inode.c

/*
 *  linux/fs/ext4/inode.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *	(jj@sunsite.ms.mff.cuni.cz)
 *
 *  Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
 */

#include <linux/fs.h>
#include <linux/time.h>
#include <linux/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 "truncate.h"

#include <trace/events/ext4.h>

#define MPAGE_DA_EXTENT_TAIL 0x01

static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
			      struct ext4_inode_info *ei)
{
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
	__u16 csum_lo;
	__u16 csum_hi = 0;
	__u32 csum;

	csum_lo = raw->i_checksum_lo;
	raw->i_checksum_lo = 0;
	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
		csum_hi = raw->i_checksum_hi;
		raw->i_checksum_hi = 0;
	}

	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
			   EXT4_INODE_SIZE(inode->i_sb));

	raw->i_checksum_lo = csum_lo;
	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
		raw->i_checksum_hi = csum_hi;

	return csum;
}

static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
				  struct ext4_inode_info *ei)
{
	__u32 provided, calculated;

	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
	    cpu_to_le32(EXT4_OS_LINUX) ||
	    !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
		return 1;

	provided = le16_to_cpu(raw->i_checksum_lo);
	calculated = ext4_inode_csum(inode, raw, ei);
	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
		provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16;
	else
		calculated &= 0xFFFF;

	return provided == calculated;
}

static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
				struct ext4_inode_info *ei)
{
	__u32 csum;

	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
	    cpu_to_le32(EXT4_OS_LINUX) ||
	    !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
		return;

	csum = ext4_inode_csum(inode, raw, ei);
	raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF);
	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
		raw->i_checksum_hi = cpu_to_le16(csum >> 16);
}

static inline int ext4_begin_ordered_truncate(struct inode *inode,
					      loff_t new_size)
{
	trace_ext4_begin_ordered_truncate(inode, new_size);
	/*
	 * If jinode is zero, then we never opened the file for
	 * writing, so there's no need to call
	 * jbd2_journal_begin_ordered_truncate() since there's no
	 * outstanding writes we need to flush.
	 */
	if (!EXT4_I(inode)->jinode)
		return 0;
	return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
						   EXT4_I(inode)->jinode,
						   new_size);
}

static void ext4_invalidatepage(struct page *page, unsigned 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);
static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
		struct inode *inode, struct page *page, loff_t from,
		loff_t length, int flags);

/*
 * 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;

	/*
	 * Protect us against freezing - iput() caller didn't have to have any
	 * protection against it
	 */
	sb_start_intwrite(inode->i_sb);
	handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3);
	if (IS_ERR(handle)) {
		ext4_std_error(inode->i_sb, PTR_ERR(handle));
		/*
		 * If we're going to skip the normal cleanup, we still need to
		 * make sure that the in-core orphan linked list is properly
		 * cleaned up.
		 */
		ext4_orphan_del(NULL, inode);
		sb_end_intwrite(inode->i_sb);
		goto no_delete;
	}

	if (IS_SYNC(inode))
		ext4_handle_sync(handle);
	inode->i_size = 0;
	err = ext4_mark_inode_dirty(handle, inode);
	if (err) {
		ext4_warning(inode->i_sb,
			     "couldn't mark inode dirty (err %d)", err);
		goto stop_handle;
	}
	if (inode->i_blocks)
		ext4_truncate(inode);

	/*
	 * ext4_ext_truncate() doesn't reserve any slop when it
	 * restarts journal transactions; therefore there may not be
	 * enough credits left in the handle to remove the inode from
	 * the orphan list and set the dtime field.
	 */
	if (!ext4_handle_has_enough_credits(handle, 3)) {
		err = ext4_journal_extend(handle, 3);
		if (err > 0)
			err = ext4_journal_restart(handle, 3);
		if (err != 0) {
			ext4_warning(inode->i_sb,
				     "couldn't extend journal (err %d)", err);
		stop_handle:
			ext4_journal_stop(handle);
			ext4_orphan_del(NULL, inode);
			sb_end_intwrite(inode->i_sb);
			goto no_delete;
		}
	}

	/*
	 * Kill off the orphan record which ext4_truncate created.
	 * AKPM: I think this can be inside the above `if'.
	 * Note that ext4_orphan_del() has to be able to cope with the
	 * deletion of a non-existent orphan - this is because we don't
	 * know if ext4_truncate() actually created an orphan record.
	 * (Well, we could do this if we need to, but heck - it works)
	 */
	ext4_orphan_del(handle, inode);
	EXT4_I(inode)->i_dtime	= get_seconds();

	/*
	 * One subtle ordering requirement: if anything has gone wrong
	 * (transaction abort, IO errors, whatever), then we can still
	 * do these next steps (the fs will already have been marked as
	 * having errors), but we can't free the inode if the mark_dirty
	 * fails.
	 */
	if (ext4_mark_inode_dirty(handle, inode))
		/* If that failed, just do the required in-core inode clear. */
		ext4_clear_inode(inode);
	else
		ext4_free_inode(handle, inode);
	ext4_journal_stop(handle);
	sb_end_intwrite(inode->i_sb);
	return;
no_delete:
	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
}

#ifdef CONFIG_QUOTA
qsize_t *ext4_get_reserved_space(struct inode *inode)
{
	return &EXT4_I(inode)->i_reserved_quota;
}
#endif

/*
 * 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, quota_claim);
	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",
			 __func__, inode->i_ino, used,
			 ei->i_reserved_data_blocks);
		WARN_ON(1);
		used = ei->i_reserved_data_blocks;
	}

	if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d "
			 "with only %d reserved metadata blocks\n", __func__,
			 inode->i_ino, ei->i_allocated_meta_blocks,
			 ei->i_reserved_meta_blocks);
		WARN_ON(1);
		ei->i_allocated_meta_blocks = ei->i_reserved_meta_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_dirtyclusters_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_dirtyclusters_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, EXT4_C2B(sbi, used));
	else {
		/*
		 * We did fallocate with an offset that is already delayed
		 * allocated. So on delayed allocated writeback we should
		 * not re-claim the quota for fallocated blocks.
		 */
		dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
	}

	/*
	 * If we have done all the pending block allocations and if
	 * there aren't any writers on the inode, we can discard the
	 * inode's preallocations.
	 */
	if ((ei->i_reserved_data_blocks == 0) &&
	    (atomic_read(&inode->i_writecount) == 0))
		ext4_discard_preallocations(inode);
}

static int __check_block_validity(struct inode *inode, const char *func,
				unsigned int line,
				struct ext4_map_blocks *map)
{
	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
				   map->m_len)) {
		ext4_error_inode(inode, func, line, map->m_pblk,
				 "lblock %lu mapped to illegal pblock "
				 "(length %d)", (unsigned long) map->m_lblk,
				 map->m_len);
		return -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 case, 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.
	 */
	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
		down_read((&EXT4_I(inode)->i_data_sem));
	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
		retval = ext4_ext_map_blocks(handle, inode, map, flags &
					     EXT4_GET_BLOCKS_KEEP_SIZE);
	} else {
		retval = ext4_ind_map_blocks(handle, inode, map, flags &
					     EXT4_GET_BLOCKS_KEEP_SIZE);
	}
	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
		up_read((&EXT4_I(inode)->i_data_sem));

	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
		int ret;
		if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
			/* delayed alloc may be allocated by fallocate and
			 * coverted to initialized by directIO.
			 * we need to handle delayed extent here.
			 */
			down_write((&EXT4_I(inode)->i_data_sem));
			goto delayed_mapped;
		}
		ret = check_block_validity(inode, map);
		if (ret != 0)
			return ret;
	}

	/* If it is only a block(s) look up */
	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
		return retval;

	/*
	 * Returns if the blocks have already allocated
	 *
	 * Note that if blocks have been preallocated
	 * ext4_ext_get_block() returns the create = 0
	 * with buffer head unmapped.
	 */
	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
		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);

		if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
			int ret;
delayed_mapped:
			/* delayed allocation blocks has been allocated */
			ret = ext4_es_remove_extent(inode, map->m_lblk,
						    map->m_len);
			if (ret < 0)
				retval = ret;
		}
	}

	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;

	if (ext4_has_inline_data(inode))
		return -ERANGE;

	map.m_lblk = iblock;
	map.m_len = bh->b_size >> inode->i_blkbits;

	if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !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);

	/* ensure we send some value back into *errp */
	*errp = 0;

	if (err < 0)
		*errp = err;
	if (err <= 0)
		return NULL;

	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_get_block_write_nolock(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().
 *