X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Fmemory.c;h=c24a375ae5a5dab78e580778fe85bc13604cd78a;hb=refs%2Fheads%2Fvserver;hp=adaca7c22587928833d6dfa50d04cfc24a3b3c4c;hpb=9bf4aaab3e101692164d49b7ca357651eb691cb6;p=linux-2.6.git diff --git a/mm/memory.c b/mm/memory.c index adaca7c22..c24a375ae 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -34,6 +34,8 @@ * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) + * + * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include @@ -45,7 +47,9 @@ #include #include #include +#include #include +#include #include #include @@ -56,7 +60,7 @@ #include #include -#ifndef CONFIG_DISCONTIGMEM +#ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; struct page *mem_map; @@ -74,325 +78,576 @@ unsigned long num_physpages; * and ZONE_HIGHMEM. */ void * high_memory; -struct page *highmem_start_page; unsigned long vmalloc_earlyreserve; EXPORT_SYMBOL(num_physpages); -EXPORT_SYMBOL(highmem_start_page); 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); + + /* - * We special-case the C-O-W ZERO_PAGE, because it's such - * a common occurrence (no need to read the page to know - * that it's zero - better for the cache and memory subsystem). + * If a p?d_bad entry is found while walking page tables, report + * the error, before resetting entry to p?d_none. Usually (but + * very seldom) called out from the p?d_none_or_clear_bad macros. */ -static inline void copy_cow_page(struct page * from, struct page * to, unsigned long address) + +void pgd_clear_bad(pgd_t *pgd) { - if (from == ZERO_PAGE(address)) { - clear_user_highpage(to, address); - return; - } - copy_user_highpage(to, from, address); + pgd_ERROR(*pgd); + pgd_clear(pgd); +} + +void pud_clear_bad(pud_t *pud) +{ + pud_ERROR(*pud); + pud_clear(pud); +} + +void pmd_clear_bad(pmd_t *pmd) +{ + pmd_ERROR(*pmd); + pmd_clear(pmd); } /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ -static inline void free_one_pmd(struct mmu_gather *tlb, pmd_t * dir) +static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd) { - struct page *page; + struct page *page = pmd_page(*pmd); + pmd_clear(pmd); + pte_lock_deinit(page); + pte_free_tlb(tlb, page); + dec_zone_page_state(page, NR_PAGETABLE); + tlb->mm->nr_ptes--; +} - if (pmd_none(*dir)) - return; - if (unlikely(pmd_bad(*dir))) { - pmd_ERROR(*dir); - pmd_clear(dir); +static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pmd_t *pmd; + unsigned long next; + unsigned long start; + + start = addr; + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(pmd)) + continue; + free_pte_range(tlb, pmd); + } while (pmd++, addr = next, addr != end); + + start &= PUD_MASK; + if (start < floor) return; + if (ceiling) { + ceiling &= PUD_MASK; + if (!ceiling) + return; } - page = pmd_page(*dir); - pmd_clear(dir); - dec_page_state(nr_page_table_pages); - pte_free_tlb(tlb, page); + if (end - 1 > ceiling - 1) + return; + + pmd = pmd_offset(pud, start); + pud_clear(pud); + pmd_free_tlb(tlb, pmd); } -static inline void free_one_pgd(struct mmu_gather *tlb, pgd_t * dir) +static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) { - int j; - pmd_t * pmd; + pud_t *pud; + unsigned long next; + unsigned long start; - if (pgd_none(*dir)) - return; - if (unlikely(pgd_bad(*dir))) { - pgd_ERROR(*dir); - pgd_clear(dir); + start = addr; + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + free_pmd_range(tlb, pud, addr, next, floor, ceiling); + } while (pud++, addr = next, addr != end); + + start &= PGDIR_MASK; + if (start < floor) return; + if (ceiling) { + ceiling &= PGDIR_MASK; + if (!ceiling) + return; } - pmd = pmd_offset(dir, 0); - pgd_clear(dir); - for (j = 0; j < PTRS_PER_PMD ; j++) - free_one_pmd(tlb, pmd+j); - pmd_free_tlb(tlb, pmd); + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(pgd, start); + pgd_clear(pgd); + pud_free_tlb(tlb, pud); } /* - * This function clears all user-level page tables of a process - this - * is needed by execve(), so that old pages aren't in the way. + * This function frees user-level page tables of a process. * * Must be called with pagetable lock held. */ -void clear_page_tables(struct mmu_gather *tlb, unsigned long first, int nr) +void free_pgd_range(struct mmu_gather **tlb, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) { - pgd_t * page_dir = tlb->mm->pgd; + pgd_t *pgd; + unsigned long next; + unsigned long start; + + /* + * The next few lines have given us lots of grief... + * + * Why are we testing PMD* at this top level? Because often + * there will be no work to do at all, and we'd prefer not to + * go all the way down to the bottom just to discover that. + * + * Why all these "- 1"s? Because 0 represents both the bottom + * of the address space and the top of it (using -1 for the + * top wouldn't help much: the masks would do the wrong thing). + * The rule is that addr 0 and floor 0 refer to the bottom of + * the address space, but end 0 and ceiling 0 refer to the top + * Comparisons need to use "end - 1" and "ceiling - 1" (though + * that end 0 case should be mythical). + * + * Wherever addr is brought up or ceiling brought down, we must + * be careful to reject "the opposite 0" before it confuses the + * subsequent tests. But what about where end is brought down + * by PMD_SIZE below? no, end can't go down to 0 there. + * + * Whereas we round start (addr) and ceiling down, by different + * masks at different levels, in order to test whether a table + * now has no other vmas using it, so can be freed, we don't + * bother to round floor or end up - the tests don't need that. + */ - page_dir += first; + addr &= PMD_MASK; + if (addr < floor) { + addr += PMD_SIZE; + if (!addr) + return; + } + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + end -= PMD_SIZE; + if (addr > end - 1) + return; + + start = addr; + pgd = pgd_offset((*tlb)->mm, addr); do { - free_one_pgd(tlb, page_dir); - page_dir++; - } while (--nr); + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + free_pud_range(*tlb, pgd, addr, next, floor, ceiling); + } while (pgd++, addr = next, addr != end); + + if (!(*tlb)->fullmm) + flush_tlb_pgtables((*tlb)->mm, start, end); } -pte_t fastcall * pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address) +void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, + unsigned long floor, unsigned long ceiling) { - if (!pmd_present(*pmd)) { - struct page *new; - - spin_unlock(&mm->page_table_lock); - new = pte_alloc_one(mm, address); - spin_lock(&mm->page_table_lock); - if (!new) - return NULL; + while (vma) { + struct vm_area_struct *next = vma->vm_next; + unsigned long addr = vma->vm_start; /* - * Because we dropped the lock, we should re-check the - * entry, as somebody else could have populated it.. + * Hide vma from rmap and vmtruncate before freeing pgtables */ - if (pmd_present(*pmd)) { - pte_free(new); - goto out; + 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 { + /* + * Optimization: gather nearby vmas into one call down + */ + while (next && next->vm_start <= vma->vm_end + PMD_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); } - inc_page_state(nr_page_table_pages); + vma = next; + } +} + +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) +{ + struct page *new = pte_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + pte_lock_init(new); + spin_lock(&mm->page_table_lock); + if (pmd_present(*pmd)) { /* Another has populated it */ + pte_lock_deinit(new); + pte_free(new); + } else { + mm->nr_ptes++; + inc_zone_page_state(new, NR_PAGETABLE); pmd_populate(mm, pmd, new); } -out: - return pte_offset_map(pmd, address); + spin_unlock(&mm->page_table_lock); + return 0; } -pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address) +int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) { - if (!pmd_present(*pmd)) { - pte_t *new; + pte_t *new = pte_alloc_one_kernel(&init_mm, address); + if (!new) + return -ENOMEM; + + spin_lock(&init_mm.page_table_lock); + if (pmd_present(*pmd)) /* Another has populated it */ + pte_free_kernel(new); + else + pmd_populate_kernel(&init_mm, pmd, new); + spin_unlock(&init_mm.page_table_lock); + return 0; +} + +static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) +{ + if (file_rss) + add_mm_counter(mm, file_rss, file_rss); + if (anon_rss) + add_mm_counter(mm, anon_rss, anon_rss); +} - spin_unlock(&mm->page_table_lock); - new = pte_alloc_one_kernel(mm, address); - spin_lock(&mm->page_table_lock); - if (!new) +/* + * 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. + */ +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); + 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; + } - /* - * Because we dropped the lock, we should re-check the - * entry, as somebody else could have populated it.. - */ - if (pmd_present(*pmd)) { - pte_free_kernel(new); - goto out; - } - pmd_populate_kernel(mm, pmd, new); + /* + * 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))) { + if (!(vma->vm_flags & VM_RESERVED)) + print_bad_pte(vma, pte, addr); + return NULL; } -out: - return pte_offset_kernel(pmd, address); + + /* + * 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); } -#define PTE_TABLE_MASK ((PTRS_PER_PTE-1) * sizeof(pte_t)) -#define PMD_TABLE_MASK ((PTRS_PER_PMD-1) * sizeof(pmd_t)) /* * 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 * covered by this vma. - * - * 08Jan98 Merged into one routine from several inline routines to reduce - * variable count and make things faster. -jj - * - * dst->page_table_lock is held on entry and exit, - * but may be dropped within pmd_alloc() and pte_alloc_map(). */ -int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma) + +static inline void +copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, + unsigned long addr, int *rss) { - pgd_t * src_pgd, * dst_pgd; - unsigned long address = vma->vm_start; - unsigned long end = vma->vm_end; - unsigned long cow; + unsigned long vm_flags = vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; - if (is_vm_hugetlb_page(vma)) - return copy_hugetlb_page_range(dst, src, vma); - - cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; - src_pgd = pgd_offset(src, address)-1; - dst_pgd = pgd_offset(dst, address)-1; - - for (;;) { - pmd_t * src_pmd, * dst_pmd; - - src_pgd++; dst_pgd++; - - /* copy_pmd_range */ - - if (pgd_none(*src_pgd)) - goto skip_copy_pmd_range; - if (unlikely(pgd_bad(*src_pgd))) { - pgd_ERROR(*src_pgd); - pgd_clear(src_pgd); -skip_copy_pmd_range: address = (address + PGDIR_SIZE) & PGDIR_MASK; - if (!address || (address >= end)) - goto out; - continue; + /* pte contains position in swap or file, so copy. */ + if (unlikely(!pte_present(pte))) { + if (!pte_file(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); + 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; + } - src_pmd = pmd_offset(src_pgd, address); - dst_pmd = pmd_alloc(dst, dst_pgd, address); - if (!dst_pmd) - goto nomem; + /* + * If it's a COW mapping, write protect it both + * in the parent and the child + */ + if (is_cow_mapping(vm_flags)) { + ptep_set_wrprotect(src_mm, addr, src_pte); + pte = pte_wrprotect(pte); + } - do { - pte_t * src_pte, * dst_pte; - - /* copy_pte_range */ - - if (pmd_none(*src_pmd)) - goto skip_copy_pte_range; - if (unlikely(pmd_bad(*src_pmd))) { - pmd_ERROR(*src_pmd); - pmd_clear(src_pmd); -skip_copy_pte_range: - address = (address + PMD_SIZE) & PMD_MASK; - if (address >= end) - goto out; - goto cont_copy_pmd_range; - } + /* + * If it's a shared mapping, mark it clean in + * the child + */ + if (vm_flags & VM_SHARED) + pte = pte_mkclean(pte); + pte = pte_mkold(pte); + + page = vm_normal_page(vma, addr, pte); + if (page) { + get_page(page); + page_dup_rmap(page); + rss[!!PageAnon(page)]++; + } - dst_pte = pte_alloc_map(dst, dst_pmd, address); - if (!dst_pte) - goto nomem; - spin_lock(&src->page_table_lock); - src_pte = pte_offset_map_nested(src_pmd, address); - do { - pte_t pte = *src_pte; - struct page *page; - unsigned long pfn; - - if (!vx_rsspages_avail(dst, 1)) { - spin_unlock(&src->page_table_lock); - goto nomem; - } - /* copy_one_pte */ - - if (pte_none(pte)) - goto cont_copy_pte_range_noset; - /* pte contains position in swap, so copy. */ - if (!pte_present(pte)) { - if (!pte_file(pte)) - swap_duplicate(pte_to_swp_entry(pte)); - set_pte(dst_pte, pte); - goto cont_copy_pte_range_noset; - } - pfn = pte_pfn(pte); - /* the pte points outside of valid memory, the - * mapping is assumed to be good, meaningful - * and not mapped via rmap - duplicate the - * mapping as is. - */ - page = NULL; - if (pfn_valid(pfn)) - page = pfn_to_page(pfn); +out_set_pte: + set_pte_at(dst_mm, addr, dst_pte, pte); +} - if (!page || PageReserved(page)) { - set_pte(dst_pte, pte); - goto cont_copy_pte_range_noset; - } +static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + pte_t *src_pte, *dst_pte; + spinlock_t *src_ptl, *dst_ptl; + int progress = 0; + int rss[2]; + + if (!vx_rss_avail(dst_mm, ((end - addr)/PAGE_SIZE + 1))) + return -ENOMEM; + +again: + rss[1] = rss[0] = 0; + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); + if (!dst_pte) + return -ENOMEM; + src_pte = pte_offset_map_nested(src_pmd, addr); + src_ptl = pte_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + arch_enter_lazy_mmu_mode(); - /* - * If it's a COW mapping, write protect it both - * in the parent and the child - */ - if (cow) { - ptep_set_wrprotect(src_pte); - pte = *src_pte; - } + do { + /* + * We are holding two locks at this point - either of them + * could generate latencies in another task on another CPU. + */ + if (progress >= 32) { + progress = 0; + if (need_resched() || + need_lockbreak(src_ptl) || + need_lockbreak(dst_ptl)) + break; + } + if (pte_none(*src_pte)) { + progress++; + continue; + } + copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss); + progress += 8; + } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + + arch_leave_lazy_mmu_mode(); + spin_unlock(src_ptl); + pte_unmap_nested(src_pte - 1); + add_mm_rss(dst_mm, rss[0], rss[1]); + pte_unmap_unlock(dst_pte - 1, dst_ptl); + cond_resched(); + if (addr != end) + goto again; + return 0; +} - /* - * If it's a shared mapping, mark it clean in - * the child - */ - if (vma->vm_flags & VM_SHARED) - pte = pte_mkclean(pte); - pte = pte_mkold(pte); - get_page(page); - // dst->rss++; - vx_rsspages_inc(dst); - set_pte(dst_pte, pte); - page_dup_rmap(page); -cont_copy_pte_range_noset: - address += PAGE_SIZE; - if (address >= end) { - pte_unmap_nested(src_pte); - pte_unmap(dst_pte); - goto out_unlock; - } - src_pte++; - dst_pte++; - } while ((unsigned long)src_pte & PTE_TABLE_MASK); - pte_unmap_nested(src_pte-1); - pte_unmap(dst_pte-1); - spin_unlock(&src->page_table_lock); - cond_resched_lock(&dst->page_table_lock); -cont_copy_pmd_range: - src_pmd++; - dst_pmd++; - } while ((unsigned long)src_pmd & PMD_TABLE_MASK); - } -out_unlock: - spin_unlock(&src->page_table_lock); -out: +static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + pmd_t *src_pmd, *dst_pmd; + unsigned long next; + + dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); + if (!dst_pmd) + return -ENOMEM; + src_pmd = pmd_offset(src_pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(src_pmd)) + continue; + if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, + vma, addr, next)) + return -ENOMEM; + } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; -nomem: - return -ENOMEM; } -static void zap_pte_range(struct mmu_gather *tlb, - pmd_t *pmd, unsigned long address, - unsigned long size, struct zap_details *details) +static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) { - unsigned long offset; - pte_t *ptep; + pud_t *src_pud, *dst_pud; + unsigned long next; - if (pmd_none(*pmd)) - return; - if (unlikely(pmd_bad(*pmd))) { - pmd_ERROR(*pmd); - pmd_clear(pmd); - return; + dst_pud = pud_alloc(dst_mm, dst_pgd, addr); + if (!dst_pud) + return -ENOMEM; + src_pud = pud_offset(src_pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(src_pud)) + continue; + if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, + vma, addr, next)) + return -ENOMEM; + } while (dst_pud++, src_pud++, addr = next, addr != end); + return 0; +} + +int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + struct vm_area_struct *vma) +{ + pgd_t *src_pgd, *dst_pgd; + unsigned long next; + unsigned long addr = vma->vm_start; + unsigned long end = vma->vm_end; + + /* + * Don't copy ptes where a page fault will fill them correctly. + * Fork becomes much lighter when there are big shared or private + * readonly mappings. The tradeoff is that copy_page_range is more + * efficient than faulting. + */ + if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) { + if (!vma->anon_vma) + return 0; } - ptep = pte_offset_map(pmd, address); - offset = address & ~PMD_MASK; - if (offset + size > PMD_SIZE) - size = PMD_SIZE - offset; - size &= PAGE_MASK; - if (details && !details->check_mapping && !details->nonlinear_vma) - details = NULL; - for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) { - pte_t pte = *ptep; - if (pte_none(pte)) + + if (is_vm_hugetlb_page(vma)) + return copy_hugetlb_page_range(dst_mm, src_mm, vma); + + 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 (pte_present(pte)) { - struct page *page = NULL; - unsigned long pfn = pte_pfn(pte); - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (PageReserved(page)) - page = NULL; - } + if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + vma, addr, next)) + return -ENOMEM; + } while (dst_pgd++, src_pgd++, addr = next, addr != end); + return 0; +} + +static unsigned long zap_pte_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, + 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_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); + do { + pte_t ptent = *pte; + if (pte_none(ptent)) { + (*zap_work)--; + continue; + } + + (*zap_work) -= PAGE_SIZE; + + if (pte_present(ptent)) { + struct page *page; + + page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to @@ -411,20 +666,26 @@ static void zap_pte_range(struct mmu_gather *tlb, page->index > details->last_index)) continue; } - pte = ptep_get_and_clear(ptep); - tlb_remove_tlb_entry(tlb, ptep, address+offset); + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; if (unlikely(details) && details->nonlinear_vma && linear_page_index(details->nonlinear_vma, - address+offset) != page->index) - set_pte(ptep, pgoff_to_pte(page->index)); - if (pte_dirty(pte)) - set_page_dirty(page); - if (pte_young(pte) && !PageAnon(page)) - mark_page_accessed(page); - tlb->freed++; - page_remove_rmap(page); + addr) != page->index) + set_pte_at(mm, addr, pte, + pgoff_to_pte(page->index)); + if (PageAnon(page)) + anon_rss--; + else { + if (pte_dirty(ptent)) + set_page_dirty(page); + if (pte_young(ptent)) + mark_page_accessed(page); + file_rss--; + } + page_remove_rmap(page, vma); tlb_remove_page(tlb, page); continue; } @@ -434,86 +695,112 @@ static void zap_pte_range(struct mmu_gather *tlb, */ if (unlikely(details)) continue; - if (!pte_file(pte)) - free_swap_and_cache(pte_to_swp_entry(pte)); - pte_clear(ptep); - } - pte_unmap(ptep-1); + if (!pte_file(ptent)) + free_swap_and_cache(pte_to_swp_entry(ptent)); + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); + + add_mm_rss(mm, file_rss, anon_rss); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(pte - 1, ptl); + + return addr; } -static void zap_pmd_range(struct mmu_gather *tlb, - pgd_t * dir, unsigned long address, - unsigned long size, struct zap_details *details) +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, + long *zap_work, struct zap_details *details) { - pmd_t * pmd; - unsigned long end; + pmd_t *pmd; + unsigned long next; - if (pgd_none(*dir)) - return; - if (unlikely(pgd_bad(*dir))) { - pgd_ERROR(*dir); - pgd_clear(dir); - return; - } - pmd = pmd_offset(dir, address); - end = address + size; - if (end > ((address + PGDIR_SIZE) & PGDIR_MASK)) - end = ((address + PGDIR_SIZE) & PGDIR_MASK); + pmd = pmd_offset(pud, addr); do { - zap_pte_range(tlb, pmd, address, end - address, details); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address && (address < end)); + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(pmd)) { + (*zap_work)--; + continue; + } + next = zap_pte_range(tlb, vma, pmd, addr, next, + zap_work, details); + } while (pmd++, addr = next, (addr != end && *zap_work > 0)); + + return addr; } -static void unmap_page_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, unsigned long address, - unsigned long end, struct zap_details *details) +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, + long *zap_work, struct zap_details *details) { - pgd_t * dir; + pud_t *pud; + unsigned long next; - BUG_ON(address >= end); - dir = pgd_offset(vma->vm_mm, address); - tlb_start_vma(tlb, vma); + pud = pud_offset(pgd, addr); do { - zap_pmd_range(tlb, dir, address, end - address, details); - address = (address + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } while (address && (address < end)); - tlb_end_vma(tlb, vma); + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) { + (*zap_work)--; + continue; + } + next = zap_pmd_range(tlb, vma, pud, addr, next, + zap_work, details); + } while (pud++, addr = next, (addr != end && *zap_work > 0)); + + return addr; } -/* Dispose of an entire struct mmu_gather per rescheduling point */ -#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT) -#define ZAP_BLOCK_SIZE (FREE_PTE_NR * PAGE_SIZE) -#endif +static unsigned long unmap_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + long *zap_work, struct zap_details *details) +{ + pgd_t *pgd; + unsigned long next; -/* For UP, 256 pages at a time gives nice low latency */ -#if !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT) -#define ZAP_BLOCK_SIZE (256 * PAGE_SIZE) -#endif + if (details && !details->check_mapping && !details->nonlinear_vma) + details = NULL; + BUG_ON(addr >= end); + tlb_start_vma(tlb, vma); + pgd = pgd_offset(vma->vm_mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) { + (*zap_work)--; + continue; + } + 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 +# define ZAP_BLOCK_SIZE (8 * PAGE_SIZE) +#else /* No preempt: go for improved straight-line efficiency */ -#if !defined(CONFIG_PREEMPT) -#define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE) +# define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE) #endif /** * 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 * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here * @details: details of nonlinear truncation or shared cache invalidation * - * Returns the number of vma's which were covered by the unmapping. + * 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. @@ -525,19 +812,19 @@ static void unmap_page_range(struct mmu_gather *tlb, * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ -int 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; - int ret = 0; - int atomic = details && details->atomic; + unsigned long start = start_addr; + spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; + int fullmm = (*tlbp)->fullmm; for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { - unsigned long start; unsigned long end; start = max(vma->vm_start, start_addr); @@ -550,39 +837,44 @@ int unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm, if (vma->vm_flags & VM_ACCOUNT) *nr_accounted += (end - start) >> PAGE_SHIFT; - ret++; 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; - if (!atomic && need_resched()) { - int fullmm = tlb_is_full_mm(*tlbp); - tlb_finish_mmu(*tlbp, tlb_start, start); - cond_resched_lock(&mm->page_table_lock); - *tlbp = tlb_gather_mmu(mm, fullmm); - tlb_start_valid = 0; + tlb_finish_mmu(*tlbp, tlb_start, start); + + if (need_resched() || + (i_mmap_lock && need_lockbreak(i_mmap_lock))) { + if (i_mmap_lock) { + *tlbp = NULL; + goto out; + } + cond_resched(); } - zap_bytes = ZAP_BLOCK_SIZE; + + *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm); + tlb_start_valid = 0; + zap_work = ZAP_BLOCK_SIZE; } } - return ret; +out: + return start; /* which is now the end (or restart) address */ } /** @@ -592,7 +884,7 @@ int unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm, * @size: number of bytes to zap * @details: details of nonlinear truncation or shared cache invalidation */ -void zap_page_range(struct vm_area_struct *vma, unsigned long address, +unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mm_struct *mm = vma->vm_mm; @@ -600,154 +892,144 @@ void 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; - } - lru_add_drain(); - spin_lock(&mm->page_table_lock); tlb = tlb_gather_mmu(mm, 0); - unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details); - tlb_finish_mmu(tlb, address, end); - spin_unlock(&mm->page_table_lock); + update_hiwater_rss(mm); + end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); + if (tlb) + tlb_finish_mmu(tlb, address, end); + return end; } +EXPORT_SYMBOL(zap_page_range); /* * Do a quick page-table lookup for a single page. - * mm->page_table_lock must be held. */ -struct page * -follow_page(struct mm_struct *mm, unsigned long address, int write) +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; - pmd = pmd_offset(pgd, address); - if (pmd_none(*pmd)) - goto out; - if (pmd_huge(*pmd)) - return follow_huge_pmd(mm, address, pmd, write); - if (unlikely(pmd_bad(*pmd))) + pud = pud_offset(pgd, address); + if (pud_none(*pud) || unlikely(pud_bad(*pud))) + 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; + } - 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; - pfn = pte_pfn(pte); - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - 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; -} - -/* - * Given a physical address, is there a useful struct page pointing to - * it? This may become more complex in the future if we start dealing - * with IO-aperture pages for direct-IO. - */ - -static inline struct page *get_page_map(struct page *page) -{ - if (!pfn_valid(page_to_pfn(page))) - return NULL; return page; -} - -static inline int -untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma, - unsigned long address) -{ - pgd_t *pgd; - 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; - - /* Check if page middle directory entry exists. */ - pmd = pmd_offset(pgd, address); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - return 1; - - /* 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, unsigned long start, int len, int write, int force, 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)) { unsigned long pg = start & PAGE_MASK; struct vm_area_struct *gate_vma = get_gate_vma(tsk); pgd_t *pgd; + pud_t *pud; pmd_t *pmd; pte_t *pte; if (write) /* user gate pages are read-only */ return i ? : -EFAULT; - pgd = pgd_offset_gate(mm, pg); - if (!pgd) - return i ? : -EFAULT; - pmd = pmd_offset(pgd, pg); - if (!pmd) + if (pg > TASK_SIZE) + pgd = pgd_offset_k(pg); + else + pgd = pgd_offset_gate(mm, pg); + BUG_ON(pgd_none(*pgd)); + pud = pud_offset(pgd, pg); + BUG_ON(pud_none(*pud)); + pmd = pmd_offset(pud, pg); + if (pmd_none(*pmd)) return i ? : -EFAULT; pte = pte_offset_map(pmd, pg); - if (!pte) - return i ? : -EFAULT; - if (!pte_present(*pte)) { + if (pte_none(*pte)) { pte_unmap(pte); 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) @@ -758,8 +1040,28 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } - if (!vma || (pages && (vma->vm_flags & VM_IO)) - || !(flags & vma->vm_flags)) +#ifdef CONFIG_XEN + if (vma && (vma->vm_flags & VM_FOREIGN)) { + struct page **map = vma->vm_private_data; + int offset = (start - vma->vm_start) >> PAGE_SHIFT; + if (map[offset] != NULL) { + if (pages) { + struct page *page = map[offset]; + + pages[i] = page; + get_page(page); + } + if (vmas) + vmas[i] = vma; + i++; + start += PAGE_SIZE; + len--; + continue; + } + } +#endif + if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP)) + || !(vm_flags & vma->vm_flags)) return i ? : -EFAULT; if (is_vm_hugetlb_page(vma)) { @@ -767,25 +1069,35 @@ 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 { - struct page *map; - int lookup_write = write; - while (!(map = follow_page(mm, start, lookup_write))) { + struct page *page; + + 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); /* - * Shortcut for anonymous pages. We don't want - * to force the creation of pages tables for - * insanly big anonymously mapped areas that - * nobody touched so far. This is important - * for doing a core dump for these mappings. + * The VM_FAULT_WRITE bit tells us that 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. */ - if (!lookup_write && - untouched_anonymous_page(mm,vma,start)) { - map = ZERO_PAGE(start); - break; - } - spin_unlock(&mm->page_table_lock); - switch (handle_mm_fault(mm,vma,start,write)) { + if (ret & VM_FAULT_WRITE) + foll_flags &= ~FOLL_WRITE; + + switch (ret & ~VM_FAULT_WRITE) { case VM_FAULT_MINOR: tsk->min_flt++; break; @@ -799,201 +1111,443 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, default: BUG(); } - /* - * Now that we have performed a write fault - * and surely no longer have a shared page we - * shouldn't write, we shouldn't ignore an - * unwritable page in the page table if - * we are forcing write access. - */ - lookup_write = write && !force; - spin_lock(&mm->page_table_lock); + cond_resched(); } if (pages) { - pages[i] = get_page_map(map); - if (!pages[i]) { - spin_unlock(&mm->page_table_lock); - while (i--) - page_cache_release(pages[i]); - i = -EFAULT; - goto out; - } - flush_dcache_page(pages[i]); - if (!PageReserved(pages[i])) - page_cache_get(pages[i]); + pages[i] = page; + + flush_anon_page(vma, page, start); + flush_dcache_page(page); } if (vmas) vmas[i] = vma; i++; start += PAGE_SIZE; len--; - } while(len && start < vma->vm_end); - spin_unlock(&mm->page_table_lock); - } while(len); -out: + } while (len && start < vma->vm_end); + } while (len); return i; } - EXPORT_SYMBOL(get_user_pages); -static void zeromap_pte_range(pte_t * pte, unsigned long address, - unsigned long size, pgprot_t prot) +static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, pgprot_t prot) { - unsigned long end; + pte_t *pte; + spinlock_t *ptl; + int err = 0; + + pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -EAGAIN; + arch_enter_lazy_mmu_mode(); + do { + struct page *page = ZERO_PAGE(addr); + pte_t zero_pte = pte_wrprotect(mk_pte(page, prot)); - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; + if (unlikely(!pte_none(*pte))) { + err = -EEXIST; + pte++; + break; + } + page_cache_get(page); + page_add_file_rmap(page); + inc_mm_counter(mm, file_rss); + set_pte_at(mm, addr, pte, zero_pte); + } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(pte - 1, ptl); + return err; +} + +static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, pgprot_t prot) +{ + pmd_t *pmd; + unsigned long next; + int err; + + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -EAGAIN; do { - pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address), prot)); - BUG_ON(!pte_none(*pte)); - set_pte(pte, zero_pte); - address += PAGE_SIZE; - pte++; - } while (address && (address < end)); + next = pmd_addr_end(addr, end); + err = zeromap_pte_range(mm, pmd, addr, next, prot); + if (err) + break; + } while (pmd++, addr = next, addr != end); + return err; } -static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, - unsigned long size, pgprot_t prot) +static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, pgprot_t prot) { - unsigned long base, end; + pud_t *pud; + unsigned long next; + int err; - base = address & PGDIR_MASK; - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return -EAGAIN; do { - pte_t * pte = pte_alloc_map(mm, pmd, base + address); - if (!pte) - return -ENOMEM; - zeromap_pte_range(pte, base + address, end - address, prot); - pte_unmap(pte); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address && (address < end)); - return 0; + next = pud_addr_end(addr, end); + err = zeromap_pmd_range(mm, pud, addr, next, prot); + if (err) + break; + } while (pud++, addr = next, addr != end); + return err; } -int zeromap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, pgprot_t prot) +int zeromap_page_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long size, pgprot_t prot) { - int error = 0; - pgd_t * dir; - unsigned long beg = address; - unsigned long end = address + size; + pgd_t *pgd; + unsigned long next; + unsigned long end = addr + size; struct mm_struct *mm = vma->vm_mm; + int err; - dir = pgd_offset(mm, address); - flush_cache_range(vma, beg, end); - if (address >= end) - BUG(); - - spin_lock(&mm->page_table_lock); + BUG_ON(addr >= end); + pgd = pgd_offset(mm, addr); + flush_cache_range(vma, addr, end); do { - pmd_t *pmd = pmd_alloc(mm, dir, address); - error = -ENOMEM; - if (!pmd) + next = pgd_addr_end(addr, end); + err = zeromap_pud_range(mm, pgd, addr, next, prot); + if (err) break; - error = zeromap_pmd_range(mm, pmd, address, end - address, prot); - if (error) - break; - address = (address + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } while (address && (address < end)); - /* - * Why flush? zeromap_pte_range has a BUG_ON for !pte_none() - */ - flush_tlb_range(vma, beg, end); - spin_unlock(&mm->page_table_lock); - return error; + } while (pgd++, addr = next, addr != end); + 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; +} + +/** + * vm_insert_page - insert single page into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @page: source kernel page + * + * 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 * in null mappings (currently treated as "copy-on-access") */ -static inline void remap_pte_range(pte_t * pte, unsigned long address, unsigned long size, - unsigned long phys_addr, pgprot_t prot) +static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) { - unsigned long end; - unsigned long pfn; + pte_t *pte; + spinlock_t *ptl; - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - pfn = phys_addr >> PAGE_SHIFT; + pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); - if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn))) - set_pte(pte, pfn_pte(pfn, prot)); - address += PAGE_SIZE; + set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); pfn++; - pte++; - } while (address && (address < end)); + } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(pte - 1, ptl); + return 0; } -static inline int remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long phys_addr, pgprot_t prot) +static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) { - unsigned long base, end; + pmd_t *pmd; + unsigned long next; - base = address & PGDIR_MASK; - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - phys_addr -= address; + pfn -= addr >> PAGE_SHIFT; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -ENOMEM; do { - pte_t * pte = pte_alloc_map(mm, pmd, base + address); - if (!pte) + next = pmd_addr_end(addr, end); + if (remap_pte_range(mm, pmd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) return -ENOMEM; - remap_pte_range(pte, base + address, end - address, address + phys_addr, prot); - pte_unmap(pte); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address && (address < end)); + } while (pmd++, addr = next, addr != end); return 0; } -/* Note: this is only safe if the mm semaphore is held when called. */ -int remap_page_range(struct vm_area_struct *vma, unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot) +static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) { - int error = 0; - pgd_t * dir; - unsigned long beg = from; - unsigned long end = from + size; + pud_t *pud; + unsigned long next; + + pfn -= addr >> PAGE_SHIFT; + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + if (remap_pmd_range(mm, pud, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) + return -ENOMEM; + } while (pud++, addr = next, addr != end); + return 0; +} + +/** + * remap_pfn_range - remap kernel memory to userspace + * @vma: user vma to map to + * @addr: target user address to start at + * @pfn: physical address of kernel memory + * @size: size of map area + * @prot: page protection flags for this mapping + * + * Note: this is only safe if the mm semaphore is held when called. + */ +int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + pgd_t *pgd; + unsigned long next; + unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; + int err; - phys_addr -= from; - dir = pgd_offset(mm, from); - flush_cache_range(vma, beg, end); - if (from >= end) - BUG(); + /* + * Physically remapped pages are special. Tell the + * rest of the world about it: + * VM_IO tells people not to look at these pages + * (accesses can have side effects). + * 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". + */ + if (is_cow_mapping(vma->vm_flags)) { + if (addr != vma->vm_start || end != vma->vm_end) + return -EINVAL; + vma->vm_pgoff = pfn; + } - spin_lock(&mm->page_table_lock); + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + + BUG_ON(addr >= end); + pfn -= addr >> PAGE_SHIFT; + pgd = pgd_offset(mm, addr); + flush_cache_range(vma, addr, end); do { - pmd_t *pmd = pmd_alloc(mm, dir, from); - error = -ENOMEM; - if (!pmd) + next = pgd_addr_end(addr, end); + err = remap_pud_range(mm, pgd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) break; - error = remap_pmd_range(mm, pmd, from, end - from, phys_addr + from, prot); - if (error) + } while (pgd++, addr = next, addr != end); + return err; +} +EXPORT_SYMBOL(remap_pfn_range); + +#ifdef CONFIG_XEN +static inline int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + pte_t *pte; + int err; + struct page *pmd_page; + spinlock_t *ptl; + + pte = (mm == &init_mm) ? + pte_alloc_kernel(pmd, addr) : + pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + + BUG_ON(pmd_huge(*pmd)); + + pmd_page = pmd_page(*pmd); + + do { + err = fn(pte, pmd_page, addr, data); + if (err) break; - from = (from + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } while (from && (from < end)); - /* - * Why flush? remap_pte_range has a BUG_ON for !pte_none() - */ - flush_tlb_range(vma, beg, end); - spin_unlock(&mm->page_table_lock); - return error; + } while (pte++, addr += PAGE_SIZE, addr != end); + + if (mm != &init_mm) + pte_unmap_unlock(pte-1, ptl); + return err; } -EXPORT_SYMBOL(remap_page_range); +static inline int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + pmd_t *pmd; + unsigned long next; + int err; + + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -ENOMEM; + do { + next = pmd_addr_end(addr, end); + err = apply_to_pte_range(mm, pmd, addr, next, fn, data); + if (err) + break; + } while (pmd++, addr = next, addr != end); + return err; +} + +static inline int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + pud_t *pud; + unsigned long next; + int err; + + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + err = apply_to_pmd_range(mm, pud, addr, next, fn, data); + if (err) + break; + } while (pud++, addr = next, addr != end); + return err; +} + +/* + * Scan a region of virtual memory, filling in page tables as necessary + * and calling a provided function on each leaf page table. + */ +int apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + pgd_t *pgd; + unsigned long next; + unsigned long end = addr + size; + int err; + + BUG_ON(addr >= end); + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + err = apply_to_pud_range(mm, pgd, addr, next, fn, data); + if (err) + break; + } while (pgd++, addr = next, addr != end); + return err; +} +EXPORT_SYMBOL_GPL(apply_to_page_range); +#endif + +/* + * 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 @@ -1008,19 +1562,32 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -/* - * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock - */ -static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address, - pte_t *page_table) +static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) { - pte_t entry; + /* + * 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); - flush_cache_page(vma, address); - entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)), - vma); - ptep_establish(vma, address, page_table, entry); - update_mmu_cache(vma, address, entry); + /* + * 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); + flush_dcache_page(dst); + return; + + } + copy_user_highpage(dst, src, va, vma); } /* @@ -1028,9 +1595,6 @@ static inline void break_cow(struct vm_area_struct * vma, struct page * new_page * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * - * Goto-purists beware: the only reason for goto's here is that it results - * in better assembly code.. The "default" path will see no jumps at all. - * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary @@ -1040,101 +1604,257 @@ static inline void break_cow(struct vm_area_struct * vma, struct page * new_page * 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 pte) +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, *new_page; - unsigned long pfn = pte_pfn(pte); pte_t entry; + int reuse = 0, ret = VM_FAULT_MINOR; + struct page *dirty_page = NULL; - if (unlikely(!pfn_valid(pfn))) { + old_page = vm_normal_page(vma, address, orig_pte); + if (!old_page) + 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); + } + } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED))) { /* - * This should really halt the system so it can be debugged or - * at least the kernel stops what it's doing before it corrupts - * data, but for the moment just pretend this is OOM. + * Only catch write-faults on shared writable pages, + * read-only shared pages can get COWed by + * get_user_pages(.write=1, .force=1). */ - pte_unmap(page_table); - printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n", - address); - spin_unlock(&mm->page_table_lock); - return VM_FAULT_OOM; - } - old_page = pfn_to_page(pfn); - - if (!TestSetPageLocked(old_page)) { - int reuse = can_share_swap_page(old_page); - unlock_page(old_page); - if (reuse) { - flush_cache_page(vma, address); - entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)), - vma); - ptep_set_access_flags(vma, address, page_table, entry, 1); - update_mmu_cache(vma, address, entry); - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); - return VM_FAULT_MINOR; + 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 (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; } + dirty_page = old_page; + get_page(dirty_page); + reuse = 1; + } + + 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; } - pte_unmap(page_table); /* * Ok, we need to copy. Oh, well.. */ - if (!PageReserved(old_page)) - page_cache_get(old_page); - spin_unlock(&mm->page_table_lock); + page_cache_get(old_page); +gotten: + pte_unmap_unlock(page_table, ptl); if (unlikely(anon_vma_prepare(vma))) - goto no_new_page; - new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); - if (!new_page) - goto no_new_page; - copy_cow_page(old_page,new_page,address); + goto oom; + if (old_page == ZERO_PAGE(address)) { + new_page = alloc_zeroed_user_highpage(vma, address); + if (!new_page) + goto oom; + } else { + new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); + if (!new_page) + goto oom; + cow_user_page(new_page, old_page, address, vma); + } /* * Re-check the pte - we dropped the lock */ - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); - if (likely(pte_same(*page_table, pte))) { - if (PageReserved(old_page)) - // ++mm->rss; - vx_rsspages_inc(mm); - else - page_remove_rmap(old_page); - break_cow(vma, new_page, address, page_table); + 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); + } + } else + inc_mm_counter(mm, anon_rss); + 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); + /* + * Clear the pte entry and flush it first, before updating the + * pte with the new entry. This will avoid a race condition + * seen in the presence of one thread doing SMC and another + * thread doing COW. + */ + ptep_clear_flush(vma, address, page_table); + set_pte_at(mm, address, page_table, entry); + update_mmu_cache(vma, address, entry); lru_cache_add_active(new_page); - page_add_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; + } + if (new_page) + page_cache_release(new_page); + if (old_page) + page_cache_release(old_page); +unlock: + pte_unmap_unlock(page_table, ptl); + if (dirty_page) { + set_page_dirty_balance(dirty_page); + put_page(dirty_page); + } + return ret; +oom: + if (old_page) + page_cache_release(old_page); + return VM_FAULT_OOM; + +unwritable_page: + page_cache_release(old_page); + return VM_FAULT_SIGBUS; +} + +/* + * Helper functions for unmap_mapping_range(). + * + * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __ + * + * We have to restart searching the prio_tree whenever we drop the lock, + * since the iterator is only valid while the lock is held, and anyway + * a later vma might be split and reinserted earlier while lock dropped. + * + * The list of nonlinear vmas could be handled more efficiently, using + * a placeholder, but handle it in the same way until a need is shown. + * It is important to search the prio_tree before nonlinear list: a vma + * may become nonlinear and be shifted from prio_tree to nonlinear list + * while the lock is dropped; but never shifted from list to prio_tree. + * + * In order to make forward progress despite restarting the search, + * vm_truncate_count is used to mark a vma as now dealt with, so we can + * quickly skip it next time around. Since the prio_tree search only + * shows us those vmas affected by unmapping the range in question, we + * can't efficiently keep all vmas in step with mapping->truncate_count: + * so instead reset them all whenever it wraps back to 0 (then go to 1). + * mapping->truncate_count and vma->vm_truncate_count are protected by + * i_mmap_lock. + * + * In order to make forward progress despite repeatedly restarting some + * large vma, note the restart_addr from unmap_vmas when it breaks out: + * and restart from that address when we reach that vma again. It might + * have been split or merged, shrunk or extended, but never shifted: so + * restart_addr remains valid so long as it remains in the vma's range. + * unmap_mapping_range forces truncate_count to leap over page-aligned + * values so we can save vma's restart_addr in its truncate_count field. + */ +#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK)) + +static void reset_vma_truncate_counts(struct address_space *mapping) +{ + struct vm_area_struct *vma; + struct prio_tree_iter iter; + + vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX) + vma->vm_truncate_count = 0; + list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) + vma->vm_truncate_count = 0; +} + +static int unmap_mapping_range_vma(struct vm_area_struct *vma, + unsigned long start_addr, unsigned long end_addr, + struct zap_details *details) +{ + unsigned long restart_addr; + int need_break; + +again: + restart_addr = vma->vm_truncate_count; + if (is_restart_addr(restart_addr) && start_addr < restart_addr) { + start_addr = restart_addr; + if (start_addr >= end_addr) { + /* Top of vma has been split off since last time */ + vma->vm_truncate_count = details->truncate_count; + return 0; + } + } - /* Free the old page.. */ - new_page = old_page; + restart_addr = zap_page_range(vma, start_addr, + end_addr - start_addr, details); + need_break = need_resched() || + need_lockbreak(details->i_mmap_lock); + + if (restart_addr >= end_addr) { + /* We have now completed this vma: mark it so */ + vma->vm_truncate_count = details->truncate_count; + if (!need_break) + return 0; + } else { + /* Note restart_addr in vma's truncate_count field */ + vma->vm_truncate_count = restart_addr; + if (!need_break) + goto again; } - pte_unmap(page_table); - page_cache_release(new_page); - page_cache_release(old_page); - spin_unlock(&mm->page_table_lock); - return VM_FAULT_MINOR; -no_new_page: - page_cache_release(old_page); - return VM_FAULT_OOM; + spin_unlock(details->i_mmap_lock); + cond_resched(); + spin_lock(details->i_mmap_lock); + return -EINTR; } -/* - * Helper function for unmap_mapping_range(). - */ -static inline void unmap_mapping_range_list(struct prio_tree_root *root, +static inline void unmap_mapping_range_tree(struct prio_tree_root *root, struct zap_details *details) { - struct vm_area_struct *vma = NULL; + struct vm_area_struct *vma; struct prio_tree_iter iter; pgoff_t vba, vea, zba, zea; - while ((vma = vma_prio_tree_next(vma, root, &iter, - details->first_index, details->last_index)) != NULL) { +restart: + vma_prio_tree_foreach(vma, &iter, root, + details->first_index, details->last_index) { + /* Skip quickly over those we have already dealt with */ + if (vma->vm_truncate_count == details->truncate_count) + continue; + vba = vma->vm_pgoff; vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1; /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */ @@ -1144,9 +1864,35 @@ static inline void unmap_mapping_range_list(struct prio_tree_root *root, zea = details->last_index; if (zea > vea) zea = vea; - zap_page_range(vma, + + if (unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, - (zea - zba + 1) << PAGE_SHIFT, details); + ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, + details) < 0) + goto restart; + } +} + +static inline void unmap_mapping_range_list(struct list_head *head, + struct zap_details *details) +{ + struct vm_area_struct *vma; + + /* + * In nonlinear VMAs there is no correspondence between virtual address + * offset and file offset. So we must perform an exhaustive search + * across *all* the pages in each nonlinear VMA, not just the pages + * whose virtual address lies outside the file truncation point. + */ +restart: + list_for_each_entry(vma, head, shared.vm_set.list) { + /* Skip quickly over those we have already dealt with */ + if (vma->vm_truncate_count == details->truncate_count) + continue; + details->nonlinear_vma = vma; + if (unmap_mapping_range_vma(vma, vma->vm_start, + vma->vm_end, details) < 0) + goto restart; } } @@ -1154,7 +1900,7 @@ static inline void unmap_mapping_range_list(struct prio_tree_root *root, * unmap_mapping_range - unmap the portion of all mmaps * in the specified address_space corresponding to the specified * page range in the underlying file. - * @address_space: the address space containing mmaps to be unmapped. + * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from vmtruncate(), which @@ -1185,39 +1931,42 @@ void unmap_mapping_range(struct address_space *mapping, details.nonlinear_vma = NULL; details.first_index = hba; details.last_index = hba + hlen - 1; - details.atomic = 1; /* A spinlock is held */ if (details.last_index < details.first_index) details.last_index = ULONG_MAX; + details.i_mmap_lock = &mapping->i_mmap_lock; spin_lock(&mapping->i_mmap_lock); - /* Protect against page fault */ - atomic_inc(&mapping->truncate_count); - - if (unlikely(!prio_tree_empty(&mapping->i_mmap))) - unmap_mapping_range_list(&mapping->i_mmap, &details); + /* serialize i_size write against truncate_count write */ + smp_wmb(); + /* Protect against page faults, and endless unmapping loops */ + mapping->truncate_count++; /* - * In nonlinear VMAs there is no correspondence between virtual address - * offset and file offset. So we must perform an exhaustive search - * across *all* the pages in each nonlinear VMA, not just the pages - * whose virtual address lies outside the file truncation point. + * For archs where spin_lock has inclusive semantics like ia64 + * this smp_mb() will prevent to read pagetable contents + * before the truncate_count increment is visible to + * other cpus. */ - if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) { - struct vm_area_struct *vma; - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.vm_set.list) { - details.nonlinear_vma = vma; - zap_page_range(vma, vma->vm_start, - vma->vm_end - vma->vm_start, &details); - } + smp_mb(); + if (unlikely(is_restart_addr(mapping->truncate_count))) { + if (mapping->truncate_count == 0) + reset_vma_truncate_counts(mapping); + mapping->truncate_count++; } + details.truncate_count = mapping->truncate_count; + + if (unlikely(!prio_tree_empty(&mapping->i_mmap))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) + unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); spin_unlock(&mapping->i_mmap_lock); } EXPORT_SYMBOL(unmap_mapping_range); -/* - * Handle all mappings that got truncated by a "truncate()" - * system call. +/** + * vmtruncate - unmap mappings "freed" by truncate() syscall + * @inode: inode of the file used + * @offset: file offset to start truncating * * NOTE! We have to be ready to update the memory sharing * between the file and the memory map for a potential last @@ -1242,7 +1991,7 @@ int vmtruncate(struct inode * inode, loff_t offset) goto out_truncate; do_expand: - limit = current->rlim[RLIMIT_FSIZE].rlim_cur; + limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; if (limit != RLIM_INFINITY && offset > limit) goto out_sig; if (offset > inode->i_sb->s_maxbytes) @@ -1260,14 +2009,41 @@ 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; +} + +/** + * swapin_readahead - swap in pages in hope we need them soon + * @entry: swap entry of this memory + * @addr: address to start + * @vma: user vma this addresses belong to + * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen * because it doesn't cost us any seek time. We also make sure to queue - * the 'original' request together with the readahead ones... + * the 'original' request together with the readahead ones... * * This has been extended to use the NUMA policies from the mm triggering * the readahead. @@ -1320,161 +2096,171 @@ 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, pte_t orig_pte, int write_access) +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_to_swp_entry(orig_pte); + 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) { + grab_swap_token(); /* Contend for token _before_ read-in */ 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; - else - ret = VM_FAULT_MINOR; - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); - goto out; + 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); } - if (!vx_rsspages_avail(mm, 1)) { + if (!vx_rss_avail(mm, 1)) { ret = VM_FAULT_OOM; goto out; } + + 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); - if (unlikely(!pte_same(*page_table, orig_pte))) { - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); - unlock_page(page); - page_cache_release(page); - ret = VM_FAULT_MINOR; - goto out; + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*page_table, orig_pte))) + goto out_nomap; + + if (unlikely(!PageUptodate(page))) { + ret = VM_FAULT_SIGBUS; + goto out_nomap; } /* The page isn't present yet, go ahead with the fault. */ - - swap_free(entry); - if (vm_swap_full()) - remove_exclusive_swap_page(page); - // mm->rss++; - vx_rsspages_inc(mm); + inc_mm_counter(mm, anon_rss); pte = mk_pte(page, vma->vm_page_prot); if (write_access && can_share_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); write_access = 0; } - unlock_page(page); flush_icache_page(vma, page); - set_pte(page_table, pte); + set_pte_at(mm, address, page_table, pte); page_add_anon_rmap(page, vma, address); + swap_free(entry); + if (vm_swap_full()) + remove_exclusive_swap_page(page); + unlock_page(page); + 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; } /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, address, pte); - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + lazy_mmu_prot_update(pte); +unlock: + pte_unmap_unlock(page_table, ptl); out: return ret; +out_nomap: + 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, - pte_t *page_table, pmd_t *pmd, int write_access, - unsigned long addr) +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; + spinlock_t *ptl; pte_t entry; - struct page * page = ZERO_PAGE(addr); - /* Read-only mapping of ZERO_PAGE. */ - entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot)); - - /* ..except if it's a write access */ if (write_access) { /* Allocate our own private page. */ pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + if (!vx_rss_avail(mm, 1)) + goto oom; if (unlikely(anon_vma_prepare(vma))) - goto no_mem; - if (!vx_rsspages_avail(mm, 1)) - goto no_mem; - - page = alloc_page_vma(GFP_HIGHUSER, vma, addr); + goto oom; + page = alloc_zeroed_user_highpage(vma, address); if (!page) - goto no_mem; - clear_user_highpage(page, addr); + goto oom; - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, addr); + entry = mk_pte(page, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (!pte_none(*page_table)) { - pte_unmap(page_table); - page_cache_release(page); - spin_unlock(&mm->page_table_lock); - goto out; - } - // mm->rss++; - vx_rsspages_inc(mm); - entry = maybe_mkwrite(pte_mkdirty(mk_pte(page, - vma->vm_page_prot)), - 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); - mark_page_accessed(page); - page_add_anon_rmap(page, vma, addr); + 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); } - set_pte(page_table, entry); - pte_unmap(page_table); + set_pte_at(mm, address, page_table, entry); /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, addr, entry); - spin_unlock(&mm->page_table_lock); -out: + update_mmu_cache(vma, address, entry); + lazy_mmu_prot_update(entry); +unlock: + pte_unmap_unlock(page_table, ptl); return VM_FAULT_MINOR; -no_mem: +release: + page_cache_release(page); + goto unlock; +oom: return VM_FAULT_OOM; } @@ -1487,73 +2273,96 @@ no_mem: * 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, int write_access, pte_t *page_table, pmd_t *pmd) +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) { - struct page * new_page; + spinlock_t *ptl; + struct page *new_page; struct address_space *mapping = NULL; pte_t entry; - int sequence = 0; + unsigned int sequence = 0; int ret = VM_FAULT_MINOR; int anon = 0; + struct page *dirty_page = NULL; - if (!vma->vm_ops || !vma->vm_ops->nopage) - return do_anonymous_page(mm, vma, page_table, - pmd, write_access, address); pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + BUG_ON(vma->vm_flags & VM_PFNMAP); + + if (!vx_rss_avail(mm, 1)) + return VM_FAULT_OOM; if (vma->vm_file) { mapping = vma->vm_file->f_mapping; - sequence = atomic_read(&mapping->truncate_count); + sequence = mapping->truncate_count; + smp_rmb(); /* serializes i_size against truncate_count */ } - smp_rmb(); /* Prevent CPU from reordering lock-free ->nopage() */ retry: new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret); + /* + * No smp_rmb is needed here as long as there's a full + * spin_lock/unlock sequence inside the ->nopage callback + * (for the pagecache lookup) that acts as an implicit + * smp_mb() and prevents the i_size read to happen + * after the next truncate_count read. + */ - /* no page was available -- either SIGBUS or OOM */ - if (new_page == NOPAGE_SIGBUS) + /* no page was available -- either SIGBUS, OOM or REFAULT */ + if (unlikely(new_page == NOPAGE_SIGBUS)) return VM_FAULT_SIGBUS; - if (new_page == NOPAGE_OOM) - return VM_FAULT_OOM; - if (!vx_rsspages_avail(mm, 1)) + else if (unlikely(new_page == NOPAGE_OOM)) return VM_FAULT_OOM; + else if (unlikely(new_page == NOPAGE_REFAULT)) + return VM_FAULT_MINOR; /* * 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, vma); + 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 != atomic_read(&mapping->truncate_count)))) { - sequence = atomic_read(&mapping->truncate_count); - spin_unlock(&mm->page_table_lock); + if (mapping && unlikely(sequence != mapping->truncate_count)) { + 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 @@ -1567,67 +2376,123 @@ retry: */ /* Only go through if we didn't race with anybody else... */ if (pte_none(*page_table)) { - if (!PageReserved(new_page)) - // ++mm->rss; - vx_rsspages_inc(mm); flush_icache_page(vma, new_page); entry = mk_pte(new_page, vma->vm_page_prot); if (write_access) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - set_pte(page_table, entry); + set_pte_at(mm, address, page_table, entry); if (anon) { + inc_mm_counter(mm, anon_rss); lru_cache_add_active(new_page); - page_add_anon_rmap(new_page, vma, address); - } else + page_add_new_anon_rmap(new_page, vma, address); + } else { + inc_mm_counter(mm, file_rss); page_add_file_rmap(new_page); - pte_unmap(page_table); + if (write_access) { + dirty_page = new_page; + get_page(dirty_page); + } + } } else { /* One of our sibling threads was faster, back out. */ - pte_unmap(page_table); page_cache_release(new_page); - spin_unlock(&mm->page_table_lock); - goto out; + goto unlock; } /* no need to invalidate: a not-present page shouldn't be cached */ update_mmu_cache(vma, address, entry); - spin_unlock(&mm->page_table_lock); -out: + lazy_mmu_prot_update(entry); +unlock: + pte_unmap_unlock(page_table, ptl); + if (dirty_page) { + set_page_dirty_balance(dirty_page); + put_page(dirty_page); + } return ret; oom: page_cache_release(new_page); - ret = VM_FAULT_OOM; - goto out; + return VM_FAULT_OOM; +} + +/* + * 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; + int ret = VM_FAULT_MINOR; + + 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 (pfn == NOPFN_OOM) + return VM_FAULT_OOM; + if (pfn == NOPFN_SIGBUS) + return VM_FAULT_SIGBUS; + + 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 ret; } /* * 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, int write_access, pte_t *pte, pmd_t *pmd) +static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access, pte_t orig_pte) { - unsigned long pgoff; + pgoff_t pgoff; int err; - BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage); - /* - * Fall back to the linear mapping if the fs does not support - * ->populate: - */ - if (!vma->vm_ops || !vma->vm_ops->populate || - (write_access && !(vma->vm_flags & VM_SHARED))) { - pte_clear(pte); - return do_no_page(mm, vma, address, write_access, pte, pmd); - } - - pgoff = pte_to_pgoff(*pte); + if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + return VM_FAULT_MINOR; - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { + /* + * Page table corrupted: show pte and kill process. + */ + print_bad_pte(vma, orig_pte, address); + return VM_FAULT_OOM; + } + /* We can then assume vm->vm_ops && vma->vm_ops->populate */ - err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, vma->vm_page_prot, pgoff, 0); + pgoff = pte_to_pgoff(orig_pte); + err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, + vma->vm_page_prot, pgoff, 0); if (err == -ENOMEM) return VM_FAULT_OOM; if (err) @@ -1644,116 +2509,171 @@ static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma, * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * - * Note the "page_table_lock". It is to protect against kswapd removing - * pages from under us. Note that kswapd only ever _removes_ pages, never - * adds them. As such, once we have noticed that the page is not present, - * we can drop the lock early. - * - * The adding of pages is protected by the MM semaphore (which we hold), - * so we don't need to worry about a page being suddenly been added into - * our VM. - * - * We enter with the pagetable spinlock held, we are supposed to - * release it when done. + * 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 inline int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct * vma, unsigned long address, - int write_access, pte_t *pte, pmd_t *pmd) + struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pmd_t *pmd, int write_access) { pte_t entry; + pte_t old_entry; + spinlock_t *ptl; + int ret, type = VXPT_UNKNOWN; - entry = *pte; + old_entry = entry = *pte; if (!pte_present(entry)) { - /* - * If it truly wasn't present, we know that kswapd - * and the PTE updates will not touch it later. So - * drop the lock. - */ - if (pte_none(entry)) - return do_no_page(mm, vma, address, write_access, pte, pmd); + if (pte_none(entry)) { + if (vma->vm_ops) { + if (vma->vm_ops->nopage) + return do_no_page(mm, vma, address, + pte, pmd, + write_access); + 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); + } if (pte_file(entry)) - return do_file_page(mm, vma, address, write_access, pte, pmd); - return do_swap_page(mm, vma, address, pte, pmd, entry, write_access); + return do_file_page(mm, vma, address, + pte, pmd, write_access, entry); + return do_swap_page(mm, vma, address, + 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); - + if (!pte_write(entry)) { + ret = do_wp_page(mm, vma, address, + pte, pmd, ptl, entry); + type = VXPT_WRITE; + goto out; + } entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - ptep_set_access_flags(vma, address, pte, entry, write_access); - update_mmu_cache(vma, address, entry); - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); - return VM_FAULT_MINOR; + 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); + ret = VM_FAULT_MINOR; +out: + vx_page_fault(mm, vma, type, ret); + return ret; } /* * By the time we get here, we already hold the mm semaphore */ -int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma, - unsigned long address, int write_access) +int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, int write_access) { pgd_t *pgd; + pud_t *pud; pmd_t *pmd; + pte_t *pte; __set_current_state(TASK_RUNNING); + + count_vm_event(PGFAULT); + + if (unlikely(is_vm_hugetlb_page(vma))) + return hugetlb_fault(mm, vma, address, write_access); + pgd = pgd_offset(mm, address); + pud = pud_alloc(mm, pgd, address); + if (!pud) + return VM_FAULT_OOM; + pmd = pmd_alloc(mm, pud, address); + if (!pmd) + return VM_FAULT_OOM; + pte = pte_alloc_map(mm, pmd, address); + if (!pte) + return VM_FAULT_OOM; + + return handle_pte_fault(mm, vma, address, pte, pmd, write_access); +} - inc_page_state(pgfault); +EXPORT_SYMBOL_GPL(__handle_mm_fault); - if (is_vm_hugetlb_page(vma)) - return VM_FAULT_SIGBUS; /* mapping truncation does this. */ +#ifndef __PAGETABLE_PUD_FOLDED +/* + * Allocate page upper directory. + * We've already handled the fast-path in-line. + */ +int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + pud_t *new = pud_alloc_one(mm, address); + if (!new) + return -ENOMEM; - /* - * We need the page table lock to synchronize with kswapd - * and the SMP-safe atomic PTE updates. - */ spin_lock(&mm->page_table_lock); - pmd = pmd_alloc(mm, pgd, address); - - if (pmd) { - pte_t * pte = pte_alloc_map(mm, pmd, address); - if (pte) - return handle_pte_fault(mm, vma, address, write_access, pte, pmd); - } + if (pgd_present(*pgd)) /* Another has populated it */ + pud_free(new); + else + pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); - return VM_FAULT_OOM; + 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 /* * Allocate page middle directory. - * - * We've already handled the fast-path in-line, and we own the - * page table lock. - * - * On a two-level page table, this ends up actually being entirely - * optimized away. + * We've already handled the fast-path in-line. */ -pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { - pmd_t *new; - - spin_unlock(&mm->page_table_lock); - new = pmd_alloc_one(mm, address); - spin_lock(&mm->page_table_lock); + pmd_t *new = pmd_alloc_one(mm, address); if (!new) - return NULL; + return -ENOMEM; - /* - * Because we dropped the lock, we should re-check the - * entry, as somebody else could have populated it.. - */ - if (pgd_present(*pgd)) { + spin_lock(&mm->page_table_lock); +#ifndef __ARCH_HAS_4LEVEL_HACK + if (pud_present(*pud)) /* Another has populated it */ pmd_free(new); - goto out; - } - pgd_populate(mm, pgd, new); -out: - return pmd_offset(pgd, address); + else + pud_populate(mm, pud, new); +#else + if (pgd_present(*pud)) /* Another has populated it */ + pmd_free(new); + else + pgd_populate(mm, pud, new); +#endif /* __ARCH_HAS_4LEVEL_HACK */ + 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) { @@ -1761,11 +2681,11 @@ int make_pages_present(unsigned long addr, unsigned long end) struct vm_area_struct * vma; vma = find_vma(current->mm, addr); + 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); @@ -1782,19 +2702,21 @@ struct page * vmalloc_to_page(void * vmalloc_addr) unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); + pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; if (!pgd_none(*pgd)) { - pmd = pmd_offset(pgd, addr); - if (!pmd_none(*pmd)) { - preempt_disable(); - ptep = pte_offset_map(pmd, addr); - pte = *ptep; - if (pte_present(pte)) - page = pte_page(pte); - pte_unmap(ptep); - preempt_enable(); + pud = pud_offset(pgd, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) { + ptep = pte_offset_map(pmd, addr); + pte = *ptep; + if (pte_present(pte)) + page = pte_page(pte); + pte_unmap(ptep); + } } } return page; @@ -1802,18 +2724,35 @@ struct page * vmalloc_to_page(void * vmalloc_addr) EXPORT_SYMBOL(vmalloc_to_page); -#if !defined(CONFIG_ARCH_GATE_AREA) +/* + * Map a vmalloc()-space virtual address to the physical page frame number. + */ +unsigned long vmalloc_to_pfn(void * vmalloc_addr) +{ + return page_to_pfn(vmalloc_to_page(vmalloc_addr)); +} + +EXPORT_SYMBOL(vmalloc_to_pfn); + +#if !defined(__HAVE_ARCH_GATE_AREA) #if defined(AT_SYSINFO_EHDR) -struct vm_area_struct gate_vma; +static struct vm_area_struct gate_vma; static int __init gate_vma_init(void) { gate_vma.vm_mm = NULL; 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 = 0; + gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + gate_vma.vm_page_prot = __P101; + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + gate_vma.vm_flags |= VM_ALWAYSDUMP; return 0; } __initcall(gate_vma_init); @@ -1828,7 +2767,7 @@ struct vm_area_struct *get_gate_vma(struct task_struct *tsk) #endif } -int in_gate_area(struct task_struct *task, unsigned long addr) +int in_gate_area_no_task(unsigned long addr) { #ifdef AT_SYSINFO_EHDR if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END)) @@ -1837,4 +2776,57 @@ int in_gate_area(struct task_struct *task, unsigned long addr) return 0; } -#endif +#endif /* __HAVE_ARCH_GATE_AREA */ + +/* + * Access another process' address space. + * Source/target buffer must be kernel space, + * Do not walk the page table directly, use get_user_pages + */ +int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write) +{ + struct mm_struct *mm; + struct vm_area_struct *vma; + struct page *page; + void *old_buf = buf; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + down_read(&mm->mmap_sem); + /* ignore errors, just check how much was sucessfully transfered */ + while (len) { + int bytes, ret, offset; + void *maddr; + + 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); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + page_cache_release(page); + len -= bytes; + buf += bytes; + addr += bytes; + } + up_read(&mm->mmap_sem); + mmput(mm); + + return buf - old_buf; +}