cregit-Linux how code gets into the kernel

Release 4.7 mm/mremap.c

Directory: mm
/*
 *      mm/mremap.c
 *
 *      (C) Copyright 1996 Linus Torvalds
 *
 *      Address space accounting code   <alan@lxorguk.ukuu.org.uk>
 *      (C) Copyright 2002 Red Hat Inc, All Rights Reserved
 */

#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <linux/ksm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/swapops.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/mmu_notifier.h>
#include <linux/uaccess.h>
#include <linux/mm-arch-hooks.h>

#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

#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; pgd = pgd_offset(mm, addr); if (pgd_none_or_clear_bad(pgd)) return NULL; pud = pud_offset(pgd, addr); if (pud_none_or_clear_bad(pud)) return NULL; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return NULL; return pmd; }

Contributors

PersonTokensPropCommitsCommitProp
andrew mortonandrew morton5865.17%228.57%
andi kleenandi kleen2325.84%114.29%
hugh dickinshugh dickins33.37%228.57%
pre-gitpre-git33.37%114.29%
andrea arcangeliandrea arcangeli22.25%114.29%
Total89100.00%7100.00%


static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; }

Contributors

PersonTokensPropCommitsCommitProp
pre-gitpre-git3436.96%116.67%
andi kleenandi kleen3133.70%116.67%
andrea arcangeliandrea arcangeli1415.22%116.67%
hugh dickinshugh dickins1111.96%233.33%
linus torvaldslinus torvalds22.17%116.67%
Total92100.00%6100.00%


static void take_rmap_locks(struct vm_area_struct *vma) { if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); if (vma->anon_vma) anon_vma_lock_write(vma->anon_vma); }

Contributors

PersonTokensPropCommitsCommitProp
hugh dickinshugh dickins39100.00%1100.00%
Total39100.00%1100.00%


static void drop_rmap_locks(struct vm_area_struct *vma) { if (vma->anon_vma) anon_vma_unlock_write(vma->anon_vma); if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping); }

Contributors

PersonTokensPropCommitsCommitProp
hugh dickinshugh dickins39100.00%1100.00%
Total39100.00%1100.00%


static pte_t move_soft_dirty_pte(pte_t pte) { /* * Set soft dirty bit so we can notice * in userspace the ptes were moved. */ #ifdef CONFIG_MEM_SOFT_DIRTY if (pte_present(pte)) pte = pte_mksoft_dirty(pte); else if (is_swap_pte(pte)) pte = pte_swp_mksoft_dirty(pte); #endif return pte; }

Contributors

PersonTokensPropCommitsCommitProp
cyrill gorcunovcyrill gorcunov47100.00%1100.00%
Total47100.00%1100.00%


static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, unsigned long old_addr, unsigned long old_end, struct vm_area_struct *new_vma, pmd_t *new_pmd, unsigned long new_addr, bool need_rmap_locks) { struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; /* * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma * locks to ensure that rmap will always observe either the old or the * new ptes. This is the easiest way to avoid races with * truncate_pagecache(), page migration, etc... * * When need_rmap_locks is false, we use other ways to avoid * such races: * * - During exec() shift_arg_pages(), we use a specially tagged vma * which rmap call sites look for using is_vma_temporary_stack(). * * - During mremap(), new_vma is often known to be placed after vma * in rmap traversal order. This ensures rmap will always observe * either the old pte, or the new pte, or both (the page table locks * serialize access to individual ptes, but only rmap traversal * order guarantees that we won't miss both the old and new ptes). */ if (need_rmap_locks) take_rmap_locks(vma); /* * 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(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_get_and_clear(mm, old_addr, old_pte); pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); pte = move_soft_dirty_pte(pte); 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(new_pte - 1); pte_unmap_unlock(old_pte - 1, old_ptl); if (need_rmap_locks) drop_rmap_locks(vma); }

Contributors

PersonTokensPropCommitsCommitProp
hugh dickinshugh dickins11146.64%518.52%
pre-gitpre-git2811.76%27.41%
andrew mortonandrew morton2811.76%622.22%
nick pigginnick piggin156.30%27.41%
kanoj sarcarkanoj sarcar114.62%13.70%
ingo molnaringo molnar104.20%27.41%
michel lespinassemichel lespinasse104.20%27.41%
cyrill gorcunovcyrill gorcunov72.94%13.70%
zachary amsdenzachary amsden62.52%13.70%
david s. millerdavid s. miller52.10%13.70%
linus torvaldslinus torvalds20.84%13.70%
peter zijlstrapeter zijlstra20.84%13.70%
andrea arcangeliandrea arcangeli20.84%13.70%
davidlohr buesodavidlohr bueso10.42%13.70%
Total238100.00%27100.00%

#define LATENCY_LIMIT (64 * PAGE_SIZE)
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, bool need_rmap_locks) { unsigned long extent, next, old_end; pmd_t *old_pmd, *new_pmd; bool need_flush = false; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); mmun_start = old_addr; mmun_end = old_end; mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end); for (; old_addr < old_end; old_addr += extent, new_addr += extent) { cond_resched(); next = (old_addr + PMD_SIZE) & PMD_MASK; /* even if next overflowed, extent below will be ok */ extent = next - old_addr; if (extent > old_end - old_addr) extent = old_end - old_addr; old_pmd = get_old_pmd(vma->vm_mm, old_addr); if (!old_pmd) continue; new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr); if (!new_pmd) break; if (pmd_trans_huge(*old_pmd)) { if (extent == HPAGE_PMD_SIZE) { bool moved; /* See comment in move_ptes() */ if (need_rmap_locks) take_rmap_locks(vma); moved = move_huge_pmd(vma, old_addr, new_addr, old_end, old_pmd, new_pmd); if (need_rmap_locks) drop_rmap_locks(vma); if (moved) { need_flush = true; continue; } } split_huge_pmd(vma, old_pmd, old_addr); if (pmd_none(*old_pmd)) continue; VM_BUG_ON(pmd_trans_huge(*old_pmd)); } if (pte_alloc(new_vma->vm_mm, new_pmd, new_addr)) break; next = (new_addr + PMD_SIZE) & PMD_MASK; if (extent > next - new_addr) extent = next - new_addr; if (extent > LATENCY_LIMIT) extent = LATENCY_LIMIT; move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma, new_pmd, new_addr, need_rmap_locks); need_flush = true; } if (likely(need_flush)) flush_tlb_range(vma, old_end-len, old_addr); mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); return len + old_addr - old_end; /* how much done */ }

Contributors

PersonTokensPropCommitsCommitProp
hugh dickinshugh dickins14537.47%418.18%
andrea arcangeliandrea arcangeli12732.82%418.18%
kirill a. shutemovkirill a. shutemov389.82%627.27%
pre-gitpre-git379.56%29.09%
sagi grimbergsagi grimberg225.68%14.55%
andrew mortonandrew morton92.33%29.09%
michel lespinassemichel lespinasse51.29%14.55%
linus torvaldslinus torvalds30.78%14.55%
kanoj sarcarkanoj sarcar10.26%14.55%
Total387100.00%22100.00%


static unsigned long move_vma(struct vm_area_struct *vma, unsigned long old_addr, unsigned long old_len, unsigned long new_len, unsigned long new_addr, bool *locked) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; unsigned long vm_flags = vma->vm_flags; unsigned long new_pgoff; unsigned long moved_len; unsigned long excess = 0; unsigned long hiwater_vm; int split = 0; int err; bool need_rmap_locks; /* * We'd prefer to avoid failure later on in do_munmap: * which may split one vma into three before unmapping. */ if (mm->map_count >= sysctl_max_map_count - 3) return -ENOMEM; /* * Advise KSM to break any KSM pages in the area to be moved: * it would be confusing if they were to turn up at the new * location, where they happen to coincide with different KSM * pages recently unmapped. But leave vma->vm_flags as it was, * so KSM can come around to merge on vma and new_vma afterwards. */ err = ksm_madvise(vma, old_addr, old_addr + old_len, MADV_UNMERGEABLE, &vm_flags); if (err) return err; new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT); new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff, &need_rmap_locks); if (!new_vma) return -ENOMEM; moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len, need_rmap_locks); if (moved_len < old_len) { err = -ENOMEM; } else if (vma->vm_ops && vma->vm_ops->mremap) { err = vma->vm_ops->mremap(new_vma); } if (unlikely(err)) { /* * On error, move entries back from new area to old, * which will succeed since page tables still there, * and then proceed to unmap new area instead of old. */ move_page_tables(new_vma, new_addr, vma, old_addr, moved_len, true); vma = new_vma; old_len = new_len; old_addr = new_addr; new_addr = err; } else { arch_remap(mm, old_addr, old_addr + old_len, new_addr, new_addr + new_len); } /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT) { vma->vm_flags &= ~VM_ACCOUNT; excess = vma->vm_end - vma->vm_start - old_len; if (old_addr > vma->vm_start && old_addr + old_len < vma->vm_end) split = 1; } /* * 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; vm_stat_account(mm, vma->vm_flags, new_len >> PAGE_SHIFT); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn_moved(vma); if (do_munmap(mm, old_addr, old_len) < 0) { /* OOM: unable to split vma, just get accounts right */ 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) { vma->vm_flags |= VM_ACCOUNT; if (split) vma->vm_next->vm_flags |= VM_ACCOUNT; } if (vm_flags & VM_LOCKED) { mm->locked_vm += new_len >> PAGE_SHIFT; *locked = true; } return new_addr; }

Contributors

PersonTokensPropCommitsCommitProp
hugh dickinshugh dickins12427.43%832.00%
andrew mortonandrew morton10924.12%28.00%
pre-gitpre-git7215.93%520.00%
oleg nesterovoleg nesterov275.97%28.00%
linus torvaldslinus torvalds265.75%28.00%
al viroal viro255.53%14.00%
pavel emelianovpavel emelianov183.98%14.00%
laurent dufourlaurent dufour183.98%14.00%
toshi kanitoshi kani173.76%14.00%
michel lespinassemichel lespinasse163.54%28.00%
Total452100.00%25100.00%


static struct vm_area_struct *vma_to_resize(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long *p) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = find_vma(mm, addr); unsigned long pgoff; if (!vma || vma->vm_start > addr) return ERR_PTR(-EFAULT); if (is_vm_hugetlb_page(vma)) return ERR_PTR(-EINVAL); /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) return ERR_PTR(-EFAULT); if (new_len == old_len) return vma; /* Need to be careful about a growing mapping */ pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; if (pgoff + (new_len >> PAGE_SHIFT) < pgoff) return ERR_PTR(-EINVAL); if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) return ERR_PTR(-EFAULT); if (vma->vm_flags & VM_LOCKED) { unsigned long locked, lock_limit; locked = mm->locked_vm << PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); locked += new_len - old_len; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return ERR_PTR(-EAGAIN); } if (!may_expand_vm(mm, vma->vm_flags, (new_len - old_len) >> PAGE_SHIFT)) return ERR_PTR(-ENOMEM); if (vma->vm_flags & VM_ACCOUNT) { unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) return ERR_PTR(-ENOMEM); *p = charged; } return vma; }

Contributors

PersonTokensPropCommitsCommitProp
al viroal viro18061.02%228.57%
derek716 at gmail.comderek716 at gmail.com5117.29%114.29%
linus torvaldslinus torvalds3110.51%114.29%
oleg nesterovoleg nesterov268.81%114.29%
konstantin khlebnikovkonstantin khlebnikov41.36%114.29%
jiri slabyjiri slaby31.02%114.29%
Total295100.00%7100.00%


static unsigned long mremap_to(unsigned long addr, unsigned long old_len, unsigned long new_addr, unsigned long new_len, bool *locked) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long ret = -EINVAL; unsigned long charged = 0; unsigned long map_flags; if (offset_in_page(new_addr)) goto out; if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len) goto out; /* Ensure the old/new locations do not overlap */ if (addr + old_len > new_addr && new_addr + new_len > addr) goto out; ret = do_munmap(mm, new_addr, new_len); if (ret) goto out; if (old_len >= new_len) { ret = do_munmap(mm, addr+new_len, old_len - new_len); if (ret && old_len != new_len) goto out; old_len = new_len; } vma = vma_to_resize(addr, old_len, new_len, &charged); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } map_flags = MAP_FIXED; if (vma->vm_flags & VM_MAYSHARE) map_flags |= MAP_SHARED; ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT), map_flags); if (offset_in_page(ret)) goto out1; ret = move_vma(vma, addr, old_len, new_len, new_addr, locked); if (!(offset_in_page(ret))) goto out; out1: vm_unacct_memory(charged); out: return ret; }

Contributors

PersonTokensPropCommitsCommitProp
al viroal viro13245.67%215.38%
pre-gitpre-git9633.22%538.46%
andrew mortonandrew morton3211.07%215.38%
alexander kuleshovalexander kuleshov93.11%17.69%
hugh dickinshugh dickins93.11%17.69%
michel lespinassemichel lespinasse62.08%17.69%
oleg nesterovoleg nesterov51.73%17.69%
Total289100.00%13100.00%


static int vma_expandable(struct vm_area_struct *vma, unsigned long delta) { unsigned long end = vma->vm_end + delta; if (end < vma->vm_end) /* overflow */ return 0; if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */ return 0; if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start, 0, MAP_FIXED) & ~PAGE_MASK) return 0; return 1; }

Contributors

PersonTokensPropCommitsCommitProp
al viroal viro85100.00%3100.00%
Total85100.00%3100.00%

/* * Expand (or shrink) an existing mapping, potentially moving it at the * same time (controlled by the MREMAP_MAYMOVE flag and available VM space) * * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise * This option implies MREMAP_MAYMOVE. */ SYSCALL_DEFINE5(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; bool locked = false; if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) return ret; if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE)) return ret; if (offset_in_page(addr)) return ret; old_len = PAGE_ALIGN(old_len); new_len = PAGE_ALIGN(new_len); /* * We allow a zero old-len as a special case * for DOS-emu "duplicate shm area" thing. But * a zero new-len is nonsensical. */ if (!new_len) return ret; if (down_write_killable(&current->mm->mmap_sem)) return -EINTR; if (flags & MREMAP_FIXED) { ret = mremap_to(addr, old_len, new_addr, new_len, &locked); goto out; } /* * Always allow a shrinking remap: that just unmaps * the unnecessary pages.. * do_munmap does all the needed commit accounting */ if (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; goto out; } /* * Ok, we need to grow.. */ vma = vma_to_resize(addr, old_len, new_len, &charged); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } /* old_len exactly to the end of the area.. */ if (old_len == vma->vm_end - addr) { /* can we just expand the current mapping? */ if (vma_expandable(vma, new_len - old_len)) { int pages = (new_len - old_len) >> PAGE_SHIFT; if (vma_adjust(vma, vma->vm_start, addr + new_len, vma->vm_pgoff, NULL)) { ret = -ENOMEM; goto out; } vm_stat_account(mm, vma->vm_flags, pages); if (vma->vm_flags & VM_LOCKED) { mm->locked_vm += pages; locked = true; new_addr = addr; } ret = addr; goto out; } } /* * We weren't able to just expand or shrink the area, * we need to create a new one and move it.. */ ret = -ENOMEM; if (flags & MREMAP_MAYMOVE) { unsigned long map_flags = 0; if (vma->vm_flags & VM_MAYSHARE) map_flags |= MAP_SHARED; new_addr = get_unmapped_area(vma->vm_file, 0, new_len, vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT), map_flags); if (offset_in_page(new_addr)) { ret = new_addr; goto out; } ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked); } out: if (offset_in_page(ret)) { vm_unacct_memory(charged); locked = 0; } up_write(&current->mm->mmap_sem); if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); return ret; }

Overall Contributors

PersonTokensPropCommitsCommitProp
al viroal viro59722.86%109.09%
hugh dickinshugh dickins49418.91%1513.64%
pre-gitpre-git42216.16%1210.91%
andrew mortonandrew morton26910.30%1513.64%
andrea arcangeliandrea arcangeli1485.67%54.55%
linus torvaldslinus torvalds953.64%65.45%
michel lespinassemichel lespinasse732.79%32.73%
oleg nesterovoleg nesterov642.45%54.55%
cyrill gorcunovcyrill gorcunov572.18%10.91%
andi kleenandi kleen542.07%10.91%
derek716 at gmail.comderek716 at gmail.com511.95%10.91%
kirill a. shutemovkirill a. shutemov381.45%65.45%
rasmus villemoesrasmus villemoes331.26%10.91%
sagi grimbergsagi grimberg220.84%10.91%
laurent dufourlaurent dufour210.80%10.91%
pavel emelianovpavel emelianov180.69%10.91%
alexander kuleshovalexander kuleshov180.69%10.91%
toshi kanitoshi kani170.65%10.91%
rik van rielrik van riel160.61%32.73%
nick pigginnick piggin150.57%21.82%
kanoj sarcarkanoj sarcar120.46%10.91%
eric pariseric paris110.42%10.91%
ingo molnaringo molnar100.38%21.82%
william lee irwin iiiwilliam lee irwin iii90.34%10.91%
michal hockomichal hocko80.31%10.91%
richard hendersonrichard henderson70.27%10.91%
zachary amsdenzachary amsden60.23%10.91%
david s. millerdavid s. miller50.19%10.91%
konstantin khlebnikovkonstantin khlebnikov40.15%10.91%
randy dunlaprandy dunlap30.11%10.91%
jiri slabyjiri slaby30.11%10.91%
dave jonesdave jones30.11%10.91%
arnd bergmannarnd bergmann30.11%10.91%
peter zijlstrapeter zijlstra20.08%10.91%
james bottomleyjames bottomley10.04%10.91%
paul mcquadepaul mcquade10.04%10.91%
alan coxalan cox10.04%10.91%
davidlohr buesodavidlohr bueso10.04%10.91%
Total2612100.00%110100.00%
Directory: mm
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
{% endraw %}