These filesystems may be used for inspiration:
- ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt
+- ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
Shortcomings
i_version Enable 64-bit inode version support. This option is
off by default.
+dax Use direct access (no page cache). See
+ Documentation/filesystems/dax.txt. Note that
+ this option is incompatible with data=journal.
+
Data Mode
=========
There are 3 different data modes:
#define EXT4_MOUNT_ERRORS_MASK 0x00070
#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/
+#ifdef CONFIG_FS_DAX
+#define EXT4_MOUNT_DAX 0x00200 /* Direct Access */
+#else
+#define EXT4_MOUNT_DAX 0
+#endif
#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */
#define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */
#define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */
/* file.c */
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
+extern const struct file_operations ext4_dax_file_operations;
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
/* inline.c */
struct inode *inode = file_inode(iocb->ki_filp);
struct mutex *aio_mutex = NULL;
struct blk_plug plug;
- int o_direct = file->f_flags & O_DIRECT;
+ int o_direct = io_is_direct(file);
int overwrite = 0;
size_t length = iov_iter_count(from);
ssize_t ret;
return ret;
}
+#ifdef CONFIG_FS_DAX
+static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ return dax_fault(vma, vmf, ext4_get_block);
+ /* Is this the right get_block? */
+}
+
+static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ return dax_mkwrite(vma, vmf, ext4_get_block);
+}
+
+static const struct vm_operations_struct ext4_dax_vm_ops = {
+ .fault = ext4_dax_fault,
+ .page_mkwrite = ext4_dax_mkwrite,
+};
+#else
+#define ext4_dax_vm_ops ext4_file_vm_ops
+#endif
+
static const struct vm_operations_struct ext4_file_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
file_accessed(file);
- vma->vm_ops = &ext4_file_vm_ops;
+ if (IS_DAX(file_inode(file))) {
+ vma->vm_ops = &ext4_dax_vm_ops;
+ vma->vm_flags |= VM_MIXEDMAP;
+ } else {
+ vma->vm_ops = &ext4_file_vm_ops;
+ }
return 0;
}
.fallocate = ext4_fallocate,
};
+#ifdef CONFIG_FS_DAX
+const struct file_operations ext4_dax_file_operations = {
+ .llseek = ext4_llseek,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = ext4_file_write_iter,
+ .unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ext4_compat_ioctl,
+#endif
+ .mmap = ext4_file_mmap,
+ .open = ext4_file_open,
+ .release = ext4_release_file,
+ .fsync = ext4_sync_file,
+ /* Splice not yet supported with DAX */
+ .fallocate = ext4_fallocate,
+};
+#endif
+
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
.getattr = ext4_getattr,
inode_dio_done(inode);
goto locked;
}
- ret = __blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iter, offset,
- ext4_get_block, NULL, NULL, 0);
+ if (IS_DAX(inode))
+ ret = dax_do_io(rw, iocb, inode, iter, offset,
+ ext4_get_block, NULL, 0);
+ else
+ ret = __blockdev_direct_IO(rw, iocb, inode,
+ inode->i_sb->s_bdev, iter, offset,
+ ext4_get_block, NULL, NULL, 0);
inode_dio_done(inode);
} else {
locked:
- ret = blockdev_direct_IO(rw, iocb, inode, iter,
- offset, ext4_get_block);
+ if (IS_DAX(inode))
+ ret = dax_do_io(rw, iocb, inode, iter, offset,
+ ext4_get_block, NULL, DIO_LOCKING);
+ else
+ ret = blockdev_direct_IO(rw, iocb, inode, iter,
+ offset, ext4_get_block);
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
return retval;
}
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+ struct inode *inode = bh->b_assoc_map->host;
+ /* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+ loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+ int err;
+ if (!uptodate)
+ return;
+ WARN_ON(!buffer_unwritten(bh));
+ err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+ if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+ bh->b_assoc_map = inode->i_mapping;
+ bh->b_private = (void *)(unsigned long)iblock;
+ bh->b_end_io = ext4_end_io_unwritten;
+ }
if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
set_buffer_defer_completion(bh);
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
get_block_func = ext4_get_block_write;
dio_flags = DIO_LOCKING;
}
- ret = __blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iter,
- offset,
- get_block_func,
- ext4_end_io_dio,
- NULL,
- dio_flags);
+ if (IS_DAX(inode))
+ ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
+ ext4_end_io_dio, dio_flags);
+ else
+ ret = __blockdev_direct_IO(rw, iocb, inode,
+ inode->i_sb->s_bdev, iter, offset,
+ get_block_func,
+ ext4_end_io_dio, NULL, dio_flags);
/*
* Put our reference to io_end. This can free the io_end structure e.g.
inode->i_mapping->a_ops = &ext4_aops;
}
-/*
- * ext4_block_zero_page_range() zeros out a mapping of length 'length'
- * starting from file offset 'from'. The range to be zero'd must
- * be contained with in one block. If the specified range exceeds
- * the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
- */
-static int ext4_block_zero_page_range(handle_t *handle,
+static int __ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
- unsigned blocksize, max, pos;
+ unsigned blocksize, pos;
ext4_lblk_t iblock;
struct inode *inode = mapping->host;
struct buffer_head *bh;
return -ENOMEM;
blocksize = inode->i_sb->s_blocksize;
- max = blocksize - (offset & (blocksize - 1));
-
- /*
- * correct length if it does not fall between
- * 'from' and the end of the block
- */
- if (length > max || length < 0)
- length = max;
iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
return err;
}
+/*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'. The range to be zero'd must
+ * be contained with in one block. If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+static int ext4_block_zero_page_range(handle_t *handle,
+ struct address_space *mapping, loff_t from, loff_t length)
+{
+ struct inode *inode = mapping->host;
+ unsigned offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned blocksize = inode->i_sb->s_blocksize;
+ unsigned max = blocksize - (offset & (blocksize - 1));
+
+ /*
+ * correct length if it does not fall between
+ * 'from' and the end of the block
+ */
+ if (length > max || length < 0)
+ length = max;
+
+ if (IS_DAX(inode))
+ return dax_zero_page_range(inode, from, length, ext4_get_block);
+ return __ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
+ if (test_opt(inode->i_sb, DAX))
+ new_fl |= S_DAX;
inode_set_flags(inode, new_fl,
- S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+ S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
}
/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
- inode->i_fop = &ext4_file_operations;
+ if (test_opt(inode->i_sb, DAX))
+ inode->i_fop = &ext4_dax_file_operations;
+ else
+ inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &ext4_dir_inode_operations;
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
*/
- truncate_pagecache(inode, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
}
/*
* We want to call ext4_truncate() even if attr->ia_size ==
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &ext4_file_inode_operations;
- inode->i_fop = &ext4_file_operations;
+ if (test_opt(inode->i_sb, DAX))
+ inode->i_fop = &ext4_dax_file_operations;
+ else
+ inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
err = ext4_add_nondir(handle, dentry, inode);
if (!err && IS_DIRSYNC(dir))
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &ext4_file_inode_operations;
- inode->i_fop = &ext4_file_operations;
+ if (test_opt(inode->i_sb, DAX))
+ inode->i_fop = &ext4_dax_file_operations;
+ else
+ inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
d_tmpfile(dentry, inode);
err = ext4_orphan_add(handle, inode);
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
- Opt_usrquota, Opt_grpquota, Opt_i_version,
+ Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
{Opt_barrier, "barrier"},
{Opt_nobarrier, "nobarrier"},
{Opt_i_version, "i_version"},
+ {Opt_dax, "dax"},
{Opt_stripe, "stripe=%u"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_min_batch_time, 0, MOPT_GTE0},
{Opt_inode_readahead_blks, 0, MOPT_GTE0},
{Opt_init_itable, 0, MOPT_GTE0},
+ {Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
{Opt_stripe, 0, MOPT_GTE0},
{Opt_resuid, 0, MOPT_GTE0},
{Opt_resgid, 0, MOPT_GTE0},
return -1;
}
sbi->s_jquota_fmt = m->mount_opt;
+#endif
+#ifndef CONFIG_FS_DAX
+ } else if (token == Opt_dax) {
+ ext4_msg(sb, KERN_INFO, "dax option not supported");
+ return -1;
#endif
} else {
if (!args->from)
"both data=journal and dioread_nolock");
goto failed_mount;
}
+ if (test_opt(sb, DAX)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dax");
+ goto failed_mount;
+ }
if (test_opt(sb, DELALLOC))
clear_opt(sb, DELALLOC);
}
goto failed_mount;
}
+ if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+ if (blocksize != PAGE_SIZE) {
+ ext4_msg(sb, KERN_ERR,
+ "error: unsupported blocksize for dax");
+ goto failed_mount;
+ }
+ if (!sb->s_bdev->bd_disk->fops->direct_access) {
+ ext4_msg(sb, KERN_ERR,
+ "error: device does not support dax");
+ goto failed_mount;
+ }
+ }
+
if (sb->s_blocksize != blocksize) {
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
err = -EINVAL;
goto restore_opts;
}
+ if (test_opt(sb, DAX)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dax");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ }
+
+ if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
+ ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
+ "dax flag with busy inodes while remounting");
+ sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
}
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
projects / cascardo / linux.git / commitdiff