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

Pull VFS fixes from Al Viro:
 "A bunch of assorted fixes, most of them followups to overlayfs merge"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  ovl: initialize ->is_cursor
  Return short read or 0 at end of a raw device, not EIO
  isofs: don't bother with ->d_op for normal case
  isofs_cmp(): we'll never see a dentry for . or ..
  overlayfs: fix lockdep misannotation
  ovl: fix check for cursor
  overlayfs: barriers for opening upper-layer directory
  rcu: Provide counterpart to rcu_dereference() for non-RCU situations
  staging: android: logger: Fix log corruption regression

9 files changed, 50 insertions, 58 deletions

diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index 0102dc788608..a24891b97547 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -285,7 +285,7 @@ static long raw_ctl_compat_ioctl(struct file *file, unsigned int cmd,
 
 static const struct file_operations raw_fops = {
 	.read		= new_sync_read,
-	.read_iter	= generic_file_read_iter,
+	.read_iter	= blkdev_read_iter,
 	.write		= new_sync_write,
 	.write_iter	= blkdev_write_iter,
 	.fsync		= blkdev_fsync,
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
index 28b93d39a94e..a673ffa34aa3 100644
--- a/drivers/staging/android/logger.c
+++ b/drivers/staging/android/logger.c
@@ -420,7 +420,7 @@ static ssize_t logger_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct logger_log *log = file_get_log(iocb->ki_filp);
 	struct logger_entry header;
 	struct timespec now;
-	size_t len, count;
+	size_t len, count, w_off;
 
 	count = min_t(size_t, iocb->ki_nbytes, LOGGER_ENTRY_MAX_PAYLOAD);
 
@@ -452,11 +452,14 @@ static ssize_t logger_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	memcpy(log->buffer + log->w_off, &header, len);
 	memcpy(log->buffer, (char *)&header + len, sizeof(header) - len);
 
-	len = min(count, log->size - log->w_off);
+	/* Work with a copy until we are ready to commit the whole entry */
+	w_off =  logger_offset(log, log->w_off + sizeof(struct logger_entry));
 
-	if (copy_from_iter(log->buffer + log->w_off, len, from) != len) {
+	len = min(count, log->size - w_off);
+
+	if (copy_from_iter(log->buffer + w_off, len, from) != len) {
 		/*
-		 * Note that by not updating w_off, this abandons the
+		 * Note that by not updating log->w_off, this abandons the
 		 * portion of the new entry that *was* successfully
 		 * copied, just above.  This is intentional to avoid
 		 * message corruption from missing fragments.
@@ -470,7 +473,7 @@ static ssize_t logger_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		return -EFAULT;
 	}
 
-	log->w_off = logger_offset(log, log->w_off + count);
+	log->w_off = logger_offset(log, w_off + count);
 	mutex_unlock(&log->mutex);
 
 	/* wake up any blocked readers */
diff --git a/fs/block_dev.c b/fs/block_dev.c
index cc9d4114cda0..1d9c9f3754f8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1585,7 +1585,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 }
 EXPORT_SYMBOL_GPL(blkdev_write_iter);
 
-static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *bd_inode = file->f_mapping->host;
@@ -1599,6 +1599,7 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	iov_iter_truncate(to, size);
 	return generic_file_read_iter(iocb, to);
 }
+EXPORT_SYMBOL_GPL(blkdev_read_iter);
 
 /*
  * Try to release a page associated with block device when the system
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 881b3bd0143f..fe839b915116 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -29,13 +29,9 @@
 #define BEQUIET
 
 static int isofs_hashi(const struct dentry *parent, struct qstr *qstr);
-static int isofs_hash(const struct dentry *parent, struct qstr *qstr);
 static int isofs_dentry_cmpi(const struct dentry *parent,
 		const struct dentry *dentry,
 		unsigned int len, const char *str, const struct qstr *name);
-static int isofs_dentry_cmp(const struct dentry *parent,
-		const struct dentry *dentry,
-		unsigned int len, const char *str, const struct qstr *name);
 
 #ifdef CONFIG_JOLIET
 static int isofs_hashi_ms(const struct dentry *parent, struct qstr *qstr);
@@ -135,10 +131,6 @@ static const struct super_operations isofs_sops = {
 
 static const struct dentry_operations isofs_dentry_ops[] = {
 	{
-		.d_hash		= isofs_hash,
-		.d_compare	= isofs_dentry_cmp,
-	},
-	{
 		.d_hash		= isofs_hashi,
 		.d_compare	= isofs_dentry_cmpi,
 	},
@@ -258,25 +250,12 @@ static int isofs_dentry_cmp_common(
 }
 
 static int
-isofs_hash(const struct dentry *dentry, struct qstr *qstr)
-{
-	return isofs_hash_common(qstr, 0);
-}
-
-static int
 isofs_hashi(const struct dentry *dentry, struct qstr *qstr)
 {
 	return isofs_hashi_common(qstr, 0);
 }
 
 static int
-isofs_dentry_cmp(const struct dentry *parent, const struct dentry *dentry,
-		unsigned int len, const char *str, const struct qstr *name)
-{
-	return isofs_dentry_cmp_common(len, str, name, 0, 0);
-}
-
-static int
 isofs_dentry_cmpi(const struct dentry *parent, const struct dentry *dentry,
 		unsigned int len, const char *str, const struct qstr *name)
 {
@@ -930,7 +909,8 @@ root_found:
 	if (opt.check == 'r')
 		table++;
 
-	s->s_d_op = &isofs_dentry_ops[table];
+	if (table)
+		s->s_d_op = &isofs_dentry_ops[table - 1];
 
 	/* get the root dentry */
 	s->s_root = d_make_root(inode);
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index 95295640d9c8..7b543e6b6526 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -18,25 +18,10 @@ static int
 isofs_cmp(struct dentry *dentry, const char *compare, int dlen)
 {
 	struct qstr qstr;
-
-	if (!compare)
-		return 1;
-
-	/* check special "." and ".." files */
-	if (dlen == 1) {
-		/* "." */
-		if (compare[0] == 0) {
-			if (!dentry->d_name.len)
-				return 0;
-			compare = ".";
-		} else if (compare[0] == 1) {
-			compare = "..";
-			dlen = 2;
-		}
-	}
-
 	qstr.name = compare;
 	qstr.len = dlen;
+	if (likely(!dentry->d_op))
+		return dentry->d_name.len != dlen || memcmp(dentry->d_name.name, compare, dlen);
 	return dentry->d_op->d_compare(NULL, NULL, dentry->d_name.len, dentry->d_name.name, &qstr);
 }
 
@@ -146,7 +131,8 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry,
 				(!(de->flags[-sbi->s_high_sierra] & 1))) &&
 			(sbi->s_showassoc ||
 				(!(de->flags[-sbi->s_high_sierra] & 4)))) {
-			match = (isofs_cmp(dentry, dpnt, dlen) == 0);
+			if (dpnt && (dlen > 1 || dpnt[0] > 1))
+				match = (isofs_cmp(dentry, dpnt, dlen) == 0);
 		}
 		if (match) {
 			isofs_normalize_block_and_offset(de,
diff --git a/fs/namei.c b/fs/namei.c
index 78512898d3ba..db5fe86319e6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2497,7 +2497,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 	}
 
 	mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
+	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2);
 	return NULL;
 }
 EXPORT_SYMBOL(lock_rename);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 910553f37aca..4e9d7c1fea52 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -21,9 +21,10 @@ struct ovl_cache_entry {
 	unsigned int len;
 	unsigned int type;
 	u64 ino;
-	bool is_whiteout;
 	struct list_head l_node;
 	struct rb_node node;
+	bool is_whiteout;
+	bool is_cursor;
 	char name[];
 };
 
@@ -92,6 +93,7 @@ static struct ovl_cache_entry *ovl_cache_entry_new(const char *name, int len,
 		p->type = d_type;
 		p->ino = ino;
 		p->is_whiteout = false;
+		p->is_cursor = false;
 	}
 
 	return p;
@@ -251,7 +253,7 @@ static int ovl_dir_mark_whiteouts(struct dentry *dir,
 
 	mutex_lock(&dir->d_inode->i_mutex);
 	list_for_each_entry(p, rdd->list, l_node) {
-		if (!p->name)
+		if (p->is_cursor)
 			continue;
 
 		if (p->type != DT_CHR)
@@ -307,7 +309,6 @@ static inline int ovl_dir_read_merged(struct path *upperpath,
 	}
 out:
 	return err;
-
 }
 
 static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
@@ -316,7 +317,7 @@ static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
 	loff_t off = 0;
 
 	list_for_each_entry(p, &od->cache->entries, l_node) {
-		if (!p->name)
+		if (p->is_cursor)
 			continue;
 		if (off >= pos)
 			break;
@@ -389,7 +390,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 
 		p = list_entry(od->cursor.l_node.next, struct ovl_cache_entry, l_node);
 		/* Skip cursors */
-		if (p->name) {
+		if (!p->is_cursor) {
 			if (!p->is_whiteout) {
 				if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
 					break;
@@ -454,12 +455,13 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 	if (!od->is_upper && ovl_path_type(dentry) == OVL_PATH_MERGE) {
 		struct inode *inode = file_inode(file);
 
-		realfile = od->upperfile;
+		realfile =lockless_dereference(od->upperfile);
 		if (!realfile) {
 			struct path upperpath;
 
 			ovl_path_upper(dentry, &upperpath);
 			realfile = ovl_path_open(&upperpath, O_RDONLY);
+			smp_mb__before_spinlock();
 			mutex_lock(&inode->i_mutex);
 			if (!od->upperfile) {
 				if (IS_ERR(realfile)) {
@@ -518,6 +520,7 @@ static int ovl_dir_open(struct inode *inode, struct file *file)
 	od->realfile = realfile;
 	od->is_real = (type != OVL_PATH_MERGE);
 	od->is_upper = (type != OVL_PATH_LOWER);
+	od->cursor.is_cursor = true;
 	file->private_data = od;
 
 	return 0;
@@ -569,7 +572,7 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
 {
 	struct ovl_cache_entry *p;
 
-	mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_PARENT);
+	mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD);
 	list_for_each_entry(p, list, l_node) {
 		struct dentry *dentry;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4e41a4a331bb..9ab779e8a63c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -639,11 +639,13 @@ static inline int inode_unhashed(struct inode *inode)
  * 2: child/target
  * 3: xattr
  * 4: second non-directory
- * The last is for certain operations (such as rename) which lock two
+ * 5: second parent (when locking independent directories in rename)
+ *
+ * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
  * non-directories at once.
  *
  * The locking order between these classes is
- * parent -> child -> normal -> xattr -> second non-directory
+ * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
  */
 enum inode_i_mutex_lock_class
 {
@@ -651,7 +653,8 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_PARENT,
 	I_MUTEX_CHILD,
 	I_MUTEX_XATTR,
-	I_MUTEX_NONDIR2
+	I_MUTEX_NONDIR2,
+	I_MUTEX_PARENT2,
 };
 
 void lock_two_nondirectories(struct inode *, struct inode*);
@@ -2466,6 +2469,7 @@ extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 
 /* fs/block_dev.c */
+extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
 extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
 extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
 			int datasync);
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a4a819ffb2d1..53ff1a752d7e 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -617,6 +617,21 @@ static inline void rcu_preempt_sleep_check(void)
 #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
 
 /**
+ * lockless_dereference() - safely load a pointer for later dereference
+ * @p: The pointer to load
+ *
+ * Similar to rcu_dereference(), but for situations where the pointed-to
+ * object's lifetime is managed by something other than RCU.  That
+ * "something other" might be reference counting or simple immortality.
+ */
+#define lockless_dereference(p) \
+({ \
+	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
+	(_________p1); \
+})
+
+/**
  * rcu_assign_pointer() - assign to RCU-protected pointer
  * @p: pointer to assign to
  * @v: value to assign (publish)