ext4: add the basic function for inline data support
Implement inline data with xattr.
Now we use "system.data" to store xattr, and the xattr will
be extended if the i_size is increased while we don't release
the space during truncate.
Signed-off-by: Tao Ma <boyu.mt@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 41f22be..3d96d56 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -9,6 +9,6 @@
ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
mmp.o indirect.o extents_status.o
-ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
+ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o inline.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2e9ffa9..c827e47 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -402,6 +402,7 @@
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
+#define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */
@@ -458,6 +459,7 @@
EXT4_INODE_EXTENTS = 19, /* Inode uses extents */
EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */
+ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */
EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
};
@@ -504,6 +506,7 @@
CHECK_FLAG_VALUE(EXTENTS);
CHECK_FLAG_VALUE(EA_INODE);
CHECK_FLAG_VALUE(EOFBLOCKS);
+ CHECK_FLAG_VALUE(INLINE_DATA);
CHECK_FLAG_VALUE(RESERVED);
}
@@ -918,6 +921,10 @@
/* on-disk additional length */
__u16 i_extra_isize;
+ /* Indicate the inline data space. */
+ u16 i_inline_off;
+ u16 i_inline_size;
+
#ifdef CONFIG_QUOTA
/* quota space reservation, managed internally by quota code */
qsize_t i_reserved_quota;
@@ -1376,6 +1383,7 @@
EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */
EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read
nolocking */
+ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
};
#define EXT4_INODE_BIT_FNS(name, field, offset) \
@@ -1497,7 +1505,7 @@
#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */
#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */
#define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */
-#define EXT4_FEATURE_INCOMPAT_INLINEDATA 0x8000 /* data in inode */
+#define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */
#define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
new file mode 100644
index 0000000..bec68b3
--- /dev/null
+++ b/fs/ext4/inline.c
@@ -0,0 +1,466 @@
+/*
+ * Copyright (c) 2012 Taobao.
+ * Written by Tao Ma <boyu.mt@taobao.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "xattr.h"
+
+#define EXT4_XATTR_SYSTEM_DATA "data"
+#define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS))
+
+int ext4_get_inline_size(struct inode *inode)
+{
+ if (EXT4_I(inode)->i_inline_off)
+ return EXT4_I(inode)->i_inline_size;
+
+ return 0;
+}
+
+static int get_max_inline_xattr_value_size(struct inode *inode,
+ struct ext4_iloc *iloc)
+{
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_xattr_entry *entry;
+ struct ext4_inode *raw_inode;
+ int free, min_offs;
+
+ min_offs = EXT4_SB(inode->i_sb)->s_inode_size -
+ EXT4_GOOD_OLD_INODE_SIZE -
+ EXT4_I(inode)->i_extra_isize -
+ sizeof(struct ext4_xattr_ibody_header);
+
+ /*
+ * We need to subtract another sizeof(__u32) since an in-inode xattr
+ * needs an empty 4 bytes to indicate the gap between the xattr entry
+ * and the name/value pair.
+ */
+ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
+ return EXT4_XATTR_SIZE(min_offs -
+ EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)) -
+ EXT4_XATTR_ROUND - sizeof(__u32));
+
+ raw_inode = ext4_raw_inode(iloc);
+ header = IHDR(inode, raw_inode);
+ entry = IFIRST(header);
+
+ /* Compute min_offs. */
+ for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+ if (!entry->e_value_block && entry->e_value_size) {
+ size_t offs = le16_to_cpu(entry->e_value_offs);
+ if (offs < min_offs)
+ min_offs = offs;
+ }
+ }
+ free = min_offs -
+ ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32);
+
+ if (EXT4_I(inode)->i_inline_off) {
+ entry = (struct ext4_xattr_entry *)
+ ((void *)raw_inode + EXT4_I(inode)->i_inline_off);
+
+ free += le32_to_cpu(entry->e_value_size);
+ goto out;
+ }
+
+ free -= EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA));
+
+ if (free > EXT4_XATTR_ROUND)
+ free = EXT4_XATTR_SIZE(free - EXT4_XATTR_ROUND);
+ else
+ free = 0;
+
+out:
+ return free;
+}
+
+/*
+ * Get the maximum size we now can store in an inode.
+ * If we can't find the space for a xattr entry, don't use the space
+ * of the extents since we have no space to indicate the inline data.
+ */
+int ext4_get_max_inline_size(struct inode *inode)
+{
+ int error, max_inline_size;
+ struct ext4_iloc iloc;
+
+ if (EXT4_I(inode)->i_extra_isize == 0)
+ return 0;
+
+ error = ext4_get_inode_loc(inode, &iloc);
+ if (error) {
+ ext4_error_inode(inode, __func__, __LINE__, 0,
+ "can't get inode location %lu",
+ inode->i_ino);
+ return 0;
+ }
+
+ down_read(&EXT4_I(inode)->xattr_sem);
+ max_inline_size = get_max_inline_xattr_value_size(inode, &iloc);
+ up_read(&EXT4_I(inode)->xattr_sem);
+
+ brelse(iloc.bh);
+
+ if (!max_inline_size)
+ return 0;
+
+ return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE;
+}
+
+int ext4_has_inline_data(struct inode *inode)
+{
+ return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
+ EXT4_I(inode)->i_inline_off;
+}
+
+/*
+ * this function does not take xattr_sem, which is OK because it is
+ * currently only used in a code path coming form ext4_iget, before
+ * the new inode has been unlocked
+ */
+int ext4_find_inline_data_nolock(struct inode *inode)
+{
+ struct ext4_xattr_ibody_find is = {
+ .s = { .not_found = -ENODATA, },
+ };
+ struct ext4_xattr_info i = {
+ .name_index = EXT4_XATTR_INDEX_SYSTEM,
+ .name = EXT4_XATTR_SYSTEM_DATA,
+ };
+ int error;
+
+ if (EXT4_I(inode)->i_extra_isize == 0)
+ return 0;
+
+ error = ext4_get_inode_loc(inode, &is.iloc);
+ if (error)
+ return error;
+
+ error = ext4_xattr_ibody_find(inode, &i, &is);
+ if (error)
+ goto out;
+
+ if (!is.s.not_found) {
+ EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
+ (void *)ext4_raw_inode(&is.iloc));
+ EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
+ le32_to_cpu(is.s.here->e_value_size);
+ ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+ }
+out:
+ brelse(is.iloc.bh);
+ return error;
+}
+
+static int ext4_read_inline_data(struct inode *inode, void *buffer,
+ unsigned int len,
+ struct ext4_iloc *iloc)
+{
+ struct ext4_xattr_entry *entry;
+ struct ext4_xattr_ibody_header *header;
+ int cp_len = 0;
+ struct ext4_inode *raw_inode;
+
+ if (!len)
+ return 0;
+
+ BUG_ON(len > EXT4_I(inode)->i_inline_size);
+
+ cp_len = len < EXT4_MIN_INLINE_DATA_SIZE ?
+ len : EXT4_MIN_INLINE_DATA_SIZE;
+
+ raw_inode = ext4_raw_inode(iloc);
+ memcpy(buffer, (void *)(raw_inode->i_block), cp_len);
+
+ len -= cp_len;
+ buffer += cp_len;
+
+ if (!len)
+ goto out;
+
+ header = IHDR(inode, raw_inode);
+ entry = (struct ext4_xattr_entry *)((void *)raw_inode +
+ EXT4_I(inode)->i_inline_off);
+ len = min_t(unsigned int, len,
+ (unsigned int)le32_to_cpu(entry->e_value_size));
+
+ memcpy(buffer,
+ (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs), len);
+ cp_len += len;
+
+out:
+ return cp_len;
+}
+
+/*
+ * write the buffer to the inline inode.
+ * If 'create' is set, we don't need to do the extra copy in the xattr
+ * value since it is already handled by ext4_xattr_ibody_set. That saves
+ * us one memcpy.
+ */
+void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
+ void *buffer, loff_t pos, unsigned int len)
+{
+ struct ext4_xattr_entry *entry;
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_inode *raw_inode;
+ int cp_len = 0;
+
+ BUG_ON(!EXT4_I(inode)->i_inline_off);
+ BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
+
+ raw_inode = ext4_raw_inode(iloc);
+ buffer += pos;
+
+ if (pos < EXT4_MIN_INLINE_DATA_SIZE) {
+ cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ?
+ EXT4_MIN_INLINE_DATA_SIZE - pos : len;
+ memcpy((void *)raw_inode->i_block + pos, buffer, cp_len);
+
+ len -= cp_len;
+ buffer += cp_len;
+ pos += cp_len;
+ }
+
+ if (!len)
+ return;
+
+ pos -= EXT4_MIN_INLINE_DATA_SIZE;
+ header = IHDR(inode, raw_inode);
+ entry = (struct ext4_xattr_entry *)((void *)raw_inode +
+ EXT4_I(inode)->i_inline_off);
+
+ memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos,
+ buffer, len);
+}
+
+static int ext4_create_inline_data(handle_t *handle,
+ struct inode *inode, unsigned len)
+{
+ int error;
+ void *value = NULL;
+ struct ext4_xattr_ibody_find is = {
+ .s = { .not_found = -ENODATA, },
+ };
+ struct ext4_xattr_info i = {
+ .name_index = EXT4_XATTR_INDEX_SYSTEM,
+ .name = EXT4_XATTR_SYSTEM_DATA,
+ };
+
+ error = ext4_get_inode_loc(inode, &is.iloc);
+ if (error)
+ return error;
+
+ error = ext4_journal_get_write_access(handle, is.iloc.bh);
+ if (error)
+ goto out;
+
+ if (len > EXT4_MIN_INLINE_DATA_SIZE) {
+ value = (void *)empty_zero_page;
+ len -= EXT4_MIN_INLINE_DATA_SIZE;
+ } else {
+ value = "";
+ len = 0;
+ }
+
+ /* Insert the the xttr entry. */
+ i.value = value;
+ i.value_len = len;
+
+ error = ext4_xattr_ibody_find(inode, &i, &is);
+ if (error)
+ goto out;
+
+ BUG_ON(!is.s.not_found);
+
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ if (error) {
+ if (error == -ENOSPC)
+ ext4_clear_inode_state(inode,
+ EXT4_STATE_MAY_INLINE_DATA);
+ goto out;
+ }
+
+ memset((void *)ext4_raw_inode(&is.iloc)->i_block,
+ 0, EXT4_MIN_INLINE_DATA_SIZE);
+
+ EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
+ (void *)ext4_raw_inode(&is.iloc));
+ EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE;
+ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
+ ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA);
+ get_bh(is.iloc.bh);
+ error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
+
+out:
+ brelse(is.iloc.bh);
+ return error;
+}
+
+static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len)
+{
+ int error;
+ void *value = NULL;
+ struct ext4_xattr_ibody_find is = {
+ .s = { .not_found = -ENODATA, },
+ };
+ struct ext4_xattr_info i = {
+ .name_index = EXT4_XATTR_INDEX_SYSTEM,
+ .name = EXT4_XATTR_SYSTEM_DATA,
+ };
+
+ /* If the old space is ok, write the data directly. */
+ if (len <= EXT4_I(inode)->i_inline_size)
+ return 0;
+
+ error = ext4_get_inode_loc(inode, &is.iloc);
+ if (error)
+ return error;
+
+ error = ext4_xattr_ibody_find(inode, &i, &is);
+ if (error)
+ goto out;
+
+ BUG_ON(is.s.not_found);
+
+ len -= EXT4_MIN_INLINE_DATA_SIZE;
+ value = kzalloc(len, GFP_NOFS);
+ if (!value)
+ goto out;
+
+ error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
+ value, len);
+ if (error == -ENODATA)
+ goto out;
+
+ error = ext4_journal_get_write_access(handle, is.iloc.bh);
+ if (error)
+ goto out;
+
+ /* Update the xttr entry. */
+ i.value = value;
+ i.value_len = len;
+
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ if (error)
+ goto out;
+
+ EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
+ (void *)ext4_raw_inode(&is.iloc));
+ EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
+ le32_to_cpu(is.s.here->e_value_size);
+ ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+ get_bh(is.iloc.bh);
+ error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
+
+out:
+ kfree(value);
+ brelse(is.iloc.bh);
+ return error;
+}
+
+int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len)
+{
+ int ret, size;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+ if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
+ return -ENOSPC;
+
+ size = ext4_get_max_inline_size(inode);
+ if (size < len)
+ return -ENOSPC;
+
+ down_write(&EXT4_I(inode)->xattr_sem);
+
+ if (ei->i_inline_off)
+ ret = ext4_update_inline_data(handle, inode, len);
+ else
+ ret = ext4_create_inline_data(handle, inode, len);
+
+ up_write(&EXT4_I(inode)->xattr_sem);
+
+ return ret;
+}
+
+static int ext4_destroy_inline_data_nolock(handle_t *handle,
+ struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_xattr_ibody_find is = {
+ .s = { .not_found = 0, },
+ };
+ struct ext4_xattr_info i = {
+ .name_index = EXT4_XATTR_INDEX_SYSTEM,
+ .name = EXT4_XATTR_SYSTEM_DATA,
+ .value = NULL,
+ .value_len = 0,
+ };
+ int error;
+
+ if (!ei->i_inline_off)
+ return 0;
+
+ error = ext4_get_inode_loc(inode, &is.iloc);
+ if (error)
+ return error;
+
+ error = ext4_xattr_ibody_find(inode, &i, &is);
+ if (error)
+ goto out;
+
+ error = ext4_journal_get_write_access(handle, is.iloc.bh);
+ if (error)
+ goto out;
+
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ if (error)
+ goto out;
+
+ memset((void *)ext4_raw_inode(&is.iloc)->i_block,
+ 0, EXT4_MIN_INLINE_DATA_SIZE);
+
+ if (EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+ if (S_ISDIR(inode->i_mode) ||
+ S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) {
+ ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
+ ext4_ext_tree_init(handle, inode);
+ }
+ }
+ ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
+
+ get_bh(is.iloc.bh);
+ error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
+
+ EXT4_I(inode)->i_inline_off = 0;
+ EXT4_I(inode)->i_inline_size = 0;
+ ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+out:
+ brelse(is.iloc.bh);
+ if (error == -ENODATA)
+ error = 0;
+ return error;
+}
+
+int ext4_destroy_inline_data(handle_t *handle, struct inode *inode)
+{
+ int ret;
+
+ down_write(&EXT4_I(inode)->xattr_sem);
+ ret = ext4_destroy_inline_data_nolock(handle, inode);
+ up_write(&EXT4_I(inode)->xattr_sem);
+
+ return ret;
+}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index befa005..e23f114 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3706,8 +3706,10 @@
{
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
- if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
+ if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
+ ext4_find_inline_data_nolock(inode);
+ }
}
struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
@@ -3780,6 +3782,7 @@
set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
+ ei->i_inline_off = 0;
ei->i_dir_start_lookup = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 40ca7a6..7ae0d05 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -21,6 +21,7 @@
#define EXT4_XATTR_INDEX_TRUSTED 4
#define EXT4_XATTR_INDEX_LUSTRE 5
#define EXT4_XATTR_INDEX_SECURITY 6
+#define EXT4_XATTR_INDEX_SYSTEM 7
struct ext4_xattr_header {
__le32 h_magic; /* magic number for identification */
@@ -125,6 +126,19 @@
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is);
+extern int ext4_has_inline_data(struct inode *inode);
+extern int ext4_get_inline_size(struct inode *inode);
+extern int ext4_get_max_inline_size(struct inode *inode);
+extern int ext4_find_inline_data_nolock(struct inode *inode);
+extern void ext4_write_inline_data(struct inode *inode,
+ struct ext4_iloc *iloc,
+ void *buffer, loff_t pos,
+ unsigned int len);
+extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len);
+extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len);
+extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
# else /* CONFIG_EXT4_FS_XATTR */
static inline int
@@ -201,6 +215,46 @@
return -EOPNOTSUPP;
}
+static inline int ext4_find_inline_data_nolock(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int ext4_has_inline_data(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int ext4_get_inline_size(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int ext4_get_max_inline_size(struct inode *inode)
+{
+ return 0;
+}
+
+static inline void ext4_write_inline_data(struct inode *inode,
+ struct ext4_iloc *iloc,
+ void *buffer, loff_t pos,
+ unsigned int len)
+{
+ return;
+}
+
+static inline int ext4_init_inline_data(handle_t *handle,
+ struct inode *inode,
+ unsigned int len)
+{
+ return 0;
+}
+
+static inline int ext4_destroy_inline_data(handle_t *handle,
+ struct inode *inode)
+{
+ return 0;
+}
# endif /* CONFIG_EXT4_FS_XATTR */
#ifdef CONFIG_EXT4_FS_SECURITY