linux/drivers/xen/manage.c

340 lines
6.8 KiB
C
Raw Normal View History

/*
* Handle extern requests for shutdown, reboot and sysrq
*/
#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 08:04:11 +00:00
#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/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;
unsigned long arg; /* extra hypercall argument */
void (*pre)(void);
void (*post)(int cancelled);
};
static void xen_hvm_post_suspend(int cancelled)
{
xen_arch_hvm_post_suspend(cancelled);
gnttab_resume();
}
static void xen_pre_suspend(void)
{
xen_mm_pin_all();
gnttab_suspend();
xen_arch_pre_suspend();
}
static void xen_post_suspend(int cancelled)
{
xen_arch_post_suspend(cancelled);
gnttab_resume();
xen_mm_unpin_all();
}
#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) {
printk(KERN_ERR "xen_suspend: system core suspend failed: %d\n",
err);
return err;
}
if (si->pre)
si->pre();
/*
* 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(si->arg);
if (si->post)
si->post(si->cancelled);
if (!si->cancelled) {
xen_irq_resume();
xen_console_resume();
xen_timer_resume();
}
syscore_resume();
return 0;
}
static void do_suspend(void)
{
int err;
struct suspend_info si;
shutting_down = SHUTDOWN_SUSPEND;
#ifdef CONFIG_PREEMPT
/* If the kernel is preemptible, we need to freeze all the processes
to prevent them from being in the middle of a pagetable update
during suspend. */
err = freeze_processes();
if (err) {
printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
goto out;
}
#endif
err = dpm_suspend_start(PMSG_FREEZE);
if (err) {
printk(KERN_ERR "xen suspend: dpm_suspend_start %d\n", 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>
2012-01-29 19:38:29 +00:00
err = dpm_suspend_end(PMSG_FREEZE);
if (err) {
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>
2012-01-29 19:38:29 +00:00
printk(KERN_ERR "dpm_suspend_end failed: %d\n", err);
si.cancelled = 0;
goto out_resume;
}
si.cancelled = 1;
if (xen_hvm_domain()) {
si.arg = 0UL;
si.pre = NULL;
si.post = &xen_hvm_post_suspend;
} else {
si.arg = virt_to_mfn(xen_start_info);
si.pre = &xen_pre_suspend;
si.post = &xen_post_suspend;
}
err = stop_machine(xen_suspend, &si, cpumask_of(0));
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>
2012-01-29 19:38:29 +00:00
dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
if (err) {
printk(KERN_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);
/* Make sure timer events get retriggered on all CPUs */
clock_was_set();
out_thaw:
#ifdef CONFIG_PREEMPT
thaw_processes();
out:
#endif
shutting_down = SHUTDOWN_INVALID;
}
#endif /* CONFIG_HIBERNATE_CALLBACKS */
struct shutdown_handler {
const char *command;
void (*cb)(void);
};
static void do_poweroff(void)
{
shutting_down = SHUTDOWN_POWEROFF;
orderly_poweroff(false);
}
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 {
printk(KERN_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)) {
printk(KERN_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 int setup_shutdown_watcher(void)
{
int err;
err = register_xenbus_watch(&shutdown_watch);
if (err) {
printk(KERN_ERR "Failed to set shutdown watcher\n");
return err;
}
#ifdef CONFIG_MAGIC_SYSRQ
err = register_xenbus_watch(&sysrq_watch);
if (err) {
printk(KERN_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);
return 0;
}
EXPORT_SYMBOL_GPL(xen_setup_shutdown_event);
subsys_initcall(xen_setup_shutdown_event);