X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemory.c;h=b1443ac07c00a4f1a46de6bb260d00e8f52f99db;hb=d3ddec7635b6fb37cb49e3553bdeea59642be653;hp=2302d228fe04f3926f8c52bf65965623f1caff05;hpb=7a36a752d006f6874049da510297eeb7f09d92a7;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memory.c b/mm/memory.c index 2302d22..b1443ac 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -45,21 +45,26 @@ #include #include #include +#include #include #include #include #include #include #include +#include +#include +#include +#include +#include #include #include #include #include #include -#include -#include +#include "internal.h" #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ @@ -103,6 +108,18 @@ static int __init disable_randmaps(char *s) } __setup("norandmaps", disable_randmaps); +unsigned long zero_pfn __read_mostly; +unsigned long highest_memmap_pfn __read_mostly; + +/* + * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() + */ +static int __init init_zero_pfn(void) +{ + zero_pfn = page_to_pfn(ZERO_PAGE(0)); + return 0; +} +core_initcall(init_zero_pfn); /* * If a p?d_bad entry is found while walking page tables, report @@ -132,11 +149,12 @@ 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--; } @@ -154,7 +172,7 @@ 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; @@ -170,7 +188,7 @@ 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, @@ -203,7 +221,7 @@ 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); } /* @@ -211,7 +229,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, * * Must be called with pagetable lock held. */ -void free_pgd_range(struct mmu_gather **tlb, +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { @@ -262,16 +280,16 @@ void free_pgd_range(struct mmu_gather **tlb, return; start = addr; - pgd = pgd_offset((*tlb)->mm, addr); + pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - free_pud_range(*tlb, pgd, addr, next, floor, ceiling); + free_pud_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, +void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { @@ -372,14 +390,65 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) * * The calling function must still handle the error. */ -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) { + printk(KERN_ALERT + "page:%p flags:%p count:%d mapcount:%d mapping:%p index:%lx\n", + page, (void *)page->flags, page_count(page), + page_mapcount(page), page->mapping, page->index); + } + 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) @@ -387,6 +456,20 @@ 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. * @@ -437,21 +520,20 @@ 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)) @@ -467,11 +549,16 @@ 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: @@ -541,8 +628,8 @@ 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); + rss[PageAnon(page)]++; } out_set_pte: @@ -649,6 +736,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long next; unsigned long addr = vma->vm_start; unsigned long end = vma->vm_end; + int ret; /* * Don't copy ptes where a page fault will fill them correctly. @@ -664,17 +752,43 @@ 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 (unlikely(is_pfn_mapping(vma))) { + /* + * We do not free on error cases below as remove_vma + * gets called on error from higher level routine + */ + ret = track_pfn_vma_copy(vma); + if (ret) + return ret; + } + + /* + * We need to invalidate the secondary MMU mappings only when + * there could be a permission downgrade on the ptes of the + * parent mm. And a permission downgrade will only happen if + * is_cow_mapping() returns true. + */ + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_start(src_mm, addr, end); + + ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next)) - return -ENOMEM; + if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + vma, addr, next))) { + ret = -ENOMEM; + break; + } } while (dst_pgd++, src_pgd++, addr = next, addr != end); - return 0; + + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_end(src_mm, + vma->vm_start, end); + return ret; } static unsigned long zap_pte_range(struct mmu_gather *tlb, @@ -736,11 +850,14 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, else { if (pte_dirty(ptent)) set_page_dirty(page); - if (pte_young(ptent)) - SetPageReferenced(page); + if (pte_young(ptent) && + likely(!VM_SequentialReadHint(vma))) + mark_page_accessed(page); file_rss--; } - 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; } @@ -750,8 +867,12 @@ 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 if + (unlikely(!free_swap_and_cache(pte_to_swp_entry(ptent)))) + 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)); @@ -878,7 +999,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, unsigned long start = start_addr; spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; int fullmm = (*tlbp)->fullmm; + struct mm_struct *mm = vma->vm_mm; + mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { unsigned long end; @@ -892,6 +1015,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, if (vma->vm_flags & VM_ACCOUNT) *nr_accounted += (end - start) >> PAGE_SHIFT; + if (unlikely(is_pfn_mapping(vma))) + untrack_pfn_vma(vma, 0, 0); + while (start != end) { if (!tlb_start_valid) { tlb_start = start; @@ -899,9 +1025,23 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, } if (unlikely(is_vm_hugetlb_page(vma))) { - unmap_hugepage_range(vma, start, end); - zap_work -= (end - start) / - (HPAGE_SIZE / PAGE_SIZE); + /* + * It is undesirable to test vma->vm_file as it + * should be non-null for valid hugetlb area. + * However, vm_file will be NULL in the error + * cleanup path of do_mmap_pgoff. When + * hugetlbfs ->mmap method fails, + * do_mmap_pgoff() nullifies vma->vm_file + * before calling this function to clean up. + * Since no pte has actually been setup, it is + * safe to do nothing in this case. + */ + if (vma->vm_file) { + unmap_hugepage_range(vma, start, end, NULL); + zap_work -= (end - start) / + pages_per_huge_page(hstate_vma(vma)); + } + start = end; } else start = unmap_page_range(*tlbp, vma, @@ -929,6 +1069,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, } } out: + mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); return start; /* which is now the end (or restart) address */ } @@ -956,6 +1097,29 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, return end; } +/** + * zap_vma_ptes - remove ptes mapping the vma + * @vma: vm_area_struct holding ptes to be zapped + * @address: starting address of pages to zap + * @size: number of bytes to zap + * + * This function only unmaps ptes assigned to VM_PFNMAP vmas. + * + * The entire address range must be fully contained within the vma. + * + * Returns 0 if successful. + */ +int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size) +{ + if (address < vma->vm_start || address + size > vma->vm_end || + !(vma->vm_flags & VM_PFNMAP)) + return -1; + zap_page_range(vma, address, size, NULL); + return 0; +} +EXPORT_SYMBOL_GPL(zap_vma_ptes); + /* * Do a quick page-table lookup for a single page. */ @@ -982,19 +1146,24 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, goto no_page_table; pud = pud_offset(pgd, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) + if (pud_none(*pud)) + goto no_page_table; + if (pud_huge(*pud)) { + BUG_ON(flags & FOLL_GET); + page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); + goto out; + } + if (unlikely(pud_bad(*pud))) goto no_page_table; - + pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) goto no_page_table; - if (pmd_huge(*pmd)) { BUG_ON(flags & FOLL_GET); page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); goto out; } - if (unlikely(pmd_bad(*pmd))) goto no_page_table; @@ -1005,9 +1174,14 @@ 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); @@ -1015,6 +1189,11 @@ 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: @@ -1030,61 +1209,46 @@ 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; } -/* 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 or a nopfn routine, it's not an - * anonymous region. - */ - return !vma->vm_ops || - (!vma->vm_ops->fault && !vma->vm_ops->nopfn); -} - -int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int write, int force, - struct page **pages, struct vm_area_struct **vmas) +int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int nr_pages, unsigned int gup_flags, + struct page **pages, struct vm_area_struct **vmas) { int i; - unsigned int vm_flags; + 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)) { @@ -1094,7 +1258,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pud_t *pud; pmd_t *pmd; pte_t *pte; - if (write) /* user gate pages are read-only */ + + /* user gate pages are read-only */ + if (gup_flags & FOLL_WRITE) return i ? : -EFAULT; if (pg > TASK_SIZE) pgd = pgd_offset_k(pg); @@ -1122,45 +1288,40 @@ 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)) - || !(vm_flags & vma->vm_flags)) + if (!vma || + (vma->vm_flags & (VM_IO | VM_PFNMAP)) || + !(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; @@ -1178,9 +1339,15 @@ 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(); @@ -1197,13 +1364,107 @@ 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 nr_pages, int write, int force, + struct page **pages, struct vm_area_struct **vmas) +{ + int flags = FOLL_TOUCH; + + if (pages) + flags |= FOLL_GET; + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + 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) { @@ -1232,18 +1493,14 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, pte_t *pte; spinlock_t *ptl; - retval = mem_cgroup_charge(page, mm, GFP_KERNEL); - if (retval) - goto out; - retval = -EINVAL; if (PageAnon(page)) - goto out_uncharge; + goto out; retval = -ENOMEM; flush_dcache_page(page); pte = get_locked_pte(mm, addr, &ptl); if (!pte) - goto out_uncharge; + goto out; retval = -EBUSY; if (!pte_none(*pte)) goto out_unlock; @@ -1259,8 +1516,6 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, return retval; out_unlock: pte_unmap_unlock(pte, ptl); -out_uncharge: - mem_cgroup_uncharge_page(page); out: return retval; } @@ -1338,10 +1593,17 @@ out: * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return NULL. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. */ 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 @@ -1356,7 +1618,15 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; - return insert_pfn(vma, addr, pfn, vma->vm_page_prot); + if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE)) + return -EINVAL; + + ret = insert_pfn(vma, addr, pfn, pgprot); + + if (ret) + untrack_pfn_vma(vma, pfn, PAGE_SIZE); + + return ret; } EXPORT_SYMBOL(vm_insert_pfn); @@ -1372,7 +1642,8 @@ 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; @@ -1487,14 +1758,25 @@ 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 (is_cow_mapping(vma->vm_flags)) { - if (addr != vma->vm_start || end != vma->vm_end) - return -EINVAL; + if (addr == vma->vm_start && end == vma->vm_end) { vma->vm_pgoff = pfn; - } + 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) { + /* + * 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; pgd = pgd_offset(mm, addr); @@ -1506,6 +1788,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, if (err) break; } while (pgd++, addr = next, addr != end); + + if (err) + untrack_pfn_vma(vma, pfn, PAGE_ALIGN(size)); + return err; } EXPORT_SYMBOL(remap_pfn_range); @@ -1527,6 +1813,8 @@ 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 { @@ -1535,6 +1823,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, break; } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); + if (mm != &init_mm) pte_unmap_unlock(pte-1, ptl); return err; @@ -1548,6 +1838,8 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long next; int err; + BUG_ON(pud_huge(*pud)); + pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; @@ -1589,10 +1881,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, { pgd_t *pgd; unsigned long next; - unsigned long end = addr + size; + unsigned long start = addr, end = addr + size; int err; BUG_ON(addr >= end); + mmu_notifier_invalidate_range_start(mm, start, end); pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); @@ -1600,6 +1893,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, if (err) break; } while (pgd++, addr = next, addr != end); + mmu_notifier_invalidate_range_end(mm, start, end); return err; } EXPORT_SYMBOL_GPL(apply_to_page_range); @@ -1715,11 +2009,22 @@ 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 (!TestSetPageLocked(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); + unlock_page(old_page); } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { /* @@ -1728,6 +2033,15 @@ 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 @@ -1739,8 +2053,21 @@ 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 @@ -1750,9 +2077,11 @@ 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; } @@ -1781,14 +2110,30 @@ 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; - cow_user_page(new_page, old_page, address, vma); + + 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); - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + /* + * Don't let another task, with possibly unlocked vma, + * keep the mlocked page. + */ + if ((vma->vm_flags & VM_LOCKED) && old_page) { + lock_page(old_page); /* for LRU manipulation */ + clear_page_mlock(old_page); + unlock_page(old_page); + } + + if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; /* @@ -1813,11 +2158,14 @@ gotten: * thread doing COW. */ ptep_clear_flush(vma, address, page_table); - set_pte_at(mm, address, page_table, entry); - update_mmu_cache(vma, address, entry); - lru_cache_add_active(new_page); page_add_new_anon_rmap(new_page, vma, address); - + /* + * 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, entry); if (old_page) { /* * Only after switching the pte to the new page may @@ -1841,7 +2189,7 @@ 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.. */ @@ -1857,9 +2205,6 @@ 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 @@ -1868,21 +2213,46 @@ 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; } /* @@ -2134,7 +2504,7 @@ int vmtruncate(struct inode * inode, loff_t offset) unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); } - if (inode->i_op && inode->i_op->truncate) + if (inode->i_op->truncate) inode->i_op->truncate(inode); return 0; @@ -2154,7 +2524,7 @@ 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); @@ -2176,12 +2546,13 @@ 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)) @@ -2195,7 +2566,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, 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) { @@ -2215,16 +2586,14 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(PGMAJFAULT); } - if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - ret = VM_FAULT_OOM; - goto out; - } - - mark_page_accessed(page); lock_page(page); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + 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. */ @@ -2237,25 +2606,38 @@ 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); 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()) - remove_exclusive_swap_page(page); + if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(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; @@ -2269,8 +2651,9 @@ unlock: 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); page_cache_release(page); return ret; @@ -2283,12 +2666,22 @@ 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); @@ -2299,18 +2692,20 @@ 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); - lru_cache_add_active(page); 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 */ @@ -2350,6 +2745,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page; pte_t entry; int anon = 0; + int charged = 0; struct page *dirty_page = NULL; struct vm_fault vmf; int ret; @@ -2390,6 +2786,18 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, ret = VM_FAULT_OOM; goto out; } + if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) { + ret = VM_FAULT_OOM; + page_cache_release(page); + goto out; + } + charged = 1; + /* + * Don't let another task, with possibly unlocked vma, + * keep the mlocked page. + */ + if (vma->vm_flags & VM_LOCKED) + clear_page_mlock(vmf.page); copy_user_highpage(page, vmf.page, address, vma); __SetPageUptodate(page); } else { @@ -2399,36 +2807,31 @@ 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; } } } - if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { - ret = VM_FAULT_OOM; - goto out; - } - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); /* @@ -2436,7 +2839,7 @@ 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. @@ -2447,11 +2850,9 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, entry = mk_pte(page, vma->vm_page_prot); if (flags & FAULT_FLAG_WRITE) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - set_pte_at(mm, address, page_table, entry); if (anon) { - inc_mm_counter(mm, anon_rss); - lru_cache_add_active(page); - page_add_new_anon_rmap(page, vma, address); + inc_mm_counter(mm, anon_rss); + page_add_new_anon_rmap(page, vma, address); } else { inc_mm_counter(mm, file_rss); page_add_file_rmap(page); @@ -2460,11 +2861,13 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, get_page(dirty_page); } } + 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); } else { - mem_cgroup_uncharge_page(page); + if (charged) + mem_cgroup_uncharge_page(page); if (anon) page_cache_release(page); else @@ -2474,86 +2877,48 @@ 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); } - -/* - * do_no_pfn() tries to create a new page mapping for a page without - * a struct_page backing it - * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte mapped but not yet locked. - * We return with mmap_sem still held, but pte unmapped and unlocked. - * - * It is expected that the ->nopfn handler always returns the same pfn - * for a given virtual mapping. - * - * Mark this `noinline' to prevent it from bloating the main pagefault code. - */ -static noinline int do_no_pfn(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access) -{ - spinlock_t *ptl; - pte_t entry; - unsigned long pfn; - - pte_unmap(page_table); - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); - BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - - pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK); - - BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); - - if (unlikely(pfn == NOPFN_OOM)) - return VM_FAULT_OOM; - else if (unlikely(pfn == NOPFN_SIGBUS)) - return VM_FAULT_SIGBUS; - else if (unlikely(pfn == NOPFN_REFAULT)) - return 0; - - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - - /* Only go through if we didn't race with anybody else... */ - if (pte_none(*page_table)) { - entry = pfn_pte(pfn, vma->vm_page_prot); - if (write_access) - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - set_pte_at(mm, address, page_table, entry); - } - pte_unmap_unlock(page_table, ptl); - return 0; -} - /* * Fault of a previously existing named mapping. Repopulate the pte * from the encoded file_pte if possible. This enables swappable @@ -2565,21 +2930,20 @@ static noinline int do_no_pfn(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); + print_bad_pte(vma, address, orig_pte, NULL); return VM_FAULT_OOM; } @@ -2602,7 +2966,7 @@ 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; @@ -2613,33 +2977,30 @@ 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); - if (unlikely(vma->vm_ops->nopfn)) - return do_no_pfn(mm, vma, address, pte, - pmd, write_access); + 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)) { + if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vma, address, entry); } else { /* @@ -2648,7 +3009,7 @@ 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: @@ -2660,7 +3021,7 @@ 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; @@ -2672,7 +3033,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(PGFAULT); 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); @@ -2685,7 +3046,7 @@ 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 @@ -2748,7 +3109,7 @@ int make_pages_present(unsigned long addr, unsigned long end) vma = find_vma(current->mm, addr); if (!vma) - return -1; + return -ENOMEM; write = (vma->vm_flags & VM_WRITE) != 0; BUG_ON(addr >= end); BUG_ON(end > vma->vm_end); @@ -2757,7 +3118,7 @@ int make_pages_present(unsigned long addr, unsigned long end) len, write, 0, NULL, NULL); if (ret < 0) return ret; - return ret == len ? 0 : -1; + return ret == len ? 0 : -EFAULT; } #if !defined(__HAVE_ARCH_GATE_AREA) @@ -2804,6 +3165,123 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ +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; + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + goto out; + + pud = pud_offset(pgd, address); + if (pud_none(*pud) || unlikely(pud_bad(*pud))) + goto out; + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + goto out; + + /* We cannot handle huge page PFN maps. Luckily they don't exist. */ + if (pmd_huge(*pmd)) + goto out; + + 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 ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + + *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 ret; +} + +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + resource_size_t phys_addr; + unsigned long prot = 0; + void __iomem *maddr; + int offset = addr & (PAGE_SIZE-1); + + if (follow_phys(vma, addr, write, &prot, &phys_addr)) + return -EINVAL; + + maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + if (write) + memcpy_toio(maddr + offset, buf, len); + else + memcpy_fromio(buf, maddr + offset, len); + iounmap(maddr); + + return len; +} +#endif + /* * Access another process' address space. * Source/target buffer must be kernel space, @@ -2813,7 +3291,6 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in { struct mm_struct *mm; struct vm_area_struct *vma; - struct page *page; void *old_buf = buf; mm = get_task_mm(tsk); @@ -2825,28 +3302,44 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in while (len) { int bytes, ret, offset; void *maddr; + struct page *page = NULL; ret = get_user_pages(tsk, mm, addr, 1, write, 1, &page, &vma); - if (ret <= 0) - break; - - bytes = len; - offset = addr & (PAGE_SIZE-1); - if (bytes > PAGE_SIZE-offset) - bytes = PAGE_SIZE-offset; - - maddr = kmap(page); - if (write) { - copy_to_user_page(vma, page, addr, - maddr + offset, buf, bytes); - set_page_dirty_lock(page); + if (ret <= 0) { + /* + * Check if this is a VM_IO | VM_PFNMAP VMA, which + * we can access using slightly different code. + */ +#ifdef CONFIG_HAVE_IOREMAP_PROT + vma = find_vma(mm, addr); + if (!vma) + break; + if (vma->vm_ops && vma->vm_ops->access) + ret = vma->vm_ops->access(vma, addr, buf, + len, write); + if (ret <= 0) +#endif + break; + bytes = ret; } else { - copy_from_user_page(vma, page, addr, - buf, maddr + offset, bytes); + bytes = len; + offset = addr & (PAGE_SIZE-1); + if (bytes > PAGE_SIZE-offset) + bytes = PAGE_SIZE-offset; + + maddr = kmap(page); + if (write) { + copy_to_user_page(vma, page, addr, + maddr + offset, buf, bytes); + set_page_dirty_lock(page); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + page_cache_release(page); } - kunmap(page); - page_cache_release(page); len -= bytes; buf += bytes; addr += bytes; @@ -2894,3 +3387,27 @@ 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