X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemory.c;h=4126dd16778c36595af938988c9d8ec144d0f8aa;hb=0f181328287db30671e9997329cff71395d4af8b;hp=717aa0e3be2d7d9b0385411257a89d50f6ea3afc;hpb=900cf086fd2fbad07f72f4575449e0d0958f860f;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/memory.c b/mm/memory.c index 717aa0e..4126dd1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -51,6 +51,10 @@ #include #include #include +#include +#include +#include +#include #include #include @@ -58,8 +62,7 @@ #include #include -#include -#include +#include "internal.h" #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ @@ -211,7 +214,7 @@ 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 +265,16 @@ 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) { @@ -311,6 +314,21 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) if (!new) return -ENOMEM; + /* + * Ensure all pte setup (eg. pte page lock and page clearing) are + * visible before the pte is made visible to other CPUs by being + * put into page tables. + * + * The other side of the story is the pointer chasing in the page + * table walking code (when walking the page table without locking; + * ie. most of the time). Fortunately, these data accesses consist + * of a chain of data-dependent loads, meaning most CPUs (alpha + * being the notable exception) will already guarantee loads are + * seen in-order. See the alpha page table accessors for the + * smp_read_barrier_depends() barriers in page table walking code. + */ + smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ + spin_lock(&mm->page_table_lock); if (!pmd_present(*pmd)) { /* Has another populated it ? */ mm->nr_ptes++; @@ -329,6 +347,8 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&init_mm.page_table_lock); if (!pmd_present(*pmd)) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); @@ -355,14 +375,65 @@ 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) @@ -371,57 +442,93 @@ static inline int is_cow_mapping(unsigned int flags) } /* - * This function gets the "struct page" associated with a pte. + * vm_normal_page -- 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". + * "Special" mappings do not wish to be associated with a "struct page" (either + * it doesn't exist, or it exists but they don't want to touch it). In this + * case, NULL is returned here. "Normal" mappings do have 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 + * There are 2 broad cases. Firstly, an architecture may define a pte_special() + * pte bit, in which case this function is trivial. Secondly, an architecture + * may not have a spare pte bit, which requires a more complicated scheme, + * described below. + * + * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a + * special mapping (even if there are underlying and valid "struct pages"). + * COWed pages of a VM_PFNMAP are always normal. + * + * The way we recognize COWed pages within VM_PFNMAP 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 special + * 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). + * And for normal mappings this is false. + * + * This restricts such mappings to be a linear translation from virtual address + * to pfn. To get around this restriction, we allow arbitrary mappings so long + * as the vma is not a COW mapping; in that case, we know that all ptes are + * special (because none can have been COWed). + * + * + * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. + * + * VM_MIXEDMAP mappings can likewise contain memory with or without "struct + * page" backing, however the difference is that _all_ pages with a struct + * page (that is, those where pfn_valid is true) are refcounted and considered + * normal pages by the VM. The disadvantage is that pages are refcounted + * (which can be slower and simply not an option for some PFNMAP users). The + * advantage is that we don't have to follow the strict linearity rule of + * PFNMAP mappings in order to support COWable mappings. + * */ -struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) +#ifdef __HAVE_ARCH_PTE_SPECIAL +# define HAVE_PTE_SPECIAL 1 +#else +# define HAVE_PTE_SPECIAL 0 +#endif +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; + if (HAVE_PTE_SPECIAL) { + if (likely(!pte_special(pte))) + goto check_pfn; + if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))) + print_bad_pte(vma, addr, pte, NULL); + return NULL; } -#ifdef CONFIG_DEBUG_VM - /* - * 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); + /* !HAVE_PTE_SPECIAL case follows: */ + + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + +check_pfn: + if (unlikely(pfn > highest_memmap_pfn)) { + print_bad_pte(vma, addr, pte, NULL); return NULL; } -#endif /* - * NOTE! We still have PageReserved() pages in the page - * tables. - * - * The PAGE_ZERO() pages and various VDSO mappings can - * cause them to exist. + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. */ +out: return pfn_to_page(pfn); } @@ -596,6 +703,7 @@ 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. @@ -611,17 +719,43 @@ 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, @@ -683,11 +817,14 @@ 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; } @@ -697,8 +834,12 @@ 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)); @@ -825,7 +966,9 @@ 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; @@ -839,6 +982,9 @@ 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; @@ -846,9 +992,23 @@ 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, @@ -876,6 +1036,7 @@ 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 */ } @@ -903,6 +1064,29 @@ 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. */ @@ -929,31 +1113,37 @@ 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; - - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + 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; ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!ptep) - goto out; pte = *ptep; if (!pte_present(pte)) - goto unlock; + goto no_page; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; page = vm_normal_page(vma, address, pte); if (unlikely(!page)) - goto unlock; + goto bad_page; if (flags & FOLL_GET) get_page(page); @@ -961,6 +1151,11 @@ 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: @@ -968,6 +1163,15 @@ unlock: out: return page; +bad_page: + pte_unmap_unlock(ptep, ptl); + return ERR_PTR(-EFAULT); + +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 @@ -982,12 +1186,36 @@ no_page_table: return page; } -int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int write, int force, +/* Can we do the FOLL_ANON optimization? */ +static inline int use_zero_page(struct vm_area_struct *vma) +{ + /* + * We don't want to optimize FOLL_ANON for make_pages_present() + * when it tries to page in a VM_LOCKED region. As to VM_SHARED, + * we want to get the page from the page tables to make sure + * that we serialize and update with any other user of that + * mapping. + */ + if (vma->vm_flags & (VM_LOCKED | VM_SHARED)) + return 0; + /* + * And if we have a fault routine, it's not an anonymous region. + */ + return !vma->vm_ops || !vma->vm_ops->fault; +} + + + +int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int len, int flags, struct page **pages, struct vm_area_struct **vmas) { int i; - unsigned int vm_flags; + unsigned int vm_flags = 0; + int write = !!(flags & GUP_FLAGS_WRITE); + int force = !!(flags & GUP_FLAGS_FORCE); + int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS); + int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL); if (len <= 0) return 0; @@ -1011,7 +1239,9 @@ 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 (!ignore && write) return i ? : -EFAULT; if (pg > TASK_SIZE) pgd = pgd_offset_k(pg); @@ -1043,8 +1273,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } - if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP)) - || !(vm_flags & vma->vm_flags)) + if (!vma || + (vma->vm_flags & (VM_IO | VM_PFNMAP)) || + (!ignore && !(vm_flags & vma->vm_flags))) return i ? : -EFAULT; if (is_vm_hugetlb_page(vma)) { @@ -1056,21 +1287,22 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, foll_flags = FOLL_TOUCH; if (pages) foll_flags |= FOLL_GET; - if (!write && !(vma->vm_flags & VM_LOCKED) && - (!vma->vm_ops || (!vma->vm_ops->nopage && - !vma->vm_ops->fault))) + if (!write && use_zero_page(vma)) foll_flags |= FOLL_ANON; do { struct page *page; /* - * 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, unless + * current is handling munlock--e.g., on exit. In + * that case, we are not allocating memory. Rather, + * we're only unlocking already resident/mapped pages. */ - if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE))) - return -ENOMEM; + if (unlikely(!ignore_sigkill && + fatal_signal_pending(current))) + return i ? i : -ERESTARTSYS; if (write) foll_flags |= FOLL_WRITE; @@ -1097,13 +1329,21 @@ 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(); } + if (IS_ERR(page)) + return i ? i : PTR_ERR(page); if (pages) { pages[i] = page; @@ -1119,6 +1359,23 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, } while (len); return i; } + +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 flags = 0; + + if (write) + flags |= GUP_FLAGS_WRITE; + if (force) + flags |= GUP_FLAGS_FORCE; + + return __get_user_pages(tsk, mm, + start, len, flags, + pages, vmas); +} + EXPORT_SYMBOL(get_user_pages); pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, @@ -1141,24 +1398,22 @@ pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, * 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) +static int insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, pgprot_t prot) { + struct mm_struct *mm = vma->vm_mm; int retval; 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; @@ -1174,8 +1429,6 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa return retval; out_unlock: pte_unmap_unlock(pte, ptl); -out_uncharge: - mem_cgroup_uncharge_page(page); out: return retval; } @@ -1202,40 +1455,26 @@ out: * * The page does not need to be reserved. */ -int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) +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); + return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); -/** - * vm_insert_pfn - insert single pfn into user vma - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * - * Similar to vm_inert_page, this allows drivers to insert individual pages - * they've allocated into a user vma. Same comments apply. - * - * This function should only be called from a vm_ops->fault handler, and - * in that case the handler should return NULL. - */ -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) +static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte, entry; spinlock_t *ptl; - BUG_ON(!(vma->vm_flags & VM_PFNMAP)); - BUG_ON(is_cow_mapping(vma->vm_flags)); - retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) @@ -1245,19 +1484,89 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, goto out_unlock; /* Ok, finally just insert the thing.. */ - entry = pfn_pte(pfn, vma->vm_page_prot); + entry = pte_mkspecial(pfn_pte(pfn, prot)); set_pte_at(mm, addr, pte, entry); - update_mmu_cache(vma, addr, entry); + update_mmu_cache(vma, addr, entry); /* XXX: why not for insert_page? */ retval = 0; out_unlock: pte_unmap_unlock(pte, ptl); - out: return retval; } + +/** + * vm_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_inert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * 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 + * consistency in testing and feature parity among all, so we should + * try to keep these invariants in place for everybody. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + 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); +int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + + /* + * 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). + */ + if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { + struct page *page; + + page = pfn_to_page(pfn); + return insert_page(vma, addr, page, vma->vm_page_prot); + } + return insert_pfn(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_mixed); + /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results @@ -1276,7 +1585,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); - set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); + set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); @@ -1361,14 +1670,25 @@ 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); @@ -1380,6 +1700,10 @@ 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); @@ -1401,6 +1725,8 @@ 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 { @@ -1409,6 +1735,8 @@ 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; @@ -1422,6 +1750,8 @@ 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; @@ -1463,10 +1793,11 @@ 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); @@ -1474,6 +1805,7 @@ 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); @@ -1571,18 +1903,40 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *dirty_page = NULL; old_page = vm_normal_page(vma, address, orig_pte); - if (!old_page) + if (!old_page) { + /* + * VM_MIXEDMAP !pfn_valid() case + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable as we can't do any dirty + * accounting on raw pfn maps. + */ + if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED)) + goto reuse; goto gotten; + } /* * 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 (!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))) { /* @@ -1591,6 +1945,15 @@ 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 @@ -1602,8 +1965,21 @@ 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 @@ -1613,9 +1989,11 @@ 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; } @@ -1625,6 +2003,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, } if (reuse) { +reuse: flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -1647,10 +2026,19 @@ gotten: new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (!new_page) goto oom; + /* + * 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); + } cow_user_page(new_page, old_page, address, vma); __SetPageUptodate(new_page); - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; /* @@ -1659,7 +2047,6 @@ gotten: page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { - page_remove_rmap(old_page, vma); if (!PageAnon(old_page)) { dec_mm_counter(mm, file_rss); inc_mm_counter(mm, anon_rss); @@ -1675,11 +2062,35 @@ gotten: * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush(vma, address, page_table); + ptep_clear_flush_notify(vma, address, page_table); + page_add_new_anon_rmap(new_page, vma, address); 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); + if (old_page) { + /* + * Only after switching the pte to the new page may + * we remove the mapcount here. Otherwise another + * process may come and find the rmap count decremented + * before the pte is switched to the new page, and + * "reuse" the old page writing into it while our pte + * here still points into it and can be read by other + * threads. + * + * The critical issue is to order this + * page_remove_rmap with the ptp_clear_flush above. + * Those stores are ordered by (if nothing else,) + * the barrier present in the atomic_add_negative + * in page_remove_rmap. + * + * Then the TLB flush in ptep_clear_flush ensures that + * no process can access the old page before the + * decremented mapcount is visible. And the old page + * cannot be reused until after the decremented + * mapcount is visible. So transitively, TLBs to + * old page will be flushed before it can be reused. + */ + page_remove_rmap(old_page); + } /* Free the old page.. */ new_page = old_page; @@ -1694,9 +2105,6 @@ 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 @@ -1705,21 +2113,46 @@ 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: - __free_page(new_page); + 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; } /* @@ -1971,7 +2404,7 @@ 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; @@ -1991,7 +2424,7 @@ 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); @@ -2019,6 +2452,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, 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)) @@ -2052,16 +2486,14 @@ 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. */ @@ -2074,31 +2506,41 @@ 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 (write_access && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); write_access = 0; } - 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) { - /* XXX: We could OR the do_wp_page code with this one? */ - if (do_wp_page(mm, vma, address, - page_table, pmd, ptl, pte) & VM_FAULT_OOM) { - mem_cgroup_uncharge_page(page); - ret = VM_FAULT_OOM; - } + ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); + if (ret & VM_FAULT_ERROR) + ret &= VM_FAULT_ERROR; goto out; } @@ -2109,8 +2551,9 @@ 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; @@ -2139,7 +2582,7 @@ 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); @@ -2149,7 +2592,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, 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); set_pte_at(mm, address, page_table, entry); @@ -2163,7 +2605,7 @@ release: page_cache_release(page); goto unlock; oom_free_page: - __free_page(page); + page_cache_release(page); oom: return VM_FAULT_OOM; } @@ -2190,6 +2632,7 @@ 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; @@ -2200,22 +2643,9 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, vmf.flags = flags; vmf.page = NULL; - BUG_ON(vma->vm_flags & VM_PFNMAP); - - if (likely(vma->vm_ops->fault)) { - ret = vma->vm_ops->fault(vma, &vmf); - if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) - return ret; - } else { - /* Legacy ->nopage path */ - ret = 0; - vmf.page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret); - /* no page was available -- either SIGBUS or OOM */ - if (unlikely(vmf.page == NOPAGE_SIGBUS)) - return VM_FAULT_SIGBUS; - else if (unlikely(vmf.page == NOPAGE_OOM)) - return VM_FAULT_OOM; - } + ret = vma->vm_ops->fault(vma, &vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + return ret; /* * For consistency in subsequent calls, make the faulted page always @@ -2243,6 +2673,18 @@ 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 { @@ -2252,36 +2694,31 @@ 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); /* @@ -2300,11 +2737,9 @@ 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); @@ -2313,11 +2748,13 @@ 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 @@ -2327,19 +2764,35 @@ 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, @@ -2354,56 +2807,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, 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)); - BUG_ON(is_cow_mapping(vma->vm_flags)); - - pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK); - 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 @@ -2424,12 +2827,11 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, 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; } @@ -2461,12 +2863,9 @@ static inline int handle_pte_fault(struct mm_struct *mm, if (!pte_present(entry)) { if (pte_none(entry)) { if (vma->vm_ops) { - if (vma->vm_ops->fault || vma->vm_ops->nopage) + 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); } return do_anonymous_page(mm, vma, address, pte, pmd, write_access); @@ -2549,6 +2948,8 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ pud_free(mm, new); @@ -2570,6 +2971,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK if (pud_present(*pud)) /* Another has populated it */ @@ -2594,7 +2997,7 @@ 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); @@ -2603,7 +3006,7 @@ 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) @@ -2650,6 +3053,83 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ +#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) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + resource_size_t phys_addr = 0; + struct mm_struct *mm = vma->vm_mm; + int ret = -EINVAL; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; + + 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, &ptl); + if (!ptep) + goto out; + + pte = *ptep; + if (!pte_present(pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + phys_addr = pte_pfn(pte); + phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ + + *prot = pgprot_val(pte_pgprot(pte)); + *phys = phys_addr; + 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, @@ -2659,7 +3139,6 @@ 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); @@ -2671,28 +3150,44 @@ 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; @@ -2711,6 +3206,13 @@ void print_vma_addr(char *prefix, unsigned long ip) struct mm_struct *mm = current->mm; struct vm_area_struct *vma; + /* + * Do not print if we are in atomic + * contexts (in exception stacks, etc.): + */ + if (preempt_count()) + return; + down_read(&mm->mmap_sem); vma = find_vma(mm, ip); if (vma && vma->vm_file) { @@ -2719,7 +3221,7 @@ void print_vma_addr(char *prefix, unsigned long ip) if (buf) { char *p, *s; - p = d_path(f->f_dentry, f->f_vfsmnt, buf, PAGE_SIZE); + p = d_path(&f->f_path, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; s = strrchr(p, '/'); @@ -2733,3 +3235,27 @@ 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