mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![Mel Gorman](/assets/img/avatar_default.png)
Commit 5d1904204c
("mremap: fix race between mremap() and page
cleanning") fixed races between mremap and other operations for both
file-backed and anonymous mappings. The file-backed was the most
critical as it allowed the possibility that data could be changed on a
physical page after page_mkclean returned which could trigger data loss
or data integrity issues.
A customer reported that the cost of the TLBs for anonymous regressions
was excessive and resulting in a 30-50% drop in performance overall
since this commit on a microbenchmark. Unfortunately I neither have
access to the test-case nor can I describe what it does other than
saying that mremap operations dominate heavily.
This patch removes the LATENCY_LIMIT to handle TLB flushes on a PMD
boundary instead of every 64 pages to reduce the number of TLB
shootdowns by a factor of 8 in the ideal case. LATENCY_LIMIT was almost
certainly used originally to limit the PTL hold times but the latency
savings are likely offset by the cost of IPIs in many cases. This patch
is not reported to completely restore performance but gets it within an
acceptable percentage. The given metric here is simply described as
"higher is better".
Baseline that was known good
002: Metric: 91.05
004: Metric: 109.45
008: Metric: 73.08
016: Metric: 58.14
032: Metric: 61.09
064: Metric: 57.76
128: Metric: 55.43
Current
001: Metric: 54.98
002: Metric: 56.56
004: Metric: 41.22
008: Metric: 35.96
016: Metric: 36.45
032: Metric: 35.71
064: Metric: 35.73
128: Metric: 34.96
With patch
001: Metric: 61.43
002: Metric: 81.64
004: Metric: 67.92
008: Metric: 51.67
016: Metric: 50.47
032: Metric: 52.29
064: Metric: 50.01
128: Metric: 49.04
So for low threads, it's not restored but for larger number of threads,
it's closer to the "known good" baseline.
Using a different mremap-intensive workload that is not representative
of the real workload there is little difference observed outside of
noise in the headline metrics However, the TLB shootdowns are reduced by
11% on average and at the peak, TLB shootdowns were reduced by 21%.
Interrupts were sampled every second while the workload ran to get those
figures. It's known that the figures will vary as the
non-representative load is non-deterministic.
An alternative patch was posted that should have significantly reduced
the TLB flushes but unfortunately it does not perform as well as this
version on the customer test case. If revisited, the two patches can
stack on top of each other.
Link: http://lkml.kernel.org/r/20180606183803.k7qaw2xnbvzshv34@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
641 lines
17 KiB
C
641 lines
17 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* 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 <linux/userfaultfd_k.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;
|
|
p4d_t *p4d;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
|
|
pgd = pgd_offset(mm, addr);
|
|
if (pgd_none_or_clear_bad(pgd))
|
|
return NULL;
|
|
|
|
p4d = p4d_offset(pgd, addr);
|
|
if (p4d_none_or_clear_bad(p4d))
|
|
return NULL;
|
|
|
|
pud = pud_offset(p4d, addr);
|
|
if (pud_none_or_clear_bad(pud))
|
|
return NULL;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
if (pmd_none(*pmd))
|
|
return NULL;
|
|
|
|
return pmd;
|
|
}
|
|
|
|
static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
unsigned long addr)
|
|
{
|
|
pgd_t *pgd;
|
|
p4d_t *p4d;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
|
|
pgd = pgd_offset(mm, addr);
|
|
p4d = p4d_alloc(mm, pgd, addr);
|
|
if (!p4d)
|
|
return NULL;
|
|
pud = pud_alloc(mm, p4d, addr);
|
|
if (!pud)
|
|
return NULL;
|
|
|
|
pmd = pmd_alloc(mm, pud, addr);
|
|
if (!pmd)
|
|
return NULL;
|
|
|
|
VM_BUG_ON(pmd_trans_huge(*pmd));
|
|
|
|
return pmd;
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
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, bool *need_flush)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
pte_t *old_pte, *new_pte, pte;
|
|
spinlock_t *old_ptl, *new_ptl;
|
|
bool force_flush = false;
|
|
unsigned long len = old_end - old_addr;
|
|
|
|
/*
|
|
* 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);
|
|
flush_tlb_batched_pending(vma->vm_mm);
|
|
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);
|
|
/*
|
|
* If we are remapping a dirty PTE, make sure
|
|
* to flush TLB before we drop the PTL for the
|
|
* old PTE or we may race with page_mkclean().
|
|
*
|
|
* This check has to be done after we removed the
|
|
* old PTE from page tables or another thread may
|
|
* dirty it after the check and before the removal.
|
|
*/
|
|
if (pte_present(pte) && pte_dirty(pte))
|
|
force_flush = true;
|
|
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);
|
|
if (force_flush)
|
|
flush_tlb_range(vma, old_end - len, old_end);
|
|
else
|
|
*need_flush = true;
|
|
pte_unmap_unlock(old_pte - 1, old_ptl);
|
|
if (need_rmap_locks)
|
|
drop_rmap_locks(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,
|
|
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 (is_swap_pmd(*old_pmd) || 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,
|
|
&need_flush);
|
|
if (need_rmap_locks)
|
|
drop_rmap_locks(vma);
|
|
if (moved)
|
|
continue;
|
|
}
|
|
split_huge_pmd(vma, old_pmd, old_addr);
|
|
if (pmd_trans_unstable(old_pmd))
|
|
continue;
|
|
}
|
|
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;
|
|
move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
|
|
new_pmd, new_addr, need_rmap_locks, &need_flush);
|
|
}
|
|
if (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 */
|
|
}
|
|
|
|
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 vm_userfaultfd_ctx *uf,
|
|
struct list_head *uf_unmap)
|
|
{
|
|
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 {
|
|
mremap_userfaultfd_prep(new_vma, uf);
|
|
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, uf_unmap) < 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;
|
|
}
|
|
|
|
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);
|
|
|
|
/*
|
|
* !old_len is a special case where an attempt is made to 'duplicate'
|
|
* a mapping. This makes no sense for private mappings as it will
|
|
* instead create a fresh/new mapping unrelated to the original. This
|
|
* is contrary to the basic idea of mremap which creates new mappings
|
|
* based on the original. There are no known use cases for this
|
|
* behavior. As a result, fail such attempts.
|
|
*/
|
|
if (!old_len && !(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) {
|
|
pr_warn_once("%s (%d): attempted to duplicate a private mapping with mremap. This is not supported.\n", current->comm, current->pid);
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
|
|
unsigned long new_addr, unsigned long new_len, bool *locked,
|
|
struct vm_userfaultfd_ctx *uf,
|
|
struct list_head *uf_unmap_early,
|
|
struct list_head *uf_unmap)
|
|
{
|
|
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, uf_unmap_early);
|
|
if (ret)
|
|
goto out;
|
|
|
|
if (old_len >= new_len) {
|
|
ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap);
|
|
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, uf,
|
|
uf_unmap);
|
|
if (!(offset_in_page(ret)))
|
|
goto out;
|
|
out1:
|
|
vm_unacct_memory(charged);
|
|
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
|
|
LIST_HEAD(uf_unmap_early);
|
|
LIST_HEAD(uf_unmap);
|
|
|
|
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(¤t->mm->mmap_sem))
|
|
return -EINTR;
|
|
|
|
if (flags & MREMAP_FIXED) {
|
|
ret = mremap_to(addr, old_len, new_addr, new_len,
|
|
&locked, &uf, &uf_unmap_early, &uf_unmap);
|
|
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, &uf_unmap);
|
|
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, &uf, &uf_unmap);
|
|
}
|
|
out:
|
|
if (offset_in_page(ret)) {
|
|
vm_unacct_memory(charged);
|
|
locked = 0;
|
|
}
|
|
up_write(¤t->mm->mmap_sem);
|
|
if (locked && new_len > old_len)
|
|
mm_populate(new_addr + old_len, new_len - old_len);
|
|
userfaultfd_unmap_complete(mm, &uf_unmap_early);
|
|
mremap_userfaultfd_complete(&uf, addr, new_addr, old_len);
|
|
userfaultfd_unmap_complete(mm, &uf_unmap);
|
|
return ret;
|
|
}
|