1 files changed, 279 insertions, 74 deletions

diff --git a/fs/libfs.c b/fs/libfs.c
index c686bd9caac6..682d56345a1c 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -15,21 +15,25 @@
 #include <linux/mutex.h>
 #include <linux/namei.h>
 #include <linux/exportfs.h>
+#include <linux/iversion.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h> /* sync_mapping_buffers */
 #include <linux/fs_context.h>
 #include <linux/pseudo_fs.h>
 #include <linux/fsnotify.h>
+#include <linux/unicode.h>
+#include <linux/fscrypt.h>
 
 #include <linux/uaccess.h>
 
 #include "internal.h"
 
-int simple_getattr(const struct path *path, struct kstat *stat,
-		   u32 request_mask, unsigned int query_flags)
+int simple_getattr(struct user_namespace *mnt_userns, const struct path *path,
+		   struct kstat *stat, u32 request_mask,
+		   unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
-	generic_fillattr(inode, stat);
+	generic_fillattr(&init_user_ns, inode, stat);
 	stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9);
 	return 0;
 }
@@ -137,11 +141,11 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 		case 1:
 			offset += file->f_pos;
-			/* fall through */
+			fallthrough;
 		case 0:
 			if (offset >= 0)
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EINVAL;
 	}
@@ -445,16 +449,43 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry)
 }
 EXPORT_SYMBOL(simple_rmdir);
 
-int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
-		  struct inode *new_dir, struct dentry *new_dentry,
-		  unsigned int flags)
+int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
+			   struct inode *new_dir, struct dentry *new_dentry)
+{
+	bool old_is_dir = d_is_dir(old_dentry);
+	bool new_is_dir = d_is_dir(new_dentry);
+
+	if (old_dir != new_dir && old_is_dir != new_is_dir) {
+		if (old_is_dir) {
+			drop_nlink(old_dir);
+			inc_nlink(new_dir);
+		} else {
+			drop_nlink(new_dir);
+			inc_nlink(old_dir);
+		}
+	}
+	old_dir->i_ctime = old_dir->i_mtime =
+	new_dir->i_ctime = new_dir->i_mtime =
+	d_inode(old_dentry)->i_ctime =
+	d_inode(new_dentry)->i_ctime = current_time(old_dir);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(simple_rename_exchange);
+
+int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+		  struct dentry *old_dentry, struct inode *new_dir,
+		  struct dentry *new_dentry, unsigned int flags)
 {
 	struct inode *inode = d_inode(old_dentry);
 	int they_are_dirs = d_is_dir(old_dentry);
 
-	if (flags & ~RENAME_NOREPLACE)
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
 		return -EINVAL;
 
+	if (flags & RENAME_EXCHANGE)
+		return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry);
+
 	if (!simple_empty(new_dentry))
 		return -ENOTEMPTY;
 
@@ -478,6 +509,7 @@ EXPORT_SYMBOL(simple_rename);
 
 /**
  * simple_setattr - setattr for simple filesystem
+ * @mnt_userns: user namespace of the target mount
  * @dentry: dentry
  * @iattr: iattr structure
  *
@@ -490,35 +522,35 @@ EXPORT_SYMBOL(simple_rename);
  * on simple regular filesystems.  Anything that needs to change on-disk
  * or wire state on size changes needs its own setattr method.
  */
-int simple_setattr(struct dentry *dentry, struct iattr *iattr)
+int simple_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		   struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
 	int error;
 
-	error = setattr_prepare(dentry, iattr);
+	error = setattr_prepare(mnt_userns, dentry, iattr);
 	if (error)
 		return error;
 
 	if (iattr->ia_valid & ATTR_SIZE)
 		truncate_setsize(inode, iattr->ia_size);
-	setattr_copy(inode, iattr);
+	setattr_copy(mnt_userns, inode, iattr);
 	mark_inode_dirty(inode);
 	return 0;
 }
 EXPORT_SYMBOL(simple_setattr);
 
-int simple_readpage(struct file *file, struct page *page)
+static int simple_read_folio(struct file *file, struct folio *folio)
 {
-	clear_highpage(page);
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
+	folio_zero_range(folio, 0, folio_size(folio));
+	flush_dcache_folio(folio);
+	folio_mark_uptodate(folio);
+	folio_unlock(folio);
 	return 0;
 }
-EXPORT_SYMBOL(simple_readpage);
 
 int simple_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	struct page *page;
@@ -526,7 +558,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 
 	index = pos >> PAGE_SHIFT;
 
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	page = grab_cache_page_write_begin(mapping, index);
 	if (!page)
 		return -ENOMEM;
 
@@ -561,9 +593,9 @@ EXPORT_SYMBOL(simple_write_begin);
  * should extend on what's done here with a call to mark_inode_dirty() in the
  * case that i_size has changed.
  *
- * Use *ONLY* with simple_readpage()
+ * Use *ONLY* with simple_read_folio()
  */
-int simple_write_end(struct file *file, struct address_space *mapping,
+static int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
@@ -592,7 +624,17 @@ int simple_write_end(struct file *file, struct address_space *mapping,
 
 	return copied;
 }
-EXPORT_SYMBOL(simple_write_end);
+
+/*
+ * Provides ramfs-style behavior: data in the pagecache, but no writeback.
+ */
+const struct address_space_operations ram_aops = {
+	.read_folio	= simple_read_folio,
+	.write_begin	= simple_write_begin,
+	.write_end	= simple_write_end,
+	.dirty_folio	= noop_dirty_folio,
+};
+EXPORT_SYMBOL(ram_aops);
 
 /*
  * the inodes created here are not hashed. If you use iunique to generate
@@ -891,7 +933,7 @@ int simple_attr_open(struct inode *inode, struct file *file,
 {
 	struct simple_attr *attr;
 
-	attr = kmalloc(sizeof(*attr), GFP_KERNEL);
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
 	if (!attr)
 		return -ENOMEM;
 
@@ -931,9 +973,11 @@ ssize_t simple_attr_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 
-	if (*ppos) {		/* continued read */
+	if (*ppos && attr->get_buf[0]) {
+		/* continued read */
 		size = strlen(attr->get_buf);
-	} else {		/* first read */
+	} else {
+		/* first read */
 		u64 val;
 		ret = attr->get(attr->data, &val);
 		if (ret)
@@ -955,7 +999,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf,
 			  size_t len, loff_t *ppos)
 {
 	struct simple_attr *attr;
-	u64 val;
+	unsigned long long val;
 	size_t size;
 	ssize_t ret;
 
@@ -973,7 +1017,9 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf,
 		goto out;
 
 	attr->set_buf[size] = '\0';
-	val = simple_strtoll(attr->set_buf, NULL, 0);
+	ret = kstrtoull(attr->set_buf, 0, &val);
+	if (ret)
+		goto out;
 	ret = attr->set(attr->data, val);
 	if (ret == 0)
 		ret = len; /* on success, claim we got the whole input */
@@ -1111,7 +1157,7 @@ int generic_file_fsync(struct file *file, loff_t start, loff_t end,
 	err = __generic_file_fsync(file, start, end, datasync);
 	if (err)
 		return err;
-	return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+	return blkdev_issue_flush(inode->i_sb->s_bdev);
 }
 EXPORT_SYMBOL(generic_file_fsync);
 
@@ -1153,33 +1199,6 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 }
 EXPORT_SYMBOL(noop_fsync);
 
-int noop_set_page_dirty(struct page *page)
-{
-	/*
-	 * Unlike __set_page_dirty_no_writeback that handles dirty page
-	 * tracking in the page object, dax does all dirty tracking in
-	 * the inode address_space in response to mkwrite faults. In the
-	 * dax case we only need to worry about potentially dirty CPU
-	 * caches, not dirty page cache pages to write back.
-	 *
-	 * This callback is defined to prevent fallback to
-	 * __set_page_dirty_buffers() in set_page_dirty().
-	 */
-	return 0;
-}
-EXPORT_SYMBOL_GPL(noop_set_page_dirty);
-
-void noop_invalidatepage(struct page *page, unsigned int offset,
-		unsigned int length)
-{
-	/*
-	 * There is no page cache to invalidate in the dax case, however
-	 * we need this callback defined to prevent falling back to
-	 * block_invalidatepage() in do_invalidatepage().
-	 */
-}
-EXPORT_SYMBOL_GPL(noop_invalidatepage);
-
 ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	/*
@@ -1199,24 +1218,10 @@ void kfree_link(void *p)
 }
 EXPORT_SYMBOL(kfree_link);
 
-/*
- * nop .set_page_dirty method so that people can use .page_mkwrite on
- * anon inodes.
- */
-static int anon_set_page_dirty(struct page *page)
-{
-	return 0;
-};
-
-/*
- * A single inode exists for all anon_inode files. Contrary to pipes,
- * anon_inode inodes have no associated per-instance data, so we need
- * only allocate one of them.
- */
 struct inode *alloc_anon_inode(struct super_block *s)
 {
 	static const struct address_space_operations anon_aops = {
-		.set_page_dirty = anon_set_page_dirty,
+		.dirty_folio	= noop_dirty_folio,
 	};
 	struct inode *inode = new_inode_pseudo(s);
 
@@ -1294,15 +1299,17 @@ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry,
 	return ERR_PTR(-ENOENT);
 }
 
-static int empty_dir_getattr(const struct path *path, struct kstat *stat,
+static int empty_dir_getattr(struct user_namespace *mnt_userns,
+			     const struct path *path, struct kstat *stat,
 			     u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
-	generic_fillattr(inode, stat);
+	generic_fillattr(&init_user_ns, inode, stat);
 	return 0;
 }
 
-static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr)
+static int empty_dir_setattr(struct user_namespace *mnt_userns,
+			     struct dentry *dentry, struct iattr *attr)
 {
 	return -EPERM;
 }
@@ -1361,3 +1368,201 @@ bool is_empty_dir_inode(struct inode *inode)
 	return (inode->i_fop == &empty_dir_operations) &&
 		(inode->i_op == &empty_dir_inode_operations);
 }
+
+#if IS_ENABLED(CONFIG_UNICODE)
+/*
+ * Determine if the name of a dentry should be casefolded.
+ *
+ * Return: if names will need casefolding
+ */
+static bool needs_casefold(const struct inode *dir)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding;
+}
+
+/**
+ * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
+ * @dentry:	dentry whose name we are checking against
+ * @len:	len of name of dentry
+ * @str:	str pointer to name of dentry
+ * @name:	Name to compare against
+ *
+ * Return: 0 if names match, 1 if mismatch, or -ERRNO
+ */
+static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+				const char *str, const struct qstr *name)
+{
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *dir = READ_ONCE(parent->d_inode);
+	const struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	struct qstr qstr = QSTR_INIT(str, len);
+	char strbuf[DNAME_INLINE_LEN];
+	int ret;
+
+	if (!dir || !needs_casefold(dir))
+		goto fallback;
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+	ret = utf8_strncasecmp(um, name, &qstr);
+	if (ret >= 0)
+		return ret;
+
+	if (sb_has_strict_encoding(sb))
+		return -EINVAL;
+fallback:
+	if (len != name->len)
+		return 1;
+	return !!memcmp(str, name->name, len);
+}
+
+/**
+ * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
+ * @dentry:	dentry of the parent directory
+ * @str:	qstr of name whose hash we should fill in
+ *
+ * Return: 0 if hash was successful or unchanged, and -EINVAL on error
+ */
+static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct inode *dir = READ_ONCE(dentry->d_inode);
+	struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	int ret = 0;
+
+	if (!dir || !needs_casefold(dir))
+		return 0;
+
+	ret = utf8_casefold_hash(um, dentry, str);
+	if (ret < 0 && sb_has_strict_encoding(sb))
+		return -EINVAL;
+	return 0;
+}
+
+static const struct dentry_operations generic_ci_dentry_ops = {
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+};
+#endif
+
+#ifdef CONFIG_FS_ENCRYPTION
+static const struct dentry_operations generic_encrypted_dentry_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
+#endif
+
+#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
+static const struct dentry_operations generic_encrypted_ci_dentry_ops = {
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+	.d_revalidate = fscrypt_d_revalidate,
+};
+#endif
+
+/**
+ * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry
+ * @dentry:	dentry to set ops on
+ *
+ * Casefolded directories need d_hash and d_compare set, so that the dentries
+ * contained in them are handled case-insensitively.  Note that these operations
+ * are needed on the parent directory rather than on the dentries in it, and
+ * while the casefolding flag can be toggled on and off on an empty directory,
+ * dentry_operations can't be changed later.  As a result, if the filesystem has
+ * casefolding support enabled at all, we have to give all dentries the
+ * casefolding operations even if their inode doesn't have the casefolding flag
+ * currently (and thus the casefolding ops would be no-ops for now).
+ *
+ * Encryption works differently in that the only dentry operation it needs is
+ * d_revalidate, which it only needs on dentries that have the no-key name flag.
+ * The no-key flag can't be set "later", so we don't have to worry about that.
+ *
+ * Finally, to maximize compatibility with overlayfs (which isn't compatible
+ * with certain dentry operations) and to avoid taking an unnecessary
+ * performance hit, we use custom dentry_operations for each possible
+ * combination rather than always installing all operations.
+ */
+void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
+{
+#ifdef CONFIG_FS_ENCRYPTION
+	bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME;
+#endif
+#if IS_ENABLED(CONFIG_UNICODE)
+	bool needs_ci_ops = dentry->d_sb->s_encoding;
+#endif
+#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
+	if (needs_encrypt_ops && needs_ci_ops) {
+		d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops);
+		return;
+	}
+#endif
+#ifdef CONFIG_FS_ENCRYPTION
+	if (needs_encrypt_ops) {
+		d_set_d_op(dentry, &generic_encrypted_dentry_ops);
+		return;
+	}
+#endif
+#if IS_ENABLED(CONFIG_UNICODE)
+	if (needs_ci_ops) {
+		d_set_d_op(dentry, &generic_ci_dentry_ops);
+		return;
+	}
+#endif
+}
+EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops);
+
+/**
+ * inode_maybe_inc_iversion - increments i_version
+ * @inode: inode with the i_version that should be updated
+ * @force: increment the counter even if it's not necessary?
+ *
+ * Every time the inode is modified, the i_version field must be seen to have
+ * changed by any observer.
+ *
+ * If "force" is set or the QUERIED flag is set, then ensure that we increment
+ * the value, and clear the queried flag.
+ *
+ * In the common case where neither is set, then we can return "false" without
+ * updating i_version.
+ *
+ * If this function returns false, and no other metadata has changed, then we
+ * can avoid logging the metadata.
+ */
+bool inode_maybe_inc_iversion(struct inode *inode, bool force)
+{
+	u64 cur, new;
+
+	/*
+	 * The i_version field is not strictly ordered with any other inode
+	 * information, but the legacy inode_inc_iversion code used a spinlock
+	 * to serialize increments.
+	 *
+	 * Here, we add full memory barriers to ensure that any de-facto
+	 * ordering with other info is preserved.
+	 *
+	 * This barrier pairs with the barrier in inode_query_iversion()
+	 */
+	smp_mb();
+	cur = inode_peek_iversion_raw(inode);
+	do {
+		/* If flag is clear then we needn't do anything */
+		if (!force && !(cur & I_VERSION_QUERIED))
+			return false;
+
+		/* Since lowest bit is flag, add 2 to avoid it */
+		new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT;
+	} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
+	return true;
+}
+EXPORT_SYMBOL(inode_maybe_inc_iversion);