Merge branch 'for-linus' of git://xenbits.xen.org/people/sstabellini/linux-pvhvm

* 'for-linus' of git://xenbits.xen.org/people/sstabellini/linux-pvhvm:
  xen: suspend: remove xen_hvm_suspend
  xen: suspend: pull pre/post suspend hooks out into suspend_info
  xen: suspend: move arch specific pre/post suspend hooks into generic hooks
  xen: suspend: refactor non-arch specific pre/post suspend hooks
  xen: suspend: add "arch" to pre/post suspend hooks
  xen: suspend: pass extra hypercall argument via suspend_info struct
  xen: suspend: refactor cancellation flag into a structure
  xen: suspend: use HYPERVISOR_suspend for PVHVM case instead of open coding
  xen: switch to new schedop hypercall by default.
  xen: use new schedop interface for suspend
  xen: do not respond to unknown xenstore control requests
  xen: fix compile issue if XEN is enabled but XEN_PVHVM is disabled
  xen: PV on HVM: support PV spinlocks and IPIs
  xen: make the ballon driver work for hvm domains
  xen-blkfront: handle Xen major numbers other than XENVBD
  xen: do not use xen_info on HVM, set pv_info name to "Xen HVM"
  xen: no need to delay xen_setup_shutdown_event for hvm guests anymore
This commit is contained in:
Linus Torvalds 2011-03-15 10:59:09 -07:00
commit 76ca078328
13 changed files with 260 additions and 104 deletions

View File

@ -37,19 +37,14 @@ xen_mm_unpin_all(void)
/* nothing */
}
void xen_pre_device_suspend(void)
void
xen_arch_pre_suspend()
{
/* nothing */
}
void
xen_pre_suspend()
{
/* nothing */
}
void
xen_post_suspend(int suspend_cancelled)
xen_arch_post_suspend(int suspend_cancelled)
{
if (suspend_cancelled)
return;

View File

@ -287,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set)
static inline int
HYPERVISOR_sched_op(int cmd, void *arg)
{
return _hypercall2(int, sched_op_new, cmd, arg);
return _hypercall2(int, sched_op, cmd, arg);
}
static inline long
@ -422,10 +422,17 @@ HYPERVISOR_set_segment_base(int reg, unsigned long value)
#endif
static inline int
HYPERVISOR_suspend(unsigned long srec)
HYPERVISOR_suspend(unsigned long start_info_mfn)
{
return _hypercall3(int, sched_op, SCHEDOP_shutdown,
SHUTDOWN_suspend, srec);
struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
/*
* For a PV guest the tools require that the start_info mfn be
* present in rdx/edx when the hypercall is made. Per the
* hypercall calling convention this is the third hypercall
* argument, which is start_info_mfn here.
*/
return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn);
}
static inline int

View File

@ -1284,8 +1284,7 @@ static int init_hvm_pv_info(int *major, int *minor)
xen_setup_features();
pv_info = xen_info;
pv_info.kernel_rpl = 0;
pv_info.name = "Xen HVM";
xen_domain_type = XEN_HVM_DOMAIN;
@ -1331,6 +1330,8 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
switch (action) {
case CPU_UP_PREPARE:
per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
if (xen_have_vector_callback)
xen_init_lock_cpu(cpu);
break;
default:
break;
@ -1355,6 +1356,7 @@ static void __init xen_hvm_guest_init(void)
if (xen_feature(XENFEAT_hvm_callback_vector))
xen_have_vector_callback = 1;
xen_hvm_smp_init();
register_cpu_notifier(&xen_hvm_cpu_notifier);
xen_unplug_emulated_devices();
have_vcpu_info_placement = 0;

View File

@ -509,3 +509,41 @@ void __init xen_smp_init(void)
xen_fill_possible_map();
xen_init_spinlocks();
}
static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
{
native_smp_prepare_cpus(max_cpus);
WARN_ON(xen_smp_intr_init(0));
if (!xen_have_vector_callback)
return;
xen_init_lock_cpu(0);
xen_init_spinlocks();
}
static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
{
int rc;
rc = native_cpu_up(cpu);
WARN_ON (xen_smp_intr_init(cpu));
return rc;
}
static void xen_hvm_cpu_die(unsigned int cpu)
{
unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
native_cpu_die(cpu);
}
void __init xen_hvm_smp_init(void)
{
smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
smp_ops.cpu_up = xen_hvm_cpu_up;
smp_ops.cpu_die = xen_hvm_cpu_die;
smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
}

View File

@ -12,7 +12,7 @@
#include "xen-ops.h"
#include "mmu.h"
void xen_pre_suspend(void)
void xen_arch_pre_suspend(void)
{
xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
xen_start_info->console.domU.mfn =
@ -26,8 +26,9 @@ void xen_pre_suspend(void)
BUG();
}
void xen_hvm_post_suspend(int suspend_cancelled)
void xen_arch_hvm_post_suspend(int suspend_cancelled)
{
#ifdef CONFIG_XEN_PVHVM
int cpu;
xen_hvm_init_shared_info();
xen_callback_vector();
@ -37,9 +38,10 @@ void xen_hvm_post_suspend(int suspend_cancelled)
xen_setup_runstate_info(cpu);
}
}
#endif
}
void xen_post_suspend(int suspend_cancelled)
void xen_arch_post_suspend(int suspend_cancelled)
{
xen_build_mfn_list_list();

View File

@ -64,10 +64,12 @@ void xen_setup_vcpu_info_placement(void);
#ifdef CONFIG_SMP
void xen_smp_init(void);
void __init xen_hvm_smp_init(void);
extern cpumask_var_t xen_cpu_initialized_map;
#else
static inline void xen_smp_init(void) {}
static inline void xen_hvm_smp_init(void) {}
#endif
#ifdef CONFIG_PARAVIRT_SPINLOCKS

View File

@ -120,6 +120,10 @@ static DEFINE_SPINLOCK(minor_lock);
#define EXTENDED (1<<EXT_SHIFT)
#define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
#define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
#define EMULATED_HD_DISK_MINOR_OFFSET (0)
#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
#define DEV_NAME "xvd" /* name in /dev */
@ -434,6 +438,65 @@ static void xlvbd_flush(struct blkfront_info *info)
info->feature_flush ? "enabled" : "disabled");
}
static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
{
int major;
major = BLKIF_MAJOR(vdevice);
*minor = BLKIF_MINOR(vdevice);
switch (major) {
case XEN_IDE0_MAJOR:
*offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET;
*minor = ((*minor / 64) * PARTS_PER_DISK) +
EMULATED_HD_DISK_MINOR_OFFSET;
break;
case XEN_IDE1_MAJOR:
*offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET;
*minor = (((*minor / 64) + 2) * PARTS_PER_DISK) +
EMULATED_HD_DISK_MINOR_OFFSET;
break;
case XEN_SCSI_DISK0_MAJOR:
*offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET;
*minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET;
break;
case XEN_SCSI_DISK1_MAJOR:
case XEN_SCSI_DISK2_MAJOR:
case XEN_SCSI_DISK3_MAJOR:
case XEN_SCSI_DISK4_MAJOR:
case XEN_SCSI_DISK5_MAJOR:
case XEN_SCSI_DISK6_MAJOR:
case XEN_SCSI_DISK7_MAJOR:
*offset = (*minor / PARTS_PER_DISK) +
((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) +
EMULATED_SD_DISK_NAME_OFFSET;
*minor = *minor +
((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) +
EMULATED_SD_DISK_MINOR_OFFSET;
break;
case XEN_SCSI_DISK8_MAJOR:
case XEN_SCSI_DISK9_MAJOR:
case XEN_SCSI_DISK10_MAJOR:
case XEN_SCSI_DISK11_MAJOR:
case XEN_SCSI_DISK12_MAJOR:
case XEN_SCSI_DISK13_MAJOR:
case XEN_SCSI_DISK14_MAJOR:
case XEN_SCSI_DISK15_MAJOR:
*offset = (*minor / PARTS_PER_DISK) +
((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) +
EMULATED_SD_DISK_NAME_OFFSET;
*minor = *minor +
((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) +
EMULATED_SD_DISK_MINOR_OFFSET;
break;
case XENVBD_MAJOR:
*offset = *minor / PARTS_PER_DISK;
break;
default:
printk(KERN_WARNING "blkfront: your disk configuration is "
"incorrect, please use an xvd device instead\n");
return -ENODEV;
}
return 0;
}
static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
struct blkfront_info *info,
@ -441,7 +504,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
{
struct gendisk *gd;
int nr_minors = 1;
int err = -ENODEV;
int err;
unsigned int offset;
int minor;
int nr_parts;
@ -456,12 +519,20 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
}
if (!VDEV_IS_EXTENDED(info->vdevice)) {
minor = BLKIF_MINOR(info->vdevice);
err = xen_translate_vdev(info->vdevice, &minor, &offset);
if (err)
return err;
nr_parts = PARTS_PER_DISK;
} else {
minor = BLKIF_MINOR_EXT(info->vdevice);
nr_parts = PARTS_PER_EXT_DISK;
offset = minor / nr_parts;
if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
"emulated IDE disks,\n\t choose an xvd device name"
"from xvde on\n", info->vdevice);
}
err = -ENODEV;
if ((minor % nr_parts) == 0)
nr_minors = nr_parts;
@ -475,8 +546,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
if (gd == NULL)
goto release;
offset = minor / nr_parts;
if (nr_minors > 1) {
if (offset < 26)
sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset);

View File

@ -232,7 +232,7 @@ static int increase_reservation(unsigned long nr_pages)
set_phys_to_machine(pfn, frame_list[i]);
/* Link back into the page tables if not highmem. */
if (pfn < max_low_pfn) {
if (!xen_hvm_domain() && pfn < max_low_pfn) {
int ret;
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
@ -280,7 +280,7 @@ static int decrease_reservation(unsigned long nr_pages)
scrub_page(page);
if (!PageHighMem(page)) {
if (!xen_hvm_domain() && !PageHighMem(page)) {
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
__pte_ma(0), 0);
@ -392,15 +392,19 @@ static struct notifier_block xenstore_notifier;
static int __init balloon_init(void)
{
unsigned long pfn, extra_pfn_end;
unsigned long pfn, nr_pages, extra_pfn_end;
struct page *page;
if (!xen_pv_domain())
if (!xen_domain())
return -ENODEV;
pr_info("xen_balloon: Initialising balloon driver.\n");
balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
if (xen_pv_domain())
nr_pages = xen_start_info->nr_pages;
else
nr_pages = max_pfn;
balloon_stats.current_pages = min(nr_pages, max_pfn);
balloon_stats.target_pages = balloon_stats.current_pages;
balloon_stats.balloon_low = 0;
balloon_stats.balloon_high = 0;

View File

@ -34,42 +34,38 @@ enum shutdown_state {
/* Ignore multiple shutdown requests. */
static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
#ifdef CONFIG_PM_SLEEP
static int xen_hvm_suspend(void *data)
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)
{
int err;
struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
int *cancelled = data;
BUG_ON(!irqs_disabled());
err = sysdev_suspend(PMSG_SUSPEND);
if (err) {
printk(KERN_ERR "xen_hvm_suspend: sysdev_suspend failed: %d\n",
err);
return err;
}
*cancelled = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
xen_hvm_post_suspend(*cancelled);
xen_arch_hvm_post_suspend(cancelled);
gnttab_resume();
if (!*cancelled) {
xen_irq_resume();
xen_console_resume();
xen_timer_resume();
}
sysdev_resume();
return 0;
}
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_PM_SLEEP
static int xen_suspend(void *data)
{
struct suspend_info *si = data;
int err;
int *cancelled = data;
BUG_ON(!irqs_disabled());
@ -80,22 +76,20 @@ static int xen_suspend(void *data)
return err;
}
xen_mm_pin_all();
gnttab_suspend();
xen_pre_suspend();
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.
*/
*cancelled = HYPERVISOR_suspend(virt_to_mfn(xen_start_info));
si->cancelled = HYPERVISOR_suspend(si->arg);
xen_post_suspend(*cancelled);
gnttab_resume();
xen_mm_unpin_all();
if (si->post)
si->post(si->cancelled);
if (!*cancelled) {
if (!si->cancelled) {
xen_irq_resume();
xen_console_resume();
xen_timer_resume();
@ -109,7 +103,7 @@ static int xen_suspend(void *data)
static void do_suspend(void)
{
int err;
int cancelled = 1;
struct suspend_info si;
shutting_down = SHUTDOWN_SUSPEND;
@ -139,20 +133,29 @@ static void do_suspend(void)
goto out_resume;
}
if (xen_hvm_domain())
err = stop_machine(xen_hvm_suspend, &cancelled, cpumask_of(0));
else
err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
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));
dpm_resume_noirq(PMSG_RESUME);
if (err) {
printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
cancelled = 1;
si.cancelled = 1;
}
out_resume:
if (!cancelled) {
if (!si.cancelled) {
xen_arch_resume();
xs_resume();
} else
@ -172,12 +175,39 @@ out:
}
#endif /* CONFIG_PM_SLEEP */
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_PM_SLEEP
{ "suspend", do_suspend },
#endif
{NULL, NULL},
};
static struct shutdown_handler *handler;
if (shutting_down != SHUTDOWN_INVALID)
return;
@ -194,6 +224,13 @@ static void shutdown_handler(struct xenbus_watch *watch,
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);
@ -202,17 +239,8 @@ static void shutdown_handler(struct xenbus_watch *watch,
goto again;
}
if (strcmp(str, "poweroff") == 0 ||
strcmp(str, "halt") == 0) {
shutting_down = SHUTDOWN_POWEROFF;
orderly_poweroff(false);
} else if (strcmp(str, "reboot") == 0) {
shutting_down = SHUTDOWN_POWEROFF; /* ? */
ctrl_alt_del();
#ifdef CONFIG_PM_SLEEP
} else if (strcmp(str, "suspend") == 0) {
do_suspend();
#endif
if (handler->cb) {
handler->cb();
} else {
printk(KERN_INFO "Ignoring shutdown request: %s\n", str);
shutting_down = SHUTDOWN_INVALID;
@ -291,27 +319,18 @@ static int shutdown_event(struct notifier_block *notifier,
return NOTIFY_DONE;
}
static int __init __setup_shutdown_event(void)
{
/* Delay initialization in the PV on HVM case */
if (xen_hvm_domain())
return 0;
if (!xen_pv_domain())
return -ENODEV;
return xen_setup_shutdown_event();
}
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(__setup_shutdown_event);
subsys_initcall(xen_setup_shutdown_event);

View File

@ -156,9 +156,6 @@ static int __devinit platform_pci_init(struct pci_dev *pdev,
if (ret)
goto out;
xenbus_probe(NULL);
ret = xen_setup_shutdown_event();
if (ret)
goto out;
return 0;
out:

View File

@ -97,4 +97,25 @@ DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response);
#define VDISK_REMOVABLE 0x2
#define VDISK_READONLY 0x4
/* Xen-defined major numbers for virtual disks, they look strangely
* familiar */
#define XEN_IDE0_MAJOR 3
#define XEN_IDE1_MAJOR 22
#define XEN_SCSI_DISK0_MAJOR 8
#define XEN_SCSI_DISK1_MAJOR 65
#define XEN_SCSI_DISK2_MAJOR 66
#define XEN_SCSI_DISK3_MAJOR 67
#define XEN_SCSI_DISK4_MAJOR 68
#define XEN_SCSI_DISK5_MAJOR 69
#define XEN_SCSI_DISK6_MAJOR 70
#define XEN_SCSI_DISK7_MAJOR 71
#define XEN_SCSI_DISK8_MAJOR 128
#define XEN_SCSI_DISK9_MAJOR 129
#define XEN_SCSI_DISK10_MAJOR 130
#define XEN_SCSI_DISK11_MAJOR 131
#define XEN_SCSI_DISK12_MAJOR 132
#define XEN_SCSI_DISK13_MAJOR 133
#define XEN_SCSI_DISK14_MAJOR 134
#define XEN_SCSI_DISK15_MAJOR 135
#endif /* __XEN_PUBLIC_IO_BLKIF_H__ */

View File

@ -30,7 +30,7 @@
#define __HYPERVISOR_stack_switch 3
#define __HYPERVISOR_set_callbacks 4
#define __HYPERVISOR_fpu_taskswitch 5
#define __HYPERVISOR_sched_op 6
#define __HYPERVISOR_sched_op_compat 6
#define __HYPERVISOR_dom0_op 7
#define __HYPERVISOR_set_debugreg 8
#define __HYPERVISOR_get_debugreg 9
@ -52,7 +52,7 @@
#define __HYPERVISOR_mmuext_op 26
#define __HYPERVISOR_acm_op 27
#define __HYPERVISOR_nmi_op 28
#define __HYPERVISOR_sched_op_new 29
#define __HYPERVISOR_sched_op 29
#define __HYPERVISOR_callback_op 30
#define __HYPERVISOR_xenoprof_op 31
#define __HYPERVISOR_event_channel_op 32

View File

@ -5,9 +5,9 @@
DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
void xen_pre_suspend(void);
void xen_post_suspend(int suspend_cancelled);
void xen_hvm_post_suspend(int suspend_cancelled);
void xen_arch_pre_suspend(void);
void xen_arch_post_suspend(int suspend_cancelled);
void xen_arch_hvm_post_suspend(int suspend_cancelled);
void xen_mm_pin_all(void);
void xen_mm_unpin_all(void);