blob: 9c064727ed62978e95f27f2fe73c5e946ce672b0 [file] [log] [blame]
/*
* linux/fs/ext4/inode.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* 64-bit file support on 64-bit platforms by Jakub Jelinek
* (jj@sunsite.ms.mff.cuni.cz)
*
* Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
*/
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "truncate.h"
#include <trace/events/ext4.h>
#define MPAGE_DA_EXTENT_TAIL 0x01
static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__u16 dummy_csum = 0;
int offset = offsetof(struct ext4_inode, i_checksum_lo);
unsigned int csum_size = sizeof(dummy_csum);
csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
offset += csum_size;
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_GOOD_OLD_INODE_SIZE - offset);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
offset = offsetof(struct ext4_inode, i_checksum_hi);
csum = ext4_chksum(sbi, csum, (__u8 *)raw +
EXT4_GOOD_OLD_INODE_SIZE,
offset - EXT4_GOOD_OLD_INODE_SIZE);
if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
csum_size);
offset += csum_size;
csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
EXT4_INODE_SIZE(inode->i_sb) -
offset);
}
}
return csum;
}
static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
__u32 provided, calculated;
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
!ext4_has_metadata_csum(inode->i_sb))
return 1;
provided = le16_to_cpu(raw->i_checksum_lo);
calculated = ext4_inode_csum(inode, raw, ei);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16;
else
calculated &= 0xFFFF;
return provided == calculated;
}
static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
__u32 csum;
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_LINUX) ||
!ext4_has_metadata_csum(inode->i_sb))
return;
csum = ext4_inode_csum(inode, raw, ei);
raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
raw->i_checksum_hi = cpu_to_le16(csum >> 16);
}
static inline int ext4_begin_ordered_truncate(struct inode *inode,
loff_t new_size)
{
trace_ext4_begin_ordered_truncate(inode, new_size);
/*
* If jinode is zero, then we never opened the file for
* writing, so there's no need to call
* jbd2_journal_begin_ordered_truncate() since there's no
* outstanding writes we need to flush.
*/
if (!EXT4_I(inode)->jinode)
return 0;
return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode,
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_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
int pextents);
/*
* Test whether an inode is a fast symlink.
*/
int ext4_inode_is_fast_symlink(struct inode *inode)
{
int ea_blocks = EXT4_I(inode)->i_file_acl ?
EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
if (ext4_has_inline_data(inode))
return 0;
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
/*
* Restart the transaction associated with *handle. This does a commit,
* so before we call here everything must be consistently dirtied against
* this transaction.
*/
int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
int nblocks)
{
int ret;
/*
* 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.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
up_write(&EXT4_I(inode)->i_data_sem);
ret = ext4_journal_restart(handle, nblocks);
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
return ret;
}
/*
* Called at the last iput() if i_nlink is zero.
*/
void ext4_evict_inode(struct inode *inode)
{
handle_t *handle;
int err;
trace_ext4_evict_inode(inode);
if (inode->i_nlink) {
/*
* When journalling data dirty buffers are tracked only in the
* 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()
* (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
* is reaped and thus user could see stale data if he tries to
* read them before the transaction is checkpointed. So be
* careful and force everything to disk here... We use
* ei->i_datasync_tid to store the newest transaction
* containing inode's data.
*
* Note that directories do not have this problem because they
* don't use page cache.
*/
if (inode->i_ino != EXT4_JOURNAL_INO &&
ext4_should_journal_data(inode) &&
(S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
jbd2_complete_transaction(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages_final(&inode->i_data);
goto no_delete;
}
if (is_bad_inode(inode))
goto no_delete;
dquot_initialize(inode);
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages_final(&inode->i_data);
/*
* Protect us against freezing - iput() caller didn't have to have any
* protection against it
*/
sb_start_intwrite(inode->i_sb);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
ext4_blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
* cleaned up.
*/
ext4_orphan_del(NULL, inode);
sb_end_intwrite(inode->i_sb);
goto no_delete;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_warning(inode->i_sb,
"couldn't mark inode dirty (err %d)", err);
goto stop_handle;
}
if (inode->i_blocks)
ext4_truncate(inode);
/*
* ext4_ext_truncate() doesn't reserve any slop when it
* restarts journal transactions; therefore there may not be
* enough credits left in the handle to remove the inode from
* the orphan list and set the dtime field.
*/
if (!ext4_handle_has_enough_credits(handle, 3)) {
err = ext4_journal_extend(handle, 3);
if (err > 0)
err = ext4_journal_restart(handle, 3);
if (err != 0) {
ext4_warning(inode->i_sb,
"couldn't extend journal (err %d)", err);
stop_handle:
ext4_journal_stop(handle);
ext4_orphan_del(NULL, inode);
sb_end_intwrite(inode->i_sb);
goto no_delete;
}
}
/*
* Kill off the orphan record which ext4_truncate created.
* AKPM: I think this can be inside the above `if'.
* Note that ext4_orphan_del() has to be able to cope with the
* deletion of a non-existent orphan - this is because we don't
* know if ext4_truncate() actually created an orphan record.
* (Well, we could do this if we need to, but heck - it works)
*/
ext4_orphan_del(handle, inode);
EXT4_I(inode)->i_dtime = get_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
if (ext4_mark_inode_dirty(handle, inode))
/* If that failed, just do the required in-core inode clear. */
ext4_clear_inode(inode);
else
ext4_free_inode(handle, inode);
ext4_journal_stop(handle);
sb_end_intwrite(inode->i_sb);
return;
no_delete:
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
#ifdef CONFIG_QUOTA
qsize_t *ext4_get_reserved_space(struct inode *inode)
{
return &EXT4_I(inode)->i_reserved_quota;
}
#endif
/*
* Called with i_data_sem down, which is important since we can call
* ext4_discard_preallocations() from here.
*/
void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_warning(inode->i_sb, "%s: ino %lu, used %d "
"with only %d reserved data blocks",
__func__, inode->i_ino, used,
ei->i_reserved_data_blocks);
WARN_ON(1);
used = ei->i_reserved_data_blocks;
}
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
percpu_counter_sub(&sbi->s_dirtyclusters_counter, used);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/* Update quota subsystem for data blocks */
if (quota_claim)
dquot_claim_block(inode, EXT4_C2B(sbi, used));
else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
* not re-claim the quota for fallocated blocks.
*/
dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
* If we have done all the pending block allocations and if
* there aren't any writers on the inode, we can discard the
* inode's preallocations.
*/
if ((ei->i_reserved_data_blocks == 0) &&
(atomic_read(&inode->i_writecount) == 0))
ext4_discard_preallocations(inode);
}
static int __check_block_validity(struct inode *inode, const char *func,
unsigned int line,
struct ext4_map_blocks *map)
{
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
map->m_len)) {
ext4_error_inode(inode, func, line, map->m_pblk,
"lblock %lu mapped to illegal pblock "
"(length %d)", (unsigned long) map->m_lblk,
map->m_len);
return -EFSCORRUPTED;
}
return 0;
}
int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
ext4_lblk_t len)
{
int ret;
if (ext4_encrypted_inode(inode))
return fscrypt_zeroout_range(inode, lblk, pblk, len);
ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
if (ret > 0)
ret = 0;
return ret;
}
#define check_block_validity(inode, map) \
__check_block_validity((inode), __func__, __LINE__, (map))
#ifdef ES_AGGRESSIVE_TEST
static void ext4_map_blocks_es_recheck(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *es_map,
struct ext4_map_blocks *map,
int flags)
{
int retval;
map->m_flags = 0;
/*
* There is a race window that the result is not the same.
* e.g. xfstests #223 when dioread_nolock enables. The reason
* is that we lookup a block mapping in extent status tree with
* out taking i_data_sem. So at the time the unwritten extent
* could be converted.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
}
up_read((&EXT4_I(inode)->i_data_sem));
/*
* We don't check m_len because extent will be collpased in status
* tree. So the m_len might not equal.
*/
if (es_map->m_lblk != map->m_lblk ||
es_map->m_flags != map->m_flags ||
es_map->m_pblk != map->m_pblk) {
printk("ES cache assertion failed for inode: %lu "
"es_cached ex [%d/%d/%llu/%x] != "
"found ex [%d/%d/%llu/%x] retval %d flags %x\n",
inode->i_ino, es_map->m_lblk, es_map->m_len,
es_map->m_pblk, es_map->m_flags, map->m_lblk,
map->m_len, map->m_pblk, map->m_flags,
retval, flags);
}
}
#endif /* ES_AGGRESSIVE_TEST */
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
* Otherwise it takes the write lock of the i_data_sem and allocate blocks
* and store the allocated blocks in the result buffer head and mark it
* mapped.
*
* If file type is extents based, it will call ext4_ext_map_blocks(),
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
* On success, it returns the number of blocks being mapped or allocated. if
* create==0 and the blocks are pre-allocated and unwritten, the resulting @map
* is marked as unwritten. If the create == 1, it will mark @map as mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
* that case, @map is returned as unmapped but we still do fill map->m_len to
* indicate the length of a hole starting at map->m_lblk.
*
* It returns the error in case of allocation failure.
*/
int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct extent_status es;
int retval;
int ret = 0;
#ifdef ES_AGGRESSIVE_TEST
struct ext4_map_blocks orig_map;
memcpy(&orig_map, map, sizeof(*map));
#endif
map->m_flags = 0;
ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
/*
* ext4_map_blocks returns an int, and m_len is an unsigned int
*/
if (unlikely(map->m_len > INT_MAX))
map->m_len = INT_MAX;
/* We can handle the block number less than EXT_MAX_BLOCKS */
if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
return -EFSCORRUPTED;
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
map->m_pblk = ext4_es_pblock(&es) +
map->m_lblk - es.es_lblk;
map->m_flags |= ext4_es_is_written(&es) ?
EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
retval = es.es_len - (map->m_lblk - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
map->m_pblk = 0;
retval = es.es_len - (map->m_lblk - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
retval = 0;
} else {
BUG_ON(1);
}
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(handle, inode, map,
&orig_map, flags);
#endif
goto found;
}
/*
* Try to see if we can get the block without requesting a new
* file system block.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
}
if (retval > 0) {
unsigned int status;
if (unlikely(retval != map->m_len)) {
ext4_warning(inode->i_sb,
"ES len assertion failed for inode "
"%lu: retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
!(status & EXTENT_STATUS_WRITTEN) &&
ext4_find_delalloc_range(inode, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
ret = ext4_es_insert_extent(inode, map->m_lblk,
map->m_len, map->m_pblk, status);
if (ret < 0)
retval = ret;
}
up_read((&EXT4_I(inode)->i_data_sem));
found:
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
/* If it is only a block(s) look up */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
return retval;
/*
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
* ext4_ext_get_block() returns the create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
/*
* If we need to convert extent to unwritten
* we continue and do the actual work in
* ext4_ext_map_blocks()
*/
if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
return retval;
/*
* Here we clear m_flags because after allocating an new extent,
* it will be set again.
*/
map->m_flags &= ~EXT4_MAP_FLAGS;
/*
* New blocks allocate and/or writing to unwritten extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_block()
* with create == 1 flag.
*/
down_write(&EXT4_I(inode)->i_data_sem);
/*
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags);
if (retval > 0 && map->m_flags & EXT4_MAP_NEW) {
/*
* We allocated new blocks which will result in
* i_data's format changing. Force the migrate
* to fail by clearing migrate flags
*/
ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
/*
* Update reserved blocks/metadata blocks after successful
* block allocation which had been deferred till now. We don't
* support fallocate for non extent files. So we can update
* reserve space here.
*/
if ((retval > 0) &&
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
if (retval > 0) {
unsigned int status;
if (unlikely(retval != map->m_len)) {
ext4_warning(inode->i_sb,
"ES len assertion failed for inode "
"%lu: retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
/*
* We have to zeroout blocks before inserting them into extent
* status tree. Otherwise someone could look them up there and
* use them before they are really zeroed. We also have to
* unmap metadata before zeroing as otherwise writeback can
* overwrite zeros with stale data from block device.
*/
if (flags & EXT4_GET_BLOCKS_ZERO &&
map->m_flags & EXT4_MAP_MAPPED &&
map->m_flags & EXT4_MAP_NEW) {
ext4_lblk_t i;
for (i = 0; i < map->m_len; i++) {
unmap_underlying_metadata(inode->i_sb->s_bdev,
map->m_pblk + i);
}
ret = ext4_issue_zeroout(inode, map->m_lblk,
map->m_pblk, map->m_len);
if (ret) {
retval = ret;
goto out_sem;
}
}
/*
* If the extent has been zeroed out, we don't need to update
* extent status tree.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
if (ext4_es_is_written(&es))
goto out_sem;
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
!(status & EXTENT_STATUS_WRITTEN) &&
ext4_find_delalloc_range(inode, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status);
if (ret < 0) {
retval = ret;
goto out_sem;
}
}
out_sem:
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
/*
* Inodes with freshly allocated blocks where contents will be
* visible after transaction commit must be on transaction's
* ordered data list.
*/
if (map->m_flags & EXT4_MAP_NEW &&
!(map->m_flags & EXT4_MAP_UNWRITTEN) &&
!(flags & EXT4_GET_BLOCKS_ZERO) &&
!IS_NOQUOTA(inode) &&
ext4_should_order_data(inode)) {
if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
ret = ext4_jbd2_inode_add_wait(handle, inode);
else
ret = ext4_jbd2_inode_add_write(handle, inode);
if (ret)
return ret;
}
}
return retval;
}
/*
* Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
* we have to be careful as someone else may be manipulating b_state as well.
*/
static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
{
unsigned long old_state;
unsigned long new_state;
flags &= EXT4_MAP_FLAGS;
/* Dummy buffer_head? Set non-atomically. */
if (!bh->b_page) {
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
return;
}
/*
* Someone else may be modifying b_state. Be careful! This is ugly but
* once we get rid of using bh as a container for mapping information
* to pass to / from get_block functions, this can go away.
*/
do {
old_state = READ_ONCE(bh->b_state);
new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
} while (unlikely(
cmpxchg(&bh->b_state, old_state, new_state) != old_state));
}
static int _ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int flags)
{
struct ext4_map_blocks map;
int ret = 0;
if (ext4_has_inline_data(inode))
return -ERANGE;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map,
flags);
if (ret > 0) {
map_bh(bh, inode->i_sb, map.m_pblk);
ext4_update_bh_state(bh, map.m_flags);
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
ret = 0;
}
return ret;
}
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
return _ext4_get_block(inode, iblock, bh,
create ? EXT4_GET_BLOCKS_CREATE : 0);
}
/*
* Get block function used when preparing for buffered write if we require
* creating an unwritten extent if blocks haven't been allocated. The extent
* will be converted to written after the IO is complete.
*/
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n",
inode->i_ino, create);
return _ext4_get_block(inode, iblock, bh_result,
EXT4_GET_BLOCKS_IO_CREATE_EXT);
}
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
/*
* Get blocks function for the cases that need to start a transaction -
* generally difference cases of direct IO and DAX IO. It also handles retries
* in case of ENOSPC.
*/
static int ext4_get_block_trans(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int flags)
{
int dio_credits;
handle_t *handle;
int retries = 0;
int ret;
/* Trim mapping request to maximum we can map at once for DIO */
if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS)
bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits;
dio_credits = ext4_chunk_trans_blocks(inode,
bh_result->b_size >> inode->i_blkbits);
retry:
handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = _ext4_get_block(inode, iblock, bh_result, flags);
ext4_journal_stop(handle);
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
return ret;
}
/* Get block function for DIO reads and writes to inodes without extents */
int ext4_dio_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
/* We don't expect handle for direct IO */
WARN_ON_ONCE(ext4_journal_current_handle());
if (!create)
return _ext4_get_block(inode, iblock, bh, 0);
return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
}
/*
* Get block function for AIO DIO writes when we create unwritten extent if
* blocks are not allocated yet. The extent will be converted to written
* after IO is complete.
*/
static int ext4_dio_get_block_unwritten_async(struct inode *inode,
sector_t iblock, struct buffer_head *bh_result, int create)
{
int ret;
/* We don't expect handle for direct IO */
WARN_ON_ONCE(ext4_journal_current_handle());
ret = ext4_get_block_trans(inode, iblock, bh_result,
EXT4_GET_BLOCKS_IO_CREATE_EXT);
/*
* When doing DIO using unwritten extents, we need io_end to convert
* unwritten extents to written on IO completion. We allocate io_end
* once we spot unwritten extent and store it in b_private. Generic
* DIO code keeps b_private set and furthermore passes the value to
* our completion callback in 'private' argument.
*/
if (!ret && buffer_unwritten(bh_result)) {
if (!bh_result->b_private) {
ext4_io_end_t *io_end;
io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!io_end)
return -ENOMEM;
bh_result->b_private = io_end;
ext4_set_io_unwritten_flag(inode, io_end);
}
set_buffer_defer_completion(bh_result);
}
return ret;
}
/*
* Get block function for non-AIO DIO writes when we create unwritten extent if
* blocks are not allocated yet. The extent will be converted to written
* after IO is complete from ext4_ext_direct_IO() function.
*/
static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
sector_t iblock, struct buffer_head *bh_result, int create)
{
int ret;
/* We don't expect handle for direct IO */
WARN_ON_ONCE(ext4_journal_current_handle());
ret = ext4_get_block_trans(inode, iblock, bh_result,
EXT4_GET_BLOCKS_IO_CREATE_EXT);
/*
* Mark inode as having pending DIO writes to unwritten extents.
* ext4_ext_direct_IO() checks this flag and converts extents to
* written.
*/
if (!ret && buffer_unwritten(bh_result))
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
return ret;
}
static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret;
ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n",
inode->i_ino, create);
/* We don't expect handle for direct IO */
WARN_ON_ONCE(ext4_journal_current_handle());
ret = _ext4_get_block(inode, iblock, bh_result, 0);
/*
* Blocks should have been preallocated! ext4_file_write_iter() checks
* that.
*/
WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result));
return ret;
}
/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int map_flags)
{
struct ext4_map_blocks map;
struct buffer_head *bh;
int create = map_flags & EXT4_GET_BLOCKS_CREATE;
int err;
J_ASSERT(handle != NULL || create == 0);
map.m_lblk = block;
map.m_len = 1;
err = ext4_map_blocks(handle, inode, &map, map_flags);
if (err == 0)
return create ? ERR_PTR(-ENOSPC) : NULL;
if (err < 0)
return ERR_PTR(err);
bh = sb_getblk(inode->i_sb, map.m_pblk);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
if (map.m_flags & EXT4_MAP_NEW) {
J_ASSERT(create != 0);
J_ASSERT(handle != NULL);
/*
* Now that we do not always journal data, we should
* keep in mind whether this should always journal the
* new buffer as metadata. For now, regular file
* writes use ext4_get_block instead, so it's not a
* problem.
*/
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
err = ext4_journal_get_create_access(handle, bh);
if (unlikely(err)) {
unlock_buffer(bh);
goto errout;
}
if (!buffer_uptodate(bh)) {
memset(bh->b_data, 0, inode->i_sb->s_blocksize);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (unlikely(err))
goto errout;
} else
BUFFER_TRACE(bh, "not a new buffer");
return bh;
errout:
brelse(bh);
return ERR_PTR(err);
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int map_flags)
{
struct buffer_head *bh;
bh = ext4_getblk(handle, inode, block, map_flags);
if (IS_ERR(bh))
return bh;
if (!bh || buffer_uptodate(bh))
return bh;
ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
put_bh(bh);
return ERR_PTR(-EIO);
}
int ext4_walk_page_buffers(handle_t *handle,
struct buffer_head *head,
unsigned from,
unsigned to,
int *partial,
int (*fn)(handle_t *handle,
struct buffer_head *bh))
{
struct buffer_head *bh;
unsigned block_start, block_end;
unsigned blocksize = head->b_size;
int err, ret = 0;
struct buffer_head *next;
for (bh = head, block_start = 0;
ret == 0 && (bh != head || !block_start);
block_start = block_end, bh = next) {
next = bh->b_this_page;
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (partial && !buffer_uptodate(bh))
*partial = 1;
continue;
}
err = (*fn)(handle, bh);
if (!ret)
ret = err;
}
return ret;
}
/*
* To preserve ordering, it is essential that the hole instantiation and
* the data write be encapsulated in a single transaction. We cannot
* close off a transaction and start a new one between the ext4_get_block()
* and the commit_write(). So doing the jbd2_journal_start at the start of
* prepare_write() is the right place.
*
* Also, this function can nest inside ext4_writepage(). In that case, we
* *know* that ext4_writepage() has generated enough buffer credits to do the
* whole page. So we won't block on the journal in that case, which is good,
* because the caller may be PF_MEMALLOC.
*
* By accident, ext4 can be reentered when a transaction is open via
* quota file writes. If we were to commit the transaction while thus
* reentered, there can be a deadlock - we would be holding a quota
* lock, and the commit would never complete if another thread had a
* transaction open and was blocking on the quota lock - a ranking
* violation.
*
* So what we do is to rely on the fact that jbd2_journal_stop/journal_start
* will _not_ run commit under these circumstances because handle->h_ref
* is elevated. We'll still have enough credits for the tiny quotafile
* write.
*/
int do_journal_get_write_access(handle_t *handle,
struct buffer_head *bh)
{
int dirty = buffer_dirty(bh);
int ret;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
/*
* __block_write_begin() could have dirtied some buffers. Clean
* the dirty bit as jbd2_journal_get_write_access() could complain
* otherwise about fs integrity issues. Setting of the dirty bit
* by __block_write_begin() isn't a real problem here as we clear
* the bit before releasing a page lock and thus writeback cannot
* ever write the buffer.
*/
if (dirty)
clear_buffer_dirty(bh);
BUFFER_TRACE(bh, "get write access");
ret = ext4_journal_get_write_access(handle, bh);
if (!ret && dirty)
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
return ret;
}
#ifdef CONFIG_EXT4_FS_ENCRYPTION
static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
get_block_t *get_block)
{
unsigned from = pos & (PAGE_SIZE - 1);
unsigned to = from + len;
struct inode *inode = page->mapping->host;
unsigned block_start, block_end;
sector_t block;
int err = 0;
unsigned blocksize = inode->i_sb->s_blocksize;
unsigned bbits;
struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
bool decrypt = false;
BUG_ON(!PageLocked(page));
BUG_ON(from > PAGE_SIZE);
BUG_ON(to > PAGE_SIZE);
BUG_ON(from > to);
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
head = page_buffers(page);
bbits = ilog2(blocksize);
block = (sector_t)page->index << (PAGE_SHIFT - bbits);
for (bh = head, block_start = 0; bh != head || !block_start;
block++, block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (PageUptodate(page)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
}
continue;
}
if (buffer_new(bh))
clear_buffer_new(bh);
if (!buffer_mapped(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
break;
if (buffer_new(bh)) {
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
if (PageUptodate(page)) {
clear_buffer_new(bh);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
continue;
}
if (block_end > to || block_start < from)
zero_user_segments(page, to, block_end,
block_start, from);
continue;
}
}
if (PageUptodate(page)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
continue;
}
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
ll_rw_block(REQ_OP_READ, 0, 1, &bh);
*wait_bh++ = bh;
decrypt = ext4_encrypted_inode(inode) &&
S_ISREG(inode->i_mode);
}
}
/*
* If we issued read requests, let them complete.
*/
while (wait_bh > wait) {
wait_on_buffer(*--wait_bh);
if (!buffer_uptodate(*wait_bh))
err = -EIO;
}
if (unlikely(err))
page_zero_new_buffers(page, from, to);
else if (decrypt)
err = fscrypt_decrypt_page(page);
return err;
}
#endif
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
int ret, needed_blocks;
handle_t *handle;
int retries = 0;
struct page *page;
pgoff_t index;
unsigned from, to;
trace_ext4_write_begin(inode, pos, len, flags);
/*
* Reserve one block more for addition to orphan list in case
* we allocate blocks but write fails for some reason
*/
needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
index = pos >> PAGE_SHIFT;
from = pos & (PAGE_SIZE - 1);
to = from + len;
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
flags, pagep);
if (ret < 0)
return ret;
if (ret == 1)
return 0;
}
/*
* grab_cache_page_write_begin() can take a long time if the
* system is thrashing due to memory pressure, or if the page
* is being written back. So grab it first before we start
* the transaction handle. This also allows us to allocate
* the page (if needed) without using GFP_NOFS.
*/
retry_grab:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
unlock_page(page);
retry_journal:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
put_page(page);
return PTR_ERR(handle);
}
lock_page(page);
if (page->mapping != mapping) {
/* The page got truncated from under us */
unlock_page(page);
put_page(page);
ext4_journal_stop(handle);
goto retry_grab;
}
/* In case writeback began while the page was unlocked */
wait_for_stable_page(page);
#ifdef CONFIG_EXT4_FS_ENCRYPTION
if (ext4_should_dioread_nolock(inode))
ret = ext4_block_write_begin(page, pos, len,
ext4_get_block_unwritten);
else
ret = ext4_block_write_begin(page, pos, len,
ext4_get_block);
#else
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(page, pos, len,
ext4_get_block_unwritten);
else
ret = __block_write_begin(page, pos, len, ext4_get_block);
#endif
if (!ret && ext4_should_journal_data(inode)) {
ret = ext4_walk_page_buffers(handle, page_buffers(page),
from, to, NULL,
do_journal_get_write_access);
}
if (ret) {
unlock_page(page);
/*
* __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.
*
* Add inode to orphan list in case we crash before
* truncate finishes
*/
if (pos + len > inode->i_size && ext4_can_truncate(inode))
ext4_orphan_add(handle, inode);
ext4_journal_stop(handle);
if (pos + len > inode->i_size) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
* make sure the inode is removed from the
* orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_journal;
put_page(page);
return ret;
}
*pagep = page;
return ret;
}
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
int ret;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
clear_buffer_meta(bh);
clear_buffer_prio(bh);
return ret;
}
/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
*
* ext4 never places buffers on inode->i_mapping->private_list. metadata
* buffers are managed internally.
*/
static int ext4_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int i_size_changed = 0;
trace_ext4_write_end(inode, pos, len, copied);
if (ext4_has_inline_data(inode)) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
if (ret < 0)
goto errout;
copied = ret;
} else
copied = block_write_end(file, mapping, pos,
len, copied, page, fsdata);
/*
* it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
*/
i_size_changed = ext4_update_inode_size(inode, pos + copied);
unlock_page(page);
put_page(page);
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
/*
* Don't mark the inode dirty under page lock. First, it unnecessarily
* makes the holding time of page lock longer. Second, it forces lock
* ordering of page lock and transaction start for journaling
* filesystems.
*/
if (i_size_changed)
ext4_mark_inode_dirty(handle, inode);
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
errout:
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
/*
* This is a private version of page_zero_new_buffers() which doesn't
* set the buffer to be dirty, since in data=journalled mode we need
* to call ext4_handle_dirty_metadata() instead.
*/
static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
{
unsigned int block_start = 0, block_end;
struct buffer_head *head, *bh;
bh = head = page_buffers(page);
do {
block_end = block_start + bh->b_size;
if (buffer_new(bh)) {
if (block_end > from && block_start < to) {
if (!PageUptodate(page)) {
unsigned start, size;
start = max(from, block_start);
size = min(to, block_end) - start;
zero_user(page, start, size);
set_buffer_uptodate(bh);
}
clear_buffer_new(bh);
}
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
}
static int ext4_journalled_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
int size_changed = 0;
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_SIZE - 1);
to = from + len;
BUG_ON(!ext4_handle_valid(handle));
if (ext4_has_inline_data(inode))
copied = ext4_write_inline_data_end(inode, pos, len,
copied, page);
else {
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
zero_new_buffers(page, from+copied, to);
}
ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
}
size_changed = ext4_update_inode_size(inode, pos + copied);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
unlock_page(page);
put_page(page);
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
if (size_changed) {
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
}
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
/*
* Reserve space for a single cluster
*/
static int ext4_da_reserve_space(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
int ret;
/*
* We will charge metadata quota at writeout time; this saves
* us from metadata over-estimation, though we may go over by
* a small amount in the end. Here we just reserve for data.
*/
ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
if (ret)
return ret;
spin_lock(&ei->i_block_reservation_lock);
if (ext4_claim_free_clusters(sbi, 1, 0)) {
spin_unlock(&ei->i_block_reservation_lock);
dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
return -ENOSPC;
}
ei->i_reserved_data_blocks++;
trace_ext4_da_reserve_space(inode);
spin_unlock(&ei->i_block_reservation_lock);
return 0; /* success */
}
static void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
if (!to_free)
return; /* Nothing to release, exit */
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
trace_ext4_da_release_space(inode, to_free);
if (unlikely(to_free > ei->i_reserved_data_blocks)) {
/*
* if there aren't enough reserved blocks, then the
* counter is messed up somewhere. Since this
* function is called from invalidate page, it's
* harmless to return without any action.
*/
ext4_warning(inode->i_sb, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
"data blocks", inode->i_ino, to_free,
ei->i_reserved_data_blocks);
WARN_ON(1);
to_free = ei->i_reserved_data_blocks;
}
ei->i_reserved_data_blocks -= to_free;
/* update fs dirty data blocks counter */
percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
static void ext4_da_page_release_reservation(struct page *page,
unsigned int offset,
unsigned int length)
{
int to_release = 0, contiguous_blks = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
struct inode *inode = page->mapping->host;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned int stop = offset + length;
int num_clusters;
ext4_fsblk_t lblk;
BUG_ON(stop > PAGE_SIZE || stop < length);
head = page_buffers(page);
bh = head;
do {
unsigned int next_off = curr_off + bh->b_size;
if (next_off > stop)
break;
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
contiguous_blks++;
clear_buffer_delay(bh);
} else if (contiguous_blks) {
lblk = page->index <<
(PAGE_SHIFT - inode->i_blkbits);
lblk += (curr_off >> inode->i_blkbits) -
contiguous_blks;
ext4_es_remove_extent(inode, lblk, contiguous_blks);
contiguous_blks = 0;
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
if (contiguous_blks) {
lblk = page->index << (PAGE_SHIFT - inode->i_blkbits);
lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
ext4_es_remove_extent(inode, lblk, contiguous_blks);
}
/* If we have released all the blocks belonging to a cluster, then we
* need to release the reserved space for that cluster. */
num_clusters = EXT4_NUM_B2C(sbi, to_release);
while (num_clusters > 0) {
lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) +
((num_clusters - 1) << sbi->s_cluster_bits);
if (sbi->s_cluster_ratio == 1 ||
!ext4_find_delalloc_cluster(inode, lblk))
ext4_da_release_space(inode, 1);
num_clusters--;
}
}
/*
* Delayed allocation stuff
*/
struct mpage_da_data {
struct inode *inode;
struct writeback_control *wbc;
pgoff_t first_page; /* The first page to write */
pgoff_t next_page; /* Current page to examine */
pgoff_t last_page; /* Last page to examine */
/*
* Extent to map - this can be after first_page because that can be
* fully mapped. We somewhat abuse m_flags to store whether the extent
* is delalloc or unwritten.
*/
struct ext4_map_blocks map;
struct ext4_io_submit io_submit; /* IO submission data */
};
static void mpage_release_unused_pages(struct mpage_da_data *mpd,
bool invalidate)
{
int nr_pages, i;
pgoff_t index, end;
struct pagevec pvec;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
/* This is necessary when next_page == 0. */
if (mpd->first_page >= mpd->next_page)
return;
index = mpd->first_page;
end = mpd->next_page - 1;
if (invalidate) {
ext4_lblk_t start, last;
start = index << (PAGE_SHIFT - inode->i_blkbits);
last = end << (PAGE_SHIFT - inode->i_blkbits);
ext4_es_remove_extent(inode, start, last - start + 1);
}
pagevec_init(&pvec, 0);
while (index <= end) {
nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (page->index > end)
break;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
if (invalidate) {
if (page_mapped(page))
clear_page_dirty_for_io(page);
block_invalidatepage(page, 0, PAGE_SIZE);
ClearPageUptodate(page);
}
unlock_page(page);
}
index = pvec.pages[nr_pages - 1]->index + 1;
pagevec_release(&pvec);
}
}
static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld",
EXT4_C2B(EXT4_SB(inode->i_sb),
ext4_count_free_clusters(sb)));
ext4_msg(sb, KERN_CRIT, "Free/Dirty block details");
ext4_msg(sb, KERN_CRIT, "free_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_freeclusters_counter)));
ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld",
(long long) EXT4_C2B(EXT4_SB(sb),
percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
ext4_msg(sb, KERN_CRIT, "Block reservation details");
ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u",
ei->i_reserved_data_blocks);
return;
}
static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
{
return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
}
/*
* This function is grabs code from the very beginning of
* ext4_map_blocks, but assumes that the caller is from delayed write
* time. This function looks up the requested blocks and sets the
* buffer delay bit under the protection of i_data_sem.
*/
static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
struct ext4_map_blocks *map,
struct buffer_head *bh)
{
struct extent_status es;
int retval;
sector_t invalid_block = ~((sector_t) 0xffff);
#ifdef ES_AGGRESSIVE_TEST
struct ext4_map_blocks orig_map;
memcpy(&orig_map, map, sizeof(*map));
#endif
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
invalid_block = ~0;
map->m_flags = 0;
ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
"logical block %lu\n", inode->i_ino, map->m_len,
(unsigned long) map->m_lblk);
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, iblock, &es)) {
if (ext4_es_is_hole(&es)) {
retval = 0;
down_read(&EXT4_I(inode)->i_data_sem);
goto add_delayed;
}
/*
* Delayed extent could be allocated by fallocate.
* So we need to check it.
*/
if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
return 0;
}
map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
retval = es.es_len - (iblock - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
map->m_len = retval;
if (ext4_es_is_written(&es))
map->m_flags |= EXT4_MAP_MAPPED;
else if (ext4_es_is_unwritten(&es))
map->m_flags |= EXT4_MAP_UNWRITTEN;
else
BUG_ON(1);
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
#endif
return retval;
}
/*
* Try to see if we can get the block without requesting a new
* file system block.
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_has_inline_data(inode))
retval = 0;
else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
retval = ext4_ext_map_blocks(NULL, inode, map, 0);
else
retval = ext4_ind_map_blocks(NULL, inode, map, 0);
add_delayed:
if (retval == 0) {
int ret;
/*
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
/*
* If the block was allocated from previously allocated cluster,
* then we don't need to reserve it again. However we still need
* to reserve metadata for every block we're going to write.
*/
if (EXT4_SB(inode->i_sb)->s_cluster_ratio == 1 ||
!ext4_find_delalloc_cluster(inode, map->m_lblk)) {
ret = ext4_da_reserve_space(inode);
if (ret) {
/* not enough space to reserve */
retval = ret;
goto out_unlock;
}
}
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
~0, EXTENT_STATUS_DELAYED);
if (ret) {
retval = ret;
goto out_unlock;
}
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
} else if (retval > 0) {
int ret;
unsigned int status;
if (unlikely(retval != map->m_len)) {
ext4_warning(inode->i_sb,
"ES len assertion failed for inode "
"%lu: retval %d != map->m_len %d",
inode->i_ino, retval, map->m_len);
WARN_ON(1);
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status);
if (ret != 0)
retval = ret;
}
out_unlock:
up_read((&EXT4_I(inode)->i_data_sem));
return retval;
}
/*
* This is a special get_block_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
*
* For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
* We also have b_blocknr = -1 and b_bdev initialized properly
*
* For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
* We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
* initialized properly.
*/
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
struct ext4_map_blocks map;
int ret = 0;
BUG_ON(create == 0);
BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
map.m_lblk = iblock;
map.m_len = 1;
/*
* first, we need to know whether the block is allocated already
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
ret = ext4_da_map_blocks(inode, iblock, &map, bh);
if (ret <= 0)
return ret;
map_bh(bh, inode->i_sb, map.m_pblk);
ext4_update_bh_state(bh, map.m_flags);
if (buffer_unwritten(bh)) {
/* A delayed write to unwritten bh should be marked
* new and mapped. Mapped ensures that we don't do
* get_block multiple times when we write to the same
* offset and new ensures that we do proper zero out
* for partial write.
*/
set_buffer_new(bh);
set_buffer_mapped(bh);
}
return 0;
}
static int bget_one(handle_t *handle, struct buffer_head *bh)
{
get_bh(bh);
return 0;
}
static int bput_one(handle_t *handle, struct buffer_head *bh)
{
put_bh(bh);
return 0;
}
static int __ext4_journalled_writepage(struct page *page,
unsigned int len)
{
struct address_space *mapping = page->mapping;
struct inode *inode = mapping->host;
struct buffer_head *page_bufs = NULL;
handle_t *handle = NULL;
int ret = 0, err = 0;
int inline_data = ext4_has_inline_data(inode);
struct buffer_head *inode_bh = NULL;
ClearPageChecked(page);
if (inline_data) {
BUG_ON(page->index != 0);
BUG_ON(len > ext4_get_max_inline_size(inode));
inode_bh = ext4_journalled_write_inline_data(inode, len, page);
if (inode_bh == NULL)
goto out;
} else {
page_bufs = page_buffers(page);
if (!page_bufs) {
BUG();
goto out;
}
ext4_walk_page_buffers(handle, page_bufs, 0, len,
NULL, bget_one);
}
/*
* We need to release the page lock before we start the
* journal, so grab a reference so the page won't disappear
* out from under us.
*/
get_page(page);
unlock_page(page);
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
put_page(page);
goto out_no_pagelock;
}
BUG_ON(!ext4_handle_valid(handle));
lock_page(page);
put_page(page);
if (page->mapping != mapping) {
/* The page got truncated from under us */
ext4_journal_stop(handle);
ret = 0;
goto out;
}
if (inline_data) {
BUFFER_TRACE(inode_bh, "get write access");
ret = ext4_journal_get_write_access(handle, inode_bh);
err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
} else {
ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
err = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL,
write_end_fn);
}
if (ret == 0)
ret = err;
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
if (!ext4_has_inline_data(inode))
ext4_walk_page_buffers(NULL, page_bufs, 0, len,
NULL, bput_one);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
unlock_page(page);
out_no_pagelock:
brelse(inode_bh);
return ret;
}
/*
* Note that we don't need to start a transaction unless we're journaling data
* because we should have holes filled from ext4_page_mkwrite(). We even don't
* need to file the inode to the transaction's list in ordered mode because if
* we are writing back data added by write(), the inode is already there and if
* we are writing back data modified via mmap(), no one guarantees in which
* transaction the data will hit the disk. In case we are journaling data, we
* cannot start transaction directly because transaction start ranks above page
* lock so we have to do some magic.
*
* This function can get called via...
* - ext4_writepages after taking page lock (have journal handle)
* - journal_submit_inode_data_buffers (no journal handle)
* - shrink_page_list via the kswapd/direct reclaim (no journal handle)
* - grab_page_cache when doing write_begin (have journal handle)
*
* We don't do any block allocation in this function. If we have page with
* multiple blocks we need to write those buffer_heads that are mapped. This
* is important for mmaped based write. So if we do with blocksize 1K
* truncate(f, 1024);
* a = mmap(f, 0, 4096);
* a[0] = 'a';
* truncate(f, 4096);
* we have in the page first buffer_head mapped via page_mkwrite call back
* but other buffer_heads would be unmapped but dirty (dirty done via the
* do_wp_page). So writepage should write the first block. If we modify
* the mmap area beyond 1024 we will again get a page_fault and the
* page_mkwrite callback will do the block allocation and mark the
* buffer_heads mapped.
*
* We redirty the page if we have any buffer_heads that is either delay or
* unwritten in the page.
*
* We can get recursively called as show below.
*
* ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
* ext4_writepage()
*
* But since we don't do any block allocation we should not deadlock.
* Page also have the dirty flag cleared so we don't get recurive page_lock.
*/
static int ext4_writepage(struct page *page,
struct writeback_control *wbc)
{
int ret = 0;
loff_t size;
unsigned int len;
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
struct ext4_io_submit io_submit;
bool keep_towrite = false;
trace_ext4_writepage(page);
size = i_size_read(inode);
if (page->index == size >> PAGE_SHIFT)
len = size & ~PAGE_MASK;
else
len = PAGE_SIZE;
page_bufs = page_buffers(page);
/*
* We cannot do block allocation or other extent handling in this
* function. If there are buffers needing that, we have to redirty
* the page. But we may reach here when we do a journal commit via
* journal_submit_inode_data_buffers() and in that case we must write
* allocated buffers to achieve data=ordered mode guarantees.
*
* Also, if there is only one buffer per page (the fs block
* size == the page size), if one buffer needs block
* allocation or needs to modify the extent tree to clear the
* unwritten flag, we know that the page can't be written at
* all, so we might as well refuse the write immediately.
* Unfortunately if the block size != page size, we can't as
* easily detect this case using ext4_walk_page_buffers(), but
* for the extremely common case, this is an optimization that
* skips a useless round trip through ext4_bio_write_page().
*/
if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL,
ext4_bh_delay_or_unwritten)) {
redirty_page_for_writepage(wbc, page);
if ((current->flags & PF_MEMALLOC) ||
(inode->i_sb->s_blocksize == PAGE_SIZE)) {
/*
* For memory cleaning there's no point in writing only
* some buffers. So just bail out. Warn if we came here
* from direct reclaim.
*/
WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD))
== PF_MEMALLOC);
unlock_page(page);
return 0;
}
keep_towrite = true;
}
if (PageChecked(page) && ext4_should_journal_data(inode))
/*
* It's mmapped pagecache. Add buffers and journal it. There
* doesn't seem much point in redirtying the page here.
*/
return __ext4_journalled_writepage(page, len);
ext4_io_submit_init(&io_submit, wbc);
io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_submit.io_end) {
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return -ENOMEM;
}
ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
return ret;
}
static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
{
int len;
loff_t size = i_size_read(mpd->inode);
int err;
BUG_ON(page->index != mpd->first_page);
if (page->index == size >> PAGE_SHIFT)
len = size & ~PAGE_MASK;
else
len = PAGE_SIZE;
clear_page_dirty_for_io(page);
err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
if (!err)
mpd->wbc->nr_to_write--;
mpd->first_page++;
return err;
}
#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay))
/*
* mballoc gives us at most this number of blocks...
* XXX: That seems to be only a limitation of ext4_mb_normalize_request().
* The rest of mballoc seems to handle chunks up to full group size.
*/
#define MAX_WRITEPAGES_EXTENT_LEN 2048
/*
* mpage_add_bh_to_extent - try to add bh to extent of blocks to map
*
* @mpd - extent of blocks
* @lblk - logical number of the block in the file
* @bh - buffer head we want to add to the extent
*
* The function is used to collect contig. blocks in the same state. If the
* buffer doesn't require mapping for writeback and we haven't started the
* extent of buffers to map yet, the function returns 'true' immediately - the
* caller can write the buffer right away. Otherwise the function returns true
* if the block has been added to the extent, false if the block couldn't be
* added.
*/
static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
struct buffer_head *bh)
{
struct ext4_map_blocks *map = &mpd->map;
/* Buffer that doesn't need mapping for writeback? */
if (!buffer_dirty(bh) || !buffer_mapped(bh) ||
(!buffer_delay(bh) && !buffer_unwritten(bh))) {
/* So far no extent to map => we write the buffer right away */
if (map->m_len == 0)
return true;
return false;
}
/* First block in the extent? */
if (map->m_len == 0) {
map->m_lblk = lblk;
map->m_len = 1;
map->m_flags = bh->b_state & BH_FLAGS;
return true;
}
/* Don't go larger than mballoc is willing to allocate */
if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN)
return false;
/* Can we merge the block to our big extent? */
if (lblk == map->m_lblk + map->m_len &&
(bh->b_state & BH_FLAGS) == map->m_flags) {
map->m_len++;
return true;
}
return false;
}
/*
* mpage_process_page_bufs - submit page buffers for IO or add them to extent
*
* @mpd - extent of blocks for mapping
* @head - the first buffer in the page
* @bh - buffer we should start processing from
* @lblk - logical number of the block in the file corresponding to @bh
*
* Walk through page buffers from @bh upto @head (exclusive) and either submit
* the page for IO if all buffers in this page were mapped and there's no
* accumulated extent of buffers to map or add buffers in the page to the
* extent of buffers to map. The function returns 1 if the caller can continue
* by processing the next page, 0 if it should stop adding buffers to the
* extent to map because we cannot extend it anymore. It can also return value
* < 0 in case of error during IO submission.
*/
static int mpage_process_page_bufs(struct mpage_da_data *mpd,
struct buffer_head *head,
struct buffer_head *bh,
ext4_lblk_t lblk)
{
struct inode *inode = mpd->inode;
int err;
ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
>> inode->i_blkbits;
do {
BUG_ON(buffer_locked(bh));
if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) {
/* Found extent to map? */
if (mpd->map.m_len)
return 0;
/* Everything mapped so far and we hit EOF */
break;
}
} while (lblk++, (bh = bh->b_this_page) != head);
/* So far everything mapped? Submit the page for IO. */
if (mpd->map.m_len == 0) {
err = mpage_submit_page(mpd, head->b_page);
if (err < 0)
return err;
}
return lblk < blocks;
}
/*
* mpage_map_buffers - update buffers corresponding to changed extent and
* submit fully mapped pages for IO
*
* @mpd - description of extent to map, on return next extent to map
*
* Scan buffers corresponding to changed extent (we expect corresponding pages
* to be already locked) and update buffer state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits,
* and mark buffers as uninit when we perform writes to unwritten extents
* and do extent conversion after IO is finished. If the last page is not fully
* mapped, we update @map to the next extent in the last page that needs
* mapping. Otherwise we submit the page for IO.
*/
static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
{
struct pagevec pvec;
int nr_pages, i;
struct inode *inode = mpd->inode;
struct buffer_head *head, *bh;
int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
pgoff_t start, end;
ext4_lblk_t lblk;
sector_t pblock;
int err;
start = mpd->map.m_lblk >> bpp_bits;
end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
lblk = start << bpp_bits;
pblock = mpd->map.m_pblk;
pagevec_init(&pvec, 0);
while (start <= end) {
nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start,
PAGEVEC_SIZE);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (page->index > end)
break;
/* Up to 'end' pages must be contiguous */
BUG_ON(page->index != start);
bh = head = page_buffers(page);
do {
if (lblk < mpd->map.m_lblk)
continue;
if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
/*
* Buffer after end of mapped extent.
* Find next buffer in the page to map.
*/
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
/*
* FIXME: If dioread_nolock supports
* blocksize < pagesize, we need to make
* sure we add size mapped so far to
* io_end->size as the following call
* can submit the page for IO.
*/
err = mpage_process_page_bufs(mpd, head,
bh, lblk);
pagevec_release(&pvec);
if (err > 0)
err = 0;
return err;
}
if (buffer_delay(bh)) {
clear_buffer_delay(bh);
bh->b_blocknr = pblock++;
}
clear_buffer_unwritten(bh);
} while (lblk++, (bh = bh->b_this_page) != head);
/*
* FIXME: This is going to break if dioread_nolock
* supports blocksize < pagesize as we will try to
* convert potentially unmapped parts of inode.
*/
mpd->io_submit.io_end->size += PAGE_SIZE;
/* Page fully mapped - let IO run! */
err = mpage_submit_page(mpd, page);
if (err < 0) {
pagevec_release(&pvec);
return err;
}
start++;
}
pagevec_release(&pvec);
}
/* Extent fully mapped and matches with page boundary. We are done. */
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
return 0;
}
static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
{
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int get_blocks_flags;
int err, dioread_nolock;
trace_ext4_da_write_pages_extent(inode, map);
/*
* Call ext4_map_blocks() to allocate any delayed allocation blocks, or
* to convert an unwritten extent to be initialized (in the case
* where we have written into one or more preallocated blocks). It is
* possible that we're going to need more metadata blocks than
* previously reserved. However we must not fail because we're in
* writeback and there is nothing we can do about it so it might result
* in data loss. So use reserved blocks to allocate metadata if
* possible.
*
* We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if
* the blocks in question are delalloc blocks. This indicates
* that the blocks and quotas has already been checked when
* the data was copied into the page cache.
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_METADATA_NOFAIL |
EXT4_GET_BLOCKS_IO_SUBMIT;
dioread_nolock = ext4_should_dioread_nolock(inode);
if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (map->m_flags & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
if (err < 0)
return err;
if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
if (!mpd->io_submit.io_end->handle &&
ext4_handle_valid(handle)) {
mpd->io_submit.io_end->handle = handle->h_rsv_handle;
handle->h_rsv_handle = NULL;
}
ext4_set_io_unwritten_flag(inode, mpd->io_submit.io_end);
}
BUG_ON(map->m_len == 0);
if (map->m_flags & EXT4_MAP_NEW) {
struct block_device *bdev = inode->i_sb->s_bdev;
int i;
for (i = 0; i < map->m_len; i++)
unmap_underlying_metadata(bdev, map->m_pblk + i);
}
return 0;
}
/*
* mpage_map_and_submit_extent - map extent starting at mpd->lblk of length
* mpd->len and submit pages underlying it for IO
*
* @handle - handle for journal operations
* @mpd - extent to map
* @give_up_on_write - we set this to true iff there is a fatal error and there
* is no hope of writing the data. The caller should discard
* dirty pages to avoid infinite loops.
*
* The function maps extent starting at mpd->lblk of length mpd->len. If it is
* delayed, blocks are allocated, if it is unwritten, we may need to convert
* them to initialized or split the described range from larger unwritten
* extent. Note that we need not map all the described range since allocation
* can return less blocks or the range is covered by more unwritten extents. We
* cannot map more because we are limited by reserved transaction credits. On
* the other hand we always make sure that the last touched page is fully
* mapped so that it can be written out (and thus forward progress is
* guaranteed). After mapping we submit all mapped pages for IO.
*/
static int mpage_map_and_submit_extent(handle_t *handle,
struct mpage_da_data *mpd,
bool *give_up_on_write)
{
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int err;
loff_t disksize;
int progress = 0;
mpd->io_submit.io_end->offset =
((loff_t)map->m_lblk) << inode->i_blkbits;
do {
err = mpage_map_one_extent(handle, mpd);
if (err < 0) {
struct super_block *sb = inode->i_sb;
if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
goto invalidate_dirty_pages;
/*
* Let the uper layers retry transient errors.
* In the case of ENOSPC, if ext4_count_free_blocks()
* is non-zero, a commit should free up blocks.
*/
if ((err == -ENOMEM) ||
(err == -ENOSPC && ext4_count_free_clusters(sb))) {
if (progress)
goto update_disksize;
return err;
}
ext4_msg(sb, KERN_CRIT,
"Delayed block allocation failed for "
"inode %lu at logical offset %llu with"
" max blocks %u with error %d",
inode->i_ino,
(unsigned long long)map->m_lblk,
(unsigned)map->m_len, -err);
ext4_msg(sb, KERN_CRIT,
"This should not happen!! Data will "
"be lost\n");
if (err == -ENOSPC)
ext4_print_free_blocks(inode);
invalidate_dirty_pages:
*give_up_on_write = true;
return err;
}
progress = 1;
/*
* Update buffer state, submit mapped pages, and get us new
* extent to map
*/
err = mpage_map_and_submit_buffers(mpd);
if (err < 0)
goto update_disksize;
} while (map->m_len);
update_disksize:
/*
* Update on-disk size after IO is submitted. Races with
* truncate are avoided by checking i_size under i_data_sem.
*/
disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
if (disksize > EXT4_I(inode)->i_disksize) {
int err2;
loff_t i_size;
down_write(&EXT4_I(inode)->i_data_sem);
i_size = i_size_read(inode);
if (disksize > i_size)
disksize = i_size;
if (disksize > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = disksize;
err2 = ext4_mark_inode_dirty(handle, inode);
up_write(&EXT4_I(inode)->i_data_sem);
if (err2)
ext4_error(inode->i_sb,
"Failed to mark inode %lu dirty",
inode->i_ino);
if (!err)
err = err2;
}
return err;
}
/*
* Calculate the total number of credits to reserve for one writepages
* iteration. This is called from ext4_writepages(). We map an extent of
* up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
* the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN +
* bpp - 1 blocks in bpp different extents.
*/
static int ext4_da_writepages_trans_blocks(struct inode *inode)
{
int bpp = ext4_journal_blocks_per_page(inode);
return ext4_meta_trans_blocks(inode,
MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp);
}
/*
* mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages
* and underlying extent to map
*
* @mpd - where to look for pages
*
* Walk dirty pages in the mapping. If they are fully mapped, submit them for
* IO immediately. When we find a page which isn't mapped we start accumulating
* extent of buffers underlying these pages that needs mapping (formed by
* either delayed or unwritten buffers). We also lock the pages containing
* these buffers. The extent found is returned in @mpd structure (starting at
* mpd->lblk with length mpd->len blocks).
*
* Note that this function can attach bios to one io_end structure which are
* neither logically nor physically contiguous. Although it may seem as an
* unnecessary complication, it is actually inevitable in blocksize < pagesize
* case as we need to track IO to all buffers underlying a page in one io_end.
*/
static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
{
struct address_space *mapping = mpd->inode->i_mapping;
struct pagevec pvec;
unsigned int nr_pages;
long left = mpd->wbc->nr_to_write;
pgoff_t index = mpd->first_page;
pgoff_t end = mpd->last_page;
int tag;
int i, err = 0;
int blkbits = mpd->inode->i_blkbits;
ext4_lblk_t lblk;
struct buffer_head *head;
if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
pagevec_init(&pvec, 0);
mpd->map.m_len = 0;
mpd->next_page = index;
while (index <= end) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
goto out;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end)
goto out;
/*
* Accumulated enough dirty pages? This doesn't apply
* to WB_SYNC_ALL mode. For integrity sync we have to
* keep going because someone may be concurrently
* dirtying pages, and we might have synced a lot of
* newly appeared dirty pages, but have not synced all
* of the old dirty pages.
*/
if (mpd->wbc->sync_mode == WB_SYNC_NONE && left <= 0)
goto out;
/* If we can't merge this page, we are done. */
if (mpd->map.m_len > 0 && mpd->next_page != page->index)
goto out;
lock_page(page);
/*
* If the page is no longer dirty, or its mapping no
* longer corresponds to inode we are writing (which
* means it has been truncated or invalidated), or the
* page is already under writeback and we are not doing
* a data integrity writeback, skip the page
*/
if (!PageDirty(page) ||
(PageWriteback(page) &&
(mpd->wbc->sync_mode == WB_SYNC_NONE)) ||
unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
if (mpd->map.m_len == 0)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
/* Add all dirty buffers to mpd */
lblk = ((ext4_lblk_t)page->index) <<
(PAGE_SHIFT - blkbits);
head = page_buffers(page);
err = mpage_process_page_bufs(mpd, head, head, lblk);
if (err <= 0)
goto out;
err = 0;
left--;
}
pagevec_release(&pvec);
cond_resched();
}
return 0;
out:
pagevec_release(&pvec);
return err;
}
static int __writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
struct address_space *mapping = data;
int ret = ext4_writepage(page, wbc);
mapping_set_error(mapping, ret);
return ret;
}
static int ext4_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
pgoff_t writeback_index = 0;
long nr_to_write = wbc->nr_to_write;
int range_whole = 0;
int cycled = 1;
handle_t *handle = NULL;
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
int needed_blocks, rsv_blocks = 0, ret = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
bool done;
struct blk_plug plug;
bool give_up_on_write = false;
percpu_down_read(&sbi->s_journal_flag_rwsem);
trace_ext4_writepages(inode, wbc);
if (dax_mapping(mapping)) {
ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
wbc);
goto out_writepages;
}
/*
* No pages to write? This is mainly a kludge to avoid starting
* a transaction for special inodes like journal inode on last iput()
* because that could violate lock ordering on umount
*/
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
goto out_writepages;
if (ext4_should_journal_data(inode)) {
struct blk_plug plug;
blk_start_plug(&plug);
ret = write_cache_pages(mapping, wbc, __writepage, mapping);
blk_finish_plug(&plug);
goto out_writepages;
}
/*
* If the filesystem has aborted, it is read-only, so return
* right away instead of dumping stack traces later on that
* will obscure the real source of the problem. We test
* EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because
* the latter could be true if the filesystem is mounted
* read-only, and in that case, ext4_writepages should
* *never* be called, so if that ever happens, we would want
* the stack trace.
*/
if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
ret = -EROFS;
goto out_writepages;
}
if (ext4_should_dioread_nolock(inode)) {
/*
* We may need to convert up to one extent per block in
* the page and we may dirty the inode.
*/
rsv_blocks = 1 + (PAGE_SIZE >> inode->i_blkbits);
}
/*
* If we have inline data and arrive here, it means that
* we will soon create the block for the 1st page, so
* we'd better clear the inline data here.
*/
if (ext4_has_inline_data(inode)) {
/* Just inode will be modified... */
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out_writepages;
}
BUG_ON(ext4_test_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA));
ext4_destroy_inline_data(handle, inode);
ext4_journal_stop(handle);
}
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index;
if (writeback_index)
cycled = 0;
mpd.first_page = writeback_index;
mpd.last_page = -1;
} else {
mpd.first_page = wbc->range_start >> PAGE_SHIFT;
mpd.last_page = wbc->range_end >> PAGE_SHIFT;
}
mpd.inode = inode;
mpd.wbc = wbc;
ext4_io_submit_init(&mpd.io_submit, wbc);
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
done = false;
blk_start_plug(&plug);
while (!done && mpd.first_page <= mpd.last_page) {
/* For each extent of pages we use new io_end */
mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd.io_submit.io_end) {
ret = -ENOMEM;
break;
}
/*
* We have two constraints: We find one extent to map and we
* must always write out whole page (makes a difference when
* blocksize < pagesize) so that we don't block on IO when we
* try to write out the rest of the page. Journalled mode is
* not supported by delalloc.
*/
BUG_ON(ext4_should_journal_data(inode));
needed_blocks = ext4_da_writepages_trans_blocks(inode);
/* start a new transaction */
handle = ext4_journal_start_with_reserve(inode,
EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
"%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
/* Release allocated io_end */
ext4_put_io_end(mpd.io_submit.io_end);
break;
}
trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
ret = mpage_prepare_extent_to_map(&mpd);
if (!ret) {
if (mpd.map.m_len)
ret = mpage_map_and_submit_extent(handle, &mpd,
&give_up_on_write);
else {
/*
* We scanned the whole range (or exhausted
* nr_to_write), submitted what was mapped and
* didn't find anything needing mapping. We are
* done.
*/
done = true;
}
}
/*
* Caution: If the handle is synchronous,
* ext4_journal_stop() can wait for transaction commit
* to finish which may depend on writeback of pages to
* complete or on page lock to be released. In that
* case, we have to wait until after after we have
* submitted all the IO, released page locks we hold,
* and dropped io_end reference (for extent conversion
* to be able to complete) before stopping the handle.
*/
if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
ext4_journal_stop(handle);
handle = NULL;
}
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
/*
* Drop our io_end reference we got from init. We have
* to be careful and use deferred io_end finishing if
* we are still holding the transaction as we can
* release the last reference to io_end which may end
* up doing unwritten extent conversion.
*/
if (handle) {
ext4_put_io_end_defer(mpd.io_submit.io_end);