Received: by 2002:a17:90a:9103:0:0:0:0 with SMTP id k3csp11794677pjo; Thu, 2 Jan 2020 14:24:12 -0800 (PST) X-Google-Smtp-Source: APXvYqwPmtmHalZInqymsdvqaSNENBlsEg44688/AD3LScOdZMHryUd26FXzV+jplP2S2yebN5p1 X-Received: by 2002:a9d:6196:: with SMTP id g22mr97900074otk.204.1578003852116; Thu, 02 Jan 2020 14:24:12 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1578003852; cv=none; d=google.com; s=arc-20160816; b=LuEhogV7DBdAswCg38t7xTM0PaAbB/9+os74vuJcw7ACZtM8EOnMVrZ+b1FNC5HkxB 6lm6hN2jkE0BhGjeotVwfJOWhg6XL5OSlyexrh1VK5k92PDCX8f3xs9+VwuFeDpBTXt0 uwPYM+MaFGyFxwWmdUkvLM1rR19M/m7RaHjU0myEkPrIYbJUQF64r6bUJCI0oxAp0g/k bA2ZAoZKkuMWsYzztv870JzFPZajyR9SnxlAQ2dpi+FoPNtr9e6SdqSFFRwqdp4I/VEO LC/s9Lf1DvfTYCGHxlUKmdsoPhvy+ixCLyhmTUvqNgEiDV4KYY/2DyKIwsNB394/8KFc ziCA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:content-transfer-encoding:mime-version :user-agent:references:in-reply-to:message-id:date:subject:cc:to :from:dkim-signature; bh=LvEXh7HkiM3uUtAT8YTE8dYJY4sVNSuTliGFh1HE+o4=; b=mdc3G0mx4wjqp9ZQbHIAHt8IAcreuin/2QT/9zDu3c10PjSpAQFdT2VrzGvduHEFfY qD5l8dCHcWn8kUaDyIoN2ZYhWrQajkzWzGceUU7Ma+h3LkjJ7CwBakCTxD+Sy1gMDSMG lIlf0jda9EKwsYjSfAAdbkbYweZSARkqqrsM8gu+V/e99PC8wSEbC/sNQLFW2HfRvInh Poc2JLPHYwv/qZJluDoiEi2ThzAsYYvQCjYoEdNVnQtA3wh02KSOqZ5Fb79NxnmCWVJ8 JO+EK4nZw8gbgyLWhhRuJreVNlu+60G4uYHbpwRe+GWIIScho6+LKjEZuXxp/DoSnna2 7xqA== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@kernel.org header.s=default header.b=DDtGV7D+; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id p21si20400835otk.162.2020.01.02.14.23.59; Thu, 02 Jan 2020 14:24:12 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; dkim=pass header.i=@kernel.org header.s=default header.b=DDtGV7D+; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727809AbgABWWV (ORCPT + 99 others); Thu, 2 Jan 2020 17:22:21 -0500 Received: from mail.kernel.org ([198.145.29.99]:42642 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728762AbgABWWS (ORCPT ); Thu, 2 Jan 2020 17:22:18 -0500 Received: from localhost (83-86-89-107.cable.dynamic.v4.ziggo.nl [83.86.89.107]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 3F72320866; Thu, 2 Jan 2020 22:22:17 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1578003737; bh=PaPRZjE3RkHrDJQtqnusFNMR3lGJLhG4F8Z9RlBquHE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=DDtGV7D+N3IO6bhRRc4mVxoSTol4JVx1HCVlzZFGeD20EF9vYxM23mx+K8Up6jsSs sTkKc0zk5CJnxclugpin+tugnEN5P07uwWfWiKpUXPXKOFtIUgTIZwR4c6gcvZjPwu tEmpyX0KeRo38E71kgvArvhftsxAZzR5wymRAS4k= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Vladis Dronov , Richard Cochran , "David S. Miller" , Stephen Johnston , Vern Lovejoy Subject: [PATCH 4.19 093/114] ptp: fix the race between the release of ptp_clock and cdev Date: Thu, 2 Jan 2020 23:07:45 +0100 Message-Id: <20200102220038.534436112@linuxfoundation.org> X-Mailer: git-send-email 2.24.1 In-Reply-To: <20200102220029.183913184@linuxfoundation.org> References: <20200102220029.183913184@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Vladis Dronov [ Upstream commit a33121e5487b424339636b25c35d3a180eaa5f5e ] In a case when a ptp chardev (like /dev/ptp0) is open but an underlying device is removed, closing this file leads to a race. This reproduces easily in a kvm virtual machine: ts# cat openptp0.c int main() { ... fp = fopen("/dev/ptp0", "r"); ... sleep(10); } ts# uname -r 5.5.0-rc3-46cf053e ts# cat /proc/cmdline ... slub_debug=FZP ts# modprobe ptp_kvm ts# ./openptp0 & [1] 670 opened /dev/ptp0, sleeping 10s... ts# rmmod ptp_kvm ts# ls /dev/ptp* ls: cannot access '/dev/ptp*': No such file or directory ts# ...woken up [ 48.010809] general protection fault: 0000 [#1] SMP [ 48.012502] CPU: 6 PID: 658 Comm: openptp0 Not tainted 5.5.0-rc3-46cf053e #25 [ 48.014624] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ... [ 48.016270] RIP: 0010:module_put.part.0+0x7/0x80 [ 48.017939] RSP: 0018:ffffb3850073be00 EFLAGS: 00010202 [ 48.018339] RAX: 000000006b6b6b6b RBX: 6b6b6b6b6b6b6b6b RCX: ffff89a476c00ad0 [ 48.018936] RDX: fffff65a08d3ea08 RSI: 0000000000000247 RDI: 6b6b6b6b6b6b6b6b [ 48.019470] ... ^^^ a slub poison [ 48.023854] Call Trace: [ 48.024050] __fput+0x21f/0x240 [ 48.024288] task_work_run+0x79/0x90 [ 48.024555] do_exit+0x2af/0xab0 [ 48.024799] ? vfs_write+0x16a/0x190 [ 48.025082] do_group_exit+0x35/0x90 [ 48.025387] __x64_sys_exit_group+0xf/0x10 [ 48.025737] do_syscall_64+0x3d/0x130 [ 48.026056] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 48.026479] RIP: 0033:0x7f53b12082f6 [ 48.026792] ... [ 48.030945] Modules linked in: ptp i6300esb watchdog [last unloaded: ptp_kvm] [ 48.045001] Fixing recursive fault but reboot is needed! This happens in: static void __fput(struct file *file) { ... if (file->f_op->release) file->f_op->release(inode, file); <<< cdev is kfree'd here if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); <<< cdev fields are accessed here Namely: __fput() posix_clock_release() kref_put(&clk->kref, delete_clock) <<< the last reference delete_clock() delete_ptp_clock() kfree(ptp) <<< cdev is embedded in ptp cdev_put module_put(p->owner) <<< *p is kfree'd, bang! Here cdev is embedded in posix_clock which is embedded in ptp_clock. The race happens because ptp_clock's lifetime is controlled by two refcounts: kref and cdev.kobj in posix_clock. This is wrong. Make ptp_clock's sysfs device a parent of cdev with cdev_device_add() created especially for such cases. This way the parent device with its ptp_clock is not released until all references to the cdev are released. This adds a requirement that an initialized but not exposed struct device should be provided to posix_clock_register() by a caller instead of a simple dev_t. This approach was adopted from the commit 72139dfa2464 ("watchdog: Fix the race between the release of watchdog_core_data and cdev"). See details of the implementation in the commit 233ed09d7fda ("chardev: add helper function to register char devs with a struct device"). Link: https://lore.kernel.org/linux-fsdevel/20191125125342.6189-1-vdronov@redhat.com/T/#u Analyzed-by: Stephen Johnston Analyzed-by: Vern Lovejoy Signed-off-by: Vladis Dronov Acked-by: Richard Cochran Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/ptp/ptp_clock.c | 31 ++++++++++++++----------------- drivers/ptp/ptp_private.h | 2 +- include/linux/posix-clock.h | 19 +++++++++++-------- kernel/time/posix-clock.c | 31 +++++++++++++------------------ 4 files changed, 39 insertions(+), 44 deletions(-) --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -175,9 +175,9 @@ static struct posix_clock_operations ptp .read = ptp_read, }; -static void delete_ptp_clock(struct posix_clock *pc) +static void ptp_clock_release(struct device *dev) { - struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); @@ -222,7 +222,6 @@ struct ptp_clock *ptp_clock_register(str } ptp->clock.ops = ptp_clock_ops; - ptp->clock.release = delete_ptp_clock; ptp->info = info; ptp->devid = MKDEV(major, index); ptp->index = index; @@ -249,15 +248,6 @@ struct ptp_clock *ptp_clock_register(str if (err) goto no_pin_groups; - /* Create a new device in our class. */ - ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid, - ptp, ptp->pin_attr_groups, - "ptp%d", ptp->index); - if (IS_ERR(ptp->dev)) { - err = PTR_ERR(ptp->dev); - goto no_device; - } - /* Register a new PPS source. */ if (info->pps) { struct pps_source_info pps; @@ -273,8 +263,18 @@ struct ptp_clock *ptp_clock_register(str } } - /* Create a posix clock. */ - err = posix_clock_register(&ptp->clock, ptp->devid); + /* Initialize a new device of our class in our clock structure. */ + device_initialize(&ptp->dev); + ptp->dev.devt = ptp->devid; + ptp->dev.class = ptp_class; + ptp->dev.parent = parent; + ptp->dev.groups = ptp->pin_attr_groups; + ptp->dev.release = ptp_clock_release; + dev_set_drvdata(&ptp->dev, ptp); + dev_set_name(&ptp->dev, "ptp%d", ptp->index); + + /* Create a posix clock and link it to the device. */ + err = posix_clock_register(&ptp->clock, &ptp->dev); if (err) { pr_err("failed to create posix clock\n"); goto no_clock; @@ -286,8 +286,6 @@ no_clock: if (ptp->pps_source) pps_unregister_source(ptp->pps_source); no_pps: - device_destroy(ptp_class, ptp->devid); -no_device: ptp_cleanup_pin_groups(ptp); no_pin_groups: if (ptp->kworker) @@ -317,7 +315,6 @@ int ptp_clock_unregister(struct ptp_cloc if (ptp->pps_source) pps_unregister_source(ptp->pps_source); - device_destroy(ptp_class, ptp->devid); ptp_cleanup_pin_groups(ptp); posix_clock_unregister(&ptp->clock); --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -41,7 +41,7 @@ struct timestamp_event_queue { struct ptp_clock { struct posix_clock clock; - struct device *dev; + struct device dev; struct ptp_clock_info *info; dev_t devid; int index; /* index into clocks.map */ --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -82,29 +82,32 @@ struct posix_clock_operations { * * @ops: Functional interface to the clock * @cdev: Character device instance for this clock - * @kref: Reference count. + * @dev: Pointer to the clock's device. * @rwsem: Protects the 'zombie' field from concurrent access. * @zombie: If 'zombie' is true, then the hardware has disappeared. - * @release: A function to free the structure when the reference count reaches - * zero. May be NULL if structure is statically allocated. * * Drivers should embed their struct posix_clock within a private * structure, obtaining a reference to it during callbacks using * container_of(). + * + * Drivers should supply an initialized but not exposed struct device + * to posix_clock_register(). It is used to manage lifetime of the + * driver's private structure. It's 'release' field should be set to + * a release function for this private structure. */ struct posix_clock { struct posix_clock_operations ops; struct cdev cdev; - struct kref kref; + struct device *dev; struct rw_semaphore rwsem; bool zombie; - void (*release)(struct posix_clock *clk); }; /** * posix_clock_register() - register a new clock - * @clk: Pointer to the clock. Caller must provide 'ops' and 'release' - * @devid: Allocated device id + * @clk: Pointer to the clock. Caller must provide 'ops' field + * @dev: Pointer to the initialized device. Caller must provide + * 'release' field * * A clock driver calls this function to register itself with the * clock device subsystem. If 'clk' points to dynamically allocated @@ -113,7 +116,7 @@ struct posix_clock { * * Returns zero on success, non-zero otherwise. */ -int posix_clock_register(struct posix_clock *clk, dev_t devid); +int posix_clock_register(struct posix_clock *clk, struct device *dev); /** * posix_clock_unregister() - unregister a clock --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -27,8 +27,6 @@ #include "posix-timers.h" -static void delete_clock(struct kref *kref); - /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ @@ -138,7 +136,7 @@ static int posix_clock_open(struct inode err = 0; if (!err) { - kref_get(&clk->kref); + get_device(clk->dev); fp->private_data = clk; } out: @@ -154,7 +152,7 @@ static int posix_clock_release(struct in if (clk->ops.release) err = clk->ops.release(clk); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); fp->private_data = NULL; @@ -174,38 +172,35 @@ static const struct file_operations posi #endif }; -int posix_clock_register(struct posix_clock *clk, dev_t devid) +int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; - kref_init(&clk->kref); init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); + err = cdev_device_add(&clk->cdev, dev); + if (err) { + pr_err("%s unable to add device %d:%d\n", + dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); + return err; + } clk->cdev.owner = clk->ops.owner; - err = cdev_add(&clk->cdev, devid, 1); + clk->dev = dev; - return err; + return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); -static void delete_clock(struct kref *kref) -{ - struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - - if (clk->release) - clk->release(clk); -} - void posix_clock_unregister(struct posix_clock *clk) { - cdev_del(&clk->cdev); + cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister);