Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "For this cycle we add support for the shutdown ioctl, which is
  primarily used for testing, but which can be useful on production
  systems when a scratch volume is being destroyed and the data on it
  doesn't need to be saved.

  This found (and we fixed) a number of bugs with ext4's recovery to
  corrupted file system --- the bugs increased the amount of data that
  could be potentially lost, and in the case of the inline data feature,
  could cause the kernel to BUG.

  Also included are a number of other bug fixes, including in ext4's
  fscrypt, DAX, inline data support"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (26 commits)
  ext4: rename EXT4_IOC_GOINGDOWN to EXT4_IOC_SHUTDOWN
  ext4: fix fencepost in s_first_meta_bg validation
  ext4: don't BUG when truncating encrypted inodes on the orphan list
  ext4: do not use stripe_width if it is not set
  ext4: fix stripe-unaligned allocations
  dax: assert that i_rwsem is held exclusive for writes
  ext4: fix DAX write locking
  ext4: add EXT4_IOC_GOINGDOWN ioctl
  ext4: add shutdown bit and check for it
  ext4: rename s_resize_flags to s_ext4_flags
  ext4: return EROFS if device is r/o and journal replay is needed
  ext4: preserve the needs_recovery flag when the journal is aborted
  jbd2: don't leak modified metadata buffers on an aborted journal
  ext4: fix inline data error paths
  ext4: move halfmd4 into hash.c directly
  ext4: fix use-after-iput when fscrypt contexts are inconsistent
  jbd2: fix use after free in kjournald2()
  ext4: fix data corruption in data=journal mode
  ext4: trim allocation requests to group size
  ext4: replace BUG_ON with WARN_ON in mb_find_extent()
  ...

fs/dax.c

@@ -1086,8 +1086,12 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos, ret = 0, done = 0;
 	unsigned flags = 0;
 
-	if (iov_iter_rw(iter) == WRITE)
+	if (iov_iter_rw(iter) == WRITE) {
+		lockdep_assert_held_exclusive(&inode->i_rwsem);
 		flags |= IOMAP_WRITE;
+	} else {
+		lockdep_assert_held(&inode->i_rwsem);
+	}
 
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,

fs/ext4/ext4.h

@@ -683,6 +683,16 @@ struct fsxattr {
 #define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
 #define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
 
+#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
+
+/*
+ * Flags for going down operation
+ */
+#define EXT4_GOING_FLAGS_DEFAULT		0x0	/* going down */
+#define EXT4_GOING_FLAGS_LOGFLUSH		0x1	/* flush log but not data */
+#define EXT4_GOING_FLAGS_NOLOGFLUSH		0x2	/* don't flush log nor data */
+
+
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
  * ioctl commands in 32 bit emulation
@@ -1403,8 +1413,7 @@ struct ext4_sb_info {
 	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	struct mutex s_orphan_lock;
-	unsigned long s_resize_flags;		/* Flags indicating if there
-						   is a resizer */
+	unsigned long s_ext4_flags;		/* Ext4 superblock flags */
 	unsigned long s_commit_interval;
 	u32 s_max_batch_time;
 	u32 s_min_batch_time;
@@ -1837,6 +1846,18 @@ static inline bool ext4_has_incompat_features(struct super_block *sb)
 	return (EXT4_SB(sb)->s_es->s_feature_incompat != 0);
 }
 
+/*
+ * Superblock flags
+ */
+#define EXT4_FLAGS_RESIZING	0
+#define EXT4_FLAGS_SHUTDOWN	1
+
+static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
+{
+	return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+}
+
+
 /*
  * Default values for user and/or group using reserved blocks
  */
@@ -3005,7 +3026,7 @@ extern int ext4_inline_data_fiemap(struct inode *inode,
 extern int ext4_try_to_evict_inline_data(handle_t *handle,
 					 struct inode *inode,
 					 int needed);
-extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
+extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
 
 extern int ext4_convert_inline_data(struct inode *inode);
 
@@ -3199,7 +3220,6 @@ static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
 					    EXT4_WQ_HASH_SZ])
 extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
 
-#define EXT4_RESIZING	0
 extern int ext4_resize_begin(struct super_block *sb);
 extern void ext4_resize_end(struct super_block *sb);
 

fs/ext4/ext4_jbd2.c

@@ -43,6 +43,10 @@ static int ext4_journal_check_start(struct super_block *sb)
 	journal_t *journal;
 
 	might_sleep();
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return -EIO;
+
 	if (sb->s_flags & MS_RDONLY)
 		return -EROFS;
 	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
@@ -161,6 +165,13 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 	might_sleep();
 
 	if (ext4_handle_valid(handle)) {
+		struct super_block *sb;
+
+		sb = handle->h_transaction->t_journal->j_private;
+		if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) {
+			jbd2_journal_abort_handle(handle);
+			return -EIO;
+		}
 		err = jbd2_journal_get_write_access(handle, bh);
 		if (err)
 			ext4_journal_abort_handle(where, line, __func__, bh,

fs/ext4/extents.c

@@ -5334,7 +5334,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	ext4_lblk_t stop, *iterator, ex_start, ex_end;
 
 	/* Let path point to the last extent */
-	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+				EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 
@@ -5343,15 +5344,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	if (!extent)
 		goto out;
 
-	stop = le32_to_cpu(extent->ee_block) +
-			ext4_ext_get_actual_len(extent);
+	stop = le32_to_cpu(extent->ee_block);
 
        /*
 	 * In case of left shift, Don't start shifting extents until we make
 	 * sure the hole is big enough to accommodate the shift.
 	*/
 	if (SHIFT == SHIFT_LEFT) {
-		path = ext4_find_extent(inode, start - 1, &path, 0);
+		path = ext4_find_extent(inode, start - 1, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5383,9 +5384,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	else
 		iterator = &stop;
 
-	/* Its safe to start updating extents */
-	while (start < stop) {
-		path = ext4_find_extent(inode, *iterator, &path, 0);
+	/*
+	 * Its safe to start updating extents.  Start and stop are unsigned, so
+	 * in case of right shift if extent with 0 block is reached, iterator
+	 * becomes NULL to indicate the end of the loop.
+	 */
+	while (iterator && start <= stop) {
+		path = ext4_find_extent(inode, *iterator, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5412,8 +5418,11 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 					ext4_ext_get_actual_len(extent);
 		} else {
 			extent = EXT_FIRST_EXTENT(path[depth].p_hdr);
-			*iterator =  le32_to_cpu(extent->ee_block) > 0 ?
-				le32_to_cpu(extent->ee_block) - 1 : 0;
+			if (le32_to_cpu(extent->ee_block) > 0)
+				*iterator = le32_to_cpu(extent->ee_block) - 1;
+			else
+				/* Beginning is reached, end of the loop */
+				iterator = NULL;
 			/* Update path extent in case we need to stop */
 			while (le32_to_cpu(extent->ee_block) < start)
 				extent++;

fs/ext4/file.c

@@ -57,6 +57,9 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+		return -EIO;
+
 	if (!iov_iter_count(to))
 		return 0; /* skip atime */
 
@@ -175,7 +178,6 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
-	bool overwrite = false;
 
 	inode_lock(inode);
 	ret = ext4_write_checks(iocb, from);
@@ -188,16 +190,9 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out;
 
-	if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
-		overwrite = true;
-		downgrade_write(&inode->i_rwsem);
-	}
 	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 out:
-	if (!overwrite)
-		inode_unlock(inode);
-	else
-		inode_unlock_shared(inode);
+	inode_unlock(inode);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
 	return ret;
@@ -213,6 +208,9 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int overwrite = 0;
 	ssize_t ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 #ifdef CONFIG_FS_DAX
 	if (IS_DAX(inode))
 		return ext4_dax_write_iter(iocb, from);
@@ -348,6 +346,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_mapping->host;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (ext4_encrypted_inode(inode)) {
 		int err = fscrypt_get_encryption_info(inode);
 		if (err)
@@ -375,6 +376,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	char buf[64], *cp;
 	int ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
 		     !(sb->s_flags & MS_RDONLY))) {
 		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;

fs/ext4/fsync.c

@@ -100,6 +100,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	tid_t commit_tid;
 	bool needs_barrier = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
 	trace_ext4_sync_file_enter(file, datasync);

fs/ext4/hash.c

@@ -10,7 +10,8 @@
  */
 
 #include <linux/fs.h>
-#include <linux/cryptohash.h>
+#include <linux/compiler.h>
+#include <linux/bitops.h>
 #include "ext4.h"
 
 #define DELTA 0x9E3779B9
@@ -32,6 +33,74 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 	buf[1] += b1;
 }
 
+/* F, G and H are basic MD4 functions: selection, majority, parity */
+#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
+#define H(x, y, z) ((x) ^ (y) ^ (z))
+
+/*
+ * The generic round function.  The application is so specific that
+ * we don't bother protecting all the arguments with parens, as is generally
+ * good macro practice, in favor of extra legibility.
+ * Rotation is separate from addition to prevent recomputation
+ */
+#define ROUND(f, a, b, c, d, x, s)	\
+	(a += f(b, c, d) + x, a = rol32(a, s))
+#define K1 0
+#define K2 013240474631UL
+#define K3 015666365641UL
+
+/*
+ * Basic cut-down MD4 transform.  Returns only 32 bits of result.
+ */
+static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
+{
+	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
+
+	/* Round 1 */
+	ROUND(F, a, b, c, d, in[0] + K1,  3);
+	ROUND(F, d, a, b, c, in[1] + K1,  7);
+	ROUND(F, c, d, a, b, in[2] + K1, 11);
+	ROUND(F, b, c, d, a, in[3] + K1, 19);
+	ROUND(F, a, b, c, d, in[4] + K1,  3);
+	ROUND(F, d, a, b, c, in[5] + K1,  7);
+	ROUND(F, c, d, a, b, in[6] + K1, 11);
+	ROUND(F, b, c, d, a, in[7] + K1, 19);
+
+	/* Round 2 */
+	ROUND(G, a, b, c, d, in[1] + K2,  3);
+	ROUND(G, d, a, b, c, in[3] + K2,  5);
+	ROUND(G, c, d, a, b, in[5] + K2,  9);
+	ROUND(G, b, c, d, a, in[7] + K2, 13);
+	ROUND(G, a, b, c, d, in[0] + K2,  3);
+	ROUND(G, d, a, b, c, in[2] + K2,  5);
+	ROUND(G, c, d, a, b, in[4] + K2,  9);
+	ROUND(G, b, c, d, a, in[6] + K2, 13);
+
+	/* Round 3 */
+	ROUND(H, a, b, c, d, in[3] + K3,  3);
+	ROUND(H, d, a, b, c, in[7] + K3,  9);
+	ROUND(H, c, d, a, b, in[2] + K3, 11);
+	ROUND(H, b, c, d, a, in[6] + K3, 15);
+	ROUND(H, a, b, c, d, in[1] + K3,  3);
+	ROUND(H, d, a, b, c, in[5] + K3,  9);
+	ROUND(H, c, d, a, b, in[0] + K3, 11);
+	ROUND(H, b, c, d, a, in[4] + K3, 15);
+
+	buf[0] += a;
+	buf[1] += b;
+	buf[2] += c;
+	buf[3] += d;
+
+	return buf[1]; /* "most hashed" word */
+}
+#undef ROUND
+#undef K1
+#undef K2
+#undef K3
+#undef F
+#undef G
+#undef H
 
 /* The old legacy hash */
 static __u32 dx_hack_hash_unsigned(const char *name, int len)

fs/ext4/ialloc.c

@@ -764,6 +764,9 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	if (!dir || !dir->i_nlink)
 		return ERR_PTR(-EPERM);
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return ERR_PTR(-EIO);
+
 	if ((ext4_encrypted_inode(dir) ||
 	     DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
 	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {