int ret;
/*
- * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this
+ * 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.
if (blk &&
unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
blk, 1))) {
- __ext4_error(inode->i_sb, function,
- "invalid block reference %u "
- "in inode #%lu", blk, inode->i_ino);
+ ext4_error_inode(function, inode,
+ "invalid block reference %u", blk);
return -EIO;
}
}
/* Allocation failed, free what we already allocated */
ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
for (i = 1; i <= n ; i++) {
- /*
+ /*
* branch[i].bh is newly allocated, so there is no
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
err_out:
for (i = 1; i <= num; i++) {
- /*
+ /*
* branch[i].bh is newly allocated, so there is no
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
}
/*
- * The ext4_ind_get_blocks() function handles non-extents inodes
+ * The ext4_ind_map_blocks() function handles non-extents inodes
* (i.e., using the traditional indirect/double-indirect i_blocks
- * scheme) for ext4_get_blocks().
+ * scheme) for ext4_map_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
* down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
* blocks.
*/
- static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, unsigned int maxblocks,
- struct buffer_head *bh_result,
+ static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map,
int flags)
{
int err = -EIO;
int count = 0;
ext4_fsblk_t first_block = 0;
- J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
+ J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
- depth = ext4_block_to_path(inode, iblock, offsets,
+ depth = ext4_block_to_path(inode, map->m_lblk, offsets,
&blocks_to_boundary);
if (depth == 0)
/* Simplest case - block found, no allocation needed */
if (!partial) {
first_block = le32_to_cpu(chain[depth - 1].key);
- clear_buffer_new(bh_result);
count++;
/*map more blocks*/
- while (count < maxblocks && count <= blocks_to_boundary) {
+ while (count < map->m_len && count <= blocks_to_boundary) {
ext4_fsblk_t blk;
blk = le32_to_cpu(*(chain[depth-1].p + count));
/*
* Okay, we need to do block allocation.
*/
- goal = ext4_find_goal(inode, iblock, partial);
+ goal = ext4_find_goal(inode, map->m_lblk, partial);
/* the number of blocks need to allocate for [d,t]indirect blocks */
indirect_blks = (chain + depth) - partial - 1;
* direct blocks to allocate for this branch.
*/
count = ext4_blks_to_allocate(partial, indirect_blks,
- maxblocks, blocks_to_boundary);
+ map->m_len, blocks_to_boundary);
/*
* Block out ext4_truncate while we alter the tree
*/
- err = ext4_alloc_branch(handle, inode, iblock, indirect_blks,
+ err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
&count, goal,
offsets + (partial - chain), partial);
* may need to return -EAGAIN upwards in the worst case. --sct
*/
if (!err)
- err = ext4_splice_branch(handle, inode, iblock,
+ err = ext4_splice_branch(handle, inode, map->m_lblk,
partial, indirect_blks, count);
if (err)
goto cleanup;
- set_buffer_new(bh_result);
+ map->m_flags |= EXT4_MAP_NEW;
ext4_update_inode_fsync_trans(handle, inode, 1);
got_it:
- map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
+ map->m_flags |= EXT4_MAP_MAPPED;
+ map->m_pblk = le32_to_cpu(chain[depth-1].key);
+ map->m_len = count;
if (count > blocks_to_boundary)
- set_buffer_boundary(bh_result);
+ map->m_flags |= EXT4_MAP_BOUNDARY;
err = count;
/* Clean up and exit */
partial = chain + depth - 1; /* the whole chain */
brelse(partial->bh);
partial--;
}
- BUFFER_TRACE(bh_result, "returned");
out:
return err;
}
*/
static int ext4_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_calc_metadata_amount(inode, lblock);
return ext4_indirect_calc_metadata_amount(inode, lblock);
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
- int mdb_free = 0, allocated_meta_blocks = 0;
spin_lock(&ei->i_block_reservation_lock);
trace_ext4_da_update_reserve_space(inode, used);
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
- used += ei->i_allocated_meta_blocks;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
- allocated_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;
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, used);
if (ei->i_reserved_data_blocks == 0) {
/*
* only when we have written all of the delayed
* allocation blocks.
*/
- mdb_free = ei->i_reserved_meta_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;
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
}
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- /* Update quota subsystem */
- if (quota_claim) {
+ /* Update quota subsystem for data blocks */
+ if (quota_claim)
dquot_claim_block(inode, used);
- if (mdb_free)
- dquot_release_reservation_block(inode, mdb_free);
- } else {
+ else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
- * not update the quota for allocated blocks. But then
- * converting an fallocate region to initialized region would
- * have caused a metadata allocation. So claim quota for
- * that
+ * not re-claim the quota for fallocated blocks.
*/
- if (allocated_meta_blocks)
- dquot_claim_block(inode, allocated_meta_blocks);
- dquot_release_reservation_block(inode, mdb_free + used);
+ dquot_release_reservation_block(inode, used);
}
/*
ext4_discard_preallocations(inode);
}
- static int check_block_validity(struct inode *inode, const char *msg,
- sector_t logical, sector_t phys, int len)
+ static int check_block_validity(struct inode *inode, const char *func,
+ struct ext4_map_blocks *map)
{
- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
- __ext4_error(inode->i_sb, msg,
- "inode #%lu logical block %llu mapped to %llu "
- "(size %d)", inode->i_ino,
- (unsigned long long) logical,
- (unsigned long long) phys, len);
+ if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
+ map->m_len)) {
+ ext4_error_inode(func, inode,
+ "lblock %lu mapped to illegal pblock %llu "
+ "(length %d)", (unsigned long) map->m_lblk,
+ map->m_pblk, map->m_len);
return -EIO;
}
return 0;
}
/*
- * The ext4_get_blocks() function tries to look up the requested blocks,
+ * 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_get_blocks(),
- * Otherwise, call with ext4_ind_get_blocks() to handle indirect mapping
+ * 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.
*
* It returns the error in case of allocation failure.
*/
- int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
- unsigned int max_blocks, struct buffer_head *bh,
- int flags)
+ int ext4_map_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map, int flags)
{
int retval;
- clear_buffer_mapped(bh);
- clear_buffer_unwritten(bh);
-
- ext_debug("ext4_get_blocks(): inode %lu, flag %d, max_blocks %u,"
- "logical block %lu\n", inode->i_ino, flags, max_blocks,
- (unsigned long)block);
+ 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_I(inode)->i_flags & EXT4_EXTENTS_FL) {
- retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
- bh, 0);
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
- retval = ext4_ind_get_blocks(handle, inode, block, max_blocks,
- bh, 0);
+ retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
- if (retval > 0 && buffer_mapped(bh)) {
- int ret = check_block_validity(inode, "file system corruption",
- block, bh->b_blocknr, retval);
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+ int ret = check_block_validity(inode, __func__, map);
if (ret != 0)
return ret;
}
* ext4_ext_get_block() returns th create = 0
* with buffer head unmapped.
*/
- if (retval > 0 && buffer_mapped(bh))
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
return retval;
/*
* of BH_Unwritten and BH_Mapped flags being simultaneously
* set on the buffer_head.
*/
- clear_buffer_unwritten(bh);
+ map->m_flags &= ~EXT4_MAP_UNWRITTEN;
/*
* New blocks allocate and/or writing to uninitialized extent
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
- retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
- bh, flags);
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ retval = ext4_ext_map_blocks(handle, inode, map, flags);
} else {
- retval = ext4_ind_get_blocks(handle, inode, block,
- max_blocks, bh, flags);
+ retval = ext4_ind_map_blocks(handle, inode, map, flags);
- if (retval > 0 && buffer_new(bh)) {
+ 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
EXT4_I(inode)->i_delalloc_reserved_flag = 0;
up_write((&EXT4_I(inode)->i_data_sem));
- if (retval > 0 && buffer_mapped(bh)) {
- int ret = check_block_validity(inode, "file system "
- "corruption after allocation",
- block, bh->b_blocknr, retval);
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+ int ret = check_block_validity(inode,
+ "ext4_map_blocks_after_alloc",
+ map);
if (ret != 0)
return ret;
}
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
- int ext4_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+ 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;
- unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
int dio_credits;
- if (create && !handle) {
+ map.m_lblk = iblock;
+ map.m_len = bh->b_size >> inode->i_blkbits;
+
+ if (flags && !handle) {
/* Direct IO write... */
- if (max_blocks > DIO_MAX_BLOCKS)
- max_blocks = DIO_MAX_BLOCKS;
- dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
+ 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);
- goto out;
+ return ret;
}
started = 1;
}
- ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
- create ? EXT4_GET_BLOCKS_CREATE : 0);
+ ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret > 0) {
- bh_result->b_size = (ret << inode->i_blkbits);
+ 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);
- out:
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 buffer_head dummy;
+ struct ext4_map_blocks map;
+ struct buffer_head *bh;
int fatal = 0, err;
- int flags = 0;
J_ASSERT(handle != NULL || create == 0);
- dummy.b_state = 0;
- dummy.b_blocknr = -1000;
- buffer_trace_init(&dummy.b_history);
- if (create)
- flags |= EXT4_GET_BLOCKS_CREATE;
- err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags);
- /*
- * ext4_get_blocks() returns number of blocks mapped. 0 in
- * case of a HOLE.
- */
- if (err > 0) {
- if (err > 1)
- WARN_ON(1);
- err = 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;
}
- *errp = err;
- if (!err && buffer_mapped(&dummy)) {
- struct buffer_head *bh;
- bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
- if (!bh) {
- *errp = -EIO;
- goto err;
- }
- if (buffer_new(&dummy)) {
- J_ASSERT(create != 0);
- J_ASSERT(handle != 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;
+ /*
+ * 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);
}
- return 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");
}
- err:
- return NULL;
+ if (fatal) {
+ *errp = fatal;
+ brelse(bh);
+ bh = NULL;
+ }
+ return bh;
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
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, md_reserved;
+ unsigned long md_needed;
int ret;
/*
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
- md_reserved = ei->i_reserved_meta_blocks;
md_needed = ext4_calc_metadata_amount(inode, lblock);
trace_ext4_da_reserve_space(inode, md_needed);
spin_unlock(&ei->i_block_reservation_lock);
/*
- * Make quota reservation here to prevent quota overflow
- * later. Real quota accounting is done at pages writeout
- * time.
+ * 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, md_needed + 1);
+ 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)) {
- dquot_release_reservation_block(inode, md_needed + 1);
+ dquot_release_reservation_block(inode, 1);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
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
* only when we have written all of the delayed
* allocation blocks.
*/
- to_free += ei->i_reserved_meta_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 blocks counter */
+ /* update fs dirty data blocks counter */
percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/*
* mpage_put_bnr_to_bhs - walk blocks and assign them actual numbers
*
- * @mpd->inode - inode to walk through
- * @exbh->b_blocknr - first block on a disk
- * @exbh->b_size - amount of space in bytes
- * @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 and BH_Unwritten
*/
- static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
- struct buffer_head *exbh)
+ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd,
+ struct ext4_map_blocks *map)
{
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
- int blocks = exbh->b_size >> inode->i_blkbits;
- sector_t pblock = exbh->b_blocknr, cur_logical;
+ int blocks = map->m_len;
+ sector_t pblock = map->m_pblk, cur_logical;
struct buffer_head *head, *bh;
pgoff_t index, end;
struct pagevec pvec;
int nr_pages, i;
- index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
- end = (logical + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (map->m_lblk + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
pagevec_init(&pvec, 0);
/* skip blocks out of the range */
do {
- if (cur_logical >= logical)
+ if (cur_logical >= map->m_lblk)
break;
cur_logical++;
} while ((bh = bh->b_this_page) != head);
do {
- if (cur_logical >= logical + blocks)
+ if (cur_logical >= map->m_lblk + blocks)
break;
- if (buffer_delay(bh) ||
- buffer_unwritten(bh)) {
+ if (buffer_delay(bh) || buffer_unwritten(bh)) {
BUG_ON(bh->b_bdev != inode->i_sb->s_bdev);
} else if (buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
- if (buffer_uninit(exbh))
+ if (map->m_flags & EXT4_MAP_UNINIT)
set_buffer_uninit(bh);
cur_logical++;
pblock++;
}
- /*
- * __unmap_underlying_blocks - just a helper function to unmap
- * set of blocks described by @bh
- */
- static inline void __unmap_underlying_blocks(struct inode *inode,
- struct buffer_head *bh)
- {
- struct block_device *bdev = inode->i_sb->s_bdev;
- int blocks, i;
-
- blocks = bh->b_size >> inode->i_blkbits;
- for (i = 0; i < blocks; i++)
- unmap_underlying_metadata(bdev, bh->b_blocknr + i);
- }
-
static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
sector_t logical, long blk_cnt)
{
static int mpage_da_map_blocks(struct mpage_da_data *mpd)
{
int err, blks, get_blocks_flags;
- struct buffer_head new;
+ struct ext4_map_blocks map;
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;
* EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
* variables are updated after the blocks have been allocated.
*/
- new.b_state = 0;
+ 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_get_blocks(handle, mpd->inode, next, max_blocks,
- &new, get_blocks_flags);
+ blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
if (blks < 0) {
err = blks;
/*
ext4_msg(mpd->inode->i_sb, KERN_CRIT,
"delayed block allocation failed for inode %lu at "
"logical offset %llu with max blocks %zd with "
- "error %d\n", mpd->inode->i_ino,
+ "error %d", mpd->inode->i_ino,
(unsigned long long) next,
mpd->b_size >> mpd->inode->i_blkbits, err);
printk(KERN_CRIT "This should not happen!! "
}
BUG_ON(blks == 0);
- new.b_size = (blks << mpd->inode->i_blkbits);
+ if (map.m_flags & EXT4_MAP_NEW) {
+ struct block_device *bdev = mpd->inode->i_sb->s_bdev;
+ int i;
- if (buffer_new(&new))
- __unmap_underlying_blocks(mpd->inode, &new);
+ for (i = 0; i < map.m_len; i++)
+ unmap_underlying_metadata(bdev, map.m_pblk + i);
+ }
/*
* If blocks are delayed marked, we need to
*/
if ((mpd->b_state & (1 << BH_Delay)) ||
(mpd->b_state & (1 << BH_Unwritten)))
- mpage_put_bnr_to_bhs(mpd, next, &new);
+ mpage_put_bnr_to_bhs(mpd, &map);
if (ext4_should_order_data(mpd->inode)) {
err = ext4_jbd2_file_inode(handle, mpd->inode);
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_get_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_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) {
+ 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
struct buffer_head *bh, *head;
sector_t logical;
- if (mpd->io_done) {
- /*
- * Rest of the page in the page_vec
- * redirty then and skip then. We will
- * try to write them again after
- * starting a new transaction
- */
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- return MPAGE_DA_EXTENT_TAIL;
- }
/*
* Can we merge this page to current extent?
*/
* initialized properly.
*/
static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+ struct buffer_head *bh, int create)
{
+ struct ext4_map_blocks map;
int ret = 0;
sector_t invalid_block = ~((sector_t) 0xffff);
invalid_block = ~0;
BUG_ON(create == 0);
- BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+ 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_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 */
+ 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_prepare_write() unmaps passed block,
* is it OK?
/* not enough space to reserve */
return ret;
- 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);
- 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;
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ return 0;
}
- return ret;
+ 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;
}
/*
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(NULL, inode, iblock, max_blocks, bh_result, 0);
- if (ret > 0) {
- bh_result->b_size = (ret << inode->i_blkbits);
- ret = 0;
- }
- return ret;
+ return _ext4_get_block(inode, iblock, bh_result, 0);
}
static int bget_one(handle_t *handle, struct buffer_head *bh)
* number of contiguous block. So we will limit
* number of contiguous block to a sane value
*/
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) &&
+ 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 call the callback function (which usually writes
+ * the pages).
+ *
+ * This is a forked version of write_cache_pages(). Differences:
+ * Range cyclic is ignored.
+ * no_nrwrite_index_update is always presumed true
+ */
+ static int write_cache_pages_da(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct mpage_da_data *mpd)
+ {
+ int ret = 0;
+ int done = 0;
+ struct pagevec pvec;
+ int nr_pages;
+ pgoff_t index;
+ pgoff_t end; /* Inclusive */
+ long nr_to_write = wbc->nr_to_write;
+
+ pagevec_init(&pvec, 0);
+ index = wbc->range_start >> PAGE_CACHE_SHIFT;
+ end = wbc->range_end >> PAGE_CACHE_SHIFT;
+
+ while (!done && (index <= end)) {
+ int i;
+
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ 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) {
+ done = 1;
+ break;
+ }
+
+ lock_page(page);
+
+ /*
+ * Page truncated or invalidated. We can freely skip it
+ * then, even for data integrity operations: the page
+ * has disappeared concurrently, so there could be no
+ * real expectation of this data interity operation
+ * even if there is now a new, dirty page at the same
+ * pagecache address.
+ */
+ if (unlikely(page->mapping != mapping)) {
+ continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+
+ if (!PageDirty(page)) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ if (PageWriteback(page)) {
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ wait_on_page_writeback(page);
+ else
+ goto continue_unlock;
+ }
+
+ BUG_ON(PageWriteback(page));
+ if (!clear_page_dirty_for_io(page))
+ goto continue_unlock;
+
+ ret = __mpage_da_writepage(page, wbc, mpd);
+ if (unlikely(ret)) {
+ if (ret == AOP_WRITEPAGE_ACTIVATE) {
+ unlock_page(page);
+ ret = 0;
+ } else {
+ done = 1;
+ break;
+ }
+ }
+
+ 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.
+ */
+ done = 1;
+ break;
+ }
+ }
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+ return ret;
+ }
+
+
static int ext4_da_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
handle_t *handle = NULL;
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
- int no_nrwrite_index_update;
int pages_written = 0;
long pages_skipped;
unsigned int max_pages;
mpd.wbc = wbc;
mpd.inode = mapping->host;
- /*
- * we don't want write_cache_pages to update
- * nr_to_write and writeback_index
- */
- no_nrwrite_index_update = wbc->no_nrwrite_index_update;
- wbc->no_nrwrite_index_update = 1;
pages_skipped = wbc->pages_skipped;
retry:
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
- "%ld pages, ino %lu; err %d\n", __func__,
+ "%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
goto out_writepages;
}
mpd.io_done = 0;
mpd.pages_written = 0;
mpd.retval = 0;
- ret = write_cache_pages(mapping, wbc, __mpage_da_writepage,
- &mpd);
+ ret = write_cache_pages_da(mapping, wbc, &mpd);
/*
* If we have a contiguous extent of pages and we
* haven't done the I/O yet, map the blocks and submit
if (pages_skipped != wbc->pages_skipped)
ext4_msg(inode->i_sb, KERN_CRIT,
"This should not happen leaving %s "
- "with nr_to_write = %ld ret = %d\n",
+ "with nr_to_write = %ld ret = %d",
__func__, wbc->nr_to_write, ret);
/* Update index */
mapping->writeback_index = index;
out_writepages:
- if (!no_nrwrite_index_update)
- wbc->no_nrwrite_index_update = 0;
wbc->nr_to_write -= nr_to_writebump;
wbc->range_start = range_start;
trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- int ret, retries = 0, quota_retries = 0;
+ int ret, retries = 0;
struct page *page;
pgoff_t index;
unsigned from, to;
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
-
- if ((ret == -EDQUOT) &&
- EXT4_I(inode)->i_reserved_meta_blocks &&
- (quota_retries++ < 3)) {
- /*
- * Since we often over-estimate the number of meta
- * data blocks required, we may sometimes get a
- * spurios out of quota error even though there would
- * be enough space once we write the data blocks and
- * find out how many meta data blocks were _really_
- * required. So try forcing the inode write to see if
- * that helps.
- */
- write_inode_now(inode, (quota_retries == 3));
- goto retry;
- }
out:
return ret;
}
return ret;
}
+ /*
+ * 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)
{
- handle_t *handle = ext4_journal_current_handle();
- int ret = 0;
- unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
- int dio_credits;
- int started = 0;
-
ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
inode->i_ino, create);
- /*
- * ext4_get_block in prepare 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 IO complete.
- */
- create = EXT4_GET_BLOCKS_IO_CREATE_EXT;
-
- if (!handle) {
- if (max_blocks > DIO_MAX_BLOCKS)
- max_blocks = DIO_MAX_BLOCKS;
- dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
- handle = ext4_journal_start(inode, dio_credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- started = 1;
- }
-
- ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
- create);
- if (ret > 0) {
- bh_result->b_size = (ret << inode->i_blkbits);
- ret = 0;
- }
- if (started)
- ext4_journal_stop(handle);
- out:
- return ret;
+ return _ext4_get_block(inode, iblock, bh_result,
+ EXT4_GET_BLOCKS_IO_CREATE_EXT);
}
static void dump_completed_IO(struct inode * inode)
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
count)) {
- ext4_error(inode->i_sb, "inode #%lu: "
- "attempt to clear blocks %llu len %lu, invalid",
- inode->i_ino, (unsigned long long) block_to_free,
- count);
+ EXT4_ERROR_INODE(inode, "attempt to clear invalid "
+ "blocks %llu len %lu",
+ (unsigned long long) block_to_free, count);
return 1;
}
if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
ext4_handle_dirty_metadata(handle, inode, this_bh);
else
- ext4_error(inode->i_sb,
- "circular indirect block detected, "
- "inode=%lu, block=%llu",
- inode->i_ino,
- (unsigned long long) this_bh->b_blocknr);
+ EXT4_ERROR_INODE(inode,
+ "circular indirect block detected at "
+ "block %llu",
+ (unsigned long long) this_bh->b_blocknr);
}
}
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
nr, 1)) {
- ext4_error(inode->i_sb,
- "indirect mapped block in inode "
- "#%lu invalid (level %d, blk #%lu)",
- inode->i_ino, depth,
- (unsigned long) nr);
+ EXT4_ERROR_INODE(inode,
+ "invalid indirect mapped "
+ "block %lu (level %d)",
+ (unsigned long) nr, depth);
break;
}
* (should be rare).
*/
if (!bh) {
- ext4_error(inode->i_sb,
- "Read failure, inode=%lu, block=%llu",
- inode->i_ino, nr);
+ EXT4_ERROR_INODE(inode,
+ "Read failure block=%llu",
+ (unsigned long long) nr);
continue;
}
if (!ext4_can_truncate(inode))
return;
- EXT4_I(inode)->i_flags &= ~EXT4_EOFBLOCKS_FL;
+ 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_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
ext4_ext_truncate(inode);
return;
}
bh = sb_getblk(sb, block);
if (!bh) {
- ext4_error(sb, "unable to read inode block - "
- "inode=%lu, block=%llu", inode->i_ino, block);
+ EXT4_ERROR_INODE(inode, "unable to read inode block - "
+ "block %llu", block);
return -EIO;
}
if (!buffer_uptodate(bh)) {
submit_bh(READ_META, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
- ext4_error(sb, "unable to read inode block - inode=%lu,"
- " block=%llu", inode->i_ino, block);
+ EXT4_ERROR_INODE(inode, "unable to read inode "
+ "block %llu", block);
brelse(bh);
return -EIO;
}
ret = 0;
if (ei->i_file_acl &&
!ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
- ext4_error(sb, "bad extended attribute block %llu inode #%lu",
- ei->i_file_acl, inode->i_ino);
+ EXT4_ERROR_INODE(inode, "bad extended attribute block %llu",
+ ei->i_file_acl);
ret = -EIO;
goto bad_inode;
} else if (ei->i_flags & EXT4_EXTENTS_FL) {
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
} else {
ret = -EIO;
- ext4_error(inode->i_sb, "bogus i_mode (%o) for inode=%lu",
- inode->i_mode, inode->i_ino);
+ EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);
goto bad_inode;
}
brelse(iloc.bh);
if (wbc->sync_mode == WB_SYNC_ALL)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
- ext4_error(inode->i_sb, "IO error syncing inode, "
- "inode=%lu, block=%llu", inode->i_ino,
- (unsigned long long)iloc.bh->b_blocknr);
+ EXT4_ERROR_INODE(inode,
+ "IO error syncing inode (block=%llu)",
+ (unsigned long long) iloc.bh->b_blocknr);
err = -EIO;
}
brelse(iloc.bh);
if (error)
return error;
- if (ia_valid & ATTR_SIZE)
+ 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)) {
}
if (attr->ia_valid & ATTR_SIZE) {
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+ 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) {
if (S_ISREG(inode->i_mode) &&
attr->ia_valid & ATTR_SIZE &&
(attr->ia_size < inode->i_size ||
- (EXT4_I(inode)->i_flags & EXT4_EOFBLOCKS_FL))) {
+ (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))) {
handle_t *handle;
handle = ext4_journal_start(inode, 3);
}
}
/* ext4_truncate will clear the flag */
- if ((EXT4_I(inode)->i_flags & EXT4_EOFBLOCKS_FL))
+ if ((ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))
ext4_truncate(inode);
}
static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
}
*/
if (val)
- EXT4_I(inode)->i_flags |= EXT4_JOURNAL_DATA_FL;
+ ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else
- EXT4_I(inode)->i_flags &= ~EXT4_JOURNAL_DATA_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
/*
* There are three quota SMP locks. dq_list_lock protects all lists with quotas
- * and quota formats, dqstats structure containing statistics about the lists
+ * and quota formats.
* dq_data_lock protects data from dq_dqb and also mem_dqinfo structures and
* also guards consistency of dquot->dq_dqb with inode->i_blocks, i_bytes.
* i_blocks and i_bytes updates itself are guarded by i_lock acquired directly
__cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock);
EXPORT_SYMBOL(dq_data_lock);
+#if defined(CONFIG_QUOTA_DEBUG) || defined(CONFIG_PRINT_QUOTA_WARNING)
static char *quotatypes[] = INITQFNAMES;
+#endif
static struct quota_format_type *quota_formats; /* List of registered formats */
static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES;
struct dqstats dqstats;
EXPORT_SYMBOL(dqstats);
+#ifdef CONFIG_SMP
+struct dqstats *dqstats_pcpu;
+EXPORT_SYMBOL(dqstats_pcpu);
+#endif
static qsize_t inode_get_rsv_space(struct inode *inode);
static void __dquot_initialize(struct inode *inode, int type);
static inline void put_dquot_last(struct dquot *dquot)
{
list_add_tail(&dquot->dq_free, &free_dquots);
- dqstats.free_dquots++;
+ dqstats_inc(DQST_FREE_DQUOTS);
}
static inline void remove_free_dquot(struct dquot *dquot)
if (list_empty(&dquot->dq_free))
return;
list_del_init(&dquot->dq_free);
- dqstats.free_dquots--;
+ dqstats_dec(DQST_FREE_DQUOTS);
}
static inline void put_inuse(struct dquot *dquot)
/* We add to the back of inuse list so we don't have to restart
* when traversing this list and we block */
list_add_tail(&dquot->dq_inuse, &inuse_list);
- dqstats.allocated_dquots++;
+ dqstats_inc(DQST_ALLOC_DQUOTS);
}
static inline void remove_inuse(struct dquot *dquot)
{
- dqstats.allocated_dquots--;
+ dqstats_dec(DQST_ALLOC_DQUOTS);
list_del(&dquot->dq_inuse);
}
/*
return dquot->dq_sb->dq_op->mark_dirty(dquot);
}
+/* Mark dquot dirty in atomic manner, and return it's old dirty flag state */
int dquot_mark_dquot_dirty(struct dquot *dquot)
{
+ int ret = 1;
+
+ /* If quota is dirty already, we don't have to acquire dq_list_lock */
+ if (test_bit(DQ_MOD_B, &dquot->dq_flags))
+ return 1;
+
spin_lock(&dq_list_lock);
- if (!test_and_set_bit(DQ_MOD_B, &dquot->dq_flags))
+ if (!test_and_set_bit(DQ_MOD_B, &dquot->dq_flags)) {
list_add(&dquot->dq_dirty, &sb_dqopt(dquot->dq_sb)->
info[dquot->dq_type].dqi_dirty_list);
+ ret = 0;
+ }
spin_unlock(&dq_list_lock);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(dquot_mark_dquot_dirty);
continue;
/* Now we have active dquot so we can just increase use count */
atomic_inc(&dquot->dq_count);
- dqstats.lookups++;
spin_unlock(&dq_list_lock);
+ dqstats_inc(DQST_LOOKUPS);
dqput(old_dquot);
old_dquot = dquot;
ret = fn(dquot, priv);
* holding reference so we can safely just increase
* use count */
atomic_inc(&dquot->dq_count);
- dqstats.lookups++;
spin_unlock(&dq_list_lock);
+ dqstats_inc(DQST_LOOKUPS);
sb->dq_op->write_dquot(dquot);
dqput(dquot);
spin_lock(&dq_list_lock);
if ((cnt == type || type == -1) && sb_has_quota_active(sb, cnt)
&& info_dirty(&dqopt->info[cnt]))
sb->dq_op->write_info(sb, cnt);
- spin_lock(&dq_list_lock);
- dqstats.syncs++;
- spin_unlock(&dq_list_lock);
+ dqstats_inc(DQST_SYNCS);
mutex_unlock(&dqopt->dqonoff_mutex);
if (!wait || (sb_dqopt(sb)->flags & DQUOT_QUOTA_SYS_FILE))
}
}
+static int dqstats_read(unsigned int type)
+{
+ int count = 0;
+#ifdef CONFIG_SMP
+ int cpu;
+ for_each_possible_cpu(cpu)
+ count += per_cpu_ptr(dqstats_pcpu, cpu)->stat[type];
+ /* Statistics reading is racy, but absolute accuracy isn't required */
+ if (count < 0)
+ count = 0;
+#else
+ count = dqstats.stat[type];
+#endif
+ return count;
+}
+
/*
* This is called from kswapd when we think we need some
* more memory
prune_dqcache(nr);
spin_unlock(&dq_list_lock);
}
- return (dqstats.free_dquots / 100) * sysctl_vfs_cache_pressure;
+ return (dqstats_read(DQST_FREE_DQUOTS)/100) * sysctl_vfs_cache_pressure;
}
static struct shrinker dqcache_shrinker = {
BUG();
}
#endif
-
- spin_lock(&dq_list_lock);
- dqstats.drops++;
- spin_unlock(&dq_list_lock);
+ dqstats_inc(DQST_DROPS);
we_slept:
spin_lock(&dq_list_lock);
if (atomic_read(&dquot->dq_count) > 1) {
put_inuse(dquot);
/* hash it first so it can be found */
insert_dquot_hash(dquot);
- dqstats.lookups++;
spin_unlock(&dq_list_lock);
+ dqstats_inc(DQST_LOOKUPS);
} else {
if (!atomic_read(&dquot->dq_count))
remove_free_dquot(dquot);
atomic_inc(&dquot->dq_count);
- dqstats.cache_hits++;
- dqstats.lookups++;
spin_unlock(&dq_list_lock);
+ dqstats_inc(DQST_CACHE_HITS);
+ dqstats_inc(DQST_LOOKUPS);
}
/* Wait for dq_lock - after this we know that either dquot_release() is
* already finished or it will be canceled due to dq_count > 1 test */
/*
* This operation can block, but only after everything is updated
*/
- int __dquot_alloc_space(struct inode *inode, qsize_t number,
- int warn, int reserve)
+ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
{
int cnt, ret = 0;
char warntype[MAXQUOTAS];
+ int warn = flags & DQUOT_SPACE_WARN;
+ int reserve = flags & DQUOT_SPACE_RESERVE;
+ int nofail = flags & DQUOT_SPACE_NOFAIL;
/*
* First test before acquiring mutex - solves deadlocks when we
continue;
ret = check_bdq(inode->i_dquot[cnt], number, !warn,
warntype+cnt);
- if (ret) {
+ if (ret && !nofail) {
spin_unlock(&dq_data_lock);
goto out_flush_warn;
}
/*
* This operation can block, but only after everything is updated
*/
- void __dquot_free_space(struct inode *inode, qsize_t number, int reserve)
+ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
{
unsigned int cnt;
char warntype[MAXQUOTAS];
+ int reserve = flags & DQUOT_SPACE_RESERVE;
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
/*
* Transfer the number of inode and blocks from one diskquota to an other.
+ * On success, dquot references in transfer_to are consumed and references
+ * to original dquots that need to be released are placed there. On failure,
+ * references are kept untouched.
*
* This operation can block, but only after everything is updated
* A transaction must be started when entering this function.
+ *
*/
-static int __dquot_transfer(struct inode *inode, qid_t *chid, unsigned long mask)
+int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
{
qsize_t space, cur_space;
qsize_t rsv_space = 0;
- struct dquot *transfer_from[MAXQUOTAS];
- struct dquot *transfer_to[MAXQUOTAS];
+ struct dquot *transfer_from[MAXQUOTAS] = {};
int cnt, ret = 0;
char warntype_to[MAXQUOTAS];
char warntype_from_inodes[MAXQUOTAS], warntype_from_space[MAXQUOTAS];
if (IS_NOQUOTA(inode))
return 0;
/* Initialize the arrays */
- for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- transfer_from[cnt] = NULL;
- transfer_to[cnt] = NULL;
+ for (cnt = 0; cnt < MAXQUOTAS; cnt++)
warntype_to[cnt] = QUOTA_NL_NOWARN;
- }
- for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (mask & (1 << cnt))
- transfer_to[cnt] = dqget(inode->i_sb, chid[cnt], cnt);
- }
down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
if (IS_NOQUOTA(inode)) { /* File without quota accounting? */
up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
- goto put_all;
+ return 0;
}
spin_lock(&dq_data_lock);
cur_space = inode_get_bytes(inode);
mark_all_dquot_dirty(transfer_from);
mark_all_dquot_dirty(transfer_to);
- /* The reference we got is transferred to the inode */
+ /* Pass back references to put */
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
- transfer_to[cnt] = NULL;
-warn_put_all:
+ transfer_to[cnt] = transfer_from[cnt];
+warn:
flush_warnings(transfer_to, warntype_to);
flush_warnings(transfer_from, warntype_from_inodes);
flush_warnings(transfer_from, warntype_from_space);
-put_all:
- dqput_all(transfer_from);
- dqput_all(transfer_to);
return ret;
over_quota:
spin_unlock(&dq_data_lock);
up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
- /* Clear dquot pointers we don't want to dqput() */
- for (cnt = 0; cnt < MAXQUOTAS; cnt++)
- transfer_from[cnt] = NULL;
- goto warn_put_all;
+ goto warn;
}
+EXPORT_SYMBOL(__dquot_transfer);
/* Wrapper for transferring ownership of an inode for uid/gid only
* Called from FSXXX_setattr()
*/
int dquot_transfer(struct inode *inode, struct iattr *iattr)
{
- qid_t chid[MAXQUOTAS];
- unsigned long mask = 0;
+ struct dquot *transfer_to[MAXQUOTAS] = {};
+ struct super_block *sb = inode->i_sb;
+ int ret;
- if (iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) {
- mask |= 1 << USRQUOTA;
- chid[USRQUOTA] = iattr->ia_uid;
- }
- if (iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid) {
- mask |= 1 << GRPQUOTA;
- chid[GRPQUOTA] = iattr->ia_gid;
- }
- if (sb_any_quota_active(inode->i_sb) && !IS_NOQUOTA(inode)) {
- dquot_initialize(inode);
- return __dquot_transfer(inode, chid, mask);
- }
- return 0;
+ if (!sb_any_quota_active(sb) || IS_NOQUOTA(inode))
+ return 0;
+
+ if (iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid)
+ transfer_to[USRQUOTA] = dqget(sb, iattr->ia_uid, USRQUOTA);
+ if (iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid)
+ transfer_to[GRPQUOTA] = dqget(sb, iattr->ia_uid, GRPQUOTA);
+
+ ret = __dquot_transfer(inode, transfer_to);
+ dqput_all(transfer_to);
+ return ret;
}
EXPORT_SYMBOL(dquot_transfer);
}
/* Generic routine for getting common part of quota structure */
-static void do_get_dqblk(struct dquot *dquot, struct if_dqblk *di)
+static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
{
struct mem_dqblk *dm = &dquot->dq_dqb;
+ memset(di, 0, sizeof(*di));
+ di->d_version = FS_DQUOT_VERSION;
+ di->d_flags = dquot->dq_type == USRQUOTA ?
+ XFS_USER_QUOTA : XFS_GROUP_QUOTA;
+ di->d_id = dquot->dq_id;
+
spin_lock(&dq_data_lock);
- di->dqb_bhardlimit = stoqb(dm->dqb_bhardlimit);
- di->dqb_bsoftlimit = stoqb(dm->dqb_bsoftlimit);
- di->dqb_curspace = dm->dqb_curspace + dm->dqb_rsvspace;
- di->dqb_ihardlimit = dm->dqb_ihardlimit;
- di->dqb_isoftlimit = dm->dqb_isoftlimit;
- di->dqb_curinodes = dm->dqb_curinodes;
- di->dqb_btime = dm->dqb_btime;
- di->dqb_itime = dm->dqb_itime;
- di->dqb_valid = QIF_ALL;
+ di->d_blk_hardlimit = stoqb(dm->dqb_bhardlimit);
+ di->d_blk_softlimit = stoqb(dm->dqb_bsoftlimit);
+ di->d_ino_hardlimit = dm->dqb_ihardlimit;
+ di->d_ino_softlimit = dm->dqb_isoftlimit;
+ di->d_bcount = dm->dqb_curspace + dm->dqb_rsvspace;
+ di->d_icount = dm->dqb_curinodes;
+ di->d_btimer = dm->dqb_btime;
+ di->d_itimer = dm->dqb_itime;
spin_unlock(&dq_data_lock);
}
int vfs_get_dqblk(struct super_block *sb, int type, qid_t id,
- struct if_dqblk *di)
+ struct fs_disk_quota *di)
{
struct dquot *dquot;
}
EXPORT_SYMBOL(vfs_get_dqblk);
+#define VFS_FS_DQ_MASK \
+ (FS_DQ_BCOUNT | FS_DQ_BSOFT | FS_DQ_BHARD | \
+ FS_DQ_ICOUNT | FS_DQ_ISOFT | FS_DQ_IHARD | \
+ FS_DQ_BTIMER | FS_DQ_ITIMER)
+
/* Generic routine for setting common part of quota structure */
-static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
+static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
{
struct mem_dqblk *dm = &dquot->dq_dqb;
int check_blim = 0, check_ilim = 0;
struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_type];
- if ((di->dqb_valid & QIF_BLIMITS &&
- (di->dqb_bhardlimit > dqi->dqi_maxblimit ||
- di->dqb_bsoftlimit > dqi->dqi_maxblimit)) ||
- (di->dqb_valid & QIF_ILIMITS &&
- (di->dqb_ihardlimit > dqi->dqi_maxilimit ||
- di->dqb_isoftlimit > dqi->dqi_maxilimit)))
+ if (di->d_fieldmask & ~VFS_FS_DQ_MASK)
+ return -EINVAL;
+
+ if (((di->d_fieldmask & FS_DQ_BSOFT) &&
+ (di->d_blk_softlimit > dqi->dqi_maxblimit)) ||
+ ((di->d_fieldmask & FS_DQ_BHARD) &&
+ (di->d_blk_hardlimit > dqi->dqi_maxblimit)) ||
+ ((di->d_fieldmask & FS_DQ_ISOFT) &&
+ (di->d_ino_softlimit > dqi->dqi_maxilimit)) ||
+ ((di->d_fieldmask & FS_DQ_IHARD) &&
+ (di->d_ino_hardlimit > dqi->dqi_maxilimit)))
return -ERANGE;
spin_lock(&dq_data_lock);
- if (di->dqb_valid & QIF_SPACE) {
- dm->dqb_curspace = di->dqb_curspace - dm->dqb_rsvspace;
+ if (di->d_fieldmask & FS_DQ_BCOUNT) {
+ dm->dqb_curspace = di->d_bcount - dm->dqb_rsvspace;
check_blim = 1;
set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
}
- if (di->dqb_valid & QIF_BLIMITS) {
- dm->dqb_bsoftlimit = qbtos(di->dqb_bsoftlimit);
- dm->dqb_bhardlimit = qbtos(di->dqb_bhardlimit);
+
+ if (di->d_fieldmask & FS_DQ_BSOFT)
+ dm->dqb_bsoftlimit = qbtos(di->d_blk_softlimit);
+ if (di->d_fieldmask & FS_DQ_BHARD)
+ dm->dqb_bhardlimit = qbtos(di->d_blk_hardlimit);
+ if (di->d_fieldmask & (FS_DQ_BSOFT | FS_DQ_BHARD)) {
check_blim = 1;
set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
}
- if (di->dqb_valid & QIF_INODES) {
- dm->dqb_curinodes = di->dqb_curinodes;
+
+ if (di->d_fieldmask & FS_DQ_ICOUNT) {
+ dm->dqb_curinodes = di->d_icount;
check_ilim = 1;
set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
}
- if (di->dqb_valid & QIF_ILIMITS) {
- dm->dqb_isoftlimit = di->dqb_isoftlimit;
- dm->dqb_ihardlimit = di->dqb_ihardlimit;
+
+ if (di->d_fieldmask & FS_DQ_ISOFT)
+ dm->dqb_isoftlimit = di->d_ino_softlimit;
+ if (di->d_fieldmask & FS_DQ_IHARD)
+ dm->dqb_ihardlimit = di->d_ino_hardlimit;
+ if (di->d_fieldmask & (FS_DQ_ISOFT | FS_DQ_IHARD)) {
check_ilim = 1;
set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
}
- if (di->dqb_valid & QIF_BTIME) {
- dm->dqb_btime = di->dqb_btime;
+
+ if (di->d_fieldmask & FS_DQ_BTIMER) {
+ dm->dqb_btime = di->d_btimer;
check_blim = 1;
set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
}
- if (di->dqb_valid & QIF_ITIME) {
- dm->dqb_itime = di->dqb_itime;
+
+ if (di->d_fieldmask & FS_DQ_ITIMER) {
+ dm->dqb_itime = di->d_itimer;
check_ilim = 1;
set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
}
dm->dqb_curspace < dm->dqb_bsoftlimit) {
dm->dqb_btime = 0;
clear_bit(DQ_BLKS_B, &dquot->dq_flags);
- } else if (!(di->dqb_valid & QIF_BTIME))
+ } else if (!(di->d_fieldmask & FS_DQ_BTIMER))
/* Set grace only if user hasn't provided his own... */
dm->dqb_btime = get_seconds() + dqi->dqi_bgrace;
}
dm->dqb_curinodes < dm->dqb_isoftlimit) {
dm->dqb_itime = 0;
clear_bit(DQ_INODES_B, &dquot->dq_flags);
- } else if (!(di->dqb_valid & QIF_ITIME))
+ } else if (!(di->d_fieldmask & FS_DQ_ITIMER))
/* Set grace only if user hasn't provided his own... */
dm->dqb_itime = get_seconds() + dqi->dqi_igrace;
}
}
int vfs_set_dqblk(struct super_block *sb, int type, qid_t id,
- struct if_dqblk *di)
+ struct fs_disk_quota *di)
{
struct dquot *dquot;
int rc;
.set_dqblk = vfs_set_dqblk
};
+
+static int do_proc_dqstats(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+#ifdef CONFIG_SMP
+ /* Update global table */
+ unsigned int type = (int *)table->data - dqstats.stat;
+ dqstats.stat[type] = dqstats_read(type);
+#endif
+ return proc_dointvec(table, write, buffer, lenp, ppos);
+}
+
static ctl_table fs_dqstats_table[] = {
{
.procname = "lookups",
- .data = &dqstats.lookups,
+ .data = &dqstats.stat[DQST_LOOKUPS],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
{
.procname = "drops",
- .data = &dqstats.drops,
+ .data = &dqstats.stat[DQST_DROPS],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
{
.procname = "reads",
- .data = &dqstats.reads,
+ .data = &dqstats.stat[DQST_READS],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
{
.procname = "writes",
- .data = &dqstats.writes,
+ .data = &dqstats.stat[DQST_WRITES],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
{
.procname = "cache_hits",
- .data = &dqstats.cache_hits,
+ .data = &dqstats.stat[DQST_CACHE_HITS],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
{
.procname = "allocated_dquots",
- .data = &dqstats.allocated_dquots,
+ .data = &dqstats.stat[DQST_ALLOC_DQUOTS],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
{
.procname = "free_dquots",
- .data = &dqstats.free_dquots,
+ .data = &dqstats.stat[DQST_FREE_DQUOTS],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
{
.procname = "syncs",
- .data = &dqstats.syncs,
+ .data = &dqstats.stat[DQST_SYNCS],
.maxlen = sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = do_proc_dqstats,
},
#ifdef CONFIG_PRINT_QUOTA_WARNING
{
if (!dquot_hash)
panic("Cannot create dquot hash table");
+#ifdef CONFIG_SMP
+ dqstats_pcpu = alloc_percpu(struct dqstats);
+ if (!dqstats_pcpu)
+ panic("Cannot create dquot stats table");
+#endif
+ memset(&dqstats, 0, sizeof(struct dqstats));
+
/* Find power-of-two hlist_heads which can fit into allocation */
nr_hash = (1UL << order) * PAGE_SIZE / sizeof(struct hlist_head);
dq_hash_bits = 0;
projects / cascardo / linux.git / commitdiff