OpenCloudOS-Kernel/drivers/tty/tty_io.c

3643 lines
89 KiB
C
Raw Normal View History

tty: add SPDX identifiers to all remaining files in drivers/tty/ It's good to have SPDX identifiers in all files to make it easier to audit the kernel tree for correct licenses. Update the drivers/tty files files with the correct SPDX license identifier based on the license text in the file itself. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This work is based on a script and data from Thomas Gleixner, Philippe Ombredanne, and Kate Stewart. Cc: Jiri Slaby <jslaby@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Jiri Kosina <jikos@kernel.org> Cc: David Sterba <dsterba@suse.com> Cc: James Hogan <jhogan@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Eric Anholt <eric@anholt.net> Cc: Stefan Wahren <stefan.wahren@i2se.com> Cc: Florian Fainelli <f.fainelli@gmail.com> Cc: Ray Jui <rjui@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: bcm-kernel-feedback-list@broadcom.com Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Joachim Eastwood <manabian@gmail.com> Cc: Matthias Brugger <matthias.bgg@gmail.com> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Tobias Klauser <tklauser@distanz.ch> Cc: Russell King <linux@armlinux.org.uk> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Richard Genoud <richard.genoud@gmail.com> Cc: Alexander Shiyan <shc_work@mail.ru> Cc: Baruch Siach <baruch@tkos.co.il> Cc: "Maciej W. Rozycki" <macro@linux-mips.org> Cc: "Uwe Kleine-König" <kernel@pengutronix.de> Cc: Pat Gefre <pfg@sgi.com> Cc: "Guilherme G. Piccoli" <gpiccoli@linux.vnet.ibm.com> Cc: Jason Wessel <jason.wessel@windriver.com> Cc: Vladimir Zapolskiy <vz@mleia.com> Cc: Sylvain Lemieux <slemieux.tyco@gmail.com> Cc: Carlo Caione <carlo@caione.org> Cc: Kevin Hilman <khilman@baylibre.com> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andy Gross <andy.gross@linaro.org> Cc: David Brown <david.brown@linaro.org> Cc: "Andreas Färber" <afaerber@suse.de> Cc: Kevin Cernekee <cernekee@gmail.com> Cc: Laxman Dewangan <ldewangan@nvidia.com> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: Jonathan Hunter <jonathanh@nvidia.com> Cc: Barry Song <baohua@kernel.org> Cc: Patrice Chotard <patrice.chotard@st.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Alexandre Torgue <alexandre.torgue@st.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Peter Korsgaard <jacmet@sunsite.dk> Cc: Timur Tabi <timur@tabi.org> Cc: Tony Prisk <linux@prisktech.co.nz> Cc: Michal Simek <michal.simek@xilinx.com> Cc: "Sören Brinkmann" <soren.brinkmann@xilinx.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Jiri Slaby <jslaby@suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-07 01:11:51 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles
* or rs-channels. It also implements echoing, cooked mode etc.
*
* Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0.
*
* Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the
* tty_struct and tty_queue structures. Previously there was an array
* of 256 tty_struct's which was statically allocated, and the
* tty_queue structures were allocated at boot time. Both are now
* dynamically allocated only when the tty is open.
*
* Also restructured routines so that there is more of a separation
* between the high-level tty routines (tty_io.c and tty_ioctl.c) and
* the low-level tty routines (serial.c, pty.c, console.c). This
* makes for cleaner and more compact code. -TYT, 9/17/92
*
* Modified by Fred N. van Kempen, 01/29/93, to add line disciplines
* which can be dynamically activated and de-activated by the line
* discipline handling modules (like SLIP).
*
* NOTE: pay no attention to the line discipline code (yet); its
* interface is still subject to change in this version...
* -- TYT, 1/31/92
*
* Added functionality to the OPOST tty handling. No delays, but all
* other bits should be there.
* -- Nick Holloway <alfie@dcs.warwick.ac.uk>, 27th May 1993.
*
* Rewrote canonical mode and added more termios flags.
* -- julian@uhunix.uhcc.hawaii.edu (J. Cowley), 13Jan94
*
* Reorganized FASYNC support so mouse code can share it.
* -- ctm@ardi.com, 9Sep95
*
* New TIOCLINUX variants added.
* -- mj@k332.feld.cvut.cz, 19-Nov-95
*
* Restrict vt switching via ioctl()
* -- grif@cs.ucr.edu, 5-Dec-95
*
* Move console and virtual terminal code to more appropriate files,
* implement CONFIG_VT and generalize console device interface.
* -- Marko Kohtala <Marko.Kohtala@hut.fi>, March 97
*
* Rewrote tty_init_dev and tty_release_dev to eliminate races.
* -- Bill Hawes <whawes@star.net>, June 97
*
* Added devfs support.
* -- C. Scott Ananian <cananian@alumni.princeton.edu>, 13-Jan-1998
*
* Added support for a Unix98-style ptmx device.
* -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998
*
* Reduced memory usage for older ARM systems
* -- Russell King <rmk@arm.linux.org.uk>
*
* Move do_SAK() into process context. Less stack use in devfs functions.
* alloc_tty_struct() always uses kmalloc()
* -- Andrew Morton <andrewm@uow.edu.eu> 17Mar01
*/
#include <linux/types.h>
#include <linux/major.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/fcntl.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/interrupt.h>
#include <linux/tty.h>
#include <linux/tty_driver.h>
#include <linux/tty_flip.h>
#include <linux/devpts_fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/console.h>
#include <linux/timer.h>
#include <linux/ctype.h>
#include <linux/kd.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/ppp-ioctl.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/wait.h>
#include <linux/bitops.h>
#include <linux/delay.h>
#include <linux/seq_file.h>
#include <linux/serial.h>
#include <linux/ratelimit.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/termios_internal.h>
#include <linux/kbd_kern.h>
#include <linux/vt_kern.h>
#include <linux/selection.h>
#include <linux/kmod.h>
#include <linux/nsproxy.h>
#include "tty.h"
#undef TTY_DEBUG_HANGUP
#ifdef TTY_DEBUG_HANGUP
# define tty_debug_hangup(tty, f, args...) tty_debug(tty, f, ##args)
#else
# define tty_debug_hangup(tty, f, args...) do { } while (0)
#endif
#define TTY_PARANOIA_CHECK 1
#define CHECK_TTY_COUNT 1
struct ktermios tty_std_termios = { /* for the benefit of tty drivers */
.c_iflag = ICRNL | IXON,
.c_oflag = OPOST | ONLCR,
.c_cflag = B38400 | CS8 | CREAD | HUPCL,
.c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK |
ECHOCTL | ECHOKE | IEXTEN,
.c_cc = INIT_C_CC,
.c_ispeed = 38400,
.c_ospeed = 38400,
/* .c_line = N_TTY, */
};
EXPORT_SYMBOL(tty_std_termios);
/* This list gets poked at by procfs and various bits of boot up code. This
* could do with some rationalisation such as pulling the tty proc function
* into this file.
*/
LIST_HEAD(tty_drivers); /* linked list of tty drivers */
/* Mutex to protect creating and releasing a tty */
DEFINE_MUTEX(tty_mutex);
static ssize_t tty_read(struct kiocb *, struct iov_iter *);
static ssize_t tty_write(struct kiocb *, struct iov_iter *);
static __poll_t tty_poll(struct file *, poll_table *);
static int tty_open(struct inode *, struct file *);
#ifdef CONFIG_COMPAT
static long tty_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg);
#else
#define tty_compat_ioctl NULL
#endif
static int __tty_fasync(int fd, struct file *filp, int on);
static int tty_fasync(int fd, struct file *filp, int on);
static void release_tty(struct tty_struct *tty, int idx);
/**
* free_tty_struct - free a disused tty
* @tty: tty struct to free
*
* Free the write buffers, tty queue and tty memory itself.
*
* Locking: none. Must be called after tty is definitely unused
*/
static void free_tty_struct(struct tty_struct *tty)
{
tty_ldisc_deinit(tty);
put_device(tty->dev);
kvfree(tty->write_buf);
kfree(tty);
}
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
static inline struct tty_struct *file_tty(struct file *file)
{
return ((struct tty_file_private *)file->private_data)->tty;
}
int tty_alloc_file(struct file *file)
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
{
struct tty_file_private *priv;
priv = kmalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
file->private_data = priv;
return 0;
}
/* Associate a new file with the tty structure */
void tty_add_file(struct tty_struct *tty, struct file *file)
{
struct tty_file_private *priv = file->private_data;
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
priv->tty = tty;
priv->file = file;
spin_lock(&tty->files_lock);
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
list_add(&priv->list, &tty->tty_files);
spin_unlock(&tty->files_lock);
}
/**
* tty_free_file - free file->private_data
* @file: to free private_data of
*
* This shall be used only for fail path handling when tty_add_file was not
* called yet.
*/
void tty_free_file(struct file *file)
{
struct tty_file_private *priv = file->private_data;
file->private_data = NULL;
kfree(priv);
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
}
/* Delete file from its tty */
static void tty_del_file(struct file *file)
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
{
struct tty_file_private *priv = file->private_data;
struct tty_struct *tty = priv->tty;
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
spin_lock(&tty->files_lock);
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
list_del(&priv->list);
spin_unlock(&tty->files_lock);
tty_free_file(file);
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
}
/**
* tty_name - return tty naming
* @tty: tty structure
*
* Convert a tty structure into a name. The name reflects the kernel naming
* policy and if udev is in use may not reflect user space
*
* Locking: none
*/
const char *tty_name(const struct tty_struct *tty)
{
if (!tty) /* Hmm. NULL pointer. That's fun. */
return "NULL tty";
return tty->name;
}
EXPORT_SYMBOL(tty_name);
const char *tty_driver_name(const struct tty_struct *tty)
{
if (!tty || !tty->driver)
return "";
return tty->driver->name;
}
static int tty_paranoia_check(struct tty_struct *tty, struct inode *inode,
const char *routine)
{
#ifdef TTY_PARANOIA_CHECK
if (!tty) {
pr_warn("(%d:%d): %s: NULL tty\n",
imajor(inode), iminor(inode), routine);
return 1;
}
#endif
return 0;
}
/* Caller must hold tty_lock */
static int check_tty_count(struct tty_struct *tty, const char *routine)
{
#ifdef CHECK_TTY_COUNT
struct list_head *p;
int count = 0, kopen_count = 0;
spin_lock(&tty->files_lock);
list_for_each(p, &tty->tty_files) {
count++;
}
spin_unlock(&tty->files_lock);
if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
tty->driver->subtype == PTY_TYPE_SLAVE &&
tty->link && tty->link->count)
count++;
if (tty_port_kopened(tty->port))
kopen_count++;
if (tty->count != (count + kopen_count)) {
tty_warn(tty, "%s: tty->count(%d) != (#fd's(%d) + #kopen's(%d))\n",
routine, tty->count, count, kopen_count);
return (count + kopen_count);
[PATCH] tty: ->signal->tty locking Fix the locking of signal->tty. Use ->sighand->siglock to protect ->signal->tty; this lock is already used by most other members of ->signal/->sighand. And unless we are 'current' or the tasklist_lock is held we need ->siglock to access ->signal anyway. (NOTE: sys_unshare() is broken wrt ->sighand locking rules) Note that tty_mutex is held over tty destruction, so while holding tty_mutex any tty pointer remains valid. Otherwise the lifetime of ttys are governed by their open file handles. This leaves some holes for tty access from signal->tty (or any other non file related tty access). It solves the tty SLAB scribbles we were seeing. (NOTE: the change from group_send_sig_info to __group_send_sig_info needs to be examined by someone familiar with the security framework, I think it is safe given the SEND_SIG_PRIV from other __group_send_sig_info invocations) [schwidefsky@de.ibm.com: 3270 fix] [akpm@osdl.org: various post-viro fixes] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Alan Cox <alan@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Roland McGrath <roland@redhat.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jan Kara <jack@ucw.cz> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:36:04 +08:00
}
#endif
return 0;
}
/**
* get_tty_driver - find device of a tty
* @device: device identifier
* @index: returns the index of the tty
*
* This routine returns a tty driver structure, given a device number and also
* passes back the index number.
*
* Locking: caller must hold tty_mutex
*/
static struct tty_driver *get_tty_driver(dev_t device, int *index)
{
struct tty_driver *p;
list_for_each_entry(p, &tty_drivers, tty_drivers) {
dev_t base = MKDEV(p->major, p->minor_start);
if (device < base || device >= base + p->num)
continue;
*index = device - base;
return tty_driver_kref_get(p);
}
return NULL;
}
/**
* tty_dev_name_to_number - return dev_t for device name
* @name: user space name of device under /dev
* @number: pointer to dev_t that this function will populate
*
* This function converts device names like ttyS0 or ttyUSB1 into dev_t like
* (4, 64) or (188, 1). If no corresponding driver is registered then the
* function returns -%ENODEV.
*
* Locking: this acquires tty_mutex to protect the tty_drivers list from
* being modified while we are traversing it, and makes sure to
* release it before exiting.
*/
int tty_dev_name_to_number(const char *name, dev_t *number)
{
struct tty_driver *p;
int ret;
int index, prefix_length = 0;
const char *str;
for (str = name; *str && !isdigit(*str); str++)
;
if (!*str)
return -EINVAL;
ret = kstrtoint(str, 10, &index);
if (ret)
return ret;
prefix_length = str - name;
mutex_lock(&tty_mutex);
list_for_each_entry(p, &tty_drivers, tty_drivers)
if (prefix_length == strlen(p->name) && strncmp(name,
p->name, prefix_length) == 0) {
if (index < p->num) {
*number = MKDEV(p->major, p->minor_start + index);
goto out;
}
}
/* if here then driver wasn't found */
ret = -ENODEV;
out:
mutex_unlock(&tty_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(tty_dev_name_to_number);
#ifdef CONFIG_CONSOLE_POLL
/**
* tty_find_polling_driver - find device of a polled tty
* @name: name string to match
* @line: pointer to resulting tty line nr
*
* This routine returns a tty driver structure, given a name and the condition
* that the tty driver is capable of polled operation.
*/
struct tty_driver *tty_find_polling_driver(char *name, int *line)
{
struct tty_driver *p, *res = NULL;
int tty_line = 0;
int len;
char *str, *stp;
for (str = name; *str; str++)
if ((*str >= '0' && *str <= '9') || *str == ',')
break;
if (!*str)
return NULL;
len = str - name;
tty_line = simple_strtoul(str, &str, 10);
mutex_lock(&tty_mutex);
/* Search through the tty devices to look for a match */
list_for_each_entry(p, &tty_drivers, tty_drivers) {
tty: check name length in tty_find_polling_driver() The issue is found by a fuzzing test. If tty_find_polling_driver() recevies an incorrect input such as ',,' or '0b', the len becomes 0 and strncmp() always return 0. In this case, a null p->ops->poll_init() is called and it causes a kernel panic. Fix this by checking name length against zero in tty_find_polling_driver(). $echo ,, > /sys/module/kgdboc/parameters/kgdboc [ 20.804451] WARNING: CPU: 1 PID: 104 at drivers/tty/serial/serial_core.c:457 uart_get_baud_rate+0xe8/0x190 [ 20.804917] Modules linked in: [ 20.805317] CPU: 1 PID: 104 Comm: sh Not tainted 4.19.0-rc7ajb #8 [ 20.805469] Hardware name: linux,dummy-virt (DT) [ 20.805732] pstate: 20000005 (nzCv daif -PAN -UAO) [ 20.805895] pc : uart_get_baud_rate+0xe8/0x190 [ 20.806042] lr : uart_get_baud_rate+0xc0/0x190 [ 20.806476] sp : ffffffc06acff940 [ 20.806676] x29: ffffffc06acff940 x28: 0000000000002580 [ 20.806977] x27: 0000000000009600 x26: 0000000000009600 [ 20.807231] x25: ffffffc06acffad0 x24: 00000000ffffeff0 [ 20.807576] x23: 0000000000000001 x22: 0000000000000000 [ 20.807807] x21: 0000000000000001 x20: 0000000000000000 [ 20.808049] x19: ffffffc06acffac8 x18: 0000000000000000 [ 20.808277] x17: 0000000000000000 x16: 0000000000000000 [ 20.808520] x15: ffffffffffffffff x14: ffffffff00000000 [ 20.808757] x13: ffffffffffffffff x12: 0000000000000001 [ 20.809011] x11: 0101010101010101 x10: ffffff880d59ff5f [ 20.809292] x9 : ffffff880d59ff5e x8 : ffffffc06acffaf3 [ 20.809549] x7 : 0000000000000000 x6 : ffffff880d59ff5f [ 20.809803] x5 : 0000000080008001 x4 : 0000000000000003 [ 20.810056] x3 : ffffff900853e6b4 x2 : dfffff9000000000 [ 20.810693] x1 : ffffffc06acffad0 x0 : 0000000000000cb0 [ 20.811005] Call trace: [ 20.811214] uart_get_baud_rate+0xe8/0x190 [ 20.811479] serial8250_do_set_termios+0xe0/0x6f4 [ 20.811719] serial8250_set_termios+0x48/0x54 [ 20.811928] uart_set_options+0x138/0x1bc [ 20.812129] uart_poll_init+0x114/0x16c [ 20.812330] tty_find_polling_driver+0x158/0x200 [ 20.812545] configure_kgdboc+0xbc/0x1bc [ 20.812745] param_set_kgdboc_var+0xb8/0x150 [ 20.812960] param_attr_store+0xbc/0x150 [ 20.813160] module_attr_store+0x40/0x58 [ 20.813364] sysfs_kf_write+0x8c/0xa8 [ 20.813563] kernfs_fop_write+0x154/0x290 [ 20.813764] vfs_write+0xf0/0x278 [ 20.813951] __arm64_sys_write+0x84/0xf4 [ 20.814400] el0_svc_common+0xf4/0x1dc [ 20.814616] el0_svc_handler+0x98/0xbc [ 20.814804] el0_svc+0x8/0xc [ 20.822005] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 20.826913] Mem abort info: [ 20.827103] ESR = 0x84000006 [ 20.827352] Exception class = IABT (current EL), IL = 16 bits [ 20.827655] SET = 0, FnV = 0 [ 20.827855] EA = 0, S1PTW = 0 [ 20.828135] user pgtable: 4k pages, 39-bit VAs, pgdp = (____ptrval____) [ 20.828484] [0000000000000000] pgd=00000000aadee003, pud=00000000aadee003, pmd=0000000000000000 [ 20.829195] Internal error: Oops: 84000006 [#1] SMP [ 20.829564] Modules linked in: [ 20.829890] CPU: 1 PID: 104 Comm: sh Tainted: G W 4.19.0-rc7ajb #8 [ 20.830545] Hardware name: linux,dummy-virt (DT) [ 20.830829] pstate: 60000085 (nZCv daIf -PAN -UAO) [ 20.831174] pc : (null) [ 20.831457] lr : serial8250_do_set_termios+0x358/0x6f4 [ 20.831727] sp : ffffffc06acff9b0 [ 20.831936] x29: ffffffc06acff9b0 x28: ffffff9008d7c000 [ 20.832267] x27: ffffff900969e16f x26: 0000000000000000 [ 20.832589] x25: ffffff900969dfb0 x24: 0000000000000000 [ 20.832906] x23: ffffffc06acffad0 x22: ffffff900969e160 [ 20.833232] x21: 0000000000000000 x20: ffffffc06acffac8 [ 20.833559] x19: ffffff900969df90 x18: 0000000000000000 [ 20.833878] x17: 0000000000000000 x16: 0000000000000000 [ 20.834491] x15: ffffffffffffffff x14: ffffffff00000000 [ 20.834821] x13: ffffffffffffffff x12: 0000000000000001 [ 20.835143] x11: 0101010101010101 x10: ffffff880d59ff5f [ 20.835467] x9 : ffffff880d59ff5e x8 : ffffffc06acffaf3 [ 20.835790] x7 : 0000000000000000 x6 : ffffff880d59ff5f [ 20.836111] x5 : c06419717c314100 x4 : 0000000000000007 [ 20.836419] x3 : 0000000000000000 x2 : 0000000000000000 [ 20.836732] x1 : 0000000000000001 x0 : ffffff900969df90 [ 20.837100] Process sh (pid: 104, stack limit = 0x(____ptrval____)) [ 20.837396] Call trace: [ 20.837566] (null) [ 20.837816] serial8250_set_termios+0x48/0x54 [ 20.838089] uart_set_options+0x138/0x1bc [ 20.838570] uart_poll_init+0x114/0x16c [ 20.838834] tty_find_polling_driver+0x158/0x200 [ 20.839119] configure_kgdboc+0xbc/0x1bc [ 20.839380] param_set_kgdboc_var+0xb8/0x150 [ 20.839658] param_attr_store+0xbc/0x150 [ 20.839920] module_attr_store+0x40/0x58 [ 20.840183] sysfs_kf_write+0x8c/0xa8 [ 20.840183] sysfs_kf_write+0x8c/0xa8 [ 20.840440] kernfs_fop_write+0x154/0x290 [ 20.840702] vfs_write+0xf0/0x278 [ 20.840942] __arm64_sys_write+0x84/0xf4 [ 20.841209] el0_svc_common+0xf4/0x1dc [ 20.841471] el0_svc_handler+0x98/0xbc [ 20.841713] el0_svc+0x8/0xc [ 20.842057] Code: bad PC value [ 20.842764] ---[ end trace a8835d7de79aaadf ]--- [ 20.843134] Kernel panic - not syncing: Fatal exception [ 20.843515] SMP: stopping secondary CPUs [ 20.844289] Kernel Offset: disabled [ 20.844634] CPU features: 0x0,21806002 [ 20.844857] Memory Limit: none [ 20.845172] ---[ end Kernel panic - not syncing: Fatal exception ]--- Signed-off-by: Miles Chen <miles.chen@mediatek.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-10-08 10:39:17 +08:00
if (!len || strncmp(name, p->name, len) != 0)
continue;
stp = str;
if (*stp == ',')
stp++;
if (*stp == '\0')
stp = NULL;
if (tty_line >= 0 && tty_line < p->num && p->ops &&
p->ops->poll_init && !p->ops->poll_init(p, tty_line, stp)) {
res = tty_driver_kref_get(p);
*line = tty_line;
break;
}
}
mutex_unlock(&tty_mutex);
return res;
}
EXPORT_SYMBOL_GPL(tty_find_polling_driver);
#endif
static ssize_t hung_up_tty_read(struct kiocb *iocb, struct iov_iter *to)
{
return 0;
}
static ssize_t hung_up_tty_write(struct kiocb *iocb, struct iov_iter *from)
{
return -EIO;
}
/* No kernel lock held - none needed ;) */
static __poll_t hung_up_tty_poll(struct file *filp, poll_table *wait)
{
return EPOLLIN | EPOLLOUT | EPOLLERR | EPOLLHUP | EPOLLRDNORM | EPOLLWRNORM;
}
static long hung_up_tty_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
return cmd == TIOCSPGRP ? -ENOTTY : -EIO;
}
static long hung_up_tty_compat_ioctl(struct file *file,
unsigned int cmd, unsigned long arg)
{
return cmd == TIOCSPGRP ? -ENOTTY : -EIO;
}
static int hung_up_tty_fasync(int fd, struct file *file, int on)
{
return -ENOTTY;
}
static void tty_show_fdinfo(struct seq_file *m, struct file *file)
{
struct tty_struct *tty = file_tty(file);
if (tty && tty->ops && tty->ops->show_fdinfo)
tty->ops->show_fdinfo(tty, m);
}
static const struct file_operations tty_fops = {
.llseek = no_llseek,
.read_iter = tty_read,
.write_iter = tty_write,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.poll = tty_poll,
.unlocked_ioctl = tty_ioctl,
.compat_ioctl = tty_compat_ioctl,
.open = tty_open,
.release = tty_release,
.fasync = tty_fasync,
.show_fdinfo = tty_show_fdinfo,
};
static const struct file_operations console_fops = {
.llseek = no_llseek,
.read_iter = tty_read,
.write_iter = redirected_tty_write,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.poll = tty_poll,
.unlocked_ioctl = tty_ioctl,
.compat_ioctl = tty_compat_ioctl,
.open = tty_open,
.release = tty_release,
.fasync = tty_fasync,
};
static const struct file_operations hung_up_tty_fops = {
.llseek = no_llseek,
.read_iter = hung_up_tty_read,
.write_iter = hung_up_tty_write,
.poll = hung_up_tty_poll,
.unlocked_ioctl = hung_up_tty_ioctl,
.compat_ioctl = hung_up_tty_compat_ioctl,
.release = tty_release,
.fasync = hung_up_tty_fasync,
};
static DEFINE_SPINLOCK(redirect_lock);
static struct file *redirect;
/**
* tty_wakeup - request more data
* @tty: terminal
*
* Internal and external helper for wakeups of tty. This function informs the
* line discipline if present that the driver is ready to receive more output
* data.
*/
void tty_wakeup(struct tty_struct *tty)
{
struct tty_ldisc *ld;
if (test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) {
ld = tty_ldisc_ref(tty);
if (ld) {
if (ld->ops->write_wakeup)
ld->ops->write_wakeup(tty);
tty_ldisc_deref(ld);
}
}
wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT);
}
EXPORT_SYMBOL_GPL(tty_wakeup);
/**
* tty_release_redirect - Release a redirect on a pty if present
* @tty: tty device
*
* This is available to the pty code so if the master closes, if the slave is a
* redirect it can release the redirect.
*/
static struct file *tty_release_redirect(struct tty_struct *tty)
{
struct file *f = NULL;
spin_lock(&redirect_lock);
if (redirect && file_tty(redirect) == tty) {
f = redirect;
redirect = NULL;
}
spin_unlock(&redirect_lock);
return f;
}
/**
* __tty_hangup - actual handler for hangup events
* @tty: tty device
* @exit_session: if non-zero, signal all foreground group processes
*
* This can be called by a "kworker" kernel thread. That is process synchronous
* but doesn't hold any locks, so we need to make sure we have the appropriate
* locks for what we're doing.
*
* The hangup event clears any pending redirections onto the hung up device. It
* ensures future writes will error and it does the needed line discipline
* hangup and signal delivery. The tty object itself remains intact.
*
* Locking:
* * BTM
*
* * redirect lock for undoing redirection
* * file list lock for manipulating list of ttys
* * tty_ldiscs_lock from called functions
* * termios_rwsem resetting termios data
* * tasklist_lock to walk task list for hangup event
*
* * ->siglock to protect ->signal/->sighand
*
*/
static void __tty_hangup(struct tty_struct *tty, int exit_session)
{
struct file *cons_filp = NULL;
struct file *filp, *f;
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_file_private *priv;
int closecount = 0, n;
int refs;
if (!tty)
return;
f = tty_release_redirect(tty);
tty_lock(tty);
tty: Only hangup once Instrumented testing shows a tty can be hungup multiple times [1]. Although concurrent hangups are properly serialized, multiple hangups for the same tty should be prevented. If tty has already been HUPPED, abort hangup. Note it is not necessary to cleanup file *redirect on subsequent hangups, as only TIOCCONS can set that value and ioctls are disabled after hangup. [1] Test performed by simulating a concurrent async hangup via tty_hangup() with a sync hangup via tty_vhangup(), while __tty_hangup() was instrumented with: diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 26bb78c..fe8b061 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -629,6 +629,8 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session) tty_lock(tty); + WARN_ON(test_bit(TTY_HUPPED, &tty->flags)); + /* some functions below drop BTM, so we need this bit */ set_bit(TTY_HUPPING, &tty->flags); Test result: WARNING: at /home/peter/src/kernels/mainline/drivers/tty/tty_io.c:632 __tty_hangup+0x459/0x460() Modules linked in: ip6table_filter ip6_tables ebtable_nat <...snip...> CPU: 6 PID: 1197 Comm: kworker/6:2 Not tainted 3.10.0-0+rfcomm-xeon #0+rfcomm Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 Workqueue: events do_tty_hangup 0000000000000009 ffff8802b16d7d18 ffffffff816b553e ffff8802b16d7d58 ffffffff810407e0 ffff880254f95c00 ffff880254f95c00 ffff8802bfd92b00 ffff8802bfd96b00 ffff880254f95e40 0000000000000180 ffff8802b16d7d68 Call Trace: [<ffffffff816b553e>] dump_stack+0x19/0x1b [<ffffffff810407e0>] warn_slowpath_common+0x70/0xa0 [<ffffffff8104082a>] warn_slowpath_null+0x1a/0x20 [<ffffffff813fb279>] __tty_hangup+0x459/0x460 [<ffffffff8107409c>] ? finish_task_switch+0xbc/0xe0 [<ffffffff813fb297>] do_tty_hangup+0x17/0x20 [<ffffffff8105fd6f>] process_one_work+0x16f/0x450 [<ffffffff8106007c>] process_scheduled_works+0x2c/0x40 [<ffffffff8106060a>] worker_thread+0x26a/0x380 [<ffffffff810603a0>] ? rescuer_thread+0x310/0x310 [<ffffffff810698a0>] kthread+0xc0/0xd0 [<ffffffff816b0000>] ? destroy_compound_page+0x65/0x92 [<ffffffff810697e0>] ? kthread_create_on_node+0x130/0x130 [<ffffffff816c495c>] ret_from_fork+0x7c/0xb0 [<ffffffff810697e0>] ? kthread_create_on_node+0x130/0x130 ---[ end trace 98d9f01536cf411e ]--- Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-08-01 02:05:45 +08:00
if (test_bit(TTY_HUPPED, &tty->flags)) {
tty_unlock(tty);
return;
}
tty: make n_tty_read() always abort if hangup is in progress A tty is hung up by __tty_hangup() setting file->f_op to hung_up_tty_fops, which is skipped on ttys whose write operation isn't tty_write(). This means that, for example, /dev/console whose write op is redirected_tty_write() is never actually marked hung up. Because n_tty_read() uses the hung up status to decide whether to abort the waiting readers, the lack of hung-up marking can lead to the following scenario. 1. A session contains two processes. The leader and its child. The child ignores SIGHUP. 2. The leader exits and starts disassociating from the controlling terminal (/dev/console). 3. __tty_hangup() skips setting f_op to hung_up_tty_fops. 4. SIGHUP is delivered and ignored. 5. tty_ldisc_hangup() is invoked. It wakes up the waits which should clear the read lockers of tty->ldisc_sem. 6. The reader wakes up but because tty_hung_up_p() is false, it doesn't abort and goes back to sleep while read-holding tty->ldisc_sem. 7. The leader progresses to tty_ldisc_lock() in tty_ldisc_hangup() and is now stuck in D sleep indefinitely waiting for tty->ldisc_sem. The following is Alan's explanation on why some ttys aren't hung up. http://lkml.kernel.org/r/20171101170908.6ad08580@alans-desktop 1. It broke the serial consoles because they would hang up and close down the hardware. With tty_port that *should* be fixable properly for any cases remaining. 2. The console layer was (and still is) completely broken and doens't refcount properly. So if you turn on console hangups it breaks (as indeed does freeing consoles and half a dozen other things). As neither can be fixed quickly, this patch works around the problem by introducing a new flag, TTY_HUPPING, which is used solely to tell n_tty_read() that hang-up is in progress for the console and the readers should be aborted regardless of the hung-up status of the device. The following is a sample hung task warning caused by this issue. INFO: task agetty:2662 blocked for more than 120 seconds. Not tainted 4.11.3-dbg-tty-lockup-02478-gfd6c7ee-dirty #28 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. 0 2662 1 0x00000086 Call Trace: __schedule+0x267/0x890 schedule+0x36/0x80 schedule_timeout+0x23c/0x2e0 ldsem_down_write+0xce/0x1f6 tty_ldisc_lock+0x16/0x30 tty_ldisc_hangup+0xb3/0x1b0 __tty_hangup+0x300/0x410 disassociate_ctty+0x6c/0x290 do_exit+0x7ef/0xb00 do_group_exit+0x3f/0xa0 get_signal+0x1b3/0x5d0 do_signal+0x28/0x660 exit_to_usermode_loop+0x46/0x86 do_syscall_64+0x9c/0xb0 entry_SYSCALL64_slow_path+0x25/0x25 The following is the repro. Run "$PROG /dev/console". The parent process hangs in D state. #include <sys/types.h> #include <sys/stat.h> #include <sys/wait.h> #include <sys/ioctl.h> #include <fcntl.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> #include <errno.h> #include <signal.h> #include <time.h> #include <termios.h> int main(int argc, char **argv) { struct sigaction sact = { .sa_handler = SIG_IGN }; struct timespec ts1s = { .tv_sec = 1 }; pid_t pid; int fd; if (argc < 2) { fprintf(stderr, "test-hung-tty /dev/$TTY\n"); return 1; } /* fork a child to ensure that it isn't already the session leader */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { /* top parent, wait for everyone */ while (waitpid(-1, NULL, 0) >= 0) ; if (errno != ECHILD) perror("waitpid"); return 0; } /* new session, start a new session and set the controlling tty */ if (setsid() < 0) { perror("setsid"); return 1; } fd = open(argv[1], O_RDWR); if (fd < 0) { perror("open"); return 1; } if (ioctl(fd, TIOCSCTTY, 1) < 0) { perror("ioctl"); return 1; } /* fork a child, sleep a bit and exit */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { nanosleep(&ts1s, NULL); printf("Session leader exiting\n"); exit(0); } /* * The child ignores SIGHUP and keeps reading from the controlling * tty. Because SIGHUP is ignored, the child doesn't get killed on * parent exit and the bug in n_tty makes the read(2) block the * parent's control terminal hangup attempt. The parent ends up in * D sleep until the child is explicitly killed. */ sigaction(SIGHUP, &sact, NULL); printf("Child reading tty\n"); while (1) { char buf[1024]; if (read(fd, buf, sizeof(buf)) < 0) { perror("read"); return 1; } } return 0; } Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Alan Cox <alan@llwyncelyn.cymru> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-13 23:38:08 +08:00
/*
* Some console devices aren't actually hung up for technical and
* historical reasons, which can lead to indefinite interruptible
* sleep in n_tty_read(). The following explicitly tells
* n_tty_read() to abort readers.
*/
set_bit(TTY_HUPPING, &tty->flags);
/* inuse_filps is protected by the single tty lock,
* this really needs to change if we want to flush the
* workqueue with the lock held.
*/
check_tty_count(tty, "tty_hangup");
spin_lock(&tty->files_lock);
/* This breaks for file handles being sent over AF_UNIX sockets ? */
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
list_for_each_entry(priv, &tty->tty_files, list) {
filp = priv->file;
if (filp->f_op->write_iter == redirected_tty_write)
cons_filp = filp;
if (filp->f_op->write_iter != tty_write)
continue;
closecount++;
__tty_fasync(-1, filp, 0); /* can't block */
filp->f_op = &hung_up_tty_fops;
}
spin_unlock(&tty->files_lock);
tty: Signal SIGHUP before hanging up ldisc An exiting session leader can hang if a foreground process is blocking for line discipline i/o, eg. in n_tty_read(). This happens because the blocking reader is holding an ldisc reference (indicating the line discipline is in-use) which prevents __tty_hangup() from recycling the line discipline. Although waiters are woken before attempting to gain exclusive access for changing the ldisc, the blocking reader in this case will not exit the i/o loop since it has not yet received SIGHUP (because it has not been sent). Instead, perform signalling first, then recycle the line discipline. Fixes: INFO: task init:1 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. init D 00000000001d7180 2688 1 0 0x00000002 ffff8800b9acfba8 0000000000000002 00000000001d7180 ffff8800b9b10048 ffff8800b94cb000 ffff8800b9b10000 00000000001d7180 00000000001d7180 ffff8800b9b10000 ffff8800b9acffd8 00000000001d7180 00000000001d7180 Call Trace: [<ffffffff83db9909>] __schedule+0x2e9/0x3b0 [<ffffffff83db9b35>] schedule+0x55/0x60 [<ffffffff83db74ba>] schedule_timeout+0x3a/0x370 [<ffffffff81182349>] ? mark_held_locks+0xf9/0x130 [<ffffffff83dbab38>] ? down_failed+0x108/0x200 [<ffffffff83dbb7ab>] ? _raw_spin_unlock_irq+0x2b/0x80 [<ffffffff81182608>] ? trace_hardirqs_on_caller+0x128/0x160 [<ffffffff83dbab61>] down_failed+0x131/0x200 [<ffffffff83dbbfad>] ? tty_ldisc_lock_pair_timeout+0xcd/0x120 [<ffffffff83dbae03>] ldsem_down_write+0xd3/0x113 [<ffffffff83dbbfad>] ? tty_ldisc_lock_pair_timeout+0xcd/0x120 [<ffffffff8118264d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff83dbbfad>] tty_ldisc_lock_pair_timeout+0xcd/0x120 [<ffffffff81c3df60>] tty_ldisc_hangup+0xd0/0x220 [<ffffffff81c35bd7>] __tty_hangup+0x137/0x4f0 [<ffffffff81c37c7c>] disassociate_ctty+0x6c/0x230 [<ffffffff8111290c>] do_exit+0x41c/0x590 [<ffffffff8107ad34>] ? syscall_trace_enter+0x24/0x2e0 [<ffffffff81112b4a>] do_group_exit+0x8a/0xc0 [<ffffffff81112b92>] sys_exit_group+0x12/0x20 [<ffffffff83dc49d8>] tracesys+0xe1/0xe6 1 lock held by init/1: #0: (&tty->ldisc_sem){++++++}, at: [<ffffffff83dbbfad>] tty_ldisc_lock_pair_timeout+0xcd/0x120 Reported-by: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Acked-by: Jiri Slaby <jslaby@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-03-06 20:20:57 +08:00
refs = tty_signal_session_leader(tty, exit_session);
/* Account for the p->signal references we killed */
while (refs--)
tty_kref_put(tty);
tty: Destroy ldisc instance on hangup Currently, when the tty is hungup, the ldisc is re-instanced; ie., the current instance is destroyed and a new instance is created. The purpose of this design was to guarantee a valid, open ldisc for the lifetime of the tty. However, now that tty buffers are owned by and have lifetime equivalent to the tty_port (since v3.10), any data received immediately after the ldisc is re-instanced may cause continued driver i/o operations concurrently with the driver's hangup() operation. For drivers that shutdown h/w on hangup, this is unexpected and usually bad. For example, the serial core may free the xmit buffer page concurrently with an in-progress write() operation (triggered by echo). With the existing stable and robust ldisc reference handling, the cleaned-up tty_reopen(), the straggling unsafe ldisc use cleaned up, and the preparation to properly handle a NULL tty->ldisc, the ldisc instance can be destroyed and only re-instanced when the tty is re-opened. If the tty was opened as /dev/console or /dev/tty0, the original behavior of re-instancing the ldisc is retained (the 'reinit' parameter to tty_ldisc_hangup() is true). This is required since those file descriptors are never hungup. This patch has neglible impact on userspace; the tty file_operations ptr is changed to point to the hungup file operations _before_ the ldisc instance is destroyed, so only racing file operations might now retrieve a NULL ldisc reference (which is simply handled as if the hungup file operation had been called instead -- see "tty: Prepare for destroying line discipline on hangup"). This resolves a long-standing FIXME and several crash reports. Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-01-11 14:41:06 +08:00
tty_ldisc_hangup(tty, cons_filp != NULL);
spin_lock_irq(&tty->ctrl.lock);
clear_bit(TTY_THROTTLED, &tty->flags);
clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
put_pid(tty->ctrl.session);
put_pid(tty->ctrl.pgrp);
tty->ctrl.session = NULL;
tty->ctrl.pgrp = NULL;
tty->ctrl.pktstatus = 0;
spin_unlock_irq(&tty->ctrl.lock);
/*
* If one of the devices matches a console pointer, we
* cannot just call hangup() because that will cause
* tty->count and state->count to go out of sync.
* So we just call close() the right number of times.
*/
if (cons_filp) {
if (tty->ops->close)
for (n = 0; n < closecount; n++)
tty->ops->close(tty, cons_filp);
} else if (tty->ops->hangup)
tty->ops->hangup(tty);
/*
tty: Destroy ldisc instance on hangup Currently, when the tty is hungup, the ldisc is re-instanced; ie., the current instance is destroyed and a new instance is created. The purpose of this design was to guarantee a valid, open ldisc for the lifetime of the tty. However, now that tty buffers are owned by and have lifetime equivalent to the tty_port (since v3.10), any data received immediately after the ldisc is re-instanced may cause continued driver i/o operations concurrently with the driver's hangup() operation. For drivers that shutdown h/w on hangup, this is unexpected and usually bad. For example, the serial core may free the xmit buffer page concurrently with an in-progress write() operation (triggered by echo). With the existing stable and robust ldisc reference handling, the cleaned-up tty_reopen(), the straggling unsafe ldisc use cleaned up, and the preparation to properly handle a NULL tty->ldisc, the ldisc instance can be destroyed and only re-instanced when the tty is re-opened. If the tty was opened as /dev/console or /dev/tty0, the original behavior of re-instancing the ldisc is retained (the 'reinit' parameter to tty_ldisc_hangup() is true). This is required since those file descriptors are never hungup. This patch has neglible impact on userspace; the tty file_operations ptr is changed to point to the hungup file operations _before_ the ldisc instance is destroyed, so only racing file operations might now retrieve a NULL ldisc reference (which is simply handled as if the hungup file operation had been called instead -- see "tty: Prepare for destroying line discipline on hangup"). This resolves a long-standing FIXME and several crash reports. Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-01-11 14:41:06 +08:00
* We don't want to have driver/ldisc interactions beyond the ones
* we did here. The driver layer expects no calls after ->hangup()
* from the ldisc side, which is now guaranteed.
*/
set_bit(TTY_HUPPED, &tty->flags);
tty: make n_tty_read() always abort if hangup is in progress A tty is hung up by __tty_hangup() setting file->f_op to hung_up_tty_fops, which is skipped on ttys whose write operation isn't tty_write(). This means that, for example, /dev/console whose write op is redirected_tty_write() is never actually marked hung up. Because n_tty_read() uses the hung up status to decide whether to abort the waiting readers, the lack of hung-up marking can lead to the following scenario. 1. A session contains two processes. The leader and its child. The child ignores SIGHUP. 2. The leader exits and starts disassociating from the controlling terminal (/dev/console). 3. __tty_hangup() skips setting f_op to hung_up_tty_fops. 4. SIGHUP is delivered and ignored. 5. tty_ldisc_hangup() is invoked. It wakes up the waits which should clear the read lockers of tty->ldisc_sem. 6. The reader wakes up but because tty_hung_up_p() is false, it doesn't abort and goes back to sleep while read-holding tty->ldisc_sem. 7. The leader progresses to tty_ldisc_lock() in tty_ldisc_hangup() and is now stuck in D sleep indefinitely waiting for tty->ldisc_sem. The following is Alan's explanation on why some ttys aren't hung up. http://lkml.kernel.org/r/20171101170908.6ad08580@alans-desktop 1. It broke the serial consoles because they would hang up and close down the hardware. With tty_port that *should* be fixable properly for any cases remaining. 2. The console layer was (and still is) completely broken and doens't refcount properly. So if you turn on console hangups it breaks (as indeed does freeing consoles and half a dozen other things). As neither can be fixed quickly, this patch works around the problem by introducing a new flag, TTY_HUPPING, which is used solely to tell n_tty_read() that hang-up is in progress for the console and the readers should be aborted regardless of the hung-up status of the device. The following is a sample hung task warning caused by this issue. INFO: task agetty:2662 blocked for more than 120 seconds. Not tainted 4.11.3-dbg-tty-lockup-02478-gfd6c7ee-dirty #28 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. 0 2662 1 0x00000086 Call Trace: __schedule+0x267/0x890 schedule+0x36/0x80 schedule_timeout+0x23c/0x2e0 ldsem_down_write+0xce/0x1f6 tty_ldisc_lock+0x16/0x30 tty_ldisc_hangup+0xb3/0x1b0 __tty_hangup+0x300/0x410 disassociate_ctty+0x6c/0x290 do_exit+0x7ef/0xb00 do_group_exit+0x3f/0xa0 get_signal+0x1b3/0x5d0 do_signal+0x28/0x660 exit_to_usermode_loop+0x46/0x86 do_syscall_64+0x9c/0xb0 entry_SYSCALL64_slow_path+0x25/0x25 The following is the repro. Run "$PROG /dev/console". The parent process hangs in D state. #include <sys/types.h> #include <sys/stat.h> #include <sys/wait.h> #include <sys/ioctl.h> #include <fcntl.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> #include <errno.h> #include <signal.h> #include <time.h> #include <termios.h> int main(int argc, char **argv) { struct sigaction sact = { .sa_handler = SIG_IGN }; struct timespec ts1s = { .tv_sec = 1 }; pid_t pid; int fd; if (argc < 2) { fprintf(stderr, "test-hung-tty /dev/$TTY\n"); return 1; } /* fork a child to ensure that it isn't already the session leader */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { /* top parent, wait for everyone */ while (waitpid(-1, NULL, 0) >= 0) ; if (errno != ECHILD) perror("waitpid"); return 0; } /* new session, start a new session and set the controlling tty */ if (setsid() < 0) { perror("setsid"); return 1; } fd = open(argv[1], O_RDWR); if (fd < 0) { perror("open"); return 1; } if (ioctl(fd, TIOCSCTTY, 1) < 0) { perror("ioctl"); return 1; } /* fork a child, sleep a bit and exit */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { nanosleep(&ts1s, NULL); printf("Session leader exiting\n"); exit(0); } /* * The child ignores SIGHUP and keeps reading from the controlling * tty. Because SIGHUP is ignored, the child doesn't get killed on * parent exit and the bug in n_tty makes the read(2) block the * parent's control terminal hangup attempt. The parent ends up in * D sleep until the child is explicitly killed. */ sigaction(SIGHUP, &sact, NULL); printf("Child reading tty\n"); while (1) { char buf[1024]; if (read(fd, buf, sizeof(buf)) < 0) { perror("read"); return 1; } } return 0; } Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Alan Cox <alan@llwyncelyn.cymru> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-13 23:38:08 +08:00
clear_bit(TTY_HUPPING, &tty->flags);
tty_unlock(tty);
if (f)
fput(f);
}
static void do_tty_hangup(struct work_struct *work)
{
struct tty_struct *tty =
container_of(work, struct tty_struct, hangup_work);
__tty_hangup(tty, 0);
}
/**
* tty_hangup - trigger a hangup event
* @tty: tty to hangup
*
* A carrier loss (virtual or otherwise) has occurred on @tty. Schedule a
* hangup sequence to run after this event.
*/
void tty_hangup(struct tty_struct *tty)
{
tty_debug_hangup(tty, "hangup\n");
schedule_work(&tty->hangup_work);
}
EXPORT_SYMBOL(tty_hangup);
/**
* tty_vhangup - process vhangup
* @tty: tty to hangup
*
* The user has asked via system call for the terminal to be hung up. We do
* this synchronously so that when the syscall returns the process is complete.
* That guarantee is necessary for security reasons.
*/
void tty_vhangup(struct tty_struct *tty)
{
tty_debug_hangup(tty, "vhangup\n");
__tty_hangup(tty, 0);
}
EXPORT_SYMBOL(tty_vhangup);
/**
* tty_vhangup_self - process vhangup for own ctty
*
* Perform a vhangup on the current controlling tty
*/
void tty_vhangup_self(void)
{
struct tty_struct *tty;
tty = get_current_tty();
if (tty) {
tty_vhangup(tty);
tty_kref_put(tty);
}
}
/**
* tty_vhangup_session - hangup session leader exit
* @tty: tty to hangup
*
* The session leader is exiting and hanging up its controlling terminal.
* Every process in the foreground process group is signalled %SIGHUP.
*
* We do this synchronously so that when the syscall returns the process is
* complete. That guarantee is necessary for security reasons.
*/
void tty_vhangup_session(struct tty_struct *tty)
{
tty_debug_hangup(tty, "session hangup\n");
__tty_hangup(tty, 1);
}
/**
* tty_hung_up_p - was tty hung up
* @filp: file pointer of tty
*
* Return: true if the tty has been subject to a vhangup or a carrier loss
*/
int tty_hung_up_p(struct file *filp)
{
tty_port: allow a port to be opened with a tty that has no file handle Let us create tty objects entirely in kernel space. Untested proposal to show why all the ideas around rewriting half the uart stack are not needed. With this a kernel created non file backed tty object could be used to handle data, and set terminal modes. Not all ldiscs can cope with this as N_TTY in particular has to work back to the fs/tty layer. The tty_port code is however otherwise clean of file handles as far as I can tell as is the low level tty port write path used by the ldisc, the configuration low level interfaces and most of the ldiscs. Currently you don't have any exposure to see tty hangups because those are built around the file layer. However a) it's a fixed port so you probably don't care about that b) if you do we can add a callback and c) you almost certainly don't want the userspace tear down/rebuild behaviour anyway. This should however be sufficient if we wanted for example to enumerate all the bluetooth bound fixed ports via ACPI and make them directly available. It doesn't deal with the case of a user opening a port that's also kernel opened and that would need some locking out (so it returned EBUSY if bound to a kernel device of some kind). That needs resolving along with how you "up" or "down" your new bluetooth device, or enumerate it while providing the existing tty API to avoid regressions (and to debug). Signed-off-by: Alan Cox <alan@linux.intel.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Reviewed-By: Sebastian Reichel <sre@kernel.org> Signed-off-by: Rob Herring <robh@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-01-17 06:54:29 +08:00
return (filp && filp->f_op == &hung_up_tty_fops);
}
EXPORT_SYMBOL(tty_hung_up_p);
void __stop_tty(struct tty_struct *tty)
{
if (tty->flow.stopped)
return;
tty->flow.stopped = true;
if (tty->ops->stop)
tty->ops->stop(tty);
}
/**
* stop_tty - propagate flow control
* @tty: tty to stop
*
* Perform flow control to the driver. May be called on an already stopped
* device and will not re-call the &tty_driver->stop() method.
*
* This functionality is used by both the line disciplines for halting incoming
* flow and by the driver. It may therefore be called from any context, may be
* under the tty %atomic_write_lock but not always.
*
* Locking:
* flow.lock
*/
void stop_tty(struct tty_struct *tty)
{
unsigned long flags;
tty: cumulate and document tty_struct::flow* members Group the flow flags under a single struct called flow. The new struct contains 'stopped' and 'tco_stopped' bools which used to be bits in a bitfield. The struct also contains the lock protecting them to potentially share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. This is also the perfect time to start the documentation of tty_struct where all this lives. So we start by documenting what these bools actually serve for. And why we do all the alignment dances. Only the few up-to-date information from the Theodore's comment made it into this new Kerneldoc comment. Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Shawn Guo <shawnguo@kernel.org> Cc: Sascha Hauer <s.hauer@pengutronix.de> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: "Maciej W. Rozycki" <macro@orcam.me.uk> Link: https://lore.kernel.org/r/20210505091928.22010-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-05-05 17:19:05 +08:00
spin_lock_irqsave(&tty->flow.lock, flags);
__stop_tty(tty);
tty: cumulate and document tty_struct::flow* members Group the flow flags under a single struct called flow. The new struct contains 'stopped' and 'tco_stopped' bools which used to be bits in a bitfield. The struct also contains the lock protecting them to potentially share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. This is also the perfect time to start the documentation of tty_struct where all this lives. So we start by documenting what these bools actually serve for. And why we do all the alignment dances. Only the few up-to-date information from the Theodore's comment made it into this new Kerneldoc comment. Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Shawn Guo <shawnguo@kernel.org> Cc: Sascha Hauer <s.hauer@pengutronix.de> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: "Maciej W. Rozycki" <macro@orcam.me.uk> Link: https://lore.kernel.org/r/20210505091928.22010-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-05-05 17:19:05 +08:00
spin_unlock_irqrestore(&tty->flow.lock, flags);
}
EXPORT_SYMBOL(stop_tty);
void __start_tty(struct tty_struct *tty)
{
if (!tty->flow.stopped || tty->flow.tco_stopped)
return;
tty->flow.stopped = false;
if (tty->ops->start)
tty->ops->start(tty);
tty_wakeup(tty);
}
/**
* start_tty - propagate flow control
* @tty: tty to start
*
* Start a tty that has been stopped if at all possible. If @tty was previously
* stopped and is now being started, the &tty_driver->start() method is invoked
* and the line discipline woken.
*
* Locking:
* flow.lock
*/
void start_tty(struct tty_struct *tty)
{
unsigned long flags;
tty: cumulate and document tty_struct::flow* members Group the flow flags under a single struct called flow. The new struct contains 'stopped' and 'tco_stopped' bools which used to be bits in a bitfield. The struct also contains the lock protecting them to potentially share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. This is also the perfect time to start the documentation of tty_struct where all this lives. So we start by documenting what these bools actually serve for. And why we do all the alignment dances. Only the few up-to-date information from the Theodore's comment made it into this new Kerneldoc comment. Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Shawn Guo <shawnguo@kernel.org> Cc: Sascha Hauer <s.hauer@pengutronix.de> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: "Maciej W. Rozycki" <macro@orcam.me.uk> Link: https://lore.kernel.org/r/20210505091928.22010-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-05-05 17:19:05 +08:00
spin_lock_irqsave(&tty->flow.lock, flags);
__start_tty(tty);
tty: cumulate and document tty_struct::flow* members Group the flow flags under a single struct called flow. The new struct contains 'stopped' and 'tco_stopped' bools which used to be bits in a bitfield. The struct also contains the lock protecting them to potentially share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. This is also the perfect time to start the documentation of tty_struct where all this lives. So we start by documenting what these bools actually serve for. And why we do all the alignment dances. Only the few up-to-date information from the Theodore's comment made it into this new Kerneldoc comment. Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Shawn Guo <shawnguo@kernel.org> Cc: Sascha Hauer <s.hauer@pengutronix.de> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: "Maciej W. Rozycki" <macro@orcam.me.uk> Link: https://lore.kernel.org/r/20210505091928.22010-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-05-05 17:19:05 +08:00
spin_unlock_irqrestore(&tty->flow.lock, flags);
}
EXPORT_SYMBOL(start_tty);
static void tty_update_time(struct timespec64 *time)
{
time64_t sec = ktime_get_real_seconds();
/*
* We only care if the two values differ in anything other than the
* lower three bits (i.e every 8 seconds). If so, then we can update
* the time of the tty device, otherwise it could be construded as a
* security leak to let userspace know the exact timing of the tty.
*/
if ((sec ^ time->tv_sec) & ~7)
time->tv_sec = sec;
}
/*
* Iterate on the ldisc ->read() function until we've gotten all
* the data the ldisc has for us.
*
* The "cookie" is something that the ldisc read function can fill
* in to let us know that there is more data to be had.
*
* We promise to continue to call the ldisc until it stops returning
* data or clears the cookie. The cookie may be something that the
* ldisc maintains state for and needs to free.
*/
static int iterate_tty_read(struct tty_ldisc *ld, struct tty_struct *tty,
struct file *file, struct iov_iter *to)
{
int retval = 0;
void *cookie = NULL;
unsigned long offset = 0;
char kernel_buf[64];
size_t count = iov_iter_count(to);
do {
int size, copied;
size = count > sizeof(kernel_buf) ? sizeof(kernel_buf) : count;
size = ld->ops->read(tty, file, kernel_buf, size, &cookie, offset);
if (!size)
break;
if (size < 0) {
/* Did we have an earlier error (ie -EFAULT)? */
if (retval)
break;
retval = size;
/*
* -EOVERFLOW means we didn't have enough space
* for a whole packet, and we shouldn't return
* a partial result.
*/
if (retval == -EOVERFLOW)
offset = 0;
break;
}
copied = copy_to_iter(kernel_buf, size, to);
offset += copied;
count -= copied;
/*
* If the user copy failed, we still need to do another ->read()
* call if we had a cookie to let the ldisc clear up.
*
* But make sure size is zeroed.
*/
if (unlikely(copied != size)) {
count = 0;
retval = -EFAULT;
}
} while (cookie);
/* We always clear tty buffer in case they contained passwords */
memzero_explicit(kernel_buf, sizeof(kernel_buf));
return offset ? offset : retval;
}
/**
* tty_read - read method for tty device files
* @iocb: kernel I/O control block
* @to: destination for the data read
*
* Perform the read system call function on this terminal device. Checks
* for hung up devices before calling the line discipline method.
*
* Locking:
* Locks the line discipline internally while needed. Multiple read calls
* may be outstanding in parallel.
*/
static ssize_t tty_read(struct kiocb *iocb, struct iov_iter *to)
{
int i;
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_struct *tty = file_tty(file);
struct tty_ldisc *ld;
if (tty_paranoia_check(tty, inode, "tty_read"))
return -EIO;
if (!tty || tty_io_error(tty))
return -EIO;
/* We want to wait for the line discipline to sort out in this
* situation.
*/
ld = tty_ldisc_ref_wait(tty);
if (!ld)
return hung_up_tty_read(iocb, to);
i = -EIO;
if (ld->ops->read)
i = iterate_tty_read(ld, tty, file, to);
tty_ldisc_deref(ld);
if (i > 0)
tty_update_time(&inode->i_atime);
return i;
}
void tty_write_unlock(struct tty_struct *tty)
{
mutex_unlock(&tty->atomic_write_lock);
wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT);
}
int tty_write_lock(struct tty_struct *tty, int ndelay)
{
if (!mutex_trylock(&tty->atomic_write_lock)) {
if (ndelay)
return -EAGAIN;
if (mutex_lock_interruptible(&tty->atomic_write_lock))
return -ERESTARTSYS;
}
return 0;
}
/*
* Split writes up in sane blocksizes to avoid
* denial-of-service type attacks
*/
static inline ssize_t do_tty_write(
ssize_t (*write)(struct tty_struct *, struct file *, const unsigned char *, size_t),
struct tty_struct *tty,
struct file *file,
struct iov_iter *from)
{
size_t count = iov_iter_count(from);
ssize_t ret, written = 0;
unsigned int chunk;
ret = tty_write_lock(tty, file->f_flags & O_NDELAY);
if (ret < 0)
return ret;
/*
* We chunk up writes into a temporary buffer. This
* simplifies low-level drivers immensely, since they
* don't have locking issues and user mode accesses.
*
* But if TTY_NO_WRITE_SPLIT is set, we should use a
* big chunk-size..
*
* The default chunk-size is 2kB, because the NTTY
* layer has problems with bigger chunks. It will
* claim to be able to handle more characters than
* it actually does.
*/
chunk = 2048;
if (test_bit(TTY_NO_WRITE_SPLIT, &tty->flags))
chunk = 65536;
if (count < chunk)
chunk = count;
/* write_buf/write_cnt is protected by the atomic_write_lock mutex */
if (tty->write_cnt < chunk) {
unsigned char *buf_chunk;
if (chunk < 1024)
chunk = 1024;
buf_chunk = kvmalloc(chunk, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
if (!buf_chunk) {
ret = -ENOMEM;
goto out;
}
kvfree(tty->write_buf);
tty->write_cnt = chunk;
tty->write_buf = buf_chunk;
}
/* Do the write .. */
for (;;) {
size_t size = count;
if (size > chunk)
size = chunk;
ret = -EFAULT;
if (copy_from_iter(tty->write_buf, size, from) != size)
break;
ret = write(tty, file, tty->write_buf, size);
if (ret <= 0)
break;
written += ret;
if (ret > size)
break;
/* FIXME! Have Al check this! */
if (ret != size)
iov_iter_revert(from, size-ret);
count -= ret;
if (!count)
break;
ret = -ERESTARTSYS;
if (signal_pending(current))
break;
cond_resched();
}
if (written) {
tty_update_time(&file_inode(file)->i_mtime);
ret = written;
}
out:
tty_write_unlock(tty);
return ret;
}
/**
* tty_write_message - write a message to a certain tty, not just the console.
* @tty: the destination tty_struct
* @msg: the message to write
*
* This is used for messages that need to be redirected to a specific tty. We
* don't put it into the syslog queue right now maybe in the future if really
* needed.
*
* We must still hold the BTM and test the CLOSING flag for the moment.
*/
void tty_write_message(struct tty_struct *tty, char *msg)
{
if (tty) {
mutex_lock(&tty->atomic_write_lock);
tty_lock(tty);
if (tty->ops->write && tty->count > 0)
tty->ops->write(tty, msg, strlen(msg));
tty_unlock(tty);
tty_write_unlock(tty);
}
}
tty: avoid using vfs_iocb_iter_write() for redirected console writes It turns out that the vfs_iocb_iter_{read,write}() functions are entirely broken, and don't actually use the passed-in file pointer for IO - only for the preparatory work (permission checking and for the write_iter function lookup). That worked fine for overlayfs, which always builds the new iocb with the same file pointer that it passes in, but in the general case it ends up doing nonsensical things (and could cause an iterator call that doesn't even match the passed-in file pointer). This subtly broke the tty conversion to write_iter in commit 9bb48c82aced ("tty: implement write_iter"), because the console redirection didn't actually end up redirecting anything, since the passed-in file pointer was basically ignored, and the actual write was done with the original non-redirected console tty after all. The main visible effect of this is that the console messages were no longer logged to /var/log/boot.log during graphical boot. Fix the issue by simply not using the vfs write "helper" function at all, and just redirecting the write entirely internally to the tty layer. Do the target writability permission checks when actually registering the target tty with TIOCCONS instead of at write time. Fixes: 9bb48c82aced ("tty: implement write_iter") Reported-and-tested-by: Hans de Goede <hdegoede@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-01-30 04:28:20 +08:00
static ssize_t file_tty_write(struct file *file, struct kiocb *iocb, struct iov_iter *from)
{
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_struct *tty = file_tty(file);
struct tty_ldisc *ld;
ssize_t ret;
if (tty_paranoia_check(tty, file_inode(file), "tty_write"))
return -EIO;
if (!tty || !tty->ops->write || tty_io_error(tty))
return -EIO;
/* Short term debug to catch buggy drivers */
if (tty->ops->write_room == NULL)
tty_err(tty, "missing write_room method\n");
ld = tty_ldisc_ref_wait(tty);
if (!ld)
return hung_up_tty_write(iocb, from);
if (!ld->ops->write)
ret = -EIO;
else
ret = do_tty_write(ld->ops->write, tty, file, from);
tty_ldisc_deref(ld);
return ret;
}
/**
* tty_write - write method for tty device file
* @iocb: kernel I/O control block
* @from: iov_iter with data to write
*
* Write data to a tty device via the line discipline.
*
* Locking:
* Locks the line discipline as required
* Writes to the tty driver are serialized by the atomic_write_lock
* and are then processed in chunks to the device. The line
* discipline write method will not be invoked in parallel for
* each device.
*/
tty: avoid using vfs_iocb_iter_write() for redirected console writes It turns out that the vfs_iocb_iter_{read,write}() functions are entirely broken, and don't actually use the passed-in file pointer for IO - only for the preparatory work (permission checking and for the write_iter function lookup). That worked fine for overlayfs, which always builds the new iocb with the same file pointer that it passes in, but in the general case it ends up doing nonsensical things (and could cause an iterator call that doesn't even match the passed-in file pointer). This subtly broke the tty conversion to write_iter in commit 9bb48c82aced ("tty: implement write_iter"), because the console redirection didn't actually end up redirecting anything, since the passed-in file pointer was basically ignored, and the actual write was done with the original non-redirected console tty after all. The main visible effect of this is that the console messages were no longer logged to /var/log/boot.log during graphical boot. Fix the issue by simply not using the vfs write "helper" function at all, and just redirecting the write entirely internally to the tty layer. Do the target writability permission checks when actually registering the target tty with TIOCCONS instead of at write time. Fixes: 9bb48c82aced ("tty: implement write_iter") Reported-and-tested-by: Hans de Goede <hdegoede@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-01-30 04:28:20 +08:00
static ssize_t tty_write(struct kiocb *iocb, struct iov_iter *from)
{
return file_tty_write(iocb->ki_filp, iocb, from);
}
ssize_t redirected_tty_write(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *p = NULL;
spin_lock(&redirect_lock);
if (redirect)
p = get_file(redirect);
spin_unlock(&redirect_lock);
tty: avoid using vfs_iocb_iter_write() for redirected console writes It turns out that the vfs_iocb_iter_{read,write}() functions are entirely broken, and don't actually use the passed-in file pointer for IO - only for the preparatory work (permission checking and for the write_iter function lookup). That worked fine for overlayfs, which always builds the new iocb with the same file pointer that it passes in, but in the general case it ends up doing nonsensical things (and could cause an iterator call that doesn't even match the passed-in file pointer). This subtly broke the tty conversion to write_iter in commit 9bb48c82aced ("tty: implement write_iter"), because the console redirection didn't actually end up redirecting anything, since the passed-in file pointer was basically ignored, and the actual write was done with the original non-redirected console tty after all. The main visible effect of this is that the console messages were no longer logged to /var/log/boot.log during graphical boot. Fix the issue by simply not using the vfs write "helper" function at all, and just redirecting the write entirely internally to the tty layer. Do the target writability permission checks when actually registering the target tty with TIOCCONS instead of at write time. Fixes: 9bb48c82aced ("tty: implement write_iter") Reported-and-tested-by: Hans de Goede <hdegoede@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-01-30 04:28:20 +08:00
/*
* We know the redirected tty is just another tty, we can
tty: avoid using vfs_iocb_iter_write() for redirected console writes It turns out that the vfs_iocb_iter_{read,write}() functions are entirely broken, and don't actually use the passed-in file pointer for IO - only for the preparatory work (permission checking and for the write_iter function lookup). That worked fine for overlayfs, which always builds the new iocb with the same file pointer that it passes in, but in the general case it ends up doing nonsensical things (and could cause an iterator call that doesn't even match the passed-in file pointer). This subtly broke the tty conversion to write_iter in commit 9bb48c82aced ("tty: implement write_iter"), because the console redirection didn't actually end up redirecting anything, since the passed-in file pointer was basically ignored, and the actual write was done with the original non-redirected console tty after all. The main visible effect of this is that the console messages were no longer logged to /var/log/boot.log during graphical boot. Fix the issue by simply not using the vfs write "helper" function at all, and just redirecting the write entirely internally to the tty layer. Do the target writability permission checks when actually registering the target tty with TIOCCONS instead of at write time. Fixes: 9bb48c82aced ("tty: implement write_iter") Reported-and-tested-by: Hans de Goede <hdegoede@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-01-30 04:28:20 +08:00
* call file_tty_write() directly with that file pointer.
*/
if (p) {
ssize_t res;
tty: avoid using vfs_iocb_iter_write() for redirected console writes It turns out that the vfs_iocb_iter_{read,write}() functions are entirely broken, and don't actually use the passed-in file pointer for IO - only for the preparatory work (permission checking and for the write_iter function lookup). That worked fine for overlayfs, which always builds the new iocb with the same file pointer that it passes in, but in the general case it ends up doing nonsensical things (and could cause an iterator call that doesn't even match the passed-in file pointer). This subtly broke the tty conversion to write_iter in commit 9bb48c82aced ("tty: implement write_iter"), because the console redirection didn't actually end up redirecting anything, since the passed-in file pointer was basically ignored, and the actual write was done with the original non-redirected console tty after all. The main visible effect of this is that the console messages were no longer logged to /var/log/boot.log during graphical boot. Fix the issue by simply not using the vfs write "helper" function at all, and just redirecting the write entirely internally to the tty layer. Do the target writability permission checks when actually registering the target tty with TIOCCONS instead of at write time. Fixes: 9bb48c82aced ("tty: implement write_iter") Reported-and-tested-by: Hans de Goede <hdegoede@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-01-30 04:28:20 +08:00
res = file_tty_write(p, iocb, iter);
fput(p);
return res;
}
return tty_write(iocb, iter);
}
/**
* tty_send_xchar - send priority character
* @tty: the tty to send to
* @ch: xchar to send
*
* Send a high priority character to the tty even if stopped.
*
* Locking: none for xchar method, write ordering for write method.
*/
int tty_send_xchar(struct tty_struct *tty, char ch)
{
tty: cumulate and document tty_struct::flow* members Group the flow flags under a single struct called flow. The new struct contains 'stopped' and 'tco_stopped' bools which used to be bits in a bitfield. The struct also contains the lock protecting them to potentially share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. This is also the perfect time to start the documentation of tty_struct where all this lives. So we start by documenting what these bools actually serve for. And why we do all the alignment dances. Only the few up-to-date information from the Theodore's comment made it into this new Kerneldoc comment. Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Shawn Guo <shawnguo@kernel.org> Cc: Sascha Hauer <s.hauer@pengutronix.de> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: "Maciej W. Rozycki" <macro@orcam.me.uk> Link: https://lore.kernel.org/r/20210505091928.22010-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-05-05 17:19:05 +08:00
bool was_stopped = tty->flow.stopped;
if (tty->ops->send_xchar) {
down_read(&tty->termios_rwsem);
tty->ops->send_xchar(tty, ch);
up_read(&tty->termios_rwsem);
return 0;
}
if (tty_write_lock(tty, 0) < 0)
return -ERESTARTSYS;
down_read(&tty->termios_rwsem);
if (was_stopped)
start_tty(tty);
tty->ops->write(tty, &ch, 1);
if (was_stopped)
stop_tty(tty);
up_read(&tty->termios_rwsem);
tty_write_unlock(tty);
return 0;
}
/**
* pty_line_name - generate name for a pty
* @driver: the tty driver in use
* @index: the minor number
* @p: output buffer of at least 6 bytes
*
* Generate a name from a @driver reference and write it to the output buffer
* @p.
*
* Locking: None
*/
static void pty_line_name(struct tty_driver *driver, int index, char *p)
{
static const char ptychar[] = "pqrstuvwxyzabcde";
int i = index + driver->name_base;
/* ->name is initialized to "ttyp", but "tty" is expected */
sprintf(p, "%s%c%x",
driver->subtype == PTY_TYPE_SLAVE ? "tty" : driver->name,
ptychar[i >> 4 & 0xf], i & 0xf);
}
/**
* tty_line_name - generate name for a tty
* @driver: the tty driver in use
* @index: the minor number
* @p: output buffer of at least 7 bytes
*
* Generate a name from a @driver reference and write it to the output buffer
* @p.
*
* Locking: None
*/
static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p)
{
if (driver->flags & TTY_DRIVER_UNNUMBERED_NODE)
return sprintf(p, "%s", driver->name);
else
return sprintf(p, "%s%d", driver->name,
index + driver->name_base);
}
/**
* tty_driver_lookup_tty() - find an existing tty, if any
* @driver: the driver for the tty
* @file: file object
* @idx: the minor number
*
* Return: the tty, if found. If not found, return %NULL or ERR_PTR() if the
* driver lookup() method returns an error.
*
* Locking: tty_mutex must be held. If the tty is found, bump the tty kref.
*/
static struct tty_struct *tty_driver_lookup_tty(struct tty_driver *driver,
devpts: more pty driver interface cleanups This is more prep-work for the upcoming pty changes. Still just code cleanup with no actual semantic changes. This removes a bunch pointless complexity by just having the slave pty side remember the dentry associated with the devpts slave rather than the inode. That allows us to remove all the "look up the dentry" code for when we want to remove it again. Together with moving the tty pointer from "inode->i_private" to "dentry->d_fsdata" and getting rid of pointless inode locking, this removes about 30 lines of code. Not only is the end result smaller, it's simpler and easier to understand. The old code, for example, depended on the d_find_alias() to not just find the dentry, but also to check that it is still hashed, which in turn validated the tty pointer in the inode. That is a _very_ roundabout way to say "invalidate the cached tty pointer when the dentry is removed". The new code just does dentry->d_fsdata = NULL; in devpts_pty_kill() instead, invalidating the tty pointer rather more directly and obviously. Don't do something complex and subtle when the obvious straightforward approach will do. The rest of the patch (ie apart from code deletion and the above tty pointer clearing) is just switching the calling convention to pass the dentry or file pointer around instead of the inode. Cc: Eric Biederman <ebiederm@xmission.com> Cc: Peter Anvin <hpa@zytor.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Serge Hallyn <serge.hallyn@ubuntu.com> Cc: Willy Tarreau <w@1wt.eu> Cc: Aurelien Jarno <aurelien@aurel32.net> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: Jann Horn <jann@thejh.net> Cc: Greg KH <greg@kroah.com> Cc: Jiri Slaby <jslaby@suse.com> Cc: Florian Weimer <fw@deneb.enyo.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-26 11:04:08 +08:00
struct file *file, int idx)
{
struct tty_struct *tty;
if (driver->ops->lookup) {
tty: export tty_open_by_driver This exports tty_open_by_driver so that it can be called from other places inside the kernel. The checks for null file pointer are based on Alan Cox's patch here: http://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1215095.html. Description below is quoted from it: "[RFC] tty_port: allow a port to be opened with a tty that has no file handle Let us create tty objects entirely in kernel space. Untested proposal to show why all the ideas around rewriting half the uart stack are not needed. With this a kernel created non file backed tty object could be used to handle data, and set terminal modes. Not all ldiscs can cope with this as N_TTY in particular has to work back to the fs/tty layer. The tty_port code is however otherwise clean of file handles as far as I can tell as is the low level tty port write path used by the ldisc, the configuration low level interfaces and most of the ldiscs. Currently you don't have any exposure to see tty hangups because those are built around the file layer. However a) it's a fixed port so you probably don't care about that b) if you do we can add a callback and c) you almost certainly don't want the userspace tear down/rebuild behaviour anyway. This should however be sufficient if we wanted for example to enumerate all the bluetooth bound fixed ports via ACPI and make them directly available. It doesn't deal with the case of a user opening a port that's also kernel opened and that would need some locking out (so it returned EBUSY if bound to a kernel device of some kind). That needs resolving along with how you "up" or "down" your new bluetooth device, or enumerate it while providing the existing tty API to avoid regressions (and to debug)." The exported funtion is used later in this patch set to gain access to tty_struct. [changed export symbol level - gkh] Signed-off-by: Okash Khawaja <okash.khawaja@gmail.com> Reviewed-by: Samuel Thibault <samuel.thibault@ens-lyon.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-05-16 01:45:32 +08:00
if (!file)
tty = ERR_PTR(-EIO);
else
tty = driver->ops->lookup(driver, file, idx);
} else {
if (idx >= driver->num)
return ERR_PTR(-EINVAL);
tty = driver->ttys[idx];
}
if (!IS_ERR(tty))
tty_kref_get(tty);
return tty;
}
/**
* tty_init_termios - helper for termios setup
* @tty: the tty to set up
*
* Initialise the termios structure for this tty. This runs under the
* %tty_mutex currently so we can be relaxed about ordering.
*/
void tty_init_termios(struct tty_struct *tty)
{
struct ktermios *tp;
int idx = tty->index;
if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS)
tty->termios = tty->driver->init_termios;
else {
/* Check for lazy saved data */
tp = tty->driver->termios[idx];
if (tp != NULL) {
tty->termios = *tp;
tty->termios.c_line = tty->driver->init_termios.c_line;
} else
tty->termios = tty->driver->init_termios;
}
/* Compatibility until drivers always set this */
tty->termios.c_ispeed = tty_termios_input_baud_rate(&tty->termios);
tty->termios.c_ospeed = tty_termios_baud_rate(&tty->termios);
}
EXPORT_SYMBOL_GPL(tty_init_termios);
/**
* tty_standard_install - usual tty->ops->install
* @driver: the driver for the tty
* @tty: the tty
*
* If the @driver overrides @tty->ops->install, it still can call this function
* to perform the standard install operations.
*/
int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty)
{
tty_init_termios(tty);
tty_driver_kref_get(driver);
tty->count++;
driver->ttys[tty->index] = tty;
return 0;
}
EXPORT_SYMBOL_GPL(tty_standard_install);
/**
* tty_driver_install_tty() - install a tty entry in the driver
* @driver: the driver for the tty
* @tty: the tty
*
* Install a tty object into the driver tables. The @tty->index field will be
* set by the time this is called. This method is responsible for ensuring any
* need additional structures are allocated and configured.
*
* Locking: tty_mutex for now
*/
static int tty_driver_install_tty(struct tty_driver *driver,
struct tty_struct *tty)
{
return driver->ops->install ? driver->ops->install(driver, tty) :
tty_standard_install(driver, tty);
}
/**
* tty_driver_remove_tty() - remove a tty from the driver tables
* @driver: the driver for the tty
* @tty: tty to remove
*
* Remove a tty object from the driver tables. The tty->index field will be set
* by the time this is called.
*
* Locking: tty_mutex for now
*/
static void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct *tty)
{
if (driver->ops->remove)
driver->ops->remove(driver, tty);
else
driver->ttys[tty->index] = NULL;
}
/**
* tty_reopen() - fast re-open of an open tty
* @tty: the tty to open
*
* Re-opens on master ptys are not allowed and return -%EIO.
*
* Locking: Caller must hold tty_lock
* Return: 0 on success, -errno on error.
*/
static int tty_reopen(struct tty_struct *tty)
{
struct tty_driver *driver = tty->driver;
struct tty_ldisc *ld;
int retval = 0;
if (driver->type == TTY_DRIVER_TYPE_PTY &&
tty: Clarify re-open behavior of master ptys Re-opening master ptys is not allowed. Once opened and for the remaining lifetime of the master pty, its tty count is 1. If its tty count has dropped to 0, then the master pty was closed and TTY_CLOSING was set, and destruction may begin imminently. Besides the normal case of a legacy BSD pty master being re-opened (which always returns -EIO), this code is only reachable in 2 degenerate cases: 1. The pty master is the controlling terminal (this is possible through the TIOCSCTTY ioctl). pty masters are not designed to be controlling terminals and it's an oversight that tiocsctty() ever let that happen. The attempted open of /dev/tty will always fail. No known program does this. 2. The legacy BSD pty slave was opened first. The slave open will fail in pty_open() and tty_release() will commence. But before tty_release() claims the tty_mutex, there is a very small window where a parallel master open might succeed. In a test of racing legacy BSD slave and master parallel opens, where: slave open attempts: 10000 success:4527 failure:5473 master open attempts: 11728 success:5789 failure:5939 only 8 master open attempts would have succeeded reaching this code and successfully opened the master pty. This case is not possible with SysV ptys. Always return -EIO if a master pty is re-opened or the slave is opened first and the master opened in parallel (for legacy BSD ptys). Furthermore, now that changing the slave's count is not required, the tty_lock is sufficient for preventing concurrent changes to the tty being re-opened (or failing re-opening). Reviewed-by: Alan Cox <alan@linux.intel.com> Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-06 01:12:47 +08:00
driver->subtype == PTY_TYPE_MASTER)
return -EIO;
if (!tty->count)
return -EAGAIN;
if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN))
return -EBUSY;
ld = tty_ldisc_ref_wait(tty);
if (ld) {
tty_ldisc_deref(ld);
} else {
retval = tty_ldisc_lock(tty, 5 * HZ);
if (retval)
return retval;
if (!tty->ldisc)
retval = tty_ldisc_reinit(tty, tty->termios.c_line);
tty_ldisc_unlock(tty);
}
if (retval == 0)
tty->count++;
return retval;
}
/**
* tty_init_dev - initialise a tty device
* @driver: tty driver we are opening a device on
* @idx: device index
*
* Prepare a tty device. This may not be a "new" clean device but could also be
* an active device. The pty drivers require special handling because of this.
*
* Locking:
* The function is called under the tty_mutex, which protects us from the
* tty struct or driver itself going away.
*
* On exit the tty device has the line discipline attached and a reference
* count of 1. If a pair was created for pty/tty use and the other was a pty
* master then it too has a reference count of 1.
*
* WSH 06/09/97: Rewritten to remove races and properly clean up after a failed
* open. The new code protects the open with a mutex, so it's really quite
* straightforward. The mutex locking can probably be relaxed for the (most
* common) case of reopening a tty.
*
* Return: new tty structure
*/
struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx)
{
struct tty_struct *tty;
int retval;
/*
* First time open is complex, especially for PTY devices.
* This code guarantees that either everything succeeds and the
* TTY is ready for operation, or else the table slots are vacated
* and the allocated memory released. (Except that the termios
* may be retained.)
*/
if (!try_module_get(driver->owner))
return ERR_PTR(-ENODEV);
tty = alloc_tty_struct(driver, idx);
if (!tty) {
retval = -ENOMEM;
goto err_module_put;
}
tty_lock(tty);
retval = tty_driver_install_tty(driver, tty);
if (retval < 0)
goto err_free_tty;
if (!tty->port)
tty->port = driver->ports[idx];
if (WARN_RATELIMIT(!tty->port,
"%s: %s driver does not set tty->port. This would crash the kernel. Fix the driver!\n",
__func__, tty->driver->name)) {
retval = -EINVAL;
goto err_release_lock;
}
retval = tty_ldisc_lock(tty, 5 * HZ);
if (retval)
goto err_release_lock;
tty->port->itty = tty;
/*
* Structures all installed ... call the ldisc open routines.
* If we fail here just call release_tty to clean up. No need
* to decrement the use counts, as release_tty doesn't care.
*/
retval = tty_ldisc_setup(tty, tty->link);
if (retval)
goto err_release_tty;
tty_ldisc_unlock(tty);
/* Return the tty locked so that it cannot vanish under the caller */
return tty;
err_free_tty:
tty_unlock(tty);
free_tty_struct(tty);
err_module_put:
module_put(driver->owner);
return ERR_PTR(retval);
/* call the tty release_tty routine to clean out this slot */
err_release_tty:
tty_ldisc_unlock(tty);
tty_info_ratelimited(tty, "ldisc open failed (%d), clearing slot %d\n",
retval, idx);
err_release_lock:
tty_unlock(tty);
release_tty(tty, idx);
return ERR_PTR(retval);
}
USB: serial: console: fix reported terminal settings The USB-serial console implementation has never reported the actual terminal settings used. Despite storing the corresponding cflags in its struct console, these were never honoured on later tty open() where the tty termios would be left initialised to the driver defaults. Unlike the serial console implementation, the USB-serial code calls subdriver open() already at console setup. While calling set_termios() and write() before open() looks like it could work for some USB-serial drivers, others definitely do not expect this, so modelling this after serial core is going to be intrusive, if at all possible. Instead, use a (renamed) tty helper to save the termios data used at console setup so that the tty termios reflects the actual terminal settings after a subsequent tty open(). Note that the calls to tty_init_termios() (tty_driver_install()) and tty_save_termios() are serialised using the disconnect mutex. This specifically fixes a regression that was triggered by a recent change adding software flow control to the pl2303 driver: a getty trying to disable flow control while leaving the baud rate unchanged would now also set the baud rate to the driver default (prior to the flow-control change this had been a noop). Fixes: 7041d9c3f01b ("USB: serial: pl2303: add support for tx xon/xoff flow control") Cc: stable <stable@vger.kernel.org> # 4.18 Cc: Florian Zumbiehl <florz@florz.de> Reported-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Tested-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Johan Hovold <johan@kernel.org>
2018-12-05 00:00:36 +08:00
/**
* tty_save_termios() - save tty termios data in driver table
* @tty: tty whose termios data to save
*
* Locking: Caller guarantees serialisation with tty_init_termios().
*/
void tty_save_termios(struct tty_struct *tty)
{
struct ktermios *tp;
int idx = tty->index;
/* If the port is going to reset then it has no termios to save */
if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS)
return;
/* Stash the termios data */
tp = tty->driver->termios[idx];
if (tp == NULL) {
tp = kmalloc(sizeof(*tp), GFP_KERNEL);
if (tp == NULL)
return;
tty->driver->termios[idx] = tp;
}
*tp = tty->termios;
}
USB: serial: console: fix reported terminal settings The USB-serial console implementation has never reported the actual terminal settings used. Despite storing the corresponding cflags in its struct console, these were never honoured on later tty open() where the tty termios would be left initialised to the driver defaults. Unlike the serial console implementation, the USB-serial code calls subdriver open() already at console setup. While calling set_termios() and write() before open() looks like it could work for some USB-serial drivers, others definitely do not expect this, so modelling this after serial core is going to be intrusive, if at all possible. Instead, use a (renamed) tty helper to save the termios data used at console setup so that the tty termios reflects the actual terminal settings after a subsequent tty open(). Note that the calls to tty_init_termios() (tty_driver_install()) and tty_save_termios() are serialised using the disconnect mutex. This specifically fixes a regression that was triggered by a recent change adding software flow control to the pl2303 driver: a getty trying to disable flow control while leaving the baud rate unchanged would now also set the baud rate to the driver default (prior to the flow-control change this had been a noop). Fixes: 7041d9c3f01b ("USB: serial: pl2303: add support for tx xon/xoff flow control") Cc: stable <stable@vger.kernel.org> # 4.18 Cc: Florian Zumbiehl <florz@florz.de> Reported-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Tested-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Johan Hovold <johan@kernel.org>
2018-12-05 00:00:36 +08:00
EXPORT_SYMBOL_GPL(tty_save_termios);
/**
* tty_flush_works - flush all works of a tty/pty pair
* @tty: tty device to flush works for (or either end of a pty pair)
*
* Sync flush all works belonging to @tty (and the 'other' tty).
*/
static void tty_flush_works(struct tty_struct *tty)
{
flush_work(&tty->SAK_work);
flush_work(&tty->hangup_work);
if (tty->link) {
flush_work(&tty->link->SAK_work);
flush_work(&tty->link->hangup_work);
}
}
/**
* release_one_tty - release tty structure memory
* @work: work of tty we are obliterating
*
* Releases memory associated with a tty structure, and clears out the
* driver table slots. This function is called when a device is no longer
* in use. It also gets called when setup of a device fails.
*
* Locking:
* takes the file list lock internally when working on the list of ttys
* that the driver keeps.
*
* This method gets called from a work queue so that the driver private
* cleanup ops can sleep (needed for USB at least)
*/
static void release_one_tty(struct work_struct *work)
{
struct tty_struct *tty =
container_of(work, struct tty_struct, hangup_work);
struct tty_driver *driver = tty->driver;
tty: Fix potential use after free in release_one_tty In case if we're releasing the last tty reference the following call sequence is possible tty_driver_kref_put destruct_tty_driver kfree(driver); where @driver is used in next module_put call, which leads to | [ 285.964007] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 | [ 285.964007] Workqueue: events release_one_tty | [ 285.964007] task: ffff8800cc7ea5f0 ti: ffff8800cb800000 task.ti: ffff8800cb800000 | [ 285.964007] RIP: 0010:[<ffffffff810aeaf5>] [<ffffffff810aeaf5>] module_put+0x24/0xf4 | [ 285.964007] RSP: 0018:ffff8800cb801d48 EFLAGS: 00010213 | [ 285.964007] RAX: ffff8800cb801fd8 RBX: ffff8800ca3429d0 RCX: ffff8800cb1db400 | [ 285.964007] RDX: 0000000000000000 RSI: ffffffff817349c1 RDI: 0000000000000001 | [ 285.964007] RBP: ffff8800cb801d60 R08: ffff8800cd632b40 R09: 0000000000000000 | [ 285.964007] R10: 00000000ffffffff R11: ffff88011f40a000 R12: 6b6b6b6b6b6b6b6b | [ 285.964007] R13: ffff8800ca342520 R14: 0000000000000000 R15: ffff88011f5d8200 | [ 285.964007] FS: 0000000000000000(0000) GS:ffff88011f400000(0000) knlGS:0000000000000000 | [ 285.964007] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b | [ 285.964007] CR2: 00007faf5229d090 CR3: 0000000001c0b000 CR4: 00000000000006f0 | [ 285.964007] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 | [ 285.964007] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 | [ 285.964007] Stack: | [ 285.964007] ffff8800ca3429d0 ffff8800ca342a30 ffff8800ca342520 ffff8800cb801d88 | [ 285.964007] ffffffff8146554a ffff8800cc77cc78 ffff8800ca3429d0 ffff88011f5d3800 | [ 285.964007] ffff8800cb801e08 ffffffff810683c1 ffffffff810682ff 0000000000000046 | [ 285.964007] Call Trace: | [ 285.964007] [<ffffffff8146554a>] release_one_tty+0x54/0xa3 | [ 285.964007] [<ffffffff810683c1>] process_one_work+0x223/0x404 | [ 285.964007] [<ffffffff810682ff>] ? process_one_work+0x161/0x404 | [ 285.964007] [<ffffffff81068971>] worker_thread+0x136/0x205 | [ 285.964007] [<ffffffff8106883b>] ? rescuer_thread+0x26a/0x26a | [ 285.964007] [<ffffffff8106e5bf>] kthread+0xa2/0xaa | [ 285.964007] [<ffffffff810a4586>] ? trace_hardirqs_on_caller+0x16/0x1eb | [ 285.964007] [<ffffffff8106e51d>] ? __kthread_parkme+0x65/0x65 | [ 285.964007] [<ffffffff8173f59c>] ret_from_fork+0x7c/0xb0 | [ 285.964007] [<ffffffff8106e51d>] ? __kthread_parkme+0x65/0x65 | [ 285.964007] Code: 09 00 5b 41 5c 5d c3 0f 1f 44 00 00 55 48 85 ff 48 89 e5 41 55 41 54 49 89 fc 53 0f 84 d3 00 | 00 00 bf 01 00 00 00 e8 d0 a1 fc ff <49> 8b 84 24 50 02 00 00 65 48 ff 40 08 4c 8b 6d 08 0f 1f 44 00 so simply keep a local reference to the module owner and use it later. CC: Pavel Emelyanov <xemul@parallels.com> CC: Jiri Slaby <jslaby@suse.cz> CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-08-08 04:26:15 +08:00
struct module *owner = driver->owner;
tty: Fix regressions caused by commit b50989dc The following commit made console open fails while booting: commit b50989dc444599c8b21edc23536fc305f4e9b7d5 Author: Alan Cox <alan@linux.intel.com> Date: Sat Sep 19 13:13:22 2009 -0700 tty: make the kref destructor occur asynchronously Due to tty release routines run in a workqueue now, error like the following will be reported while booting: INIT open /dev/console Input/output error It also causes hibernation regression to appear as reported at http://bugzilla.kernel.org/show_bug.cgi?id=14229 The reason is that now there's latency issue with closing, but when we open a "closing not finished" tty, -EIO will be returned. Fix it as per the following Alan's suggestion: Fun but it's actually not a bug and the fix is wrong in itself as the port may be closing but not yet being destructed, in which case it seems to do the wrong thing. Opening a tty that is closing (and could be closing for long periods) is supposed to return -EIO. I suspect a better way to deal with this and keep the old console timing is to split tty->shutdown into two functions. tty->shutdown() - called synchronously just before we dump the tty onto the waitqueue for destruction tty->cleanup() - called when the destructor runs. We would then do the shutdown part which can occur in IRQ context fine, before queueing the rest of the release (from tty->magic = 0 ... the end) to occur asynchronously The USB update in -next would then need a call like if (tty->cleanup) tty->cleanup(tty); at the top of the async function and the USB shutdown to be split between shutdown and cleanup as the USB resource cleanup and final tidy cannot occur synchronously as it needs to sleep. In other words the logic becomes final kref put make object unfindable async clean it up Signed-off-by: Dave Young <hidave.darkstar@gmail.com> [ rjw: Rebased on top of 2.6.31-git, reworked the changelog. ] Signed-off-by: "Rafael J. Wysocki" <rjw@sisk.pl> [ Changed serial naming to match new rules, dropped tty_shutdown as per comments from Alan Stern - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-28 00:00:42 +08:00
if (tty->ops->cleanup)
tty->ops->cleanup(tty);
tty_driver_kref_put(driver);
tty: Fix potential use after free in release_one_tty In case if we're releasing the last tty reference the following call sequence is possible tty_driver_kref_put destruct_tty_driver kfree(driver); where @driver is used in next module_put call, which leads to | [ 285.964007] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 | [ 285.964007] Workqueue: events release_one_tty | [ 285.964007] task: ffff8800cc7ea5f0 ti: ffff8800cb800000 task.ti: ffff8800cb800000 | [ 285.964007] RIP: 0010:[<ffffffff810aeaf5>] [<ffffffff810aeaf5>] module_put+0x24/0xf4 | [ 285.964007] RSP: 0018:ffff8800cb801d48 EFLAGS: 00010213 | [ 285.964007] RAX: ffff8800cb801fd8 RBX: ffff8800ca3429d0 RCX: ffff8800cb1db400 | [ 285.964007] RDX: 0000000000000000 RSI: ffffffff817349c1 RDI: 0000000000000001 | [ 285.964007] RBP: ffff8800cb801d60 R08: ffff8800cd632b40 R09: 0000000000000000 | [ 285.964007] R10: 00000000ffffffff R11: ffff88011f40a000 R12: 6b6b6b6b6b6b6b6b | [ 285.964007] R13: ffff8800ca342520 R14: 0000000000000000 R15: ffff88011f5d8200 | [ 285.964007] FS: 0000000000000000(0000) GS:ffff88011f400000(0000) knlGS:0000000000000000 | [ 285.964007] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b | [ 285.964007] CR2: 00007faf5229d090 CR3: 0000000001c0b000 CR4: 00000000000006f0 | [ 285.964007] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 | [ 285.964007] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 | [ 285.964007] Stack: | [ 285.964007] ffff8800ca3429d0 ffff8800ca342a30 ffff8800ca342520 ffff8800cb801d88 | [ 285.964007] ffffffff8146554a ffff8800cc77cc78 ffff8800ca3429d0 ffff88011f5d3800 | [ 285.964007] ffff8800cb801e08 ffffffff810683c1 ffffffff810682ff 0000000000000046 | [ 285.964007] Call Trace: | [ 285.964007] [<ffffffff8146554a>] release_one_tty+0x54/0xa3 | [ 285.964007] [<ffffffff810683c1>] process_one_work+0x223/0x404 | [ 285.964007] [<ffffffff810682ff>] ? process_one_work+0x161/0x404 | [ 285.964007] [<ffffffff81068971>] worker_thread+0x136/0x205 | [ 285.964007] [<ffffffff8106883b>] ? rescuer_thread+0x26a/0x26a | [ 285.964007] [<ffffffff8106e5bf>] kthread+0xa2/0xaa | [ 285.964007] [<ffffffff810a4586>] ? trace_hardirqs_on_caller+0x16/0x1eb | [ 285.964007] [<ffffffff8106e51d>] ? __kthread_parkme+0x65/0x65 | [ 285.964007] [<ffffffff8173f59c>] ret_from_fork+0x7c/0xb0 | [ 285.964007] [<ffffffff8106e51d>] ? __kthread_parkme+0x65/0x65 | [ 285.964007] Code: 09 00 5b 41 5c 5d c3 0f 1f 44 00 00 55 48 85 ff 48 89 e5 41 55 41 54 49 89 fc 53 0f 84 d3 00 | 00 00 bf 01 00 00 00 e8 d0 a1 fc ff <49> 8b 84 24 50 02 00 00 65 48 ff 40 08 4c 8b 6d 08 0f 1f 44 00 so simply keep a local reference to the module owner and use it later. CC: Pavel Emelyanov <xemul@parallels.com> CC: Jiri Slaby <jslaby@suse.cz> CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-08-08 04:26:15 +08:00
module_put(owner);
spin_lock(&tty->files_lock);
list_del_init(&tty->tty_files);
spin_unlock(&tty->files_lock);
put_pid(tty->ctrl.pgrp);
put_pid(tty->ctrl.session);
free_tty_struct(tty);
}
static void queue_release_one_tty(struct kref *kref)
{
struct tty_struct *tty = container_of(kref, struct tty_struct, kref);
tty: Fix regressions caused by commit b50989dc The following commit made console open fails while booting: commit b50989dc444599c8b21edc23536fc305f4e9b7d5 Author: Alan Cox <alan@linux.intel.com> Date: Sat Sep 19 13:13:22 2009 -0700 tty: make the kref destructor occur asynchronously Due to tty release routines run in a workqueue now, error like the following will be reported while booting: INIT open /dev/console Input/output error It also causes hibernation regression to appear as reported at http://bugzilla.kernel.org/show_bug.cgi?id=14229 The reason is that now there's latency issue with closing, but when we open a "closing not finished" tty, -EIO will be returned. Fix it as per the following Alan's suggestion: Fun but it's actually not a bug and the fix is wrong in itself as the port may be closing but not yet being destructed, in which case it seems to do the wrong thing. Opening a tty that is closing (and could be closing for long periods) is supposed to return -EIO. I suspect a better way to deal with this and keep the old console timing is to split tty->shutdown into two functions. tty->shutdown() - called synchronously just before we dump the tty onto the waitqueue for destruction tty->cleanup() - called when the destructor runs. We would then do the shutdown part which can occur in IRQ context fine, before queueing the rest of the release (from tty->magic = 0 ... the end) to occur asynchronously The USB update in -next would then need a call like if (tty->cleanup) tty->cleanup(tty); at the top of the async function and the USB shutdown to be split between shutdown and cleanup as the USB resource cleanup and final tidy cannot occur synchronously as it needs to sleep. In other words the logic becomes final kref put make object unfindable async clean it up Signed-off-by: Dave Young <hidave.darkstar@gmail.com> [ rjw: Rebased on top of 2.6.31-git, reworked the changelog. ] Signed-off-by: "Rafael J. Wysocki" <rjw@sisk.pl> [ Changed serial naming to match new rules, dropped tty_shutdown as per comments from Alan Stern - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-28 00:00:42 +08:00
/* The hangup queue is now free so we can reuse it rather than
* waste a chunk of memory for each port.
*/
INIT_WORK(&tty->hangup_work, release_one_tty);
schedule_work(&tty->hangup_work);
}
/**
* tty_kref_put - release a tty kref
* @tty: tty device
*
* Release a reference to the @tty device and if need be let the kref layer
* destruct the object for us.
*/
void tty_kref_put(struct tty_struct *tty)
{
if (tty)
kref_put(&tty->kref, queue_release_one_tty);
}
EXPORT_SYMBOL(tty_kref_put);
/**
* release_tty - release tty structure memory
* @tty: tty device release
* @idx: index of the tty device release
*
* Release both @tty and a possible linked partner (think pty pair),
* and decrement the refcount of the backing module.
*
* Locking:
* tty_mutex
* takes the file list lock internally when working on the list of ttys
* that the driver keeps.
*/
static void release_tty(struct tty_struct *tty, int idx)
{
/* This should always be true but check for the moment */
WARN_ON(tty->index != idx);
WARN_ON(!mutex_is_locked(&tty_mutex));
if (tty->ops->shutdown)
tty->ops->shutdown(tty);
USB: serial: console: fix reported terminal settings The USB-serial console implementation has never reported the actual terminal settings used. Despite storing the corresponding cflags in its struct console, these were never honoured on later tty open() where the tty termios would be left initialised to the driver defaults. Unlike the serial console implementation, the USB-serial code calls subdriver open() already at console setup. While calling set_termios() and write() before open() looks like it could work for some USB-serial drivers, others definitely do not expect this, so modelling this after serial core is going to be intrusive, if at all possible. Instead, use a (renamed) tty helper to save the termios data used at console setup so that the tty termios reflects the actual terminal settings after a subsequent tty open(). Note that the calls to tty_init_termios() (tty_driver_install()) and tty_save_termios() are serialised using the disconnect mutex. This specifically fixes a regression that was triggered by a recent change adding software flow control to the pl2303 driver: a getty trying to disable flow control while leaving the baud rate unchanged would now also set the baud rate to the driver default (prior to the flow-control change this had been a noop). Fixes: 7041d9c3f01b ("USB: serial: pl2303: add support for tx xon/xoff flow control") Cc: stable <stable@vger.kernel.org> # 4.18 Cc: Florian Zumbiehl <florz@florz.de> Reported-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Tested-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Johan Hovold <johan@kernel.org>
2018-12-05 00:00:36 +08:00
tty_save_termios(tty);
tty_driver_remove_tty(tty->driver, tty);
if (tty->port)
tty->port->itty = NULL;
if (tty->link)
tty->link->port->itty = NULL;
if (tty->port)
tty_buffer_cancel_work(tty->port);
pty: cancel pty slave port buf's work in tty_release In case that CONFIG_SLUB_DEBUG is on and pty is used, races between release_one_tty and flush_to_ldisc work threads may happen and lead to use-after-free condition on tty->link->port. Because SLUB_DEBUG is turned on, freed tty->link->port is filled with POISON_FREE value. So far without SLUB_DEBUG, port was filled with zero and flush_to_ldisc could return without a problem by checking if tty is NULL. CPU 0 CPU 1 ----- ----- release_tty pty_write cancel_work_sync(tty) to = tty->link tty_kref_put(tty->link) tty_schedule_flip(to->port) << workqueue >> ... release_one_tty ... pty_cleanup ... kfree(tty->link->port) << workqueue >> flush_to_ldisc tty = READ_ONCE(port->itty) tty is 0x6b6b6b6b6b6b6b6b !!PANIC!! access tty->ldisc Unable to handle kernel paging request at virtual address 6b6b6b6b6b6b6b93 pgd = ffffffc0eb1c3000 [6b6b6b6b6b6b6b93] *pgd=0000000000000000, *pud=0000000000000000 ------------[ cut here ]------------ Kernel BUG at ffffff800851154c [verbose debug info unavailable] Internal error: Oops - BUG: 96000004 [#1] PREEMPT SMP CPU: 3 PID: 265 Comm: kworker/u8:9 Tainted: G W 3.18.31-g0a58eeb #1 Hardware name: Qualcomm Technologies, Inc. MSM 8996pro v1.1 + PMI8996 Carbide (DT) Workqueue: events_unbound flush_to_ldisc task: ffffffc0ed610ec0 ti: ffffffc0ed624000 task.ti: ffffffc0ed624000 PC is at ldsem_down_read_trylock+0x0/0x4c LR is at tty_ldisc_ref+0x24/0x4c pc : [<ffffff800851154c>] lr : [<ffffff800850f6c0>] pstate: 80400145 sp : ffffffc0ed627cd0 x29: ffffffc0ed627cd0 x28: 0000000000000000 x27: ffffff8009e05000 x26: ffffffc0d382cfa0 x25: 0000000000000000 x24: ffffff800a012f08 x23: 0000000000000000 x22: ffffffc0703fbc88 x21: 6b6b6b6b6b6b6b6b x20: 6b6b6b6b6b6b6b93 x19: 0000000000000000 x18: 0000000000000001 x17: 00e80000f80d6f53 x16: 0000000000000001 x15: 0000007f7d826fff x14: 00000000000000a0 x13: 0000000000000000 x12: 0000000000000109 x11: 0000000000000000 x10: 0000000000000000 x9 : ffffffc0ed624000 x8 : ffffffc0ed611580 x7 : 0000000000000000 x6 : ffffff800a42e000 x5 : 00000000000003fc x4 : 0000000003bd1201 x3 : 0000000000000001 x2 : 0000000000000001 x1 : ffffff800851004c x0 : 6b6b6b6b6b6b6b93 Signed-off-by: Sahara <keun-o.park@darkmatter.ae> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-12-13 13:10:48 +08:00
if (tty->link)
tty_buffer_cancel_work(tty->link->port);
tty_kref_put(tty->link);
tty_kref_put(tty);
}
/**
* tty_release_checks - check a tty before real release
* @tty: tty to check
* @idx: index of the tty
*
* Performs some paranoid checking before true release of the @tty. This is a
* no-op unless %TTY_PARANOIA_CHECK is defined.
*/
static int tty_release_checks(struct tty_struct *tty, int idx)
{
#ifdef TTY_PARANOIA_CHECK
if (idx < 0 || idx >= tty->driver->num) {
tty_debug(tty, "bad idx %d\n", idx);
return -1;
}
/* not much to check for devpts */
if (tty->driver->flags & TTY_DRIVER_DEVPTS_MEM)
return 0;
if (tty != tty->driver->ttys[idx]) {
tty_debug(tty, "bad driver table[%d] = %p\n",
idx, tty->driver->ttys[idx]);
return -1;
}
if (tty->driver->other) {
struct tty_struct *o_tty = tty->link;
if (o_tty != tty->driver->other->ttys[idx]) {
tty_debug(tty, "bad other table[%d] = %p\n",
idx, tty->driver->other->ttys[idx]);
return -1;
}
if (o_tty->link != tty) {
tty_debug(tty, "bad link = %p\n", o_tty->link);
return -1;
}
}
#endif
return 0;
}
/**
* tty_kclose - closes tty opened by tty_kopen
* @tty: tty device
*
* Performs the final steps to release and free a tty device. It is the same as
* tty_release_struct() except that it also resets %TTY_PORT_KOPENED flag on
* @tty->port.
*/
void tty_kclose(struct tty_struct *tty)
{
/*
* Ask the line discipline code to release its structures
*/
tty_ldisc_release(tty);
/* Wait for pending work before tty destruction commences */
tty_flush_works(tty);
tty_debug_hangup(tty, "freeing structure\n");
/*
* The release_tty function takes care of the details of clearing
* the slots and preserving the termios structure.
*/
mutex_lock(&tty_mutex);
tty_port_set_kopened(tty->port, 0);
release_tty(tty, tty->index);
mutex_unlock(&tty_mutex);
}
EXPORT_SYMBOL_GPL(tty_kclose);
/**
* tty_release_struct - release a tty struct
* @tty: tty device
* @idx: index of the tty
*
* Performs the final steps to release and free a tty device. It is roughly the
* reverse of tty_init_dev().
*/
void tty_release_struct(struct tty_struct *tty, int idx)
{
/*
* Ask the line discipline code to release its structures
*/
tty_ldisc_release(tty);
/* Wait for pending work before tty destruction commmences */
tty_flush_works(tty);
tty_debug_hangup(tty, "freeing structure\n");
/*
* The release_tty function takes care of the details of clearing
* the slots and preserving the termios structure.
*/
mutex_lock(&tty_mutex);
release_tty(tty, idx);
mutex_unlock(&tty_mutex);
}
EXPORT_SYMBOL_GPL(tty_release_struct);
/**
* tty_release - vfs callback for close
* @inode: inode of tty
* @filp: file pointer for handle to tty
*
* Called the last time each file handle is closed that references this tty.
* There may however be several such references.
*
* Locking:
* Takes BKL. See tty_release_dev().
*
* Even releasing the tty structures is a tricky business. We have to be very
* careful that the structures are all released at the same time, as interrupts
* might otherwise get the wrong pointers.
*
* WSH 09/09/97: rewritten to avoid some nasty race conditions that could
* lead to double frees or releasing memory still in use.
*/
int tty_release(struct inode *inode, struct file *filp)
{
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_struct *tty = file_tty(filp);
struct tty_struct *o_tty = NULL;
int do_sleep, final;
int idx;
long timeout = 0;
int once = 1;
if (tty_paranoia_check(tty, inode, __func__))
return 0;
tty_lock(tty);
check_tty_count(tty, __func__);
__tty_fasync(-1, filp, 0);
idx = tty->index;
if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
tty->driver->subtype == PTY_TYPE_MASTER)
o_tty = tty->link;
if (tty_release_checks(tty, idx)) {
tty_unlock(tty);
return 0;
}
tty_debug_hangup(tty, "releasing (count=%d)\n", tty->count);
if (tty->ops->close)
tty->ops->close(tty, filp);
/* If tty is pty master, lock the slave pty (stable lock order) */
tty_lock_slave(o_tty);
/*
* Sanity check: if tty->count is going to zero, there shouldn't be
* any waiters on tty->read_wait or tty->write_wait. We test the
* wait queues and kick everyone out _before_ actually starting to
* close. This ensures that we won't block while releasing the tty
* structure.
*
* The test for the o_tty closing is necessary, since the master and
* slave sides may close in any order. If the slave side closes out
* first, its count will be one, since the master side holds an open.
* Thus this test wouldn't be triggered at the time the slave closed,
* so we do it now.
*/
while (1) {
do_sleep = 0;
if (tty->count <= 1) {
if (waitqueue_active(&tty->read_wait)) {
wake_up_poll(&tty->read_wait, EPOLLIN);
do_sleep++;
}
if (waitqueue_active(&tty->write_wait)) {
wake_up_poll(&tty->write_wait, EPOLLOUT);
do_sleep++;
}
}
if (o_tty && o_tty->count <= 1) {
if (waitqueue_active(&o_tty->read_wait)) {
wake_up_poll(&o_tty->read_wait, EPOLLIN);
do_sleep++;
}
if (waitqueue_active(&o_tty->write_wait)) {
wake_up_poll(&o_tty->write_wait, EPOLLOUT);
do_sleep++;
}
}
if (!do_sleep)
break;
if (once) {
once = 0;
tty_warn(tty, "read/write wait queue active!\n");
}
schedule_timeout_killable(timeout);
if (timeout < 120 * HZ)
timeout = 2 * timeout + 1;
else
timeout = MAX_SCHEDULE_TIMEOUT;
}
if (o_tty) {
if (--o_tty->count < 0) {
tty_warn(tty, "bad slave count (%d)\n", o_tty->count);
o_tty->count = 0;
}
}
if (--tty->count < 0) {
tty_warn(tty, "bad tty->count (%d)\n", tty->count);
tty->count = 0;
}
/*
* We've decremented tty->count, so we need to remove this file
* descriptor off the tty->tty_files list; this serves two
* purposes:
* - check_tty_count sees the correct number of file descriptors
* associated with this tty.
* - do_tty_hangup no longer sees this file descriptor as
* something that needs to be handled for hangups.
*/
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
tty_del_file(filp);
/*
* Perform some housekeeping before deciding whether to return.
*
* If _either_ side is closing, make sure there aren't any
* processes that still think tty or o_tty is their controlling
* tty.
*/
if (!tty->count) {
read_lock(&tasklist_lock);
session_clear_tty(tty->ctrl.session);
if (o_tty)
session_clear_tty(o_tty->ctrl.session);
read_unlock(&tasklist_lock);
}
/* check whether both sides are closing ... */
final = !tty->count && !(o_tty && o_tty->count);
tty_unlock_slave(o_tty);
tty_unlock(tty);
/* At this point, the tty->count == 0 should ensure a dead tty
* cannot be re-opened by a racing opener.
*/
if (!final)
return 0;
tty_debug_hangup(tty, "final close\n");
tty_release_struct(tty, idx);
return 0;
}
/**
* tty_open_current_tty - get locked tty of current task
* @device: device number
* @filp: file pointer to tty
* @return: locked tty of the current task iff @device is /dev/tty
tty: Re-open /dev/tty without tty_mutex Opening /dev/tty (ie., the controlling tty for the current task) is always a re-open of the underlying tty. Because holding the tty_lock is sufficient for safely re-opening a tty, and because having a tty kref is sufficient for safely acquiring the tty_lock [1], tty_open_current_tty() does not require holding tty_mutex. Repurpose tty_open_current_tty() to perform the re-open itself and refactor tty_open(). [1] Analysis of safely re-opening the current tty w/o tty_mutex get_current_tty() gets a tty kref from the already kref'ed tty value of current->signal->tty while holding the sighand lock for the current task. This guarantees that the tty pointer returned from get_current_tty() points to a tty which remains referenceable while holding the kref. Although release_tty() may run concurrently, and thus the driver reference may be removed, release_one_tty() cannot have run, and won't while holding the tty kref. This, in turn, guarantees the tty_lock() can safely be acquired (since tty->magic and tty->legacy_mutex are still a valid dereferences). The tty_lock() also gets a tty kref to prevent the tty_unlock() from dereferencing a released tty. Thus, the kref returned from get_current_tty() can be released. Lastly, the first operation of tty_reopen() is to check the tty count. If non-zero, this ensures release_tty() is not running concurrently, and the driver references have not been removed. Reviewed-by: Alan Cox <alan@linux.intel.com> Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-06 01:12:50 +08:00
*
* Performs a re-open of the current task's controlling tty.
*
* We cannot return driver and index like for the other nodes because devpts
* will not work then. It expects inodes to be from devpts FS.
*/
static struct tty_struct *tty_open_current_tty(dev_t device, struct file *filp)
{
struct tty_struct *tty;
tty: Re-open /dev/tty without tty_mutex Opening /dev/tty (ie., the controlling tty for the current task) is always a re-open of the underlying tty. Because holding the tty_lock is sufficient for safely re-opening a tty, and because having a tty kref is sufficient for safely acquiring the tty_lock [1], tty_open_current_tty() does not require holding tty_mutex. Repurpose tty_open_current_tty() to perform the re-open itself and refactor tty_open(). [1] Analysis of safely re-opening the current tty w/o tty_mutex get_current_tty() gets a tty kref from the already kref'ed tty value of current->signal->tty while holding the sighand lock for the current task. This guarantees that the tty pointer returned from get_current_tty() points to a tty which remains referenceable while holding the kref. Although release_tty() may run concurrently, and thus the driver reference may be removed, release_one_tty() cannot have run, and won't while holding the tty kref. This, in turn, guarantees the tty_lock() can safely be acquired (since tty->magic and tty->legacy_mutex are still a valid dereferences). The tty_lock() also gets a tty kref to prevent the tty_unlock() from dereferencing a released tty. Thus, the kref returned from get_current_tty() can be released. Lastly, the first operation of tty_reopen() is to check the tty count. If non-zero, this ensures release_tty() is not running concurrently, and the driver references have not been removed. Reviewed-by: Alan Cox <alan@linux.intel.com> Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-06 01:12:50 +08:00
int retval;
if (device != MKDEV(TTYAUX_MAJOR, 0))
return NULL;
tty = get_current_tty();
if (!tty)
return ERR_PTR(-ENXIO);
filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */
/* noctty = 1; */
tty: Re-open /dev/tty without tty_mutex Opening /dev/tty (ie., the controlling tty for the current task) is always a re-open of the underlying tty. Because holding the tty_lock is sufficient for safely re-opening a tty, and because having a tty kref is sufficient for safely acquiring the tty_lock [1], tty_open_current_tty() does not require holding tty_mutex. Repurpose tty_open_current_tty() to perform the re-open itself and refactor tty_open(). [1] Analysis of safely re-opening the current tty w/o tty_mutex get_current_tty() gets a tty kref from the already kref'ed tty value of current->signal->tty while holding the sighand lock for the current task. This guarantees that the tty pointer returned from get_current_tty() points to a tty which remains referenceable while holding the kref. Although release_tty() may run concurrently, and thus the driver reference may be removed, release_one_tty() cannot have run, and won't while holding the tty kref. This, in turn, guarantees the tty_lock() can safely be acquired (since tty->magic and tty->legacy_mutex are still a valid dereferences). The tty_lock() also gets a tty kref to prevent the tty_unlock() from dereferencing a released tty. Thus, the kref returned from get_current_tty() can be released. Lastly, the first operation of tty_reopen() is to check the tty count. If non-zero, this ensures release_tty() is not running concurrently, and the driver references have not been removed. Reviewed-by: Alan Cox <alan@linux.intel.com> Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-06 01:12:50 +08:00
tty_lock(tty);
tty_kref_put(tty); /* safe to drop the kref now */
retval = tty_reopen(tty);
if (retval < 0) {
tty_unlock(tty);
tty = ERR_PTR(retval);
}
return tty;
}
/**
* tty_lookup_driver - lookup a tty driver for a given device file
* @device: device number
* @filp: file pointer to tty
* @index: index for the device in the @return driver
*
* If returned value is not erroneous, the caller is responsible to decrement
* the refcount by tty_driver_kref_put().
*
* Locking: %tty_mutex protects get_tty_driver()
*
* Return: driver for this inode (with increased refcount)
*/
static struct tty_driver *tty_lookup_driver(dev_t device, struct file *filp,
int *index)
{
struct tty_driver *driver = NULL;
switch (device) {
#ifdef CONFIG_VT
case MKDEV(TTY_MAJOR, 0): {
extern struct tty_driver *console_driver;
driver = tty_driver_kref_get(console_driver);
*index = fg_console;
break;
}
#endif
case MKDEV(TTYAUX_MAJOR, 1): {
struct tty_driver *console_driver = console_device(index);
if (console_driver) {
driver = tty_driver_kref_get(console_driver);
tty: export tty_open_by_driver This exports tty_open_by_driver so that it can be called from other places inside the kernel. The checks for null file pointer are based on Alan Cox's patch here: http://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1215095.html. Description below is quoted from it: "[RFC] tty_port: allow a port to be opened with a tty that has no file handle Let us create tty objects entirely in kernel space. Untested proposal to show why all the ideas around rewriting half the uart stack are not needed. With this a kernel created non file backed tty object could be used to handle data, and set terminal modes. Not all ldiscs can cope with this as N_TTY in particular has to work back to the fs/tty layer. The tty_port code is however otherwise clean of file handles as far as I can tell as is the low level tty port write path used by the ldisc, the configuration low level interfaces and most of the ldiscs. Currently you don't have any exposure to see tty hangups because those are built around the file layer. However a) it's a fixed port so you probably don't care about that b) if you do we can add a callback and c) you almost certainly don't want the userspace tear down/rebuild behaviour anyway. This should however be sufficient if we wanted for example to enumerate all the bluetooth bound fixed ports via ACPI and make them directly available. It doesn't deal with the case of a user opening a port that's also kernel opened and that would need some locking out (so it returned EBUSY if bound to a kernel device of some kind). That needs resolving along with how you "up" or "down" your new bluetooth device, or enumerate it while providing the existing tty API to avoid regressions (and to debug)." The exported funtion is used later in this patch set to gain access to tty_struct. [changed export symbol level - gkh] Signed-off-by: Okash Khawaja <okash.khawaja@gmail.com> Reviewed-by: Samuel Thibault <samuel.thibault@ens-lyon.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-05-16 01:45:32 +08:00
if (driver && filp) {
/* Don't let /dev/console block */
filp->f_flags |= O_NONBLOCK;
break;
}
}
if (driver)
tty_driver_kref_put(driver);
return ERR_PTR(-ENODEV);
}
default:
driver = get_tty_driver(device, index);
if (!driver)
return ERR_PTR(-ENODEV);
break;
}
return driver;
}
static struct tty_struct *tty_kopen(dev_t device, int shared)
{
struct tty_struct *tty;
struct tty_driver *driver;
int index = -1;
mutex_lock(&tty_mutex);
driver = tty_lookup_driver(device, NULL, &index);
if (IS_ERR(driver)) {
mutex_unlock(&tty_mutex);
return ERR_CAST(driver);
}
/* check whether we're reopening an existing tty */
tty = tty_driver_lookup_tty(driver, NULL, index);
if (IS_ERR(tty) || shared)
goto out;
if (tty) {
/* drop kref from tty_driver_lookup_tty() */
tty_kref_put(tty);
tty = ERR_PTR(-EBUSY);
} else { /* tty_init_dev returns tty with the tty_lock held */
tty = tty_init_dev(driver, index);
if (IS_ERR(tty))
goto out;
tty_port_set_kopened(tty->port, 1);
}
out:
mutex_unlock(&tty_mutex);
tty_driver_kref_put(driver);
return tty;
}
/**
* tty_kopen_exclusive - open a tty device for kernel
* @device: dev_t of device to open
*
* Opens tty exclusively for kernel. Performs the driver lookup, makes sure
* it's not already opened and performs the first-time tty initialization.
*
* Claims the global %tty_mutex to serialize:
* * concurrent first-time tty initialization
* * concurrent tty driver removal w/ lookup
* * concurrent tty removal from driver table
*
* Return: the locked initialized &tty_struct
*/
struct tty_struct *tty_kopen_exclusive(dev_t device)
{
return tty_kopen(device, 0);
}
EXPORT_SYMBOL_GPL(tty_kopen_exclusive);
/**
* tty_kopen_shared - open a tty device for shared in-kernel use
* @device: dev_t of device to open
*
* Opens an already existing tty for in-kernel use. Compared to
* tty_kopen_exclusive() above it doesn't ensure to be the only user.
*
* Locking: identical to tty_kopen() above.
*/
struct tty_struct *tty_kopen_shared(dev_t device)
{
return tty_kopen(device, 1);
}
EXPORT_SYMBOL_GPL(tty_kopen_shared);
/**
* tty_open_by_driver - open a tty device
* @device: dev_t of device to open
* @filp: file pointer to tty
*
* Performs the driver lookup, checks for a reopen, or otherwise performs the
* first-time tty initialization.
*
*
* Claims the global tty_mutex to serialize:
* * concurrent first-time tty initialization
* * concurrent tty driver removal w/ lookup
* * concurrent tty removal from driver table
*
* Return: the locked initialized or re-opened &tty_struct
*/
static struct tty_struct *tty_open_by_driver(dev_t device,
struct file *filp)
{
struct tty_struct *tty;
struct tty_driver *driver = NULL;
int index = -1;
int retval;
mutex_lock(&tty_mutex);
driver = tty_lookup_driver(device, filp, &index);
if (IS_ERR(driver)) {
mutex_unlock(&tty_mutex);
return ERR_CAST(driver);
}
/* check whether we're reopening an existing tty */
devpts: more pty driver interface cleanups This is more prep-work for the upcoming pty changes. Still just code cleanup with no actual semantic changes. This removes a bunch pointless complexity by just having the slave pty side remember the dentry associated with the devpts slave rather than the inode. That allows us to remove all the "look up the dentry" code for when we want to remove it again. Together with moving the tty pointer from "inode->i_private" to "dentry->d_fsdata" and getting rid of pointless inode locking, this removes about 30 lines of code. Not only is the end result smaller, it's simpler and easier to understand. The old code, for example, depended on the d_find_alias() to not just find the dentry, but also to check that it is still hashed, which in turn validated the tty pointer in the inode. That is a _very_ roundabout way to say "invalidate the cached tty pointer when the dentry is removed". The new code just does dentry->d_fsdata = NULL; in devpts_pty_kill() instead, invalidating the tty pointer rather more directly and obviously. Don't do something complex and subtle when the obvious straightforward approach will do. The rest of the patch (ie apart from code deletion and the above tty pointer clearing) is just switching the calling convention to pass the dentry or file pointer around instead of the inode. Cc: Eric Biederman <ebiederm@xmission.com> Cc: Peter Anvin <hpa@zytor.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Serge Hallyn <serge.hallyn@ubuntu.com> Cc: Willy Tarreau <w@1wt.eu> Cc: Aurelien Jarno <aurelien@aurel32.net> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: Jann Horn <jann@thejh.net> Cc: Greg KH <greg@kroah.com> Cc: Jiri Slaby <jslaby@suse.com> Cc: Florian Weimer <fw@deneb.enyo.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-26 11:04:08 +08:00
tty = tty_driver_lookup_tty(driver, filp, index);
if (IS_ERR(tty)) {
mutex_unlock(&tty_mutex);
goto out;
}
if (tty) {
if (tty_port_kopened(tty->port)) {
tty_kref_put(tty);
mutex_unlock(&tty_mutex);
tty = ERR_PTR(-EBUSY);
goto out;
}
mutex_unlock(&tty_mutex);
retval = tty_lock_interruptible(tty);
tty_kref_put(tty); /* drop kref from tty_driver_lookup_tty() */
if (retval) {
if (retval == -EINTR)
retval = -ERESTARTSYS;
tty = ERR_PTR(retval);
goto out;
}
retval = tty_reopen(tty);
if (retval < 0) {
tty_unlock(tty);
tty = ERR_PTR(retval);
}
} else { /* Returns with the tty_lock held for now */
tty = tty_init_dev(driver, index);
mutex_unlock(&tty_mutex);
}
out:
tty_driver_kref_put(driver);
return tty;
}
/**
* tty_open - open a tty device
* @inode: inode of device file
* @filp: file pointer to tty
*
* tty_open() and tty_release() keep up the tty count that contains the number
* of opens done on a tty. We cannot use the inode-count, as different inodes
* might point to the same tty.
*
* Open-counting is needed for pty masters, as well as for keeping track of
* serial lines: DTR is dropped when the last close happens.
* (This is not done solely through tty->count, now. - Ted 1/27/92)
*
* The termios state of a pty is reset on the first open so that settings don't
* persist across reuse.
*
* Locking:
* * %tty_mutex protects tty, tty_lookup_driver() and tty_init_dev().
* * @tty->count should protect the rest.
* * ->siglock protects ->signal/->sighand
*
* Note: the tty_unlock/lock cases without a ref are only safe due to %tty_mutex
*/
static int tty_open(struct inode *inode, struct file *filp)
{
struct tty_struct *tty;
int noctty, retval;
dev_t device = inode->i_rdev;
unsigned saved_flags = filp->f_flags;
nonseekable_open(inode, filp);
retry_open:
retval = tty_alloc_file(filp);
if (retval)
return -ENOMEM;
tty = tty_open_current_tty(device, filp);
if (!tty)
tty = tty_open_by_driver(device, filp);
tty: Re-open /dev/tty without tty_mutex Opening /dev/tty (ie., the controlling tty for the current task) is always a re-open of the underlying tty. Because holding the tty_lock is sufficient for safely re-opening a tty, and because having a tty kref is sufficient for safely acquiring the tty_lock [1], tty_open_current_tty() does not require holding tty_mutex. Repurpose tty_open_current_tty() to perform the re-open itself and refactor tty_open(). [1] Analysis of safely re-opening the current tty w/o tty_mutex get_current_tty() gets a tty kref from the already kref'ed tty value of current->signal->tty while holding the sighand lock for the current task. This guarantees that the tty pointer returned from get_current_tty() points to a tty which remains referenceable while holding the kref. Although release_tty() may run concurrently, and thus the driver reference may be removed, release_one_tty() cannot have run, and won't while holding the tty kref. This, in turn, guarantees the tty_lock() can safely be acquired (since tty->magic and tty->legacy_mutex are still a valid dereferences). The tty_lock() also gets a tty kref to prevent the tty_unlock() from dereferencing a released tty. Thus, the kref returned from get_current_tty() can be released. Lastly, the first operation of tty_reopen() is to check the tty count. If non-zero, this ensures release_tty() is not running concurrently, and the driver references have not been removed. Reviewed-by: Alan Cox <alan@linux.intel.com> Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-06 01:12:50 +08:00
if (IS_ERR(tty)) {
tty_free_file(filp);
retval = PTR_ERR(tty);
if (retval != -EAGAIN || signal_pending(current))
return retval;
schedule();
goto retry_open;
}
tty_add_file(tty, filp);
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
check_tty_count(tty, __func__);
tty_debug_hangup(tty, "opening (count=%d)\n", tty->count);
if (tty->ops->open)
retval = tty->ops->open(tty, filp);
else
retval = -ENODEV;
filp->f_flags = saved_flags;
if (retval) {
tty_debug_hangup(tty, "open error %d, releasing\n", retval);
tty_unlock(tty); /* need to call tty_release without BTM */
tty_release(inode, filp);
if (retval != -ERESTARTSYS)
return retval;
if (signal_pending(current))
return retval;
schedule();
/*
* Need to reset f_op in case a hangup happened.
*/
if (tty_hung_up_p(filp))
filp->f_op = &tty_fops;
goto retry_open;
}
clear_bit(TTY_HUPPED, &tty->flags);
noctty = (filp->f_flags & O_NOCTTY) ||
(IS_ENABLED(CONFIG_VT) && device == MKDEV(TTY_MAJOR, 0)) ||
device == MKDEV(TTYAUX_MAJOR, 1) ||
(tty->driver->type == TTY_DRIVER_TYPE_PTY &&
tty->driver->subtype == PTY_TYPE_MASTER);
if (!noctty)
tty_open_proc_set_tty(filp, tty);
tty_unlock(tty);
return 0;
}
/**
* tty_poll - check tty status
* @filp: file being polled
* @wait: poll wait structures to update
*
* Call the line discipline polling method to obtain the poll status of the
* device.
*
* Locking: locks called line discipline but ldisc poll method may be
* re-entered freely by other callers.
*/
static __poll_t tty_poll(struct file *filp, poll_table *wait)
{
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_struct *tty = file_tty(filp);
struct tty_ldisc *ld;
__poll_t ret = 0;
if (tty_paranoia_check(tty, file_inode(filp), "tty_poll"))
return 0;
ld = tty_ldisc_ref_wait(tty);
if (!ld)
return hung_up_tty_poll(filp, wait);
if (ld->ops->poll)
ret = ld->ops->poll(tty, filp, wait);
tty_ldisc_deref(ld);
return ret;
}
static int __tty_fasync(int fd, struct file *filp, int on)
{
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_struct *tty = file_tty(filp);
unsigned long flags;
int retval = 0;
if (tty_paranoia_check(tty, file_inode(filp), "tty_fasync"))
goto out;
retval = fasync_helper(fd, filp, on, &tty->fasync);
if (retval <= 0)
goto out;
if (on) {
enum pid_type type;
struct pid *pid;
spin_lock_irqsave(&tty->ctrl.lock, flags);
if (tty->ctrl.pgrp) {
pid = tty->ctrl.pgrp;
type = PIDTYPE_PGID;
} else {
pid = task_pid(current);
type = PIDTYPE_TGID;
}
Fix race in tty_fasync() properly This reverts commit 703625118069 ("tty: fix race in tty_fasync") and commit b04da8bfdfbb ("fnctl: f_modown should call write_lock_irqsave/ restore") that tried to fix up some of the fallout but was incomplete. It turns out that we really cannot hold 'tty->ctrl_lock' over calling __f_setown, because not only did that cause problems with interrupt disables (which the second commit fixed), it also causes a potential ABBA deadlock due to lock ordering. Thanks to Tetsuo Handa for following up on the issue, and running lockdep to show the problem. It goes roughly like this: - f_getown gets filp->f_owner.lock for reading without interrupts disabled, so an interrupt that happens while that lock is held can cause a lockdep chain from f_owner.lock -> sighand->siglock. - at the same time, the tty->ctrl_lock -> f_owner.lock chain that commit 703625118069 introduced, together with the pre-existing sighand->siglock -> tty->ctrl_lock chain means that we have a lock dependency the other way too. So instead of extending tty->ctrl_lock over the whole __f_setown() call, we now just take a reference to the 'pid' structure while holding the lock, and then release it after having done the __f_setown. That still guarantees that 'struct pid' won't go away from under us, which is all we really ever needed. Reported-and-tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: Américo Wang <xiyou.wangcong@gmail.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-02-08 02:11:23 +08:00
get_pid(pid);
spin_unlock_irqrestore(&tty->ctrl.lock, flags);
__f_setown(filp, pid, type, 0);
Fix race in tty_fasync() properly This reverts commit 703625118069 ("tty: fix race in tty_fasync") and commit b04da8bfdfbb ("fnctl: f_modown should call write_lock_irqsave/ restore") that tried to fix up some of the fallout but was incomplete. It turns out that we really cannot hold 'tty->ctrl_lock' over calling __f_setown, because not only did that cause problems with interrupt disables (which the second commit fixed), it also causes a potential ABBA deadlock due to lock ordering. Thanks to Tetsuo Handa for following up on the issue, and running lockdep to show the problem. It goes roughly like this: - f_getown gets filp->f_owner.lock for reading without interrupts disabled, so an interrupt that happens while that lock is held can cause a lockdep chain from f_owner.lock -> sighand->siglock. - at the same time, the tty->ctrl_lock -> f_owner.lock chain that commit 703625118069 introduced, together with the pre-existing sighand->siglock -> tty->ctrl_lock chain means that we have a lock dependency the other way too. So instead of extending tty->ctrl_lock over the whole __f_setown() call, we now just take a reference to the 'pid' structure while holding the lock, and then release it after having done the __f_setown. That still guarantees that 'struct pid' won't go away from under us, which is all we really ever needed. Reported-and-tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: Américo Wang <xiyou.wangcong@gmail.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-02-08 02:11:23 +08:00
put_pid(pid);
retval = 0;
}
out:
return retval;
}
static int tty_fasync(int fd, struct file *filp, int on)
{
struct tty_struct *tty = file_tty(filp);
int retval = -ENOTTY;
tty_lock(tty);
if (!tty_hung_up_p(filp))
retval = __tty_fasync(fd, filp, on);
tty_unlock(tty);
return retval;
}
static bool tty_legacy_tiocsti __read_mostly = IS_ENABLED(CONFIG_LEGACY_TIOCSTI);
/**
* tiocsti - fake input character
* @tty: tty to fake input into
* @p: pointer to character
*
* Fake input to a tty device. Does the necessary locking and input management.
*
* FIXME: does not honour flow control ??
*
* Locking:
* * Called functions take tty_ldiscs_lock
* * current->signal->tty check is safe without locks
*/
static int tiocsti(struct tty_struct *tty, char __user *p)
{
char ch, mbz = 0;
struct tty_ldisc *ld;
if (!tty_legacy_tiocsti)
return -EIO;
if ((current->signal->tty != tty) && !capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(ch, p))
return -EFAULT;
tty_audit_tiocsti(tty, ch);
ld = tty_ldisc_ref_wait(tty);
if (!ld)
return -EIO;
tty_buffer_lock_exclusive(tty->port);
if (ld->ops->receive_buf)
ld->ops->receive_buf(tty, &ch, &mbz, 1);
tty_buffer_unlock_exclusive(tty->port);
tty_ldisc_deref(ld);
return 0;
}
/**
* tiocgwinsz - implement window query ioctl
* @tty: tty
* @arg: user buffer for result
*
* Copies the kernel idea of the window size into the user buffer.
*
* Locking: @tty->winsize_mutex is taken to ensure the winsize data is
* consistent.
*/
static int tiocgwinsz(struct tty_struct *tty, struct winsize __user *arg)
{
int err;
tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [<ffffffff81452656>] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b797>] down_read+0x47/0x5c [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff810430a7>] console_lock+0x77/0x80 [<ffffffff8146b2a1>] con_flush_chars+0x31/0x50 [<ffffffff8145780c>] n_tty_write+0x1ec/0x4d0 [<ffffffff814541b9>] tty_write+0x159/0x2e0 [<ffffffff814543f5>] redirected_tty_write+0xb5/0xc0 [<ffffffff811ab9d5>] vfs_write+0xc5/0x1f0 [<ffffffff811abec5>] SyS_write+0x55/0xa0 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b5b>] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b69>] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [<ffffffffa008a6dd>] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [<ffffffff813d93f5>] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [<ffffffff813d8116>] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [<ffffffff813d95a4>] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [<ffffffff81755f19>] dump_stack+0x19/0x1b [<ffffffff8174f506>] print_circular_bug+0x1fb/0x20c [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b775e>] ? mark_held_locks+0xae/0x120 [<ffffffff810b78d5>] ? trace_hardirqs_on_caller+0x105/0x1d0 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffff8173cbcb>] ? kmemleak_alloc+0x5b/0xc0 [<ffffffff81198874>] ? kmem_cache_alloc_trace+0x104/0x290 [<ffffffffa01035e1>] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff8175f162>] ? _raw_spin_unlock_irqrestore+0x42/0x80 [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff81497b00>] ? driver_probe_device+0x3a0/0x3a0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff81399a50>] ? ddebug_proc_open+0xb0/0xb0 [<ffffffff813855ae>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-25 04:43:51 +08:00
mutex_lock(&tty->winsize_mutex);
err = copy_to_user(arg, &tty->winsize, sizeof(*arg));
tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [<ffffffff81452656>] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b797>] down_read+0x47/0x5c [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff810430a7>] console_lock+0x77/0x80 [<ffffffff8146b2a1>] con_flush_chars+0x31/0x50 [<ffffffff8145780c>] n_tty_write+0x1ec/0x4d0 [<ffffffff814541b9>] tty_write+0x159/0x2e0 [<ffffffff814543f5>] redirected_tty_write+0xb5/0xc0 [<ffffffff811ab9d5>] vfs_write+0xc5/0x1f0 [<ffffffff811abec5>] SyS_write+0x55/0xa0 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b5b>] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b69>] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [<ffffffffa008a6dd>] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [<ffffffff813d93f5>] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [<ffffffff813d8116>] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [<ffffffff813d95a4>] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [<ffffffff81755f19>] dump_stack+0x19/0x1b [<ffffffff8174f506>] print_circular_bug+0x1fb/0x20c [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b775e>] ? mark_held_locks+0xae/0x120 [<ffffffff810b78d5>] ? trace_hardirqs_on_caller+0x105/0x1d0 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffff8173cbcb>] ? kmemleak_alloc+0x5b/0xc0 [<ffffffff81198874>] ? kmem_cache_alloc_trace+0x104/0x290 [<ffffffffa01035e1>] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff8175f162>] ? _raw_spin_unlock_irqrestore+0x42/0x80 [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff81497b00>] ? driver_probe_device+0x3a0/0x3a0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff81399a50>] ? ddebug_proc_open+0xb0/0xb0 [<ffffffff813855ae>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-25 04:43:51 +08:00
mutex_unlock(&tty->winsize_mutex);
return err ? -EFAULT : 0;
}
/**
* tty_do_resize - resize event
* @tty: tty being resized
* @ws: new dimensions
*
* Update the termios variables and send the necessary signals to peform a
* terminal resize correctly.
*/
int tty_do_resize(struct tty_struct *tty, struct winsize *ws)
{
struct pid *pgrp;
/* Lock the tty */
tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [<ffffffff81452656>] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b797>] down_read+0x47/0x5c [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff810430a7>] console_lock+0x77/0x80 [<ffffffff8146b2a1>] con_flush_chars+0x31/0x50 [<ffffffff8145780c>] n_tty_write+0x1ec/0x4d0 [<ffffffff814541b9>] tty_write+0x159/0x2e0 [<ffffffff814543f5>] redirected_tty_write+0xb5/0xc0 [<ffffffff811ab9d5>] vfs_write+0xc5/0x1f0 [<ffffffff811abec5>] SyS_write+0x55/0xa0 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b5b>] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b69>] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [<ffffffffa008a6dd>] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [<ffffffff813d93f5>] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [<ffffffff813d8116>] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [<ffffffff813d95a4>] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [<ffffffff81755f19>] dump_stack+0x19/0x1b [<ffffffff8174f506>] print_circular_bug+0x1fb/0x20c [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b775e>] ? mark_held_locks+0xae/0x120 [<ffffffff810b78d5>] ? trace_hardirqs_on_caller+0x105/0x1d0 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffff8173cbcb>] ? kmemleak_alloc+0x5b/0xc0 [<ffffffff81198874>] ? kmem_cache_alloc_trace+0x104/0x290 [<ffffffffa01035e1>] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff8175f162>] ? _raw_spin_unlock_irqrestore+0x42/0x80 [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff81497b00>] ? driver_probe_device+0x3a0/0x3a0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff81399a50>] ? ddebug_proc_open+0xb0/0xb0 [<ffffffff813855ae>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-25 04:43:51 +08:00
mutex_lock(&tty->winsize_mutex);
if (!memcmp(ws, &tty->winsize, sizeof(*ws)))
goto done;
/* Signal the foreground process group */
pgrp = tty_get_pgrp(tty);
if (pgrp)
kill_pgrp(pgrp, SIGWINCH, 1);
put_pid(pgrp);
tty->winsize = *ws;
done:
tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [<ffffffff81452656>] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b797>] down_read+0x47/0x5c [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff810430a7>] console_lock+0x77/0x80 [<ffffffff8146b2a1>] con_flush_chars+0x31/0x50 [<ffffffff8145780c>] n_tty_write+0x1ec/0x4d0 [<ffffffff814541b9>] tty_write+0x159/0x2e0 [<ffffffff814543f5>] redirected_tty_write+0xb5/0xc0 [<ffffffff811ab9d5>] vfs_write+0xc5/0x1f0 [<ffffffff811abec5>] SyS_write+0x55/0xa0 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b5b>] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b69>] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [<ffffffffa008a6dd>] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [<ffffffff813d93f5>] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [<ffffffff813d8116>] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [<ffffffff813d95a4>] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [<ffffffff81755f19>] dump_stack+0x19/0x1b [<ffffffff8174f506>] print_circular_bug+0x1fb/0x20c [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b775e>] ? mark_held_locks+0xae/0x120 [<ffffffff810b78d5>] ? trace_hardirqs_on_caller+0x105/0x1d0 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffff8173cbcb>] ? kmemleak_alloc+0x5b/0xc0 [<ffffffff81198874>] ? kmem_cache_alloc_trace+0x104/0x290 [<ffffffffa01035e1>] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff8175f162>] ? _raw_spin_unlock_irqrestore+0x42/0x80 [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff81497b00>] ? driver_probe_device+0x3a0/0x3a0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff81399a50>] ? ddebug_proc_open+0xb0/0xb0 [<ffffffff813855ae>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-25 04:43:51 +08:00
mutex_unlock(&tty->winsize_mutex);
return 0;
}
EXPORT_SYMBOL(tty_do_resize);
/**
* tiocswinsz - implement window size set ioctl
* @tty: tty side of tty
* @arg: user buffer for result
*
* Copies the user idea of the window size to the kernel. Traditionally this is
* just advisory information but for the Linux console it actually has driver
* level meaning and triggers a VC resize.
*
* Locking:
* Driver dependent. The default do_resize method takes the tty termios
* mutex and ctrl.lock. The console takes its own lock then calls into the
* default method.
*/
static int tiocswinsz(struct tty_struct *tty, struct winsize __user *arg)
{
struct winsize tmp_ws;
if (copy_from_user(&tmp_ws, arg, sizeof(*arg)))
return -EFAULT;
if (tty->ops->resize)
return tty->ops->resize(tty, &tmp_ws);
else
return tty_do_resize(tty, &tmp_ws);
}
/**
* tioccons - allow admin to move logical console
* @file: the file to become console
*
* Allow the administrator to move the redirected console device.
*
* Locking: uses redirect_lock to guard the redirect information
*/
static int tioccons(struct file *file)
{
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (file->f_op->write_iter == redirected_tty_write) {
struct file *f;
spin_lock(&redirect_lock);
f = redirect;
redirect = NULL;
spin_unlock(&redirect_lock);
if (f)
fput(f);
return 0;
}
tty: avoid using vfs_iocb_iter_write() for redirected console writes It turns out that the vfs_iocb_iter_{read,write}() functions are entirely broken, and don't actually use the passed-in file pointer for IO - only for the preparatory work (permission checking and for the write_iter function lookup). That worked fine for overlayfs, which always builds the new iocb with the same file pointer that it passes in, but in the general case it ends up doing nonsensical things (and could cause an iterator call that doesn't even match the passed-in file pointer). This subtly broke the tty conversion to write_iter in commit 9bb48c82aced ("tty: implement write_iter"), because the console redirection didn't actually end up redirecting anything, since the passed-in file pointer was basically ignored, and the actual write was done with the original non-redirected console tty after all. The main visible effect of this is that the console messages were no longer logged to /var/log/boot.log during graphical boot. Fix the issue by simply not using the vfs write "helper" function at all, and just redirecting the write entirely internally to the tty layer. Do the target writability permission checks when actually registering the target tty with TIOCCONS instead of at write time. Fixes: 9bb48c82aced ("tty: implement write_iter") Reported-and-tested-by: Hans de Goede <hdegoede@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-01-30 04:28:20 +08:00
if (file->f_op->write_iter != tty_write)
return -ENOTTY;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
spin_lock(&redirect_lock);
if (redirect) {
spin_unlock(&redirect_lock);
return -EBUSY;
}
redirect = get_file(file);
spin_unlock(&redirect_lock);
return 0;
}
/**
* tiocsetd - set line discipline
* @tty: tty device
* @p: pointer to user data
*
* Set the line discipline according to user request.
*
* Locking: see tty_set_ldisc(), this function is just a helper
*/
static int tiocsetd(struct tty_struct *tty, int __user *p)
{
int disc;
int ret;
if (get_user(disc, p))
return -EFAULT;
ret = tty_set_ldisc(tty, disc);
return ret;
}
/**
* tiocgetd - get line discipline
* @tty: tty device
* @p: pointer to user data
*
* Retrieves the line discipline id directly from the ldisc.
*
* Locking: waits for ldisc reference (in case the line discipline is changing
* or the @tty is being hungup)
*/
static int tiocgetd(struct tty_struct *tty, int __user *p)
{
struct tty_ldisc *ld;
int ret;
ld = tty_ldisc_ref_wait(tty);
if (!ld)
return -EIO;
ret = put_user(ld->ops->num, p);
tty_ldisc_deref(ld);
return ret;
}
/**
* send_break - performed time break
* @tty: device to break on
* @duration: timeout in mS
*
* Perform a timed break on hardware that lacks its own driver level timed
* break functionality.
*
* Locking:
* @tty->atomic_write_lock serializes
*/
static int send_break(struct tty_struct *tty, unsigned int duration)
{
int retval;
if (tty->ops->break_ctl == NULL)
return 0;
if (tty->driver->flags & TTY_DRIVER_HARDWARE_BREAK)
retval = tty->ops->break_ctl(tty, duration);
else {
/* Do the work ourselves */
if (tty_write_lock(tty, 0) < 0)
return -EINTR;
retval = tty->ops->break_ctl(tty, -1);
if (retval)
goto out;
if (!signal_pending(current))
msleep_interruptible(duration);
retval = tty->ops->break_ctl(tty, 0);
out:
tty_write_unlock(tty);
if (signal_pending(current))
retval = -EINTR;
}
return retval;
}
/**
* tty_tiocmget - get modem status
* @tty: tty device
* @p: pointer to result
*
* Obtain the modem status bits from the tty driver if the feature is
* supported. Return -%ENOTTY if it is not available.
*
* Locking: none (up to the driver)
*/
static int tty_tiocmget(struct tty_struct *tty, int __user *p)
{
int retval = -ENOTTY;
if (tty->ops->tiocmget) {
retval = tty->ops->tiocmget(tty);
if (retval >= 0)
retval = put_user(retval, p);
}
return retval;
}
/**
* tty_tiocmset - set modem status
* @tty: tty device
* @cmd: command - clear bits, set bits or set all
* @p: pointer to desired bits
*
* Set the modem status bits from the tty driver if the feature
* is supported. Return -%ENOTTY if it is not available.
*
* Locking: none (up to the driver)
*/
static int tty_tiocmset(struct tty_struct *tty, unsigned int cmd,
unsigned __user *p)
{
int retval;
unsigned int set, clear, val;
if (tty->ops->tiocmset == NULL)
return -ENOTTY;
retval = get_user(val, p);
if (retval)
return retval;
set = clear = 0;
switch (cmd) {
case TIOCMBIS:
set = val;
break;
case TIOCMBIC:
clear = val;
break;
case TIOCMSET:
set = val;
clear = ~val;
break;
}
set &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP;
clear &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP;
return tty->ops->tiocmset(tty, set, clear);
}
/**
* tty_get_icount - get tty statistics
* @tty: tty device
* @icount: output parameter
*
* Gets a copy of the @tty's icount statistics.
*
* Locking: none (up to the driver)
*/
int tty_get_icount(struct tty_struct *tty,
struct serial_icounter_struct *icount)
{
memset(icount, 0, sizeof(*icount));
if (tty->ops->get_icount)
return tty->ops->get_icount(tty, icount);
else
return -ENOTTY;
}
EXPORT_SYMBOL_GPL(tty_get_icount);
static int tty_tiocgicount(struct tty_struct *tty, void __user *arg)
{
struct serial_icounter_struct icount;
int retval;
retval = tty_get_icount(tty, &icount);
if (retval != 0)
return retval;
if (copy_to_user(arg, &icount, sizeof(icount)))
return -EFAULT;
return 0;
}
static int tty_set_serial(struct tty_struct *tty, struct serial_struct *ss)
{
char comm[TASK_COMM_LEN];
int flags;
flags = ss->flags & ASYNC_DEPRECATED;
if (flags)
pr_warn_ratelimited("%s: '%s' is using deprecated serial flags (with no effect): %.8x\n",
__func__, get_task_comm(comm, current), flags);
if (!tty->ops->set_serial)
return -ENOTTY;
return tty->ops->set_serial(tty, ss);
}
static int tty_tiocsserial(struct tty_struct *tty, struct serial_struct __user *ss)
{
struct serial_struct v;
if (copy_from_user(&v, ss, sizeof(*ss)))
return -EFAULT;
return tty_set_serial(tty, &v);
}
static int tty_tiocgserial(struct tty_struct *tty, struct serial_struct __user *ss)
{
struct serial_struct v;
int err;
memset(&v, 0, sizeof(v));
if (!tty->ops->get_serial)
return -ENOTTY;
err = tty->ops->get_serial(tty, &v);
if (!err && copy_to_user(ss, &v, sizeof(v)))
err = -EFAULT;
return err;
}
/*
* if pty, return the slave side (real_tty)
* otherwise, return self
*/
static struct tty_struct *tty_pair_get_tty(struct tty_struct *tty)
{
if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
tty->driver->subtype == PTY_TYPE_MASTER)
tty = tty->link;
return tty;
}
/*
* Split this up, as gcc can choke on it otherwise..
*/
long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_struct *tty = file_tty(file);
struct tty_struct *real_tty;
void __user *p = (void __user *)arg;
int retval;
struct tty_ldisc *ld;
if (tty_paranoia_check(tty, file_inode(file), "tty_ioctl"))
return -EINVAL;
real_tty = tty_pair_get_tty(tty);
/*
* Factor out some common prep work
*/
switch (cmd) {
case TIOCSETD:
case TIOCSBRK:
case TIOCCBRK:
case TCSBRK:
case TCSBRKP:
retval = tty_check_change(tty);
if (retval)
return retval;
if (cmd != TIOCCBRK) {
tty_wait_until_sent(tty, 0);
if (signal_pending(current))
return -EINTR;
}
break;
}
/*
* Now do the stuff.
*/
switch (cmd) {
case TIOCSTI:
return tiocsti(tty, p);
case TIOCGWINSZ:
return tiocgwinsz(real_tty, p);
case TIOCSWINSZ:
return tiocswinsz(real_tty, p);
case TIOCCONS:
return real_tty != tty ? -EINVAL : tioccons(file);
case TIOCEXCL:
set_bit(TTY_EXCLUSIVE, &tty->flags);
return 0;
case TIOCNXCL:
clear_bit(TTY_EXCLUSIVE, &tty->flags);
return 0;
case TIOCGEXCL:
{
int excl = test_bit(TTY_EXCLUSIVE, &tty->flags);
return put_user(excl, (int __user *)p);
}
case TIOCGETD:
return tiocgetd(tty, p);
case TIOCSETD:
return tiocsetd(tty, p);
case TIOCVHANGUP:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
tty_vhangup(tty);
return 0;
case TIOCGDEV:
{
unsigned int ret = new_encode_dev(tty_devnum(real_tty));
return put_user(ret, (unsigned int __user *)p);
}
/*
* Break handling
*/
case TIOCSBRK: /* Turn break on, unconditionally */
if (tty->ops->break_ctl)
return tty->ops->break_ctl(tty, -1);
return 0;
case TIOCCBRK: /* Turn break off, unconditionally */
if (tty->ops->break_ctl)
return tty->ops->break_ctl(tty, 0);
return 0;
case TCSBRK: /* SVID version: non-zero arg --> no break */
/* non-zero arg means wait for all output data
* to be sent (performed above) but don't send break.
* This is used by the tcdrain() termios function.
*/
if (!arg)
return send_break(tty, 250);
return 0;
case TCSBRKP: /* support for POSIX tcsendbreak() */
return send_break(tty, arg ? arg*100 : 250);
case TIOCMGET:
return tty_tiocmget(tty, p);
case TIOCMSET:
case TIOCMBIC:
case TIOCMBIS:
return tty_tiocmset(tty, cmd, p);
case TIOCGICOUNT:
return tty_tiocgicount(tty, p);
case TCFLSH:
switch (arg) {
case TCIFLUSH:
case TCIOFLUSH:
/* flush tty buffer and allow ldisc to process ioctl */
tty_buffer_flush(tty, NULL);
break;
}
break;
case TIOCSSERIAL:
return tty_tiocsserial(tty, p);
case TIOCGSERIAL:
return tty_tiocgserial(tty, p);
pty: Repair TIOCGPTPEER The implementation of TIOCGPTPEER has two issues. When /dev/ptmx (as opposed to /dev/pts/ptmx) is opened the wrong vfsmount is passed to dentry_open. Which results in the kernel displaying the wrong pathname for the peer. The second is simply by caching the vfsmount and dentry of the peer it leaves them open, in a way they were not previously Which because of the inreased reference counts can cause unnecessary behaviour differences resulting in regressions. To fix these move the ioctl into tty_io.c at a generic level allowing the ioctl to have access to the struct file on which the ioctl is being called. This allows the path of the slave to be derived when opening the slave through TIOCGPTPEER instead of requiring the path to the slave be cached. Thus removing the need for caching the path. A new function devpts_ptmx_path is factored out of devpts_acquire and used to implement a function devpts_mntget. The new function devpts_mntget takes a filp to perform the lookup on and fsi so that it can confirm that the superblock that is found by devpts_ptmx_path is the proper superblock. v2: Lots of fixes to make the code actually work v3: Suggestions by Linus - Removed the unnecessary initialization of filp in ptm_open_peer - Simplified devpts_ptmx_path as gotos are no longer required [ This is the fix for the issue that was reverted in commit 143c97cc6529, but this time without breaking 'pbuilder' due to increased reference counts - Linus ] Fixes: 54ebbfb16034 ("tty: add TIOCGPTPEER ioctl") Reported-by: Christian Brauner <christian.brauner@canonical.com> Reported-and-tested-by: Stefan Lippers-Hollmann <s.l-h@gmx.de> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-25 04:13:29 +08:00
case TIOCGPTPEER:
/* Special because the struct file is needed */
return ptm_open_peer(file, tty, (int)arg);
default:
retval = tty_jobctrl_ioctl(tty, real_tty, file, cmd, arg);
if (retval != -ENOIOCTLCMD)
return retval;
}
if (tty->ops->ioctl) {
retval = tty->ops->ioctl(tty, cmd, arg);
if (retval != -ENOIOCTLCMD)
return retval;
}
ld = tty_ldisc_ref_wait(tty);
if (!ld)
return hung_up_tty_ioctl(file, cmd, arg);
retval = -EINVAL;
if (ld->ops->ioctl) {
retval = ld->ops->ioctl(tty, cmd, arg);
if (retval == -ENOIOCTLCMD)
retval = -ENOTTY;
}
tty_ldisc_deref(ld);
return retval;
}
#ifdef CONFIG_COMPAT
struct serial_struct32 {
compat_int_t type;
compat_int_t line;
compat_uint_t port;
compat_int_t irq;
compat_int_t flags;
compat_int_t xmit_fifo_size;
compat_int_t custom_divisor;
compat_int_t baud_base;
unsigned short close_delay;
char io_type;
char reserved_char;
compat_int_t hub6;
unsigned short closing_wait; /* time to wait before closing */
unsigned short closing_wait2; /* no longer used... */
compat_uint_t iomem_base;
unsigned short iomem_reg_shift;
unsigned int port_high;
/* compat_ulong_t iomap_base FIXME */
compat_int_t reserved;
};
static int compat_tty_tiocsserial(struct tty_struct *tty,
struct serial_struct32 __user *ss)
{
struct serial_struct32 v32;
struct serial_struct v;
if (copy_from_user(&v32, ss, sizeof(*ss)))
return -EFAULT;
memcpy(&v, &v32, offsetof(struct serial_struct32, iomem_base));
v.iomem_base = compat_ptr(v32.iomem_base);
v.iomem_reg_shift = v32.iomem_reg_shift;
v.port_high = v32.port_high;
v.iomap_base = 0;
return tty_set_serial(tty, &v);
}
static int compat_tty_tiocgserial(struct tty_struct *tty,
struct serial_struct32 __user *ss)
{
struct serial_struct32 v32;
struct serial_struct v;
int err;
memset(&v, 0, sizeof(v));
memset(&v32, 0, sizeof(v32));
if (!tty->ops->get_serial)
return -ENOTTY;
err = tty->ops->get_serial(tty, &v);
if (!err) {
memcpy(&v32, &v, offsetof(struct serial_struct32, iomem_base));
v32.iomem_base = (unsigned long)v.iomem_base >> 32 ?
0xfffffff : ptr_to_compat(v.iomem_base);
v32.iomem_reg_shift = v.iomem_reg_shift;
v32.port_high = v.port_high;
if (copy_to_user(ss, &v32, sizeof(v32)))
err = -EFAULT;
}
return err;
}
static long tty_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
struct tty_struct *tty = file_tty(file);
struct tty_ldisc *ld;
int retval = -ENOIOCTLCMD;
switch (cmd) {
case TIOCOUTQ:
case TIOCSTI:
case TIOCGWINSZ:
case TIOCSWINSZ:
case TIOCGEXCL:
case TIOCGETD:
case TIOCSETD:
case TIOCGDEV:
case TIOCMGET:
case TIOCMSET:
case TIOCMBIC:
case TIOCMBIS:
case TIOCGICOUNT:
case TIOCGPGRP:
case TIOCSPGRP:
case TIOCGSID:
case TIOCSERGETLSR:
case TIOCGRS485:
case TIOCSRS485:
#ifdef TIOCGETP
case TIOCGETP:
case TIOCSETP:
case TIOCSETN:
#endif
#ifdef TIOCGETC
case TIOCGETC:
case TIOCSETC:
#endif
#ifdef TIOCGLTC
case TIOCGLTC:
case TIOCSLTC:
#endif
case TCSETSF:
case TCSETSW:
case TCSETS:
case TCGETS:
#ifdef TCGETS2
case TCGETS2:
case TCSETSF2:
case TCSETSW2:
case TCSETS2:
#endif
case TCGETA:
case TCSETAF:
case TCSETAW:
case TCSETA:
case TIOCGLCKTRMIOS:
case TIOCSLCKTRMIOS:
#ifdef TCGETX
case TCGETX:
case TCSETX:
case TCSETXW:
case TCSETXF:
#endif
case TIOCGSOFTCAR:
case TIOCSSOFTCAR:
case PPPIOCGCHAN:
case PPPIOCGUNIT:
return tty_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
case TIOCCONS:
case TIOCEXCL:
case TIOCNXCL:
case TIOCVHANGUP:
case TIOCSBRK:
case TIOCCBRK:
case TCSBRK:
case TCSBRKP:
case TCFLSH:
case TIOCGPTPEER:
case TIOCNOTTY:
case TIOCSCTTY:
case TCXONC:
case TIOCMIWAIT:
case TIOCSERCONFIG:
return tty_ioctl(file, cmd, arg);
}
if (tty_paranoia_check(tty, file_inode(file), "tty_ioctl"))
return -EINVAL;
switch (cmd) {
case TIOCSSERIAL:
return compat_tty_tiocsserial(tty, compat_ptr(arg));
case TIOCGSERIAL:
return compat_tty_tiocgserial(tty, compat_ptr(arg));
}
if (tty->ops->compat_ioctl) {
retval = tty->ops->compat_ioctl(tty, cmd, arg);
if (retval != -ENOIOCTLCMD)
return retval;
}
ld = tty_ldisc_ref_wait(tty);
if (!ld)
return hung_up_tty_compat_ioctl(file, cmd, arg);
if (ld->ops->compat_ioctl)
retval = ld->ops->compat_ioctl(tty, cmd, arg);
if (retval == -ENOIOCTLCMD && ld->ops->ioctl)
retval = ld->ops->ioctl(tty, (unsigned long)compat_ptr(cmd),
arg);
tty_ldisc_deref(ld);
return retval;
}
#endif
static int this_tty(const void *t, struct file *file, unsigned fd)
{
if (likely(file->f_op->read_iter != tty_read))
return 0;
return file_tty(file) != t ? 0 : fd + 1;
}
/*
* This implements the "Secure Attention Key" --- the idea is to
* prevent trojan horses by killing all processes associated with this
* tty when the user hits the "Secure Attention Key". Required for
* super-paranoid applications --- see the Orange Book for more details.
*
* This code could be nicer; ideally it should send a HUP, wait a few
* seconds, then send a INT, and then a KILL signal. But you then
* have to coordinate with the init process, since all processes associated
* with the current tty must be dead before the new getty is allowed
* to spawn.
*
* Now, if it would be correct ;-/ The current code has a nasty hole -
* it doesn't catch files in flight. We may send the descriptor to ourselves
* via AF_UNIX socket, close it and later fetch from socket. FIXME.
*
* Nasty bug: do_SAK is being called in interrupt context. This can
* deadlock. We punt it up to process context. AKPM - 16Mar2001
*/
void __do_SAK(struct tty_struct *tty)
{
struct task_struct *g, *p;
struct pid *session;
int i;
tty: Fix ->session locking Currently, locking of ->session is very inconsistent; most places protect it using the legacy tty mutex, but disassociate_ctty(), __do_SAK(), tiocspgrp() and tiocgsid() don't. Two of the writers hold the ctrl_lock (because they already need it for ->pgrp), but __proc_set_tty() doesn't do that yet. On a PREEMPT=y system, an unprivileged user can theoretically abuse this broken locking to read 4 bytes of freed memory via TIOCGSID if tiocgsid() is preempted long enough at the right point. (Other things might also go wrong, especially if root-only ioctls are involved; I'm not sure about that.) Change the locking on ->session such that: - tty_lock() is held by all writers: By making disassociate_ctty() hold it. This should be fine because the same lock can already be taken through the call to tty_vhangup_session(). The tricky part is that we need to shorten the area covered by siglock to be able to take tty_lock() without ugly retry logic; as far as I can tell, this should be fine, since nothing in the signal_struct is touched in the `if (tty)` branch. - ctrl_lock is held by all writers: By changing __proc_set_tty() to hold the lock a little longer. - All readers that aren't holding tty_lock() hold ctrl_lock: By adding locking to tiocgsid() and __do_SAK(), and expanding the area covered by ctrl_lock in tiocspgrp(). Cc: stable@kernel.org Signed-off-by: Jann Horn <jannh@google.com> Reviewed-by: Jiri Slaby <jirislaby@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-12-03 09:25:05 +08:00
unsigned long flags;
spin_lock_irqsave(&tty->ctrl.lock, flags);
session = get_pid(tty->ctrl.session);
spin_unlock_irqrestore(&tty->ctrl.lock, flags);
tty_ldisc_flush(tty);
tty_driver_flush_buffer(tty);
read_lock(&tasklist_lock);
/* Kill the entire session */
do_each_pid_task(session, PIDTYPE_SID, p) {
tty_notice(tty, "SAK: killed process %d (%s): by session\n",
task_pid_nr(p), p->comm);
tty_io: Use group_send_sig_info in __do_SACK to note it is a session being killed Replace send_sig and force_sig in __do_SAK with group_send_sig_info the general helper for sending a signal to a process group. This is wordier but it allows specifying PIDTYPE_SID so that the signal code knows the signal went to a session. Both force_sig() and send_sig(..., 1) specify SEND_SIG_PRIV and the new call of group_send_sig_info does that explicitly. This is enough to ensure even a pid namespace init is killed. The global init remains unkillable. The guarantee that __do_SAK tries to provide is a clean path to login to a machine. As the global init is unkillable, if it chooses to hold open a tty it can violate this guarantee. A technique other than killing processes would be needed to provide this guarantee to userspace. The only difference between force_sig and send_sig when sending SIGKILL is that SIGNAL_UNKILLABLE is cleared. This has no affect on the processing of a signal sent with SEND_SIG_PRIV by any process, making it unnecessary, and not behavior that needs to be preserved. force_sig was used originally because it did not take as many locks as send_sig. Today send_sig, force_sig and group_send_sig_info take the same locks when delivering a signal. group_send_sig_info also contains a permission check that force_sig and send_sig do not. However the presence of SEND_SIG_PRIV makes the permission check a noop. So the permission check does not result in any behavioral differences. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2018-07-21 04:59:17 +08:00
group_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_SID);
} while_each_pid_task(session, PIDTYPE_SID, p);
/* Now kill any processes that happen to have the tty open */
do_each_thread(g, p) {
if (p->signal->tty == tty) {
tty_notice(tty, "SAK: killed process %d (%s): by controlling tty\n",
task_pid_nr(p), p->comm);
group_send_sig_info(SIGKILL, SEND_SIG_PRIV, p,
PIDTYPE_SID);
continue;
}
task_lock(p);
i = iterate_fd(p->files, 0, this_tty, tty);
if (i != 0) {
tty_notice(tty, "SAK: killed process %d (%s): by fd#%d\n",
task_pid_nr(p), p->comm, i - 1);
group_send_sig_info(SIGKILL, SEND_SIG_PRIV, p,
PIDTYPE_SID);
}
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
tty: Fix ->session locking Currently, locking of ->session is very inconsistent; most places protect it using the legacy tty mutex, but disassociate_ctty(), __do_SAK(), tiocspgrp() and tiocgsid() don't. Two of the writers hold the ctrl_lock (because they already need it for ->pgrp), but __proc_set_tty() doesn't do that yet. On a PREEMPT=y system, an unprivileged user can theoretically abuse this broken locking to read 4 bytes of freed memory via TIOCGSID if tiocgsid() is preempted long enough at the right point. (Other things might also go wrong, especially if root-only ioctls are involved; I'm not sure about that.) Change the locking on ->session such that: - tty_lock() is held by all writers: By making disassociate_ctty() hold it. This should be fine because the same lock can already be taken through the call to tty_vhangup_session(). The tricky part is that we need to shorten the area covered by siglock to be able to take tty_lock() without ugly retry logic; as far as I can tell, this should be fine, since nothing in the signal_struct is touched in the `if (tty)` branch. - ctrl_lock is held by all writers: By changing __proc_set_tty() to hold the lock a little longer. - All readers that aren't holding tty_lock() hold ctrl_lock: By adding locking to tiocgsid() and __do_SAK(), and expanding the area covered by ctrl_lock in tiocspgrp(). Cc: stable@kernel.org Signed-off-by: Jann Horn <jannh@google.com> Reviewed-by: Jiri Slaby <jirislaby@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-12-03 09:25:05 +08:00
put_pid(session);
}
static void do_SAK_work(struct work_struct *work)
{
struct tty_struct *tty =
container_of(work, struct tty_struct, SAK_work);
__do_SAK(tty);
}
/*
* The tq handling here is a little racy - tty->SAK_work may already be queued.
* Fortunately we don't need to worry, because if ->SAK_work is already queued,
* the values which we write to it will be identical to the values which it
* already has. --akpm
*/
void do_SAK(struct tty_struct *tty)
{
if (!tty)
return;
schedule_work(&tty->SAK_work);
}
EXPORT_SYMBOL(do_SAK);
/* Must put_device() after it's unused! */
static struct device *tty_get_device(struct tty_struct *tty)
{
dev_t devt = tty_devnum(tty);
return class_find_device_by_devt(&tty_class, devt);
}
/**
* alloc_tty_struct - allocate a new tty
* @driver: driver which will handle the returned tty
* @idx: minor of the tty
*
* This subroutine allocates and initializes a tty structure.
*
* Locking: none - @tty in question is not exposed at this point
*/
struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
{
struct tty_struct *tty;
memcg: enable accounting for tty-related objects At each login the user forces the kernel to create a new terminal and allocate up to ~1Kb memory for the tty-related structures. By default it's allowed to create up to 4096 ptys with 1024 reserve for initial mount namespace only and the settings are controlled by host admin. Though this default is not enough for hosters with thousands of containers per node. Host admin can be forced to increase it up to NR_UNIX98_PTY_MAX = 1<<20. By default container is restricted by pty mount_opt.max = 1024, but admin inside container can change it via remount. As a result, one container can consume almost all allowed ptys and allocate up to 1Gb of unaccounted memory. It is not enough per-se to trigger OOM on host, however anyway, it allows to significantly exceed the assigned memcg limit and leads to troubles on the over-committed node. It makes sense to account for them to restrict the host's memory consumption from inside the memcg-limited container. Link: https://lkml.kernel.org/r/5d4bca06-7d4f-a905-e518-12981ebca1b3@virtuozzo.com Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jirislaby@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 05:41:41 +08:00
tty = kzalloc(sizeof(*tty), GFP_KERNEL_ACCOUNT);
if (!tty)
return NULL;
kref_init(&tty->kref);
if (tty_ldisc_init(tty)) {
kfree(tty);
return NULL;
}
tty->ctrl.session = NULL;
tty->ctrl.pgrp = NULL;
mutex_init(&tty->legacy_mutex);
mutex_init(&tty->throttle_mutex);
init_rwsem(&tty->termios_rwsem);
tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [<ffffffff81452656>] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b797>] down_read+0x47/0x5c [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff810430a7>] console_lock+0x77/0x80 [<ffffffff8146b2a1>] con_flush_chars+0x31/0x50 [<ffffffff8145780c>] n_tty_write+0x1ec/0x4d0 [<ffffffff814541b9>] tty_write+0x159/0x2e0 [<ffffffff814543f5>] redirected_tty_write+0xb5/0xc0 [<ffffffff811ab9d5>] vfs_write+0xc5/0x1f0 [<ffffffff811abec5>] SyS_write+0x55/0xa0 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b5b>] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [<ffffffff81497b69>] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [<ffffffffa008a6dd>] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [<ffffffff813d93f5>] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [<ffffffff813d8116>] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [<ffffffff813d95a4>] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [<ffffffff8107aac6>] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [<ffffffff81755f19>] dump_stack+0x19/0x1b [<ffffffff8174f506>] print_circular_bug+0x1fb/0x20c [<ffffffff810b65c3>] __lock_acquire+0x1c43/0x1d30 [<ffffffff810b775e>] ? mark_held_locks+0xae/0x120 [<ffffffff810b78d5>] ? trace_hardirqs_on_caller+0x105/0x1d0 [<ffffffff810b6d62>] lock_acquire+0x92/0x1f0 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff8175b724>] down_write+0x44/0x70 [<ffffffff81452656>] ? tty_do_resize+0x36/0xe0 [<ffffffff81452656>] tty_do_resize+0x36/0xe0 [<ffffffff8146c841>] vc_do_resize+0x3e1/0x4c0 [<ffffffff8146c99f>] vc_resize+0x1f/0x30 [<ffffffff813e4535>] fbcon_init+0x385/0x5a0 [<ffffffff8146a4bc>] visual_init+0xbc/0x120 [<ffffffff8146cd13>] do_bind_con_driver+0x163/0x320 [<ffffffff8146cfa1>] do_take_over_console+0x61/0x70 [<ffffffff813e2b93>] do_fbcon_takeover+0x63/0xc0 [<ffffffff813e67a5>] fbcon_event_notify+0x715/0x820 [<ffffffff81762f9d>] notifier_call_chain+0x5d/0x110 [<ffffffff8107aadc>] __blocking_notifier_call_chain+0x6c/0xc0 [<ffffffff8107ab46>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff813d7c0b>] fb_notifier_call_chain+0x1b/0x20 [<ffffffff813d95b2>] register_framebuffer+0x1e2/0x320 [<ffffffffa01043e1>] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [<ffffffff8173cbcb>] ? kmemleak_alloc+0x5b/0xc0 [<ffffffff81198874>] ? kmem_cache_alloc_trace+0x104/0x290 [<ffffffffa01035e1>] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [<ffffffffa01bcb05>] nouveau_fbcon_init+0x105/0x140 [nouveau] [<ffffffffa01ad0af>] nouveau_drm_load+0x43f/0x610 [nouveau] [<ffffffffa008a79e>] drm_get_pci_dev+0x17e/0x2a0 [drm] [<ffffffffa01ad4da>] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [<ffffffff8175f162>] ? _raw_spin_unlock_irqrestore+0x42/0x80 [<ffffffff813b13db>] local_pci_probe+0x4b/0x80 [<ffffffff813b1701>] pci_device_probe+0x111/0x120 [<ffffffff814977eb>] driver_probe_device+0x8b/0x3a0 [<ffffffff81497bab>] __driver_attach+0xab/0xb0 [<ffffffff81497b00>] ? driver_probe_device+0x3a0/0x3a0 [<ffffffff814956ad>] bus_for_each_dev+0x5d/0xa0 [<ffffffff814971fe>] driver_attach+0x1e/0x20 [<ffffffff81496cc1>] bus_add_driver+0x111/0x290 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff814982b7>] driver_register+0x77/0x170 [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffff813b0454>] __pci_register_driver+0x64/0x70 [<ffffffffa008a9da>] drm_pci_init+0x11a/0x130 [drm] [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a000>] ? 0xffffffffa0229fff [<ffffffffa022a04d>] nouveau_drm_init+0x4d/0x1000 [nouveau] [<ffffffff810002ea>] do_one_initcall+0xea/0x1a0 [<ffffffff810c54cb>] load_module+0x123b/0x1bf0 [<ffffffff81399a50>] ? ddebug_proc_open+0xb0/0xb0 [<ffffffff813855ae>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810c5f57>] SyS_init_module+0xd7/0x120 [<ffffffff817677c2>] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-25 04:43:51 +08:00
mutex_init(&tty->winsize_mutex);
init_ldsem(&tty->ldisc_sem);
init_waitqueue_head(&tty->write_wait);
init_waitqueue_head(&tty->read_wait);
2006-11-22 22:55:48 +08:00
INIT_WORK(&tty->hangup_work, do_tty_hangup);
mutex_init(&tty->atomic_write_lock);
spin_lock_init(&tty->ctrl.lock);
tty: cumulate and document tty_struct::flow* members Group the flow flags under a single struct called flow. The new struct contains 'stopped' and 'tco_stopped' bools which used to be bits in a bitfield. The struct also contains the lock protecting them to potentially share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. This is also the perfect time to start the documentation of tty_struct where all this lives. So we start by documenting what these bools actually serve for. And why we do all the alignment dances. Only the few up-to-date information from the Theodore's comment made it into this new Kerneldoc comment. Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Shawn Guo <shawnguo@kernel.org> Cc: Sascha Hauer <s.hauer@pengutronix.de> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: "Maciej W. Rozycki" <macro@orcam.me.uk> Link: https://lore.kernel.org/r/20210505091928.22010-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-05-05 17:19:05 +08:00
spin_lock_init(&tty->flow.lock);
spin_lock_init(&tty->files_lock);
INIT_LIST_HEAD(&tty->tty_files);
INIT_WORK(&tty->SAK_work, do_SAK_work);
tty->driver = driver;
tty->ops = driver->ops;
tty->index = idx;
tty_line_name(driver, idx, tty->name);
tty->dev = tty_get_device(tty);
return tty;
}
/**
* tty_put_char - write one character to a tty
* @tty: tty
* @ch: character to write
*
* Write one byte to the @tty using the provided @tty->ops->put_char() method
* if present.
*
* Note: the specific put_char operation in the driver layer may go
* away soon. Don't call it directly, use this method
*
* Return: the number of characters successfully output.
*/
int tty_put_char(struct tty_struct *tty, unsigned char ch)
{
if (tty->ops->put_char)
return tty->ops->put_char(tty, ch);
return tty->ops->write(tty, &ch, 1);
}
EXPORT_SYMBOL_GPL(tty_put_char);
static int tty_cdev_add(struct tty_driver *driver, dev_t dev,
unsigned int index, unsigned int count)
{
int err;
/* init here, since reused cdevs cause crashes */
driver->cdevs[index] = cdev_alloc();
if (!driver->cdevs[index])
return -ENOMEM;
driver->cdevs[index]->ops = &tty_fops;
driver->cdevs[index]->owner = driver->owner;
err = cdev_add(driver->cdevs[index], dev, count);
if (err)
kobject_put(&driver->cdevs[index]->kobj);
return err;
}
/**
* tty_register_device - register a tty device
* @driver: the tty driver that describes the tty device
* @index: the index in the tty driver for this tty device
* @device: a struct device that is associated with this tty device.
* This field is optional, if there is no known struct device
* for this tty device it can be set to NULL safely.
*
* This call is required to be made to register an individual tty device
* if the tty driver's flags have the %TTY_DRIVER_DYNAMIC_DEV bit set. If
* that bit is not set, this function should not be called by a tty
* driver.
*
* Locking: ??
*
* Return: A pointer to the struct device for this tty device (or
* ERR_PTR(-EFOO) on error).
*/
struct device *tty_register_device(struct tty_driver *driver, unsigned index,
struct device *device)
{
return tty_register_device_attr(driver, index, device, NULL, NULL);
}
EXPORT_SYMBOL(tty_register_device);
static void tty_device_create_release(struct device *dev)
{
dev_dbg(dev, "releasing...\n");
kfree(dev);
}
/**
* tty_register_device_attr - register a tty device
* @driver: the tty driver that describes the tty device
* @index: the index in the tty driver for this tty device
* @device: a struct device that is associated with this tty device.
* This field is optional, if there is no known struct device
* for this tty device it can be set to %NULL safely.
* @drvdata: Driver data to be set to device.
* @attr_grp: Attribute group to be set on device.
*
* This call is required to be made to register an individual tty device if the
* tty driver's flags have the %TTY_DRIVER_DYNAMIC_DEV bit set. If that bit is
* not set, this function should not be called by a tty driver.
*
* Locking: ??
*
* Return: A pointer to the struct device for this tty device (or
* ERR_PTR(-EFOO) on error).
*/
struct device *tty_register_device_attr(struct tty_driver *driver,
unsigned index, struct device *device,
void *drvdata,
const struct attribute_group **attr_grp)
{
char name[64];
dev_t devt = MKDEV(driver->major, driver->minor_start) + index;
struct ktermios *tp;
struct device *dev;
int retval;
if (index >= driver->num) {
pr_err("%s: Attempt to register invalid tty line number (%d)\n",
driver->name, index);
return ERR_PTR(-EINVAL);
}
if (driver->type == TTY_DRIVER_TYPE_PTY)
pty_line_name(driver, index, name);
else
tty_line_name(driver, index, name);
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
return ERR_PTR(-ENOMEM);
dev->devt = devt;
dev->class = &tty_class;
dev->parent = device;
dev->release = tty_device_create_release;
dev_set_name(dev, "%s", name);
dev->groups = attr_grp;
dev_set_drvdata(dev, drvdata);
dev_set_uevent_suppress(dev, 1);
retval = device_register(dev);
if (retval)
goto err_put;
if (!(driver->flags & TTY_DRIVER_DYNAMIC_ALLOC)) {
/*
* Free any saved termios data so that the termios state is
* reset when reusing a minor number.
*/
tp = driver->termios[index];
if (tp) {
driver->termios[index] = NULL;
kfree(tp);
}
retval = tty_cdev_add(driver, devt, index, 1);
if (retval)
goto err_del;
}
dev_set_uevent_suppress(dev, 0);
kobject_uevent(&dev->kobj, KOBJ_ADD);
return dev;
err_del:
device_del(dev);
err_put:
put_device(dev);
return ERR_PTR(retval);
}
EXPORT_SYMBOL_GPL(tty_register_device_attr);
/**
* tty_unregister_device - unregister a tty device
* @driver: the tty driver that describes the tty device
* @index: the index in the tty driver for this tty device
*
* If a tty device is registered with a call to tty_register_device() then
* this function must be called when the tty device is gone.
*
* Locking: ??
*/
void tty_unregister_device(struct tty_driver *driver, unsigned index)
{
device_destroy(&tty_class, MKDEV(driver->major, driver->minor_start) + index);
if (!(driver->flags & TTY_DRIVER_DYNAMIC_ALLOC)) {
cdev_del(driver->cdevs[index]);
driver->cdevs[index] = NULL;
}
}
EXPORT_SYMBOL(tty_unregister_device);
/**
* __tty_alloc_driver -- allocate tty driver
* @lines: count of lines this driver can handle at most
* @owner: module which is responsible for this driver
* @flags: some of %TTY_DRIVER_ flags, will be set in driver->flags
*
* This should not be called directly, some of the provided macros should be
* used instead. Use IS_ERR() and friends on @retval.
*/
struct tty_driver *__tty_alloc_driver(unsigned int lines, struct module *owner,
unsigned long flags)
{
struct tty_driver *driver;
unsigned int cdevs = 1;
int err;
if (!lines || (flags & TTY_DRIVER_UNNUMBERED_NODE && lines > 1))
return ERR_PTR(-EINVAL);
driver = kzalloc(sizeof(*driver), GFP_KERNEL);
if (!driver)
return ERR_PTR(-ENOMEM);
kref_init(&driver->kref);
driver->num = lines;
driver->owner = owner;
driver->flags = flags;
if (!(flags & TTY_DRIVER_DEVPTS_MEM)) {
driver->ttys = kcalloc(lines, sizeof(*driver->ttys),
GFP_KERNEL);
driver->termios = kcalloc(lines, sizeof(*driver->termios),
GFP_KERNEL);
if (!driver->ttys || !driver->termios) {
err = -ENOMEM;
goto err_free_all;
}
}
if (!(flags & TTY_DRIVER_DYNAMIC_ALLOC)) {
driver->ports = kcalloc(lines, sizeof(*driver->ports),
GFP_KERNEL);
if (!driver->ports) {
err = -ENOMEM;
goto err_free_all;
}
cdevs = lines;
}
driver->cdevs = kcalloc(cdevs, sizeof(*driver->cdevs), GFP_KERNEL);
if (!driver->cdevs) {
err = -ENOMEM;
goto err_free_all;
}
return driver;
err_free_all:
kfree(driver->ports);
kfree(driver->ttys);
kfree(driver->termios);
kfree(driver->cdevs);
kfree(driver);
return ERR_PTR(err);
}
EXPORT_SYMBOL(__tty_alloc_driver);
static void destruct_tty_driver(struct kref *kref)
{
struct tty_driver *driver = container_of(kref, struct tty_driver, kref);
int i;
struct ktermios *tp;
if (driver->flags & TTY_DRIVER_INSTALLED) {
for (i = 0; i < driver->num; i++) {
tp = driver->termios[i];
if (tp) {
driver->termios[i] = NULL;
kfree(tp);
}
if (!(driver->flags & TTY_DRIVER_DYNAMIC_DEV))
tty_unregister_device(driver, i);
}
proc_tty_unregister_driver(driver);
if (driver->flags & TTY_DRIVER_DYNAMIC_ALLOC)
cdev_del(driver->cdevs[0]);
}
kfree(driver->cdevs);
kfree(driver->ports);
kfree(driver->termios);
kfree(driver->ttys);
kfree(driver);
}
/**
* tty_driver_kref_put -- drop a reference to a tty driver
* @driver: driver of which to drop the reference
*
* The final put will destroy and free up the driver.
*/
void tty_driver_kref_put(struct tty_driver *driver)
{
kref_put(&driver->kref, destruct_tty_driver);
}
EXPORT_SYMBOL(tty_driver_kref_put);
/**
* tty_register_driver -- register a tty driver
* @driver: driver to register
*
* Called by a tty driver to register itself.
*/
int tty_register_driver(struct tty_driver *driver)
{
int error;
int i;
dev_t dev;
struct device *d;
if (!driver->major) {
error = alloc_chrdev_region(&dev, driver->minor_start,
driver->num, driver->name);
if (!error) {
driver->major = MAJOR(dev);
driver->minor_start = MINOR(dev);
}
} else {
dev = MKDEV(driver->major, driver->minor_start);
error = register_chrdev_region(dev, driver->num, driver->name);
}
if (error < 0)
goto err;
if (driver->flags & TTY_DRIVER_DYNAMIC_ALLOC) {
error = tty_cdev_add(driver, dev, 0, driver->num);
if (error)
goto err_unreg_char;
}
Protect tty drivers list with tty_mutex Additions and removal from tty_drivers list were just done as well as iterating on it for /proc/tty/drivers generation. testing: modprobe/rmmod loop of simple module which does nothing but tty_register_driver() vs cat /proc/tty/drivers loop BUG: unable to handle kernel paging request at virtual address 6b6b6b6b printing eip: c01cefa7 *pde = 00000000 Oops: 0000 [#1] PREEMPT last sysfs file: devices/pci0000:00/0000:00:1d.7/usb5/5-0:1.0/bInterfaceProtocol Modules linked in: ohci_hcd af_packet e1000 ehci_hcd uhci_hcd usbcore xfs CPU: 0 EIP: 0060:[<c01cefa7>] Not tainted VLI EFLAGS: 00010297 (2.6.21-rc4-mm1 #4) EIP is at vsnprintf+0x3a4/0x5fc eax: 6b6b6b6b ebx: f6cb50f2 ecx: 6b6b6b6b edx: fffffffe esi: c0354700 edi: f6cb6000 ebp: 6b6b6b6b esp: f31f5e68 ds: 007b es: 007b fs: 00d8 gs: 0033 ss: 0068 Process cat (pid: 31864, ti=f31f4000 task=c1998030 task.ti=f31f4000) Stack: 00000000 c0103f20 c013003a c0103f20 00000000 f6cb50da 0000000a 00000f0e f6cb50f2 00000010 00000014 ffffffff ffffffff 00000007 c0354753 f6cb50f2 f73e39dc f73e39dc 00000001 c0175416 f31f5ed8 f31f5ed4 0ee00000 f32090bc Call Trace: [<c0103f20>] restore_nocheck+0x12/0x15 [<c013003a>] mark_held_locks+0x6d/0x86 [<c0103f20>] restore_nocheck+0x12/0x15 [<c0175416>] seq_printf+0x2e/0x52 [<c0192895>] show_tty_range+0x35/0x1f3 [<c0175416>] seq_printf+0x2e/0x52 [<c0192add>] show_tty_driver+0x8a/0x1d9 [<c01758f6>] seq_read+0x70/0x2ba [<c0175886>] seq_read+0x0/0x2ba [<c018d8e6>] proc_reg_read+0x63/0x9f [<c015e764>] vfs_read+0x7d/0xb5 [<c018d883>] proc_reg_read+0x0/0x9f [<c015eab1>] sys_read+0x41/0x6a [<c0103e4e>] sysenter_past_esp+0x5f/0x99 ======================= Code: 00 8b 4d 04 e9 44 ff ff ff 8d 4d 04 89 4c 24 50 8b 6d 00 81 fd ff 0f 00 00 b8 a4 c1 35 c0 0f 46 e8 8b 54 24 2c 89 e9 89 c8 eb 06 <80> 38 00 74 07 40 4a 83 fa ff 75 f4 29 c8 89 c6 8b 44 24 28 89 EIP: [<c01cefa7>] vsnprintf+0x3a4/0x5fc SS:ESP 0068:f31f5e68 Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:27:12 +08:00
mutex_lock(&tty_mutex);
list_add(&driver->tty_drivers, &tty_drivers);
Protect tty drivers list with tty_mutex Additions and removal from tty_drivers list were just done as well as iterating on it for /proc/tty/drivers generation. testing: modprobe/rmmod loop of simple module which does nothing but tty_register_driver() vs cat /proc/tty/drivers loop BUG: unable to handle kernel paging request at virtual address 6b6b6b6b printing eip: c01cefa7 *pde = 00000000 Oops: 0000 [#1] PREEMPT last sysfs file: devices/pci0000:00/0000:00:1d.7/usb5/5-0:1.0/bInterfaceProtocol Modules linked in: ohci_hcd af_packet e1000 ehci_hcd uhci_hcd usbcore xfs CPU: 0 EIP: 0060:[<c01cefa7>] Not tainted VLI EFLAGS: 00010297 (2.6.21-rc4-mm1 #4) EIP is at vsnprintf+0x3a4/0x5fc eax: 6b6b6b6b ebx: f6cb50f2 ecx: 6b6b6b6b edx: fffffffe esi: c0354700 edi: f6cb6000 ebp: 6b6b6b6b esp: f31f5e68 ds: 007b es: 007b fs: 00d8 gs: 0033 ss: 0068 Process cat (pid: 31864, ti=f31f4000 task=c1998030 task.ti=f31f4000) Stack: 00000000 c0103f20 c013003a c0103f20 00000000 f6cb50da 0000000a 00000f0e f6cb50f2 00000010 00000014 ffffffff ffffffff 00000007 c0354753 f6cb50f2 f73e39dc f73e39dc 00000001 c0175416 f31f5ed8 f31f5ed4 0ee00000 f32090bc Call Trace: [<c0103f20>] restore_nocheck+0x12/0x15 [<c013003a>] mark_held_locks+0x6d/0x86 [<c0103f20>] restore_nocheck+0x12/0x15 [<c0175416>] seq_printf+0x2e/0x52 [<c0192895>] show_tty_range+0x35/0x1f3 [<c0175416>] seq_printf+0x2e/0x52 [<c0192add>] show_tty_driver+0x8a/0x1d9 [<c01758f6>] seq_read+0x70/0x2ba [<c0175886>] seq_read+0x0/0x2ba [<c018d8e6>] proc_reg_read+0x63/0x9f [<c015e764>] vfs_read+0x7d/0xb5 [<c018d883>] proc_reg_read+0x0/0x9f [<c015eab1>] sys_read+0x41/0x6a [<c0103e4e>] sysenter_past_esp+0x5f/0x99 ======================= Code: 00 8b 4d 04 e9 44 ff ff ff 8d 4d 04 89 4c 24 50 8b 6d 00 81 fd ff 0f 00 00 b8 a4 c1 35 c0 0f 46 e8 8b 54 24 2c 89 e9 89 c8 eb 06 <80> 38 00 74 07 40 4a 83 fa ff 75 f4 29 c8 89 c6 8b 44 24 28 89 EIP: [<c01cefa7>] vsnprintf+0x3a4/0x5fc SS:ESP 0068:f31f5e68 Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:27:12 +08:00
mutex_unlock(&tty_mutex);
if (!(driver->flags & TTY_DRIVER_DYNAMIC_DEV)) {
for (i = 0; i < driver->num; i++) {
d = tty_register_device(driver, i, NULL);
if (IS_ERR(d)) {
error = PTR_ERR(d);
goto err_unreg_devs;
}
}
}
proc_tty_register_driver(driver);
driver->flags |= TTY_DRIVER_INSTALLED;
return 0;
err_unreg_devs:
for (i--; i >= 0; i--)
tty_unregister_device(driver, i);
mutex_lock(&tty_mutex);
list_del(&driver->tty_drivers);
mutex_unlock(&tty_mutex);
err_unreg_char:
unregister_chrdev_region(dev, driver->num);
err:
return error;
}
EXPORT_SYMBOL(tty_register_driver);
/**
* tty_unregister_driver -- unregister a tty driver
* @driver: driver to unregister
*
* Called by a tty driver to unregister itself.
*/
void tty_unregister_driver(struct tty_driver *driver)
{
unregister_chrdev_region(MKDEV(driver->major, driver->minor_start),
driver->num);
Protect tty drivers list with tty_mutex Additions and removal from tty_drivers list were just done as well as iterating on it for /proc/tty/drivers generation. testing: modprobe/rmmod loop of simple module which does nothing but tty_register_driver() vs cat /proc/tty/drivers loop BUG: unable to handle kernel paging request at virtual address 6b6b6b6b printing eip: c01cefa7 *pde = 00000000 Oops: 0000 [#1] PREEMPT last sysfs file: devices/pci0000:00/0000:00:1d.7/usb5/5-0:1.0/bInterfaceProtocol Modules linked in: ohci_hcd af_packet e1000 ehci_hcd uhci_hcd usbcore xfs CPU: 0 EIP: 0060:[<c01cefa7>] Not tainted VLI EFLAGS: 00010297 (2.6.21-rc4-mm1 #4) EIP is at vsnprintf+0x3a4/0x5fc eax: 6b6b6b6b ebx: f6cb50f2 ecx: 6b6b6b6b edx: fffffffe esi: c0354700 edi: f6cb6000 ebp: 6b6b6b6b esp: f31f5e68 ds: 007b es: 007b fs: 00d8 gs: 0033 ss: 0068 Process cat (pid: 31864, ti=f31f4000 task=c1998030 task.ti=f31f4000) Stack: 00000000 c0103f20 c013003a c0103f20 00000000 f6cb50da 0000000a 00000f0e f6cb50f2 00000010 00000014 ffffffff ffffffff 00000007 c0354753 f6cb50f2 f73e39dc f73e39dc 00000001 c0175416 f31f5ed8 f31f5ed4 0ee00000 f32090bc Call Trace: [<c0103f20>] restore_nocheck+0x12/0x15 [<c013003a>] mark_held_locks+0x6d/0x86 [<c0103f20>] restore_nocheck+0x12/0x15 [<c0175416>] seq_printf+0x2e/0x52 [<c0192895>] show_tty_range+0x35/0x1f3 [<c0175416>] seq_printf+0x2e/0x52 [<c0192add>] show_tty_driver+0x8a/0x1d9 [<c01758f6>] seq_read+0x70/0x2ba [<c0175886>] seq_read+0x0/0x2ba [<c018d8e6>] proc_reg_read+0x63/0x9f [<c015e764>] vfs_read+0x7d/0xb5 [<c018d883>] proc_reg_read+0x0/0x9f [<c015eab1>] sys_read+0x41/0x6a [<c0103e4e>] sysenter_past_esp+0x5f/0x99 ======================= Code: 00 8b 4d 04 e9 44 ff ff ff 8d 4d 04 89 4c 24 50 8b 6d 00 81 fd ff 0f 00 00 b8 a4 c1 35 c0 0f 46 e8 8b 54 24 2c 89 e9 89 c8 eb 06 <80> 38 00 74 07 40 4a 83 fa ff 75 f4 29 c8 89 c6 8b 44 24 28 89 EIP: [<c01cefa7>] vsnprintf+0x3a4/0x5fc SS:ESP 0068:f31f5e68 Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:27:12 +08:00
mutex_lock(&tty_mutex);
list_del(&driver->tty_drivers);
Protect tty drivers list with tty_mutex Additions and removal from tty_drivers list were just done as well as iterating on it for /proc/tty/drivers generation. testing: modprobe/rmmod loop of simple module which does nothing but tty_register_driver() vs cat /proc/tty/drivers loop BUG: unable to handle kernel paging request at virtual address 6b6b6b6b printing eip: c01cefa7 *pde = 00000000 Oops: 0000 [#1] PREEMPT last sysfs file: devices/pci0000:00/0000:00:1d.7/usb5/5-0:1.0/bInterfaceProtocol Modules linked in: ohci_hcd af_packet e1000 ehci_hcd uhci_hcd usbcore xfs CPU: 0 EIP: 0060:[<c01cefa7>] Not tainted VLI EFLAGS: 00010297 (2.6.21-rc4-mm1 #4) EIP is at vsnprintf+0x3a4/0x5fc eax: 6b6b6b6b ebx: f6cb50f2 ecx: 6b6b6b6b edx: fffffffe esi: c0354700 edi: f6cb6000 ebp: 6b6b6b6b esp: f31f5e68 ds: 007b es: 007b fs: 00d8 gs: 0033 ss: 0068 Process cat (pid: 31864, ti=f31f4000 task=c1998030 task.ti=f31f4000) Stack: 00000000 c0103f20 c013003a c0103f20 00000000 f6cb50da 0000000a 00000f0e f6cb50f2 00000010 00000014 ffffffff ffffffff 00000007 c0354753 f6cb50f2 f73e39dc f73e39dc 00000001 c0175416 f31f5ed8 f31f5ed4 0ee00000 f32090bc Call Trace: [<c0103f20>] restore_nocheck+0x12/0x15 [<c013003a>] mark_held_locks+0x6d/0x86 [<c0103f20>] restore_nocheck+0x12/0x15 [<c0175416>] seq_printf+0x2e/0x52 [<c0192895>] show_tty_range+0x35/0x1f3 [<c0175416>] seq_printf+0x2e/0x52 [<c0192add>] show_tty_driver+0x8a/0x1d9 [<c01758f6>] seq_read+0x70/0x2ba [<c0175886>] seq_read+0x0/0x2ba [<c018d8e6>] proc_reg_read+0x63/0x9f [<c015e764>] vfs_read+0x7d/0xb5 [<c018d883>] proc_reg_read+0x0/0x9f [<c015eab1>] sys_read+0x41/0x6a [<c0103e4e>] sysenter_past_esp+0x5f/0x99 ======================= Code: 00 8b 4d 04 e9 44 ff ff ff 8d 4d 04 89 4c 24 50 8b 6d 00 81 fd ff 0f 00 00 b8 a4 c1 35 c0 0f 46 e8 8b 54 24 2c 89 e9 89 c8 eb 06 <80> 38 00 74 07 40 4a 83 fa ff 75 f4 29 c8 89 c6 8b 44 24 28 89 EIP: [<c01cefa7>] vsnprintf+0x3a4/0x5fc SS:ESP 0068:f31f5e68 Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:27:12 +08:00
mutex_unlock(&tty_mutex);
}
EXPORT_SYMBOL(tty_unregister_driver);
[PATCH] tty: ->signal->tty locking Fix the locking of signal->tty. Use ->sighand->siglock to protect ->signal->tty; this lock is already used by most other members of ->signal/->sighand. And unless we are 'current' or the tasklist_lock is held we need ->siglock to access ->signal anyway. (NOTE: sys_unshare() is broken wrt ->sighand locking rules) Note that tty_mutex is held over tty destruction, so while holding tty_mutex any tty pointer remains valid. Otherwise the lifetime of ttys are governed by their open file handles. This leaves some holes for tty access from signal->tty (or any other non file related tty access). It solves the tty SLAB scribbles we were seeing. (NOTE: the change from group_send_sig_info to __group_send_sig_info needs to be examined by someone familiar with the security framework, I think it is safe given the SEND_SIG_PRIV from other __group_send_sig_info invocations) [schwidefsky@de.ibm.com: 3270 fix] [akpm@osdl.org: various post-viro fixes] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Alan Cox <alan@redhat.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Roland McGrath <roland@redhat.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jan Kara <jack@ucw.cz> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:36:04 +08:00
dev_t tty_devnum(struct tty_struct *tty)
{
return MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index;
}
EXPORT_SYMBOL(tty_devnum);
void tty_default_fops(struct file_operations *fops)
{
*fops = tty_fops;
}
driver core: make struct class.devnode() take a const * The devnode() in struct class should not be modifying the device that is passed into it, so mark it as a const * and propagate the function signature changes out into all relevant subsystems that use this callback. Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Reinette Chatre <reinette.chatre@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: x86@kernel.org Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Jens Axboe <axboe@kernel.dk> Cc: Justin Sanders <justin@coraid.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Sumit Semwal <sumit.semwal@linaro.org> Cc: Benjamin Gaignard <benjamin.gaignard@collabora.com> Cc: Liam Mark <lmark@codeaurora.org> Cc: Laura Abbott <labbott@redhat.com> Cc: Brian Starkey <Brian.Starkey@arm.com> Cc: John Stultz <jstultz@google.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Cc: Maxime Ripard <mripard@kernel.org> Cc: Thomas Zimmermann <tzimmermann@suse.de> Cc: David Airlie <airlied@gmail.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Leon Romanovsky <leon@kernel.org> Cc: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: Mauro Carvalho Chehab <mchehab@kernel.org> Cc: Sean Young <sean@mess.org> Cc: Frank Haverkamp <haver@linux.ibm.com> Cc: Jiri Slaby <jirislaby@kernel.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Cornelia Huck <cohuck@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Jaroslav Kysela <perex@perex.cz> Cc: Takashi Iwai <tiwai@suse.com> Cc: Hans Verkuil <hverkuil-cisco@xs4all.nl> Cc: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Cc: Xie Yongji <xieyongji@bytedance.com> Cc: Gautam Dawar <gautam.dawar@xilinx.com> Cc: Dan Carpenter <error27@gmail.com> Cc: Eli Cohen <elic@nvidia.com> Cc: Parav Pandit <parav@nvidia.com> Cc: Maxime Coquelin <maxime.coquelin@redhat.com> Cc: alsa-devel@alsa-project.org Cc: dri-devel@lists.freedesktop.org Cc: kvm@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Cc: linux-block@vger.kernel.org Cc: linux-input@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linux-rdma@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: linux-usb@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Link: https://lore.kernel.org/r/20221123122523.1332370-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-11-23 20:25:20 +08:00
static char *tty_devnode(const struct device *dev, umode_t *mode)
{
if (!mode)
return NULL;
if (dev->devt == MKDEV(TTYAUX_MAJOR, 0) ||
dev->devt == MKDEV(TTYAUX_MAJOR, 2))
*mode = 0666;
return NULL;
}
const struct class tty_class = {
.name = "tty",
.devnode = tty_devnode,
};
static int __init tty_class_init(void)
{
return class_register(&tty_class);
}
postcore_initcall(tty_class_init);
/* 3/2004 jmc: why do these devices exist? */
static struct cdev tty_cdev, console_cdev;
static ssize_t show_cons_active(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct console *cs[16];
int i = 0;
struct console *c;
ssize_t count = 0;
/*
* Hold the console_list_lock to guarantee that no consoles are
* unregistered until all console processing is complete.
* This also allows safe traversal of the console list and
* race-free reading of @flags.
*/
console_list_lock();
for_each_console(c) {
if (!c->device)
continue;
if (!c->write)
continue;
if ((c->flags & CON_ENABLED) == 0)
continue;
cs[i++] = c;
if (i >= ARRAY_SIZE(cs))
break;
}
/*
* Take console_lock to serialize device() callback with
* other console operations. For example, fg_console is
* modified under console_lock when switching vt.
*/
console_lock();
while (i--) {
int index = cs[i]->index;
struct tty_driver *drv = cs[i]->device(cs[i], &index);
/* don't resolve tty0 as some programs depend on it */
if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR))
count += tty_line_name(drv, index, buf + count);
else
count += sprintf(buf + count, "%s%d",
cs[i]->name, cs[i]->index);
count += sprintf(buf + count, "%c", i ? ' ':'\n');
}
console_unlock();
console_list_unlock();
return count;
}
static DEVICE_ATTR(active, S_IRUGO, show_cons_active, NULL);
static struct attribute *cons_dev_attrs[] = {
&dev_attr_active.attr,
NULL
};
ATTRIBUTE_GROUPS(cons_dev);
static struct device *consdev;
void console_sysfs_notify(void)
{
if (consdev)
sysfs_notify(&consdev->kobj, NULL, "active");
}
static struct ctl_table tty_table[] = {
{
.procname = "legacy_tiocsti",
.data = &tty_legacy_tiocsti,
.maxlen = sizeof(tty_legacy_tiocsti),
.mode = 0644,
.proc_handler = proc_dobool,
},
{
.procname = "ldisc_autoload",
.data = &tty_ldisc_autoload,
.maxlen = sizeof(tty_ldisc_autoload),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{ }
};
/*
* Ok, now we can initialize the rest of the tty devices and can count
* on memory allocations, interrupts etc..
*/
int __init tty_init(void)
{
register_sysctl_init("dev/tty", tty_table);
cdev_init(&tty_cdev, &tty_fops);
if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) ||
register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0)
panic("Couldn't register /dev/tty driver\n");
device_create(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 0), NULL, "tty");
cdev_init(&console_cdev, &console_fops);
if (cdev_add(&console_cdev, MKDEV(TTYAUX_MAJOR, 1), 1) ||
register_chrdev_region(MKDEV(TTYAUX_MAJOR, 1), 1, "/dev/console") < 0)
panic("Couldn't register /dev/console driver\n");
consdev = device_create_with_groups(&tty_class, NULL,
MKDEV(TTYAUX_MAJOR, 1), NULL,
cons_dev_groups, "console");
if (IS_ERR(consdev))
consdev = NULL;
#ifdef CONFIG_VT
vty_init(&console_fops);
#endif
return 0;
}