diff options
Diffstat (limited to 'arch/x86/xen')
-rw-r--r-- | arch/x86/xen/Makefile | 3 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 772 | ||||
-rw-r--r-- | arch/x86/xen/irq.c | 22 | ||||
-rw-r--r-- | arch/x86/xen/mmu.c | 753 | ||||
-rw-r--r-- | arch/x86/xen/mmu.h | 3 | ||||
-rw-r--r-- | arch/x86/xen/multicalls.h | 2 | ||||
-rw-r--r-- | arch/x86/xen/smp.c | 41 | ||||
-rw-r--r-- | arch/x86/xen/suspend.c | 1 | ||||
-rw-r--r-- | arch/x86/xen/xen-asm.S | 142 | ||||
-rw-r--r-- | arch/x86/xen/xen-asm.h | 12 | ||||
-rw-r--r-- | arch/x86/xen/xen-asm_32.S | 343 | ||||
-rw-r--r-- | arch/x86/xen/xen-asm_64.S | 252 | ||||
-rw-r--r-- | arch/x86/xen/xen-ops.h | 10 |
13 files changed, 1158 insertions, 1198 deletions
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 6dcefba7836..3b767d03fd6 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -6,7 +6,8 @@ CFLAGS_REMOVE_irq.o = -pg endif obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ - time.o xen-asm_$(BITS).o grant-table.o suspend.o + time.o xen-asm.o xen-asm_$(BITS).o \ + grant-table.o suspend.o obj-$(CONFIG_SMP) += smp.o spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
\ No newline at end of file diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bea215230b2..37230342c2c 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -61,40 +61,13 @@ 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. - */ -static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss; - -#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 */ - -/* - * 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the actual vcpu cr3; it is set once the - * hypercall to set the vcpu cr3 is complete (so it may be a little - * out of date, but it will never be set early).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 */ - struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); 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. @@ -114,14 +87,7 @@ 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; static void xen_vcpu_setup(int cpu) { @@ -237,7 +203,7 @@ static unsigned long xen_get_debugreg(int reg) return HYPERVISOR_get_debugreg(reg); } -static void xen_leave_lazy(void) +void xen_leave_lazy(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); xen_mc_flush(); @@ -598,83 +564,6 @@ static struct apic_ops xen_basic_apic_ops = { #endif -static void xen_flush_tlb(void) -{ - struct mmuext_op *op; - struct multicall_space mcs; - - preempt_disable(); - - 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(); -} - -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(); -} - -static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm, - unsigned long va) -{ - 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; - } - - MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); - - xen_mc_issue(PARAVIRT_LAZY_MMU); -} static void xen_clts(void) { @@ -700,21 +589,6 @@ 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; @@ -723,71 +597,6 @@ 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) -{ - x86_write_percpu(xen_current_cr3, (unsigned long)v); -} - -static void __xen_write_cr3(bool kernel, unsigned long cr3) -{ - 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); - } -} - -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; @@ -829,185 +638,6 @@ 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)) { @@ -1028,37 +658,6 @@ 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 */ void xen_setup_vcpu_info_placement(void) { @@ -1072,10 +671,10 @@ void xen_setup_vcpu_info_placement(void) 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; + 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; } } @@ -1133,49 +732,6 @@ 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); - -#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); - } -#endif -} - static const struct pv_info xen_info __initdata = { .paravirt_enabled = 1, .shared_kernel_pmd = 0, @@ -1271,87 +827,6 @@ static const struct pv_apic_ops xen_apic_ops __initdata = { #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 }; @@ -1394,223 +869,6 @@ static const struct machine_ops __initdata xen_machine_ops = { }; -static void __init xen_reserve_top(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; - - reserve_top_address(-top); -#endif /* CONFIG_X86_32 */ -} - -/* - * Like __va(), but returns address in the kernel mapping (which is - * all we have until the physical memory mapping has been set up. - */ -static void *__ka(phys_addr_t paddr) -{ -#ifdef CONFIG_X86_64 - return (void *)(paddr + __START_KERNEL_map); -#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)) - 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; - } - } - - 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; - - /* 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); -} - -/* - * 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. - */ -static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, - unsigned long max_pfn) -{ - 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; - - /* - * 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); - - 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; -} -#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) -{ - 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); - - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - - xen_write_cr3(__pa(swapper_pg_dir)); - - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); - - return swapper_pg_dir; -} -#endif /* CONFIG_X86_64 */ - /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { @@ -1650,10 +908,18 @@ 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(); + /* + * 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 + /* + * 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(); diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index bb042608c60..5a070900ad3 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -39,7 +39,7 @@ static unsigned long xen_save_fl(void) struct vcpu_info *vcpu; unsigned long flags; - vcpu = x86_read_percpu(xen_vcpu); + vcpu = percpu_read(xen_vcpu); /* flag has opposite sense of mask */ flags = !vcpu->evtchn_upcall_mask; @@ -50,6 +50,7 @@ static unsigned long xen_save_fl(void) */ return (-flags) & X86_EFLAGS_IF; } +PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl); static void xen_restore_fl(unsigned long flags) { @@ -62,7 +63,7 @@ static void xen_restore_fl(unsigned long flags) make sure we're don't switch CPUs between getting the vcpu pointer and updating the mask. */ preempt_disable(); - vcpu = x86_read_percpu(xen_vcpu); + vcpu = percpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = flags; preempt_enable_no_resched(); @@ -76,6 +77,7 @@ static void xen_restore_fl(unsigned long flags) xen_force_evtchn_callback(); } } +PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl); static void xen_irq_disable(void) { @@ -83,9 +85,10 @@ static void xen_irq_disable(void) make sure we're don't switch CPUs between getting the vcpu pointer and updating the mask. */ preempt_disable(); - x86_read_percpu(xen_vcpu)->evtchn_upcall_mask = 1; + percpu_read(xen_vcpu)->evtchn_upcall_mask = 1; preempt_enable_no_resched(); } +PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable); static void xen_irq_enable(void) { @@ -96,7 +99,7 @@ static void xen_irq_enable(void) the caller is confused and is trying to re-enable interrupts on an indeterminate processor. */ - vcpu = x86_read_percpu(xen_vcpu); + vcpu = percpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = 0; /* Doesn't matter if we get preempted here, because any @@ -106,6 +109,7 @@ static void xen_irq_enable(void) if (unlikely(vcpu->evtchn_upcall_pending)) xen_force_evtchn_callback(); } +PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable); static void xen_safe_halt(void) { @@ -124,10 +128,12 @@ static void xen_halt(void) static const struct pv_irq_ops xen_irq_ops __initdata = { .init_IRQ = __xen_init_IRQ, - .save_fl = xen_save_fl, - .restore_fl = xen_restore_fl, - .irq_disable = xen_irq_disable, - .irq_enable = xen_irq_enable, + + .save_fl = PV_CALLEE_SAVE(xen_save_fl), + .restore_fl = PV_CALLEE_SAVE(xen_restore_fl), + .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), + .irq_enable = PV_CALLEE_SAVE(xen_irq_enable), + .safe_halt = xen_safe_halt, .halt = xen_halt, #ifdef CONFIG_X86_64 diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 503c240e26c..d2e8ed1aff3 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -47,6 +47,7 @@ #include <asm/tlbflush.h> #include <asm/fixmap.h> #include <asm/mmu_context.h> +#include <asm/setup.h> #include <asm/paravirt.h> #include <asm/linkage.h> @@ -55,6 +56,8 @@ #include <xen/page.h> #include <xen/interface/xen.h> +#include <xen/interface/version.h> +#include <xen/hvc-console.h> #include "multicalls.h" #include "mmu.h" @@ -114,6 +117,37 @@ static inline void check_zero(void) #endif /* CONFIG_XEN_DEBUG_FS */ + +/* + * 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. + */ +static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss; + +#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 */ + +/* + * 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 */ + + /* * Just beyond the highest usermode address. STACK_TOP_MAX has a * redzone above it, so round it up to a PGD boundary. @@ -458,28 +492,33 @@ pteval_t xen_pte_val(pte_t pte) { return pte_mfn_to_pfn(pte.pte); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val); pgdval_t xen_pgd_val(pgd_t pgd) { return pte_mfn_to_pfn(pgd.pgd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val); pte_t xen_make_pte(pteval_t pte) { pte = pte_pfn_to_mfn(pte); return native_make_pte(pte); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); return native_make_pgd(pgd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd); pmdval_t xen_pmd_val(pmd_t pmd) { return pte_mfn_to_pfn(pmd.pmd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val); void xen_set_pud_hyper(pud_t *ptr, pud_t val) { @@ -556,12 +595,14 @@ pmd_t xen_make_pmd(pmdval_t pmd) pmd = pte_pfn_to_mfn(pmd); return native_make_pmd(pmd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); #if PAGETABLE_LEVELS == 4 pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val); pud_t xen_make_pud(pudval_t pud) { @@ -569,6 +610,7 @@ pud_t xen_make_pud(pudval_t pud) return native_make_pud(pud); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud); pgd_t *xen_get_user_pgd(pgd_t *pgd) { @@ -1063,18 +1105,14 @@ static void drop_other_mm_ref(void *info) struct mm_struct *mm = info; struct mm_struct *active_mm; -#ifdef CONFIG_X86_64 - active_mm = read_pda(active_mm); -#else - active_mm = __get_cpu_var(cpu_tlbstate).active_mm; -#endif + active_mm = percpu_read(cpu_tlbstate.active_mm); if (active_mm == mm) leave_mm(smp_processor_id()); /* If this cpu still has a stale cr3 reference, then make sure it has been flushed. */ - if (x86_read_percpu(xen_current_cr3) == __pa(mm->pgd)) { + if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) { load_cr3(swapper_pg_dir); arch_flush_lazy_cpu_mode(); } @@ -1156,6 +1194,709 @@ void xen_exit_mmap(struct mm_struct *mm) spin_unlock(&mm->page_table_lock); } +static __init void xen_pagetable_setup_start(pgd_t *base) +{ +} + +static __init void xen_pagetable_setup_done(pgd_t *base) +{ + xen_setup_shared_info(); +} + +static void xen_write_cr2(unsigned long cr2) +{ + percpu_read(xen_vcpu)->arch.cr2 = cr2; +} + +static unsigned long xen_read_cr2(void) +{ + return percpu_read(xen_vcpu)->arch.cr2; +} + +unsigned long xen_read_cr2_direct(void) +{ + return percpu_read(xen_vcpu_info.arch.cr2); +} + +static void xen_flush_tlb(void) +{ + struct mmuext_op *op; + struct multicall_space mcs; + + preempt_disable(); + + 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(); +} + +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(); +} + +static void xen_flush_tlb_others(const struct cpumask *cpus, + struct mm_struct *mm, unsigned long va) +{ + struct { + struct mmuext_op op; + DECLARE_BITMAP(mask, NR_CPUS); + } *args; + struct multicall_space mcs; + + BUG_ON(cpumask_empty(cpus)); + BUG_ON(!mm); + + mcs = xen_mc_entry(sizeof(*args)); + args = mcs.args; + args->op.arg2.vcpumask = to_cpumask(args->mask); + + /* Remove us, and any offline CPUS. */ + cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); + if (unlikely(cpumask_empty(to_cpumask(args->mask)))) + goto issue; + + 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; + } + + MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); + +issue: + xen_mc_issue(PARAVIRT_LAZY_MMU); +} + +static unsigned long xen_read_cr3(void) +{ + return percpu_read(xen_cr3); +} + +static void set_current_cr3(void *v) +{ + percpu_write(xen_current_cr3, (unsigned long)v); +} + +static void __xen_write_cr3(bool kernel, unsigned long cr3) +{ + 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) { + percpu_write(xen_cr3, cr3); + + /* Update xen_current_cr3 once the batch has actually + been submitted. */ + xen_mc_callback(set_current_cr3, (void *)cr3); + } +} + +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 */ + percpu_write(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_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 +} + +#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 + +/* 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); +} + +/* 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 + +void __init xen_reserve_top(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; + + reserve_top_address(-top); +#endif /* CONFIG_X86_32 */ +} + +/* + * Like __va(), but returns address in the kernel mapping (which is + * all we have until the physical memory mapping has been set up. + */ +static void *__ka(phys_addr_t paddr) +{ +#ifdef CONFIG_X86_64 + return (void *)(paddr + __START_KERNEL_map); +#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)) + 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; + } + } + + 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; + + /* 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); +} + +/* + * 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. + */ +__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, + unsigned long max_pfn) +{ + 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; + + /* + * 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); + + 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; +} +#else /* !CONFIG_X86_64 */ +static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss; + +__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, + unsigned long max_pfn) +{ + 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); + + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); + + xen_write_cr3(__pa(swapper_pg_dir)); + + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + + return swapper_pg_dir; +} +#endif /* CONFIG_X86_64 */ + +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); + +#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); + } +#endif +} + +__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(); +} + + +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 = PV_CALLEE_SAVE(xen_pte_val), + .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), + + .make_pte = PV_CALLEE_SAVE(xen_make_pte), + .make_pgd = PV_CALLEE_SAVE(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 = PV_CALLEE_SAVE(xen_make_pmd), + .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), + +#if PAGETABLE_LEVELS == 4 + .pud_val = PV_CALLEE_SAVE(xen_pud_val), + .make_pud = PV_CALLEE_SAVE(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, +}; + + #ifdef CONFIG_XEN_DEBUG_FS static struct dentry *d_mmu_debug; diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 98d71659da5..24d1b44a337 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -54,4 +54,7 @@ pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); +unsigned long xen_read_cr2_direct(void); + +extern const struct pv_mmu_ops xen_mmu_ops; #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h index fa3e10725d9..9e565da5d1f 100644 --- a/arch/x86/xen/multicalls.h +++ b/arch/x86/xen/multicalls.h @@ -41,7 +41,7 @@ static inline void xen_mc_issue(unsigned mode) xen_mc_flush(); /* restore flags saved in xen_mc_batch */ - local_irq_restore(x86_read_percpu(xen_mc_irq_flags)); + local_irq_restore(percpu_read(xen_mc_irq_flags)); } /* Set up a callback to be called when the current batch is flushed */ diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index c44e2069c7c..035582ae815 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -50,11 +50,7 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { -#ifdef CONFIG_X86_32 - __get_cpu_var(irq_stat).irq_resched_count++; -#else - add_pda(irq_resched_count, 1); -#endif + inc_irq_stat(irq_resched_count); return IRQ_HANDLED; } @@ -78,7 +74,7 @@ static __cpuinit void cpu_bringup(void) xen_setup_cpu_clockevents(); cpu_set(cpu, cpu_online_map); - x86_write_percpu(cpu_state, CPU_ONLINE); + percpu_write(cpu_state, CPU_ONLINE); wmb(); /* We can take interrupts now: we're officially "up". */ @@ -174,7 +170,7 @@ static void __init xen_smp_prepare_boot_cpu(void) /* We've switched to the "real" per-cpu gdt, so make sure the old memory can be recycled */ - make_lowmem_page_readwrite(&per_cpu_var(gdt_page)); + make_lowmem_page_readwrite(xen_initial_gdt); xen_setup_vcpu_info_placement(); } @@ -239,6 +235,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) ctxt->user_regs.ss = __KERNEL_DS; #ifdef CONFIG_X86_32 ctxt->user_regs.fs = __KERNEL_PERCPU; +#else + ctxt->gs_base_kernel = per_cpu_offset(cpu); #endif ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle; ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ @@ -283,23 +281,14 @@ static int __cpuinit xen_cpu_up(unsigned int cpu) struct task_struct *idle = idle_task(cpu); int rc; -#ifdef CONFIG_X86_64 - /* Allocate node local memory for AP pdas */ - WARN_ON(cpu == 0); - if (cpu > 0) { - rc = get_local_pda(cpu); - if (rc) - return rc; - } -#endif - -#ifdef CONFIG_X86_32 - init_gdt(cpu); per_cpu(current_task, cpu) = idle; +#ifdef CONFIG_X86_32 irq_ctx_init(cpu); #else - cpu_pda(cpu)->pcurrent = idle; clear_tsk_thread_flag(idle, TIF_FORK); + per_cpu(kernel_stack, cpu) = + (unsigned long)task_stack_page(idle) - + KERNEL_STACK_OFFSET + THREAD_SIZE; #endif xen_setup_timer(cpu); xen_init_lock_cpu(cpu); @@ -445,11 +434,7 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id) { irq_enter(); generic_smp_call_function_interrupt(); -#ifdef CONFIG_X86_32 - __get_cpu_var(irq_stat).irq_call_count++; -#else - add_pda(irq_call_count, 1); -#endif + inc_irq_stat(irq_call_count); irq_exit(); return IRQ_HANDLED; @@ -459,11 +444,7 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id) { irq_enter(); generic_smp_call_function_single_interrupt(); -#ifdef CONFIG_X86_32 - __get_cpu_var(irq_stat).irq_call_count++; -#else - add_pda(irq_call_count, 1); -#endif + inc_irq_stat(irq_call_count); irq_exit(); return IRQ_HANDLED; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 212ffe012b7..95be7b43472 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -6,6 +6,7 @@ #include <asm/xen/hypercall.h> #include <asm/xen/page.h> +#include <asm/fixmap.h> #include "xen-ops.h" #include "mmu.h" diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S new file mode 100644 index 00000000000..79d7362ad6d --- /dev/null +++ b/arch/x86/xen/xen-asm.S @@ -0,0 +1,142 @@ +/* + * Asm versions of Xen pv-ops, suitable for either direct use or + * inlining. The inline versions are the same as the direct-use + * versions, with the pre- and post-amble chopped off. + * + * This code is encoded for size rather than absolute efficiency, with + * a view to being able to inline as much as possible. + * + * We only bother with direct forms (ie, vcpu in percpu data) of the + * operations here; the indirect forms are better handled in C, since + * they're generally too large to inline anyway. + */ + +#include <asm/asm-offsets.h> +#include <asm/percpu.h> +#include <asm/processor-flags.h> + +#include "xen-asm.h" + +/* + * Enable events. This clears the event mask and tests the pending + * event status with one and operation. If there are pending events, + * then enter the hypervisor to get them handled. + */ +ENTRY(xen_irq_enable_direct) + /* Unmask events */ + movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + + /* + * Preempt here doesn't matter because that will deal with any + * pending interrupts. The pending check may end up being run + * on the wrong CPU, but that doesn't hurt. + */ + + /* Test for pending */ + testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending + jz 1f + +2: call check_events +1: +ENDPATCH(xen_irq_enable_direct) + ret + ENDPROC(xen_irq_enable_direct) + RELOC(xen_irq_enable_direct, 2b+1) + + +/* + * Disabling events is simply a matter of making the event mask + * non-zero. + */ +ENTRY(xen_irq_disable_direct) + movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask +ENDPATCH(xen_irq_disable_direct) + ret + ENDPROC(xen_irq_disable_direct) + RELOC(xen_irq_disable_direct, 0) + +/* + * (xen_)save_fl is used to get the current interrupt enable status. + * Callers expect the status to be in X86_EFLAGS_IF, and other bits + * may be set in the return value. We take advantage of this by + * making sure that X86_EFLAGS_IF has the right value (and other bits + * in that byte are 0), but other bits in the return value are + * undefined. We need to toggle the state of the bit, because Xen and + * x86 use opposite senses (mask vs enable). + */ +ENTRY(xen_save_fl_direct) + testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + setz %ah + addb %ah, %ah +ENDPATCH(xen_save_fl_direct) + ret + ENDPROC(xen_save_fl_direct) + RELOC(xen_save_fl_direct, 0) + + +/* + * In principle the caller should be passing us a value return from + * xen_save_fl_direct, but for robustness sake we test only the + * X86_EFLAGS_IF flag rather than the whole byte. After setting the + * interrupt mask state, it checks for unmasked pending events and + * enters the hypervisor to get them delivered if so. + */ +ENTRY(xen_restore_fl_direct) +#ifdef CONFIG_X86_64 + testw $X86_EFLAGS_IF, %di +#else + testb $X86_EFLAGS_IF>>8, %ah +#endif + setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + /* + * Preempt here doesn't matter because that will deal with any + * pending interrupts. The pending check may end up being run + * on the wrong CPU, but that doesn't hurt. + */ + + /* check for unmasked and pending */ + cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending + jz 1f +2: call check_events +1: +ENDPATCH(xen_restore_fl_direct) + ret + ENDPROC(xen_restore_fl_direct) + RELOC(xen_restore_fl_direct, 2b+1) + + +/* + * Force an event check by making a hypercall, but preserve regs + * before making the call. + */ +check_events: +#ifdef CONFIG_X86_32 + push %eax + push %ecx + push %edx + call xen_force_evtchn_callback + pop %edx + pop %ecx + pop %eax +#else + push %rax + push %rcx + push %rdx + push %rsi + push %rdi + push %r8 + push %r9 + push %r10 + push %r11 + call xen_force_evtchn_callback + pop %r11 + pop %r10 + pop %r9 + pop %r8 + pop %rdi + pop %rsi + pop %rdx + pop %rcx + pop %rax +#endif + ret diff --git a/arch/x86/xen/xen-asm.h b/arch/x86/xen/xen-asm.h new file mode 100644 index 00000000000..465276467a4 --- /dev/null +++ b/arch/x86/xen/xen-asm.h @@ -0,0 +1,12 @@ +#ifndef _XEN_XEN_ASM_H +#define _XEN_XEN_ASM_H + +#include <linux/linkage.h> + +#define RELOC(x, v) .globl x##_reloc; x##_reloc=v +#define ENDPATCH(x) .globl x##_end; x##_end=. + +/* Pseudo-flag used for virtual NMI, which we don't implement yet */ +#define XEN_EFLAGS_NMI 0x80000000 + +#endif diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index 42786f59d9c..88e15deb8b8 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -1,117 +1,43 @@ /* - Asm versions of Xen pv-ops, suitable for either direct use or inlining. - The inline versions are the same as the direct-use versions, with the - pre- and post-amble chopped off. - - This code is encoded for size rather than absolute efficiency, - with a view to being able to inline as much as possible. - - We only bother with direct forms (ie, vcpu in pda) of the operations - here; the indirect forms are better handled in C, since they're - generally too large to inline anyway. + * Asm versions of Xen pv-ops, suitable for either direct use or + * inlining. The inline versions are the same as the direct-use + * versions, with the pre- and post-amble chopped off. + * + * This code is encoded for size rather than absolute efficiency, with + * a view to being able to inline as much as possible. + * + * We only bother with direct forms (ie, vcpu in pda) of the + * operations here; the indirect forms are better handled in C, since + * they're generally too large to inline anyway. */ -#include <linux/linkage.h> - -#include <asm/asm-offsets.h> #include <asm/thread_info.h> -#include <asm/percpu.h> #include <asm/processor-flags.h> #include <asm/segment.h> #include <xen/interface/xen.h> -#define RELOC(x, v) .globl x##_reloc; x##_reloc=v -#define ENDPATCH(x) .globl x##_end; x##_end=. - -/* Pseudo-flag used for virtual NMI, which we don't implement yet */ -#define XEN_EFLAGS_NMI 0x80000000 - -/* - Enable events. This clears the event mask and tests the pending - event status with one and operation. If there are pending - events, then enter the hypervisor to get them handled. - */ -ENTRY(xen_irq_enable_direct) - /* Unmask events */ - movb $0, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask - - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* Test for pending */ - testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending - jz 1f - -2: call check_events -1: -ENDPATCH(xen_irq_enable_direct) - ret - ENDPROC(xen_irq_enable_direct) - RELOC(xen_irq_enable_direct, 2b+1) - - -/* - Disabling events is simply a matter of making the event mask - non-zero. - */ -ENTRY(xen_irq_disable_direct) - movb $1, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask -ENDPATCH(xen_irq_disable_direct) - ret - ENDPROC(xen_irq_disable_direct) - RELOC(xen_irq_disable_direct, 0) +#include "xen-asm.h" /* - (xen_)save_fl is used to get the current interrupt enable status. - Callers expect the status to be in X86_EFLAGS_IF, and other bits - may be set in the return value. We take advantage of this by - making sure that X86_EFLAGS_IF has the right value (and other bits - in that byte are 0), but other bits in the return value are - undefined. We need to toggle the state of the bit, because - Xen and x86 use opposite senses (mask vs enable). + * Force an event check by making a hypercall, but preserve regs + * before making the call. */ -ENTRY(xen_save_fl_direct) - testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask - setz %ah - addb %ah,%ah -ENDPATCH(xen_save_fl_direct) - ret - ENDPROC(xen_save_fl_direct) - RELOC(xen_save_fl_direct, 0) - - -/* - In principle the caller should be passing us a value return - from xen_save_fl_direct, but for robustness sake we test only - the X86_EFLAGS_IF flag rather than the whole byte. After - setting the interrupt mask state, it checks for unmasked - pending events and enters the hypervisor to get them delivered - if so. - */ -ENTRY(xen_restore_fl_direct) - testb $X86_EFLAGS_IF>>8, %ah - setz PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* check for unmasked and pending */ - cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending - jz 1f -2: call check_events -1: -ENDPATCH(xen_restore_fl_direct) +check_events: + push %eax + push %ecx + push %edx + call xen_force_evtchn_callback + pop %edx + pop %ecx + pop %eax ret - ENDPROC(xen_restore_fl_direct) - RELOC(xen_restore_fl_direct, 2b+1) /* - We can't use sysexit directly, because we're not running in ring0. - But we can easily fake it up using iret. Assuming xen_sysexit - is jumped to with a standard stack frame, we can just strip it - back to a standard iret frame and use iret. + * We can't use sysexit directly, because we're not running in ring0. + * But we can easily fake it up using iret. Assuming xen_sysexit is + * jumped to with a standard stack frame, we can just strip it back to + * a standard iret frame and use iret. */ ENTRY(xen_sysexit) movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ @@ -122,33 +48,31 @@ ENTRY(xen_sysexit) ENDPROC(xen_sysexit) /* - This is run where a normal iret would be run, with the same stack setup: - 8: eflags - 4: cs - esp-> 0: eip - - This attempts to make sure that any pending events are dealt - with on return to usermode, but there is a small window in - which an event can happen just before entering usermode. If - the nested interrupt ends up setting one of the TIF_WORK_MASK - pending work flags, they will not be tested again before - returning to usermode. This means that a process can end up - with pending work, which will be unprocessed until the process - enters and leaves the kernel again, which could be an - unbounded amount of time. This means that a pending signal or - reschedule event could be indefinitely delayed. - - The fix is to notice a nested interrupt in the critical - window, and if one occurs, then fold the nested interrupt into - the current interrupt stack frame, and re-process it - iteratively rather than recursively. This means that it will - exit via the normal path, and all pending work will be dealt - with appropriately. - - Because the nested interrupt handler needs to deal with the - current stack state in whatever form its in, we keep things - simple by only using a single register which is pushed/popped - on the stack. + * This is run where a normal iret would be run, with the same stack setup: + * 8: eflags + * 4: cs + * esp-> 0: eip + * + * This attempts to make sure that any pending events are dealt with + * on return to usermode, but there is a small window in which an + * event can happen just before entering usermode. If the nested + * interrupt ends up setting one of the TIF_WORK_MASK pending work + * flags, they will not be tested again before returning to + * usermode. This means that a process can end up with pending work, + * which will be unprocessed until the process enters and leaves the + * kernel again, which could be an unbounded amount of time. This + * means that a pending signal or reschedule event could be + * indefinitely delayed. + * + * The fix is to notice a nested interrupt in the critical window, and + * if one occurs, then fold the nested interrupt into the current + * interrupt stack frame, and re-process it iteratively rather than + * recursively. This means that it will exit via the normal path, and + * all pending work will be dealt with appropriately. + * + * Because the nested interrupt handler needs to deal with the current + * stack state in whatever form its in, we keep things simple by only + * using a single register which is pushed/popped on the stack. */ ENTRY(xen_iret) /* test eflags for special cases */ @@ -158,13 +82,15 @@ ENTRY(xen_iret) push %eax ESP_OFFSET=4 # bytes pushed onto stack - /* Store vcpu_info pointer for easy access. Do it this - way to avoid having to reload %fs */ + /* + * Store vcpu_info pointer for easy access. Do it this way to + * avoid having to reload %fs + */ #ifdef CONFIG_SMP GET_THREAD_INFO(%eax) - movl TI_cpu(%eax),%eax - movl __per_cpu_offset(,%eax,4),%eax - mov per_cpu__xen_vcpu(%eax),%eax + movl TI_cpu(%eax), %eax + movl __per_cpu_offset(,%eax,4), %eax + mov per_cpu__xen_vcpu(%eax), %eax #else movl per_cpu__xen_vcpu, %eax #endif @@ -172,37 +98,46 @@ ENTRY(xen_iret) /* check IF state we're restoring */ testb $X86_EFLAGS_IF>>8, 8+1+ESP_OFFSET(%esp) - /* Maybe enable events. Once this happens we could get a - recursive event, so the critical region starts immediately - afterwards. However, if that happens we don't end up - resuming the code, so we don't have to be worried about - being preempted to another CPU. */ + /* + * Maybe enable events. Once this happens we could get a + * recursive event, so the critical region starts immediately + * afterwards. However, if that happens we don't end up + * resuming the code, so we don't have to be worried about + * being preempted to another CPU. + */ setz XEN_vcpu_info_mask(%eax) xen_iret_start_crit: /* check for unmasked and pending */ cmpw $0x0001, XEN_vcpu_info_pending(%eax) - /* If there's something pending, mask events again so we - can jump back into xen_hypervisor_callback */ + /* + * If there's something pending, mask events again so we can + * jump back into xen_hypervisor_callback + */ sete XEN_vcpu_info_mask(%eax) popl %eax - /* From this point on the registers are restored and the stack - updated, so we don't need to worry about it if we're preempted */ + /* + * From this point on the registers are restored and the stack + * updated, so we don't need to worry about it if we're + * preempted + */ iret_restore_end: - /* Jump to hypervisor_callback after fixing up the stack. - Events are masked, so jumping out of the critical - region is OK. */ + /* + * Jump to hypervisor_callback after fixing up the stack. + * Events are masked, so jumping out of the critical region is + * OK. + */ je xen_hypervisor_callback 1: iret xen_iret_end_crit: -.section __ex_table,"a" +.section __ex_table, "a" .align 4 - .long 1b,iret_exc + .long 1b, iret_exc .previous hyper_iret: @@ -212,55 +147,55 @@ hyper_iret: .globl xen_iret_start_crit, xen_iret_end_crit /* - This is called by xen_hypervisor_callback in entry.S when it sees - that the EIP at the time of interrupt was between xen_iret_start_crit - and xen_iret_end_crit. We're passed the EIP in %eax so we can do - a more refined determination of what to do. - - The stack format at this point is: - ---------------- - ss : (ss/esp may be present if we came from usermode) - esp : - eflags } outer exception info - cs } - eip } - ---------------- <- edi (copy dest) - eax : outer eax if it hasn't been restored - ---------------- - eflags } nested exception info - cs } (no ss/esp because we're nested - eip } from the same ring) - orig_eax }<- esi (copy src) - - - - - - - - - - fs } - es } - ds } SAVE_ALL state - eax } - : : - ebx }<- esp - ---------------- - - In order to deliver the nested exception properly, we need to shift - everything from the return addr up to the error code so it - sits just under the outer exception info. This means that when we - handle the exception, we do it in the context of the outer exception - rather than starting a new one. - - The only caveat is that if the outer eax hasn't been - restored yet (ie, it's still on stack), we need to insert - its value into the SAVE_ALL state before going on, since - it's usermode state which we eventually need to restore. + * This is called by xen_hypervisor_callback in entry.S when it sees + * that the EIP at the time of interrupt was between + * xen_iret_start_crit and xen_iret_end_crit. We're passed the EIP in + * %eax so we can do a more refined determination of what to do. + * + * The stack format at this point is: + * ---------------- + * ss : (ss/esp may be present if we came from usermode) + * esp : + * eflags } outer exception info + * cs } + * eip } + * ---------------- <- edi (copy dest) + * eax : outer eax if it hasn't been restored + * ---------------- + * eflags } nested exception info + * cs } (no ss/esp because we're nested + * eip } from the same ring) + * orig_eax }<- esi (copy src) + * - - - - - - - - + * fs } + * es } + * ds } SAVE_ALL state + * eax } + * : : + * ebx }<- esp + * ---------------- + * + * In order to deliver the nested exception properly, we need to shift + * everything from the return addr up to the error code so it sits + * just under the outer exception info. This means that when we + * handle the exception, we do it in the context of the outer + * exception rather than starting a new one. + * + * The only caveat is that if the outer eax hasn't been restored yet + * (ie, it's still on stack), we need to insert its value into the + * SAVE_ALL state before going on, since it's usermode state which we + * eventually need to restore. */ ENTRY(xen_iret_crit_fixup) /* - Paranoia: Make sure we're really coming from kernel space. - One could imagine a case where userspace jumps into the - critical range address, but just before the CPU delivers a GP, - it decides to deliver an interrupt instead. Unlikely? - Definitely. Easy to avoid? Yes. The Intel documents - explicitly say that the reported EIP for a bad jump is the - jump instruction itself, not the destination, but some virtual - environments get this wrong. + * Paranoia: Make sure we're really coming from kernel space. + * One could imagine a case where userspace jumps into the + * critical range address, but just before the CPU delivers a + * GP, it decides to deliver an interrupt instead. Unlikely? + * Definitely. Easy to avoid? Yes. The Intel documents + * explicitly say that the reported EIP for a bad jump is the + * jump instruction itself, not the destination, but some + * virtual environments get this wrong. */ movl PT_CS(%esp), %ecx andl $SEGMENT_RPL_MASK, %ecx @@ -270,15 +205,17 @@ ENTRY(xen_iret_crit_fixup) lea PT_ORIG_EAX(%esp), %esi lea PT_EFLAGS(%esp), %edi - /* If eip is before iret_restore_end then stack - hasn't been restored yet. */ + /* + * If eip is before iret_restore_end then stack + * hasn't been restored yet. + */ cmp $iret_restore_end, %eax jae 1f - movl 0+4(%edi),%eax /* copy EAX (just above top of frame) */ + movl 0+4(%edi), %eax /* copy EAX (just above top of frame) */ movl %eax, PT_EAX(%esp) - lea ESP_OFFSET(%edi),%edi /* move dest up over saved regs */ + lea ESP_OFFSET(%edi), %edi /* move dest up over saved regs */ /* set up the copy */ 1: std @@ -286,20 +223,6 @@ ENTRY(xen_iret_crit_fixup) rep movsl cld - lea 4(%edi),%esp /* point esp to new frame */ + lea 4(%edi), %esp /* point esp to new frame */ 2: jmp xen_do_upcall - -/* - Force an event check by making a hypercall, - but preserve regs before making the call. - */ -check_events: - push %eax - push %ecx - push %edx - call xen_force_evtchn_callback - pop %edx - pop %ecx - pop %eax - ret diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 05794c566e8..02f496a8dba 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -1,174 +1,45 @@ /* - Asm versions of Xen pv-ops, suitable for either direct use or inlining. - The inline versions are the same as the direct-use versions, with the - pre- and post-amble chopped off. - - This code is encoded for size rather than absolute efficiency, - with a view to being able to inline as much as possible. - - We only bother with direct forms (ie, vcpu in pda) of the operations - here; the indirect forms are better handled in C, since they're - generally too large to inline anyway. + * Asm versions of Xen pv-ops, suitable for either direct use or + * inlining. The inline versions are the same as the direct-use + * versions, with the pre- and post-amble chopped off. + * + * This code is encoded for size rather than absolute efficiency, with + * a view to being able to inline as much as possible. + * + * We only bother with direct forms (ie, vcpu in pda) of the + * operations here; the indirect forms are better handled in C, since + * they're generally too large to inline anyway. */ -#include <linux/linkage.h> - -#include <asm/asm-offsets.h> -#include <asm/processor-flags.h> #include <asm/errno.h> +#include <asm/percpu.h> +#include <asm/processor-flags.h> #include <asm/segment.h> #include <xen/interface/xen.h> -#define RELOC(x, v) .globl x##_reloc; x##_reloc=v -#define ENDPATCH(x) .globl x##_end; x##_end=. - -/* Pseudo-flag used for virtual NMI, which we don't implement yet */ -#define XEN_EFLAGS_NMI 0x80000000 - -#if 1 -/* - x86-64 does not yet support direct access to percpu variables - via a segment override, so we just need to make sure this code - never gets used - */ -#define BUG ud2a -#define PER_CPU_VAR(var, off) 0xdeadbeef -#endif - -/* - Enable events. This clears the event mask and tests the pending - event status with one and operation. If there are pending - events, then enter the hypervisor to get them handled. - */ -ENTRY(xen_irq_enable_direct) - BUG - - /* Unmask events */ - movb $0, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) - - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* Test for pending */ - testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending) - jz 1f - -2: call check_events -1: -ENDPATCH(xen_irq_enable_direct) - ret - ENDPROC(xen_irq_enable_direct) - RELOC(xen_irq_enable_direct, 2b+1) - -/* - Disabling events is simply a matter of making the event mask - non-zero. - */ -ENTRY(xen_irq_disable_direct) - BUG - - movb $1, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) -ENDPATCH(xen_irq_disable_direct) - ret - ENDPROC(xen_irq_disable_direct) - RELOC(xen_irq_disable_direct, 0) - -/* - (xen_)save_fl is used to get the current interrupt enable status. - Callers expect the status to be in X86_EFLAGS_IF, and other bits - may be set in the return value. We take advantage of this by - making sure that X86_EFLAGS_IF has the right value (and other bits - in that byte are 0), but other bits in the return value are - undefined. We need to toggle the state of the bit, because - Xen and x86 use opposite senses (mask vs enable). - */ -ENTRY(xen_save_fl_direct) - BUG - - testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) - setz %ah - addb %ah,%ah -ENDPATCH(xen_save_fl_direct) - ret - ENDPROC(xen_save_fl_direct) - RELOC(xen_save_fl_direct, 0) - -/* - In principle the caller should be passing us a value return - from xen_save_fl_direct, but for robustness sake we test only - the X86_EFLAGS_IF flag rather than the whole byte. After - setting the interrupt mask state, it checks for unmasked - pending events and enters the hypervisor to get them delivered - if so. - */ -ENTRY(xen_restore_fl_direct) - BUG - - testb $X86_EFLAGS_IF>>8, %ah - setz PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* check for unmasked and pending */ - cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending) - jz 1f -2: call check_events -1: -ENDPATCH(xen_restore_fl_direct) - ret - ENDPROC(xen_restore_fl_direct) - RELOC(xen_restore_fl_direct, 2b+1) - - -/* - Force an event check by making a hypercall, - but preserve regs before making the call. - */ -check_events: - push %rax - push %rcx - push %rdx - push %rsi - push %rdi - push %r8 - push %r9 - push %r10 - push %r11 - call xen_force_evtchn_callback - pop %r11 - pop %r10 - pop %r9 - pop %r8 - pop %rdi - pop %rsi - pop %rdx - pop %rcx - pop %rax - ret +#include "xen-asm.h" ENTRY(xen_adjust_exception_frame) - mov 8+0(%rsp),%rcx - mov 8+8(%rsp),%r11 + mov 8+0(%rsp), %rcx + mov 8+8(%rsp), %r11 ret $16 hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* - Xen64 iret frame: - - ss - rsp - rflags - cs - rip <-- standard iret frame - - flags - - rcx } - r11 }<-- pushed by hypercall page -rsp -> rax } + * Xen64 iret frame: + * + * ss + * rsp + * rflags + * cs + * rip <-- standard iret frame + * + * flags + * + * rcx } + * r11 }<-- pushed by hypercall page + * rsp->rax } */ ENTRY(xen_iret) pushq $0 @@ -177,8 +48,8 @@ ENDPATCH(xen_iret) RELOC(xen_iret, 1b+1) /* - sysexit is not used for 64-bit processes, so it's - only ever used to return to 32-bit compat userspace. + * sysexit is not used for 64-bit processes, so it's only ever used to + * return to 32-bit compat userspace. */ ENTRY(xen_sysexit) pushq $__USER32_DS @@ -193,13 +64,15 @@ ENDPATCH(xen_sysexit) RELOC(xen_sysexit, 1b+1) ENTRY(xen_sysret64) - /* We're already on the usermode stack at this point, but still - with the kernel gs, so we can easily switch back */ - movq %rsp, %gs:pda_oldrsp - movq %gs:pda_kernelstack,%rsp + /* + * We're already on the usermode stack at this point, but + * still with the kernel gs, so we can easily switch back + */ + movq %rsp, PER_CPU_VAR(old_rsp) + movq PER_CPU_VAR(kernel_stack), %rsp pushq $__USER_DS - pushq %gs:pda_oldrsp + pushq PER_CPU_VAR(old_rsp) pushq %r11 pushq $__USER_CS pushq %rcx @@ -210,13 +83,15 @@ ENDPATCH(xen_sysret64) RELOC(xen_sysret64, 1b+1) ENTRY(xen_sysret32) - /* We're already on the usermode stack at this point, but still - with the kernel gs, so we can easily switch back */ - movq %rsp, %gs:pda_oldrsp - movq %gs:pda_kernelstack, %rsp + /* + * We're already on the usermode stack at this point, but + * still with the kernel gs, so we can easily switch back + */ + movq %rsp, PER_CPU_VAR(old_rsp) + movq PER_CPU_VAR(kernel_stack), %rsp pushq $__USER32_DS - pushq %gs:pda_oldrsp + pushq PER_CPU_VAR(old_rsp) pushq %r11 pushq $__USER32_CS pushq %rcx @@ -227,28 +102,27 @@ ENDPATCH(xen_sysret32) RELOC(xen_sysret32, 1b+1) /* - Xen handles syscall callbacks much like ordinary exceptions, - which means we have: - - kernel gs - - kernel rsp - - an iret-like stack frame on the stack (including rcx and r11): - ss - rsp - rflags - cs - rip - r11 - rsp-> rcx - - In all the entrypoints, we undo all that to make it look - like a CPU-generated syscall/sysenter and jump to the normal - entrypoint. + * Xen handles syscall callbacks much like ordinary exceptions, which + * means we have: + * - kernel gs + * - kernel rsp + * - an iret-like stack frame on the stack (including rcx and r11): + * ss + * rsp + * rflags + * cs + * rip + * r11 + * rsp->rcx + * + * In all the entrypoints, we undo all that to make it look like a + * CPU-generated syscall/sysenter and jump to the normal entrypoint. */ .macro undo_xen_syscall - mov 0*8(%rsp),%rcx - mov 1*8(%rsp),%r11 - mov 5*8(%rsp),%rsp + mov 0*8(%rsp), %rcx + mov 1*8(%rsp), %r11 + mov 5*8(%rsp), %rsp .endm /* Normal 64-bit system call target */ @@ -275,7 +149,7 @@ ENDPROC(xen_sysenter_target) ENTRY(xen_syscall32_target) ENTRY(xen_sysenter_target) - lea 16(%rsp), %rsp /* strip %rcx,%r11 */ + lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $VGCF_in_syscall jmp hypercall_iret diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index c1f8faf0a2c..2f5ef2632ea 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -10,9 +10,12 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; +extern void *xen_initial_gdt; + struct trap_info; void xen_copy_trap_info(struct trap_info *traps); +DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); @@ -22,6 +25,13 @@ extern struct shared_info *HYPERVISOR_shared_info; void xen_setup_mfn_list_list(void); void xen_setup_shared_info(void); +void xen_setup_machphys_mapping(void); +pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); +void xen_ident_map_ISA(void); +void xen_reserve_top(void); + +void xen_leave_lazy(void); +void xen_post_allocator_init(void); char * __init xen_memory_setup(void); void __init xen_arch_setup(void); |