Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 726EBC7EE23 for ; Thu, 11 May 2023 03:47:36 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 6BF7710E597; Thu, 11 May 2023 03:47:35 +0000 (UTC) Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by gabe.freedesktop.org (Postfix) with ESMTPS id D944510E591 for ; Thu, 11 May 2023 03:47:30 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1683776850; x=1715312850; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=rloFFGp0qQ7/JHeAX9NuYTG2+a3qQqkvRJPFUJqyVvw=; b=aZLodcLkrDJCO1Frgd+Q41s2igbltn6VL6t3B0svxOmJF1ADLyc1p+c4 mnWMdYQSZgEW1ziAUcpuGaTB0jVRRBBwALU9L6ywUcKqkiD0FkCgi1Y2Y mRxdiThw7pYBBKUXih3fAe2PlxcCA1WxB4GF8arkLvyd7KYVkpZxf0mut M+jZdKYHbPpDpDkYQJxFsBllHrV02Ma32Yb5ErzIuNp0uOaPG/VZf5AJi xcAIQa9dp0AMDW3g4Ll7mM7SVRp5RUHhyCqLpQ3RAt7SXx4nmXcboo0pH 3vrEbq+aw6qlGauDFYhA5i7vS0pqa7RMObdYZ/YRiMiT3RvNEh+hnboKi A==; X-IronPort-AV: E=McAfee;i="6600,9927,10706"; a="347850635" X-IronPort-AV: E=Sophos;i="5.99,266,1677571200"; d="scan'208";a="347850635" Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by fmsmga102.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 10 May 2023 20:47:30 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10706"; a="789203191" X-IronPort-AV: E=Sophos;i="5.99,266,1677571200"; d="scan'208";a="789203191" Received: from mdroper-desk1.fm.intel.com ([10.1.27.134]) by fmsmga003-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 10 May 2023 20:47:30 -0700 From: Matt Roper To: intel-xe@lists.freedesktop.org Date: Wed, 10 May 2023 20:47:02 -0700 Message-Id: <20230511034722.1929038-7-matthew.d.roper@intel.com> X-Mailer: git-send-email 2.40.0 In-Reply-To: <20230511034722.1929038-1-matthew.d.roper@intel.com> References: <20230511034722.1929038-1-matthew.d.roper@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Subject: [Intel-xe] [PATCH 06/26] drm/xe: Move VRAM from GT to tile X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: matthew.d.roper@intel.com Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" On platforms with VRAM, the VRAM is associated with the tile, not the GT. Signed-off-by: Matt Roper --- drivers/gpu/drm/xe/Makefile | 1 + drivers/gpu/drm/xe/display/xe_fb_pin.c | 6 +- drivers/gpu/drm/xe/display/xe_plane_initial.c | 8 +- drivers/gpu/drm/xe/xe_bo.c | 50 +++++----- drivers/gpu/drm/xe/xe_bo.h | 4 +- drivers/gpu/drm/xe/xe_bo_evict.c | 8 +- drivers/gpu/drm/xe/xe_device.c | 14 ++- drivers/gpu/drm/xe/xe_device_types.h | 36 +++++++ drivers/gpu/drm/xe/xe_ggtt.c | 30 +++--- drivers/gpu/drm/xe/xe_ggtt.h | 6 +- drivers/gpu/drm/xe/xe_ggtt_types.h | 2 +- drivers/gpu/drm/xe/xe_gt.c | 93 ++----------------- drivers/gpu/drm/xe/xe_gt_debugfs.c | 2 +- drivers/gpu/drm/xe/xe_gt_pagefault.c | 6 +- drivers/gpu/drm/xe/xe_gt_types.h | 38 -------- drivers/gpu/drm/xe/xe_irq.c | 2 +- drivers/gpu/drm/xe/xe_mmio.c | 45 +++++---- drivers/gpu/drm/xe/xe_pci.c | 2 - drivers/gpu/drm/xe/xe_pt.c | 4 +- drivers/gpu/drm/xe/xe_query.c | 4 +- drivers/gpu/drm/xe/xe_res_cursor.h | 2 +- drivers/gpu/drm/xe/xe_tile.c | 74 +++++++++++++++ drivers/gpu/drm/xe/xe_tile.h | 14 +++ drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 16 ++-- drivers/gpu/drm/xe/xe_ttm_vram_mgr.h | 4 +- drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h | 6 +- 26 files changed, 245 insertions(+), 232 deletions(-) create mode 100644 drivers/gpu/drm/xe/xe_tile.c create mode 100644 drivers/gpu/drm/xe/xe_tile.h diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index b6c41cd7dbe3..7da33bf5a0e4 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -83,6 +83,7 @@ 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/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index ed691d28b34d..78ac58244f24 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -123,7 +123,7 @@ static int __xe_pin_fb_vma_ggtt(struct intel_framebuffer *fb, { struct xe_bo *bo = intel_fb_obj(&fb->base); struct xe_device *xe = to_xe_device(fb->base.dev); - struct xe_ggtt *ggtt = to_gt(xe)->mem.ggtt; + struct xe_ggtt *ggtt = xe_device_get_root_tile(xe)->mem.ggtt; u32 align; int ret; @@ -173,7 +173,7 @@ static int __xe_pin_fb_vma_ggtt(struct intel_framebuffer *fb, rot_info->plane[i].dst_stride); } - xe_ggtt_invalidate(to_gt(xe)); + xe_ggtt_invalidate(ggtt); out: mutex_unlock(&ggtt->lock); @@ -233,7 +233,7 @@ static struct i915_vma *__xe_pin_fb_vma(struct intel_framebuffer *fb, static void __xe_unpin_fb_vma(struct i915_vma *vma) { struct xe_device *xe = to_xe_device(vma->bo->ttm.base.dev); - struct xe_ggtt *ggtt = to_gt(xe)->mem.ggtt; + struct xe_ggtt *ggtt = xe_device_get_root_tile(xe)->mem.ggtt; if (vma->dpt) xe_bo_unpin_map_no_vm(vma->dpt); diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c index d0f91f37b6d8..556ede2e459e 100644 --- a/drivers/gpu/drm/xe/display/xe_plane_initial.c +++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c @@ -51,7 +51,7 @@ static struct xe_bo * initial_plane_bo(struct xe_device *xe, struct intel_initial_plane_config *plane_config) { - struct xe_gt *gt0 = xe_device_get_gt(xe, 0); + struct xe_tile *tile0 = xe_device_get_root_tile(xe); struct xe_bo *bo; resource_size_t phys_base; u32 base, size, flags; @@ -64,7 +64,7 @@ initial_plane_bo(struct xe_device *xe, base = round_down(plane_config->base, page_size); if (IS_DGFX(xe)) { - u64 __iomem *gte = gt0->mem.ggtt->gsm; + u64 __iomem *gte = tile0->mem.ggtt->gsm; u64 pte; gte += base / XE_PAGE_SIZE; @@ -83,7 +83,7 @@ initial_plane_bo(struct xe_device *xe, * We don't currently expect this to ever be placed in the * stolen portion. */ - if (phys_base >= gt0->mem.vram.size) { + if (phys_base >= tile0->mem.vram.size) { drm_err(&xe->drm, "Initial plane programming using invalid range, phys_base=%pa\n", &phys_base); @@ -115,7 +115,7 @@ initial_plane_bo(struct xe_device *xe, page_size); size -= base; - bo = xe_bo_create_pin_map_at(xe, gt0, NULL, size, phys_base, + bo = xe_bo_create_pin_map_at(xe, &tile0->primary_gt, NULL, size, phys_base, ttm_bo_type_kernel, flags); if (IS_ERR(bo)) { drm_dbg(&xe->drm, diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index c82e995df779..5dbca5bbca8f 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -71,25 +71,25 @@ static bool xe_bo_is_user(struct xe_bo *bo) return bo->flags & XE_BO_CREATE_USER_BIT; } -static struct xe_gt * -mem_type_to_gt(struct xe_device *xe, u32 mem_type) +static struct xe_tile * +mem_type_to_tile(struct xe_device *xe, u32 mem_type) { XE_BUG_ON(mem_type != XE_PL_STOLEN && !mem_type_is_vram(mem_type)); - return xe_device_get_gt(xe, mem_type == XE_PL_STOLEN ? 0 : (mem_type - XE_PL_VRAM0)); + return &xe->tiles[mem_type == XE_PL_STOLEN ? 0 : (mem_type - XE_PL_VRAM0)]; } /** - * xe_bo_to_gt() - Get a GT from a BO's memory location + * xe_bo_to_tile() - Get a tile from a BO's memory location * @bo: The buffer object * - * Get a GT from a BO's memory location, should be called on BOs in VRAM only. + * Get a tile from a BO's memory location, should be called on BOs in VRAM only. * - * Return: xe_gt object which is closest to the BO + * Return: xe_tile object which is closest to the BO */ -struct xe_gt *xe_bo_to_gt(struct xe_bo *bo) +struct xe_tile *xe_bo_to_tile(struct xe_bo *bo) { - return mem_type_to_gt(xe_bo_device(bo), bo->ttm.resource->mem_type); + return mem_type_to_tile(xe_bo_device(bo), bo->ttm.resource->mem_type); } static void try_add_system(struct xe_bo *bo, struct ttm_place *places, @@ -109,9 +109,9 @@ static void try_add_system(struct xe_bo *bo, struct ttm_place *places, static void add_vram(struct xe_device *xe, struct xe_bo *bo, struct ttm_place *places, u32 bo_flags, u32 mem_type, u32 *c) { - struct xe_gt *gt = mem_type_to_gt(xe, mem_type); + struct xe_tile *tile = mem_type_to_tile(xe, mem_type); - XE_BUG_ON(!gt->mem.vram.size); + XE_BUG_ON(!tile->mem.vram.size); places[*c] = (struct ttm_place) { .mem_type = mem_type, @@ -356,7 +356,7 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) { struct xe_device *xe = ttm_to_xe_device(bdev); - struct xe_gt *gt; + struct xe_tile *tile; switch (mem->mem_type) { case XE_PL_SYSTEM: @@ -364,15 +364,15 @@ static int xe_ttm_io_mem_reserve(struct ttm_device *bdev, return 0; case XE_PL_VRAM0: case XE_PL_VRAM1: - gt = mem_type_to_gt(xe, mem->mem_type); + tile = mem_type_to_tile(xe, mem->mem_type); mem->bus.offset = mem->start << PAGE_SHIFT; - if (gt->mem.vram.mapping && + if (tile->mem.vram.mapping && mem->placement & TTM_PL_FLAG_CONTIGUOUS) - mem->bus.addr = (u8 *)gt->mem.vram.mapping + + mem->bus.addr = (u8 *)tile->mem.vram.mapping + mem->bus.offset; - mem->bus.offset += gt->mem.vram.io_start; + mem->bus.offset += tile->mem.vram.io_start; mem->bus.is_iomem = true; #if !defined(CONFIG_X86) @@ -632,9 +632,9 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, if (bo->gt) gt = bo->gt; else if (resource_is_vram(new_mem)) - gt = mem_type_to_gt(xe, new_mem->mem_type); + gt = &mem_type_to_tile(xe, new_mem->mem_type)->primary_gt; else if (resource_is_vram(old_mem)) - gt = mem_type_to_gt(xe, old_mem->mem_type); + gt = &mem_type_to_tile(xe, old_mem->mem_type)->primary_gt; XE_BUG_ON(!gt); XE_BUG_ON(!gt->migrate); @@ -658,7 +658,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, /* Create a new VMAP once kernel BO back in VRAM */ if (!ret && resource_is_vram(new_mem)) { - void *new_addr = gt->mem.vram.mapping + + void *new_addr = gt_to_tile(gt)->mem.vram.mapping + (new_mem->start << PAGE_SHIFT); if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) { @@ -830,14 +830,14 @@ static unsigned long xe_ttm_io_mem_pfn(struct ttm_buffer_object *ttm_bo, { struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev); struct xe_bo *bo = ttm_to_xe_bo(ttm_bo); - struct xe_gt *gt = mem_type_to_gt(xe, ttm_bo->resource->mem_type); + struct xe_tile *tile = mem_type_to_tile(xe, ttm_bo->resource->mem_type); struct xe_res_cursor cursor; if (ttm_bo->resource->mem_type == XE_PL_STOLEN) return xe_ttm_stolen_io_offset(bo, page_offset << PAGE_SHIFT) >> PAGE_SHIFT; xe_res_first(ttm_bo->resource, (u64)page_offset << PAGE_SHIFT, 0, &cursor); - return (gt->mem.vram.io_start + cursor.start) >> PAGE_SHIFT; + return (tile->mem.vram.io_start + cursor.start) >> PAGE_SHIFT; } static void __xe_bo_vunmap(struct xe_bo *bo); @@ -958,7 +958,7 @@ 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); @@ -1235,10 +1235,10 @@ xe_bo_create_locked_range(struct xe_device *xe, XE_BUG_ON(!gt); if (flags & XE_BO_FIXED_PLACEMENT_BIT) { - err = xe_ggtt_insert_bo_at(gt->mem.ggtt, bo, + err = xe_ggtt_insert_bo_at(gt_to_tile(gt)->mem.ggtt, bo, start + bo->size, U64_MAX); } 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; @@ -1338,12 +1338,12 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_gt *gt, uint64_t vram_region_io_offset(struct ttm_resource *res) { struct xe_device *xe = ttm_to_xe_device(res->bo->bdev); - struct xe_gt *gt = mem_type_to_gt(xe, res->mem_type); + struct xe_tile *tile = mem_type_to_tile(xe, res->mem_type); if (res->mem_type == XE_PL_STOLEN) return xe_ttm_stolen_gpu_offset(xe); - return gt->mem.vram.io_start - xe->mem.vram.io_start; + return tile->mem.vram.io_start - xe->mem.vram.io_start; } /** diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 7e111332c35a..7a79f3893260 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -22,7 +22,7 @@ /* -- */ #define XE_BO_CREATE_STOLEN_BIT BIT(4) #define XE_BO_CREATE_VRAM_IF_DGFX(gt) \ - (IS_DGFX(gt_to_xe(gt)) ? XE_BO_CREATE_VRAM0_BIT << gt->info.vram_id : \ + (IS_DGFX(gt_to_xe(gt)) ? XE_BO_CREATE_VRAM0_BIT << gt_to_tile(gt)->id : \ XE_BO_CREATE_SYSTEM_BIT) #define XE_BO_CREATE_GGTT_BIT BIT(5) #define XE_BO_CREATE_IGNORE_MIN_PAGE_SIZE_BIT BIT(6) @@ -107,7 +107,7 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_gt *gt, int xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo, u32 bo_flags); -struct xe_gt *xe_bo_to_gt(struct xe_bo *bo); +struct xe_tile *xe_bo_to_tile(struct xe_bo *bo); static inline struct xe_bo *ttm_to_xe_bo(const struct ttm_buffer_object *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 32cc83c43b2a..038074a90584 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" @@ -239,6 +240,7 @@ 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; @@ -248,8 +250,12 @@ int xe_device_probe(struct xe_device *xe) if (err) return err; - 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; } @@ -284,8 +290,8 @@ 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; } diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 2481b2045284..6b9e7847161c 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -53,6 +53,8 @@ const struct xe_tile *: (const struct xe_device *)((tile__)->xe), \ struct xe_tile *: (tile__)->xe) +struct xe_ggtt; + /** * struct xe_tile - hardware tile structure * @@ -96,6 +98,40 @@ struct xe_tile { /** @regs: pointer to tile's MMIO space (starting with registers) */ void *regs; } mmio; + + /** @mem: memory management info for tile */ + struct { + /** + * @vram: VRAM info for tile. + * + * Although VRAM is associated with a specific tile, it can + * still be accessed by all tiles' GTs. + */ + struct { + /** @io_start: IO start address of this VRAM instance */ + resource_size_t io_start; + /** + * @io_size: IO size of this VRAM instance + * + * This represents how much of this VRAM we can access + * via the CPU through the VRAM BAR. This can be smaller + * than @size, in which case only part of VRAM is CPU + * accessible (typically the first 256M). This + * configuration is known as small-bar. + */ + resource_size_t io_size; + /** @size: size of VRAM. */ + resource_size_t size; + /** @mapping: pointer to VRAM mappable space */ + void *__iomem mapping; + } vram; + + /** @vram_mgr: VRAM TTM manager */ + struct xe_ttm_vram_mgr *vram_mgr; + + /** @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 200976da3dc1..52d293d61cc0 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) @@ -147,13 +142,14 @@ static void xe_ggtt_initial_clear(struct xe_ggtt *ggtt) 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); } -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; @@ -193,8 +189,14 @@ int xe_ggtt_init(struct xe_gt *gt, struct xe_ggtt *ggtt) #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) { @@ -267,7 +269,7 @@ 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, @@ -318,7 +320,7 @@ void xe_ggtt_remove_node(struct xe_ggtt *ggtt, struct drm_mm_node *node) drm_mm_remove_node(node); node->size = 0; - xe_ggtt_invalidate(ggtt->gt); + xe_ggtt_invalidate(ggtt); mutex_unlock(&ggtt->lock); } diff --git a/drivers/gpu/drm/xe/xe_ggtt.h b/drivers/gpu/drm/xe/xe_ggtt.h index 333947100504..205a6d058bbd 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 cbe063a40aca..1e424ce8ef3e 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -36,7 +36,6 @@ #include "xe_ring_ops.h" #include "xe_sa.h" #include "xe_sched_job.h" -#include "xe_ttm_vram_mgr.h" #include "xe_tuning.h" #include "xe_uc.h" #include "xe_vm.h" @@ -45,64 +44,23 @@ struct xe_gt *xe_find_full_gt(struct xe_gt *gt) { - struct xe_gt *search; - u8 id; - - XE_BUG_ON(!xe_gt_is_media_type(gt)); - - for_each_gt(search, gt_to_xe(gt), id) { - if (search->info.vram_id == gt->info.vram_id) - return search; - } - - XE_BUG_ON("NOT POSSIBLE"); - return NULL; + /* + * FIXME: Media GTs are disabled at the moment. Once re-enabled, + * the proper handling here is to return the primary GT from the + * parameter GT's tile. + */ + return gt; } int xe_gt_alloc(struct xe_device *xe, struct xe_gt *gt) { - struct drm_device *drm = &xe->drm; - 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) - return -ENOMEM; - - } 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; - } - gt->ordered_wq = alloc_ordered_workqueue("gt-ordered-wq", 0); return 0; } -static int gt_ttm_mgr_init(struct xe_gt *gt) -{ - struct xe_device *xe = gt_to_xe(gt); - int err; - - if (gt->mem.vram.size) { - err = xe_ttm_vram_mgr_init(gt, gt->mem.vram_mgr); - if (err) - return err; - xe->info.mem_region_mask |= BIT(gt->info.vram_id) << 1; - } - - return 0; -} - void xe_gt_sanitize(struct xe_gt *gt) { /* @@ -320,43 +278,6 @@ int xe_gt_init_early(struct xe_gt *gt) return 0; } -/** - * xe_gt_init_noalloc - Init GT up to the point where allocations can happen. - * @gt: The GT to initialize. - * - * This function prepares the GT 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. - * - * Returns: 0 on success, negative error code on error. - */ -int xe_gt_init_noalloc(struct xe_gt *gt) -{ - int err, err2; - - if (xe_gt_is_media_type(gt)) - return 0; - - xe_device_mem_access_get(gt_to_xe(gt)); - err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); - if (err) - goto err; - - err = gt_ttm_mgr_init(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); - xe_device_mem_access_put(gt_to_xe(gt)); -err: - return err; -} - static int gt_fw_domain_init(struct xe_gt *gt) { int err, i; @@ -369,7 +290,7 @@ 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 c45486c2015a..b71b584c9bdc 100644 --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c @@ -97,7 +97,7 @@ 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_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 1677640e1075..f4f3d95ae6b1 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -107,6 +107,7 @@ static struct xe_vma *lookup_vma(struct xe_vm *vm, u64 page_addr) static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) { struct xe_device *xe = gt_to_xe(gt); + struct xe_tile *tile = gt_to_tile(gt); struct xe_vm *vm; struct xe_vma *vma = NULL; struct xe_bo *bo; @@ -195,7 +196,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) } /* Migrate to VRAM, move should invalidate the VMA first */ - ret = xe_bo_migrate(bo, XE_PL_VRAM0 + gt->info.vram_id); + ret = xe_bo_migrate(bo, XE_PL_VRAM0 + tile->id); if (ret) goto unlock_dma_resv; } else if (bo) { @@ -498,6 +499,7 @@ static struct xe_vma *get_acc_vma(struct xe_vm *vm, struct acc *acc) static int handle_acc(struct xe_gt *gt, struct acc *acc) { struct xe_device *xe = gt_to_xe(gt); + struct xe_tile *tile = gt_to_tile(gt); struct xe_vm *vm; struct xe_vma *vma; struct xe_bo *bo; @@ -553,7 +555,7 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc) goto unlock_vm; /* Migrate to VRAM, move should invalidate the VMA first */ - ret = xe_bo_migrate(bo, XE_PL_VRAM0 + gt->info.vram_id); + ret = xe_bo_migrate(bo, XE_PL_VRAM0 + tile->id); if (only_needs_bo_lock(bo)) xe_bo_unlock(bo, &ww); diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h index 03dd625b2781..bb5271277e3b 100644 --- a/drivers/gpu/drm/xe/xe_gt_types.h +++ b/drivers/gpu/drm/xe/xe_gt_types.h @@ -14,11 +14,8 @@ #include "xe_uc_types.h" struct xe_engine_ops; -struct xe_ggtt; struct xe_migrate; struct xe_ring_ops; -struct xe_ttm_gtt_mgr; -struct xe_ttm_vram_mgr; enum xe_gt_type { XE_GT_TYPE_UNINITIALIZED, @@ -109,8 +106,6 @@ struct xe_gt { enum xe_gt_type type; /** @id: id of GT */ u8 id; - /** @vram: id of the VRAM for this GT */ - u8 vram_id; /** @clock_freq: clock frequency */ u32 clock_freq; /** @engine_mask: mask of engines present on GT */ @@ -145,39 +140,6 @@ struct xe_gt { */ struct xe_reg_sr reg_sr; - /** - * @mem: memory management info for GT, multiple GTs can point to same - * objects (virtual split) - */ - struct { - /** - * @vram: VRAM info for GT, multiple GTs can point to same info - * (virtual split), can be subset of global device VRAM - */ - struct { - /** @io_start: IO start address of this VRAM instance */ - resource_size_t io_start; - /** - * @io_size: IO size of this VRAM instance - * - * This represents how much of this VRAM we can access - * via the CPU through the VRAM BAR. This can be smaller - * than @size, in which case only part of VRAM is CPU - * accessible (typically the first 256M). This - * configuration is known as small-bar. - */ - resource_size_t io_size; - /** @size: size of VRAM. */ - resource_size_t size; - /** @mapping: pointer to VRAM mappable space */ - void *__iomem mapping; - } 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 */ struct { /** diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c index 5bf359c81cc5..5be31855d789 100644 --- a/drivers/gpu/drm/xe/xe_irq.c +++ b/drivers/gpu/drm/xe/xe_irq.c @@ -369,7 +369,7 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg) } for_each_gt(gt, xe, id) { - if ((master_tile_ctl & DG1_MSTR_TILE(gt->info.vram_id)) == 0) + if ((master_tile_ctl & DG1_MSTR_TILE(gt_to_tile(gt)->id)) == 0) continue; if (!xe_gt_is_media_type(gt)) diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index 54fa1212fcd9..17b3a9880409 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -182,7 +182,7 @@ int xe_mmio_total_vram_size(struct xe_device *xe, u64 *vram_size, u64 *usable_si int xe_mmio_probe_vram(struct xe_device *xe) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); - struct xe_gt *gt; + struct xe_tile *tile; u8 id; u64 vram_size; u64 original_size; @@ -195,11 +195,11 @@ int xe_mmio_probe_vram(struct xe_device *xe) xe->mem.vram.io_start = 0; xe->mem.vram.io_size = 0; - for_each_gt(gt, xe, id) { - gt->mem.vram.mapping = 0; - gt->mem.vram.size = 0; - gt->mem.vram.io_start = 0; - gt->mem.vram.io_size = 0; + for_each_tile(tile, xe, id) { + tile->mem.vram.mapping = 0; + tile->mem.vram.size = 0; + tile->mem.vram.io_start = 0; + tile->mem.vram.io_size = 0; } return 0; } @@ -209,7 +209,6 @@ int xe_mmio_probe_vram(struct xe_device *xe) return -ENXIO; } - 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); @@ -239,23 +238,19 @@ int xe_mmio_probe_vram(struct xe_device *xe) u8 adj_tile_count = xe->info.tile_count; resource_size_t size, io_start, io_size; - for_each_gt(gt, xe, id) - if (xe_gt_is_media_type(gt)) - --adj_tile_count; - XE_BUG_ON(!adj_tile_count); size = xe->mem.vram.size / adj_tile_count; io_start = xe->mem.vram.io_start; io_size = xe->mem.vram.io_size; - for_each_gt(gt, xe, id) { - if (id && !xe_gt_is_media_type(gt)) { + for_each_tile(tile, xe, id) { + if (id) { io_size -= min(io_size, size); io_start += io_size; } - gt->mem.vram.size = size; + tile->mem.vram.size = size; /* * XXX: multi-tile small-bar might be wild. Hopefully @@ -263,10 +258,10 @@ int xe_mmio_probe_vram(struct xe_device *xe) * we care about. */ - gt->mem.vram.io_size = min(size, io_size); + tile->mem.vram.io_size = min(size, io_size); if (io_size) { - gt->mem.vram.io_start = io_start; - gt->mem.vram.mapping = xe->mem.vram.mapping + + tile->mem.vram.io_start = io_start; + tile->mem.vram.mapping = xe->mem.vram.mapping + (io_start - xe->mem.vram.io_start); } else { drm_err(&xe->drm, "Tile without any CPU visible VRAM. Aborting.\n"); @@ -274,16 +269,18 @@ int xe_mmio_probe_vram(struct xe_device *xe) } drm_info(&xe->drm, "VRAM[%u, %u]: %pa, %pa\n", - id, gt->info.vram_id, >->mem.vram.io_start, - >->mem.vram.size); + id, tile->id, &tile->mem.vram.io_start, + &tile->mem.vram.size); } } else { - gt->mem.vram.size = xe->mem.vram.size; - gt->mem.vram.io_start = xe->mem.vram.io_start; - gt->mem.vram.io_size = xe->mem.vram.io_size; - gt->mem.vram.mapping = xe->mem.vram.mapping; + tile = xe_device_get_root_tile(xe); + + tile->mem.vram.size = xe->mem.vram.size; + tile->mem.vram.io_start = xe->mem.vram.io_start; + tile->mem.vram.io_size = xe->mem.vram.io_size; + tile->mem.vram.mapping = xe->mem.vram.mapping; - drm_info(&xe->drm, "VRAM: %pa\n", >->mem.vram.size); + drm_info(&xe->drm, "VRAM: %pa\n", &tile->mem.vram.size); } return 0; } diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index bef65d3a440e..be7c41024838 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -536,7 +536,6 @@ static int xe_info_init(struct xe_device *xe, gt->info.id = id; if (id == 0) { gt->info.type = XE_GT_TYPE_MAIN; - gt->info.vram_id = id; gt->info.__engine_mask = graphics_desc->hw_engine_mask; if (MEDIA_VER(xe) < 13 && media_desc) @@ -546,7 +545,6 @@ static int xe_info_init(struct xe_device *xe, gt->mmio.adj_offset = 0; } else { gt->info.type = desc->extra_gts[id - 1].type; - gt->info.vram_id = desc->extra_gts[id - 1].vram_id; gt->info.__engine_mask = xe_gt_is_media_type(gt) ? media_desc->hw_engine_mask : graphics_desc->hw_engine_mask; diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 61126cefe0b5..ad42a21c0e22 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -758,12 +758,12 @@ xe_pt_stage_bind(struct xe_gt *gt, struct xe_vma *vma, int ret; if (is_vram) { - struct xe_gt *bo_gt = xe_bo_to_gt(bo); + struct xe_tile *bo_tile = xe_bo_to_tile(bo); xe_walk.default_pte = XE_PPGTT_PTE_LM; if (vma && vma->use_atomic_access_pte_bit) xe_walk.default_pte |= XE_USM_PPGTT_PTE_AE; - xe_walk.dma_offset = bo_gt->mem.vram.io_start - + xe_walk.dma_offset = bo_tile->mem.vram.io_start - gt_to_xe(gt)->mem.vram.io_start; xe_walk.cache = XE_CACHE_WB; } else { diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index dd64ff0d2a57..c81652d7f4ec 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -182,7 +182,7 @@ static int query_config(struct xe_device *xe, struct drm_xe_device_query *query) config->num_params = num_params; config->info[XE_QUERY_CONFIG_REV_AND_DEVICE_ID] = xe->info.devid | (xe->info.revid << 16); - if (to_gt(xe)->mem.vram.size) + if (xe_device_get_root_tile(xe)->mem.vram.size) config->info[XE_QUERY_CONFIG_FLAGS] = XE_QUERY_CONFIG_FLAGS_HAS_VRAM; if (xe->info.enable_guc) @@ -242,7 +242,7 @@ static int query_gts(struct xe_device *xe, struct drm_xe_device_query *query) gts->gts[id].native_mem_regions = 0x1; else gts->gts[id].native_mem_regions = - BIT(gt->info.vram_id) << 1; + BIT(gt_to_tile(gt)->id) << 1; gts->gts[id].slow_mem_regions = xe->info.mem_region_mask ^ gts->gts[id].native_mem_regions; } diff --git a/drivers/gpu/drm/xe/xe_res_cursor.h b/drivers/gpu/drm/xe/xe_res_cursor.h index 4e99fae26b4c..f2ba609712d3 100644 --- a/drivers/gpu/drm/xe/xe_res_cursor.h +++ b/drivers/gpu/drm/xe/xe_res_cursor.h @@ -53,7 +53,7 @@ static struct drm_buddy *xe_res_get_buddy(struct ttm_resource *res) struct xe_device *xe = ttm_to_xe_device(res->bo->bdev); if (res->mem_type != XE_PL_STOLEN) { - return &xe_device_get_gt(xe, res->mem_type - XE_PL_VRAM0)->mem.vram_mgr->mm; + return &xe->tiles[res->mem_type - XE_PL_VRAM0].mem.vram_mgr->mm; } else { struct ttm_resource_manager *mgr = ttm_manager_type(&xe->ttm, XE_PL_STOLEN); diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c new file mode 100644 index 000000000000..9553d252b56c --- /dev/null +++ b/drivers/gpu/drm/xe/xe_tile.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2023 Intel Corporation + */ + +#include + +#include "xe_device.h" +#include "xe_ggtt.h" +#include "xe_tile.h" +#include "xe_ttm_vram_mgr.h" + +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; + + tile->mem.vram_mgr = drmm_kzalloc(drm, sizeof(*tile->mem.vram_mgr), GFP_KERNEL); + if (!tile->mem.vram_mgr) + return -ENOMEM; + + return 0; +} + +static int tile_ttm_mgr_init(struct xe_tile *tile) +{ + struct xe_device *xe = tile_to_xe(tile); + int err; + + if (tile->mem.vram.size) { + err = xe_ttm_vram_mgr_init(tile, tile->mem.vram_mgr); + if (err) + return err; + xe->info.mem_region_mask |= BIT(tile->id) << 1; + } + + 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) +{ + int err; + + xe_device_mem_access_get(tile_to_xe(tile)); + + err = tile_ttm_mgr_init(tile); + if (err) + goto err_mem_access; + + err = xe_ggtt_init_noalloc(tile->mem.ggtt); + +err_mem_access: + xe_device_mem_access_put(tile_to_xe(tile)); + return err; +} diff --git a/drivers/gpu/drm/xe/xe_tile.h b/drivers/gpu/drm/xe/xe_tile.h new file mode 100644 index 000000000000..49b64d83ce91 --- /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 diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c index 73836b9b7fed..1a84abd35fcf 100644 --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c @@ -353,16 +353,14 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr, return drmm_add_action_or_reset(&xe->drm, ttm_vram_mgr_fini, mgr); } -int xe_ttm_vram_mgr_init(struct xe_gt *gt, struct xe_ttm_vram_mgr *mgr) +int xe_ttm_vram_mgr_init(struct xe_tile *tile, struct xe_ttm_vram_mgr *mgr) { - struct xe_device *xe = gt_to_xe(gt); + struct xe_device *xe = tile_to_xe(tile); - XE_BUG_ON(xe_gt_is_media_type(gt)); + mgr->tile = tile; - mgr->gt = gt; - - return __xe_ttm_vram_mgr_init(xe, mgr, XE_PL_VRAM0 + gt->info.vram_id, - gt->mem.vram.size, gt->mem.vram.io_size, + return __xe_ttm_vram_mgr_init(xe, mgr, XE_PL_VRAM0 + tile->id, + tile->mem.vram.size, tile->mem.vram.io_size, PAGE_SIZE); } @@ -373,7 +371,7 @@ int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe, enum dma_data_direction dir, struct sg_table **sgt) { - struct xe_gt *gt = xe_device_get_gt(xe, res->mem_type - XE_PL_VRAM0); + struct xe_tile *tile = &xe->tiles[res->mem_type - XE_PL_VRAM0]; struct xe_res_cursor cursor; struct scatterlist *sg; int num_entries = 0; @@ -406,7 +404,7 @@ int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe, */ xe_res_first(res, offset, length, &cursor); for_each_sgtable_sg((*sgt), sg, i) { - phys_addr_t phys = cursor.start + gt->mem.vram.io_start; + phys_addr_t phys = cursor.start + tile->mem.vram.io_start; size_t size = cursor.size; dma_addr_t addr; diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h index 35e5367a79fb..6e1d6033d739 100644 --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h @@ -10,12 +10,12 @@ enum dma_data_direction; struct xe_device; -struct xe_gt; +struct xe_tile; int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr, u32 mem_type, u64 size, u64 io_size, u64 default_page_size); -int xe_ttm_vram_mgr_init(struct xe_gt *gt, struct xe_ttm_vram_mgr *mgr); +int xe_ttm_vram_mgr_init(struct xe_tile *tile, struct xe_ttm_vram_mgr *mgr); int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe, struct ttm_resource *res, u64 offset, u64 length, diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h index 3d9417ff7434..48bb991c14a5 100644 --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h @@ -9,7 +9,7 @@ #include #include -struct xe_gt; +struct xe_tile; /** * struct xe_ttm_vram_mgr - XE TTM VRAM manager @@ -17,8 +17,8 @@ struct xe_gt; * Manages placement of TTM resource in VRAM. */ struct xe_ttm_vram_mgr { - /** @gt: Graphics tile which the VRAM belongs to */ - struct xe_gt *gt; + /** @tile: Tile which the VRAM belongs to */ + struct xe_tile *tile; /** @manager: Base TTM resource manager */ struct ttm_resource_manager manager; /** @mm: DRM buddy allocator which manages the VRAM */ -- 2.40.0