#include <asm/reboot.h>
#include <asm/stackprotector.h>
#include <asm/hypervisor.h>
+#include <asm/mwait.h>
+#include <asm/pci_x86.h>
+
+#ifdef CONFIG_ACPI
+#include <linux/acpi.h>
+#include <asm/acpi.h>
+#include <acpi/pdc_intel.h>
+#include <acpi/processor.h>
+#include <xen/interface/platform.h>
+#endif
#include "xen-ops.h"
#include "mmu.h"
unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
EXPORT_SYMBOL(machine_to_phys_mapping);
-unsigned int machine_to_phys_order;
-EXPORT_SYMBOL(machine_to_phys_order);
+unsigned long machine_to_phys_nr;
+EXPORT_SYMBOL(machine_to_phys_nr);
struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);
static void clamp_max_cpus(void)
{
#ifdef CONFIG_SMP
- if (setup_max_cpus > MAX_VIRT_CPUS)
- setup_max_cpus = MAX_VIRT_CPUS;
+ if (setup_max_cpus > XEN_LEGACY_MAX_VCPUS)
+ setup_max_cpus = XEN_LEGACY_MAX_VCPUS;
#endif
}
BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
- if (cpu < MAX_VIRT_CPUS)
+ if (cpu < XEN_LEGACY_MAX_VCPUS)
per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
if (!have_vcpu_info_placement) {
- if (cpu >= MAX_VIRT_CPUS)
+ if (cpu >= XEN_LEGACY_MAX_VCPUS)
clamp_max_cpus();
return;
}
static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
+static __read_mostly unsigned int cpuid_leaf1_ecx_set_mask;
+static __read_mostly unsigned int cpuid_leaf5_ecx_val;
+static __read_mostly unsigned int cpuid_leaf5_edx_val;
+
static void xen_cpuid(unsigned int *ax, unsigned int *bx,
unsigned int *cx, unsigned int *dx)
{
unsigned maskebx = ~0;
unsigned maskecx = ~0;
unsigned maskedx = ~0;
-
+ unsigned setecx = 0;
/*
* Mask out inconvenient features, to try and disable as many
* unsupported kernel subsystems as possible.
switch (*ax) {
case 1:
maskecx = cpuid_leaf1_ecx_mask;
+ setecx = cpuid_leaf1_ecx_set_mask;
maskedx = cpuid_leaf1_edx_mask;
break;
+ case CPUID_MWAIT_LEAF:
+ /* Synthesize the values.. */
+ *ax = 0;
+ *bx = 0;
+ *cx = cpuid_leaf5_ecx_val;
+ *dx = cpuid_leaf5_edx_val;
+ return;
+
case 0xb:
/* Suppress extended topology stuff */
maskebx = 0;
*bx &= maskebx;
*cx &= maskecx;
+ *cx |= setecx;
*dx &= maskedx;
+
}
-static __init void xen_init_cpuid_mask(void)
+static bool __init xen_check_mwait(void)
{
+#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \
+ !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ uint32_t buf[3];
unsigned int ax, bx, cx, dx;
+ unsigned int mwait_mask;
+
+ /* We need to determine whether it is OK to expose the MWAIT
+ * capability to the kernel to harvest deeper than C3 states from ACPI
+ * _CST using the processor_harvest_xen.c module. For this to work, we
+ * need to gather the MWAIT_LEAF values (which the cstate.c code
+ * checks against). The hypervisor won't expose the MWAIT flag because
+ * it would break backwards compatibility; so we will find out directly
+ * from the hardware and hypercall.
+ */
+ if (!xen_initial_domain())
+ return false;
+
+ ax = 1;
+ cx = 0;
+
+ native_cpuid(&ax, &bx, &cx, &dx);
+
+ mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
+ (1 << (X86_FEATURE_MWAIT % 32));
+
+ if ((cx & mwait_mask) != mwait_mask)
+ return false;
+
+ /* We need to emulate the MWAIT_LEAF and for that we need both
+ * ecx and edx. The hypercall provides only partial information.
+ */
+
+ ax = CPUID_MWAIT_LEAF;
+ bx = 0;
+ cx = 0;
+ dx = 0;
+
+ native_cpuid(&ax, &bx, &cx, &dx);
+
+ /* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
+ * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
+ */
+ buf[0] = ACPI_PDC_REVISION_ID;
+ buf[1] = 1;
+ buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+
+ if ((HYPERVISOR_dom0_op(&op) == 0) &&
+ (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
+ cpuid_leaf5_ecx_val = cx;
+ cpuid_leaf5_edx_val = dx;
+ }
+ return true;
+#else
+ return false;
+#endif
+}
+static void __init xen_init_cpuid_mask(void)
+{
+ unsigned int ax, bx, cx, dx;
+ unsigned int xsave_mask;
cpuid_leaf1_edx_mask =
~((1 << X86_FEATURE_MCE) | /* disable MCE */
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_APIC) | /* disable local APIC */
(1 << X86_FEATURE_ACPI)); /* disable ACPI */
-
ax = 1;
cx = 0;
xen_cpuid(&ax, &bx, &cx, &dx);
- /* cpuid claims we support xsave; try enabling it to see what happens */
- if (cx & (1 << (X86_FEATURE_XSAVE % 32))) {
- unsigned long cr4;
+ xsave_mask =
+ (1 << (X86_FEATURE_XSAVE % 32)) |
+ (1 << (X86_FEATURE_OSXSAVE % 32));
- set_in_cr4(X86_CR4_OSXSAVE);
-
- cr4 = read_cr4();
-
- if ((cr4 & X86_CR4_OSXSAVE) == 0)
- cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32));
-
- clear_in_cr4(X86_CR4_OSXSAVE);
- }
+ /* Xen will set CR4.OSXSAVE if supported and not disabled by force */
+ if ((cx & xsave_mask) != xsave_mask)
+ cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
+ if (xen_check_mwait())
+ cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
}
static void xen_set_debugreg(int reg, unsigned long val)
struct mmuext_op *op;
struct multicall_space mcs = xen_mc_entry(sizeof(*op));
+ trace_xen_cpu_set_ldt(addr, entries);
+
op = mcs.args;
op->cmd = MMUEXT_SET_LDT;
op->arg1.linear_addr = (unsigned long)addr;
/*
* load_gdt for early boot, when the gdt is only mapped once
*/
-static __init void xen_load_gdt_boot(const struct desc_ptr *dtr)
+static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
u64 entry = *(u64 *)ptr;
+ trace_xen_cpu_write_ldt_entry(dt, entrynum, entry);
+
preempt_disable();
xen_mc_flush();
unsigned long p = (unsigned long)&dt[entrynum];
unsigned long start, end;
+ trace_xen_cpu_write_idt_entry(dt, entrynum, g);
+
preempt_disable();
- start = __get_cpu_var(idt_desc).address;
- end = start + __get_cpu_var(idt_desc).size + 1;
+ start = __this_cpu_read(idt_desc.address);
+ end = start + __this_cpu_read(idt_desc.size) + 1;
xen_mc_flush();
static DEFINE_SPINLOCK(lock);
static struct trap_info traps[257];
+ trace_xen_cpu_load_idt(desc);
+
spin_lock(&lock);
__get_cpu_var(idt_desc) = *desc;
static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
const void *desc, int type)
{
+ trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
preempt_disable();
switch (type) {
* Version of write_gdt_entry for use at early boot-time needed to
* update an entry as simply as possible.
*/
-static __init void xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
+static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
const void *desc, int type)
{
+ trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
switch (type) {
case DESC_LDT:
case DESC_TSS:
static void xen_load_sp0(struct tss_struct *tss,
struct thread_struct *thread)
{
- struct multicall_space mcs = xen_mc_entry(0);
+ struct multicall_space mcs;
+
+ mcs = xen_mc_entry(0);
MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
}
#ifdef CONFIG_X86_LOCAL_APIC
+static unsigned long xen_set_apic_id(unsigned int x)
+{
+ WARN_ON(1);
+ return x;
+}
+static unsigned int xen_get_apic_id(unsigned long x)
+{
+ return ((x)>>24) & 0xFFu;
+}
static u32 xen_apic_read(u32 reg)
{
- return 0;
+ struct xen_platform_op op = {
+ .cmd = XENPF_get_cpuinfo,
+ .interface_version = XENPF_INTERFACE_VERSION,
+ .u.pcpu_info.xen_cpuid = 0,
+ };
+ int ret = 0;
+
+ /* Shouldn't need this as APIC is turned off for PV, and we only
+ * get called on the bootup processor. But just in case. */
+ if (!xen_initial_domain() || smp_processor_id())
+ return 0;
+
+ if (reg == APIC_LVR)
+ return 0x10;
+
+ if (reg != APIC_ID)
+ return 0;
+
+ ret = HYPERVISOR_dom0_op(&op);
+ if (ret)
+ return 0;
+
+ return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
apic->icr_write = xen_apic_icr_write;
apic->wait_icr_idle = xen_apic_wait_icr_idle;
apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
+ apic->set_apic_id = xen_set_apic_id;
+ apic->get_apic_id = xen_get_apic_id;
}
#endif
static unsigned long xen_read_cr0(void)
{
- unsigned long cr0 = percpu_read(xen_cr0_value);
+ unsigned long cr0 = this_cpu_read(xen_cr0_value);
if (unlikely(cr0 == 0)) {
cr0 = native_read_cr0();
- percpu_write(xen_cr0_value, cr0);
+ this_cpu_write(xen_cr0_value, cr0);
}
return cr0;
{
struct multicall_space mcs;
- percpu_write(xen_cr0_value, cr0);
+ this_cpu_write(xen_cr0_value, cr0);
/* Only pay attention to cr0.TS; everything else is
ignored. */
xen_setup_mfn_list_list();
}
-/* This is called once we have the cpu_possible_map */
+/* This is called once we have the cpu_possible_mask */
void xen_setup_vcpu_info_placement(void)
{
int cpu;
return ret;
}
-static const struct pv_info xen_info __initdata = {
+static const struct pv_info xen_info __initconst = {
.paravirt_enabled = 1,
.shared_kernel_pmd = 0,
+#ifdef CONFIG_X86_64
+ .extra_user_64bit_cs = FLAT_USER_CS64,
+#endif
+
.name = "Xen",
};
-static const struct pv_init_ops xen_init_ops __initdata = {
+static const struct pv_init_ops xen_init_ops __initconst = {
.patch = xen_patch,
};
-static const struct pv_cpu_ops xen_cpu_ops __initdata = {
+static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.cpuid = xen_cpuid,
.set_debugreg = xen_set_debugreg,
.end_context_switch = xen_end_context_switch,
};
-static const struct pv_apic_ops xen_apic_ops __initdata = {
+static const struct pv_apic_ops xen_apic_ops __initconst = {
#ifdef CONFIG_X86_LOCAL_APIC
.startup_ipi_hook = paravirt_nop,
#endif
{
struct sched_shutdown r = { .reason = reason };
-#ifdef CONFIG_SMP
- stop_other_cpus();
-#endif
-
if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
BUG();
}
xen_reboot(SHUTDOWN_poweroff);
}
+static void xen_machine_power_off(void)
+{
+ if (pm_power_off)
+ pm_power_off();
+ xen_reboot(SHUTDOWN_poweroff);
+}
+
static void xen_crash_shutdown(struct pt_regs *regs)
{
xen_reboot(SHUTDOWN_crash);
return 0;
}
-static const struct machine_ops __initdata xen_machine_ops = {
+static const struct machine_ops xen_machine_ops __initconst = {
.restart = xen_restart,
.halt = xen_machine_halt,
- .power_off = xen_machine_halt,
+ .power_off = xen_machine_power_off,
.shutdown = xen_machine_halt,
.crash_shutdown = xen_crash_shutdown,
.emergency_restart = xen_emergency_restart,
/* Prevent unwanted bits from being set in PTEs. */
__supported_pte_mask &= ~_PAGE_GLOBAL;
+#if 0
if (!xen_initial_domain())
+#endif
__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
__supported_pte_mask |= _PAGE_IOMAP;
xen_smp_init();
- pgd = (pgd_t *)xen_start_info->pt_base;
+#ifdef CONFIG_ACPI_NUMA
+ /*
+ * The pages we from Xen are not related to machine pages, so
+ * any NUMA information the kernel tries to get from ACPI will
+ * be meaningless. Prevent it from trying.
+ */
+ acpi_numa = -1;
+#endif
- if (!xen_initial_domain())
- __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+ pgd = (pgd_t *)xen_start_info->pt_base;
- __supported_pte_mask |= _PAGE_IOMAP;
/* Don't do the full vcpu_info placement stuff until we have a
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
local_irq_disable();
- early_boot_irqs_off();
-
- memblock_init();
+ early_boot_irqs_disabled = true;
xen_raw_console_write("mapping kernel into physical memory\n");
pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
if (pci_xen)
x86_init.pci.arch_init = pci_xen_init;
} else {
+ const struct dom0_vga_console_info *info =
+ (void *)((char *)xen_start_info +
+ xen_start_info->console.dom0.info_off);
+
+ xen_init_vga(info, xen_start_info->console.dom0.info_size);
+ xen_start_info->console.domU.mfn = 0;
+ xen_start_info->console.domU.evtchn = 0;
+
/* Make sure ACS will be enabled */
pci_request_acs();
}
-
-
+#ifdef CONFIG_PCI
+ /* PCI BIOS service won't work from a PV guest. */
+ pci_probe &= ~PCI_PROBE_BIOS;
+#endif
xen_raw_console_write("about to get started...\n");
xen_setup_runstate_info(0);
#endif
}
-static uint32_t xen_cpuid_base(void)
-{
- uint32_t base, eax, ebx, ecx, edx;
- char signature[13];
-
- for (base = 0x40000000; base < 0x40010000; base += 0x100) {
- cpuid(base, &eax, &ebx, &ecx, &edx);
- *(uint32_t *)(signature + 0) = ebx;
- *(uint32_t *)(signature + 4) = ecx;
- *(uint32_t *)(signature + 8) = edx;
- signature[12] = 0;
-
- if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2))
- return base;
- }
-
- return 0;
-}
-
static int init_hvm_pv_info(int *major, int *minor)
{
uint32_t eax, ebx, ecx, edx, pages, msr, base;
xen_setup_features();
- pv_info = xen_info;
- pv_info.kernel_rpl = 0;
+ pv_info.name = "Xen HVM";
xen_domain_type = XEN_HVM_DOMAIN;
return 0;
}
-void xen_hvm_init_shared_info(void)
+void __ref xen_hvm_init_shared_info(void)
{
int cpu;
struct xen_add_to_physmap xatp;
int cpu = (long)hcpu;
switch (action) {
case CPU_UP_PREPARE:
- per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+ xen_vcpu_setup(cpu);
+ if (xen_have_vector_callback)
+ xen_init_lock_cpu(cpu);
break;
default:
break;
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = {
+static struct notifier_block xen_hvm_cpu_notifier __cpuinitdata = {
.notifier_call = xen_hvm_cpu_notify,
};
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;
x86_init.irqs.intr_init = xen_init_IRQ;
xen_hvm_init_time_ops();
xen_hvm_init_mmu_ops();
return true;
}
-const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = {
+bool xen_hvm_need_lapic(void)
+{
+ if (xen_pv_domain())
+ return false;
+ if (!xen_hvm_domain())
+ return false;
+ if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback)
+ return false;
+ return true;
+}
+EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
+
+const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
.name = "Xen HVM",
.detect = xen_hvm_platform,
.init_platform = xen_hvm_guest_init,