From mboxrd@z Thu Jan 1 00:00:00 1970 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 A81C8C7EE31 for ; Tue, 2 May 2023 00:17:40 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 78CF910E49E; Tue, 2 May 2023 00:17:40 +0000 (UTC) Received: from mga18.intel.com (mga18.intel.com [134.134.136.126]) by gabe.freedesktop.org (Postfix) with ESMTPS id 467E110E34B for ; Tue, 2 May 2023 00:17:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1682986651; x=1714522651; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=DOvkHUACFSXqu08HbaKIx4OGmzykuBmJyax6nFHxhTE=; b=d/8dPIK4fh9e/EPcav2+9rRUXTnzhleBdzVt8aVvHNoA6uWFjmmhBDeV IqCN/8/sjLDxxk/x7Ev8DcgxIm+2uj4Hw1EoY5ng3rcuKEaw13gojS99d POz4TXK0vTQ6/zN2upZjHWH0n8haoA6TgckrMmJCCxaq3jr7K6FOWX3uv FRtV1x28QOG8lrDjGiMqM7eFXOlDvOnNXBofTGJI3vB25FLHVMx2E8ane SFEjgqa+EQB1ukAB7SFjCCCO8MDXOEKqaimZyArG9oTIogOJQYP7O6M1O SWZ2uZgR3RHf0kzvQJYqW28LLdHSWfAVMrG/x46Bg2sj5TfkGsD9D3XCO Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10697"; a="332619598" X-IronPort-AV: E=Sophos;i="5.99,242,1677571200"; d="scan'208";a="332619598" Received: from fmsmga004.fm.intel.com ([10.253.24.48]) by orsmga106.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 May 2023 17:17:30 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10697"; a="765541743" X-IronPort-AV: E=Sophos;i="5.99,242,1677571200"; d="scan'208";a="765541743" Received: from lstrano-desk.jf.intel.com ([10.24.89.184]) by fmsmga004-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 01 May 2023 17:17:29 -0700 From: Matthew Brost To: Date: Mon, 1 May 2023 17:17:23 -0700 Message-Id: <20230502001727.3211096-28-matthew.brost@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230502001727.3211096-1-matthew.brost@intel.com> References: <20230502001727.3211096-1-matthew.brost@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Subject: [Intel-xe] [PATCH v2 27/31] drm/xe: Use drm_exec for locking rather than TTM exec helpers 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: Danilo Krummrich Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" drm_exec is intended to replace TTM exec helpers, use drm_exec. Also combine parts of drm_exec with gpuva where it makes sense (locking, fence installation). Suggested-by: Danilo Krummrich Signed-off-by: Matthew Brost Signed-off-by: Francois Dugast --- drivers/gpu/drm/drm_gpuva_mgr.c | 67 ++++- drivers/gpu/drm/i915/display/intel_display.c | 6 +- drivers/gpu/drm/xe/Kconfig | 1 + drivers/gpu/drm/xe/tests/xe_bo.c | 26 +- drivers/gpu/drm/xe/tests/xe_migrate.c | 6 +- drivers/gpu/drm/xe/xe_bo.c | 56 ++-- drivers/gpu/drm/xe/xe_bo.h | 6 +- drivers/gpu/drm/xe/xe_bo_evict.c | 24 +- drivers/gpu/drm/xe/xe_bo_types.h | 1 - drivers/gpu/drm/xe/xe_engine.c | 7 +- drivers/gpu/drm/xe/xe_exec.c | 37 +-- drivers/gpu/drm/xe/xe_gt_pagefault.c | 55 +--- drivers/gpu/drm/xe/xe_lrc.c | 8 +- drivers/gpu/drm/xe/xe_migrate.c | 13 +- drivers/gpu/drm/xe/xe_vm.c | 283 ++++++++----------- drivers/gpu/drm/xe/xe_vm.h | 27 +- drivers/gpu/drm/xe/xe_vm_madvise.c | 37 +-- include/drm/drm_gpuva_mgr.h | 16 +- 18 files changed, 315 insertions(+), 361 deletions(-) diff --git a/drivers/gpu/drm/drm_gpuva_mgr.c b/drivers/gpu/drm/drm_gpuva_mgr.c index e8cd6e154336..93c912c34211 100644 --- a/drivers/gpu/drm/drm_gpuva_mgr.c +++ b/drivers/gpu/drm/drm_gpuva_mgr.c @@ -483,6 +483,50 @@ drm_gpuva_manager_destroy(struct drm_gpuva_manager *mgr) } EXPORT_SYMBOL(drm_gpuva_manager_destroy); +/** + * TODO + */ +int drm_gpuva_manager_lock(struct drm_gpuva_manager *mgr, struct drm_exec *exec, + struct drm_gem_object *mgr_obj, bool intr, + unsigned int num_fences) +{ + struct drm_gpuva *gpuva; + int ret; + + drm_exec_init(exec, intr); + drm_exec_while_not_all_locked(exec) { + ret = drm_exec_prepare_obj(exec, mgr_obj, num_fences); + drm_exec_continue_on_contention(exec); + if (ret && ret != -EALREADY) + goto err_exec; + + drm_gpuva_for_each_extobj(gpuva, mgr) { + ret = drm_exec_prepare_obj(exec, gpuva->gem.obj, + num_fences); + drm_exec_break_on_contention(exec); + if (ret && ret != -EALREADY) + goto err_exec; + } + } + + return 0; + +err_exec: + drm_exec_fini(exec); + return ret; +} +EXPORT_SYMBOL(drm_gpuva_manager_lock); + +/** + * TODO + */ +void drm_gpuva_manager_unlock(struct drm_gpuva_manager *mgr, + struct drm_exec *exec) +{ + drm_exec_fini(exec); +} +EXPORT_SYMBOL(drm_gpuva_manager_unlock); + static inline bool drm_gpuva_in_mm_range(struct drm_gpuva_manager *mgr, u64 addr, u64 range) { @@ -888,7 +932,7 @@ drm_gpuva_interval_empty(struct drm_gpuva_manager *mgr, u64 addr, u64 range) EXPORT_SYMBOL(drm_gpuva_interval_empty); /** - * drm_gpuva_add_fence - add fence to private and all extobj dma-resv + * drm_gpuva_manager_add_fence - add fence to private and all extobj dma-resv * @mgr: the &drm_gpuva_manager to add a fence to * @fence: fence to add * @private_usage: private dma-resv usage @@ -896,17 +940,24 @@ EXPORT_SYMBOL(drm_gpuva_interval_empty); * * Returns: true if the interval is empty, false otherwise */ -void drm_gpuva_add_fence(struct drm_gpuva_manager *mgr, struct dma_fence *fence, - enum dma_resv_usage private_usage, - enum dma_resv_usage extobj_usage) +void drm_gpuva_manager_add_fence(struct drm_gpuva_manager *mgr, + struct drm_exec *exec, + struct dma_fence *fence, + enum dma_resv_usage private_usage, + enum dma_resv_usage extobj_usage) { - struct drm_gpuva *gpuva; + struct drm_gem_object *obj; + unsigned long index; + + dma_resv_assert_held(&mgr->resv); dma_resv_add_fence(&mgr->resv, fence, private_usage); - drm_gpuva_for_each_extobj(gpuva, mgr) - dma_resv_add_fence(gpuva->gem.obj->resv, fence, extobj_usage); + drm_exec_for_each_locked_object(exec, index, obj) + if (likely(&mgr->resv != obj->resv)) + dma_resv_add_fence(obj->resv, fence, extobj_usage); } -EXPORT_SYMBOL(drm_gpuva_add_fence); +EXPORT_SYMBOL(drm_gpuva_manager_add_fence); + /** * drm_gpuva_map - helper to insert a &drm_gpuva from &drm_gpuva_fn_ops diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 28a227450329..aab1a3a0f06d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -7340,11 +7340,11 @@ static int i915_gem_object_read_from_page(struct xe_bo *bo, void *virtual; bool is_iomem; int ret; - struct ww_acquire_ctx ww; + struct drm_exec exec; XE_BUG_ON(size != 8); - ret = xe_bo_lock(bo, &ww, 0, true); + ret = xe_bo_lock(bo, &exec, 0, true); if (ret) return ret; @@ -7361,7 +7361,7 @@ static int i915_gem_object_read_from_page(struct xe_bo *bo, ttm_bo_kunmap(&map); out_unlock: - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); return ret; } #endif diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index f6f3b491d162..bbcc9b64b776 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -8,6 +8,7 @@ config DRM_XE select SHMEM select TMPFS select DRM_BUDDY + select DRM_EXEC select DRM_KMS_HELPER select DRM_PANEL select DRM_SUBALLOC_HELPER diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index 9bd381e5b7a6..316c6cf2bb86 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -175,17 +175,17 @@ static int evict_test_run_gt(struct xe_device *xe, struct xe_gt *gt, struct kuni unsigned int bo_flags = XE_BO_CREATE_USER_BIT | XE_BO_CREATE_VRAM_IF_DGFX(gt); struct xe_vm *vm = xe_migrate_get_vm(xe->gt[0].migrate); - struct ww_acquire_ctx ww; + struct drm_exec exec; int err, i; kunit_info(test, "Testing device %s gt id %u vram id %u\n", dev_name(xe->drm.dev), gt->info.id, gt->info.vram_id); for (i = 0; i < 2; ++i) { - xe_vm_lock(vm, &ww, 0, false); + xe_vm_lock(vm, &exec, 0, false); bo = xe_bo_create(xe, NULL, vm, 0x10000, ttm_bo_type_device, bo_flags); - xe_vm_unlock(vm, &ww); + xe_vm_unlock(vm, &exec); if (IS_ERR(bo)) { KUNIT_FAIL(test, "bo create err=%pe\n", bo); break; @@ -198,9 +198,9 @@ static int evict_test_run_gt(struct xe_device *xe, struct xe_gt *gt, struct kuni goto cleanup_bo; } - xe_bo_lock(external, &ww, 0, false); + xe_bo_lock(external, &exec, 0, false); err = xe_bo_pin_external(external); - xe_bo_unlock(external, &ww); + xe_bo_unlock(external, &exec); if (err) { KUNIT_FAIL(test, "external bo pin err=%pe\n", ERR_PTR(err)); @@ -240,18 +240,18 @@ static int evict_test_run_gt(struct xe_device *xe, struct xe_gt *gt, struct kuni if (i) { down_read(&vm->lock); - xe_vm_lock(vm, &ww, 0, false); + xe_vm_lock(vm, &exec, 0, false); err = xe_bo_validate(bo, bo->vm, false); - xe_vm_unlock(vm, &ww); + xe_vm_unlock(vm, &exec); up_read(&vm->lock); if (err) { KUNIT_FAIL(test, "bo valid err=%pe\n", ERR_PTR(err)); goto cleanup_all; } - xe_bo_lock(external, &ww, 0, false); + xe_bo_lock(external, &exec, 0, false); err = xe_bo_validate(external, NULL, false); - xe_bo_unlock(external, &ww); + xe_bo_unlock(external, &exec); if (err) { KUNIT_FAIL(test, "external bo valid err=%pe\n", ERR_PTR(err)); @@ -259,18 +259,18 @@ static int evict_test_run_gt(struct xe_device *xe, struct xe_gt *gt, struct kuni } } - xe_bo_lock(external, &ww, 0, false); + xe_bo_lock(external, &exec, 0, false); xe_bo_unpin_external(external); - xe_bo_unlock(external, &ww); + xe_bo_unlock(external, &exec); xe_bo_put(external); xe_bo_put(bo); continue; cleanup_all: - xe_bo_lock(external, &ww, 0, false); + xe_bo_lock(external, &exec, 0, false); xe_bo_unpin_external(external); - xe_bo_unlock(external, &ww); + xe_bo_unlock(external, &exec); cleanup_external: xe_bo_put(external); cleanup_bo: diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index 0f4371ad1fd9..e1482b4491b1 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -394,14 +394,14 @@ static int migrate_test_run_device(struct xe_device *xe) for_each_gt(gt, xe, id) { struct xe_migrate *m = gt->migrate; - struct ww_acquire_ctx ww; + struct drm_exec exec; kunit_info(test, "Testing gt id %d.\n", id); - xe_vm_lock(m->eng->vm, &ww, 0, true); + xe_vm_lock(m->eng->vm, &exec, 0, true); xe_device_mem_access_get(xe); xe_migrate_sanity_test(m, test); xe_device_mem_access_put(xe); - xe_vm_unlock(m->eng->vm, &ww); + xe_vm_unlock(m->eng->vm, &exec); } return 0; diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index e0422ffb6327..a427edbf486b 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -991,13 +992,13 @@ static void xe_gem_object_close(struct drm_gem_object *obj, struct xe_bo *bo = gem_to_xe_bo(obj); if (bo->vm && !xe_vm_no_dma_fences(bo->vm)) { - struct ww_acquire_ctx ww; + struct drm_exec exec; XE_BUG_ON(!xe_bo_is_user(bo)); - xe_bo_lock(bo, &ww, 0, false); + xe_bo_lock(bo, &exec, 0, false); ttm_bo_set_bulk_move(&bo->ttm, NULL); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); } } @@ -1402,11 +1403,6 @@ int xe_bo_pin_external(struct xe_bo *bo) } ttm_bo_pin(&bo->ttm); - - /* - * FIXME: If we always use the reserve / unreserve functions for locking - * we do not need this. - */ ttm_bo_move_to_lru_tail_unlocked(&bo->ttm); return 0; @@ -1461,11 +1457,6 @@ int xe_bo_pin(struct xe_bo *bo) } ttm_bo_pin(&bo->ttm); - - /* - * FIXME: If we always use the reserve / unreserve functions for locking - * we do not need this. - */ ttm_bo_move_to_lru_tail_unlocked(&bo->ttm); return 0; @@ -1496,11 +1487,6 @@ void xe_bo_unpin_external(struct xe_bo *bo) } ttm_bo_unpin(&bo->ttm); - - /* - * FIXME: If we always use the reserve / unreserve functions for locking - * we do not need this. - */ ttm_bo_move_to_lru_tail_unlocked(&bo->ttm); } @@ -1650,7 +1636,7 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, struct xe_device *xe = to_xe_device(dev); struct xe_file *xef = to_xe_file(file); struct drm_xe_gem_create *args = data; - struct ww_acquire_ctx ww; + struct drm_exec exec; struct xe_vm *vm = NULL; struct xe_bo *bo; unsigned bo_flags = XE_BO_CREATE_USER_BIT; @@ -1686,7 +1672,7 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, vm = xe_vm_lookup(xef, args->vm_id); if (XE_IOCTL_ERR(xe, !vm)) return -ENOENT; - err = xe_vm_lock(vm, &ww, 0, true); + err = xe_vm_lock(vm, &exec, 0, true); if (err) { xe_vm_put(vm); return err; @@ -1703,7 +1689,7 @@ int xe_gem_create_ioctl(struct drm_device *dev, void *data, bo = xe_bo_create(xe, NULL, vm, args->size, ttm_bo_type_device, bo_flags); if (vm) { - xe_vm_unlock(vm, &ww); + xe_vm_unlock(vm, &exec); xe_vm_put(vm); } @@ -1744,26 +1730,30 @@ int xe_gem_mmap_offset_ioctl(struct drm_device *dev, void *data, return 0; } -int xe_bo_lock(struct xe_bo *bo, struct ww_acquire_ctx *ww, +int xe_bo_lock(struct xe_bo *bo, struct drm_exec *exec, int num_resv, bool intr) { - struct ttm_validate_buffer tv_bo; - LIST_HEAD(objs); - LIST_HEAD(dups); + int err; - XE_BUG_ON(!ww); + drm_exec_init(exec, intr); + drm_exec_while_not_all_locked(exec) { + err = drm_exec_prepare_obj(exec, &bo->ttm.base, + num_resv); + drm_exec_continue_on_contention(exec); + if (err && err != -EALREADY) + goto out_err; + } - tv_bo.num_shared = num_resv; - tv_bo.bo = &bo->ttm;; - list_add_tail(&tv_bo.head, &objs); + return 0; - return ttm_eu_reserve_buffers(ww, &objs, intr, &dups); +out_err: + drm_exec_fini(exec); + return err; } -void xe_bo_unlock(struct xe_bo *bo, struct ww_acquire_ctx *ww) +void xe_bo_unlock(struct xe_bo *bo, struct drm_exec *exec) { - dma_resv_unlock(bo->ttm.base.resv); - ww_acquire_fini(ww); + drm_exec_fini(exec); } /** diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 9b401d30a130..5a80ebf72d10 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -75,6 +75,7 @@ #define XE_BO_PROPS_INVALID (-1) +struct drm_exec; struct sg_table; struct xe_bo *xe_bo_alloc(void); @@ -142,10 +143,9 @@ static inline void xe_bo_assert_held(struct xe_bo *bo) dma_resv_assert_held((bo)->ttm.base.resv); } -int xe_bo_lock(struct xe_bo *bo, struct ww_acquire_ctx *ww, +int xe_bo_lock(struct xe_bo *bo, struct drm_exec *exec, int num_resv, bool intr); - -void xe_bo_unlock(struct xe_bo *bo, struct ww_acquire_ctx *ww); +void xe_bo_unlock(struct xe_bo *bo, struct drm_exec *exec); static inline void xe_bo_unlock_vm_held(struct xe_bo *bo) { diff --git a/drivers/gpu/drm/xe/xe_bo_evict.c b/drivers/gpu/drm/xe/xe_bo_evict.c index 6642c5f52009..46d9d9eb110c 100644 --- a/drivers/gpu/drm/xe/xe_bo_evict.c +++ b/drivers/gpu/drm/xe/xe_bo_evict.c @@ -3,6 +3,8 @@ * Copyright © 2022 Intel Corporation */ +#include + #include "xe_bo_evict.h" #include "xe_bo.h" @@ -27,7 +29,7 @@ int xe_bo_evict_all(struct xe_device *xe) { struct ttm_device *bdev = &xe->ttm; - struct ww_acquire_ctx ww; + struct drm_exec exec; struct xe_bo *bo; struct xe_gt *gt; struct list_head still_in_list; @@ -62,9 +64,9 @@ int xe_bo_evict_all(struct xe_device *xe) list_move_tail(&bo->pinned_link, &still_in_list); spin_unlock(&xe->pinned.lock); - xe_bo_lock(bo, &ww, 0, false); + xe_bo_lock(bo, &exec, 0, false); ret = xe_bo_evict_pinned(bo); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); xe_bo_put(bo); if (ret) { spin_lock(&xe->pinned.lock); @@ -96,9 +98,9 @@ int xe_bo_evict_all(struct xe_device *xe) list_move_tail(&bo->pinned_link, &xe->pinned.evicted); spin_unlock(&xe->pinned.lock); - xe_bo_lock(bo, &ww, 0, false); + xe_bo_lock(bo, &exec, 0, false); ret = xe_bo_evict_pinned(bo); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); xe_bo_put(bo); if (ret) return ret; @@ -123,7 +125,7 @@ int xe_bo_evict_all(struct xe_device *xe) */ int xe_bo_restore_kernel(struct xe_device *xe) { - struct ww_acquire_ctx ww; + struct drm_exec exec; struct xe_bo *bo; int ret; @@ -140,9 +142,9 @@ int xe_bo_restore_kernel(struct xe_device *xe) list_move_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present); spin_unlock(&xe->pinned.lock); - xe_bo_lock(bo, &ww, 0, false); + xe_bo_lock(bo, &exec, 0, false); ret = xe_bo_restore_pinned(bo); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); if (ret) { xe_bo_put(bo); return ret; @@ -182,7 +184,7 @@ int xe_bo_restore_kernel(struct xe_device *xe) */ int xe_bo_restore_user(struct xe_device *xe) { - struct ww_acquire_ctx ww; + struct drm_exec exec; struct xe_bo *bo; struct xe_gt *gt; struct list_head still_in_list; @@ -204,9 +206,9 @@ int xe_bo_restore_user(struct xe_device *xe) xe_bo_get(bo); spin_unlock(&xe->pinned.lock); - xe_bo_lock(bo, &ww, 0, false); + xe_bo_lock(bo, &exec, 0, false); ret = xe_bo_restore_pinned(bo); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); xe_bo_put(bo); if (ret) { spin_lock(&xe->pinned.lock); diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 06de3330211d..2ba34a8c9b66 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -11,7 +11,6 @@ #include #include #include -#include #include struct xe_device; diff --git a/drivers/gpu/drm/xe/xe_engine.c b/drivers/gpu/drm/xe/xe_engine.c index 91600b1e8249..8b425b777259 100644 --- a/drivers/gpu/drm/xe/xe_engine.c +++ b/drivers/gpu/drm/xe/xe_engine.c @@ -8,6 +8,7 @@ #include #include +#include #include #include @@ -89,18 +90,18 @@ struct xe_engine *xe_engine_create(struct xe_device *xe, struct xe_vm *vm, u32 logical_mask, u16 width, struct xe_hw_engine *hwe, u32 flags) { - struct ww_acquire_ctx ww; + struct drm_exec exec; struct xe_engine *e; int err; if (vm) { - err = xe_vm_lock(vm, &ww, 0, true); + err = xe_vm_lock(vm, &exec, 0, true); if (err) return ERR_PTR(err); } e = __xe_engine_create(xe, vm, logical_mask, width, hwe, flags); if (vm) - xe_vm_unlock(vm, &ww); + xe_vm_unlock(vm, &exec); return e; } diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 2ae02f1500d5..9f7f1088c403 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -6,6 +6,7 @@ #include "xe_exec.h" #include +#include #include #include @@ -92,21 +93,16 @@ * Unlock all */ -static int xe_exec_begin(struct xe_engine *e, struct ww_acquire_ctx *ww, - struct ttm_validate_buffer tv_onstack[], - struct ttm_validate_buffer **tv, - struct list_head *objs) +static int xe_exec_begin(struct xe_engine *e, struct drm_exec *exec) { struct xe_vm *vm = e->vm; struct xe_vma *vma; - LIST_HEAD(dups); int err; - *tv = NULL; if (xe_vm_no_dma_fences(e->vm)) return 0; - err = xe_vm_lock_dma_resv(vm, ww, tv_onstack, tv, objs, true, 1); + err = xe_vm_lock_dma_resv(vm, exec, true, 1); if (err) return err; @@ -123,8 +119,7 @@ static int xe_exec_begin(struct xe_engine *e, struct ww_acquire_ctx *ww, err = xe_bo_validate(xe_vma_bo(vma), vm, false); if (err) { - xe_vm_unlock_dma_resv(vm, tv_onstack, *tv, ww, objs); - *tv = NULL; + xe_vm_unlock_dma_resv(vm, exec); return err; } } @@ -132,14 +127,10 @@ static int xe_exec_begin(struct xe_engine *e, struct ww_acquire_ctx *ww, return 0; } -static void xe_exec_end(struct xe_engine *e, - struct ttm_validate_buffer *tv_onstack, - struct ttm_validate_buffer *tv, - struct ww_acquire_ctx *ww, - struct list_head *objs) +static void xe_exec_end(struct xe_engine *e, struct drm_exec *exec) { if (!xe_vm_no_dma_fences(e->vm)) - xe_vm_unlock_dma_resv(e->vm, tv_onstack, tv, ww, objs); + xe_vm_unlock_dma_resv(e->vm, exec); } int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) @@ -149,17 +140,14 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct drm_xe_exec *args = data; struct drm_xe_sync __user *syncs_user = u64_to_user_ptr(args->syncs); u64 __user *addresses_user = u64_to_user_ptr(args->address); + struct drm_exec exec; struct xe_engine *engine; struct xe_sync_entry *syncs = NULL; u64 addresses[XE_HW_ENGINE_MAX_INSTANCE]; - struct ttm_validate_buffer tv_onstack[XE_ONSTACK_TV]; - struct ttm_validate_buffer *tv = NULL; u32 i, num_syncs = 0; struct xe_sched_job *job; struct dma_fence *rebind_fence; struct xe_vm *vm; - struct ww_acquire_ctx ww; - struct list_head objs; bool write_locked; int err = 0; @@ -270,7 +258,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_unlock_list; } - err = xe_exec_begin(engine, &ww, tv_onstack, &tv, &objs); + err = xe_exec_begin(engine, &exec); if (err) goto err_unlock_list; @@ -361,9 +349,10 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) * are written as we don't pass in a read / write list. */ if (!xe_vm_no_dma_fences(vm)) - drm_gpuva_add_fence(&vm->mgr, &job->drm.s_fence->finished, - DMA_RESV_USAGE_BOOKKEEP, - DMA_RESV_USAGE_WRITE); + drm_gpuva_manager_add_fence(&vm->mgr, &exec, + &job->drm.s_fence->finished, + DMA_RESV_USAGE_BOOKKEEP, + DMA_RESV_USAGE_WRITE); for (i = 0; i < num_syncs; i++) xe_sync_entry_signal(&syncs[i], job, @@ -387,7 +376,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) if (err) xe_sched_job_put(job); err_engine_end: - xe_exec_end(engine, tv_onstack, tv, &ww, &objs); + xe_exec_end(engine, &exec); err_unlock_list: if (write_locked) up_write(&vm->lock); diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index d7bf6b0a0697..1145c6eaa17d 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -9,7 +9,7 @@ #include #include -#include +#include #include "xe_bo.h" #include "xe_gt.h" @@ -84,11 +84,6 @@ static bool vma_matches(struct xe_vma *vma, u64 page_addr) return true; } -static bool only_needs_bo_lock(struct xe_bo *bo) -{ - return bo && bo->vm; -} - static struct xe_vma *lookup_vma(struct xe_vm *vm, u64 page_addr) { struct xe_vma *vma = NULL; @@ -109,10 +104,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) struct xe_vm *vm; struct xe_vma *vma = NULL; struct xe_bo *bo; - LIST_HEAD(objs); - LIST_HEAD(dups); - struct ttm_validate_buffer tv_bo, tv_vm; - struct ww_acquire_ctx ww; + struct drm_exec exec; struct dma_fence *fence; bool write_locked; int ret = 0; @@ -170,20 +162,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) /* Lock VM and BOs dma-resv */ bo = xe_vma_bo(vma); - if (only_needs_bo_lock(bo)) { - /* This path ensures the BO's LRU is updated */ - ret = xe_bo_lock(bo, &ww, xe->info.tile_count, false); - } else { - tv_vm.num_shared = xe->info.tile_count; - tv_vm.bo = xe_vm_ttm_bo(vm); - list_add(&tv_vm.head, &objs); - if (bo) { - tv_bo.bo = &bo->ttm; - tv_bo.num_shared = xe->info.tile_count; - list_add(&tv_bo.head, &objs); - } - ret = ttm_eu_reserve_buffers(&ww, &objs, false, &dups); - } + ret = xe_vm_bo_lock(vm, bo, &exec, xe->info.tile_count, false); if (ret) goto unlock_vm; @@ -226,10 +205,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) vma->usm.gt_invalidated &= ~BIT(gt->info.id); unlock_dma_resv: - if (only_needs_bo_lock(bo)) - xe_bo_unlock(bo, &ww); - else - ttm_eu_backoff_reservation(&ww, &objs); + xe_vm_bo_unlock(vm, bo, &exec, true); unlock_vm: if (!ret) vm->usm.last_fault_vma = vma; @@ -496,10 +472,7 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc) struct xe_vm *vm; struct xe_vma *vma; struct xe_bo *bo; - LIST_HEAD(objs); - LIST_HEAD(dups); - struct ttm_validate_buffer tv_bo, tv_vm; - struct ww_acquire_ctx ww; + struct drm_exec exec; int ret = 0; /* We only support ACC_TRIGGER at the moment */ @@ -532,28 +505,14 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc) /* Lock VM and BOs dma-resv */ bo = xe_vma_bo(vma); - if (only_needs_bo_lock(bo)) { - /* This path ensures the BO's LRU is updated */ - ret = xe_bo_lock(bo, &ww, xe->info.tile_count, false); - } else { - tv_vm.num_shared = xe->info.tile_count; - tv_vm.bo = xe_vm_ttm_bo(vm); - list_add(&tv_vm.head, &objs); - tv_bo.bo = &bo->ttm; - tv_bo.num_shared = xe->info.tile_count; - list_add(&tv_bo.head, &objs); - ret = ttm_eu_reserve_buffers(&ww, &objs, false, &dups); - } + ret = xe_vm_bo_lock(vm, bo, &exec, xe->info.tile_count, false); if (ret) goto unlock_vm; /* Migrate to VRAM, move should invalidate the VMA first */ ret = xe_bo_migrate(bo, XE_PL_VRAM0 + gt->info.vram_id); - if (only_needs_bo_lock(bo)) - xe_bo_unlock(bo, &ww); - else - ttm_eu_backoff_reservation(&ww, &objs); + xe_vm_bo_unlock(vm, bo, &exec, true); unlock_vm: up_read(&vm->lock); xe_vm_put(vm); diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index ae605e7805de..3cc34efe8dd8 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -3,6 +3,8 @@ * Copyright © 2021 Intel Corporation */ +#include + #include "xe_lrc.h" #include "regs/xe_engine_regs.h" @@ -712,16 +714,16 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, void xe_lrc_finish(struct xe_lrc *lrc) { - struct ww_acquire_ctx ww; + struct drm_exec exec; xe_hw_fence_ctx_finish(&lrc->fence_ctx); if (lrc->bo->vm) - xe_vm_lock(lrc->bo->vm, &ww, 0, false); + xe_vm_lock(lrc->bo->vm, &exec, 0, false); else xe_bo_lock_no_vm(lrc->bo, NULL); xe_bo_unpin(lrc->bo); if (lrc->bo->vm) - xe_vm_unlock(lrc->bo->vm, &ww); + xe_vm_unlock(lrc->bo->vm, &exec); else xe_bo_unlock_no_vm(lrc->bo); xe_bo_put(lrc->bo); diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 91a06c925a1e..1dd497252640 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -9,6 +9,7 @@ #include #include +#include #include #include @@ -86,13 +87,13 @@ struct xe_engine *xe_gt_migrate_engine(struct xe_gt *gt) static void xe_migrate_fini(struct drm_device *dev, void *arg) { struct xe_migrate *m = arg; - struct ww_acquire_ctx ww; + struct drm_exec exec; - xe_vm_lock(m->eng->vm, &ww, 0, false); + xe_vm_lock(m->eng->vm, &exec, 0, false); xe_bo_unpin(m->pt_bo); if (m->cleared_bo) xe_bo_unpin(m->cleared_bo); - xe_vm_unlock(m->eng->vm, &ww); + xe_vm_unlock(m->eng->vm, &exec); dma_fence_put(m->fence); if (m->cleared_bo) @@ -315,7 +316,7 @@ struct xe_migrate *xe_migrate_init(struct xe_gt *gt) struct xe_device *xe = gt_to_xe(gt); struct xe_migrate *m; struct xe_vm *vm; - struct ww_acquire_ctx ww; + struct drm_exec exec; int err; XE_BUG_ON(xe_gt_is_media_type(gt)); @@ -332,9 +333,9 @@ struct xe_migrate *xe_migrate_init(struct xe_gt *gt) if (IS_ERR(vm)) return ERR_CAST(vm); - xe_vm_lock(vm, &ww, 0, false); + xe_vm_lock(vm, &exec, 0, false); err = xe_migrate_prepare_vm(gt, m, vm); - xe_vm_unlock(vm, &ww); + xe_vm_unlock(vm, &exec); if (err) { xe_vm_close_and_put(vm); return ERR_PTR(err); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 4d734ec4d6ab..55cced8870e6 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -7,7 +7,7 @@ #include -#include +#include #include #include #include @@ -260,10 +260,10 @@ static void arm_preempt_fences(struct xe_vm *vm, struct list_head *list) static int add_preempt_fences(struct xe_vm *vm, struct xe_bo *bo) { struct xe_engine *e; - struct ww_acquire_ctx ww; + struct drm_exec exec; int err; - err = xe_bo_lock(bo, &ww, vm->preempt.num_engines, true); + err = xe_bo_lock(bo, &exec, vm->preempt.num_engines, true); if (err) return err; @@ -274,11 +274,12 @@ static int add_preempt_fences(struct xe_vm *vm, struct xe_bo *bo) DMA_RESV_USAGE_BOOKKEEP); } - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); return 0; } -static void resume_and_reinstall_preempt_fences(struct xe_vm *vm) +static void resume_and_reinstall_preempt_fences(struct xe_vm *vm, + struct drm_exec *exec) { struct xe_engine *e; @@ -288,18 +289,15 @@ static void resume_and_reinstall_preempt_fences(struct xe_vm *vm) list_for_each_entry(e, &vm->preempt.engines, compute.link) { e->ops->resume(e); - drm_gpuva_add_fence(&vm->mgr, e->compute.pfence, - DMA_RESV_USAGE_BOOKKEEP, - DMA_RESV_USAGE_BOOKKEEP); + drm_gpuva_manager_add_fence(&vm->mgr, exec, e->compute.pfence, + DMA_RESV_USAGE_BOOKKEEP, + DMA_RESV_USAGE_BOOKKEEP); } } int xe_vm_add_compute_engine(struct xe_vm *vm, struct xe_engine *e) { - struct ttm_validate_buffer tv_onstack[XE_ONSTACK_TV]; - struct ttm_validate_buffer *tv; - struct ww_acquire_ctx ww; - struct list_head objs; + struct drm_exec exec; struct dma_fence *pfence; int err; bool wait; @@ -308,7 +306,7 @@ int xe_vm_add_compute_engine(struct xe_vm *vm, struct xe_engine *e) down_write(&vm->lock); - err = xe_vm_lock_dma_resv(vm, &ww, tv_onstack, &tv, &objs, true, 1); + err = xe_vm_lock_dma_resv(vm, &exec, true, 1); if (err) goto out_unlock_outer; @@ -325,9 +323,9 @@ int xe_vm_add_compute_engine(struct xe_vm *vm, struct xe_engine *e) down_read(&vm->userptr.notifier_lock); - drm_gpuva_add_fence(&vm->mgr, pfence, - DMA_RESV_USAGE_BOOKKEEP, - DMA_RESV_USAGE_BOOKKEEP); + drm_gpuva_manager_add_fence(&vm->mgr, &exec, pfence, + DMA_RESV_USAGE_BOOKKEEP, + DMA_RESV_USAGE_BOOKKEEP); /* * Check to see if a preemption on VM is in flight or userptr @@ -341,7 +339,7 @@ int xe_vm_add_compute_engine(struct xe_vm *vm, struct xe_engine *e) up_read(&vm->userptr.notifier_lock); out_unlock: - xe_vm_unlock_dma_resv(vm, tv_onstack, tv, &ww, &objs); + xe_vm_unlock_dma_resv(vm, &exec); out_unlock_outer: up_write(&vm->lock); @@ -367,25 +365,24 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm) list_empty(&vm->userptr.invalidated)) ? 0 : -EAGAIN; } +static struct drm_gem_object *xe_vm_gem(struct xe_vm *vm) +{ + int idx = vm->flags & XE_VM_FLAG_MIGRATION ? + XE_VM_FLAG_GT_ID(vm->flags) : 0; + + /* Safe to use index 0 as all BO in the VM share a single dma-resv lock */ + return &vm->pt_root[idx]->bo->ttm.base; +} + /** * xe_vm_lock_dma_resv() - Lock the vm dma_resv object and the dma_resv * objects of the vm's external buffer objects. - * @vm: The vm. - * @ww: Pointer to a struct ww_acquire_ctx locking context. - * @tv_onstack: Array size XE_ONSTACK_TV of storage for the struct - * ttm_validate_buffers used for locking. - * @tv: Pointer to a pointer that on output contains the actual storage used. - * @objs: List head for the buffer objects locked. + * @vm: The vm * @intr: Whether to lock interruptible. * @num_shared: Number of dma-fence slots to reserve in the locked objects. * * Locks the vm dma-resv objects and all the dma-resv objects of the - * buffer objects on the vm external object list. The TTM utilities require - * a list of struct ttm_validate_buffers pointing to the actual buffer - * objects to lock. Storage for those struct ttm_validate_buffers should - * be provided in @tv_onstack, and is typically reserved on the stack - * of the caller. If the size of @tv_onstack isn't sufficient, then - * storage will be allocated internally using kvmalloc(). + * buffer objects on the vm external object list. * * The function performs deadlock handling internally, and after a * successful return the ww locking transaction should be considered @@ -395,46 +392,18 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm) * @intr is set to true, -EINTR or -ERESTARTSYS may be returned. In case * of error, any locking performed has been reverted. */ -int xe_vm_lock_dma_resv(struct xe_vm *vm, struct ww_acquire_ctx *ww, - struct ttm_validate_buffer *tv_onstack, - struct ttm_validate_buffer **tv, - struct list_head *objs, - bool intr, +int xe_vm_lock_dma_resv(struct xe_vm *vm, struct drm_exec *exec, bool intr, unsigned int num_shared) { - struct ttm_validate_buffer *tv_vm, *tv_bo; struct xe_vma *vma, *next; - struct drm_gpuva *gpuva; - LIST_HEAD(dups); int err; lockdep_assert_held(&vm->lock); - if (vm->mgr.extobj.entries < XE_ONSTACK_TV) { - tv_vm = tv_onstack; - } else { - tv_vm = kvmalloc_array(vm->mgr.extobj.entries + 1, - sizeof(*tv_vm), - GFP_KERNEL); - if (!tv_vm) - return -ENOMEM; - } - tv_bo = tv_vm + 1; - - INIT_LIST_HEAD(objs); - drm_gpuva_for_each_extobj(gpuva, &vm->mgr) { - tv_bo->num_shared = num_shared; - tv_bo->bo = &gem_to_xe_bo(gpuva->gem.obj)->ttm; - - list_add_tail(&tv_bo->head, objs); - tv_bo++; - } - tv_vm->num_shared = num_shared; - tv_vm->bo = xe_vm_ttm_bo(vm); - list_add_tail(&tv_vm->head, objs); - err = ttm_eu_reserve_buffers(ww, objs, intr, &dups); + err = drm_gpuva_manager_lock(&vm->mgr, exec, xe_vm_gem(vm), intr, + num_shared); if (err) - goto out_err; + return err; spin_lock(&vm->notifier.list_lock); list_for_each_entry_safe(vma, next, &vm->notifier.rebind_list, @@ -447,34 +416,22 @@ int xe_vm_lock_dma_resv(struct xe_vm *vm, struct ww_acquire_ctx *ww, } spin_unlock(&vm->notifier.list_lock); - *tv = tv_vm; return 0; - -out_err: - if (tv_vm != tv_onstack) - kvfree(tv_vm); - - return err; } /** * xe_vm_unlock_dma_resv() - Unlock reservation objects locked by * xe_vm_lock_dma_resv() * @vm: The vm. - * @tv_onstack: The @tv_onstack array given to xe_vm_lock_dma_resv(). - * @tv: The value of *@tv given by xe_vm_lock_dma_resv(). - * @ww: The ww_acquire_context used for locking. - * @objs: The list returned from xe_vm_lock_dma_resv(). * * Unlocks the reservation objects and frees any memory allocated by * xe_vm_lock_dma_resv(). */ -void xe_vm_unlock_dma_resv(struct xe_vm *vm, - struct ttm_validate_buffer *tv_onstack, - struct ttm_validate_buffer *tv, - struct ww_acquire_ctx *ww, - struct list_head *objs) +void xe_vm_unlock_dma_resv(struct xe_vm *vm, struct drm_exec *exec) { + struct drm_gem_object *obj, *skip = xe_vm_gem(vm); + unsigned long index; + /* * Nothing should've been able to enter the list while we were locked, * since we've held the dma-resvs of all the vm's external objects, @@ -483,19 +440,20 @@ void xe_vm_unlock_dma_resv(struct xe_vm *vm, */ XE_WARN_ON(!list_empty(&vm->notifier.rebind_list)); - ttm_eu_backoff_reservation(ww, objs); - if (tv && tv != tv_onstack) - kvfree(tv); + drm_exec_for_each_locked_object(exec, index, obj) { + struct xe_bo *bo = gem_to_xe_bo(obj); + + if (obj != skip) + ttm_bo_move_to_lru_tail_unlocked(&bo->ttm); + } + drm_gpuva_manager_unlock(&vm->mgr, exec); } static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); + struct drm_exec exec; struct xe_vma *vma; - struct ttm_validate_buffer tv_onstack[XE_ONSTACK_TV]; - struct ttm_validate_buffer *tv; - struct ww_acquire_ctx ww; - struct list_head objs; struct dma_fence *rebind_fence; unsigned int fence_count = 0; LIST_HEAD(preempt_fences); @@ -536,8 +494,7 @@ static void preempt_rebind_work_func(struct work_struct *w) goto out_unlock_outer; } - err = xe_vm_lock_dma_resv(vm, &ww, tv_onstack, &tv, &objs, - false, vm->preempt.num_engines); + err = xe_vm_lock_dma_resv(vm, &exec, false, vm->preempt.num_engines); if (err) goto out_unlock_outer; @@ -608,11 +565,11 @@ static void preempt_rebind_work_func(struct work_struct *w) /* Point of no return. */ arm_preempt_fences(vm, &preempt_fences); - resume_and_reinstall_preempt_fences(vm); + resume_and_reinstall_preempt_fences(vm, &exec); up_read(&vm->userptr.notifier_lock); out_unlock: - xe_vm_unlock_dma_resv(vm, tv_onstack, tv, &ww, &objs); + xe_vm_unlock_dma_resv(vm, &exec); out_unlock_outer: if (err == -EAGAIN) { trace_xe_vm_rebind_worker_retry(vm); @@ -963,27 +920,16 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence) static void xe_vma_destroy_unlocked(struct xe_vma *vma) { - struct ttm_validate_buffer tv[2]; - struct ww_acquire_ctx ww; + struct xe_vm *vm = xe_vma_vm(vma); struct xe_bo *bo = xe_vma_bo(vma); - LIST_HEAD(objs); - LIST_HEAD(dups); + struct drm_exec exec; int err; - memset(tv, 0, sizeof(tv)); - tv[0].bo = xe_vm_ttm_bo(xe_vma_vm(vma)); - list_add(&tv[0].head, &objs); - - if (bo) { - tv[1].bo = &xe_bo_get(bo)->ttm; - list_add(&tv[1].head, &objs); - } - err = ttm_eu_reserve_buffers(&ww, &objs, false, &dups); + err = xe_vm_bo_lock(vm, xe_bo_get(bo), &exec, 0, false); XE_WARN_ON(err); - xe_vma_destroy(vma, NULL); + xe_vm_bo_unlock(vm, bo, &exec, false); - ttm_eu_backoff_reservation(&ww, &objs); if (bo) xe_bo_put(bo); } @@ -1254,7 +1200,7 @@ static void vm_error_capture(struct xe_vm *vm, int err, void xe_vm_close_and_put(struct xe_vm *vm) { struct list_head contested; - struct ww_acquire_ctx ww; + struct drm_exec exec; struct xe_device *xe = xe_vm_device(vm); struct xe_gt *gt; struct xe_vma *vma, *next_vma; @@ -1281,7 +1227,7 @@ void xe_vm_close_and_put(struct xe_vm *vm) } down_write(&vm->lock); - xe_vm_lock(vm, &ww, 0, false); + xe_vm_lock(vm, &exec, 0, false); drm_gpuva_iter_for_each(gpuva, it) { vma = gpuva_to_vma(gpuva); @@ -1323,7 +1269,7 @@ void xe_vm_close_and_put(struct xe_vm *vm) NULL); } } - xe_vm_unlock(vm, &ww); + xe_vm_unlock(vm, &exec); /* * VM is now dead, cannot re-add nodes to vm->vmas if it's NULL @@ -1356,7 +1302,7 @@ static void vm_destroy_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, destroy_work); - struct ww_acquire_ctx ww; + struct drm_exec exec; struct xe_device *xe = xe_vm_device(vm); struct xe_gt *gt; u8 id; @@ -1382,14 +1328,14 @@ static void vm_destroy_work_func(struct work_struct *w) * is needed for xe_vm_lock to work. If we remove that dependency this * can be moved to xe_vm_close_and_put. */ - xe_vm_lock(vm, &ww, 0, false); + xe_vm_lock(vm, &exec, 0, false); for_each_gt(gt, xe, id) { if (vm->pt_root[id]) { xe_pt_destroy(vm->pt_root[id], vm->flags, NULL); vm->pt_root[id] = NULL; } } - xe_vm_unlock(vm, &ww); + xe_vm_unlock(vm, &exec); trace_xe_vm_free(vm); dma_fence_put(vm->rebind_fence); @@ -1969,21 +1915,6 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma, #define VM_BIND_OP(op) (op & 0xffff) -struct ttm_buffer_object *xe_vm_ttm_bo(struct xe_vm *vm) -{ - int idx = vm->flags & XE_VM_FLAG_MIGRATION ? - XE_VM_FLAG_GT_ID(vm->flags) : 0; - - /* Safe to use index 0 as all BO in the VM share a single dma-resv lock */ - return &vm->pt_root[idx]->bo->ttm; -} - -static void xe_vm_tv_populate(struct xe_vm *vm, struct ttm_validate_buffer *tv) -{ - tv->num_shared = 1; - tv->bo = xe_vm_ttm_bo(vm); -} - static void vm_set_async_error(struct xe_vm *vm, int err) { lockdep_assert_held(&vm->lock); @@ -2088,7 +2019,7 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, u32 operation, u8 gt_mask, u32 region) { struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL; - struct ww_acquire_ctx ww; + struct drm_exec exec; struct drm_gpuva_ops *ops; struct drm_gpuva_op *__op; struct xe_vma_op *op; @@ -2136,11 +2067,11 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, case XE_VM_BIND_OP_UNMAP_ALL: XE_BUG_ON(!bo); - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return ERR_PTR(err); ops = drm_gpuva_gem_unmap_ops_create(&vm->mgr, obj); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); drm_gpuva_for_each_op(__op, ops) { struct xe_vma_op *op = gpuva_op_to_vma_op(__op); @@ -2174,13 +2105,13 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op, { struct xe_bo *bo = op->gem.obj ? gem_to_xe_bo(op->gem.obj) : NULL; struct xe_vma *vma; - struct ww_acquire_ctx ww; + struct drm_exec exec; int err; lockdep_assert_held_write(&vm->lock); if (bo) { - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return ERR_PTR(err); } @@ -2189,7 +2120,7 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op, op->va.range - 1, read_only, null, gt_mask); if (bo) - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); if (xe_vma_is_userptr(vma)) { err = xe_vma_userptr_pin_pages(vma); @@ -2441,19 +2372,15 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op) static int __xe_vma_op_execute(struct xe_vm *vm, struct xe_vma *vma, struct xe_vma_op *op) { - LIST_HEAD(objs); - LIST_HEAD(dups); - struct ttm_validate_buffer tv_bo, tv_vm; - struct ww_acquire_ctx ww; struct xe_bo *vbo; + struct drm_exec exec; int err; + bool lru_update = op->base.op != DRM_GPUVA_OP_UNMAP; lockdep_assert_held_write(&vm->lock); - xe_vm_tv_populate(vm, &tv_vm); - list_add_tail(&tv_vm.head, &objs); vbo = xe_vma_bo(vma); - if (vbo) { + if (vbo) /* * An unbind can drop the last reference to the BO and * the BO is needed for ttm_eu_backoff_reservation so @@ -2461,22 +2388,15 @@ static int __xe_vma_op_execute(struct xe_vm *vm, struct xe_vma *vma, */ xe_bo_get(vbo); - if (!vbo->vm) { - tv_bo.bo = &vbo->ttm; - tv_bo.num_shared = 1; - list_add(&tv_bo.head, &objs); - } - } - again: - err = ttm_eu_reserve_buffers(&ww, &objs, true, &dups); + err = xe_vm_bo_lock(vm, vbo, &exec, 1, false); if (err) { xe_bo_put(vbo); return err; } xe_vm_assert_held(vm); - xe_bo_assert_held(xe_vma_bo(vma)); + xe_bo_assert_held(vbo); switch (op->base.op) { case DRM_GPUVA_OP_MAP: @@ -2552,7 +2472,7 @@ static int __xe_vma_op_execute(struct xe_vm *vm, struct xe_vma *vma, XE_BUG_ON("NOT POSSIBLE"); } - ttm_eu_backoff_reservation(&ww, &objs); + xe_vm_bo_unlock(vm, vbo, &exec, lru_update); if (err == -EAGAIN && xe_vma_is_userptr(vma)) { lockdep_assert_held_write(&vm->lock); err = xe_vma_userptr_pin_pages(vma); @@ -3208,30 +3128,67 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) return err == -ENODATA ? 0 : err; } -/* - * XXX: Using the TTM wrappers for now, likely can call into dma-resv code - * directly to optimize. Also this likely should be an inline function. - */ -int xe_vm_lock(struct xe_vm *vm, struct ww_acquire_ctx *ww, +int xe_vm_lock(struct xe_vm *vm, struct drm_exec *exec, int num_resv, bool intr) { - struct ttm_validate_buffer tv_vm; - LIST_HEAD(objs); - LIST_HEAD(dups); + int err; - XE_BUG_ON(!ww); + drm_exec_init(exec, intr); + drm_exec_while_not_all_locked(exec) { + err = drm_exec_prepare_obj(exec, xe_vm_gem(vm), + num_resv); + drm_exec_continue_on_contention(exec); + if (err && err != -EALREADY) + goto out_err; + } - tv_vm.num_shared = num_resv; - tv_vm.bo = xe_vm_ttm_bo(vm);; - list_add_tail(&tv_vm.head, &objs); + return 0; - return ttm_eu_reserve_buffers(ww, &objs, intr, &dups); +out_err: + drm_exec_fini(exec); + return err; } -void xe_vm_unlock(struct xe_vm *vm, struct ww_acquire_ctx *ww) +void xe_vm_unlock(struct xe_vm *vm, struct drm_exec *exec) { - dma_resv_unlock(xe_vm_resv(vm)); - ww_acquire_fini(ww); + drm_exec_fini(exec); +} + +int xe_vm_bo_lock(struct xe_vm *vm, struct xe_bo *bo, struct drm_exec *exec, + int num_resv, bool intr) +{ + int err; + + drm_exec_init(exec, intr); + drm_exec_while_not_all_locked(exec) { + err = drm_exec_prepare_obj(exec, xe_vm_gem(vm), + num_resv); + drm_exec_continue_on_contention(exec); + if (err && err != -EALREADY) + goto out_err; + + if (bo && !bo->vm) { + err = drm_exec_prepare_obj(exec, &bo->ttm.base, + num_resv); + drm_exec_continue_on_contention(exec); + if (err && err != -EALREADY) + goto out_err; + } + } + + return 0; + +out_err: + drm_exec_fini(exec); + return err; +} + +void xe_vm_bo_unlock(struct xe_vm *vm, struct xe_bo *bo, struct drm_exec *exec, + bool lru_update) +{ + if (lru_update && bo && (!bo->vm || xe_vm_no_dma_fences(vm))) + ttm_bo_move_to_lru_tail_unlocked(&bo->ttm); + drm_exec_fini(exec); } /** diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index f279fa622260..47b981d9fc04 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -12,6 +12,7 @@ #include "xe_vm_types.h" struct drm_device; +struct drm_exec; struct drm_printer; struct drm_file; @@ -38,10 +39,14 @@ static inline void xe_vm_put(struct xe_vm *vm) kref_put(&vm->refcount, xe_vm_free); } -int xe_vm_lock(struct xe_vm *vm, struct ww_acquire_ctx *ww, +int xe_vm_lock(struct xe_vm *vm, struct drm_exec *exec, int num_resv, bool intr); +void xe_vm_unlock(struct xe_vm *vm, struct drm_exec *exec); -void xe_vm_unlock(struct xe_vm *vm, struct ww_acquire_ctx *ww); +int xe_vm_bo_lock(struct xe_vm *vm, struct xe_bo *bo, struct drm_exec *exec, + int num_resv, bool intr); +void xe_vm_bo_unlock(struct xe_vm *vm, struct xe_bo *bo, struct drm_exec *exec, + bool lru_update); static inline bool xe_vm_is_closed(struct xe_vm *vm) { @@ -219,23 +224,9 @@ int xe_vma_userptr_pin_pages(struct xe_vma *vma); int xe_vma_userptr_check_repin(struct xe_vma *vma); -/* - * XE_ONSTACK_TV is used to size the tv_onstack array that is input - * to xe_vm_lock_dma_resv() and xe_vm_unlock_dma_resv(). - */ -#define XE_ONSTACK_TV 20 -int xe_vm_lock_dma_resv(struct xe_vm *vm, struct ww_acquire_ctx *ww, - struct ttm_validate_buffer *tv_onstack, - struct ttm_validate_buffer **tv, - struct list_head *objs, - bool intr, +int xe_vm_lock_dma_resv(struct xe_vm *vm, struct drm_exec *exec, bool intr, unsigned int num_shared); - -void xe_vm_unlock_dma_resv(struct xe_vm *vm, - struct ttm_validate_buffer *tv_onstack, - struct ttm_validate_buffer *tv, - struct ww_acquire_ctx *ww, - struct list_head *objs); +void xe_vm_unlock_dma_resv(struct xe_vm *vm, struct drm_exec *exec); int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id); diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index 03508645fa08..a68bc6fec1de 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -7,6 +7,7 @@ #include +#include #include #include @@ -28,16 +29,16 @@ static int madvise_preferred_mem_class(struct xe_device *xe, struct xe_vm *vm, for (i = 0; i < num_vmas; ++i) { struct xe_bo *bo; - struct ww_acquire_ctx ww; + struct drm_exec exec; bo = xe_vma_bo(vmas[i]); - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return err; bo->props.preferred_mem_class = value; xe_bo_placement_for_flags(xe, bo, bo->flags); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); } return 0; @@ -53,16 +54,16 @@ static int madvise_preferred_gt(struct xe_device *xe, struct xe_vm *vm, for (i = 0; i < num_vmas; ++i) { struct xe_bo *bo; - struct ww_acquire_ctx ww; + struct drm_exec exec; bo = xe_vma_bo(vmas[i]); - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return err; bo->props.preferred_gt = value; xe_bo_placement_for_flags(xe, bo, bo->flags); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); } return 0; @@ -89,17 +90,17 @@ static int madvise_preferred_mem_class_gt(struct xe_device *xe, for (i = 0; i < num_vmas; ++i) { struct xe_bo *bo; - struct ww_acquire_ctx ww; + struct drm_exec exec; bo = xe_vma_bo(vmas[i]); - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return err; bo->props.preferred_mem_class = mem_class; bo->props.preferred_gt = gt_id; xe_bo_placement_for_flags(xe, bo, bo->flags); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); } return 0; @@ -112,13 +113,13 @@ static int madvise_cpu_atomic(struct xe_device *xe, struct xe_vm *vm, for (i = 0; i < num_vmas; ++i) { struct xe_bo *bo; - struct ww_acquire_ctx ww; + struct drm_exec exec; bo = xe_vma_bo(vmas[i]); if (XE_IOCTL_ERR(xe, !(bo->flags & XE_BO_CREATE_SYSTEM_BIT))) return -EINVAL; - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return err; bo->props.cpu_atomic = !!value; @@ -130,7 +131,7 @@ static int madvise_cpu_atomic(struct xe_device *xe, struct xe_vm *vm, */ if (bo->props.cpu_atomic) ttm_bo_unmap_virtual(&bo->ttm); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); } return 0; @@ -143,18 +144,18 @@ static int madvise_device_atomic(struct xe_device *xe, struct xe_vm *vm, for (i = 0; i < num_vmas; ++i) { struct xe_bo *bo; - struct ww_acquire_ctx ww; + struct drm_exec exec; bo = xe_vma_bo(vmas[i]); if (XE_IOCTL_ERR(xe, !(bo->flags & XE_BO_CREATE_VRAM0_BIT) && !(bo->flags & XE_BO_CREATE_VRAM1_BIT))) return -EINVAL; - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return err; bo->props.device_atomic = !!value; - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); } return 0; @@ -174,16 +175,16 @@ static int madvise_priority(struct xe_device *xe, struct xe_vm *vm, for (i = 0; i < num_vmas; ++i) { struct xe_bo *bo; - struct ww_acquire_ctx ww; + struct drm_exec exec; bo = xe_vma_bo(vmas[i]); - err = xe_bo_lock(bo, &ww, 0, true); + err = xe_bo_lock(bo, &exec, 0, true); if (err) return err; bo->ttm.priority = value; ttm_bo_move_to_lru_tail(&bo->ttm); - xe_bo_unlock(bo, &ww); + xe_bo_unlock(bo, &exec); } return 0; diff --git a/include/drm/drm_gpuva_mgr.h b/include/drm/drm_gpuva_mgr.h index 943c8fcda533..a2f6d90ac899 100644 --- a/include/drm/drm_gpuva_mgr.h +++ b/include/drm/drm_gpuva_mgr.h @@ -32,6 +32,8 @@ #include #include +#include + struct drm_gpuva_manager; struct drm_gpuva_fn_ops; struct drm_gpuva_prealloc; @@ -169,9 +171,17 @@ struct drm_gpuva *drm_gpuva_find_next(struct drm_gpuva_manager *mgr, u64 end); bool drm_gpuva_interval_empty(struct drm_gpuva_manager *mgr, u64 addr, u64 range); -void drm_gpuva_add_fence(struct drm_gpuva_manager *mgr, struct dma_fence *fence, - enum dma_resv_usage private_usage, - enum dma_resv_usage extobj_usage); +int drm_gpuva_manager_lock(struct drm_gpuva_manager *mgr, struct drm_exec *exec, + struct drm_gem_object *mgr_obj, bool intr, + unsigned int num_fences); +void drm_gpuva_manager_unlock(struct drm_gpuva_manager *mgr, + struct drm_exec *exec); + +void drm_gpuva_manager_add_fence(struct drm_gpuva_manager *mgr, + struct drm_exec *exec, + struct dma_fence *fence, + enum dma_resv_usage private_usage, + enum dma_resv_usage extobj_usage); /** * drm_gpuva_evict - sets whether the backing GEM of this &drm_gpuva is evicted -- 2.34.1