linux/drivers/xen/manage.c

391 lines
8.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#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/page.h>
#include <xen/xen-ops.h>
#include <asm/xen/hypercall.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/time: do not decrease steal time after live migration on xen After guest live migration on xen, steal time in /proc/stat (cpustat[CPUTIME_STEAL]) might decrease because steal returned by xen_steal_lock() might be less than this_rq()->prev_steal_time which is derived from previous return value of xen_steal_clock(). For instance, steal time of each vcpu is 335 before live migration. cpu 198 0 368 200064 1962 0 0 1340 0 0 cpu0 38 0 81 50063 492 0 0 335 0 0 cpu1 65 0 97 49763 634 0 0 335 0 0 cpu2 38 0 81 50098 462 0 0 335 0 0 cpu3 56 0 107 50138 374 0 0 335 0 0 After live migration, steal time is reduced to 312. cpu 200 0 370 200330 1971 0 0 1248 0 0 cpu0 38 0 82 50123 500 0 0 312 0 0 cpu1 65 0 97 49832 634 0 0 312 0 0 cpu2 39 0 82 50167 462 0 0 312 0 0 cpu3 56 0 107 50207 374 0 0 312 0 0 Since runstate times are cumulative and cleared during xen live migration by xen hypervisor, the idea of this patch is to accumulate runstate times to global percpu variables before live migration suspend. Once guest VM is resumed, xen_get_runstate_snapshot_cpu() would always return the sum of new runstate times and previously accumulated times stored in global percpu variables. Comment above HYPERVISOR_suspend() has been removed as it is inaccurate: the call can return an error code (e.g., possibly -EPERM in the future). Similar and more severe issue would impact prior linux 4.8-4.10 as discussed by Michael Las at https://0xstubs.org/debugging-a-flaky-cpu-steal-time-counter-on-a-paravirtualized-xen-guest, which would overflow steal time and lead to 100% st usage in top command for linux 4.8-4.10. A backport of this patch would fix that issue. [boris: added linux/slab.h to driver/xen/time.c, slightly reformatted commit message] References: https://0xstubs.org/debugging-a-flaky-cpu-steal-time-counter-on-a-paravirtualized-xen-guest Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2017-11-01 09:46:33 +08:00
xen_manage_runstate_time(-1);
xen_arch_pre_suspend();
si->cancelled = HYPERVISOR_suspend(xen_pv_domain()
? virt_to_gfn(xen_start_info)
: 0);
xen_arch_post_suspend(si->cancelled);
xen/time: do not decrease steal time after live migration on xen After guest live migration on xen, steal time in /proc/stat (cpustat[CPUTIME_STEAL]) might decrease because steal returned by xen_steal_lock() might be less than this_rq()->prev_steal_time which is derived from previous return value of xen_steal_clock(). For instance, steal time of each vcpu is 335 before live migration. cpu 198 0 368 200064 1962 0 0 1340 0 0 cpu0 38 0 81 50063 492 0 0 335 0 0 cpu1 65 0 97 49763 634 0 0 335 0 0 cpu2 38 0 81 50098 462 0 0 335 0 0 cpu3 56 0 107 50138 374 0 0 335 0 0 After live migration, steal time is reduced to 312. cpu 200 0 370 200330 1971 0 0 1248 0 0 cpu0 38 0 82 50123 500 0 0 312 0 0 cpu1 65 0 97 49832 634 0 0 312 0 0 cpu2 39 0 82 50167 462 0 0 312 0 0 cpu3 56 0 107 50207 374 0 0 312 0 0 Since runstate times are cumulative and cleared during xen live migration by xen hypervisor, the idea of this patch is to accumulate runstate times to global percpu variables before live migration suspend. Once guest VM is resumed, xen_get_runstate_snapshot_cpu() would always return the sum of new runstate times and previously accumulated times stored in global percpu variables. Comment above HYPERVISOR_suspend() has been removed as it is inaccurate: the call can return an error code (e.g., possibly -EPERM in the future). Similar and more severe issue would impact prior linux 4.8-4.10 as discussed by Michael Las at https://0xstubs.org/debugging-a-flaky-cpu-steal-time-counter-on-a-paravirtualized-xen-guest, which would overflow steal time and lead to 100% st usage in top command for linux 4.8-4.10. A backport of this patch would fix that issue. [boris: added linux/slab.h to driver/xen/time.c, slightly reformatted commit message] References: https://0xstubs.org/debugging-a-flaky-cpu-steal-time-counter-on-a-paravirtualized-xen-guest Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
2017-11-01 09:46:33 +08:00
xen_manage_runstate_time(si->cancelled ? 1 : 0);
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) {
xen/manage: Fix USB interaction issues when resuming Commit 61a734d305e1 ("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>
2015-01-19 21:19:38 +08:00
pr_err("%s: freeze processes failed %d\n", __func__, err);
goto out;
}
xen/manage: Fix USB interaction issues when resuming Commit 61a734d305e1 ("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>
2015-01-19 21:19:38 +08:00
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();
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 03:38:29 +08:00
err = dpm_suspend_end(PMSG_FREEZE);
if (err) {
pr_err("dpm_suspend_end failed: %d\n", err);
si.cancelled = 0;
goto out_resume;
}
xen_arch_suspend();
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);
xen_arch_resume();
PM / Sleep: Introduce "late suspend" and "early resume" of devices The current device suspend/resume phases during system-wide power transitions appear to be insufficient for some platforms that want to use the same callback routines for saving device states and related operations during runtime suspend/resume as well as during system suspend/resume. In principle, they could point their .suspend_noirq() and .resume_noirq() to the same callback routines as their .runtime_suspend() and .runtime_resume(), respectively, but at least some of them require device interrupts to be enabled while the code in those routines is running. It also makes sense to have device suspend-resume callbacks that will be executed with runtime PM disabled and with device interrupts enabled in case someone needs to run some special code in that context during system-wide power transitions. Apart from this, .suspend_noirq() and .resume_noirq() were introduced as a workaround for drivers using shared interrupts and failing to prevent their interrupt handlers from accessing suspended hardware. It appears to be better not to use them for other porposes, or we may have to deal with some serious confusion (which seems to be happening already). For the above reasons, introduce new device suspend/resume phases, "late suspend" and "early resume" (and analogously for hibernation) whose callback will be executed with runtime PM disabled and with device interrupts enabled and whose callback pointers generally may point to runtime suspend/resume routines. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Reviewed-by: Kevin Hilman <khilman@ti.com>
2012-01-30 03:38:29 +08:00
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)
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 {
#define SHUTDOWN_CMD_SIZE 11
const char command[SHUTDOWN_CMD_SIZE];
bool flag;
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;
break;
default:
break;
}
return NOTIFY_DONE;
}
static void do_poweroff(void)
{
switch (system_state) {
case SYSTEM_BOOTING:
case SYSTEM_SCHEDULING:
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; /* ? */
orderly_reboot();
}
static struct shutdown_handler shutdown_handlers[] = {
{ "poweroff", true, do_poweroff },
{ "halt", false, do_poweroff },
{ "reboot", true, do_reboot },
#ifdef CONFIG_HIBERNATE_CALLBACKS
{ "suspend", true, do_suspend },
#endif
};
static void shutdown_handler(struct xenbus_watch *watch,
const char *path, const char *token)
{
char *str;
struct xenbus_transaction xbt;
int err;
int idx;
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 (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
if (strcmp(str, shutdown_handlers[idx].command) == 0)
break;
}
/* Only acknowledge commands which we are prepared to handle. */
if (idx < ARRAY_SIZE(shutdown_handlers))
xenbus_write(xbt, "control", "shutdown", "");
err = xenbus_transaction_end(xbt, 0);
if (err == -EAGAIN) {
kfree(str);
goto again;
}
if (idx < ARRAY_SIZE(shutdown_handlers)) {
shutdown_handlers[idx].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 *path,
const char *token)
{
char sysrq_key = '\0';
struct xenbus_transaction xbt;
int err;
again:
err = xenbus_transaction_start(&xbt);
if (err)
return;
err = xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key);
if (err < 0) {
/*
* The Xenstore watch fires directly after registering it and
* after a suspend/resume cycle. So ENOENT is no error but
* might happen in those cases. ERANGE is observed when we get
* an empty value (''), this happens when we acknowledge the
* request by writing '\0' below.
*/
if (err != -ENOENT && err != -ERANGE)
pr_err("Error %d reading sysrq code in control/sysrq\n",
err);
xenbus_transaction_end(xbt, 1);
return;
}
if (sysrq_key != '\0') {
err = xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
if (err) {
pr_err("%s: Error %d writing sysrq in control/sysrq\n",
__func__, err);
xenbus_transaction_end(xbt, 1);
return;
}
}
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;
int idx;
#define FEATURE_PATH_SIZE (SHUTDOWN_CMD_SIZE + sizeof("feature-"))
char node[FEATURE_PATH_SIZE];
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
for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
if (!shutdown_handlers[idx].flag)
continue;
snprintf(node, FEATURE_PATH_SIZE, "feature-%s",
shutdown_handlers[idx].command);
err = xenbus_printf(XBT_NIL, "control", node, "%u", 1);
if (err) {
pr_err("%s: Error %d writing %s\n", __func__,
err, node);
return err;
}
}
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);