#define SHORT_SYMLINK_LEN 128
/*
- * shmem_fallocate and shmem_writepage communicate via inode->i_private
- * (with i_mutex making sure that it has only one user at a time):
- * we would prefer not to enlarge the shmem inode just for that.
+ * shmem_fallocate communicates with shmem_fault or shmem_writepage via
+ * inode->i_private (with i_mutex making sure that it has only one user at
+ * a time): we would prefer not to enlarge the shmem inode just for that.
*/
struct shmem_falloc {
+ wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
pgoff_t start; /* start of range currently being fallocated */
pgoff_t next; /* the next page offset to be fallocated */
pgoff_t nr_falloced; /* how many new pages have been fallocated */
return;
index = start;
- for ( ; ; ) {
+ while (index < end) {
cond_resched();
pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr) {
- if (index == start || unfalloc)
+ /* If all gone or hole-punch or unfalloc, we're done */
+ if (index == start || end != -1)
break;
+ /* But if truncating, restart to make sure all gone */
index = start;
continue;
}
- if ((index == start || unfalloc) && indices[0] >= end) {
- shmem_deswap_pagevec(&pvec);
- pagevec_release(&pvec);
- break;
- }
mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
if (radix_tree_exceptional_entry(page)) {
if (unfalloc)
continue;
- nr_swaps_freed += !shmem_free_swap(mapping,
- index, page);
+ if (shmem_free_swap(mapping, index, page)) {
+ /* Swap was replaced by page: retry */
+ index--;
+ break;
+ }
+ nr_swaps_freed++;
continue;
}
if (page->mapping == mapping) {
VM_BUG_ON(PageWriteback(page));
truncate_inode_page(mapping, page);
+ } else {
+ /* Page was replaced by swap: retry */
+ unlock_page(page);
+ index--;
+ break;
}
}
unlock_page(page);
spin_lock(&inode->i_lock);
shmem_falloc = inode->i_private;
if (shmem_falloc &&
+ !shmem_falloc->waitq &&
index >= shmem_falloc->start &&
index < shmem_falloc->next)
shmem_falloc->nr_unswapped++;
SetPageUptodate(page);
}
+#ifndef CONFIG_MEMCG
swap = get_swap_page();
+#else
+ swap = get_swap_page_by_memcg(page);
+#endif
if (!swap.val)
goto redirty;
int error;
int ret = VM_FAULT_LOCKED;
+ /*
+ * Trinity finds that probing a hole which tmpfs is punching can
+ * prevent the hole-punch from ever completing: which in turn
+ * locks writers out with its hold on i_mutex. So refrain from
+ * faulting pages into the hole while it's being punched. Although
+ * shmem_undo_range() does remove the additions, it may be unable to
+ * keep up, as each new page needs its own unmap_mapping_range() call,
+ * and the i_mmap tree grows ever slower to scan if new vmas are added.
+ *
+ * It does not matter if we sometimes reach this check just before the
+ * hole-punch begins, so that one fault then races with the punch:
+ * we just need to make racing faults a rare case.
+ *
+ * The implementation below would be much simpler if we just used a
+ * standard mutex or completion: but we cannot take i_mutex in fault,
+ * and bloating every shmem inode for this unlikely case would be sad.
+ */
+ if (unlikely(inode->i_private)) {
+ struct shmem_falloc *shmem_falloc;
+
+ spin_lock(&inode->i_lock);
+ shmem_falloc = inode->i_private;
+ if (shmem_falloc &&
+ shmem_falloc->waitq &&
+ vmf->pgoff >= shmem_falloc->start &&
+ vmf->pgoff < shmem_falloc->next) {
+ wait_queue_head_t *shmem_falloc_waitq;
+ DEFINE_WAIT(shmem_fault_wait);
+
+ ret = VM_FAULT_NOPAGE;
+ if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+ !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+ /* It's polite to up mmap_sem if we can */
+ up_read(&vma->vm_mm->mmap_sem);
+ ret = VM_FAULT_RETRY;
+ }
+
+ shmem_falloc_waitq = shmem_falloc->waitq;
+ prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock(&inode->i_lock);
+ schedule();
+
+ /*
+ * shmem_falloc_waitq points into the shmem_fallocate()
+ * stack of the hole-punching task: shmem_falloc_waitq
+ * is usually invalid by the time we reach here, but
+ * finish_wait() does not dereference it in that case;
+ * though i_lock needed lest racing with wake_up_all().
+ */
+ spin_lock(&inode->i_lock);
+ finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
+ spin_unlock(&inode->i_lock);
+ return ret;
+ }
+ spin_unlock(&inode->i_lock);
+ }
+
error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
}
static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir,
- umode_t mode, dev_t dev, unsigned long flags)
+ umode_t mode, dev_t dev, unsigned long flags, int atomic_copy)
{
struct inode *inode;
struct shmem_inode_info *info;
inode = new_inode(sb);
if (inode) {
+ /* We don't let shmem use __GFP_SLOWHIGHMEM */
+ mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER_MOVABLE);
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
info->flags = flags & VM_NORESERVE;
+ if (atomic_copy)
+ inode->i_flags |= S_ATOMIC_COPY;
INIT_LIST_HEAD(&info->swaplist);
simple_xattrs_init(&info->xattrs);
cache_no_acl(inode);
pgoff_t start, index, end;
int error;
- mutex_lock(&inode->i_mutex);
+ //To avoid nested lock
+ if (!mutex_trylock(&inode->i_mutex))
+ return -1;
if (mode & FALLOC_FL_PUNCH_HOLE) {
struct address_space *mapping = file->f_mapping;
loff_t unmap_start = round_up(offset, PAGE_SIZE);
loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
+
+ shmem_falloc.waitq = &shmem_falloc_waitq;
+ shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+ shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
+ spin_lock(&inode->i_lock);
+ inode->i_private = &shmem_falloc;
+ spin_unlock(&inode->i_lock);
if ((u64)unmap_end > (u64)unmap_start)
unmap_mapping_range(mapping, unmap_start,
1 + unmap_end - unmap_start, 0);
shmem_truncate_range(inode, offset, offset + len - 1);
/* No need to unmap again: hole-punching leaves COWed pages */
+
+ spin_lock(&inode->i_lock);
+ inode->i_private = NULL;
+ wake_up_all(&shmem_falloc_waitq);
+ spin_unlock(&inode->i_lock);
error = 0;
goto out;
}
goto out;
}
+ shmem_falloc.waitq = NULL;
shmem_falloc.start = start;
shmem_falloc.next = start;
shmem_falloc.nr_falloced = 0;
struct inode *inode;
int error = -ENOSPC;
- inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE);
+ inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE, 0);
if (inode) {
error = security_inode_init_security(inode, dir,
&dentry->d_name,
if (new_dentry->d_inode) {
(void) shmem_unlink(new_dir, new_dentry);
- if (they_are_dirs)
+ if (they_are_dirs) {
+ drop_nlink(new_dentry->d_inode);
drop_nlink(old_dir);
+ }
} else if (they_are_dirs) {
drop_nlink(old_dir);
inc_nlink(new_dir);
if (len > PAGE_CACHE_SIZE)
return -ENAMETOOLONG;
- inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE);
+ inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE, 0);
if (!inode)
return -ENOSPC;
sb->s_flags |= MS_POSIXACL;
#endif
- inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
+ inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE, 0);
if (!inode)
goto failed;
inode->i_uid = sbinfo->uid;
#define shmem_vm_ops generic_file_vm_ops
#define shmem_file_operations ramfs_file_operations
-#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)
+#define shmem_get_inode(sb, dir, mode, dev, flags, atomic_copy) ramfs_get_inode(sb, dir, mode, dev)
#define shmem_acct_size(flags, size) 0
#define shmem_unacct_size(flags, size) do {} while (0)
/* common code */
-static char *shmem_dname(struct dentry *dentry, char *buffer, int buflen)
-{
- return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
- dentry->d_name.name);
-}
-
static struct dentry_operations anon_ops = {
- .d_dname = shmem_dname
+ .d_dname = simple_dname
};
/**
* @name: name for dentry (to be seen in /proc/<pid>/maps
* @size: size to be set for the file
* @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ * @atomic_copy: Atomically copy the area when hibernating?
*/
-struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags,
+ int atomic_copy)
{
struct file *res;
struct inode *inode;
path.mnt = mntget(shm_mnt);
res = ERR_PTR(-ENOSPC);
- inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags);
+ inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags, atomic_copy);
if (!inode)
goto put_dentry;
}
EXPORT_SYMBOL_GPL(shmem_file_setup);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = file;
+ vma->vm_ops = &shmem_vm_ops;
+}
+
/**
* shmem_zero_setup - setup a shared anonymous mapping
* @vma: the vma to be mmapped is prepared by do_mmap_pgoff
struct file *file;
loff_t size = vma->vm_end - vma->vm_start;
- file = shmem_file_setup("dev/zero", size, vma->vm_flags);
+ file = shmem_file_setup("dev/zero", size, vma->vm_flags, 0);
if (IS_ERR(file))
return PTR_ERR(file);
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = file;
- vma->vm_ops = &shmem_vm_ops;
+ shmem_set_file(vma, file);
return 0;
}