drm/xe: Rework size helper to be a little more correct

The _total_vram_size helper is device based and is not complete.

Teach the helper to be tile aware and add the ability to size
DG1 correctly.
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/regs/xe_gt_regs.h

@@ -74,7 +74,7 @@
 #define VE1_AUX_INV				XE_REG(0x42b8)
 #define   AUX_INV				REG_BIT(0)
 
-#define XEHP_TILE0_ADDR_RANGE			XE_REG_MCR(0x4900)
+#define XEHP_TILE_ADDR_RANGE(_idx)		XE_REG_MCR(0x4900 + (_idx) * 4)
 #define XEHP_FLAT_CCS_BASE_ADDR			XE_REG_MCR(0x4910)
 
 #define CHICKEN_RASTER_1			XE_REG_MCR(0x6204, XE_REG_OPTION_MASKED)

drivers/gpu/drm/xe/xe_mmio.c

 // SPDX-License-Identifier: MIT
 /*
- * Copyright © 2021 Intel Corporation
+ * Copyright © 2021-2023 Intel Corporation
  */
 
 #include "xe_mmio.h"
@@ -20,7 +20,6 @@
 
 #define XEHP_MTCFG_ADDR		XE_REG(0x101800)
 #define TILE_COUNT		REG_GENMASK(15, 8)
-#define GEN12_LMEM_BAR		2
 
 static int xe_set_dma_info(struct xe_device *xe)
 {
@@ -145,34 +144,56 @@ static bool xe_pci_resource_valid(struct pci_dev *pdev, int bar)
 	return true;
 }
 
-int xe_mmio_total_vram_size(struct xe_device *xe, u64 *vram_size, u64 *usable_size)
+/**
+ * xe_mmio_tile_vram_size() - Collect vram size and offset information
+ * @gt: tile to get info for
+ * @vram_size: available vram (size - device reserved portions)
+ * @tile_size: actual vram size
+ * @tile_offset: physical start point in the vram address space
+ *
+ * There are 4 places for size information:
+ * - io size (from pci_resource_len of LMEM bar) (only used for small bar and DG1)
+ * - TILEx size (actual vram size)
+ * - GSMBASE offset (TILEx - "stolen")
+ * - CSSBASE offset (TILEx - CSS space necessary)
+ *
+ * CSSBASE is always a lower/smaller offset then GSMBASE.
+ *
+ * The actual available size of memory is to the CCS or GSM base.
+ * NOTE: multi-tile bases will include the tile offset.
+ *
+ */
+int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64 *tile_size, u64 *tile_offset)
 {
-	struct xe_gt *gt = xe_device_get_gt(xe, 0);
-	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	u64 offset;
 	int err;
-	u32 reg_val;
-
-	if (!xe->info.has_flat_ccs)  {
-		*vram_size = pci_resource_len(pdev, GEN12_LMEM_BAR);
-		if (usable_size)
-			*usable_size = min(*vram_size,
-					   xe_mmio_read64(gt, GSMBASE));
-		return 0;
-	}
+	u32 reg;
 
 	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
 	if (err)
 		return err;
 
-	reg_val = xe_gt_mcr_unicast_read_any(gt, XEHP_TILE0_ADDR_RANGE);
-	*vram_size = (u64)REG_FIELD_GET(GENMASK(14, 8), reg_val) * SZ_1G;
-	if (usable_size) {
-		reg_val = xe_gt_mcr_unicast_read_any(gt, XEHP_FLAT_CCS_BASE_ADDR);
-		*usable_size = (u64)REG_FIELD_GET(GENMASK(31, 8), reg_val) * SZ_64K;
-		drm_info(&xe->drm, "vram_size: 0x%llx usable_size: 0x%llx\n",
-			 *vram_size, *usable_size);
+	/* actual size */
+	if (unlikely(gt->xe->info.platform == XE_DG1)) {
+		*tile_size = pci_resource_len(to_pci_dev(gt->xe->drm.dev), GEN12_LMEM_BAR);
+		*tile_offset = 0;
+	} else {
+		reg = xe_gt_mcr_unicast_read_any(gt, XEHP_TILE_ADDR_RANGE(gt->info.id));
+		*tile_size = (u64)REG_FIELD_GET(GENMASK(14, 8), reg) * SZ_1G;
+		*tile_offset = (u64)REG_FIELD_GET(GENMASK(7, 1), reg) * SZ_1G;
 	}
 
+	/* minus device usage */
+	if (gt->xe->info.has_flat_ccs) {
+		reg = xe_gt_mcr_unicast_read_any(gt, XEHP_FLAT_CCS_BASE_ADDR);
+		offset = (u64)REG_FIELD_GET(GENMASK(31, 8), reg) * SZ_64K;
+	} else {
+		offset = xe_mmio_read64(gt, GSMBASE);
+	}
+
+	/* remove the tile offset so we have just the available size */
+	*vram_size = offset - *tile_offset;
+
 	return xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
 }
 
@@ -180,11 +201,12 @@ int xe_mmio_probe_vram(struct xe_device *xe)
 {
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	struct xe_gt *gt;
-	u8 id;
-	u64 vram_size;
 	u64 original_size;
-	u64 usable_size;
+	u64 tile_offset;
+	u64 tile_size;
+	u64 vram_size;
 	int err;
+	u8 id;
 
 	if (!IS_DGFX(xe)) {
 		xe->mem.vram.mapping = 0;
@@ -209,25 +231,25 @@ int xe_mmio_probe_vram(struct xe_device *xe)
 	gt = xe_device_get_gt(xe, 0);
 	original_size = pci_resource_len(pdev, GEN12_LMEM_BAR);
 
-	err = xe_mmio_total_vram_size(xe, &vram_size, &usable_size);
+	err = xe_mmio_tile_vram_size(gt, &vram_size, &tile_size, &tile_offset);
 	if (err)
 		return err;
 
 	xe_resize_vram_bar(xe, vram_size);
 	xe->mem.vram.io_start = pci_resource_start(pdev, GEN12_LMEM_BAR);
-	xe->mem.vram.io_size = min(usable_size,
+	xe->mem.vram.io_size = min(vram_size,
 				   pci_resource_len(pdev, GEN12_LMEM_BAR));
 	xe->mem.vram.size = xe->mem.vram.io_size;
 
 	if (!xe->mem.vram.size)
 		return -EIO;
 
-	if (usable_size > xe->mem.vram.io_size)
+	if (vram_size > xe->mem.vram.io_size)
 		drm_warn(&xe->drm, "Restricting VRAM size to PCI resource size (%lluMiB->%lluMiB)\n",
-			 (u64)usable_size >> 20, (u64)xe->mem.vram.io_size >> 20);
+			 (u64)vram_size >> 20, (u64)xe->mem.vram.io_size >> 20);
 
 	xe->mem.vram.mapping = ioremap_wc(xe->mem.vram.io_start, xe->mem.vram.io_size);
-	xe->mem.vram.size = min_t(u64, xe->mem.vram.size, usable_size);
+	xe->mem.vram.size = min_t(u64, xe->mem.vram.size, vram_size);
 
 	drm_info(&xe->drm, "TOTAL VRAM: %pa, %pa\n", &xe->mem.vram.io_start, &xe->mem.vram.size);
 

drivers/gpu/drm/xe/xe_mmio.h

 /* SPDX-License-Identifier: MIT */
 /*
- * Copyright © 2021 Intel Corporation
+ * Copyright © 2021-2023 Intel Corporation
  */
 
 #ifndef _XE_MMIO_H_
@@ -16,6 +16,8 @@ struct drm_device;
 struct drm_file;
 struct xe_device;
 
+#define GEN12_LMEM_BAR		2
+
 int xe_mmio_init(struct xe_device *xe);
 
 static inline u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg)
@@ -131,6 +133,6 @@ static inline bool xe_mmio_in_range(const struct xe_mmio_range *range,
 }
 
 int xe_mmio_probe_vram(struct xe_device *xe);
-int xe_mmio_total_vram_size(struct xe_device *xe, u64 *vram_size, u64 *flat_ccs_base);
+int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64 *tile_size, u64 *tile_base);
 
 #endif

drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c

 // SPDX-License-Identifier: MIT
 /*
- * Copyright © 2021-2022 Intel Corporation
+ * Copyright © 2021-2023 Intel Corporation
  * Copyright (C) 2021-2002 Red Hat
  */
 
@@ -51,27 +51,29 @@ bool xe_ttm_stolen_cpu_access_needs_ggtt(struct xe_device *xe)
 	return GRAPHICS_VERx100(xe) < 1270 && !IS_DGFX(xe);
 }
 
-static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
+static s64 detect_bar2_dgfx(struct xe_gt *gt, struct xe_ttm_stolen_mgr *mgr)
 {
-	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
-	struct xe_gt *gt = to_gt(xe);
-	u64 vram_size, stolen_size;
-	int err;
-
-	err = xe_mmio_total_vram_size(xe, &vram_size, NULL);
-	if (err) {
-		drm_info(&xe->drm, "Querying total vram size failed\n");
+	struct pci_dev *pdev = to_pci_dev(gt->xe->drm.dev);
+	u64 stolen_size;
+	u64 tile_offset;
+	u64 tile_size;
+	u64 vram_size;
+
+	if (xe_mmio_tile_vram_size(gt, &vram_size, &tile_size, &tile_offset)) {
+		drm_err(&gt->xe->drm, "Querying total vram size failed\n");
 		return 0;
 	}
 
 	/* Use DSM base address instead for stolen memory */
-	mgr->stolen_base = xe_mmio_read64(gt, DSMBASE) & BDSM_MASK;
-	if (drm_WARN_ON(&xe->drm, vram_size < mgr->stolen_base))
+	mgr->stolen_base = (xe_mmio_read64(gt, DSMBASE) & BDSM_MASK) - tile_offset;
+	if (drm_WARN_ON(&gt->xe->drm, tile_size < mgr->stolen_base))
 		return 0;
 
-	stolen_size = vram_size - mgr->stolen_base;
-	if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, 2))
-		mgr->io_base = pci_resource_start(pdev, 2) + mgr->stolen_base;
+	stolen_size = tile_size - mgr->stolen_base;
+
+	/* Verify usage fits in the actual resource available */
+	if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, GEN12_LMEM_BAR))
+		mgr->io_base = gt->mem.vram.io_start + mgr->stolen_base;
 
 	/*
 	 * There may be few KB of platform dependent reserved memory at the end
@@ -139,7 +141,7 @@ void xe_ttm_stolen_mgr_init(struct xe_device *xe)
 	int err;
 
 	if (IS_DGFX(xe))
-		stolen_size = detect_bar2_dgfx(xe, mgr);
+		stolen_size = detect_bar2_dgfx(to_gt(xe), mgr);
 	else if (GRAPHICS_VERx100(xe) >= 1270)
 		stolen_size = detect_bar2_integrated(xe, mgr);
 	else