X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmremap.c;h=a39b7b91be46722789a0ce95ed5382405796077c;hb=8713e01295140f674a41f2199b0f7ca99dfb69d5;hp=f4e5620985007ffbc3ae4be06a146aa45fcadacc;hpb=7be7a546994f1222b2312fd348da14e16b6b7b42;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/mremap.c b/mm/mremap.c index f4e5620..a39b7b9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -3,7 +3,7 @@ * * (C) Copyright 1996 Linus Torvalds * - * Address space accounting code + * Address space accounting code * (C) Copyright 2002 Red Hat Inc, All Rights Reserved */ @@ -13,24 +13,25 @@ #include #include #include +#include #include #include #include #include +#include #include #include #include +#include "internal.h" + static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; - /* - * We don't need page_table_lock: we have mmap_sem exclusively. - */ pgd = pgd_offset(mm, addr); if (pgd_none_or_clear_bad(pgd)) return NULL; @@ -50,30 +51,20 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; pud_t *pud; - pmd_t *pmd = NULL; - pte_t *pte; + pmd_t *pmd; - /* - * We do need page_table_lock: because allocators expect that. - */ - spin_lock(&mm->page_table_lock); pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); if (!pud) - goto out; + return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) - goto out; + return NULL; + + if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr)) + return NULL; - pte = pte_alloc_map(mm, pmd, addr); - if (!pte) { - pmd = NULL; - goto out; - } - pte_unmap(pte); -out: - spin_unlock(&mm->page_table_lock); return pmd; } @@ -85,7 +76,12 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct address_space *mapping = NULL; struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; + spinlock_t *old_ptl, *new_ptl; + unsigned long old_start; + old_start = old_addr; + mmu_notifier_invalidate_range_start(vma->vm_mm, + old_start, old_end); if (vma->vm_file) { /* * Subtle point from Rajesh Venkatasubramanian: before @@ -100,30 +96,39 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_vma->vm_truncate_count = 0; } - spin_lock(&mm->page_table_lock); - old_pte = pte_offset_map(old_pmd, old_addr); - new_pte = pte_offset_map_nested(new_pmd, new_addr); + /* + * We don't have to worry about the ordering of src and dst + * pte locks because exclusive mmap_sem prevents deadlock. + */ + old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); + new_pte = pte_offset_map_nested(new_pmd, new_addr); + new_ptl = pte_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + arch_enter_lazy_mmu_mode(); for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, new_pte++, new_addr += PAGE_SIZE) { if (pte_none(*old_pte)) continue; pte = ptep_clear_flush(vma, old_addr, old_pte); - /* ZERO_PAGE can be dependant on virtual addr */ pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); set_pte_at(mm, new_addr, new_pte, pte); } + arch_leave_lazy_mmu_mode(); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); pte_unmap_nested(new_pte - 1); - pte_unmap(old_pte - 1); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) spin_unlock(&mapping->i_mmap_lock); + mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end); } #define LATENCY_LIMIT (64 * PAGE_SIZE) -static unsigned long move_page_tables(struct vm_area_struct *vma, +unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len) { @@ -167,6 +172,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, unsigned long new_pgoff; unsigned long moved_len; unsigned long excess = 0; + unsigned long hiwater_vm; int split = 0; /* @@ -205,9 +211,15 @@ static unsigned long move_vma(struct vm_area_struct *vma, } /* - * if we failed to move page tables we still do total_vm increment - * since do_munmap() will decrement it by old_len == new_len + * If we failed to move page tables we still do total_vm increment + * since do_munmap() will decrement it by old_len == new_len. + * + * Since total_vm is about to be raised artificially high for a + * moment, we need to restore high watermark afterwards: if stats + * are taken meanwhile, total_vm and hiwater_vm appear too high. + * If this were a serious issue, we'd add a flag to do_munmap(). */ + hiwater_vm = mm->hiwater_vm; mm->total_vm += new_len >> PAGE_SHIFT; vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); @@ -216,6 +228,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, vm_unacct_memory(excess >> PAGE_SHIFT); excess = 0; } + mm->hiwater_vm = hiwater_vm; /* Restore VM_ACCOUNT if one or two pieces of vma left */ if (excess) { @@ -227,8 +240,8 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (vm_flags & VM_LOCKED) { mm->locked_vm += new_len >> PAGE_SHIFT; if (new_len > old_len) - make_pages_present(new_addr + old_len, - new_addr + new_len); + mlock_vma_pages_range(new_vma, new_addr + old_len, + new_addr + new_len); } return new_addr; @@ -245,6 +258,7 @@ unsigned long do_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr) { + struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long ret = -EINVAL; unsigned long charged = 0; @@ -285,7 +299,11 @@ unsigned long do_mremap(unsigned long addr, if ((addr <= new_addr) && (addr+old_len) > new_addr) goto out; - ret = do_munmap(current->mm, new_addr, new_len); + ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + if (ret) + goto out; + + ret = do_munmap(mm, new_addr, new_len); if (ret) goto out; } @@ -296,7 +314,7 @@ unsigned long do_mremap(unsigned long addr, * do_munmap does all the needed commit accounting */ if (old_len >= new_len) { - ret = do_munmap(current->mm, addr+new_len, old_len - new_len); + ret = do_munmap(mm, addr+new_len, old_len - new_len); if (ret && old_len != new_len) goto out; ret = addr; @@ -309,7 +327,7 @@ unsigned long do_mremap(unsigned long addr, * Ok, we need to grow.. or relocate. */ ret = -EFAULT; - vma = find_vma(current->mm, addr); + vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) goto out; if (is_vm_hugetlb_page(vma)) { @@ -319,20 +337,20 @@ unsigned long do_mremap(unsigned long addr, /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) goto out; - if (vma->vm_flags & VM_DONTEXPAND) { + if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) { if (new_len > old_len) goto out; } if (vma->vm_flags & VM_LOCKED) { unsigned long locked, lock_limit; - locked = current->mm->locked_vm << PAGE_SHIFT; + locked = mm->locked_vm << PAGE_SHIFT; lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; locked += new_len - old_len; ret = -EAGAIN; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) goto out; } - if (!may_expand_vm(current->mm, (new_len - old_len) >> PAGE_SHIFT)) { + if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) { ret = -ENOMEM; goto out; } @@ -359,12 +377,11 @@ unsigned long do_mremap(unsigned long addr, vma_adjust(vma, vma->vm_start, addr + new_len, vma->vm_pgoff, NULL); - current->mm->total_vm += pages; - vm_stat_account(vma->vm_mm, vma->vm_flags, - vma->vm_file, pages); + mm->total_vm += pages; + vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); if (vma->vm_flags & VM_LOCKED) { - current->mm->locked_vm += pages; - make_pages_present(addr + old_len, + mm->locked_vm += pages; + mlock_vma_pages_range(vma, addr + old_len, addr + new_len); } ret = addr; @@ -385,8 +402,13 @@ unsigned long do_mremap(unsigned long addr, new_addr = get_unmapped_area(vma->vm_file, 0, new_len, vma->vm_pgoff, map_flags); - ret = new_addr; - if (new_addr & ~PAGE_MASK) + if (new_addr & ~PAGE_MASK) { + ret = new_addr; + goto out; + } + + ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + if (ret) goto out; } ret = move_vma(vma, addr, old_len, new_len, new_addr); @@ -398,9 +420,9 @@ out_nc: return ret; } -asmlinkage unsigned long sys_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr) +SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, + unsigned long, new_len, unsigned long, flags, + unsigned long, new_addr) { unsigned long ret;