aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/acl.c8
-rw-r--r--fs/ext4/balloc.c1
-rw-r--r--fs/ext4/block_validity.c26
-rw-r--r--fs/ext4/ext4.h39
-rw-r--r--fs/ext4/ext4_jbd2.h2
-rw-r--r--fs/ext4/extents.c25
-rw-r--r--fs/ext4/fast_commit.c306
-rw-r--r--fs/ext4/fast_commit.h2
-rw-r--r--fs/ext4/file.c10
-rw-r--r--fs/ext4/hash.c2
-rw-r--r--fs/ext4/indirect.c2
-rw-r--r--fs/ext4/inline.c37
-rw-r--r--fs/ext4/inode.c198
-rw-r--r--fs/ext4/ioctl.c10
-rw-r--r--fs/ext4/mballoc.c385
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/namei.c41
-rw-r--r--fs/ext4/orphan.c4
-rw-r--r--fs/ext4/page-io.c22
-rw-r--r--fs/ext4/readpage.c14
-rw-r--r--fs/ext4/resize.c7
-rw-r--r--fs/ext4/super.c168
-rw-r--r--fs/ext4/sysfs.c8
-rw-r--r--fs/ext4/xattr.c6
24 files changed, 788 insertions, 537 deletions
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 5a35768d6149..57e82e25f8e2 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -139,7 +139,7 @@ fail:
/*
* Inode operation get_posix_acl().
*
- * inode->i_mutex: don't care
+ * inode->i_rwsem: don't care
*/
struct posix_acl *
ext4_get_acl(struct inode *inode, int type, bool rcu)
@@ -183,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type, bool rcu)
/*
* Set the access or default ACL of an inode.
*
- * inode->i_mutex: down unless called from ext4_new_inode
+ * inode->i_rwsem: down unless called from ext4_new_inode
*/
static int
__ext4_set_acl(handle_t *handle, struct inode *inode, int type,
@@ -271,8 +271,8 @@ out_stop:
/*
* Initialize the ACLs of a new inode. Called from ext4_new_inode.
*
- * dir->i_mutex: down
- * inode->i_mutex: up (access to inode is still exclusive)
+ * dir->i_rwsem: down
+ * inode->i_rwsem: up (access to inode is still exclusive)
*/
int
ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index a0fb0c4bdc7c..78ee3ef795ae 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -411,6 +411,7 @@ verified:
* ext4_read_block_bitmap_nowait()
* @sb: super block
* @block_group: given block group
+ * @ignore_locked: ignore locked buffers
*
* Read the bitmap for a given block_group,and validate the
* bits for block/inode/inode tables are set in the bitmaps
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 4666b55b736e..5504f72bbbbe 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -292,15 +292,10 @@ void ext4_release_system_zone(struct super_block *sb)
call_rcu(&system_blks->rcu, ext4_destroy_system_zone);
}
-/*
- * Returns 1 if the passed-in block region (start_blk,
- * start_blk+count) is valid; 0 if some part of the block region
- * overlaps with some other filesystem metadata blocks.
- */
-int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
- unsigned int count)
+int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
+ ext4_fsblk_t start_blk, unsigned int count)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_system_blocks *system_blks;
struct ext4_system_zone *entry;
struct rb_node *n;
@@ -329,7 +324,9 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
else if (start_blk >= (entry->start_blk + entry->count))
n = n->rb_right;
else {
- ret = (entry->ino == inode->i_ino);
+ ret = 0;
+ if (inode)
+ ret = (entry->ino == inode->i_ino);
break;
}
}
@@ -338,6 +335,17 @@ out_rcu:
return ret;
}
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with some other filesystem metadata blocks.
+ */
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
+ unsigned int count)
+{
+ return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count);
+}
+
int ext4_check_blockref(const char *function, unsigned int line,
struct inode *inode, __le32 *p, unsigned int max)
{
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 715ee206dfe1..3f87cca49f0c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1028,7 +1028,7 @@ struct ext4_inode_info {
/*
* Extended attributes can be read independently of the main file
- * data. Taking i_mutex even when reading would cause contention
+ * data. Taking i_rwsem even when reading would cause contention
* between readers of EAs and writers of regular file data, so
* instead we synchronize on xattr_sem when reading or changing
* EAs.
@@ -1046,6 +1046,8 @@ struct ext4_inode_info {
/* Fast commit related info */
+ /* For tracking dentry create updates */
+ struct list_head i_fc_dilist;
struct list_head i_fc_list; /*
* inodes that need fast commit
* protected by sbi->s_fc_lock.
@@ -1279,7 +1281,7 @@ struct ext4_inode_info {
#define ext4_find_next_zero_bit find_next_zero_bit_le
#define ext4_find_next_bit find_next_bit_le
-extern void ext4_set_bits(void *bm, int cur, int len);
+extern void mb_set_bits(void *bm, int cur, int len);
/*
* Maximal mount counts between two filesystem checks
@@ -1699,6 +1701,7 @@ struct ext4_sb_info {
*/
struct percpu_rw_semaphore s_writepages_rwsem;
struct dax_device *s_daxdev;
+ u64 s_dax_part_off;
#ifdef CONFIG_EXT4_DEBUG
unsigned long s_simulate_fail;
#endif
@@ -1749,6 +1752,7 @@ struct ext4_sb_info {
spinlock_t s_fc_lock;
struct buffer_head *s_fc_bh;
struct ext4_fc_stats s_fc_stats;
+ tid_t s_fc_ineligible_tid;
#ifdef CONFIG_EXT4_DEBUG
int s_fc_debug_max_replay;
#endif
@@ -1794,10 +1798,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
enum {
EXT4_MF_MNTDIR_SAMPLED,
EXT4_MF_FS_ABORTED, /* Fatal error detected */
- EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */
- EXT4_MF_FC_COMMITTING /* File system underoing a fast
- * commit.
- */
+ EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */
};
static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
@@ -2484,7 +2485,7 @@ struct ext4_filename {
#ifdef CONFIG_FS_ENCRYPTION
struct fscrypt_str crypto_buf;
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
struct fscrypt_str cf_name;
#endif
};
@@ -2720,7 +2721,7 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
extern int ext4_fname_setup_ci_filename(struct inode *dir,
const struct qstr *iname,
struct ext4_filename *fname);
@@ -2753,7 +2754,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
ext4_fname_from_fscrypt_name(fname, &name);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
return err;
@@ -2772,7 +2773,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
ext4_fname_from_fscrypt_name(fname, &name);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
#endif
return err;
@@ -2789,7 +2790,7 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname)
fname->usr_fname = NULL;
fname->disk_name.name = NULL;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
kfree(fname->cf_name.name);
fname->cf_name.name = NULL;
#endif
@@ -2805,7 +2806,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
fname->disk_name.name = (unsigned char *) iname->name;
fname->disk_name.len = iname->len;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
@@ -2821,7 +2822,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
kfree(fname->cf_name.name);
fname->cf_name.name = NULL;
#endif
@@ -2925,7 +2926,7 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
struct dentry *dentry);
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
-void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
void ext4_fc_start_update(struct inode *inode);
void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
@@ -2934,6 +2935,9 @@ void ext4_fc_replay_cleanup(struct super_block *sb);
int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
int __init ext4_fc_init_dentry_cache(void);
void ext4_fc_destroy_dentry_cache(void);
+int ext4_fc_record_regions(struct super_block *sb, int ino,
+ ext4_lblk_t lblk, ext4_fsblk_t pblk,
+ int len, int replay);
/* mballoc.c */
extern const struct seq_operations ext4_mb_seq_groups_ops;
@@ -3406,7 +3410,7 @@ do { \
#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
-/* Update i_disksize. Requires i_mutex to avoid races with truncate */
+/* Update i_disksize. Requires i_rwsem to avoid races with truncate */
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
@@ -3417,7 +3421,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
up_write(&EXT4_I(inode)->i_data_sem);
}
-/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
+/* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */
static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
{
int changed = 0;
@@ -3705,6 +3709,9 @@ extern int ext4_inode_block_valid(struct inode *inode,
unsigned int count);
extern int ext4_check_blockref(const char *, unsigned int,
struct inode *, __le32 *, unsigned int);
+extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
+ ext4_fsblk_t start_blk, unsigned int count);
+
/* extents.c */
struct ext4_ext_path;
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 0e4fa644df01..db2ae4a2b38d 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -491,7 +491,7 @@ static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks)
/*
* This function controls whether or not we should try to go down the
* dioread_nolock code paths, which makes it safe to avoid taking
- * i_mutex for direct I/O reads. This only works for extent-based
+ * i_rwsem for direct I/O reads. This only works for extent-based
* files, and it doesn't work if data journaling is enabled, since the
* dioread_nolock code uses b_private to pass information back to the
* I/O completion handler, and this conflicts with the jbd's use of
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 1077ce7e189f..0d98cf402282 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -27,8 +27,8 @@
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/fiemap.h>
-#include <linux/backing-dev.h>
#include <linux/iomap.h>
+#include <linux/sched/mm.h>
#include "ext4_jbd2.h"
#include "ext4_extents.h"
#include "xattr.h"
@@ -97,7 +97,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
* Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
* moment, get_block can be called only for blocks inside i_size since
* page cache has been already dropped and writes are blocked by
- * i_mutex. So we can safely drop the i_data_sem here.
+ * i_rwsem. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
ext4_discard_preallocations(inode, 0);
@@ -3368,7 +3368,6 @@ static int ext4_split_extent(handle_t *handle,
return -EFSCORRUPTED;
}
unwritten = ext4_ext_is_unwritten(ex);
- split_flag1 = 0;
if (map->m_lblk >= ee_block) {
split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
@@ -4404,8 +4403,7 @@ retry:
err = ext4_es_remove_extent(inode, last_block,
EXT_MAX_BLOCKS - last_block);
if (err == -ENOMEM) {
- cond_resched();
- congestion_wait(BLK_RW_ASYNC, HZ/50);
+ memalloc_retry_wait(GFP_ATOMIC);
goto retry;
}
if (err)
@@ -4413,8 +4411,7 @@ retry:
retry_remove_space:
err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
if (err == -ENOMEM) {
- cond_resched();
- congestion_wait(BLK_RW_ASYNC, HZ/50);
+ memalloc_retry_wait(GFP_ATOMIC);
goto retry_remove_space;
}
return err;
@@ -4574,7 +4571,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
- /* Wait all existing dio workers, newcomers will block on i_mutex */
+ /* Wait all existing dio workers, newcomers will block on i_rwsem */
inode_dio_wait(inode);
/* Preallocate the range including the unaligned edges */
@@ -4740,7 +4737,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
goto out;
}
- /* Wait all existing dio workers, newcomers will block on i_mutex */
+ /* Wait all existing dio workers, newcomers will block on i_rwsem */
inode_dio_wait(inode);
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags);
@@ -5336,7 +5333,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
ret = PTR_ERR(handle);
goto out_mmap;
}
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode, 0);
@@ -5476,7 +5473,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
ret = PTR_ERR(handle);
goto out_mmap;
}
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
/* Expand file to avoid data loss if there is error while shifting */
inode->i_size += len;
@@ -5573,7 +5570,7 @@ out_mutex:
* stuff such as page-cache locking consistency, bh mapping consistency or
* extent's data copying must be performed by caller.
* Locking:
- * i_mutex is held for both inodes
+ * i_rwsem is held for both inodes
* i_data_sem is locked for write for both inodes
* Assumptions:
* All pages from requested range are locked for both inodes
@@ -6093,11 +6090,15 @@ int ext4_ext_clear_bb(struct inode *inode)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 0);
+ ext4_fc_record_regions(inode->i_sb, inode->i_ino,
+ 0, path[j].p_block, 1, 1);
}
ext4_ext_drop_refs(path);
kfree(path);
}
ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+ ext4_fc_record_regions(inode->i_sb, inode->i_ino,
+ map.m_lblk, map.m_pblk, map.m_len, 1);
}
cur = cur + map.m_len;
}
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 5ae8026a0c56..3d72565ec6e8 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -199,6 +199,7 @@ void ext4_fc_init_inode(struct inode *inode)
ext4_fc_reset_inode(inode);
ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING);
INIT_LIST_HEAD(&ei->i_fc_list);
+ INIT_LIST_HEAD(&ei->i_fc_dilist);
init_waitqueue_head(&ei->i_fc_wait);
atomic_set(&ei->i_fc_updates, 0);
}
@@ -279,6 +280,8 @@ void ext4_fc_stop_update(struct inode *inode)
void ext4_fc_del(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_fc_dentry_update *fc_dentry;
if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
@@ -286,7 +289,7 @@ void ext4_fc_del(struct inode *inode)
restart:
spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- if (list_empty(&ei->i_fc_list)) {
+ if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) {
spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
return;
}
@@ -295,23 +298,62 @@ restart:
ext4_fc_wait_committing_inode(inode);
goto restart;
}
- list_del_init(&ei->i_fc_list);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+
+ if (!list_empty(&ei->i_fc_list))
+ list_del_init(&ei->i_fc_list);
+
+ /*
+ * Since this inode is getting removed, let's also remove all FC
+ * dentry create references, since it is not needed to log it anyways.
+ */
+ if (list_empty(&ei->i_fc_dilist)) {
+ spin_unlock(&sbi->s_fc_lock);
+ return;
+ }
+
+ fc_dentry = list_first_entry(&ei->i_fc_dilist, struct ext4_fc_dentry_update, fcd_dilist);
+ WARN_ON(fc_dentry->fcd_op != EXT4_FC_TAG_CREAT);
+ list_del_init(&fc_dentry->fcd_list);
+ list_del_init(&fc_dentry->fcd_dilist);
+
+ WARN_ON(!list_empty(&ei->i_fc_dilist));
+ spin_unlock(&sbi->s_fc_lock);
+
+ if (fc_dentry->fcd_name.name &&
+ fc_dentry->fcd_name.len > DNAME_INLINE_LEN)
+ kfree(fc_dentry->fcd_name.name);
+ kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry);
+
+ return;
}
/*
- * Mark file system as fast commit ineligible. This means that next commit
- * operation would result in a full jbd2 commit.
+ * Mark file system as fast commit ineligible, and record latest
+ * ineligible transaction tid. This means until the recorded
+ * transaction, commit operation would result in a full jbd2 commit.
*/
-void ext4_fc_mark_ineligible(struct super_block *sb, int reason)
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
+ tid_t tid;
if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
return;
ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ if (handle && !IS_ERR(handle))
+ tid = handle->h_transaction->t_tid;
+ else {
+ read_lock(&sbi->s_journal->j_state_lock);
+ tid = sbi->s_journal->j_running_transaction ?
+ sbi->s_journal->j_running_transaction->t_tid : 0;
+ read_unlock(&sbi->s_journal->j_state_lock);
+ }
+ spin_lock(&sbi->s_fc_lock);
+ if (sbi->s_fc_ineligible_tid < tid)
+ sbi->s_fc_ineligible_tid = tid;
+ spin_unlock(&sbi->s_fc_lock);
WARN_ON(reason >= EXT4_FC_REASON_MAX);
sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
}
@@ -337,13 +379,6 @@ static int ext4_fc_track_template(
tid_t tid = 0;
int ret;
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (sbi->s_mount_state & EXT4_FC_REPLAY))
- return -EOPNOTSUPP;
-
- if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
- return -EINVAL;
-
tid = handle->h_transaction->t_tid;
mutex_lock(&ei->i_fc_lock);
if (tid == ei->i_sync_tid) {
@@ -361,7 +396,8 @@ static int ext4_fc_track_template(
spin_lock(&sbi->s_fc_lock);
if (list_empty(&EXT4_I(inode)->i_fc_list))
list_add_tail(&EXT4_I(inode)->i_fc_list,
- (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
+ (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+ sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ?
&sbi->s_fc_q[FC_Q_STAGING] :
&sbi->s_fc_q[FC_Q_MAIN]);
spin_unlock(&sbi->s_fc_lock);
@@ -387,7 +423,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
mutex_unlock(&ei->i_fc_lock);
node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
if (!node) {
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -400,7 +436,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
if (!node->fcd_name.name) {
kmem_cache_free(ext4_fc_dentry_cachep, node);
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_NOMEM);
+ EXT4_FC_REASON_NOMEM, NULL);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -412,13 +448,28 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
node->fcd_name.name = node->fcd_iname;
}
node->fcd_name.len = dentry->d_name.len;
-
+ INIT_LIST_HEAD(&node->fcd_dilist);
spin_lock(&sbi->s_fc_lock);
- if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
+ if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+ sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING)
list_add_tail(&node->fcd_list,
&sbi->s_fc_dentry_q[FC_Q_STAGING]);
else
list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_MAIN]);
+
+ /*
+ * This helps us keep a track of all fc_dentry updates which is part of
+ * this ext4 inode. So in case the inode is getting unlinked, before
+ * even we get a chance to fsync, we could remove all fc_dentry
+ * references while evicting the inode in ext4_fc_del().
+ * Also with this, we don't need to loop over all the inodes in
+ * sbi->s_fc_q to get the corresponding inode in
+ * ext4_fc_commit_dentry_updates().
+ */
+ if (dentry_update->op == EXT4_FC_TAG_CREAT) {
+ WARN_ON(!list_empty(&ei->i_fc_dilist));
+ list_add_tail(&node->fcd_dilist, &ei->i_fc_dilist);
+ }
spin_unlock(&sbi->s_fc_lock);
mutex_lock(&ei->i_fc_lock);
@@ -436,12 +487,22 @@ void __ext4_fc_track_unlink(handle_t *handle,
ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
- trace_ext4_fc_track_unlink(inode, dentry, ret);
+ trace_ext4_fc_track_unlink(handle, inode, dentry, ret);
}
void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
{
- __ext4_fc_track_unlink(handle, d_inode(dentry), dentry);
+ struct inode *inode = d_inode(dentry);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
+ __ext4_fc_track_unlink(handle, inode, dentry);
}
void __ext4_fc_track_link(handle_t *handle,
@@ -455,12 +516,22 @@ void __ext4_fc_track_link(handle_t *handle,
ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
- trace_ext4_fc_track_link(inode, dentry, ret);
+ trace_ext4_fc_track_link(handle, inode, dentry, ret);
}
void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
{
- __ext4_fc_track_link(handle, d_inode(dentry), dentry);
+ struct inode *inode = d_inode(dentry);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
+ __ext4_fc_track_link(handle, inode, dentry);
}
void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
@@ -474,12 +545,22 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
- trace_ext4_fc_track_create(inode, dentry, ret);
+ trace_ext4_fc_track_create(handle, inode, dentry, ret);
}
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
{
- __ext4_fc_track_create(handle, d_inode(dentry), dentry);
+ struct inode *inode = d_inode(dentry);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
+ __ext4_fc_track_create(handle, inode, dentry);
}
/* __track_fn for inode tracking */
@@ -495,6 +576,7 @@ static int __track_inode(struct inode *inode, void *arg, bool update)
void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int ret;
if (S_ISDIR(inode->i_mode))
@@ -502,12 +584,19 @@ void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
if (ext4_should_journal_data(inode)) {
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_INODE_JOURNAL_DATA);
+ EXT4_FC_REASON_INODE_JOURNAL_DATA, handle);
return;
}
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
- trace_ext4_fc_track_inode(inode, ret);
+ trace_ext4_fc_track_inode(handle, inode, ret);
}
struct __track_range_args {
@@ -545,18 +634,26 @@ static int __track_range(struct inode *inode, void *arg, bool update)
void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct __track_range_args args;
int ret;
if (S_ISDIR(inode->i_mode))
return;
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
args.start = start;
args.end = end;
ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1);
- trace_ext4_fc_track_range(inode, start, end, ret);
+ trace_ext4_fc_track_range(handle, inode, start, end, ret);
}
static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
@@ -879,7 +976,6 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
int ret = 0;
spin_lock(&sbi->s_fc_lock);
- ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
while (atomic_read(&ei->i_fc_updates)) {
@@ -939,7 +1035,7 @@ __releases(&sbi->s_fc_lock)
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n;
struct inode *inode;
- struct ext4_inode_info *ei, *ei_n;
+ struct ext4_inode_info *ei;
int ret;
if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN]))
@@ -955,21 +1051,16 @@ __releases(&sbi->s_fc_lock)
spin_lock(&sbi->s_fc_lock);
continue;
}
-
- inode = NULL;
- list_for_each_entry_safe(ei, ei_n, &sbi->s_fc_q[FC_Q_MAIN],
- i_fc_list) {
- if (ei->vfs_inode.i_ino == fc_dentry->fcd_ino) {
- inode = &ei->vfs_inode;
- break;
- }
- }
/*
- * If we don't find inode in our list, then it was deleted,
- * in which case, we don't need to record it's create tag.
+ * With fcd_dilist we need not loop in sbi->s_fc_q to get the
+ * corresponding inode pointer
*/
- if (!inode)
- continue;
+ WARN_ON(list_empty(&fc_dentry->fcd_dilist));
+ ei = list_first_entry(&fc_dentry->fcd_dilist,
+ struct ext4_inode_info, i_fc_dilist);
+ inode = &ei->vfs_inode;
+ WARN_ON(inode->i_ino != fc_dentry->fcd_ino);
+
spin_unlock(&sbi->s_fc_lock);
/*
@@ -1073,11 +1164,12 @@ out:
}
static void ext4_fc_update_stats(struct super_block *sb, int status,
- u64 commit_time, int nblks)
+ u64 commit_time, int nblks, tid_t commit_tid)
{
struct ext4_fc_stats *stats = &EXT4_SB(sb)->s_fc_stats;
- jbd_debug(1, "Fast commit ended with status = %d", status);
+ jbd_debug(1, "Fast commit ended with status = %d for tid %u",
+ status, commit_tid);
if (status == EXT4_FC_STATUS_OK) {
stats->fc_num_commits++;
stats->fc_numblks += nblks;
@@ -1095,7 +1187,7 @@ static void ext4_fc_update_stats(struct super_block *sb, int status,
} else {
stats->fc_skipped_commits++;
}
- trace_ext4_fc_commit_stop(sb, nblks, status);
+ trace_ext4_fc_commit_stop(sb, nblks, status, commit_tid);
}
/*
@@ -1113,13 +1205,13 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
int status = EXT4_FC_STATUS_OK, fc_bufs_before = 0;
ktime_t start_time, commit_time;
- trace_ext4_fc_commit_start(sb);
-
- start_time = ktime_get();
-
if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
return jbd2_complete_transaction(journal, commit_tid);
+ trace_ext4_fc_commit_start(sb, commit_tid);
+
+ start_time = ktime_get();
+
restart_fc:
ret = jbd2_fc_begin_commit(journal, commit_tid);
if (ret == -EALREADY) {
@@ -1127,14 +1219,16 @@ restart_fc:
if (atomic_read(&sbi->s_fc_subtid) <= subtid &&
commit_tid > journal->j_commit_sequence)
goto restart_fc;
- ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0);
+ ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0,
+ commit_tid);
return 0;
} else if (ret) {
/*
* Commit couldn't start. Just update stats and perform a
* full commit.
*/
- ext4_fc_update_stats(sb, EXT4_FC_STATUS_FAILED, 0, 0);
+ ext4_fc_update_stats(sb, EXT4_FC_STATUS_FAILED, 0, 0,
+ commit_tid);
return jbd2_complete_transaction(journal, commit_tid);
}
@@ -1166,12 +1260,12 @@ restart_fc:
* don't react too strongly to vast changes in the commit time
*/
commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
- ext4_fc_update_stats(sb, status, commit_time, nblks);
+ ext4_fc_update_stats(sb, status, commit_time, nblks, commit_tid);
return ret;
fallback:
ret = jbd2_fc_end_commit_fallback(journal);
- ext4_fc_update_stats(sb, status, 0, 0);
+ ext4_fc_update_stats(sb, status, 0, 0, commit_tid);
return ret;
}
@@ -1179,7 +1273,7 @@ fallback:
* Fast commit cleanup routine. This is called after every fast commit and
* full commit. full is true if we are called after a full commit.
*/
-static void ext4_fc_cleanup(journal_t *journal, int full)
+static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
{
struct super_block *sb = journal->j_private;
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -1189,6 +1283,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
if (full && sbi->s_fc_bh)
sbi->s_fc_bh = NULL;
+ trace_ext4_fc_cleanup(journal, full, tid);
jbd2_fc_release_bufs(journal);
spin_lock(&sbi->s_fc_lock);
@@ -1197,7 +1292,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_del_init(&iter->i_fc_list);
ext4_clear_inode_state(&iter->vfs_inode,
EXT4_STATE_FC_COMMITTING);
- ext4_fc_reset_inode(&iter->vfs_inode);
+ if (iter->i_sync_tid <= tid)
+ ext4_fc_reset_inode(&iter->vfs_inode);
/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
smp_mb();
#if (BITS_PER_LONG < 64)
@@ -1212,6 +1308,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
struct ext4_fc_dentry_update,
fcd_list);
list_del_init(&fc_dentry->fcd_list);
+ list_del_init(&fc_dentry->fcd_dilist);
spin_unlock(&sbi->s_fc_lock);
if (fc_dentry->fcd_name.name &&
@@ -1226,8 +1323,10 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
&sbi->s_fc_q[FC_Q_MAIN]);
- ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
- ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ if (tid >= sbi->s_fc_ineligible_tid) {
+ sbi->s_fc_ineligible_tid = 0;
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ }
if (full)
sbi->s_fc_bytes = 0;
@@ -1392,14 +1491,15 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
if (state->fc_modified_inodes[i] == ino)
return 0;
if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) {
- state->fc_modified_inodes_size +=
- EXT4_FC_REPLAY_REALLOC_INCREMENT;
state->fc_modified_inodes = krealloc(
- state->fc_modified_inodes, sizeof(int) *
- state->fc_modified_inodes_size,
- GFP_KERNEL);
+ state->fc_modified_inodes,
+ sizeof(int) * (state->fc_modified_inodes_size +
+ EXT4_FC_REPLAY_REALLOC_INCREMENT),
+ GFP_KERNEL);
if (!state->fc_modified_inodes)
return -ENOMEM;
+ state->fc_modified_inodes_size +=
+ EXT4_FC_REPLAY_REALLOC_INCREMENT;
}
state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino;
return 0;
@@ -1431,7 +1531,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
}
inode = NULL;
- ext4_fc_record_modified_inode(sb, ino);
+ ret = ext4_fc_record_modified_inode(sb, ino);
+ if (ret)
+ goto out;
raw_fc_inode = (struct ext4_inode *)
(val + offsetof(struct ext4_fc_inode, fc_raw_inode));
@@ -1563,16 +1665,23 @@ out:
}
/*
- * Record physical disk regions which are in use as per fast commit area. Our
- * simple replay phase allocator excludes these regions from allocation.
+ * Record physical disk regions which are in use as per fast commit area,
+ * and used by inodes during replay phase. Our simple replay phase
+ * allocator excludes these regions from allocation.
*/
-static int ext4_fc_record_regions(struct super_block *sb, int ino,
- ext4_lblk_t lblk, ext4_fsblk_t pblk, int len)
+int ext4_fc_record_regions(struct super_block *sb, int ino,
+ ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay)
{
struct ext4_fc_replay_state *state;
struct ext4_fc_alloc_region *region;
state = &EXT4_SB(sb)->s_fc_replay_state;
+ /*
+ * during replay phase, the fc_regions_valid may not same as
+ * fc_regions_used, update it when do new additions.
+ */
+ if (replay && state->fc_regions_used != state->fc_regions_valid)
+ state->fc_regions_used = state->fc_regions_valid;
if (state->fc_regions_used == state->fc_regions_size) {
state->fc_regions_size +=
EXT4_FC_REPLAY_REALLOC_INCREMENT;
@@ -1590,6 +1699,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino,
region->pblk = pblk;
region->len = len;
+ if (replay)
+ state->fc_regions_valid++;
+
return 0;
}
@@ -1621,6 +1733,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
}
ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+ if (ret)
+ goto out;
start = le32_to_cpu(ex->ee_block);
start_pblk = ext4_ext_pblock(ex);
@@ -1638,18 +1752,14 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
map.m_pblk = 0;
ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0) {
- iput(inode);
- return 0;
- }
+ if (ret < 0)
+ goto out;
if (ret == 0) {
/* Range is not mapped */
path = ext4_find_extent(inode, cur, NULL, 0);
- if (IS_ERR(path)) {
- iput(inode);
- return 0;
- }
+ if (IS_ERR(path))
+ goto out;
memset(&newex, 0, sizeof(newex));
newex.ee_block = cpu_to_le32(cur);
ext4_ext_store_pblock(
@@ -1663,10 +1773,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
up_write((&EXT4_I(inode)->i_data_sem));
ext4_ext_drop_refs(path);
kfree(path);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
goto next;
}
@@ -1679,10 +1787,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
ext4_ext_is_unwritten(ex),
start_pblk + cur - start);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
/*
* Mark the old blocks as free since they aren't used
* anymore. We maintain an array of all the modified
@@ -1702,10 +1808,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
ext4_ext_is_unwritten(ex), map.m_pblk);
ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
ext4_ext_is_unwritten(ex), map.m_pblk);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
/*
* We may have split the extent tree while toggling the state.
* Try to shrink the extent tree now.
@@ -1717,6 +1821,7 @@ next:
}
ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >>
sb->s_blocksize_bits);
+out:
iput(inode);
return 0;
}
@@ -1746,6 +1851,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
}
ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+ if (ret)
+ goto out;
jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n",
inode->i_ino, le32_to_cpu(lrange.fc_lblk),
@@ -1755,10 +1862,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
map.m_len = remaining;
ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0) {
- iput(inode);
- return 0;
- }
+ if (ret < 0)
+ goto out;
if (ret > 0) {
remaining -= ret;
cur += ret;
@@ -1770,18 +1875,17 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
}
down_write(&EXT4_I(inode)->i_data_sem);
- ret = ext4_ext_remove_space(inode, lrange.fc_lblk,
- lrange.fc_lblk + lrange.fc_len - 1);
+ ret = ext4_ext_remove_space(inode, le32_to_cpu(lrange.fc_lblk),
+ le32_to_cpu(lrange.fc_lblk) +
+ le32_to_cpu(lrange.fc_len) - 1);
up_write(&EXT4_I(inode)->i_data_sem);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
ext4_ext_replay_shrink_inode(inode,
i_size_read(inode) >> sb->s_blocksize_bits);
ext4_mark_inode_dirty(NULL, inode);
+out:
iput(inode);
-
return 0;
}
@@ -1852,8 +1956,8 @@ bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk)
if (state->fc_regions[i].ino == 0 ||
state->fc_regions[i].len == 0)
continue;
- if (blk >= state->fc_regions[i].pblk &&
- blk < state->fc_regions[i].pblk + state->fc_regions[i].len)
+ if (in_range(blk, state->fc_regions[i].pblk,
+ state->fc_regions[i].len))
return true;
}
return false;
@@ -1937,7 +2041,7 @@ static int ext4_fc_replay_scan(journal_t *journal,
ret = ext4_fc_record_regions(sb,
le32_to_cpu(ext.fc_ino),
le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex),
- ext4_ext_get_actual_len(ex));
+ ext4_ext_get_actual_len(ex), 0);
if (ret < 0)
break;
ret = JBD2_FC_REPLAY_CONTINUE;
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 083ad1cb705a..80414dcba6e1 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -93,7 +93,6 @@ enum {
EXT4_FC_REASON_RENAME_DIR,
EXT4_FC_REASON_FALLOC_RANGE,
EXT4_FC_REASON_INODE_JOURNAL_DATA,
- EXT4_FC_COMMIT_FAILED,
EXT4_FC_REASON_MAX
};
@@ -109,6 +108,7 @@ struct ext4_fc_dentry_update {
struct qstr fcd_name; /* Dirent name */
unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */
struct list_head fcd_list;
+ struct list_head fcd_dilist;
};
struct ext4_fc_stats {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8cc11715518a..8bd66cdc41be 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -36,9 +36,11 @@
#include "acl.h"
#include "truncate.h"
-static bool ext4_dio_supported(struct inode *inode)
+static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
{
- if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ if (!fscrypt_dio_supported(iocb, iter))
return false;
if (fsverity_active(inode))
return false;
@@ -61,7 +63,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
inode_lock_shared(inode);
}
- if (!ext4_dio_supported(inode)) {
+ if (!ext4_dio_supported(iocb, to)) {
inode_unlock_shared(inode);
/*
* Fallback to buffered I/O if the operation being performed on
@@ -509,7 +511,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
}
/* Fallback to buffered I/O if the inode does not support direct I/O. */
- if (!ext4_dio_supported(inode)) {
+ if (!ext4_dio_supported(iocb, from)) {
if (ilock_shared)
inode_unlock_shared(inode);
else
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index f34f4176c1e7..147b5241dd94 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -290,7 +290,7 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
struct dx_hash_info *hinfo)
{
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
const struct unicode_map *um = dir->i_sb->s_encoding;
int r, dlen;
unsigned char *buff;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 89efa78ed4b2..07a8c75b65ed 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
* Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
* moment, get_block can be called only for blocks inside i_size since
* page cache has been already dropped and writes are blocked by
- * i_mutex. So we can safely drop the i_data_sem here.
+ * i_rwsem. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
ext4_discard_preallocations(inode, 0);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 39a1ab129fdc..9c076262770d 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -7,7 +7,7 @@
#include <linux/iomap.h>
#include <linux/fiemap.h>
#include <linux/iversion.h>
-#include <linux/backing-dev.h>
+#include <linux/sched/mm.h>
#include "ext4_jbd2.h"
#include "ext4.h"
@@ -911,7 +911,7 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping,
struct page **pagep,
void **fsdata)
{
- int ret, inline_size;
+ int ret;
handle_t *handle;
struct page *page;
struct ext4_iloc iloc;
@@ -928,14 +928,9 @@ retry_journal:
goto out;
}
- inline_size = ext4_get_max_inline_size(inode);
-
- ret = -ENOSPC;
- if (inline_size >= pos + len) {
- ret = ext4_prepare_inline_data(handle, inode, pos + len);
- if (ret && ret != -ENOSPC)
- goto out_journal;
- }
+ ret = ext4_prepare_inline_data(handle, inode, pos + len);
+ if (ret && ret != -ENOSPC)
+ goto out_journal;
/*
* We cannot recurse into the filesystem as the transaction
@@ -1133,7 +1128,15 @@ static void ext4_restore_inline_data(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc,
void *buf, int inline_size)
{
- ext4_create_inline_data(handle, inode, inline_size);
+ int ret;
+
+ ret = ext4_create_inline_data(handle, inode, inline_size);
+ if (ret) {
+ ext4_msg(inode->i_sb, KERN_EMERG,
+ "error restoring inline_data for inode -- potential data loss! (inode %lu, error %d)",
+ inode->i_ino, ret);
+ return;
+ }
ext4_write_inline_data(inode, iloc, buf, 0, inline_size);
ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
}
@@ -1780,19 +1783,20 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
void *inline_pos;
unsigned int offset;
struct ext4_dir_entry_2 *de;
- bool ret = true;
+ bool ret = false;
err = ext4_get_inode_loc(dir, &iloc);
if (err) {
EXT4_ERROR_INODE_ERR(dir, -err,
"error %d getting inode %lu block",
err, dir->i_ino);
- return true;
+ return false;
}
down_read(&EXT4_I(dir)->xattr_sem);
if (!ext4_has_inline_data(dir)) {
*has_inline_data = 0;
+ ret = true;
goto out;
}
@@ -1801,7 +1805,6 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
ext4_warning(dir->i_sb,
"bad inline directory (dir #%lu) - no `..'",
dir->i_ino);
- ret = true;
goto out;
}
@@ -1820,16 +1823,15 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
dir->i_ino, le32_to_cpu(de->inode),
le16_to_cpu(de->rec_len), de->name_len,
inline_size);
- ret = true;
goto out;
}
if (le32_to_cpu(de->inode)) {
- ret = false;
goto out;
}
offset += ext4_rec_len_from_disk(de->rec_len, inline_size);
}
+ ret = true;
out:
up_read(&EXT4_I(dir)->xattr_sem);
brelse(iloc.bh);
@@ -1929,8 +1931,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
retry:
err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
if (err == -ENOMEM) {
- cond_resched();
- congestion_wait(BLK_RW_ASYNC, HZ/50);
+ memalloc_retry_wait(GFP_ATOMIC);
goto retry;
}
if (err)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9dbeb772de60..1ce13f69fbec 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -41,6 +41,7 @@
#include <linux/bitops.h>
#include <linux/iomap.h>
#include <linux/iversion.h>
+#include <linux/dax.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -136,8 +137,6 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode,
new_size);
}
-static void ext4_invalidatepage(struct page *page, unsigned int offset,
- unsigned int length);
static int __ext4_journalled_writepage(struct page *page, unsigned int len);
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
int pextents);
@@ -185,7 +184,7 @@ void ext4_evict_inode(struct inode *inode)
* journal. So although mm thinks everything is clean and
* ready for reaping the inode might still have some pages to
* write in the running transaction or waiting to be
- * checkpointed. Thus calling jbd2_journal_invalidatepage()
+ * checkpointed. Thus calling jbd2_journal_invalidate_folio()
* (via truncate_inode_pages()) to discard these buffers can
* cause data loss. Also even if we did not discard these
* buffers, we would have no way to find them after the inode
@@ -337,7 +336,7 @@ stop_handle:
return;
no_delete:
if (!list_empty(&EXT4_I(inode)->i_fc_list))
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL);
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
@@ -1223,7 +1222,7 @@ retry_journal:
/*
* __block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
- * i_size_read because we hold i_mutex.
+ * i_size_read because we hold i_rwsem.
*
* Add inode to orphan list in case we crash before
* truncate finishes
@@ -1570,16 +1569,18 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ struct folio *folio = page_folio(page);
- BUG_ON(!PageLocked(page));
- BUG_ON(PageWriteback(page));
+ BUG_ON(!folio_test_locked(folio));
+ BUG_ON(folio_test_writeback(folio));
if (invalidate) {
- if (page_mapped(page))
- clear_page_dirty_for_io(page);
- block_invalidatepage(page, 0, PAGE_SIZE);
- ClearPageUptodate(page);
+ if (folio_mapped(folio))
+ folio_clear_dirty_for_io(folio);
+ block_invalidate_folio(folio, 0,
+ folio_size(folio));
+ folio_clear_uptodate(folio);
}
- unlock_page(page);
+ folio_unlock(folio);
}
pagevec_release(&pvec);
}
@@ -1970,6 +1971,7 @@ out_no_pagelock:
static int ext4_writepage(struct page *page,
struct writeback_control *wbc)
{
+ struct folio *folio = page_folio(page);
int ret = 0;
loff_t size;
unsigned int len;
@@ -1979,8 +1981,8 @@ static int ext4_writepage(struct page *page,
bool keep_towrite = false;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
- inode->i_mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE);
- unlock_page(page);
+ folio_invalidate(folio, 0, folio_size(folio));
+ folio_unlock(folio);
return -EIO;
}
@@ -1992,6 +1994,15 @@ static int ext4_writepage(struct page *page,
else
len = PAGE_SIZE;
+ /* Should never happen but for bugs in other kernel subsystems */
+ if (!page_has_buffers(page)) {
+ ext4_warning_inode(inode,
+ "page %lu does not have buffers attached", page->index);
+ ClearPageDirty(page);
+ unlock_page(page);
+ return 0;
+ }
+
page_bufs = page_buffers(page);
/*
* We cannot do block allocation or other extent handling in this
@@ -2593,6 +2604,22 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
+ /*
+ * Should never happen but for buggy code in
+ * other subsystems that call
+ * set_page_dirty() without properly warning
+ * the file system first. See [1] for more
+ * information.
+ *
+ * [1] https://lore.kernel.org/linux-mm/[email protected]
+ */
+ if (!page_has_buffers(page)) {
+ ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index);
+ ClearPageDirty(page);
+ unlock_page(page);
+ continue;
+ }
+
if (mpd->map.m_len == 0)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
@@ -3181,40 +3208,39 @@ static void ext4_readahead(struct readahead_control *rac)
ext4_mpage_readpages(inode, rac, NULL);
}
-static void ext4_invalidatepage(struct page *page, unsigned int offset,
- unsigned int length)
+static void ext4_invalidate_folio(struct folio *folio, size_t offset,
+ size_t length)
{
- trace_ext4_invalidatepage(page, offset, length);
+ trace_ext4_invalidate_folio(folio, offset, length);
/* No journalling happens on data buffers when this function is used */
- WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page)));
+ WARN_ON(folio_buffers(folio) && buffer_jbd(folio_buffers(folio)));
- block_invalidatepage(page, offset, length);
+ block_invalidate_folio(folio, offset, length);
}
-static int __ext4_journalled_invalidatepage(struct page *page,
- unsigned int offset,
- unsigned int length)
+static int __ext4_journalled_invalidate_folio(struct folio *folio,
+ size_t offset, size_t length)
{
- journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+ journal_t *journal = EXT4_JOURNAL(folio->mapping->host);
- trace_ext4_journalled_invalidatepage(page, offset, length);
+ trace_ext4_journalled_invalidate_folio(folio, offset, length);
/*
* If it's a full truncate we just forget about the pending dirtying
*/
- if (offset == 0 && length == PAGE_SIZE)
- ClearPageChecked(page);
+ if (offset == 0 && length == folio_size(folio))
+ folio_clear_checked(folio);
- return jbd2_journal_invalidatepage(journal, page, offset, length);
+ return jbd2_journal_invalidate_folio(journal, folio, offset, length);
}
/* Wrapper for aops... */
-static void ext4_journalled_invalidatepage(struct page *page,
- unsigned int offset,
- unsigned int length)
+static void ext4_journalled_invalidate_folio(struct folio *folio,
+ size_t offset,
+ size_t length)
{
- WARN_ON(__ext4_journalled_invalidatepage(page, offset, length) < 0);
+ WARN_ON(__ext4_journalled_invalidate_folio(folio, offset, length) < 0);
}
static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -3253,7 +3279,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
struct ext4_map_blocks *map, loff_t offset,
- loff_t length)
+ loff_t length, unsigned int flags)
{
u8 blkbits = inode->i_blkbits;
@@ -3270,8 +3296,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
if (map->m_flags & EXT4_MAP_NEW)
iomap->flags |= IOMAP_F_NEW;
- iomap->bdev = inode->i_sb->s_bdev;
- iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+ if (flags & IOMAP_DAX)
+ iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+ else
+ iomap->bdev = inode->i_sb->s_bdev;
iomap->offset = (u64) map->m_lblk << blkbits;
iomap->length = (u64) map->m_len << blkbits;
@@ -3291,9 +3319,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
if (map->m_flags & EXT4_MAP_UNWRITTEN) {
iomap->type = IOMAP_UNWRITTEN;
iomap->addr = (u64) map->m_pblk << blkbits;
+ if (flags & IOMAP_DAX)
+ iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
} else if (map->m_flags & EXT4_MAP_MAPPED) {
iomap->type = IOMAP_MAPPED;
iomap->addr = (u64) map->m_pblk << blkbits;
+ if (flags & IOMAP_DAX)
+ iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
} else {
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
@@ -3330,8 +3362,8 @@ retry:
* DAX and direct I/O are the only two operations that are currently
* supported with IOMAP_WRITE.
*/
- WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
- if (IS_DAX(inode))
+ WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT)));
+ if (flags & IOMAP_DAX)
m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
/*
* We use i_size instead of i_disksize here because delalloc writeback
@@ -3402,7 +3434,14 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
if (ret < 0)
return ret;
out:
- ext4_set_iomap(inode, iomap, &map, offset, length);
+ /*
+ * When inline encryption is enabled, sometimes I/O to an encrypted file
+ * has to be broken up to guarantee DUN contiguity. Handle this by
+ * limiting the length of the mapping returned.
+ */
+ map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len);
+
+ ext4_set_iomap(inode, iomap, &map, offset, length, flags);
return 0;
}
@@ -3522,7 +3561,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
delalloc = ext4_iomap_is_delalloc(inode, &map);
set_iomap:
- ext4_set_iomap(inode, iomap, &map, offset, length);
+ ext4_set_iomap(inode, iomap, &map, offset, length, flags);
if (delalloc && iomap->type == IOMAP_HOLE)
iomap->type = IOMAP_DELALLOC;
@@ -3534,29 +3573,32 @@ const struct iomap_ops ext4_iomap_report_ops = {
};
/*
- * Pages can be marked dirty completely asynchronously from ext4's journalling
- * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do
- * much here because ->set_page_dirty is called under VFS locks. The page is
- * not necessarily locked.
+ * Whenever the folio is being dirtied, corresponding buffers should already
+ * be attached to the transaction (we take care of this in ext4_page_mkwrite()
+ * and ext4_write_begin()). However we cannot move buffers to dirty transaction
+ * lists here because ->dirty_folio is called under VFS locks and the folio
+ * is not necessarily locked.
*
- * We cannot just dirty the page and leave attached buffers clean, because the
+ * We cannot just dirty the folio and leave attached buffers clean, because the
* buffers' dirty state is "definitive". We cannot just set the buffers dirty
* or jbddirty because all the journalling code will explode.
*
- * So what we do is to mark the page "pending dirty" and next time writepage
+ * So what we do is to mark the folio "pending dirty" and next time writepage
* is called, propagate that into the buffers appropriately.
*/
-static int ext4_journalled_set_page_dirty(struct page *page)
+static bool ext4_journalled_dirty_folio(struct address_space *mapping,
+ struct folio *folio)
{
- SetPageChecked(page);
- return __set_page_dirty_nobuffers(page);
+ WARN_ON_ONCE(!page_has_buffers(&folio->page));
+ folio_set_checked(folio);
+ return filemap_dirty_folio(mapping, folio);
}
-static int ext4_set_page_dirty(struct page *page)
+static bool ext4_dirty_folio(struct address_space *mapping, struct folio *folio)
{
- WARN_ON_ONCE(!PageLocked(page) && !PageDirty(page));
- WARN_ON_ONCE(!page_has_buffers(page));
- return __set_page_dirty_buffers(page);
+ WARN_ON_ONCE(!folio_test_locked(folio) && !folio_test_dirty(folio));
+ WARN_ON_ONCE(!folio_buffers(folio));
+ return block_dirty_folio(mapping, folio);
}
static int ext4_iomap_swap_activate(struct swap_info_struct *sis,
@@ -3573,9 +3615,9 @@ static const struct address_space_operations ext4_aops = {
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_write_end,
- .set_page_dirty = ext4_set_page_dirty,
+ .dirty_folio = ext4_dirty_folio,
.bmap = ext4_bmap,
- .invalidatepage = ext4_invalidatepage,
+ .invalidate_folio = ext4_invalidate_folio,
.releasepage = ext4_releasepage,
.direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
@@ -3591,9 +3633,9 @@ static const struct address_space_operations ext4_journalled_aops = {
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
- .set_page_dirty = ext4_journalled_set_page_dirty,
+ .dirty_folio = ext4_journalled_dirty_folio,
.bmap = ext4_bmap,
- .invalidatepage = ext4_journalled_invalidatepage,
+ .invalidate_folio = ext4_journalled_invalidate_folio,
.releasepage = ext4_releasepage,
.direct_IO = noop_direct_IO,
.is_partially_uptodate = block_is_partially_uptodate,
@@ -3608,9 +3650,9 @@ static const struct address_space_operations ext4_da_aops = {
.writepages = ext4_writepages,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
- .set_page_dirty = ext4_set_page_dirty,
+ .dirty_folio = ext4_dirty_folio,
.bmap = ext4_bmap,
- .invalidatepage = ext4_invalidatepage,
+ .invalidate_folio = ext4_invalidate_folio,
.releasepage = ext4_releasepage,
.direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
@@ -3622,9 +3664,8 @@ static const struct address_space_operations ext4_da_aops = {
static const struct address_space_operations ext4_dax_aops = {
.writepages = ext4_dax_writepages,
.direct_IO = noop_direct_IO,
- .set_page_dirty = __set_page_dirty_no_writeback,
+ .dirty_folio = noop_dirty_folio,
.bmap = ext4_bmap,
- .invalidatepage = noop_invalidatepage,
.swap_activate = ext4_iomap_swap_activate,
};
@@ -3762,8 +3803,8 @@ static int ext4_block_zero_page_range(handle_t *handle,
length = max;
if (IS_DAX(inode)) {
- return iomap_zero_range(inode, from, length, NULL,
- &ext4_iomap_ops);
+ return dax_zero_range(inode, from, length, NULL,
+ &ext4_iomap_ops);
}
return __ext4_block_zero_page_range(handle, mapping, from, length);
}
@@ -3972,7 +4013,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
}
- /* Wait all existing dio workers, newcomers will block on i_mutex */
+ /* Wait all existing dio workers, newcomers will block on i_rwsem */
inode_dio_wait(inode);
/*
@@ -4122,7 +4163,7 @@ int ext4_truncate(struct inode *inode)
/*
* There is a possibility that we're either freeing the inode
* or it's a completely new inode. In those cases we might not
- * have i_mutex locked because it's not necessary.
+ * have i_rwsem locked because it's not necessary.
*/
if (!(inode->i_state & (I_NEW|I_FREEING)))
WARN_ON(!inode_is_locked(inode));
@@ -5197,13 +5238,12 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
}
/*
- * In data=journal mode ext4_journalled_invalidatepage() may fail to invalidate
- * buffers that are attached to a page stradding i_size and are undergoing
+ * In data=journal mode ext4_journalled_invalidate_folio() may fail to invalidate
+ * buffers that are attached to a folio straddling i_size and are undergoing
* commit. In that case we have to wait for commit to finish and try again.
*/
static void ext4_wait_for_tail_page_commit(struct inode *inode)
{
- struct page *page;
unsigned offset;
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = 0;
@@ -5211,25 +5251,25 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
offset = inode->i_size & (PAGE_SIZE - 1);
/*
- * If the page is fully truncated, we don't need to wait for any commit
- * (and we even should not as __ext4_journalled_invalidatepage() may
- * strip all buffers from the page but keep the page dirty which can then
- * confuse e.g. concurrent ext4_writepage() seeing dirty page without
+ * If the folio is fully truncated, we don't need to wait for any commit
+ * (and we even should not as __ext4_journalled_invalidate_folio() may
+ * strip all buffers from the folio but keep the folio dirty which can then
+ * confuse e.g. concurrent ext4_writepage() seeing dirty folio without
* buffers). Also we don't need to wait for any commit if all buffers in
- * the page remain valid. This is most beneficial for the common case of
+ * the folio remain valid. This is most beneficial for the common case of
* blocksize == PAGESIZE.
*/
if (!offset || offset > (PAGE_SIZE - i_blocksize(inode)))
return;
while (1) {
- page = find_lock_page(inode->i_mapping,
+ struct folio *folio = filemap_lock_folio(inode->i_mapping,
inode->i_size >> PAGE_SHIFT);
- if (!page)
+ if (!folio)
return;
- ret = __ext4_journalled_invalidatepage(page, offset,
- PAGE_SIZE - offset);
- unlock_page(page);
- put_page(page);
+ ret = __ext4_journalled_invalidate_folio(folio, offset,
+ folio_size(folio) - offset);
+ folio_unlock(folio);
+ folio_put(folio);
if (ret != -EBUSY)
return;
commit_tid = 0;
@@ -5264,7 +5304,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
* transaction are already on disk (truncate waits for pages under
* writeback).
*
- * Called with inode->i_mutex down.
+ * Called with inode->i_rwsem down.
*/
int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
struct iattr *attr)
@@ -5976,7 +6016,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
return PTR_ERR(handle);
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
+ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle);
err = ext4_mark_inode_dirty(handle, inode);
ext4_handle_sync(handle);
ext4_journal_stop(handle);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bbbedf27b71c..992229ca2d83 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -269,7 +269,7 @@ out:
return err ? err : 0;
}
-/**
+/*
* Swap memory between @a and @b for @len bytes.
*
* @a: pointer to first memory area
@@ -290,7 +290,7 @@ static void memswap(void *a, void *b, size_t len)
}
}
-/**
+/*
* Swap i_data and associated attributes between @inode1 and @inode2.
* This function is used for the primary swap between inode1 and inode2
* and also to revert this primary swap in case of errors.
@@ -344,7 +344,7 @@ void ext4_reset_inode_seed(struct inode *inode)
ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen));
}
-/**
+/*
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
@@ -411,7 +411,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
err = -EINVAL;
goto err_out;
}
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle);
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
@@ -1373,7 +1373,7 @@ mext_out:
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL);
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cf2fd9fc7d98..252c168454c7 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1000,7 +1000,7 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac)
return 0;
if (ac->ac_criteria >= 2)
return 0;
- if (ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))
+ if (!ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))
return 0;
return 1;
}
@@ -1689,7 +1689,7 @@ static int mb_test_and_clear_bits(void *bm, int cur, int len)
return zero_bit;
}
-void ext4_set_bits(void *bm, int cur, int len)
+void mb_set_bits(void *bm, int cur, int len)
{
__u32 *addr;
@@ -1996,7 +1996,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info);
- ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
+ mb_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
mb_check_buddy(e4b);
return ret;
@@ -2834,7 +2834,7 @@ out:
static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
ext4_group_t group;
if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
@@ -2845,7 +2845,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
ext4_group_t group;
++*pos;
@@ -2857,7 +2857,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
ext4_group_t group = (ext4_group_t) ((unsigned long) v);
int i;
int err, buddy_loaded = 0;
@@ -2985,7 +2985,7 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset)
static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos)
__acquires(&EXT4_SB(sb)->s_mb_rb_lock)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
unsigned long position;
read_lock(&EXT4_SB(sb)->s_mb_rb_lock);
@@ -2998,7 +2998,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock)
static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
unsigned long position;
++*pos;
@@ -3010,7 +3010,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof
static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned long position = ((unsigned long) v);
struct ext4_group_info *grp;
@@ -3058,7 +3058,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v)
__releases(&EXT4_SB(sb)->s_mb_rb_lock)
{
- struct super_block *sb = PDE_DATA(file_inode(seq->file));
+ struct super_block *sb = pde_data(file_inode(seq->file));
read_unlock(&EXT4_SB(sb)->s_mb_rb_lock);
}
@@ -3825,7 +3825,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
* We leak some of the blocks here.
*/
ext4_lock_group(sb, ac->ac_b_ex.fe_group);
- ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+ mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -3844,7 +3844,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
}
}
#endif
- ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+ mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
if (ext4_has_group_desc_csum(sb) &&
(gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
@@ -3899,69 +3899,103 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i, clen, err;
+ int i, err;
int already;
+ unsigned int clen, clen_changed, thisgrp_len;
- clen = EXT4_B2C(sbi, len);
+ while (len > 0) {
+ ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
- ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
- bitmap_bh = ext4_read_block_bitmap(sb, group);
- if (IS_ERR(bitmap_bh)) {
- err = PTR_ERR(bitmap_bh);
- bitmap_bh = NULL;
- goto out_err;
- }
+ /*
+ * Check to see if we are freeing blocks across a group
+ * boundary.
+ * In case of flex_bg, this can happen that (block, len) may
+ * span across more than one group. In that case we need to
+ * get the corresponding group metadata to work with.
+ * For this we have goto again loop.
+ */
+ thisgrp_len = min_t(unsigned int, (unsigned int)len,
+ EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
+ clen = EXT4_NUM_B2C(sbi, thisgrp_len);
+
+ if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) {
+ ext4_error(sb, "Marking blocks in system zone - "
+ "Block = %llu, len = %u",
+ block, thisgrp_len);
+ bitmap_bh = NULL;
+ break;
+ }
- err = -EIO;
- gdp = ext4_get_group_desc(sb, group, &gdp_bh);
- if (!gdp)
- goto out_err;
+ bitmap_bh = ext4_read_block_bitmap(sb, group);
+ if (IS_ERR(bitmap_bh)) {
+ err = PTR_ERR(bitmap_bh);
+ bitmap_bh = NULL;
+ break;
+ }
- ext4_lock_group(sb, group);
- already = 0;
- for (i = 0; i < clen; i++)
- if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
- already++;
+ err = -EIO;
+ gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+ if (!gdp)
+ break;
- if (state)
- ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
- else
- mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
- if (ext4_has_group_desc_csum(sb) &&
- (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
- gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- ext4_free_group_clusters_set(sb, gdp,
- ext4_free_clusters_after_init(sb,
- group, gdp));
- }
- if (state)
- clen = ext4_free_group_clusters(sb, gdp) - clen + already;
- else
- clen = ext4_free_group_clusters(sb, gdp) + clen - already;
+ ext4_lock_group(sb, group);
+ already = 0;
+ for (i = 0; i < clen; i++)
+ if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) ==
+ !state)
+ already++;
+
+ clen_changed = clen - already;
+ if (state)
+ mb_set_bits(bitmap_bh->b_data, blkoff, clen);
+ else
+ mb_clear_bits(bitmap_bh->b_data, blkoff, clen);
+ if (ext4_has_group_desc_csum(sb) &&
+ (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb, group, gdp));
+ }
+ if (state)
+ clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
+ else
+ clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
- ext4_free_group_clusters_set(sb, gdp, clen);
- ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
- ext4_group_desc_csum_set(sb, group, gdp);
+ ext4_free_group_clusters_set(sb, gdp, clen);
+ ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+ ext4_group_desc_csum_set(sb, group, gdp);
- ext4_unlock_group(sb, group);
+ ext4_unlock_group(sb, group);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t flex_group = ext4_flex_group(sbi, group);
+ if (sbi->s_log_groups_per_flex) {
+ ext4_group_t flex_group = ext4_flex_group(sbi, group);
+ struct flex_groups *fg = sbi_array_rcu_deref(sbi,
+ s_flex_groups, flex_group);
- atomic64_sub(len,
- &sbi_array_rcu_deref(sbi, s_flex_groups,
- flex_group)->free_clusters);
+ if (state)
+ atomic64_sub(clen_changed, &fg->free_clusters);
+ else
+ atomic64_add(clen_changed, &fg->free_clusters);
+
+ }
+
+ err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+ if (err)
+ break;
+ sync_dirty_buffer(bitmap_bh);
+ err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+ sync_dirty_buffer(gdp_bh);
+ if (err)
+ break;
+
+ block += thisgrp_len;
+ len -= thisgrp_len;
+ brelse(bitmap_bh);
+ BUG_ON(len < 0);
}
- err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
if (err)
- goto out_err;
- sync_dirty_buffer(bitmap_bh);
- err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
- sync_dirty_buffer(gdp_bh);
-
-out_err:
- brelse(bitmap_bh);
+ brelse(bitmap_bh);
}
/*
@@ -4433,7 +4467,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
while (n) {
entry = rb_entry(n, struct ext4_free_data, efd_node);
- ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
+ mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
n = rb_next(n);
}
return;
@@ -4474,7 +4508,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
if (unlikely(len == 0))
continue;
BUG_ON(groupnr != group);
- ext4_set_bits(bitmap, start, len);
+ mb_set_bits(bitmap, start, len);
preallocated += len;
}
mb_debug(sb, "preallocated %d for group %u\n", preallocated, group);
@@ -5753,7 +5787,8 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
struct super_block *sb = ar->inode->i_sb;
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i = sb->s_blocksize;
+ ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
+ ext4_grpblk_t i = 0;
ext4_fsblk_t goal, block;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
@@ -5775,19 +5810,26 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
ext4_get_group_no_and_offset(sb,
max(ext4_group_first_block_no(sb, group), goal),
NULL, &blkoff);
- i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize,
+ while (1) {
+ i = mb_find_next_zero_bit(bitmap_bh->b_data, max,
blkoff);
+ if (i >= max)
+ break;
+ if (ext4_fc_replay_check_excluded(sb,
+ ext4_group_first_block_no(sb, group) + i)) {
+ blkoff = i + 1;
+ } else
+ break;
+ }
brelse(bitmap_bh);
- if (i >= sb->s_blocksize)
- continue;
- if (ext4_fc_replay_check_excluded(sb,
- ext4_group_first_block_no(sb, group) + i))
- continue;
- break;
+ if (i < max)
+ break;
}
- if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize)
+ if (group >= ext4_get_groups_count(sb) || i >= max) {
+ *errp = -ENOSPC;
return 0;
+ }
block = ext4_group_first_block_no(sb, group) + i;
ext4_mb_mark_bb(sb, block, 1, 1);
@@ -5838,17 +5880,17 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
}
/**
- * ext4_free_blocks() -- Free given blocks and update quota
+ * ext4_mb_clear_bb() -- helper function for freeing blocks.
+ * Used by ext4_free_blocks()
* @handle: handle for this transaction
* @inode: inode
- * @bh: optional buffer of the block to be freed
* @block: starting physical block to be freed
* @count: number of blocks to be freed
* @flags: flags used by ext4_free_blocks
*/
-void ext4_free_blocks(handle_t *handle, struct inode *inode,
- struct buffer_head *bh, ext4_fsblk_t block,
- unsigned long count, int flags)
+static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t block, unsigned long count,
+ int flags)
{
struct buffer_head *bitmap_bh = NULL;
struct super_block *sb = inode->i_sb;
@@ -5865,80 +5907,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
sbi = EXT4_SB(sb);
- if (sbi->s_mount_state & EXT4_FC_REPLAY) {
- ext4_free_blocks_simple(inode, block, count);
- return;
- }
-
- might_sleep();
- if (bh) {
- if (block)
- BUG_ON(block != bh->b_blocknr);
- else
- block = bh->b_blocknr;
- }
-
- if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
- !ext4_inode_block_valid(inode, block, count)) {
- ext4_error(sb, "Freeing blocks not in datazone - "
- "block = %llu, count = %lu", block, count);
- goto error_return;
- }
-
- ext4_debug("freeing block %llu\n", block);
- trace_ext4_free_blocks(inode, block, count, flags);
-
- if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
- BUG_ON(count > 1);
-
- ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
- inode, bh, block);
- }
-
- /*
- * If the extent to be freed does not begin on a cluster
- * boundary, we need to deal with partial clusters at the
- * beginning and end of the extent. Normally we will free
- * blocks at the beginning or the end unless we are explicitly
- * requested to avoid doing so.
- */
- overflow = EXT4_PBLK_COFF(sbi, block);
- if (overflow) {
- if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
- overflow = sbi->s_cluster_ratio - overflow;
- block += overflow;
- if (count > overflow)
- count -= overflow;
- else
- return;
- } else {
- block -= overflow;
- count += overflow;
- }
- }
- overflow = EXT4_LBLK_COFF(sbi, count);
- if (overflow) {
- if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
- if (count > overflow)
- count -= overflow;
- else
- return;
- } else
- count += sbi->s_cluster_ratio - overflow;
- }
-
- if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
- int i;
- int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
-
- for (i = 0; i < count; i++) {
- cond_resched();
- if (is_metadata)
- bh = sb_find_get_block(inode->i_sb, block + i);
- ext4_forget(handle, is_metadata, inode, bh, block + i);
- }
- }
-
do_more:
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
@@ -5969,13 +5937,7 @@ do_more:
goto error_return;
}
- if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
- in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
- in_range(block, ext4_inode_table(sb, gdp),
- sbi->s_itb_per_group) ||
- in_range(block + count - 1, ext4_inode_table(sb, gdp),
- sbi->s_itb_per_group)) {
-
+ if (!ext4_inode_block_valid(inode, block, count)) {
ext4_error(sb, "Freeing blocks in system zone - "
"Block = %llu, count = %lu", block, count);
/* err = 0. ext4_std_error should be a no op */
@@ -6046,7 +6008,7 @@ do_more:
NULL);
if (err && err != -EOPNOTSUPP)
ext4_msg(sb, KERN_WARNING, "discard request in"
- " group:%d block:%d count:%lu failed"
+ " group:%u block:%d count:%lu failed"
" with %d", block_group, bit, count,
err);
} else
@@ -6107,6 +6069,103 @@ error_return:
}
/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle: handle for this transaction
+ * @inode: inode
+ * @bh: optional buffer of the block to be freed
+ * @block: starting physical block to be freed
+ * @count: number of blocks to be freed
+ * @flags: flags used by ext4_free_blocks
+ */
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t block,
+ unsigned long count, int flags)
+{
+ struct super_block *sb = inode->i_sb;
+ unsigned int overflow;
+ struct ext4_sb_info *sbi;
+
+ sbi = EXT4_SB(sb);
+
+ if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+ ext4_free_blocks_simple(inode, block, count);
+ return;
+ }
+
+ might_sleep();
+ if (bh) {
+ if (block)
+ BUG_ON(block != bh->b_blocknr);
+ else
+ block = bh->b_blocknr;
+ }
+
+ if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
+ !ext4_inode_block_valid(inode, block, count)) {
+ ext4_error(sb, "Freeing blocks not in datazone - "
+ "block = %llu, count = %lu", block, count);
+ return;
+ }
+
+ ext4_debug("freeing block %llu\n", block);
+ trace_ext4_free_blocks(inode, block, count, flags);
+
+ if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
+ BUG_ON(count > 1);
+
+ ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
+ inode, bh, block);
+ }
+
+ /*
+ * If the extent to be freed does not begin on a cluster
+ * boundary, we need to deal with partial clusters at the
+ * beginning and end of the extent. Normally we will free
+ * blocks at the beginning or the end unless we are explicitly
+ * requested to avoid doing so.
+ */
+ overflow = EXT4_PBLK_COFF(sbi, block);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
+ overflow = sbi->s_cluster_ratio - overflow;
+ block += overflow;
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else {
+ block -= overflow;
+ count += overflow;
+ }
+ }
+ overflow = EXT4_LBLK_COFF(sbi, count);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else
+ count += sbi->s_cluster_ratio - overflow;
+ }
+
+ if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
+ int i;
+ int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
+
+ for (i = 0; i < count; i++) {
+ cond_resched();
+ if (is_metadata)
+ bh = sb_find_get_block(inode->i_sb, block + i);
+ ext4_forget(handle, is_metadata, inode, bh, block + i);
+ }
+ }
+
+ ext4_mb_clear_bb(handle, inode, block, count, flags);
+ return;
+}
+
+/**
* ext4_group_add_blocks() -- Add given blocks to an existing group
* @handle: handle to this transaction
* @sb: super block
@@ -6162,11 +6221,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
goto error_return;
}
- if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
- in_range(ext4_inode_bitmap(sb, desc), block, count) ||
- in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
- in_range(block + count - 1, ext4_inode_table(sb, desc),
- sbi->s_itb_per_group)) {
+ if (!ext4_sb_block_valid(sb, NULL, block, count)) {
ext4_error(sb, "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index ff8916e1d38e..7a5353a8cfd7 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -485,7 +485,7 @@ int ext4_ext_migrate(struct inode *inode)
* when we add extents we extent the journal
*/
/*
- * Even though we take i_mutex we can still cause block
+ * Even though we take i_rwsem we can still cause block
* allocation via mmap write to holes. If we have allocated
* new blocks we fail migrate. New block allocation will
* clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 52c9bd154122..e37da8d5cd0c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1317,7 +1317,7 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
dx_set_count(entries, count + 1);
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/*
* Test whether a case-insensitive directory entry matches the filename
* being searched for. If quick is set, assume the name being looked up
@@ -1428,7 +1428,7 @@ static bool ext4_match(struct inode *parent,
f.crypto_buf = fname->crypto_buf;
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) &&
(!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
if (fname->cf_name.name) {
@@ -1800,7 +1800,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
}
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (!inode && IS_CASEFOLDED(dir)) {
/* Eventually we want to call d_add_ci(dentry, NULL)
* for negative dentries in the encoding case as
@@ -2308,7 +2308,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
if (fscrypt_is_nokey_name(dentry))
return -ENOKEY;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
return -EINVAL;
@@ -2997,14 +2997,14 @@ bool ext4_empty_dir(struct inode *inode)
if (inode->i_size < ext4_dir_rec_len(1, NULL) +
ext4_dir_rec_len(2, NULL)) {
EXT4_ERROR_INODE(inode, "invalid size");
- return true;
+ return false;
}
/* The first directory block must not be a hole,
* so treat it as DIRENT_HTREE
*/
bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
if (IS_ERR(bh))
- return true;
+ return false;
de = (struct ext4_dir_entry_2 *) bh->b_data;
if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size,
@@ -3012,7 +3012,7 @@ bool ext4_empty_dir(struct inode *inode)
le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) {
ext4_warning_inode(inode, "directory missing '.'");
brelse(bh);
- return true;
+ return false;
}
offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
de = ext4_next_entry(de, sb->s_blocksize);
@@ -3021,7 +3021,7 @@ bool ext4_empty_dir(struct inode *inode)
le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) {
ext4_warning_inode(inode, "directory missing '..'");
brelse(bh);
- return true;
+ return false;
}
offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
while (offset < inode->i_size) {
@@ -3035,7 +3035,7 @@ bool ext4_empty_dir(struct inode *inode)
continue;
}
if (IS_ERR(bh))
- return true;
+ return false;
}
de = (struct ext4_dir_entry_2 *) (bh->b_data +
(offset & (sb->s_blocksize - 1)));
@@ -3126,7 +3126,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
ext4_fc_track_unlink(handle, dentry);
retval = ext4_mark_inode_dirty(handle, dir);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
@@ -3231,7 +3231,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
if (!retval)
ext4_fc_track_unlink(handle, dentry);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
@@ -3889,14 +3889,21 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
* dirents in directories.
*/
ext4_fc_mark_ineligible(old.inode->i_sb,
- EXT4_FC_REASON_RENAME_DIR);
+ EXT4_FC_REASON_RENAME_DIR, handle);
} else {
+ struct super_block *sb = old.inode->i_sb;
+
if (new.inode)
ext4_fc_track_unlink(handle, new.dentry);
- __ext4_fc_track_link(handle, old.inode, new.dentry);
- __ext4_fc_track_unlink(handle, old.inode, old.dentry);
- if (whiteout)
- __ext4_fc_track_create(handle, whiteout, old.dentry);
+ if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+ !(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+ !(ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE))) {
+ __ext4_fc_track_link(handle, old.inode, new.dentry);
+ __ext4_fc_track_unlink(handle, old.inode, old.dentry);
+ if (whiteout)
+ __ext4_fc_track_create(handle, whiteout,
+ old.dentry);
+ }
}
if (new.inode) {
@@ -4049,7 +4056,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
if (unlikely(retval))
goto end_rename;
ext4_fc_mark_ineligible(new.inode->i_sb,
- EXT4_FC_REASON_CROSS_RENAME);
+ EXT4_FC_REASON_CROSS_RENAME, handle);
if (old.dir_bh) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
if (retval)
diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c
index 53adc8f570a3..7de0612eb42d 100644
--- a/fs/ext4/orphan.c
+++ b/fs/ext4/orphan.c
@@ -93,7 +93,7 @@ static int ext4_orphan_file_add(handle_t *handle, struct inode *inode)
* At filesystem recovery time, we walk this list deleting unlinked
* inodes and truncating linked inodes in ext4_orphan_cleanup().
*
- * Orphan list manipulation functions must be called under i_mutex unless
+ * Orphan list manipulation functions must be called under i_rwsem unless
* we are just creating the inode or deleting it.
*/
int ext4_orphan_add(handle_t *handle, struct inode *inode)
@@ -119,7 +119,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
/*
* Orphan handling is only valid for files with data blocks
* being truncated, or files being unlinked. Note that we either
- * hold i_mutex, or the inode can not be referenced from outside,
+ * hold i_rwsem, or the inode can not be referenced from outside,
* so i_nlink should not be bumped due to race
*/
ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 9cb261714991..17bb78ebd784 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -24,7 +24,7 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
-#include <linux/backing-dev.h>
+#include <linux/sched/mm.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -323,10 +323,9 @@ static void ext4_end_bio(struct bio *bio)
{
ext4_io_end_t *io_end = bio->bi_private;
sector_t bi_sector = bio->bi_iter.bi_sector;
- char b[BDEVNAME_SIZE];
- if (WARN_ONCE(!io_end, "io_end is NULL: %s: sector %Lu len %u err %d\n",
- bio_devname(bio, b),
+ if (WARN_ONCE(!io_end, "io_end is NULL: %pg: sector %Lu len %u err %d\n",
+ bio->bi_bdev,
(long long) bio->bi_iter.bi_sector,
(unsigned) bio_sectors(bio),
bio->bi_status)) {
@@ -372,10 +371,9 @@ void ext4_io_submit(struct ext4_io_submit *io)
struct bio *bio = io->io_bio;
if (bio) {
- int io_op_flags = io->io_wbc->sync_mode == WB_SYNC_ALL ?
- REQ_SYNC : 0;
+ if (io->io_wbc->sync_mode == WB_SYNC_ALL)
+ io->io_bio->bi_opf |= REQ_SYNC;
io->io_bio->bi_write_hint = io->io_end->inode->i_write_hint;
- bio_set_op_attrs(io->io_bio, REQ_OP_WRITE, io_op_flags);
submit_bio(io->io_bio);
}
io->io_bio = NULL;
@@ -398,10 +396,9 @@ static void io_submit_init_bio(struct ext4_io_submit *io,
* bio_alloc will _always_ be able to allocate a bio if
* __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset().
*/
- bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
+ bio = bio_alloc(bh->b_bdev, BIO_MAX_VECS, REQ_OP_WRITE, GFP_NOIO);
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio_set_dev(bio, bh->b_bdev);
bio->bi_end_io = ext4_end_bio;
bio->bi_private = ext4_get_io_end(io->io_end);
io->io_bio = bio;
@@ -523,12 +520,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
ret = PTR_ERR(bounce_page);
if (ret == -ENOMEM &&
(io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
- gfp_flags = GFP_NOFS;
+ gfp_t new_gfp_flags = GFP_NOFS;
if (io->io_bio)
ext4_io_submit(io);
else
- gfp_flags |= __GFP_NOFAIL;
- congestion_wait(BLK_RW_ASYNC, HZ/50);
+ new_gfp_flags |= __GFP_NOFAIL;
+ memalloc_retry_wait(gfp_flags);
+ gfp_flags = new_gfp_flags;
goto retry_encrypt;
}
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 3db923403505..1aa26d6634fc 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -43,7 +43,6 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
-#include <linux/cleancache.h>
#include "ext4.h"
@@ -350,11 +349,6 @@ int ext4_mpage_readpages(struct inode *inode,
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
- if (fully_mapped && blocks_per_page == 1 &&
- !PageUptodate(page) && cleancache_get_page(page) == 0) {
- SetPageUptodate(page);
- goto confused;
- }
/*
* This page will go to BIO. Do we need to send this
@@ -371,15 +365,15 @@ int ext4_mpage_readpages(struct inode *inode,
* bio_alloc will _always_ be able to allocate a bio if
* __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset().
*/
- bio = bio_alloc(GFP_KERNEL, bio_max_segs(nr_pages));
+ bio = bio_alloc(bdev, bio_max_segs(nr_pages),
+ REQ_OP_READ, GFP_KERNEL);
fscrypt_set_bio_crypt_ctx(bio, inode, next_block,
GFP_KERNEL);
ext4_set_bio_post_read_ctx(bio, inode, page->index);
- bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
bio->bi_end_io = mpage_end_io;
- bio_set_op_attrs(bio, REQ_OP_READ,
- rac ? REQ_RAHEAD : 0);
+ if (rac)
+ bio->bi_opf |= REQ_RAHEAD;
}
length = first_hole << blkbits;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ee8f02f406cb..90a941d20dff 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -14,6 +14,7 @@
#include <linux/errno.h>
#include <linux/slab.h>
+#include <linux/jiffies.h>
#include "ext4_jbd2.h"
@@ -483,7 +484,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
}
ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n",
first_cluster, first_cluster - start, count2);
- ext4_set_bits(bh->b_data, first_cluster - start, count2);
+ mb_set_bits(bh->b_data, first_cluster - start, count2);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
@@ -632,7 +633,7 @@ handle_bb:
if (overhead != 0) {
ext4_debug("mark backup superblock %#04llx (+0)\n",
start);
- ext4_set_bits(bh->b_data, 0,
+ mb_set_bits(bh->b_data, 0,
EXT4_NUM_B2C(sbi, overhead));
}
ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count),
@@ -2100,7 +2101,7 @@ retry:
*/
while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
flexbg_size)) {
- if (jiffies - last_update_time > HZ * 10) {
+ if (time_is_before_jiffies(last_update_time + HZ * 10)) {
if (last_update_time)
ext4_msg(sb, KERN_INFO,
"resized to %llu blocks",
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9a936ecbaa3b..81749eaddf4c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -39,7 +39,6 @@
#include <linux/log2.h>
#include <linux/crc16.h>
#include <linux/dax.h>
-#include <linux/cleancache.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
#include <linux/unicode.h>
@@ -1302,7 +1301,7 @@ static void ext4_put_super(struct super_block *sb)
kfree(sbi->s_blockgroup_lock);
fs_put_dax(sbi->s_daxdev);
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
utf8_unload(sb->s_encoding);
#endif
kfree(sbi);
@@ -1317,7 +1316,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
{
struct ext4_inode_info *ei;
- ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
+ ei = alloc_inode_sb(sb, ext4_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
@@ -1962,33 +1961,26 @@ static const struct mount_opts {
{Opt_err, 0, 0}
};
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
static const struct ext4_sb_encodings {
__u16 magic;
char *name;
- char *version;
+ unsigned int version;
} ext4_sb_encoding_map[] = {
- {EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"},
+ {EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)},
};
-static int ext4_sb_read_encoding(const struct ext4_super_block *es,
- const struct ext4_sb_encodings **encoding,
- __u16 *flags)
+static const struct ext4_sb_encodings *
+ext4_sb_read_encoding(const struct ext4_super_block *es)
{
__u16 magic = le16_to_cpu(es->s_encoding);
int i;
for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++)
if (magic == ext4_sb_encoding_map[i].magic)
- break;
-
- if (i >= ARRAY_SIZE(ext4_sb_encoding_map))
- return -EINVAL;
-
- *encoding = &ext4_sb_encoding_map[i];
- *flags = le16_to_cpu(es->s_encoding_flags);
+ return &ext4_sb_encoding_map[i];
- return 0;
+ return NULL;
}
#endif
@@ -2029,12 +2021,12 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb, char *arg)
#define EXT4_SPEC_s_commit_interval (1 << 16)
#define EXT4_SPEC_s_fc_debug_max_replay (1 << 17)
#define EXT4_SPEC_s_sb_block (1 << 18)
+#define EXT4_SPEC_mb_optimize_scan (1 << 19)
struct ext4_fs_context {
char *s_qf_names[EXT4_MAXQUOTAS];
char *test_dummy_enc_arg;
int s_jquota_fmt; /* Format of quota to use */
- int mb_optimize_scan;
#ifdef CONFIG_EXT4_DEBUG
int s_fc_debug_max_replay;
#endif
@@ -2053,8 +2045,8 @@ struct ext4_fs_context {
unsigned int mask_s_mount_opt;
unsigned int vals_s_mount_opt2;
unsigned int mask_s_mount_opt2;
- unsigned int vals_s_mount_flags;
- unsigned int mask_s_mount_flags;
+ unsigned long vals_s_mount_flags;
+ unsigned long mask_s_mount_flags;
unsigned int opt_flags; /* MOPT flags */
unsigned int spec;
u32 s_max_batch_time;
@@ -2157,23 +2149,36 @@ static inline void ctx_set_##name(struct ext4_fs_context *ctx, \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name |= flag; \
-} \
+}
+
+#define EXT4_CLEAR_CTX(name) \
static inline void ctx_clear_##name(struct ext4_fs_context *ctx, \
unsigned long flag) \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name &= ~flag; \
-} \
+}
+
+#define EXT4_TEST_CTX(name) \
static inline unsigned long \
ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \
{ \
return (ctx->vals_s_##name & flag); \
-} \
+}
-EXT4_SET_CTX(flags);
+EXT4_SET_CTX(flags); /* set only */
EXT4_SET_CTX(mount_opt);
+EXT4_CLEAR_CTX(mount_opt);
+EXT4_TEST_CTX(mount_opt);
EXT4_SET_CTX(mount_opt2);
-EXT4_SET_CTX(mount_flags);
+EXT4_CLEAR_CTX(mount_opt2);
+EXT4_TEST_CTX(mount_opt2);
+
+static inline void ctx_set_mount_flag(struct ext4_fs_context *ctx, int bit)
+{
+ set_bit(bit, &ctx->mask_s_mount_flags);
+ set_bit(bit, &ctx->vals_s_mount_flags);
+}
static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
@@ -2243,7 +2248,7 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
param->key);
return 0;
case Opt_abort:
- ctx_set_mount_flags(ctx, EXT4_MF_FS_ABORTED);
+ ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED);
return 0;
case Opt_i_version:
ext4_msg(NULL, KERN_WARNING, deprecated_msg, param->key, "5.20");
@@ -2459,12 +2464,17 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
ctx_clear_mount_opt(ctx, m->mount_opt);
return 0;
case Opt_mb_optimize_scan:
- if (result.int_32 != 0 && result.int_32 != 1) {
+ if (result.int_32 == 1) {
+ ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
+ ctx->spec |= EXT4_SPEC_mb_optimize_scan;
+ } else if (result.int_32 == 0) {
+ ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
+ ctx->spec |= EXT4_SPEC_mb_optimize_scan;
+ } else {
ext4_msg(NULL, KERN_WARNING,
"mb_optimize_scan should be set to 0 or 1.");
return -EINVAL;
}
- ctx->mb_optimize_scan = result.int_32;
return 0;
}
@@ -3156,8 +3166,6 @@ done:
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt, sbi->s_mount_opt2);
-
- cleancache_init_fs(sb);
return err;
}
@@ -3478,8 +3486,9 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files)
*/
static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
{
- unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS;
+ loff_t upper_limit, res = EXT4_NDIR_BLOCKS;
int meta_blocks;
+ unsigned int ppb = 1 << (bits - 2);
/*
* This is calculated to be the largest file size for a dense, block
@@ -3511,27 +3520,42 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
}
+ /* Compute how many blocks we can address by block tree */
+ res += ppb;
+ res += ppb * ppb;
+ res += ((loff_t)ppb) * ppb * ppb;
+ /* 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 -= EXT4_NDIR_BLOCKS;
/* indirect blocks */
meta_blocks = 1;
+ upper_limit -= ppb;
/* 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;
-
- res += 1LL << (bits-2);
- res += 1LL << (2*(bits-2));
- res += 1LL << (3*(bits-2));
+ if (upper_limit < ppb * ppb) {
+ meta_blocks += 1 + DIV_ROUND_UP_ULL(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_ULL(upper_limit, ppb) +
+ DIV_ROUND_UP_ULL(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;
- return (loff_t)res;
+ return res;
}
static ext4_fsblk_t descriptor_loc(struct super_block *sb,
@@ -3616,7 +3640,7 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly)
return 0;
}
-#ifndef CONFIG_UNICODE
+#if !IS_ENABLED(CONFIG_UNICODE)
if (ext4_has_feature_casefold(sb)) {
ext4_msg(sb, KERN_ERR,
"Filesystem with casefold feature cannot be "
@@ -4338,7 +4362,7 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb)
if (!sbi)
return NULL;
- sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
+ sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
@@ -4379,7 +4403,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
/* Set defaults for the variables that will be set during parsing */
ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
- ctx->mb_optimize_scan = DEFAULT_MB_OPTIMIZE_SCAN;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sectors_written_start =
@@ -4620,14 +4643,14 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
if (err < 0)
goto failed_mount;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (ext4_has_feature_casefold(sb) && !sb->s_encoding) {
const struct ext4_sb_encodings *encoding_info;
struct unicode_map *encoding;
- __u16 encoding_flags;
+ __u16 encoding_flags = le16_to_cpu(es->s_encoding_flags);
- if (ext4_sb_read_encoding(es, &encoding_info,
- &encoding_flags)) {
+ encoding_info = ext4_sb_read_encoding(es);
+ if (!encoding_info) {
ext4_msg(sb, KERN_ERR,
"Encoding requested by superblock is unknown");
goto failed_mount;
@@ -4636,15 +4659,21 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
encoding = utf8_load(encoding_info->version);
if (IS_ERR(encoding)) {
ext4_msg(sb, KERN_ERR,
- "can't mount with superblock charset: %s-%s "
+ "can't mount with superblock charset: %s-%u.%u.%u "
"not supported by the kernel. flags: 0x%x.",
- encoding_info->name, encoding_info->version,
+ encoding_info->name,
+ unicode_major(encoding_info->version),
+ unicode_minor(encoding_info->version),
+ unicode_rev(encoding_info->version),
encoding_flags);
goto failed_mount;
}
ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: "
- "%s-%s with flags 0x%hx", encoding_info->name,
- encoding_info->version?:"\b", encoding_flags);
+ "%s-%u.%u.%u with flags 0x%hx", encoding_info->name,
+ unicode_major(encoding_info->version),
+ unicode_minor(encoding_info->version),
+ unicode_rev(encoding_info->version),
+ encoding_flags);
sb->s_encoding = encoding;
sb->s_encoding_flags = encoding_flags;
@@ -4756,9 +4785,12 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
goto failed_mount;
}
- if (dax_supported(sbi->s_daxdev, sb->s_bdev, blocksize, 0,
- bdev_nr_sectors(sb->s_bdev)))
- set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+ if (sbi->s_daxdev) {
+ if (blocksize == PAGE_SIZE)
+ set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+ else
+ ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+ }
if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
if (ext4_has_feature_inline_data(sb)) {
@@ -5083,7 +5115,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
sbi->s_fc_bytes = 0;
ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
- ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+ sbi->s_fc_ineligible_tid = 0;
spin_lock_init(&sbi->s_fc_lock);
memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
sbi->s_fc_replay_state.fc_regions = NULL;
@@ -5321,12 +5353,12 @@ no_journal:
* turned off by passing "mb_optimize_scan=0". This can also be
* turned on forcefully by passing "mb_optimize_scan=1".
*/
- if (ctx->mb_optimize_scan == 1)
- set_opt2(sb, MB_OPTIMIZE_SCAN);
- else if (ctx->mb_optimize_scan == 0)
- clear_opt2(sb, MB_OPTIMIZE_SCAN);
- else if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
- set_opt2(sb, MB_OPTIMIZE_SCAN);
+ if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) {
+ if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
+ set_opt2(sb, MB_OPTIMIZE_SCAN);
+ else
+ clear_opt2(sb, MB_OPTIMIZE_SCAN);
+ }
err = ext4_mb_init(sb);
if (err) {
@@ -5515,7 +5547,7 @@ failed_mount:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
utf8_unload(sb->s_encoding);
#endif
@@ -5541,7 +5573,7 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc)
sbi = ext4_alloc_sbi(sb);
if (!sbi)
- ret = -ENOMEM;
+ return -ENOMEM;
fc->s_fs_info = sbi;
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index f61e65ae27d8..d233c24ea342 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -309,7 +309,7 @@ EXT4_ATTR_FEATURE(meta_bg_resize);
EXT4_ATTR_FEATURE(encryption);
EXT4_ATTR_FEATURE(test_dummy_encryption_v2);
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
EXT4_ATTR_FEATURE(casefold);
#endif
#ifdef CONFIG_FS_VERITY
@@ -317,7 +317,7 @@ EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
EXT4_ATTR_FEATURE(fast_commit);
-#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
+#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
EXT4_ATTR_FEATURE(encrypted_casefold);
#endif
@@ -329,7 +329,7 @@ static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(encryption),
ATTR_LIST(test_dummy_encryption_v2),
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
ATTR_LIST(casefold),
#endif
#ifdef CONFIG_FS_VERITY
@@ -337,7 +337,7 @@ static struct attribute *ext4_feat_attrs[] = {
#endif
ATTR_LIST(metadata_csum_seed),
ATTR_LIST(fast_commit),
-#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
+#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
ATTR_LIST(encrypted_casefold),
#endif
NULL,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 1e0fc1ed845b..042325349098 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2408,7 +2408,7 @@ retry_inode:
if (IS_SYNC(inode))
ext4_handle_sync(handle);
}
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle);
cleanup:
brelse(is.iloc.bh);
@@ -2486,7 +2486,7 @@ retry:
if (error == 0)
error = error2;
}
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL);
return error;
}
@@ -2920,7 +2920,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
error);
goto cleanup;
}
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle);
}
error = 0;
cleanup:
Powered by cgit, Gruvboxed by Blaster4385.