#include <linux/delay.h>
#include <linux/start_kernel.h>
#include <linux/sched.h>
+#include <linux/kprobes.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <asm/xen/hypervisor.h>
#include <asm/fixmap.h>
#include <asm/processor.h>
+#include <asm/proto.h>
#include <asm/msr-index.h>
+#include <asm/traps.h>
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
struct shared_info xen_dummy_shared_info;
+void *xen_initial_gdt;
+
/*
* Point at some empty memory to start with. We map the real shared_info
* page as soon as fixmap is up and running.
*
* 0: not available, 1: available
*/
-static int have_vcpu_info_placement =
-#ifdef CONFIG_X86_32
- 1
-#else
- 0
-#endif
- ;
-
+static int have_vcpu_info_placement = 1;
static void xen_vcpu_setup(int cpu)
{
vcpup = &per_cpu(xen_vcpu_info, cpu);
- info.mfn = virt_to_mfn(vcpup);
+ info.mfn = arbitrary_virt_to_mfn(vcpup);
info.offset = offset_in_page(vcpup);
printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n",
xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
}
+static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
+static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
+
static void xen_cpuid(unsigned int *ax, unsigned int *bx,
unsigned int *cx, unsigned int *dx)
{
+ unsigned maskecx = ~0;
unsigned maskedx = ~0;
/*
* Mask out inconvenient features, to try and disable as many
* unsupported kernel subsystems as possible.
*/
- if (*ax == 1)
- maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */
- (1 << X86_FEATURE_ACPI) | /* disable ACPI */
- (1 << X86_FEATURE_MCE) | /* disable MCE */
- (1 << X86_FEATURE_MCA) | /* disable MCA */
- (1 << X86_FEATURE_ACC)); /* thermal monitoring */
+ if (*ax == 1) {
+ maskecx = cpuid_leaf1_ecx_mask;
+ maskedx = cpuid_leaf1_edx_mask;
+ }
asm(XEN_EMULATE_PREFIX "cpuid"
: "=a" (*ax),
"=c" (*cx),
"=d" (*dx)
: "0" (*ax), "2" (*cx));
+
+ *cx &= maskecx;
*dx &= maskedx;
}
+static __init void xen_init_cpuid_mask(void)
+{
+ unsigned int ax, bx, cx, dx;
+
+ cpuid_leaf1_edx_mask =
+ ~((1 << X86_FEATURE_MCE) | /* disable MCE */
+ (1 << X86_FEATURE_MCA) | /* disable MCA */
+ (1 << X86_FEATURE_ACC)); /* thermal monitoring */
+
+ if (!xen_initial_domain())
+ cpuid_leaf1_edx_mask &=
+ ~((1 << X86_FEATURE_APIC) | /* disable local APIC */
+ (1 << X86_FEATURE_ACPI)); /* disable ACPI */
+
+ ax = 1;
+ 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;
+
+ 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);
+ }
+}
+
static void xen_set_debugreg(int reg, unsigned long val)
{
HYPERVISOR_set_debugreg(reg, val);
return HYPERVISOR_get_debugreg(reg);
}
-void xen_leave_lazy(void)
+static void xen_end_context_switch(struct task_struct *next)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
xen_mc_flush();
+ paravirt_end_context_switch(next);
}
static unsigned long xen_store_tr(void)
static void xen_load_gdt(const struct desc_ptr *dtr)
{
- unsigned long *frames;
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+ unsigned long frames[pages];
int f;
- struct multicall_space mcs;
/* A GDT can be up to 64k in size, which corresponds to 8192
8-byte entries, or 16 4k pages.. */
BUG_ON(size > 65536);
BUG_ON(va & ~PAGE_MASK);
- mcs = xen_mc_entry(sizeof(*frames) * pages);
- frames = mcs.args;
-
for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
- frames[f] = virt_to_mfn(va);
+ int level;
+ pte_t *ptep = lookup_address(va, &level);
+ unsigned long pfn, mfn;
+ void *virt;
+
+ BUG_ON(ptep == NULL);
+
+ pfn = pte_pfn(*ptep);
+ mfn = pfn_to_mfn(pfn);
+ virt = __va(PFN_PHYS(pfn));
+
+ frames[f] = mfn;
+
make_lowmem_page_readonly((void *)va);
+ make_lowmem_page_readonly(virt);
}
- MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct));
-
- xen_mc_issue(PARAVIRT_LAZY_CPU);
+ if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+ BUG();
}
static void load_TLS_descriptor(struct thread_struct *t,
unsigned int cpu, unsigned int i)
{
struct desc_struct *gdt = get_cpu_gdt_table(cpu);
- xmaddr_t maddr = virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
+ xmaddr_t maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
struct multicall_space mc = __xen_mc_entry(0);
MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]);
static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
/*
- * XXX sleazy hack: If we're being called in a lazy-cpu zone,
- * it means we're in a context switch, and %gs has just been
- * saved. This means we can zero it out to prevent faults on
- * exit from the hypervisor if the next process has no %gs.
- * Either way, it has been saved, and the new value will get
- * loaded properly. This will go away as soon as Xen has been
- * modified to not save/restore %gs for normal hypercalls.
+ * XXX sleazy hack: If we're being called in a lazy-cpu zone
+ * and lazy gs handling is enabled, it means we're in a
+ * context switch, and %gs has just been saved. This means we
+ * can zero it out to prevent faults on exit from the
+ * hypervisor if the next process has no %gs. Either way, it
+ * has been saved, and the new value will get loaded properly.
+ * This will go away as soon as Xen has been modified to not
+ * save/restore %gs for normal hypercalls.
*
* On x86_64, this hack is not used for %gs, because gs points
* to KERNEL_GS_BASE (and uses it for PDA references), so we
*/
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
#ifdef CONFIG_X86_32
- loadsegment(gs, 0);
+ lazy_load_gs(0);
#else
loadsegment(fs, 0);
#endif
static int cvt_gate_to_trap(int vector, const gate_desc *val,
struct trap_info *info)
{
- if (val->type != 0xf && val->type != 0xe)
+ unsigned long addr;
+
+ if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
return 0;
info->vector = vector;
- info->address = gate_offset(*val);
+
+ addr = gate_offset(*val);
+#ifdef CONFIG_X86_64
+ /*
+ * Look for known traps using IST, and substitute them
+ * appropriately. The debugger ones are the only ones we care
+ * about. Xen will handle faults like double_fault and
+ * machine_check, so we should never see them. Warn if
+ * there's an unexpected IST-using fault handler.
+ */
+ if (addr == (unsigned long)debug)
+ addr = (unsigned long)xen_debug;
+ else if (addr == (unsigned long)int3)
+ addr = (unsigned long)xen_int3;
+ else if (addr == (unsigned long)stack_segment)
+ addr = (unsigned long)xen_stack_segment;
+ else if (addr == (unsigned long)double_fault ||
+ addr == (unsigned long)nmi) {
+ /* Don't need to handle these */
+ return 0;
+#ifdef CONFIG_X86_MCE
+ } else if (addr == (unsigned long)machine_check) {
+ return 0;
+#endif
+ } else {
+ /* Some other trap using IST? */
+ if (WARN_ON(val->ist != 0))
+ return 0;
+ }
+#endif /* CONFIG_X86_64 */
+ info->address = addr;
+
info->cs = gate_segment(*val);
info->flags = val->dpl;
/* interrupt gates clear IF */
- if (val->type == 0xe)
- info->flags |= 4;
+ if (val->type == GATE_INTERRUPT)
+ info->flags |= 1 << 2;
return 1;
}
break;
default: {
- xmaddr_t maddr = virt_to_machine(&dt[entry]);
+ xmaddr_t maddr = arbitrary_virt_to_machine(&dt[entry]);
xen_mc_flush();
if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
return 0;
}
-static struct apic_ops xen_basic_apic_ops = {
- .read = xen_apic_read,
- .write = xen_apic_write,
- .icr_read = xen_apic_icr_read,
- .icr_write = xen_apic_icr_write,
- .wait_icr_idle = xen_apic_wait_icr_idle,
- .safe_wait_icr_idle = xen_safe_apic_wait_icr_idle,
-};
+static void set_xen_basic_apic_ops(void)
+{
+ apic->read = xen_apic_read;
+ apic->write = xen_apic_write;
+ apic->icr_read = xen_apic_icr_read;
+ 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;
+}
#endif
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+ unsigned long cr0 = percpu_read(xen_cr0_value);
+
+ if (unlikely(cr0 == 0)) {
+ cr0 = native_read_cr0();
+ percpu_write(xen_cr0_value, cr0);
+ }
+
+ return cr0;
+}
+
static void xen_write_cr0(unsigned long cr0)
{
struct multicall_space mcs;
+ percpu_write(xen_cr0_value, cr0);
+
/* Only pay attention to cr0.TS; everything else is
ignored. */
mcs = xen_mc_entry(0);
static const struct pv_init_ops xen_init_ops __initdata = {
.patch = xen_patch,
-
- .banner = xen_banner,
- .memory_setup = xen_memory_setup,
- .arch_setup = xen_arch_setup,
- .post_allocator_init = xen_post_allocator_init,
};
static const struct pv_time_ops xen_time_ops __initdata = {
- .time_init = xen_time_init,
-
.set_wallclock = xen_set_wallclock,
.get_wallclock = xen_get_wallclock,
- .get_tsc_khz = xen_tsc_khz,
.sched_clock = xen_sched_clock,
};
.clts = xen_clts,
- .read_cr0 = native_read_cr0,
+ .read_cr0 = xen_read_cr0,
.write_cr0 = xen_write_cr0,
.read_cr4 = native_read_cr4,
/* Xen takes care of %gs when switching to usermode for us */
.swapgs = paravirt_nop,
- .lazy_mode = {
- .enter = paravirt_enter_lazy_cpu,
- .leave = xen_leave_lazy,
- },
+ .start_context_switch = paravirt_start_context_switch,
+ .end_context_switch = xen_end_context_switch,
};
static const struct pv_apic_ops xen_apic_ops __initdata = {
#ifdef CONFIG_X86_LOCAL_APIC
- .setup_boot_clock = paravirt_nop,
- .setup_secondary_clock = paravirt_nop,
.startup_ipi_hook = paravirt_nop,
#endif
};
.emergency_restart = xen_emergency_restart,
};
-
/* First C function to be called on Xen boot */
asmlinkage void __init xen_start_kernel(void)
{
xen_domain_type = XEN_PV_DOMAIN;
- BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0);
-
- xen_setup_features();
-
/* Install Xen paravirt ops */
pv_info = xen_info;
pv_init_ops = xen_init_ops;
pv_time_ops = xen_time_ops;
pv_cpu_ops = xen_cpu_ops;
pv_apic_ops = xen_apic_ops;
- pv_mmu_ops = xen_mmu_ops;
+ x86_init.resources.memory_setup = xen_memory_setup;
+ x86_init.oem.arch_setup = xen_arch_setup;
+ x86_init.oem.banner = xen_banner;
+
+ x86_init.timers.timer_init = xen_time_init;
+ x86_init.timers.setup_percpu_clockev = x86_init_noop;
+ x86_cpuinit.setup_percpu_clockev = x86_init_noop;
+
+ x86_platform.calibrate_tsc = xen_tsc_khz;
+
+#ifdef CONFIG_X86_64
+ /*
+ * Setup percpu state. We only need to do this for 64-bit
+ * because 32-bit already has %fs set properly.
+ */
+ load_percpu_segment(0);
+#endif
+
+ xen_init_mmu_ops();
xen_init_irq_ops();
+ xen_init_cpuid_mask();
#ifdef CONFIG_X86_LOCAL_APIC
/*
* set up the basic apic ops.
*/
- apic_ops = &xen_basic_apic_ops;
+ set_xen_basic_apic_ops();
#endif
+ xen_setup_features();
+
if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
machine_ops = xen_machine_ops;
-#ifdef CONFIG_X86_64
- /* Disable until direct per-cpu data access. */
- have_vcpu_info_placement = 0;
-#endif
-
- /* setup percpu state */
- load_percpu_segment(0);
+ /*
+ * The only reliable way to retain the initial address of the
+ * percpu gdt_page is to remember it here, so we can go and
+ * mark it RW later, when the initial percpu area is freed.
+ */
+ xen_initial_gdt = &per_cpu(gdt_page, 0);
xen_smp_init();
if (!xen_initial_domain())
__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+#ifdef CONFIG_X86_64
+ /* Work out if we support NX */
+ check_efer();
+#endif
+
/* 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();
+
xen_raw_console_write("mapping kernel into physical memory\n");
pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff