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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 69814C3A5A7 for ; Tue, 6 Dec 2022 09:52:45 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235558AbiLFJwn (ORCPT ); Tue, 6 Dec 2022 04:52:43 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57844 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235150AbiLFJvR (ORCPT ); Tue, 6 Dec 2022 04:51:17 -0500 Received: from dfw.source.kernel.org (dfw.source.kernel.org [IPv6:2604:1380:4641:c500::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 851CED79; Tue, 6 Dec 2022 01:50:25 -0800 (PST) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id 201F9615FA; Tue, 6 Dec 2022 09:50:25 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id E69C0C43142; Tue, 6 Dec 2022 09:50:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1670320224; bh=hy3KNMnbe22CQ1fU6zKhmEZCUxAeUJtEnsGnEUh5p2o=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=H9SY/R7hOxHC8Y7PNysSXBLMGUrvU4t9/ZITTiGft7QHoBCdVnxNqmOLg2yfNUult A8RZbblGsoZNuleQHOrp2RA9P2JVa71r8uaVEGvTQ2QYa4iBWEhNonhYvh8CvqnEJO d2VOrWlCAlZS6QTYyXtkGEf6WwPPEhgMqrZQEEhlWY+PPNepWKQ5vj84UIudKxXT1n c3VPoZ9/fHGJOzDfli7BDhfSGNZMrOb0gVw0jAWayUcHzxEntyi1e85Pc9MD5x8s5T jbCN6Kd0yJybjdlbb+B9vTpGYG6+dFF4zZSTOeDxhvv9ps/QxaV4slKcoFvW3TfLnw iKzRXdYSWSI2Q== From: Sasha Levin To: linux-kernel@vger.kernel.org, stable@vger.kernel.org Cc: Peter Zijlstra , syzbot+9228d6098455bb209ec8@syzkaller.appspotmail.com, Marco Elver , Sasha Levin , mingo@redhat.com, acme@kernel.org, linux-perf-users@vger.kernel.org Subject: [PATCH AUTOSEL 5.15 11/12] perf: Fix perf_pending_task() UaF Date: Tue, 6 Dec 2022 04:49:53 -0500 Message-Id: <20221206094955.987437-11-sashal@kernel.org> X-Mailer: git-send-email 2.35.1 In-Reply-To: <20221206094955.987437-1-sashal@kernel.org> References: <20221206094955.987437-1-sashal@kernel.org> MIME-Version: 1.0 X-stable: review X-Patchwork-Hint: Ignore Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Peter Zijlstra [ Upstream commit 517e6a301f34613bff24a8e35b5455884f2d83d8 ] Per syzbot it is possible for perf_pending_task() to run after the event is free()'d. There are two related but distinct cases: - the task_work was already queued before destroying the event; - destroying the event itself queues the task_work. The first cannot be solved using task_work_cancel() since perf_release() itself might be called from a task_work (____fput), which means the current->task_works list is already empty and task_work_cancel() won't be able to find the perf_pending_task() entry. The simplest alternative is extending the perf_event lifetime to cover the task_work. The second is just silly, queueing a task_work while you know the event is going away makes no sense and is easily avoided by re-arranging how the event is marked STATE_DEAD and ensuring it goes through STATE_OFF on the way down. Reported-by: syzbot+9228d6098455bb209ec8@syzkaller.appspotmail.com Signed-off-by: Peter Zijlstra (Intel) Tested-by: Marco Elver Signed-off-by: Sasha Levin --- kernel/events/core.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 60cb300fa0d0..a2bf2d1ea0b9 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2367,6 +2367,7 @@ event_sched_out(struct perf_event *event, !event->pending_work) { event->pending_work = 1; dec = false; + WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount)); task_work_add(current, &event->pending_task, TWA_RESUME); } if (dec) @@ -2412,6 +2413,7 @@ group_sched_out(struct perf_event *group_event, #define DETACH_GROUP 0x01UL #define DETACH_CHILD 0x02UL +#define DETACH_DEAD 0x04UL /* * Cross CPU call to remove a performance event @@ -2432,12 +2434,20 @@ __perf_remove_from_context(struct perf_event *event, update_cgrp_time_from_cpuctx(cpuctx, false); } + /* + * Ensure event_sched_out() switches to OFF, at the very least + * this avoids raising perf_pending_task() at this time. + */ + if (flags & DETACH_DEAD) + event->pending_disable = 1; event_sched_out(event, cpuctx, ctx); if (flags & DETACH_GROUP) perf_group_detach(event); if (flags & DETACH_CHILD) perf_child_detach(event); list_del_event(event, ctx); + if (flags & DETACH_DEAD) + event->state = PERF_EVENT_STATE_DEAD; if (!ctx->nr_events && ctx->is_active) { if (ctx == &cpuctx->ctx) @@ -5212,9 +5222,7 @@ int perf_event_release_kernel(struct perf_event *event) ctx = perf_event_ctx_lock(event); WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, DETACH_GROUP); - raw_spin_lock_irq(&ctx->lock); /* * Mark this event as STATE_DEAD, there is no external reference to it * anymore. @@ -5226,8 +5234,7 @@ int perf_event_release_kernel(struct perf_event *event) * Thus this guarantees that we will in fact observe and kill _ALL_ * child events. */ - event->state = PERF_EVENT_STATE_DEAD; - raw_spin_unlock_irq(&ctx->lock); + perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD); perf_event_ctx_unlock(event, ctx); @@ -6662,6 +6669,8 @@ static void perf_pending_task(struct callback_head *head) if (rctx >= 0) perf_swevent_put_recursion_context(rctx); preempt_enable_notrace(); + + put_event(event); } /* -- 2.35.1