drm/xe: Use dynamic allocation for tile and device VRAM region structures

[ Upstream commit f92cfd72d9a650f90260c54accd840c6500c4c3a ]

In future platforms, we will need to represent the device and tile
VRAM regions in a more dynamic way, so let's abandon the static
allocation of these structures and start use a dynamic allocation.

v2:
 - Add a helpers for accessing fields of the xe_vram_region structure
v3:
- Add missing EXPORT_SYMBOL_IF_KUNIT for
  xe_vram_region_actual_physical_size

Signed-off-by: Piotr Piórkowski <[email protected]>
Cc: Stuart Summers <[email protected]>
Cc: Matthew Auld <[email protected]>
Cc: Satyanarayana K V P <[email protected]>
Reviewed-by: Satyanarayana K V P <[email protected]>
Acked-by: Matthew Brost <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Lucas De Marchi <[email protected]>
Stable-dep-of: d30203739be7 ("drm/xe: Move rebar to be done earlier")
Signed-off-by: Sasha Levin <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: piorkov

drivers/gpu/drm/xe/display/xe_fb_pin.c

@@ -289,15 +289,15 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
 	if (IS_DGFX(to_xe_device(bo->ttm.base.dev)) &&
 	    intel_fb_rc_ccs_cc_plane(&fb->base) >= 0 &&
 	    !(bo->flags & XE_BO_FLAG_NEEDS_CPU_ACCESS)) {
-		struct xe_tile *tile = xe_device_get_root_tile(xe);
+		struct xe_vram_region *vram = xe_device_get_root_tile(xe)->mem.vram;
 
 		/*
 		 * If we need to able to access the clear-color value stored in
 		 * the buffer, then we require that such buffers are also CPU
 		 * accessible.  This is important on small-bar systems where
 		 * only some subset of VRAM is CPU accessible.
 		 */
-		if (tile->mem.vram.io_size < tile->mem.vram.usable_size) {
+		if (xe_vram_region_io_size(vram) < xe_vram_region_usable_size(vram)) {
 			ret = -EINVAL;
 			goto err;
 		}

drivers/gpu/drm/xe/display/xe_plane_initial.c

@@ -103,7 +103,7 @@ initial_plane_bo(struct xe_device *xe,
 		 * We don't currently expect this to ever be placed in the
 		 * stolen portion.
 		 */
-		if (phys_base >= tile0->mem.vram.usable_size) {
+		if (phys_base >= xe_vram_region_usable_size(tile0->mem.vram)) {
 			drm_err(&xe->drm,
 				"Initial plane programming using invalid range, phys_base=%pa\n",
 				&phys_base);

drivers/gpu/drm/xe/xe_assert.h

@@ -12,6 +12,7 @@
 
 #include "xe_gt_types.h"
 #include "xe_step.h"
+#include "xe_vram.h"
 
 /**
  * DOC: Xe Asserts
@@ -145,7 +146,8 @@
 	const struct xe_tile *__tile = (tile);							\
 	char __buf[10] __maybe_unused;								\
 	xe_assert_msg(tile_to_xe(__tile), condition, "tile: %u VRAM %s\n" msg,			\
-		      __tile->id, ({ string_get_size(__tile->mem.vram.actual_physical_size, 1,	\
+		      __tile->id, ({ string_get_size(						\
+				     xe_vram_region_actual_physical_size(__tile->mem.vram), 1,	\
 				     STRING_UNITS_2, __buf, sizeof(__buf)); __buf; }), ## arg);	\
 })
 

drivers/gpu/drm/xe/xe_device.c

@@ -688,6 +688,21 @@ static void sriov_update_device_info(struct xe_device *xe)
 	}
 }
 
+static int xe_device_vram_alloc(struct xe_device *xe)
+{
+	struct xe_vram_region *vram;
+
+	if (!IS_DGFX(xe))
+		return 0;
+
+	vram = drmm_kzalloc(&xe->drm, sizeof(*vram), GFP_KERNEL);
+	if (!vram)
+		return -ENOMEM;
+
+	xe->mem.vram = vram;
+	return 0;
+}
+
 /**
  * xe_device_probe_early: Device early probe
  * @xe: xe device instance
@@ -735,6 +750,10 @@ int xe_device_probe_early(struct xe_device *xe)
 
 	xe->wedged.mode = xe_modparam.wedged_mode;
 
+	err = xe_device_vram_alloc(xe);
+	if (err)
+		return err;
+
 	return 0;
 }
 ALLOW_ERROR_INJECTION(xe_device_probe_early, ERRNO); /* See xe_pci_probe() */

drivers/gpu/drm/xe/xe_device_types.h

@@ -77,6 +77,8 @@ struct xe_pxp;
  * device, such as HBM memory or CXL extension memory.
  */
 struct xe_vram_region {
+	/** @tile: Back pointer to tile */
+	struct xe_tile *tile;
 	/** @io_start: IO start address of this VRAM instance */
 	resource_size_t io_start;
 	/**
@@ -216,7 +218,7 @@ struct xe_tile {
 		 * Although VRAM is associated with a specific tile, it can
 		 * still be accessed by all tiles' GTs.
 		 */
-		struct xe_vram_region vram;
+		struct xe_vram_region *vram;
 
 		/** @mem.ggtt: Global graphics translation table */
 		struct xe_ggtt *ggtt;
@@ -412,7 +414,7 @@ struct xe_device {
 	/** @mem: memory info for device */
 	struct {
 		/** @mem.vram: VRAM info for device */
-		struct xe_vram_region vram;
+		struct xe_vram_region *vram;
 		/** @mem.sys_mgr: system TTM manager */
 		struct ttm_resource_manager sys_mgr;
 		/** @mem.sys_mgr: system memory shrinker. */

drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c

@@ -1604,7 +1604,7 @@ static u64 pf_query_free_lmem(struct xe_gt *gt)
 {
 	struct xe_tile *tile = gt->tile;
 
-	return xe_ttm_vram_get_avail(&tile->mem.vram.ttm.manager);
+	return xe_ttm_vram_get_avail(&tile->mem.vram->ttm.manager);
 }
 
 static u64 pf_query_max_lmem(struct xe_gt *gt)

drivers/gpu/drm/xe/xe_migrate.c

@@ -34,6 +34,7 @@
 #include "xe_sync.h"
 #include "xe_trace_bo.h"
 #include "xe_vm.h"
+#include "xe_vram.h"
 
 /**
  * struct xe_migrate - migrate context.
@@ -130,34 +131,36 @@ static u64 xe_migrate_vram_ofs(struct xe_device *xe, u64 addr, bool is_comp_pte)
 	u64 identity_offset = IDENTITY_OFFSET;
 
 	if (GRAPHICS_VER(xe) >= 20 && is_comp_pte)
-		identity_offset += DIV_ROUND_UP_ULL(xe->mem.vram.actual_physical_size, SZ_1G);
+		identity_offset += DIV_ROUND_UP_ULL(xe_vram_region_actual_physical_size
+							(xe->mem.vram), SZ_1G);
 
-	addr -= xe->mem.vram.dpa_base;
+	addr -= xe_vram_region_dpa_base(xe->mem.vram);
 	return addr + (identity_offset << xe_pt_shift(2));
 }
 
 static void xe_migrate_program_identity(struct xe_device *xe, struct xe_vm *vm, struct xe_bo *bo,
 					u64 map_ofs, u64 vram_offset, u16 pat_index, u64 pt_2m_ofs)
 {
+	struct xe_vram_region *vram = xe->mem.vram;
+	resource_size_t dpa_base = xe_vram_region_dpa_base(vram);
 	u64 pos, ofs, flags;
 	u64 entry;
 	/* XXX: Unclear if this should be usable_size? */
-	u64 vram_limit =  xe->mem.vram.actual_physical_size +
-		xe->mem.vram.dpa_base;
+	u64 vram_limit = xe_vram_region_actual_physical_size(vram) + dpa_base;
 	u32 level = 2;
 
 	ofs = map_ofs + XE_PAGE_SIZE * level + vram_offset * 8;
 	flags = vm->pt_ops->pte_encode_addr(xe, 0, pat_index, level,
 					    true, 0);
 
-	xe_assert(xe, IS_ALIGNED(xe->mem.vram.usable_size, SZ_2M));
+	xe_assert(xe, IS_ALIGNED(xe_vram_region_usable_size(vram), SZ_2M));
 
 	/*
 	 * Use 1GB pages when possible, last chunk always use 2M
 	 * pages as mixing reserved memory (stolen, WOCPM) with a single
 	 * mapping is not allowed on certain platforms.
 	 */
-	for (pos = xe->mem.vram.dpa_base; pos < vram_limit;
+	for (pos = dpa_base; pos < vram_limit;
 	     pos += SZ_1G, ofs += 8) {
 		if (pos + SZ_1G >= vram_limit) {
 			entry = vm->pt_ops->pde_encode_bo(bo, pt_2m_ofs,
@@ -307,11 +310,11 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	/* Identity map the entire vram at 256GiB offset */
 	if (IS_DGFX(xe)) {
 		u64 pt30_ofs = xe_bo_size(bo) - 2 * XE_PAGE_SIZE;
+		resource_size_t actual_phy_size = xe_vram_region_actual_physical_size(xe->mem.vram);
 
 		xe_migrate_program_identity(xe, vm, bo, map_ofs, IDENTITY_OFFSET,
 					    pat_index, pt30_ofs);
-		xe_assert(xe, xe->mem.vram.actual_physical_size <=
-					(MAX_NUM_PTE - IDENTITY_OFFSET) * SZ_1G);
+		xe_assert(xe, actual_phy_size <= (MAX_NUM_PTE - IDENTITY_OFFSET) * SZ_1G);
 
 		/*
 		 * Identity map the entire vram for compressed pat_index for xe2+
@@ -320,11 +323,11 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 		if (GRAPHICS_VER(xe) >= 20 && xe_device_has_flat_ccs(xe)) {
 			u16 comp_pat_index = xe->pat.idx[XE_CACHE_NONE_COMPRESSION];
 			u64 vram_offset = IDENTITY_OFFSET +
-				DIV_ROUND_UP_ULL(xe->mem.vram.actual_physical_size, SZ_1G);
+				DIV_ROUND_UP_ULL(actual_phy_size, SZ_1G);
 			u64 pt31_ofs = xe_bo_size(bo) - XE_PAGE_SIZE;
 
-			xe_assert(xe, xe->mem.vram.actual_physical_size <= (MAX_NUM_PTE -
-						IDENTITY_OFFSET - IDENTITY_OFFSET / 2) * SZ_1G);
+			xe_assert(xe, actual_phy_size <= (MAX_NUM_PTE - IDENTITY_OFFSET -
+							  IDENTITY_OFFSET / 2) * SZ_1G);
 			xe_migrate_program_identity(xe, vm, bo, map_ofs, vram_offset,
 						    comp_pat_index, pt31_ofs);
 		}

drivers/gpu/drm/xe/xe_pci.c

@@ -687,13 +687,19 @@ static int xe_info_init(struct xe_device *xe,
 	 * All of these together determine the overall GT count.
 	 */
 	for_each_tile(tile, xe, id) {
+		int err;
+
 		gt = tile->primary_gt;
 		gt->info.type = XE_GT_TYPE_MAIN;
 		gt->info.id = tile->id * xe->info.max_gt_per_tile;
 		gt->info.has_indirect_ring_state = graphics_desc->has_indirect_ring_state;
 		gt->info.engine_mask = graphics_desc->hw_engine_mask;
 		xe->info.gt_count++;
 
+		err = xe_tile_alloc_vram(tile);
+		if (err)
+			return err;
+
 		if (MEDIA_VER(xe) < 13 && media_desc)
 			gt->info.engine_mask |= media_desc->hw_engine_mask;
 

drivers/gpu/drm/xe/xe_query.c

@@ -334,7 +334,7 @@ static int query_config(struct xe_device *xe, struct drm_xe_device_query *query)
 	config->num_params = num_params;
 	config->info[DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID] =
 		xe->info.devid | (xe->info.revid << 16);
-	if (xe_device_get_root_tile(xe)->mem.vram.usable_size)
+	if (xe->mem.vram)
 		config->info[DRM_XE_QUERY_CONFIG_FLAGS] |=
 			DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM;
 	if (xe->info.has_usm && IS_ENABLED(CONFIG_DRM_XE_GPUSVM))

drivers/gpu/drm/xe/xe_svm.c

@@ -306,16 +306,11 @@ static struct xe_vram_region *page_to_vr(struct page *page)
 	return container_of(page_pgmap(page), struct xe_vram_region, pagemap);
 }
 
-static struct xe_tile *vr_to_tile(struct xe_vram_region *vr)
-{
-	return container_of(vr, struct xe_tile, mem.vram);
-}
-
 static u64 xe_vram_region_page_to_dpa(struct xe_vram_region *vr,
 				      struct page *page)
 {
 	u64 dpa;
-	struct xe_tile *tile = vr_to_tile(vr);
+	struct xe_tile *tile = vr->tile;
 	u64 pfn = page_to_pfn(page);
 	u64 offset;
 
@@ -370,7 +365,7 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 
 		if (!vr && spage) {
 			vr = page_to_vr(spage);
-			tile = vr_to_tile(vr);
+			tile = vr->tile;
 		}
 		XE_WARN_ON(spage && page_to_vr(spage) != vr);
 
@@ -508,7 +503,7 @@ static u64 block_offset_to_pfn(struct xe_vram_region *vr, u64 offset)
 
 static struct drm_buddy *tile_to_buddy(struct xe_tile *tile)
 {
-	return &tile->mem.vram.ttm.mm;
+	return &tile->mem.vram->ttm.mm;
 }
 
 static int xe_svm_populate_devmem_pfn(struct drm_pagemap_devmem *devmem_allocation,
@@ -522,7 +517,7 @@ static int xe_svm_populate_devmem_pfn(struct drm_pagemap_devmem *devmem_allocati
 
 	list_for_each_entry(block, blocks, link) {
 		struct xe_vram_region *vr = block->private;
-		struct xe_tile *tile = vr_to_tile(vr);
+		struct xe_tile *tile = vr->tile;
 		struct drm_buddy *buddy = tile_to_buddy(tile);
 		u64 block_pfn = block_offset_to_pfn(vr, drm_buddy_block_offset(block));
 		int i;
@@ -683,20 +678,15 @@ u64 xe_svm_find_vma_start(struct xe_vm *vm, u64 start, u64 end, struct xe_vma *v
 }
 
 #if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
-static struct xe_vram_region *tile_to_vr(struct xe_tile *tile)
-{
-	return &tile->mem.vram;
-}
-
 static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 				      unsigned long start, unsigned long end,
 				      struct mm_struct *mm,
 				      unsigned long timeslice_ms)
 {
-	struct xe_tile *tile = container_of(dpagemap, typeof(*tile), mem.vram.dpagemap);
+	struct xe_vram_region *vr = container_of(dpagemap, typeof(*vr), dpagemap);
+	struct xe_tile *tile = vr->tile;
 	struct xe_device *xe = tile_to_xe(tile);
 	struct device *dev = xe->drm.dev;
-	struct xe_vram_region *vr = tile_to_vr(tile);
 	struct drm_buddy_block *block;
 	struct list_head *blocks;
 	struct xe_bo *bo;
@@ -722,7 +712,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 
 	drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm,
 				&dpagemap_devmem_ops,
-				&tile->mem.vram.dpagemap,
+				&tile->mem.vram->dpagemap,
 				end - start);
 
 	blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks;