diff options
Diffstat (limited to 'arch/x86/xen/enlighten.c')
| -rw-r--r-- | arch/x86/xen/enlighten.c | 1843 |
1 files changed, 991 insertions, 852 deletions
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bea215230b2..ffb101e4573 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -11,6 +11,7 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/smp.h> @@ -20,86 +21,119 @@ #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 <linux/page-flags.h> #include <linux/highmem.h> #include <linux/console.h> +#include <linux/pci.h> +#include <linux/gfp.h> +#include <linux/memblock.h> +#include <linux/edd.h> +#include <xen/xen.h> +#include <xen/events.h> #include <xen/interface/xen.h> #include <xen/interface/version.h> #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> +#include <xen/interface/memory.h> +#include <xen/interface/xen-mca.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/hvm.h> #include <xen/hvc-console.h> +#include <xen/acpi.h> #include <asm/paravirt.h> #include <asm/apic.h> #include <asm/page.h> +#include <asm/xen/pci.h> #include <asm/xen/hypercall.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/pgalloc.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/reboot.h> +#include <asm/stackprotector.h> +#include <asm/hypervisor.h> +#include <asm/mwait.h> +#include <asm/pci_x86.h> +#include <asm/pat.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" +#include "smp.h" #include "multicalls.h" EXPORT_SYMBOL_GPL(hypercall_page); +/* + * Pointer to the xen_vcpu_info structure or + * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info + * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info + * but if the hypervisor supports VCPUOP_register_vcpu_info then it can point + * to xen_vcpu_info. The pointer is used in __xen_evtchn_do_upcall to + * acknowledge pending events. + * Also more subtly it is used by the patched version of irq enable/disable + * e.g. xen_irq_enable_direct and xen_iret in PV mode. + * + * The desire to be able to do those mask/unmask operations as a single + * instruction by using the per-cpu offset held in %gs is the real reason + * vcpu info is in a per-cpu pointer and the original reason for this + * hypercall. + * + */ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); -DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); - -enum xen_domain_type xen_domain_type = XEN_NATIVE; -EXPORT_SYMBOL_GPL(xen_domain_type); /* - * Identity map, in addition to plain kernel map. This needs to be - * large enough to allocate page table pages to allocate the rest. - * Each page can map 2MB. + * Per CPU pages used if hypervisor supports VCPUOP_register_vcpu_info + * hypercall. This can be used both in PV and PVHVM mode. The structure + * overrides the default per_cpu(xen_vcpu, cpu) value. */ -static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss; +DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); -#ifdef CONFIG_X86_64 -/* l3 pud for userspace vsyscall mapping */ -static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; -#endif /* CONFIG_X86_64 */ +enum xen_domain_type xen_domain_type = XEN_NATIVE; +EXPORT_SYMBOL_GPL(xen_domain_type); -/* - * Note about cr3 (pagetable base) values: - * - * xen_cr3 contains the current logical cr3 value; it contains the - * last set cr3. This may not be the current effective cr3, because - * its update may be being lazily deferred. However, a vcpu looking - * at its own cr3 can use this value knowing that it everything will - * be self-consistent. - * - * xen_current_cr3 contains the actual vcpu cr3; it is set once the - * hypercall to set the vcpu cr3 is complete (so it may be a little - * out of date, but it will never be set early). If one vcpu is - * looking at another vcpu's cr3 value, it should use this variable. - */ -DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */ -DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ +unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; +EXPORT_SYMBOL(machine_to_phys_mapping); +unsigned long machine_to_phys_nr; +EXPORT_SYMBOL(machine_to_phys_nr); struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); struct shared_info xen_dummy_shared_info; +void *xen_initial_gdt; + +RESERVE_BRK(shared_info_page_brk, PAGE_SIZE); +__read_mostly int xen_have_vector_callback; +EXPORT_SYMBOL_GPL(xen_have_vector_callback); + /* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ -struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; +struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; /* * Flag to determine whether vcpu info placement is available on all @@ -114,14 +148,28 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; * * 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; + +struct tls_descs { + struct desc_struct desc[3]; +}; + +/* + * Updating the 3 TLS descriptors in the GDT on every task switch is + * surprisingly expensive so we avoid updating them if they haven't + * changed. Since Xen writes different descriptors than the one + * passed in the update_descriptor hypercall we keep shadow copies to + * compare against. + */ +static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); +static void clamp_max_cpus(void) +{ +#ifdef CONFIG_SMP + if (setup_max_cpus > MAX_VIRT_CPUS) + setup_max_cpus = MAX_VIRT_CPUS; +#endif +} static void xen_vcpu_setup(int cpu) { @@ -130,34 +178,53 @@ static void xen_vcpu_setup(int cpu) struct vcpu_info *vcpup; BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); - per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; - if (!have_vcpu_info_placement) - return; /* already tested, not available */ + /* + * 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 (cpu < MAX_VIRT_CPUS) + per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + + if (!have_vcpu_info_placement) { + if (cpu >= MAX_VIRT_CPUS) + clamp_max_cpus(); + return; + } 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", - cpu, vcpup, info.mfn, info.offset); - /* Check to see if the hypervisor will put the vcpu_info structure where we want it, which allows direct access via - a percpu-variable. */ + 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, cpu, &info); if (err) { printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err); 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; - - printk(KERN_DEBUG "cpu %d using vcpu_info at %p\n", - cpu, vcpup); } } @@ -168,24 +235,24 @@ static void xen_vcpu_setup(int cpu) */ void xen_vcpu_restore(void) { - if (have_vcpu_info_placement) { - int cpu; + int cpu; - for_each_online_cpu(cpu) { - bool other_cpu = (cpu != smp_processor_id()); + for_each_possible_cpu(cpu) { + bool other_cpu = (cpu != smp_processor_id()); + bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL); - if (other_cpu && - HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL)) - BUG(); + if (other_cpu && is_up && + HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL)) + BUG(); - xen_vcpu_setup(cpu); + xen_setup_runstate_info(cpu); - if (other_cpu && - HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL)) - BUG(); - } + if (have_vcpu_info_placement) + xen_vcpu_setup(cpu); - BUG_ON(!have_vcpu_info_placement); + if (other_cpu && is_up && + HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL)) + BUG(); } } @@ -195,28 +262,75 @@ static void __init xen_banner(void) struct xen_extraversion extra; HYPERVISOR_xen_version(XENVER_extraversion, &extra); - printk(KERN_INFO "Booting paravirtualized kernel on %s\n", - pv_info.name); + pr_info("Booting paravirtualized kernel %son %s\n", + xen_feature(XENFEAT_auto_translated_physmap) ? + "with PVH extensions " : "", pv_info.name); printk(KERN_INFO "Xen version: %d.%d%s%s\n", version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } +/* Check if running on Xen version (major, minor) or later */ +bool +xen_running_on_version_or_later(unsigned int major, unsigned int minor) +{ + unsigned int version; + + if (!xen_domain()) + return false; + + version = HYPERVISOR_xen_version(XENVER_version, NULL); + if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || + ((version >> 16) > major)) + return true; + return false; +} + +#define CPUID_THERM_POWER_LEAF 6 +#define APERFMPERF_PRESENT 0 + +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. */ - 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 */ + 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 CPUID_THERM_POWER_LEAF: + /* Disabling APERFMPERF for kernel usage */ + maskecx = ~(1 << APERFMPERF_PRESENT); + break; + + case 0xb: + /* Suppress extended topology stuff */ + maskebx = 0; + break; + } asm(XEN_EMULATE_PREFIX "cpuid" : "=a" (*ax), @@ -224,7 +338,113 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, "=c" (*cx), "=d" (*dx) : "0" (*ax), "2" (*cx)); + + *bx &= maskebx; + *cx &= maskecx; + *cx |= setecx; *dx &= maskedx; + +} + +static bool __init xen_check_mwait(void) +{ +#ifdef CONFIG_ACPI + 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; + + /* + * When running under platform earlier than Xen4.2, do not expose + * mwait, to avoid the risk of loading native acpi pad driver + */ + if (!xen_running_on_version_or_later(4, 2)) + 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_MTRR) | /* disable MTRR */ + (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + + if (!xen_initial_domain()) + cpuid_leaf1_edx_mask &= + ~((1 << X86_FEATURE_ACPI)); /* disable ACPI */ + + cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32)); + + ax = 1; + cx = 0; + cpuid(1, &ax, &bx, &cx, &dx); + + xsave_mask = + (1 << (X86_FEATURE_XSAVE % 32)) | + (1 << (X86_FEATURE_OSXSAVE % 32)); + + /* 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) @@ -237,10 +457,10 @@ static unsigned long xen_get_debugreg(int reg) return HYPERVISOR_get_debugreg(reg); } -static 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) @@ -306,6 +526,8 @@ static void xen_set_ldt(const void *addr, unsigned entries) 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; @@ -318,38 +540,110 @@ static void xen_set_ldt(const void *addr, unsigned entries) 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.. */ + /* + * 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; + unsigned long pfn, mfn; + void *virt; + + /* + * The GDT is per-cpu and is in the percpu data area. + * That can be virtually mapped, so we need to do a + * page-walk to get the underlying MFN for the + * hypercall. The page can also be in the kernel's + * linear range, so we need to RO that mapping too. + */ + ptep = lookup_address(va, &level); + 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)); + if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + BUG(); +} - xen_mc_issue(PARAVIRT_LAZY_CPU); +/* + * load_gdt for early boot, when the gdt is only mapped once + */ +static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) +{ + 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; + + /* + * 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); + + for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { + pte_t pte; + unsigned long pfn, mfn; + + pfn = virt_to_pfn(va); + mfn = pfn_to_mfn(pfn); + + pte = pfn_pte(pfn, PAGE_KERNEL_RO); + + if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0)) + BUG(); + + frames[f] = mfn; + } + + if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + BUG(); +} + +static inline bool desc_equal(const struct desc_struct *d1, + const struct desc_struct *d2) +{ + return d1->a == d2->a && d1->b == d2->b; } 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]); - struct multicall_space mc = __xen_mc_entry(0); + struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i]; + struct desc_struct *gdt; + xmaddr_t maddr; + struct multicall_space mc; + + if (desc_equal(shadow, &t->tls_array[i])) + return; + + *shadow = t->tls_array[i]; + + gdt = get_cpu_gdt_table(cpu); + maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); + mc = __xen_mc_entry(0); MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]); } @@ -357,13 +651,14 @@ static void load_TLS_descriptor(struct thread_struct *t, 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 @@ -375,7 +670,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu) */ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) { #ifdef CONFIG_X86_32 - loadsegment(gs, 0); + lazy_load_gs(0); #else loadsegment(fs, 0); #endif @@ -404,6 +699,8 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, 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(); @@ -416,16 +713,57 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, 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, + * 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) { + /* Don't need to handle these */ + return 0; +#ifdef CONFIG_X86_MCE + } else if (addr == (unsigned long)machine_check) { + /* + * when xen hypervisor inject vMCE to guest, + * use native mce handler to handle it + */ + ; +#endif + } else if (addr == (unsigned long)nmi) + /* + * Use the native version as well. + */ + ; + 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; } @@ -440,10 +778,12 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) 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(); @@ -494,6 +834,8 @@ static void xen_load_idt(const struct desc_ptr *desc) 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; @@ -512,6 +854,8 @@ static void xen_load_idt(const struct desc_ptr *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) { @@ -521,7 +865,7 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry, 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)) @@ -533,10 +877,37 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry, preempt_enable(); } +/* + * Version of write_gdt_entry for use at early boot-time needed to + * update an entry as simply as possible. + */ +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: + /* ignore */ + break; + + default: { + xmaddr_t maddr = virt_to_machine(&dt[entry]); + + if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc)) + dt[entry] = *(struct desc_struct *)desc; + } + + } +} + 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); } @@ -555,9 +926,40 @@ static void xen_io_delay(void) } #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) @@ -587,110 +989,59 @@ static u32 xen_safe_apic_wait_icr_idle(void) 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, -}; - -#endif - -static void xen_flush_tlb(void) +static void set_xen_basic_apic_ops(void) { - struct mmuext_op *op; - struct multicall_space mcs; - - preempt_disable(); + 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; + apic->set_apic_id = xen_set_apic_id; + apic->get_apic_id = xen_get_apic_id; - mcs = xen_mc_entry(sizeof(*op)); - - op = mcs.args; - op->cmd = MMUEXT_TLB_FLUSH_LOCAL; - MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - - xen_mc_issue(PARAVIRT_LAZY_MMU); - - preempt_enable(); +#ifdef CONFIG_SMP + apic->send_IPI_allbutself = xen_send_IPI_allbutself; + apic->send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself; + apic->send_IPI_mask = xen_send_IPI_mask; + apic->send_IPI_all = xen_send_IPI_all; + apic->send_IPI_self = xen_send_IPI_self; +#endif } -static void xen_flush_tlb_single(unsigned long addr) -{ - struct mmuext_op *op; - struct multicall_space mcs; - - preempt_disable(); - - mcs = xen_mc_entry(sizeof(*op)); - op = mcs.args; - op->cmd = MMUEXT_INVLPG_LOCAL; - op->arg1.linear_addr = addr & PAGE_MASK; - MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - - xen_mc_issue(PARAVIRT_LAZY_MMU); - - preempt_enable(); -} +#endif -static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm, - unsigned long va) +static void xen_clts(void) { - struct { - struct mmuext_op op; - cpumask_t mask; - } *args; - cpumask_t cpumask = *cpus; struct multicall_space mcs; - /* - * A couple of (to be removed) sanity checks: - * - * - current CPU must not be in mask - * - mask must exist :) - */ - BUG_ON(cpus_empty(cpumask)); - BUG_ON(cpu_isset(smp_processor_id(), cpumask)); - BUG_ON(!mm); - - /* If a CPU which we ran on has gone down, OK. */ - cpus_and(cpumask, cpumask, cpu_online_map); - if (cpus_empty(cpumask)) - return; - - mcs = xen_mc_entry(sizeof(*args)); - args = mcs.args; - args->mask = cpumask; - args->op.arg2.vcpumask = &args->mask; - - if (va == TLB_FLUSH_ALL) { - args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - } else { - args->op.cmd = MMUEXT_INVLPG_MULTI; - args->op.arg1.linear_addr = va; - } + mcs = xen_mc_entry(0); - MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); + MULTI_fpu_taskswitch(mcs.mc, 0); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(PARAVIRT_LAZY_CPU); } -static void xen_clts(void) -{ - struct multicall_space mcs; +static DEFINE_PER_CPU(unsigned long, xen_cr0_value); - mcs = xen_mc_entry(0); +static unsigned long xen_read_cr0(void) +{ + unsigned long cr0 = this_cpu_read(xen_cr0_value); - MULTI_fpu_taskswitch(mcs.mc, 0); + if (unlikely(cr0 == 0)) { + cr0 = native_read_cr0(); + this_cpu_write(xen_cr0_value, cr0); + } - xen_mc_issue(PARAVIRT_LAZY_CPU); + return cr0; } static void xen_write_cr0(unsigned long cr0) { struct multicall_space mcs; + this_cpu_write(xen_cr0_value, cr0); + /* Only pay attention to cr0.TS; everything else is ignored. */ mcs = xen_mc_entry(0); @@ -700,21 +1051,6 @@ static void xen_write_cr0(unsigned long cr0) xen_mc_issue(PARAVIRT_LAZY_CPU); } -static void xen_write_cr2(unsigned long cr2) -{ - x86_read_percpu(xen_vcpu)->arch.cr2 = cr2; -} - -static unsigned long xen_read_cr2(void) -{ - return x86_read_percpu(xen_vcpu)->arch.cr2; -} - -static unsigned long xen_read_cr2_direct(void) -{ - return x86_read_percpu(xen_vcpu_info.arch.cr2); -} - static void xen_write_cr4(unsigned long cr4) { cr4 &= ~X86_CR4_PGE; @@ -722,72 +1058,16 @@ static void xen_write_cr4(unsigned long cr4) native_write_cr4(cr4); } - -static unsigned long xen_read_cr3(void) -{ - return x86_read_percpu(xen_cr3); -} - -static void set_current_cr3(void *v) +#ifdef CONFIG_X86_64 +static inline unsigned long xen_read_cr8(void) { - x86_write_percpu(xen_current_cr3, (unsigned long)v); + return 0; } - -static void __xen_write_cr3(bool kernel, unsigned long cr3) +static inline void xen_write_cr8(unsigned long val) { - struct mmuext_op *op; - struct multicall_space mcs; - unsigned long mfn; - - if (cr3) - mfn = pfn_to_mfn(PFN_DOWN(cr3)); - else - mfn = 0; - - WARN_ON(mfn == 0 && kernel); - - mcs = __xen_mc_entry(sizeof(*op)); - - op = mcs.args; - op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR; - op->arg1.mfn = mfn; - - MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - - if (kernel) { - x86_write_percpu(xen_cr3, cr3); - - /* Update xen_current_cr3 once the batch has actually - been submitted. */ - xen_mc_callback(set_current_cr3, (void *)cr3); - } + BUG_ON(val); } - -static void xen_write_cr3(unsigned long cr3) -{ - BUG_ON(preemptible()); - - xen_mc_batch(); /* disables interrupts */ - - /* Update while interrupts are disabled, so its atomic with - respect to ipis */ - x86_write_percpu(xen_cr3, cr3); - - __xen_write_cr3(true, cr3); - -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(__va(cr3)); - if (user_pgd) - __xen_write_cr3(false, __pa(user_pgd)); - else - __xen_write_cr3(false, 0); - } #endif - - xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ -} - static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; @@ -806,7 +1086,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) set: base = ((u64)high << 32) | low; if (HYPERVISOR_set_segment_base(which, base) != 0) - ret = -EFAULT; + ret = -EIO; break; #endif @@ -822,6 +1102,11 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) Xen console noise. */ break; + case MSR_IA32_CR_PAT: + if (smp_processor_id() == 0) + xen_set_pat(((u64)high << 32) | low); + break; + default: ret = native_write_msr_safe(msr, low, high); } @@ -829,185 +1114,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) return ret; } -/* Early in boot, while setting up the initial pagetable, assume - everything is pinned. */ -static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) -{ -#ifdef CONFIG_FLATMEM - BUG_ON(mem_map); /* should only be used early */ -#endif - make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); -} - -/* Early release_pte assumes that all pts are pinned, since there's - only init_mm and anything attached to that is pinned. */ -static void xen_release_pte_init(unsigned long pfn) -{ - make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); -} - -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) -{ - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); -} - -/* This needs to make sure the new pte page is pinned iff its being - attached to a pinned pagetable. */ -static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level) -{ - struct page *page = pfn_to_page(pfn); - - if (PagePinned(virt_to_page(mm->pgd))) { - SetPagePinned(page); - - vm_unmap_aliases(); - if (!PageHighMem(page)) { - make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn))); - if (level == PT_PTE && USE_SPLIT_PTLOCKS) - pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); - } else { - /* make sure there are no stray mappings of - this page */ - kmap_flush_unused(); - } - } -} - -static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn) -{ - xen_alloc_ptpage(mm, pfn, PT_PTE); -} - -static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn) -{ - xen_alloc_ptpage(mm, pfn, PT_PMD); -} - -static int xen_pgd_alloc(struct mm_struct *mm) -{ - pgd_t *pgd = mm->pgd; - int ret = 0; - - BUG_ON(PagePinned(virt_to_page(pgd))); - -#ifdef CONFIG_X86_64 - { - struct page *page = virt_to_page(pgd); - pgd_t *user_pgd; - - BUG_ON(page->private != 0); - - ret = -ENOMEM; - - user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - page->private = (unsigned long)user_pgd; - - if (user_pgd != NULL) { - user_pgd[pgd_index(VSYSCALL_START)] = - __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); - ret = 0; - } - - BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); - } -#endif - - return ret; -} - -static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ -#ifdef CONFIG_X86_64 - pgd_t *user_pgd = xen_get_user_pgd(pgd); - - if (user_pgd) - free_page((unsigned long)user_pgd); -#endif -} - -/* This should never happen until we're OK to use struct page */ -static void xen_release_ptpage(unsigned long pfn, unsigned level) -{ - struct page *page = pfn_to_page(pfn); - - if (PagePinned(page)) { - if (!PageHighMem(page)) { - if (level == PT_PTE && USE_SPLIT_PTLOCKS) - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); - make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); - } - ClearPagePinned(page); - } -} - -static void xen_release_pte(unsigned long pfn) -{ - xen_release_ptpage(pfn, PT_PTE); -} - -static void xen_release_pmd(unsigned long pfn) -{ - xen_release_ptpage(pfn, PT_PMD); -} - -#if PAGETABLE_LEVELS == 4 -static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) -{ - xen_alloc_ptpage(mm, pfn, PT_PUD); -} - -static void xen_release_pud(unsigned long pfn) -{ - xen_release_ptpage(pfn, PT_PUD); -} -#endif - -#ifdef CONFIG_HIGHPTE -static void *xen_kmap_atomic_pte(struct page *page, enum km_type type) -{ - pgprot_t prot = PAGE_KERNEL; - - if (PagePinned(page)) - prot = PAGE_KERNEL_RO; - - if (0 && PageHighMem(page)) - printk("mapping highpte %lx type %d prot %s\n", - page_to_pfn(page), type, - (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ"); - - return kmap_atomic_prot(page, type, prot); -} -#endif - -#ifdef CONFIG_X86_32 -static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte) -{ - /* If there's an existing pte, then don't allow _PAGE_RW to be set */ - if (pte_val_ma(*ptep) & _PAGE_PRESENT) - pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & - pte_val_ma(pte)); - - return pte; -} - -/* Init-time set_pte while constructing initial pagetables, which - doesn't allow RO pagetable pages to be remapped RW */ -static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) -{ - pte = mask_rw_pte(ptep, pte); - - xen_set_pte(ptep, pte); -} -#endif - -static __init void xen_pagetable_setup_start(pgd_t *base) -{ -} - void xen_setup_shared_info(void) { if (!xen_feature(XENFEAT_auto_translated_physmap)) { @@ -1028,38 +1134,7 @@ void xen_setup_shared_info(void) xen_setup_mfn_list_list(); } -static __init void xen_pagetable_setup_done(pgd_t *base) -{ - xen_setup_shared_info(); -} - -static __init void xen_post_allocator_init(void) -{ - pv_mmu_ops.set_pte = xen_set_pte; - pv_mmu_ops.set_pmd = xen_set_pmd; - pv_mmu_ops.set_pud = xen_set_pud; -#if PAGETABLE_LEVELS == 4 - pv_mmu_ops.set_pgd = xen_set_pgd; -#endif - - /* This will work as long as patching hasn't happened yet - (which it hasn't) */ - pv_mmu_ops.alloc_pte = xen_alloc_pte; - pv_mmu_ops.alloc_pmd = xen_alloc_pmd; - pv_mmu_ops.release_pte = xen_release_pte; - pv_mmu_ops.release_pmd = xen_release_pmd; -#if PAGETABLE_LEVELS == 4 - pv_mmu_ops.alloc_pud = xen_alloc_pud; - pv_mmu_ops.release_pud = xen_release_pud; -#endif - -#ifdef CONFIG_X86_64 - SetPagePinned(virt_to_page(level3_user_vsyscall)); -#endif - xen_mark_init_mm_pinned(); -} - -/* 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; @@ -1068,14 +1143,13 @@ void xen_setup_vcpu_info_placement(void) xen_vcpu_setup(cpu); /* xen_vcpu_setup managed to place the vcpu_info within the - percpu area for all cpus, so make use of it */ - if (have_vcpu_info_placement) { - printk(KERN_INFO "Xen: using vcpu_info placement\n"); - - pv_irq_ops.save_fl = xen_save_fl_direct; - pv_irq_ops.restore_fl = xen_restore_fl_direct; - pv_irq_ops.irq_disable = xen_irq_disable_direct; - pv_irq_ops.irq_enable = xen_irq_enable_direct; + * percpu area for all cpus, so make use of it. Note that for + * PVH we want to use native IRQ mechanism. */ + if (have_vcpu_info_placement && !xen_pvh_domain()) { + pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); + pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct); + pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); + pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct); pv_mmu_ops.read_cr2 = xen_read_cr2_direct; } } @@ -1133,75 +1207,22 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf, return ret; } -static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) -{ - pte_t pte; - - phys >>= PAGE_SHIFT; - - switch (idx) { - case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: -#ifdef CONFIG_X86_F00F_BUG - case FIX_F00F_IDT: -#endif -#ifdef CONFIG_X86_32 - case FIX_WP_TEST: - case FIX_VDSO: -# ifdef CONFIG_HIGHMEM - case FIX_KMAP_BEGIN ... FIX_KMAP_END: -# endif -#else - case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE: -#endif -#ifdef CONFIG_X86_LOCAL_APIC - case FIX_APIC_BASE: /* maps dummy local APIC */ -#endif - pte = pfn_pte(phys, prot); - break; - - default: - pte = mfn_pte(phys, prot); - break; - } - - __native_set_fixmap(idx, pte); +static const struct pv_info xen_info __initconst = { + .paravirt_enabled = 1, + .shared_kernel_pmd = 0, #ifdef CONFIG_X86_64 - /* Replicate changes to map the vsyscall page into the user - pagetable vsyscall mapping. */ - if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) { - unsigned long vaddr = __fix_to_virt(idx); - set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); - } + .extra_user_64bit_cs = FLAT_USER_CS64, #endif -} - -static const struct pv_info xen_info __initdata = { - .paravirt_enabled = 1, - .shared_kernel_pmd = 0, .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, - - .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, }; -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, @@ -1209,20 +1230,28 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { .clts = xen_clts, - .read_cr0 = native_read_cr0, + .read_cr0 = xen_read_cr0, .write_cr0 = xen_write_cr0, .read_cr4 = native_read_cr4, .read_cr4_safe = native_read_cr4_safe, .write_cr4 = xen_write_cr4, +#ifdef CONFIG_X86_64 + .read_cr8 = xen_read_cr8, + .write_cr8 = xen_write_cr8, +#endif + .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, .write_msr = xen_write_msr_safe, + .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, + .read_tscp = native_read_tscp, + .iret = xen_iret, .irq_enable_sysexit = xen_sysexit, #ifdef CONFIG_X86_64 @@ -1242,7 +1271,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { .alloc_ldt = xen_alloc_ldt, .free_ldt = xen_free_ldt, - .store_gdt = native_store_gdt, .store_idt = native_store_idt, .store_tr = xen_store_tr, @@ -1257,109 +1285,20 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { /* 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 = { +static const struct pv_apic_ops xen_apic_ops __initconst = { #ifdef CONFIG_X86_LOCAL_APIC - .setup_boot_clock = paravirt_nop, - .setup_secondary_clock = paravirt_nop, .startup_ipi_hook = paravirt_nop, #endif }; -static const struct pv_mmu_ops xen_mmu_ops __initdata = { - .pagetable_setup_start = xen_pagetable_setup_start, - .pagetable_setup_done = xen_pagetable_setup_done, - - .read_cr2 = xen_read_cr2, - .write_cr2 = xen_write_cr2, - - .read_cr3 = xen_read_cr3, - .write_cr3 = xen_write_cr3, - - .flush_tlb_user = xen_flush_tlb, - .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, - .flush_tlb_others = xen_flush_tlb_others, - - .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, - - .pgd_alloc = xen_pgd_alloc, - .pgd_free = xen_pgd_free, - - .alloc_pte = xen_alloc_pte_init, - .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pte_init, - .alloc_pmd_clone = paravirt_nop, - .release_pmd = xen_release_pte_init, - -#ifdef CONFIG_HIGHPTE - .kmap_atomic_pte = xen_kmap_atomic_pte, -#endif - -#ifdef CONFIG_X86_64 - .set_pte = xen_set_pte, -#else - .set_pte = xen_set_pte_init, -#endif - .set_pte_at = xen_set_pte_at, - .set_pmd = xen_set_pmd_hyper, - - .ptep_modify_prot_start = __ptep_modify_prot_start, - .ptep_modify_prot_commit = __ptep_modify_prot_commit, - - .pte_val = xen_pte_val, - .pte_flags = native_pte_flags, - .pgd_val = xen_pgd_val, - - .make_pte = xen_make_pte, - .make_pgd = xen_make_pgd, - -#ifdef CONFIG_X86_PAE - .set_pte_atomic = xen_set_pte_atomic, - .set_pte_present = xen_set_pte_at, - .pte_clear = xen_pte_clear, - .pmd_clear = xen_pmd_clear, -#endif /* CONFIG_X86_PAE */ - .set_pud = xen_set_pud_hyper, - - .make_pmd = xen_make_pmd, - .pmd_val = xen_pmd_val, - -#if PAGETABLE_LEVELS == 4 - .pud_val = xen_pud_val, - .make_pud = xen_make_pud, - .set_pgd = xen_set_pgd_hyper, - - .alloc_pud = xen_alloc_pte_init, - .release_pud = xen_release_pte_init, -#endif /* PAGETABLE_LEVELS == 4 */ - - .activate_mm = xen_activate_mm, - .dup_mmap = xen_dup_mmap, - .exit_mmap = xen_exit_mmap, - - .lazy_mode = { - .enter = paravirt_enter_lazy_mmu, - .leave = xen_leave_lazy, - }, - - .set_fixmap = xen_set_fixmap, -}; - static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; -#ifdef CONFIG_SMP - smp_send_stop(); -#endif - if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r)) BUG(); } @@ -1379,267 +1318,275 @@ static void xen_machine_halt(void) 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); } -static const struct machine_ops __initdata xen_machine_ops = { +static int +xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + xen_reboot(SHUTDOWN_crash); + return NOTIFY_DONE; +} + +static struct notifier_block xen_panic_block = { + .notifier_call= xen_panic_event, + .priority = INT_MIN +}; + +int xen_panic_handler_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &xen_panic_block); + return 0; +} + +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, }; - -static void __init xen_reserve_top(void) +static void __init xen_boot_params_init_edd(void) { -#ifdef CONFIG_X86_32 - unsigned long top = HYPERVISOR_VIRT_START; - struct xen_platform_parameters pp; - - if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0) - top = pp.virt_start; +#if IS_ENABLED(CONFIG_EDD) + struct xen_platform_op op; + struct edd_info *edd_info; + u32 *mbr_signature; + unsigned nr; + int ret; - reserve_top_address(-top); -#endif /* CONFIG_X86_32 */ + edd_info = boot_params.eddbuf; + mbr_signature = boot_params.edd_mbr_sig_buffer; + + op.cmd = XENPF_firmware_info; + + op.u.firmware_info.type = XEN_FW_DISK_INFO; + for (nr = 0; nr < EDDMAXNR; nr++) { + struct edd_info *info = edd_info + nr; + + op.u.firmware_info.index = nr; + info->params.length = sizeof(info->params); + set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params, + &info->params); + ret = HYPERVISOR_dom0_op(&op); + if (ret) + break; + +#define C(x) info->x = op.u.firmware_info.u.disk_info.x + C(device); + C(version); + C(interface_support); + C(legacy_max_cylinder); + C(legacy_max_head); + C(legacy_sectors_per_track); +#undef C + } + boot_params.eddbuf_entries = nr; + + op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE; + for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) { + op.u.firmware_info.index = nr; + ret = HYPERVISOR_dom0_op(&op); + if (ret) + break; + mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature; + } + boot_params.edd_mbr_sig_buf_entries = nr; +#endif } /* - * Like __va(), but returns address in the kernel mapping (which is - * all we have until the physical memory mapping has been set up. + * Set up the GDT and segment registers for -fstack-protector. Until + * we do this, we have to be careful not to call any stack-protected + * function, which is most of the kernel. + * + * Note, that it is __ref because the only caller of this after init + * is PVH which is not going to use xen_load_gdt_boot or other + * __init functions. */ -static void *__ka(phys_addr_t paddr) +static void __ref xen_setup_gdt(int cpu) { + if (xen_feature(XENFEAT_auto_translated_physmap)) { #ifdef CONFIG_X86_64 - return (void *)(paddr + __START_KERNEL_map); + unsigned long dummy; + + load_percpu_segment(cpu); /* We need to access per-cpu area */ + switch_to_new_gdt(cpu); /* GDT and GS set */ + + /* We are switching of the Xen provided GDT to our HVM mode + * GDT. The new GDT has __KERNEL_CS with CS.L = 1 + * and we are jumping to reload it. + */ + asm volatile ("pushq %0\n" + "leaq 1f(%%rip),%0\n" + "pushq %0\n" + "lretq\n" + "1:\n" + : "=&r" (dummy) : "0" (__KERNEL_CS)); + + /* + * While not needed, we also set the %es, %ds, and %fs + * to zero. We don't care about %ss as it is NULL. + * Strictly speaking this is not needed as Xen zeros those + * out (and also MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE) + * + * Linux zeros them in cpu_init() and in secondary_startup_64 + * (for BSP). + */ + loadsegment(es, 0); + loadsegment(ds, 0); + loadsegment(fs, 0); #else - return __va(paddr); -#endif -} - -/* Convert a machine address to physical address */ -static unsigned long m2p(phys_addr_t maddr) -{ - phys_addr_t paddr; - - maddr &= PTE_PFN_MASK; - paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT; - - return paddr; -} - -/* Convert a machine address to kernel virtual */ -static void *m2v(phys_addr_t maddr) -{ - return __ka(m2p(maddr)); -} - -static void set_page_prot(void *addr, pgprot_t prot) -{ - unsigned long pfn = __pa(addr) >> PAGE_SHIFT; - pte_t pte = pfn_pte(pfn, prot); - - if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0)) + /* PVH: TODO Implement. */ BUG(); -} - -static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) -{ - unsigned pmdidx, pteidx; - unsigned ident_pte; - unsigned long pfn; - - ident_pte = 0; - pfn = 0; - for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) { - pte_t *pte_page; - - /* Reuse or allocate a page of ptes */ - if (pmd_present(pmd[pmdidx])) - pte_page = m2v(pmd[pmdidx].pmd); - else { - /* Check for free pte pages */ - if (ident_pte == ARRAY_SIZE(level1_ident_pgt)) - break; - - pte_page = &level1_ident_pgt[ident_pte]; - ident_pte += PTRS_PER_PTE; - - pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE); - } - - /* Install mappings */ - for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { - pte_t pte; - - if (pfn > max_pfn_mapped) - max_pfn_mapped = pfn; - - if (!pte_none(pte_page[pteidx])) - continue; - - pte = pfn_pte(pfn, PAGE_KERNEL_EXEC); - pte_page[pteidx] = pte; - } +#endif + return; /* PVH does not need any PV GDT ops. */ } + pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot; + pv_cpu_ops.load_gdt = xen_load_gdt_boot; - for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE) - set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO); - - set_page_prot(pmd, PAGE_KERNEL_RO); -} - -#ifdef CONFIG_X86_64 -static void convert_pfn_mfn(void *v) -{ - pte_t *pte = v; - int i; + setup_stack_canary_segment(0); + switch_to_new_gdt(0); - /* All levels are converted the same way, so just treat them - as ptes. */ - for (i = 0; i < PTRS_PER_PTE; i++) - pte[i] = xen_make_pte(pte[i].pte); + pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry; + pv_cpu_ops.load_gdt = xen_load_gdt; } /* - * Set up the inital kernel pagetable. - * - * We can construct this by grafting the Xen provided pagetable into - * head_64.S's preconstructed pagetables. We copy the Xen L2's into - * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This - * means that only the kernel has a physical mapping to start with - - * but that's enough to get __va working. We need to fill in the rest - * of the physical mapping once some sort of allocator has been set - * up. + * A PV guest starts with default flags that are not set for PVH, set them + * here asap. */ -static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, - unsigned long max_pfn) +static void xen_pvh_set_cr_flags(int cpu) { - pud_t *l3; - pmd_t *l2; - - /* Zap identity mapping */ - init_level4_pgt[0] = __pgd(0); - - /* Pre-constructed entries are in pfn, so convert to mfn */ - convert_pfn_mfn(init_level4_pgt); - convert_pfn_mfn(level3_ident_pgt); - convert_pfn_mfn(level3_kernel_pgt); - - l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud); - - memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - - l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); - memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - - /* Set up identity map */ - xen_map_identity_early(level2_ident_pgt, max_pfn); - - /* Make pagetable pieces RO */ - set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - - /* Pin down new L4 */ - pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa_symbol(init_level4_pgt))); - /* Unpin Xen-provided one */ - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - - /* Switch over */ - pgd = init_level4_pgt; + /* Some of these are setup in 'secondary_startup_64'. The others: + * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests + * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */ + write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM); + if (!cpu) + return; /* - * At this stage there can be no user pgd, and no page - * structure to attach it to, so make sure we just set kernel - * pgd. - */ - xen_mc_batch(); - __xen_write_cr3(true, __pa(pgd)); - xen_mc_issue(PARAVIRT_LAZY_CPU); + * For BSP, PSE PGE are set in probe_page_size_mask(), for APs + * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init. + */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); - reserve_early(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); - - return pgd; + if (cpu_has_pge) + set_in_cr4(X86_CR4_PGE); } -#else /* !CONFIG_X86_64 */ -static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss; -static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, - unsigned long max_pfn) +/* + * Note, that it is ref - because the only caller of this after init + * is PVH which is not going to use xen_load_gdt_boot or other + * __init functions. + */ +void __ref xen_pvh_secondary_vcpu_init(int cpu) { - pmd_t *kernel_pmd; - - init_pg_tables_start = __pa(pgd); - init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE; - max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024); - - kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); - memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); - - xen_map_identity_early(level2_kernel_pgt, max_pfn); - - memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD); - set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY], - __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT)); - - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); - set_page_prot(empty_zero_page, PAGE_KERNEL_RO); + xen_setup_gdt(cpu); + xen_pvh_set_cr_flags(cpu); +} - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); +static void __init xen_pvh_early_guest_init(void) +{ + if (!xen_feature(XENFEAT_auto_translated_physmap)) + return; - xen_write_cr3(__pa(swapper_pg_dir)); + if (!xen_feature(XENFEAT_hvm_callback_vector)) + return; - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + xen_have_vector_callback = 1; + xen_pvh_set_cr_flags(0); - return swapper_pg_dir; +#ifdef CONFIG_X86_32 + BUG(); /* PVH: Implement proper support. */ +#endif } -#endif /* CONFIG_X86_64 */ /* First C function to be called on Xen boot */ -asmlinkage void __init xen_start_kernel(void) +asmlinkage __visible void __init xen_start_kernel(void) { - pgd_t *pgd; + struct physdev_set_iopl set_iopl; + int rc; if (!xen_start_info) return; xen_domain_type = XEN_PV_DOMAIN; - BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0); - xen_setup_features(); + xen_pvh_early_guest_init(); + xen_setup_machphys_mapping(); /* 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; + if (!xen_pvh_domain()) + pv_cpu_ops = xen_cpu_ops; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + x86_init.resources.memory_setup = xen_auto_xlated_memory_setup; + else + x86_init.resources.memory_setup = xen_memory_setup; + x86_init.oem.arch_setup = xen_arch_setup; + x86_init.oem.banner = xen_banner; + + xen_init_time_ops(); + + /* + * Set up some pagetable state before starting to set any ptes. + */ + + xen_init_mmu_ops(); + + /* 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; + + /* + * Prevent page tables from being allocated in highmem, even + * if CONFIG_HIGHPTE is enabled. + */ + __userpte_alloc_gfp &= ~__GFP_HIGHMEM; + + /* Work out if we support NX */ + x86_configure_nx(); + + /* Get mfn list */ + xen_build_dynamic_phys_to_machine(); + + /* + * Set up kernel GDT and segment registers, mainly so that + * -fstack-protector code can be executed. + */ + xen_setup_gdt(0); 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 if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) { @@ -1649,47 +1596,74 @@ asmlinkage void __init xen_start_kernel(void) machine_ops = xen_machine_ops; -#ifdef CONFIG_X86_64 - /* Disable until direct per-cpu data access. */ - have_vcpu_info_placement = 0; - x86_64_init_pda(); -#endif + /* + * 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(); - /* Get mfn list */ - if (!xen_feature(XENFEAT_auto_translated_physmap)) - xen_build_dynamic_phys_to_machine(); - - pgd = (pgd_t *)xen_start_info->pt_base; - - /* Prevent unwanted bits from being set in PTEs. */ - __supported_pte_mask &= ~_PAGE_GLOBAL; - if (!xen_initial_domain()) - __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); - +#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 +#ifdef CONFIG_X86_PAT + /* + * For right now disable the PAT. We should remove this once + * git commit 8eaffa67b43e99ae581622c5133e20b0f48bcef1 + * (xen/pat: Disable PAT support for now) is reverted. + */ + pat_enabled = 0; +#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_disabled = true; + xen_raw_console_write("mapping kernel into physical memory\n"); - pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages); + xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages); - init_mm.pgd = pgd; + /* Allocate and initialize top and mid mfn levels for p2m structure */ + xen_build_mfn_list_list(); /* keep using Xen gdt for now; no urgent need to change it */ +#ifdef CONFIG_X86_32 pv_info.kernel_rpl = 1; if (xen_feature(XENFEAT_supervisor_mode_kernel)) pv_info.kernel_rpl = 0; - +#else + pv_info.kernel_rpl = 0; +#endif /* set the limit of our address space */ xen_reserve_top(); + /* PVH: runs at default kernel iopl of 0 */ + if (!xen_pvh_domain()) { + /* + * We used to do this in xen_arch_setup, but that is too late + * on AMD were early_cpu_init (run before ->arch_setup()) calls + * early_amd_init which pokes 0xcf8 port. + */ + set_iopl.iopl = 1; + rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); + if (rc != 0) + xen_raw_printk("physdev_op failed %d\n", rc); + } + #ifdef CONFIG_X86_32 /* set up basic CPUID stuff */ cpu_detect(&new_cpu_data); - new_cpu_data.hard_math = 1; + set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); + new_cpu_data.wp_works_ok = 1; new_cpu_data.x86_capability[0] = cpuid_edx(1); #endif @@ -1704,10 +1678,46 @@ asmlinkage void __init xen_start_kernel(void) add_preferred_console("xenboot", 0, NULL); add_preferred_console("tty", 0, NULL); add_preferred_console("hvc", 0, NULL); - } + 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); + struct xen_platform_op op = { + .cmd = XENPF_firmware_info, + .interface_version = XENPF_INTERFACE_VERSION, + .u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS, + }; + + 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; + + if (HYPERVISOR_dom0_op(&op) == 0) + boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; + + xen_init_apic(); + + /* Make sure ACS will be enabled */ + pci_request_acs(); + + xen_acpi_sleep_register(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = x86_init_uint_noop; + xen_boot_params_init_edd(); + } +#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); + /* Start the world */ #ifdef CONFIG_X86_32 i386_start_kernel(); @@ -1715,3 +1725,132 @@ asmlinkage void __init xen_start_kernel(void) x86_64_start_reservations((char *)__pa_symbol(&boot_params)); #endif } + +void __ref xen_hvm_init_shared_info(void) +{ + int cpu; + struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + + 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 (cpu >= MAX_VIRT_CPUS) + continue; + per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + } +} + +#ifdef CONFIG_XEN_PVHVM +static void __init init_hvm_pv_info(void) +{ + int major, minor; + uint32_t eax, ebx, ecx, edx, pages, msr, base; + u64 pfn; + + base = xen_cpuid_base(); + cpuid(base + 1, &eax, &ebx, &ecx, &edx); + + major = eax >> 16; + minor = eax & 0xffff; + printk(KERN_INFO "Xen version %d.%d.\n", major, minor); + + cpuid(base + 2, &pages, &msr, &ecx, &edx); + + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + xen_setup_features(); + + pv_info.name = "Xen HVM"; + + xen_domain_type = XEN_HVM_DOMAIN; +} + +static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + switch (action) { + case CPU_UP_PREPARE: + xen_vcpu_setup(cpu); + if (xen_have_vector_callback) { + if (xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_setup_timer(cpu); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block xen_hvm_cpu_notifier = { + .notifier_call = xen_hvm_cpu_notify, +}; + +static void __init xen_hvm_guest_init(void) +{ + init_hvm_pv_info(); + + xen_hvm_init_shared_info(); + + xen_panic_handler_init(); + + 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(); + x86_init.irqs.intr_init = xen_init_IRQ; + xen_hvm_init_time_ops(); + xen_hvm_init_mmu_ops(); +} + +static uint32_t __init xen_hvm_platform(void) +{ + if (xen_pv_domain()) + return 0; + + return xen_cpuid_base(); +} + +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, + .x2apic_available = xen_x2apic_para_available, +}; +EXPORT_SYMBOL(x86_hyper_xen_hvm); +#endif |