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 E97B8D2ECF7 for ; Tue, 20 Jan 2026 06:09:22 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id AA0C110E554; Tue, 20 Jan 2026 06:09:22 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="G4HoSJba"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.13]) by gabe.freedesktop.org (Postfix) with ESMTPS id 887CB10E074 for ; Tue, 20 Jan 2026 06:09:20 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1768889360; x=1800425360; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=+ytDiaTYYyI55zUDWdNxSw+Z37XED+1MqnCR4ZtzA+A=; b=G4HoSJbaoUPZ/poLRuZLX2rEjq66I7ABSQv6JvC7stHHDNJwBB++ToJ+ GT80Z0bChGXTC+1kMEOQR+ufCIPKTAKA27/d2o+LFZWHmAXpLRiF1KUd6 n6A2pQ1p3uTDIaAuEz0zB8ESnInK4gw3R+hg+snAGF+wWn+XnFl28CFM9 qzFxjySo5X8hBpUNwcPIb2OgU3mwLJ/Y55o8nTAdcf9nLrV+ebM53D1B3 9jbTM3iYIz63Z7zS35sE46QHWBFJ+5l6tMAApui6ajn01wj+jEScn5gZU pc+LOtSXjIZhq4yRo/OnQY6vYJ8JJfDKQZ0SrjT4OFW0zgM1yrUPbwZX0 Q==; X-CSE-ConnectionGUID: YyTfVMjZSqed+rGR+fuxbQ== X-CSE-MsgGUID: krreiCJ2Q0mm/MxbqScosQ== X-IronPort-AV: E=McAfee;i="6800,10657,11676"; a="72676983" X-IronPort-AV: E=Sophos;i="6.21,240,1763452800"; d="scan'208";a="72676983" Received: from fmviesa007.fm.intel.com ([10.60.135.147]) by fmvoesa107.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 19 Jan 2026 22:09:20 -0800 X-CSE-ConnectionGUID: qyM3GWYBTnmHdhlFJQ494w== X-CSE-MsgGUID: z6J9GShETTORc4XRHbzgJQ== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.21,240,1763452800"; d="scan'208";a="205658600" Received: from varungup-desk.iind.intel.com ([10.190.238.71]) by fmviesa007-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 19 Jan 2026 22:09:18 -0800 From: Arvind Yadav To: intel-xe@lists.freedesktop.org Cc: matthew.brost@intel.com, himal.prasad.ghimiray@intel.com, thomas.hellstrom@linux.intel.com, pallavi.mishra@intel.com Subject: [PATCH v4 3/8] drm/xe/madvise: Implement purgeable buffer object support Date: Tue, 20 Jan 2026 11:38:49 +0530 Message-ID: <20260120060900.3137984-4-arvind.yadav@intel.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20260120060900.3137984-1-arvind.yadav@intel.com> References: <20260120060900.3137984-1-arvind.yadav@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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: , Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" This allows userspace applications to provide memory usage hints to the kernel for better memory management under pressure: Add the core implementation for purgeable buffer objects, enabling memory reclamation of user-designated DONTNEED buffers during eviction. This patch implements the purge operation and state machine transitions: Purgeable States (from xe_madv_purgeable_state): - WILLNEED (0): BO should be retained, actively used - DONTNEED (1): BO eligible for purging, not currently needed - PURGED (2): BO backing store reclaimed, permanently invalid Design Rationale: - Async TLB invalidation via trigger_rebind (no blocking xe_vm_invalidate_vma) - i915 compatibility: retained field, "once purged always purged" semantics - Shared BO protection prevents multi-process memory corruption - Scratch PTE reuse avoids new infrastructure, safe for fault mode v2: - Use xe_bo_trigger_rebind() for async TLB invalidation (Thomas Hellström) - Add NULL rebind with scratch PTEs for fault mode (Thomas Hellström) - Implement i915-compatible retained field logic (Thomas Hellström) - Skip BO validation for purged BOs in page fault handler (crash fix) - Add scratch VM check in page fault path (non-scratch VMs fail fault) - Force clear_pt for non-scratch VMs to avoid phys addr 0 mapping (review fix) - Add !is_purged check to resource cursor setup to prevent stale access v3: - Rebase as xe_gt_pagefault.c is gone upstream and replaced with xe_pagefault.c (Matthew Brost) - Xe specific warn on (Matthew Brost) - Call helpers for madv_purgeable access(Matthew Brost) - Remove bo NULL check(Matthew Brost) - Use xe_bo_assert_held instead of dma assert(Matthew Brost) - Move the xe_bo_is_purged check under the dma-resv lock( by Matt) - Drop is_purged from xe_pt_stage_bind_entry and just set is_null to true for purged BO rename s/is_null/is_null_or_purged (by Matt) - UAPI rule should not be changed.(Matthew Brost) - Make 'retained' a userptr (Matthew Brost) v4: - @madv_purgeable atomic_t → u32 change across all relevant patches. (Matt) Cc: Matthew Brost Cc: Thomas Hellström Cc: Himal Prasad Ghimiray Signed-off-by: Arvind Yadav --- drivers/gpu/drm/xe/xe_bo.c | 61 +++++++++++++++++---- drivers/gpu/drm/xe/xe_pagefault.c | 12 ++++ drivers/gpu/drm/xe/xe_pt.c | 38 +++++++++++-- drivers/gpu/drm/xe/xe_vm.c | 11 +++- drivers/gpu/drm/xe/xe_vm_madvise.c | 88 ++++++++++++++++++++++++++++++ 5 files changed, 191 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 408c74216fdf..d0a6d340b255 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -836,6 +836,43 @@ static int xe_bo_move_notify(struct xe_bo *bo, return 0; } +/** + * xe_ttm_bo_purge() - Purge buffer object backing store + * @ttm_bo: The TTM buffer object to purge + * @ctx: TTM operation context + * + * This function purges the backing store of a BO marked as DONTNEED and + * triggers rebind to invalidate stale GPU mappings. For fault-mode VMs, + * this zaps the PTEs. The next GPU access will trigger a page fault and + * perform NULL rebind (scratch pages or clear PTEs based on VM config). + */ +static void xe_ttm_bo_purge(struct ttm_buffer_object *ttm_bo, struct ttm_operation_ctx *ctx) +{ + struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev); + struct xe_bo *bo = ttm_to_xe_bo(ttm_bo); + + if (ttm_bo->ttm) { + struct ttm_placement place = {}; + int ret = ttm_bo_validate(ttm_bo, &place, ctx); + + drm_WARN_ON(&xe->drm, ret); + if (!ret) { + if (xe_bo_madv_is_dontneed(bo)) { + bo->madv_purgeable = XE_MADV_PURGEABLE_PURGED; + + /* + * Trigger rebind to invalidate stale GPU mappings. + * - Non-fault mode: Marks VMAs for rebind + * - Fault mode: Zaps PTEs (sets to 0), next access triggers fault + * and NULL rebind with scratch/clear PTEs per VM config + */ + ret = xe_bo_trigger_rebind(xe, bo, ctx); + XE_WARN_ON(ret); + } + } + } +} + static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, struct ttm_operation_ctx *ctx, struct ttm_resource *new_mem, @@ -855,6 +892,15 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, ttm && ttm_tt_is_populated(ttm)) ? true : false; int ret = 0; + /* + * Purge only non-shared BOs explicitly marked DONTNEED by userspace. + * The move_notify callback will handle invalidation asynchronously. + */ + if (evict && xe_bo_madv_is_dontneed(bo)) { + xe_ttm_bo_purge(ttm_bo, ctx); + return 0; + } + /* Bo creation path, moving to system or TT. */ if ((!old_mem && ttm) && !handle_system_ccs) { if (new_mem->mem_type == XE_PL_TT) @@ -1604,18 +1650,6 @@ static void xe_ttm_bo_delete_mem_notify(struct ttm_buffer_object *ttm_bo) } } -static void xe_ttm_bo_purge(struct ttm_buffer_object *ttm_bo, struct ttm_operation_ctx *ctx) -{ - struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev); - - if (ttm_bo->ttm) { - struct ttm_placement place = {}; - int ret = ttm_bo_validate(ttm_bo, &place, ctx); - - drm_WARN_ON(&xe->drm, ret); - } -} - static void xe_ttm_bo_swap_notify(struct ttm_buffer_object *ttm_bo) { struct ttm_operation_ctx ctx = { @@ -2196,6 +2230,9 @@ struct xe_bo *xe_bo_init_locked(struct xe_device *xe, struct xe_bo *bo, #endif INIT_LIST_HEAD(&bo->vram_userfault_link); + /* Initialize purge advisory state */ + bo->madv_purgeable = XE_MADV_PURGEABLE_WILLNEED; + drm_gem_private_object_init(&xe->drm, &bo->ttm.base, size); if (resv) { diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c index 6bee53d6ffc3..e3ace179e9cf 100644 --- a/drivers/gpu/drm/xe/xe_pagefault.c +++ b/drivers/gpu/drm/xe/xe_pagefault.c @@ -59,6 +59,18 @@ static int xe_pagefault_begin(struct drm_exec *exec, struct xe_vma *vma, if (!bo) return 0; + /* + * Check if BO is purged (under dma-resv lock). + * For purged BOs: + * - Scratch VMs: Skip validation, rebind will use scratch PTEs + * - Non-scratch VMs: FAIL the page fault (no scratch page available) + */ + if (unlikely(xe_bo_is_purged(bo))) { + if (!xe_vm_has_scratch(vm)) + return -EACCES; + return 0; + } + return need_vram_move ? xe_bo_migrate(bo, vram->placement, NULL, exec) : xe_bo_validate(bo, vm, true, exec); } diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 6703a7049227..c8c66300e25b 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -533,20 +533,26 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset, /* Is this a leaf entry ?*/ if (level == 0 || xe_pt_hugepte_possible(addr, next, level, xe_walk)) { struct xe_res_cursor *curs = xe_walk->curs; - bool is_null = xe_vma_is_null(xe_walk->vma); - bool is_vram = is_null ? false : xe_res_is_vram(curs); + struct xe_bo *bo = xe_vma_bo(xe_walk->vma); + bool is_null_or_purged = xe_vma_is_null(xe_walk->vma) || + (bo && xe_bo_is_purged(bo)); + bool is_vram = is_null_or_purged ? false : xe_res_is_vram(curs); XE_WARN_ON(xe_walk->va_curs_start != addr); if (xe_walk->clear_pt) { pte = 0; } else { - pte = vm->pt_ops->pte_encode_vma(is_null ? 0 : + /* + * For purged BOs, treat like null VMAs - pass address 0. + * The pte_encode_vma will set XE_PTE_NULL flag for scratch mapping. + */ + pte = vm->pt_ops->pte_encode_vma(is_null_or_purged ? 0 : xe_res_dma(curs) + xe_walk->dma_offset, xe_walk->vma, pat_index, level); - if (!is_null) + if (!is_null_or_purged) pte |= is_vram ? xe_walk->default_vram_pte : xe_walk->default_system_pte; @@ -570,7 +576,7 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset, if (unlikely(ret)) return ret; - if (!is_null && !xe_walk->clear_pt) + if (!is_null_or_purged && !xe_walk->clear_pt) xe_res_next(curs, next - addr); xe_walk->va_curs_start = next; xe_walk->vma->gpuva.flags |= (XE_VMA_PTE_4K << level); @@ -723,6 +729,26 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, }; struct xe_pt *pt = vm->pt_root[tile->id]; int ret; + bool is_purged = false; + + /* + * Check if BO is purged: + * - Scratch VMs: Use scratch PTEs (XE_PTE_NULL) for safe zero reads + * - Non-scratch VMs: Clear PTEs to zero (non-present) to avoid mapping to phys addr 0 + * + * For non-scratch VMs, we force clear_pt=true so leaf PTEs become completely + * zero instead of creating a PRESENT mapping to physical address 0. + */ + if (bo && xe_bo_is_purged(bo)) { + is_purged = true; + + /* + * For non-scratch VMs, a NULL rebind should use zero PTEs + * (non-present), not a present PTE to phys 0. + */ + if (!xe_vm_has_scratch(vm)) + xe_walk.clear_pt = true; + } if (range) { /* Move this entire thing to xe_svm.c? */ @@ -762,7 +788,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, if (!range) xe_bo_assert_held(bo); - if (!xe_vma_is_null(vma) && !range) { + if (!xe_vma_is_null(vma) && !range && !is_purged) { if (xe_vma_is_userptr(vma)) xe_res_first_dma(to_userptr_vma(vma)->userptr.pages.dma_addr, 0, xe_vma_size(vma), &curs); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 694f592a0f01..c3a5fe76ff96 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1359,6 +1359,9 @@ static u64 xelp_pte_encode_bo(struct xe_bo *bo, u64 bo_offset, static u64 xelp_pte_encode_vma(u64 pte, struct xe_vma *vma, u16 pat_index, u32 pt_level) { + struct xe_bo *bo = xe_vma_bo(vma); + struct xe_vm *vm = xe_vma_vm(vma); + pte |= XE_PAGE_PRESENT; if (likely(!xe_vma_read_only(vma))) @@ -1367,7 +1370,13 @@ static u64 xelp_pte_encode_vma(u64 pte, struct xe_vma *vma, pte |= pte_encode_pat_index(pat_index, pt_level); pte |= pte_encode_ps(pt_level); - if (unlikely(xe_vma_is_null(vma))) + /* + * NULL PTEs redirect to scratch page (return zeros on read). + * Set for: 1) explicit null VMAs, 2) purged BOs on scratch VMs. + * Never set NULL flag without scratch page - causes undefined behavior. + */ + if (unlikely(xe_vma_is_null(vma) || + (bo && xe_bo_is_purged(bo) && xe_vm_has_scratch(vm)))) pte |= XE_PTE_NULL; return pte; diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index add9a6ca2390..dfeab9e24a09 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -179,6 +179,56 @@ static void madvise_pat_index(struct xe_device *xe, struct xe_vm *vm, } } +/* + * Handle purgeable buffer object advice for DONTNEED/WILLNEED/PURGED. + * Returns true if any BO was purged, false otherwise. + * Caller must copy retained value to userspace after releasing locks. + */ +static bool xe_vm_madvise_purgeable_bo(struct xe_device *xe, struct xe_vm *vm, + struct xe_vma **vmas, int num_vmas, + struct drm_xe_madvise *op) +{ + bool has_purged_bo = false; + int i; + + xe_assert(vm->xe, op->type == DRM_XE_VMA_ATTR_PURGEABLE_STATE); + + for (i = 0; i < num_vmas; i++) { + struct xe_bo *bo = xe_vma_bo(vmas[i]); + + if (!bo) + continue; + + /* BO must be locked before modifying madv state */ + xe_bo_assert_held(bo); + + /* + * Once purged, always purged. Cannot transition back to WILLNEED. + * This matches i915 semantics where purged BOs are permanently invalid. + */ + if (xe_bo_is_purged(bo)) { + has_purged_bo = true; + continue; + } + + switch (op->purge_state_val.val) { + case DRM_XE_VMA_PURGEABLE_STATE_WILLNEED: + bo->madv_purgeable = XE_MADV_PURGEABLE_WILLNEED; + break; + case DRM_XE_VMA_PURGEABLE_STATE_DONTNEED: + bo->madv_purgeable = XE_MADV_PURGEABLE_DONTNEED; + break; + default: + drm_warn(&vm->xe->drm, "Invalid madvice value = %d\n", + op->purge_state_val.val); + return false; + } + } + + /* Return whether any BO was purged; caller will copy to user after unlocking */ + return has_purged_bo; +} + typedef void (*madvise_func)(struct xe_device *xe, struct xe_vm *vm, struct xe_vma **vmas, int num_vmas, struct drm_xe_madvise *op, @@ -306,6 +356,16 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv return false; break; } + case DRM_XE_VMA_ATTR_PURGEABLE_STATE: + { + u32 val = args->purge_state_val.val; + + if (XE_IOCTL_DBG(xe, !(val == DRM_XE_VMA_PURGEABLE_STATE_WILLNEED || + val == DRM_XE_VMA_PURGEABLE_STATE_DONTNEED))) + return false; + + break; + } default: if (XE_IOCTL_DBG(xe, 1)) return false; @@ -465,6 +525,34 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil goto err_fini; } } + if (args->type == DRM_XE_VMA_ATTR_PURGEABLE_STATE) { + bool has_purged_bo; + + has_purged_bo = xe_vm_madvise_purgeable_bo(xe, vm, madvise_range.vmas, + madvise_range.num_vmas, args); + + /* Release BO locks */ + drm_exec_fini(&exec); + kfree(madvise_range.vmas); + up_write(&vm->lock); + + /* + * Set retained flag to indicate if backing store still exists. + * Matches i915: retained = 1 if not purged, 0 if purged. + * Must copy_to_user AFTER releasing ALL locks to avoid circular dependency. + */ + if (args->purge_state_val.retained) { + u32 retained = !has_purged_bo; + + if (copy_to_user(u64_to_user_ptr(args->purge_state_val.retained), + &retained, sizeof(retained))) + drm_warn(&vm->xe->drm, "Failed to copy retained value to user\n"); + } + + /* Final cleanup for early return */ + xe_vm_put(vm); + return 0; + } } if (madvise_range.has_svm_userptr_vmas) { -- 2.43.0