Merge branch 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull overlayfs updates from Miklos Szeredi:
 "Because copy up can take a long time, serialized copy ups could be a
  big performance bottleneck. This update allows concurrent copy up of
  regular files eliminating this potential problem.

  There are also minor fixes"

* 'overlayfs-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ovl: drop CAP_SYS_RESOURCE from saved mounter's credentials
  ovl: properly implement sync_filesystem()
  ovl: concurrent copy up of regular files
  ovl: introduce copy up waitqueue
  ovl: copy up regular file using O_TMPFILE
  ovl: rearrange code in ovl_copy_up_locked()
  ovl: check if upperdir fs supports O_TMPFILE

5 files changed, 148 insertions, 27 deletions

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 2d49850..906ea6c 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -21,6 +21,7 @@
 #include <linux/fdtable.h>
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
+#include "ovl_entry.h"
 
 #define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
 
@@ -233,12 +234,14 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 
 static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 			      struct dentry *dentry, struct path *lowerpath,
-			      struct kstat *stat, const char *link)
+			      struct kstat *stat, const char *link,
+			      struct kstat *pstat, bool tmpfile)
 {
 	struct inode *wdir = workdir->d_inode;
 	struct inode *udir = upperdir->d_inode;
 	struct dentry *newdentry = NULL;
 	struct dentry *upper = NULL;
+	struct dentry *temp = NULL;
 	int err;
 	const struct cred *old_creds = NULL;
 	struct cred *new_creds = NULL;
@@ -249,25 +252,30 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 		.link = link
 	};
 
-	newdentry = ovl_lookup_temp(workdir, dentry);
-	err = PTR_ERR(newdentry);
-	if (IS_ERR(newdentry))
-		goto out;
-
 	upper = lookup_one_len(dentry->d_name.name, upperdir,
 			       dentry->d_name.len);
 	err = PTR_ERR(upper);
 	if (IS_ERR(upper))
-		goto out1;
+		goto out;
 
 	err = security_inode_copy_up(dentry, &new_creds);
 	if (err < 0)
-		goto out2;
+		goto out1;
 
 	if (new_creds)
 		old_creds = override_creds(new_creds);
 
-	err = ovl_create_real(wdir, newdentry, &cattr, NULL, true);
+	if (tmpfile)
+		temp = ovl_do_tmpfile(upperdir, stat->mode);
+	else
+		temp = ovl_lookup_temp(workdir, dentry);
+	err = PTR_ERR(temp);
+	if (IS_ERR(temp))
+		goto out1;
+
+	err = 0;
+	if (!tmpfile)
+		err = ovl_create_real(wdir, temp, &cattr, NULL, true);
 
 	if (new_creds) {
 		revert_creds(old_creds);
@@ -282,39 +290,55 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 
 		ovl_path_upper(dentry, &upperpath);
 		BUG_ON(upperpath.dentry != NULL);
-		upperpath.dentry = newdentry;
+		upperpath.dentry = temp;
+
+		if (tmpfile) {
+			inode_unlock(udir);
+			err = ovl_copy_up_data(lowerpath, &upperpath,
+					       stat->size);
+			inode_lock_nested(udir, I_MUTEX_PARENT);
+		} else {
+			err = ovl_copy_up_data(lowerpath, &upperpath,
+					       stat->size);
+		}
 
-		err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
 		if (err)
 			goto out_cleanup;
 	}
 
-	err = ovl_copy_xattr(lowerpath->dentry, newdentry);
+	err = ovl_copy_xattr(lowerpath->dentry, temp);
 	if (err)
 		goto out_cleanup;
 
-	inode_lock(newdentry->d_inode);
-	err = ovl_set_attr(newdentry, stat);
-	inode_unlock(newdentry->d_inode);
+	inode_lock(temp->d_inode);
+	err = ovl_set_attr(temp, stat);
+	inode_unlock(temp->d_inode);
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+	if (tmpfile)
+		err = ovl_do_link(temp, udir, upper, true);
+	else
+		err = ovl_do_rename(wdir, temp, udir, upper, 0);
 	if (err)
 		goto out_cleanup;
 
+	newdentry = dget(tmpfile ? upper : temp);
 	ovl_dentry_update(dentry, newdentry);
 	ovl_inode_update(d_inode(dentry), d_inode(newdentry));
-	newdentry = NULL;
+
+	/* Restore timestamps on parent (best effort) */
+	ovl_set_timestamps(upperdir, pstat);
 out2:
-	dput(upper);
+	dput(temp);
 out1:
-	dput(newdentry);
+	dput(upper);
 out:
 	return err;
 
 out_cleanup:
-	ovl_cleanup(wdir, newdentry);
+	if (!tmpfile)
+		ovl_cleanup(wdir, temp);
 	goto out2;
 }
 
@@ -338,6 +362,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	struct dentry *lowerdentry = lowerpath->dentry;
 	struct dentry *upperdir;
 	const char *link = NULL;
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
 
 	if (WARN_ON(!workdir))
 		return -EROFS;
@@ -358,6 +383,25 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 			return PTR_ERR(link);
 	}
 
+	/* Should we copyup with O_TMPFILE or with workdir? */
+	if (S_ISREG(stat->mode) && ofs->tmpfile) {
+		err = ovl_copy_up_start(dentry);
+		/* err < 0: interrupted, err > 0: raced with another copy-up */
+		if (unlikely(err)) {
+			pr_debug("ovl_copy_up_start(%pd2) = %i\n", dentry, err);
+			if (err > 0)
+				err = 0;
+			goto out_done;
+		}
+
+		inode_lock_nested(upperdir->d_inode, I_MUTEX_PARENT);
+		err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
+					 stat, link, &pstat, true);
+		inode_unlock(upperdir->d_inode);
+		ovl_copy_up_end(dentry);
+		goto out_done;
+	}
+
 	err = -EIO;
 	if (lock_rename(workdir, upperdir) != NULL) {
 		pr_err("overlayfs: failed to lock workdir+upperdir\n");
@@ -370,13 +414,10 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	}
 
 	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-				 stat, link);
-	if (!err) {
-		/* Restore timestamps on parent (best effort) */
-		ovl_set_timestamps(upperdir, &pstat);
-	}
+				 stat, link, &pstat, false);
 out_unlock:
 	unlock_rename(workdir, upperdir);
+out_done:
 	do_delayed_call(&done);
 
 	return err;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8af450b..741dc0b 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -127,6 +127,15 @@ static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
 	return err;
 }
 
+static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode)
+{
+	struct dentry *ret = vfs_tmpfile(dentry, mode, 0);
+	int err = IS_ERR(ret) ? PTR_ERR(ret) : 0;
+
+	pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return ret;
+}
+
 static inline struct inode *ovl_inode_real(struct inode *inode, bool *is_upper)
 {
 	unsigned long x = (unsigned long) READ_ONCE(inode->i_private);
@@ -169,6 +178,8 @@ void ovl_dentry_version_inc(struct dentry *dentry);
 u64 ovl_dentry_version_get(struct dentry *dentry);
 bool ovl_is_whiteout(struct dentry *dentry);
 struct file *ovl_path_open(struct path *path, int flags);
+int ovl_copy_up_start(struct dentry *dentry);
+void ovl_copy_up_end(struct dentry *dentry);
 
 /* namei.c */
 int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index d14bca1..59614fa 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -27,6 +27,8 @@ struct ovl_fs {
 	struct ovl_config config;
 	/* creds of process who forced instantiation of super block */
 	const struct cred *creator_cred;
+	bool tmpfile;
+	wait_queue_head_t copyup_wq;
 };
 
 /* private information held for every overlayfs dentry */
@@ -38,6 +40,7 @@ struct ovl_entry {
 			u64 version;
 			const char *redirect;
 			bool opaque;
+			bool copying;
 		};
 		struct rcu_head rcu;
 	};
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 9aa37c2..c9e70d3 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -161,6 +161,25 @@ static void ovl_put_super(struct super_block *sb)
 	kfree(ufs);
 }
 
+static int ovl_sync_fs(struct super_block *sb, int wait)
+{
+	struct ovl_fs *ufs = sb->s_fs_info;
+	struct super_block *upper_sb;
+	int ret;
+
+	if (!ufs->upper_mnt)
+		return 0;
+	upper_sb = ufs->upper_mnt->mnt_sb;
+	if (!upper_sb->s_op->sync_fs)
+		return 0;
+
+	/* real inodes have already been synced by sync_filesystem(ovl_sb) */
+	down_read(&upper_sb->s_umount);
+	ret = upper_sb->s_op->sync_fs(upper_sb, wait);
+	up_read(&upper_sb->s_umount);
+	return ret;
+}
+
 /**
  * ovl_statfs
  * @sb: The overlayfs super block
@@ -223,6 +242,7 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data)
 
 static const struct super_operations ovl_super_operations = {
 	.put_super	= ovl_put_super,
+	.sync_fs	= ovl_sync_fs,
 	.statfs		= ovl_statfs,
 	.show_options	= ovl_show_options,
 	.remount_fs	= ovl_remount,
@@ -702,6 +722,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int stacklen = 0;
 	unsigned int i;
 	bool remote = false;
+	struct cred *cred;
 	int err;
 
 	err = -ENOMEM;
@@ -709,6 +730,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ufs)
 		goto out;
 
+	init_waitqueue_head(&ufs->copyup_wq);
 	ufs->config.redirect_dir = ovl_redirect_dir_def;
 	err = ovl_parse_opt((char *) data, &ufs->config);
 	if (err)
@@ -826,6 +848,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		 * creation of workdir in previous step.
 		 */
 		if (ufs->workdir) {
+			struct dentry *temp;
+
 			err = ovl_check_d_type_supported(&workpath);
 			if (err < 0)
 				goto out_put_workdir;
@@ -837,6 +861,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			 */
 			if (!err)
 				pr_warn("overlayfs: upper fs needs to support d_type.\n");
+
+			/* Check if upper/work fs supports O_TMPFILE */
+			temp = ovl_do_tmpfile(ufs->workdir, S_IFREG | 0);
+			ufs->tmpfile = !IS_ERR(temp);
+			if (ufs->tmpfile)
+				dput(temp);
+			else
+				pr_warn("overlayfs: upper fs does not support tmpfile.\n");
 		}
 	}
 
@@ -871,10 +903,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	else
 		sb->s_d_op = &ovl_dentry_operations;
 
-	ufs->creator_cred = prepare_creds();
-	if (!ufs->creator_cred)
+	ufs->creator_cred = cred = prepare_creds();
+	if (!cred)
 		goto out_put_lower_mnt;
 
+	/* Never override disk quota limits or use reserved space */
+	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
+
 	err = -ENOMEM;
 	oe = ovl_alloc_entry(numlower);
 	if (!oe)
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 9dc1c0a..1953986 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/cred.h>
 #include <linux/xattr.h>
+#include <linux/sched/signal.h>
 #include "overlayfs.h"
 #include "ovl_entry.h"
 
@@ -264,3 +265,33 @@ struct file *ovl_path_open(struct path *path, int flags)
 {
 	return dentry_open(path, flags | O_NOATIME, current_cred());
 }
+
+int ovl_copy_up_start(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+	int err;
+
+	spin_lock(&ofs->copyup_wq.lock);
+	err = wait_event_interruptible_locked(ofs->copyup_wq, !oe->copying);
+	if (!err) {
+		if (oe->__upperdentry)
+			err = 1; /* Already copied up */
+		else
+			oe->copying = true;
+	}
+	spin_unlock(&ofs->copyup_wq.lock);
+
+	return err;
+}
+
+void ovl_copy_up_end(struct dentry *dentry)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	spin_lock(&ofs->copyup_wq.lock);
+	oe->copying = false;
+	wake_up_locked(&ofs->copyup_wq);
+	spin_unlock(&ofs->copyup_wq.lock);
+}