13 files changed, 112 insertions, 70 deletions

diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 1feb68ecef95..842d00048a65 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -94,25 +94,21 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev,
 {
         struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
         struct list_head *next;
-        struct dentry *p, *q;
+        struct dentry *q;
 
         spin_lock(&sbi->lookup_lock);
+        spin_lock(&root->d_lock);
 
-        if (prev == NULL) {
-                spin_lock(&root->d_lock);
+        if (prev)
+                next = prev->d_u.d_child.next;
+        else {
                 prev = dget_dlock(root);
                 next = prev->d_subdirs.next;
-                p = prev;
-                goto start;
         }
 
-        p = prev;
-        spin_lock(&p->d_lock);
-again:
-        next = p->d_u.d_child.next;
-start:
+cont:
         if (next == &root->d_subdirs) {
-                spin_unlock(&p->d_lock);
+                spin_unlock(&root->d_lock);
                 spin_unlock(&sbi->lookup_lock);
                 dput(prev);
                 return NULL;
@@ -121,16 +117,15 @@ start:
         q = list_entry(next, struct dentry, d_u.d_child);
 
         spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED);
-        /* Negative dentry - try next */
-        if (!simple_positive(q)) {
-                spin_unlock(&p->d_lock);
-                lock_set_subclass(&q->d_lock.dep_map, 0, _RET_IP_);
-                p = q;
-                goto again;
+        /* Already gone or negative dentry (under construction) - try next */
+        if (q->d_count == 0 || !simple_positive(q)) {
+                spin_unlock(&q->d_lock);
+                next = q->d_u.d_child.next;
+                goto cont;
         }
         dget_dlock(q);
         spin_unlock(&q->d_lock);
-        spin_unlock(&p->d_lock);
+        spin_unlock(&root->d_lock);
         spin_unlock(&sbi->lookup_lock);
 
         dput(prev);
@@ -404,11 +399,6 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
                         DPRINTK("checking mountpoint %p %.*s",
                                 dentry, (int)dentry->d_name.len, dentry->d_name.name);
 
-                        /* Path walk currently on this dentry? */
-                        ino_count = atomic_read(&ino->count) + 2;
-                        if (dentry->d_count > ino_count)
-                                goto next;
-
                         /* Can we umount this guy */
                         if (autofs4_mount_busy(mnt, dentry))
                                 goto next;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bc2f6ffff3cf..7bb755677a22 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -664,10 +664,6 @@ static noinline int btrfs_mksubvol(struct path *parent,
         struct dentry *dentry;
         int error;
 
-        error = mnt_want_write(parent->mnt);
-        if (error)
-                return error;
-
         mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
 
         dentry = lookup_one_len(name, parent->dentry, namelen);
@@ -703,7 +699,6 @@ out_dput:
         dput(dentry);
 out_unlock:
         mutex_unlock(&dir->i_mutex);
-        mnt_drop_write(parent->mnt);
         return error;
 }
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index d23b31ca9d7a..1b5089067d01 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -280,14 +280,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
         return desc;
 }
 
-static int ext4_valid_block_bitmap(struct super_block *sb,
-                                   struct ext4_group_desc *desc,
-                                   unsigned int block_group,
-                                   struct buffer_head *bh)
+/*
+ * Return the block number which was discovered to be invalid, or 0 if
+ * the block bitmap is valid.
+ */
+static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
+                                            struct ext4_group_desc *desc,
+                                            unsigned int block_group,
+                                            struct buffer_head *bh)
 {
         ext4_grpblk_t offset;
         ext4_grpblk_t next_zero_bit;
-        ext4_fsblk_t bitmap_blk;
+        ext4_fsblk_t blk;
         ext4_fsblk_t group_first_block;
 
         if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
@@ -297,37 +301,33 @@ static int ext4_valid_block_bitmap(struct super_block *sb,
                  * or it has to also read the block group where the bitmaps
                  * are located to verify they are set.
                  */
-                return 1;
+                return 0;
         }
         group_first_block = ext4_group_first_block_no(sb, block_group);
 
         /* check whether block bitmap block number is set */
-        bitmap_blk = ext4_block_bitmap(sb, desc);
-        offset = bitmap_blk - group_first_block;
+        blk = ext4_block_bitmap(sb, desc);
+        offset = blk - group_first_block;
         if (!ext4_test_bit(offset, bh->b_data))
                 /* bad block bitmap */
-                goto err_out;
+                return blk;
 
         /* check whether the inode bitmap block number is set */
-        bitmap_blk = ext4_inode_bitmap(sb, desc);
-        offset = bitmap_blk - group_first_block;
+        blk = ext4_inode_bitmap(sb, desc);
+        offset = blk - group_first_block;
         if (!ext4_test_bit(offset, bh->b_data))
                 /* bad block bitmap */
-                goto err_out;
+                return blk;
 
         /* check whether the inode table block number is set */
-        bitmap_blk = ext4_inode_table(sb, desc);
-        offset = bitmap_blk - group_first_block;
+        blk = ext4_inode_table(sb, desc);
+        offset = blk - group_first_block;
         next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
                                 offset + EXT4_SB(sb)->s_itb_per_group,
                                 offset);
-        if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
-                /* good bitmap for inode tables */
-                return 1;
-
-err_out:
-        ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu",
-                        block_group, bitmap_blk);
+        if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group)
+                /* bad bitmap for inode tables */
+                return blk;
         return 0;
 }
 
@@ -336,14 +336,26 @@ void ext4_validate_block_bitmap(struct super_block *sb,
                                unsigned int block_group,
                                struct buffer_head *bh)
 {
+        ext4_fsblk_t    blk;
+
         if (buffer_verified(bh))
                 return;
 
         ext4_lock_group(sb, block_group);
-        if (ext4_valid_block_bitmap(sb, desc, block_group, bh) &&
-            ext4_block_bitmap_csum_verify(sb, block_group, desc, bh,
-                                          EXT4_BLOCKS_PER_GROUP(sb) / 8))
-                set_buffer_verified(bh);
+        blk = ext4_valid_block_bitmap(sb, desc, block_group, bh);
+        if (unlikely(blk != 0)) {
+                ext4_unlock_group(sb, block_group);
+                ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
+                           block_group, blk);
+                return;
+        }
+        if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
+                        desc, bh, EXT4_BLOCKS_PER_GROUP(sb) / 8))) {
+                ext4_unlock_group(sb, block_group);
+                ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+                return;
+        }
+        set_buffer_verified(bh);
         ext4_unlock_group(sb, block_group);
 }
 
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index f8716eab9995..5c2d1813ebe9 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -79,7 +79,6 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
         if (provided == calculated)
                 return 1;
 
-        ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group);
         return 0;
 }
 
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index cd0c7ed06772..aabbb3f53683 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2662,6 +2662,7 @@ cont:
                 }
                 path[0].p_depth = depth;
                 path[0].p_hdr = ext_inode_hdr(inode);
+                i = 0;
 
                 if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
                         err = -EIO;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3e0851e4f468..c6e0cb3d1f4a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -948,6 +948,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
         ei->i_reserved_meta_blocks = 0;
         ei->i_allocated_meta_blocks = 0;
         ei->i_da_metadata_calc_len = 0;
+        ei->i_da_metadata_calc_last_lblock = 0;
         spin_lock_init(&(ei->i_block_reservation_lock));
 #ifdef CONFIG_QUOTA
         ei->i_reserved_quota = 0;
@@ -3108,6 +3109,10 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp,
         ext4_group_t            i, ngroups = ext4_get_groups_count(sb);
         int                     s, j, count = 0;
 
+        if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC))
+                return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) +
+                        sbi->s_itb_per_group + 2);
+
         first_block = le32_to_cpu(sbi->s_es->s_first_data_block) +
                 (grp * EXT4_BLOCKS_PER_GROUP(sb));
         last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1;
@@ -4419,6 +4424,7 @@ static void ext4_clear_journal_err(struct super_block *sb,
                 ext4_commit_super(sb, 1);
 
                 jbd2_journal_clear_err(journal);
+                jbd2_journal_update_sb_errno(journal);
         }
 }
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 8964cf3999b2..324bc0850534 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -383,6 +383,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
         struct fuse_entry_out outentry;
         struct fuse_file *ff;
 
+        /* Userspace expects S_IFREG in create mode */
+        BUG_ON((mode & S_IFMT) != S_IFREG);
+
         forget = fuse_alloc_forget();
         err = -ENOMEM;
         if (!forget)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 93d8d6c9494d..aba15f1b7ad2 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -703,13 +703,16 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
                                   unsigned long nr_segs, loff_t pos)
 {
         struct inode *inode = iocb->ki_filp->f_mapping->host;
+        struct fuse_conn *fc = get_fuse_conn(inode);
 
-        if (pos + iov_length(iov, nr_segs) > i_size_read(inode)) {
+        /*
+         * In auto invalidate mode, always update attributes on read.
+         * Otherwise, only update if we attempt to read past EOF (to ensure
+         * i_size is up to date).
+         */
+        if (fc->auto_inval_data ||
+            (pos + iov_length(iov, nr_segs) > i_size_read(inode))) {
                 int err;
-                /*
-                 * If trying to read past EOF, make sure the i_size
-                 * attribute is up-to-date.
-                 */
                 err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL);
                 if (err)
                         return err;
@@ -1700,7 +1703,7 @@ static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count)
         size_t n;
         u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT;
 
-        for (n = 0; n < count; n++) {
+        for (n = 0; n < count; n++, iov++) {
                 if (iov->iov_len > (size_t) max)
                         return -ENOMEM;
                 max -= iov->iov_len;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 771fb6322c07..e24dd74e3068 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -484,6 +484,9 @@ struct fuse_conn {
         /** Is fallocate not implemented by fs? */
         unsigned no_fallocate:1;
 
+        /** Use enhanced/automatic page cache invalidation. */
+        unsigned auto_inval_data:1;
+
         /** The number of requests waiting for completion */
         atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1cd61652018c..ce0a2838ccd0 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -197,6 +197,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
         struct fuse_conn *fc = get_fuse_conn(inode);
         struct fuse_inode *fi = get_fuse_inode(inode);
         loff_t oldsize;
+        struct timespec old_mtime;
 
         spin_lock(&fc->lock);
         if (attr_version != 0 && fi->attr_version > attr_version) {
@@ -204,15 +205,35 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
                 return;
         }
 
+        old_mtime = inode->i_mtime;
         fuse_change_attributes_common(inode, attr, attr_valid);
 
         oldsize = inode->i_size;
         i_size_write(inode, attr->size);
         spin_unlock(&fc->lock);
 
-        if (S_ISREG(inode->i_mode) && oldsize != attr->size) {
-                truncate_pagecache(inode, oldsize, attr->size);
-                invalidate_inode_pages2(inode->i_mapping);
+        if (S_ISREG(inode->i_mode)) {
+                bool inval = false;
+
+                if (oldsize != attr->size) {
+                        truncate_pagecache(inode, oldsize, attr->size);
+                        inval = true;
+                } else if (fc->auto_inval_data) {
+                        struct timespec new_mtime = {
+                                .tv_sec = attr->mtime,
+                                .tv_nsec = attr->mtimensec,
+                        };
+
+                        /*
+                         * Auto inval mode also checks and invalidates if mtime
+                         * has changed.
+                         */
+                        if (!timespec_equal(&old_mtime, &new_mtime))
+                                inval = true;
+                }
+
+                if (inval)
+                        invalidate_inode_pages2(inode->i_mapping);
         }
 }
 
@@ -834,6 +855,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
                                 fc->big_writes = 1;
                         if (arg->flags & FUSE_DONT_MASK)
                                 fc->dont_mask = 1;
+                        if (arg->flags & FUSE_AUTO_INVAL_DATA)
+                                fc->auto_inval_data = 1;
                 } else {
                         ra_pages = fc->max_read / PAGE_CACHE_SIZE;
                         fc->no_lock = 1;
@@ -859,7 +882,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
         arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
         arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
                 FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
-                FUSE_FLOCK_LOCKS;
+                FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
+                FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA;
         req->in.h.opcode = FUSE_INIT;
         req->in.numargs = 1;
         req->in.args[0].size = sizeof(*arg);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 8625da27eccf..e149b99a7ffb 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1377,7 +1377,7 @@ static void jbd2_mark_journal_empty(journal_t *journal)
  * Update a journal's errno.  Write updated superblock to disk waiting for IO
  * to complete.
  */
-static void jbd2_journal_update_sb_errno(journal_t *journal)
+void jbd2_journal_update_sb_errno(journal_t *journal)
 {
         journal_superblock_t *sb = journal->j_superblock;
 
@@ -1390,6 +1390,7 @@ static void jbd2_journal_update_sb_errno(journal_t *journal)
 
         jbd2_write_superblock(journal, WRITE_SYNC);
 }
+EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
 
 /*
  * Read the superblock for a given journal, performing initial
diff --git a/fs/namei.c b/fs/namei.c
index 1b464390dde8..db76b866a097 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2414,7 +2414,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
                 goto out;
         }
 
-        mode = op->mode & S_IALLUGO;
+        mode = op->mode;
         if ((open_flag & O_CREAT) && !IS_POSIXACL(dir))
                 mode &= ~current_umask();
 
@@ -2452,7 +2452,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
         }
 
         if (open_flag & O_CREAT) {
-                error = may_o_create(&nd->path, dentry, op->mode);
+                error = may_o_create(&nd->path, dentry, mode);
                 if (error) {
                         create_error = error;
                         if (open_flag & O_EXCL)
@@ -2489,6 +2489,10 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
                         dput(dentry);
                         dentry = file->f_path.dentry;
                 }
+                if (create_error && dentry->d_inode == NULL) {
+                        error = create_error;
+                        goto out;
+                }
                 goto looked_up;
         }
 
diff --git a/fs/open.c b/fs/open.c
index bc132e167d2d..e1f2cdb91a4d 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -852,9 +852,10 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
         int lookup_flags = 0;
         int acc_mode;
 
-        if (!(flags & O_CREAT))
-                mode = 0;
-        op->mode = mode;
+        if (flags & O_CREAT)
+                op->mode = (mode & S_IALLUGO) | S_IFREG;
+        else
+                op->mode = 0;
 
         /* Must never be set by userspace */
         flags &= ~FMODE_NONOTIFY;