[PATCH] New ioctl "EXT4_IOC_SWAP_BOOT" to secure boot loader code.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: "Dr. Tilmann Bubeck" <t.bubeck@xxxxxxxxxxx>

Implementation of a new ioctl for ext4 called "EXT4_IOC_SWAP_BOOT":

  "Swap i_blocks and associated attributes (like i_blocks, i_size,
   i_flags, ...) from the associated 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 the user on accident.  The data blocks of the previous
   boot loader will be associated with the given inode."

The implementation uses existing (static) functions from move_extent.c
which therefore had to be changed in name and linkage.

Also "ext4_iget()" was extended, so that it is able to return inode
EXT4_BOOT_LOADER_INO, which has no valid i_mode and i_nlink.

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_RDONLY);
  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);
}

Signed-off-by: Dr. Tilmann Bubeck <t.bubeck@xxxxxxxxxxx>
---
 Documentation/filesystems/ext4.txt |  10 +++
 fs/ext4/ext4.h                     |  10 ++-
 fs/ext4/inode.c                    |  20 +++--
 fs/ext4/ioctl.c                    | 163 +++++++++++++++++++++++++++++++++++++
 fs/ext4/move_extent.c              |  47 +++++------
 5 files changed, 218 insertions(+), 32 deletions(-)

diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 34ea4f1..47f130e 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -587,6 +587,16 @@ Table of Ext4 specific ioctls
 			      bitmaps and inode table, the userspace tool thus
 			      just passes the new number of blocks.
 
+ EXT4_IOC_SWAP_BOOT	      Swap i_blocks and associated attributes
+ 			      (like i_blocks, i_size, i_flags, ...) from
+			      the associated 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 the
+			      user on accident.
+			      The data blocks of the previous boot loader
+			      will be associated with the given inode.
+
 ..............................................................................
 
 References
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index d93393e..e4c02b9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -614,6 +614,7 @@ enum {
 #define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
 #define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
 #define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
+#define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
@@ -1335,6 +1336,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 	return ino == EXT4_ROOT_INO ||
 		ino == EXT4_USR_QUOTA_INO ||
 		ino == EXT4_GRP_QUOTA_INO ||
+		ino == EXT4_BOOT_LOADER_INO ||
 		ino == EXT4_JOURNAL_INO ||
 		ino == EXT4_RESIZE_INO ||
 		(ino >= EXT4_FIRST_INO(sb) &&
@@ -2523,9 +2525,13 @@ extern int ext4_ext_check_inode(struct inode *inode);
 extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
-
-
 /* move_extent.c */
+extern void ext4_double_down_write_data_sem(struct inode *first, 
+                                       struct inode *second);
+extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
+                                     struct inode *donor_inode);
+void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2);
+void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2);
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 07d9def..767d2da 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3748,14 +3748,18 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	if (inode->i_nlink == 0) {
 		if (inode->i_mode == 0 ||
 		    !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
-			/* this inode is deleted */
-			ret = -ESTALE;
-			goto bad_inode;
+			if (ino != EXT4_BOOT_LOADER_INO) {
+				/* this inode is deleted */
+				ret = -ESTALE;
+				goto bad_inode;
+			}
+			/* The only unlinked inodes we let through here have
+			 * valid i_mode and are being read by the orphan
+			 * recovery code: that's fine, we're about to complete
+			 * the process of deleting those.
+			 * OR it is the EXT4_BOOT_LOADER_INO which is
+			 * not initialized on a prune filesystem. */
 		}
-		/* The only unlinked inodes we let through here have
-		 * valid i_mode and are being read by the orphan
-		 * recovery code: that's fine, we're about to complete
-		 * the process of deleting those. */
 	}
 	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
 	inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
@@ -3875,6 +3879,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		else
 			init_special_inode(inode, inode->i_mode,
 			   new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
+	} else if (ino == EXT4_BOOT_LOADER_INO) {
+		make_bad_inode(inode);
 	} else {
 		ret = -EIO;
 		EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 4784ac2..b17a1c2 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -17,9 +17,166 @@
 #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 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, err2;
+	struct inode *inode_bl;
+	struct ext4_inode_info *ei;
+	struct ext4_inode_info *ei_bl;
+	long long isize;
+	struct ext4_sb_info *sbi;
+
+	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);
+
+	if (!inode_owner_or_capable(inode_bl)) {
+		err = -EPERM;
+		goto swap_boot_out;
+	}
+
+	/* This is non obvious task to swap blocks for inodes with full
+	 * jornaling enabled */
+	if (ext4_should_journal_data(inode) ||
+	    ext4_should_journal_data(inode_bl)) {
+		err = -EINVAL;
+		goto swap_boot_out;
+	}
+	/* Protect orig and boot loader inodes against a truncate */
+	ext4_inode_double_lock(inode, inode_bl);
+
+	/* 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);
+
+	/* Protect extent tree against block allocations via delalloc */
+	ext4_double_down_write_data_sem(inode, inode_bl);
+
+	handle = ext4_journal_start(inode_bl, 2);
+	if (IS_ERR(handle)) {
+		err = -EINVAL;
+		goto swap_boot_out;
+	}
+
+	if (inode_bl->i_nlink == 0) {
+		/* this inode has never been used as a BOOT_LOADER */
+		set_nlink(inode_bl, 1);
+		inode_bl->i_uid = 0;
+		inode_bl->i_gid = 0;
+		inode_bl->i_flags = inode->i_flags;
+		ei_bl->i_flags = ei->i_flags;
+		inode_bl->i_version = 1;
+		ext4_ext_tree_init(handle, inode_bl);
+	}
+
+	__memswap(&inode->i_flags, &inode_bl->i_flags, sizeof(inode->i_flags));
+	__memswap(&inode->i_version, &inode_bl->i_version,
+		  sizeof(inode->i_version));
+	__memswap(&inode->i_blocks, &inode_bl->i_blocks,
+		  sizeof(inode->i_blocks));
+	__memswap(&inode->i_bytes, &inode_bl->i_bytes, sizeof(inode->i_bytes));
+	__memswap(&inode->i_atime, &inode_bl->i_atime, sizeof(inode->i_atime));
+	__memswap(&inode->i_mtime, &inode_bl->i_mtime, sizeof(inode->i_mtime));
+
+	__memswap(ei->i_data, ei_bl->i_data, sizeof(ei->i_data));
+	__memswap(&ei->i_flags, &ei_bl->i_flags, sizeof(ei->i_flags));
+	__memswap(&ei->i_disksize, &ei_bl->i_disksize, sizeof(ei->i_disksize));
+	__memswap(&ei->i_cached_extent, &ei_bl->i_cached_extent,
+		  sizeof(ei->i_cached_extent));
+
+	isize = i_size_read(inode);
+	i_size_write(inode, i_size_read(inode_bl));
+	i_size_write(inode_bl, isize);
+
+	inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode);
+
+	spin_lock(&sbi->s_next_gen_lock);
+	inode_bl->i_generation = sbi->s_next_generation++;
+	spin_unlock(&sbi->s_next_gen_lock);
+
+	ext4_ext_invalidate_cache(inode);
+	ext4_ext_invalidate_cache(inode_bl);
+	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode_bl);
+
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err < 0) {
+		ext4_warning(inode->i_sb,
+			     "couldn't mark inode dirty (err %d)", err);
+	}
+	err2 = ext4_mark_inode_dirty(handle, inode_bl);
+	if (err2 < 0) {
+		ext4_warning(inode->i_sb,
+			     "couldn't mark inode dirty (err %d)", err2);
+		err = err2;
+	}
+
+	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);
+
+	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages(&inode_bl->i_data, 0);
+	filemap_flush(inode->i_mapping);
+	filemap_flush(inode_bl->i_mapping);
+
+	iput(inode_bl);
+
+swap_boot_out:
+	return err;
+}
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = filp->f_dentry->d_inode;
@@ -357,6 +514,12 @@ group_add_out:
 		return err;
 	}
 
+	case EXT4_IOC_SWAP_BOOT:
+	{
+		ext4_msg(sb, KERN_ERR, "%s/%d", __func__, __LINE__);
+		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;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index d9cc5ee..ee7da4e 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -142,12 +142,13 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 }
 
 /**
- * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
+ * ext4_double_down_write_data_sem - Acquire two inodes' write lock 
+ *                                   of i_data_sem
  *
  * Acquire write lock of i_data_sem of the two inodes
  */
-static void
-double_down_write_data_sem(struct inode *first, struct inode *second)
+void
+ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
 {
 	if (first < second) {
 		down_write(&EXT4_I(first)->i_data_sem);
@@ -160,14 +161,14 @@ double_down_write_data_sem(struct inode *first, struct inode *second)
 }
 
 /**
- * double_up_write_data_sem - Release two inodes' write lock of i_data_sem
+ * ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem
  *
  * @orig_inode:		original inode structure to be released its lock first
  * @donor_inode:	donor inode structure to be released its lock second
  * Release write lock of i_data_sem of two inodes (orig and donor).
  */
-static void
-double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
+void
+ext4_double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
 {
 	up_write(&EXT4_I(orig_inode)->i_data_sem);
 	up_write(&EXT4_I(donor_inode)->i_data_sem);
@@ -965,7 +966,7 @@ again:
 	 * necessary, just swap data blocks between orig and donor.
 	 */
 	if (uninit) {
-		double_down_write_data_sem(orig_inode, donor_inode);
+		ext4_double_down_write_data_sem(orig_inode, donor_inode);
 		/* If any of extents in range became initialized we have to
 		 * fallback to data copying */
 		uninit = mext_check_coverage(orig_inode, orig_blk_offset,
@@ -979,7 +980,7 @@ again:
 			goto drop_data_sem;
 
 		if (!uninit) {
-			double_up_write_data_sem(orig_inode, donor_inode);
+			ext4_double_up_write_data_sem(orig_inode, donor_inode);
 			goto data_copy;
 		}
 		if ((page_has_private(pagep[0]) &&
@@ -993,7 +994,7 @@ again:
 						donor_inode, orig_blk_offset,
 						block_len_in_page, err);
 	drop_data_sem:
-		double_up_write_data_sem(orig_inode, donor_inode);
+		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 		goto unlock_pages;
 	}
 data_copy:
@@ -1054,11 +1055,11 @@ repair_branches:
 	 * Extents are swapped already, but we are not able to copy data.
 	 * Try to swap extents to it's original places
 	 */
-	double_down_write_data_sem(orig_inode, donor_inode);
+	ext4_double_down_write_data_sem(orig_inode, donor_inode);
 	replaced_count = mext_replace_branches(handle, donor_inode, orig_inode,
 					       orig_blk_offset,
 					       block_len_in_page, &err2);
-	double_up_write_data_sem(orig_inode, donor_inode);
+	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	if (replaced_count != block_len_in_page) {
 		EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset),
 				       "Unable to copy data block,"
@@ -1198,15 +1199,15 @@ mext_check_arguments(struct inode *orig_inode,
 }
 
 /**
- * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
+ * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
  *
  * @inode1:	the inode structure
  * @inode2:	the inode structure
  *
  * Lock two inodes' i_mutex
  */
-static void
-mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
+void
+ext4_inode_double_lock(struct inode *inode1, struct inode *inode2)
 {
 	BUG_ON(inode1 == inode2);
 	if (inode1 < inode2) {
@@ -1219,15 +1220,15 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
 }
 
 /**
- * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
+ * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
  *
  * @inode1:     the inode that is released first
  * @inode2:     the inode that is released second
  *
  */
 
-static void
-mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
+void
+ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2)
 {
 	mutex_unlock(&inode1->i_mutex);
 	mutex_unlock(&inode2->i_mutex);
@@ -1322,7 +1323,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		return -EINVAL;
 	}
 	/* Protect orig and donor inodes against a truncate */
-	mext_inode_double_lock(orig_inode, donor_inode);
+	ext4_inode_double_lock(orig_inode, donor_inode);
 
 	/* Wait for all existing dio workers */
 	ext4_inode_block_unlocked_dio(orig_inode);
@@ -1331,7 +1332,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 	inode_dio_wait(donor_inode);
 
 	/* Protect extent tree against block allocations via delalloc */
-	double_down_write_data_sem(orig_inode, donor_inode);
+	ext4_double_down_write_data_sem(orig_inode, donor_inode);
 	/* Check the filesystem environment whether move_extent can be done */
 	ret = mext_check_arguments(orig_inode, donor_inode, orig_start,
 				    donor_start, &len);
@@ -1455,7 +1456,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		 * b. racing with ->readpage, ->write_begin, and ext4_get_block
 		 *    in move_extent_per_page
 		 */
-		double_up_write_data_sem(orig_inode, donor_inode);
+		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 
 		while (orig_page_offset <= seq_end_page) {
 
@@ -1489,7 +1490,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 				block_len_in_page = rest_blocks;
 		}
 
-		double_down_write_data_sem(orig_inode, donor_inode);
+		ext4_double_down_write_data_sem(orig_inode, donor_inode);
 		if (ret < 0)
 			break;
 
@@ -1527,10 +1528,10 @@ out:
 		ext4_ext_drop_refs(holecheck_path);
 		kfree(holecheck_path);
 	}
-	double_up_write_data_sem(orig_inode, donor_inode);
+	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	ext4_inode_resume_unlocked_dio(orig_inode);
 	ext4_inode_resume_unlocked_dio(donor_inode);
-	mext_inode_double_unlock(orig_inode, donor_inode);
+	ext4_inode_double_unlock(orig_inode, donor_inode);
 
 	return ret;
 }
-- 
1.8.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [Reiser Filesystem Development]     [Ceph FS]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite National Park]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Device Mapper]     [Linux Media]

  Powered by Linux