AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity
367069f16e
kernel_optimize_test/fs/ext4/inode.c
Mel Gorman 966dbde2c2 ext4: warn if direct reclaim tries to writeback pages 
Direct reclaim should never writeback pages.  Warn if an attempt is made.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Alex Elder <aelder@sgi.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-10-31 17:30:46 -07:00

4435 lines
128 KiB
C
Raw Blame History

/*
* 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/module.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/jbd2.h>
#include <linux/highuid.h>
#include <linux/pagemap.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/ratelimit.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "ext4_extents.h"
#include "truncate.h"
#include <trace/events/ext4.h>
#define MPAGE_DA_EXTENT_TAIL 0x01
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 long offset);
static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
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);
/*
* Test whether an inode is a fast symlink.
*/
static int ext4_inode_is_fast_symlink(struct inode *inode)
{
int ea_blocks = EXT4_I(inode)->i_file_acl ?
(inode->i_sb->s_blocksize >> 9) : 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);
ext4_ioend_wait(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 (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_log_start_commit(journal, commit_tid);
jbd2_log_wait_commit(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages(&inode->i_data, 0);
goto no_delete;
}
if (!is_bad_inode(inode))
dquot_initialize(inode);
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages(&inode->i_data, 0);
if (is_bad_inode(inode))
goto no_delete;
handle = ext4_journal_start(inode, 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);
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);
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);
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
/*
* Calculate the number of metadata blocks need to reserve
* to allocate a block located at @lblock
*/
static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
{
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_calc_metadata_amount(inode, lblock);
return ext4_ind_calc_metadata_amount(inode, lblock);
}
/*
* 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);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
"with only %d reserved data blocks\n",
__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;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
percpu_counter_sub(&sbi->s_dirtyblocks_counter,
used + ei->i_allocated_meta_blocks);
ei->i_allocated_meta_blocks = 0;
if (ei->i_reserved_data_blocks == 0) {
/*
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
*/
percpu_counter_sub(&sbi->s_dirtyblocks_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
}
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/* Update quota subsystem for data blocks */
if (quota_claim)
dquot_claim_block(inode, 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, 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 -EIO;
}
return 0;
}
#define check_block_validity(inode, map) \
__check_block_validity((inode), __func__, __LINE__, (map))
/*
* Return the number of contiguous dirty pages in a given inode
* starting at page frame idx.
*/
static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
unsigned int max_pages)
{
struct address_space *mapping = inode->i_mapping;
pgoff_t index;
struct pagevec pvec;
pgoff_t num = 0;
int i, nr_pages, done = 0;
if (max_pages == 0)
return 0;
pagevec_init(&pvec, 0);
while (!done) {
index = idx;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
(pgoff_t)PAGEVEC_SIZE);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
struct buffer_head *bh, *head;
lock_page(page);
if (unlikely(page->mapping != mapping) ||
!PageDirty(page) ||
PageWriteback(page) ||
page->index != idx) {
done = 1;
unlock_page(page);
break;
}
if (page_has_buffers(page)) {
bh = head = page_buffers(page);
do {
if (!buffer_delay(bh) &&
!buffer_unwritten(bh))
done = 1;
bh = bh->b_this_page;
} while (!done && (bh != head));
}
unlock_page(page);
if (done)
break;
idx++;
num++;
if (num >= max_pages) {
done = 1;
break;
}
}
pagevec_release(&pvec);
}
return num;
}
/*
* 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 allocate.
* if create==0 and the blocks are pre-allocated and uninitialized block,
* the result buffer head is unmapped. If the create ==1, it will make sure
* the buffer head is mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
* that casem, buffer head is unmapped
*
* 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)
{
int retval;
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);
/*
* 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, 0);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int 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 th create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
return retval;
/*
* When we call get_blocks without the create flag, the
* BH_Unwritten flag could have gotten set if the blocks
* requested were part of a uninitialized extent. We need to
* clear this flag now that we are committed to convert all or
* part of the uninitialized extent to be an initialized
* extent. This is because we need to avoid the combination
* of BH_Unwritten and BH_Mapped flags being simultaneously
* set on the buffer_head.
*/
map->m_flags &= ~EXT4_MAP_UNWRITTEN;
/*
* New blocks allocate and/or writing to uninitialized extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_blocks()
* with create == 1 flag.
*/
down_write((&EXT4_I(inode)->i_data_sem));
/*
* if the caller is from delayed allocation writeout path
* we have already reserved fs blocks for allocation
* let the underlying get_block() function know to
* avoid double accounting
*/
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
/*
* 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 (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
return retval;
}
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
static int _ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int flags)
{
handle_t *handle = ext4_journal_current_handle();
struct ext4_map_blocks map;
int ret = 0, started = 0;
int dio_credits;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
if (flags && !handle) {
/* Direct IO write... */
if (map.m_len > DIO_MAX_BLOCKS)
map.m_len = DIO_MAX_BLOCKS;
dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
handle = ext4_journal_start(inode, dio_credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
return ret;
}
started = 1;
}
ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret > 0) {
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
ret = 0;
}
if (started)
ext4_journal_stop(handle);
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);
}
/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int create, int *errp)
{
struct ext4_map_blocks map;
struct buffer_head *bh;
int fatal = 0, err;
J_ASSERT(handle != NULL || create == 0);
map.m_lblk = block;
map.m_len = 1;
err = ext4_map_blocks(handle, inode, &map,
create ? EXT4_GET_BLOCKS_CREATE : 0);
if (err < 0)
*errp = err;
if (err <= 0)
return NULL;
*errp = 0;
bh = sb_getblk(inode->i_sb, map.m_pblk);
if (!bh) {
*errp = -EIO;
return NULL;
}
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");
fatal = ext4_journal_get_create_access(handle, bh);
if (!fatal && !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 (!fatal)
fatal = err;
} else {
BUFFER_TRACE(bh, "not a new buffer");
}
if (fatal) {
*errp = fatal;
brelse(bh);
bh = NULL;
}
return bh;
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int create, int *err)
{
struct buffer_head *bh;
bh = ext4_getblk(handle, inode, block, create, err);
if (!bh)
return bh;
if (buffer_uptodate(bh))
return bh;
ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
put_bh(bh);
*err = -EIO;
return NULL;
}
static int 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() ->
* block_write_full_page(). 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.
*/
static 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);
ret = ext4_journal_get_write_access(handle, bh);
if (!ret && dirty)
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
return ret;
}
static int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
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_CACHE_SHIFT;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
retry:
handle = ext4_journal_start(inode, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
/* We cannot recurse into the filesystem as the transaction is already
* started */
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
ext4_journal_stop(handle);
ret = -ENOMEM;
goto out;
}
*pagep = page;
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(page, pos, len, ext4_get_block_write);
else
ret = __block_write_begin(page, pos, len, ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
from, to, NULL, do_journal_get_write_access);
}
if (ret) {
unlock_page(page);
page_cache_release(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;
out:
return ret;
}
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
return ext4_handle_dirty_metadata(handle, NULL, bh);
}
static int ext4_generic_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
int i_size_changed = 0;
struct inode *inode = mapping->host;
handle_t *handle = ext4_journal_current_handle();
copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
/*
* No need to use i_size_read() here, the i_size
* cannot change under us because we hold i_mutex.
*
* But it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
*/
if (pos + copied > inode->i_size) {
i_size_write(inode, pos + copied);
i_size_changed = 1;
}
if (pos + copied > EXT4_I(inode)->i_disksize) {
/* We need to mark inode dirty even if
* new_i_size is less that inode->i_size
* bu greater than i_disksize.(hint delalloc)
*/
ext4_update_i_disksize(inode, (pos + copied));
i_size_changed = 1;
}
unlock_page(page);
page_cache_release(page);
/*
* 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);
return copied;
}
/*
* 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_ordered_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;
int ret = 0, ret2;
trace_ext4_ordered_write_end(inode, pos, len, copied);
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = 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);
if (ret2 < 0)
ret = ret2;
}
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;
}
static int ext4_writeback_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;
int ret = 0, ret2;
trace_ext4_writeback_write_end(inode, pos, len, copied);
ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = 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);
if (ret2 < 0)
ret = ret2;
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;
}
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;
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
loff_t new_i_size;
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
BUG_ON(!ext4_handle_valid(handle));
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
page_zero_new_buffers(page, from+copied, to);
}
ret = walk_page_buffers(handle, page_buffers(page), from,
to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
new_i_size = pos + copied;
if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
}
unlock_page(page);
page_cache_release(page);
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 a single block located at lblock
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned long md_needed;
int ret;
/*
* recalculate the amount of metadata blocks to reserve
* in order to allocate nrblocks
* worse case is one extent per block
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
md_needed = ext4_calc_metadata_amount(inode, lblock);
trace_ext4_da_reserve_space(inode, md_needed);
spin_unlock(&ei->i_block_reservation_lock);
/*
* 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, 1);
if (ret)
return ret;
/*
* We do still charge estimated metadata to the sb though;
* we cannot afford to run out of free blocks.
*/
if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
dquot_release_reservation_block(inode, 1);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
}
return -ENOSPC;
}
spin_lock(&ei->i_block_reservation_lock);
ei->i_reserved_data_blocks++;
ei->i_reserved_meta_blocks += md_needed;
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_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
"data blocks\n", 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;
if (ei->i_reserved_data_blocks == 0) {
/*
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
*/
percpu_counter_sub(&sbi->s_dirtyblocks_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
}
/* update fs dirty data blocks counter */
percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_release_reservation_block(inode, to_free);
}
static void ext4_da_page_release_reservation(struct page *page,
unsigned long offset)
{
int to_release = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
head = page_buffers(page);
bh = head;
do {
unsigned int next_off = curr_off + bh->b_size;
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
clear_buffer_delay(bh);
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
ext4_da_release_space(page->mapping->host, to_release);
}
/*
* Delayed allocation stuff
*/
/*
* mpage_da_submit_io - walks through extent of pages and try to write
* them with writepage() call back
*
* @mpd->inode: inode
* @mpd->first_page: first page of the extent
* @mpd->next_page: page after the last page of the extent
*
* By the time mpage_da_submit_io() is called we expect all blocks
* to be allocated. this may be wrong if allocation failed.
*
* As pages are already locked by write_cache_pages(), we can't use it
*/
static int mpage_da_submit_io(struct mpage_da_data *mpd,
struct ext4_map_blocks *map)
{
struct pagevec pvec;
unsigned long index, end;
int ret = 0, err, nr_pages, i;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
loff_t size = i_size_read(inode);
unsigned int len, block_start;
struct buffer_head *bh, *page_bufs = NULL;
int journal_data = ext4_should_journal_data(inode);
sector_t pblock = 0, cur_logical = 0;
struct ext4_io_submit io_submit;
BUG_ON(mpd->next_page <= mpd->first_page);
memset(&io_submit, 0, sizeof(io_submit));
/*
* We need to start from the first_page to the next_page - 1
* to make sure we also write the mapped dirty buffer_heads.
* If we look at mpd->b_blocknr we would only be looking
* at the currently mapped buffer_heads.
*/
index = mpd->first_page;
end = mpd->next_page - 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++) {
int commit_write = 0, skip_page = 0;
struct page *page = pvec.pages[i];
index = page->index;
if (index > end)
break;
if (index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
if (map) {
cur_logical = index << (PAGE_CACHE_SHIFT -
inode->i_blkbits);
pblock = map->m_pblk + (cur_logical -
map->m_lblk);
}
index++;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
/*
* If the page does not have buffers (for
* whatever reason), try to create them using
* __block_write_begin. If this fails,
* skip the page and move on.
*/
if (!page_has_buffers(page)) {
if (__block_write_begin(page, 0, len,
noalloc_get_block_write)) {
skip_page:
unlock_page(page);
continue;
}
commit_write = 1;
}
bh = page_bufs = page_buffers(page);
block_start = 0;
do {
if (!bh)
goto skip_page;
if (map && (cur_logical >= map->m_lblk) &&
(cur_logical <= (map->m_lblk +
(map->m_len - 1)))) {
if (buffer_delay(bh)) {
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
}
if (buffer_unwritten(bh) ||
buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
if (map->m_flags & EXT4_MAP_UNINIT)
set_buffer_uninit(bh);
clear_buffer_unwritten(bh);
}
/* skip page if block allocation undone */
if (buffer_delay(bh) || buffer_unwritten(bh))
skip_page = 1;
bh = bh->b_this_page;
block_start += bh->b_size;
cur_logical++;
pblock++;
} while (bh != page_bufs);
if (skip_page)
goto skip_page;
if (commit_write)
/* mark the buffer_heads as dirty & uptodate */
block_commit_write(page, 0, len);
clear_page_dirty_for_io(page);
/*
* Delalloc doesn't support data journalling,
* but eventually maybe we'll lift this
* restriction.
*/
if (unlikely(journal_data && PageChecked(page)))
err = __ext4_journalled_writepage(page, len);
else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
err = ext4_bio_write_page(&io_submit, page,
len, mpd->wbc);
else if (buffer_uninit(page_bufs)) {
ext4_set_bh_endio(page_bufs, inode);
err = block_write_full_page_endio(page,
noalloc_get_block_write,
mpd->wbc, ext4_end_io_buffer_write);
} else
err = block_write_full_page(page,
noalloc_get_block_write, mpd->wbc);
if (!err)
mpd->pages_written++;
/*
* In error case, we have to continue because
* remaining pages are still locked
*/
if (ret == 0)
ret = err;
}
pagevec_release(&pvec);
}
ext4_io_submit(&io_submit);
return ret;
}
static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
{
int nr_pages, i;
pgoff_t index, end;
struct pagevec pvec;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
index = mpd->first_page;
end = mpd->next_page - 1;
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));
block_invalidatepage(page, 0);
ClearPageUptodate(page);
unlock_page(page);
}
index = pvec.pages[nr_pages - 1]->index + 1;
pagevec_release(&pvec);
}
return;
}
static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
printk(KERN_CRIT "Total free blocks count %lld\n",
ext4_count_free_blocks(inode->i_sb));
printk(KERN_CRIT "Free/Dirty block details\n");
printk(KERN_CRIT "free_blocks=%lld\n",
(long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
printk(KERN_CRIT "dirty_blocks=%lld\n",
(long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
printk(KERN_CRIT "Block reservation details\n");
printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
printk(KERN_CRIT "i_reserved_meta_blocks=%u\n",
EXT4_I(inode)->i_reserved_meta_blocks);
return;
}
/*
* mpage_da_map_and_submit - go through given space, map them
* if necessary, and then submit them for I/O
*
* @mpd - bh describing space
*
* The function skips space we know is already mapped to disk blocks.
*
*/
static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
{
int err, blks, get_blocks_flags;
struct ext4_map_blocks map, *mapp = NULL;
sector_t next = mpd->b_blocknr;
unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
handle_t *handle = NULL;
/*
* If the blocks are mapped already, or we couldn't accumulate
* any blocks, then proceed immediately to the submission stage.
*/
if ((mpd->b_size == 0) ||
((mpd->b_state & (1 << BH_Mapped)) &&
!(mpd->b_state & (1 << BH_Delay)) &&
!(mpd->b_state & (1 << BH_Unwritten))))
goto submit_io;
handle = ext4_journal_current_handle();
BUG_ON(!handle);
/*
* Call ext4_map_blocks() to allocate any delayed allocation
* blocks, or to convert an uninitialized extent to be
* initialized (in the case where we have written into
* one or more preallocated blocks).
*
* We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to
* indicate that we are on the delayed allocation path. This
* affects functions in many different parts of the allocation
* call path. This flag exists primarily because we don't
* want to change *many* call functions, so ext4_map_blocks()
* will set the EXT4_STATE_DELALLOC_RESERVED flag once the
* inode's allocation semaphore is taken.
*
* If the blocks in questions were delalloc blocks, set
* EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
* variables are updated after the blocks have been allocated.
*/
map.m_lblk = next;
map.m_len = max_blocks;
get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
if (ext4_should_dioread_nolock(mpd->inode))
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (mpd->b_state & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
if (blks < 0) {
struct super_block *sb = mpd->inode->i_sb;
err = blks;
/*
* If get block returns EAGAIN or ENOSPC and there
* appears to be free blocks we will just let
* mpage_da_submit_io() unlock all of the pages.
*/
if (err == -EAGAIN)
goto submit_io;
if (err == -ENOSPC &&
ext4_count_free_blocks(sb)) {
mpd->retval = err;
goto submit_io;
}
/*
* get block failure will cause us to loop in
* writepages, because a_ops->writepage won't be able
* to make progress. The page will be redirtied by
* writepage and writepages will again try to write
* the same.
*/
if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) {
ext4_msg(sb, KERN_CRIT,
"delayed block allocation failed for inode %lu "
"at logical offset %llu with max blocks %zd "
"with error %d", mpd->inode->i_ino,
(unsigned long long) next,
mpd->b_size >> mpd->inode->i_blkbits, err);
ext4_msg(sb, KERN_CRIT,
"This should not happen!! Data will be lost\n");
if (err == -ENOSPC)
ext4_print_free_blocks(mpd->inode);
}
/* invalidate all the pages */
ext4_da_block_invalidatepages(mpd);
/* Mark this page range as having been completed */
mpd->io_done = 1;
return;
}
BUG_ON(blks == 0);
mapp = &map;
if (map.m_flags & EXT4_MAP_NEW) {
struct block_device *bdev = mpd->inode->i_sb->s_bdev;
int i;
for (i = 0; i < map.m_len; i++)
unmap_underlying_metadata(bdev, map.m_pblk + i);
}
if (ext4_should_order_data(mpd->inode)) {
err = ext4_jbd2_file_inode(handle, mpd->inode);
if (err)
/* This only happens if the journal is aborted */
return;
}
/*
* Update on-disk size along with block allocation.
*/
disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits;
if (disksize > i_size_read(mpd->inode))
disksize = i_size_read(mpd->inode);
if (disksize > EXT4_I(mpd->inode)->i_disksize) {
ext4_update_i_disksize(mpd->inode, disksize);
err = ext4_mark_inode_dirty(handle, mpd->inode);
if (err)
ext4_error(mpd->inode->i_sb,
"Failed to mark inode %lu dirty",
mpd->inode->i_ino);
}
submit_io:
mpage_da_submit_io(mpd, mapp);
mpd->io_done = 1;
}
#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
(1 << BH_Delay) | (1 << BH_Unwritten))
/*
* mpage_add_bh_to_extent - try to add one more block to extent of blocks
*
* @mpd->lbh - extent of blocks
* @logical - logical number of the block in the file
* @bh - bh of the block (used to access block's state)
*
* the function is used to collect contig. blocks in same state
*/
static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
sector_t logical, size_t b_size,
unsigned long b_state)
{
sector_t next;
int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;
/*
* XXX Don't go larger than mballoc is willing to allocate
* This is a stopgap solution. We eventually need to fold
* mpage_da_submit_io() into this function and then call
* ext4_map_blocks() multiple times in a loop
*/
if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
goto flush_it;
/* check if thereserved journal credits might overflow */
if (!(ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS))) {
if (nrblocks >= EXT4_MAX_TRANS_DATA) {
/*
* With non-extent format we are limited by the journal
* credit available. Total credit needed to insert
* nrblocks contiguous blocks is dependent on the
* nrblocks. So limit nrblocks.
*/
goto flush_it;
} else if ((nrblocks + (b_size >> mpd->inode->i_blkbits)) >
EXT4_MAX_TRANS_DATA) {
/*
* Adding the new buffer_head would make it cross the
* allowed limit for which we have journal credit
* reserved. So limit the new bh->b_size
*/
b_size = (EXT4_MAX_TRANS_DATA - nrblocks) <<
mpd->inode->i_blkbits;
/* we will do mpage_da_submit_io in the next loop */
}
}
/*
* First block in the extent
*/
if (mpd->b_size == 0) {
mpd->b_blocknr = logical;
mpd->b_size = b_size;
mpd->b_state = b_state & BH_FLAGS;
return;
}
next = mpd->b_blocknr + nrblocks;
/*
* Can we merge the block to our big extent?
*/
if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) {
mpd->b_size += b_size;
return;
}
flush_it:
/*
* We couldn't merge the block to our extent, so we
* need to flush current extent and start new one
*/
mpage_da_map_and_submit(mpd);
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 is a special get_blocks_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.
*/
static 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;
sector_t invalid_block = ~((sector_t) 0xffff);
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
invalid_block = ~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_map_blocks(NULL, inode, &map, 0);
if (ret < 0)
return ret;
if (ret == 0) {
if (buffer_delay(bh))
return 0; /* Not sure this could or should happen */
/*
* XXX: __block_write_begin() unmaps passed block, is it OK?
*/
ret = ext4_da_reserve_space(inode, iblock);
if (ret)
/* not enough space to reserve */
return ret;
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
return 0;
}
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | 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;
}
/*
* This function is used as a standard get_block_t calback function
* when there is no desire to allocate any blocks. It is used as a
* callback function for block_write_begin() and block_write_full_page().
* These functions should only try to map a single block at a time.
*
* Since this function doesn't do block allocations even if the caller
* requests it by passing in create=1, it is critically important that
* any caller checks to make sure that any buffer heads are returned
* by this function are either all already mapped or marked for
* delayed allocation before calling block_write_full_page(). Otherwise,
* b_blocknr could be left unitialized, and the page write functions will
* be taken by surprise.
*/
static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
return _ext4_get_block(inode, iblock, bh_result, 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;
handle_t *handle = NULL;
int ret = 0;
int err;
ClearPageChecked(page);
page_bufs = page_buffers(page);
BUG_ON(!page_bufs);
walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
/* As soon as we unlock the page, it can go away, but we have
* references to buffers so we are safe */
unlock_page(page);
handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
BUG_ON(!ext4_handle_valid(handle));
ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
err = 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;
walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
return ret;
}
static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
/*
* 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_da_writepages after taking page lock (have journal handle)
* - journal_submit_inode_data_buffers (no journal handle)
* - shrink_page_list via pdflush (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 bufer_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, commit_write = 0;
loff_t size;
unsigned int len;
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
trace_ext4_writepage(page);
size = i_size_read(inode);
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
/*
* If the page does not have buffers (for whatever reason),
* try to create them using __block_write_begin. If this
* fails, redirty the page and move on.
*/
if (!page_has_buffers(page)) {
if (__block_write_begin(page, 0, len,
noalloc_get_block_write)) {
redirty_page:
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
}
commit_write = 1;
}
page_bufs = page_buffers(page);
if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
ext4_bh_delay_or_unwritten)) {
/*
* We don't want to do block allocation, so redirty
* the page and return. We may reach here when we do
* a journal commit via journal_submit_inode_data_buffers.
* We can also reach here via shrink_page_list but it
* should never be for direct reclaim so warn if that
* happens
*/
WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
PF_MEMALLOC);
goto redirty_page;
}
if (commit_write)
/* now mark the buffer_heads as dirty and uptodate */
block_commit_write(page, 0, len);
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);
if (buffer_uninit(page_bufs)) {
ext4_set_bh_endio(page_bufs, inode);
ret = block_write_full_page_endio(page, noalloc_get_block_write,
wbc, ext4_end_io_buffer_write);
} else
ret = block_write_full_page(page, noalloc_get_block_write,
wbc);
return ret;
}
/*
* This is called via ext4_da_writepages() to
* calculate the total number of credits to reserve to fit
* a single extent allocation into a single transaction,
* ext4_da_writpeages() will loop calling this before
* the block allocation.
*/
static int ext4_da_writepages_trans_blocks(struct inode *inode)
{
int max_blocks = EXT4_I(inode)->i_reserved_data_blocks;
/*
* With non-extent format the journal credit needed to
* insert nrblocks contiguous block is dependent on
* number of contiguous block. So we will limit
* number of contiguous block to a sane value
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
(max_blocks > EXT4_MAX_TRANS_DATA))
max_blocks = EXT4_MAX_TRANS_DATA;
return ext4_chunk_trans_blocks(inode, max_blocks);
}
/*
* write_cache_pages_da - walk the list of dirty pages of the given
* address space and accumulate pages that need writing, and call
* mpage_da_map_and_submit to map a single contiguous memory region
* and then write them.
*/
static int write_cache_pages_da(struct address_space *mapping,
struct writeback_control *wbc,
struct mpage_da_data *mpd,
pgoff_t *done_index)
{
struct buffer_head *bh, *head;
struct inode *inode = mapping->host;
struct pagevec pvec;
unsigned int nr_pages;
sector_t logical;
pgoff_t index, end;
long nr_to_write = wbc->nr_to_write;
int i, tag, ret = 0;
memset(mpd, 0, sizeof(struct mpage_da_data));
mpd->wbc = wbc;
mpd->inode = inode;
pagevec_init(&pvec, 0);
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
*done_index = 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)
return 0;
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;
*done_index = page->index + 1;
/*
* If we can't merge this page, and we have
* accumulated an contiguous region, write it
*/
if ((mpd->next_page != page->index) &&
(mpd->next_page != mpd->first_page)) {
mpage_da_map_and_submit(mpd);
goto ret_extent_tail;
}
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) &&
(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->next_page != page->index)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
logical = (sector_t) page->index <<
(PAGE_CACHE_SHIFT - inode->i_blkbits);
if (!page_has_buffers(page)) {
mpage_add_bh_to_extent(mpd, logical,
PAGE_CACHE_SIZE,
(1 << BH_Dirty) | (1 << BH_Uptodate));
if (mpd->io_done)
goto ret_extent_tail;
} else {
/*
* Page with regular buffer heads,
* just add all dirty ones
*/
head = page_buffers(page);
bh = head;
do {
BUG_ON(buffer_locked(bh));
/*
* We need to try to allocate
* unmapped blocks in the same page.
* Otherwise we won't make progress
* with the page in ext4_writepage
*/
if (ext4_bh_delay_or_unwritten(NULL, bh)) {
mpage_add_bh_to_extent(mpd, logical,
bh->b_size,
bh->b_state);
if (mpd->io_done)
goto ret_extent_tail;
} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
/*
* mapped dirty buffer. We need
* to update the b_state
* because we look at b_state
* in mpage_da_map_blocks. We
* don't update b_size because
* if we find an unmapped
* buffer_head later we need to
* use the b_state flag of that
* buffer_head.
*/
if (mpd->b_size == 0)
mpd->b_state = bh->b_state & BH_FLAGS;
}
logical++;
} while ((bh = bh->b_this_page) != head);
}
if (nr_to_write > 0) {
nr_to_write--;
if (nr_to_write == 0 &&
wbc->sync_mode == WB_SYNC_NONE)
/*
* We stop writing back only if we are
* not doing integrity sync. In case of
* 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.
*/
goto out;
}
}
pagevec_release(&pvec);
cond_resched();
}
return 0;
ret_extent_tail:
ret = MPAGE_DA_EXTENT_TAIL;
out:
pagevec_release(&pvec);
cond_resched();
return ret;
}
static int ext4_da_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
pgoff_t index;
int range_whole = 0;
handle_t *handle = NULL;
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
int pages_written = 0;
unsigned int max_pages;
int range_cyclic, cycled = 1, io_done = 0;
int needed_blocks, ret = 0;
long desired_nr_to_write, nr_to_writebump = 0;
loff_t range_start = wbc->range_start;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
pgoff_t done_index = 0;
pgoff_t end;
trace_ext4_da_writepages(inode, wbc);
/*
* 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))
return 0;
/*
* 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_da_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))
return -EROFS;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
range_cyclic = wbc->range_cyclic;
if (wbc->range_cyclic) {
index = mapping->writeback_index;
if (index)
cycled = 0;
wbc->range_start = index << PAGE_CACHE_SHIFT;
wbc->range_end = LLONG_MAX;
wbc->range_cyclic = 0;
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
}
/*
* This works around two forms of stupidity. The first is in
* the writeback code, which caps the maximum number of pages
* written to be 1024 pages. This is wrong on multiple
* levels; different architectues have a different page size,
* which changes the maximum amount of data which gets
* written. Secondly, 4 megabytes is way too small. XFS
* forces this value to be 16 megabytes by multiplying
* nr_to_write parameter by four, and then relies on its
* allocator to allocate larger extents to make them
* contiguous. Unfortunately this brings us to the second
* stupidity, which is that ext4's mballoc code only allocates
* at most 2048 blocks. So we force contiguous writes up to
* the number of dirty blocks in the inode, or
* sbi->max_writeback_mb_bump whichever is smaller.
*/
max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT);
if (!range_cyclic && range_whole) {
if (wbc->nr_to_write == LONG_MAX)
desired_nr_to_write = wbc->nr_to_write;
else
desired_nr_to_write = wbc->nr_to_write * 8;
} else
desired_nr_to_write = ext4_num_dirty_pages(inode, index,
max_pages);
if (desired_nr_to_write > max_pages)
desired_nr_to_write = max_pages;
if (wbc->nr_to_write < desired_nr_to_write) {
nr_to_writebump = desired_nr_to_write - wbc->nr_to_write;
wbc->nr_to_write = desired_nr_to_write;
}
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
while (!ret && wbc->nr_to_write > 0) {
/*
* we insert one extent at a time. So we need
* credit needed for single extent allocation.
* journalled mode is currently 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(inode, needed_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);
goto out_writepages;
}
/*
* Now call write_cache_pages_da() to find the next
* contiguous region of logical blocks that need
* blocks to be allocated by ext4 and submit them.
*/
ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index);
/*
* If we have a contiguous extent of pages and we
* haven't done the I/O yet, map the blocks and submit
* them for I/O.
*/
if (!mpd.io_done && mpd.next_page != mpd.first_page) {
mpage_da_map_and_submit(&mpd);
ret = MPAGE_DA_EXTENT_TAIL;
}
trace_ext4_da_write_pages(inode, &mpd);
wbc->nr_to_write -= mpd.pages_written;
ext4_journal_stop(handle);
if ((mpd.retval == -ENOSPC) && sbi->s_journal) {
/* commit the transaction which would
* free blocks released in the transaction
* and try again
*/
jbd2_journal_force_commit_nested(sbi->s_journal);
ret = 0;
} else if (ret == MPAGE_DA_EXTENT_TAIL) {
/*
* got one extent now try with
* rest of the pages
*/
pages_written += mpd.pages_written;
ret = 0;
io_done = 1;
} else if (wbc->nr_to_write)
/*
* There is no more writeout needed
* or we requested for a noblocking writeout
* and we found the device congested
*/
break;
}
if (!io_done && !cycled) {
cycled = 1;
index = 0;
wbc->range_start = index << PAGE_CACHE_SHIFT;
wbc->range_end = mapping->writeback_index - 1;
goto retry;
}
/* Update index */
wbc->range_cyclic = range_cyclic;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
/*
* set the writeback_index so that range_cyclic
* mode will write it back later
*/
mapping->writeback_index = done_index;
out_writepages:
wbc->nr_to_write -= nr_to_writebump;
wbc->range_start = range_start;
trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
return ret;
}
#define FALL_BACK_TO_NONDELALLOC 1
static int ext4_nonda_switch(struct super_block *sb)
{
s64 free_blocks, dirty_blocks;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/*
* switch to non delalloc mode if we are running low
* on free block. The free block accounting via percpu
* counters can get slightly wrong with percpu_counter_batch getting
* accumulated on each CPU without updating global counters
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
*/
return 1;
}
/*
* Even if we don't switch but are nearing capacity,
* start pushing delalloc when 1/2 of free blocks are dirty.
*/
if (free_blocks < 2 * dirty_blocks)
writeback_inodes_sb_if_idle(sb);
return 0;
}
static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
int ret, retries = 0;
struct page *page;
pgoff_t index;
struct inode *inode = mapping->host;
handle_t *handle;
index = pos >> PAGE_CACHE_SHIFT;
if (ext4_nonda_switch(inode->i_sb)) {
*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
return ext4_write_begin(file, mapping, pos,
len, flags, pagep, fsdata);
}
*fsdata = (void *)0;
trace_ext4_da_write_begin(inode, pos, len, flags);
retry:
/*
* With delayed allocation, we don't log the i_disksize update
* if there is delayed block allocation. But we still need
* to journalling the i_disksize update if writes to the end
* of file which has an already mapped buffer.
*/
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
/* We cannot recurse into the filesystem as the transaction is already
* started */
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
ext4_journal_stop(handle);
ret = -ENOMEM;
goto out;
}
*pagep = page;
ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
if (ret < 0) {
unlock_page(page);
ext4_journal_stop(handle);
page_cache_release(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.
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
out:
return ret;
}
/*
* Check if we should update i_disksize
* when write to the end of file but not require block allocation
*/
static int ext4_da_should_update_i_disksize(struct page *page,
unsigned long offset)
{
struct buffer_head *bh;
struct inode *inode = page->mapping->host;
unsigned int idx;
int i;
bh = page_buffers(page);
idx = offset >> inode->i_blkbits;
for (i = 0; i < idx; i++)
bh = bh->b_this_page;
if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
return 0;
return 1;
}
static int ext4_da_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
int ret = 0, ret2;
handle_t *handle = ext4_journal_current_handle();
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
if (ext4_should_order_data(inode)) {
return ext4_ordered_write_end(file, mapping, pos,
len, copied, page, fsdata);
} else if (ext4_should_writeback_data(inode)) {
return ext4_writeback_write_end(file, mapping, pos,
len, copied, page, fsdata);
} else {
BUG();
}
}
trace_ext4_da_write_end(inode, pos, len, copied);
start = pos & (PAGE_CACHE_SIZE - 1);
end = start + copied - 1;
/*
* generic_write_end() will run mark_inode_dirty() if i_size
* changes. So let's piggyback the i_disksize mark_inode_dirty
* into that.
*/
new_i_size = pos + copied;
if (new_i_size > EXT4_I(inode)->i_disksize) {
if (ext4_da_should_update_i_disksize(page, end)) {
down_write(&EXT4_I(inode)->i_data_sem);
if (new_i_size > EXT4_I(inode)->i_disksize) {
/*
* Updating i_disksize when extending file
* without needing block allocation
*/
if (ext4_should_order_data(inode))
ret = ext4_jbd2_file_inode(handle,
inode);
EXT4_I(inode)->i_disksize = new_i_size;
}
up_write(&EXT4_I(inode)->i_data_sem);
/* We need to mark inode dirty even if
* new_i_size is less that inode->i_size
* bu greater than i_disksize.(hint delalloc)
*/
ext4_mark_inode_dirty(handle, inode);
}
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
if (ret2 < 0)
ret = ret2;
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
return ret ? ret : copied;
}
static void ext4_da_invalidatepage(struct page *page, unsigned long offset)
{
/*
* Drop reserved blocks
*/
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
goto out;
ext4_da_page_release_reservation(page, offset);
out:
ext4_invalidatepage(page, offset);
return;
}
/*
* Force all delayed allocation blocks to be allocated for a given inode.
*/
int ext4_alloc_da_blocks(struct inode *inode)
{
trace_ext4_alloc_da_blocks(inode);
if (!EXT4_I(inode)->i_reserved_data_blocks &&
!EXT4_I(inode)->i_reserved_meta_blocks)
return 0;
/*
* We do something simple for now. The filemap_flush() will
* also start triggering a write of the data blocks, which is
* not strictly speaking necessary (and for users of
* laptop_mode, not even desirable). However, to do otherwise
* would require replicating code paths in:
*
* ext4_da_writepages() ->
* write_cache_pages() ---> (via passed in callback function)
* __mpage_da_writepage() -->
* mpage_add_bh_to_extent()
* mpage_da_map_blocks()
*
* The problem is that write_cache_pages(), located in
* mm/page-writeback.c, marks pages clean in preparation for
* doing I/O, which is not desirable if we're not planning on
* doing I/O at all.
*
* We could call write_cache_pages(), and then redirty all of
* the pages by calling redirty_page_for_writepage() but that
* would be ugly in the extreme. So instead we would need to
* replicate parts of the code in the above functions,
* simplifying them because we wouldn't actually intend to
* write out the pages, but rather only collect contiguous
* logical block extents, call the multi-block allocator, and
* then update the buffer heads with the block allocations.
*
* For now, though, we'll cheat by calling filemap_flush(),
* which will map the blocks, and start the I/O, but not
* actually wait for the I/O to complete.
*/
return filemap_flush(inode->i_mapping);
}
/*
* bmap() is special. It gets used by applications such as lilo and by
* the swapper to find the on-disk block of a specific piece of data.
*
* Naturally, this is dangerous if the block concerned is still in the
* journal. If somebody makes a swapfile on an ext4 data-journaling
* filesystem and enables swap, then they may get a nasty shock when the
* data getting swapped to that swapfile suddenly gets overwritten by
* the original zero's written out previously to the journal and
* awaiting writeback in the kernel's buffer cache.
*
* So, if we see any bmap calls here on a modified, data-journaled file,
* take extra steps to flush any blocks which might be in the cache.
*/
static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
journal_t *journal;
int err;
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
test_opt(inode->i_sb, DELALLOC)) {
/*
* With delalloc we want to sync the file
* so that we can make sure we allocate
* blocks for file
*/
filemap_write_and_wait(mapping);
}
if (EXT4_JOURNAL(inode) &&
ext4_test_inode_state(inode, EXT4_STATE_JDATA)) {
/*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
* only if we run lilo or swapon on a freshly made file
* do we expect this to happen.
*
* (bmap requires CAP_SYS_RAWIO so this does not
* represent an unprivileged user DOS attack --- we'd be
* in trouble if mortal users could trigger this path at
* will.)
*
* NB. EXT4_STATE_JDATA is not set on files other than
* regular files. If somebody wants to bmap a directory
* or symlink and gets confused because the buffer
* hasn't yet been flushed to disk, they deserve
* everything they get.
*/
ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
journal = EXT4_JOURNAL(inode);
jbd2_journal_lock_updates(journal);
err = jbd2_journal_flush(journal);
jbd2_journal_unlock_updates(journal);
if (err)
return 0;
}
return generic_block_bmap(mapping, block, ext4_get_block);
}
static int ext4_readpage(struct file *file, struct page *page)
{
trace_ext4_readpage(page);
return mpage_readpage(page, ext4_get_block);
}
static int
ext4_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
}
static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offset)
{
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
if (!page_has_buffers(page))
return;
head = bh = page_buffers(page);
do {
if (offset <= curr_off && test_clear_buffer_uninit(bh)
&& bh->b_private) {
ext4_free_io_end(bh->b_private);
bh->b_private = NULL;
bh->b_end_io = NULL;
}
curr_off = curr_off + bh->b_size;
bh = bh->b_this_page;
} while (bh != head);
}
static void ext4_invalidatepage(struct page *page, unsigned long offset)
{
journal_t *journal = EXT4_JOURNAL(page->mapping->host);
trace_ext4_invalidatepage(page, offset);
/*
* free any io_end structure allocated for buffers to be discarded
*/
if (ext4_should_dioread_nolock(page->mapping->host))
ext4_invalidatepage_free_endio(page, offset);
/*
* If it's a full truncate we just forget about the pending dirtying
*/
if (offset == 0)
ClearPageChecked(page);
if (journal)
jbd2_journal_invalidatepage(journal, page, offset);
else
block_invalidatepage(page, offset);
}
static int ext4_releasepage(struct page *page, gfp_t wait)
{
journal_t *journal = EXT4_JOURNAL(page->mapping->host);
trace_ext4_releasepage(page);
WARN_ON(PageChecked(page));
if (!page_has_buffers(page))
return 0;
if (journal)
return jbd2_journal_try_to_free_buffers(journal, page, wait);
else
return try_to_free_buffers(page);
}
/*
* ext4_get_block used when preparing for a DIO write or buffer write.
* We allocate an uinitialized extent if blocks haven't been allocated.
* The extent will be converted to initialized after the IO is complete.
*/
static int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
inode->i_ino, create);
return _ext4_get_block(inode, iblock, bh_result,
EXT4_GET_BLOCKS_IO_CREATE_EXT);
}
static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
ssize_t size, void *private, int ret,
bool is_async)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
ext4_io_end_t *io_end = iocb->private;
struct workqueue_struct *wq;
unsigned long flags;
struct ext4_inode_info *ei;
/* if not async direct IO or dio with 0 bytes write, just return */
if (!io_end || !size)
goto out;
ext_debug("ext4_end_io_dio(): io_end 0x%p"
"for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
iocb->private, io_end->inode->i_ino, iocb, offset,
size);
/* if not aio dio with unwritten extents, just free io and return */
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
ext4_free_io_end(io_end);
iocb->private = NULL;
out:
if (is_async)
aio_complete(iocb, ret, 0);
inode_dio_done(inode);
return;
}
io_end->offset = offset;
io_end->size = size;
if (is_async) {
io_end->iocb = iocb;
io_end->result = ret;
}
wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
/* Add the io_end to per-inode completed aio dio list*/
ei = EXT4_I(io_end->inode);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
list_add_tail(&io_end->list, &ei->i_completed_io_list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/* queue the work to convert unwritten extents to written */
queue_work(wq, &io_end->work);
iocb->private = NULL;
/* XXX: probably should move into the real I/O completion handler */
inode_dio_done(inode);
}
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
{
ext4_io_end_t *io_end = bh->b_private;
struct workqueue_struct *wq;
struct inode *inode;
unsigned long flags;
if (!test_clear_buffer_uninit(bh) || !io_end)
goto out;
if (!(io_end->inode->i_sb->s_flags & MS_ACTIVE)) {
printk("sb umounted, discard end_io request for inode %lu\n",
io_end->inode->i_ino);
ext4_free_io_end(io_end);
goto out;
}
/*
* It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
* but being more careful is always safe for the future change.
*/
inode = io_end->inode;
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
io_end->flag |= EXT4_IO_END_UNWRITTEN;
atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
}
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
/* queue the work to convert unwritten extents to written */
queue_work(wq, &io_end->work);
out:
bh->b_private = NULL;
bh->b_end_io = NULL;
clear_buffer_uninit(bh);
end_buffer_async_write(bh, uptodate);
}
static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
{
ext4_io_end_t *io_end;
struct page *page = bh->b_page;
loff_t offset = (sector_t)page->index << PAGE_CACHE_SHIFT;
size_t size = bh->b_size;
retry:
io_end = ext4_init_io_end(inode, GFP_ATOMIC);
if (!io_end) {
pr_warn_ratelimited("%s: allocation fail\n", __func__);
schedule();
goto retry;
}
io_end->offset = offset;
io_end->size = size;
/*
* We need to hold a reference to the page to make sure it
* doesn't get evicted before ext4_end_io_work() has a chance
* to convert the extent from written to unwritten.
*/
io_end->page = page;
get_page(io_end->page);
bh->b_private = io_end;
bh->b_end_io = ext4_end_io_buffer_write;
return 0;
}
/*
* For ext4 extent files, ext4 will do direct-io write to holes,
* preallocated extents, and those write extend the file, no need to
* fall back to buffered IO.
*
* For holes, we fallocate those blocks, mark them as uninitialized
* If those blocks were preallocated, we mark sure they are splited, but
* still keep the range to write as uninitialized.
*
* The unwrritten extents will be converted to written when DIO is completed.
* For async direct IO, since the IO may still pending when return, we
* set up an end_io call back function, which will do the conversion
* when async direct IO completed.
*
* If the O_DIRECT write will extend the file then add this inode to the
* orphan list. So recovery will truncate it back to the original size
* if the machine crashes during the write.
*
*/
static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
size_t count = iov_length(iov, nr_segs);
loff_t final_size = offset + count;
if (rw == WRITE && final_size <= inode->i_size) {
/*
* We could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as uninitialized
* to prevent parallel buffered read to expose the stale data
* before DIO complete the data IO.
*
* As to previously fallocated extents, ext4 get_block
* will just simply mark the buffer mapped but still
* keep the extents uninitialized.
*
* for non AIO case, we will convert those unwritten extents
* to written after return back from blockdev_direct_IO.
*
* for async DIO, the conversion needs to be defered when
* the IO is completed. The ext4 end_io callback function
* will be called to take care of the conversion work.
* Here for async case, we allocate an io_end structure to
* hook to the iocb.
*/
iocb->private = NULL;
EXT4_I(inode)->cur_aio_dio = NULL;
if (!is_sync_kiocb(iocb)) {
iocb->private = ext4_init_io_end(inode, GFP_NOFS);
if (!iocb->private)
return -ENOMEM;
/*
* we save the io structure for current async
* direct IO, so that later ext4_map_blocks()
* could flag the io structure whether there
* is a unwritten extents needs to be converted
* when IO is completed.
*/
EXT4_I(inode)->cur_aio_dio = iocb->private;
}
ret = __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext4_get_block_write,
ext4_end_io_dio,
NULL,
DIO_LOCKING | DIO_SKIP_HOLES);
if (iocb->private)
EXT4_I(inode)->cur_aio_dio = NULL;
/*
* The io_end structure takes a reference to the inode,
* that structure needs to be destroyed and the
* reference to the inode need to be dropped, when IO is
* complete, even with 0 byte write, or failed.
*
* In the successful AIO DIO case, the io_end structure will be
* desctroyed and the reference to the inode will be dropped
* after the end_io call back function is called.
*
* In the case there is 0 byte write, or error case, since
* VFS direct IO won't invoke the end_io call back function,
* we need to free the end_io structure here.
*/
if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
ext4_free_io_end(iocb->private);
iocb->private = NULL;
} else if (ret > 0 && ext4_test_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN)) {
int err;
/*
* for non AIO case, since the IO is already
* completed, we could do the conversion right here
*/
err = ext4_convert_unwritten_extents(inode,
offset, ret);
if (err < 0)
ret = err;
ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
}
return ret;
}
/* for write the the end of file case, we fall back to old way */
return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
}
static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
else
ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
trace_ext4_direct_IO_exit(inode, offset,
iov_length(iov, nr_segs), rw, ret);
return ret;
}
/*
* 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.
*
* We cannot just dirty the page 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
* is called, propagate that into the buffers appropriately.
*/
static int ext4_journalled_set_page_dirty(struct page *page)
{
SetPageChecked(page);
return __set_page_dirty_nobuffers(page);
}
static const struct address_space_operations ext4_ordered_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.write_begin = ext4_write_begin,
.write_end = ext4_ordered_write_end,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_writeback_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.write_begin = ext4_write_begin,
.write_end = ext4_writeback_write_end,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_journalled_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
.set_page_dirty = ext4_journalled_set_page_dirty,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_da_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
.writepages = ext4_da_writepages,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.bmap = ext4_bmap,
.invalidatepage = ext4_da_invalidatepage,
.releasepage = ext4_releasepage,
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
void ext4_set_aops(struct inode *inode)
{
if (ext4_should_order_data(inode) &&
test_opt(inode->i_sb, DELALLOC))
inode->i_mapping->a_ops = &ext4_da_aops;
else if (ext4_should_order_data(inode))
inode->i_mapping->a_ops = &ext4_ordered_aops;
else if (ext4_should_writeback_data(inode) &&
test_opt(inode->i_sb, DELALLOC))
inode->i_mapping->a_ops = &ext4_da_aops;
else if (ext4_should_writeback_data(inode))
inode->i_mapping->a_ops = &ext4_writeback_aops;
else
inode->i_mapping->a_ops = &ext4_journalled_aops;
}
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
* This required during truncate. We need to physically zero the tail end
* of that block so it doesn't yield old data if the file is later grown.
*/
int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from)
{
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned length;
unsigned blocksize;
struct inode *inode = mapping->host;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
return ext4_block_zero_page_range(handle, mapping, from, length);
}
/*
* ext4_block_zero_page_range() zeros out a mapping of length 'length'
* starting from file offset 'from'. The range to be zero'd must
* be contained with in one block. If the specified range exceeds
* the end of the block it will be shortened to end of the block
* that cooresponds to 'from'
*/
int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned blocksize, max, pos;
ext4_lblk_t iblock;
struct inode *inode = mapping->host;
struct buffer_head *bh;
struct page *page;
int err = 0;
page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
mapping_gfp_mask(mapping) & ~__GFP_FS);
if (!page)
return -EINVAL;
blocksize = inode->i_sb->s_blocksize;
max = blocksize - (offset & (blocksize - 1));
/*
* correct length if it does not fall between
* 'from' and the end of the block
*/
if (length > max || length < 0)
length = max;
iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
/* Find the buffer that contains "offset" */
bh = page_buffers(page);
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
iblock++;
pos += blocksize;
}
err = 0;
if (buffer_freed(bh)) {
BUFFER_TRACE(bh, "freed: skip");
goto unlock;
}
if (!buffer_mapped(bh)) {
BUFFER_TRACE(bh, "unmapped");
ext4_get_block(inode, iblock, bh, 0);
/* unmapped? It's a hole - nothing to do */
if (!buffer_mapped(bh)) {
BUFFER_TRACE(bh, "still unmapped");
goto unlock;
}
}
/* Ok, it's mapped. Make sure it's up-to-date */
if (PageUptodate(page))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh)) {
err = -EIO;
ll_rw_block(READ, 1, &bh);
wait_on_buffer(bh);
/* Uhhuh. Read error. Complain and punt. */
if (!buffer_uptodate(bh))
goto unlock;
}
if (ext4_should_journal_data(inode)) {
BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
goto unlock;
}
zero_user(page, offset, length);
BUFFER_TRACE(bh, "zeroed end of block");
err = 0;
if (ext4_should_journal_data(inode)) {
err = ext4_handle_dirty_metadata(handle, inode, bh);
} else {
if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
err = ext4_jbd2_file_inode(handle, inode);
mark_buffer_dirty(bh);
}
unlock:
unlock_page(page);
page_cache_release(page);
return err;
}
int ext4_can_truncate(struct inode *inode)
{
if (S_ISREG(inode->i_mode))
return 1;
if (S_ISDIR(inode->i_mode))
return 1;
if (S_ISLNK(inode->i_mode))
return !ext4_inode_is_fast_symlink(inode);
return 0;
}
/*
* ext4_punch_hole: punches a hole in a file by releaseing the blocks
* associated with the given offset and length
*
* @inode: File inode
* @offset: The offset where the hole will begin
* @len: The length of the hole
*
* Returns: 0 on sucess or negative on failure
*/
int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
{
struct inode *inode = file->f_path.dentry->d_inode;
if (!S_ISREG(inode->i_mode))
return -ENOTSUPP;
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
/* TODO: Add support for non extent hole punching */
return -ENOTSUPP;
}
return ext4_ext_punch_hole(file, offset, length);
}
/*
* ext4_truncate()
*
* We block out ext4_get_block() block instantiations across the entire
* transaction, and VFS/VM ensures that ext4_truncate() cannot run
* simultaneously on behalf of the same inode.
*
* As we work through the truncate and commmit bits of it to the journal there
* is one core, guiding principle: the file's tree must always be consistent on
* disk. We must be able to restart the truncate after a crash.
*
* The file's tree may be transiently inconsistent in memory (although it
* probably isn't), but whenever we close off and commit a journal transaction,
* the contents of (the filesystem + the journal) must be consistent and
* restartable. It's pretty simple, really: bottom up, right to left (although
* left-to-right works OK too).
*
* Note that at recovery time, journal replay occurs *before* the restart of
* truncate against the orphan inode list.
*
* The committed inode has the new, desired i_size (which is the same as
* i_disksize in this case). After a crash, ext4_orphan_cleanup() will see
* that this inode's truncate did not complete and it will again call
* ext4_truncate() to have another go. So there will be instantiated blocks
* to the right of the truncation point in a crashed ext4 filesystem. But
* that's fine - as long as they are linked from the inode, the post-crash
* ext4_truncate() run will find them and release them.
*/
void ext4_truncate(struct inode *inode)
{
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
return;
ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ext4_ext_truncate(inode);
else
ext4_ind_truncate(inode);
trace_ext4_truncate_exit(inode);
}
/*
* ext4_get_inode_loc returns with an extra refcount against the inode's
* underlying buffer_head on success. If 'in_mem' is true, we have all
* data in memory that is needed to recreate the on-disk version of this
* inode.
*/
static int __ext4_get_inode_loc(struct inode *inode,
struct ext4_iloc *iloc, int in_mem)
{
struct ext4_group_desc *gdp;
struct buffer_head *bh;
struct super_block *sb = inode->i_sb;
ext4_fsblk_t block;
int inodes_per_block, inode_offset;
iloc->bh = NULL;
if (!ext4_valid_inum(sb, inode->i_ino))
return -EIO;
iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
if (!gdp)
return -EIO;
/*
* Figure out the offset within the block group inode table
*/
inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
inode_offset = ((inode->i_ino - 1) %
EXT4_INODES_PER_GROUP(sb));
block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
bh = sb_getblk(sb, block);
if (!bh) {
EXT4_ERROR_INODE_BLOCK(inode, block,
"unable to read itable block");
return -EIO;
}
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
/*
* If the buffer has the write error flag, we have failed
* to write out another inode in the same block. In this
* case, we don't have to read the block because we may
* read the old inode data successfully.
*/
if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
set_buffer_uptodate(bh);
if (buffer_uptodate(bh)) {
/* someone brought it uptodate while we waited */
unlock_buffer(bh);
goto has_buffer;
}
/*
* If we have all information of the inode in memory and this
* is the only valid inode in the block, we need not read the
* block.
*/
if (in_mem) {
struct buffer_head *bitmap_bh;
int i, start;
start = inode_offset & ~(inodes_per_block - 1);
/* Is the inode bitmap in cache? */
bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
if (!bitmap_bh)
goto make_io;
/*
* If the inode bitmap isn't in cache then the
* optimisation may end up performing two reads instead
* of one, so skip it.
*/
if (!buffer_uptodate(bitmap_bh)) {
brelse(bitmap_bh);
goto make_io;
}
for (i = start; i < start + inodes_per_block; i++) {
if (i == inode_offset)
continue;
if (ext4_test_bit(i, bitmap_bh->b_data))
break;
}
brelse(bitmap_bh);
if (i == start + inodes_per_block) {
/* all other inodes are free, so skip I/O */
memset(bh->b_data, 0, bh->b_size);
set_buffer_uptodate(bh);
unlock_buffer(bh);
goto has_buffer;
}
}
make_io:
/*
* If we need to do any I/O, try to pre-readahead extra
* blocks from the inode table.
*/
if (EXT4_SB(sb)->s_inode_readahead_blks) {
ext4_fsblk_t b, end, table;
unsigned num;
table = ext4_inode_table(sb, gdp);
/* s_inode_readahead_blks is always a power of 2 */
b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1);
if (table > b)
b = table;
end = b + EXT4_SB(sb)->s_inode_readahead_blks;
num = EXT4_INODES_PER_GROUP(sb);
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
num -= ext4_itable_unused_count(sb, gdp);
table += num / inodes_per_block;
if (end > table)
end = table;
while (b <= end)
sb_breadahead(sb, b++);
}
/*
* There are other valid inodes in the buffer, this inode
* has in-inode xattrs, or we don't have this inode in memory.
* Read the block from disk.
*/
trace_ext4_load_inode(inode);
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(READ | REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
EXT4_ERROR_INODE_BLOCK(inode, block,
"unable to read itable block");
brelse(bh);
return -EIO;
}
}
has_buffer:
iloc->bh = bh;
return 0;
}
int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
{
/* We have all inode data except xattrs in memory here. */
return __ext4_get_inode_loc(inode, iloc,
!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
}
void ext4_set_inode_flags(struct inode *inode)
{
unsigned int flags = EXT4_I(inode)->i_flags;
inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
if (flags & EXT4_SYNC_FL)
inode->i_flags |= S_SYNC;
if (flags & EXT4_APPEND_FL)
inode->i_flags |= S_APPEND;
if (flags & EXT4_IMMUTABLE_FL)
inode->i_flags |= S_IMMUTABLE;
if (flags & EXT4_NOATIME_FL)
inode->i_flags |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
inode->i_flags |= S_DIRSYNC;
}
/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
void ext4_get_inode_flags(struct ext4_inode_info *ei)
{
unsigned int vfs_fl;
unsigned long old_fl, new_fl;
do {
vfs_fl = ei->vfs_inode.i_flags;
old_fl = ei->i_flags;
new_fl = old_fl & ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|
EXT4_DIRSYNC_FL);
if (vfs_fl & S_SYNC)
new_fl |= EXT4_SYNC_FL;
if (vfs_fl & S_APPEND)
new_fl |= EXT4_APPEND_FL;
if (vfs_fl & S_IMMUTABLE)
new_fl |= EXT4_IMMUTABLE_FL;
if (vfs_fl & S_NOATIME)
new_fl |= EXT4_NOATIME_FL;
if (vfs_fl & S_DIRSYNC)
new_fl |= EXT4_DIRSYNC_FL;
} while (cmpxchg(&ei->i_flags, old_fl, new_fl) != old_fl);
}
static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
blkcnt_t i_blocks ;
struct inode *inode = &(ei->vfs_inode);
struct super_block *sb = inode->i_sb;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
/* we are using combined 48 bit field */
i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 |
le32_to_cpu(raw_inode->i_blocks_lo);
if (ext4_test_inode_flag(inode, EXT4_INODE_HUGE_FILE)) {
/* i_blocks represent file system block size */
return i_blocks << (inode->i_blkbits - 9);
} else {
return i_blocks;
}
} else {
return le32_to_cpu(raw_inode->i_blocks_lo);
}
}
struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
{
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
struct inode *inode;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
int block;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
ei = EXT4_I(inode);
iloc.bh = NULL;
ret = __ext4_get_inode_loc(inode, &iloc, 0);
if (ret < 0)
goto bad_inode;
raw_inode = ext4_raw_inode(&iloc);
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
if (!(test_opt(inode->i_sb, NO_UID32))) {
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
ei->i_dir_start_lookup = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
* This is needed because nfsd might try to access dead inodes
* the test is that same one that e2fsck uses
* NeilBrown 1999oct15
*/
if (inode->i_nlink == 0) {
if (inode->i_mode == 0 ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
/* this inode is deleted */
ret = -ESTALE;
goto bad_inode;
}
/* The only unlinked inodes we let through here have
* valid i_mode and are being read by the orphan
* recovery code: that's fine, we're about to complete
* the process of deleting those. */
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT))
ei->i_file_acl |=
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(raw_inode);
ei->i_disksize = inode->i_size;
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
#endif
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_block_group = iloc.block_group;
ei->i_last_alloc_group = ~0;
/*
* NOTE! The in-memory inode i_data array is in little-endian order
* even on big-endian machines: we do NOT byteswap the block numbers!
*/
for (block = 0; block < EXT4_N_BLOCKS; block++)
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
/*
* Set transaction id's of transactions that have to be committed
* to finish f[data]sync. We set them to currently running transaction
* as we cannot be sure that the inode or some of its metadata isn't
* part of the transaction - the inode could have been reclaimed and
* now it is reread from disk.
*/
if (journal) {
transaction_t *transaction;
tid_t tid;
read_lock(&journal->j_state_lock);
if (journal->j_running_transaction)
transaction = journal->j_running_transaction;
else
transaction = journal->j_committing_transaction;
if (transaction)
tid = transaction->t_tid;
else
tid = journal->j_commit_sequence;
read_unlock(&journal->j_state_lock);
ei->i_sync_tid = tid;
ei->i_datasync_tid = tid;
}
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT4_INODE_SIZE(inode->i_sb)) {
ret = -EIO;
goto bad_inode;
}
if (ei->i_extra_isize == 0) {
/* The extra space is currently unused. Use it. */
ei->i_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
} else {
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE +
ei->i_extra_isize;
if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
}
} else
ei->i_extra_isize = 0;
EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode);
EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
inode->i_version |=
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
ret = 0;
if (ei->i_file_acl &&
!ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
EXT4_ERROR_INODE(inode, "bad extended attribute block %llu",
ei->i_file_acl);
ret = -EIO;
goto bad_inode;
} else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
(S_ISLNK(inode->i_mode) &&
!ext4_inode_is_fast_symlink(inode)))
/* Validate extent which is part of inode */
ret = ext4_ext_check_inode(inode);
} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
(S_ISLNK(inode->i_mode) &&
!ext4_inode_is_fast_symlink(inode))) {
/* Validate block references which are part of inode */
ret = ext4_ind_check_inode(inode);
}
if (ret)
goto bad_inode;
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
if (ext4_inode_is_fast_symlink(inode)) {
inode->i_op = &ext4_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) - 1);
} else {
inode->i_op = &ext4_symlink_inode_operations;
ext4_set_aops(inode);
}
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &ext4_special_inode_operations;
if (raw_inode->i_block[0])
init_special_inode(inode, inode->i_mode,
old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
} else {
ret = -EIO;
EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);
goto bad_inode;
}
brelse(iloc.bh);
ext4_set_inode_flags(inode);
unlock_new_inode(inode);
return inode;
bad_inode:
brelse(iloc.bh);
iget_failed(inode);
return ERR_PTR(ret);
}
static int ext4_inode_blocks_set(handle_t *handle,
struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
struct inode *inode = &(ei->vfs_inode);
u64 i_blocks = inode->i_blocks;
struct super_block *sb = inode->i_sb;
if (i_blocks <= ~0U) {
/*
* i_blocks can be represnted in a 32 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = 0;
ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
return 0;
}
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
return -EFBIG;
if (i_blocks <= 0xffffffffffffULL) {
/*
* i_blocks can be represented in a 48 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
} else {
ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE);
/* i_block is stored in file system block size */
i_blocks = i_blocks >> (inode->i_blkbits - 9);
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
}
return 0;
}
/*
* Post the struct inode info into an on-disk inode location in the
* buffer-cache. This gobbles the caller's reference to the
* buffer_head in the inode location struct.
*
* The caller must have write access to iloc->bh.
*/
static int ext4_do_update_inode(handle_t *handle,
struct inode *inode,
struct ext4_iloc *iloc)
{
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
int err = 0, rc, block;
/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
ext4_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if (!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
/*
* Fix up interoperability with old kernels. Otherwise, old inodes get
* re-used with the upper 16 bits of the uid/gid intact
*/
if (!ei->i_dtime) {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(inode->i_uid));
raw_inode->i_gid_high =
cpu_to_le16(high_16_bits(inode->i_gid));
} else {
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
}
} else {
raw_inode->i_uid_low =
cpu_to_le16(fs_high2lowuid(inode->i_uid));
raw_inode->i_gid_low =
cpu_to_le16(fs_high2lowgid(inode->i_gid));
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
if (ext4_inode_blocks_set(handle, raw_inode, ei))
goto out_brelse;
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
raw_inode->i_file_acl_high =
cpu_to_le16(ei->i_file_acl >> 32);
raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
ext4_isize_set(raw_inode, ei->i_disksize);
if (ei->i_disksize > 0x7fffffffULL) {
struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT4_SB(sb)->s_es->s_rev_level ==
cpu_to_le32(EXT4_GOOD_OLD_REV)) {
/* If this is the first large file
* created, add a flag to the superblock.
*/
err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh);
if (err)
goto out_brelse;
ext4_update_dynamic_rev(sb);
EXT4_SET_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
sb->s_dirt = 1;
ext4_handle_sync(handle);
err = ext4_handle_dirty_metadata(handle, NULL,
EXT4_SB(sb)->s_sbh);
}
}
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
raw_inode->i_block[0] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
raw_inode->i_block[1] = 0;
} else {
raw_inode->i_block[0] = 0;
raw_inode->i_block[1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
raw_inode->i_block[2] = 0;
}
} else
for (block = 0; block < EXT4_N_BLOCKS; block++)
raw_inode->i_block[block] = ei->i_data[block];
raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
if (ei->i_extra_isize) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
raw_inode->i_version_hi =
cpu_to_le32(inode->i_version >> 32);
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
rc = ext4_handle_dirty_metadata(handle, NULL, bh);
if (!err)
err = rc;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
ext4_update_inode_fsync_trans(handle, inode, 0);
out_brelse:
brelse(bh);
ext4_std_error(inode->i_sb, err);
return err;
}
/*
* ext4_write_inode()
*
* We are called from a few places:
*
* - Within generic_file_write() for O_SYNC files.
* Here, there will be no transaction running. We wait for any running
* trasnaction to commit.
*
* - Within sys_sync(), kupdate and such.
* We wait on commit, if tol to.
*
* - Within prune_icache() (PF_MEMALLOC == true)
* Here we simply return. We can't afford to block kswapd on the
* journal commit.
*
* In all cases it is actually safe for us to return without doing anything,
* because the inode has been copied into a raw inode buffer in
* ext4_mark_inode_dirty(). This is a correctness thing for O_SYNC and for
* knfsd.
*
* Note that we are absolutely dependent upon all inode dirtiers doing the
* right thing: they *must* call mark_inode_dirty() after dirtying info in
* which we are interested.
*
* It would be a bug for them to not do this. The code:
*
* mark_inode_dirty(inode)
* stuff();
* inode->i_size = expr;
*
* is in error because a kswapd-driven write_inode() could occur while
* `stuff()' is running, and the new i_size will be lost. Plus the inode
* will no longer be on the superblock's dirty inode list.
*/
int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err;
if (current->flags & PF_MEMALLOC)
return 0;
if (EXT4_SB(inode->i_sb)->s_journal) {
if (ext4_journal_current_handle()) {
jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
dump_stack();
return -EIO;
}
if (wbc->sync_mode != WB_SYNC_ALL)
return 0;
err = ext4_force_commit(inode->i_sb);
} else {
struct ext4_iloc iloc;
err = __ext4_get_inode_loc(inode, &iloc, 0);
if (err)
return err;
if (wbc->sync_mode == WB_SYNC_ALL)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
"IO error syncing inode");
err = -EIO;
}
brelse(iloc.bh);
}
return err;
}
/*
* ext4_setattr()
*
* Called from notify_change.
*
* We want to trap VFS attempts to truncate the file as soon as
* possible. In particular, we want to make sure that when the VFS
* shrinks i_size, we put the inode on the orphan list and modify
* i_disksize immediately, so that during the subsequent flushing of
* dirty pages and freeing of disk blocks, we can guarantee that any
* commit will leave the blocks being flushed in an unused state on
* disk. (On recovery, the inode will get truncated and the blocks will
* be freed, so we have a strong guarantee that no future commit will
* leave these blocks visible to the user.)
*
* Another thing we have to assure is that if we are in ordered mode
* and inode is still attached to the committing transaction, we must
* we start writeout of all the dirty pages which are being truncated.
* This way we are sure that all the data written in the previous
* transaction are already on disk (truncate waits for pages under
* writeback).
*
* Called with inode->i_mutex down.
*/
int ext4_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
int error, rc = 0;
int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
error = inode_change_ok(inode, attr);
if (error)
return error;
if (is_quota_modification(inode, attr))
dquot_initialize(inode);
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
handle_t *handle;
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
}
error = dquot_transfer(inode, attr);
if (error) {
ext4_journal_stop(handle);
return error;
}
/* Update corresponding info in inode so that everything is in
* one transaction */
if (attr->ia_valid & ATTR_UID)
inode->i_uid = attr->ia_uid;
if (attr->ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
}
if (attr->ia_valid & ATTR_SIZE) {
inode_dio_wait(inode);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (attr->ia_size > sbi->s_bitmap_maxbytes)
return -EFBIG;
}
}
if (S_ISREG(inode->i_mode) &&
attr->ia_valid & ATTR_SIZE &&
(attr->ia_size < inode->i_size)) {
handle_t *handle;
handle = ext4_journal_start(inode, 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
}
if (ext4_handle_valid(handle)) {
error = ext4_orphan_add(handle, inode);
orphan = 1;
}
EXT4_I(inode)->i_disksize = attr->ia_size;
rc = ext4_mark_inode_dirty(handle, inode);
if (!error)
error = rc;
ext4_journal_stop(handle);
if (ext4_should_order_data(inode)) {
error = ext4_begin_ordered_truncate(inode,
attr->ia_size);
if (error) {
/* Do as much error cleanup as possible */
handle = ext4_journal_start(inode, 3);
if (IS_ERR(handle)) {
ext4_orphan_del(NULL, inode);
goto err_out;
}
ext4_orphan_del(handle, inode);
orphan = 0;
ext4_journal_stop(handle);
goto err_out;
}
}
}
if (attr->ia_valid & ATTR_SIZE) {
if (attr->ia_size != i_size_read(inode)) {
truncate_setsize(inode, attr->ia_size);
ext4_truncate(inode);
} else if (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
ext4_truncate(inode);
}
if (!rc) {
setattr_copy(inode, attr);
mark_inode_dirty(inode);
}
/*
* If the call to ext4_truncate failed to get a transaction handle at
* all, we need to clean up the in-core orphan list manually.
*/
if (orphan && inode->i_nlink)
ext4_orphan_del(NULL, inode);
if (!rc && (ia_valid & ATTR_MODE))
rc = ext4_acl_chmod(inode);
err_out:
ext4_std_error(inode->i_sb, error);
if (!error)
error = rc;
return error;
}
int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode;
unsigned long delalloc_blocks;
inode = dentry->d_inode;
generic_fillattr(inode, stat);
/*
* We can't update i_blocks if the block allocation is delayed
* otherwise in the case of system crash before the real block
* allocation is done, we will have i_blocks inconsistent with
* on-disk file blocks.
* We always keep i_blocks updated together with real
* allocation. But to not confuse with user, stat
* will return the blocks that include the delayed allocation
* blocks for this file.
*/
delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks;
stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
return 0;
}
static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return ext4_ind_trans_blocks(inode, nrblocks, chunk);
return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
}
/*
* Account for index blocks, block groups bitmaps and block group
* descriptor blocks if modify datablocks and index blocks
* worse case, the indexs blocks spread over different block groups
*
* If datablocks are discontiguous, they are possible to spread over
* different block groups too. If they are contiuguous, with flexbg,
* they could still across block group boundary.
*
* Also account for superblock, inode, quota and xattr blocks
*/
static int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
int gdpblocks;
int idxblocks;
int ret = 0;
/*
* How many index blocks need to touch to modify nrblocks?
* The "Chunk" flag indicating whether the nrblocks is
* physically contiguous on disk
*
* For Direct IO and fallocate, they calls get_block to allocate
* one single extent at a time, so they could set the "Chunk" flag
*/
idxblocks = ext4_index_trans_blocks(inode, nrblocks, chunk);
ret = idxblocks;
/*
* Now let's see how many group bitmaps and group descriptors need
* to account
*/
groups = idxblocks;
if (chunk)
groups += 1;
else
groups += nrblocks;
gdpblocks = groups;
if (groups > ngroups)
groups = ngroups;
if (groups > EXT4_SB(inode->i_sb)->s_gdb_count)
gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count;
/* bitmaps and block group descriptor blocks */
ret += groups + gdpblocks;
/* Blocks for super block, inode, quota and xattr blocks */
ret += EXT4_META_TRANS_BLOCKS(inode->i_sb);
return ret;
}
/*
* Calculate the total number of credits to reserve to fit
* the modification of a single pages into a single transaction,
* which may include multiple chunks of block allocations.
*
* This could be called via ext4_write_begin()
*
* We need to consider the worse case, when
* one new block per extent.
*/
int ext4_writepage_trans_blocks(struct inode *inode)
{
int bpp = ext4_journal_blocks_per_page(inode);
int ret;
ret = ext4_meta_trans_blocks(inode, bpp, 0);
/* Account for data blocks for journalled mode */
if (ext4_should_journal_data(inode))
ret += bpp;
return ret;
}
/*
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
* ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
*/
int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks)
{
return ext4_meta_trans_blocks(inode, nrblocks, 1);
}
/*
* The caller must have previously called ext4_reserve_inode_write().
* Give this, we know that the caller already has write access to iloc->bh.
*/
int ext4_mark_iloc_dirty(handle_t *handle,
struct inode *inode, struct ext4_iloc *iloc)
{
int err = 0;
if (test_opt(inode->i_sb, I_VERSION))
inode_inc_iversion(inode);
/* the do_update_inode consumes one bh->b_count */
get_bh(iloc->bh);
/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
err = ext4_do_update_inode(handle, inode, iloc);
put_bh(iloc->bh);
return err;
}
/*
* On success, We end up with an outstanding reference count against
* iloc->bh. This _must_ be cleaned up later.
*/
int
ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc)
{
int err;
err = ext4_get_inode_loc(inode, iloc);
if (!err) {
BUFFER_TRACE(iloc->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err) {
brelse(iloc->bh);
iloc->bh = NULL;
}
}
ext4_std_error(inode->i_sb, err);
return err;
}
/*
* Expand an inode by new_extra_isize bytes.
* Returns 0 on success or negative error number on failure.
*/
static int ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc iloc,
handle_t *handle)
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;
if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
return 0;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
/* No extended attributes present */
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
new_extra_isize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
return 0;
}
/* try to expand with EAs present */
return ext4_expand_extra_isize_ea(inode, new_extra_isize,
raw_inode, handle);
}
/*
* What we do here is to mark the in-core inode as clean with respect to inode
* dirtiness (it may still be data-dirty).
* This means that the in-core inode may be reaped by prune_icache
* without having to perform any I/O. This is a very good thing,
* because *any* task may call prune_icache - even ones which
* have a transaction open against a different journal.
*
* Is this cheating? Not really. Sure, we haven't written the
* inode out, but prune_icache isn't a user-visible syncing function.
* Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
* we start and wait on commits.
*
* Is this efficient/effective? Well, we're being nice to the system
* by cleaning up our inodes proactively so they can be reaped
* without I/O. But we are potentially leaving up to five seconds'
* worth of inodes floating about which prune_icache wants us to
* write out. One way to fix that would be to get prune_icache()
* to do a write_super() to free up some memory. It has the desired
* effect.
*/
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
{
struct ext4_iloc iloc;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
static unsigned int mnt_count;
int err, ret;
might_sleep();
trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (ext4_handle_valid(handle) &&
EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
!ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
/*
* We need extra buffer credits since we may write into EA block
* with this same handle. If journal_extend fails, then it will
* only result in a minor loss of functionality for that inode.
* If this is felt to be critical, then e2fsck should be run to
* force a large enough s_min_extra_isize.
*/
if ((jbd2_journal_extend(handle,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb))) == 0) {
ret = ext4_expand_extra_isize(inode,
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
ext4_set_inode_state(inode,
EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
"Unable to expand inode %lu. Delete"
" some EAs or run e2fsck.",
inode->i_ino);
mnt_count =
le16_to_cpu(sbi->s_es->s_mnt_count);
}
}
}
}
if (!err)
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
return err;
}
/*
* ext4_dirty_inode() is called from __mark_inode_dirty()
*
* We're really interested in the case where a file is being extended.
* i_size has been changed by generic_commit_write() and we thus need
* to include the updated inode in the current transaction.
*
* Also, dquot_alloc_block() will always dirty the inode when blocks
* are allocated to the file.
*
* If the inode is marked synchronous, we don't honour that here - doing
* so would cause a commit on atime updates, which we don't bother doing.
* We handle synchronous inodes at the highest possible level.
*/
void ext4_dirty_inode(struct inode *inode, int flags)
{
handle_t *handle;
handle = ext4_journal_start(inode, 2);
if (IS_ERR(handle))
goto out;
ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
out:
return;
}
#if 0
/*
* Bind an inode's backing buffer_head into this transaction, to prevent
* it from being flushed to disk early. Unlike
* ext4_reserve_inode_write, this leaves behind no bh reference and
* returns no iloc structure, so the caller needs to repeat the iloc
* lookup to mark the inode dirty later.
*/
static int ext4_pin_inode(handle_t *handle, struct inode *inode)
{
struct ext4_iloc iloc;
int err = 0;
if (handle) {
err = ext4_get_inode_loc(inode, &iloc);
if (!err) {
BUFFER_TRACE(iloc.bh, "get_write_access");
err = jbd2_journal_get_write_access(handle, iloc.bh);
if (!err)
err = ext4_handle_dirty_metadata(handle,
NULL,
iloc.bh);
brelse(iloc.bh);
}
}
ext4_std_error(inode->i_sb, err);
return err;
}
#endif
int ext4_change_inode_journal_flag(struct inode *inode, int val)
{
journal_t *journal;
handle_t *handle;
int err;
/*
* We have to be very careful here: changing a data block's
* journaling status dynamically is dangerous. If we write a
* data block to the journal, change the status and then delete
* that block, we risk forgetting to revoke the old log record
* from the journal and so a subsequent replay can corrupt data.
* So, first we make sure that the journal is empty and that
* nobody is changing anything.
*/
journal = EXT4_JOURNAL(inode);
if (!journal)
return 0;
if (is_journal_aborted(journal))
return -EROFS;
jbd2_journal_lock_updates(journal);
jbd2_journal_flush(journal);
/*
* OK, there are no updates running now, and all cached data is
* synced to disk. We are now in a completely consistent state
* which doesn't have anything in the journal, and we know that
* no filesystem updates are running, so it is safe to modify
* the inode's in-core data-journaling state flag now.
*/
if (val)
ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else
ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
/* Finally we can mark the inode as dirty. */
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
err = ext4_mark_inode_dirty(handle, inode);
ext4_handle_sync(handle);
ext4_journal_stop(handle);
ext4_std_error(inode->i_sb, err);
return err;
}
static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh)
{
return !buffer_mapped(bh);
}
int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
loff_t size;
unsigned long len;
int ret;
struct file *file = vma->vm_file;
struct inode *inode = file->f_path.dentry->d_inode;
struct address_space *mapping = inode->i_mapping;
handle_t *handle;
get_block_t *get_block;
int retries = 0;
/*
* This check is racy but catches the common case. We rely on
* __block_page_mkwrite() to do a reliable check.
*/
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_should_journal_data(inode) &&
!ext4_nonda_switch(inode->i_sb)) {
do {
ret = __block_page_mkwrite(vma, vmf,
ext4_da_get_block_prep);
} while (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries));
goto out_ret;
}
lock_page(page);
size = i_size_read(inode);
/* Page got truncated from under us? */
if (page->mapping != mapping || page_offset(page) > size) {
unlock_page(page);
ret = VM_FAULT_NOPAGE;
goto out;
}
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
/*
* Return if we have all the buffers mapped. This avoids the need to do
* journal_start/journal_stop which can block and take a long time
*/
if (page_has_buffers(page)) {
if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
ext4_bh_unmapped)) {
/* Wait so that we don't change page under IO */
wait_on_page_writeback(page);
ret = VM_FAULT_LOCKED;
goto out;
}
}
unlock_page(page);
/* OK, we need to fill the hole... */
if (ext4_should_dioread_nolock(inode))
get_block = ext4_get_block_write;
else
get_block = ext4_get_block;
retry_alloc:
handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = VM_FAULT_SIGBUS;
goto out;
}
ret = __block_page_mkwrite(vma, vmf, get_block);
if (!ret && ext4_should_journal_data(inode)) {
if (walk_page_buffers(handle, page_buffers(page), 0,
PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
unlock_page(page);
ret = VM_FAULT_SIGBUS;
goto out;
}
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
}
ext4_journal_stop(handle);
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_alloc;
out_ret:
ret = block_page_mkwrite_return(ret);
out:
return ret;
}
View Git Blame Copy Permalink