diff options
Diffstat (limited to 'arch/x86/xen/enlighten.c')
| -rw-r--r-- | arch/x86/xen/enlighten.c | 68 |
1 files changed, 67 insertions, 1 deletions
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index e11efbd..81afe1b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -275,6 +275,7 @@ static void __init xen_init_cpuid_mask(void) ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ (1 << X86_FEATURE_ACPI)); /* disable ACPI */ ax = 1; + cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); xsave_mask = @@ -320,6 +321,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte_t pte; unsigned long pfn; struct page *page; + unsigned char dummy; ptep = lookup_address((unsigned long)v, &level); BUG_ON(ptep == NULL); @@ -329,6 +331,32 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte = pfn_pte(pfn, prot); + /* + * Careful: update_va_mapping() will fail if the virtual address + * we're poking isn't populated in the page tables. We don't + * need to worry about the direct map (that's always in the page + * tables), but we need to be careful about vmap space. In + * particular, the top level page table can lazily propagate + * entries between processes, so if we've switched mms since we + * vmapped the target in the first place, we might not have the + * top-level page table entry populated. + * + * We disable preemption because we want the same mm active when + * we probe the target and when we issue the hypercall. We'll + * have the same nominal mm, but if we're a kernel thread, lazy + * mm dropping could change our pgd. + * + * Out of an abundance of caution, this uses __get_user() to fault + * in the target address just in case there's some obscure case + * in which the target address isn't readable. + */ + + preempt_disable(); + + pagefault_disable(); /* Avoid warnings due to being atomic. */ + __get_user(dummy, (unsigned char __user __force *)v); + pagefault_enable(); + if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); @@ -340,6 +368,8 @@ static void set_aliased_prot(void *v, pgprot_t prot) BUG(); } else kmap_flush_unused(); + + preempt_enable(); } static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) @@ -347,6 +377,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; int i; + /* + * We need to mark the all aliases of the LDT pages RO. We + * don't need to call vm_flush_aliases(), though, since that's + * only responsible for flushing aliases out the TLBs, not the + * page tables, and Xen will flush the TLB for us if needed. + * + * To avoid confusing future readers: none of this is necessary + * to load the LDT. The hypervisor only checks this when the + * LDT is faulted in due to subsequent descriptor access. + */ + for(i = 0; i < entries; i += entries_per_page) set_aliased_prot(ldt + i, PAGE_KERNEL_RO); } @@ -365,6 +406,8 @@ 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; @@ -520,6 +563,8 @@ 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(); @@ -589,6 +634,8 @@ 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 = __this_cpu_read(idt_desc.address); @@ -643,6 +690,8 @@ 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; @@ -661,6 +710,8 @@ 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) { @@ -689,6 +740,8 @@ static void xen_write_gdt_entry(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: @@ -708,7 +761,9 @@ static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry, 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); } @@ -970,6 +1025,10 @@ 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", }; @@ -1000,7 +1059,10 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, + .rdmsr_regs = native_rdmsr_safe_regs, .write_msr = xen_write_msr_safe, + .wrmsr_regs = native_wrmsr_safe_regs, + .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, @@ -1298,6 +1360,10 @@ asmlinkage void __init xen_start_kernel(void) /* Make sure ACS will be enabled */ pci_request_acs(); + + /* 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; } #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ |