X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fmemory.c;h=7a11ddd5060ff51067523c7872b85e0539537385;hb=1b1dcc1b57a49136f118a0f16367256ff9994a69;hp=d1f46f4e4c8a8594ffa649f15dd03d6cd6eda944;hpb=f57e88a8d83de8d844b57e16b84d2f762fe9f092;p=linux-2.6 diff --git a/mm/memory.c b/mm/memory.c index d1f46f4e4c..7a11ddd506 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -333,9 +333,9 @@ 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_UNPAGED 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. */ @@ -349,20 +349,64 @@ 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; +} + /* - * page_is_anon applies strict checks for an anonymous page belonging to - * this vma at this address. It is used on VM_UNPAGED vmas, which are - * usually populated with shared originals (which must not be counted), - * but occasionally contain private COWed copies (when !VM_SHARED, or - * perhaps via ptrace when VM_SHARED). An mmap of /dev/mem might window - * free pages, pages from other processes, or from other parts of this: - * it's tricky, but try not to be deceived by foreign anonymous pages. + * 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). */ -static inline int page_is_anon(struct page *page, - struct vm_area_struct *vma, unsigned long addr) +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - return page && PageAnon(page) && page_mapped(page) && - page_address_in_vma(page, vma) == addr; + unsigned long pfn = pte_pfn(pte); + + if (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. + * + * Remove this test eventually! + */ + 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); } /* @@ -379,7 +423,6 @@ 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))) { @@ -397,27 +440,11 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_set_pte; } - pfn = pte_pfn(pte); - page = pfn_valid(pfn)? pfn_to_page(pfn): NULL; - - if (unlikely(vm_flags & VM_UNPAGED)) - if (!page_is_anon(page, vma, addr)) - goto out_set_pte; - - /* - * If the pte points outside of valid memory but - * the region is not VM_UNPAGED, we have a problem. - */ - if (unlikely(!page)) { - print_bad_pte(vma, pte, addr); - goto out_set_pte; /* try to do something sane */ - } - /* * 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; } @@ -429,9 +456,13 @@ 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); @@ -543,7 +574,7 @@ 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_UNPAGED))) { + if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) { if (!vma->anon_vma) return 0; } @@ -584,19 +615,10 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, } if (pte_present(ptent)) { struct page *page; - unsigned long pfn; (*zap_work) -= PAGE_SIZE; - pfn = pte_pfn(ptent); - page = pfn_valid(pfn)? pfn_to_page(pfn): NULL; - - if (unlikely(vma->vm_flags & VM_UNPAGED)) { - if (!page_is_anon(page, vma, addr)) - page = NULL; - } else if (unlikely(!page)) - print_bad_pte(vma, ptent, addr); - + page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to @@ -852,7 +874,7 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, /* * Do a quick page-table lookup for a single page. */ -struct page *follow_page(struct mm_struct *mm, unsigned long address, +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { pgd_t *pgd; @@ -860,8 +882,8 @@ struct page *follow_page(struct mm_struct *mm, unsigned long address, pmd_t *pmd; pte_t *ptep, pte; spinlock_t *ptl; - unsigned long pfn; struct page *page; + struct mm_struct *mm = vma->vm_mm; page = follow_huge_addr(mm, address, flags & FOLL_WRITE); if (!IS_ERR(page)) { @@ -897,11 +919,10 @@ struct page *follow_page(struct mm_struct *mm, unsigned long address, goto unlock; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; - pfn = pte_pfn(pte); - if (!pfn_valid(pfn)) + page = vm_normal_page(vma, address, pte); + if (unlikely(!page)) goto unlock; - page = pfn_to_page(pfn); if (flags & FOLL_GET) get_page(page); if (flags & FOLL_TOUCH) { @@ -974,8 +995,10 @@ 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) @@ -986,7 +1009,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } - if (!vma || (vma->vm_flags & VM_IO) + if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP)) || !(vm_flags & vma->vm_flags)) return i ? : -EFAULT; @@ -1010,7 +1033,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, foll_flags |= FOLL_WRITE; cond_resched(); - while (!(page = follow_page(mm, start, foll_flags))) { + while (!(page = follow_page(vma, start, foll_flags))) { int ret; ret = __handle_mm_fault(mm, vma, start, foll_flags & FOLL_WRITE); @@ -1130,6 +1153,86 @@ 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 + * (which is mainly an issue of doing "set_page_count(page, 1)" for + * each sub-page, and then freeing them one by one when you free + * them rather than freeing it as a compound 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 @@ -1214,11 +1317,21 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * 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_UNPAGED tells the core MM not to "manage" these pages - * (e.g. refcount, mapcount, try to swap them out): in - * particular, zap_pte_range does not try to free them. + * 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 | VM_UNPAGED; + 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; @@ -1273,6 +1386,33 @@ 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 @@ -1295,35 +1435,19 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte) { - struct page *old_page, *src_page, *new_page; - unsigned long pfn = pte_pfn(orig_pte); + struct page *old_page, *new_page; pte_t entry; int ret = VM_FAULT_MINOR; - if (unlikely(!pfn_valid(pfn))) { - /* - * Page table corrupted: show pte and kill process. - * Or it's an attempt to COW an out-of-map VM_UNPAGED - * entry, which copy_user_highpage does not support. - */ - print_bad_pte(vma, orig_pte, address); - ret = VM_FAULT_OOM; - goto unlock; - } - old_page = pfn_to_page(pfn); - src_page = old_page; - - if (unlikely(vma->vm_flags & VM_UNPAGED)) - if (!page_is_anon(old_page, vma, address)) { - old_page = NULL; - goto gotten; - } + old_page = vm_normal_page(vma, address, orig_pte); + if (!old_page) + goto gotten; 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); + 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); @@ -1343,7 +1467,7 @@ gotten: if (unlikely(anon_vma_prepare(vma))) goto oom; - if (src_page == ZERO_PAGE(address)) { + if (old_page == ZERO_PAGE(address)) { new_page = alloc_zeroed_user_highpage(vma, address); if (!new_page) goto oom; @@ -1351,7 +1475,7 @@ gotten: new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); if (!new_page) goto oom; - copy_user_highpage(new_page, src_page, address); + cow_user_page(new_page, old_page, address); } /* @@ -1367,14 +1491,14 @@ gotten: } } else inc_mm_counter(mm, anon_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); 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; @@ -1646,9 +1770,32 @@ 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_SYMBOL(vmtruncate_range); + /* * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen @@ -1812,16 +1959,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, spinlock_t *ptl; pte_t entry; - /* - * A VM_UNPAGED vma will normally be filled with present ptes - * by remap_pfn_range, and never arrive here; but it might have - * holes, or if !VM_DONTEXPAND, mremap might have expanded it. - * It's weird enough handling anon pages in unpaged vmas, we do - * not want to worry about ZERO_PAGEs too (it may or may not - * matter if their counts wrap): just give them anon pages. - */ - - if (write_access || (vma->vm_flags & VM_UNPAGED)) { + if (write_access) { /* Allocate our own private page. */ pte_unmap(page_table); @@ -1839,8 +1977,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, 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); @@ -1896,7 +2033,7 @@ static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma, int anon = 0; pte_unmap(page_table); - BUG_ON(vma->vm_flags & VM_UNPAGED); + BUG_ON(vma->vm_flags & VM_PFNMAP); if (vma->vm_file) { mapping = vma->vm_file->f_mapping; @@ -1971,7 +2108,7 @@ retry: if (anon) { inc_mm_counter(mm, anon_rss); lru_cache_add_active(new_page); - page_add_anon_rmap(new_page, vma, address); + page_add_new_anon_rmap(new_page, vma, address); } else { inc_mm_counter(mm, file_rss); page_add_file_rmap(new_page); @@ -2130,6 +2267,8 @@ 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. @@ -2149,6 +2288,12 @@ 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 @@ -2177,6 +2322,12 @@ 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)