*
* Written by obz.
*
- * Address space accounting code <alan@redhat.com>
+ * Address space accounting code <alan@lxorguk.ukuu.org.uk>
*/
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
+#include <linux/perf_event.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
/*
* Check that a process has enough memory to allocate a new virtual
/* Don't let a single process grow too big:
leave 3% of the size of this process for other processes */
- allowed -= mm->total_vm / 32;
+ if (mm)
+ allowed -= mm->total_vm / 32;
- /*
- * cast `allowed' as a signed long because vm_committed_space
- * sometimes has a negative value
- */
- if (atomic_long_read(&vm_committed_space) < (long)allowed)
+ if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
error:
vm_unacct_memory(pages);
return next;
}
-asmlinkage unsigned long sys_brk(unsigned long brk)
+SYSCALL_DEFINE1(brk, unsigned long, brk)
{
unsigned long rlim, retval;
unsigned long newbrk, oldbrk;
* 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;
if (vma_tmp->vm_end > addr) {
vma = vma_tmp;
if (vma_tmp->vm_start <= addr)
- return vma;
+ break;
__rb_link = &__rb_parent->rb_left;
} else {
rb_prev = __rb_parent;
rb_insert_color(&vma->vm_rb, &mm->mm_rb);
}
-static inline void __vma_link_file(struct vm_area_struct *vma)
+static void __vma_link_file(struct vm_area_struct *vma)
{
- struct file * file;
+ struct file *file;
file = vma->vm_file;
if (file) {
{
__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,
* insert vm structure into list and rbtree and anon_vma,
* but it has already been inserted into prio_tree earlier.
*/
-static void
-__insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
+static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{
- struct vm_area_struct * __vma, * prev;
- struct rb_node ** rb_link, * rb_parent;
+ struct vm_area_struct *__vma, *prev;
+ struct rb_node **rb_link, *rb_parent;
__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent);
BUG_ON(__vma && __vma->vm_start < vma->vm_end);
* 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;
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
*/
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) {
/*
* 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) {
/*
* 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) {
}
}
- /*
- * When changing only vma->vm_end, we don't really need
- * anon_vma lock: but is that case worth optimizing out?
- */
- if (vma->anon_vma)
- 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);
__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
__insert_vm_struct(mm, insert);
}
- if (anon_vma)
- spin_unlock(&anon_vma->lock);
if (mapping)
spin_unlock(&mapping->i_mmap_lock);
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);
}
validate_mm(mm);
+
+ return 0;
}
/*
* If the vma has a ->close operation then the driver probably needs to release
* per-vma resources, so we don't attempt to merge those.
*/
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
-
static inline int is_mergeable_vma(struct vm_area_struct *vma,
struct file *file, unsigned long vm_flags)
{
- if (vma->vm_flags != vm_flags)
+ /* VM_CAN_NONLINEAR may get set later by f_op->mmap() */
+ if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR)
return 0;
if (vma->vm_file != file)
return 0;
{
pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
struct vm_area_struct *area, *next;
+ int err;
/*
* We later require that vma->vm_flags == vm_flags,
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;
}
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;
}
}
/*
+ * 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
*/
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.
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:
#endif /* CONFIG_PROC_FS */
/*
- * The caller must hold down_write(current->mm->mmap_sem).
+ * The caller must hold down_write(¤t->mm->mmap_sem).
*/
-unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
+unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flags, unsigned long pgoff)
{
struct inode *inode;
unsigned int vm_flags;
int error;
- int accountable = 1;
unsigned long reqprot = prot;
/*
if (!(flags & MAP_FIXED))
addr = round_hint_to_min(addr);
- error = arch_mmap_check(addr, len, flags);
- if (error)
- return error;
-
/* Careful about overflows.. */
len = PAGE_ALIGN(len);
- if (!len || len > TASK_SIZE)
+ if (!len)
return -ENOMEM;
/* offset overflow? */
vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
- if (flags & MAP_LOCKED) {
+ if (flags & MAP_LOCKED)
if (!can_do_mlock())
return -EPERM;
- vm_flags |= VM_LOCKED;
- }
+
/* mlock MCL_FUTURE? */
if (vm_flags & VM_LOCKED) {
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;
return -EPERM;
vm_flags &= ~VM_MAYEXEC;
}
- if (is_file_hugepages(file))
- accountable = 0;
if (!file->f_op || !file->f_op->mmap)
return -ENODEV;
} else {
switch (flags & MAP_TYPE) {
case MAP_SHARED:
+ /*
+ * Ignore pgoff.
+ */
+ pgoff = 0;
vm_flags |= VM_SHARED | VM_MAYSHARE;
break;
case MAP_PRIVATE:
if (error)
return error;
- return mmap_region(file, addr, len, flags, vm_flags, pgoff,
- accountable);
+ return mmap_region(file, addr, len, flags, vm_flags, pgoff);
}
EXPORT_SYMBOL(do_mmap_pgoff);
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, unsigned long, pgoff)
+{
+ struct file *file = NULL;
+ unsigned long retval = -EBADF;
+
+ if (!(flags & MAP_ANONYMOUS)) {
+ if (unlikely(flags & MAP_HUGETLB))
+ return -EINVAL;
+ file = fget(fd);
+ if (!file)
+ goto out;
+ } else if (flags & MAP_HUGETLB) {
+ struct user_struct *user = NULL;
+ /*
+ * VM_NORESERVE is used because the reservations will be
+ * taken when vm_ops->mmap() is called
+ * A dummy user value is used because we are not locking
+ * memory so no accounting is necessary
+ */
+ len = ALIGN(len, huge_page_size(&default_hstate));
+ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
+ &user, HUGETLB_ANONHUGE_INODE);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+ }
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+ down_write(¤t->mm->mmap_sem);
+ retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(¤t->mm->mmap_sem);
+
+ if (file)
+ fput(file);
+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
mapping_cap_account_dirty(vma->vm_file->f_mapping);
}
+/*
+ * We account for memory if it's a private writeable mapping,
+ * not hugepages and VM_NORESERVE wasn't set.
+ */
+static inline int accountable_mapping(struct file *file, unsigned int vm_flags)
+{
+ /*
+ * hugetlb has its own accounting separate from the core VM
+ * VM_HUGETLB may not be set yet so we cannot check for that flag.
+ */
+ if (file && is_file_hugepages(file))
+ return 0;
+
+ return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
+}
+
unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, unsigned long flags,
- unsigned int vm_flags, unsigned long pgoff,
- int accountable)
+ unsigned int vm_flags, unsigned long pgoff)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
if (!may_expand_vm(mm, len >> PAGE_SHIFT))
return -ENOMEM;
- if (flags & MAP_NORESERVE)
- vm_flags |= VM_NORESERVE;
+ /*
+ * Set 'VM_NORESERVE' if we should not account for the
+ * memory use of this mapping.
+ */
+ if ((flags & MAP_NORESERVE)) {
+ /* We honor MAP_NORESERVE if allowed to overcommit */
+ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+ vm_flags |= VM_NORESERVE;
+
+ /* hugetlb applies strict overcommit unless MAP_NORESERVE */
+ if (file && is_file_hugepages(file))
+ vm_flags |= VM_NORESERVE;
+ }
- if (accountable && (!(flags & MAP_NORESERVE) ||
- sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
- if (vm_flags & VM_SHARED) {
- /* Check memory availability in shmem_file_setup? */
- vm_flags |= VM_ACCOUNT;
- } else if (vm_flags & VM_WRITE) {
- /*
- * Private writable mapping: check memory availability
- */
- charged = len >> PAGE_SHIFT;
- if (security_vm_enough_memory(charged))
- return -ENOMEM;
- vm_flags |= VM_ACCOUNT;
- }
+ /*
+ * Private writable mapping: check memory availability
+ */
+ if (accountable_mapping(file, vm_flags)) {
+ charged = len >> PAGE_SHIFT;
+ if (security_vm_enough_memory(charged))
+ return -ENOMEM;
+ vm_flags |= VM_ACCOUNT;
}
/*
- * Can we just expand an old private anonymous mapping?
- * The VM_SHARED test is necessary because shmem_zero_setup
- * will create the file object for a shared anonymous map below.
+ * Can we just expand an old mapping?
*/
- if (!file && !(vm_flags & VM_SHARED) &&
- vma_merge(mm, prev, addr, addr + len, vm_flags,
- NULL, NULL, pgoff, NULL))
+ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
+ if (vma)
goto out;
/*
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;
goto unmap_and_free_vma;
if (vm_flags & VM_EXECUTABLE)
added_exe_file_vma(mm);
+
+ /* Can addr have changed??
+ *
+ * Answer: Yes, several device drivers can do it in their
+ * f_op->mmap method. -DaveM
+ */
+ addr = vma->vm_start;
+ pgoff = vma->vm_pgoff;
+ vm_flags = vma->vm_flags;
} else if (vm_flags & VM_SHARED) {
error = shmem_zero_setup(vma);
if (error)
goto free_vma;
}
- /* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
- * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
- * that memory reservation must be checked; but that reservation
- * belongs to shared memory object, not to vma: so now clear it.
- */
- if ((vm_flags & (VM_SHARED|VM_ACCOUNT)) == (VM_SHARED|VM_ACCOUNT))
- vma->vm_flags &= ~VM_ACCOUNT;
-
- /* Can addr have changed??
- *
- * Answer: Yes, several device drivers can do it in their
- * f_op->mmap method. -DaveM
- */
- addr = vma->vm_start;
- pgoff = vma->vm_pgoff;
- vm_flags = vma->vm_flags;
+ if (vma_wants_writenotify(vma)) {
+ pgprot_t pprot = vma->vm_page_prot;
- if (vma_wants_writenotify(vma))
+ /* Can vma->vm_page_prot have changed??
+ *
+ * Answer: Yes, drivers may have changed it in their
+ * f_op->mmap method.
+ *
+ * Ensures that vmas marked as uncached stay that way.
+ */
vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
-
- if (file && vma_merge(mm, prev, addr, vma->vm_end,
- vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
- mpol_put(vma_policy(vma));
- kmem_cache_free(vm_area_cachep, vma);
- fput(file);
- if (vm_flags & VM_EXECUTABLE)
- removed_exe_file_vma(mm);
- } else {
- vma_link(mm, vma, prev, rb_link, rb_parent);
- file = vma->vm_file;
+ if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
}
+ vma_link(mm, vma, prev, rb_link, rb_parent);
+ file = vma->vm_file;
+
/* Once vma denies write, undo our temporary denial count */
if (correct_wcount)
atomic_inc(&inode->i_writecount);
out:
+ perf_event_mmap(vma);
+
mm->total_vm += len >> PAGE_SHIFT;
vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
if (vm_flags & VM_LOCKED) {
- mm->locked_vm += len >> PAGE_SHIFT;
- make_pages_present(addr, addr + len);
- }
- if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
+ 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;
unsigned long (*get_area)(struct file *, unsigned long,
unsigned long, unsigned long, unsigned long);
+ unsigned long error = arch_mmap_check(addr, len, flags);
+ if (error)
+ return error;
+
+ /* Careful about overflows.. */
+ if (len > TASK_SIZE)
+ return -ENOMEM;
+
get_area = current->mm->get_unmapped_area;
if (file && file->f_op && file->f_op->get_unmapped_area)
get_area = file->f_op->get_unmapped_area;
EXPORT_SYMBOL(get_unmapped_area);
/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
-struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr)
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
struct vm_area_struct *vma = NULL;
struct vm_area_struct **pprev)
{
struct vm_area_struct *vma = NULL, *prev = NULL;
- struct rb_node * rb_node;
+ struct rb_node *rb_node;
if (!mm)
goto out;
* update accounting. This is shared with both the
* grow-up and grow-down cases.
*/
-static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, unsigned long grow)
+static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
{
struct mm_struct *mm = vma->vm_mm;
struct rlimit *rlim = current->signal->rlim;
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 */
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;
}
* Overcommit.. This must be the final test, as it will
* update security statistics.
*/
- if (security_vm_enough_memory(grow))
+ if (security_vm_enough_memory_mm(mm, grow))
return -ENOMEM;
/* Ok, everything looks good - let it rip */
* vma is the last one with address > vma->vm_end. Have to extend vma.
*/
#ifndef CONFIG_IA64
-static inline
+static
#endif
int expand_upwards(struct vm_area_struct *vma, unsigned long address)
{
/*
* vma is the first one with address < vma->vm_start. Have to extend vma.
*/
-static inline int expand_downwards(struct vm_area_struct *vma,
+static int expand_downwards(struct vm_area_struct *vma,
unsigned long address)
{
int error;
return vma;
if (!prev || expand_stack(prev, addr))
return NULL;
- if (prev->vm_flags & VM_LOCKED)
- make_pages_present(addr, prev->vm_end);
+ if (prev->vm_flags & VM_LOCKED) {
+ mlock_vma_pages_range(prev, addr, prev->vm_end);
+ }
return prev;
}
#else
start = vma->vm_start;
if (expand_stack(vma, addr))
return NULL;
- if (vma->vm_flags & VM_LOCKED)
- make_pages_present(addr, start);
+ if (vma->vm_flags & VM_LOCKED) {
+ mlock_vma_pages_range(vma, addr, start);
+ }
return vma;
}
#endif
long nrpages = vma_pages(vma);
mm->total_vm -= nrpages;
- if (vma->vm_flags & VM_LOCKED)
- mm->locked_vm -= nrpages;
vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
vma = remove_vma(vma);
} while (vma);
}
/*
- * Split a vma into two pieces at address 'addr', a new vma is allocated
- * either for the first part or the tail.
+ * __split_vma() bypasses sysctl_max_map_count checking. We use this on the
+ * munmap path where it doesn't make sense to fail.
*/
-int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long addr, int new_below)
{
struct mempolicy *pol;
struct vm_area_struct *new;
+ int err = -ENOMEM;
- if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK))
+ if (is_vm_hugetlb_page(vma) && (addr &
+ ~(huge_page_mask(hstate_vma(vma)))))
return -EINVAL;
- if (mm->map_count >= sysctl_max_map_count)
- return -ENOMEM;
-
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 {
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)
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. */
+ 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;
+}
+
+/*
+ * Split a vma into two pieces at address 'addr', a new vma is allocated
+ * either for the first part or the tail.
+ */
+int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, int new_below)
+{
+ if (mm->map_count >= sysctl_max_map_count)
+ return -ENOMEM;
+
+ return __split_vma(mm, vma, addr, new_below);
}
/* Munmap is split into 2 main parts -- this part which finds
* places tmp vma above, and higher split_vma places tmp vma below.
*/
if (start > vma->vm_start) {
- int error = split_vma(mm, vma, start, 0);
+ int error;
+
+ /*
+ * Make sure that map_count on return from munmap() will
+ * not exceed its limit; but let map_count go just above
+ * its limit temporarily, to help free resources as expected.
+ */
+ if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count)
+ return -ENOMEM;
+
+ error = __split_vma(mm, vma, start, 0);
if (error)
return error;
prev = vma;
/* Does it split the last one? */
last = find_vma(mm, end);
if (last && end > last->vm_start) {
- int error = split_vma(mm, last, end, 1);
+ int error = __split_vma(mm, last, end, 1);
if (error)
return error;
}
vma = prev? prev->vm_next: mm->mmap;
/*
+ * unlock any mlock()ed ranges before detaching vmas
+ */
+ if (mm->locked_vm) {
+ struct vm_area_struct *tmp = vma;
+ while (tmp && tmp->vm_start < end) {
+ if (tmp->vm_flags & VM_LOCKED) {
+ mm->locked_vm -= vma_pages(tmp);
+ munlock_vma_pages_all(tmp);
+ }
+ tmp = tmp->vm_next;
+ }
+ }
+
+ /*
* Remove the vma's, and unmap the actual pages
*/
detach_vmas_to_be_unmapped(mm, vma, prev, end);
EXPORT_SYMBOL(do_munmap);
-asmlinkage long sys_munmap(unsigned long addr, size_t len)
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
{
int ret;
struct mm_struct *mm = current->mm;
if (!len)
return addr;
- if ((addr + len) > TASK_SIZE || (addr + len) < addr)
- return -EINVAL;
-
- if (is_hugepage_only_range(mm, addr, len))
- return -EINVAL;
-
error = security_file_mmap(NULL, 0, 0, 0, addr, 1);
if (error)
return error;
flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
- error = arch_mmap_check(addr, len, flags);
- if (error)
+ error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
+ if (error & ~PAGE_MASK)
return error;
/*
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;
return -ENOMEM;
/* Can we just expand an old private anonymous mapping? */
- if (vma_merge(mm, prev, addr, addr + len, flags,
- NULL, NULL, pgoff, NULL))
+ vma = vma_merge(mm, prev, addr, addr + len, flags,
+ NULL, NULL, pgoff, NULL);
+ if (vma)
goto out;
/*
return -ENOMEM;
}
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
vma->vm_mm = mm;
vma->vm_start = addr;
vma->vm_end = addr + len;
out:
mm->total_vm += len >> PAGE_SHIFT;
if (flags & VM_LOCKED) {
- mm->locked_vm += len >> PAGE_SHIFT;
- make_pages_present(addr, addr + len);
+ if (!mlock_vma_pages_range(vma, addr, addr + len))
+ mm->locked_vm += (len >> PAGE_SHIFT);
}
return addr;
}
void exit_mmap(struct mm_struct *mm)
{
struct mmu_gather *tlb;
- struct vm_area_struct *vma = mm->mmap;
+ struct vm_area_struct *vma;
unsigned long nr_accounted = 0;
unsigned long end;
/* mm's last user has gone, and its about to be pulled down */
+ mmu_notifier_release(mm);
+
+ if (mm->locked_vm) {
+ vma = mm->mmap;
+ while (vma) {
+ if (vma->vm_flags & VM_LOCKED)
+ munlock_vma_pages_all(vma);
+ vma = vma->vm_next;
+ }
+ }
+
arch_exit_mmap(mm);
+ vma = mm->mmap;
+ if (!vma) /* Can happen if dup_mmap() received an OOM */
+ return;
+
lru_add_drain();
flush_cache_mm(mm);
tlb = tlb_gather_mmu(mm, 1);
- /* Don't update_hiwater_rss(mm) here, do_exit already did */
+ /* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
+
free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0);
tlb_finish_mmu(tlb, 0, end);
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;
}
}
return new_vma;
+
+ out_free_mempol:
+ mpol_put(pol);
+ out_free_vma:
+ kmem_cache_free(vm_area_cachep, new_vma);
+ return NULL;
}
/*
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;
{
}
-static struct vm_operations_struct special_mapping_vmops = {
+static const struct vm_operations_struct special_mapping_vmops = {
.close = special_mapping_close,
.fault = special_mapping_fault,
};
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;
mm->total_vm += len >> PAGE_SHIFT;
+ perf_event_mmap(vma);
+
return 0;
}
+
+static DEFINE_MUTEX(mm_all_locks_mutex);
+
+static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
+{
+ if (!test_bit(0, (unsigned long *) &anon_vma->head.next)) {
+ /*
+ * The LSB of head.next can't change from under us
+ * because we hold the mm_all_locks_mutex.
+ */
+ spin_lock_nest_lock(&anon_vma->lock, &mm->mmap_sem);
+ /*
+ * We can safely modify head.next after taking the
+ * anon_vma->lock. If some other vma in this mm shares
+ * the same anon_vma we won't take it again.
+ *
+ * No need of atomic instructions here, head.next
+ * can't change from under us thanks to the
+ * anon_vma->lock.
+ */
+ if (__test_and_set_bit(0, (unsigned long *)
+ &anon_vma->head.next))
+ BUG();
+ }
+}
+
+static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
+{
+ if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
+ /*
+ * AS_MM_ALL_LOCKS can't change from under us because
+ * we hold the mm_all_locks_mutex.
+ *
+ * Operations on ->flags have to be atomic because
+ * even if AS_MM_ALL_LOCKS is stable thanks to the
+ * mm_all_locks_mutex, there may be other cpus
+ * changing other bitflags in parallel to us.
+ */
+ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
+ BUG();
+ spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
+ }
+}
+
+/*
+ * This operation locks against the VM for all pte/vma/mm related
+ * operations that could ever happen on a certain mm. This includes
+ * vmtruncate, try_to_unmap, and all page faults.
+ *
+ * The caller must take the mmap_sem in write mode before calling
+ * mm_take_all_locks(). The caller isn't allowed to release the
+ * mmap_sem until mm_drop_all_locks() returns.
+ *
+ * mmap_sem in write mode is required in order to block all operations
+ * that could modify pagetables and free pages without need of
+ * altering the vma layout (for example populate_range() with
+ * nonlinear vmas). It's also needed in write mode to avoid new
+ * anon_vmas to be associated with existing vmas.
+ *
+ * A single task can't take more than one mm_take_all_locks() in a row
+ * or it would deadlock.
+ *
+ * The LSB in anon_vma->head.next and the AS_MM_ALL_LOCKS bitflag in
+ * mapping->flags avoid to take the same lock twice, if more than one
+ * vma in this mm is backed by the same anon_vma or address_space.
+ *
+ * We can take all the locks in random order because the VM code
+ * taking i_mmap_lock or anon_vma->lock outside the mmap_sem never
+ * takes more than one of them in a row. Secondly we're protected
+ * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
+ *
+ * mm_take_all_locks() and mm_drop_all_locks are expensive operations
+ * that may have to take thousand of locks.
+ *
+ * mm_take_all_locks() can fail if it's interrupted by signals.
+ */
+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));
+
+ mutex_lock(&mm_all_locks_mutex);
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (signal_pending(current))
+ goto out_unlock;
+ if (vma->vm_file && vma->vm_file->f_mapping)
+ vm_lock_mapping(mm, vma->vm_file->f_mapping);
+ }
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (signal_pending(current))
+ goto out_unlock;
+ if (vma->anon_vma)
+ list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+ vm_lock_anon_vma(mm, avc->anon_vma);
+ }
+
+ ret = 0;
+
+out_unlock:
+ if (ret)
+ mm_drop_all_locks(mm);
+
+ return ret;
+}
+
+static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
+{
+ if (test_bit(0, (unsigned long *) &anon_vma->head.next)) {
+ /*
+ * The LSB of head.next can't change to 0 from under
+ * us because we hold the mm_all_locks_mutex.
+ *
+ * We must however clear the bitflag before unlocking
+ * the vma so the users using the anon_vma->head will
+ * never see our bitflag.
+ *
+ * No need of atomic instructions here, head.next
+ * can't change from under us until we release the
+ * anon_vma->lock.
+ */
+ if (!__test_and_clear_bit(0, (unsigned long *)
+ &anon_vma->head.next))
+ BUG();
+ spin_unlock(&anon_vma->lock);
+ }
+}
+
+static void vm_unlock_mapping(struct address_space *mapping)
+{
+ if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
+ /*
+ * AS_MM_ALL_LOCKS can't change to 0 from under us
+ * because we hold the mm_all_locks_mutex.
+ */
+ spin_unlock(&mapping->i_mmap_lock);
+ if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
+ &mapping->flags))
+ BUG();
+ }
+}
+
+/*
+ * The mmap_sem cannot be released by the caller until
+ * mm_drop_all_locks() returns.
+ */
+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)
+ 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);
+ }
+
+ mutex_unlock(&mm_all_locks_mutex);
+}
+
+/*
+ * initialise the VMA slab
+ */
+void __init mmap_init(void)
+{
+ int ret;
+
+ ret = percpu_counter_init(&vm_committed_as, 0);
+ VM_BUG_ON(ret);
+}