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 E5CE9C44500 for ; Fri, 3 Jul 2026 13:07:02 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 441EB10F7FE; Fri, 3 Jul 2026 13:07:02 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="Eum6qo8r"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.21]) by gabe.freedesktop.org (Postfix) with ESMTPS id 066A910F7E7; Fri, 3 Jul 2026 13:07:01 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1783084021; x=1814620021; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=XSSDJV30Wd36wi5sy2k20vmQlCp9wnUmTE7Bqh02MqY=; b=Eum6qo8rkSNINZ7E0qdUY9xCF2Wem9GMEHr/6LE1s5qnXnq4CXKTFnpL qV1H+0qq+c8TRHdtQ0Mgqbd9Yai4ZZ4wDa/CanOuuLLXndXzCJntxkwLW Wpg0i3ltwr3Vmp5WmNeNc7EOmkPPKuC5f0cz1Om/UyBklb4y4mrpmCWcx OabQXcGvRqsjkTv3O/fO7/G/Fu4je4u8ysbe/L2e3t/Ot5hzlKwE8fHni ih8lrxjWy6KyN0QYGHgxYnhGkvmDRYPict+zpM+YLtsN53ULOf1UH4+8/ Eo0Obq8NdwsRVdKnbhA2zqQSyemiZ9oAGAFyuAWp21Du9pOpErCt39p6O A==; X-CSE-ConnectionGUID: K5tctkTyQ4ie+vtxkMyfeA== X-CSE-MsgGUID: skFbI7aHSxSZI3uEW/9Zew== X-IronPort-AV: E=McAfee;i="6800,10657,11835"; a="83702363" X-IronPort-AV: E=Sophos;i="6.25,145,1779174000"; d="scan'208";a="83702363" 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 06:07:00 -0700 X-CSE-ConnectionGUID: dh7u1I78TRa7zRw2Z+fQVA== X-CSE-MsgGUID: DgTimVrMQFGdFTFjNIYARg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.25,145,1779174000"; d="scan'208";a="283199605" 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 06:06:56 -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 6/6] drm/amdgpu: Wire up dmem cgroup reclaim for VRAM manager Date: Fri, 3 Jul 2026 15:05:41 +0200 Message-ID: <20260703130541.2686-7-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. Guard place->flags in amdgpu_ttm_bo_eviction_valuable() against NULL, as the TTM reclaim path passes a NULL place in cgroup drain mode. Use drmm_cgroup_register_region() so that the region is automatically unregistered at DRM device release, after drm_dev_unplug() has already made drm_dev_enter() return false. The drm_dev_enter/exit guard in the reclaim callback ensures no reclaim work touches the TTM manager after driver unbind, closing the window between vram_mgr_fini() (called from drm_driver.release) and the drmm cleanup that unregisters the region. v3: - Rebased on fix for uninitialized list and buddy allocator on the drmm_cgroup_register_region() error path. v5: - Rebased on the introduction of struct dmem_cgroup_init. - Clear the reclaim callback in amdgpu_vram_mgr_fini() to prevent use-after-free if cgroup reclaim is triggered after driver unbind while userspace holds an open DRM file descriptor. (Sashiko-bot) - Switch from drmm_cgroup_register_region() to the raw dmem_cgroup_register_region() and store the region in amdgpu_vram_mgr.cg_region. Call dmem_cgroup_unregister_region() in amdgpu_vram_mgr_fini() after ttm_resource_manager_evict_all() to drain in-flight reclaim callbacks, and clear man->cg afterwards. This is required because amdgpu's vram manager fini is called explicitly during driver unbind, which may precede the DRM device release and thus precede any drmm-based cleanup. (Sashiko-bot) v6: - Fix mgr->cg_region never being assigned, so dmem_cgroup_unregister_region() in fini silently no-ops on NULL and leaks the region. (Sashiko-bot) - Reorder fini to call set_used(false) and evict_all() before dmem_cgroup_unregister_region(), so ttm_resource_free() can uncharge via man->cg during eviction; clear man->cg after unregister. (Sashiko-bot) v7: - Move dmem_cgroup_unregister_region() before the early return on evict_all() failure; not doing so leaves a dangling reclaim callback pointing to the partially-torn-down VRAM manager, causing a use-after-free when the cgroup later triggers reclaim. (Sashiko-bot) - Switch back to drmm_cgroup_register_region() with a drm_dev_enter/ exit guard in the reclaim callback (matching xe), rather than manual register/unregister. drm_dev_unplug() fires before vram_mgr_fini(), so drm_dev_enter() returning false prevents any reclaim from touching the manager during teardown. This also fixes the "vram" name collision on multi-GPU systems, since drmm_cgroup_register_region() automatically prefixes with "drm//". (Sashiko-bot) Assisted-by: GitHub_Copilot:claude-sonnet-4.6 Signed-off-by: Thomas Hellström --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 37 +++++++++++++++++--- 2 files changed, 33 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 025625e7e800..58bb21451826 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1507,7 +1507,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, dma_resv_for_each_fence(&resv_cursor, bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, f) { if (amdkfd_fence_check_mm(f, current->mm) && - !(place->flags & TTM_PL_FLAG_CONTIGUOUS)) + !(place && (place->flags & TTM_PL_FLAG_CONTIGUOUS))) return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 08f05c3aed1d..9b9d738ba794 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -906,6 +906,28 @@ static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = { .debug = amdgpu_vram_mgr_debug }; +static const struct dmem_cgroup_ops amdgpu_vram_mgr_dmem_ops; + +static int amdgpu_vram_mgr_dmem_reclaim(struct dmem_cgroup_pool_state *pool, + u64 target_bytes, void *priv) +{ + struct ttm_resource_manager *man = priv; + struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev); + int ret, idx; + + if (!drm_dev_enter(adev_to_drm(adev), &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 amdgpu_vram_mgr_dmem_ops = { + .reclaim = amdgpu_vram_mgr_dmem_reclaim, +}; + /** * amdgpu_vram_mgr_init - init VRAM manager and DRM MM * @@ -917,6 +939,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) { struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr; struct ttm_resource_manager *man = &mgr->manager; + struct dmem_cgroup_region *cg; int err; ttm_resource_manager_init(man, &adev->mman.bdev, @@ -933,12 +956,16 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) if (err) return err; - man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", - &(struct dmem_cgroup_init){ + cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", + &(struct dmem_cgroup_init){ .size = adev->gmc.real_vram_size, - }); - if (IS_ERR(man->cg)) - return PTR_ERR(man->cg); + .ops = &amdgpu_vram_mgr_dmem_ops, + .reclaim_priv = man, + }); + if (IS_ERR(cg)) + return PTR_ERR(cg); + + ttm_resource_manager_set_dmem_region(man, cg); ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager); ttm_resource_manager_set_used(man, true); -- 2.54.0