#include <linux/mm.h>
#include <linux/hugetlb.h>
-#include <linux/slab.h>
#include <linux/shm.h>
#include <linux/ksm.h>
#include <linux/mman.h>
#include "internal.h"
-#ifndef arch_mmap_check
-#define arch_mmap_check(addr, len, flags) (0)
-#endif
-
static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
return NULL;
pmd = pmd_offset(pud, addr);
- if (pmd_none_or_clear_bad(pmd))
+ if (pmd_none(*pmd))
return NULL;
return pmd;
}
-static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr)
+static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
if (!pmd)
return NULL;
- if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr))
- return NULL;
+ VM_BUG_ON(pmd_trans_huge(*pmd));
return pmd;
}
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
* and we propagate stale pages into the dst afterward.
*/
mapping = vma->vm_file->f_mapping;
- spin_lock(&mapping->i_mmap_lock);
- if (new_vma->vm_truncate_count &&
- new_vma->vm_truncate_count != vma->vm_truncate_count)
- new_vma->vm_truncate_count = 0;
+ mutex_lock(&mapping->i_mmap_mutex);
}
/*
* 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_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);
new_pte++, new_addr += PAGE_SIZE) {
if (pte_none(*old_pte))
continue;
- pte = ptep_clear_flush(vma, old_addr, old_pte);
+ pte = ptep_get_and_clear(mm, old_addr, old_pte);
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(new_pte - 1);
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);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
#define LATENCY_LIMIT (64 * PAGE_SIZE)
{
unsigned long extent, next, old_end;
pmd_t *old_pmd, *new_pmd;
+ bool need_flush = false;
old_end = old_addr + len;
flush_cache_range(vma, old_addr, old_end);
+ mmu_notifier_invalidate_range_start(vma->vm_mm, old_addr, old_end);
+
for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
cond_resched();
next = (old_addr + PMD_SIZE) & PMD_MASK;
- if (next - 1 > old_end)
- next = old_end;
+ /* 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, new_addr);
+ new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
if (!new_pmd)
break;
+ if (pmd_trans_huge(*old_pmd)) {
+ int err = 0;
+ if (extent == HPAGE_PMD_SIZE)
+ err = move_huge_pmd(vma, new_vma, old_addr,
+ new_addr, old_end,
+ old_pmd, new_pmd);
+ if (err > 0) {
+ need_flush = true;
+ continue;
+ } else if (!err) {
+ split_huge_page_pmd(vma->vm_mm, old_pmd);
+ }
+ VM_BUG_ON(pmd_trans_huge(*old_pmd));
+ }
+ if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,
+ new_pmd, new_addr))
+ break;
next = (new_addr + PMD_SIZE) & PMD_MASK;
if (extent > next - new_addr)
extent = next - new_addr;
extent = LATENCY_LIMIT;
move_ptes(vma, old_pmd, old_addr, old_addr + extent,
new_vma, new_pmd, new_addr);
+ need_flush = true;
}
+ if (likely(need_flush))
+ flush_tlb_range(vma, old_end-len, old_addr);
+
+ mmu_notifier_invalidate_range_end(vma->vm_mm, old_end-len, old_end);
return len + old_addr - old_end; /* how much done */
}
moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len);
if (moved_len < old_len) {
+ /*
+ * Before moving the page tables from the new vma to
+ * the old vma, we need to be sure the old vma is
+ * queued after new vma in the same_anon_vma list to
+ * prevent SMP races with rmap_walk (that could lead
+ * rmap_walk to miss some page table).
+ */
+ anon_vma_moveto_tail(vma);
+
/*
* On error, move entries back from new area to old,
* which will succeed since page tables still there,
if (old_len > vma->vm_end - addr)
goto Efault;
- if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) {
- if (new_len > old_len)
+ /* Need to be careful about a growing mapping */
+ if (new_len > old_len) {
+ unsigned long pgoff;
+
+ if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))
goto Efault;
+ pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
+ pgoff += vma->vm_pgoff;
+ if (pgoff + (new_len >> PAGE_SHIFT) < pgoff)
+ goto Einval;
}
if (vma->vm_flags & VM_LOCKED) {
unsigned long locked, lock_limit;
locked = mm->locked_vm << PAGE_SHIFT;
- lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ lock_limit = rlimit(RLIMIT_MEMLOCK);
locked += new_len - old_len;
if (locked > lock_limit && !capable(CAP_IPC_LOCK))
goto Eagain;
if (vma->vm_flags & VM_ACCOUNT) {
unsigned long charged = (new_len - old_len) >> PAGE_SHIFT;
- if (security_vm_enough_memory(charged))
+ if (security_vm_enough_memory_mm(mm, charged))
goto Efault;
*p = charged;
}
map_flags = MAP_FIXED;
if (vma->vm_flags & VM_MAYSHARE)
map_flags |= MAP_SHARED;
- ret = arch_mmap_check(new_addr, new_len, map_flags);
- if (ret)
- goto out1;
+
ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff +
((addr - vma->vm_start) >> PAGE_SHIFT),
map_flags);
static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
{
unsigned long end = vma->vm_end + delta;
- unsigned long max_addr = TASK_SIZE;
- if (vma->vm_next)
- max_addr = vma->vm_next->vm_start;
- if (max_addr < end || end < vma->vm_end)
+ if (end < vma->vm_end) /* overflow */
return 0;
- if (arch_mmap_check(vma->vm_start, end - vma->vm_start, MAP_FIXED))
+ 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)
if (vma_expandable(vma, new_len - old_len)) {
int pages = (new_len - old_len) >> PAGE_SHIFT;
- vma_adjust(vma, vma->vm_start,
- addr + new_len, vma->vm_pgoff, NULL);
+ if (vma_adjust(vma, vma->vm_start, addr + new_len,
+ vma->vm_pgoff, NULL)) {
+ ret = -ENOMEM;
+ goto out;
+ }
mm->total_vm += pages;
vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);