ext4: add support for multiple mount protection

Prevent an ext4 filesystem from being mounted multiple times.
A sequence number is stored on disk and is periodically updated (every 5
seconds by default) by a mounted filesystem.
At mount time, we now wait for s_mmp_update_interval seconds to make sure
that the MMP sequence does not change.
In case of failure, the nodename, bdevname and the time at which the MMP
block was last updated is displayed.

Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Johann Lombardi <johann@whamcloud.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

4 files changed, 444 insertions, 4 deletions

diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index c947e36eda6c..04109460ba9e 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -6,7 +6,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
 
 ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
 		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
-		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o
+		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
+		mmp.o
 
 ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 65fe1dc0c750..c0c56c9d5933 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1028,7 +1028,7 @@ struct ext4_super_block {
 	__le16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
 	__le32	s_flags;		/* Miscellaneous flags */
 	__le16  s_raid_stride;		/* RAID stride */
-	__le16  s_mmp_interval;         /* # seconds to wait in MMP checking */
+	__le16  s_mmp_update_interval;  /* # seconds to wait in MMP checking */
 	__le64  s_mmp_block;            /* Block for multi-mount protection */
 	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
 	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
@@ -1204,6 +1204,9 @@ struct ext4_sb_info {
 	struct ext4_li_request *s_li_request;
 	/* Wait multiplier for lazy initialization thread */
 	unsigned int s_li_wait_mult;
+
+	/* Kernel thread for multiple mount protection */
+	struct task_struct *s_mmp_tsk;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1375,7 +1378,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 					 EXT4_FEATURE_INCOMPAT_META_BG| \
 					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
 					 EXT4_FEATURE_INCOMPAT_64BIT| \
-					 EXT4_FEATURE_INCOMPAT_FLEX_BG)
+					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
+					 EXT4_FEATURE_INCOMPAT_MMP)
 #define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
 					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
 					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
@@ -1627,6 +1631,67 @@ struct ext4_features {
 };
 
 /*
+ * This structure will be used for multiple mount protection. It will be
+ * written into the block number saved in the s_mmp_block field in the
+ * superblock. Programs that check MMP should assume that if
+ * SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe
+ * to use the filesystem, regardless of how old the timestamp is.
+ */
+#define EXT4_MMP_MAGIC     0x004D4D50U /* ASCII for MMP */
+#define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */
+#define EXT4_MMP_SEQ_FSCK  0xE24D4D50U /* mmp_seq value when being fscked */
+#define EXT4_MMP_SEQ_MAX   0xE24D4D4FU /* maximum valid mmp_seq value */
+
+struct mmp_struct {
+	__le32	mmp_magic;		/* Magic number for MMP */
+	__le32	mmp_seq;		/* Sequence no. updated periodically */
+
+	/*
+	 * mmp_time, mmp_nodename & mmp_bdevname are only used for information
+	 * purposes and do not affect the correctness of the algorithm
+	 */
+	__le64	mmp_time;		/* Time last updated */
+	char	mmp_nodename[64];	/* Node which last updated MMP block */
+	char	mmp_bdevname[32];	/* Bdev which last updated MMP block */
+
+	/*
+	 * mmp_check_interval is used to verify if the MMP block has been
+	 * updated on the block device. The value is updated based on the
+	 * maximum time to write the MMP block during an update cycle.
+	 */
+	__le16	mmp_check_interval;
+
+	__le16	mmp_pad1;
+	__le32	mmp_pad2[227];
+};
+
+/* arguments passed to the mmp thread */
+struct mmpd_data {
+	struct buffer_head *bh; /* bh from initial read_mmp_block() */
+	struct super_block *sb;  /* super block of the fs */
+};
+
+/*
+ * Check interval multiplier
+ * The MMP block is written every update interval and initially checked every
+ * update interval x the multiplier (the value is then adapted based on the
+ * write latency). The reason is that writes can be delayed under load and we
+ * don't want readers to incorrectly assume that the filesystem is no longer
+ * in use.
+ */
+#define EXT4_MMP_CHECK_MULT		2UL
+
+/*
+ * Minimum interval for MMP checking in seconds.
+ */
+#define EXT4_MMP_MIN_CHECK_INTERVAL	5UL
+
+/*
+ * Maximum interval for MMP checking in seconds.
+ */
+#define EXT4_MMP_MAX_CHECK_INTERVAL	300UL
+
+/*
  * Function prototypes
  */
 
@@ -1800,6 +1865,10 @@ extern void __ext4_warning(struct super_block *, const char *, unsigned int,
 						       __LINE__, ## message)
 extern void ext4_msg(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
+extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
+			   const char *, unsigned int, const char *);
+#define dump_mmp_msg(sb, mmp, msg)	__dump_mmp_msg(sb, mmp, __func__, \
+						       __LINE__, msg)
 extern void __ext4_grp_locked_error(const char *, unsigned int, \
 				    struct super_block *, ext4_group_t, \
 				    unsigned long, ext4_fsblk_t, \
@@ -2104,6 +2173,9 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       int len,
 			       struct writeback_control *wbc);
 
+/* mmp.c */
+extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
+
 /* BH_Uninit flag: blocks are allocated but uninitialized on disk */
 enum ext4_state_bits {
 	BH_Uninit	/* blocks are allocated but uninitialized on disk */
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
new file mode 100644
index 000000000000..9bdef3f537c5
--- /dev/null
+++ b/fs/ext4/mmp.c
@@ -0,0 +1,351 @@
+#include <linux/fs.h>
+#include <linux/random.h>
+#include <linux/buffer_head.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+
+#include "ext4.h"
+
+/*
+ * Write the MMP block using WRITE_SYNC to try to get the block on-disk
+ * faster.
+ */
+static int write_mmp_block(struct buffer_head *bh)
+{
+	mark_buffer_dirty(bh);
+	lock_buffer(bh);
+	bh->b_end_io = end_buffer_write_sync;
+	get_bh(bh);
+	submit_bh(WRITE_SYNC, bh);
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh)))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Read the MMP block. It _must_ be read from disk and hence we clear the
+ * uptodate flag on the buffer.
+ */
+static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
+			  ext4_fsblk_t mmp_block)
+{
+	struct mmp_struct *mmp;
+
+	if (*bh)
+		clear_buffer_uptodate(*bh);
+
+	/* This would be sb_bread(sb, mmp_block), except we need to be sure
+	 * that the MD RAID device cache has been bypassed, and that the read
+	 * is not blocked in the elevator. */
+	if (!*bh)
+		*bh = sb_getblk(sb, mmp_block);
+	if (*bh) {
+		get_bh(*bh);
+		lock_buffer(*bh);
+		(*bh)->b_end_io = end_buffer_read_sync;
+		submit_bh(READ_SYNC, *bh);
+		wait_on_buffer(*bh);
+		if (!buffer_uptodate(*bh)) {
+			brelse(*bh);
+			*bh = NULL;
+		}
+	}
+	if (!*bh) {
+		ext4_warning(sb, "Error while reading MMP block %llu",
+			     mmp_block);
+		return -EIO;
+	}
+
+	mmp = (struct mmp_struct *)((*bh)->b_data);
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC)
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Dump as much information as possible to help the admin.
+ */
+void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
+		    const char *function, unsigned int line, const char *msg)
+{
+	__ext4_warning(sb, function, line, msg);
+	__ext4_warning(sb, function, line,
+		       "MMP failure info: last update time: %llu, last update "
+		       "node: %s, last update device: %s\n",
+		       (long long unsigned int) le64_to_cpu(mmp->mmp_time),
+		       mmp->mmp_nodename, mmp->mmp_bdevname);
+}
+
+/*
+ * kmmpd will update the MMP sequence every s_mmp_update_interval seconds
+ */
+static int kmmpd(void *data)
+{
+	struct super_block *sb = ((struct mmpd_data *) data)->sb;
+	struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct mmp_struct *mmp;
+	ext4_fsblk_t mmp_block;
+	u32 seq = 0;
+	unsigned long failed_writes = 0;
+	int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned mmp_check_interval;
+	unsigned long last_update_time;
+	unsigned long diff;
+	int retval;
+
+	mmp_block = le64_to_cpu(es->s_mmp_block);
+	mmp = (struct mmp_struct *)(bh->b_data);
+	mmp->mmp_time = cpu_to_le64(get_seconds());
+	/*
+	 * Start with the higher mmp_check_interval and reduce it if
+	 * the MMP block is being updated on time.
+	 */
+	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
+				 EXT4_MMP_MIN_CHECK_INTERVAL);
+	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	bdevname(bh->b_bdev, mmp->mmp_bdevname);
+
+	memcpy(mmp->mmp_nodename, init_utsname()->sysname,
+	       sizeof(mmp->mmp_nodename));
+
+	while (!kthread_should_stop()) {
+		if (++seq > EXT4_MMP_SEQ_MAX)
+			seq = 1;
+
+		mmp->mmp_seq = cpu_to_le32(seq);
+		mmp->mmp_time = cpu_to_le64(get_seconds());
+		last_update_time = jiffies;
+
+		retval = write_mmp_block(bh);
+		/*
+		 * Don't spew too many error messages. Print one every
+		 * (s_mmp_update_interval * 60) seconds.
+		 */
+		if (retval && (failed_writes % 60) == 0) {
+			ext4_error(sb, "Error writing to MMP block");
+			failed_writes++;
+		}
+
+		if (!(le32_to_cpu(es->s_feature_incompat) &
+		    EXT4_FEATURE_INCOMPAT_MMP)) {
+			ext4_warning(sb, "kmmpd being stopped since MMP feature"
+				     " has been disabled.");
+			EXT4_SB(sb)->s_mmp_tsk = NULL;
+			goto failed;
+		}
+
+		if (sb->s_flags & MS_RDONLY) {
+			ext4_warning(sb, "kmmpd being stopped since filesystem "
+				     "has been remounted as readonly.");
+			EXT4_SB(sb)->s_mmp_tsk = NULL;
+			goto failed;
+		}
+
+		diff = jiffies - last_update_time;
+		if (diff < mmp_update_interval * HZ)
+			schedule_timeout_interruptible(mmp_update_interval *
+						       HZ - diff);
+
+		/*
+		 * We need to make sure that more than mmp_check_interval
+		 * seconds have not passed since writing. If that has happened
+		 * we need to check if the MMP block is as we left it.
+		 */
+		diff = jiffies - last_update_time;
+		if (diff > mmp_check_interval * HZ) {
+			struct buffer_head *bh_check = NULL;
+			struct mmp_struct *mmp_check;
+
+			retval = read_mmp_block(sb, &bh_check, mmp_block);
+			if (retval) {
+				ext4_error(sb, "error reading MMP data: %d",
+					   retval);
+
+				EXT4_SB(sb)->s_mmp_tsk = NULL;
+				goto failed;
+			}
+
+			mmp_check = (struct mmp_struct *)(bh_check->b_data);
+			if (mmp->mmp_seq != mmp_check->mmp_seq ||
+			    memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
+				   sizeof(mmp->mmp_nodename))) {
+				dump_mmp_msg(sb, mmp_check,
+					     "Error while updating MMP info. "
+					     "The filesystem seems to have been"
+					     " multiply mounted.");
+				ext4_error(sb, "abort");
+				goto failed;
+			}
+			put_bh(bh_check);
+		}
+
+		 /*
+		 * Adjust the mmp_check_interval depending on how much time
+		 * it took for the MMP block to be written.
+		 */
+		mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ,
+					     EXT4_MMP_MAX_CHECK_INTERVAL),
+					 EXT4_MMP_MIN_CHECK_INTERVAL);
+		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	}
+
+	/*
+	 * Unmount seems to be clean.
+	 */
+	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
+	mmp->mmp_time = cpu_to_le64(get_seconds());
+
+	retval = write_mmp_block(bh);
+
+failed:
+	kfree(data);
+	brelse(bh);
+	return retval;
+}
+
+/*
+ * Get a random new sequence number but make sure it is not greater than
+ * EXT4_MMP_SEQ_MAX.
+ */
+static unsigned int mmp_new_seq(void)
+{
+	u32 new_seq;
+
+	do {
+		get_random_bytes(&new_seq, sizeof(u32));
+	} while (new_seq > EXT4_MMP_SEQ_MAX);
+
+	return new_seq;
+}
+
+/*
+ * Protect the filesystem from being mounted more than once.
+ */
+int ext4_multi_mount_protect(struct super_block *sb,
+				    ext4_fsblk_t mmp_block)
+{
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = NULL;
+	struct mmp_struct *mmp = NULL;
+	struct mmpd_data *mmpd_data;
+	u32 seq;
+	unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
+	unsigned int wait_time = 0;
+	int retval;
+
+	if (mmp_block < le32_to_cpu(es->s_first_data_block) ||
+	    mmp_block >= ext4_blocks_count(es)) {
+		ext4_warning(sb, "Invalid MMP block in superblock");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+
+	mmp = (struct mmp_struct *)(bh->b_data);
+
+	if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL)
+		mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL;
+
+	/*
+	 * If check_interval in MMP block is larger, use that instead of
+	 * update_interval from the superblock.
+	 */
+	if (mmp->mmp_check_interval > mmp_check_interval)
+		mmp_check_interval = mmp->mmp_check_interval;
+
+	seq = le32_to_cpu(mmp->mmp_seq);
+	if (seq == EXT4_MMP_SEQ_CLEAN)
+		goto skip;
+
+	if (seq == EXT4_MMP_SEQ_FSCK) {
+		dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
+		goto failed;
+	}
+
+	wait_time = min(mmp_check_interval * 2 + 1,
+			mmp_check_interval + 60);
+
+	/* Print MMP interval if more than 20 secs. */
+	if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4)
+		ext4_warning(sb, "MMP interval %u higher than expected, please"
+			     " wait.\n", wait_time * 2);
+
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		goto failed;
+	}
+
+skip:
+	/*
+	 * write a new random sequence number.
+	 */
+	mmp->mmp_seq = seq = cpu_to_le32(mmp_new_seq());
+
+	retval = write_mmp_block(bh);
+	if (retval)
+		goto failed;
+
+	/*
+	 * wait for MMP interval and check mmp_seq.
+	 */
+	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
+		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		goto failed;
+	}
+
+	retval = read_mmp_block(sb, &bh, mmp_block);
+	if (retval)
+		goto failed;
+	mmp = (struct mmp_struct *)(bh->b_data);
+	if (seq != le32_to_cpu(mmp->mmp_seq)) {
+		dump_mmp_msg(sb, mmp,
+			     "Device is already active on another node.");
+		goto failed;
+	}
+
+	mmpd_data = kmalloc(sizeof(struct mmpd_data), GFP_KERNEL);
+	if (!mmpd_data) {
+		ext4_warning(sb, "not enough memory for mmpd_data");
+		goto failed;
+	}
+	mmpd_data->sb = sb;
+	mmpd_data->bh = bh;
+
+	/*
+	 * Start a kernel thread to update the MMP block periodically.
+	 */
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
+					     bdevname(bh->b_bdev,
+						      mmp->mmp_bdevname));
+	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
+		EXT4_SB(sb)->s_mmp_tsk = NULL;
+		kfree(mmpd_data);
+		ext4_warning(sb, "Unable to create kmmpd thread for %s.",
+			     sb->s_id);
+		goto failed;
+	}
+
+	return 0;
+
+failed:
+	brelse(bh);
+	return 1;
+}
+
+
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 266174b268cc..d9937df7f5cf 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -822,6 +822,8 @@ static void ext4_put_super(struct super_block *sb)
 		invalidate_bdev(sbi->journal_bdev);
 		ext4_blkdev_remove(sbi);
 	}
+	if (sbi->s_mmp_tsk)
+		kthread_stop(sbi->s_mmp_tsk);
 	sb->s_fs_info = NULL;
 	/*
 	 * Now that we are completely done shutting down the
@@ -3486,6 +3488,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			  EXT4_HAS_INCOMPAT_FEATURE(sb,
 				    EXT4_FEATURE_INCOMPAT_RECOVER));
 
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
+	    !(sb->s_flags & MS_RDONLY))
+		if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
+			goto failed_mount3;
+
 	/*
 	 * The first inode we look at is the journal inode.  Don't try
 	 * root first: it may be modified in the journal!
@@ -3733,6 +3740,8 @@ failed_mount3:
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+	if (sbi->s_mmp_tsk)
+		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
@@ -4268,7 +4277,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	int enable_quota = 0;
 	ext4_group_t g;
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
-	int err;
+	int err = 0;
 #ifdef CONFIG_QUOTA
 	int i;
 #endif
@@ -4394,6 +4403,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 				goto restore_opts;
 			if (!ext4_setup_super(sb, es, 0))
 				sb->s_flags &= ~MS_RDONLY;
+			if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+						     EXT4_FEATURE_INCOMPAT_MMP))
+				if (ext4_multi_mount_protect(sb,
+						le64_to_cpu(es->s_mmp_block))) {
+					err = -EROFS;
+					goto restore_opts;
+				}
 			enable_quota = 1;
 		}
 	}