summaryrefslogtreecommitdiff
path: root/fs/ext2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext2')
-rw-r--r--fs/ext2/Kconfig35
-rw-r--r--fs/ext2/Makefile7
-rw-r--r--fs/ext2/acl.c232
-rw-r--r--fs/ext2/acl.h12
-rw-r--r--fs/ext2/balloc.c289
-rw-r--r--fs/ext2/dir.c463
-rw-r--r--fs/ext2/ext2.h122
-rw-r--r--fs/ext2/file.c306
-rw-r--r--fs/ext2/ialloc.c43
-rw-r--r--fs/ext2/inode.c500
-rw-r--r--fs/ext2/ioctl.c115
-rw-r--r--fs/ext2/namei.c269
-rw-r--r--fs/ext2/super.c1053
-rw-r--r--fs/ext2/symlink.c28
-rw-r--r--fs/ext2/trace.c6
-rw-r--r--fs/ext2/trace.h94
-rw-r--r--fs/ext2/xattr.c504
-rw-r--r--fs/ext2/xattr.h29
-rw-r--r--fs/ext2/xattr_security.c41
-rw-r--r--fs/ext2/xattr_trusted.c39
-rw-r--r--fs/ext2/xattr_user.c43
-rw-r--r--fs/ext2/xip.c90
-rw-r--r--fs/ext2/xip.h26
23 files changed, 2313 insertions, 2033 deletions
diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig
index 14a6780fd034..d5bce83ad905 100644
--- a/fs/ext2/Kconfig
+++ b/fs/ext2/Kconfig
@@ -1,20 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0-only
config EXT2_FS
- tristate "Second extended fs support"
+ tristate "Second extended fs support (DEPRECATED)"
+ select BUFFER_HEAD
+ select FS_IOMAP
help
Ext2 is a standard Linux file system for hard disks.
- To compile this file system support as a module, choose M here: the
- module will be called ext2.
+ This filesystem driver is deprecated because it does not properly
+ support inode time stamps beyond 03:14:07 UTC on 19 January 2038.
- If unsure, say Y.
+ Ext2 users are advised to use ext4 driver to access their filesystem.
+ The driver is fully compatible, supports filesystems without journal
+ or extents, and also supports larger time stamps if the filesystem
+ is created with at least 256 byte inodes.
+
+ This code is kept as a simple reference for filesystem developers.
+
+ If unsure, say N.
config EXT2_FS_XATTR
bool "Ext2 extended attributes"
depends on EXT2_FS
help
Extended attributes are name:value pairs associated with inodes by
- the kernel or by users (see the attr(5) manual page, or visit
- <http://acl.bestbits.at/> for details).
+ the kernel or by users (see the attr(5) manual page for details).
If unsure, say N.
@@ -26,9 +35,6 @@ config EXT2_FS_POSIX_ACL
Posix Access Control Lists (ACLs) support permissions for users and
groups beyond the owner/group/world scheme.
- To learn more about Access Control Lists, visit the Posix ACLs for
- Linux website <http://acl.bestbits.at/>.
-
If you don't know what Access Control Lists are, say N
config EXT2_FS_SECURITY
@@ -42,14 +48,3 @@ config EXT2_FS_SECURITY
If you are not using a security module that requires using
extended attributes for file security labels, say N.
-
-config EXT2_FS_XIP
- bool "Ext2 execute in place support"
- depends on EXT2_FS && MMU
- help
- Execute in place can be used on memory-backed block devices. If you
- enable this option, you can select to mount block devices which are
- capable of this feature without using the page cache.
-
- If you do not use a block device that is capable of using this,
- or if unsure, say N.
diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile
index f42af45cfd88..8860948ef9ca 100644
--- a/fs/ext2/Makefile
+++ b/fs/ext2/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
#
# Makefile for the linux ext2-filesystem routines.
#
@@ -5,9 +6,11 @@
obj-$(CONFIG_EXT2_FS) += ext2.o
ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
- ioctl.o namei.o super.o symlink.o
+ ioctl.o namei.o super.o symlink.o trace.o
+
+# For tracepoints to include our trace.h from tracepoint infrastructure
+CFLAGS_trace.o := -I$(src)
ext2-$(CONFIG_EXT2_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o
ext2-$(CONFIG_EXT2_FS_SECURITY) += xattr_security.o
-ext2-$(CONFIG_EXT2_FS_XIP) += xip.o
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 110b6b371a4e..7e54c31589c7 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -1,10 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/acl.c
*
* Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
*/
-#include <linux/capability.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
@@ -141,19 +141,15 @@ fail:
* inode->i_mutex: don't care
*/
struct posix_acl *
-ext2_get_acl(struct inode *inode, int type)
+ext2_get_acl(struct inode *inode, int type, bool rcu)
{
int name_index;
char *value = NULL;
struct posix_acl *acl;
int retval;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return NULL;
-
- acl = get_cached_acl(inode, type);
- if (acl != ACL_NOT_CACHED)
- return acl;
+ if (rcu)
+ return ERR_PTR(-ECHILD);
switch (type) {
case ACL_TYPE_ACCESS:
@@ -180,42 +176,20 @@ ext2_get_acl(struct inode *inode, int type)
acl = ERR_PTR(retval);
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
-
return acl;
}
-/*
- * inode->i_mutex: down
- */
static int
-ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
+__ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
int name_index;
void *value = NULL;
size_t size = 0;
int error;
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return 0;
-
switch(type) {
case ACL_TYPE_ACCESS:
name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
- if (acl) {
- error = posix_acl_equiv_mode(acl, &inode->i_mode);
- if (error < 0)
- return error;
- else {
- inode->i_ctime = CURRENT_TIME_SEC;
- mark_inode_dirty(inode);
- if (error == 0)
- acl = NULL;
- }
- }
break;
case ACL_TYPE_DEFAULT:
@@ -242,177 +216,61 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
}
/*
- * Initialize the ACLs of a new inode. Called from ext2_new_inode.
- *
- * dir->i_mutex: down
- * inode->i_mutex: up (access to inode is still exclusive)
+ * inode->i_mutex: down
*/
int
-ext2_init_acl(struct inode *inode, struct inode *dir)
+ext2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+ struct posix_acl *acl, int type)
{
- struct posix_acl *acl = NULL;
- int error = 0;
-
- if (!S_ISLNK(inode->i_mode)) {
- if (test_opt(dir->i_sb, POSIX_ACL)) {
- acl = ext2_get_acl(dir, ACL_TYPE_DEFAULT);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- }
- if (!acl)
- inode->i_mode &= ~current_umask();
- }
- if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
- if (S_ISDIR(inode->i_mode)) {
- error = ext2_set_acl(inode, ACL_TYPE_DEFAULT, acl);
- if (error)
- goto cleanup;
- }
- error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode);
- if (error < 0)
+ int error;
+ int update_mode = 0;
+ struct inode *inode = d_inode(dentry);
+ umode_t mode = inode->i_mode;
+
+ if (type == ACL_TYPE_ACCESS && acl) {
+ error = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode,
+ &acl);
+ if (error)
return error;
- if (error > 0) {
- /* This is an extended ACL */
- error = ext2_set_acl(inode, ACL_TYPE_ACCESS, acl);
- }
+ update_mode = 1;
+ }
+ error = __ext2_set_acl(inode, acl, type);
+ if (!error && update_mode) {
+ inode->i_mode = mode;
+ inode_set_ctime_current(inode);
+ mark_inode_dirty(inode);
}
-cleanup:
- posix_acl_release(acl);
- return error;
+ return error;
}
/*
- * Does chmod for an inode that may have an Access Control List. The
- * inode->i_mode field must be updated to the desired value by the caller
- * before calling this function.
- * Returns 0 on success, or a negative error number.
- *
- * We change the ACL rather than storing some ACL entries in the file
- * mode permission bits (which would be more efficient), because that
- * would break once additional permissions (like ACL_APPEND, ACL_DELETE
- * for directories) are added. There are no more bits available in the
- * file mode.
+ * Initialize the ACLs of a new inode. Called from ext2_new_inode.
*
- * inode->i_mutex: down
+ * dir->i_mutex: down
+ * inode->i_mutex: up (access to inode is still exclusive)
*/
int
-ext2_acl_chmod(struct inode *inode)
+ext2_init_acl(struct inode *inode, struct inode *dir)
{
- struct posix_acl *acl;
- int error;
+ struct posix_acl *default_acl, *acl;
+ int error;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return 0;
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
- acl = ext2_get_acl(inode, ACL_TYPE_ACCESS);
- if (IS_ERR(acl) || !acl)
- return PTR_ERR(acl);
- error = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+ error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
if (error)
return error;
- error = ext2_set_acl(inode, ACL_TYPE_ACCESS, acl);
- posix_acl_release(acl);
- return error;
-}
-/*
- * Extended attribut handlers
- */
-static size_t
-ext2_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_size,
- const char *name, size_t name_len, int type)
-{
- const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
-
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return 0;
- if (list && size <= list_size)
- memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
- return size;
-}
-
-static size_t
-ext2_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_size,
- const char *name, size_t name_len, int type)
-{
- const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
-
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return 0;
- if (list && size <= list_size)
- memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
- return size;
-}
-
-static int
-ext2_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
- size_t size, int type)
-{
- struct posix_acl *acl;
- int error;
-
- if (strcmp(name, "") != 0)
- return -EINVAL;
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return -EOPNOTSUPP;
-
- acl = ext2_get_acl(dentry->d_inode, type);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (acl == NULL)
- return -ENODATA;
- error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
- posix_acl_release(acl);
-
- return error;
-}
-
-static int
-ext2_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags, int type)
-{
- struct posix_acl *acl;
- int error;
-
- if (strcmp(name, "") != 0)
- return -EINVAL;
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return -EOPNOTSUPP;
- if (!inode_owner_or_capable(dentry->d_inode))
- return -EPERM;
-
- if (value) {
- acl = posix_acl_from_xattr(&init_user_ns, value, size);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- else if (acl) {
- error = posix_acl_valid(acl);
- if (error)
- goto release_and_out;
- }
- } else
- acl = NULL;
-
- error = ext2_set_acl(dentry->d_inode, type, acl);
-
-release_and_out:
- posix_acl_release(acl);
+ if (default_acl) {
+ error = __ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+ posix_acl_release(default_acl);
+ } else {
+ inode->i_default_acl = NULL;
+ }
+ if (acl) {
+ if (!error)
+ error = __ext2_set_acl(inode, acl, ACL_TYPE_ACCESS);
+ posix_acl_release(acl);
+ } else {
+ inode->i_acl = NULL;
+ }
return error;
}
-
-const struct xattr_handler ext2_xattr_acl_access_handler = {
- .prefix = POSIX_ACL_XATTR_ACCESS,
- .flags = ACL_TYPE_ACCESS,
- .list = ext2_xattr_list_acl_access,
- .get = ext2_xattr_get_acl,
- .set = ext2_xattr_set_acl,
-};
-
-const struct xattr_handler ext2_xattr_acl_default_handler = {
- .prefix = POSIX_ACL_XATTR_DEFAULT,
- .flags = ACL_TYPE_DEFAULT,
- .list = ext2_xattr_list_acl_default,
- .get = ext2_xattr_get_acl,
- .set = ext2_xattr_set_acl,
-};
diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h
index 503bfb0ed79b..4a8443a2b8ec 100644
--- a/fs/ext2/acl.h
+++ b/fs/ext2/acl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
File: fs/ext2/acl.h
@@ -54,8 +55,9 @@ static inline int ext2_acl_count(size_t size)
#ifdef CONFIG_EXT2_FS_POSIX_ACL
/* acl.c */
-extern struct posix_acl *ext2_get_acl(struct inode *inode, int type);
-extern int ext2_acl_chmod (struct inode *);
+extern struct posix_acl *ext2_get_acl(struct inode *inode, int type, bool rcu);
+extern int ext2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+ struct posix_acl *acl, int type);
extern int ext2_init_acl (struct inode *, struct inode *);
#else
@@ -63,12 +65,6 @@ extern int ext2_init_acl (struct inode *, struct inode *);
#define ext2_get_acl NULL
#define ext2_set_acl NULL
-static inline int
-ext2_acl_chmod (struct inode *inode)
-{
- return 0;
-}
-
static inline int ext2_init_acl (struct inode *inode, struct inode *dir)
{
return 0;
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 9f9992b37924..b8cfab8f98b9 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/balloc.c
*
@@ -15,6 +16,7 @@
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/sched.h>
+#include <linux/cred.h>
#include <linux/buffer_head.h>
#include <linux/capability.h>
@@ -34,8 +36,6 @@
*/
-#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
-
struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh)
@@ -46,10 +46,9 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
struct ext2_sb_info *sbi = EXT2_SB(sb);
if (block_group >= sbi->s_groups_count) {
- ext2_error (sb, "ext2_get_group_desc",
- "block_group >= groups_count - "
- "block_group = %d, groups_count = %lu",
- block_group, sbi->s_groups_count);
+ WARN(1, "block_group >= groups_count - "
+ "block_group = %d, groups_count = %lu",
+ block_group, sbi->s_groups_count);
return NULL;
}
@@ -57,10 +56,9 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
group_desc = block_group >> EXT2_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT2_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
- ext2_error (sb, "ext2_get_group_desc",
- "Group descriptor not loaded - "
- "block_group = %d, group_desc = %lu, desc = %lu",
- block_group, group_desc, offset);
+ WARN(1, "Group descriptor not loaded - "
+ "block_group = %d, group_desc = %lu, desc = %lu",
+ block_group, group_desc, offset);
return NULL;
}
@@ -79,26 +77,33 @@ static int ext2_valid_block_bitmap(struct super_block *sb,
ext2_grpblk_t next_zero_bit;
ext2_fsblk_t bitmap_blk;
ext2_fsblk_t group_first_block;
+ ext2_grpblk_t max_bit;
group_first_block = ext2_group_first_block_no(sb, block_group);
+ max_bit = ext2_group_last_block_no(sb, block_group) - group_first_block;
/* check whether block bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
offset = bitmap_blk - group_first_block;
- if (!ext2_test_bit(offset, bh->b_data))
+ if (offset < 0 || offset > max_bit ||
+ !ext2_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
offset = bitmap_blk - group_first_block;
- if (!ext2_test_bit(offset, bh->b_data))
+ if (offset < 0 || offset > max_bit ||
+ !ext2_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode table block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_table);
offset = bitmap_blk - group_first_block;
+ if (offset < 0 || offset > max_bit ||
+ offset + EXT2_SB(sb)->s_itb_per_group - 1 > max_bit)
+ goto err_out;
next_zero_bit = ext2_find_next_zero_bit(bh->b_data,
offset + EXT2_SB(sb)->s_itb_per_group,
offset);
@@ -126,6 +131,7 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
struct ext2_group_desc * desc;
struct buffer_head * bh = NULL;
ext2_fsblk_t bitmap_blk;
+ int ret;
desc = ext2_get_group_desc(sb, block_group, NULL);
if (!desc)
@@ -139,10 +145,10 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
block_group, le32_to_cpu(desc->bg_block_bitmap));
return NULL;
}
- if (likely(bh_uptodate_or_lock(bh)))
+ ret = bh_read(bh, 0);
+ if (ret > 0)
return bh;
-
- if (bh_submit_read(bh) < 0) {
+ if (ret < 0) {
brelse(bh);
ext2_error(sb, __func__,
"Cannot read block bitmap - "
@@ -187,7 +193,7 @@ static void group_adjust_blocks(struct super_block *sb, int group_no,
/**
* __rsv_window_dump() -- Dump the filesystem block allocation reservation map
- * @rb_root: root of per-filesystem reservation rb tree
+ * @root: root of per-filesystem reservation rb tree
* @verbose: verbose mode
* @fn: function which wishes to dump the reservation map
*
@@ -267,7 +273,7 @@ goal_in_my_reservation(struct ext2_reserve_window *rsv, ext2_grpblk_t grp_goal,
ext2_fsblk_t group_first_block, group_last_block;
group_first_block = ext2_group_first_block_no(sb, group);
- group_last_block = group_first_block + EXT2_BLOCKS_PER_GROUP(sb) - 1;
+ group_last_block = ext2_group_last_block_no(sb, group);
if ((rsv->_rsv_start > group_last_block) ||
(rsv->_rsv_end < group_first_block))
@@ -280,7 +286,7 @@ goal_in_my_reservation(struct ext2_reserve_window *rsv, ext2_grpblk_t grp_goal,
/**
* search_reserve_window()
- * @rb_root: root of reservation tree
+ * @root: root of reservation tree
* @goal: target allocation block
*
* Find the reserved window which includes the goal, or the previous one
@@ -413,7 +419,7 @@ void ext2_init_block_alloc_info(struct inode *inode)
struct ext2_block_alloc_info *block_i;
struct super_block *sb = inode->i_sb;
- block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
+ block_i = kmalloc(sizeof(*block_i), GFP_KERNEL);
if (block_i) {
struct ext2_reserve_window_node *rsv = &block_i->rsv_window_node;
@@ -473,8 +479,8 @@ void ext2_discard_reservation(struct inode *inode)
* @block: start physical block to free
* @count: number of blocks to free
*/
-void ext2_free_blocks (struct inode * inode, unsigned long block,
- unsigned long count)
+void ext2_free_blocks(struct inode * inode, ext2_fsblk_t block,
+ unsigned long count)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head * bh2;
@@ -488,9 +494,7 @@ void ext2_free_blocks (struct inode * inode, unsigned long block,
struct ext2_super_block * es = sbi->s_es;
unsigned freed = 0, group_freed;
- if (block < le32_to_cpu(es->s_first_data_block) ||
- block + count < block ||
- block + count > le32_to_cpu(es->s_blocks_count)) {
+ if (!ext2_data_block_valid(sbi, block, count)) {
ext2_error (sb, "ext2_free_blocks",
"Freeing blocks not in datazone - "
"block = %lu, count = %lu", block, count);
@@ -546,7 +550,7 @@ do_more:
}
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
group_adjust_blocks(sb, block_group, desc, bh2, group_freed);
@@ -666,37 +670,24 @@ ext2_try_to_allocate(struct super_block *sb, int group,
unsigned long *count,
struct ext2_reserve_window *my_rsv)
{
- ext2_fsblk_t group_first_block;
- ext2_grpblk_t start, end;
+ ext2_fsblk_t group_first_block = ext2_group_first_block_no(sb, group);
+ ext2_fsblk_t group_last_block = ext2_group_last_block_no(sb, group);
+ ext2_grpblk_t start, end;
unsigned long num = 0;
+ start = 0;
+ end = group_last_block - group_first_block + 1;
/* we do allocation within the reservation window if we have a window */
if (my_rsv) {
- group_first_block = ext2_group_first_block_no(sb, group);
if (my_rsv->_rsv_start >= group_first_block)
start = my_rsv->_rsv_start - group_first_block;
- else
- /* reservation window cross group boundary */
- start = 0;
- end = my_rsv->_rsv_end - group_first_block + 1;
- if (end > EXT2_BLOCKS_PER_GROUP(sb))
- /* reservation window crosses group boundary */
- end = EXT2_BLOCKS_PER_GROUP(sb);
- if ((start <= grp_goal) && (grp_goal < end))
- start = grp_goal;
- else
+ if (my_rsv->_rsv_end < group_last_block)
+ end = my_rsv->_rsv_end - group_first_block + 1;
+ if (grp_goal < start || grp_goal >= end)
grp_goal = -1;
- } else {
- if (grp_goal > 0)
- start = grp_goal;
- else
- start = 0;
- end = EXT2_BLOCKS_PER_GROUP(sb);
}
-
BUG_ON(start > EXT2_BLOCKS_PER_GROUP(sb));
-repeat:
if (grp_goal < 0) {
grp_goal = find_next_usable_block(start, bitmap_bh, end);
if (grp_goal < 0)
@@ -711,67 +702,55 @@ repeat:
;
}
}
- start = grp_goal;
- if (ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group), grp_goal,
- bitmap_bh->b_data)) {
- /*
- * The block was allocated by another thread, or it was
- * allocated and then freed by another thread
- */
- start++;
- grp_goal++;
- if (start >= end)
- goto fail_access;
- goto repeat;
- }
- num++;
- grp_goal++;
- while (num < *count && grp_goal < end
- && !ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group),
+ for (; num < *count && grp_goal < end; grp_goal++) {
+ if (ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group),
grp_goal, bitmap_bh->b_data)) {
+ if (num == 0)
+ continue;
+ break;
+ }
num++;
- grp_goal++;
}
+
+ if (num == 0)
+ goto fail_access;
+
*count = num;
return grp_goal - num;
fail_access:
- *count = num;
return -1;
}
/**
- * find_next_reservable_window():
- * find a reservable space within the given range.
- * It does not allocate the reservation window for now:
- * alloc_new_reservation() will do the work later.
- *
- * @search_head: the head of the searching list;
- * This is not necessarily the list head of the whole filesystem
+ * find_next_reservable_window - Find a reservable space within the given range.
+ * @search_head: The list to search.
+ * @my_rsv: The reservation we're currently using.
+ * @sb: The super block.
+ * @start_block: The first block we consider to start the real search from
+ * @last_block: The maximum block number that our goal reservable space
+ * could start from.
*
- * We have both head and start_block to assist the search
- * for the reservable space. The list starts from head,
- * but we will shift to the place where start_block is,
- * then start from there, when looking for a reservable space.
+ * It does not allocate the reservation window: alloc_new_reservation()
+ * will do the work later.
*
- * @size: the target new reservation window size
+ * We search the given range, rather than the whole reservation double
+ * linked list, (start_block, last_block) to find a free region that is
+ * of my size and has not been reserved.
*
- * @group_first_block: the first block we consider to start
- * the real search from
+ * @search_head is not necessarily the list head of the whole filesystem.
+ * We have both head and @start_block to assist the search for the
+ * reservable space. The list starts from head, but we will shift to
+ * the place where start_block is, then start from there, when looking
+ * for a reservable space.
*
- * @last_block:
- * the maximum block number that our goal reservable space
- * could start from. This is normally the last block in this
- * group. The search will end when we found the start of next
- * possible reservable space is out of this boundary.
- * This could handle the cross boundary reservation window
- * request.
- *
- * basically we search from the given range, rather than the whole
- * reservation double linked list, (start_block, last_block)
- * to find a free region that is of my size and has not
- * been reserved.
+ * @last_block is normally the last block in this group. The search will end
+ * when we found the start of next possible reservable space is out
+ * of this boundary. This could handle the cross boundary reservation
+ * window request.
*
+ * Return: -1 if we could not find a range of sufficient size. If we could,
+ * return 0 and fill in @my_rsv with the range information.
*/
static int find_next_reservable_window(
struct ext2_reserve_window_node *search_head,
@@ -859,41 +838,34 @@ static int find_next_reservable_window(
}
/**
- * alloc_new_reservation()--allocate a new reservation window
- *
- * To make a new reservation, we search part of the filesystem
- * reservation list (the list that inside the group). We try to
- * allocate a new reservation window near the allocation goal,
- * or the beginning of the group, if there is no goal.
- *
- * We first find a reservable space after the goal, then from
- * there, we check the bitmap for the first free block after
- * it. If there is no free block until the end of group, then the
- * whole group is full, we failed. Otherwise, check if the free
- * block is inside the expected reservable space, if so, we
- * succeed.
- * If the first free block is outside the reservable space, then
- * start from the first free block, we search for next available
- * space, and go on.
+ * alloc_new_reservation - Allocate a new reservation window.
+ * @my_rsv: The reservation we're currently using.
+ * @grp_goal: The goal block relative to the start of the group.
+ * @sb: The super block.
+ * @group: The group we are trying to allocate in.
+ * @bitmap_bh: The block group block bitmap.
*
- * on succeed, a new reservation will be found and inserted into the list
- * It contains at least one free block, and it does not overlap with other
- * reservation windows.
+ * To make a new reservation, we search part of the filesystem reservation
+ * list (the list inside the group). We try to allocate a new
+ * reservation window near @grp_goal, or the beginning of the
+ * group, if @grp_goal is negative.
*
- * failed: we failed to find a reservation window in this group
+ * We first find a reservable space after the goal, then from there,
+ * we check the bitmap for the first free block after it. If there is
+ * no free block until the end of group, then the whole group is full,
+ * we failed. Otherwise, check if the free block is inside the expected
+ * reservable space, if so, we succeed.
*
- * @rsv: the reservation
+ * If the first free block is outside the reservable space, then start
+ * from the first free block, we search for next available space, and
+ * go on.
*
- * @grp_goal: The goal (group-relative). It is where the search for a
- * free reservable space should start from.
- * if we have a goal(goal >0 ), then start from there,
- * no goal(goal = -1), we start from the first block
- * of the group.
- *
- * @sb: the super block
- * @group: the group we are trying to allocate in
- * @bitmap_bh: the block group block bitmap
+ * on succeed, a new reservation will be found and inserted into the
+ * list. It contains at least one free block, and it does not overlap
+ * with other reservation windows.
*
+ * Return: 0 on success, -1 if we failed to find a reservation window
+ * in this group
*/
static int alloc_new_reservation(struct ext2_reserve_window_node *my_rsv,
ext2_grpblk_t grp_goal, struct super_block *sb,
@@ -908,7 +880,7 @@ static int alloc_new_reservation(struct ext2_reserve_window_node *my_rsv,
spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock;
group_first_block = ext2_group_first_block_no(sb, group);
- group_end_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+ group_end_block = ext2_group_last_block_no(sb, group);
if (grp_goal < 0)
start_block = group_first_block;
@@ -1115,7 +1087,7 @@ ext2_try_to_allocate_with_rsv(struct super_block *sb, unsigned int group,
* first block is the block number of the first block in this group
*/
group_first_block = ext2_group_first_block_no(sb, group);
- group_last_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+ group_last_block = ext2_group_last_block_no(sb, group);
/*
* Basically we will allocate a new block from inode's reservation
@@ -1157,8 +1129,13 @@ ext2_try_to_allocate_with_rsv(struct super_block *sb, unsigned int group,
if ((my_rsv->rsv_start > group_last_block) ||
(my_rsv->rsv_end < group_first_block)) {
+ ext2_error(sb, __func__,
+ "Reservation out of group %u range goal %d fsb[%lu,%lu] rsv[%lu, %lu]",
+ group, grp_goal, group_first_block,
+ group_last_block, my_rsv->rsv_start,
+ my_rsv->rsv_end);
rsv_window_dump(&EXT2_SB(sb)->s_rsv_window_root, 1);
- BUG();
+ return -1;
}
ret = ext2_try_to_allocate(sb, group, bitmap_bh, grp_goal,
&num, &my_rsv->rsv_window);
@@ -1194,11 +1171,32 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
}
/*
+ * Returns 1 if the passed-in block region is valid; 0 if some part overlaps
+ * with filesystem metadata blocks.
+ */
+int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk,
+ unsigned int count)
+{
+ if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+ (start_blk + count - 1 < start_blk) ||
+ (start_blk + count - 1 >= le32_to_cpu(sbi->s_es->s_blocks_count)))
+ return 0;
+
+ /* Ensure we do not step over superblock */
+ if ((start_blk <= sbi->s_sb_block) &&
+ (start_blk + count - 1 >= sbi->s_sb_block))
+ return 0;
+
+ return 1;
+}
+
+/*
* ext2_new_blocks() -- core block(s) allocation function
* @inode: file inode
* @goal: given target block(filesystem wide)
* @count: target number of blocks to allocate
* @errp: error code
+ * @flags: allocate flags
*
* ext2_new_blocks uses a goal block to assist allocation. If the goal is
* free, or there is a free block within 32 blocks of the goal, that block
@@ -1208,7 +1206,7 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
* This function also updates quota and i_blocks field.
*/
ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal,
- unsigned long *count, int *errp)
+ unsigned long *count, int *errp, unsigned int flags)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gdp_bh;
@@ -1247,15 +1245,15 @@ ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal,
es = EXT2_SB(sb)->s_es;
ext2_debug("goal=%lu.\n", goal);
/*
- * Allocate a block from reservation only when
- * filesystem is mounted with reservation(default,-o reservation), and
- * it's a regular file, and
- * the desired window size is greater than 0 (One could use ioctl
- * command EXT2_IOC_SETRSVSZ to set the window size to 0 to turn off
- * reservation on that particular file)
+ * Allocate a block from reservation only when the filesystem is
+ * mounted with reservation(default,-o reservation), and it's a regular
+ * file, and the desired window size is greater than 0 (One could use
+ * ioctl command EXT2_IOC_SETRSVSZ to set the window size to 0 to turn
+ * off reservation on that particular file). Also do not use the
+ * reservation window if the caller asked us not to do it.
*/
block_i = EXT2_I(inode)->i_block_alloc_info;
- if (block_i) {
+ if (!(flags & EXT2_ALLOC_NORESERVE) && block_i) {
windowsz = block_i->rsv_window_node.rsv_goal_size;
if (windowsz > 0)
my_rsv = &block_i->rsv_window_node;
@@ -1293,6 +1291,13 @@ retry_alloc:
if (free_blocks > 0) {
grp_target_blk = ((goal - le32_to_cpu(es->s_first_data_block)) %
EXT2_BLOCKS_PER_GROUP(sb));
+ /*
+ * In case we retry allocation (due to fs reservation not
+ * working out or fs corruption), the bitmap_bh is non-null
+ * pointer and we have to release it before calling
+ * read_block_bitmap().
+ */
+ brelse(bitmap_bh);
bitmap_bh = read_block_bitmap(sb, group_no);
if (!bitmap_bh)
goto io_error;
@@ -1384,6 +1389,7 @@ allocated:
* use. So we may want to selectively mark some of the blocks
* as free
*/
+ num = *count;
goto retry_alloc;
}
@@ -1401,7 +1407,7 @@ allocated:
percpu_counter_sub(&sbi->s_freeblocks_counter, num);
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
*errp = 0;
@@ -1427,13 +1433,6 @@ out:
return 0;
}
-ext2_fsblk_t ext2_new_block(struct inode *inode, unsigned long goal, int *errp)
-{
- unsigned long count = 1;
-
- return ext2_new_blocks(inode, goal, &count, errp);
-}
-
#ifdef EXT2FS_DEBUG
unsigned long ext2_count_free(struct buffer_head *map, unsigned int numchars)
@@ -1477,11 +1476,11 @@ unsigned long ext2_count_free_blocks (struct super_block * sb)
desc_count, bitmap_count);
return bitmap_count;
#else
- for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
- desc = ext2_get_group_desc (sb, i, NULL);
- if (!desc)
- continue;
- desc_count += le16_to_cpu(desc->bg_free_blocks_count);
+ for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+ desc = ext2_get_group_desc(sb, i, NULL);
+ if (!desc)
+ continue;
+ desc_count += le16_to_cpu(desc->bg_free_blocks_count);
}
return desc_count;
#endif
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 6e1d4ab09d72..b07b3b369710 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/dir.c
*
@@ -25,6 +26,7 @@
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
+#include <linux/iversion.h>
typedef struct ext2_dir_entry_2 ext2_dirent;
@@ -37,7 +39,7 @@ static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
{
unsigned len = le16_to_cpu(dlen);
-#if (PAGE_CACHE_SIZE >= 65536)
+#if (PAGE_SIZE >= 65536)
if (len == EXT2_MAX_REC_LEN)
return 1 << 16;
#endif
@@ -46,7 +48,7 @@ static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
static inline __le16 ext2_rec_len_to_disk(unsigned len)
{
-#if (PAGE_CACHE_SIZE >= 65536)
+#if (PAGE_SIZE >= 65536)
if (len == (1 << 16))
return cpu_to_le16(EXT2_MAX_REC_LEN);
else
@@ -64,17 +66,6 @@ static inline unsigned ext2_chunk_size(struct inode *inode)
return inode->i_sb->s_blocksize;
}
-static inline void ext2_put_page(struct page *page)
-{
- kunmap(page);
- page_cache_release(page);
-}
-
-static inline unsigned long dir_pages(struct inode *inode)
-{
- return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
/*
* Return the offset into page `page_nr' of the last valid
* byte in that page, plus one.
@@ -84,51 +75,40 @@ ext2_last_byte(struct inode *inode, unsigned long page_nr)
{
unsigned last_byte = inode->i_size;
- last_byte -= page_nr << PAGE_CACHE_SHIFT;
- if (last_byte > PAGE_CACHE_SIZE)
- last_byte = PAGE_CACHE_SIZE;
+ last_byte -= page_nr << PAGE_SHIFT;
+ if (last_byte > PAGE_SIZE)
+ last_byte = PAGE_SIZE;
return last_byte;
}
-static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
+static void ext2_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
struct inode *dir = mapping->host;
- int err = 0;
- dir->i_version++;
- block_write_end(NULL, mapping, pos, len, len, page, NULL);
+ inode_inc_iversion(dir);
+ block_write_end(pos, len, len, folio);
if (pos+len > dir->i_size) {
i_size_write(dir, pos+len);
mark_inode_dirty(dir);
}
-
- if (IS_DIRSYNC(dir)) {
- err = write_one_page(page, 1);
- if (!err)
- err = sync_inode_metadata(dir, 1);
- } else {
- unlock_page(page);
- }
-
- return err;
+ folio_unlock(folio);
}
-static void ext2_check_page(struct page *page, int quiet)
+static bool ext2_check_folio(struct folio *folio, int quiet, char *kaddr)
{
- struct inode *dir = page->mapping->host;
+ struct inode *dir = folio->mapping->host;
struct super_block *sb = dir->i_sb;
unsigned chunk_size = ext2_chunk_size(dir);
- char *kaddr = page_address(page);
u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
unsigned offs, rec_len;
- unsigned limit = PAGE_CACHE_SIZE;
+ unsigned limit = folio_size(folio);
ext2_dirent *p;
char *error;
- if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
- limit = dir->i_size & ~PAGE_CACHE_MASK;
+ if (dir->i_size < folio_pos(folio) + limit) {
+ limit = offset_in_folio(folio, dir->i_size);
if (limit & (chunk_size - 1))
goto Ebadsize;
if (!limit)
@@ -152,8 +132,8 @@ static void ext2_check_page(struct page *page, int quiet)
if (offs != limit)
goto Eend;
out:
- SetPageChecked(page);
- return;
+ folio_set_checked(folio);
+ return true;
/* Too bad, we had an error */
@@ -180,41 +160,51 @@ Einumber:
bad_entry:
if (!quiet)
ext2_error(sb, __func__, "bad entry in directory #%lu: : %s - "
- "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
- dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+ "offset=%llu, inode=%lu, rec_len=%d, name_len=%d",
+ dir->i_ino, error, folio_pos(folio) + offs,
(unsigned long) le32_to_cpu(p->inode),
rec_len, p->name_len);
goto fail;
Eend:
if (!quiet) {
p = (ext2_dirent *)(kaddr + offs);
- ext2_error(sb, "ext2_check_page",
+ ext2_error(sb, "ext2_check_folio",
"entry in directory #%lu spans the page boundary"
- "offset=%lu, inode=%lu",
- dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+ "offset=%llu, inode=%lu",
+ dir->i_ino, folio_pos(folio) + offs,
(unsigned long) le32_to_cpu(p->inode));
}
fail:
- SetPageChecked(page);
- SetPageError(page);
+ return false;
}
-static struct page * ext2_get_page(struct inode *dir, unsigned long n,
- int quiet)
+/*
+ * Calls to ext2_get_folio()/folio_release_kmap() must be nested according
+ * to the rules documented in kmap_local_folio()/kunmap_local().
+ *
+ * NOTE: ext2_find_entry() and ext2_dotdot() act as a call
+ * to folio_release_kmap() and should be treated as a call to
+ * folio_release_kmap() for nesting purposes.
+ */
+static void *ext2_get_folio(struct inode *dir, unsigned long n,
+ int quiet, struct folio **foliop)
{
struct address_space *mapping = dir->i_mapping;
- struct page *page = read_mapping_page(mapping, n, NULL);
- if (!IS_ERR(page)) {
- kmap(page);
- if (!PageChecked(page))
- ext2_check_page(page, quiet);
- if (PageError(page))
+ struct folio *folio = read_mapping_folio(mapping, n, NULL);
+ void *kaddr;
+
+ if (IS_ERR(folio))
+ return ERR_CAST(folio);
+ kaddr = kmap_local_folio(folio, 0);
+ if (unlikely(!folio_test_checked(folio))) {
+ if (!ext2_check_folio(folio, quiet, kaddr))
goto fail;
}
- return page;
+ *foliop = folio;
+ return kaddr;
fail:
- ext2_put_page(page);
+ folio_release_kmap(folio, kaddr);
return ERR_PTR(-EIO);
}
@@ -252,36 +242,13 @@ ext2_validate_entry(char *base, unsigned offset, unsigned mask)
break;
p = ext2_next_entry(p);
}
- return (char *)p - base;
+ return offset_in_page(p);
}
-static unsigned char ext2_filetype_table[EXT2_FT_MAX] = {
- [EXT2_FT_UNKNOWN] = DT_UNKNOWN,
- [EXT2_FT_REG_FILE] = DT_REG,
- [EXT2_FT_DIR] = DT_DIR,
- [EXT2_FT_CHRDEV] = DT_CHR,
- [EXT2_FT_BLKDEV] = DT_BLK,
- [EXT2_FT_FIFO] = DT_FIFO,
- [EXT2_FT_SOCK] = DT_SOCK,
- [EXT2_FT_SYMLINK] = DT_LNK,
-};
-
-#define S_SHIFT 12
-static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = {
- [S_IFREG >> S_SHIFT] = EXT2_FT_REG_FILE,
- [S_IFDIR >> S_SHIFT] = EXT2_FT_DIR,
- [S_IFCHR >> S_SHIFT] = EXT2_FT_CHRDEV,
- [S_IFBLK >> S_SHIFT] = EXT2_FT_BLKDEV,
- [S_IFIFO >> S_SHIFT] = EXT2_FT_FIFO,
- [S_IFSOCK >> S_SHIFT] = EXT2_FT_SOCK,
- [S_IFLNK >> S_SHIFT] = EXT2_FT_SYMLINK,
-};
-
static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode)
{
- umode_t mode = inode->i_mode;
if (EXT2_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT2_FEATURE_INCOMPAT_FILETYPE))
- de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
+ de->file_type = fs_umode_to_ftype(inode->i_mode);
else
de->file_type = 0;
}
@@ -292,39 +259,39 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
loff_t pos = ctx->pos;
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
- unsigned int offset = pos & ~PAGE_CACHE_MASK;
- unsigned long n = pos >> PAGE_CACHE_SHIFT;
+ unsigned int offset = pos & ~PAGE_MASK;
+ unsigned long n = pos >> PAGE_SHIFT;
unsigned long npages = dir_pages(inode);
unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
- unsigned char *types = NULL;
- int need_revalidate = file->f_version != inode->i_version;
+ bool need_revalidate = !inode_eq_iversion(inode, *(u64 *)file->private_data);
+ bool has_filetype;
if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
return 0;
- if (EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE))
- types = ext2_filetype_table;
+ has_filetype =
+ EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE);
for ( ; n < npages; n++, offset = 0) {
- char *kaddr, *limit;
ext2_dirent *de;
- struct page *page = ext2_get_page(inode, n, 0);
+ struct folio *folio;
+ char *kaddr = ext2_get_folio(inode, n, 0, &folio);
+ char *limit;
- if (IS_ERR(page)) {
+ if (IS_ERR(kaddr)) {
ext2_error(sb, __func__,
"bad page in #%lu",
inode->i_ino);
- ctx->pos += PAGE_CACHE_SIZE - offset;
- return PTR_ERR(page);
+ ctx->pos += PAGE_SIZE - offset;
+ return PTR_ERR(kaddr);
}
- kaddr = page_address(page);
if (unlikely(need_revalidate)) {
if (offset) {
offset = ext2_validate_entry(kaddr, offset, chunk_mask);
- ctx->pos = (n<<PAGE_CACHE_SHIFT) + offset;
+ ctx->pos = (n<<PAGE_SHIFT) + offset;
}
- file->f_version = inode->i_version;
- need_revalidate = 0;
+ *(u64 *)file->private_data = inode_query_iversion(inode);
+ need_revalidate = false;
}
de = (ext2_dirent *)(kaddr+offset);
limit = kaddr + ext2_last_byte(inode, n) - EXT2_DIR_REC_LEN(1);
@@ -332,25 +299,25 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
if (de->rec_len == 0) {
ext2_error(sb, __func__,
"zero-length directory entry");
- ext2_put_page(page);
+ folio_release_kmap(folio, de);
return -EIO;
}
if (de->inode) {
unsigned char d_type = DT_UNKNOWN;
- if (types && de->file_type < EXT2_FT_MAX)
- d_type = types[de->file_type];
+ if (has_filetype)
+ d_type = fs_ftype_to_dtype(de->file_type);
if (!dir_emit(ctx, de->name, de->name_len,
le32_to_cpu(de->inode),
d_type)) {
- ext2_put_page(page);
+ folio_release_kmap(folio, de);
return 0;
}
}
ctx->pos += ext2_rec_len_from_disk(de->rec_len);
}
- ext2_put_page(page);
+ folio_release_kmap(folio, kaddr);
}
return 0;
}
@@ -362,56 +329,58 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
* returns the page in which the entry was found (as a parameter - res_page),
* and the entry itself. Page is returned mapped and unlocked.
* Entry is guaranteed to be valid.
+ *
+ * On Success folio_release_kmap() should be called on *foliop.
+ *
+ * NOTE: Calls to ext2_get_folio()/folio_release_kmap() must be nested
+ * according to the rules documented in kmap_local_folio()/kunmap_local().
+ *
+ * ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_folio()
+ * and should be treated as a call to ext2_get_folio() for nesting
+ * purposes.
*/
-struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir,
- struct qstr *child, struct page ** res_page)
+struct ext2_dir_entry_2 *ext2_find_entry (struct inode *dir,
+ const struct qstr *child, struct folio **foliop)
{
const char *name = child->name;
int namelen = child->len;
unsigned reclen = EXT2_DIR_REC_LEN(namelen);
unsigned long start, n;
unsigned long npages = dir_pages(dir);
- struct page *page = NULL;
struct ext2_inode_info *ei = EXT2_I(dir);
ext2_dirent * de;
- int dir_has_error = 0;
if (npages == 0)
goto out;
- /* OFFSET_CACHE */
- *res_page = NULL;
-
start = ei->i_dir_start_lookup;
if (start >= npages)
start = 0;
n = start;
do {
- char *kaddr;
- page = ext2_get_page(dir, n, dir_has_error);
- if (!IS_ERR(page)) {
- kaddr = page_address(page);
- de = (ext2_dirent *) kaddr;
- kaddr += ext2_last_byte(dir, n) - reclen;
- while ((char *) de <= kaddr) {
- if (de->rec_len == 0) {
- ext2_error(dir->i_sb, __func__,
- "zero-length directory entry");
- ext2_put_page(page);
- goto out;
- }
- if (ext2_match (namelen, name, de))
- goto found;
- de = ext2_next_entry(de);
+ char *kaddr = ext2_get_folio(dir, n, 0, foliop);
+ if (IS_ERR(kaddr))
+ return ERR_CAST(kaddr);
+
+ de = (ext2_dirent *) kaddr;
+ kaddr += ext2_last_byte(dir, n) - reclen;
+ while ((char *) de <= kaddr) {
+ if (de->rec_len == 0) {
+ ext2_error(dir->i_sb, __func__,
+ "zero-length directory entry");
+ folio_release_kmap(*foliop, de);
+ goto out;
}
- ext2_put_page(page);
- } else
- dir_has_error = 1;
+ if (ext2_match(namelen, name, de))
+ goto found;
+ de = ext2_next_entry(de);
+ }
+ folio_release_kmap(*foliop, kaddr);
if (++n >= npages)
n = 0;
- /* next page is past the blocks we've got */
- if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
+ /* next folio is past the blocks we've got */
+ if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) {
ext2_error(dir->i_sb, __func__,
"dir %lu size %lld exceeds block count %llu",
dir->i_ino, dir->i_size,
@@ -420,65 +389,85 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir,
}
} while (n != start);
out:
- return NULL;
+ return ERR_PTR(-ENOENT);
found:
- *res_page = page;
ei->i_dir_start_lookup = n;
return de;
}
-struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
+/*
+ * Return the '..' directory entry and the page in which the entry was found
+ * (as a parameter - p).
+ *
+ * On Success folio_release_kmap() should be called on *foliop.
+ *
+ * NOTE: Calls to ext2_get_folio()/folio_release_kmap() must be nested
+ * according to the rules documented in kmap_local_folio()/kunmap_local().
+ *
+ * ext2_find_entry() and ext2_dotdot() act as a call to ext2_get_folio()
+ * and should be treated as a call to ext2_get_folio() for nesting
+ * purposes.
+ */
+struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct folio **foliop)
{
- struct page *page = ext2_get_page(dir, 0, 0);
- ext2_dirent *de = NULL;
+ ext2_dirent *de = ext2_get_folio(dir, 0, 0, foliop);
- if (!IS_ERR(page)) {
- de = ext2_next_entry((ext2_dirent *) page_address(page));
- *p = page;
- }
- return de;
+ if (!IS_ERR(de))
+ return ext2_next_entry(de);
+ return NULL;
}
-ino_t ext2_inode_by_name(struct inode *dir, struct qstr *child)
+int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino)
{
- ino_t res = 0;
struct ext2_dir_entry_2 *de;
- struct page *page;
-
- de = ext2_find_entry (dir, child, &page);
- if (de) {
- res = le32_to_cpu(de->inode);
- ext2_put_page(page);
- }
- return res;
+ struct folio *folio;
+
+ de = ext2_find_entry(dir, child, &folio);
+ if (IS_ERR(de))
+ return PTR_ERR(de);
+
+ *ino = le32_to_cpu(de->inode);
+ folio_release_kmap(folio, de);
+ return 0;
}
-static int ext2_prepare_chunk(struct page *page, loff_t pos, unsigned len)
+static int ext2_prepare_chunk(struct folio *folio, loff_t pos, unsigned len)
{
- return __block_write_begin(page, pos, len, ext2_get_block);
+ return __block_write_begin(folio, pos, len, ext2_get_block);
+}
+
+static int ext2_handle_dirsync(struct inode *dir)
+{
+ int err;
+
+ err = filemap_write_and_wait(dir->i_mapping);
+ if (!err)
+ err = sync_inode_metadata(dir, 1);
+ return err;
}
-/* Releases the page */
-void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
- struct page *page, struct inode *inode, int update_times)
+int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
+ struct folio *folio, struct inode *inode, bool update_times)
{
- loff_t pos = page_offset(page) +
- (char *) de - (char *) page_address(page);
+ loff_t pos = folio_pos(folio) + offset_in_folio(folio, de);
unsigned len = ext2_rec_len_from_disk(de->rec_len);
int err;
- lock_page(page);
- err = ext2_prepare_chunk(page, pos, len);
- BUG_ON(err);
+ folio_lock(folio);
+ err = ext2_prepare_chunk(folio, pos, len);
+ if (err) {
+ folio_unlock(folio);
+ return err;
+ }
de->inode = cpu_to_le32(inode->i_ino);
ext2_set_de_type(de, inode);
- err = ext2_commit_chunk(page, pos, len);
- ext2_put_page(page);
+ ext2_commit_chunk(folio, pos, len);
if (update_times)
- dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
mark_inode_dirty(dir);
+ return ext2_handle_dirsync(dir);
}
/*
@@ -486,37 +475,34 @@ void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
*/
int ext2_add_link (struct dentry *dentry, struct inode *inode)
{
- struct inode *dir = dentry->d_parent->d_inode;
+ struct inode *dir = d_inode(dentry->d_parent);
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
unsigned chunk_size = ext2_chunk_size(dir);
unsigned reclen = EXT2_DIR_REC_LEN(namelen);
unsigned short rec_len, name_len;
- struct page *page = NULL;
+ struct folio *folio = NULL;
ext2_dirent * de;
unsigned long npages = dir_pages(dir);
unsigned long n;
- char *kaddr;
loff_t pos;
int err;
/*
* We take care of directory expansion in the same loop.
- * This code plays outside i_size, so it locks the page
+ * This code plays outside i_size, so it locks the folio
* to protect that region.
*/
for (n = 0; n <= npages; n++) {
+ char *kaddr = ext2_get_folio(dir, n, 0, &folio);
char *dir_end;
- page = ext2_get_page(dir, n, 0);
- err = PTR_ERR(page);
- if (IS_ERR(page))
- goto out;
- lock_page(page);
- kaddr = page_address(page);
+ if (IS_ERR(kaddr))
+ return PTR_ERR(kaddr);
+ folio_lock(folio);
dir_end = kaddr + ext2_last_byte(dir, n);
de = (ext2_dirent *)kaddr;
- kaddr += PAGE_CACHE_SIZE - reclen;
+ kaddr += folio_size(folio) - reclen;
while ((char *)de <= kaddr) {
if ((char *)de == dir_end) {
/* We hit i_size */
@@ -543,16 +529,15 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
goto got_it;
de = (ext2_dirent *) ((char *) de + rec_len);
}
- unlock_page(page);
- ext2_put_page(page);
+ folio_unlock(folio);
+ folio_release_kmap(folio, kaddr);
}
BUG();
return -EINVAL;
got_it:
- pos = page_offset(page) +
- (char*)de - (char*)page_address(page);
- err = ext2_prepare_chunk(page, pos, rec_len);
+ pos = folio_pos(folio) + offset_in_folio(folio, de);
+ err = ext2_prepare_chunk(folio, pos, rec_len);
if (err)
goto out_unlock;
if (de->inode) {
@@ -565,62 +550,65 @@ got_it:
memcpy(de->name, name, namelen);
de->inode = cpu_to_le32(inode->i_ino);
ext2_set_de_type (de, inode);
- err = ext2_commit_chunk(page, pos, rec_len);
- dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+ ext2_commit_chunk(folio, pos, rec_len);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
mark_inode_dirty(dir);
+ err = ext2_handle_dirsync(dir);
/* OFFSET_CACHE */
out_put:
- ext2_put_page(page);
-out:
+ folio_release_kmap(folio, de);
return err;
out_unlock:
- unlock_page(page);
+ folio_unlock(folio);
goto out_put;
}
/*
* ext2_delete_entry deletes a directory entry by merging it with the
- * previous entry. Page is up-to-date. Releases the page.
+ * previous entry. Page is up-to-date.
*/
-int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
+int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct folio *folio)
{
- struct inode *inode = page->mapping->host;
- char *kaddr = page_address(page);
- unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
- unsigned to = ((char *)dir - kaddr) +
- ext2_rec_len_from_disk(dir->rec_len);
+ struct inode *inode = folio->mapping->host;
+ size_t from, to;
+ char *kaddr;
loff_t pos;
- ext2_dirent * pde = NULL;
- ext2_dirent * de = (ext2_dirent *) (kaddr + from);
+ ext2_dirent *de, *pde = NULL;
int err;
+ from = offset_in_folio(folio, dir);
+ to = from + ext2_rec_len_from_disk(dir->rec_len);
+ kaddr = (char *)dir - from;
+ from &= ~(ext2_chunk_size(inode)-1);
+ de = (ext2_dirent *)(kaddr + from);
+
while ((char*)de < (char*)dir) {
if (de->rec_len == 0) {
ext2_error(inode->i_sb, __func__,
"zero-length directory entry");
- err = -EIO;
- goto out;
+ return -EIO;
}
pde = de;
de = ext2_next_entry(de);
}
if (pde)
- from = (char*)pde - (char*)page_address(page);
- pos = page_offset(page) + from;
- lock_page(page);
- err = ext2_prepare_chunk(page, pos, to - from);
- BUG_ON(err);
+ from = offset_in_folio(folio, pde);
+ pos = folio_pos(folio) + from;
+ folio_lock(folio);
+ err = ext2_prepare_chunk(folio, pos, to - from);
+ if (err) {
+ folio_unlock(folio);
+ return err;
+ }
if (pde)
pde->rec_len = ext2_rec_len_to_disk(to - from);
dir->inode = 0;
- err = ext2_commit_chunk(page, pos, to - from);
- inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
+ ext2_commit_chunk(folio, pos, to - from);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL;
mark_inode_dirty(inode);
-out:
- ext2_put_page(page);
- return err;
+ return ext2_handle_dirsync(inode);
}
/*
@@ -628,21 +616,21 @@ out:
*/
int ext2_make_empty(struct inode *inode, struct inode *parent)
{
- struct page *page = grab_cache_page(inode->i_mapping, 0);
+ struct folio *folio = filemap_grab_folio(inode->i_mapping, 0);
unsigned chunk_size = ext2_chunk_size(inode);
struct ext2_dir_entry_2 * de;
int err;
void *kaddr;
- if (!page)
- return -ENOMEM;
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
- err = ext2_prepare_chunk(page, 0, chunk_size);
+ err = ext2_prepare_chunk(folio, 0, chunk_size);
if (err) {
- unlock_page(page);
+ folio_unlock(folio);
goto fail;
}
- kaddr = kmap_atomic(page);
+ kaddr = kmap_local_folio(folio, 0);
memset(kaddr, 0, chunk_size);
de = (struct ext2_dir_entry_2 *)kaddr;
de->name_len = 1;
@@ -657,33 +645,30 @@ int ext2_make_empty(struct inode *inode, struct inode *parent)
de->inode = cpu_to_le32(parent->i_ino);
memcpy (de->name, "..\0", 4);
ext2_set_de_type (de, inode);
- kunmap_atomic(kaddr);
- err = ext2_commit_chunk(page, 0, chunk_size);
+ kunmap_local(kaddr);
+ ext2_commit_chunk(folio, 0, chunk_size);
+ err = ext2_handle_dirsync(inode);
fail:
- page_cache_release(page);
+ folio_put(folio);
return err;
}
/*
* routine to check that the specified directory is empty (for rmdir)
*/
-int ext2_empty_dir (struct inode * inode)
+int ext2_empty_dir(struct inode *inode)
{
- struct page *page = NULL;
+ struct folio *folio;
+ char *kaddr;
unsigned long i, npages = dir_pages(inode);
- int dir_has_error = 0;
for (i = 0; i < npages; i++) {
- char *kaddr;
- ext2_dirent * de;
- page = ext2_get_page(inode, i, dir_has_error);
+ ext2_dirent *de;
- if (IS_ERR(page)) {
- dir_has_error = 1;
- continue;
- }
+ kaddr = ext2_get_folio(inode, i, 0, &folio);
+ if (IS_ERR(kaddr))
+ return 0;
- kaddr = page_address(page);
de = (ext2_dirent *)kaddr;
kaddr += ext2_last_byte(inode, i) - EXT2_DIR_REC_LEN(1);
@@ -709,19 +694,41 @@ int ext2_empty_dir (struct inode * inode)
}
de = ext2_next_entry(de);
}
- ext2_put_page(page);
+ folio_release_kmap(folio, kaddr);
}
return 1;
not_empty:
- ext2_put_page(page);
+ folio_release_kmap(folio, kaddr);
return 0;
}
+static int ext2_dir_open(struct inode *inode, struct file *file)
+{
+ file->private_data = kzalloc(sizeof(u64), GFP_KERNEL);
+ if (!file->private_data)
+ return -ENOMEM;
+ return 0;
+}
+
+static int ext2_dir_release(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
+
+static loff_t ext2_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+ return generic_llseek_cookie(file, offset, whence,
+ (u64 *)file->private_data);
+}
+
const struct file_operations ext2_dir_operations = {
- .llseek = generic_file_llseek,
+ .open = ext2_dir_open,
+ .release = ext2_dir_release,
+ .llseek = ext2_dir_llseek,
.read = generic_read_dir,
- .iterate = ext2_readdir,
+ .iterate_shared = ext2_readdir,
.unlocked_ioctl = ext2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext2_compat_ioctl,
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index d9a17d0b124d..cf97b76e9fd3 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
@@ -15,6 +16,8 @@
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
#include <linux/rbtree.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
/* XXX Here for now... not interested in restructing headers JUST now */
@@ -51,8 +54,8 @@ struct ext2_block_alloc_info {
/*
* Was i_next_alloc_goal in ext2_inode_info
* is the *physical* companion to i_next_alloc_block.
- * it the the physical block number of the block which was most-recentl
- * allocated to this file. This give us the goal (target) for the next
+ * it is the physical block number of the block which was most-recently
+ * allocated to this file. This gives us the goal (target) for the next
* allocation when we detect linearly ascending requests.
*/
ext2_fsblk_t last_alloc_physical_block;
@@ -61,14 +64,13 @@ struct ext2_block_alloc_info {
#define rsv_start rsv_window._rsv_start
#define rsv_end rsv_window._rsv_end
+struct mb_cache;
+
/*
* second extended-fs super-block data in memory
*/
struct ext2_sb_info {
- unsigned long s_frag_size; /* Size of a fragment in bytes */
- unsigned long s_frags_per_block;/* Number of fragments per block */
unsigned long s_inodes_per_block;/* Number of inodes per block */
- unsigned long s_frags_per_group;/* Number of fragments in a group */
unsigned long s_blocks_per_group;/* Number of blocks in a group */
unsigned long s_inodes_per_group;/* Number of inodes in a group */
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
@@ -111,6 +113,9 @@ struct ext2_sb_info {
* of the mount options.
*/
spinlock_t s_lock;
+ struct mb_cache *s_ea_block_cache;
+ struct dax_device *s_daxdev;
+ u64 s_dax_part_off;
};
static inline spinlock_t *
@@ -170,8 +175,9 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
* Macro-instructions used to manage several block sizes
*/
#define EXT2_MIN_BLOCK_SIZE 1024
-#define EXT2_MAX_BLOCK_SIZE 4096
+#define EXT2_MAX_BLOCK_SIZE 65536
#define EXT2_MIN_BLOCK_LOG_SIZE 10
+#define EXT2_MAX_BLOCK_LOG_SIZE 16
#define EXT2_BLOCK_SIZE(s) ((s)->s_blocksize)
#define EXT2_ADDR_PER_BLOCK(s) (EXT2_BLOCK_SIZE(s) / sizeof (__u32))
#define EXT2_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
@@ -180,15 +186,6 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
#define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino)
/*
- * Macro-instructions used to manage fragments
- */
-#define EXT2_MIN_FRAG_SIZE 1024
-#define EXT2_MAX_FRAG_SIZE 4096
-#define EXT2_MIN_FRAG_LOG_SIZE 10
-#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size)
-#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block)
-
-/*
* Structure of a blocks group descriptor
*/
struct ext2_group_desc
@@ -276,8 +273,6 @@ static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
/*
* ioctl commands
*/
-#define EXT2_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define EXT2_IOC_SETFLAGS FS_IOC_SETFLAGS
#define EXT2_IOC_GETVERSION FS_IOC_GETVERSION
#define EXT2_IOC_SETVERSION FS_IOC_SETVERSION
#define EXT2_IOC_GETRSVSZ _IOR('f', 5, long)
@@ -286,8 +281,6 @@ static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
/*
* ioctl commands in 32 bit emulation
*/
-#define EXT2_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define EXT2_IOC32_SETFLAGS FS_IOC32_SETFLAGS
#define EXT2_IOC32_GETVERSION FS_IOC32_GETVERSION
#define EXT2_IOC32_SETVERSION FS_IOC32_SETVERSION
@@ -364,26 +357,28 @@ struct ext2_inode {
*/
#define EXT2_VALID_FS 0x0001 /* Unmounted cleanly */
#define EXT2_ERROR_FS 0x0002 /* Errors detected */
+#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
/*
* Mount flags
*/
-#define EXT2_MOUNT_CHECK 0x000001 /* Do mount-time checks */
#define EXT2_MOUNT_OLDALLOC 0x000002 /* Don't use the new Orlov allocator */
#define EXT2_MOUNT_GRPID 0x000004 /* Create files with directory's group */
#define EXT2_MOUNT_DEBUG 0x000008 /* Some debugging messages */
#define EXT2_MOUNT_ERRORS_CONT 0x000010 /* Continue on errors */
#define EXT2_MOUNT_ERRORS_RO 0x000020 /* Remount fs ro on errors */
#define EXT2_MOUNT_ERRORS_PANIC 0x000040 /* Panic on errors */
+#define EXT2_MOUNT_ERRORS_MASK 0x000070
#define EXT2_MOUNT_MINIX_DF 0x000080 /* Mimics the Minix statfs */
#define EXT2_MOUNT_NOBH 0x000100 /* No buffer_heads */
#define EXT2_MOUNT_NO_UID32 0x000200 /* Disable 32-bit UIDs */
#define EXT2_MOUNT_XATTR_USER 0x004000 /* Extended user attributes */
#define EXT2_MOUNT_POSIX_ACL 0x008000 /* POSIX Access Control Lists */
-#define EXT2_MOUNT_XIP 0x010000 /* Execute in place */
+#define EXT2_MOUNT_XIP 0x010000 /* Obsolete, use DAX */
#define EXT2_MOUNT_USRQUOTA 0x020000 /* user quota */
#define EXT2_MOUNT_GRPQUOTA 0x040000 /* group quota */
#define EXT2_MOUNT_RESERVATION 0x080000 /* Preallocation */
+#define EXT2_MOUNT_DAX 0x100000 /* Direct Access */
#define clear_opt(o, opt) o &= ~EXT2_MOUNT_##opt
@@ -405,6 +400,12 @@ struct ext2_inode {
#define EXT2_ERRORS_DEFAULT EXT2_ERRORS_CONTINUE
/*
+ * Allocation flags
+ */
+#define EXT2_ALLOC_NORESERVE 0x1 /* Do not use reservation
+ * window for allocation */
+
+/*
* Structure of the super block
*/
struct ext2_super_block {
@@ -597,22 +598,6 @@ struct ext2_dir_entry_2 {
};
/*
- * Ext2 directory file types. Only the low 3 bits are used. The
- * other bits are reserved for now.
- */
-enum {
- EXT2_FT_UNKNOWN = 0,
- EXT2_FT_REG_FILE = 1,
- EXT2_FT_DIR = 2,
- EXT2_FT_CHRDEV = 3,
- EXT2_FT_BLKDEV = 4,
- EXT2_FT_FIFO = 5,
- EXT2_FT_SOCK = 6,
- EXT2_FT_SYMLINK = 7,
- EXT2_FT_MAX
-};
-
-/*
* EXT2_DIR_PAD defines the directory entries boundaries
*
* NOTE: It must be a multiple of 4
@@ -689,6 +674,9 @@ struct ext2_inode_info {
struct mutex truncate_mutex;
struct inode vfs_inode;
struct list_head i_orphan; /* unlinked but open inodes */
+#ifdef CONFIG_QUOTA
+ struct dquot __rcu *i_dquot[MAXQUOTAS];
+#endif
};
/*
@@ -714,14 +702,13 @@ static inline struct ext2_inode_info *EXT2_I(struct inode *inode)
/* balloc.c */
extern int ext2_bg_has_super(struct super_block *sb, int group);
extern unsigned long ext2_bg_num_gdb(struct super_block *sb, int group);
-extern ext2_fsblk_t ext2_new_block(struct inode *, unsigned long, int *);
-extern ext2_fsblk_t ext2_new_blocks(struct inode *, unsigned long,
- unsigned long *, int *);
-extern void ext2_free_blocks (struct inode *, unsigned long,
- unsigned long);
+extern ext2_fsblk_t ext2_new_blocks(struct inode *, ext2_fsblk_t,
+ unsigned long *, int *, unsigned int);
+extern int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk,
+ unsigned int count);
+extern void ext2_free_blocks(struct inode *, ext2_fsblk_t, unsigned long);
extern unsigned long ext2_count_free_blocks (struct super_block *);
extern unsigned long ext2_count_dirs (struct super_block *);
-extern void ext2_check_blocks_bitmap (struct super_block *);
extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh);
@@ -731,34 +718,41 @@ extern void ext2_init_block_alloc_info(struct inode *);
extern void ext2_rsv_window_add(struct super_block *sb, struct ext2_reserve_window_node *rsv);
/* dir.c */
-extern int ext2_add_link (struct dentry *, struct inode *);
-extern ino_t ext2_inode_by_name(struct inode *, struct qstr *);
-extern int ext2_make_empty(struct inode *, struct inode *);
-extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct qstr *, struct page **);
-extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
-extern int ext2_empty_dir (struct inode *);
-extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **);
-extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *, int);
+int ext2_add_link(struct dentry *, struct inode *);
+int ext2_inode_by_name(struct inode *dir,
+ const struct qstr *child, ino_t *ino);
+int ext2_make_empty(struct inode *, struct inode *);
+struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *,
+ struct folio **foliop);
+int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct folio *folio);
+int ext2_empty_dir(struct inode *);
+struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct folio **foliop);
+int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
+ struct folio *folio, struct inode *inode, bool update_times);
/* ialloc.c */
extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *);
extern void ext2_free_inode (struct inode *);
extern unsigned long ext2_count_free_inodes (struct super_block *);
-extern void ext2_check_inodes_bitmap (struct super_block *);
extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
/* inode.c */
extern struct inode *ext2_iget (struct super_block *, unsigned long);
extern int ext2_write_inode (struct inode *, struct writeback_control *);
extern void ext2_evict_inode(struct inode *);
+void ext2_write_failed(struct address_space *mapping, loff_t to);
extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
-extern int ext2_setattr (struct dentry *, struct iattr *);
+extern int ext2_setattr (struct mnt_idmap *, struct dentry *, struct iattr *);
+extern int ext2_getattr (struct mnt_idmap *, const struct path *,
+ struct kstat *, u32, unsigned int);
extern void ext2_set_inode_flags(struct inode *inode);
-extern void ext2_get_inode_flags(struct ext2_inode_info *);
extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
/* ioctl.c */
+extern int ext2_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
+extern int ext2_fileattr_set(struct mnt_idmap *idmap,
+ struct dentry *dentry, struct file_kattr *fa);
extern long ext2_ioctl(struct file *, unsigned int, unsigned long);
extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -771,7 +765,8 @@ void ext2_error(struct super_block *, const char *, const char *, ...);
extern __printf(3, 4)
void ext2_msg(struct super_block *, const char *, const char *, ...);
extern void ext2_update_dynamic_rev (struct super_block *sb);
-extern void ext2_write_super (struct super_block *);
+extern void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
+ int wait);
/*
* Inodes and files operations
@@ -785,12 +780,11 @@ extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
int datasync);
extern const struct inode_operations ext2_file_inode_operations;
extern const struct file_operations ext2_file_operations;
-extern const struct file_operations ext2_xip_file_operations;
/* inode.c */
+extern void ext2_set_file_ops(struct inode *inode);
extern const struct address_space_operations ext2_aops;
-extern const struct address_space_operations ext2_aops_xip;
-extern const struct address_space_operations ext2_nobh_aops;
+extern const struct iomap_ops ext2_iomap_ops;
/* namei.c */
extern const struct inode_operations ext2_dir_inode_operations;
@@ -807,6 +801,18 @@ ext2_group_first_block_no(struct super_block *sb, unsigned long group_no)
le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block);
}
+static inline ext2_fsblk_t
+ext2_group_last_block_no(struct super_block *sb, unsigned long group_no)
+{
+ struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+ if (group_no == sbi->s_groups_count - 1)
+ return le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
+ else
+ return ext2_group_first_block_no(sb, group_no) +
+ EXT2_BLOCKS_PER_GROUP(sb) - 1;
+}
+
#define ext2_set_bit __test_and_set_bit_le
#define ext2_clear_bit __test_and_clear_bit_le
#define ext2_test_bit test_bit_le
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index a5b3a5db3120..76bddce462fc 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/file.c
*
@@ -20,10 +21,121 @@
#include <linux/time.h>
#include <linux/pagemap.h>
+#include <linux/dax.h>
#include <linux/quotaops.h>
+#include <linux/iomap.h>
+#include <linux/uio.h>
+#include <linux/buffer_head.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
+#include "trace.h"
+
+#ifdef CONFIG_FS_DAX
+static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ ssize_t ret;
+
+ if (!iov_iter_count(to))
+ return 0; /* skip atime */
+
+ inode_lock_shared(inode);
+ ret = dax_iomap_rw(iocb, to, &ext2_iomap_ops);
+ inode_unlock_shared(inode);
+
+ file_accessed(iocb->ki_filp);
+ return ret;
+}
+
+static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+
+ inode_lock(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out_unlock;
+ ret = file_remove_privs(file);
+ if (ret)
+ goto out_unlock;
+ ret = file_update_time(file);
+ if (ret)
+ goto out_unlock;
+
+ ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops);
+ if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
+ i_size_write(inode, iocb->ki_pos);
+ mark_inode_dirty(inode);
+ }
+
+out_unlock:
+ inode_unlock(inode);
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
+ return ret;
+}
+
+/*
+ * The lock ordering for ext2 DAX fault paths is:
+ *
+ * mmap_lock (MM)
+ * sb_start_pagefault (vfs, freeze)
+ * address_space->invalidate_lock
+ * address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX)
+ * ext2_inode_info->truncate_mutex
+ *
+ * The default page_lock and i_size verification done by non-DAX fault paths
+ * is sufficient because ext2 doesn't support hole punching.
+ */
+static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vmf->vma->vm_file);
+ vm_fault_t ret;
+ bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
+ (vmf->vma->vm_flags & VM_SHARED);
+
+ if (write) {
+ sb_start_pagefault(inode->i_sb);
+ file_update_time(vmf->vma->vm_file);
+ }
+ filemap_invalidate_lock_shared(inode->i_mapping);
+
+ ret = dax_iomap_fault(vmf, 0, NULL, NULL, &ext2_iomap_ops);
+
+ filemap_invalidate_unlock_shared(inode->i_mapping);
+ if (write)
+ sb_end_pagefault(inode->i_sb);
+ return ret;
+}
+
+static const struct vm_operations_struct ext2_dax_vm_ops = {
+ .fault = ext2_dax_fault,
+ /*
+ * .huge_fault is not supported for DAX because allocation in ext2
+ * cannot be reliably aligned to huge page sizes and so pmd faults
+ * will always fail and fail back to regular faults.
+ */
+ .page_mkwrite = ext2_dax_fault,
+ .pfn_mkwrite = ext2_dax_fault,
+};
+
+static int ext2_file_mmap_prepare(struct vm_area_desc *desc)
+{
+ struct file *file = desc->file;
+
+ if (!IS_DAX(file_inode(file)))
+ return generic_file_mmap_prepare(desc);
+
+ file_accessed(file);
+ desc->vm_ops = &ext2_dax_vm_ops;
+ return 0;
+}
+#else
+#define ext2_file_mmap_prepare generic_file_mmap_prepare
+#endif
/*
* Called when filp is released. This happens when all file descriptors
@@ -44,64 +156,184 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
int ret;
struct super_block *sb = file->f_mapping->host->i_sb;
- struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
- ret = generic_file_fsync(file, start, end, datasync);
- if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) {
+ ret = generic_buffers_fsync(file, start, end, datasync);
+ if (ret == -EIO)
/* We don't really know where the IO error happened... */
ext2_error(sb, __func__,
"detected IO error when writing metadata buffers");
- ret = -EIO;
+ return ret;
+}
+
+static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+
+ trace_ext2_dio_read_begin(iocb, to, 0);
+ inode_lock_shared(inode);
+ ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0);
+ inode_unlock_shared(inode);
+ trace_ext2_dio_read_end(iocb, to, ret);
+
+ return ret;
+}
+
+static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags)
+{
+ loff_t pos = iocb->ki_pos;
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ if (error)
+ goto out;
+
+ /*
+ * If we are extending the file, we have to update i_size here before
+ * page cache gets invalidated in iomap_dio_rw(). This prevents racing
+ * buffered reads from zeroing out too much from page cache pages.
+ * Note that all extending writes always happens synchronously with
+ * inode lock held by ext2_dio_write_iter(). So it is safe to update
+ * inode size here for extending file writes.
+ */
+ pos += size;
+ if (pos > i_size_read(inode)) {
+ i_size_write(inode, pos);
+ mark_inode_dirty(inode);
+ }
+out:
+ trace_ext2_dio_write_endio(iocb, size, error);
+ return error;
+}
+
+static const struct iomap_dio_ops ext2_dio_write_ops = {
+ .end_io = ext2_dio_write_end_io,
+};
+
+static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+ unsigned int flags = 0;
+ unsigned long blocksize = inode->i_sb->s_blocksize;
+ loff_t offset = iocb->ki_pos;
+ loff_t count = iov_iter_count(from);
+ ssize_t status = 0;
+
+ trace_ext2_dio_write_begin(iocb, from, 0);
+ inode_lock(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out_unlock;
+
+ ret = kiocb_modified(iocb);
+ if (ret)
+ goto out_unlock;
+
+ /* use IOMAP_DIO_FORCE_WAIT for unaligned or extending writes */
+ if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) ||
+ (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize)))
+ flags |= IOMAP_DIO_FORCE_WAIT;
+
+ ret = iomap_dio_rw(iocb, from, &ext2_iomap_ops, &ext2_dio_write_ops,
+ flags, NULL, 0);
+
+ /* ENOTBLK is magic return value for fallback to buffered-io */
+ if (ret == -ENOTBLK)
+ ret = 0;
+
+ if (ret < 0 && ret != -EIOCBQUEUED)
+ ext2_write_failed(inode->i_mapping, offset + count);
+
+ /* handle case for partial write and for fallback to buffered write */
+ if (ret >= 0 && iov_iter_count(from)) {
+ loff_t pos, endbyte;
+ int ret2;
+
+ iocb->ki_flags &= ~IOCB_DIRECT;
+ pos = iocb->ki_pos;
+ status = generic_perform_write(iocb, from);
+ if (unlikely(status < 0)) {
+ ret = status;
+ goto out_unlock;
+ }
+
+ ret += status;
+ endbyte = pos + status - 1;
+ ret2 = filemap_write_and_wait_range(inode->i_mapping, pos,
+ endbyte);
+ if (!ret2)
+ invalidate_mapping_pages(inode->i_mapping,
+ pos >> PAGE_SHIFT,
+ endbyte >> PAGE_SHIFT);
+ if (ret > 0)
+ generic_write_sync(iocb, ret);
}
+
+out_unlock:
+ inode_unlock(inode);
+ if (status)
+ trace_ext2_dio_write_buff_end(iocb, from, status);
+ trace_ext2_dio_write_end(iocb, from, ret);
return ret;
}
-/*
- * We have mostly NULL's here: the current defaults are ok for
- * the ext2 filesystem.
- */
-const struct file_operations ext2_file_operations = {
- .llseek = generic_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
- .unlocked_ioctl = ext2_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ext2_compat_ioctl,
+static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+#ifdef CONFIG_FS_DAX
+ if (IS_DAX(iocb->ki_filp->f_mapping->host))
+ return ext2_dax_read_iter(iocb, to);
#endif
- .mmap = generic_file_mmap,
- .open = dquot_file_open,
- .release = ext2_release_file,
- .fsync = ext2_fsync,
- .splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
-};
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return ext2_dio_read_iter(iocb, to);
+
+ return generic_file_read_iter(iocb, to);
+}
-#ifdef CONFIG_EXT2_FS_XIP
-const struct file_operations ext2_xip_file_operations = {
+static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+#ifdef CONFIG_FS_DAX
+ if (IS_DAX(iocb->ki_filp->f_mapping->host))
+ return ext2_dax_write_iter(iocb, from);
+#endif
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return ext2_dio_write_iter(iocb, from);
+
+ return generic_file_write_iter(iocb, from);
+}
+
+static int ext2_file_open(struct inode *inode, struct file *filp)
+{
+ filp->f_mode |= FMODE_CAN_ODIRECT;
+ return dquot_file_open(inode, filp);
+}
+
+const struct file_operations ext2_file_operations = {
.llseek = generic_file_llseek,
- .read = xip_file_read,
- .write = xip_file_write,
+ .read_iter = ext2_file_read_iter,
+ .write_iter = ext2_file_write_iter,
.unlocked_ioctl = ext2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext2_compat_ioctl,
#endif
- .mmap = xip_file_mmap,
- .open = dquot_file_open,
+ .mmap_prepare = ext2_file_mmap_prepare,
+ .open = ext2_file_open,
.release = ext2_release_file,
.fsync = ext2_fsync,
+ .get_unmapped_area = thp_get_unmapped_area,
+ .splice_read = filemap_splice_read,
+ .splice_write = iter_file_splice_write,
};
-#endif
const struct inode_operations ext2_file_inode_operations = {
-#ifdef CONFIG_EXT2_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
- .removexattr = generic_removexattr,
-#endif
+ .getattr = ext2_getattr,
.setattr = ext2_setattr,
- .get_acl = ext2_get_acl,
+ .get_inode_acl = ext2_get_acl,
+ .set_acl = ext2_set_acl,
.fiemap = ext2_fiemap,
+ .fileattr_get = ext2_fileattr_get,
+ .fileattr_set = ext2_fileattr_set,
};
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 7cadd823bb31..fdf63e9c6e7c 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/ialloc.c
*
@@ -79,6 +80,7 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir)
if (dir)
le16_add_cpu(&desc->bg_used_dirs_count, -1);
spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
+ percpu_counter_inc(&EXT2_SB(sb)->s_freeinodes_counter);
if (dir)
percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
mark_buffer_dirty(bh);
@@ -144,7 +146,7 @@ void ext2_free_inode (struct inode * inode)
else
ext2_release_inode(sb, block_group, is_directory);
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
brelse(bitmap_bh);
@@ -168,13 +170,6 @@ static void ext2_preread_inode(struct inode *inode)
unsigned long offset;
unsigned long block;
struct ext2_group_desc * gdp;
- struct backing_dev_info *bdi;
-
- bdi = inode->i_mapping->backing_dev_info;
- if (bdi_read_congested(bdi))
- return;
- if (bdi_write_congested(bdi))
- return;
block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
gdp = ext2_get_group_desc(inode->i_sb, block_group, NULL);
@@ -221,8 +216,6 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
best_desc = desc;
}
}
- if (!best_desc)
- return -1;
return best_group;
}
@@ -278,14 +271,12 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
avefreeb = free_blocks / ngroups;
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
- if ((parent == sb->s_root->d_inode) ||
+ if ((parent == d_inode(sb->s_root)) ||
(EXT2_I(parent)->i_flags & EXT2_TOPDIR_FL)) {
- struct ext2_group_desc *best_desc = NULL;
int best_ndir = inodes_per_group;
int best_group = -1;
- get_random_bytes(&group, sizeof(group));
- parent_group = (unsigned)group % ngroups;
+ parent_group = get_random_u32_below(ngroups);
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext2_get_group_desc (sb, group, NULL);
@@ -299,10 +290,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
continue;
best_group = group;
best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
- best_desc = desc;
}
if (best_group >= 0) {
- desc = best_desc;
group = best_group;
goto found;
}
@@ -465,6 +454,11 @@ struct inode *ext2_new_inode(struct inode *dir, umode_t mode,
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext2_get_group_desc(sb, group, &bh2);
+ if (!gdp) {
+ if (++group == sbi->s_groups_count)
+ group = 0;
+ continue;
+ }
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, group);
if (!bitmap_bh) {
@@ -507,11 +501,12 @@ repeat_in_this_group:
/*
* Scanned all blockgroups.
*/
+ brelse(bitmap_bh);
err = -ENOSPC;
goto fail;
got:
mark_buffer_dirty(bitmap_bh);
- if (sb->s_flags & MS_SYNCHRONOUS)
+ if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
brelse(bitmap_bh);
@@ -525,7 +520,7 @@ got:
goto fail;
}
- percpu_counter_add(&sbi->s_freeinodes_counter, -1);
+ percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
percpu_counter_inc(&sbi->s_dirs_counter);
@@ -547,11 +542,11 @@ got:
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
} else
- inode_init_owner(inode, dir, mode);
+ inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
inode->i_ino = ino;
inode->i_blocks = 0;
- inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
+ simple_inode_init_ts(inode);
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_flags =
ext2_mask_flags(mode, EXT2_I(dir)->i_flags & EXT2_FL_INHERITED);
@@ -577,7 +572,10 @@ got:
goto fail;
}
- dquot_initialize(inode);
+ err = dquot_initialize(inode);
+ if (err)
+ goto fail_drop;
+
err = dquot_alloc_inode(inode);
if (err)
goto fail_drop;
@@ -602,8 +600,7 @@ fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
clear_nlink(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
return ERR_PTR(err);
fail:
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0a87bb10998d..dbfe9098a124 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/inode.c
*
@@ -25,16 +26,18 @@
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
+#include <linux/dax.h>
+#include <linux/blkdev.h>
#include <linux/quotaops.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/fiemap.h>
+#include <linux/iomap.h>
#include <linux/namei.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
#include "ext2.h"
#include "acl.h"
-#include "xip.h"
#include "xattr.h"
static int __ext2_write_inode(struct inode *inode, int do_sync);
@@ -53,12 +56,12 @@ static inline int ext2_inode_is_fast_symlink(struct inode *inode)
static void ext2_truncate_blocks(struct inode *inode, loff_t offset);
-static void ext2_write_failed(struct address_space *mapping, loff_t to)
+void ext2_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
ext2_truncate_blocks(inode, inode->i_size);
}
}
@@ -78,12 +81,12 @@ void ext2_evict_inode(struct inode * inode)
dquot_drop(inode);
}
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (want_delete) {
sb_start_intwrite(inode->i_sb);
/* set dtime */
- EXT2_I(inode)->i_dtime = get_seconds();
+ EXT2_I(inode)->i_dtime = ktime_get_real_seconds();
mark_inode_dirty(inode);
__ext2_write_inode(inode, inode_needs_sync(inode));
/* truncate to 0 */
@@ -352,8 +355,7 @@ static inline ext2_fsblk_t ext2_find_goal(struct inode *inode, long block,
* @blks: number of data blocks to be mapped.
* @blocks_to_boundary: the offset in the indirect block
*
- * return the total number of blocks to be allocate, including the
- * direct and indirect blocks.
+ * return the number of direct blocks to allocate.
*/
static int
ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
@@ -383,14 +385,16 @@ ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
}
/**
- * ext2_alloc_blocks: multiple allocate blocks needed for a branch
- * @indirect_blks: the number of blocks need to allocate for indirect
- * blocks
+ * ext2_alloc_blocks: Allocate multiple blocks needed for a branch.
+ * @inode: Owner.
+ * @goal: Preferred place for allocation.
+ * @indirect_blks: The number of blocks needed to allocate for indirect blocks.
+ * @blks: The number of blocks need to allocate for direct blocks.
+ * @new_blocks: On return it will store the new block numbers for
+ * the indirect blocks(if needed) and the first direct block.
+ * @err: Error pointer.
*
- * @new_blocks: on return it will store the new block numbers for
- * the indirect blocks(if needed) and the first direct block,
- * @blks: on return it will store the total number of allocated
- * direct blocks
+ * Return: Number of blocks allocated.
*/
static int ext2_alloc_blocks(struct inode *inode,
ext2_fsblk_t goal, int indirect_blks, int blks,
@@ -415,7 +419,7 @@ static int ext2_alloc_blocks(struct inode *inode,
while (1) {
count = target;
/* allocating blocks for indirect blocks and direct blocks */
- current_block = ext2_new_blocks(inode,goal,&count,err);
+ current_block = ext2_new_blocks(inode, goal, &count, err, 0);
if (*err)
goto failed_out;
@@ -448,7 +452,9 @@ failed_out:
/**
* ext2_alloc_branch - allocate and set up a chain of blocks.
* @inode: owner
- * @num: depth of the chain (number of blocks to allocate)
+ * @indirect_blks: depth of the chain (number of blocks to allocate)
+ * @blks: number of allocated direct blocks
+ * @goal: preferred place for allocation
* @offsets: offsets (in the blocks) to store the pointers to next.
* @branch: place to store the chain in.
*
@@ -593,7 +599,7 @@ static void ext2_splice_branch(struct inode *inode,
if (where->bh)
mark_buffer_dirty_inode(where->bh, inode);
- inode->i_ctime = CURRENT_TIME_SEC;
+ inode_set_ctime_current(inode);
mark_inode_dirty(inode);
}
@@ -617,10 +623,10 @@ static void ext2_splice_branch(struct inode *inode,
*/
static int ext2_get_blocks(struct inode *inode,
sector_t iblock, unsigned long maxblocks,
- struct buffer_head *bh_result,
+ u32 *bno, bool *new, bool *boundary,
int create)
{
- int err = -EIO;
+ int err;
int offsets[4];
Indirect chain[4];
Indirect *partial;
@@ -632,16 +638,17 @@ static int ext2_get_blocks(struct inode *inode,
int count = 0;
ext2_fsblk_t first_block = 0;
+ BUG_ON(maxblocks == 0);
+
depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
if (depth == 0)
- return (err);
+ return -EIO;
partial = ext2_get_branch(inode, depth, offsets, chain, &err);
/* Simplest case - block found, no allocation needed */
if (!partial) {
first_block = le32_to_cpu(chain[depth - 1].key);
- clear_buffer_new(bh_result); /* What's this do? */
count++;
/*map more blocks*/
while (count < maxblocks && count <= blocks_to_boundary) {
@@ -656,6 +663,7 @@ static int ext2_get_blocks(struct inode *inode,
*/
err = -EAGAIN;
count = 0;
+ partial = chain + depth - 1;
break;
}
blk = le32_to_cpu(*(chain[depth-1].p + count));
@@ -694,11 +702,13 @@ static int ext2_get_blocks(struct inode *inode,
if (!partial) {
count++;
mutex_unlock(&ei->truncate_mutex);
- if (err)
- goto cleanup;
- clear_buffer_new(bh_result);
goto got_it;
}
+
+ if (err) {
+ mutex_unlock(&ei->truncate_mutex);
+ goto cleanup;
+ }
}
/*
@@ -713,7 +723,7 @@ static int ext2_get_blocks(struct inode *inode,
/* the number of blocks need to allocate for [d,t]indirect blocks */
indirect_blks = (chain + depth) - partial - 1;
/*
- * Next look up the indirect map to count the totoal number of
+ * Next look up the indirect map to count the total number of
* direct blocks to allocate for this branch.
*/
count = ext2_blks_to_allocate(partial, indirect_blks,
@@ -729,25 +739,34 @@ static int ext2_get_blocks(struct inode *inode,
goto cleanup;
}
- if (ext2_use_xip(inode->i_sb)) {
+ if (IS_DAX(inode)) {
+ /*
+ * We must unmap blocks before zeroing so that writeback cannot
+ * overwrite zeros with stale data from block device page cache.
+ */
+ clean_bdev_aliases(inode->i_sb->s_bdev,
+ le32_to_cpu(chain[depth-1].key),
+ count);
/*
- * we need to clear the block
+ * block must be initialised before we put it in the tree
+ * so that it's not found by another thread before it's
+ * initialised
*/
- err = ext2_clear_xip_target (inode,
- le32_to_cpu(chain[depth-1].key));
+ err = sb_issue_zeroout(inode->i_sb,
+ le32_to_cpu(chain[depth-1].key), count,
+ GFP_KERNEL);
if (err) {
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
}
+ *new = true;
ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
mutex_unlock(&ei->truncate_mutex);
- set_buffer_new(bh_result);
got_it:
- map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
if (count > blocks_to_boundary)
- set_buffer_boundary(bh_result);
+ *boundary = true;
err = count;
/* Clean up and exit */
partial = chain + depth - 1; /* the whole chain */
@@ -756,90 +775,178 @@ cleanup:
brelse(partial->bh);
partial--;
}
+ if (err > 0)
+ *bno = le32_to_cpu(chain[depth-1].key);
return err;
}
-int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
+int ext2_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
{
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
- int ret = ext2_get_blocks(inode, iblock, max_blocks,
- bh_result, create);
- if (ret > 0) {
- bh_result->b_size = (ret << inode->i_blkbits);
- ret = 0;
- }
- return ret;
+ bool new = false, boundary = false;
+ u32 bno;
+ int ret;
-}
+ ret = ext2_get_blocks(inode, iblock, max_blocks, &bno, &new, &boundary,
+ create);
+ if (ret <= 0)
+ return ret;
-int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
- u64 start, u64 len)
-{
- return generic_block_fiemap(inode, fieinfo, start, len,
- ext2_get_block);
-}
+ map_bh(bh_result, inode->i_sb, bno);
+ bh_result->b_size = (ret << inode->i_blkbits);
+ if (new)
+ set_buffer_new(bh_result);
+ if (boundary)
+ set_buffer_boundary(bh_result);
+ return 0;
-static int ext2_writepage(struct page *page, struct writeback_control *wbc)
-{
- return block_write_full_page(page, ext2_get_block, wbc);
}
-static int ext2_readpage(struct file *file, struct page *page)
+static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
- return mpage_readpage(page, ext2_get_block);
+ unsigned int blkbits = inode->i_blkbits;
+ unsigned long first_block = offset >> blkbits;
+ unsigned long max_blocks = (length + (1 << blkbits) - 1) >> blkbits;
+ struct ext2_sb_info *sbi = EXT2_SB(inode->i_sb);
+ bool new = false, boundary = false;
+ u32 bno;
+ int ret;
+ bool create = flags & IOMAP_WRITE;
+
+ /*
+ * For writes that could fill holes inside i_size on a
+ * DIO_SKIP_HOLES filesystem we forbid block creations: only
+ * overwrites are permitted.
+ */
+ if ((flags & IOMAP_DIRECT) &&
+ (first_block << blkbits) < i_size_read(inode))
+ create = 0;
+
+ /*
+ * Writes that span EOF might trigger an IO size update on completion,
+ * so consider them to be dirty for the purposes of O_DSYNC even if
+ * there is no other metadata changes pending or have been made here.
+ */
+ if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode))
+ iomap->flags |= IOMAP_F_DIRTY;
+
+ ret = ext2_get_blocks(inode, first_block, max_blocks,
+ &bno, &new, &boundary, create);
+ if (ret < 0)
+ return ret;
+
+ iomap->flags = 0;
+ iomap->offset = (u64)first_block << blkbits;
+ if (flags & IOMAP_DAX)
+ iomap->dax_dev = sbi->s_daxdev;
+ else
+ iomap->bdev = inode->i_sb->s_bdev;
+
+ if (ret == 0) {
+ /*
+ * Switch to buffered-io for writing to holes in a non-extent
+ * based filesystem to avoid stale data exposure problem.
+ */
+ if (!create && (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))
+ return -ENOTBLK;
+ iomap->type = IOMAP_HOLE;
+ iomap->addr = IOMAP_NULL_ADDR;
+ iomap->length = 1 << blkbits;
+ } else {
+ iomap->type = IOMAP_MAPPED;
+ iomap->addr = (u64)bno << blkbits;
+ if (flags & IOMAP_DAX)
+ iomap->addr += sbi->s_dax_part_off;
+ iomap->length = (u64)ret << blkbits;
+ iomap->flags |= IOMAP_F_MERGED;
+ }
+
+ if (new)
+ iomap->flags |= IOMAP_F_NEW;
+ return 0;
}
static int
-ext2_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
+ ssize_t written, unsigned flags, struct iomap *iomap)
{
- return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
+ /*
+ * Switch to buffered-io in case of any error.
+ * Blocks allocated can be used by the buffered-io path.
+ */
+ if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE) && written == 0)
+ return -ENOTBLK;
+
+ if (iomap->type == IOMAP_MAPPED &&
+ written < length &&
+ (flags & IOMAP_WRITE))
+ ext2_write_failed(inode->i_mapping, offset + length);
+ return 0;
}
-static int
-ext2_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
+const struct iomap_ops ext2_iomap_ops = {
+ .iomap_begin = ext2_iomap_begin,
+ .iomap_end = ext2_iomap_end,
+};
+
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
{
int ret;
+ loff_t i_size;
+
+ inode_lock(inode);
+ i_size = i_size_read(inode);
+ /*
+ * iomap_fiemap() returns EINVAL for 0 length. Make sure we don't trim
+ * length to 0 but still trim the range as much as possible since
+ * ext2_get_blocks() iterates unmapped space block by block which is
+ * slow.
+ */
+ if (i_size == 0)
+ i_size = 1;
+ len = min_t(u64, len, i_size);
+ ret = iomap_fiemap(inode, fieinfo, start, len, &ext2_iomap_ops);
+ inode_unlock(inode);
- ret = block_write_begin(mapping, pos, len, flags, pagep,
- ext2_get_block);
- if (ret < 0)
- ext2_write_failed(mapping, pos + len);
return ret;
}
-static int ext2_write_end(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
+static int ext2_read_folio(struct file *file, struct folio *folio)
{
- int ret;
+ return mpage_read_folio(folio, ext2_get_block);
+}
- ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
- if (ret < len)
- ext2_write_failed(mapping, pos + len);
- return ret;
+static void ext2_readahead(struct readahead_control *rac)
+{
+ mpage_readahead(rac, ext2_get_block);
}
static int
-ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
+ext2_write_begin(const struct kiocb *iocb, struct address_space *mapping,
+ loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
{
int ret;
- ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata,
- ext2_get_block);
+ ret = block_write_begin(mapping, pos, len, foliop, ext2_get_block);
if (ret < 0)
ext2_write_failed(mapping, pos + len);
return ret;
}
-static int ext2_nobh_writepage(struct page *page,
- struct writeback_control *wbc)
+static int ext2_write_end(const struct kiocb *iocb,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct folio *folio, void *fsdata)
{
- return nobh_writepage(page, ext2_get_block, wbc);
+ int ret;
+
+ ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
+ if (ret < len)
+ ext2_write_failed(mapping, pos + len);
+ return ret;
}
static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
@@ -847,58 +954,37 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
return generic_block_bmap(mapping,block,ext2_get_block);
}
-static ssize_t
-ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+static int
+ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- ssize_t ret;
-
- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- ext2_get_block);
- if (ret < 0 && (rw & WRITE))
- ext2_write_failed(mapping, offset + iov_length(iov, nr_segs));
- return ret;
+ return mpage_writepages(mapping, wbc, ext2_get_block);
}
static int
-ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
+ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
- return mpage_writepages(mapping, wbc, ext2_get_block);
+ struct ext2_sb_info *sbi = EXT2_SB(mapping->host->i_sb);
+
+ return dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
}
const struct address_space_operations ext2_aops = {
- .readpage = ext2_readpage,
- .readpages = ext2_readpages,
- .writepage = ext2_writepage,
+ .dirty_folio = block_dirty_folio,
+ .invalidate_folio = block_invalidate_folio,
+ .read_folio = ext2_read_folio,
+ .readahead = ext2_readahead,
.write_begin = ext2_write_begin,
.write_end = ext2_write_end,
.bmap = ext2_bmap,
- .direct_IO = ext2_direct_IO,
.writepages = ext2_writepages,
- .migratepage = buffer_migrate_page,
+ .migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
- .error_remove_page = generic_error_remove_page,
+ .error_remove_folio = generic_error_remove_folio,
};
-const struct address_space_operations ext2_aops_xip = {
- .bmap = ext2_bmap,
- .get_xip_mem = ext2_get_xip_mem,
-};
-
-const struct address_space_operations ext2_nobh_aops = {
- .readpage = ext2_readpage,
- .readpages = ext2_readpages,
- .writepage = ext2_nobh_writepage,
- .write_begin = ext2_nobh_write_begin,
- .write_end = nobh_write_end,
- .bmap = ext2_bmap,
- .direct_IO = ext2_direct_IO,
- .writepages = ext2_writepages,
- .migratepage = buffer_migrate_page,
- .error_remove_page = generic_error_remove_page,
+static const struct address_space_operations ext2_dax_aops = {
+ .writepages = ext2_dax_writepages,
+ .dirty_folio = noop_dirty_folio,
};
/*
@@ -1009,8 +1095,8 @@ no_top:
*/
static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
{
- unsigned long block_to_free = 0, count = 0;
- unsigned long nr;
+ ext2_fsblk_t block_to_free = 0, count = 0;
+ ext2_fsblk_t nr;
for ( ; p < q ; p++) {
nr = le32_to_cpu(*p);
@@ -1050,7 +1136,7 @@ static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int depth)
{
struct buffer_head * bh;
- unsigned long nr;
+ ext2_fsblk_t nr;
if (depth--) {
int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb);
@@ -1082,6 +1168,7 @@ static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int de
ext2_free_data(inode, p, q);
}
+/* mapping->invalidate_lock must be held when calling this function */
static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
{
__le32 *i_data = EXT2_I(inode)->i_data;
@@ -1097,6 +1184,10 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
blocksize = inode->i_sb->s_blocksize;
iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb);
+#ifdef CONFIG_FS_DAX
+ WARN_ON(!rwsem_is_locked(&inode->i_mapping->invalidate_lock));
+#endif
+
n = ext2_block_to_path(inode, iblock, offsets, NULL);
if (n == 0)
return;
@@ -1142,6 +1233,7 @@ do_indirects:
mark_inode_dirty(inode);
ext2_free_branches(inode, &nr, &nr+1, 1);
}
+ fallthrough;
case EXT2_IND_BLOCK:
nr = i_data[EXT2_DIND_BLOCK];
if (nr) {
@@ -1149,6 +1241,7 @@ do_indirects:
mark_inode_dirty(inode);
ext2_free_branches(inode, &nr, &nr+1, 2);
}
+ fallthrough;
case EXT2_DIND_BLOCK:
nr = i_data[EXT2_TIND_BLOCK];
if (nr) {
@@ -1156,6 +1249,7 @@ do_indirects:
mark_inode_dirty(inode);
ext2_free_branches(inode, &nr, &nr+1, 3);
}
+ break;
case EXT2_TIND_BLOCK:
;
}
@@ -1167,22 +1261,15 @@ do_indirects:
static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
{
- /*
- * XXX: it seems like a bug here that we don't allow
- * IS_APPEND inode to have blocks-past-i_size trimmed off.
- * review and fix this.
- *
- * Also would be nice to be able to handle IO errors and such,
- * but that's probably too much to ask.
- */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return;
if (ext2_inode_is_fast_symlink(inode))
return;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
- return;
+
+ filemap_invalidate_lock(inode->i_mapping);
__ext2_truncate_blocks(inode, offset);
+ filemap_invalidate_unlock(inode->i_mapping);
}
static int ext2_setsize(struct inode *inode, loff_t newsize)
@@ -1199,21 +1286,21 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
inode_dio_wait(inode);
- if (mapping_is_xip(inode->i_mapping))
- error = xip_truncate_page(inode->i_mapping, newsize);
- else if (test_opt(inode->i_sb, NOBH))
- error = nobh_truncate_page(inode->i_mapping,
- newsize, ext2_get_block);
+ if (IS_DAX(inode))
+ error = dax_truncate_page(inode, newsize, NULL,
+ &ext2_iomap_ops);
else
error = block_truncate_page(inode->i_mapping,
newsize, ext2_get_block);
if (error)
return error;
+ filemap_invalidate_lock(inode->i_mapping);
truncate_setsize(inode, newsize);
__ext2_truncate_blocks(inode, newsize);
+ filemap_invalidate_unlock(inode->i_mapping);
- inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
if (inode_needs_sync(inode)) {
sync_mapping_buffers(inode->i_mapping);
sync_inode_metadata(inode, 1);
@@ -1271,7 +1358,8 @@ void ext2_set_inode_flags(struct inode *inode)
{
unsigned int flags = EXT2_I(inode)->i_flags;
- inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+ inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
+ S_DIRSYNC | S_DAX);
if (flags & EXT2_SYNC_FL)
inode->i_flags |= S_SYNC;
if (flags & EXT2_APPEND_FL)
@@ -1282,31 +1370,24 @@ void ext2_set_inode_flags(struct inode *inode)
inode->i_flags |= S_NOATIME;
if (flags & EXT2_DIRSYNC_FL)
inode->i_flags |= S_DIRSYNC;
+ if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
+ inode->i_flags |= S_DAX;
}
-/* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
-void ext2_get_inode_flags(struct ext2_inode_info *ei)
+void ext2_set_file_ops(struct inode *inode)
{
- unsigned int flags = ei->vfs_inode.i_flags;
-
- ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL|
- EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL);
- if (flags & S_SYNC)
- ei->i_flags |= EXT2_SYNC_FL;
- if (flags & S_APPEND)
- ei->i_flags |= EXT2_APPEND_FL;
- if (flags & S_IMMUTABLE)
- ei->i_flags |= EXT2_IMMUTABLE_FL;
- if (flags & S_NOATIME)
- ei->i_flags |= EXT2_NOATIME_FL;
- if (flags & S_DIRSYNC)
- ei->i_flags |= EXT2_DIRSYNC_FL;
+ inode->i_op = &ext2_file_inode_operations;
+ inode->i_fop = &ext2_file_operations;
+ if (IS_DAX(inode))
+ inode->i_mapping->a_ops = &ext2_dax_aops;
+ else
+ inode->i_mapping->a_ops = &ext2_aops;
}
struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
{
struct ext2_inode_info *ei;
- struct buffer_head * bh;
+ struct buffer_head * bh = NULL;
struct ext2_inode *raw_inode;
struct inode *inode;
long ret = -EIO;
@@ -1317,7 +1398,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW))
+ if (!(inode_state_read_once(inode) & I_NEW))
return inode;
ei = EXT2_I(inode);
@@ -1340,10 +1421,9 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
i_gid_write(inode, i_gid);
set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
inode->i_size = le32_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
- inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
- inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0;
+ inode_set_atime(inode, (signed)le32_to_cpu(raw_inode->i_atime), 0);
+ inode_set_ctime(inode, (signed)le32_to_cpu(raw_inode->i_ctime), 0);
+ inode_set_mtime(inode, (signed)le32_to_cpu(raw_inode->i_mtime), 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.
* This is needed because nfsd might try to access dead inodes
@@ -1352,21 +1432,34 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
*/
if (inode->i_nlink == 0 && (inode->i_mode == 0 || ei->i_dtime)) {
/* this inode is deleted */
- brelse (bh);
ret = -ESTALE;
goto bad_inode;
}
inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
+ ext2_set_inode_flags(inode);
ei->i_faddr = le32_to_cpu(raw_inode->i_faddr);
ei->i_frag_no = raw_inode->i_frag;
ei->i_frag_size = raw_inode->i_fsize;
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
ei->i_dir_acl = 0;
+
+ if (ei->i_file_acl &&
+ !ext2_data_block_valid(EXT2_SB(sb), ei->i_file_acl, 1)) {
+ ext2_error(sb, "ext2_iget", "bad extended attribute block %u",
+ ei->i_file_acl);
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
+
if (S_ISREG(inode->i_mode))
inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
else
ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl);
+ if (i_size_read(inode) < 0) {
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
ei->i_dtime = 0;
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_state = 0;
@@ -1381,35 +1474,21 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
ei->i_data[n] = raw_inode->i_block[n];
if (S_ISREG(inode->i_mode)) {
- inode->i_op = &ext2_file_inode_operations;
- if (ext2_use_xip(inode->i_sb)) {
- inode->i_mapping->a_ops = &ext2_aops_xip;
- inode->i_fop = &ext2_xip_file_operations;
- } else if (test_opt(inode->i_sb, NOBH)) {
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- inode->i_fop = &ext2_file_operations;
- } else {
- inode->i_mapping->a_ops = &ext2_aops;
- inode->i_fop = &ext2_file_operations;
- }
+ ext2_set_file_ops(inode);
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &ext2_dir_inode_operations;
inode->i_fop = &ext2_dir_operations;
- if (test_opt(inode->i_sb, NOBH))
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- else
- inode->i_mapping->a_ops = &ext2_aops;
+ inode->i_mapping->a_ops = &ext2_aops;
} else if (S_ISLNK(inode->i_mode)) {
if (ext2_inode_is_fast_symlink(inode)) {
+ inode->i_link = (char *)ei->i_data;
inode->i_op = &ext2_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
} else {
inode->i_op = &ext2_symlink_inode_operations;
- if (test_opt(inode->i_sb, NOBH))
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- else
- inode->i_mapping->a_ops = &ext2_aops;
+ inode_nohighmem(inode);
+ inode->i_mapping->a_ops = &ext2_aops;
}
} else {
inode->i_op = &ext2_special_inode_operations;
@@ -1421,11 +1500,11 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
}
brelse (bh);
- ext2_set_inode_flags(inode);
unlock_new_inode(inode);
return inode;
bad_inode:
+ brelse(bh);
iget_failed(inode);
return ERR_PTR(ret);
}
@@ -1445,12 +1524,11 @@ static int __ext2_write_inode(struct inode *inode, int do_sync)
if (IS_ERR(raw_inode))
return -EIO;
- /* For fields not not tracking in the in-memory inode,
+ /* For fields not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
if (ei->i_state & EXT2_STATE_NEW)
memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size);
- ext2_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if (!(test_opt(sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(uid));
@@ -1474,9 +1552,9 @@ static int __ext2_write_inode(struct inode *inode, int do_sync)
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le32(inode->i_size);
- raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
- raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
- raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
+ raw_inode->i_atime = cpu_to_le32(inode_get_atime_sec(inode));
+ raw_inode->i_ctime = cpu_to_le32(inode_get_ctime_sec(inode));
+ raw_inode->i_mtime = cpu_to_le32(inode_get_mtime_sec(inode));
raw_inode->i_blocks = cpu_to_le32(inode->i_blocks);
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
@@ -1502,7 +1580,7 @@ static int __ext2_write_inode(struct inode *inode, int do_sync)
EXT2_SET_RO_COMPAT_FEATURE(sb,
EXT2_FEATURE_RO_COMPAT_LARGE_FILE);
spin_unlock(&EXT2_SB(sb)->s_lock);
- ext2_write_super(sb);
+ ext2_sync_super(sb, EXT2_SB(sb)->s_es, 1);
}
}
}
@@ -1540,20 +1618,50 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc)
return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
}
-int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
+int ext2_getattr(struct mnt_idmap *idmap, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int query_flags)
+{
+ struct inode *inode = d_inode(path->dentry);
+ struct ext2_inode_info *ei = EXT2_I(inode);
+ unsigned int flags;
+
+ flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
+ if (flags & EXT2_APPEND_FL)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (flags & EXT2_COMPR_FL)
+ stat->attributes |= STATX_ATTR_COMPRESSED;
+ if (flags & EXT2_IMMUTABLE_FL)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (flags & EXT2_NODUMP_FL)
+ stat->attributes |= STATX_ATTR_NODUMP;
+ stat->attributes_mask |= (STATX_ATTR_APPEND |
+ STATX_ATTR_COMPRESSED |
+ STATX_ATTR_ENCRYPTED |
+ STATX_ATTR_IMMUTABLE |
+ STATX_ATTR_NODUMP);
+
+ generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+ return 0;
+}
+
+int ext2_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+ struct iattr *iattr)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
int error;
- error = inode_change_ok(inode, iattr);
+ error = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
if (error)
return error;
- if (is_quota_modification(inode, iattr))
- dquot_initialize(inode);
- if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
- (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
- error = dquot_transfer(inode, iattr);
+ if (is_quota_modification(&nop_mnt_idmap, inode, iattr)) {
+ error = dquot_initialize(inode);
+ if (error)
+ return error;
+ }
+ if (i_uid_needs_update(&nop_mnt_idmap, iattr, inode) ||
+ i_gid_needs_update(&nop_mnt_idmap, iattr, inode)) {
+ error = dquot_transfer(&nop_mnt_idmap, inode, iattr);
if (error)
return error;
}
@@ -1562,9 +1670,9 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
if (error)
return error;
}
- setattr_copy(inode, iattr);
+ setattr_copy(&nop_mnt_idmap, inode, iattr);
if (iattr->ia_valid & ATTR_MODE)
- error = ext2_acl_chmod(inode);
+ error = posix_acl_chmod(&nop_mnt_idmap, dentry, inode->i_mode);
mark_inode_dirty(inode);
return error;
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 5d46c09863f0..c3fea55b8efa 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/ioctl.c
*
@@ -14,85 +15,58 @@
#include <linux/compat.h>
#include <linux/mount.h>
#include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
+#include <linux/fileattr.h>
-
-long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+int ext2_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
{
- struct inode *inode = file_inode(filp);
- struct ext2_inode_info *ei = EXT2_I(inode);
- unsigned int flags;
- unsigned short rsv_window_size;
- int ret;
+ struct ext2_inode_info *ei = EXT2_I(d_inode(dentry));
- ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+ fileattr_fill_flags(fa, ei->i_flags & EXT2_FL_USER_VISIBLE);
- switch (cmd) {
- case EXT2_IOC_GETFLAGS:
- ext2_get_inode_flags(ei);
- flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
- return put_user(flags, (int __user *) arg);
- case EXT2_IOC_SETFLAGS: {
- unsigned int oldflags;
+ return 0;
+}
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
+int ext2_fileattr_set(struct mnt_idmap *idmap,
+ struct dentry *dentry, struct file_kattr *fa)
+{
+ struct inode *inode = d_inode(dentry);
+ struct ext2_inode_info *ei = EXT2_I(inode);
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto setflags_out;
- }
+ if (fileattr_has_fsx(fa))
+ return -EOPNOTSUPP;
- if (get_user(flags, (int __user *) arg)) {
- ret = -EFAULT;
- goto setflags_out;
- }
+ /* Is it quota file? Do not allow user to mess with it */
+ if (IS_NOQUOTA(inode))
+ return -EPERM;
- flags = ext2_mask_flags(inode->i_mode, flags);
+ ei->i_flags = (ei->i_flags & ~EXT2_FL_USER_MODIFIABLE) |
+ (fa->flags & EXT2_FL_USER_MODIFIABLE);
- mutex_lock(&inode->i_mutex);
- /* Is it quota file? Do not allow user to mess with it */
- if (IS_NOQUOTA(inode)) {
- mutex_unlock(&inode->i_mutex);
- ret = -EPERM;
- goto setflags_out;
- }
- oldflags = ei->i_flags;
+ ext2_set_inode_flags(inode);
+ inode_set_ctime_current(inode);
+ mark_inode_dirty(inode);
- /*
- * The IMMUTABLE and APPEND_ONLY flags can only be changed by
- * the relevant capability.
- *
- * This test looks nicer. Thanks to Pauline Middelink
- */
- if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) {
- if (!capable(CAP_LINUX_IMMUTABLE)) {
- mutex_unlock(&inode->i_mutex);
- ret = -EPERM;
- goto setflags_out;
- }
- }
+ return 0;
+}
- flags = flags & EXT2_FL_USER_MODIFIABLE;
- flags |= oldflags & ~EXT2_FL_USER_MODIFIABLE;
- ei->i_flags = flags;
- ext2_set_inode_flags(inode);
- inode->i_ctime = CURRENT_TIME_SEC;
- mutex_unlock(&inode->i_mutex);
+long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct ext2_inode_info *ei = EXT2_I(inode);
+ unsigned short rsv_window_size;
+ int ret;
- mark_inode_dirty(inode);
-setflags_out:
- mnt_drop_write_file(filp);
- return ret;
- }
+ ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+
+ switch (cmd) {
case EXT2_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *) arg);
case EXT2_IOC_SETVERSION: {
__u32 generation;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
return -EPERM;
ret = mnt_want_write_file(filp);
if (ret)
@@ -102,10 +76,10 @@ setflags_out:
goto setversion_out;
}
- mutex_lock(&inode->i_mutex);
- inode->i_ctime = CURRENT_TIME_SEC;
+ inode_lock(inode);
+ inode_set_ctime_current(inode);
inode->i_generation = generation;
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
mark_inode_dirty(inode);
setversion_out:
@@ -125,7 +99,7 @@ setversion_out:
if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
return -ENOTTY;
- if (!inode_owner_or_capable(inode))
+ if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
return -EACCES;
if (get_user(rsv_window_size, (int __user *)arg))
@@ -153,10 +127,13 @@ setversion_out:
if (ei->i_block_alloc_info){
struct ext2_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
rsv->rsv_goal_size = rsv_window_size;
+ } else {
+ ret = -ENOMEM;
}
+
mutex_unlock(&ei->truncate_mutex);
mnt_drop_write_file(filp);
- return 0;
+ return ret;
}
default:
return -ENOTTY;
@@ -168,12 +145,6 @@ long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
/* These are just misnamed, they actually get/put from/to user an int */
switch (cmd) {
- case EXT2_IOC32_GETFLAGS:
- cmd = EXT2_IOC_GETFLAGS;
- break;
- case EXT2_IOC32_SETFLAGS:
- cmd = EXT2_IOC_SETFLAGS;
- break;
case EXT2_IOC32_GETVERSION:
cmd = EXT2_IOC_GETVERSION;
break;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 256dd5f4c1c4..bde617a66cec 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/namei.c
*
@@ -35,19 +36,16 @@
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
-#include "xip.h"
static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ext2_add_link(dentry, inode);
if (!err) {
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
return err;
}
@@ -59,13 +57,17 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, uns
{
struct inode * inode;
ino_t ino;
+ int res;
if (dentry->d_name.len > EXT2_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
- ino = ext2_inode_by_name(dir, &dentry->d_name);
- inode = NULL;
- if (ino) {
+ res = ext2_inode_by_name(dir, &dentry->d_name, &ino);
+ if (res) {
+ if (res != -ENOENT)
+ return ERR_PTR(res);
+ inode = NULL;
+ } else {
inode = ext2_iget(dir->i_sb, ino);
if (inode == ERR_PTR(-ESTALE)) {
ext2_error(dir->i_sb, __func__,
@@ -79,11 +81,14 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, uns
struct dentry *ext2_get_parent(struct dentry *child)
{
- struct qstr dotdot = QSTR_INIT("..", 2);
- unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot);
- if (!ino)
- return ERR_PTR(-ENOENT);
- return d_obtain_alias(ext2_iget(child->d_inode->i_sb, ino));
+ ino_t ino;
+ int res;
+
+ res = ext2_inode_by_name(d_inode(child), &dotdot_name, &ino);
+ if (res)
+ return ERR_PTR(res);
+
+ return d_obtain_alias(ext2_iget(child->d_sb, ino));
}
/*
@@ -94,79 +99,63 @@ struct dentry *ext2_get_parent(struct dentry *child)
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
+static int ext2_create (struct mnt_idmap * idmap,
+ struct inode * dir, struct dentry * dentry,
+ umode_t mode, bool excl)
{
struct inode *inode;
+ int err;
- dquot_initialize(dir);
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
inode = ext2_new_inode(dir, mode, &dentry->d_name);
if (IS_ERR(inode))
return PTR_ERR(inode);
- inode->i_op = &ext2_file_inode_operations;
- if (ext2_use_xip(inode->i_sb)) {
- inode->i_mapping->a_ops = &ext2_aops_xip;
- inode->i_fop = &ext2_xip_file_operations;
- } else if (test_opt(inode->i_sb, NOBH)) {
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- inode->i_fop = &ext2_file_operations;
- } else {
- inode->i_mapping->a_ops = &ext2_aops;
- inode->i_fop = &ext2_file_operations;
- }
+ ext2_set_file_ops(inode);
mark_inode_dirty(inode);
return ext2_add_nondir(dentry, inode);
}
-static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int ext2_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
+ struct file *file, umode_t mode)
{
struct inode *inode = ext2_new_inode(dir, mode, NULL);
if (IS_ERR(inode))
return PTR_ERR(inode);
- inode->i_op = &ext2_file_inode_operations;
- if (ext2_use_xip(inode->i_sb)) {
- inode->i_mapping->a_ops = &ext2_aops_xip;
- inode->i_fop = &ext2_xip_file_operations;
- } else if (test_opt(inode->i_sb, NOBH)) {
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- inode->i_fop = &ext2_file_operations;
- } else {
- inode->i_mapping->a_ops = &ext2_aops;
- inode->i_fop = &ext2_file_operations;
- }
+ ext2_set_file_ops(inode);
mark_inode_dirty(inode);
- d_tmpfile(dentry, inode);
+ d_tmpfile(file, inode);
unlock_new_inode(inode);
- return 0;
+ return finish_open_simple(file, 0);
}
-static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+static int ext2_mknod (struct mnt_idmap * idmap, struct inode * dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode * inode;
int err;
- if (!new_valid_dev(rdev))
- return -EINVAL;
-
- dquot_initialize(dir);
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
inode = ext2_new_inode (dir, mode, &dentry->d_name);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
-#ifdef CONFIG_EXT2_FS_XATTR
inode->i_op = &ext2_special_inode_operations;
-#endif
mark_inode_dirty(inode);
err = ext2_add_nondir(dentry, inode);
}
return err;
}
-static int ext2_symlink (struct inode * dir, struct dentry * dentry,
- const char * symname)
+static int ext2_symlink (struct mnt_idmap * idmap, struct inode * dir,
+ struct dentry * dentry, const char * symname)
{
struct super_block * sb = dir->i_sb;
int err = -ENAMETOOLONG;
@@ -176,7 +165,9 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry,
if (l > sb->s_blocksize)
goto out;
- dquot_initialize(dir);
+ err = dquot_initialize(dir);
+ if (err)
+ goto out;
inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO, &dentry->d_name);
err = PTR_ERR(inode);
@@ -186,17 +177,16 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry,
if (l > sizeof (EXT2_I(inode)->i_data)) {
/* slow symlink */
inode->i_op = &ext2_symlink_inode_operations;
- if (test_opt(inode->i_sb, NOBH))
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- else
- inode->i_mapping->a_ops = &ext2_aops;
+ inode_nohighmem(inode);
+ inode->i_mapping->a_ops = &ext2_aops;
err = page_symlink(inode, symname, l);
if (err)
goto out_fail;
} else {
/* fast symlink */
inode->i_op = &ext2_fast_symlink_inode_operations;
- memcpy((char*)(EXT2_I(inode)->i_data),symname,l);
+ inode->i_link = (char*)EXT2_I(inode)->i_data;
+ memcpy(inode->i_link, symname, l);
inode->i_size = l-1;
}
mark_inode_dirty(inode);
@@ -207,20 +197,21 @@ out:
out_fail:
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput (inode);
+ discard_new_inode(inode);
goto out;
}
static int ext2_link (struct dentry * old_dentry, struct inode * dir,
struct dentry *dentry)
{
- struct inode *inode = old_dentry->d_inode;
+ struct inode *inode = d_inode(old_dentry);
int err;
- dquot_initialize(dir);
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
- inode->i_ctime = CURRENT_TIME_SEC;
+ inode_set_ctime_current(inode);
inode_inc_link_count(inode);
ihold(inode);
@@ -234,12 +225,16 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir,
return err;
}
-static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
+static struct dentry *ext2_mkdir(struct mnt_idmap * idmap,
+ struct inode * dir, struct dentry * dentry,
+ umode_t mode)
{
struct inode * inode;
int err;
- dquot_initialize(dir);
+ err = dquot_initialize(dir);
+ if (err)
+ return ERR_PTR(err);
inode_inc_link_count(dir);
@@ -250,10 +245,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
inode->i_op = &ext2_dir_inode_operations;
inode->i_fop = &ext2_dir_operations;
- if (test_opt(inode->i_sb, NOBH))
- inode->i_mapping->a_ops = &ext2_nobh_aops;
- else
- inode->i_mapping->a_ops = &ext2_aops;
+ inode->i_mapping->a_ops = &ext2_aops;
inode_inc_link_count(inode);
@@ -265,39 +257,42 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
if (err)
goto out_fail;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out:
- return err;
+ return ERR_PTR(err);
out_fail:
inode_dec_link_count(inode);
inode_dec_link_count(inode);
- unlock_new_inode(inode);
- iput(inode);
+ discard_new_inode(inode);
out_dir:
inode_dec_link_count(dir);
goto out;
}
-static int ext2_unlink(struct inode * dir, struct dentry *dentry)
+static int ext2_unlink(struct inode *dir, struct dentry *dentry)
{
- struct inode * inode = dentry->d_inode;
- struct ext2_dir_entry_2 * de;
- struct page * page;
- int err = -ENOENT;
+ struct inode *inode = d_inode(dentry);
+ struct ext2_dir_entry_2 *de;
+ struct folio *folio;
+ int err;
- dquot_initialize(dir);
+ err = dquot_initialize(dir);
+ if (err)
+ goto out;
- de = ext2_find_entry (dir, &dentry->d_name, &page);
- if (!de)
+ de = ext2_find_entry(dir, &dentry->d_name, &folio);
+ if (IS_ERR(de)) {
+ err = PTR_ERR(de);
goto out;
+ }
- err = ext2_delete_entry (de, page);
+ err = ext2_delete_entry(de, folio);
+ folio_release_kmap(folio, de);
if (err)
goto out;
- inode->i_ctime = dir->i_ctime;
+ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
inode_dec_link_count(inode);
err = 0;
out:
@@ -306,7 +301,7 @@ out:
static int ext2_rmdir (struct inode * dir, struct dentry *dentry)
{
- struct inode * inode = dentry->d_inode;
+ struct inode * inode = d_inode(dentry);
int err = -ENOTEMPTY;
if (ext2_empty_dir(inode)) {
@@ -320,53 +315,69 @@ static int ext2_rmdir (struct inode * dir, struct dentry *dentry)
return err;
}
-static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
- struct inode * new_dir, struct dentry * new_dentry )
+static int ext2_rename (struct mnt_idmap * idmap,
+ struct inode * old_dir, struct dentry * old_dentry,
+ struct inode * new_dir, struct dentry * new_dentry,
+ unsigned int flags)
{
- struct inode * old_inode = old_dentry->d_inode;
- struct inode * new_inode = new_dentry->d_inode;
- struct page * dir_page = NULL;
+ struct inode * old_inode = d_inode(old_dentry);
+ struct inode * new_inode = d_inode(new_dentry);
+ struct folio *dir_folio = NULL;
struct ext2_dir_entry_2 * dir_de = NULL;
- struct page * old_page;
+ struct folio * old_folio;
struct ext2_dir_entry_2 * old_de;
- int err = -ENOENT;
+ bool old_is_dir = S_ISDIR(old_inode->i_mode);
+ int err;
- dquot_initialize(old_dir);
- dquot_initialize(new_dir);
+ if (flags & ~RENAME_NOREPLACE)
+ return -EINVAL;
- old_de = ext2_find_entry (old_dir, &old_dentry->d_name, &old_page);
- if (!old_de)
- goto out;
+ err = dquot_initialize(old_dir);
+ if (err)
+ return err;
- if (S_ISDIR(old_inode->i_mode)) {
+ err = dquot_initialize(new_dir);
+ if (err)
+ return err;
+
+ old_de = ext2_find_entry(old_dir, &old_dentry->d_name, &old_folio);
+ if (IS_ERR(old_de))
+ return PTR_ERR(old_de);
+
+ if (old_is_dir && old_dir != new_dir) {
err = -EIO;
- dir_de = ext2_dotdot(old_inode, &dir_page);
+ dir_de = ext2_dotdot(old_inode, &dir_folio);
if (!dir_de)
goto out_old;
}
if (new_inode) {
- struct page *new_page;
+ struct folio *new_folio;
struct ext2_dir_entry_2 *new_de;
err = -ENOTEMPTY;
- if (dir_de && !ext2_empty_dir (new_inode))
+ if (old_is_dir && !ext2_empty_dir(new_inode))
goto out_dir;
- err = -ENOENT;
- new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page);
- if (!new_de)
+ new_de = ext2_find_entry(new_dir, &new_dentry->d_name,
+ &new_folio);
+ if (IS_ERR(new_de)) {
+ err = PTR_ERR(new_de);
+ goto out_dir;
+ }
+ err = ext2_set_link(new_dir, new_de, new_folio, old_inode, true);
+ folio_release_kmap(new_folio, new_de);
+ if (err)
goto out_dir;
- ext2_set_link(new_dir, new_de, new_page, old_inode, 1);
- new_inode->i_ctime = CURRENT_TIME_SEC;
- if (dir_de)
+ inode_set_ctime_current(new_inode);
+ if (old_is_dir)
drop_nlink(new_inode);
inode_dec_link_count(new_inode);
} else {
err = ext2_add_link(new_dentry, old_inode);
if (err)
goto out_dir;
- if (dir_de)
+ if (old_is_dir)
inode_inc_link_count(new_dir);
}
@@ -374,32 +385,22 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
* Like most other Unix systems, set the ctime for inodes on a
* rename.
*/
- old_inode->i_ctime = CURRENT_TIME_SEC;
+ inode_set_ctime_current(old_inode);
mark_inode_dirty(old_inode);
- ext2_delete_entry (old_de, old_page);
-
- if (dir_de) {
+ err = ext2_delete_entry(old_de, old_folio);
+ if (!err && old_is_dir) {
if (old_dir != new_dir)
- ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0);
- else {
- kunmap(dir_page);
- page_cache_release(dir_page);
- }
+ err = ext2_set_link(old_inode, dir_de, dir_folio,
+ new_dir, false);
+
inode_dec_link_count(old_dir);
}
- return 0;
-
-
out_dir:
- if (dir_de) {
- kunmap(dir_page);
- page_cache_release(dir_page);
- }
+ if (dir_de)
+ folio_release_kmap(dir_folio, dir_de);
out_old:
- kunmap(old_page);
- page_cache_release(old_page);
-out:
+ folio_release_kmap(old_folio, old_de);
return err;
}
@@ -413,24 +414,20 @@ const struct inode_operations ext2_dir_inode_operations = {
.rmdir = ext2_rmdir,
.mknod = ext2_mknod,
.rename = ext2_rename,
-#ifdef CONFIG_EXT2_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
- .removexattr = generic_removexattr,
-#endif
+ .getattr = ext2_getattr,
.setattr = ext2_setattr,
- .get_acl = ext2_get_acl,
+ .get_inode_acl = ext2_get_acl,
+ .set_acl = ext2_set_acl,
.tmpfile = ext2_tmpfile,
+ .fileattr_get = ext2_fileattr_get,
+ .fileattr_set = ext2_fileattr_set,
};
const struct inode_operations ext2_special_inode_operations = {
-#ifdef CONFIG_EXT2_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
- .removexattr = generic_removexattr,
-#endif
+ .getattr = ext2_getattr,
.setattr = ext2_setattr,
- .get_acl = ext2_get_acl,
+ .get_inode_acl = ext2_get_acl,
+ .set_acl = ext2_set_acl,
};
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 288534920fe5..121e634c792a 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/ext2/super.c
*
@@ -22,7 +23,8 @@
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
-#include <linux/parser.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/random.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
@@ -31,15 +33,14 @@
#include <linux/mount.h>
#include <linux/log2.h>
#include <linux/quotaops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
+#include <linux/dax.h>
+#include <linux/iversion.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
-#include "xip.h"
-static void ext2_sync_super(struct super_block *sb,
- struct ext2_super_block *es, int wait);
-static int ext2_remount (struct super_block * sb, int * flags, char * data);
+static void ext2_write_super(struct super_block *sb);
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
static int ext2_sync_fs(struct super_block *sb, int wait);
static int ext2_freeze(struct super_block *sb);
@@ -53,7 +54,7 @@ void ext2_error(struct super_block *sb, const char *function,
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;
- if (!(sb->s_flags & MS_RDONLY)) {
+ if (!sb_rdonly(sb)) {
spin_lock(&sbi->s_lock);
sbi->s_mount_state |= EXT2_ERROR_FS;
es->s_state |= cpu_to_le16(EXT2_ERROR_FS);
@@ -73,13 +74,40 @@ void ext2_error(struct super_block *sb, const char *function,
if (test_opt(sb, ERRORS_PANIC))
panic("EXT2-fs: panic from previous error\n");
- if (test_opt(sb, ERRORS_RO)) {
+ if (!sb_rdonly(sb) && test_opt(sb, ERRORS_RO)) {
ext2_msg(sb, KERN_CRIT,
"error: remounting filesystem read-only");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
}
+static void ext2_msg_fc(struct fs_context *fc, const char *prefix,
+ const char *fmt, ...)
+{
+ struct va_format vaf;
+ va_list args;
+ const char *s_id;
+
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ s_id = fc->root->d_sb->s_id;
+ } else {
+ /* get last path component of source */
+ s_id = strrchr(fc->source, '/');
+ if (s_id)
+ s_id++;
+ else
+ s_id = fc->source;
+ }
+ va_start(args, fmt);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ printk("%sEXT2-fs (%s): %pV\n", prefix, s_id, &vaf);
+
+ va_end(args);
+}
+
void ext2_msg(struct super_block *sb, const char *prefix,
const char *fmt, ...)
{
@@ -124,16 +152,34 @@ void ext2_update_dynamic_rev(struct super_block *sb)
*/
}
+#ifdef CONFIG_QUOTA
+static int ext2_quota_off(struct super_block *sb, int type);
+
+static void ext2_quota_off_umount(struct super_block *sb)
+{
+ int type;
+
+ for (type = 0; type < MAXQUOTAS; type++)
+ ext2_quota_off(sb, type);
+}
+#else
+static inline void ext2_quota_off_umount(struct super_block *sb)
+{
+}
+#endif
+
static void ext2_put_super (struct super_block * sb)
{
int db_count;
int i;
struct ext2_sb_info *sbi = EXT2_SB(sb);
- dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+ ext2_quota_off_umount(sb);
- ext2_xattr_put_super(sb);
- if (!(sb->s_flags & MS_RDONLY)) {
+ ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
+ sbi->s_ea_block_cache = NULL;
+
+ if (!sb_rdonly(sb)) {
struct ext2_super_block *es = sbi->s_es;
spin_lock(&sbi->s_lock);
@@ -143,9 +189,8 @@ static void ext2_put_super (struct super_block * sb)
}
db_count = sbi->s_gdb_count;
for (i = 0; i < db_count; i++)
- if (sbi->s_group_desc[i])
- brelse (sbi->s_group_desc[i]);
- kfree(sbi->s_group_desc);
+ brelse(sbi->s_group_desc[i]);
+ kvfree(sbi->s_group_desc);
kfree(sbi->s_debts);
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
@@ -153,6 +198,7 @@ static void ext2_put_super (struct super_block * sb)
brelse (sbi->s_sbh);
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
+ fs_put_dax(sbi->s_daxdev, NULL);
kfree(sbi);
}
@@ -161,25 +207,23 @@ static struct kmem_cache * ext2_inode_cachep;
static struct inode *ext2_alloc_inode(struct super_block *sb)
{
struct ext2_inode_info *ei;
- ei = (struct ext2_inode_info *)kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL);
+ ei = alloc_inode_sb(sb, ext2_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
ei->i_block_alloc_info = NULL;
- ei->vfs_inode.i_version = 1;
+ inode_set_iversion(&ei->vfs_inode, 1);
+#ifdef CONFIG_QUOTA
+ memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
+#endif
+
return &ei->vfs_inode;
}
-static void ext2_i_callback(struct rcu_head *head)
+static void ext2_free_in_core_inode(struct inode *inode)
{
- struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
}
-static void ext2_destroy_inode(struct inode *inode)
-{
- call_rcu(&inode->i_rcu, ext2_i_callback);
-}
-
static void init_once(void *foo)
{
struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;
@@ -192,13 +236,14 @@ static void init_once(void *foo)
inode_init_once(&ei->vfs_inode);
}
-static int init_inodecache(void)
+static int __init init_inodecache(void)
{
- ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",
- sizeof(struct ext2_inode_info),
- 0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD),
- init_once);
+ ext2_inode_cachep = kmem_cache_create_usercopy("ext2_inode_cache",
+ sizeof(struct ext2_inode_info), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
+ offsetof(struct ext2_inode_info, i_data),
+ sizeof_field(struct ext2_inode_info, i_data),
+ init_once);
if (ext2_inode_cachep == NULL)
return -ENOMEM;
return 0;
@@ -277,21 +322,17 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",noacl");
#endif
- if (test_opt(sb, NOBH))
- seq_puts(seq, ",nobh");
-
-#if defined(CONFIG_QUOTA)
- if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA)
+ if (test_opt(sb, USRQUOTA))
seq_puts(seq, ",usrquota");
- if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA)
+ if (test_opt(sb, GRPQUOTA))
seq_puts(seq, ",grpquota");
-#endif
-#if defined(CONFIG_EXT2_FS_XIP)
- if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
+ if (test_opt(sb, XIP))
seq_puts(seq, ",xip");
-#endif
+
+ if (test_opt(sb, DAX))
+ seq_puts(seq, ",dax");
if (!test_opt(sb, RESERVATION))
seq_puts(seq, ",noreservation");
@@ -303,11 +344,28 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
#ifdef CONFIG_QUOTA
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off);
static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
+static int ext2_quota_on(struct super_block *sb, int type, int format_id,
+ const struct path *path);
+static struct dquot __rcu **ext2_get_dquots(struct inode *inode)
+{
+ return EXT2_I(inode)->i_dquot;
+}
+
+static const struct quotactl_ops ext2_quotactl_ops = {
+ .quota_on = ext2_quota_on,
+ .quota_off = ext2_quota_off,
+ .quota_sync = dquot_quota_sync,
+ .get_state = dquot_get_state,
+ .set_info = dquot_set_dqinfo,
+ .get_dqblk = dquot_get_dqblk,
+ .set_dqblk = dquot_set_dqblk,
+ .get_nextdqblk = dquot_get_next_dqblk,
+};
#endif
static const struct super_operations ext2_sops = {
.alloc_inode = ext2_alloc_inode,
- .destroy_inode = ext2_destroy_inode,
+ .free_inode = ext2_free_in_core_inode,
.write_inode = ext2_write_inode,
.evict_inode = ext2_evict_inode,
.put_super = ext2_put_super,
@@ -315,11 +373,11 @@ static const struct super_operations ext2_sops = {
.freeze_fs = ext2_freeze,
.unfreeze_fs = ext2_unfreeze,
.statfs = ext2_statfs,
- .remount_fs = ext2_remount,
.show_options = ext2_show_options,
#ifdef CONFIG_QUOTA
.quota_read = ext2_quota_read,
.quota_write = ext2_quota_write,
+ .get_dquots = ext2_get_dquots,
#endif
};
@@ -364,232 +422,224 @@ static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid,
}
static const struct export_operations ext2_export_ops = {
+ .encode_fh = generic_encode_ino32_fh,
.fh_to_dentry = ext2_fh_to_dentry,
.fh_to_parent = ext2_fh_to_parent,
.get_parent = ext2_get_parent,
};
-static unsigned long get_sb_block(void **data)
-{
- unsigned long sb_block;
- char *options = (char *) *data;
-
- if (!options || strncmp(options, "sb=", 3) != 0)
- return 1; /* Default location */
- options += 3;
- sb_block = simple_strtoul(options, &options, 0);
- if (*options && *options != ',') {
- printk("EXT2-fs: Invalid sb specification: %s\n",
- (char *) *data);
- return 1;
- }
- if (*options == ',')
- options++;
- *data = (void *) options;
- return sb_block;
-}
-
enum {
- Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
- Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
- Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
- Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
- Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
- Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
+ Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, Opt_resgid, Opt_resuid,
+ Opt_sb, Opt_errors, Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
+ Opt_nobh, Opt_user_xattr, Opt_acl, Opt_xip, Opt_dax, Opt_ignore,
+ Opt_quota, Opt_usrquota, Opt_grpquota, Opt_reservation,
+};
+
+static const struct constant_table ext2_param_errors[] = {
+ {"continue", EXT2_MOUNT_ERRORS_CONT},
+ {"panic", EXT2_MOUNT_ERRORS_PANIC},
+ {"remount-ro", EXT2_MOUNT_ERRORS_RO},
+ {}
+};
+
+static const struct fs_parameter_spec ext2_param_spec[] = {
+ fsparam_flag ("bsddf", Opt_bsd_df),
+ fsparam_flag ("minixdf", Opt_minix_df),
+ fsparam_flag ("grpid", Opt_grpid),
+ fsparam_flag ("bsdgroups", Opt_grpid),
+ fsparam_flag ("nogrpid", Opt_nogrpid),
+ fsparam_flag ("sysvgroups", Opt_nogrpid),
+ fsparam_gid ("resgid", Opt_resgid),
+ fsparam_uid ("resuid", Opt_resuid),
+ fsparam_u32 ("sb", Opt_sb),
+ fsparam_enum ("errors", Opt_errors, ext2_param_errors),
+ fsparam_flag ("nouid32", Opt_nouid32),
+ fsparam_flag ("debug", Opt_debug),
+ fsparam_flag ("oldalloc", Opt_oldalloc),
+ fsparam_flag ("orlov", Opt_orlov),
+ fsparam_flag ("nobh", Opt_nobh),
+ fsparam_flag_no ("user_xattr", Opt_user_xattr),
+ fsparam_flag_no ("acl", Opt_acl),
+ fsparam_flag ("xip", Opt_xip),
+ fsparam_flag ("dax", Opt_dax),
+ fsparam_flag ("grpquota", Opt_grpquota),
+ fsparam_flag ("noquota", Opt_ignore),
+ fsparam_flag ("quota", Opt_quota),
+ fsparam_flag ("usrquota", Opt_usrquota),
+ fsparam_flag_no ("reservation", Opt_reservation),
+ {}
};
-static const match_table_t tokens = {
- {Opt_bsd_df, "bsddf"},
- {Opt_minix_df, "minixdf"},
- {Opt_grpid, "grpid"},
- {Opt_grpid, "bsdgroups"},
- {Opt_nogrpid, "nogrpid"},
- {Opt_nogrpid, "sysvgroups"},
- {Opt_resgid, "resgid=%u"},
- {Opt_resuid, "resuid=%u"},
- {Opt_sb, "sb=%u"},
- {Opt_err_cont, "errors=continue"},
- {Opt_err_panic, "errors=panic"},
- {Opt_err_ro, "errors=remount-ro"},
- {Opt_nouid32, "nouid32"},
- {Opt_nocheck, "check=none"},
- {Opt_nocheck, "nocheck"},
- {Opt_debug, "debug"},
- {Opt_oldalloc, "oldalloc"},
- {Opt_orlov, "orlov"},
- {Opt_nobh, "nobh"},
- {Opt_user_xattr, "user_xattr"},
- {Opt_nouser_xattr, "nouser_xattr"},
- {Opt_acl, "acl"},
- {Opt_noacl, "noacl"},
- {Opt_xip, "xip"},
- {Opt_grpquota, "grpquota"},
- {Opt_ignore, "noquota"},
- {Opt_quota, "quota"},
- {Opt_usrquota, "usrquota"},
- {Opt_reservation, "reservation"},
- {Opt_noreservation, "noreservation"},
- {Opt_err, NULL}
+#define EXT2_SPEC_s_resuid (1 << 0)
+#define EXT2_SPEC_s_resgid (1 << 1)
+
+struct ext2_fs_context {
+ unsigned long vals_s_flags; /* Bits to set in s_flags */
+ unsigned long mask_s_flags; /* Bits changed in s_flags */
+ unsigned int vals_s_mount_opt;
+ unsigned int mask_s_mount_opt;
+ kuid_t s_resuid;
+ kgid_t s_resgid;
+ unsigned long s_sb_block;
+ unsigned int spec;
+
};
-static int parse_options(char *options, struct super_block *sb)
+static inline void ctx_set_mount_opt(struct ext2_fs_context *ctx,
+ unsigned long flag)
{
- char *p;
- struct ext2_sb_info *sbi = EXT2_SB(sb);
- substring_t args[MAX_OPT_ARGS];
- int option;
- kuid_t uid;
- kgid_t gid;
-
- if (!options)
- return 1;
-
- while ((p = strsep (&options, ",")) != NULL) {
- int token;
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_bsd_df:
- clear_opt (sbi->s_mount_opt, MINIX_DF);
- break;
- case Opt_minix_df:
- set_opt (sbi->s_mount_opt, MINIX_DF);
- break;
- case Opt_grpid:
- set_opt (sbi->s_mount_opt, GRPID);
- break;
- case Opt_nogrpid:
- clear_opt (sbi->s_mount_opt, GRPID);
- break;
- case Opt_resuid:
- if (match_int(&args[0], &option))
- return 0;
- uid = make_kuid(current_user_ns(), option);
- if (!uid_valid(uid)) {
- ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option);
- return 0;
-
- }
- sbi->s_resuid = uid;
- break;
- case Opt_resgid:
- if (match_int(&args[0], &option))
- return 0;
- gid = make_kgid(current_user_ns(), option);
- if (!gid_valid(gid)) {
- ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option);
- return 0;
- }
- sbi->s_resgid = gid;
- break;
- case Opt_sb:
- /* handled by get_sb_block() instead of here */
- /* *sb_block = match_int(&args[0]); */
- break;
- case Opt_err_panic:
- clear_opt (sbi->s_mount_opt, ERRORS_CONT);
- clear_opt (sbi->s_mount_opt, ERRORS_RO);
- set_opt (sbi->s_mount_opt, ERRORS_PANIC);
- break;
- case Opt_err_ro:
- clear_opt (sbi->s_mount_opt, ERRORS_CONT);
- clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
- set_opt (sbi->s_mount_opt, ERRORS_RO);
- break;
- case Opt_err_cont:
- clear_opt (sbi->s_mount_opt, ERRORS_RO);
- clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
- set_opt (sbi->s_mount_opt, ERRORS_CONT);
- break;
- case Opt_nouid32:
- set_opt (sbi->s_mount_opt, NO_UID32);
- break;
- case Opt_nocheck:
- clear_opt (sbi->s_mount_opt, CHECK);
- break;
- case Opt_debug:
- set_opt (sbi->s_mount_opt, DEBUG);
- break;
- case Opt_oldalloc:
- set_opt (sbi->s_mount_opt, OLDALLOC);
- break;
- case Opt_orlov:
- clear_opt (sbi->s_mount_opt, OLDALLOC);
- break;
- case Opt_nobh:
- set_opt (sbi->s_mount_opt, NOBH);
- break;
+ ctx->mask_s_mount_opt |= flag;
+ ctx->vals_s_mount_opt |= flag;
+}
+
+static inline void ctx_clear_mount_opt(struct ext2_fs_context *ctx,
+ unsigned long flag)
+{
+ ctx->mask_s_mount_opt |= flag;
+ ctx->vals_s_mount_opt &= ~flag;
+}
+
+static inline unsigned long
+ctx_test_mount_opt(struct ext2_fs_context *ctx, unsigned long flag)
+{
+ return (ctx->vals_s_mount_opt & flag);
+}
+
+static inline bool
+ctx_parsed_mount_opt(struct ext2_fs_context *ctx, unsigned long flag)
+{
+ return (ctx->mask_s_mount_opt & flag);
+}
+
+static void ext2_free_fc(struct fs_context *fc)
+{
+ kfree(fc->fs_private);
+}
+
+static int ext2_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct ext2_fs_context *ctx = fc->fs_private;
+ int opt;
+ struct fs_parse_result result;
+
+ opt = fs_parse(fc, ext2_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_bsd_df:
+ ctx_clear_mount_opt(ctx, EXT2_MOUNT_MINIX_DF);
+ break;
+ case Opt_minix_df:
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_MINIX_DF);
+ break;
+ case Opt_grpid:
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_GRPID);
+ break;
+ case Opt_nogrpid:
+ ctx_clear_mount_opt(ctx, EXT2_MOUNT_GRPID);
+ break;
+ case Opt_resuid:
+ ctx->s_resuid = result.uid;
+ ctx->spec |= EXT2_SPEC_s_resuid;
+ break;
+ case Opt_resgid:
+ ctx->s_resgid = result.gid;
+ ctx->spec |= EXT2_SPEC_s_resgid;
+ break;
+ case Opt_sb:
+ /* Note that this is silently ignored on remount */
+ ctx->s_sb_block = result.uint_32;
+ break;
+ case Opt_errors:
+ ctx_clear_mount_opt(ctx, EXT2_MOUNT_ERRORS_MASK);
+ ctx_set_mount_opt(ctx, result.uint_32);
+ break;
+ case Opt_nouid32:
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_NO_UID32);
+ break;
+ case Opt_debug:
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_DEBUG);
+ break;
+ case Opt_oldalloc:
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_OLDALLOC);
+ break;
+ case Opt_orlov:
+ ctx_clear_mount_opt(ctx, EXT2_MOUNT_OLDALLOC);
+ break;
+ case Opt_nobh:
+ ext2_msg_fc(fc, KERN_INFO, "nobh option not supported\n");
+ break;
#ifdef CONFIG_EXT2_FS_XATTR
- case Opt_user_xattr:
- set_opt (sbi->s_mount_opt, XATTR_USER);
- break;
- case Opt_nouser_xattr:
- clear_opt (sbi->s_mount_opt, XATTR_USER);
- break;
+ case Opt_user_xattr:
+ if (!result.negated)
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_XATTR_USER);
+ else
+ ctx_clear_mount_opt(ctx, EXT2_MOUNT_XATTR_USER);
+ break;
#else
- case Opt_user_xattr:
- case Opt_nouser_xattr:
- ext2_msg(sb, KERN_INFO, "(no)user_xattr options"
- "not supported");
- break;
+ case Opt_user_xattr:
+ ext2_msg_fc(fc, KERN_INFO, "(no)user_xattr options not supported");
+ break;
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
- case Opt_acl:
- set_opt(sbi->s_mount_opt, POSIX_ACL);
- break;
- case Opt_noacl:
- clear_opt(sbi->s_mount_opt, POSIX_ACL);
- break;
+ case Opt_acl:
+ if (!result.negated)
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_POSIX_ACL);
+ else
+ ctx_clear_mount_opt(ctx, EXT2_MOUNT_POSIX_ACL);
+ break;
#else
- case Opt_acl:
- case Opt_noacl:
- ext2_msg(sb, KERN_INFO,
- "(no)acl options not supported");
- break;
+ case Opt_acl:
+ ext2_msg_fc(fc, KERN_INFO, "(no)acl options not supported");
+ break;
#endif
- case Opt_xip:
-#ifdef CONFIG_EXT2_FS_XIP
- set_opt (sbi->s_mount_opt, XIP);
+ case Opt_xip:
+ ext2_msg_fc(fc, KERN_INFO, "use dax instead of xip");
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_XIP);
+ fallthrough;
+ case Opt_dax:
+#ifdef CONFIG_FS_DAX
+ ext2_msg_fc(fc, KERN_WARNING,
+ "DAX enabled. Warning: DAX support in ext2 driver is deprecated"
+ " and will be removed at the end of 2025. Please use ext4 driver instead.");
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_DAX);
#else
- ext2_msg(sb, KERN_INFO, "xip option not supported");
+ ext2_msg_fc(fc, KERN_INFO, "dax option not supported");
#endif
- break;
+ break;
#if defined(CONFIG_QUOTA)
- case Opt_quota:
- case Opt_usrquota:
- set_opt(sbi->s_mount_opt, USRQUOTA);
- break;
-
- case Opt_grpquota:
- set_opt(sbi->s_mount_opt, GRPQUOTA);
- break;
+ case Opt_quota:
+ case Opt_usrquota:
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_USRQUOTA);
+ break;
+
+ case Opt_grpquota:
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_GRPQUOTA);
+ break;
#else
- case Opt_quota:
- case Opt_usrquota:
- case Opt_grpquota:
- ext2_msg(sb, KERN_INFO,
- "quota operations not supported");
- break;
+ case Opt_quota:
+ case Opt_usrquota:
+ case Opt_grpquota:
+ ext2_msg_fc(fc, KERN_INFO, "quota operations not supported");
+ break;
#endif
-
- case Opt_reservation:
- set_opt(sbi->s_mount_opt, RESERVATION);
- ext2_msg(sb, KERN_INFO, "reservations ON");
- break;
- case Opt_noreservation:
- clear_opt(sbi->s_mount_opt, RESERVATION);
- ext2_msg(sb, KERN_INFO, "reservations OFF");
- break;
- case Opt_ignore:
- break;
- default:
- return 0;
+ case Opt_reservation:
+ if (!result.negated) {
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_RESERVATION);
+ ext2_msg_fc(fc, KERN_INFO, "reservations ON");
+ } else {
+ ctx_clear_mount_opt(ctx, EXT2_MOUNT_RESERVATION);
+ ext2_msg_fc(fc, KERN_INFO, "reservations OFF");
}
+ break;
+ case Opt_ignore:
+ break;
+ default:
+ return -EINVAL;
}
- return 1;
+ return 0;
}
static int ext2_setup_super (struct super_block * sb,
@@ -603,7 +653,7 @@ static int ext2_setup_super (struct super_block * sb,
ext2_msg(sb, KERN_ERR,
"error: revision level too high, "
"forcing read-only mode");
- res = MS_RDONLY;
+ res = SB_RDONLY;
}
if (read_only)
return res;
@@ -623,7 +673,8 @@ static int ext2_setup_super (struct super_block * sb,
"running e2fsck is recommended");
else if (le32_to_cpu(es->s_checkinterval) &&
(le32_to_cpu(es->s_lastcheck) +
- le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+ le32_to_cpu(es->s_checkinterval) <=
+ ktime_get_real_seconds()))
ext2_msg(sb, KERN_WARNING,
"warning: checktime reached, "
"running e2fsck is recommended");
@@ -631,10 +682,9 @@ static int ext2_setup_super (struct super_block * sb,
es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
if (test_opt (sb, DEBUG))
- ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, "
+ ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, "
"bpg=%lu, ipg=%lu, mo=%04lx]",
EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize,
- sbi->s_frag_size,
sbi->s_groups_count,
EXT2_BLOCKS_PER_GROUP(sb),
EXT2_INODES_PER_GROUP(sb),
@@ -652,13 +702,7 @@ static int ext2_check_descriptors(struct super_block *sb)
for (i = 0; i < sbi->s_groups_count; i++) {
struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL);
ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i);
- ext2_fsblk_t last_block;
-
- if (i == sbi->s_groups_count - 1)
- last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
- else
- last_block = first_block +
- (EXT2_BLOCKS_PER_GROUP(sb) - 1);
+ ext2_fsblk_t last_block = ext2_group_last_block_no(sb, i);
if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
le32_to_cpu(gdp->bg_block_bitmap) > last_block)
@@ -701,7 +745,8 @@ static loff_t ext2_max_size(int bits)
{
loff_t res = EXT2_NDIR_BLOCKS;
int meta_blocks;
- loff_t upper_limit;
+ unsigned int upper_limit;
+ unsigned int ppb = 1 << (bits-2);
/* This is calculated to be the largest file size for a
* dense, file such that the total number of
@@ -715,24 +760,38 @@ static loff_t ext2_max_size(int bits)
/* total blocks in file system block size */
upper_limit >>= (bits - 9);
-
- /* indirect blocks */
- meta_blocks = 1;
- /* double indirect blocks */
- meta_blocks += 1 + (1LL << (bits-2));
- /* tripple indirect blocks */
- meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
-
- upper_limit -= meta_blocks;
- upper_limit <<= bits;
-
+ /* Compute how many blocks we can address by block tree */
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
res += 1LL << (3*(bits-2));
+ /* Compute how many metadata blocks are needed */
+ meta_blocks = 1;
+ meta_blocks += 1 + ppb;
+ meta_blocks += 1 + ppb + ppb * ppb;
+ /* Does block tree limit file size? */
+ if (res + meta_blocks <= upper_limit)
+ goto check_lfs;
+
+ res = upper_limit;
+ /* How many metadata blocks are needed for addressing upper_limit? */
+ upper_limit -= EXT2_NDIR_BLOCKS;
+ /* indirect blocks */
+ meta_blocks = 1;
+ upper_limit -= ppb;
+ /* double indirect blocks */
+ if (upper_limit < ppb * ppb) {
+ meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb);
+ res -= meta_blocks;
+ goto check_lfs;
+ }
+ meta_blocks += 1 + ppb;
+ upper_limit -= ppb * ppb;
+ /* tripple indirect blocks for the rest */
+ meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb) +
+ DIV_ROUND_UP(upper_limit, ppb*ppb);
+ res -= meta_blocks;
+check_lfs:
res <<= bits;
- if (res > upper_limit)
- res = upper_limit;
-
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
@@ -745,7 +804,6 @@ static unsigned long descriptor_loc(struct super_block *sb,
{
struct ext2_sb_info *sbi = EXT2_SB(sb);
unsigned long bg, first_meta_bg;
- int has_super = 0;
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
@@ -753,45 +811,105 @@ static unsigned long descriptor_loc(struct super_block *sb,
nr < first_meta_bg)
return (logic_sb_block + nr + 1);
bg = sbi->s_desc_per_block * nr;
- if (ext2_bg_has_super(sb, bg))
- has_super = 1;
- return ext2_group_first_block_no(sb, bg) + has_super;
+ return ext2_group_first_block_no(sb, bg) + ext2_bg_has_super(sb, bg);
+}
+
+/*
+ * Set all mount options either from defaults on disk, or from parsed
+ * options. Parsed/specified options override on-disk defaults.
+ */
+static void ext2_set_options(struct fs_context *fc, struct ext2_sb_info *sbi)
+{
+ struct ext2_fs_context *ctx = fc->fs_private;
+ struct ext2_super_block *es = sbi->s_es;
+ unsigned long def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+
+ /* Copy parsed mount options to sbi */
+ sbi->s_mount_opt = ctx->vals_s_mount_opt;
+
+ /* Use in-superblock defaults only if not specified during parsing */
+ if (!ctx_parsed_mount_opt(ctx, EXT2_MOUNT_DEBUG) &&
+ def_mount_opts & EXT2_DEFM_DEBUG)
+ set_opt(sbi->s_mount_opt, DEBUG);
+
+ if (!ctx_parsed_mount_opt(ctx, EXT2_MOUNT_GRPID) &&
+ def_mount_opts & EXT2_DEFM_BSDGROUPS)
+ set_opt(sbi->s_mount_opt, GRPID);
+
+ if (!ctx_parsed_mount_opt(ctx, EXT2_MOUNT_NO_UID32) &&
+ def_mount_opts & EXT2_DEFM_UID16)
+ set_opt(sbi->s_mount_opt, NO_UID32);
+
+#ifdef CONFIG_EXT2_FS_XATTR
+ if (!ctx_parsed_mount_opt(ctx, EXT2_MOUNT_XATTR_USER) &&
+ def_mount_opts & EXT2_DEFM_XATTR_USER)
+ set_opt(sbi->s_mount_opt, XATTR_USER);
+#endif
+#ifdef CONFIG_EXT2_FS_POSIX_ACL
+ if (!ctx_parsed_mount_opt(ctx, EXT2_MOUNT_POSIX_ACL) &&
+ def_mount_opts & EXT2_DEFM_ACL)
+ set_opt(sbi->s_mount_opt, POSIX_ACL);
+#endif
+
+ if (!ctx_parsed_mount_opt(ctx, EXT2_MOUNT_ERRORS_MASK)) {
+ if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC)
+ set_opt(sbi->s_mount_opt, ERRORS_PANIC);
+ else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE)
+ set_opt(sbi->s_mount_opt, ERRORS_CONT);
+ else
+ set_opt(sbi->s_mount_opt, ERRORS_RO);
+ }
+
+ if (ctx->spec & EXT2_SPEC_s_resuid)
+ sbi->s_resuid = ctx->s_resuid;
+ else
+ sbi->s_resuid = make_kuid(&init_user_ns,
+ le16_to_cpu(es->s_def_resuid));
+
+ if (ctx->spec & EXT2_SPEC_s_resgid)
+ sbi->s_resgid = ctx->s_resgid;
+ else
+ sbi->s_resgid = make_kgid(&init_user_ns,
+ le16_to_cpu(es->s_def_resgid));
}
-static int ext2_fill_super(struct super_block *sb, void *data, int silent)
+static int ext2_fill_super(struct super_block *sb, struct fs_context *fc)
{
+ struct ext2_fs_context *ctx = fc->fs_private;
+ int silent = fc->sb_flags & SB_SILENT;
struct buffer_head * bh;
struct ext2_sb_info * sbi;
struct ext2_super_block * es;
struct inode *root;
unsigned long block;
- unsigned long sb_block = get_sb_block(&data);
+ unsigned long sb_block = ctx->s_sb_block;
unsigned long logic_sb_block;
unsigned long offset = 0;
- unsigned long def_mount_opts;
- long ret = -EINVAL;
+ long ret = -ENOMEM;
int blocksize = BLOCK_SIZE;
int db_count;
int i, j;
__le32 features;
int err;
- err = -ENOMEM;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
- goto failed;
+ return -ENOMEM;
sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
if (!sbi->s_blockgroup_lock) {
kfree(sbi);
- goto failed;
+ return -ENOMEM;
}
sb->s_fs_info = sbi;
sbi->s_sb_block = sb_block;
+ sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off,
+ NULL, NULL);
spin_lock_init(&sbi->s_lock);
+ ret = -EINVAL;
/*
* See what the current blocksize for the device is, and
@@ -832,44 +950,11 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (sb->s_magic != EXT2_SUPER_MAGIC)
goto cantfind_ext2;
- /* Set defaults before we parse the mount options */
- def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
- if (def_mount_opts & EXT2_DEFM_DEBUG)
- set_opt(sbi->s_mount_opt, DEBUG);
- if (def_mount_opts & EXT2_DEFM_BSDGROUPS)
- set_opt(sbi->s_mount_opt, GRPID);
- if (def_mount_opts & EXT2_DEFM_UID16)
- set_opt(sbi->s_mount_opt, NO_UID32);
-#ifdef CONFIG_EXT2_FS_XATTR
- if (def_mount_opts & EXT2_DEFM_XATTR_USER)
- set_opt(sbi->s_mount_opt, XATTR_USER);
-#endif
-#ifdef CONFIG_EXT2_FS_POSIX_ACL
- if (def_mount_opts & EXT2_DEFM_ACL)
- set_opt(sbi->s_mount_opt, POSIX_ACL);
-#endif
-
- if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC)
- set_opt(sbi->s_mount_opt, ERRORS_PANIC);
- else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE)
- set_opt(sbi->s_mount_opt, ERRORS_CONT);
- else
- set_opt(sbi->s_mount_opt, ERRORS_RO);
+ ext2_set_options(fc, sbi);
- sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
- sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
-
- set_opt(sbi->s_mount_opt, RESERVATION);
-
- if (!parse_options((char *) data, sb))
- goto failed_mount;
-
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- ((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
- MS_POSIXACL : 0);
-
- ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
- EXT2_MOUNT_XIP if not */
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
+ sb->s_iflags |= SB_I_CGROUPWB;
if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
(EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
@@ -890,21 +975,31 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
le32_to_cpu(features));
goto failed_mount;
}
- if (!(sb->s_flags & MS_RDONLY) &&
- (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){
+ if (!sb_rdonly(sb) && (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){
ext2_msg(sb, KERN_ERR, "error: couldn't mount RDWR because of "
"unsupported optional features (%x)",
le32_to_cpu(features));
goto failed_mount;
}
+ if (le32_to_cpu(es->s_log_block_size) >
+ (EXT2_MAX_BLOCK_LOG_SIZE - BLOCK_SIZE_BITS)) {
+ ext2_msg(sb, KERN_ERR,
+ "Invalid log block size: %u",
+ le32_to_cpu(es->s_log_block_size));
+ goto failed_mount;
+ }
blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
- if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) {
- if (!silent)
+ if (test_opt(sb, DAX)) {
+ if (!sbi->s_daxdev) {
ext2_msg(sb, KERN_ERR,
- "error: unsupported blocksize for xip");
- goto failed_mount;
+ "DAX unsupported by block device. Turning off DAX.");
+ clear_opt(sbi->s_mount_opt, DAX);
+ } else if (blocksize != PAGE_SIZE) {
+ ext2_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+ clear_opt(sbi->s_mount_opt, DAX);
+ }
}
/* If the blocksize doesn't match, re-read the thing.. */
@@ -935,6 +1030,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits);
sb->s_max_links = EXT2_LINK_MAX;
+ sb->s_time_min = S32_MIN;
+ sb->s_time_max = S32_MAX;
if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) {
sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE;
@@ -952,18 +1049,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
}
}
- sbi->s_frag_size = EXT2_MIN_FRAG_SIZE <<
- le32_to_cpu(es->s_log_frag_size);
- if (sbi->s_frag_size == 0)
- goto cantfind_ext2;
- sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size;
-
sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
- sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
- if (EXT2_INODE_SIZE(sb) == 0)
- goto cantfind_ext2;
sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb);
if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0)
goto cantfind_ext2;
@@ -987,11 +1075,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
- if (sb->s_blocksize != sbi->s_frag_size) {
+ if (es->s_log_frag_size != es->s_log_block_size) {
ext2_msg(sb, KERN_ERR,
- "error: fragsize %lu != blocksize %lu"
- "(not supported yet)",
- sbi->s_frag_size, sb->s_blocksize);
+ "error: fragsize log %u != blocksize log %u",
+ le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits);
goto failed_mount;
}
@@ -1001,34 +1088,52 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_blocks_per_group);
goto failed_mount;
}
- if (sbi->s_frags_per_group > sb->s_blocksize * 8) {
+ /* At least inode table, bitmaps, and sb have to fit in one group */
+ if (sbi->s_blocks_per_group <= sbi->s_itb_per_group + 3) {
ext2_msg(sb, KERN_ERR,
- "error: #fragments per group too big: %lu",
- sbi->s_frags_per_group);
+ "error: #blocks per group smaller than metadata size: %lu <= %lu",
+ sbi->s_blocks_per_group, sbi->s_inodes_per_group + 3);
goto failed_mount;
}
- if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
+ if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+ sbi->s_inodes_per_group > sb->s_blocksize * 8) {
ext2_msg(sb, KERN_ERR,
- "error: #inodes per group too big: %lu",
+ "error: invalid #inodes per group: %lu",
sbi->s_inodes_per_group);
goto failed_mount;
}
+ if (sb_bdev_nr_blocks(sb) < le32_to_cpu(es->s_blocks_count)) {
+ ext2_msg(sb, KERN_ERR,
+ "bad geometry: block count %u exceeds size of device (%u blocks)",
+ le32_to_cpu(es->s_blocks_count),
+ (unsigned)sb_bdev_nr_blocks(sb));
+ goto failed_mount;
+ }
- if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
- goto cantfind_ext2;
- sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
- le32_to_cpu(es->s_first_data_block) - 1)
- / EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+ sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
+ le32_to_cpu(es->s_first_data_block) - 1)
+ / EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+ if ((u64)sbi->s_groups_count * sbi->s_inodes_per_group !=
+ le32_to_cpu(es->s_inodes_count)) {
+ ext2_msg(sb, KERN_ERR, "error: invalid #inodes: %u vs computed %llu",
+ le32_to_cpu(es->s_inodes_count),
+ (u64)sbi->s_groups_count * sbi->s_inodes_per_group);
+ goto failed_mount;
+ }
db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
EXT2_DESC_PER_BLOCK(sb);
- sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL);
+ sbi->s_group_desc = kvmalloc_array(db_count,
+ sizeof(struct buffer_head *),
+ GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
+ ret = -ENOMEM;
ext2_msg(sb, KERN_ERR, "error: not enough memory");
goto failed_mount;
}
bgl_lock_init(sbi->s_blockgroup_lock);
sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL);
if (!sbi->s_debts) {
+ ret = -ENOMEM;
ext2_msg(sb, KERN_ERR, "error: not enough memory");
goto failed_mount_group_desc;
}
@@ -1051,7 +1156,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
- /* per fileystem reservation list head & lock */
+ /* per filesystem reservation list head & lock */
spin_lock_init(&sbi->s_rsv_window_lock);
sbi->s_rsv_window_root = RB_ROOT;
/*
@@ -1067,19 +1172,29 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);
err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext2_count_free_blocks(sb));
+ ext2_count_free_blocks(sb), GFP_KERNEL);
if (!err) {
err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext2_count_free_inodes(sb));
+ ext2_count_free_inodes(sb), GFP_KERNEL);
}
if (!err) {
err = percpu_counter_init(&sbi->s_dirs_counter,
- ext2_count_dirs(sb));
+ ext2_count_dirs(sb), GFP_KERNEL);
}
if (err) {
+ ret = err;
ext2_msg(sb, KERN_ERR, "error: insufficient memory");
goto failed_mount3;
}
+
+#ifdef CONFIG_EXT2_FS_XATTR
+ sbi->s_ea_block_cache = ext2_xattr_create_cache();
+ if (!sbi->s_ea_block_cache) {
+ ret = -ENOMEM;
+ ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache");
+ goto failed_mount3;
+ }
+#endif
/*
* set up enough so that it can read an inode
*/
@@ -1089,7 +1204,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
#ifdef CONFIG_QUOTA
sb->dq_op = &dquot_operations;
- sb->s_qcop = &dquot_quotactl_ops;
+ sb->s_qcop = &ext2_quotactl_ops;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
#endif
root = ext2_iget(sb, EXT2_ROOT_INO);
@@ -1112,8 +1228,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
ext2_msg(sb, KERN_WARNING,
"warning: mounting ext3 filesystem as ext2");
- if (ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY))
- sb->s_flags |= MS_RDONLY;
+ if (ext2_setup_super (sb, es, sb_rdonly(sb)))
+ sb->s_flags |= SB_RDONLY;
ext2_write_super(sb);
return 0;
@@ -1124,6 +1240,7 @@ cantfind_ext2:
sb->s_id);
goto failed_mount;
failed_mount3:
+ ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -1131,15 +1248,15 @@ failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
failed_mount_group_desc:
- kfree(sbi->s_group_desc);
+ kvfree(sbi->s_group_desc);
kfree(sbi->s_debts);
failed_mount:
brelse(bh);
failed_sbi:
+ fs_put_dax(sbi->s_daxdev, NULL);
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
-failed:
return ret;
}
@@ -1157,20 +1274,20 @@ static void ext2_clear_super_error(struct super_block *sb)
* write and hope for the best.
*/
ext2_msg(sb, KERN_ERR,
- "previous I/O error to superblock detected\n");
+ "previous I/O error to superblock detected");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
}
-static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
- int wait)
+void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
+ int wait)
{
ext2_clear_super_error(sb);
spin_lock(&EXT2_SB(sb)->s_lock);
es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
- es->s_wtime = cpu_to_le32(get_seconds());
+ es->s_wtime = cpu_to_le32(ktime_get_real_seconds());
/* unlock before we do IO */
spin_unlock(&EXT2_SB(sb)->s_lock);
mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
@@ -1239,93 +1356,65 @@ static int ext2_unfreeze(struct super_block *sb)
return 0;
}
-void ext2_write_super(struct super_block *sb)
+static void ext2_write_super(struct super_block *sb)
{
- if (!(sb->s_flags & MS_RDONLY))
+ if (!sb_rdonly(sb))
ext2_sync_fs(sb, 1);
}
-static int ext2_remount (struct super_block * sb, int * flags, char * data)
+static int ext2_reconfigure(struct fs_context *fc)
{
+ struct ext2_fs_context *ctx = fc->fs_private;
+ struct super_block *sb = fc->root->d_sb;
struct ext2_sb_info * sbi = EXT2_SB(sb);
struct ext2_super_block * es;
- unsigned long old_mount_opt = sbi->s_mount_opt;
- struct ext2_mount_options old_opts;
- unsigned long old_sb_flags;
+ struct ext2_mount_options new_opts;
+ int flags = fc->sb_flags;
int err;
- spin_lock(&sbi->s_lock);
+ sync_filesystem(sb);
- /* Store the old options */
- old_sb_flags = sb->s_flags;
- old_opts.s_mount_opt = sbi->s_mount_opt;
- old_opts.s_resuid = sbi->s_resuid;
- old_opts.s_resgid = sbi->s_resgid;
-
- /*
- * Allow the "check" option to be passed as a remount option.
- */
- if (!parse_options(data, sb)) {
- err = -EINVAL;
- goto restore_opts;
- }
-
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- ((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
-
- ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
- EXT2_MOUNT_XIP if not */
-
- if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
- ext2_msg(sb, KERN_WARNING,
- "warning: unsupported blocksize for xip");
- err = -EINVAL;
- goto restore_opts;
- }
+ new_opts.s_mount_opt = ctx->vals_s_mount_opt;
+ new_opts.s_resuid = ctx->s_resuid;
+ new_opts.s_resgid = ctx->s_resgid;
+ spin_lock(&sbi->s_lock);
es = sbi->s_es;
- if ((sbi->s_mount_opt ^ old_mount_opt) & EXT2_MOUNT_XIP) {
+ if ((sbi->s_mount_opt ^ new_opts.s_mount_opt) & EXT2_MOUNT_DAX) {
ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
- "xip flag with busy inodes while remounting");
- sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
- sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
+ "dax flag with busy inodes while remounting");
+ new_opts.s_mount_opt ^= EXT2_MOUNT_DAX;
}
- if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
- spin_unlock(&sbi->s_lock);
- return 0;
- }
- if (*flags & MS_RDONLY) {
+ if ((bool)(flags & SB_RDONLY) == sb_rdonly(sb))
+ goto out_set;
+ if (flags & SB_RDONLY) {
if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
- !(sbi->s_mount_state & EXT2_VALID_FS)) {
- spin_unlock(&sbi->s_lock);
- return 0;
- }
+ !(sbi->s_mount_state & EXT2_VALID_FS))
+ goto out_set;
/*
* OK, we are remounting a valid rw partition rdonly, so set
* the rdonly flag and then mark the partition as valid again.
*/
es->s_state = cpu_to_le16(sbi->s_mount_state);
- es->s_mtime = cpu_to_le32(get_seconds());
+ es->s_mtime = cpu_to_le32(ktime_get_real_seconds());
spin_unlock(&sbi->s_lock);
err = dquot_suspend(sb, -1);
- if (err < 0) {
- spin_lock(&sbi->s_lock);
- goto restore_opts;
- }
+ if (err < 0)
+ return err;
ext2_sync_super(sb, es, 1);
} else {
__le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb,
~EXT2_FEATURE_RO_COMPAT_SUPP);
if (ret) {
+ spin_unlock(&sbi->s_lock);
ext2_msg(sb, KERN_WARNING,
"warning: couldn't remount RDWR because of "
"unsupported optional features (%x).",
le32_to_cpu(ret));
- err = -EROFS;
- goto restore_opts;
+ return -EROFS;
}
/*
* Mounting a RDONLY partition read-write, so reread and
@@ -1334,7 +1423,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
*/
sbi->s_mount_state = le16_to_cpu(es->s_state);
if (!ext2_setup_super (sb, es, 0))
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
spin_unlock(&sbi->s_lock);
ext2_write_super(sb);
@@ -1342,14 +1431,16 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
dquot_resume(sb, -1);
}
- return 0;
-restore_opts:
- sbi->s_mount_opt = old_opts.s_mount_opt;
- sbi->s_resuid = old_opts.s_resuid;
- sbi->s_resgid = old_opts.s_resgid;
- sb->s_flags = old_sb_flags;
+ spin_lock(&sbi->s_lock);
+out_set:
+ sbi->s_mount_opt = new_opts.s_mount_opt;
+ sbi->s_resuid = new_opts.s_resuid;
+ sbi->s_resgid = new_opts.s_resgid;
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
spin_unlock(&sbi->s_lock);
- return err;
+
+ return 0;
}
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
@@ -1357,7 +1448,6 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
struct super_block *sb = dentry->d_sb;
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;
- u64 fsid;
spin_lock(&sbi->s_lock);
@@ -1411,18 +1501,14 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
buf->f_ffree = ext2_count_free_inodes(sb);
es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT2_NAME_LEN;
- fsid = le64_to_cpup((void *)es->s_uuid) ^
- le64_to_cpup((void *)es->s_uuid + sizeof(u64));
- buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
- buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+ buf->f_fsid = uuid_to_fsid(es->s_uuid);
spin_unlock(&sbi->s_lock);
return 0;
}
-static struct dentry *ext2_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int ext2_get_tree(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, ext2_fill_super);
+ return get_tree_bdev(fc, ext2_fill_super);
}
#ifdef CONFIG_QUOTA
@@ -1450,8 +1536,7 @@ static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
len = i_size-off;
toread = len;
while (toread > 0) {
- tocopy = sb->s_blocksize - offset < toread ?
- sb->s_blocksize - offset : toread;
+ tocopy = min_t(size_t, sb->s_blocksize - offset, toread);
tmp_bh.b_state = 0;
tmp_bh.b_size = sb->s_blocksize;
@@ -1489,10 +1574,10 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type,
struct buffer_head *bh;
while (towrite > 0) {
- tocopy = sb->s_blocksize - offset < towrite ?
- sb->s_blocksize - offset : towrite;
+ tocopy = min_t(size_t, sb->s_blocksize - offset, towrite);
tmp_bh.b_state = 0;
+ tmp_bh.b_size = sb->s_blocksize;
err = ext2_get_block(inode, blk, &tmp_bh, 1);
if (err < 0)
goto out;
@@ -1506,7 +1591,7 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type,
}
lock_buffer(bh);
memcpy(bh->b_data+offset, data, tocopy);
- flush_dcache_page(bh->b_page);
+ flush_dcache_folio(bh->b_folio);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
unlock_buffer(bh);
@@ -1521,39 +1606,118 @@ out:
return err;
if (inode->i_size < off+len-towrite)
i_size_write(inode, off+len-towrite);
- inode->i_version++;
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ inode_inc_iversion(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
mark_inode_dirty(inode);
return len - towrite;
}
+static int ext2_quota_on(struct super_block *sb, int type, int format_id,
+ const struct path *path)
+{
+ int err;
+ struct inode *inode;
+
+ err = dquot_quota_on(sb, type, format_id, path);
+ if (err)
+ return err;
+
+ inode = d_inode(path->dentry);
+ inode_lock(inode);
+ EXT2_I(inode)->i_flags |= EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL;
+ inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
+ S_NOATIME | S_IMMUTABLE);
+ inode_unlock(inode);
+ mark_inode_dirty(inode);
+
+ return 0;
+}
+
+static int ext2_quota_off(struct super_block *sb, int type)
+{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ int err;
+
+ if (!inode || !igrab(inode))
+ goto out;
+
+ err = dquot_quota_off(sb, type);
+ if (err)
+ goto out_put;
+
+ inode_lock(inode);
+ EXT2_I(inode)->i_flags &= ~(EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL);
+ inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
+ inode_unlock(inode);
+ mark_inode_dirty(inode);
+out_put:
+ iput(inode);
+ return err;
+out:
+ return dquot_quota_off(sb, type);
+}
+
#endif
+static const struct fs_context_operations ext2_context_ops = {
+ .parse_param = ext2_parse_param,
+ .get_tree = ext2_get_tree,
+ .reconfigure = ext2_reconfigure,
+ .free = ext2_free_fc,
+};
+
+static int ext2_init_fs_context(struct fs_context *fc)
+{
+ struct ext2_fs_context *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ struct super_block *sb = fc->root->d_sb;
+ struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+ spin_lock(&sbi->s_lock);
+ ctx->vals_s_mount_opt = sbi->s_mount_opt;
+ ctx->vals_s_flags = sb->s_flags;
+ ctx->s_resuid = sbi->s_resuid;
+ ctx->s_resgid = sbi->s_resgid;
+ spin_unlock(&sbi->s_lock);
+ } else {
+ ctx->s_sb_block = 1;
+ ctx_set_mount_opt(ctx, EXT2_MOUNT_RESERVATION);
+ }
+
+ fc->fs_private = ctx;
+ fc->ops = &ext2_context_ops;
+
+ return 0;
+}
+
static struct file_system_type ext2_fs_type = {
.owner = THIS_MODULE,
.name = "ext2",
- .mount = ext2_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = ext2_init_fs_context,
+ .parameters = ext2_param_spec,
};
MODULE_ALIAS_FS("ext2");
static int __init init_ext2_fs(void)
{
- int err = init_ext2_xattr();
- if (err)
- return err;
+ int err;
+
err = init_inodecache();
if (err)
- goto out1;
- err = register_filesystem(&ext2_fs_type);
+ return err;
+ err = register_filesystem(&ext2_fs_type);
if (err)
goto out;
return 0;
out:
destroy_inodecache();
-out1:
- exit_ext2_xattr();
return err;
}
@@ -1561,7 +1725,6 @@ static void __exit exit_ext2_fs(void)
{
unregister_filesystem(&ext2_fs_type);
destroy_inodecache();
- exit_ext2_xattr();
}
MODULE_AUTHOR("Remy Card and others");
diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index 565cf817bbf1..948d3a441403 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/symlink.c
*
@@ -19,36 +20,17 @@
#include "ext2.h"
#include "xattr.h"
-#include <linux/namei.h>
-
-static void *ext2_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct ext2_inode_info *ei = EXT2_I(dentry->d_inode);
- nd_set_link(nd, (char *)ei->i_data);
- return NULL;
-}
const struct inode_operations ext2_symlink_inode_operations = {
- .readlink = generic_readlink,
- .follow_link = page_follow_link_light,
- .put_link = page_put_link,
+ .get_link = page_get_link,
+ .getattr = ext2_getattr,
.setattr = ext2_setattr,
-#ifdef CONFIG_EXT2_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
- .removexattr = generic_removexattr,
-#endif
};
const struct inode_operations ext2_fast_symlink_inode_operations = {
- .readlink = generic_readlink,
- .follow_link = ext2_follow_link,
+ .get_link = simple_get_link,
+ .getattr = ext2_getattr,
.setattr = ext2_setattr,
-#ifdef CONFIG_EXT2_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
- .removexattr = generic_removexattr,
-#endif
};
diff --git a/fs/ext2/trace.c b/fs/ext2/trace.c
new file mode 100644
index 000000000000..b01cdf6526fd
--- /dev/null
+++ b/fs/ext2/trace.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "ext2.h"
+#include <linux/uio.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/ext2/trace.h b/fs/ext2/trace.h
new file mode 100644
index 000000000000..7d230e13576e
--- /dev/null
+++ b/fs/ext2/trace.h
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ext2
+
+#if !defined(_EXT2_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _EXT2_TRACE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(ext2_dio_class,
+ TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, ssize_t ret),
+ TP_ARGS(iocb, iter, ret),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, isize)
+ __field(loff_t, pos)
+ __field(size_t, count)
+ __field(int, ki_flags)
+ __field(bool, aio)
+ __field(ssize_t, ret)
+ ),
+ TP_fast_assign(
+ __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
+ __entry->ino = file_inode(iocb->ki_filp)->i_ino;
+ __entry->isize = file_inode(iocb->ki_filp)->i_size;
+ __entry->pos = iocb->ki_pos;
+ __entry->count = iov_iter_count(iter);
+ __entry->ki_flags = iocb->ki_flags;
+ __entry->aio = !is_sync_kiocb(iocb);
+ __entry->ret = ret;
+ ),
+ TP_printk("dev %d:%d ino 0x%lx isize 0x%llx pos 0x%llx len %zu flags %s aio %d ret %zd",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->isize,
+ __entry->pos,
+ __entry->count,
+ __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS),
+ __entry->aio,
+ __entry->ret)
+);
+
+#define DEFINE_DIO_RW_EVENT(name) \
+DEFINE_EVENT(ext2_dio_class, name, \
+ TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, ssize_t ret), \
+ TP_ARGS(iocb, iter, ret))
+DEFINE_DIO_RW_EVENT(ext2_dio_write_begin);
+DEFINE_DIO_RW_EVENT(ext2_dio_write_end);
+DEFINE_DIO_RW_EVENT(ext2_dio_write_buff_end);
+DEFINE_DIO_RW_EVENT(ext2_dio_read_begin);
+DEFINE_DIO_RW_EVENT(ext2_dio_read_end);
+
+TRACE_EVENT(ext2_dio_write_endio,
+ TP_PROTO(struct kiocb *iocb, ssize_t size, int ret),
+ TP_ARGS(iocb, size, ret),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, isize)
+ __field(loff_t, pos)
+ __field(ssize_t, size)
+ __field(int, ki_flags)
+ __field(bool, aio)
+ __field(int, ret)
+ ),
+ TP_fast_assign(
+ __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
+ __entry->ino = file_inode(iocb->ki_filp)->i_ino;
+ __entry->isize = file_inode(iocb->ki_filp)->i_size;
+ __entry->pos = iocb->ki_pos;
+ __entry->size = size;
+ __entry->ki_flags = iocb->ki_flags;
+ __entry->aio = !is_sync_kiocb(iocb);
+ __entry->ret = ret;
+ ),
+ TP_printk("dev %d:%d ino 0x%lx isize 0x%llx pos 0x%llx len %zd flags %s aio %d ret %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->isize,
+ __entry->pos,
+ __entry->size,
+ __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS),
+ __entry->aio,
+ __entry->ret)
+);
+
+#endif /* _EXT2_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 2d7557db3ae8..c885dcc3bd0d 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/xattr.c
*
@@ -55,6 +56,7 @@
#include <linux/buffer_head.h>
#include <linux/init.h>
+#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/mbcache.h>
#include <linux/quotaops.h>
@@ -77,34 +79,30 @@
printk("\n"); \
} while (0)
# define ea_bdebug(bh, f...) do { \
- char b[BDEVNAME_SIZE]; \
- printk(KERN_DEBUG "block %s:%lu: ", \
- bdevname(bh->b_bdev, b), \
- (unsigned long) bh->b_blocknr); \
+ printk(KERN_DEBUG "block %pg:%lu: ", \
+ bh->b_bdev, (unsigned long) bh->b_blocknr); \
printk(f); \
printk("\n"); \
} while (0)
#else
-# define ea_idebug(f...)
-# define ea_bdebug(f...)
+# define ea_idebug(inode, f...) no_printk(f)
+# define ea_bdebug(bh, f...) no_printk(f)
#endif
static int ext2_xattr_set2(struct inode *, struct buffer_head *,
struct ext2_xattr_header *);
-static int ext2_xattr_cache_insert(struct buffer_head *);
+static int ext2_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
static struct buffer_head *ext2_xattr_cache_find(struct inode *,
struct ext2_xattr_header *);
static void ext2_xattr_rehash(struct ext2_xattr_header *,
struct ext2_xattr_entry *);
-static struct mb_cache *ext2_xattr_cache;
-
-static const struct xattr_handler *ext2_xattr_handler_map[] = {
+static const struct xattr_handler * const ext2_xattr_handler_map[] = {
[EXT2_XATTR_INDEX_USER] = &ext2_xattr_user_handler,
#ifdef CONFIG_EXT2_FS_POSIX_ACL
- [EXT2_XATTR_INDEX_POSIX_ACL_ACCESS] = &ext2_xattr_acl_access_handler,
- [EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext2_xattr_acl_default_handler,
+ [EXT2_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access,
+ [EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default,
#endif
[EXT2_XATTR_INDEX_TRUSTED] = &ext2_xattr_trusted_handler,
#ifdef CONFIG_EXT2_FS_SECURITY
@@ -112,27 +110,76 @@ static const struct xattr_handler *ext2_xattr_handler_map[] = {
#endif
};
-const struct xattr_handler *ext2_xattr_handlers[] = {
+const struct xattr_handler * const ext2_xattr_handlers[] = {
&ext2_xattr_user_handler,
&ext2_xattr_trusted_handler,
-#ifdef CONFIG_EXT2_FS_POSIX_ACL
- &ext2_xattr_acl_access_handler,
- &ext2_xattr_acl_default_handler,
-#endif
#ifdef CONFIG_EXT2_FS_SECURITY
&ext2_xattr_security_handler,
#endif
NULL
};
-static inline const struct xattr_handler *
-ext2_xattr_handler(int name_index)
+#define EA_BLOCK_CACHE(inode) (EXT2_SB(inode->i_sb)->s_ea_block_cache)
+
+static inline const char *ext2_xattr_prefix(int name_index,
+ struct dentry *dentry)
{
const struct xattr_handler *handler = NULL;
if (name_index > 0 && name_index < ARRAY_SIZE(ext2_xattr_handler_map))
handler = ext2_xattr_handler_map[name_index];
- return handler;
+
+ if (!xattr_handler_can_list(handler, dentry))
+ return NULL;
+
+ return xattr_prefix(handler);
+}
+
+static bool
+ext2_xattr_header_valid(struct ext2_xattr_header *header)
+{
+ if (header->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) ||
+ header->h_blocks != cpu_to_le32(1))
+ return false;
+
+ return true;
+}
+
+static bool
+ext2_xattr_entry_valid(struct ext2_xattr_entry *entry,
+ char *end, size_t end_offs)
+{
+ struct ext2_xattr_entry *next;
+ size_t size;
+
+ next = EXT2_XATTR_NEXT(entry);
+ if ((char *)next >= end)
+ return false;
+
+ if (entry->e_value_block != 0)
+ return false;
+
+ size = le32_to_cpu(entry->e_value_size);
+ if (size > end_offs ||
+ le16_to_cpu(entry->e_value_offs) + size > end_offs)
+ return false;
+
+ return true;
+}
+
+static int
+ext2_xattr_cmp_entry(int name_index, size_t name_len, const char *name,
+ struct ext2_xattr_entry *entry)
+{
+ int cmp;
+
+ cmp = name_index - entry->e_name_index;
+ if (!cmp)
+ cmp = name_len - entry->e_name_len;
+ if (!cmp)
+ cmp = memcmp(name, entry->e_name, name_len);
+
+ return cmp;
}
/*
@@ -153,7 +200,8 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
struct ext2_xattr_entry *entry;
size_t name_len, size;
char *end;
- int error;
+ int error, not_found;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
@@ -176,9 +224,9 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(HDR(bh)->h_refcount));
end = bh->b_data + bh->b_size;
- if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) ||
- HDR(bh)->h_blocks != cpu_to_le32(1)) {
-bad_block: ext2_error(inode->i_sb, "ext2_xattr_get",
+ if (!ext2_xattr_header_valid(HDR(bh))) {
+bad_block:
+ ext2_error(inode->i_sb, "ext2_xattr_get",
"inode %ld: bad block %d", inode->i_ino,
EXT2_I(inode)->i_file_acl);
error = -EIO;
@@ -188,30 +236,26 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_get",
/* find named attribute */
entry = FIRST_ENTRY(bh);
while (!IS_LAST_ENTRY(entry)) {
- struct ext2_xattr_entry *next =
- EXT2_XATTR_NEXT(entry);
- if ((char *)next >= end)
+ if (!ext2_xattr_entry_valid(entry, end,
+ inode->i_sb->s_blocksize))
goto bad_block;
- if (name_index == entry->e_name_index &&
- name_len == entry->e_name_len &&
- memcmp(name, entry->e_name, name_len) == 0)
+
+ not_found = ext2_xattr_cmp_entry(name_index, name_len, name,
+ entry);
+ if (!not_found)
goto found;
- entry = next;
+ if (not_found < 0)
+ break;
+
+ entry = EXT2_XATTR_NEXT(entry);
}
- if (ext2_xattr_cache_insert(bh))
+ if (ext2_xattr_cache_insert(ea_block_cache, bh))
ea_idebug(inode, "cache insert failed");
error = -ENODATA;
goto cleanup;
found:
- /* check the buffer size */
- if (entry->e_value_block != 0)
- goto bad_block;
size = le32_to_cpu(entry->e_value_size);
- if (size > inode->i_sb->s_blocksize ||
- le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize)
- goto bad_block;
-
- if (ext2_xattr_cache_insert(bh))
+ if (ext2_xattr_cache_insert(ea_block_cache, bh))
ea_idebug(inode, "cache insert failed");
if (buffer) {
error = -ERANGE;
@@ -243,12 +287,13 @@ cleanup:
static int
ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct buffer_head *bh = NULL;
struct ext2_xattr_entry *entry;
char *end;
size_t rest = buffer_size;
int error;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
@@ -265,9 +310,9 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(HDR(bh)->h_refcount));
end = bh->b_data + bh->b_size;
- if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) ||
- HDR(bh)->h_blocks != cpu_to_le32(1)) {
-bad_block: ext2_error(inode->i_sb, "ext2_xattr_list",
+ if (!ext2_xattr_header_valid(HDR(bh))) {
+bad_block:
+ ext2_error(inode->i_sb, "ext2_xattr_list",
"inode %ld: bad block %d", inode->i_ino,
EXT2_I(inode)->i_file_acl);
error = -EIO;
@@ -277,32 +322,34 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list",
/* check the on-disk data structure */
entry = FIRST_ENTRY(bh);
while (!IS_LAST_ENTRY(entry)) {
- struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(entry);
-
- if ((char *)next >= end)
+ if (!ext2_xattr_entry_valid(entry, end,
+ inode->i_sb->s_blocksize))
goto bad_block;
- entry = next;
+ entry = EXT2_XATTR_NEXT(entry);
}
- if (ext2_xattr_cache_insert(bh))
+ if (ext2_xattr_cache_insert(ea_block_cache, bh))
ea_idebug(inode, "cache insert failed");
/* list the attribute names */
for (entry = FIRST_ENTRY(bh); !IS_LAST_ENTRY(entry);
entry = EXT2_XATTR_NEXT(entry)) {
- const struct xattr_handler *handler =
- ext2_xattr_handler(entry->e_name_index);
-
- if (handler) {
- size_t size = handler->list(dentry, buffer, rest,
- entry->e_name,
- entry->e_name_len,
- handler->flags);
+ const char *prefix;
+
+ prefix = ext2_xattr_prefix(entry->e_name_index, dentry);
+ if (prefix) {
+ size_t prefix_len = strlen(prefix);
+ size_t size = prefix_len + entry->e_name_len + 1;
+
if (buffer) {
if (size > rest) {
error = -ERANGE;
goto cleanup;
}
- buffer += size;
+ memcpy(buffer, prefix, prefix_len);
+ buffer += prefix_len;
+ memcpy(buffer, entry->e_name, entry->e_name_len);
+ buffer += entry->e_name_len;
+ *buffer++ = 0;
}
rest -= size;
}
@@ -319,7 +366,7 @@ cleanup:
/*
* Inode operation listxattr()
*
- * dentry->d_inode->i_mutex: don't care
+ * d_inode(dentry)->i_mutex: don't care
*/
ssize_t
ext2_listxattr(struct dentry *dentry, char *buffer, size_t size)
@@ -337,6 +384,7 @@ static void ext2_xattr_update_super_block(struct super_block *sb)
return;
spin_lock(&EXT2_SB(sb)->s_lock);
+ ext2_update_dynamic_rev(sb);
EXT2_SET_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR);
spin_unlock(&EXT2_SB(sb)->s_lock);
mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
@@ -361,7 +409,7 @@ ext2_xattr_set(struct inode *inode, int name_index, const char *name,
struct super_block *sb = inode->i_sb;
struct buffer_head *bh = NULL;
struct ext2_xattr_header *header = NULL;
- struct ext2_xattr_entry *here, *last;
+ struct ext2_xattr_entry *here = NULL, *last = NULL;
size_t name_len, free, min_offs = sb->s_blocksize;
int not_found = 1, error;
char *end;
@@ -388,6 +436,9 @@ ext2_xattr_set(struct inode *inode, int name_index, const char *name,
name_len = strlen(name);
if (name_len > 255 || value_len > sb->s_blocksize)
return -ERANGE;
+ error = dquot_initialize(inode);
+ if (error)
+ return error;
down_write(&EXT2_I(inode)->xattr_sem);
if (EXT2_I(inode)->i_file_acl) {
/* The inode already has an extended attribute block. */
@@ -400,47 +451,39 @@ ext2_xattr_set(struct inode *inode, int name_index, const char *name,
le32_to_cpu(HDR(bh)->h_refcount));
header = HDR(bh);
end = bh->b_data + bh->b_size;
- if (header->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) ||
- header->h_blocks != cpu_to_le32(1)) {
-bad_block: ext2_error(sb, "ext2_xattr_set",
+ if (!ext2_xattr_header_valid(header)) {
+bad_block:
+ ext2_error(sb, "ext2_xattr_set",
"inode %ld: bad block %d", inode->i_ino,
EXT2_I(inode)->i_file_acl);
error = -EIO;
goto cleanup;
}
- /* Find the named attribute. */
- here = FIRST_ENTRY(bh);
- while (!IS_LAST_ENTRY(here)) {
- struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(here);
- if ((char *)next >= end)
- goto bad_block;
- if (!here->e_value_block && here->e_value_size) {
- size_t offs = le16_to_cpu(here->e_value_offs);
- if (offs < min_offs)
- min_offs = offs;
- }
- not_found = name_index - here->e_name_index;
- if (!not_found)
- not_found = name_len - here->e_name_len;
- if (!not_found)
- not_found = memcmp(name, here->e_name,name_len);
- if (not_found <= 0)
- break;
- here = next;
- }
- last = here;
- /* We still need to compute min_offs and last. */
+ /*
+ * Find the named attribute. If not found, 'here' will point
+ * to entry where the new attribute should be inserted to
+ * maintain sorting.
+ */
+ last = FIRST_ENTRY(bh);
while (!IS_LAST_ENTRY(last)) {
- struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(last);
- if ((char *)next >= end)
+ if (!ext2_xattr_entry_valid(last, end, sb->s_blocksize))
goto bad_block;
- if (!last->e_value_block && last->e_value_size) {
+ if (last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < min_offs)
min_offs = offs;
}
- last = next;
+ if (not_found > 0) {
+ not_found = ext2_xattr_cmp_entry(name_index,
+ name_len,
+ name, last);
+ if (not_found <= 0)
+ here = last;
+ }
+ last = EXT2_XATTR_NEXT(last);
}
+ if (not_found > 0)
+ here = last;
/* Check whether we have enough space left. */
free = min_offs - ((char*)last - (char*)header) - sizeof(__u32);
@@ -448,7 +491,6 @@ bad_block: ext2_error(sb, "ext2_xattr_set",
/* We will use a new extended attribute block. */
free = sb->s_blocksize -
sizeof(struct ext2_xattr_header) - sizeof(__u32);
- here = last = NULL; /* avoid gcc uninitialized warning. */
}
if (not_found) {
@@ -464,14 +506,7 @@ bad_block: ext2_error(sb, "ext2_xattr_set",
error = -EEXIST;
if (flags & XATTR_CREATE)
goto cleanup;
- if (!here->e_value_block && here->e_value_size) {
- size_t size = le32_to_cpu(here->e_value_size);
-
- if (le16_to_cpu(here->e_value_offs) + size >
- sb->s_blocksize || size > sb->s_blocksize)
- goto bad_block;
- free += EXT2_XATTR_SIZE(size);
- }
+ free += EXT2_XATTR_SIZE(le32_to_cpu(here->e_value_size));
free += EXT2_XATTR_LEN(name_len);
}
error = -ENOSPC;
@@ -481,48 +516,48 @@ bad_block: ext2_error(sb, "ext2_xattr_set",
/* Here we know that we can set the new attribute. */
if (header) {
- struct mb_cache_entry *ce;
+ int offset;
- /* assert(header == HDR(bh)); */
- ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev,
- bh->b_blocknr);
lock_buffer(bh);
if (header->h_refcount == cpu_to_le32(1)) {
- ea_bdebug(bh, "modifying in-place");
- if (ce)
- mb_cache_entry_free(ce);
- /* keep the buffer locked while modifying it. */
- } else {
- int offset;
-
- if (ce)
- mb_cache_entry_release(ce);
- unlock_buffer(bh);
- ea_bdebug(bh, "cloning");
- header = kmalloc(bh->b_size, GFP_KERNEL);
- error = -ENOMEM;
- if (header == NULL)
- goto cleanup;
- memcpy(header, HDR(bh), bh->b_size);
- header->h_refcount = cpu_to_le32(1);
-
- offset = (char *)here - bh->b_data;
- here = ENTRY((char *)header + offset);
- offset = (char *)last - bh->b_data;
- last = ENTRY((char *)header + offset);
+ __u32 hash = le32_to_cpu(header->h_hash);
+ struct mb_cache_entry *oe;
+
+ oe = mb_cache_entry_delete_or_get(EA_BLOCK_CACHE(inode),
+ hash, bh->b_blocknr);
+ if (!oe) {
+ ea_bdebug(bh, "modifying in-place");
+ goto update_block;
+ }
+ /*
+ * Someone is trying to reuse the block, leave it alone
+ */
+ mb_cache_entry_put(EA_BLOCK_CACHE(inode), oe);
}
+ unlock_buffer(bh);
+ ea_bdebug(bh, "cloning");
+ header = kmemdup(HDR(bh), bh->b_size, GFP_KERNEL);
+ error = -ENOMEM;
+ if (header == NULL)
+ goto cleanup;
+ header->h_refcount = cpu_to_le32(1);
+
+ offset = (char *)here - bh->b_data;
+ here = ENTRY((char *)header + offset);
+ offset = (char *)last - bh->b_data;
+ last = ENTRY((char *)header + offset);
} else {
/* Allocate a buffer where we construct the new block. */
header = kzalloc(sb->s_blocksize, GFP_KERNEL);
error = -ENOMEM;
if (header == NULL)
goto cleanup;
- end = (char *)header + sb->s_blocksize;
header->h_magic = cpu_to_le32(EXT2_XATTR_MAGIC);
header->h_blocks = header->h_refcount = cpu_to_le32(1);
last = here = ENTRY(header+1);
}
+update_block:
/* Iff we are modifying the block in-place, bh is locked here. */
if (not_found) {
@@ -535,7 +570,7 @@ bad_block: ext2_error(sb, "ext2_xattr_set",
here->e_name_len = name_len;
memcpy(here->e_name, name, name_len);
} else {
- if (!here->e_value_block && here->e_value_size) {
+ if (here->e_value_size) {
char *first_val = (char *)header + min_offs;
size_t offs = le16_to_cpu(here->e_value_offs);
char *val = (char *)header + offs;
@@ -555,18 +590,19 @@ bad_block: ext2_error(sb, "ext2_xattr_set",
/* Remove the old value. */
memmove(first_val + size, first_val, val - first_val);
memset(first_val, 0, size);
- here->e_value_offs = 0;
min_offs += size;
/* Adjust all value offsets. */
last = ENTRY(header+1);
while (!IS_LAST_ENTRY(last)) {
size_t o = le16_to_cpu(last->e_value_offs);
- if (!last->e_value_block && o < offs)
+ if (o < offs)
last->e_value_offs =
cpu_to_le16(o + size);
last = EXT2_XATTR_NEXT(last);
}
+
+ here->e_value_offs = 0;
}
if (value == NULL) {
/* Remove the old name. */
@@ -606,14 +642,63 @@ skip_replace:
}
cleanup:
- brelse(bh);
if (!(bh && header == HDR(bh)))
kfree(header);
+ brelse(bh);
up_write(&EXT2_I(inode)->xattr_sem);
return error;
}
+static void ext2_xattr_release_block(struct inode *inode,
+ struct buffer_head *bh)
+{
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
+
+retry_ref:
+ lock_buffer(bh);
+ if (HDR(bh)->h_refcount == cpu_to_le32(1)) {
+ __u32 hash = le32_to_cpu(HDR(bh)->h_hash);
+ struct mb_cache_entry *oe;
+
+ /*
+ * This must happen under buffer lock to properly
+ * serialize with ext2_xattr_set() reusing the block.
+ */
+ oe = mb_cache_entry_delete_or_get(ea_block_cache, hash,
+ bh->b_blocknr);
+ if (oe) {
+ /*
+ * Someone is trying to reuse the block. Wait
+ * and retry.
+ */
+ unlock_buffer(bh);
+ mb_cache_entry_wait_unused(oe);
+ mb_cache_entry_put(ea_block_cache, oe);
+ goto retry_ref;
+ }
+
+ /* Free the old block. */
+ ea_bdebug(bh, "freeing");
+ ext2_free_blocks(inode, bh->b_blocknr, 1);
+ /* We let our caller release bh, so we
+ * need to duplicate the buffer before. */
+ get_bh(bh);
+ bforget(bh);
+ unlock_buffer(bh);
+ } else {
+ /* Decrement the refcount only. */
+ le32_add_cpu(&HDR(bh)->h_refcount, -1);
+ dquot_free_block(inode, 1);
+ mark_buffer_dirty(bh);
+ unlock_buffer(bh);
+ ea_bdebug(bh, "refcount now=%d",
+ le32_to_cpu(HDR(bh)->h_refcount));
+ if (IS_SYNC(inode))
+ sync_dirty_buffer(bh);
+ }
+}
+
/*
* Second half of ext2_xattr_set(): Update the file system.
*/
@@ -624,6 +709,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
struct super_block *sb = inode->i_sb;
struct buffer_head *new_bh = NULL;
int error;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
if (header) {
new_bh = ext2_xattr_cache_find(inode, header);
@@ -651,15 +737,18 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
don't need to change the reference count. */
new_bh = old_bh;
get_bh(new_bh);
- ext2_xattr_cache_insert(new_bh);
+ ext2_xattr_cache_insert(ea_block_cache, new_bh);
} else {
/* We need to allocate a new block */
ext2_fsblk_t goal = ext2_group_first_block_no(sb,
EXT2_I(inode)->i_block_group);
- int block = ext2_new_block(inode, goal, &error);
+ unsigned long count = 1;
+ ext2_fsblk_t block = ext2_new_blocks(inode, goal,
+ &count, &error,
+ EXT2_ALLOC_NORESERVE);
if (error)
goto cleanup;
- ea_idebug(inode, "creating block %d", block);
+ ea_idebug(inode, "creating block %lu", block);
new_bh = sb_getblk(sb, block);
if (unlikely(!new_bh)) {
@@ -672,7 +761,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
memcpy(new_bh->b_data, header, new_bh->b_size);
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
- ext2_xattr_cache_insert(new_bh);
+ ext2_xattr_cache_insert(ea_block_cache, new_bh);
ext2_xattr_update_super_block(sb);
}
@@ -687,7 +776,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
/* Update the inode. */
EXT2_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
- inode->i_ctime = CURRENT_TIME_SEC;
+ inode_set_ctime_current(inode);
if (IS_SYNC(inode)) {
error = sync_inode_metadata(inode, 1);
/* In case sync failed due to ENOSPC the inode was actually
@@ -705,38 +794,11 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
error = 0;
if (old_bh && old_bh != new_bh) {
- struct mb_cache_entry *ce;
-
/*
* If there was an old block and we are no longer using it,
* release the old block.
*/
- ce = mb_cache_entry_get(ext2_xattr_cache, old_bh->b_bdev,
- old_bh->b_blocknr);
- lock_buffer(old_bh);
- if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) {
- /* Free the old block. */
- if (ce)
- mb_cache_entry_free(ce);
- ea_bdebug(old_bh, "freeing");
- ext2_free_blocks(inode, old_bh->b_blocknr, 1);
- mark_inode_dirty(inode);
- /* We let our caller release old_bh, so we
- * need to duplicate the buffer before. */
- get_bh(old_bh);
- bforget(old_bh);
- } else {
- /* Decrement the refcount only. */
- le32_add_cpu(&HDR(old_bh)->h_refcount, -1);
- if (ce)
- mb_cache_entry_release(ce);
- dquot_free_block_nodirty(inode, 1);
- mark_inode_dirty(inode);
- mark_buffer_dirty(old_bh);
- ea_bdebug(old_bh, "refcount now=%d",
- le32_to_cpu(HDR(old_bh)->h_refcount));
- }
- unlock_buffer(old_bh);
+ ext2_xattr_release_block(inode, old_bh);
}
cleanup:
@@ -755,11 +817,27 @@ void
ext2_xattr_delete_inode(struct inode *inode)
{
struct buffer_head *bh = NULL;
- struct mb_cache_entry *ce;
+ struct ext2_sb_info *sbi = EXT2_SB(inode->i_sb);
- down_write(&EXT2_I(inode)->xattr_sem);
+ /*
+ * We are the only ones holding inode reference. The xattr_sem should
+ * better be unlocked! We could as well just not acquire xattr_sem at
+ * all but this makes the code more futureproof. OTOH we need trylock
+ * here to avoid false-positive warning from lockdep about reclaim
+ * circular dependency.
+ */
+ if (WARN_ON_ONCE(!down_write_trylock(&EXT2_I(inode)->xattr_sem)))
+ return;
if (!EXT2_I(inode)->i_file_acl)
goto cleanup;
+
+ if (!ext2_data_block_valid(sbi, EXT2_I(inode)->i_file_acl, 1)) {
+ ext2_error(inode->i_sb, "ext2_xattr_delete_inode",
+ "inode %ld: xattr block %d is out of data blocks range",
+ inode->i_ino, EXT2_I(inode)->i_file_acl);
+ goto cleanup;
+ }
+
bh = sb_bread(inode->i_sb, EXT2_I(inode)->i_file_acl);
if (!bh) {
ext2_error(inode->i_sb, "ext2_xattr_delete_inode",
@@ -768,34 +846,13 @@ ext2_xattr_delete_inode(struct inode *inode)
goto cleanup;
}
ea_bdebug(bh, "b_count=%d", atomic_read(&(bh->b_count)));
- if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) ||
- HDR(bh)->h_blocks != cpu_to_le32(1)) {
+ if (!ext2_xattr_header_valid(HDR(bh))) {
ext2_error(inode->i_sb, "ext2_xattr_delete_inode",
"inode %ld: bad block %d", inode->i_ino,
EXT2_I(inode)->i_file_acl);
goto cleanup;
}
- ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, bh->b_blocknr);
- lock_buffer(bh);
- if (HDR(bh)->h_refcount == cpu_to_le32(1)) {
- if (ce)
- mb_cache_entry_free(ce);
- ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
- get_bh(bh);
- bforget(bh);
- unlock_buffer(bh);
- } else {
- le32_add_cpu(&HDR(bh)->h_refcount, -1);
- if (ce)
- mb_cache_entry_release(ce);
- ea_bdebug(bh, "refcount now=%d",
- le32_to_cpu(HDR(bh)->h_refcount));
- unlock_buffer(bh);
- mark_buffer_dirty(bh);
- if (IS_SYNC(inode))
- sync_dirty_buffer(bh);
- dquot_free_block_nodirty(inode, 1);
- }
+ ext2_xattr_release_block(inode, bh);
EXT2_I(inode)->i_file_acl = 0;
cleanup:
@@ -804,18 +861,6 @@ cleanup:
}
/*
- * ext2_xattr_put_super()
- *
- * This is called when a file system is unmounted.
- */
-void
-ext2_xattr_put_super(struct super_block *sb)
-{
- mb_cache_shrink(sb->s_bdev);
-}
-
-
-/*
* ext2_xattr_cache_insert()
*
* Create a new entry in the extended attribute cache, and insert
@@ -824,28 +869,20 @@ ext2_xattr_put_super(struct super_block *sb)
* Returns 0, or a negative error number on failure.
*/
static int
-ext2_xattr_cache_insert(struct buffer_head *bh)
+ext2_xattr_cache_insert(struct mb_cache *cache, struct buffer_head *bh)
{
__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
- struct mb_cache_entry *ce;
int error;
- ce = mb_cache_entry_alloc(ext2_xattr_cache, GFP_NOFS);
- if (!ce)
- return -ENOMEM;
- error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+ error = mb_cache_entry_create(cache, GFP_KERNEL, hash, bh->b_blocknr,
+ true);
if (error) {
- mb_cache_entry_free(ce);
if (error == -EBUSY) {
- ea_bdebug(bh, "already in cache (%d cache entries)",
- atomic_read(&ext2_xattr_cache->c_entry_count));
+ ea_bdebug(bh, "already in cache");
error = 0;
}
- } else {
- ea_bdebug(bh, "inserting [%x] (%d cache entries)", (int)hash,
- atomic_read(&ext2_xattr_cache->c_entry_count));
- mb_cache_entry_release(ce);
- }
+ } else
+ ea_bdebug(bh, "inserting [%x]", (int)hash);
return error;
}
@@ -902,45 +939,40 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
{
__u32 hash = le32_to_cpu(header->h_hash);
struct mb_cache_entry *ce;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
-again:
- ce = mb_cache_entry_find_first(ext2_xattr_cache, inode->i_sb->s_bdev,
- hash);
+
+ ce = mb_cache_entry_find_first(ea_block_cache, hash);
while (ce) {
struct buffer_head *bh;
- if (IS_ERR(ce)) {
- if (PTR_ERR(ce) == -EAGAIN)
- goto again;
- break;
- }
-
- bh = sb_bread(inode->i_sb, ce->e_block);
+ bh = sb_bread(inode->i_sb, ce->e_value);
if (!bh) {
ext2_error(inode->i_sb, "ext2_xattr_cache_find",
"inode %ld: block %ld read error",
- inode->i_ino, (unsigned long) ce->e_block);
+ inode->i_ino, (unsigned long) ce->e_value);
} else {
lock_buffer(bh);
if (le32_to_cpu(HDR(bh)->h_refcount) >
- EXT2_XATTR_REFCOUNT_MAX) {
+ EXT2_XATTR_REFCOUNT_MAX) {
ea_idebug(inode, "block %ld refcount %d>%d",
- (unsigned long) ce->e_block,
+ (unsigned long) ce->e_value,
le32_to_cpu(HDR(bh)->h_refcount),
EXT2_XATTR_REFCOUNT_MAX);
} else if (!ext2_xattr_cmp(header, HDR(bh))) {
ea_bdebug(bh, "b_count=%d",
atomic_read(&(bh->b_count)));
- mb_cache_entry_release(ce);
+ mb_cache_entry_touch(ea_block_cache, ce);
+ mb_cache_entry_put(ea_block_cache, ce);
return bh;
}
unlock_buffer(bh);
brelse(bh);
}
- ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+ ce = mb_cache_entry_find_next(ea_block_cache, ce);
}
return NULL;
}
@@ -1013,17 +1045,15 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *header,
#undef BLOCK_HASH_SHIFT
-int __init
-init_ext2_xattr(void)
+#define HASH_BUCKET_BITS 10
+
+struct mb_cache *ext2_xattr_create_cache(void)
{
- ext2_xattr_cache = mb_cache_create("ext2_xattr", 6);
- if (!ext2_xattr_cache)
- return -ENOMEM;
- return 0;
+ return mb_cache_create(HASH_BUCKET_BITS);
}
-void
-exit_ext2_xattr(void)
+void ext2_xattr_destroy_cache(struct mb_cache *cache)
{
- mb_cache_destroy(ext2_xattr_cache);
+ if (cache)
+ mb_cache_destroy(cache);
}
diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h
index 5e41cccff762..6a4966949047 100644
--- a/fs/ext2/xattr.h
+++ b/fs/ext2/xattr.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
File: linux/ext2_xattr.h
@@ -38,7 +39,7 @@ struct ext2_xattr_entry {
__le32 e_value_block; /* disk block attribute is stored on (n/i) */
__le32 e_value_size; /* size of attribute value */
__le32 e_hash; /* hash value of name and value */
- char e_name[0]; /* attribute name */
+ char e_name[]; /* attribute name */
};
#define EXT2_XATTR_PAD_BITS 2
@@ -53,12 +54,12 @@ struct ext2_xattr_entry {
#define EXT2_XATTR_SIZE(size) \
(((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND)
+struct mb_cache;
+
# ifdef CONFIG_EXT2_FS_XATTR
extern const struct xattr_handler ext2_xattr_user_handler;
extern const struct xattr_handler ext2_xattr_trusted_handler;
-extern const struct xattr_handler ext2_xattr_acl_access_handler;
-extern const struct xattr_handler ext2_xattr_acl_default_handler;
extern const struct xattr_handler ext2_xattr_security_handler;
extern ssize_t ext2_listxattr(struct dentry *, char *, size_t);
@@ -67,12 +68,11 @@ extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t);
extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
extern void ext2_xattr_delete_inode(struct inode *);
-extern void ext2_xattr_put_super(struct super_block *);
-extern int init_ext2_xattr(void);
-extern void exit_ext2_xattr(void);
+extern struct mb_cache *ext2_xattr_create_cache(void);
+extern void ext2_xattr_destroy_cache(struct mb_cache *cache);
-extern const struct xattr_handler *ext2_xattr_handlers[];
+extern const struct xattr_handler * const ext2_xattr_handlers[];
# else /* CONFIG_EXT2_FS_XATTR */
@@ -95,23 +95,12 @@ ext2_xattr_delete_inode(struct inode *inode)
{
}
-static inline void
-ext2_xattr_put_super(struct super_block *sb)
-{
-}
-
-static inline int
-init_ext2_xattr(void)
-{
- return 0;
-}
-
-static inline void
-exit_ext2_xattr(void)
+static inline void ext2_xattr_destroy_cache(struct mb_cache *cache)
{
}
#define ext2_xattr_handlers NULL
+#define ext2_listxattr NULL
# endif /* CONFIG_EXT2_FS_XATTR */
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index cfedb2cb0d8c..db47b8ab153e 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/xattr_security.c
* Handler for storing security labels as extended attributes.
@@ -7,43 +8,28 @@
#include <linux/security.h>
#include "xattr.h"
-static size_t
-ext2_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
- const char *name, size_t name_len, int type)
-{
- const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
- const size_t total_len = prefix_len + name_len + 1;
-
- if (list && total_len <= list_size) {
- memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
- memcpy(list+prefix_len, name, name_len);
- list[prefix_len + name_len] = '\0';
- }
- return total_len;
-}
-
static int
-ext2_xattr_security_get(struct dentry *dentry, const char *name,
- void *buffer, size_t size, int type)
+ext2_xattr_security_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_get(inode, EXT2_XATTR_INDEX_SECURITY, name,
buffer, size);
}
static int
-ext2_xattr_security_set(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags, int type)
+ext2_xattr_security_set(const struct xattr_handler *handler,
+ struct mnt_idmap *idmap,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, name,
value, size, flags);
}
-int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
- void *fs_info)
+static int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+ void *fs_info)
{
const struct xattr *xattr;
int err = 0;
@@ -68,7 +54,6 @@ ext2_init_security(struct inode *inode, struct inode *dir,
const struct xattr_handler ext2_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
- .list = ext2_xattr_security_list,
.get = ext2_xattr_security_get,
.set = ext2_xattr_security_set,
};
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 7e192574c001..995f931228ce 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/xattr_trusted.c
* Handler for trusted extended attributes.
@@ -8,41 +9,29 @@
#include "ext2.h"
#include "xattr.h"
-static size_t
-ext2_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
- const char *name, size_t name_len, int type)
+static bool
+ext2_xattr_trusted_list(struct dentry *dentry)
{
- const int prefix_len = XATTR_TRUSTED_PREFIX_LEN;
- const size_t total_len = prefix_len + name_len + 1;
-
- if (!capable(CAP_SYS_ADMIN))
- return 0;
-
- if (list && total_len <= list_size) {
- memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
- memcpy(list+prefix_len, name, name_len);
- list[prefix_len + name_len] = '\0';
- }
- return total_len;
+ return capable(CAP_SYS_ADMIN);
}
static int
-ext2_xattr_trusted_get(struct dentry *dentry, const char *name,
- void *buffer, size_t size, int type)
+ext2_xattr_trusted_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_get(inode, EXT2_XATTR_INDEX_TRUSTED, name,
buffer, size);
}
static int
-ext2_xattr_trusted_set(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags, int type)
+ext2_xattr_trusted_set(const struct xattr_handler *handler,
+ struct mnt_idmap *idmap,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_set(inode, EXT2_XATTR_INDEX_TRUSTED, name,
value, size, flags);
}
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index f470e44c4b8d..dd1507231081 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/xattr_user.c
* Handler for extended user attributes.
@@ -10,46 +11,34 @@
#include "ext2.h"
#include "xattr.h"
-static size_t
-ext2_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
- const char *name, size_t name_len, int type)
+static bool
+ext2_xattr_user_list(struct dentry *dentry)
{
- const size_t prefix_len = XATTR_USER_PREFIX_LEN;
- const size_t total_len = prefix_len + name_len + 1;
-
- if (!test_opt(dentry->d_sb, XATTR_USER))
- return 0;
-
- if (list && total_len <= list_size) {
- memcpy(list, XATTR_USER_PREFIX, prefix_len);
- memcpy(list+prefix_len, name, name_len);
- list[prefix_len + name_len] = '\0';
- }
- return total_len;
+ return test_opt(dentry->d_sb, XATTR_USER);
}
static int
-ext2_xattr_user_get(struct dentry *dentry, const char *name,
- void *buffer, size_t size, int type)
+ext2_xattr_user_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- if (!test_opt(dentry->d_sb, XATTR_USER))
+ if (!test_opt(inode->i_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+ return ext2_xattr_get(inode, EXT2_XATTR_INDEX_USER,
name, buffer, size);
}
static int
-ext2_xattr_user_set(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags, int type)
+ext2_xattr_user_set(const struct xattr_handler *handler,
+ struct mnt_idmap *idmap,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- if (!test_opt(dentry->d_sb, XATTR_USER))
+ if (!test_opt(inode->i_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+ return ext2_xattr_set(inode, EXT2_XATTR_INDEX_USER,
name, value, size, flags);
}
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
deleted file mode 100644
index 1c3312858fcf..000000000000
--- a/fs/ext2/xip.c
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * linux/fs/ext2/xip.c
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/buffer_head.h>
-#include <linux/blkdev.h>
-#include "ext2.h"
-#include "xip.h"
-
-static inline int
-__inode_direct_access(struct inode *inode, sector_t block,
- void **kaddr, unsigned long *pfn)
-{
- struct block_device *bdev = inode->i_sb->s_bdev;
- const struct block_device_operations *ops = bdev->bd_disk->fops;
- sector_t sector;
-
- sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
-
- BUG_ON(!ops->direct_access);
- return ops->direct_access(bdev, sector, kaddr, pfn);
-}
-
-static inline int
-__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
- sector_t *result)
-{
- struct buffer_head tmp;
- int rc;
-
- memset(&tmp, 0, sizeof(struct buffer_head));
- rc = ext2_get_block(inode, pgoff, &tmp, create);
- *result = tmp.b_blocknr;
-
- /* did we get a sparse block (hole in the file)? */
- if (!tmp.b_blocknr && !rc) {
- BUG_ON(create);
- rc = -ENODATA;
- }
-
- return rc;
-}
-
-int
-ext2_clear_xip_target(struct inode *inode, sector_t block)
-{
- void *kaddr;
- unsigned long pfn;
- int rc;
-
- rc = __inode_direct_access(inode, block, &kaddr, &pfn);
- if (!rc)
- clear_page(kaddr);
- return rc;
-}
-
-void ext2_xip_verify_sb(struct super_block *sb)
-{
- struct ext2_sb_info *sbi = EXT2_SB(sb);
-
- if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
- !sb->s_bdev->bd_disk->fops->direct_access) {
- sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
- ext2_msg(sb, KERN_WARNING,
- "warning: ignoring xip option - "
- "not supported by bdev");
- }
-}
-
-int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
- void **kmem, unsigned long *pfn)
-{
- int rc;
- sector_t block;
-
- /* first, retrieve the sector number */
- rc = __ext2_get_block(mapping->host, pgoff, create, &block);
- if (rc)
- return rc;
-
- /* retrieve address of the target data */
- rc = __inode_direct_access(mapping->host, block, kmem, pfn);
- return rc;
-}
diff --git a/fs/ext2/xip.h b/fs/ext2/xip.h
deleted file mode 100644
index 18b34d2f31b3..000000000000
--- a/fs/ext2/xip.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * linux/fs/ext2/xip.h
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#ifdef CONFIG_EXT2_FS_XIP
-extern void ext2_xip_verify_sb (struct super_block *);
-extern int ext2_clear_xip_target (struct inode *, sector_t);
-
-static inline int ext2_use_xip (struct super_block *sb)
-{
- struct ext2_sb_info *sbi = EXT2_SB(sb);
- return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
-}
-int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
- void **, unsigned long *);
-#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
-#else
-#define mapping_is_xip(map) 0
-#define ext2_xip_verify_sb(sb) do { } while (0)
-#define ext2_use_xip(sb) 0
-#define ext2_clear_xip_target(inode, chain) 0
-#define ext2_get_xip_mem NULL
-#endif
generated by cgit (git 2.34.1) at 2025-12-25 08:57:02 +0000