summaryrefslogtreecommitdiffstats
path: root/mm/mmap.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/mmap.c')
-rw-r--r--mm/mmap.c262
1 files changed, 176 insertions, 86 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index ee2298936fe..456ec6f2788 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -265,7 +265,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
* segment grow beyond its set limit the in case where the limit is
* not page aligned -Ram Gupta
*/
- rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
+ rlim = rlimit(RLIMIT_DATA);
if (rlim < RLIM_INFINITY && (brk - mm->start_brk) +
(mm->end_data - mm->start_data) > rlim)
goto out;
@@ -437,7 +437,6 @@ __vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
{
__vma_link_list(mm, vma, prev, rb_parent);
__vma_link_rb(mm, vma, rb_link, rb_parent);
- __anon_vma_link(vma);
}
static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -499,7 +498,7 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
* are necessary. The "insert" vma (if any) is to be inserted
* before we drop the necessary locks.
*/
-void vma_adjust(struct vm_area_struct *vma, unsigned long start,
+int vma_adjust(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert)
{
struct mm_struct *mm = vma->vm_mm;
@@ -508,11 +507,12 @@ void vma_adjust(struct vm_area_struct *vma, unsigned long start,
struct address_space *mapping = NULL;
struct prio_tree_root *root = NULL;
struct file *file = vma->vm_file;
- struct anon_vma *anon_vma = NULL;
long adjust_next = 0;
int remove_next = 0;
if (next && !insert) {
+ struct vm_area_struct *exporter = NULL;
+
if (end >= next->vm_end) {
/*
* vma expands, overlapping all the next, and
@@ -520,7 +520,7 @@ void vma_adjust(struct vm_area_struct *vma, unsigned long start,
*/
again: remove_next = 1 + (end > next->vm_end);
end = next->vm_end;
- anon_vma = next->anon_vma;
+ exporter = next;
importer = vma;
} else if (end > next->vm_start) {
/*
@@ -528,7 +528,7 @@ again: remove_next = 1 + (end > next->vm_end);
* mprotect case 5 shifting the boundary up.
*/
adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
- anon_vma = next->anon_vma;
+ exporter = next;
importer = vma;
} else if (end < vma->vm_end) {
/*
@@ -537,9 +537,20 @@ again: remove_next = 1 + (end > next->vm_end);
* mprotect case 4 shifting the boundary down.
*/
adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
- anon_vma = next->anon_vma;
+ exporter = vma;
importer = next;
}
+
+ /*
+ * Easily overlooked: when mprotect shifts the boundary,
+ * make sure the expanding vma has anon_vma set if the
+ * shrinking vma had, to cover any anon pages imported.
+ */
+ if (exporter && exporter->anon_vma && !importer->anon_vma) {
+ if (anon_vma_clone(importer, exporter))
+ return -ENOMEM;
+ importer->anon_vma = exporter->anon_vma;
+ }
}
if (file) {
@@ -567,25 +578,6 @@ again: remove_next = 1 + (end > next->vm_end);
}
}
- /*
- * When changing only vma->vm_end, we don't really need
- * anon_vma lock.
- */
- if (vma->anon_vma && (insert || importer || start != vma->vm_start))
- anon_vma = vma->anon_vma;
- if (anon_vma) {
- spin_lock(&anon_vma->lock);
- /*
- * Easily overlooked: when mprotect shifts the boundary,
- * make sure the expanding vma has anon_vma set if the
- * shrinking vma had, to cover any anon pages imported.
- */
- if (importer && !importer->anon_vma) {
- importer->anon_vma = anon_vma;
- __anon_vma_link(importer);
- }
- }
-
if (root) {
flush_dcache_mmap_lock(mapping);
vma_prio_tree_remove(vma, root);
@@ -616,8 +608,6 @@ again: remove_next = 1 + (end > next->vm_end);
__vma_unlink(mm, next, vma);
if (file)
__remove_shared_vm_struct(next, file, mapping);
- if (next->anon_vma)
- __anon_vma_merge(vma, next);
} else if (insert) {
/*
* split_vma has split insert from vma, and needs
@@ -627,8 +617,6 @@ again: remove_next = 1 + (end > next->vm_end);
__insert_vm_struct(mm, insert);
}
- if (anon_vma)
- spin_unlock(&anon_vma->lock);
if (mapping)
spin_unlock(&mapping->i_mmap_lock);
@@ -638,6 +626,8 @@ again: remove_next = 1 + (end > next->vm_end);
if (next->vm_flags & VM_EXECUTABLE)
removed_exe_file_vma(mm);
}
+ if (next->anon_vma)
+ anon_vma_merge(vma, next);
mm->map_count--;
mpol_put(vma_policy(next));
kmem_cache_free(vm_area_cachep, next);
@@ -653,6 +643,8 @@ again: remove_next = 1 + (end > next->vm_end);
}
validate_mm(mm);
+
+ return 0;
}
/*
@@ -759,6 +751,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
{
pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
struct vm_area_struct *area, *next;
+ int err;
/*
* We later require that vma->vm_flags == vm_flags,
@@ -792,11 +785,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
is_mergeable_anon_vma(prev->anon_vma,
next->anon_vma)) {
/* cases 1, 6 */
- vma_adjust(prev, prev->vm_start,
+ err = vma_adjust(prev, prev->vm_start,
next->vm_end, prev->vm_pgoff, NULL);
} else /* cases 2, 5, 7 */
- vma_adjust(prev, prev->vm_start,
+ err = vma_adjust(prev, prev->vm_start,
end, prev->vm_pgoff, NULL);
+ if (err)
+ return NULL;
return prev;
}
@@ -808,11 +803,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
can_vma_merge_before(next, vm_flags,
anon_vma, file, pgoff+pglen)) {
if (prev && addr < prev->vm_end) /* case 4 */
- vma_adjust(prev, prev->vm_start,
+ err = vma_adjust(prev, prev->vm_start,
addr, prev->vm_pgoff, NULL);
else /* cases 3, 8 */
- vma_adjust(area, addr, next->vm_end,
+ err = vma_adjust(area, addr, next->vm_end,
next->vm_pgoff - pglen, NULL);
+ if (err)
+ return NULL;
return area;
}
@@ -820,6 +817,61 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
}
/*
+ * Rough compatbility check to quickly see if it's even worth looking
+ * at sharing an anon_vma.
+ *
+ * They need to have the same vm_file, and the flags can only differ
+ * in things that mprotect may change.
+ *
+ * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that
+ * we can merge the two vma's. For example, we refuse to merge a vma if
+ * there is a vm_ops->close() function, because that indicates that the
+ * driver is doing some kind of reference counting. But that doesn't
+ * really matter for the anon_vma sharing case.
+ */
+static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b)
+{
+ return a->vm_end == b->vm_start &&
+ mpol_equal(vma_policy(a), vma_policy(b)) &&
+ a->vm_file == b->vm_file &&
+ !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) &&
+ b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
+}
+
+/*
+ * Do some basic sanity checking to see if we can re-use the anon_vma
+ * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be
+ * the same as 'old', the other will be the new one that is trying
+ * to share the anon_vma.
+ *
+ * NOTE! This runs with mm_sem held for reading, so it is possible that
+ * the anon_vma of 'old' is concurrently in the process of being set up
+ * by another page fault trying to merge _that_. But that's ok: if it
+ * is being set up, that automatically means that it will be a singleton
+ * acceptable for merging, so we can do all of this optimistically. But
+ * we do that ACCESS_ONCE() to make sure that we never re-load the pointer.
+ *
+ * IOW: that the "list_is_singular()" test on the anon_vma_chain only
+ * matters for the 'stable anon_vma' case (ie the thing we want to avoid
+ * is to return an anon_vma that is "complex" due to having gone through
+ * a fork).
+ *
+ * We also make sure that the two vma's are compatible (adjacent,
+ * and with the same memory policies). That's all stable, even with just
+ * a read lock on the mm_sem.
+ */
+static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b)
+{
+ if (anon_vma_compatible(a, b)) {
+ struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma);
+
+ if (anon_vma && list_is_singular(&old->anon_vma_chain))
+ return anon_vma;
+ }
+ return NULL;
+}
+
+/*
* find_mergeable_anon_vma is used by anon_vma_prepare, to check
* neighbouring vmas for a suitable anon_vma, before it goes off
* to allocate a new anon_vma. It checks because a repetitive
@@ -829,28 +881,16 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
*/
struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
{
+ struct anon_vma *anon_vma;
struct vm_area_struct *near;
- unsigned long vm_flags;
near = vma->vm_next;
if (!near)
goto try_prev;
- /*
- * Since only mprotect tries to remerge vmas, match flags
- * which might be mprotected into each other later on.
- * Neither mlock nor madvise tries to remerge at present,
- * so leave their flags as obstructing a merge.
- */
- vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
- vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
-
- if (near->anon_vma && vma->vm_end == near->vm_start &&
- mpol_equal(vma_policy(vma), vma_policy(near)) &&
- can_vma_merge_before(near, vm_flags,
- NULL, vma->vm_file, vma->vm_pgoff +
- ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT)))
- return near->anon_vma;
+ anon_vma = reusable_anon_vma(near, vma, near);
+ if (anon_vma)
+ return anon_vma;
try_prev:
/*
* It is potentially slow to have to call find_vma_prev here.
@@ -863,14 +903,9 @@ try_prev:
if (!near)
goto none;
- vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
- vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
-
- if (near->anon_vma && near->vm_end == vma->vm_start &&
- mpol_equal(vma_policy(near), vma_policy(vma)) &&
- can_vma_merge_after(near, vm_flags,
- NULL, vma->vm_file, vma->vm_pgoff))
- return near->anon_vma;
+ anon_vma = reusable_anon_vma(near, near, vma);
+ if (anon_vma)
+ return anon_vma;
none:
/*
* There's no absolute need to look only at touching neighbours:
@@ -967,7 +1002,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long locked, lock_limit;
locked = len >> PAGE_SHIFT;
locked += mm->locked_vm;
- lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
if (locked > lock_limit && !capable(CAP_IPC_LOCK))
return -EAGAIN;
@@ -1083,6 +1118,30 @@ out:
return retval;
}
+#ifdef __ARCH_WANT_SYS_OLD_MMAP
+struct mmap_arg_struct {
+ unsigned long addr;
+ unsigned long len;
+ unsigned long prot;
+ unsigned long flags;
+ unsigned long fd;
+ unsigned long offset;
+};
+
+SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
+{
+ struct mmap_arg_struct a;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ return -EFAULT;
+ if (a.offset & ~PAGE_MASK)
+ return -EINVAL;
+
+ return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+ a.offset >> PAGE_SHIFT);
+}
+#endif /* __ARCH_WANT_SYS_OLD_MMAP */
+
/*
* Some shared mappigns will want the pages marked read-only
* to track write events. If so, we'll downgrade vm_page_prot
@@ -1205,6 +1264,7 @@ munmap_back:
vma->vm_flags = vm_flags;
vma->vm_page_prot = vm_get_page_prot(vm_flags);
vma->vm_pgoff = pgoff;
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
if (file) {
error = -EINVAL;
@@ -1265,13 +1325,8 @@ out:
mm->total_vm += len >> PAGE_SHIFT;
vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
- /*
- * makes pages present; downgrades, drops, reacquires mmap_sem
- */
- long nr_pages = mlock_vma_pages_range(vma, addr, addr + len);
- if (nr_pages < 0)
- return nr_pages; /* vma gone! */
- mm->locked_vm += (len >> PAGE_SHIFT) - nr_pages;
+ if (!mlock_vma_pages_range(vma, addr, addr + len))
+ mm->locked_vm += (len >> PAGE_SHIFT);
} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
make_pages_present(addr, addr + len);
return addr;
@@ -1599,7 +1654,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
return -ENOMEM;
/* Stack limit test */
- if (size > rlim[RLIMIT_STACK].rlim_cur)
+ if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
return -ENOMEM;
/* mlock limit tests */
@@ -1607,7 +1662,8 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
unsigned long locked;
unsigned long limit;
locked = mm->locked_vm + grow;
- limit = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+ limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur);
+ limit >>= PAGE_SHIFT;
if (locked > limit && !capable(CAP_IPC_LOCK))
return -ENOMEM;
}
@@ -1754,8 +1810,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
if (!prev || expand_stack(prev, addr))
return NULL;
if (prev->vm_flags & VM_LOCKED) {
- if (mlock_vma_pages_range(prev, addr, prev->vm_end) < 0)
- return NULL; /* vma gone! */
+ mlock_vma_pages_range(prev, addr, prev->vm_end);
}
return prev;
}
@@ -1783,8 +1838,7 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr)
if (expand_stack(vma, addr))
return NULL;
if (vma->vm_flags & VM_LOCKED) {
- if (mlock_vma_pages_range(vma, addr, start) < 0)
- return NULL; /* vma gone! */
+ mlock_vma_pages_range(vma, addr, start);
}
return vma;
}
@@ -1871,6 +1925,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
{
struct mempolicy *pol;
struct vm_area_struct *new;
+ int err = -ENOMEM;
if (is_vm_hugetlb_page(vma) && (addr &
~(huge_page_mask(hstate_vma(vma)))))
@@ -1878,11 +1933,13 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (!new)
- return -ENOMEM;
+ goto out_err;
/* most fields are the same, copy all, and then fixup */
*new = *vma;
+ INIT_LIST_HEAD(&new->anon_vma_chain);
+
if (new_below)
new->vm_end = addr;
else {
@@ -1892,11 +1949,14 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
pol = mpol_dup(vma_policy(vma));
if (IS_ERR(pol)) {
- kmem_cache_free(vm_area_cachep, new);
- return PTR_ERR(pol);
+ err = PTR_ERR(pol);
+ goto out_free_vma;
}
vma_set_policy(new, pol);
+ if (anon_vma_clone(new, vma))
+ goto out_free_mpol;
+
if (new->vm_file) {
get_file(new->vm_file);
if (vma->vm_flags & VM_EXECUTABLE)
@@ -1907,12 +1967,29 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
new->vm_ops->open(new);
if (new_below)
- vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff +
+ err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff +
((addr - new->vm_start) >> PAGE_SHIFT), new);
else
- vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new);
+ err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new);
- return 0;
+ /* Success. */
+ if (!err)
+ return 0;
+
+ /* Clean everything up if vma_adjust failed. */
+ if (new->vm_ops && new->vm_ops->close)
+ new->vm_ops->close(new);
+ if (new->vm_file) {
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(mm);
+ fput(new->vm_file);
+ }
+ out_free_mpol:
+ mpol_put(pol);
+ out_free_vma:
+ kmem_cache_free(vm_area_cachep, new);
+ out_err:
+ return err;
}
/*
@@ -2074,7 +2151,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
unsigned long locked, lock_limit;
locked = len >> PAGE_SHIFT;
locked += mm->locked_vm;
- lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
if (locked > lock_limit && !capable(CAP_IPC_LOCK))
return -EAGAIN;
@@ -2122,6 +2199,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
return -ENOMEM;
}
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
vma->vm_mm = mm;
vma->vm_start = addr;
vma->vm_end = addr + len;
@@ -2258,10 +2336,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
if (new_vma) {
*new_vma = *vma;
pol = mpol_dup(vma_policy(vma));
- if (IS_ERR(pol)) {
- kmem_cache_free(vm_area_cachep, new_vma);
- return NULL;
- }
+ if (IS_ERR(pol))
+ goto out_free_vma;
+ INIT_LIST_HEAD(&new_vma->anon_vma_chain);
+ if (anon_vma_clone(new_vma, vma))
+ goto out_free_mempol;
vma_set_policy(new_vma, pol);
new_vma->vm_start = addr;
new_vma->vm_end = addr + len;
@@ -2277,6 +2356,12 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
}
}
return new_vma;
+
+ out_free_mempol:
+ mpol_put(pol);
+ out_free_vma:
+ kmem_cache_free(vm_area_cachep, new_vma);
+ return NULL;
}
/*
@@ -2288,7 +2373,7 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages)
unsigned long cur = mm->total_vm; /* pages */
unsigned long lim;
- lim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+ lim = rlimit(RLIMIT_AS) >> PAGE_SHIFT;
if (cur + npages > lim)
return 0;
@@ -2354,6 +2439,7 @@ int install_special_mapping(struct mm_struct *mm,
if (unlikely(vma == NULL))
return -ENOMEM;
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
vma->vm_mm = mm;
vma->vm_start = addr;
vma->vm_end = addr + len;
@@ -2454,6 +2540,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
int mm_take_all_locks(struct mm_struct *mm)
{
struct vm_area_struct *vma;
+ struct anon_vma_chain *avc;
int ret = -EINTR;
BUG_ON(down_read_trylock(&mm->mmap_sem));
@@ -2471,7 +2558,8 @@ int mm_take_all_locks(struct mm_struct *mm)
if (signal_pending(current))
goto out_unlock;
if (vma->anon_vma)
- vm_lock_anon_vma(mm, vma->anon_vma);
+ list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+ vm_lock_anon_vma(mm, avc->anon_vma);
}
ret = 0;
@@ -2526,13 +2614,15 @@ static void vm_unlock_mapping(struct address_space *mapping)
void mm_drop_all_locks(struct mm_struct *mm)
{
struct vm_area_struct *vma;
+ struct anon_vma_chain *avc;
BUG_ON(down_read_trylock(&mm->mmap_sem));
BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma->anon_vma)
- vm_unlock_anon_vma(vma->anon_vma);
+ list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+ vm_unlock_anon_vma(avc->anon_vma);
if (vma->vm_file && vma->vm_file->f_mapping)
vm_unlock_mapping(vma->vm_file->f_mapping);
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-28 00:50:48 +0000