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 E9030C43458 for ; Fri, 3 Jul 2026 13:06:57 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 3AA3B10E5F0; Fri, 3 Jul 2026 13:06:57 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="cBXq14R4"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.21]) by gabe.freedesktop.org (Postfix) with ESMTPS id 673D710E5F0; Fri, 3 Jul 2026 13:06:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1783084016; x=1814620016; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=FsvkI3LOasYuprXDVfPJVH1qnNqYfZwMGOjwjiJ3aL0=; b=cBXq14R4ww2dyAd5TLmfXm/I4folcEikME6sdCnkGO0teG6CkKYMyErl /LVwDIQA7Ck5yWtJapNSpVFMLgMBH0P+mDP50qpQPbmv8wVYa41AwCnvQ w+m5LN8s2sfLGc4iGxA/FQ4Rt1Fgyj1Zzqabze5oWFnM50UFJmq1Nj+7+ /lBNsbsJSveky6NOUALVqx9re4T0ZJW8UUwM7Our5d/+vfyLuUcB1ZhzK U/SjwsRYWmzLG9tjT/mbYk5HRkyzGGtM8GpK7spyuUCD0RwAMlTecdwnP qxDHKJn5KHQH7OgL2ZG+MF6ZPdUeIgIvgLAoZ1Db2889+B4mkjm2StEvX A==; X-CSE-ConnectionGUID: oTxH49ssRSOEJbKIH5LS9g== X-CSE-MsgGUID: oojAVkQvRwm0PDcj1skGmw== X-IronPort-AV: E=McAfee;i="6800,10657,11835"; a="83702352" X-IronPort-AV: E=Sophos;i="6.25,145,1779174000"; d="scan'208";a="83702352" Received: from orviesa002.jf.intel.com ([10.64.159.142]) by orvoesa113.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 03 Jul 2026 06:06:56 -0700 X-CSE-ConnectionGUID: Vgujm9BnQfaZi3fIOqergQ== X-CSE-MsgGUID: QlJnEeKOSzq+JFbiqdzC8Q== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.25,145,1779174000"; d="scan'208";a="283199598" Received: from smoticic-mobl1.ger.corp.intel.com (HELO fedora) ([10.245.245.146]) by orviesa002-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 03 Jul 2026 06:06:51 -0700 From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= To: intel-xe@lists.freedesktop.org Cc: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= , Natalie Vock , Johannes Weiner , Tejun Heo , =?UTF-8?q?Michal=20Koutn=C3=BD?= , cgroups@vger.kernel.org, Huang Rui , Matthew Brost , Matthew Auld , Maarten Lankhorst , Maxime Ripard , Thomas Zimmermann , Simona Vetter , David Airlie , =?UTF-8?q?Christian=20K=C3=B6nig?= , Thadeu Lima de Souza Cascardo , Alex Deucher , Rodrigo Vivi , dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org, linux-kernel@vger.kernel.org Subject: [PATCH v7 5/6] drm/xe: Wire up dmem cgroup reclaim for VRAM manager Date: Fri, 3 Jul 2026 15:05:40 +0200 Message-ID: <20260703130541.2686-6-thomas.hellstrom@linux.intel.com> X-Mailer: git-send-email 2.54.0 In-Reply-To: <20260703130541.2686-1-thomas.hellstrom@linux.intel.com> References: <20260703130541.2686-1-thomas.hellstrom@linux.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" Register the VRAM manager with the dmem cgroup reclaim infrastructure so that lowering dmem.max below current VRAM usage triggers TTM eviction rather than failing with -EBUSY. v4: - Rebased on drm-tip; dropped the XE_PL_STOLEN guard as stolen memory uses a separate TTM manager and never calls __xe_ttm_vram_mgr_init(). v5: - Rebased on the introduction of struct dmem_cgroup_init. - Register the fini drmm action before drmm_cgroup_register_region() so that devres LIFO teardown runs unregister_region() first (draining any in-flight reclaim callbacks via the rwsem) and xe_ttm_vram_mgr_fini() second, ensuring the manager is never accessed by a reclaim callback after teardown. (Sashiko-bot) - Wrap the reclaim callback in xe_ttm_vram_mgr_dmem_reclaim() using drm_dev_enter()/drm_dev_exit() to prevent TTM reclaim from running after driver unbind. Assisted-by: GitHub_Copilot:claude-sonnet-4.6 Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 54 +++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c index 308fda4248eb..b2500344cd57 100644 --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c @@ -276,6 +276,28 @@ static const struct ttm_resource_manager_func xe_ttm_vram_mgr_func = { .debug = xe_ttm_vram_mgr_debug }; +static const struct dmem_cgroup_ops xe_ttm_vram_mgr_dmem_ops; + +static int xe_ttm_vram_mgr_dmem_reclaim(struct dmem_cgroup_pool_state *pool, + u64 target_bytes, void *priv) +{ + struct ttm_resource_manager *man = priv; + struct xe_device *xe = ttm_to_xe_device(man->bdev); + int ret, idx; + + if (!drm_dev_enter(&xe->drm, &idx)) + return -ENODEV; + + ret = ttm_resource_manager_dmem_reclaim(pool, target_bytes, priv); + + drm_dev_exit(idx); + return ret; +} + +static const struct dmem_cgroup_ops xe_ttm_vram_mgr_dmem_ops = { + .reclaim = xe_ttm_vram_mgr_dmem_reclaim, +}; + static void xe_ttm_vram_mgr_fini(struct drm_device *dev, void *arg) { struct xe_device *xe = to_xe_device(dev); @@ -301,17 +323,10 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr, u64 default_page_size) { struct ttm_resource_manager *man = &mgr->manager; + struct dmem_cgroup_region *cg; const char *name; int err; - name = mem_type == XE_PL_VRAM0 ? "vram0" : "vram1"; - man->cg = drmm_cgroup_register_region(&xe->drm, name, - &(struct dmem_cgroup_init){ - .size = size, - }); - if (IS_ERR(man->cg)) - return PTR_ERR(man->cg); - man->func = &xe_ttm_vram_mgr_func; mgr->mem_type = mem_type; err = drmm_mutex_init(&xe->drm, &mgr->lock); @@ -330,7 +345,28 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr, ttm_set_driver_manager(&xe->ttm, mem_type, &mgr->manager); ttm_resource_manager_set_used(&mgr->manager, true); - return drmm_add_action_or_reset(&xe->drm, xe_ttm_vram_mgr_fini, mgr); + /* + * Register the fini action before the cgroup region so that devres + * LIFO teardown runs unregister_region first (draining any in-flight + * reclaim callbacks) and the manager fini second. + */ + err = drmm_add_action_or_reset(&xe->drm, xe_ttm_vram_mgr_fini, mgr); + if (err) + return err; + + name = mem_type == XE_PL_VRAM0 ? "vram0" : "vram1"; + cg = drmm_cgroup_register_region(&xe->drm, name, + &(struct dmem_cgroup_init){ + .size = size, + .ops = &xe_ttm_vram_mgr_dmem_ops, + .reclaim_priv = man, + }); + if (IS_ERR(cg)) + return PTR_ERR(cg); + + ttm_resource_manager_set_dmem_region(man, cg); + + return 0; } /** -- 2.54.0