aboutsummaryrefslogtreecommitdiff
path: root/mm/mremap.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/mremap.c')
-rw-r--r--mm/mremap.c215
1 files changed, 141 insertions, 74 deletions
diff --git a/mm/mremap.c b/mm/mremap.c
index 563fbdd6293..05f1180e9f2 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -15,10 +15,12 @@
#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/sched/sysctl.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
@@ -41,13 +43,14 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
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;
@@ -62,38 +65,66 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr)
if (!pmd)
return NULL;
- if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr))
- return NULL;
+ VM_BUG_ON(pmd_trans_huge(*pmd));
return pmd;
}
+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);
+ else if (pte_file(pte))
+ pte = pte_file_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)
+ unsigned long new_addr, bool need_rmap_locks)
{
struct address_space *mapping = NULL;
+ struct anon_vma *anon_vma = 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
- * moving file-based ptes, we must lock truncate_pagecache
- * out, since it might clean the dst vma before the src vma,
- * 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;
+ /*
+ * When need_rmap_locks is true, we take the i_mmap_mutex 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) {
+ if (vma->vm_file) {
+ mapping = vma->vm_file->f_mapping;
+ mutex_lock(&mapping->i_mmap_mutex);
+ }
+ if (vma->anon_vma) {
+ anon_vma = vma->anon_vma;
+ anon_vma_lock_write(anon_vma);
+ }
}
/*
@@ -111,8 +142,9 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
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);
+ pte = move_soft_dirty_pte(pte);
set_pte_at(mm, new_addr, new_pte, pte);
}
@@ -121,50 +153,89 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
spin_unlock(new_ptl);
pte_unmap(new_pte - 1);
pte_unmap_unlock(old_pte - 1, old_ptl);
+ if (anon_vma)
+ anon_vma_unlock_write(anon_vma);
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 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)
+ 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;
- 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) {
+ VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+ /* See comment in move_ptes() */
+ if (need_rmap_locks)
+ anon_vma_lock_write(vma->anon_vma);
+ err = move_huge_pmd(vma, new_vma, old_addr,
+ new_addr, old_end,
+ old_pmd, new_pmd);
+ if (need_rmap_locks)
+ anon_vma_unlock_write(vma->anon_vma);
+ }
+ if (err > 0) {
+ need_flush = true;
+ continue;
+ } else if (!err) {
+ split_huge_page_pmd(vma, old_addr, 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;
if (extent > LATENCY_LIMIT)
extent = LATENCY_LIMIT;
move_ptes(vma, old_pmd, old_addr, old_addr + extent,
- new_vma, new_pmd, new_addr);
+ 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 */
}
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)
+ unsigned long new_len, unsigned long new_addr, bool *locked)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *new_vma;
@@ -175,6 +246,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
unsigned long hiwater_vm;
int split = 0;
int err;
+ bool need_rmap_locks;
/*
* We'd prefer to avoid failure later on in do_munmap:
@@ -196,18 +268,21 @@ static unsigned long move_vma(struct vm_area_struct *vma,
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);
+ 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);
+ moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len,
+ need_rmap_locks);
if (moved_len < old_len) {
/*
* 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);
+ move_page_tables(new_vma, new_addr, vma, old_addr, moved_len,
+ true);
vma = new_vma;
old_len = new_len;
old_addr = new_addr;
@@ -233,7 +308,6 @@ static unsigned long move_vma(struct vm_area_struct *vma,
* 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);
if (do_munmap(mm, old_addr, old_len) < 0) {
@@ -252,9 +326,7 @@ 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)
- mlock_vma_pages_range(new_vma, new_addr + old_len,
- new_addr + new_len);
+ *locked = true;
}
return new_addr;
@@ -276,9 +348,16 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
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) {
@@ -295,7 +374,7 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
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;
}
@@ -312,9 +391,8 @@ Eagain:
return ERR_PTR(-EAGAIN);
}
-static unsigned long mremap_to(unsigned long addr,
- unsigned long old_len, unsigned long new_addr,
- unsigned long new_len)
+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;
@@ -337,10 +415,6 @@ static unsigned long mremap_to(unsigned long addr,
if ((addr <= new_addr) && (addr+old_len) > new_addr)
goto out;
- 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;
@@ -368,7 +442,7 @@ static unsigned long mremap_to(unsigned long addr,
if (ret & ~PAGE_MASK)
goto out1;
- ret = move_vma(vma, addr, old_len, new_len, new_addr);
+ ret = move_vma(vma, addr, old_len, new_len, new_addr, locked);
if (!(ret & ~PAGE_MASK))
goto out;
out1:
@@ -398,20 +472,24 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
* MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
* This option implies MREMAP_MAYMOVE.
*/
-unsigned long do_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)
{
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))
- goto out;
+ return ret;
+
+ if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE))
+ return ret;
if (addr & ~PAGE_MASK)
- goto out;
+ return ret;
old_len = PAGE_ALIGN(old_len);
new_len = PAGE_ALIGN(new_len);
@@ -422,11 +500,13 @@ unsigned long do_mremap(unsigned long addr,
* a zero new-len is nonsensical.
*/
if (!new_len)
- goto out;
+ return ret;
+
+ down_write(&current->mm->mmap_sem);
if (flags & MREMAP_FIXED) {
- if (flags & MREMAP_MAYMOVE)
- ret = mremap_to(addr, old_len, new_addr, new_len);
+ ret = mremap_to(addr, old_len, new_addr, new_len,
+ &locked);
goto out;
}
@@ -465,12 +545,11 @@ unsigned long do_mremap(unsigned long addr,
goto out;
}
- mm->total_vm += pages;
vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages);
if (vma->vm_flags & VM_LOCKED) {
mm->locked_vm += pages;
- mlock_vma_pages_range(vma, addr + old_len,
- addr + new_len);
+ locked = true;
+ new_addr = addr;
}
ret = addr;
goto out;
@@ -496,25 +575,13 @@ unsigned long do_mremap(unsigned long 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);
+ ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked);
}
out:
if (ret & ~PAGE_MASK)
vm_unacct_memory(charged);
- return ret;
-}
-
-SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
- unsigned long, new_len, unsigned long, flags,
- unsigned long, new_addr)
-{
- unsigned long ret;
-
- down_write(&current->mm->mmap_sem);
- ret = do_mremap(addr, old_len, new_len, flags, new_addr);
up_write(&current->mm->mmap_sem);
+ if (locked && new_len > old_len)
+ mm_populate(new_addr + old_len, new_len - old_len);
return ret;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-03 18:26:29 +0000