X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemory.c;h=109e9866237ec7992daa1e7c441e07dbfe976151;hb=2ec7df0457b710d9201f211dbccdbecf0ad38b7e;hp=a40e4b1cee4ff13cdca07b10a6afffa6933fcf30;hpb=c74df32c724a1652ad8399b4891bb02c9d43743a;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memory.c b/mm/memory.c index a40e4b1..109e986 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -82,6 +83,16 @@ EXPORT_SYMBOL(num_physpages); EXPORT_SYMBOL(high_memory); EXPORT_SYMBOL(vmalloc_earlyreserve); +int randomize_va_space __read_mostly = 1; + +static int __init disable_randmaps(char *s) +{ + randomize_va_space = 0; + return 1; +} +__setup("norandmaps", disable_randmaps); + + /* * If a p?d_bad entry is found while walking page tables, report * the error, before resetting entry to p?d_none. Usually (but @@ -114,8 +125,9 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd) { struct page *page = pmd_page(*pmd); pmd_clear(pmd); + pte_lock_deinit(page); pte_free_tlb(tlb, page); - dec_page_state(nr_page_table_pages); + dec_zone_page_state(page, NR_PAGETABLE); tlb->mm->nr_ptes--; } @@ -260,7 +272,13 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; - if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) { + /* + * Hide vma from rmap and vmtruncate before freeing pgtables + */ + anon_vma_unlink(vma); + unlink_file_vma(vma); + + if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next? next->vm_start: ceiling); } else { @@ -268,10 +286,11 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE - && !is_hugepage_only_range(vma->vm_mm, next->vm_start, - HPAGE_SIZE)) { + && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; + anon_vma_unlink(vma); + unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next? next->vm_start: ceiling); @@ -286,12 +305,14 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) if (!new) return -ENOMEM; + pte_lock_init(new); spin_lock(&mm->page_table_lock); - if (pmd_present(*pmd)) /* Another has populated it */ + if (pmd_present(*pmd)) { /* Another has populated it */ + pte_lock_deinit(new); pte_free(new); - else { + } else { mm->nr_ptes++; - inc_page_state(nr_page_table_pages); + inc_zone_page_state(new, NR_PAGETABLE); pmd_populate(mm, pmd, new); } spin_unlock(&mm->page_table_lock); @@ -322,9 +343,9 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) } /* - * This function is called to print an error when a pte in a - * !VM_RESERVED region is found pointing to an invalid pfn (which - * is an error. + * This function is called to print an error when a bad pte + * is found. For example, we might have a PFN-mapped pte in + * a region that doesn't allow it. * * The calling function must still handle the error. */ @@ -338,6 +359,64 @@ void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr) dump_stack(); } +static inline int is_cow_mapping(unsigned int flags) +{ + return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; +} + +/* + * This function gets the "struct page" associated with a pte. + * + * NOTE! Some mappings do not have "struct pages". A raw PFN mapping + * will have each page table entry just pointing to a raw page frame + * number, and as far as the VM layer is concerned, those do not have + * pages associated with them - even if the PFN might point to memory + * that otherwise is perfectly fine and has a "struct page". + * + * The way we recognize those mappings is through the rules set up + * by "remap_pfn_range()": the vma will have the VM_PFNMAP bit set, + * and the vm_pgoff will point to the first PFN mapped: thus every + * page that is a raw mapping will always honor the rule + * + * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) + * + * and if that isn't true, the page has been COW'ed (in which case it + * _does_ have a "struct page" associated with it even if it is in a + * VM_PFNMAP range). + */ +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); + + if (unlikely(vma->vm_flags & VM_PFNMAP)) { + unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + + /* + * Add some anal sanity checks for now. Eventually, + * we should just do "return pfn_to_page(pfn)", but + * in the meantime we check that we get a valid pfn, + * and that the resulting page looks ok. + */ + if (unlikely(!pfn_valid(pfn))) { + print_bad_pte(vma, pte, addr); + return NULL; + } + + /* + * NOTE! We still have PageReserved() pages in the page + * tables. + * + * The PAGE_ZERO() pages and various VDSO mappings can + * cause them to exist. + */ + return pfn_to_page(pfn); +} + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range @@ -352,44 +431,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long vm_flags = vma->vm_flags; pte_t pte = *src_pte; struct page *page; - unsigned long pfn; /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { if (!pte_file(pte)) { - swap_duplicate(pte_to_swp_entry(pte)); + swp_entry_t entry = pte_to_swp_entry(pte); + + swap_duplicate(entry); /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); - list_add(&dst_mm->mmlist, &src_mm->mmlist); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); spin_unlock(&mmlist_lock); } + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both parent + * and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + set_pte_at(src_mm, addr, src_pte, pte); + } } goto out_set_pte; } - /* If the region is VM_RESERVED, the mapping is not - * mapped via rmap - duplicate the pte as is. - */ - if (vm_flags & VM_RESERVED) - goto out_set_pte; - - pfn = pte_pfn(pte); - /* If the pte points outside of valid memory but - * the region is not VM_RESERVED, we have a problem. - */ - if (unlikely(!pfn_valid(pfn))) { - print_bad_pte(vma, pte, addr); - goto out_set_pte; /* try to do something sane */ - } - - page = pfn_to_page(pfn); - /* * If it's a COW mapping, write protect it both * in the parent and the child */ - if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) { + if (is_cow_mapping(vm_flags)) { ptep_set_wrprotect(src_mm, addr, src_pte); pte = *src_pte; } @@ -401,9 +476,13 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); - get_page(page); - page_dup_rmap(page); - rss[!!PageAnon(page)]++; + + page = vm_normal_page(vma, addr, pte); + if (page) { + get_page(page); + page_dup_rmap(page); + rss[!!PageAnon(page)]++; + } out_set_pte: set_pte_at(dst_mm, addr, dst_pte, pte); @@ -424,8 +503,8 @@ again: if (!dst_pte) return -ENOMEM; src_pte = pte_offset_map_nested(src_pmd, addr); - src_ptl = &src_mm->page_table_lock; - spin_lock(src_ptl); + src_ptl = pte_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); do { /* @@ -515,7 +594,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_RESERVED))) { + if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) { if (!vma->anon_vma) return 0; } @@ -536,30 +615,31 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, return 0; } -static void zap_pte_range(struct mmu_gather *tlb, +static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, - struct zap_details *details) + long *zap_work, struct zap_details *details) { struct mm_struct *mm = tlb->mm; pte_t *pte; + spinlock_t *ptl; int file_rss = 0; int anon_rss = 0; - pte = pte_offset_map(pmd, addr); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); do { pte_t ptent = *pte; - if (pte_none(ptent)) + if (pte_none(ptent)) { + (*zap_work)--; continue; + } + + (*zap_work) -= PAGE_SIZE; + if (pte_present(ptent)) { - struct page *page = NULL; - if (!(vma->vm_flags & VM_RESERVED)) { - unsigned long pfn = pte_pfn(ptent); - if (unlikely(!pfn_valid(pfn))) - print_bad_pte(vma, ptent, addr); - else - page = pfn_to_page(pfn); - } + struct page *page; + + page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to @@ -610,16 +690,18 @@ static void zap_pte_range(struct mmu_gather *tlb, if (!pte_file(ptent)) free_swap_and_cache(pte_to_swp_entry(ptent)); pte_clear_full(mm, addr, pte, tlb->fullmm); - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); add_mm_rss(mm, file_rss, anon_rss); - pte_unmap(pte - 1); + pte_unmap_unlock(pte - 1, ptl); + + return addr; } -static inline void zap_pmd_range(struct mmu_gather *tlb, +static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, - struct zap_details *details) + long *zap_work, struct zap_details *details) { pmd_t *pmd; unsigned long next; @@ -627,16 +709,21 @@ static inline void zap_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_none_or_clear_bad(pmd)) + if (pmd_none_or_clear_bad(pmd)) { + (*zap_work)--; continue; - zap_pte_range(tlb, vma, pmd, addr, next, details); - } while (pmd++, addr = next, addr != end); + } + next = zap_pte_range(tlb, vma, pmd, addr, next, + zap_work, details); + } while (pmd++, addr = next, (addr != end && *zap_work > 0)); + + return addr; } -static inline void zap_pud_range(struct mmu_gather *tlb, +static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, - struct zap_details *details) + long *zap_work, struct zap_details *details) { pud_t *pud; unsigned long next; @@ -644,15 +731,21 @@ static inline void zap_pud_range(struct mmu_gather *tlb, pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) + if (pud_none_or_clear_bad(pud)) { + (*zap_work)--; continue; - zap_pmd_range(tlb, vma, pud, addr, next, details); - } while (pud++, addr = next, addr != end); + } + next = zap_pmd_range(tlb, vma, pud, addr, next, + zap_work, details); + } while (pud++, addr = next, (addr != end && *zap_work > 0)); + + return addr; } -static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, +static unsigned long unmap_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, unsigned long end, - struct zap_details *details) + long *zap_work, struct zap_details *details) { pgd_t *pgd; unsigned long next; @@ -665,11 +758,16 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) + if (pgd_none_or_clear_bad(pgd)) { + (*zap_work)--; continue; - zap_pud_range(tlb, vma, pgd, addr, next, details); - } while (pgd++, addr = next, addr != end); + } + next = zap_pud_range(tlb, vma, pgd, addr, next, + zap_work, details); + } while (pgd++, addr = next, (addr != end && *zap_work > 0)); tlb_end_vma(tlb, vma); + + return addr; } #ifdef CONFIG_PREEMPT @@ -682,7 +780,6 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlbp: address of the caller's struct mmu_gather - * @mm: the controlling mm_struct * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping @@ -691,10 +788,10 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * * Returns the end address of the unmapping (restart addr if interrupted). * - * Unmap all pages in the vma list. Called under page_table_lock. + * Unmap all pages in the vma list. * - * We aim to not hold page_table_lock for too long (for scheduling latency - * reasons). So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to + * We aim to not hold locks for too long (for scheduling latency reasons). + * So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to * return the ending mmu_gather to the caller. * * Only addresses between `start' and `end' will be unmapped. @@ -706,12 +803,12 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ -unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm, +unsigned long unmap_vmas(struct mmu_gather **tlbp, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, unsigned long *nr_accounted, struct zap_details *details) { - unsigned long zap_bytes = ZAP_BLOCK_SIZE; + long zap_work = ZAP_BLOCK_SIZE; unsigned long tlb_start = 0; /* For tlb_finish_mmu */ int tlb_start_valid = 0; unsigned long start = start_addr; @@ -732,45 +829,39 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm, *nr_accounted += (end - start) >> PAGE_SHIFT; while (start != end) { - unsigned long block; - if (!tlb_start_valid) { tlb_start = start; tlb_start_valid = 1; } - if (is_vm_hugetlb_page(vma)) { - block = end - start; + if (unlikely(is_vm_hugetlb_page(vma))) { unmap_hugepage_range(vma, start, end); - } else { - block = min(zap_bytes, end - start); - unmap_page_range(*tlbp, vma, start, - start + block, details); + zap_work -= (end - start) / + (HPAGE_SIZE / PAGE_SIZE); + start = end; + } else + start = unmap_page_range(*tlbp, vma, + start, end, &zap_work, details); + + if (zap_work > 0) { + BUG_ON(start != end); + break; } - start += block; - zap_bytes -= block; - if ((long)zap_bytes > 0) - continue; - tlb_finish_mmu(*tlbp, tlb_start, start); if (need_resched() || - need_lockbreak(&mm->page_table_lock) || (i_mmap_lock && need_lockbreak(i_mmap_lock))) { if (i_mmap_lock) { - /* must reset count of rss freed */ - *tlbp = tlb_gather_mmu(mm, fullmm); + *tlbp = NULL; goto out; } - spin_unlock(&mm->page_table_lock); cond_resched(); - spin_lock(&mm->page_table_lock); } - *tlbp = tlb_gather_mmu(mm, fullmm); + *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm); tlb_start_valid = 0; - zap_bytes = ZAP_BLOCK_SIZE; + zap_work = ZAP_BLOCK_SIZE; } } out: @@ -792,124 +883,92 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long end = address + size; unsigned long nr_accounted = 0; - if (is_vm_hugetlb_page(vma)) { - zap_hugepage_range(vma, address, size); - return end; - } - lru_add_drain(); - spin_lock(&mm->page_table_lock); tlb = tlb_gather_mmu(mm, 0); update_hiwater_rss(mm); - end = unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details); - tlb_finish_mmu(tlb, address, end); - spin_unlock(&mm->page_table_lock); + end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); + if (tlb) + tlb_finish_mmu(tlb, address, end); return end; } /* * Do a quick page-table lookup for a single page. - * mm->page_table_lock must be held. */ -static struct page *__follow_page(struct mm_struct *mm, unsigned long address, - int read, int write, int accessed) +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int flags) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; - unsigned long pfn; + spinlock_t *ptl; struct page *page; + struct mm_struct *mm = vma->vm_mm; - page = follow_huge_addr(mm, address, write); - if (! IS_ERR(page)) - return page; + page = follow_huge_addr(mm, address, flags & FOLL_WRITE); + if (!IS_ERR(page)) { + BUG_ON(flags & FOLL_GET); + goto out; + } + page = NULL; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto out; + goto no_page_table; pud = pud_offset(pgd, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) - goto out; + goto no_page_table; pmd = pmd_offset(pud, address); if (pmd_none(*pmd) || unlikely(pmd_bad(*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 (pmd_huge(*pmd)) - return follow_huge_pmd(mm, address, pmd, write); + } - ptep = pte_offset_map(pmd, address); + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) goto out; pte = *ptep; - pte_unmap(ptep); - if (pte_present(pte)) { - if (write && !pte_write(pte)) - goto out; - if (read && !pte_read(pte)) - goto out; - pfn = pte_pfn(pte); - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (accessed) { - if (write && !pte_dirty(pte) &&!PageDirty(page)) - set_page_dirty(page); - mark_page_accessed(page); - } - return page; - } - } + if (!pte_present(pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + page = vm_normal_page(vma, address, pte); + if (unlikely(!page)) + goto unlock; + if (flags & FOLL_GET) + get_page(page); + if (flags & FOLL_TOUCH) { + if ((flags & FOLL_WRITE) && + !pte_dirty(pte) && !PageDirty(page)) + set_page_dirty(page); + mark_page_accessed(page); + } +unlock: + pte_unmap_unlock(ptep, ptl); out: - return NULL; -} - -inline struct page * -follow_page(struct mm_struct *mm, unsigned long address, int write) -{ - return __follow_page(mm, address, 0, write, 1); -} - -/* - * check_user_page_readable() can be called frm niterrupt context by oprofile, - * so we need to avoid taking any non-irq-safe locks - */ -int check_user_page_readable(struct mm_struct *mm, unsigned long address) -{ - return __follow_page(mm, address, 1, 0, 0) != NULL; -} -EXPORT_SYMBOL(check_user_page_readable); - -static inline int -untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma, - unsigned long address) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - - /* Check if the vma is for an anonymous mapping. */ - if (vma->vm_ops && vma->vm_ops->nopage) - return 0; - - /* Check if page directory entry exists. */ - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return 1; - - pud = pud_offset(pgd, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return 1; - - /* Check if page middle directory entry exists. */ - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - return 1; + return page; - /* There is a pte slot for 'address' in 'mm'. */ - return 0; +no_page_table: + /* + * When core dumping an enormous anonymous area that nobody + * has touched so far, we don't want to allocate page tables. + */ + if (flags & FOLL_ANON) { + page = ZERO_PAGE(address); + if (flags & FOLL_GET) + get_page(page); + BUG_ON(flags & FOLL_WRITE); + } + return page; } int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, @@ -917,18 +976,19 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, struct page **pages, struct vm_area_struct **vmas) { int i; - unsigned int flags; + unsigned int vm_flags; /* * Require read or write permissions. * If 'force' is set, we only require the "MAY" flags. */ - flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); + vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); + vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); i = 0; do { - struct vm_area_struct * vma; + struct vm_area_struct *vma; + unsigned int foll_flags; vma = find_extend_vma(mm, start); if (!vma && in_gate_area(tsk, start)) { @@ -956,8 +1016,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, return i ? : -EFAULT; } if (pages) { - pages[i] = pte_page(*pte); - get_page(pages[i]); + struct page *page = vm_normal_page(gate_vma, start, *pte); + pages[i] = page; + if (page) + get_page(page); } pte_unmap(pte); if (vmas) @@ -968,8 +1030,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } - if (!vma || (vma->vm_flags & (VM_IO | VM_RESERVED)) - || !(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)) { @@ -977,29 +1039,25 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, &start, &len, i); continue; } - spin_lock(&mm->page_table_lock); + + foll_flags = FOLL_TOUCH; + if (pages) + foll_flags |= FOLL_GET; + if (!write && !(vma->vm_flags & VM_LOCKED) && + (!vma->vm_ops || !vma->vm_ops->nopage)) + foll_flags |= FOLL_ANON; + do { - int write_access = write; struct page *page; - cond_resched_lock(&mm->page_table_lock); - while (!(page = follow_page(mm, start, write_access))) { - int ret; - - /* - * Shortcut for anonymous pages. We don't want - * to force the creation of pages tables for - * insanely big anonymously mapped areas that - * nobody touched so far. This is important - * for doing a core dump for these mappings. - */ - if (!write && untouched_anonymous_page(mm,vma,start)) { - page = ZERO_PAGE(start); - break; - } - spin_unlock(&mm->page_table_lock); - ret = __handle_mm_fault(mm, vma, start, write_access); + if (write) + foll_flags |= FOLL_WRITE; + cond_resched(); + while (!(page = follow_page(vma, start, foll_flags))) { + int ret; + ret = __handle_mm_fault(mm, vma, start, + foll_flags & FOLL_WRITE); /* * The VM_FAULT_WRITE bit tells us that do_wp_page has * broken COW when necessary, even if maybe_mkwrite @@ -1007,7 +1065,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * subsequent page lookups as if they were reads. */ if (ret & VM_FAULT_WRITE) - write_access = 0; + foll_flags &= ~FOLL_WRITE; switch (ret & ~VM_FAULT_WRITE) { case VM_FAULT_MINOR: @@ -1023,12 +1081,12 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, default: BUG(); } - spin_lock(&mm->page_table_lock); } if (pages) { pages[i] = page; + + flush_anon_page(page, start); flush_dcache_page(page); - page_cache_get(page); } if (vmas) vmas[i] = vma; @@ -1036,7 +1094,6 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, start += PAGE_SIZE; len--; } while (len && start < vma->vm_end); - spin_unlock(&mm->page_table_lock); } while (len); return i; } @@ -1119,6 +1176,84 @@ int zeromap_page_range(struct vm_area_struct *vma, return err; } +pte_t * fastcall get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) +{ + pgd_t * pgd = pgd_offset(mm, addr); + pud_t * pud = pud_alloc(mm, pgd, addr); + if (pud) { + pmd_t * pmd = pmd_alloc(mm, pud, addr); + if (pmd) + return pte_alloc_map_lock(mm, pmd, addr, ptl); + } + return NULL; +} + +/* + * This is the old fallback for page remapping. + * + * For historical reasons, it only allows reserved pages. Only + * old drivers should use this, and they needed to mark their + * pages reserved for the old functions anyway. + */ +static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *page, pgprot_t prot) +{ + int retval; + pte_t *pte; + spinlock_t *ptl; + + retval = -EINVAL; + if (PageAnon(page)) + goto out; + retval = -ENOMEM; + flush_dcache_page(page); + pte = get_locked_pte(mm, addr, &ptl); + if (!pte) + goto out; + retval = -EBUSY; + if (!pte_none(*pte)) + goto out_unlock; + + /* Ok, finally just insert the thing.. */ + get_page(page); + inc_mm_counter(mm, file_rss); + page_add_file_rmap(page); + set_pte_at(mm, addr, pte, mk_pte(page, prot)); + + retval = 0; +out_unlock: + pte_unmap_unlock(pte, ptl); +out: + return retval; +} + +/* + * This allows drivers to insert individual pages they've allocated + * into a user vma. + * + * The page has to be a nice clean _individual_ kernel allocation. + * If you allocate a compound page, you need to have marked it as + * such (__GFP_COMP), or manually just split the page up yourself + * (see split_page()). + * + * NOTE! Traditionally this was done with "remap_pfn_range()" which + * took an arbitrary page protection parameter. This doesn't allow + * that. Your vma protection will have to be set up correctly, which + * means that if you want a shared writable mapping, you'd better + * ask for a shared writable mapping! + * + * The page does not need to be reserved. + */ +int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) +{ + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + if (!page_count(page)) + return -EINVAL; + vma->vm_flags |= VM_INSERTPAGE; + return insert_page(vma->vm_mm, addr, page, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_page); + /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results @@ -1198,10 +1333,26 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). - * VM_RESERVED tells the core MM not to "manage" these pages - * (e.g. refcount, mapcount, try to swap them out). + * VM_RESERVED is specified all over the place, because + * in 2.4 it kept swapout's vma scan off this vma; but + * in 2.6 the LRU scan won't even find its pages, so this + * flag means no more than count its pages in reserved_vm, + * and omit it from core dump, even when VM_IO turned off. + * VM_PFNMAP tells the core MM that the base pages are just + * raw PFN mappings, and do not have a "struct page" associated + * with them. + * + * There's a horrible special case to handle copy-on-write + * behaviour that some programs depend on. We mark the "original" + * un-COW'ed pages by matching them up with "vma->vm_pgoff". */ - vma->vm_flags |= VM_IO | VM_RESERVED; + if (is_cow_mapping(vma->vm_flags)) { + if (addr != vma->vm_start || end != vma->vm_end) + return -EINVAL; + vma->vm_pgoff = pfn; + } + + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; @@ -1219,6 +1370,31 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, EXPORT_SYMBOL(remap_pfn_range); /* + * handle_pte_fault chooses page fault handler according to an entry + * which was read non-atomically. Before making any commitment, on + * those architectures or configurations (e.g. i386 with PAE) which + * might give a mix of unmatched parts, do_swap_page and do_file_page + * must check under lock before unmapping the pte and proceeding + * (but do_wp_page is only called after already making such a check; + * and do_anonymous_page and do_no_page can safely check later on). + */ +static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, + pte_t *page_table, pte_t orig_pte) +{ + int same = 1; +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) + if (sizeof(pte_t) > sizeof(unsigned long)) { + spinlock_t *ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + same = pte_same(*page_table, orig_pte); + spin_unlock(ptl); + } +#endif + pte_unmap(page_table); + return same; +} + +/* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings @@ -1231,6 +1407,33 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } +static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va) +{ + /* + * If the source page was a PFN mapping, we don't have + * a "struct page" for it. We do a best-effort copy by + * just copying from the original user address. If that + * fails, we just zero-fill it. Live with it. + */ + if (unlikely(!src)) { + void *kaddr = kmap_atomic(dst, KM_USER0); + void __user *uaddr = (void __user *)(va & PAGE_MASK); + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) + memset(kaddr, 0, PAGE_SIZE); + kunmap_atomic(kaddr, KM_USER0); + return; + + } + copy_user_highpage(dst, src, va); +} + /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address @@ -1245,51 +1448,78 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * - * We hold the mm semaphore and the page_table_lock on entry and exit - * with the page_table_lock released. + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), with pte both mapped and locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. */ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - pte_t orig_pte) + spinlock_t *ptl, pte_t orig_pte) { struct page *old_page, *new_page; - unsigned long pfn = pte_pfn(orig_pte); pte_t entry; - int ret = VM_FAULT_MINOR; + int reuse, ret = VM_FAULT_MINOR; - BUG_ON(vma->vm_flags & VM_RESERVED); + old_page = vm_normal_page(vma, address, orig_pte); + if (!old_page) + goto gotten; - if (unlikely(!pfn_valid(pfn))) { - /* - * Page table corrupted: show pte and kill process. - */ - print_bad_pte(vma, orig_pte, address); - ret = VM_FAULT_OOM; - goto unlock; - } - old_page = pfn_to_page(pfn); + if (unlikely((vma->vm_flags & (VM_SHARED|VM_WRITE)) == + (VM_SHARED|VM_WRITE))) { + if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + /* + * Notify the address space that the page is about to + * become writable so that it can prohibit this or wait + * for the page to get into an appropriate state. + * + * We do this without the lock held, so that it can + * sleep if it needs to. + */ + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); - if (PageAnon(old_page) && !TestSetPageLocked(old_page)) { - int reuse = can_share_swap_page(old_page); - unlock_page(old_page); - if (reuse) { - flush_cache_page(vma, address, pfn); - entry = pte_mkyoung(orig_pte); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - ptep_set_access_flags(vma, address, page_table, entry, 1); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); - ret |= VM_FAULT_WRITE; - goto unlock; + if (vma->vm_ops->page_mkwrite(vma, old_page) < 0) + goto unwritable_page; + + page_cache_release(old_page); + + /* + * Since we dropped the lock we need to revalidate + * the PTE as someone else may have changed it. If + * they did, we just return, as we can count on the + * MMU to tell us if they didn't also make it writable. + */ + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + if (!pte_same(*page_table, orig_pte)) + goto unlock; } + + reuse = 1; + } else if (PageAnon(old_page) && !TestSetPageLocked(old_page)) { + reuse = can_share_swap_page(old_page); + unlock_page(old_page); + } else { + reuse = 0; + } + + if (reuse) { + flush_cache_page(vma, address, pte_pfn(orig_pte)); + entry = pte_mkyoung(orig_pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + ptep_set_access_flags(vma, address, page_table, entry, 1); + update_mmu_cache(vma, address, entry); + lazy_mmu_prot_update(entry); + ret |= VM_FAULT_WRITE; + goto unlock; } /* * Ok, we need to copy. Oh, well.. */ page_cache_get(old_page); - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); +gotten: + pte_unmap_unlock(page_table, ptl); if (unlikely(anon_vma_prepare(vma))) goto oom; @@ -1301,43 +1531,50 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); if (!new_page) goto oom; - copy_user_highpage(new_page, old_page, address); + cow_user_page(new_page, old_page, address); } /* * Re-check the pte - we dropped the lock */ - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (likely(pte_same(*page_table, orig_pte))) { - page_remove_rmap(old_page); - if (!PageAnon(old_page)) { + if (old_page) { + page_remove_rmap(old_page); + if (!PageAnon(old_page)) { + dec_mm_counter(mm, file_rss); + inc_mm_counter(mm, anon_rss); + } + } else inc_mm_counter(mm, anon_rss); - dec_mm_counter(mm, file_rss); - } - flush_cache_page(vma, address, pfn); + 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); + lazy_mmu_prot_update(entry); ptep_establish(vma, address, page_table, entry); update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); - lru_cache_add_active(new_page); - page_add_anon_rmap(new_page, vma, address); + page_add_new_anon_rmap(new_page, vma, address); /* Free the old page.. */ new_page = old_page; ret |= VM_FAULT_WRITE; } - page_cache_release(new_page); - page_cache_release(old_page); + if (new_page) + page_cache_release(new_page); + if (old_page) + page_cache_release(old_page); unlock: - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); return ret; oom: - page_cache_release(old_page); + if (old_page) + page_cache_release(old_page); return VM_FAULT_OOM; + +unwritable_page: + page_cache_release(old_page); + return VM_FAULT_SIGBUS; } /* @@ -1405,13 +1642,6 @@ again: restart_addr = zap_page_range(vma, start_addr, end_addr - start_addr, details); - - /* - * We cannot rely on the break test in unmap_vmas: - * on the one hand, we don't want to restart our loop - * just because that broke out for the page_table_lock; - * on the other hand, it does no test when vma is small. - */ need_break = need_resched() || need_lockbreak(details->i_mmap_lock); @@ -1600,9 +1830,32 @@ out_big: out_busy: return -ETXTBSY; } - EXPORT_SYMBOL(vmtruncate); +int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) +{ + struct address_space *mapping = inode->i_mapping; + + /* + * If the underlying filesystem is not going to provide + * 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) + return -ENOSYS; + + mutex_lock(&inode->i_mutex); + down_write(&inode->i_alloc_sem); + unmap_mapping_range(mapping, offset, (end - offset), 1); + truncate_inode_pages_range(mapping, offset, end); + inode->i_op->truncate_range(inode, offset, end); + up_write(&inode->i_alloc_sem); + mutex_unlock(&inode->i_mutex); + + return 0; +} +EXPORT_UNUSED_SYMBOL(vmtruncate_range); /* June 2006 */ + /* * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen @@ -1660,53 +1913,59 @@ void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struc } /* - * We hold the mm semaphore and the page_table_lock on entry and - * should release the pagetable lock on exit.. + * 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. */ 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) { + spinlock_t *ptl; struct page *page; swp_entry_t entry; pte_t pte; int ret = VM_FAULT_MINOR; - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + 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); + goto out; + } + delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry); if (!page) { swapin_readahead(entry, address, vma); page = read_swap_cache_async(entry, vma, address); if (!page) { /* - * Back out if somebody else faulted in this pte while - * we released the page table lock. + * Back out if somebody else faulted in this pte + * while we released the pte lock. */ - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (likely(pte_same(*page_table, orig_pte))) ret = VM_FAULT_OOM; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; - inc_page_state(pgmajfault); + count_vm_event(PGMAJFAULT); grab_swap_token(); } + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); mark_page_accessed(page); lock_page(page); /* - * Back out if somebody else faulted in this pte while we - * released the page table lock. + * Back out if somebody else already faulted in this pte. */ - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (unlikely(!pte_same(*page_table, orig_pte))) goto out_nomap; @@ -1735,7 +1994,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (write_access) { if (do_wp_page(mm, vma, address, - page_table, pmd, pte) == VM_FAULT_OOM) + page_table, pmd, ptl, pte) == VM_FAULT_OOM) ret = VM_FAULT_OOM; goto out; } @@ -1744,37 +2003,32 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, update_mmu_cache(vma, address, pte); lazy_mmu_prot_update(pte); unlock: - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); out: return ret; out_nomap: - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); unlock_page(page); page_cache_release(page); return ret; } /* - * We are called with the MM semaphore and page_table_lock - * spinlock held to protect against concurrent faults in - * multithreaded programs. + * 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. */ 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) { - struct page *page = ZERO_PAGE(addr); + struct page *page; + spinlock_t *ptl; pte_t entry; - /* Mapping of ZERO_PAGE - vm_page_prot is readonly */ - entry = mk_pte(page, vma->vm_page_prot); - if (write_access) { /* Allocate our own private page. */ pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); if (unlikely(anon_vma_prepare(vma))) goto oom; @@ -1782,23 +2036,27 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!page) goto oom; - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); - - if (!pte_none(*page_table)) { - page_cache_release(page); - goto unlock; - } - inc_mm_counter(mm, anon_rss); entry = mk_pte(page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); + + 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); - SetPageReferenced(page); - page_add_anon_rmap(page, vma, address); + page_add_new_anon_rmap(page, vma, address); } else { + /* Map the ZERO_PAGE - vm_page_prot is readonly */ + page = ZERO_PAGE(address); + page_cache_get(page); + entry = mk_pte(page, vma->vm_page_prot); + + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (!pte_none(*page_table)) + goto release; inc_mm_counter(mm, file_rss); page_add_file_rmap(page); - page_cache_get(page); } set_pte_at(mm, address, page_table, entry); @@ -1807,9 +2065,11 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, update_mmu_cache(vma, address, entry); lazy_mmu_prot_update(entry); unlock: - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); return VM_FAULT_MINOR; +release: + page_cache_release(page); + goto unlock; oom: return VM_FAULT_OOM; } @@ -1823,13 +2083,15 @@ oom: * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * - * This is called with the MM semaphore held and the page table - * spinlock held. Exit with the spinlock released. + * 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. */ static int do_no_page(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; struct page *new_page; struct address_space *mapping = NULL; pte_t entry; @@ -1838,7 +2100,7 @@ static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma, int anon = 0; pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + BUG_ON(vma->vm_flags & VM_PFNMAP); if (vma->vm_file) { mapping = vma->vm_file->f_mapping; @@ -1864,35 +2126,47 @@ retry: /* * Should we do an early C-O-W break? */ - if (write_access && !(vma->vm_flags & VM_SHARED)) { - struct page *page; + if (write_access) { + if (!(vma->vm_flags & VM_SHARED)) { + struct page *page; - if (unlikely(anon_vma_prepare(vma))) - goto oom; - page = alloc_page_vma(GFP_HIGHUSER, vma, address); - if (!page) - goto oom; - copy_user_highpage(page, new_page, address); - page_cache_release(new_page); - new_page = page; - anon = 1; + if (unlikely(anon_vma_prepare(vma))) + goto oom; + page = alloc_page_vma(GFP_HIGHUSER, vma, address); + if (!page) + goto oom; + copy_user_highpage(page, new_page, address); + page_cache_release(new_page); + new_page = page; + anon = 1; + + } else { + /* if the page will be shareable, see if the backing + * address space wants to know that the page is about + * to become writable */ + if (vma->vm_ops->page_mkwrite && + vma->vm_ops->page_mkwrite(vma, new_page) < 0 + ) { + page_cache_release(new_page); + return VM_FAULT_SIGBUS; + } + } } - spin_lock(&mm->page_table_lock); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); /* * For a file-backed vma, someone could have truncated or otherwise * invalidated this page. If unmap_mapping_range got called, * retry getting the page. */ if (mapping && unlikely(sequence != mapping->truncate_count)) { - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); page_cache_release(new_page); cond_resched(); sequence = mapping->truncate_count; smp_rmb(); goto retry; } - page_table = pte_offset_map(pmd, address); /* * This silly early PAGE_DIRTY setting removes a race @@ -1914,8 +2188,8 @@ retry: if (anon) { inc_mm_counter(mm, anon_rss); lru_cache_add_active(new_page); - page_add_anon_rmap(new_page, vma, address); - } else if (!(vma->vm_flags & VM_RESERVED)) { + page_add_new_anon_rmap(new_page, vma, address); + } else { inc_mm_counter(mm, file_rss); page_add_file_rmap(new_page); } @@ -1929,8 +2203,7 @@ retry: update_mmu_cache(vma, address, entry); lazy_mmu_prot_update(entry); unlock: - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); return ret; oom: page_cache_release(new_page); @@ -1941,6 +2214,10 @@ oom: * Fault of a previously existing named mapping. Repopulate the pte * from the encoded file_pte if possible. This enables swappable * nonlinear vmas. + * + * 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. */ static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, @@ -1949,8 +2226,8 @@ static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma, pgoff_t pgoff; int err; - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + return VM_FAULT_MINOR; if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { /* @@ -1989,9 +2266,10 @@ static inline int handle_pte_fault(struct mm_struct *mm, pte_t *pte, pmd_t *pmd, int write_access) { pte_t entry; + pte_t old_entry; + spinlock_t *ptl; - spin_lock(&mm->page_table_lock); - entry = *pte; + old_entry = entry = *pte; if (!pte_present(entry)) { if (pte_none(entry)) { if (!vma->vm_ops || !vma->vm_ops->nopage) @@ -2007,17 +2285,33 @@ static inline int handle_pte_fault(struct mm_struct *mm, pte, pmd, write_access, entry); } + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (unlikely(!pte_same(*pte, entry))) + goto unlock; if (write_access) { if (!pte_write(entry)) - return do_wp_page(mm, vma, address, pte, pmd, entry); + return do_wp_page(mm, vma, address, + pte, pmd, ptl, entry); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - ptep_set_access_flags(vma, address, pte, entry, write_access); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + if (!pte_same(old_entry, entry)) { + ptep_set_access_flags(vma, address, pte, entry, write_access); + update_mmu_cache(vma, address, entry); + lazy_mmu_prot_update(entry); + } else { + /* + * This is needed only for protection faults but the arch code + * is not yet telling us if this is a protection fault or not. + * This still avoids useless tlb flushes for .text page faults + * with threads. + */ + if (write_access) + flush_tlb_page(vma, address); + } +unlock: + pte_unmap_unlock(pte, ptl); return VM_FAULT_MINOR; } @@ -2034,7 +2328,7 @@ int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, __set_current_state(TASK_RUNNING); - inc_page_state(pgfault); + count_vm_event(PGFAULT); if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, write_access); @@ -2053,6 +2347,8 @@ int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, return handle_pte_fault(mm, vma, address, pte, pmd, write_access); } +EXPORT_SYMBOL_GPL(__handle_mm_fault); + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. @@ -2072,6 +2368,12 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) spin_unlock(&mm->page_table_lock); return 0; } +#else +/* Workaround for gcc 2.96 */ +int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + return 0; +} #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED @@ -2100,6 +2402,12 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) spin_unlock(&mm->page_table_lock); return 0; } +#else +/* Workaround for gcc 2.96 */ +int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) +{ + return 0; +} #endif /* __PAGETABLE_PMD_FOLDED */ int make_pages_present(unsigned long addr, unsigned long end) @@ -2111,10 +2419,8 @@ int make_pages_present(unsigned long addr, unsigned long end) if (!vma) return -1; write = (vma->vm_flags & VM_WRITE) != 0; - if (addr >= end) - BUG(); - if (end > vma->vm_end) - BUG(); + BUG_ON(addr >= end); + BUG_ON(end > vma->vm_end); len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE; ret = get_user_pages(current, current->mm, addr, len, write, 0, NULL, NULL); @@ -2174,7 +2480,7 @@ static int __init gate_vma_init(void) gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_page_prot = PAGE_READONLY; - gate_vma.vm_flags = VM_RESERVED; + gate_vma.vm_flags = 0; return 0; } __initcall(gate_vma_init);