return n;
}
+static int __ext4_check_blockref(const char *function, struct inode *inode,
+ __le32 *p, unsigned int max) {
+
+ unsigned int maxblocks = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es);
+ __le32 *bref = p;
+ while (bref < p+max) {
+ if (unlikely(le32_to_cpu(*bref) >= maxblocks)) {
+ ext4_error(inode->i_sb, function,
+ "block reference %u >= max (%u) "
+ "in inode #%lu, offset=%d",
+ le32_to_cpu(*bref), maxblocks,
+ inode->i_ino, (int)(bref-p));
+ return -EIO;
+ }
+ bref++;
+ }
+ return 0;
+}
+
+
+#define ext4_check_indirect_blockref(inode, bh) \
+ __ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data, \
+ EXT4_ADDR_PER_BLOCK((inode)->i_sb))
+
+#define ext4_check_inode_blockref(inode) \
+ __ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data, \
+ EXT4_NDIR_BLOCKS)
+
/**
* ext4_get_branch - read the chain of indirect blocks leading to data
* @inode: inode in question
if (!p->key)
goto no_block;
while (--depth) {
- bh = sb_bread(sb, le32_to_cpu(p->key));
- if (!bh)
+ bh = sb_getblk(sb, le32_to_cpu(p->key));
+ if (unlikely(!bh))
goto failure;
+
+ if (!bh_uptodate_or_lock(bh)) {
+ if (bh_submit_read(bh) < 0) {
+ put_bh(bh);
+ goto failure;
+ }
+ /* validate block references */
+ if (ext4_check_indirect_blockref(inode, bh)) {
+ put_bh(bh);
+ goto failure;
+ }
+ }
+
add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
/* Reader: end */
if (!p->key)
ext4_fsblk_t bg_start;
ext4_fsblk_t last_block;
ext4_grpblk_t colour;
+ ext4_group_t block_group;
+ int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
/* Try to find previous block */
for (p = ind->p - 1; p >= start; p--) {
* It is going to be referred to from the inode itself? OK, just put it
* into the same cylinder group then.
*/
- bg_start = ext4_group_first_block_no(inode->i_sb, ei->i_block_group);
+ block_group = ei->i_block_group;
+ if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
+ block_group &= ~(flex_size-1);
+ if (S_ISREG(inode->i_mode))
+ block_group++;
+ }
+ bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+ /*
+ * If we are doing delayed allocation, we don't need take
+ * colour into account.
+ */
+ if (test_opt(inode->i_sb, DELALLOC))
+ return bg_start;
+
if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
colour = (current->pid % 16) *
(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
}
/*
+ * The ext4_ind_get_blocks() function handles non-extents inodes
+ * (i.e., using the traditional indirect/double-indirect i_blocks
+ * scheme) for ext4_get_blocks().
+ *
* Allocation strategy is simple: if we have to allocate something, we will
* have to go the whole way to leaf. So let's do it before attaching anything
* to tree, set linkage between the newborn blocks, write them if sync is
* return = 0, if plain lookup failed.
* return < 0, error case.
*
- *
- * Need to be called with
- * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
- * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ * The ext4_ind_get_blocks() function should be called with
+ * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
+ * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
+ * blocks.
*/
-static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, unsigned int maxblocks,
struct buffer_head *bh_result,
- int create, int extend_disksize)
+ int flags)
{
int err = -EIO;
ext4_lblk_t offsets[4];
J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
- J_ASSERT(handle != NULL || create == 0);
+ J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
depth = ext4_block_to_path(inode, iblock, offsets,
&blocks_to_boundary);
}
/* Next simple case - plain lookup or failed read of indirect block */
- if (!create || err == -EIO)
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
goto cleanup;
/*
* protect it if you're about to implement concurrent
* ext4_get_block() -bzzz
*/
- if (!err && extend_disksize) {
+ if (!err && (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE)) {
disksize = ((loff_t) iblock + count) << inode->i_blkbits;
if (disksize > i_size_read(inode))
disksize = i_size_read(inode);
return err;
}
+qsize_t ext4_get_reserved_space(struct inode *inode)
+{
+ unsigned long long total;
+
+ spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+ total = EXT4_I(inode)->i_reserved_data_blocks +
+ EXT4_I(inode)->i_reserved_meta_blocks;
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
+ return total;
+}
/*
* Calculate the number of metadata blocks need to reserve
* to allocate @blocks for non extent file based file
/* update per-inode reservations */
BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
EXT4_I(inode)->i_reserved_data_blocks -= used;
-
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
+ /*
+ * free those over-booking quota for metadata blocks
+ */
+ if (mdb_free)
+ vfs_dq_release_reservation_block(inode, mdb_free);
+
+ /*
+ * 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 (!total && (atomic_read(&inode->i_writecount) == 0))
+ ext4_discard_preallocations(inode);
}
/*
- * The ext4_get_blocks_wrap() function try to look up the requested blocks,
+ * The ext4_get_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
* mapped.
*
* If file type is extents based, it will call ext4_ext_get_blocks(),
- * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping
+ * Otherwise, call with ext4_ind_get_blocks() to handle indirect mapping
* based files
*
* On success, it returns the number of blocks being mapped or allocate.
*
* It returns the error in case of allocation failure.
*/
-int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
- unsigned int max_blocks, struct buffer_head *bh,
- int create, int extend_disksize, int flag)
+int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
+ unsigned int max_blocks, struct buffer_head *bh,
+ int flags)
{
int retval;
clear_buffer_mapped(bh);
+ clear_buffer_unwritten(bh);
/*
- * Try to see if we can get the block without requesting
- * for new file system block.
+ * 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_I(inode)->i_flags & EXT4_EXTENTS_FL) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
- bh, 0, 0);
+ bh, 0);
} else {
- retval = ext4_get_blocks_handle(handle,
- inode, block, max_blocks, bh, 0, 0);
+ retval = ext4_ind_get_blocks(handle, inode, block, max_blocks,
+ bh, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
/* If it is only a block(s) look up */
- if (!create)
+ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
return retval;
/*
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.
+ */
+ clear_buffer_unwritten(bh);
+
+ /*
* 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()
* let the underlying get_block() function know to
* avoid double accounting
*/
- if (flag)
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
EXT4_I(inode)->i_delalloc_reserved_flag = 1;
/*
* We need to check for EXT4 here because migrate
*/
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
- bh, create, extend_disksize);
+ bh, flags);
} else {
- retval = ext4_get_blocks_handle(handle, inode, block,
- max_blocks, bh, create, extend_disksize);
+ retval = ext4_ind_get_blocks(handle, inode, block,
+ max_blocks, bh, flags);
if (retval > 0 && buffer_new(bh)) {
/*
}
}
- if (flag) {
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
EXT4_I(inode)->i_delalloc_reserved_flag = 0;
/*
* Update reserved blocks/metadata blocks
started = 1;
}
- ret = ext4_get_blocks_wrap(handle, inode, iblock,
- max_blocks, bh_result, create, 0, 0);
+ ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
+ create ? EXT4_GET_BLOCKS_CREATE : 0);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
{
struct buffer_head dummy;
int fatal = 0, err;
+ int flags = EXT4_GET_BLOCKS_EXTEND_DISKSIZE;
J_ASSERT(handle != NULL || create == 0);
dummy.b_state = 0;
dummy.b_blocknr = -1000;
buffer_trace_init(&dummy.b_history);
- err = ext4_get_blocks_wrap(handle, inode, block, 1,
- &dummy, create, 1, 0);
+ if (create)
+ flags |= EXT4_GET_BLOCKS_CREATE;
+ err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags);
/*
- * ext4_get_blocks_handle() returns number of blocks
- * mapped. 0 in case of a HOLE.
+ * ext4_get_blocks() returns number of blocks mapped. 0 in
+ * case of a HOLE.
*/
if (err > 0) {
if (err > 1)
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);
*pagep = page;
ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- ext4_get_block);
+ ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
{
int retries = 0;
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned long md_needed, mdblocks, total = 0;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ unsigned long md_needed, mdblocks, total = 0;
/*
* recalculate the amount of metadata blocks to reserve
md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
total = md_needed + nrblocks;
+ /*
+ * Make quota reservation here to prevent quota overflow
+ * later. Real quota accounting is done at pages writeout
+ * time.
+ */
+ if (vfs_dq_reserve_block(inode, total)) {
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ return -EDQUOT;
+ }
+
if (ext4_claim_free_blocks(sbi, total)) {
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
}
+ vfs_dq_release_reservation_block(inode, total);
return -ENOSPC;
}
EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
EXT4_I(inode)->i_reserved_meta_blocks = mdb;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
+ vfs_dq_release_reservation_block(inode, release);
}
static void ext4_da_page_release_reservation(struct page *page,
struct mpage_da_data {
struct inode *inode;
- struct buffer_head lbh; /* extent of blocks */
+ sector_t b_blocknr; /* start block number of extent */
+ size_t b_size; /* size of extent */
+ unsigned long b_state; /* state of the extent */
unsigned long first_page, next_page; /* extent of pages */
- get_block_t *get_block;
struct writeback_control *wbc;
int io_done;
int pages_written;
* @mpd->inode: inode
* @mpd->first_page: first page of the extent
* @mpd->next_page: page after the last page of the extent
- * @mpd->get_block: the filesystem's block mapper function
*
* By the time mpage_da_submit_io() is called we expect all blocks
* to be allocated. this may be wrong if allocation failed.
/*
* 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->lbh.b_blocknr we would only be looking
+ * If we look at mpd->b_blocknr we would only be looking
* at the currently mapped buffer_heads.
*/
index = mpd->first_page;
* @logical - first logical block to start assignment with
*
* the function goes through all passed space and put actual disk
- * block numbers into buffer heads, dropping BH_Delay
+ * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten
*/
static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
struct buffer_head *exbh)
do {
if (cur_logical >= logical + blocks)
break;
- if (buffer_delay(bh)) {
- bh->b_blocknr = pblock;
- clear_buffer_delay(bh);
- bh->b_bdev = inode->i_sb->s_bdev;
- } else if (buffer_unwritten(bh)) {
- bh->b_blocknr = pblock;
- clear_buffer_unwritten(bh);
- set_buffer_mapped(bh);
- set_buffer_new(bh);
- bh->b_bdev = inode->i_sb->s_bdev;
+
+ if (buffer_delay(bh) ||
+ buffer_unwritten(bh)) {
+
+ BUG_ON(bh->b_bdev != inode->i_sb->s_bdev);
+
+ if (buffer_delay(bh)) {
+ clear_buffer_delay(bh);
+ bh->b_blocknr = pblock;
+ } else {
+ /*
+ * unwritten already should have
+ * blocknr assigned. Verify that
+ */
+ clear_buffer_unwritten(bh);
+ BUG_ON(bh->b_blocknr != pblock);
+ }
+
} else if (buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
}
/*
+ * This function is used by mpage_da_map_blocks(). We separate it out
+ * as a separate function just to make life easier, and because
+ * mpage_da_map_blocks() used to be a generic function that took a
+ * get_block_t.
+ */
+static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result)
+{
+ int ret;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+ loff_t disksize = EXT4_I(inode)->i_disksize;
+ handle_t *handle = NULL;
+
+ handle = ext4_journal_current_handle();
+ BUG_ON(!handle);
+ ret = ext4_get_blocks(handle, inode, iblock, max_blocks,
+ bh_result, EXT4_GET_BLOCKS_CREATE|
+ EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+ if (ret <= 0)
+ return ret;
+
+ bh_result->b_size = (ret << inode->i_blkbits);
+
+ if (ext4_should_order_data(inode)) {
+ int retval;
+ retval = ext4_jbd2_file_inode(handle, inode);
+ if (retval)
+ /*
+ * Failed to add inode for ordered mode. Don't
+ * update file size
+ */
+ return retval;
+ }
+
+ /*
+ * Update on-disk size along with block allocation we don't
+ * use EXT4_GET_BLOCKS_EXTEND_DISKSIZE as size may change
+ * within already allocated block -bzzz
+ */
+ disksize = ((loff_t) iblock + ret) << inode->i_blkbits;
+ if (disksize > i_size_read(inode))
+ disksize = i_size_read(inode);
+ if (disksize > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, disksize);
+ ret = ext4_mark_inode_dirty(handle, inode);
+ return ret;
+ }
+ return 0;
+}
+
+/*
* mpage_da_map_blocks - go through given space
*
- * @mpd->lbh - bh describing space
- * @mpd->get_block - the filesystem's block mapper function
+ * @mpd - bh describing space
*
* The function skips space we know is already mapped to disk blocks.
*
*/
-static int mpage_da_map_blocks(struct mpage_da_data *mpd)
+static int mpage_da_map_blocks(struct mpage_da_data *mpd)
{
int err = 0;
struct buffer_head new;
- struct buffer_head *lbh = &mpd->lbh;
sector_t next;
/*
* We consider only non-mapped and non-allocated blocks
*/
- if (buffer_mapped(lbh) && !buffer_delay(lbh))
+ if ((mpd->b_state & (1 << BH_Mapped)) &&
+ !(mpd->b_state & (1 << BH_Delay)) &&
+ !(mpd->b_state & (1 << BH_Unwritten)))
return 0;
- new.b_state = lbh->b_state;
+ /*
+ * We need to make sure the BH_Delay flag is passed down to
+ * ext4_da_get_block_write(), since it calls ext4_get_blocks()
+ * with the EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. This flag
+ * causes ext4_get_blocks() to call
+ * ext4_da_update_reserve_space() if the passed buffer head
+ * has the BH_Delay flag set. In the future, once we clean up
+ * the interfaces to ext4_get_blocks(), we should pass in a
+ * separate flag which requests that the delayed allocation
+ * statistics should be updated, instead of depending on the
+ * state information getting passed down via the map_bh's
+ * state bitmasks plus the magic
+ * EXT4_GET_BLOCKS_DELALLOC_RESERVE flag.
+ */
+ new.b_state = mpd->b_state & (1 << BH_Delay);
new.b_blocknr = 0;
- new.b_size = lbh->b_size;
- next = lbh->b_blocknr;
+ new.b_size = mpd->b_size;
+ next = mpd->b_blocknr;
/*
* If we didn't accumulate anything
* to write simply return
*/
if (!new.b_size)
return 0;
- err = mpd->get_block(mpd->inode, next, &new, 1);
- if (err) {
- /* If get block returns with error
- * we simply return. Later writepage
- * will redirty the page and writepages
- * will find the dirty page again
+ err = ext4_da_get_block_write(mpd->inode, next, &new);
+ if (err) {
+ /*
+ * If get block returns with error we simply
+ * return. Later writepage will redirty the page and
+ * writepages will find the dirty page again
*/
if (err == -EAGAIN)
return 0;
if (err == -ENOSPC &&
- ext4_count_free_blocks(mpd->inode->i_sb)) {
+ ext4_count_free_blocks(mpd->inode->i_sb)) {
mpd->retval = err;
return 0;
}
/*
- * 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.
+ * 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.
*/
printk(KERN_EMERG "%s block allocation failed for inode %lu "
"at logical offset %llu with max blocks "
"%zd with error %d\n",
__func__, mpd->inode->i_ino,
(unsigned long long)next,
- lbh->b_size >> mpd->inode->i_blkbits, err);
+ mpd->b_size >> mpd->inode->i_blkbits, err);
printk(KERN_EMERG "This should not happen.!! "
"Data will be lost\n");
if (err == -ENOSPC) {
}
/* invlaidate all the pages */
ext4_da_block_invalidatepages(mpd, next,
- lbh->b_size >> mpd->inode->i_blkbits);
+ mpd->b_size >> mpd->inode->i_blkbits);
return err;
}
BUG_ON(new.b_size == 0);
* If blocks are delayed marked, we need to
* put actual blocknr and drop delayed bit
*/
- if (buffer_delay(lbh) || buffer_unwritten(lbh))
+ if ((mpd->b_state & (1 << BH_Delay)) ||
+ (mpd->b_state & (1 << BH_Unwritten)))
mpage_put_bnr_to_bhs(mpd, next, &new);
return 0;
* 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, struct buffer_head *bh)
+ sector_t logical, size_t b_size,
+ unsigned long b_state)
{
sector_t next;
- size_t b_size = bh->b_size;
- struct buffer_head *lbh = &mpd->lbh;
- int nrblocks = lbh->b_size >> mpd->inode->i_blkbits;
+ int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;
/* check if thereserved journal credits might overflow */
if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) {
/*
* First block in the extent
*/
- if (lbh->b_size == 0) {
- lbh->b_blocknr = logical;
- lbh->b_size = b_size;
- lbh->b_state = bh->b_state & BH_FLAGS;
+ if (mpd->b_size == 0) {
+ mpd->b_blocknr = logical;
+ mpd->b_size = b_size;
+ mpd->b_state = b_state & BH_FLAGS;
return;
}
- next = lbh->b_blocknr + nrblocks;
+ next = mpd->b_blocknr + nrblocks;
/*
* Can we merge the block to our big extent?
*/
- if (logical == next && (bh->b_state & BH_FLAGS) == lbh->b_state) {
- lbh->b_size += b_size;
+ if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) {
+ mpd->b_size += b_size;
return;
}
return;
}
+static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+{
+ /*
+ * unmapped buffer is possible for holes.
+ * delay buffer is possible with delayed allocation.
+ * We also need to consider unwritten buffer as unmapped.
+ */
+ return (!buffer_mapped(bh) || buffer_delay(bh) ||
+ buffer_unwritten(bh)) && buffer_dirty(bh);
+}
+
/*
* __mpage_da_writepage - finds extent of pages and blocks
*
{
struct mpage_da_data *mpd = data;
struct inode *inode = mpd->inode;
- struct buffer_head *bh, *head, fake;
+ struct buffer_head *bh, *head;
sector_t logical;
if (mpd->io_done) {
/*
* ... and blocks
*/
- mpd->lbh.b_size = 0;
- mpd->lbh.b_state = 0;
- mpd->lbh.b_blocknr = 0;
+ mpd->b_size = 0;
+ mpd->b_state = 0;
+ mpd->b_blocknr = 0;
}
mpd->next_page = page->index + 1;
(PAGE_CACHE_SHIFT - inode->i_blkbits);
if (!page_has_buffers(page)) {
- /*
- * There is no attached buffer heads yet (mmap?)
- * we treat the page asfull of dirty blocks
- */
- bh = &fake;
- bh->b_size = PAGE_CACHE_SIZE;
- bh->b_state = 0;
- set_buffer_dirty(bh);
- set_buffer_uptodate(bh);
- mpage_add_bh_to_extent(mpd, logical, bh);
+ mpage_add_bh_to_extent(mpd, logical, PAGE_CACHE_SIZE,
+ (1 << BH_Dirty) | (1 << BH_Uptodate));
if (mpd->io_done)
return MPAGE_DA_EXTENT_TAIL;
} else {
* Otherwise we won't make progress
* with the page in ext4_da_writepage
*/
- if (buffer_dirty(bh) &&
- (!buffer_mapped(bh) || buffer_delay(bh))) {
- mpage_add_bh_to_extent(mpd, logical, bh);
+ if (ext4_bh_unmapped_or_delay(NULL, bh)) {
+ mpage_add_bh_to_extent(mpd, logical,
+ bh->b_size,
+ bh->b_state);
if (mpd->io_done)
return MPAGE_DA_EXTENT_TAIL;
} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
* unmapped buffer_head later we need to
* use the b_state flag of that buffer_head.
*/
- if (mpd->lbh.b_size == 0)
- mpd->lbh.b_state =
- bh->b_state & BH_FLAGS;
+ if (mpd->b_size == 0)
+ mpd->b_state = bh->b_state & BH_FLAGS;
}
logical++;
} while ((bh = bh->b_this_page) != head);
}
/*
- * mpage_da_writepages - walk the list of dirty pages of the given
- * address space, allocates non-allocated blocks, maps newly-allocated
- * blocks to existing bhs and issue IO them
+ * 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.
*
- * @mapping: address space structure to write
- * @wbc: subtract the number of written pages from *@wbc->nr_to_write
- * @get_block: the filesystem's block mapper function.
+ * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
+ * We also have b_blocknr = -1 and b_bdev initialized properly
*
- * This is a library function, which implements the writepages()
- * address_space_operation.
- */
-static int mpage_da_writepages(struct address_space *mapping,
- struct writeback_control *wbc,
- struct mpage_da_data *mpd)
-{
- int ret;
-
- if (!mpd->get_block)
- return generic_writepages(mapping, wbc);
-
- mpd->lbh.b_size = 0;
- mpd->lbh.b_state = 0;
- mpd->lbh.b_blocknr = 0;
- mpd->first_page = 0;
- mpd->next_page = 0;
- mpd->io_done = 0;
- mpd->pages_written = 0;
- mpd->retval = 0;
-
- ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
- /*
- * Handle last extent of pages
- */
- if (!mpd->io_done && mpd->next_page != mpd->first_page) {
- if (mpage_da_map_blocks(mpd) == 0)
- mpage_da_submit_io(mpd);
-
- mpd->io_done = 1;
- ret = MPAGE_DA_EXTENT_TAIL;
- }
- wbc->nr_to_write -= mpd->pages_written;
- return ret;
-}
-
-/*
- * this is a special callback for ->write_begin() only
- * it's intention is to return mapped block or reserve space
+ * 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_result, int create)
{
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_result->b_size != inode->i_sb->s_blocksize);
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
- ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0);
+ ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0);
if ((ret == 0) && !buffer_delay(bh_result)) {
/* the block isn't (pre)allocated yet, let's reserve space */
/*
/* not enough space to reserve */
return ret;
- map_bh(bh_result, inode->i_sb, 0);
+ map_bh(bh_result, inode->i_sb, invalid_block);
set_buffer_new(bh_result);
set_buffer_delay(bh_result);
} else if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
- ret = 0;
- }
-
- return ret;
-}
-#define EXT4_DELALLOC_RSVED 1
-static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret;
- unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
- loff_t disksize = EXT4_I(inode)->i_disksize;
- handle_t *handle = NULL;
-
- handle = ext4_journal_current_handle();
- BUG_ON(!handle);
- ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
- bh_result, create, 0, EXT4_DELALLOC_RSVED);
- if (ret > 0) {
-
- bh_result->b_size = (ret << inode->i_blkbits);
-
- if (ext4_should_order_data(inode)) {
- int retval;
- retval = ext4_jbd2_file_inode(handle, inode);
- if (retval)
- /*
- * Failed to add inode for ordered
- * mode. Don't update file size
- */
- return retval;
- }
-
- /*
- * Update on-disk size along with block allocation
- * we don't use 'extend_disksize' as size may change
- * within already allocated block -bzzz
- */
- disksize = ((loff_t) iblock + ret) << inode->i_blkbits;
- if (disksize > i_size_read(inode))
- disksize = i_size_read(inode);
- if (disksize > EXT4_I(inode)->i_disksize) {
- ext4_update_i_disksize(inode, disksize);
- ret = ext4_mark_inode_dirty(handle, inode);
- return ret;
+ if (buffer_unwritten(bh_result)) {
+ /* 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_result);
+ set_buffer_mapped(bh_result);
}
ret = 0;
}
- return ret;
-}
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
-{
- /*
- * unmapped buffer is possible for holes.
- * delay buffer is possible with delayed allocation
- */
- return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh));
+ return ret;
}
-static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock,
+/*
+ * 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_prepare_write(), nobh_writepage(), 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 nobh_writepage() or
+ * 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)
{
int ret = 0;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+ BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+
/*
* we don't want to do block allocation in writepage
* so call get_block_wrap with create = 0
*/
- ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks,
- bh_result, 0, 0, 0);
+ ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0);
+ BUG_ON(create && ret == 0);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
}
/*
- * get called vi ext4_da_writepages after taking page lock (have journal handle)
- * get called via journal_submit_inode_data_buffers (no journal handle)
- * get called via shrink_page_list via pdflush (no journal handle)
- * or grab_page_cache when doing write_begin (have journal handle)
+ * 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)
*/
static int ext4_da_writepage(struct page *page,
struct writeback_control *wbc)
* do block allocation here.
*/
ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
- ext4_normal_get_block_write);
+ noalloc_get_block_write);
if (!ret) {
page_bufs = page_buffers(page);
/* check whether all are mapped and non delay */
}
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
- ret = nobh_writepage(page, ext4_normal_get_block_write, wbc);
+ ret = nobh_writepage(page, noalloc_get_block_write, wbc);
else
- ret = block_write_full_page(page,
- ext4_normal_get_block_write,
- wbc);
+ ret = block_write_full_page(page, noalloc_get_block_write,
+ wbc);
return ret;
}
int no_nrwrite_index_update;
int pages_written = 0;
long pages_skipped;
+ int range_cyclic, cycled = 1, io_done = 0;
int needed_blocks, ret = 0, nr_to_writebump = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
- if (wbc->range_cyclic)
+ range_cyclic = wbc->range_cyclic;
+ if (wbc->range_cyclic) {
index = mapping->writeback_index;
- else
+ if (index)
+ cycled = 0;
+ wbc->range_start = index << PAGE_CACHE_SHIFT;
+ wbc->range_end = LLONG_MAX;
+ wbc->range_cyclic = 0;
+ } else
index = wbc->range_start >> PAGE_CACHE_SHIFT;
mpd.wbc = wbc;
wbc->no_nrwrite_index_update = 1;
pages_skipped = wbc->pages_skipped;
+retry:
while (!ret && wbc->nr_to_write > 0) {
/*
dump_stack();
goto out_writepages;
}
- mpd.get_block = ext4_da_get_block_write;
- ret = mpage_da_writepages(mapping, wbc, &mpd);
+
+ /*
+ * Now call __mpage_da_writepage to find the next
+ * contiguous region of logical blocks that need
+ * blocks to be allocated by ext4. We don't actually
+ * submit the blocks for I/O here, even though
+ * write_cache_pages thinks it will, and will set the
+ * pages as clean for write before calling
+ * __mpage_da_writepage().
+ */
+ mpd.b_size = 0;
+ mpd.b_state = 0;
+ mpd.b_blocknr = 0;
+ mpd.first_page = 0;
+ mpd.next_page = 0;
+ mpd.io_done = 0;
+ mpd.pages_written = 0;
+ mpd.retval = 0;
+ ret = write_cache_pages(mapping, wbc, __mpage_da_writepage,
+ &mpd);
+ /*
+ * If we have a contigous 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) {
+ if (mpage_da_map_blocks(&mpd) == 0)
+ mpage_da_submit_io(&mpd);
+ mpd.io_done = 1;
+ ret = MPAGE_DA_EXTENT_TAIL;
+ }
+ wbc->nr_to_write -= mpd.pages_written;
ext4_journal_stop(handle);
- if (mpd.retval == -ENOSPC) {
+ if ((mpd.retval == -ENOSPC) && sbi->s_journal) {
/* commit the transaction which would
* free blocks released in the transaction
* and try again
pages_written += mpd.pages_written;
wbc->pages_skipped = pages_skipped;
ret = 0;
+ io_done = 1;
} else if (wbc->nr_to_write)
/*
* There is no more writeout needed
*/
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;
+ }
if (pages_skipped != wbc->pages_skipped)
printk(KERN_EMERG "This should not happen leaving %s "
"with nr_to_write = %ld ret = %d\n",
/* Update index */
index += pages_written;
+ wbc->range_cyclic = range_cyclic;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
/*
* set the writeback_index so that range_cyclic
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) {
*pagep = page;
ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- ext4_da_get_block_prep);
+ ext4_da_get_block_prep);
if (ret < 0) {
unlock_page(page);
ext4_journal_stop(handle);
for (i = 0; i < idx; i++)
bh = bh->b_this_page;
- if (!buffer_mapped(bh) || (buffer_delay(bh)))
+ if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
return 0;
return 1;
}
return;
}
+/*
+ * Force all delayed allocation blocks to be allocated for a given inode.
+ */
+int ext4_alloc_da_blocks(struct inode *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_writeback() 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 becuase 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
struct inode *inode = page->mapping->host;
if (test_opt(inode->i_sb, NOBH))
- return nobh_writepage(page,
- ext4_normal_get_block_write, wbc);
+ return nobh_writepage(page, noalloc_get_block_write, wbc);
else
- return block_write_full_page(page,
- ext4_normal_get_block_write,
- wbc);
+ return block_write_full_page(page, noalloc_get_block_write,
+ wbc);
}
static int ext4_normal_writepage(struct page *page,
int err;
ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
- ext4_normal_get_block_write);
+ noalloc_get_block_write);
if (ret != 0)
goto out_unlock;
* really know unless we go poke around in the buffer_heads.
* But block_write_full_page will do the right thing.
*/
- return block_write_full_page(page,
- ext4_normal_get_block_write,
- wbc);
+ return block_write_full_page(page, noalloc_get_block_write,
+ wbc);
}
no_write:
redirty_page_for_writepage(wbc, page);
if (!ext4_can_truncate(inode))
return;
+ if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
+ ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
+
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
ext4_ext_truncate(inode);
return;
unsigned num;
table = ext4_inode_table(sb, gdp);
- /* Make sure s_inode_readahead_blks is a power of 2 */
- while (EXT4_SB(sb)->s_inode_readahead_blks &
- (EXT4_SB(sb)->s_inode_readahead_blks-1))
- EXT4_SB(sb)->s_inode_readahead_blks =
- (EXT4_SB(sb)->s_inode_readahead_blks &
- (EXT4_SB(sb)->s_inode_readahead_blks-1));
+ /* 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;
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_SB(inode->i_sb)->s_es->s_creator_os !=
- cpu_to_le32(EXT4_OS_HURD)) {
+ 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;
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!
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
+ ret = 0;
+ if (ei->i_file_acl &&
+ ((ei->i_file_acl <
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
+ EXT4_SB(sb)->s_gdb_count)) ||
+ (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) {
+ ext4_error(sb, __func__,
+ "bad extended attribute block %llu in inode #%lu",
+ ei->i_file_acl, inode->i_ino);
+ ret = -EIO;
+ goto bad_inode;
+ } else if (ei->i_flags & EXT4_EXTENTS_FL) {
+ 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_check_inode_blockref(inode);
+ }
+ if (ret) {
+ brelse(bh);
+ goto bad_inode;
+ }
+
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
inode->i_op = &ext4_symlink_inode_operations;
ext4_set_aops(inode);
}
- } else {
+ } 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,
else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
+ } else {
+ brelse(bh);
+ ret = -EIO;
+ ext4_error(inode->i_sb, __func__,
+ "bogus i_mode (%o) for inode=%lu",
+ inode->i_mode, inode->i_ino);
+ goto bad_inode;
}
brelse(iloc.bh);
ext4_set_inode_flags(inode);
error = PTR_ERR(handle);
goto err_out;
}
- error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
+ error = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0;
if (error) {
ext4_journal_stop(handle);
return error;
*/
int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
- int groups, gdpblocks;
+ ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
+ int gdpblocks;
int idxblocks;
int ret = 0;
groups += nrblocks;
gdpblocks = groups;
- if (groups > EXT4_SB(inode->i_sb)->s_groups_count)
- groups = EXT4_SB(inode->i_sb)->s_groups_count;
+ if (groups > ngroups)
+ groups = ngroups;
if (groups > EXT4_SB(inode->i_sb)->s_gdb_count)
gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count;
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
- * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks.
+ * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
* 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_SPACE() will always dirty the inode when blocks
+ * Also, vfs_dq_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
return !buffer_mapped(bh);
}
-int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+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 = -EINVAL;
goto out_unlock;
ret = 0;
out_unlock:
+ if (ret)
+ ret = VM_FAULT_SIGBUS;
up_read(&inode->i_alloc_sem);
return ret;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff