X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemory.c;h=119b7ccdf39b8ee542d3f4d695bff3c9d5322987;hb=ac39cf8cb86c45eeac6a592ce0d58f9021a97235;hp=1e8f0d347c0e3943be549c0dfce465555b84e876;hpb=2ab640379a0ab4cef746ced1d7e04a0941774bcb;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memory.c b/mm/memory.c index 1e8f0d3..119b7cc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include #include @@ -52,16 +53,18 @@ #include #include #include +#include +#include +#include +#include +#include #include #include #include #include #include -#include -#include - #include "internal.h" #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -99,57 +102,96 @@ int randomize_va_space __read_mostly = 2; #endif -#ifndef track_pfn_vma_new -/* - * Interface that can be used by architecture code to keep track of - * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) - * - * track_pfn_vma_new is called when a _new_ pfn mapping is being established - * for physical range indicated by pfn and size. - */ -int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot, - unsigned long pfn, unsigned long size) +static int __init disable_randmaps(char *s) { - return 0; + randomize_va_space = 0; + return 1; } -#endif +__setup("norandmaps", disable_randmaps); + +unsigned long zero_pfn __read_mostly; +unsigned long highest_memmap_pfn __read_mostly; -#ifndef track_pfn_vma_copy /* - * Interface that can be used by architecture code to keep track of - * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) - * - * track_pfn_vma_copy is called when vma that is covering the pfnmap gets - * copied through copy_page_range(). + * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ -int track_pfn_vma_copy(struct vm_area_struct *vma) +static int __init init_zero_pfn(void) { + zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } -#endif +core_initcall(init_zero_pfn); -#ifndef untrack_pfn_vma -/* - * Interface that can be used by architecture code to keep track of - * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) - * - * untrack_pfn_vma is called while unmapping a pfnmap for a region. - * untrack can be called for a specific region indicated by pfn and size or - * can be for the entire vma (in which case size can be zero). - */ -void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size) + +#if defined(SPLIT_RSS_COUNTING) + +static void __sync_task_rss_stat(struct task_struct *task, struct mm_struct *mm) +{ + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) { + if (task->rss_stat.count[i]) { + add_mm_counter(mm, i, task->rss_stat.count[i]); + task->rss_stat.count[i] = 0; + } + } + task->rss_stat.events = 0; +} + +static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) { + struct task_struct *task = current; + + if (likely(task->mm == mm)) + task->rss_stat.count[member] += val; + else + add_mm_counter(mm, member, val); } -#endif +#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) +#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) -static int __init disable_randmaps(char *s) +/* sync counter once per 64 page faults */ +#define TASK_RSS_EVENTS_THRESH (64) +static void check_sync_rss_stat(struct task_struct *task) { - randomize_va_space = 0; - return 1; + if (unlikely(task != current)) + return; + if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) + __sync_task_rss_stat(task, task->mm); +} + +unsigned long get_mm_counter(struct mm_struct *mm, int member) +{ + long val = 0; + + /* + * Don't use task->mm here...for avoiding to use task_get_mm().. + * The caller must guarantee task->mm is not invalid. + */ + val = atomic_long_read(&mm->rss_stat.count[member]); + /* + * counter is updated in asynchronous manner and may go to minus. + * But it's never be expected number for users. + */ + if (val < 0) + return 0; + return (unsigned long)val; } -__setup("norandmaps", disable_randmaps); +void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) +{ + __sync_task_rss_stat(task, mm); +} +#else + +#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) +#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) + +static void check_sync_rss_stat(struct task_struct *task) +{ +} + +#endif /* * If a p?d_bad entry is found while walking page tables, report @@ -179,11 +221,12 @@ void pmd_clear_bad(pmd_t *pmd) * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ -static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd) +static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); - pte_free_tlb(tlb, token); + pte_free_tlb(tlb, token, addr); tlb->mm->nr_ptes--; } @@ -201,7 +244,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; - free_pte_range(tlb, pmd); + free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; @@ -217,7 +260,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); - pmd_free_tlb(tlb, pmd); + pmd_free_tlb(tlb, pmd, start); } static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, @@ -250,7 +293,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, pud = pud_offset(pgd, start); pgd_clear(pgd); - pud_free_tlb(tlb, pud); + pud_free_tlb(tlb, pud, start); } /* @@ -326,9 +369,10 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr = vma->vm_start; /* - * Hide vma from rmap and vmtruncate before freeing pgtables + * Hide vma from rmap and truncate_pagecache before freeing + * pgtables */ - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { @@ -342,7 +386,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, @@ -404,12 +448,20 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) return 0; } -static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) +static inline void init_rss_vec(int *rss) { - if (file_rss) - add_mm_counter(mm, file_rss, file_rss); - if (anon_rss) - add_mm_counter(mm, anon_rss, anon_rss); + memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); +} + +static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) +{ + int i; + + if (current->mm == mm) + sync_mm_rss(current, mm); + for (i = 0; i < NR_MM_COUNTERS; i++) + if (rss[i]) + add_mm_counter(mm, i, rss[i]); } /* @@ -419,15 +471,61 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) * * The calling function must still handle the error. */ -static void print_bad_pte(struct vm_area_struct *vma, pte_t pte, - unsigned long vaddr) -{ - printk(KERN_ERR "Bad pte = %08llx, process = %s, " - "vm_flags = %lx, vaddr = %lx\n", - (long long)pte_val(pte), - (vma->vm_mm == current->mm ? current->comm : "???"), - vma->vm_flags, vaddr); +static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, + pte_t pte, struct page *page) +{ + pgd_t *pgd = pgd_offset(vma->vm_mm, addr); + pud_t *pud = pud_offset(pgd, addr); + pmd_t *pmd = pmd_offset(pud, addr); + struct address_space *mapping; + pgoff_t index; + static unsigned long resume; + static unsigned long nr_shown; + static unsigned long nr_unshown; + + /* + * Allow a burst of 60 reports, then keep quiet for that minute; + * or allow a steady drip of one report per second. + */ + if (nr_shown == 60) { + if (time_before(jiffies, resume)) { + nr_unshown++; + return; + } + if (nr_unshown) { + printk(KERN_ALERT + "BUG: Bad page map: %lu messages suppressed\n", + nr_unshown); + nr_unshown = 0; + } + nr_shown = 0; + } + if (nr_shown++ == 0) + resume = jiffies + 60 * HZ; + + mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; + index = linear_page_index(vma, addr); + + printk(KERN_ALERT + "BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", + current->comm, + (long long)pte_val(pte), (long long)pmd_val(*pmd)); + if (page) + dump_page(page); + printk(KERN_ALERT + "addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n", + (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); + /* + * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y + */ + if (vma->vm_ops) + print_symbol(KERN_ALERT "vma->vm_ops->fault: %s\n", + (unsigned long)vma->vm_ops->fault); + if (vma->vm_file && vma->vm_file->f_op) + print_symbol(KERN_ALERT "vma->vm_file->f_op->mmap: %s\n", + (unsigned long)vma->vm_file->f_op->mmap); dump_stack(); + add_taint(TAINT_BAD_PAGE); } static inline int is_cow_mapping(unsigned int flags) @@ -435,6 +533,20 @@ static inline int is_cow_mapping(unsigned int flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +#ifndef is_zero_pfn +static inline int is_zero_pfn(unsigned long pfn) +{ + return pfn == zero_pfn; +} +#endif + +#ifndef my_zero_pfn +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + return zero_pfn; +} +#endif + /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * @@ -485,21 +597,20 @@ static inline int is_cow_mapping(unsigned int flags) struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - unsigned long pfn; + unsigned long pfn = pte_pfn(pte); if (HAVE_PTE_SPECIAL) { - if (likely(!pte_special(pte))) { - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - return pte_page(pte); - } - VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); + if (likely(!pte_special(pte))) + goto check_pfn; + if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + return NULL; + if (!is_zero_pfn(pfn)) + print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !HAVE_PTE_SPECIAL case follows: */ - pfn = pte_pfn(pte); - if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) @@ -515,11 +626,16 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, } } - VM_BUG_ON(!pfn_valid(pfn)); + if (is_zero_pfn(pfn)) + return NULL; +check_pfn: + if (unlikely(pfn > highest_memmap_pfn)) { + print_bad_pte(vma, addr, pte, NULL); + return NULL; + } /* * NOTE! We still have PageReserved() pages in the page tables. - * * eg. VDSO mappings can cause them to exist. */ out: @@ -532,7 +648,7 @@ out: * covered by this vma. */ -static inline void +static inline unsigned long copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr, int *rss) @@ -546,7 +662,9 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!pte_file(pte)) { swp_entry_t entry = pte_to_swp_entry(pte); - swap_duplicate(entry); + if (swap_duplicate(entry) < 0) + return entry.val; + /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); @@ -555,7 +673,9 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, &src_mm->mmlist); spin_unlock(&mmlist_lock); } - if (is_write_migration_entry(entry) && + if (likely(!non_swap_entry(entry))) + rss[MM_SWAPENTS]++; + else if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both parent @@ -589,31 +709,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, page = vm_normal_page(vma, addr, pte); if (page) { get_page(page); - page_dup_rmap(page, vma, addr); - rss[!!PageAnon(page)]++; + page_dup_rmap(page); + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; } out_set_pte: set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; } static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { + pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress = 0; - int rss[2]; + int rss[NR_MM_COUNTERS]; + swp_entry_t entry = (swp_entry_t){0}; again: - rss[1] = rss[0] = 0; + init_rss_vec(rss); + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) return -ENOMEM; src_pte = pte_offset_map_nested(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + orig_src_pte = src_pte; + orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { @@ -631,16 +760,25 @@ again: progress++; continue; } - copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss); + entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, + vma, addr, rss); + if (entry.val) + break; progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); - pte_unmap_nested(src_pte - 1); - add_mm_rss(dst_mm, rss[0], rss[1]); - pte_unmap_unlock(dst_pte - 1, dst_ptl); + pte_unmap_nested(orig_src_pte); + add_mm_rss_vec(dst_mm, rss); + pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); + + if (entry.val) { + if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) + return -ENOMEM; + progress = 0; + } if (addr != end) goto again; return 0; @@ -713,7 +851,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); - if (is_pfn_mapping(vma)) { + if (unlikely(is_pfn_mapping(vma))) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine @@ -760,8 +898,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, struct mm_struct *mm = tlb->mm; pte_t *pte; spinlock_t *ptl; - int file_rss = 0; - int anon_rss = 0; + int rss[NR_MM_COUNTERS]; + + init_rss_vec(rss); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); @@ -807,15 +946,18 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, set_pte_at(mm, addr, pte, pgoff_to_pte(page->index)); if (PageAnon(page)) - anon_rss--; + rss[MM_ANONPAGES]--; else { if (pte_dirty(ptent)) set_page_dirty(page); - if (pte_young(ptent)) - SetPageReferenced(page); - file_rss--; + if (pte_young(ptent) && + likely(!VM_SequentialReadHint(vma))) + mark_page_accessed(page); + rss[MM_FILEPAGES]--; } - page_remove_rmap(page, vma); + page_remove_rmap(page); + if (unlikely(page_mapcount(page) < 0)) + print_bad_pte(vma, addr, ptent, page); tlb_remove_page(tlb, page); continue; } @@ -825,12 +967,21 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, */ if (unlikely(details)) continue; - if (!pte_file(ptent)) - free_swap_and_cache(pte_to_swp_entry(ptent)); + if (pte_file(ptent)) { + if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) + print_bad_pte(vma, addr, ptent, NULL); + } else { + swp_entry_t entry = pte_to_swp_entry(ptent); + + if (!non_swap_entry(entry)) + rss[MM_SWAPENTS]--; + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); + } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); - add_mm_rss(mm, file_rss, anon_rss); + add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); @@ -893,6 +1044,7 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, details = NULL; BUG_ON(addr >= end); + mem_cgroup_uncharge_start(); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { @@ -905,6 +1057,7 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, zap_work, details); } while (pgd++, addr = next, (addr != end && *zap_work > 0)); tlb_end_vma(tlb, vma); + mem_cgroup_uncharge_end(); return addr; } @@ -969,7 +1122,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, if (vma->vm_flags & VM_ACCOUNT) *nr_accounted += (end - start) >> PAGE_SHIFT; - if (is_pfn_mapping(vma)) + if (unlikely(is_pfn_mapping(vma))) untrack_pfn_vma(vma, 0, 0); while (start != end) { @@ -1074,8 +1227,17 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(zap_vma_ptes); -/* - * Do a quick page-table lookup for a single page. +/** + * follow_page - look up a page descriptor from a user-virtual address + * @vma: vm_area_struct mapping @address + * @address: virtual address to look up + * @flags: flags modifying lookup behaviour + * + * @flags can have FOLL_ flags set, defined in + * + * Returns the mapped (struct page *), %NULL if no mapping exists, or + * an error pointer if there is a mapping to something not represented + * by a page descriptor (see also vm_normal_page()). */ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int flags) @@ -1128,9 +1290,14 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, goto no_page; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; + page = vm_normal_page(vma, address, pte); - if (unlikely(!page)) - goto bad_page; + if (unlikely(!page)) { + if ((flags & FOLL_DUMP) || + !is_zero_pfn(pte_pfn(pte))) + goto bad_page; + page = pte_page(pte); + } if (flags & FOLL_GET) get_page(page); @@ -1138,6 +1305,11 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); + /* + * pte_mkyoung() would be more correct here, but atomic care + * is needed to avoid losing the dirty bit: it is easier to use + * mark_page_accessed(). + */ mark_page_accessed(page); } unlock: @@ -1153,107 +1325,46 @@ no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return page; - /* Fall through to ZERO_PAGE handling */ + no_page_table: /* * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate page tables. + * has touched so far, we don't want to allocate unnecessary pages or + * page tables. Return error instead of NULL to skip handle_mm_fault, + * then get_dump_page() will return NULL to leave a hole in the dump. + * But we can only make this optimization where a hole would surely + * be zero-filled if handle_mm_fault() actually did handle it. */ - if (flags & FOLL_ANON) { - page = ZERO_PAGE(0); - if (flags & FOLL_GET) - get_page(page); - BUG_ON(flags & FOLL_WRITE); - } + if ((flags & FOLL_DUMP) && + (!vma->vm_ops || !vma->vm_ops->fault)) + return ERR_PTR(-EFAULT); return page; } -int follow_pfnmap_pte(struct vm_area_struct *vma, unsigned long address, - pte_t *ret_ptep) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - struct page *page; - struct mm_struct *mm = vma->vm_mm; - - if (!is_pfn_mapping(vma)) - goto err; - - page = NULL; - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto err; - - pud = pud_offset(pgd, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - goto err; - - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - goto err; - - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - - pte = *ptep; - if (!pte_present(pte)) - goto err_unlock; - - *ret_ptep = pte; - pte_unmap_unlock(ptep, ptl); - return 0; - -err_unlock: - pte_unmap_unlock(ptep, ptl); -err: - return -EINVAL; -} - -/* Can we do the FOLL_ANON optimization? */ -static inline int use_zero_page(struct vm_area_struct *vma) -{ - /* - * We don't want to optimize FOLL_ANON for make_pages_present() - * when it tries to page in a VM_LOCKED region. As to VM_SHARED, - * we want to get the page from the page tables to make sure - * that we serialize and update with any other user of that - * mapping. - */ - if (vma->vm_flags & (VM_LOCKED | VM_SHARED)) - return 0; - /* - * And if we have a fault routine, it's not an anonymous region. - */ - return !vma->vm_ops || !vma->vm_ops->fault; -} - - - int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int flags, - struct page **pages, struct vm_area_struct **vmas) + unsigned long start, int nr_pages, unsigned int gup_flags, + struct page **pages, struct vm_area_struct **vmas) { int i; - unsigned int vm_flags = 0; - int write = !!(flags & GUP_FLAGS_WRITE); - int force = !!(flags & GUP_FLAGS_FORCE); - int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS); + unsigned long vm_flags; - if (len <= 0) + if (nr_pages <= 0) return 0; + + VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); + /* * Require read or write permissions. - * If 'force' is set, we only require the "MAY" flags. + * If FOLL_FORCE is set, we only require the "MAY" flags. */ - vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); + vm_flags = (gup_flags & FOLL_WRITE) ? + (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); + vm_flags &= (gup_flags & FOLL_FORCE) ? + (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); i = 0; do { struct vm_area_struct *vma; - unsigned int foll_flags; vma = find_extend_vma(mm, start); if (!vma && in_gate_area(tsk, start)) { @@ -1265,7 +1376,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pte_t *pte; /* user gate pages are read-only */ - if (!ignore && write) + if (gup_flags & FOLL_WRITE) return i ? : -EFAULT; if (pg > TASK_SIZE) pgd = pgd_offset_k(pg); @@ -1293,50 +1404,45 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vmas[i] = gate_vma; i++; start += PAGE_SIZE; - len--; + nr_pages--; continue; } if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP)) || - (!ignore && !(vm_flags & vma->vm_flags))) + !(vm_flags & vma->vm_flags)) return i ? : -EFAULT; if (is_vm_hugetlb_page(vma)) { i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &len, i, write); + &start, &nr_pages, i, gup_flags); continue; } - foll_flags = FOLL_TOUCH; - if (pages) - foll_flags |= FOLL_GET; - if (!write && use_zero_page(vma)) - foll_flags |= FOLL_ANON; - do { struct page *page; + unsigned int foll_flags = gup_flags; /* - * If tsk is ooming, cut off its access to large memory - * allocations. It has a pending SIGKILL, but it can't - * be processed until returning to user space. + * If we have a pending SIGKILL, don't keep faulting + * pages and potentially allocating memory. */ - if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE))) - return i ? i : -ENOMEM; - - if (write) - foll_flags |= FOLL_WRITE; + if (unlikely(fatal_signal_pending(current))) + return i ? i : -ERESTARTSYS; cond_resched(); while (!(page = follow_page(vma, start, foll_flags))) { int ret; + ret = handle_mm_fault(mm, vma, start, - foll_flags & FOLL_WRITE); + (foll_flags & FOLL_WRITE) ? + FAULT_FLAG_WRITE : 0); + if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) return i ? i : -ENOMEM; - else if (ret & VM_FAULT_SIGBUS) + if (ret & + (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS)) return i ? i : -EFAULT; BUG(); } @@ -1350,9 +1456,15 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * do_wp_page has broken COW when necessary, * even if maybe_mkwrite decided not to set * pte_write. We can thus safely do subsequent - * page lookups as if they were reads. + * page lookups as if they were reads. But only + * do so when looping for pte_write is futile: + * in some cases userspace may also be wanting + * to write to the gotten user page, which a + * read fault here might prevent (a readonly + * page might get reCOWed by userspace write). */ - if (ret & VM_FAULT_WRITE) + if ((ret & VM_FAULT_WRITE) && + !(vma->vm_flags & VM_WRITE)) foll_flags &= ~FOLL_WRITE; cond_resched(); @@ -1369,30 +1481,107 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vmas[i] = vma; i++; start += PAGE_SIZE; - len--; - } while (len && start < vma->vm_end); - } while (len); + nr_pages--; + } while (nr_pages && start < vma->vm_end); + } while (nr_pages); return i; } +/** + * get_user_pages() - pin user pages in memory + * @tsk: task_struct of target task + * @mm: mm_struct of target mm + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to by the caller + * @force: whether to force write access even if user mapping is + * readonly. This will result in the page being COWed even + * in MAP_SHARED mappings. You do not want this. + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. vmas will only + * remain valid while mmap_sem is held. + * + * Must be called with mmap_sem held for read or write. + * + * get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If write=0, the page must not be written to. If the page is written to, + * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called + * after the page is finished with, and before put_page is called. + * + * get_user_pages is typically used for fewer-copy IO operations, to get a + * handle on the memory by some means other than accesses via the user virtual + * addresses. The pages may be submitted for DMA to devices or accessed via + * their kernel linear mapping (via the kmap APIs). Care should be taken to + * use the correct cache flushing APIs. + * + * See also get_user_pages_fast, for performance critical applications. + */ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int write, int force, + unsigned long start, int nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { - int flags = 0; + int flags = FOLL_TOUCH; + if (pages) + flags |= FOLL_GET; if (write) - flags |= GUP_FLAGS_WRITE; + flags |= FOLL_WRITE; if (force) - flags |= GUP_FLAGS_FORCE; + flags |= FOLL_FORCE; - return __get_user_pages(tsk, mm, - start, len, flags, - pages, vmas); + return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas); } - EXPORT_SYMBOL(get_user_pages); +/** + * get_dump_page() - pin user page in memory while writing it to core dump + * @addr: user address + * + * Returns struct page pointer of user page pinned for dump, + * to be freed afterwards by page_cache_release() or put_page(). + * + * Returns NULL on any kind of failure - a hole must then be inserted into + * the corefile, to preserve alignment with its headers; and also returns + * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - + * allowing a hole to be left in the corefile to save diskspace. + * + * Called without mmap_sem, but after all other threads have been killed. + */ +#ifdef CONFIG_ELF_CORE +struct page *get_dump_page(unsigned long addr) +{ + struct vm_area_struct *vma; + struct page *page; + + if (__get_user_pages(current, current->mm, addr, 1, + FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1) + return NULL; + flush_cache_page(vma, addr, page_to_pfn(page)); + return page; +} +#endif /* CONFIG_ELF_CORE */ + pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { @@ -1435,7 +1624,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ get_page(page); - inc_mm_counter(mm, file_rss); + inc_mm_counter_fast(mm, MM_FILEPAGES); page_add_file_rmap(page); set_pte_at(mm, addr, pte, mk_pte(page, prot)); @@ -1501,7 +1690,7 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ entry = pte_mkspecial(pfn_pte(pfn, prot)); set_pte_at(mm, addr, pte, entry); - update_mmu_cache(vma, addr, entry); /* XXX: why not for insert_page? */ + update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ retval = 0; out_unlock: @@ -1531,6 +1720,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { int ret; + pgprot_t pgprot = vma->vm_page_prot; /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like @@ -1545,10 +1735,10 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; - if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE)) + if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE)) return -EINVAL; - ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot); + ret = insert_pfn(vma, addr, pfn, pgprot); if (ret) untrack_pfn_vma(vma, pfn, PAGE_SIZE); @@ -1569,7 +1759,8 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather - * than insert_pfn). + * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP + * without pte special, it would there be refcounted as a normal page. */ if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { struct page *page; @@ -1684,16 +1875,24 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". */ - if (addr == vma->vm_start && end == vma->vm_end) + if (addr == vma->vm_start && end == vma->vm_end) { vma->vm_pgoff = pfn; - else if (is_cow_mapping(vma->vm_flags)) + vma->vm_flags |= VM_PFN_AT_MMAP; + } else if (is_cow_mapping(vma->vm_flags)) return -EINVAL; vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; - err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size)); - if (err) + err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size)); + if (err) { + /* + * To indicate that track_pfn related cleanup is not + * needed from higher level routine calling unmap_vmas + */ + vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP); + vma->vm_flags &= ~VM_PFN_AT_MMAP; return -EINVAL; + } BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; @@ -1731,13 +1930,17 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, BUG_ON(pmd_huge(*pmd)); + arch_enter_lazy_mmu_mode(); + token = pmd_pgtable(*pmd); do { - err = fn(pte, token, addr, data); + err = fn(pte++, token, addr, data); if (err) break; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (addr += PAGE_SIZE, addr != end); + + arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(pte-1, ptl); @@ -1923,11 +2126,29 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ - if (PageAnon(old_page)) { - if (trylock_page(old_page)) { - reuse = can_share_swap_page(old_page); - unlock_page(old_page); + if (PageAnon(old_page) && !PageKsm(old_page)) { + if (!trylock_page(old_page)) { + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); + lock_page(old_page); + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + if (!pte_same(*page_table, orig_pte)) { + unlock_page(old_page); + page_cache_release(old_page); + goto unlock; + } + page_cache_release(old_page); } + reuse = reuse_swap_page(old_page); + if (reuse) + /* + * The page is all ours. Move it to our anon_vma so + * the rmap code will not search our parent or siblings. + * Protected against the rmap code by the page lock. + */ + page_move_anon_rmap(old_page, vma, address); + unlock_page(old_page); } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { /* @@ -1936,6 +2157,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * get_user_pages(.write=1, .force=1). */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + struct vm_fault vmf; + int tmp; + + vmf.virtual_address = (void __user *)(address & + PAGE_MASK); + vmf.pgoff = old_page->index; + vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + vmf.page = old_page; + /* * Notify the address space that the page is about to * become writable so that it can prohibit this or wait @@ -1947,8 +2177,21 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, page_cache_get(old_page); pte_unmap_unlock(page_table, ptl); - if (vma->vm_ops->page_mkwrite(vma, old_page) < 0) + tmp = vma->vm_ops->page_mkwrite(vma, &vmf); + if (unlikely(tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { + ret = tmp; goto unwritable_page; + } + if (unlikely(!(tmp & VM_FAULT_LOCKED))) { + lock_page(old_page); + if (!old_page->mapping) { + ret = 0; /* retry the fault */ + unlock_page(old_page); + goto unwritable_page; + } + } else + VM_BUG_ON(!PageLocked(old_page)); /* * Since we dropped the lock we need to revalidate @@ -1958,9 +2201,11 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, */ page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - page_cache_release(old_page); - if (!pte_same(*page_table, orig_pte)) + if (!pte_same(*page_table, orig_pte)) { + unlock_page(old_page); + page_cache_release(old_page); goto unlock; + } page_mkwrite = 1; } @@ -1975,7 +2220,7 @@ reuse: entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, address, page_table, entry,1)) - update_mmu_cache(vma, address, entry); + update_mmu_cache(vma, address, page_table); ret |= VM_FAULT_WRITE; goto unlock; } @@ -1989,23 +2234,30 @@ gotten: if (unlikely(anon_vma_prepare(vma))) goto oom; - VM_BUG_ON(old_page == ZERO_PAGE(0)); - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!new_page) - goto oom; + + if (is_zero_pfn(pte_pfn(orig_pte))) { + new_page = alloc_zeroed_user_highpage_movable(vma, address); + if (!new_page) + goto oom; + } else { + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (!new_page) + goto oom; + cow_user_page(new_page, old_page, address, vma); + } + __SetPageUptodate(new_page); + /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ - if (vma->vm_flags & VM_LOCKED) { + if ((vma->vm_flags & VM_LOCKED) && old_page) { lock_page(old_page); /* for LRU manipulation */ clear_page_mlock(old_page); unlock_page(old_page); } - cow_user_page(new_page, old_page, address, vma); - __SetPageUptodate(new_page); - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; /* @@ -2015,11 +2267,11 @@ gotten: if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { - dec_mm_counter(mm, file_rss); - inc_mm_counter(mm, anon_rss); + dec_mm_counter_fast(mm, MM_FILEPAGES); + inc_mm_counter_fast(mm, MM_ANONPAGES); } } else - inc_mm_counter(mm, anon_rss); + inc_mm_counter_fast(mm, MM_ANONPAGES); flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2029,14 +2281,15 @@ gotten: * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush_notify(vma, address, page_table); - SetPageSwapBacked(new_page); - lru_cache_add_active_or_unevictable(new_page, vma); + ptep_clear_flush(vma, address, page_table); page_add_new_anon_rmap(new_page, vma, address); - -//TODO: is this safe? do_anonymous_page() does it this way. - set_pte_at(mm, address, page_table, entry); - update_mmu_cache(vma, address, entry); + /* + * We call the notify macro here because, when using secondary + * mmu page tables (such as kvm shadow page tables), we want the + * new page to be mapped directly into the secondary page table. + */ + set_pte_at_notify(mm, address, page_table, entry); + update_mmu_cache(vma, address, page_table); if (old_page) { /* * Only after switching the pte to the new page may @@ -2060,7 +2313,7 @@ gotten: * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ - page_remove_rmap(old_page, vma); + page_remove_rmap(old_page); } /* Free the old page.. */ @@ -2076,9 +2329,6 @@ gotten: unlock: pte_unmap_unlock(page_table, ptl); if (dirty_page) { - if (vma->vm_file) - file_update_time(vma->vm_file); - /* * Yes, Virginia, this is actually required to prevent a race * with clear_page_dirty_for_io() from clearing the page dirty @@ -2087,21 +2337,46 @@ unlock: * * do_no_page is protected similarly. */ - wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page, page_mkwrite); + if (!page_mkwrite) { + wait_on_page_locked(dirty_page); + set_page_dirty_balance(dirty_page, page_mkwrite); + } put_page(dirty_page); + if (page_mkwrite) { + struct address_space *mapping = dirty_page->mapping; + + set_page_dirty(dirty_page); + unlock_page(dirty_page); + page_cache_release(dirty_page); + if (mapping) { + /* + * Some device drivers do not set page.mapping + * but still dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + } + + /* file_update_time outside page_lock */ + if (vma->vm_file) + file_update_time(vma->vm_file); } return ret; oom_free_new: page_cache_release(new_page); oom: - if (old_page) + if (old_page) { + if (page_mkwrite) { + unlock_page(old_page); + page_cache_release(old_page); + } page_cache_release(old_page); + } return VM_FAULT_OOM; unwritable_page: page_cache_release(old_page); - return VM_FAULT_SIGBUS; + return ret; } /* @@ -2256,7 +2531,7 @@ restart: * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE - * boundary. Note that this is different from vmtruncate(), which + * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded @@ -2307,63 +2582,6 @@ void unmap_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL(unmap_mapping_range); -/** - * vmtruncate - unmap mappings "freed" by truncate() syscall - * @inode: inode of the file used - * @offset: file offset to start truncating - * - * NOTE! We have to be ready to update the memory sharing - * between the file and the memory map for a potential last - * incomplete page. Ugly, but necessary. - */ -int vmtruncate(struct inode * inode, loff_t offset) -{ - if (inode->i_size < offset) { - unsigned long limit; - - limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; - if (limit != RLIM_INFINITY && offset > limit) - goto out_sig; - if (offset > inode->i_sb->s_maxbytes) - goto out_big; - i_size_write(inode, offset); - } else { - struct address_space *mapping = inode->i_mapping; - - /* - * truncation of in-use swapfiles is disallowed - it would - * cause subsequent swapout to scribble on the now-freed - * blocks. - */ - if (IS_SWAPFILE(inode)) - return -ETXTBSY; - i_size_write(inode, offset); - - /* - * unmap_mapping_range is called twice, first simply for - * efficiency so that truncate_inode_pages does fewer - * single-page unmaps. However after this first call, and - * before truncate_inode_pages finishes, it is possible for - * private pages to be COWed, which remain after - * truncate_inode_pages finishes, hence the second - * unmap_mapping_range call must be made for correctness. - */ - unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); - truncate_inode_pages(mapping, offset); - unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); - } - - if (inode->i_op && inode->i_op->truncate) - inode->i_op->truncate(inode); - return 0; - -out_sig: - send_sig(SIGXFSZ, current, 0); -out_big: - return -EFBIG; -} -EXPORT_SYMBOL(vmtruncate); - int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) { struct address_space *mapping = inode->i_mapping; @@ -2373,7 +2591,7 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) * a way to truncate a range of blocks (punch a hole) - * we should return failure right now. */ - if (!inode->i_op || !inode->i_op->truncate_range) + if (!inode->i_op->truncate_range) return -ENOSYS; mutex_lock(&inode->i_mutex); @@ -2395,26 +2613,34 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) */ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access, pte_t orig_pte) + unsigned int flags, pte_t orig_pte) { spinlock_t *ptl; struct page *page; swp_entry_t entry; pte_t pte; + struct mem_cgroup *ptr = NULL; int ret = 0; if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) goto out; entry = pte_to_swp_entry(orig_pte); - if (is_migration_entry(entry)) { - migration_entry_wait(mm, pmd, address); + if (unlikely(non_swap_entry(entry))) { + if (is_migration_entry(entry)) { + migration_entry_wait(mm, pmd, address); + } else if (is_hwpoison_entry(entry)) { + ret = VM_FAULT_HWPOISON; + } else { + print_bad_pte(vma, address, orig_pte, NULL); + ret = VM_FAULT_SIGBUS; + } goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry); if (!page) { - grab_swap_token(); /* Contend for token _before_ read-in */ + grab_swap_token(mm); /* Contend for token _before_ read-in */ page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vma, address); if (!page) { @@ -2432,19 +2658,30 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); + } else if (PageHWPoison(page)) { + /* + * hwpoisoned dirty swapcache pages are kept for killing + * owner processes (which may be unknown at hwpoison time) + */ + ret = VM_FAULT_HWPOISON; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + goto out_release; } - mark_page_accessed(page); - lock_page(page); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { + page = ksm_might_need_to_copy(page, vma, address); + if (!page) { ret = VM_FAULT_OOM; - unlock_page(page); goto out; } + if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) { + ret = VM_FAULT_OOM; + goto out_page; + } + /* * Back out if somebody else already faulted in this pte. */ @@ -2457,25 +2694,39 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_nomap; } - /* The page isn't present yet, go ahead with the fault. */ + /* + * The page isn't present yet, go ahead with the fault. + * + * Be careful about the sequence of operations here. + * To get its accounting right, reuse_swap_page() must be called + * while the page is counted on swap but not yet in mapcount i.e. + * before page_add_anon_rmap() and swap_free(); try_to_free_swap() + * must be called after the swap_free(), or it will never succeed. + * Because delete_from_swap_page() may be called by reuse_swap_page(), + * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry + * in page->private. In this case, a record in swap_cgroup is silently + * discarded at swap_free(). + */ - inc_mm_counter(mm, anon_rss); + inc_mm_counter_fast(mm, MM_ANONPAGES); + dec_mm_counter_fast(mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if (write_access && can_share_swap_page(page)) { + if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); - write_access = 0; + flags &= ~FAULT_FLAG_WRITE; } - flush_icache_page(vma, page); set_pte_at(mm, address, page_table, pte); page_add_anon_rmap(page, vma, address); + /* It's better to call commit-charge after rmap is established */ + mem_cgroup_commit_charge_swapin(page, ptr); swap_free(entry); if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) - remove_exclusive_swap_page(page); + try_to_free_swap(page); unlock_page(page); - if (write_access) { + if (flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; @@ -2483,15 +2734,17 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, } /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, address, pte); + update_mmu_cache(vma, address, page_table); unlock: pte_unmap_unlock(page_table, ptl); out: return ret; out_nomap: - mem_cgroup_uncharge_page(page); + mem_cgroup_cancel_charge_swapin(ptr); pte_unmap_unlock(page_table, ptl); +out_page: unlock_page(page); +out_release: page_cache_release(page); return ret; } @@ -2503,12 +2756,22 @@ out_nomap: */ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access) + unsigned int flags) { struct page *page; spinlock_t *ptl; pte_t entry; + if (!(flags & FAULT_FLAG_WRITE)) { + entry = pte_mkspecial(pfn_pte(my_zero_pfn(address), + vma->vm_page_prot)); + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (!pte_none(*page_table)) + goto unlock; + goto setpte; + } + /* Allocate our own private page. */ pte_unmap(page_table); @@ -2519,23 +2782,24 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, goto oom; __SetPageUptodate(page); - if (mem_cgroup_charge(page, mm, GFP_KERNEL)) + if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) goto oom_free_page; entry = mk_pte(page, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (vma->vm_flags & VM_WRITE) + entry = pte_mkwrite(pte_mkdirty(entry)); page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte_none(*page_table)) goto release; - inc_mm_counter(mm, anon_rss); - SetPageSwapBacked(page); - lru_cache_add_active_or_unevictable(page, vma); + + inc_mm_counter_fast(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); +setpte: set_pte_at(mm, address, page_table, entry); /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, address, entry); + update_mmu_cache(vma, address, page_table); unlock: pte_unmap_unlock(page_table, ptl); return 0; @@ -2586,6 +2850,12 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; + if (unlikely(PageHWPoison(vmf.page))) { + if (ret & VM_FAULT_LOCKED) + unlock_page(vmf.page); + return VM_FAULT_HWPOISON; + } + /* * For consistency in subsequent calls, make the faulted page always * locked. @@ -2612,7 +2882,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, ret = VM_FAULT_OOM; goto out; } - if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { + if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) { ret = VM_FAULT_OOM; page_cache_release(page); goto out; @@ -2633,25 +2903,25 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, * to become writable */ if (vma->vm_ops->page_mkwrite) { + int tmp; + unlock_page(page); - if (vma->vm_ops->page_mkwrite(vma, page) < 0) { - ret = VM_FAULT_SIGBUS; - anon = 1; /* no anon but release vmf.page */ - goto out_unlocked; - } - lock_page(page); - /* - * XXX: this is not quite right (racy vs - * invalidate) to unlock and relock the page - * like this, however a better fix requires - * reworking page_mkwrite locking API, which - * is better done later. - */ - if (!page->mapping) { - ret = 0; - anon = 1; /* no anon but release vmf.page */ - goto out; + vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + tmp = vma->vm_ops->page_mkwrite(vma, &vmf); + if (unlikely(tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { + ret = tmp; + goto unwritable_page; } + if (unlikely(!(tmp & VM_FAULT_LOCKED))) { + lock_page(page); + if (!page->mapping) { + ret = 0; /* retry the fault */ + unlock_page(page); + goto unwritable_page; + } + } else + VM_BUG_ON(!PageLocked(page)); page_mkwrite = 1; } } @@ -2665,7 +2935,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, * due to the bad i386 page protection. But it's valid * for other architectures too. * - * Note that if write_access is true, we either now have + * Note that if FAULT_FLAG_WRITE is set, we either now have * an exclusive copy of the page, or this is a shared mapping, * so we can make it writable and dirty to avoid having to * handle that later. @@ -2677,23 +2947,20 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (flags & FAULT_FLAG_WRITE) entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (anon) { - inc_mm_counter(mm, anon_rss); - SetPageSwapBacked(page); - lru_cache_add_active_or_unevictable(page, vma); + inc_mm_counter_fast(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); } else { - inc_mm_counter(mm, file_rss); + inc_mm_counter_fast(mm, MM_FILEPAGES); page_add_file_rmap(page); if (flags & FAULT_FLAG_WRITE) { dirty_page = page; get_page(dirty_page); } } -//TODO: is this safe? do_anonymous_page() does it this way. set_pte_at(mm, address, page_table, entry); /* no need to invalidate: a not-present page won't be cached */ - update_mmu_cache(vma, address, entry); + update_mmu_cache(vma, address, page_table); } else { if (charged) mem_cgroup_uncharge_page(page); @@ -2706,28 +2973,43 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(page_table, ptl); out: - unlock_page(vmf.page); -out_unlocked: - if (anon) - page_cache_release(vmf.page); - else if (dirty_page) { - if (vma->vm_file) - file_update_time(vma->vm_file); + if (dirty_page) { + struct address_space *mapping = page->mapping; - set_page_dirty_balance(dirty_page, page_mkwrite); + if (set_page_dirty(dirty_page)) + page_mkwrite = 1; + unlock_page(dirty_page); put_page(dirty_page); + if (page_mkwrite && mapping) { + /* + * Some device drivers do not set page.mapping but still + * dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + + /* file_update_time outside page_lock */ + if (vma->vm_file) + file_update_time(vma->vm_file); + } else { + unlock_page(vmf.page); + if (anon) + page_cache_release(vmf.page); } return ret; + +unwritable_page: + page_cache_release(page); + return ret; } static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access, pte_t orig_pte) + unsigned int flags, pte_t orig_pte) { pgoff_t pgoff = (((address & PAGE_MASK) - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0); pte_unmap(page_table); return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); @@ -2744,22 +3026,21 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, */ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access, pte_t orig_pte) + unsigned int flags, pte_t orig_pte) { - unsigned int flags = FAULT_FLAG_NONLINEAR | - (write_access ? FAULT_FLAG_WRITE : 0); pgoff_t pgoff; + flags |= FAULT_FLAG_NONLINEAR; + if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) return 0; - if (unlikely(!(vma->vm_flags & VM_NONLINEAR) || - !(vma->vm_flags & VM_CAN_NONLINEAR))) { + if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { /* * Page table corrupted: show pte and kill process. */ - print_bad_pte(vma, orig_pte, address); - return VM_FAULT_OOM; + print_bad_pte(vma, address, orig_pte, NULL); + return VM_FAULT_SIGBUS; } pgoff = pte_to_pgoff(orig_pte); @@ -2781,7 +3062,7 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, */ static inline int handle_pte_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pmd_t *pmd, int write_access) + pte_t *pte, pmd_t *pmd, unsigned int flags) { pte_t entry; spinlock_t *ptl; @@ -2792,31 +3073,31 @@ static inline int handle_pte_fault(struct mm_struct *mm, if (vma->vm_ops) { if (likely(vma->vm_ops->fault)) return do_linear_fault(mm, vma, address, - pte, pmd, write_access, entry); + pte, pmd, flags, entry); } return do_anonymous_page(mm, vma, address, - pte, pmd, write_access); + pte, pmd, flags); } if (pte_file(entry)) return do_nonlinear_fault(mm, vma, address, - pte, pmd, write_access, entry); + pte, pmd, flags, entry); return do_swap_page(mm, vma, address, - pte, pmd, write_access, entry); + pte, pmd, flags, entry); } ptl = pte_lockptr(mm, pmd); spin_lock(ptl); if (unlikely(!pte_same(*pte, entry))) goto unlock; - if (write_access) { + if (flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(mm, vma, address, pte, pmd, ptl, entry); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - if (ptep_set_access_flags(vma, address, pte, entry, write_access)) { - update_mmu_cache(vma, address, entry); + if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) { + update_mmu_cache(vma, address, pte); } else { /* * This is needed only for protection faults but the arch code @@ -2824,7 +3105,7 @@ static inline int handle_pte_fault(struct mm_struct *mm, * This still avoids useless tlb flushes for .text page faults * with threads. */ - if (write_access) + if (flags & FAULT_FLAG_WRITE) flush_tlb_page(vma, address); } unlock: @@ -2836,7 +3117,7 @@ unlock: * By the time we get here, we already hold the mm semaphore */ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, int write_access) + unsigned long address, unsigned int flags) { pgd_t *pgd; pud_t *pud; @@ -2847,8 +3128,11 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(PGFAULT); + /* do counter updates before entering really critical section. */ + check_sync_rss_stat(current); + if (unlikely(is_vm_hugetlb_page(vma))) - return hugetlb_fault(mm, vma, address, write_access); + return hugetlb_fault(mm, vma, address, flags); pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); @@ -2861,7 +3145,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte) return VM_FAULT_OOM; - return handle_pte_fault(mm, vma, address, pte, pmd, write_access); + return handle_pte_fault(mm, vma, address, pte, pmd, flags); } #ifndef __PAGETABLE_PUD_FOLDED @@ -2980,57 +3264,99 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ -#ifdef CONFIG_HAVE_IOREMAP_PROT -static resource_size_t follow_phys(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned long *prot) +static int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - resource_size_t phys_addr = 0; - struct mm_struct *mm = vma->vm_mm; - - VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP))); + pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto no_page_table; + goto out; pud = pud_offset(pgd, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) - goto no_page_table; + goto out; pmd = pmd_offset(pud, address); if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - goto no_page_table; + goto out; /* We cannot handle huge page PFN maps. Luckily they don't exist. */ if (pmd_huge(*pmd)) - goto no_page_table; + goto out; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!ptep) goto out; + if (!pte_present(*ptep)) + goto unlock; + *ptepp = ptep; + return 0; +unlock: + pte_unmap_unlock(ptep, *ptlp); +out: + return -EINVAL; +} +/** + * follow_pfn - look up PFN at a user virtual address + * @vma: memory mapping + * @address: user virtual address + * @pfn: location to store found PFN + * + * Only IO mappings and raw PFN mappings are allowed. + * + * Returns zero and the pfn at @pfn on success, -ve otherwise. + */ +int follow_pfn(struct vm_area_struct *vma, unsigned long address, + unsigned long *pfn) +{ + int ret = -EINVAL; + spinlock_t *ptl; + pte_t *ptep; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return ret; + + ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); + if (ret) + return ret; + *pfn = pte_pfn(*ptep); + pte_unmap_unlock(ptep, ptl); + return 0; +} +EXPORT_SYMBOL(follow_pfn); + +#ifdef CONFIG_HAVE_IOREMAP_PROT +int follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot, resource_size_t *phys) +{ + int ret = -EINVAL; + pte_t *ptep, pte; + spinlock_t *ptl; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; + + if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) + goto out; pte = *ptep; - if (!pte_present(pte)) - goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; - phys_addr = pte_pfn(pte); - phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ *prot = pgprot_val(pte_pgprot(pte)); + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: - return phys_addr; -no_page_table: - return 0; + return ret; } int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, @@ -3038,15 +3364,10 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, { resource_size_t phys_addr; unsigned long prot = 0; - void *maddr; + void __iomem *maddr; int offset = addr & (PAGE_SIZE-1); - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - return -EINVAL; - - phys_addr = follow_phys(vma, addr, write, &prot); - - if (!phys_addr) + if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); @@ -3165,3 +3486,27 @@ void print_vma_addr(char *prefix, unsigned long ip) } up_read(¤t->mm->mmap_sem); } + +#ifdef CONFIG_PROVE_LOCKING +void might_fault(void) +{ + /* + * Some code (nfs/sunrpc) uses socket ops on kernel memory while + * holding the mmap_sem, this is safe because kernel memory doesn't + * get paged out, therefore we'll never actually fault, and the + * below annotations will generate false positives. + */ + if (segment_eq(get_fs(), KERNEL_DS)) + return; + + might_sleep(); + /* + * it would be nicer only to annotate paths which are not under + * pagefault_disable, however that requires a larger audit and + * providing helpers like get_user_atomic. + */ + if (!in_atomic() && current->mm) + might_lock_read(¤t->mm->mmap_sem); +} +EXPORT_SYMBOL(might_fault); +#endif