From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 29DED4183CC; Thu, 11 Jun 2026 14:23:30 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.19 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1781187811; cv=none; b=CAdSr209J+K8oJJRJu6YdEHCEXP6b6AZJjHL1lkDLNyLtoIKpVoNFzuiUWeQ8SyyV7G1UXh6220/q+M32uF0kyUZiGhBvo/IFfmv+fd4nSA6UlHZXCWo2OWQwo+KSclZSPFjldqB72ZRxTSX/dSWKKH5aFZ+Ci8whRFDUaMt90c= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1781187811; c=relaxed/simple; bh=FsvkI3LOasYuprXDVfPJVH1qnNqYfZwMGOjwjiJ3aL0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=jVNArXTe9253YyptXQ3sVKqbCxjaboX6Za+NppcRFf93ivzLvUSRxKClhj9O/FgR+TsT/XGzBfAUoWcn//C4BgVOq/LWSnmu9Ly14oc7hyG6IjamX//JeMTPe48S92FZRBFSrKBhPXMIyTMOuC4xYPaMjyLK3P3pOjLYm3eVuC0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com; spf=pass smtp.mailfrom=linux.intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=llPrgSha; arc=none smtp.client-ip=198.175.65.19 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="llPrgSha" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1781187810; x=1812723810; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=FsvkI3LOasYuprXDVfPJVH1qnNqYfZwMGOjwjiJ3aL0=; b=llPrgShaQTkXJC2HcU9eQw1WeMtMWzbqWVJULS+OcNl2qBCuFAgPfP6M nUmmr1/OQdo68+rzSE48YB8bRgMQ7H25iv14z5DRZUy04MKVL2pB1n2ML FzqCUBeZQ7qL1WB4Jqcqm45B21M8O9OnKAUA3QdOlOb/SKqnb01l1I2a5 ZHjJRkMC15Kh007nABBSle9566ZX8Om7+5B8Ky5V6hhAAE5DNoO6vgw0g +lAC03CSpnkm4ZpHWhWJiGspS/Wv73XdSOma3MqQKGsfUOS4QUE31Xd55 YJxQ4We/7KOgKmENI8yqhe2ZJDgM6EDEPyLg2pf1owFa82SwRCSIUnAUP g==; X-CSE-ConnectionGUID: waLMmPqBQaO24s7axQZ7Mg== X-CSE-MsgGUID: QrBv77R+Qg6a4NWLqEElvg== X-IronPort-AV: E=McAfee;i="6800,10657,11813"; a="81983445" X-IronPort-AV: E=Sophos;i="6.24,199,1774335600"; d="scan'208";a="81983445" Received: from orviesa001.jf.intel.com ([10.64.159.141]) by orvoesa111.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Jun 2026 07:23:30 -0700 X-CSE-ConnectionGUID: iEq5kIJUSpuBvxUHauSL0w== X-CSE-MsgGUID: eefaeiGmRd+c6DId46Vv1g== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.24,199,1774335600"; d="scan'208";a="284574360" Received: from amilburn-desk.amilburn-desk (HELO fedora) ([10.245.244.169]) by smtpauth.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Jun 2026 07:23:26 -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?= , Alex Deucher , Rodrigo Vivi , dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org, linux-kernel@vger.kernel.org Subject: [PATCH v5 5/6] drm/xe: Wire up dmem cgroup reclaim for VRAM manager Date: Thu, 11 Jun 2026 16:22:41 +0200 Message-ID: <20260611142242.2529-6-thomas.hellstrom@linux.intel.com> X-Mailer: git-send-email 2.54.0 In-Reply-To: <20260611142242.2529-1-thomas.hellstrom@linux.intel.com> References: <20260611142242.2529-1-thomas.hellstrom@linux.intel.com> Precedence: bulk X-Mailing-List: cgroups@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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