linux/drivers/tty/hvc/hvc_console.c
Andrew Melnychenko 9a9fc42b86 tty: hvc: fix buffer overflow during hvc_alloc().
If there is a lot(more then 16) of virtio-console devices
or virtio_console module is reloaded
- buffers 'vtermnos' and 'cons_ops' are overflowed.
In older kernels it overruns spinlock which leads to kernel freezing:
https://bugzilla.redhat.com/show_bug.cgi?id=1786239

To reproduce the issue, you can try simple script that
loads/unloads module. Something like this:
while [ 1 ]
do
  modprobe virtio_console
  sleep 2
  modprobe -r virtio_console
  sleep 2
done

Description of problem:
Guest get 'Call Trace' when loading module "virtio_console"
and unloading it frequently - clearly reproduced on kernel-4.18.0:

[   81.498208] ------------[ cut here ]------------
[   81.499263] pvqspinlock: lock 0xffffffff92080020 has corrupted value 0xc0774ca0!
[   81.501000] WARNING: CPU: 0 PID: 785 at kernel/locking/qspinlock_paravirt.h:500 __pv_queued_spin_unlock_slowpath+0xc0/0xd0
[   81.503173] Modules linked in: virtio_console fuse xt_CHECKSUM ipt_MASQUERADE xt_conntrack ipt_REJECT nft_counter nf_nat_tftp nft_objref nf_conntrack_tftp tun bridge stp llc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nf_tables_set nft_chain_nat_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 nft_chain_route_ipv6 nft_chain_nat_ipv4 nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack nft_chain_route_ipv4 ip6_tables nft_compat ip_set nf_tables nfnetlink sunrpc bochs_drm drm_vram_helper ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm i2c_piix4 pcspkr crct10dif_pclmul crc32_pclmul joydev ghash_clmulni_intel ip_tables xfs libcrc32c sd_mod sg ata_generic ata_piix virtio_net libata crc32c_intel net_failover failover serio_raw virtio_scsi dm_mirror dm_region_hash dm_log dm_mod [last unloaded: virtio_console]
[   81.517019] CPU: 0 PID: 785 Comm: kworker/0:2 Kdump: loaded Not tainted 4.18.0-167.el8.x86_64 #1
[   81.518639] Hardware name: Red Hat KVM, BIOS 1.12.0-5.scrmod+el8.2.0+5159+d8aa4d83 04/01/2014
[   81.520205] Workqueue: events control_work_handler [virtio_console]
[   81.521354] RIP: 0010:__pv_queued_spin_unlock_slowpath+0xc0/0xd0
[   81.522450] Code: 07 00 48 63 7a 10 e8 bf 64 f5 ff 66 90 c3 8b 05 e6 cf d6 01 85 c0 74 01 c3 8b 17 48 89 fe 48 c7 c7 38 4b 29 91 e8 3a 6c fa ff <0f> 0b c3 0f 0b 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 48
[   81.525830] RSP: 0018:ffffb51a01ffbd70 EFLAGS: 00010282
[   81.526798] RAX: 0000000000000000 RBX: 0000000000000010 RCX: 0000000000000000
[   81.528110] RDX: ffff9e66f1826480 RSI: ffff9e66f1816a08 RDI: ffff9e66f1816a08
[   81.529437] RBP: ffffffff9153ff10 R08: 000000000000026c R09: 0000000000000053
[   81.530732] R10: 0000000000000000 R11: ffffb51a01ffbc18 R12: ffff9e66cd682200
[   81.532133] R13: ffffffff9153ff10 R14: ffff9e6685569500 R15: ffff9e66cd682000
[   81.533442] FS:  0000000000000000(0000) GS:ffff9e66f1800000(0000) knlGS:0000000000000000
[   81.534914] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   81.535971] CR2: 00005624c55b14d0 CR3: 00000003a023c000 CR4: 00000000003406f0
[   81.537283] Call Trace:
[   81.537763]  __raw_callee_save___pv_queued_spin_unlock_slowpath+0x11/0x20
[   81.539011]  .slowpath+0x9/0xe
[   81.539585]  hvc_alloc+0x25e/0x300
[   81.540237]  init_port_console+0x28/0x100 [virtio_console]
[   81.541251]  handle_control_message.constprop.27+0x1c4/0x310 [virtio_console]
[   81.542546]  control_work_handler+0x70/0x10c [virtio_console]
[   81.543601]  process_one_work+0x1a7/0x3b0
[   81.544356]  worker_thread+0x30/0x390
[   81.545025]  ? create_worker+0x1a0/0x1a0
[   81.545749]  kthread+0x112/0x130
[   81.546358]  ? kthread_flush_work_fn+0x10/0x10
[   81.547183]  ret_from_fork+0x22/0x40
[   81.547842] ---[ end trace aa97649bd16c8655 ]---
[   83.546539] general protection fault: 0000 [#1] SMP NOPTI
[   83.547422] CPU: 5 PID: 3225 Comm: modprobe Kdump: loaded Tainted: G        W        --------- -  - 4.18.0-167.el8.x86_64 #1
[   83.549191] Hardware name: Red Hat KVM, BIOS 1.12.0-5.scrmod+el8.2.0+5159+d8aa4d83 04/01/2014
[   83.550544] RIP: 0010:__pv_queued_spin_lock_slowpath+0x19a/0x2a0
[   83.551504] Code: c4 c1 ea 12 41 be 01 00 00 00 4c 8d 6d 14 41 83 e4 03 8d 42 ff 49 c1 e4 05 48 98 49 81 c4 40 a5 02 00 4c 03 24 c5 60 48 34 91 <49> 89 2c 24 b8 00 80 00 00 eb 15 84 c0 75 0a 41 0f b6 54 24 14 84
[   83.554449] RSP: 0018:ffffb51a0323fdb0 EFLAGS: 00010202
[   83.555290] RAX: 000000000000301c RBX: ffffffff92080020 RCX: 0000000000000001
[   83.556426] RDX: 000000000000301d RSI: 0000000000000000 RDI: 0000000000000000
[   83.557556] RBP: ffff9e66f196a540 R08: 000000000000028a R09: ffff9e66d2757788
[   83.558688] R10: 0000000000000000 R11: 0000000000000000 R12: 646e61725f770b07
[   83.559821] R13: ffff9e66f196a554 R14: 0000000000000001 R15: 0000000000180000
[   83.560958] FS:  00007fd5032e8740(0000) GS:ffff9e66f1940000(0000) knlGS:0000000000000000
[   83.562233] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   83.563149] CR2: 00007fd5022b0da0 CR3: 000000038c334000 CR4: 00000000003406e0

Signed-off-by: Andrew Melnychenko <andrew@daynix.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20200414191503.3471783-1-andrew@daynix.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-04-23 16:02:07 +02:00

1077 lines
25 KiB
C

// SPDX-License-Identifier: GPL-2.0+
/*
* Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
* Copyright (C) 2001 Paul Mackerras <paulus@au.ibm.com>, IBM
* Copyright (C) 2004 Benjamin Herrenschmidt <benh@kernel.crashing.org>, IBM Corp.
* Copyright (C) 2004 IBM Corporation
*
* Additional Author(s):
* Ryan S. Arnold <rsa@us.ibm.com>
*/
#include <linux/console.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/kbd_kern.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/list.h>
#include <linux/major.h>
#include <linux/atomic.h>
#include <linux/sysrq.h>
#include <linux/tty.h>
#include <linux/tty_flip.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/slab.h>
#include <linux/serial_core.h>
#include <linux/uaccess.h>
#include "hvc_console.h"
#define HVC_MAJOR 229
#define HVC_MINOR 0
/*
* Wait this long per iteration while trying to push buffered data to the
* hypervisor before allowing the tty to complete a close operation.
*/
#define HVC_CLOSE_WAIT (HZ/100) /* 1/10 of a second */
/*
* These sizes are most efficient for vio, because they are the
* native transfer size. We could make them selectable in the
* future to better deal with backends that want other buffer sizes.
*/
#define N_OUTBUF 16
#define N_INBUF 16
#define __ALIGNED__ __attribute__((__aligned__(sizeof(long))))
static struct tty_driver *hvc_driver;
static struct task_struct *hvc_task;
/* Picks up late kicks after list walk but before schedule() */
static int hvc_kicked;
/* hvc_init is triggered from hvc_alloc, i.e. only when actually used */
static atomic_t hvc_needs_init __read_mostly = ATOMIC_INIT(-1);
static int hvc_init(void);
#ifdef CONFIG_MAGIC_SYSRQ
static int sysrq_pressed;
#endif
/* dynamic list of hvc_struct instances */
static LIST_HEAD(hvc_structs);
/*
* Protect the list of hvc_struct instances from inserts and removals during
* list traversal.
*/
static DEFINE_MUTEX(hvc_structs_mutex);
/*
* This value is used to assign a tty->index value to a hvc_struct based
* upon order of exposure via hvc_probe(), when we can not match it to
* a console candidate registered with hvc_instantiate().
*/
static int last_hvc = -1;
/*
* Do not call this function with either the hvc_structs_mutex or the hvc_struct
* lock held. If successful, this function increments the kref reference
* count against the target hvc_struct so it should be released when finished.
*/
static struct hvc_struct *hvc_get_by_index(int index)
{
struct hvc_struct *hp;
unsigned long flags;
mutex_lock(&hvc_structs_mutex);
list_for_each_entry(hp, &hvc_structs, next) {
spin_lock_irqsave(&hp->lock, flags);
if (hp->index == index) {
tty_port_get(&hp->port);
spin_unlock_irqrestore(&hp->lock, flags);
mutex_unlock(&hvc_structs_mutex);
return hp;
}
spin_unlock_irqrestore(&hp->lock, flags);
}
hp = NULL;
mutex_unlock(&hvc_structs_mutex);
return hp;
}
static int __hvc_flush(const struct hv_ops *ops, uint32_t vtermno, bool wait)
{
if (wait)
might_sleep();
if (ops->flush)
return ops->flush(vtermno, wait);
return 0;
}
static int hvc_console_flush(const struct hv_ops *ops, uint32_t vtermno)
{
return __hvc_flush(ops, vtermno, false);
}
/*
* Wait for the console to flush before writing more to it. This sleeps.
*/
static int hvc_flush(struct hvc_struct *hp)
{
return __hvc_flush(hp->ops, hp->vtermno, true);
}
/*
* Initial console vtermnos for console API usage prior to full console
* initialization. Any vty adapter outside this range will not have usable
* console interfaces but can still be used as a tty device. This has to be
* static because kmalloc will not work during early console init.
*/
static const struct hv_ops *cons_ops[MAX_NR_HVC_CONSOLES];
static uint32_t vtermnos[MAX_NR_HVC_CONSOLES] =
{[0 ... MAX_NR_HVC_CONSOLES - 1] = -1};
/*
* Console APIs, NOT TTY. These APIs are available immediately when
* hvc_console_setup() finds adapters.
*/
static void hvc_console_print(struct console *co, const char *b,
unsigned count)
{
char c[N_OUTBUF] __ALIGNED__;
unsigned i = 0, n = 0;
int r, donecr = 0, index = co->index;
/* Console access attempt outside of acceptable console range. */
if (index >= MAX_NR_HVC_CONSOLES)
return;
/* This console adapter was removed so it is not usable. */
if (vtermnos[index] == -1)
return;
while (count > 0 || i > 0) {
if (count > 0 && i < sizeof(c)) {
if (b[n] == '\n' && !donecr) {
c[i++] = '\r';
donecr = 1;
} else {
c[i++] = b[n++];
donecr = 0;
--count;
}
} else {
r = cons_ops[index]->put_chars(vtermnos[index], c, i);
if (r <= 0) {
/* throw away characters on error
* but spin in case of -EAGAIN */
if (r != -EAGAIN) {
i = 0;
} else {
hvc_console_flush(cons_ops[index],
vtermnos[index]);
}
} else if (r > 0) {
i -= r;
if (i > 0)
memmove(c, c+r, i);
}
}
}
hvc_console_flush(cons_ops[index], vtermnos[index]);
}
static struct tty_driver *hvc_console_device(struct console *c, int *index)
{
if (vtermnos[c->index] == -1)
return NULL;
*index = c->index;
return hvc_driver;
}
static int hvc_console_setup(struct console *co, char *options)
{
if (co->index < 0 || co->index >= MAX_NR_HVC_CONSOLES)
return -ENODEV;
if (vtermnos[co->index] == -1)
return -ENODEV;
return 0;
}
static struct console hvc_console = {
.name = "hvc",
.write = hvc_console_print,
.device = hvc_console_device,
.setup = hvc_console_setup,
.flags = CON_PRINTBUFFER,
.index = -1,
};
/*
* Early console initialization. Precedes driver initialization.
*
* (1) we are first, and the user specified another driver
* -- index will remain -1
* (2) we are first and the user specified no driver
* -- index will be set to 0, then we will fail setup.
* (3) we are first and the user specified our driver
* -- index will be set to user specified driver, and we will fail
* (4) we are after driver, and this initcall will register us
* -- if the user didn't specify a driver then the console will match
*
* Note that for cases 2 and 3, we will match later when the io driver
* calls hvc_instantiate() and call register again.
*/
static int __init hvc_console_init(void)
{
register_console(&hvc_console);
return 0;
}
console_initcall(hvc_console_init);
/* callback when the kboject ref count reaches zero. */
static void hvc_port_destruct(struct tty_port *port)
{
struct hvc_struct *hp = container_of(port, struct hvc_struct, port);
unsigned long flags;
mutex_lock(&hvc_structs_mutex);
spin_lock_irqsave(&hp->lock, flags);
list_del(&(hp->next));
spin_unlock_irqrestore(&hp->lock, flags);
mutex_unlock(&hvc_structs_mutex);
kfree(hp);
}
static void hvc_check_console(int index)
{
/* Already enabled, bail out */
if (hvc_console.flags & CON_ENABLED)
return;
/* If this index is what the user requested, then register
* now (setup won't fail at this point). It's ok to just
* call register again if previously .setup failed.
*/
if (index == hvc_console.index)
register_console(&hvc_console);
}
/*
* hvc_instantiate() is an early console discovery method which locates
* consoles * prior to the vio subsystem discovering them. Hotplugged
* vty adapters do NOT get an hvc_instantiate() callback since they
* appear after early console init.
*/
int hvc_instantiate(uint32_t vtermno, int index, const struct hv_ops *ops)
{
struct hvc_struct *hp;
if (index < 0 || index >= MAX_NR_HVC_CONSOLES)
return -1;
if (vtermnos[index] != -1)
return -1;
/* make sure no no tty has been registered in this index */
hp = hvc_get_by_index(index);
if (hp) {
tty_port_put(&hp->port);
return -1;
}
vtermnos[index] = vtermno;
cons_ops[index] = ops;
/* check if we need to re-register the kernel console */
hvc_check_console(index);
return 0;
}
EXPORT_SYMBOL_GPL(hvc_instantiate);
/* Wake the sleeping khvcd */
void hvc_kick(void)
{
hvc_kicked = 1;
wake_up_process(hvc_task);
}
EXPORT_SYMBOL_GPL(hvc_kick);
static void hvc_unthrottle(struct tty_struct *tty)
{
hvc_kick();
}
static int hvc_install(struct tty_driver *driver, struct tty_struct *tty)
{
struct hvc_struct *hp;
int rc;
/* Auto increments kref reference if found. */
hp = hvc_get_by_index(tty->index);
if (!hp)
return -ENODEV;
tty->driver_data = hp;
rc = tty_port_install(&hp->port, driver, tty);
if (rc)
tty_port_put(&hp->port);
return rc;
}
/*
* The TTY interface won't be used until after the vio layer has exposed the vty
* adapter to the kernel.
*/
static int hvc_open(struct tty_struct *tty, struct file * filp)
{
struct hvc_struct *hp = tty->driver_data;
unsigned long flags;
int rc = 0;
spin_lock_irqsave(&hp->port.lock, flags);
/* Check and then increment for fast path open. */
if (hp->port.count++ > 0) {
spin_unlock_irqrestore(&hp->port.lock, flags);
hvc_kick();
return 0;
} /* else count == 0 */
spin_unlock_irqrestore(&hp->port.lock, flags);
tty_port_tty_set(&hp->port, tty);
if (hp->ops->notifier_add)
rc = hp->ops->notifier_add(hp, hp->data);
/*
* If the notifier fails we return an error. The tty layer
* will call hvc_close() after a failed open but we don't want to clean
* up there so we'll clean up here and clear out the previously set
* tty fields and return the kref reference.
*/
if (rc) {
tty_port_tty_set(&hp->port, NULL);
tty->driver_data = NULL;
tty_port_put(&hp->port);
printk(KERN_ERR "hvc_open: request_irq failed with rc %d.\n", rc);
} else
/* We are ready... raise DTR/RTS */
if (C_BAUD(tty))
if (hp->ops->dtr_rts)
hp->ops->dtr_rts(hp, 1);
/* Force wakeup of the polling thread */
hvc_kick();
return rc;
}
static void hvc_close(struct tty_struct *tty, struct file * filp)
{
struct hvc_struct *hp;
unsigned long flags;
if (tty_hung_up_p(filp))
return;
/*
* No driver_data means that this close was issued after a failed
* hvc_open by the tty layer's release_dev() function and we can just
* exit cleanly because the kref reference wasn't made.
*/
if (!tty->driver_data)
return;
hp = tty->driver_data;
spin_lock_irqsave(&hp->port.lock, flags);
if (--hp->port.count == 0) {
spin_unlock_irqrestore(&hp->port.lock, flags);
/* We are done with the tty pointer now. */
tty_port_tty_set(&hp->port, NULL);
if (C_HUPCL(tty))
if (hp->ops->dtr_rts)
hp->ops->dtr_rts(hp, 0);
if (hp->ops->notifier_del)
hp->ops->notifier_del(hp, hp->data);
/* cancel pending tty resize work */
cancel_work_sync(&hp->tty_resize);
/*
* Chain calls chars_in_buffer() and returns immediately if
* there is no buffered data otherwise sleeps on a wait queue
* waking periodically to check chars_in_buffer().
*/
tty_wait_until_sent(tty, HVC_CLOSE_WAIT);
} else {
if (hp->port.count < 0)
printk(KERN_ERR "hvc_close %X: oops, count is %d\n",
hp->vtermno, hp->port.count);
spin_unlock_irqrestore(&hp->port.lock, flags);
}
}
static void hvc_cleanup(struct tty_struct *tty)
{
struct hvc_struct *hp = tty->driver_data;
tty_port_put(&hp->port);
}
static void hvc_hangup(struct tty_struct *tty)
{
struct hvc_struct *hp = tty->driver_data;
unsigned long flags;
if (!hp)
return;
/* cancel pending tty resize work */
cancel_work_sync(&hp->tty_resize);
spin_lock_irqsave(&hp->port.lock, flags);
/*
* The N_TTY line discipline has problems such that in a close vs
* open->hangup case this can be called after the final close so prevent
* that from happening for now.
*/
if (hp->port.count <= 0) {
spin_unlock_irqrestore(&hp->port.lock, flags);
return;
}
hp->port.count = 0;
spin_unlock_irqrestore(&hp->port.lock, flags);
tty_port_tty_set(&hp->port, NULL);
hp->n_outbuf = 0;
if (hp->ops->notifier_hangup)
hp->ops->notifier_hangup(hp, hp->data);
}
/*
* Push buffered characters whether they were just recently buffered or waiting
* on a blocked hypervisor. Call this function with hp->lock held.
*/
static int hvc_push(struct hvc_struct *hp)
{
int n;
n = hp->ops->put_chars(hp->vtermno, hp->outbuf, hp->n_outbuf);
if (n <= 0) {
if (n == 0 || n == -EAGAIN) {
hp->do_wakeup = 1;
return 0;
}
/* throw away output on error; this happens when
there is no session connected to the vterm. */
hp->n_outbuf = 0;
} else
hp->n_outbuf -= n;
if (hp->n_outbuf > 0)
memmove(hp->outbuf, hp->outbuf + n, hp->n_outbuf);
else
hp->do_wakeup = 1;
return n;
}
static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count)
{
struct hvc_struct *hp = tty->driver_data;
unsigned long flags;
int rsize, written = 0;
/* This write was probably executed during a tty close. */
if (!hp)
return -EPIPE;
/* FIXME what's this (unprotected) check for? */
if (hp->port.count <= 0)
return -EIO;
while (count > 0) {
int ret = 0;
spin_lock_irqsave(&hp->lock, flags);
rsize = hp->outbuf_size - hp->n_outbuf;
if (rsize) {
if (rsize > count)
rsize = count;
memcpy(hp->outbuf + hp->n_outbuf, buf, rsize);
count -= rsize;
buf += rsize;
hp->n_outbuf += rsize;
written += rsize;
}
if (hp->n_outbuf > 0)
ret = hvc_push(hp);
spin_unlock_irqrestore(&hp->lock, flags);
if (!ret)
break;
if (count) {
if (hp->n_outbuf > 0)
hvc_flush(hp);
cond_resched();
}
}
/*
* Racy, but harmless, kick thread if there is still pending data.
*/
if (hp->n_outbuf)
hvc_kick();
return written;
}
/**
* hvc_set_winsz() - Resize the hvc tty terminal window.
* @work: work structure.
*
* The routine shall not be called within an atomic context because it
* might sleep.
*
* Locking: hp->lock
*/
static void hvc_set_winsz(struct work_struct *work)
{
struct hvc_struct *hp;
unsigned long hvc_flags;
struct tty_struct *tty;
struct winsize ws;
hp = container_of(work, struct hvc_struct, tty_resize);
tty = tty_port_tty_get(&hp->port);
if (!tty)
return;
spin_lock_irqsave(&hp->lock, hvc_flags);
ws = hp->ws;
spin_unlock_irqrestore(&hp->lock, hvc_flags);
tty_do_resize(tty, &ws);
tty_kref_put(tty);
}
/*
* This is actually a contract between the driver and the tty layer outlining
* how much write room the driver can guarantee will be sent OR BUFFERED. This
* driver MUST honor the return value.
*/
static int hvc_write_room(struct tty_struct *tty)
{
struct hvc_struct *hp = tty->driver_data;
if (!hp)
return 0;
return hp->outbuf_size - hp->n_outbuf;
}
static int hvc_chars_in_buffer(struct tty_struct *tty)
{
struct hvc_struct *hp = tty->driver_data;
if (!hp)
return 0;
return hp->n_outbuf;
}
/*
* timeout will vary between the MIN and MAX values defined here. By default
* and during console activity we will use a default MIN_TIMEOUT of 10. When
* the console is idle, we increase the timeout value on each pass through
* msleep until we reach the max. This may be noticeable as a brief (average
* one second) delay on the console before the console responds to input when
* there has been no input for some time.
*/
#define MIN_TIMEOUT (10)
#define MAX_TIMEOUT (2000)
static u32 timeout = MIN_TIMEOUT;
/*
* Maximum number of bytes to get from the console driver if hvc_poll is
* called from driver (and can't sleep). Any more than this and we break
* and start polling with khvcd. This value was derived from from an OpenBMC
* console with the OPAL driver that results in about 0.25ms interrupts off
* latency.
*/
#define HVC_ATOMIC_READ_MAX 128
#define HVC_POLL_READ 0x00000001
#define HVC_POLL_WRITE 0x00000002
static int __hvc_poll(struct hvc_struct *hp, bool may_sleep)
{
struct tty_struct *tty;
int i, n, count, poll_mask = 0;
char buf[N_INBUF] __ALIGNED__;
unsigned long flags;
int read_total = 0;
int written_total = 0;
spin_lock_irqsave(&hp->lock, flags);
/* Push pending writes */
if (hp->n_outbuf > 0)
written_total = hvc_push(hp);
/* Reschedule us if still some write pending */
if (hp->n_outbuf > 0) {
poll_mask |= HVC_POLL_WRITE;
/* If hvc_push() was not able to write, sleep a few msecs */
timeout = (written_total) ? 0 : MIN_TIMEOUT;
}
if (may_sleep) {
spin_unlock_irqrestore(&hp->lock, flags);
cond_resched();
spin_lock_irqsave(&hp->lock, flags);
}
/* No tty attached, just skip */
tty = tty_port_tty_get(&hp->port);
if (tty == NULL)
goto bail;
/* Now check if we can get data (are we throttled ?) */
if (tty_throttled(tty))
goto out;
/* If we aren't notifier driven and aren't throttled, we always
* request a reschedule
*/
if (!hp->irq_requested)
poll_mask |= HVC_POLL_READ;
read_again:
/* Read data if any */
count = tty_buffer_request_room(&hp->port, N_INBUF);
/* If flip is full, just reschedule a later read */
if (count == 0) {
poll_mask |= HVC_POLL_READ;
goto out;
}
n = hp->ops->get_chars(hp->vtermno, buf, count);
if (n <= 0) {
/* Hangup the tty when disconnected from host */
if (n == -EPIPE) {
spin_unlock_irqrestore(&hp->lock, flags);
tty_hangup(tty);
spin_lock_irqsave(&hp->lock, flags);
} else if ( n == -EAGAIN ) {
/*
* Some back-ends can only ensure a certain min
* num of bytes read, which may be > 'count'.
* Let the tty clear the flip buff to make room.
*/
poll_mask |= HVC_POLL_READ;
}
goto out;
}
for (i = 0; i < n; ++i) {
#ifdef CONFIG_MAGIC_SYSRQ
if (hp->index == hvc_console.index) {
/* Handle the SysRq Hack */
/* XXX should support a sequence */
if (buf[i] == '\x0f') { /* ^O */
/* if ^O is pressed again, reset
* sysrq_pressed and flip ^O char */
sysrq_pressed = !sysrq_pressed;
if (sysrq_pressed)
continue;
} else if (sysrq_pressed) {
handle_sysrq(buf[i]);
sysrq_pressed = 0;
continue;
}
}
#endif /* CONFIG_MAGIC_SYSRQ */
tty_insert_flip_char(&hp->port, buf[i], 0);
}
read_total += n;
if (may_sleep) {
/* Keep going until the flip is full */
spin_unlock_irqrestore(&hp->lock, flags);
cond_resched();
spin_lock_irqsave(&hp->lock, flags);
goto read_again;
} else if (read_total < HVC_ATOMIC_READ_MAX) {
/* Break and defer if it's a large read in atomic */
goto read_again;
}
/*
* Latency break, schedule another poll immediately.
*/
poll_mask |= HVC_POLL_READ;
out:
/* Wakeup write queue if necessary */
if (hp->do_wakeup) {
hp->do_wakeup = 0;
tty_wakeup(tty);
}
bail:
spin_unlock_irqrestore(&hp->lock, flags);
if (read_total) {
/* Activity is occurring, so reset the polling backoff value to
a minimum for performance. */
timeout = MIN_TIMEOUT;
tty_flip_buffer_push(&hp->port);
}
tty_kref_put(tty);
return poll_mask;
}
int hvc_poll(struct hvc_struct *hp)
{
return __hvc_poll(hp, false);
}
EXPORT_SYMBOL_GPL(hvc_poll);
/**
* __hvc_resize() - Update terminal window size information.
* @hp: HVC console pointer
* @ws: Terminal window size structure
*
* Stores the specified window size information in the hvc structure of @hp.
* The function schedule the tty resize update.
*
* Locking: Locking free; the function MUST be called holding hp->lock
*/
void __hvc_resize(struct hvc_struct *hp, struct winsize ws)
{
hp->ws = ws;
schedule_work(&hp->tty_resize);
}
EXPORT_SYMBOL_GPL(__hvc_resize);
/*
* This kthread is either polling or interrupt driven. This is determined by
* calling hvc_poll() who determines whether a console adapter support
* interrupts.
*/
static int khvcd(void *unused)
{
int poll_mask;
struct hvc_struct *hp;
set_freezable();
do {
poll_mask = 0;
hvc_kicked = 0;
try_to_freeze();
wmb();
if (!cpus_are_in_xmon()) {
mutex_lock(&hvc_structs_mutex);
list_for_each_entry(hp, &hvc_structs, next) {
poll_mask |= __hvc_poll(hp, true);
cond_resched();
}
mutex_unlock(&hvc_structs_mutex);
} else
poll_mask |= HVC_POLL_READ;
if (hvc_kicked)
continue;
set_current_state(TASK_INTERRUPTIBLE);
if (!hvc_kicked) {
if (poll_mask == 0)
schedule();
else {
unsigned long j_timeout;
if (timeout < MAX_TIMEOUT)
timeout += (timeout >> 6) + 1;
/*
* We don't use msleep_interruptible otherwise
* "kick" will fail to wake us up
*/
j_timeout = msecs_to_jiffies(timeout) + 1;
schedule_timeout_interruptible(j_timeout);
}
}
__set_current_state(TASK_RUNNING);
} while (!kthread_should_stop());
return 0;
}
static int hvc_tiocmget(struct tty_struct *tty)
{
struct hvc_struct *hp = tty->driver_data;
if (!hp || !hp->ops->tiocmget)
return -EINVAL;
return hp->ops->tiocmget(hp);
}
static int hvc_tiocmset(struct tty_struct *tty,
unsigned int set, unsigned int clear)
{
struct hvc_struct *hp = tty->driver_data;
if (!hp || !hp->ops->tiocmset)
return -EINVAL;
return hp->ops->tiocmset(hp, set, clear);
}
#ifdef CONFIG_CONSOLE_POLL
static int hvc_poll_init(struct tty_driver *driver, int line, char *options)
{
return 0;
}
static int hvc_poll_get_char(struct tty_driver *driver, int line)
{
struct tty_struct *tty = driver->ttys[0];
struct hvc_struct *hp = tty->driver_data;
int n;
char ch;
n = hp->ops->get_chars(hp->vtermno, &ch, 1);
if (n <= 0)
return NO_POLL_CHAR;
return ch;
}
static void hvc_poll_put_char(struct tty_driver *driver, int line, char ch)
{
struct tty_struct *tty = driver->ttys[0];
struct hvc_struct *hp = tty->driver_data;
int n;
do {
n = hp->ops->put_chars(hp->vtermno, &ch, 1);
} while (n <= 0);
}
#endif
static const struct tty_operations hvc_ops = {
.install = hvc_install,
.open = hvc_open,
.close = hvc_close,
.cleanup = hvc_cleanup,
.write = hvc_write,
.hangup = hvc_hangup,
.unthrottle = hvc_unthrottle,
.write_room = hvc_write_room,
.chars_in_buffer = hvc_chars_in_buffer,
.tiocmget = hvc_tiocmget,
.tiocmset = hvc_tiocmset,
#ifdef CONFIG_CONSOLE_POLL
.poll_init = hvc_poll_init,
.poll_get_char = hvc_poll_get_char,
.poll_put_char = hvc_poll_put_char,
#endif
};
static const struct tty_port_operations hvc_port_ops = {
.destruct = hvc_port_destruct,
};
struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
const struct hv_ops *ops,
int outbuf_size)
{
struct hvc_struct *hp;
int i;
/* We wait until a driver actually comes along */
if (atomic_inc_not_zero(&hvc_needs_init)) {
int err = hvc_init();
if (err)
return ERR_PTR(err);
}
hp = kzalloc(ALIGN(sizeof(*hp), sizeof(long)) + outbuf_size,
GFP_KERNEL);
if (!hp)
return ERR_PTR(-ENOMEM);
hp->vtermno = vtermno;
hp->data = data;
hp->ops = ops;
hp->outbuf_size = outbuf_size;
hp->outbuf = &((char *)hp)[ALIGN(sizeof(*hp), sizeof(long))];
tty_port_init(&hp->port);
hp->port.ops = &hvc_port_ops;
INIT_WORK(&hp->tty_resize, hvc_set_winsz);
spin_lock_init(&hp->lock);
mutex_lock(&hvc_structs_mutex);
/*
* find index to use:
* see if this vterm id matches one registered for console.
*/
for (i=0; i < MAX_NR_HVC_CONSOLES; i++)
if (vtermnos[i] == hp->vtermno &&
cons_ops[i] == hp->ops)
break;
if (i >= MAX_NR_HVC_CONSOLES) {
/* find 'empty' slot for console */
for (i = 0; i < MAX_NR_HVC_CONSOLES && vtermnos[i] != -1; i++) {
}
/* no matching slot, just use a counter */
if (i == MAX_NR_HVC_CONSOLES)
i = ++last_hvc + MAX_NR_HVC_CONSOLES;
}
hp->index = i;
if (i < MAX_NR_HVC_CONSOLES) {
cons_ops[i] = ops;
vtermnos[i] = vtermno;
}
list_add_tail(&(hp->next), &hvc_structs);
mutex_unlock(&hvc_structs_mutex);
/* check if we need to re-register the kernel console */
hvc_check_console(i);
return hp;
}
EXPORT_SYMBOL_GPL(hvc_alloc);
int hvc_remove(struct hvc_struct *hp)
{
unsigned long flags;
struct tty_struct *tty;
tty = tty_port_tty_get(&hp->port);
console_lock();
spin_lock_irqsave(&hp->lock, flags);
if (hp->index < MAX_NR_HVC_CONSOLES) {
vtermnos[hp->index] = -1;
cons_ops[hp->index] = NULL;
}
/* Don't whack hp->irq because tty_hangup() will need to free the irq. */
spin_unlock_irqrestore(&hp->lock, flags);
console_unlock();
/*
* We 'put' the instance that was grabbed when the kref instance
* was initialized using kref_init(). Let the last holder of this
* kref cause it to be removed, which will probably be the tty_vhangup
* below.
*/
tty_port_put(&hp->port);
/*
* This function call will auto chain call hvc_hangup.
*/
if (tty) {
tty_vhangup(tty);
tty_kref_put(tty);
}
return 0;
}
EXPORT_SYMBOL_GPL(hvc_remove);
/* Driver initialization: called as soon as someone uses hvc_alloc(). */
static int hvc_init(void)
{
struct tty_driver *drv;
int err;
/* We need more than hvc_count adapters due to hotplug additions. */
drv = alloc_tty_driver(HVC_ALLOC_TTY_ADAPTERS);
if (!drv) {
err = -ENOMEM;
goto out;
}
drv->driver_name = "hvc";
drv->name = "hvc";
drv->major = HVC_MAJOR;
drv->minor_start = HVC_MINOR;
drv->type = TTY_DRIVER_TYPE_SYSTEM;
drv->init_termios = tty_std_termios;
drv->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_RESET_TERMIOS;
tty_set_operations(drv, &hvc_ops);
/* Always start the kthread because there can be hotplug vty adapters
* added later. */
hvc_task = kthread_run(khvcd, NULL, "khvcd");
if (IS_ERR(hvc_task)) {
printk(KERN_ERR "Couldn't create kthread for console.\n");
err = PTR_ERR(hvc_task);
goto put_tty;
}
err = tty_register_driver(drv);
if (err) {
printk(KERN_ERR "Couldn't register hvc console driver\n");
goto stop_thread;
}
/*
* Make sure tty is fully registered before allowing it to be
* found by hvc_console_device.
*/
smp_mb();
hvc_driver = drv;
return 0;
stop_thread:
kthread_stop(hvc_task);
hvc_task = NULL;
put_tty:
put_tty_driver(drv);
out:
return err;
}