summaryrefslogtreecommitdiff
path: root/mm/vma.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/vma.c')
-rw-r--r--mm/vma.c113
1 files changed, 79 insertions, 34 deletions
diff --git a/mm/vma.c b/mm/vma.c
index a325376e62ea..35e7a64855fa 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -18,6 +18,7 @@ struct mmap_state {
unsigned long addr;
unsigned long end;
pgoff_t pgoff;
+ pgoff_t anon_pgoff;
unsigned long pglen;
union {
vm_flags_t vm_flags;
@@ -46,13 +47,14 @@ struct mmap_state {
bool file_doesnt_need_get :1;
};
-#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, vma_flags_, file_) \
+#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, anon_pgoff_, vma_flags_, file_) \
struct mmap_state name = { \
.mm = mm_, \
.vmi = vmi_, \
.addr = addr_, \
.end = (addr_) + (len_), \
.pgoff = pgoff_, \
+ .anon_pgoff = anon_pgoff_, \
.pglen = PHYS_PFN(len_), \
.vma_flags = vma_flags_, \
.file = file_, \
@@ -67,6 +69,7 @@ struct mmap_state {
.end = (map_)->end, \
.vma_flags = (map_)->vma_flags, \
.pgoff = (map_)->pgoff, \
+ .anon_pgoff = (map_)->anon_pgoff, \
.file = (map_)->file, \
.prev = (map_)->prev, \
.middle = vma_, \
@@ -82,10 +85,11 @@ static void __vma_set_range(struct vm_area_struct *vma, unsigned long start,
}
static void vma_set_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end, pgoff_t pgoff)
+ unsigned long end, pgoff_t pgoff, pgoff_t anon_pgoff)
{
__vma_set_range(vma, start, end);
vma_set_pgoff(vma, pgoff);
+ vma_set_anon_pgoff(vma, anon_pgoff);
}
/* Was this VMA ever forked from a parent, i.e. maybe contains CoW mappings? */
@@ -201,6 +205,25 @@ static void init_multi_vma_prep(struct vma_prepare *vp,
}
/*
+ * Does this merge require that adjacent VMAs must have adjacent anonymous page
+ * offsets in addition to having adjacent vma->vm_pgoff?
+ *
+ * This is only required for MAP_PRIVATE-file backed mappings as the page offset
+ * for pure anonymous VMAs is equal to the anonymous page offset.
+ *
+ * Read-only shared mappings (with VMA_SHARED_BIT cleared) are always unfaulted
+ * so automatically have correct anonymous page offset (as it is always updated
+ * on remap).
+ *
+ * 'Special' mappings in the sense of VDSO, VVAR etc. have !file but would in
+ * any case not be candidates for merge nor be mergeable.
+ */
+static bool needs_adjacent_anon_pgoff(const struct vma_merge_struct *vmg)
+{
+ return vmg->file && vma_flags_is_cow_mapping(&vmg->vma_flags);
+}
+
+/*
* Return true if we can merge this (vma_flags,anon_vma,file,vm_pgoff)
* in front of (at a lower virtual address and file offset than) the vma.
*
@@ -221,6 +244,9 @@ static bool can_vma_merge_before(struct vma_merge_struct *vmg)
return false;
if (vmg_end_pgoff(vmg) != vma_start_pgoff(vmg->next))
return false;
+ if (needs_adjacent_anon_pgoff(vmg) &&
+ vmg_end_anon_pgoff(vmg) != vma_start_anon_pgoff(vmg->next))
+ return false;
return true;
}
@@ -241,6 +267,9 @@ static bool can_vma_merge_after(struct vma_merge_struct *vmg)
return false;
if (vma_end_pgoff(vmg->prev) != vmg_start_pgoff(vmg))
return false;
+ if (needs_adjacent_anon_pgoff(vmg) &&
+ vma_end_anon_pgoff(vmg->prev) != vmg_start_anon_pgoff(vmg))
+ return false;
return true;
}
@@ -812,7 +841,8 @@ static int commit_merge(struct vma_merge_struct *vmg)
*/
vma_adjust_trans_huge(vma, vmg->start, vmg->end,
vmg->__adjust_middle_start ? vmg->middle : NULL);
- vma_set_range(vma, vmg->start, vmg->end, vmg_start_pgoff(vmg));
+ vma_set_range(vma, vmg->start, vmg->end, vmg_start_pgoff(vmg),
+ vmg_start_anon_pgoff(vmg));
vmg_adjust_set_range(vmg);
vma_iter_store_overwrite(vmg->vmi, vmg->target);
@@ -982,6 +1012,7 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
vmg->start = prev->vm_start;
vmg->end = next->vm_end;
vmg->pgoff = vma_start_pgoff(prev);
+ vmg->anon_pgoff = vma_start_anon_pgoff(prev);
/*
* We already ensured anon_vma compatibility above, so now it's
@@ -1000,6 +1031,7 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
*/
vmg->start = prev->vm_start;
vmg->pgoff = vma_start_pgoff(prev);
+ vmg->anon_pgoff = vma_start_anon_pgoff(prev);
if (!vmg->__remove_middle)
vmg->__adjust_middle_start = true;
@@ -1022,12 +1054,14 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
if (vmg->__remove_middle) {
vmg->end = next->vm_end;
vmg->pgoff = vma_start_pgoff(next) - pglen;
+ vmg->anon_pgoff = vma_start_anon_pgoff(next) - pglen;
} else {
/* We shrink middle and expand next. */
vmg->__adjust_next_start = true;
vmg->start = middle->vm_start;
vmg->end = start;
vmg->pgoff = vma_start_pgoff(middle);
+ vmg->anon_pgoff = vma_start_anon_pgoff(middle);
}
err = dup_anon_vma(next, middle, &anon_dup);
@@ -1137,6 +1171,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
vmg->start = prev->vm_start;
vmg->target = prev;
vmg->pgoff = vma_start_pgoff(prev);
+ vmg->anon_pgoff = vma_start_anon_pgoff(prev);
/*
* If this merge would result in removal of the next VMA but we
@@ -1908,23 +1943,27 @@ static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma)
*/
struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
unsigned long addr, unsigned long len, pgoff_t pgoff,
- bool *need_rmap_locks)
+ pgoff_t anon_pgoff, bool *need_rmap_locks)
{
struct vm_area_struct *vma = *vmap;
- unsigned long vma_start = vma->vm_start;
+ unsigned long old_vma_start = vma->vm_start;
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *new_vma;
- bool faulted_in_anon_vma = true;
+ bool can_self_merge = false;
VMA_ITERATOR(vmi, mm, addr);
VMG_VMA_STATE(vmg, &vmi, NULL, vma, addr, addr + len);
/*
- * If anonymous vma has not yet been faulted, update new pgoff
- * to match new location, to increase its chance of merging.
+ * If a vma has not yet been faulted, update its anonymous pgoff to
+ * match the new location to increase its chance of merging.
*/
- if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) {
- pgoff = addr >> PAGE_SHIFT;
- faulted_in_anon_vma = false;
+ if (!vma->anon_vma) {
+ anon_pgoff = addr >> PAGE_SHIFT;
+
+ if (vma_is_anonymous(vma)) {
+ pgoff = anon_pgoff;
+ can_self_merge = true;
+ }
}
/*
@@ -1940,28 +1979,26 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
return NULL; /* should never get here */
vmg.pgoff = pgoff;
+ vmg.anon_pgoff = anon_pgoff;
vmg.next = vma_iter_next_rewind(&vmi, NULL);
new_vma = vma_merge_copied_range(&vmg);
if (new_vma) {
- /*
- * Source vma may have been merged into new_vma
- */
- if (unlikely(vma_start >= new_vma->vm_start &&
- vma_start < new_vma->vm_end)) {
+ /* Self-merged and VMA replaced. */
+ if (unlikely(new_vma->vm_start < old_vma_start &&
+ new_vma->vm_end > old_vma_start)) {
/*
- * The only way we can get a vma_merge with
- * self during an mremap is if the vma hasn't
- * been faulted in yet and we were allowed to
- * reset the dst vma->vm_pgoff to the
- * destination address of the mremap to allow
- * the merge to happen. mremap must change the
- * vm_pgoff linearity between src and dst vmas
- * (in turn preventing a vma_merge) to be
- * safe. It is only safe to keep the vm_pgoff
- * linear if there are no pages mapped yet.
+ * The only way a VMA can both self-merge and be
+ * replaced is if the remap places the new VMA
+ * immediately prior to its old self ('next') and
+ * immediately after another VMA ('prev') causing the
+ * next to be removed and prev to be expanded to cover
+ * the entire range.
+ *
+ * This should only be possible if the anonymous page
+ * offset was updated, i.e. the VMA is unfaulted.
*/
- VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma);
+ VM_WARN_ON_ONCE_VMA(!can_self_merge, new_vma);
*vmap = vma = new_vma;
}
*need_rmap_locks =
@@ -1970,7 +2007,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
new_vma = vm_area_dup(vma);
if (!new_vma)
goto out;
- vma_set_range(new_vma, addr, addr + len, pgoff);
+ vma_set_range(new_vma, addr, addr + len, pgoff, anon_pgoff);
if (vma_dup_policy(vma, new_vma))
goto out_free_vma;
if (anon_vma_clone(new_vma, vma, VMA_OP_REMAP))
@@ -2036,7 +2073,12 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *
if (!vma_flags_empty(&diff))
return false;
/* Page offset must align. */
- return vma_end_pgoff(a) == vma_start_pgoff(b);
+ if (vma_end_pgoff(a) != vma_start_pgoff(b))
+ return false;
+ /* Only reached from anon path, so either MAP_PRIVATE file or anon. */
+ if (vma_end_anon_pgoff(a) != vma_start_anon_pgoff(b))
+ return false;
+ return true;
}
/*
@@ -2612,7 +2654,7 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap,
if (is_anon)
vma_set_anonymous(vma);
- vma_set_range(vma, map->addr, map->end, map->pgoff);
+ vma_set_range(vma, map->addr, map->end, map->pgoff, map->anon_pgoff);
vma->flags = map->vma_flags;
vma->vm_page_prot = map->page_prot;
@@ -2801,7 +2843,8 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr,
struct vm_area_struct *vma = NULL;
bool have_mmap_prepare = file && file->f_op->mmap_prepare;
VMA_ITERATOR(vmi, mm, addr);
- MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vma_flags, file);
+ const pgoff_t anon_pgoff = addr >> PAGE_SHIFT;
+ MMAP_STATE(map, mm, &vmi, addr, len, pgoff, anon_pgoff, vma_flags, file);
struct vm_area_desc desc = {
.mm = mm,
.file = file,
@@ -2946,6 +2989,7 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
unsigned long addr, unsigned long len, vma_flags_t vma_flags)
{
struct mm_struct *mm = current->mm;
+ const pgoff_t pgoff = addr >> PAGE_SHIFT;
/*
* Check against address space limits by the changed size
@@ -2970,7 +3014,7 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
* occur after forking, so the expand will only happen on new VMAs.
*/
if (vma && vma->vm_end == addr) {
- VMG_STATE(vmg, mm, vmi, addr, addr + len, vma_flags, PHYS_PFN(addr));
+ VMG_STATE(vmg, mm, vmi, addr, addr + len, vma_flags, pgoff, pgoff);
vmg.prev = vma;
/* vmi is positioned at prev, which this mode expects. */
@@ -2990,7 +3034,7 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
goto unacct_fail;
vma_set_anonymous(vma);
- vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT);
+ vma_set_range(vma, addr, addr + len, pgoff, pgoff);
vma->flags = vma_flags;
vma->vm_page_prot = vm_get_page_prot(vma_flags_to_legacy(vma_flags));
vma_start_write(vma);
@@ -3382,6 +3426,7 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
WARN_ON_ONCE(vma->anon_vma);
vma_set_pgoff(vma, vma->vm_start >> PAGE_SHIFT);
}
+ vma_set_anon_pgoff(vma, vma->vm_start >> PAGE_SHIFT);
if (vma_link(mm, vma)) {
if (vma_test(vma, VMA_ACCOUNT_BIT))
@@ -3437,7 +3482,7 @@ struct vm_area_struct *__install_special_mapping(
vma->vm_ops = ops;
vma->vm_private_data = priv;
- vma_set_range(vma, addr, addr + len, 0);
+ vma_set_range(vma, addr, addr + len, 0, addr >> PAGE_SHIFT);
ret = insert_vm_struct(mm, vma);
if (ret)