void __ref xen_hvm_init_shared_info(void)
{
int cpu;
struct xen_add_to_physmap xatp;
static struct shared_info *shared_info_page;
if (!shared_info_page)
shared_info_page = (struct shared_info *)
extend_brk(PAGE_SIZE, PAGE_SIZE);
xatp.domid = DOMID_SELF;
xatp.idx = 0;
xatp.space = XENMAPSPACE_shared_info;
xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
BUG();
HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
* page, we use it in the event channel upcall and in some pvclock
* related functions. We don't need the vcpu_info placement
* optimizations because we don't use any pv_mmu or pv_irq op on
* HVM.
* When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
* online but xen_hvm_init_shared_info is run at resume time too and
* in that case multiple vcpus might be online. */
for_each_online_cpu(cpu) {
/* Leave it to be NULL. */
if (xen_vcpu_nr(cpu) >= MAX_VIRT_CPUS)
continue;
per_cpu(xen_vcpu, cpu) =
&HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
}
}
void xen_vcpu_setup(int cpu)
{
struct vcpu_register_vcpu_info info;
int err;
struct vcpu_info *vcpup;
BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
/*
* This path is called twice on PVHVM - first during bootup via
* smp_init -> xen_hvm_cpu_notify, and then if the VCPU is being
* hotplugged: cpu_up -> xen_hvm_cpu_notify.
* As we can only do the VCPUOP_register_vcpu_info once lets
* not over-write its result.
*
* For PV it is called during restore (xen_vcpu_restore) and bootup
* (xen_setup_vcpu_info_placement). The hotplug mechanism does not
* use this function.
*/
if (xen_hvm_domain()) {
if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
return;
}
if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS)
per_cpu(xen_vcpu, cpu) =
&HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
if (!xen_have_vcpu_info_placement) {
if (cpu >= MAX_VIRT_CPUS)
clamp_max_cpus();
return;
}
vcpup = &per_cpu(xen_vcpu_info, cpu);
info.mfn = arbitrary_virt_to_mfn(vcpup);
info.offset = offset_in_page(vcpup);
/* Check to see if the hypervisor will put the vcpu_info
structure where we want it, which allows direct access via
a percpu-variable.
N.B. This hypercall can _only_ be called once per CPU. Subsequent
calls will error out with -EINVAL. This is due to the fact that
hypervisor has no unregister variant and this hypercall does not
allow to over-write info.mfn and info.offset.
*/
err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
&info);
if (err) {
printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
xen_have_vcpu_info_placement = 0;
clamp_max_cpus();
} else {
/* This cpu is using the registered vcpu info, even if
later ones fail to. */
per_cpu(xen_vcpu, cpu) = vcpup;
}
}
static int xen_vcpuop_shutdown(struct clock_event_device *evt)
{
int cpu = smp_processor_id();
if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, xen_vcpu_nr(cpu),
NULL) ||
HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, xen_vcpu_nr(cpu),
NULL))
BUG();
return 0;
}
static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
{
int rc;
common_cpu_up(cpu, idle);
xen_setup_runstate_info(cpu);
/*
* PV VCPUs are always successfully taken down (see 'while' loop
* in xen_cpu_die()), so -EBUSY is an error.
*/
rc = cpu_check_up_prepare(cpu);
if (rc)
return rc;
/* make sure interrupts start blocked */
per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
rc = cpu_initialize_context(cpu, idle);
if (rc)
return rc;
xen_pmu_init(cpu);
rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL);
BUG_ON(rc);
while (cpu_report_state(cpu) != CPU_ONLINE)
HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
return 0;
}
static void xen_halt(void)
{
if (irqs_disabled())
HYPERVISOR_vcpu_op(VCPUOP_down,
xen_vcpu_nr(smp_processor_id()), NULL);
else
xen_safe_halt();
}
static void stop_self(void *v)
{
int cpu = smp_processor_id();
/* make sure we're not pinning something down */
load_cr3(swapper_pg_dir);
/* should set up a minimal gdt */
set_cpu_online(cpu, false);
HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL);
BUG();
}
static void xen_pv_cpu_die(unsigned int cpu)
{
while (HYPERVISOR_vcpu_op(VCPUOP_is_up,
xen_vcpu_nr(cpu), NULL)) {
__set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(HZ/10);
}
if (common_cpu_die(cpu) == 0) {
xen_smp_intr_free(cpu);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
xen_pmu_finish(cpu);
}
}
static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */
{
play_dead_common();
HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);
cpu_bringup();
/*
* commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
* clears certain data that the cpu_idle loop (which called us
* and that we return from) expects. The only way to get that
* data back is to call:
*/
tick_nohz_idle_enter();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
static int xen_vcpuop_set_next_event(unsigned long delta,
struct clock_event_device *evt)
{
int cpu = smp_processor_id();
struct vcpu_set_singleshot_timer single;
int ret;
WARN_ON(!clockevent_state_oneshot(evt));
single.timeout_abs_ns = get_abs_timeout(delta);
/* Get an event anyway, even if the timeout is already expired */
single.flags = 0;
ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, xen_vcpu_nr(cpu),
&single);
BUG_ON(ret != 0);
return ret;
}
static int
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
struct vcpu_guest_context *ctxt;
struct desc_struct *gdt;
unsigned long gdt_mfn;
/* used to tell cpu_init() that it can proceed with initialization */
cpumask_set_cpu(cpu, cpu_callout_mask);
if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
return 0;
ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
if (ctxt == NULL)
return -ENOMEM;
gdt = get_cpu_gdt_rw(cpu);
#ifdef CONFIG_X86_32
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#endif
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
/*
* Bring up the CPU in cpu_bringup_and_idle() with the stack
* pointing just below where pt_regs would be if it were a normal
* kernel entry.
*/
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
ctxt->user_regs.ds = __USER_DS;
ctxt->user_regs.es = __USER_DS;
ctxt->user_regs.ss = __KERNEL_DS;
ctxt->user_regs.cs = __KERNEL_CS;
ctxt->user_regs.esp = (unsigned long)task_pt_regs(idle);
xen_copy_trap_info(ctxt->trap_ctxt);
ctxt->ldt_ents = 0;
BUG_ON((unsigned long)gdt & ~PAGE_MASK);
gdt_mfn = arbitrary_virt_to_mfn(gdt);
make_lowmem_page_readonly(gdt);
make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
ctxt->gdt_frames[0] = gdt_mfn;
ctxt->gdt_ents = GDT_ENTRIES;
/*
* Set SS:SP that Xen will use when entering guest kernel mode
* from guest user mode. Subsequent calls to load_sp0() can
* change this value.
*/
ctxt->kernel_ss = __KERNEL_DS;
ctxt->kernel_sp = task_top_of_stack(idle);
#ifdef CONFIG_X86_32
ctxt->event_callback_cs = __KERNEL_CS;
ctxt->failsafe_callback_cs = __KERNEL_CS;
#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->event_callback_eip =
(unsigned long)xen_hypervisor_callback;
ctxt->failsafe_callback_eip =
(unsigned long)xen_failsafe_callback;
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
BUG();
kfree(ctxt);
return 0;
}
static int
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
struct vcpu_guest_context *ctxt;
struct desc_struct *gdt;
unsigned long gdt_mfn;
/* used to tell cpu_init() that it can proceed with initialization */
cpumask_set_cpu(cpu, cpu_callout_mask);
if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
return 0;
ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
if (ctxt == NULL)
return -ENOMEM;
gdt = get_cpu_gdt_rw(cpu);
#ifdef CONFIG_X86_32
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#endif
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
ctxt->user_regs.ds = __USER_DS;
ctxt->user_regs.es = __USER_DS;
ctxt->user_regs.ss = __KERNEL_DS;
xen_copy_trap_info(ctxt->trap_ctxt);
ctxt->ldt_ents = 0;
BUG_ON((unsigned long)gdt & ~PAGE_MASK);
gdt_mfn = arbitrary_virt_to_mfn(gdt);
make_lowmem_page_readonly(gdt);
make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
ctxt->gdt_frames[0] = gdt_mfn;
ctxt->gdt_ents = GDT_ENTRIES;
ctxt->kernel_ss = __KERNEL_DS;
ctxt->kernel_sp = idle->thread.sp0;
#ifdef CONFIG_X86_32
ctxt->event_callback_cs = __KERNEL_CS;
ctxt->failsafe_callback_cs = __KERNEL_CS;
#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
ctxt->event_callback_eip =
(unsigned long)xen_hypervisor_callback;
ctxt->failsafe_callback_eip =
(unsigned long)xen_failsafe_callback;
ctxt->user_regs.cs = __KERNEL_CS;
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
BUG();
kfree(ctxt);
return 0;
}
