Commit 61a734d305 ("xen/manage: Always freeze/thaw processes when
suspend/resuming") ensured that userspace processes were always frozen
before suspending to reduce interaction issues when resuming devices.
However, freeze_processes() does not freeze kernel threads.  Freeze
kernel threads as well to prevent deadlocks with the khubd thread when
resuming devices.
This is what native suspend and resume does.
Example deadlock:
[ 7279.648010]  [<ffffffff81446bde>] ? xen_poll_irq_timeout+0x3e/0x50
[ 7279.648010]  [<ffffffff81448d60>] xen_poll_irq+0x10/0x20
[ 7279.648010]  [<ffffffff81011723>] xen_lock_spinning+0xb3/0x120
[ 7279.648010]  [<ffffffff810115d1>] __raw_callee_save_xen_lock_spinning+0x11/0x20
[ 7279.648010]  [<ffffffff815620b6>] ? usb_control_msg+0xe6/0x120
[ 7279.648010]  [<ffffffff81747e50>] ? _raw_spin_lock_irq+0x50/0x60
[ 7279.648010]  [<ffffffff8174522c>] wait_for_completion+0xac/0x160
[ 7279.648010]  [<ffffffff8109c520>] ? try_to_wake_up+0x2c0/0x2c0
[ 7279.648010]  [<ffffffff814b60f2>] dpm_wait+0x32/0x40
[ 7279.648010]  [<ffffffff814b6eb0>] device_resume+0x90/0x210
[ 7279.648010]  [<ffffffff814b7d71>] dpm_resume+0x121/0x250
[ 7279.648010]  [<ffffffff8144c570>] ? xenbus_dev_request_and_reply+0xc0/0xc0
[ 7279.648010]  [<ffffffff814b80d5>] dpm_resume_end+0x15/0x30
[ 7279.648010]  [<ffffffff81449fba>] do_suspend+0x10a/0x200
[ 7279.648010]  [<ffffffff8144a2f0>] ? xen_pre_suspend+0x20/0x20
[ 7279.648010]  [<ffffffff8144a1d0>] shutdown_handler+0x120/0x150
[ 7279.648010]  [<ffffffff8144c60f>] xenwatch_thread+0x9f/0x160
[ 7279.648010]  [<ffffffff810ac510>] ? finish_wait+0x80/0x80
[ 7279.648010]  [<ffffffff8108d189>] kthread+0xc9/0xe0
[ 7279.648010]  [<ffffffff8108d0c0>] ? flush_kthread_worker+0x80/0x80
[ 7279.648010]  [<ffffffff8175087c>] ret_from_fork+0x7c/0xb0
[ 7279.648010]  [<ffffffff8108d0c0>] ? flush_kthread_worker+0x80/0x80
[ 7441.216287] INFO: task khubd:89 blocked for more than 120 seconds.
[ 7441.219457]       Tainted: G            X 3.13.11-ckt12.kz #1
[ 7441.222176] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 7441.225827] khubd           D ffff88003f433440     0    89      2 0x00000000
[ 7441.229258]  ffff88003ceb9b98 0000000000000046 ffff88003ce83000 0000000000013440
[ 7441.232959]  ffff88003ceb9fd8 0000000000013440 ffff88003cd13000 ffff88003ce83000
[ 7441.236658]  0000000000000286 ffff88003d3e0000 ffff88003ceb9bd0 00000001001aa01e
[ 7441.240415] Call Trace:
[ 7441.241614]  [<ffffffff817442f9>] schedule+0x29/0x70
[ 7441.243930]  [<ffffffff81743406>] schedule_timeout+0x166/0x2c0
[ 7441.246681]  [<ffffffff81075b80>] ? call_timer_fn+0x110/0x110
[ 7441.249339]  [<ffffffff8174357e>] schedule_timeout_uninterruptible+0x1e/0x20
[ 7441.252644]  [<ffffffff81077710>] msleep+0x20/0x30
[ 7441.254812]  [<ffffffff81555f00>] hub_port_reset+0xf0/0x580
[ 7441.257400]  [<ffffffff81558465>] hub_port_init+0x75/0xb40
[ 7441.259981]  [<ffffffff814bb3c9>] ? update_autosuspend+0x39/0x60
[ 7441.262817]  [<ffffffff814bb4f0>] ? pm_runtime_set_autosuspend_delay+0x50/0xa0
[ 7441.266212]  [<ffffffff8155a64a>] hub_thread+0x71a/0x1750
[ 7441.268728]  [<ffffffff810ac510>] ? finish_wait+0x80/0x80
[ 7441.271272]  [<ffffffff81559f30>] ? usb_port_resume+0x670/0x670
[ 7441.274067]  [<ffffffff8108d189>] kthread+0xc9/0xe0
[ 7441.276305]  [<ffffffff8108d0c0>] ? flush_kthread_worker+0x80/0x80
[ 7441.279131]  [<ffffffff8175087c>] ret_from_fork+0x7c/0xb0
[ 7441.281659]  [<ffffffff8108d0c0>] ? flush_kthread_worker+0x80/0x80
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Cc: stable@vger.kernel.org
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
		
	
			
		
			
				
	
	
		
			352 lines
		
	
	
	
		
			7.2 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			352 lines
		
	
	
	
		
			7.2 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/*
 | 
						|
 * Handle extern requests for shutdown, reboot and sysrq
 | 
						|
 */
 | 
						|
 | 
						|
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 | 
						|
 | 
						|
#include <linux/kernel.h>
 | 
						|
#include <linux/err.h>
 | 
						|
#include <linux/slab.h>
 | 
						|
#include <linux/reboot.h>
 | 
						|
#include <linux/sysrq.h>
 | 
						|
#include <linux/stop_machine.h>
 | 
						|
#include <linux/freezer.h>
 | 
						|
#include <linux/syscore_ops.h>
 | 
						|
#include <linux/export.h>
 | 
						|
 | 
						|
#include <xen/xen.h>
 | 
						|
#include <xen/xenbus.h>
 | 
						|
#include <xen/grant_table.h>
 | 
						|
#include <xen/events.h>
 | 
						|
#include <xen/hvc-console.h>
 | 
						|
#include <xen/xen-ops.h>
 | 
						|
 | 
						|
#include <asm/xen/hypercall.h>
 | 
						|
#include <asm/xen/page.h>
 | 
						|
#include <asm/xen/hypervisor.h>
 | 
						|
 | 
						|
enum shutdown_state {
 | 
						|
	SHUTDOWN_INVALID = -1,
 | 
						|
	SHUTDOWN_POWEROFF = 0,
 | 
						|
	SHUTDOWN_SUSPEND = 2,
 | 
						|
	/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only
 | 
						|
	   report a crash, not be instructed to crash!
 | 
						|
	   HALT is the same as POWEROFF, as far as we're concerned.  The tools use
 | 
						|
	   the distinction when we return the reason code to them.  */
 | 
						|
	 SHUTDOWN_HALT = 4,
 | 
						|
};
 | 
						|
 | 
						|
/* Ignore multiple shutdown requests. */
 | 
						|
static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
 | 
						|
 | 
						|
struct suspend_info {
 | 
						|
	int cancelled;
 | 
						|
};
 | 
						|
 | 
						|
static RAW_NOTIFIER_HEAD(xen_resume_notifier);
 | 
						|
 | 
						|
void xen_resume_notifier_register(struct notifier_block *nb)
 | 
						|
{
 | 
						|
	raw_notifier_chain_register(&xen_resume_notifier, nb);
 | 
						|
}
 | 
						|
EXPORT_SYMBOL_GPL(xen_resume_notifier_register);
 | 
						|
 | 
						|
void xen_resume_notifier_unregister(struct notifier_block *nb)
 | 
						|
{
 | 
						|
	raw_notifier_chain_unregister(&xen_resume_notifier, nb);
 | 
						|
}
 | 
						|
EXPORT_SYMBOL_GPL(xen_resume_notifier_unregister);
 | 
						|
 | 
						|
#ifdef CONFIG_HIBERNATE_CALLBACKS
 | 
						|
static int xen_suspend(void *data)
 | 
						|
{
 | 
						|
	struct suspend_info *si = data;
 | 
						|
	int err;
 | 
						|
 | 
						|
	BUG_ON(!irqs_disabled());
 | 
						|
 | 
						|
	err = syscore_suspend();
 | 
						|
	if (err) {
 | 
						|
		pr_err("%s: system core suspend failed: %d\n", __func__, err);
 | 
						|
		return err;
 | 
						|
	}
 | 
						|
 | 
						|
	gnttab_suspend();
 | 
						|
	xen_arch_pre_suspend();
 | 
						|
 | 
						|
	/*
 | 
						|
	 * This hypercall returns 1 if suspend was cancelled
 | 
						|
	 * or the domain was merely checkpointed, and 0 if it
 | 
						|
	 * is resuming in a new domain.
 | 
						|
	 */
 | 
						|
	si->cancelled = HYPERVISOR_suspend(xen_pv_domain()
 | 
						|
                                           ? virt_to_mfn(xen_start_info)
 | 
						|
                                           : 0);
 | 
						|
 | 
						|
	xen_arch_post_suspend(si->cancelled);
 | 
						|
	gnttab_resume();
 | 
						|
 | 
						|
	if (!si->cancelled) {
 | 
						|
		xen_irq_resume();
 | 
						|
		xen_timer_resume();
 | 
						|
	}
 | 
						|
 | 
						|
	syscore_resume();
 | 
						|
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
static void do_suspend(void)
 | 
						|
{
 | 
						|
	int err;
 | 
						|
	struct suspend_info si;
 | 
						|
 | 
						|
	shutting_down = SHUTDOWN_SUSPEND;
 | 
						|
 | 
						|
	err = freeze_processes();
 | 
						|
	if (err) {
 | 
						|
		pr_err("%s: freeze processes failed %d\n", __func__, err);
 | 
						|
		goto out;
 | 
						|
	}
 | 
						|
 | 
						|
	err = freeze_kernel_threads();
 | 
						|
	if (err) {
 | 
						|
		pr_err("%s: freeze kernel threads failed %d\n", __func__, err);
 | 
						|
		goto out_thaw;
 | 
						|
	}
 | 
						|
 | 
						|
	err = dpm_suspend_start(PMSG_FREEZE);
 | 
						|
	if (err) {
 | 
						|
		pr_err("%s: dpm_suspend_start %d\n", __func__, err);
 | 
						|
		goto out_thaw;
 | 
						|
	}
 | 
						|
 | 
						|
	printk(KERN_DEBUG "suspending xenstore...\n");
 | 
						|
	xs_suspend();
 | 
						|
 | 
						|
	err = dpm_suspend_end(PMSG_FREEZE);
 | 
						|
	if (err) {
 | 
						|
		pr_err("dpm_suspend_end failed: %d\n", err);
 | 
						|
		si.cancelled = 0;
 | 
						|
		goto out_resume;
 | 
						|
	}
 | 
						|
 | 
						|
	si.cancelled = 1;
 | 
						|
 | 
						|
	err = stop_machine(xen_suspend, &si, cpumask_of(0));
 | 
						|
 | 
						|
	/* Resume console as early as possible. */
 | 
						|
	if (!si.cancelled)
 | 
						|
		xen_console_resume();
 | 
						|
 | 
						|
	raw_notifier_call_chain(&xen_resume_notifier, 0, NULL);
 | 
						|
 | 
						|
	dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
 | 
						|
 | 
						|
	if (err) {
 | 
						|
		pr_err("failed to start xen_suspend: %d\n", err);
 | 
						|
		si.cancelled = 1;
 | 
						|
	}
 | 
						|
 | 
						|
out_resume:
 | 
						|
	if (!si.cancelled) {
 | 
						|
		xen_arch_resume();
 | 
						|
		xs_resume();
 | 
						|
	} else
 | 
						|
		xs_suspend_cancel();
 | 
						|
 | 
						|
	dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
 | 
						|
 | 
						|
out_thaw:
 | 
						|
	thaw_processes();
 | 
						|
out:
 | 
						|
	shutting_down = SHUTDOWN_INVALID;
 | 
						|
}
 | 
						|
#endif	/* CONFIG_HIBERNATE_CALLBACKS */
 | 
						|
 | 
						|
struct shutdown_handler {
 | 
						|
	const char *command;
 | 
						|
	void (*cb)(void);
 | 
						|
};
 | 
						|
 | 
						|
static int poweroff_nb(struct notifier_block *cb, unsigned long code, void *unused)
 | 
						|
{
 | 
						|
	switch (code) {
 | 
						|
	case SYS_DOWN:
 | 
						|
	case SYS_HALT:
 | 
						|
	case SYS_POWER_OFF:
 | 
						|
		shutting_down = SHUTDOWN_POWEROFF;
 | 
						|
	default:
 | 
						|
		break;
 | 
						|
	}
 | 
						|
	return NOTIFY_DONE;
 | 
						|
}
 | 
						|
static void do_poweroff(void)
 | 
						|
{
 | 
						|
	switch (system_state) {
 | 
						|
	case SYSTEM_BOOTING:
 | 
						|
		orderly_poweroff(true);
 | 
						|
		break;
 | 
						|
	case SYSTEM_RUNNING:
 | 
						|
		orderly_poweroff(false);
 | 
						|
		break;
 | 
						|
	default:
 | 
						|
		/* Don't do it when we are halting/rebooting. */
 | 
						|
		pr_info("Ignoring Xen toolstack shutdown.\n");
 | 
						|
		break;
 | 
						|
	}
 | 
						|
}
 | 
						|
 | 
						|
static void do_reboot(void)
 | 
						|
{
 | 
						|
	shutting_down = SHUTDOWN_POWEROFF; /* ? */
 | 
						|
	ctrl_alt_del();
 | 
						|
}
 | 
						|
 | 
						|
static void shutdown_handler(struct xenbus_watch *watch,
 | 
						|
			     const char **vec, unsigned int len)
 | 
						|
{
 | 
						|
	char *str;
 | 
						|
	struct xenbus_transaction xbt;
 | 
						|
	int err;
 | 
						|
	static struct shutdown_handler handlers[] = {
 | 
						|
		{ "poweroff",	do_poweroff },
 | 
						|
		{ "halt",	do_poweroff },
 | 
						|
		{ "reboot",	do_reboot   },
 | 
						|
#ifdef CONFIG_HIBERNATE_CALLBACKS
 | 
						|
		{ "suspend",	do_suspend  },
 | 
						|
#endif
 | 
						|
		{NULL, NULL},
 | 
						|
	};
 | 
						|
	static struct shutdown_handler *handler;
 | 
						|
 | 
						|
	if (shutting_down != SHUTDOWN_INVALID)
 | 
						|
		return;
 | 
						|
 | 
						|
 again:
 | 
						|
	err = xenbus_transaction_start(&xbt);
 | 
						|
	if (err)
 | 
						|
		return;
 | 
						|
 | 
						|
	str = (char *)xenbus_read(xbt, "control", "shutdown", NULL);
 | 
						|
	/* Ignore read errors and empty reads. */
 | 
						|
	if (XENBUS_IS_ERR_READ(str)) {
 | 
						|
		xenbus_transaction_end(xbt, 1);
 | 
						|
		return;
 | 
						|
	}
 | 
						|
 | 
						|
	for (handler = &handlers[0]; handler->command; handler++) {
 | 
						|
		if (strcmp(str, handler->command) == 0)
 | 
						|
			break;
 | 
						|
	}
 | 
						|
 | 
						|
	/* Only acknowledge commands which we are prepared to handle. */
 | 
						|
	if (handler->cb)
 | 
						|
		xenbus_write(xbt, "control", "shutdown", "");
 | 
						|
 | 
						|
	err = xenbus_transaction_end(xbt, 0);
 | 
						|
	if (err == -EAGAIN) {
 | 
						|
		kfree(str);
 | 
						|
		goto again;
 | 
						|
	}
 | 
						|
 | 
						|
	if (handler->cb) {
 | 
						|
		handler->cb();
 | 
						|
	} else {
 | 
						|
		pr_info("Ignoring shutdown request: %s\n", str);
 | 
						|
		shutting_down = SHUTDOWN_INVALID;
 | 
						|
	}
 | 
						|
 | 
						|
	kfree(str);
 | 
						|
}
 | 
						|
 | 
						|
#ifdef CONFIG_MAGIC_SYSRQ
 | 
						|
static void sysrq_handler(struct xenbus_watch *watch, const char **vec,
 | 
						|
			  unsigned int len)
 | 
						|
{
 | 
						|
	char sysrq_key = '\0';
 | 
						|
	struct xenbus_transaction xbt;
 | 
						|
	int err;
 | 
						|
 | 
						|
 again:
 | 
						|
	err = xenbus_transaction_start(&xbt);
 | 
						|
	if (err)
 | 
						|
		return;
 | 
						|
	if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) {
 | 
						|
		pr_err("Unable to read sysrq code in control/sysrq\n");
 | 
						|
		xenbus_transaction_end(xbt, 1);
 | 
						|
		return;
 | 
						|
	}
 | 
						|
 | 
						|
	if (sysrq_key != '\0')
 | 
						|
		xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
 | 
						|
 | 
						|
	err = xenbus_transaction_end(xbt, 0);
 | 
						|
	if (err == -EAGAIN)
 | 
						|
		goto again;
 | 
						|
 | 
						|
	if (sysrq_key != '\0')
 | 
						|
		handle_sysrq(sysrq_key);
 | 
						|
}
 | 
						|
 | 
						|
static struct xenbus_watch sysrq_watch = {
 | 
						|
	.node = "control/sysrq",
 | 
						|
	.callback = sysrq_handler
 | 
						|
};
 | 
						|
#endif
 | 
						|
 | 
						|
static struct xenbus_watch shutdown_watch = {
 | 
						|
	.node = "control/shutdown",
 | 
						|
	.callback = shutdown_handler
 | 
						|
};
 | 
						|
 | 
						|
static struct notifier_block xen_reboot_nb = {
 | 
						|
	.notifier_call = poweroff_nb,
 | 
						|
};
 | 
						|
 | 
						|
static int setup_shutdown_watcher(void)
 | 
						|
{
 | 
						|
	int err;
 | 
						|
 | 
						|
	err = register_xenbus_watch(&shutdown_watch);
 | 
						|
	if (err) {
 | 
						|
		pr_err("Failed to set shutdown watcher\n");
 | 
						|
		return err;
 | 
						|
	}
 | 
						|
 | 
						|
 | 
						|
#ifdef CONFIG_MAGIC_SYSRQ
 | 
						|
	err = register_xenbus_watch(&sysrq_watch);
 | 
						|
	if (err) {
 | 
						|
		pr_err("Failed to set sysrq watcher\n");
 | 
						|
		return err;
 | 
						|
	}
 | 
						|
#endif
 | 
						|
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
 | 
						|
static int shutdown_event(struct notifier_block *notifier,
 | 
						|
			  unsigned long event,
 | 
						|
			  void *data)
 | 
						|
{
 | 
						|
	setup_shutdown_watcher();
 | 
						|
	return NOTIFY_DONE;
 | 
						|
}
 | 
						|
 | 
						|
int xen_setup_shutdown_event(void)
 | 
						|
{
 | 
						|
	static struct notifier_block xenstore_notifier = {
 | 
						|
		.notifier_call = shutdown_event
 | 
						|
	};
 | 
						|
 | 
						|
	if (!xen_domain())
 | 
						|
		return -ENODEV;
 | 
						|
	register_xenstore_notifier(&xenstore_notifier);
 | 
						|
	register_reboot_notifier(&xen_reboot_nb);
 | 
						|
 | 
						|
	return 0;
 | 
						|
}
 | 
						|
EXPORT_SYMBOL_GPL(xen_setup_shutdown_event);
 | 
						|
 | 
						|
subsys_initcall(xen_setup_shutdown_event);
 |