_ttm_sys_mgr_init(xe);
 
-	for_each_gt(gt, xe, id) {
-		err = xe_gt_init_noalloc(gt);
+	for_each_tile(tile, xe, id) {
+		err = xe_tile_init_noalloc(tile);
+		if (err)
+			goto err_irq_shutdown;
+
+		err = xe_gt_init_noalloc(&tile->primary_gt);
 		if (err)
 			goto err_irq_shutdown;
 	}
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 107a947a7361..358b70ae888d 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -17,6 +17,8 @@
 #include "xe_platform_types.h"
 #include "xe_step_types.h"
 
+struct xe_ggtt;
+
 #define XE_BO_INVALID_OFFSET	LONG_MAX
 
 #define GRAPHICS_VER(xe) ((xe)->info.graphics_verx100 / 100)
@@ -91,6 +93,12 @@ struct xe_tile {
 		/** @regs: pointer to tile's MMIO space (starting with registers) */
 		void *regs;
 	} mmio;
+
+	/** @mem: memory management info for tile */
+	struct {
+		/** @ggtt: Global graphics translation table */
+		struct xe_ggtt *ggtt;
+	} mem;
 };
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index cd8ada94e688..ff70a01f1591 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -90,24 +90,19 @@ static void ggtt_fini_noalloc(struct drm_device *drm, void *arg)
 	xe_bo_unpin_map_no_vm(ggtt->scratch);
 }
 
-int xe_ggtt_init_noalloc(struct xe_gt *gt, struct xe_ggtt *ggtt)
+int xe_ggtt_init_noalloc(struct xe_ggtt *ggtt)
 {
-	struct xe_device *xe = gt_to_xe(gt);
-	struct xe_tile *tile = gt_to_tile(gt);
+	struct xe_device *xe = tile_to_xe(ggtt->tile);
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	unsigned int gsm_size;
 
-	XE_BUG_ON(xe_gt_is_media_type(gt));
-
-	ggtt->gt = gt;
-
 	gsm_size = probe_gsm_size(pdev);
 	if (gsm_size == 0) {
 		drm_err(&xe->drm, "Hardware reported no preallocated GSM\n");
 		return -ENOMEM;
 	}
 
-	ggtt->gsm = tile->mmio.regs + SZ_8M;
+	ggtt->gsm = ggtt->tile->mmio.regs + SZ_8M;
 	ggtt->size = (gsm_size / 8) * (u64) XE_PAGE_SIZE;
 
 	if (IS_DGFX(xe) && xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K)
@@ -143,19 +138,20 @@ static void xe_ggtt_initial_clear(struct xe_ggtt *ggtt)
 	u64 start, end;
 
 	/* Display may have allocated inside ggtt, so be careful with clearing here */
-	xe_device_mem_access_get(gt_to_xe(ggtt->gt));
+	xe_device_mem_access_get(tile_to_xe(ggtt->tile));
 	mutex_lock(&ggtt->lock);
 	drm_mm_for_each_hole(hole, &ggtt->mm, start, end)
 		xe_ggtt_clear(ggtt, start, end - start);
 
-	xe_ggtt_invalidate(ggtt->gt);
+	xe_ggtt_invalidate(ggtt);
 	mutex_unlock(&ggtt->lock);
-	xe_device_mem_access_put(gt_to_xe(ggtt->gt));
+	xe_device_mem_access_put(tile_to_xe(ggtt->tile));
 }
 
-int xe_ggtt_init(struct xe_gt *gt, struct xe_ggtt *ggtt)
+int xe_ggtt_init(struct xe_ggtt *ggtt)
 {
-	struct xe_device *xe = gt_to_xe(gt);
+	struct xe_device *xe = tile_to_xe(ggtt->tile);
+	struct xe_gt *gt = &ggtt->tile->primary_gt;
 	unsigned int flags;
 	int err;
 
@@ -195,8 +191,14 @@ err:
 #define PVC_GUC_TLB_INV_DESC1			XE_REG(0xcf80)
 #define   PVC_GUC_TLB_INV_DESC1_INVALIDATE	REG_BIT(6)
 
-void xe_ggtt_invalidate(struct xe_gt *gt)
+void xe_ggtt_invalidate(struct xe_ggtt *ggtt)
 {
+	/*
+	 * TODO: Loop over each GT in tile once media GT support is
+	 * re-added
+	 */
+	struct xe_gt *gt = &ggtt->tile->primary_gt;
+
 	/* TODO: vfunc for GuC vs. non-GuC */
 
 	if (gt->uc.guc.submission_state.enabled) {
@@ -269,7 +271,7 @@ void xe_ggtt_map_bo(struct xe_ggtt *ggtt, struct xe_bo *bo)
 		xe_ggtt_set_pte(ggtt, start + offset, pte);
 	}
 
-	xe_ggtt_invalidate(ggtt->gt);
+	xe_ggtt_invalidate(ggtt);
 }
 
 static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
@@ -287,14 +289,14 @@ static int __xe_ggtt_insert_bo_at(struct xe_ggtt *ggtt, struct xe_bo *bo,
 	if (err)
 		return err;
 
-	xe_device_mem_access_get(gt_to_xe(ggtt->gt));
+	xe_device_mem_access_get(tile_to_xe(ggtt->tile));
 	mutex_lock(&ggtt->lock);
 	err = drm_mm_insert_node_in_range(&ggtt->mm, &bo->ggtt_node, bo->size,
 					  alignment, 0, start, end, 0);
 	if (!err)
 		xe_ggtt_map_bo(ggtt, bo);
 	mutex_unlock(&ggtt->lock);
-	xe_device_mem_access_put(gt_to_xe(ggtt->gt));
+	xe_device_mem_access_put(tile_to_xe(ggtt->tile));
 
 	return err;
 }
@@ -323,17 +325,17 @@ int xe_ggtt_insert_bo(struct xe_ggtt *ggtt, struct xe_bo *bo)
 
 void xe_ggtt_remove_node(struct xe_ggtt *ggtt, struct drm_mm_node *node)
 {
-	xe_device_mem_access_get(gt_to_xe(ggtt->gt));
+	xe_device_mem_access_get(tile_to_xe(ggtt->tile));
 	mutex_lock(&ggtt->lock);
 
 	xe_ggtt_clear(ggtt, node->start, node->size);
 	drm_mm_remove_node(node);
 	node->size = 0;
 
-	xe_ggtt_invalidate(ggtt->gt);
+	xe_ggtt_invalidate(ggtt);
 
 	mutex_unlock(&ggtt->lock);
-	xe_device_mem_access_put(gt_to_xe(ggtt->gt));
+	xe_device_mem_access_put(tile_to_xe(ggtt->tile));
 }
 
 void xe_ggtt_remove_bo(struct xe_ggtt *ggtt, struct xe_bo *bo)
diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h
index 3469aa2b1a02..8e7360926bea 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.h
+++ b/drivers/gpu/drm/xe/xe_ggtt.h
@@ -12,9 +12,9 @@ struct drm_printer;
 
 u64 xe_ggtt_pte_encode(struct xe_bo *bo, u64 bo_offset);
 void xe_ggtt_set_pte(struct xe_ggtt *ggtt, u64 addr, u64 pte);
-void xe_ggtt_invalidate(struct xe_gt *gt);
-int xe_ggtt_init_noalloc(struct xe_gt *gt, struct xe_ggtt *ggtt);
-int xe_ggtt_init(struct xe_gt *gt, struct xe_ggtt *ggtt);
+void xe_ggtt_invalidate(struct xe_ggtt *ggtt);
+int xe_ggtt_init_noalloc(struct xe_ggtt *ggtt);
+int xe_ggtt_init(struct xe_ggtt *ggtt);
 void xe_ggtt_printk(struct xe_ggtt *ggtt, const char *prefix);
 
 int xe_ggtt_insert_special_node(struct xe_ggtt *ggtt, struct drm_mm_node *node,
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index ea70aaef4b31..d34b3e733945 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -12,7 +12,7 @@ struct xe_bo;
 struct xe_gt;
 
 struct xe_ggtt {
-	struct xe_gt *gt;
+	struct xe_tile *tile;
 
 	u64 size;
 
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 18eda5b1377f..0f07f810bb1f 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -67,11 +67,6 @@ int xe_gt_alloc(struct xe_device *xe, struct xe_gt *gt)
 	XE_BUG_ON(gt->info.type == XE_GT_TYPE_UNINITIALIZED);
 
 	if (!xe_gt_is_media_type(gt)) {
-		gt->mem.ggtt = drmm_kzalloc(drm, sizeof(*gt->mem.ggtt),
-					    GFP_KERNEL);
-		if (!gt->mem.ggtt)
-			return -ENOMEM;
-
 		gt->mem.vram_mgr = drmm_kzalloc(drm, sizeof(*gt->mem.vram_mgr),
 						GFP_KERNEL);
 		if (!gt->mem.vram_mgr)
@@ -80,7 +75,6 @@ int xe_gt_alloc(struct xe_device *xe, struct xe_gt *gt)
 	} else {
 		struct xe_gt *full_gt = xe_find_full_gt(gt);
 
-		gt->mem.ggtt = full_gt->mem.ggtt;
 		gt->mem.vram_mgr = full_gt->mem.vram_mgr;
 	}
 
@@ -354,8 +348,6 @@ int xe_gt_init_noalloc(struct xe_gt *gt)
 	if (err)
 		goto err_force_wake;
 
-	err = xe_ggtt_init_noalloc(gt, gt->mem.ggtt);
-
 err_force_wake:
 	err2 = xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
 	XE_WARN_ON(err2);
@@ -376,7 +368,7 @@ static int gt_fw_domain_init(struct xe_gt *gt)
 	xe_pat_init(gt);
 
 	if (!xe_gt_is_media_type(gt)) {
-		err = xe_ggtt_init(gt, gt->mem.ggtt);
+		err = xe_ggtt_init(gt_to_tile(gt)->mem.ggtt);
 		if (err)
 			goto err_force_wake;
 	}
diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 339ecd5fad9b..1114254bc519 100644
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -98,7 +98,7 @@ static int ggtt(struct seq_file *m, void *data)
 	struct xe_gt *gt = node_to_gt(m->private);
 	struct drm_printer p = drm_seq_file_printer(m);
 
-	return xe_ggtt_dump(gt->mem.ggtt, &p);
+	return xe_ggtt_dump(gt_to_tile(gt)->mem.ggtt, &p);
 }
 
 static int register_save_restore(struct seq_file *m, void *data)
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 81e6ab0c77e0..c06a0b27d6fc 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -14,7 +14,6 @@
 #include "xe_uc_types.h"
 
 struct xe_engine_ops;
-struct xe_ggtt;
 struct xe_migrate;
 struct xe_ring_ops;
 struct xe_ttm_gtt_mgr;
@@ -176,8 +175,6 @@ struct xe_gt {
 		} vram;
 		/** @vram_mgr: VRAM TTM manager */
 		struct xe_ttm_vram_mgr *vram_mgr;
-		/** @ggtt: Global graphics translation table */
-		struct xe_ggtt *ggtt;
 	} mem;
 
 	/** @reset: state for GT resets */
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
new file mode 100644
index 000000000000..7ef594f301ca
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2023 Intel Corporation
+ */
+
+#include <drm/drm_managed.h>
+
+#include "xe_device.h"
+#include "xe_ggtt.h"
+#include "xe_tile.h"
+#include "xe_ttm_vram_mgr.h"
+
+/**
+ * xe_tile_alloc - Perform per-tile memory allocation
+ * @tile: Tile to perform allocations for
+ *
+ * Allocates various per-tile data structures using DRM-managed allocations.
+ * Does not touch the hardware.
+ *
+ * Returns -ENOMEM if allocations fail, otherwise 0.
+ */
+int xe_tile_alloc(struct xe_tile *tile)
+{
+	struct drm_device *drm = &tile_to_xe(tile)->drm;
+
+	tile->mem.ggtt = drmm_kzalloc(drm, sizeof(*tile->mem.ggtt),
+				      GFP_KERNEL);
+	if (!tile->mem.ggtt)
+		return -ENOMEM;
+	tile->mem.ggtt->tile = tile;
+
+	return 0;
+}
+
+/**
+ * xe_tile_init_noalloc - Init tile up to the point where allocations can happen.
+ * @tile: The tile to initialize.
+ *
+ * This function prepares the tile to allow memory allocations to VRAM, but is
+ * not allowed to allocate memory itself. This state is useful for display
+ * readout, because the inherited display framebuffer will otherwise be
+ * overwritten as it is usually put at the start of VRAM.
+ *
+ * Note that since this is tile initialization, it should not perform any
+ * GT-specific operations, and thus does not need to hold GT forcewake.
+ *
+ * Returns: 0 on success, negative error code on error.
+ */
+int xe_tile_init_noalloc(struct xe_tile *tile)
+{
+	return xe_ggtt_init_noalloc(tile->mem.ggtt);
+}
diff --git a/drivers/gpu/drm/xe/xe_tile.h b/drivers/gpu/drm/xe/xe_tile.h
new file mode 100644
index 000000000000..77529ea136a6
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_tile.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2023 Intel Corporation
+ */
+
+#ifndef _XE_TILE_H_
+#define _XE_TILE_H_
+
+struct xe_tile;
+
+int xe_tile_alloc(struct xe_tile *tile);
+int xe_tile_init_noalloc(struct xe_tile *tile);
+
+#endif