X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=arch%2Fx86%2Fxen%2Fmmu.c;h=4ceb28581652ef0ab7ff7bcc5426dd914954d100;hb=4aac047323e3082d0866b8ad3784236632105af4;hp=688936044dc95cdac8d6ce79e3ee10f39e898178;hpb=cb110171a65c5a2d85ec814d498986db611040fd;p=safe%2Fjmp%2Flinux-2.6 diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 6889360..4ceb285 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,11 +42,13 @@ #include #include #include +#include #include #include #include #include +#include #include #include @@ -55,6 +57,8 @@ #include #include +#include +#include #include "multicalls.h" #include "mmu.h" @@ -114,6 +118,37 @@ 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the actual vcpu cr3; it is set once the + * hypercall to set the vcpu cr3 is complete (so it may be a little + * out of date, but it will never be set early).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. @@ -150,21 +185,24 @@ static inline unsigned p2m_index(unsigned long pfn) } /* Build the parallel p2m_top_mfn structures */ -void xen_setup_mfn_list_list(void) +static void __init xen_build_mfn_list_list(void) { unsigned pfn, idx; - for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) { + for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) { unsigned topidx = p2m_top_index(pfn); p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]); } - for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) { + for (idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) { unsigned topidx = idx * P2M_ENTRIES_PER_PAGE; p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]); } +} +void xen_setup_mfn_list_list(void) +{ BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = @@ -179,11 +217,13 @@ void __init xen_build_dynamic_phys_to_machine(void) unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages); unsigned pfn; - for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) { + for (pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) { unsigned topidx = p2m_top_index(pfn); p2m_top[topidx] = &mfn_list[pfn]; } + + xen_build_mfn_list_list(); } unsigned long get_phys_to_machine(unsigned long pfn) @@ -199,47 +239,81 @@ unsigned long get_phys_to_machine(unsigned long pfn) } EXPORT_SYMBOL_GPL(get_phys_to_machine); -static void alloc_p2m(unsigned long **pp, unsigned long *mfnp) +/* install a new p2m_top page */ +bool install_p2mtop_page(unsigned long pfn, unsigned long *p) { - unsigned long *p; + unsigned topidx = p2m_top_index(pfn); + unsigned long **pfnp, *mfnp; unsigned i; - p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); - BUG_ON(p == NULL); + pfnp = &p2m_top[topidx]; + mfnp = &p2m_top_mfn[topidx]; - for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++) + for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++) p[i] = INVALID_P2M_ENTRY; - if (cmpxchg(pp, p2m_missing, p) != p2m_missing) - free_page((unsigned long)p); - else + if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) { *mfnp = virt_to_mfn(p); + return true; + } + + return false; } -void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +static void alloc_p2m(unsigned long pfn) { - unsigned topidx, idx; + unsigned long *p; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return; - } + p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); + BUG_ON(p == NULL); + + if (!install_p2mtop_page(pfn, p)) + free_page((unsigned long)p); +} + +/* Try to install p2m mapping; fail if intermediate bits missing */ +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, idx; if (unlikely(pfn >= MAX_DOMAIN_PAGES)) { BUG_ON(mfn != INVALID_P2M_ENTRY); - return; + return true; } topidx = p2m_top_index(pfn); if (p2m_top[topidx] == p2m_missing) { - /* no need to allocate a page to store an invalid entry */ if (mfn == INVALID_P2M_ENTRY) - return; - alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]); + return true; + return false; } idx = p2m_index(pfn); p2m_top[topidx][idx] = mfn; + + return true; +} + +void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + + if (unlikely(!__set_phys_to_machine(pfn, mfn))) { + alloc_p2m(pfn); + + if (!__set_phys_to_machine(pfn, mfn)) + BUG(); + } +} + +unsigned long arbitrary_virt_to_mfn(void *vaddr) +{ + xmaddr_t maddr = arbitrary_virt_to_machine(vaddr); + + return PFN_DOWN(maddr.maddr); } xmaddr_t arbitrary_virt_to_machine(void *vaddr) @@ -378,10 +452,6 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { - /* updates to init_mm may be done without lock */ - if (mm == &init_mm) - preempt_disable(); - ADD_STATS(set_pte_at, 1); // ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep)); ADD_STATS(set_pte_at_current, mm == current->mm); @@ -402,12 +472,11 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, } xen_set_pte(ptep, pteval); -out: - if (mm == &init_mm) - preempt_enable(); +out: return; } -pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { /* Just return the pte as-is. We preserve the bits on commit */ return *ptep; @@ -457,28 +526,33 @@ 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) { @@ -555,12 +629,14 @@ 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) { @@ -568,6 +644,7 @@ 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) { @@ -661,12 +738,11 @@ void xen_set_pgd(pgd_t *ptr, pgd_t val) * For 64-bit, we must skip the Xen hole in the middle of the address * space, just after the big x86-64 virtual hole. */ -static int xen_pgd_walk(struct mm_struct *mm, - int (*func)(struct mm_struct *mm, struct page *, - enum pt_level), - unsigned long limit) +static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, + int (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + unsigned long limit) { - pgd_t *pgd = mm->pgd; int flush = 0; unsigned hole_low, hole_high; unsigned pgdidx_limit, pudidx_limit, pmdidx_limit; @@ -753,6 +829,14 @@ out: return flush; } +static int xen_pgd_walk(struct mm_struct *mm, + int (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + unsigned long limit) +{ + return __xen_pgd_walk(mm, mm->pgd, func, limit); +} + /* If we're using split pte locks, then take the page's lock and return a pointer to it. Otherwise return NULL. */ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) @@ -854,7 +938,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd) xen_mc_batch(); - if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) { + if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) { /* re-enable interrupts for flushing */ xen_mc_issue(0); @@ -871,7 +955,8 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd) if (user_pgd) { xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD); - xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(user_pgd))); + xen_do_pin(MMUEXT_PIN_L4_TABLE, + PFN_DOWN(__pa(user_pgd))); } } #else /* CONFIG_X86_32 */ @@ -929,7 +1014,7 @@ static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page, return 0; } -void __init xen_mark_init_mm_pinned(void) +static void __init xen_mark_init_mm_pinned(void) { xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -986,7 +1071,8 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd) pgd_t *user_pgd = xen_get_user_pgd(pgd); if (user_pgd) { - xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(user_pgd))); + xen_do_pin(MMUEXT_UNPIN_TABLE, + PFN_DOWN(__pa(user_pgd))); xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD); } } @@ -998,7 +1084,7 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd) PT_PMD); #endif - xen_pgd_walk(mm, xen_unpin_page, USER_LIMIT); + __xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT); xen_mc_issue(0); } @@ -1053,26 +1139,20 @@ 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(); - } } static void xen_drop_mm_ref(struct mm_struct *mm) { - cpumask_t mask; + cpumask_var_t mask; unsigned cpu; if (current->active_mm == mm) { @@ -1080,11 +1160,19 @@ static void xen_drop_mm_ref(struct mm_struct *mm) load_cr3(swapper_pg_dir); else leave_mm(smp_processor_id()); - arch_flush_lazy_cpu_mode(); } /* Get the "official" set of cpus referring to our pagetable. */ - mask = mm->cpu_vm_mask; + if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) { + for_each_online_cpu(cpu) { + if (!cpumask_test_cpu(cpu, &mm->cpu_vm_mask) + && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) + continue; + smp_call_function_single(cpu, drop_other_mm_ref, mm, 1); + } + return; + } + cpumask_copy(mask, &mm->cpu_vm_mask); /* It's possible that a vcpu may have a stale reference to our cr3, because its in lazy mode, and it hasn't yet flushed @@ -1093,11 +1181,12 @@ static void xen_drop_mm_ref(struct mm_struct *mm) if needed. */ for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd)) - cpu_set(cpu, mask); + cpumask_set_cpu(cpu, mask); } - if (!cpus_empty(mask)) - smp_call_function_mask(mask, drop_other_mm_ref, mm, 1); + if (!cpumask_empty(mask)) + smp_call_function_many(mask, drop_other_mm_ref, mm, 1); + free_cpumask_var(mask); } #else static void xen_drop_mm_ref(struct mm_struct *mm) @@ -1136,6 +1225,736 @@ 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; + + if (cpumask_empty(cpus)) + return; /* nothing to do */ + + 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 (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 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 + +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(); +} + +/* 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))); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); +} + +/* Used for pmd and pud */ +static __init void xen_alloc_pmd_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 __init void xen_release_pte_init(unsigned long pfn) +{ + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); +} + +static __init void xen_release_pmd_init(unsigned long pfn) +{ + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); +} + +/* 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; + + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + + xen_start_info->nr_pt_frames * PAGE_SIZE + + 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))); + + 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 swapper_pg_dir; +} +#endif /* CONFIG_X86_64 */ + +static void xen_set_fixmap(unsigned idx, phys_addr_t 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 + case FIX_TEXT_POKE0: + case FIX_TEXT_POKE1: + /* All local page mappings */ + 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(); +} + +static void xen_leave_lazy_mmu(void) +{ + preempt_disable(); + xen_mc_flush(); + paravirt_leave_lazy_mmu(); + preempt_enable(); +} + +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_pmd_init, + .alloc_pmd_clone = paravirt_nop, + .release_pmd = xen_release_pmd_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, + .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_pmd_init, + .release_pud = xen_release_pmd_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_mmu, + }, + + .set_fixmap = xen_set_fixmap, +}; + + #ifdef CONFIG_XEN_DEBUG_FS static struct dentry *d_mmu_debug;