ext4: implementation of a new ioctl called EXT4_IOC_SWAP_BOOT

Add a new ioctl, EXT4_IOC_SWAP_BOOT which swaps i_blocks and
associated attributes (like i_blocks, i_size, i_flags, ...) from the
specified inode with inode EXT4_BOOT_LOADER_INO (#5). This is
typically used to store a boot loader in a secure part of the
filesystem, where it can't be changed by a normal user by accident.
The data blocks of the previous boot loader will be associated with
the given inode.

This usercode program is a simple example of the usage:

int main(int argc, char *argv[])
{
  int fd;
  int err;

  if ( argc != 2 ) {
    printf("usage: ext4-swap-boot-inode FILE-TO-SWAP\n");
    exit(1);
  }

  fd = open(argv[1], O_WRONLY);
  if ( fd < 0 ) {
    perror("open");
    exit(1);
  }

  err = ioctl(fd, EXT4_IOC_SWAP_BOOT);
  if ( err < 0 ) {
    perror("ioctl");
    exit(1);
  }

  close(fd);
  exit(0);
}

[ Modified by Theodore Ts'o to fix a number of bugs in the original code.]

Signed-off-by: Dr. Tilmann Bubeck <t.bubeck@reinform.de>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/ext4/ioctl.c

@@ -17,9 +17,201 @@
 #include <asm/uaccess.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
+#include "ext4_extents.h"
 
 #define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1)
 
+/**
+ * Swap memory between @a and @b for @len bytes.
+ *
+ * @a:          pointer to first memory area
+ * @b:          pointer to second memory area
+ * @len:        number of bytes to swap
+ *
+ */
+static void memswap(void *a, void *b, size_t len)
+{
+	unsigned char *ap, *bp;
+	unsigned char tmp;
+
+	ap = (unsigned char *)a;
+	bp = (unsigned char *)b;
+	while (len-- > 0) {
+		tmp = *ap;
+		*ap = *bp;
+		*bp = tmp;
+		ap++;
+		bp++;
+	}
+}
+
+/**
+ * Swap i_data and associated attributes between @inode1 and @inode2.
+ * This function is used for the primary swap between inode1 and inode2
+ * and also to revert this primary swap in case of errors.
+ *
+ * Therefore you have to make sure, that calling this method twice
+ * will revert all changes.
+ *
+ * @inode1:     pointer to first inode
+ * @inode2:     pointer to second inode
+ */
+static void swap_inode_data(struct inode *inode1, struct inode *inode2)
+{
+	loff_t isize;
+	struct ext4_inode_info *ei1;
+	struct ext4_inode_info *ei2;
+
+	ei1 = EXT4_I(inode1);
+	ei2 = EXT4_I(inode2);
+
+	memswap(&inode1->i_flags, &inode2->i_flags, sizeof(inode1->i_flags));
+	memswap(&inode1->i_version, &inode2->i_version,
+		  sizeof(inode1->i_version));
+	memswap(&inode1->i_blocks, &inode2->i_blocks,
+		  sizeof(inode1->i_blocks));
+	memswap(&inode1->i_bytes, &inode2->i_bytes, sizeof(inode1->i_bytes));
+	memswap(&inode1->i_atime, &inode2->i_atime, sizeof(inode1->i_atime));
+	memswap(&inode1->i_mtime, &inode2->i_mtime, sizeof(inode1->i_mtime));
+
+	memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
+	memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags));
+	memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
+	memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree));
+	memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr));
+
+	isize = i_size_read(inode1);
+	i_size_write(inode1, i_size_read(inode2));
+	i_size_write(inode2, isize);
+}
+
+/**
+ * Swap the information from the given @inode and the inode
+ * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
+ * important fields of the inodes.
+ *
+ * @sb:         the super block of the filesystem
+ * @inode:      the inode to swap with EXT4_BOOT_LOADER_INO
+ *
+ */
+static long swap_inode_boot_loader(struct super_block *sb,
+				struct inode *inode)
+{
+	handle_t *handle;
+	int err;
+	struct inode *inode_bl;
+	struct ext4_inode_info *ei;
+	struct ext4_inode_info *ei_bl;
+	struct ext4_sb_info *sbi;
+
+	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
+		err = -EINVAL;
+		goto swap_boot_out;
+	}
+
+	if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto swap_boot_out;
+	}
+
+	sbi = EXT4_SB(sb);
+	ei = EXT4_I(inode);
+
+	inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
+	if (IS_ERR(inode_bl)) {
+		err = PTR_ERR(inode_bl);
+		goto swap_boot_out;
+	}
+	ei_bl = EXT4_I(inode_bl);
+
+	filemap_flush(inode->i_mapping);
+	filemap_flush(inode_bl->i_mapping);
+
+	/* Protect orig inodes against a truncate and make sure,
+	 * that only 1 swap_inode_boot_loader is running. */
+	ext4_inode_double_lock(inode, inode_bl);
+
+	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages(&inode_bl->i_data, 0);
+
+	/* Wait for all existing dio workers */
+	ext4_inode_block_unlocked_dio(inode);
+	ext4_inode_block_unlocked_dio(inode_bl);
+	inode_dio_wait(inode);
+	inode_dio_wait(inode_bl);
+
+	handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
+	if (IS_ERR(handle)) {
+		err = -EINVAL;
+		goto swap_boot_out;
+	}
+
+	/* Protect extent tree against block allocations via delalloc */
+	ext4_double_down_write_data_sem(inode, inode_bl);
+
+	if (inode_bl->i_nlink == 0) {
+		/* this inode has never been used as a BOOT_LOADER */
+		set_nlink(inode_bl, 1);
+		i_uid_write(inode_bl, 0);
+		i_gid_write(inode_bl, 0);
+		inode_bl->i_flags = 0;
+		ei_bl->i_flags = 0;
+		inode_bl->i_version = 1;
+		i_size_write(inode_bl, 0);
+		inode_bl->i_mode = S_IFREG;
+		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+					      EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+			ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
+			ext4_ext_tree_init(handle, inode_bl);
+		} else
+			memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
+	}
+
+	swap_inode_data(inode, inode_bl);
+
+	inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode);
+
+	spin_lock(&sbi->s_next_gen_lock);
+	inode->i_generation = sbi->s_next_generation++;
+	inode_bl->i_generation = sbi->s_next_generation++;
+	spin_unlock(&sbi->s_next_gen_lock);
+
+	ext4_discard_preallocations(inode);
+
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err < 0) {
+		ext4_warning(inode->i_sb,
+			"couldn't mark inode #%lu dirty (err %d)",
+			inode->i_ino, err);
+		/* Revert all changes: */
+		swap_inode_data(inode, inode_bl);
+	} else {
+		err = ext4_mark_inode_dirty(handle, inode_bl);
+		if (err < 0) {
+			ext4_warning(inode_bl->i_sb,
+				"couldn't mark inode #%lu dirty (err %d)",
+				inode_bl->i_ino, err);
+			/* Revert all changes: */
+			swap_inode_data(inode, inode_bl);
+			ext4_mark_inode_dirty(handle, inode);
+		}
+	}
+
+	ext4_journal_stop(handle);
+
+	ext4_double_up_write_data_sem(inode, inode_bl);
+
+	ext4_inode_resume_unlocked_dio(inode);
+	ext4_inode_resume_unlocked_dio(inode_bl);
+
+	ext4_inode_double_unlock(inode, inode_bl);
+
+	iput(inode_bl);
+
+swap_boot_out:
+	return err;
+}
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -353,6 +545,11 @@ group_add_out:
 		return err;
 	}
 
+	case EXT4_IOC_SWAP_BOOT:
+		if (!(filp->f_mode & FMODE_WRITE))
+			return -EBADF;
+		return swap_inode_boot_loader(sb, inode);
+
 	case EXT4_IOC_RESIZE_FS: {
 		ext4_fsblk_t n_blocks_count;
 		struct super_block *sb = inode->i_sb;