1 files changed, 116 insertions, 107 deletions

diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 214461e42a05..6f57c181ff77 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/fs.h>
 #include <linux/random.h>
 #include <linux/buffer_head.h>
@@ -13,56 +14,57 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
 	int offset = offsetof(struct mmp_struct, mmp_checksum);
 	__u32 csum;
 
-	csum = ext4_chksum(sbi, sbi->s_csum_seed, (char *)mmp, offset);
+	csum = ext4_chksum(sbi->s_csum_seed, (char *)mmp, offset);
 
 	return cpu_to_le32(csum);
 }
 
-int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
+static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_feature_metadata_csum(sb))
 		return 1;
 
 	return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
 }
 
-void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
+static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_feature_metadata_csum(sb))
 		return;
 
 	mmp->mmp_checksum = ext4_mmp_csum(sb, mmp);
 }
 
 /*
- * Write the MMP block using WRITE_SYNC to try to get the block on-disk
+ * Write the MMP block using REQ_SYNC to try to get the block on-disk
  * faster.
  */
-static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+static int write_mmp_block_thawed(struct super_block *sb,
+				  struct buffer_head *bh)
 {
 	struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
 
-	/*
-	 * We protect against freezing so that we don't create dirty buffers
-	 * on frozen filesystem.
-	 */
-	sb_start_write(sb);
 	ext4_mmp_csum_set(sb, mmp);
-	mark_buffer_dirty(bh);
 	lock_buffer(bh);
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
-	submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
-	sb_end_write(sb);
 	if (unlikely(!buffer_uptodate(bh)))
-		return 1;
-
+		return -EIO;
 	return 0;
 }
 
+static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+{
+	/*
+	 * We protect against freezing so that we don't create dirty buffers
+	 * on frozen filesystem.
+	 */
+	scoped_guard(super_write, sb)
+		return write_mmp_block_thawed(sb, bh);
+}
+
 /*
  * Read the MMP block. It _must_ be read from disk and hence we clear the
  * uptodate flag on the buffer.
@@ -71,6 +73,7 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
 			  ext4_fsblk_t mmp_block)
 {
 	struct mmp_struct *mmp;
+	int ret;
 
 	if (*bh)
 		clear_buffer_uptodate(*bh);
@@ -78,33 +81,35 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **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)
+	if (!*bh) {
 		*bh = sb_getblk(sb, mmp_block);
-	if (!*bh)
-		return -ENOMEM;
-	if (*bh) {
-		get_bh(*bh);
-		lock_buffer(*bh);
-		(*bh)->b_end_io = end_buffer_read_sync;
-		submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh);
-		wait_on_buffer(*bh);
-		if (!buffer_uptodate(*bh)) {
-			brelse(*bh);
-			*bh = NULL;
+		if (!*bh) {
+			ret = -ENOMEM;
+			goto warn_exit;
 		}
 	}
-	if (unlikely(!*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 ||
-	    !ext4_mmp_csum_verify(sb, mmp))
-		return -EINVAL;
+	lock_buffer(*bh);
+	ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL, false);
+	if (ret)
+		goto warn_exit;
 
+	mmp = (struct mmp_struct *)((*bh)->b_data);
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) {
+		ret = -EFSCORRUPTED;
+		goto warn_exit;
+	}
+	if (!ext4_mmp_csum_verify(sb, mmp)) {
+		ret = -EFSBADCRC;
+		goto warn_exit;
+	}
 	return 0;
+warn_exit:
+	brelse(*bh);
+	*bh = NULL;
+	ext4_warning(sb, "Error %d while reading MMP block %llu",
+		     ret, mmp_block);
+	return ret;
 }
 
 /*
@@ -113,12 +118,12 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
 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, "%s", 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);
+		       "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s",
+		       (unsigned long long)le64_to_cpu(mmp->mmp_time),
+		       (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename,
+		       (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname);
 }
 
 /*
@@ -126,9 +131,9 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
  */
 static int kmmpd(void *data)
 {
-	struct super_block *sb = ((struct mmpd_data *) data)->sb;
-	struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
+	struct super_block *sb = data;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh;
 	struct mmp_struct *mmp;
 	ext4_fsblk_t mmp_block;
 	u32 seq = 0;
@@ -137,11 +142,11 @@ static int kmmpd(void *data)
 	unsigned mmp_check_interval;
 	unsigned long last_update_time;
 	unsigned long diff;
-	int retval;
+	int retval = 0;
 
 	mmp_block = le64_to_cpu(es->s_mmp_block);
 	mmp = (struct mmp_struct *)(bh->b_data);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 	/*
 	 * Start with the higher mmp_check_interval and reduce it if
 	 * the MMP block is being updated on time.
@@ -149,17 +154,21 @@ static int kmmpd(void *data)
 	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()->nodename,
 	       sizeof(mmp->mmp_nodename));
 
-	while (!kthread_should_stop()) {
+	while (!kthread_should_stop() && !ext4_emergency_state(sb)) {
+		if (!ext4_has_feature_mmp(sb)) {
+			ext4_warning(sb, "kmmpd being stopped since MMP feature"
+				     " has been disabled.");
+			goto wait_to_exit;
+		}
 		if (++seq > EXT4_MMP_SEQ_MAX)
 			seq = 1;
 
 		mmp->mmp_seq = cpu_to_le32(seq);
-		mmp->mmp_time = cpu_to_le64(get_seconds());
+		mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 		last_update_time = jiffies;
 
 		retval = write_mmp_block(sb, bh);
@@ -168,26 +177,13 @@ static int kmmpd(void *data)
 		 * (s_mmp_update_interval * 60) seconds.
 		 */
 		if (retval) {
-			if ((failed_writes % 60) == 0)
-				ext4_error(sb, "Error writing to MMP block");
+			if ((failed_writes % 60) == 0) {
+				ext4_error_err(sb, -retval,
+					       "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 *
@@ -205,11 +201,10 @@ static int kmmpd(void *data)
 
 			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;
+				ext4_error_err(sb, -retval,
+					       "error reading MMP data: %d",
+					       retval);
+				goto wait_to_exit;
 			}
 
 			mmp_check = (struct mmp_struct *)(bh_check->b_data);
@@ -220,8 +215,10 @@ static int kmmpd(void *data)
 					     "Error while updating MMP info. "
 					     "The filesystem seems to have been"
 					     " multiply mounted.");
-				ext4_error(sb, "abort");
-				goto failed;
+				ext4_error_err(sb, EBUSY, "abort");
+				put_bh(bh_check);
+				retval = -EBUSY;
+				goto wait_to_exit;
 			}
 			put_bh(bh_check);
 		}
@@ -230,9 +227,9 @@ static int kmmpd(void *data)
 		 * 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_check_interval = clamp(EXT4_MMP_CHECK_MULT * diff / HZ,
+					   EXT4_MMP_MIN_CHECK_INTERVAL,
+					   EXT4_MMP_MAX_CHECK_INTERVAL);
 		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
 	}
 
@@ -240,29 +237,36 @@ static int kmmpd(void *data)
 	 * Unmount seems to be clean.
 	 */
 	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 
 	retval = write_mmp_block(sb, bh);
 
-failed:
-	kfree(data);
-	brelse(bh);
+wait_to_exit:
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!kthread_should_stop())
+			schedule();
+	}
+	set_current_state(TASK_RUNNING);
 	return retval;
 }
 
+void ext4_stop_mmpd(struct ext4_sb_info *sbi)
+{
+	if (sbi->s_mmp_tsk) {
+		kthread_stop(sbi->s_mmp_tsk);
+		brelse(sbi->s_mmp_bh);
+		sbi->s_mmp_tsk = NULL;
+	}
+}
+
 /*
  * 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;
+	return get_random_u32_below(EXT4_MMP_SEQ_MAX + 1);
 }
 
 /*
@@ -274,7 +278,6 @@ int ext4_multi_mount_protect(struct super_block *sb,
 	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;
@@ -283,6 +286,7 @@ int ext4_multi_mount_protect(struct super_block *sb,
 	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");
+		retval = -EINVAL;
 		goto failed;
 	}
 
@@ -308,6 +312,7 @@ int ext4_multi_mount_protect(struct super_block *sb,
 
 	if (seq == EXT4_MMP_SEQ_FSCK) {
 		dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
+		retval = -EBUSY;
 		goto failed;
 	}
 
@@ -321,6 +326,7 @@ int ext4_multi_mount_protect(struct super_block *sb,
 
 	if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
 		ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+		retval = -ETIMEDOUT;
 		goto failed;
 	}
 
@@ -331,6 +337,7 @@ int ext4_multi_mount_protect(struct super_block *sb,
 	if (seq != le32_to_cpu(mmp->mmp_seq)) {
 		dump_mmp_msg(sb, mmp,
 			     "Device is already active on another node.");
+		retval = -EBUSY;
 		goto failed;
 	}
 
@@ -341,7 +348,11 @@ skip:
 	seq = mmp_new_seq();
 	mmp->mmp_seq = cpu_to_le32(seq);
 
-	retval = write_mmp_block(sb, bh);
+	/*
+	 * On mount / remount we are protected against fs freezing (by s_umount
+	 * semaphore) and grabbing freeze protection upsets lockdep
+	 */
+	retval = write_mmp_block_thawed(sb, bh);
 	if (retval)
 		goto failed;
 
@@ -349,7 +360,8 @@ skip:
 	 * 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");
+		ext4_warning(sb, "MMP startup interrupted, failing mount");
+		retval = -ETIMEDOUT;
 		goto failed;
 	}
 
@@ -360,28 +372,27 @@ skip:
 	if (seq != le32_to_cpu(mmp->mmp_seq)) {
 		dump_mmp_msg(sb, mmp,
 			     "Device is already active on another node.");
+		retval = -EBUSY;
 		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;
+	EXT4_SB(sb)->s_mmp_bh = bh;
+
+	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
+	snprintf(mmp->mmp_bdevname, sizeof(mmp->mmp_bdevname),
+		 "%pg", bh->b_bdev);
 
 	/*
 	 * 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));
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s",
+					     (int)sizeof(mmp->mmp_bdevname),
+					     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);
+		retval = -ENOMEM;
 		goto failed;
 	}
 
@@ -389,7 +400,5 @@ skip:
 
 failed:
 	brelse(bh);
-	return 1;
+	return retval;
 }
-
-