#include <linux/module.h>
#include <linux/fs.h>
#include <linux/time.h>
-#include <linux/ext4_jbd2.h>
#include <linux/jbd2.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/falloc.h>
-#include <linux/ext4_fs_extents.h>
#include <asm/uaccess.h>
+#include "ext4_jbd2.h"
+#include "ext4_extents.h"
/*
* idx_pblock:
* combine low and high parts of a leaf physical block number into ext4_fsblk_t
*/
-static ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
+ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
{
ext4_fsblk_t block;
* stores a large physical block number into an extent struct,
* breaking it into parts
*/
-static void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
+void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
{
ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
{
struct ext4_inode_info *ei = EXT4_I(inode);
ext4_fsblk_t bg_start;
+ ext4_fsblk_t last_block;
ext4_grpblk_t colour;
int depth;
/* OK. use inode's group */
bg_start = (ei->i_block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
- colour = (current->pid % 16) *
+ last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+ if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+ colour = (current->pid % 16) *
(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+ else
+ colour = (current->pid % 16) * ((last_block - bg_start) / 16);
return bg_start + colour + block;
}
}
#define ext4_ext_check_header(inode, eh, depth) \
- __ext4_ext_check_header(__FUNCTION__, inode, eh, depth)
+ __ext4_ext_check_header(__func__, inode, eh, depth)
#ifdef EXT_DEBUG
static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
#define ext4_ext_show_leaf(inode,path)
#endif
-static void ext4_ext_drop_refs(struct ext4_ext_path *path)
+void ext4_ext_drop_refs(struct ext4_ext_path *path)
{
int depth = path->p_depth;
int i;
ix->ei_block = cpu_to_le32(logical);
ext4_idx_store_pblock(ix, ptr);
- curp->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(curp->p_hdr->eh_entries)+1);
+ le16_add_cpu(&curp->p_hdr->eh_entries, 1);
BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries)
> le16_to_cpu(curp->p_hdr->eh_max));
}
if (m) {
memmove(ex, path[depth].p_ext-m, sizeof(struct ext4_extent)*m);
- neh->eh_entries = cpu_to_le16(le16_to_cpu(neh->eh_entries)+m);
+ le16_add_cpu(&neh->eh_entries, m);
}
set_buffer_uptodate(bh);
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto cleanup;
- path[depth].p_hdr->eh_entries =
- cpu_to_le16(le16_to_cpu(path[depth].p_hdr->eh_entries)-m);
+ le16_add_cpu(&path[depth].p_hdr->eh_entries, -m);
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto cleanup;
if (m) {
memmove(++fidx, path[i].p_idx - m,
sizeof(struct ext4_extent_idx) * m);
- neh->eh_entries =
- cpu_to_le16(le16_to_cpu(neh->eh_entries) + m);
+ le16_add_cpu(&neh->eh_entries, m);
}
set_buffer_uptodate(bh);
unlock_buffer(bh);
err = ext4_ext_get_access(handle, inode, path + i);
if (err)
goto cleanup;
- path[i].p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path[i].p_hdr->eh_entries)-m);
+ le16_add_cpu(&path[i].p_hdr->eh_entries, -m);
err = ext4_ext_dirty(handle, inode, path + i);
if (err)
goto cleanup;
for (i = 0; i < depth; i++) {
if (!ablocks[i])
continue;
- ext4_free_blocks(handle, inode, ablocks[i], 1);
+ ext4_free_blocks(handle, inode, ablocks[i], 1, 1);
}
}
kfree(ablocks);
return err;
}
+/*
+ * search the closest allocated block to the left for *logical
+ * and returns it at @logical + it's physical address at @phys
+ * if *logical is the smallest allocated block, the function
+ * returns 0 at @phys
+ * return value contains 0 (success) or error code
+ */
+int
+ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
+ ext4_lblk_t *logical, ext4_fsblk_t *phys)
+{
+ struct ext4_extent_idx *ix;
+ struct ext4_extent *ex;
+ int depth, ee_len;
+
+ BUG_ON(path == NULL);
+ depth = path->p_depth;
+ *phys = 0;
+
+ if (depth == 0 && path->p_ext == NULL)
+ return 0;
+
+ /* usually extent in the path covers blocks smaller
+ * then *logical, but it can be that extent is the
+ * first one in the file */
+
+ ex = path[depth].p_ext;
+ ee_len = ext4_ext_get_actual_len(ex);
+ if (*logical < le32_to_cpu(ex->ee_block)) {
+ BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ while (--depth >= 0) {
+ ix = path[depth].p_idx;
+ BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ }
+ return 0;
+ }
+
+ BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+
+ *logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
+ *phys = ext_pblock(ex) + ee_len - 1;
+ return 0;
+}
+
+/*
+ * search the closest allocated block to the right for *logical
+ * and returns it at @logical + it's physical address at @phys
+ * if *logical is the smallest allocated block, the function
+ * returns 0 at @phys
+ * return value contains 0 (success) or error code
+ */
+int
+ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
+ ext4_lblk_t *logical, ext4_fsblk_t *phys)
+{
+ struct buffer_head *bh = NULL;
+ struct ext4_extent_header *eh;
+ struct ext4_extent_idx *ix;
+ struct ext4_extent *ex;
+ ext4_fsblk_t block;
+ int depth, ee_len;
+
+ BUG_ON(path == NULL);
+ depth = path->p_depth;
+ *phys = 0;
+
+ if (depth == 0 && path->p_ext == NULL)
+ return 0;
+
+ /* usually extent in the path covers blocks smaller
+ * then *logical, but it can be that extent is the
+ * first one in the file */
+
+ ex = path[depth].p_ext;
+ ee_len = ext4_ext_get_actual_len(ex);
+ if (*logical < le32_to_cpu(ex->ee_block)) {
+ BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ while (--depth >= 0) {
+ ix = path[depth].p_idx;
+ BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ }
+ *logical = le32_to_cpu(ex->ee_block);
+ *phys = ext_pblock(ex);
+ return 0;
+ }
+
+ BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+
+ if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
+ /* next allocated block in this leaf */
+ ex++;
+ *logical = le32_to_cpu(ex->ee_block);
+ *phys = ext_pblock(ex);
+ return 0;
+ }
+
+ /* go up and search for index to the right */
+ while (--depth >= 0) {
+ ix = path[depth].p_idx;
+ if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
+ break;
+ }
+
+ if (depth < 0) {
+ /* we've gone up to the root and
+ * found no index to the right */
+ return 0;
+ }
+
+ /* we've found index to the right, let's
+ * follow it and find the closest allocated
+ * block to the right */
+ ix++;
+ block = idx_pblock(ix);
+ while (++depth < path->p_depth) {
+ bh = sb_bread(inode->i_sb, block);
+ if (bh == NULL)
+ return -EIO;
+ eh = ext_block_hdr(bh);
+ if (ext4_ext_check_header(inode, eh, depth)) {
+ put_bh(bh);
+ return -EIO;
+ }
+ ix = EXT_FIRST_INDEX(eh);
+ block = idx_pblock(ix);
+ put_bh(bh);
+ }
+
+ bh = sb_bread(inode->i_sb, block);
+ if (bh == NULL)
+ return -EIO;
+ eh = ext_block_hdr(bh);
+ if (ext4_ext_check_header(inode, eh, path->p_depth - depth)) {
+ put_bh(bh);
+ return -EIO;
+ }
+ ex = EXT_FIRST_EXTENT(eh);
+ *logical = le32_to_cpu(ex->ee_block);
+ *phys = ext_pblock(ex);
+ put_bh(bh);
+ return 0;
+
+}
+
/*
* ext4_ext_next_allocated_block:
* returns allocated block in subsequent extent or EXT_MAX_BLOCK.
* then we have to correct all indexes above.
* TODO: do we need to correct tree in all cases?
*/
-int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
+static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
struct ext4_extent_header *eh;
if (ext1_ee_len + ext2_ee_len > max_len)
return 0;
#ifdef AGGRESSIVE_TEST
- if (le16_to_cpu(ex1->ee_len) >= 4)
+ if (ext1_ee_len >= 4)
return 0;
#endif
* sizeof(struct ext4_extent);
memmove(ex + 1, ex + 2, len);
}
- eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries) - 1);
+ le16_add_cpu(&eh->eh_entries, -1);
merge_done = 1;
WARN_ON(eh->eh_entries == 0);
if (!eh->eh_entries)
path[depth].p_ext = nearex;
}
- eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)+1);
+ le16_add_cpu(&eh->eh_entries, 1);
nearex = path[depth].p_ext;
nearex->ee_block = newext->ee_block;
ext4_ext_store_pblock(nearex, ext_pblock(newext));
* It's used in truncate case only, thus all requests are for
* last index in the block only.
*/
-int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
+static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
struct buffer_head *bh;
err = ext4_ext_get_access(handle, inode, path);
if (err)
return err;
- path->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path->p_hdr->eh_entries)-1);
+ le16_add_cpu(&path->p_hdr->eh_entries, -1);
err = ext4_ext_dirty(handle, inode, path);
if (err)
return err;
ext_debug("index is empty, remove it, free block %llu\n", leaf);
bh = sb_find_get_block(inode->i_sb, leaf);
ext4_forget(handle, 1, inode, bh, leaf);
- ext4_free_blocks(handle, inode, leaf, 1);
+ ext4_free_blocks(handle, inode, leaf, 1, 1);
return err;
}
* This routine returns max. credits that the extent tree can consume.
* It should be OK for low-performance paths like ->writepage()
* To allow many writing processes to fit into a single transaction,
- * the caller should calculate credits under truncate_mutex and
+ * the caller should calculate credits under i_data_sem and
* pass the actual path.
*/
int ext4_ext_calc_credits_for_insert(struct inode *inode,
{
struct buffer_head *bh;
unsigned short ee_len = ext4_ext_get_actual_len(ex);
- int i;
+ int i, metadata = 0;
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ metadata = 1;
#ifdef EXTENTS_STATS
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
bh = sb_find_get_block(inode->i_sb, start + i);
ext4_forget(handle, 0, inode, bh, start + i);
}
- ext4_free_blocks(handle, inode, start, num);
+ ext4_free_blocks(handle, inode, start, num, metadata);
} else if (from == le32_to_cpu(ex->ee_block)
&& to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
if (num == 0) {
/* this extent is removed; mark slot entirely unused */
ext4_ext_store_pblock(ex, 0);
- eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1);
+ le16_add_cpu(&eh->eh_entries, -1);
}
ex->ee_block = cpu_to_le32(block);
return 1;
}
-int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
- path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_KERNEL);
+ path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
if (path == NULL) {
ext4_journal_stop(handle);
return -ENOMEM;
#endif
}
+static void bi_complete(struct bio *bio, int error)
+{
+ complete((struct completion *)bio->bi_private);
+}
+
+/* FIXME!! we need to try to merge to left or right after zero-out */
+static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+ int ret = -EIO;
+ struct bio *bio;
+ int blkbits, blocksize;
+ sector_t ee_pblock;
+ struct completion event;
+ unsigned int ee_len, len, done, offset;
+
+
+ blkbits = inode->i_blkbits;
+ blocksize = inode->i_sb->s_blocksize;
+ ee_len = ext4_ext_get_actual_len(ex);
+ ee_pblock = ext_pblock(ex);
+
+ /* convert ee_pblock to 512 byte sectors */
+ ee_pblock = ee_pblock << (blkbits - 9);
+
+ while (ee_len > 0) {
+
+ if (ee_len > BIO_MAX_PAGES)
+ len = BIO_MAX_PAGES;
+ else
+ len = ee_len;
+
+ bio = bio_alloc(GFP_NOIO, len);
+ if (!bio)
+ return -ENOMEM;
+ bio->bi_sector = ee_pblock;
+ bio->bi_bdev = inode->i_sb->s_bdev;
+
+ done = 0;
+ offset = 0;
+ while (done < len) {
+ ret = bio_add_page(bio, ZERO_PAGE(0),
+ blocksize, offset);
+ if (ret != blocksize) {
+ /*
+ * We can't add any more pages because of
+ * hardware limitations. Start a new bio.
+ */
+ break;
+ }
+ done++;
+ offset += blocksize;
+ if (offset >= PAGE_CACHE_SIZE)
+ offset = 0;
+ }
+
+ init_completion(&event);
+ bio->bi_private = &event;
+ bio->bi_end_io = bi_complete;
+ submit_bio(WRITE, bio);
+ wait_for_completion(&event);
+
+ if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ ret = 0;
+ else {
+ ret = -EIO;
+ break;
+ }
+ bio_put(bio);
+ ee_len -= done;
+ ee_pblock += done << (blkbits - 9);
+ }
+ return ret;
+}
+
+#define EXT4_EXT_ZERO_LEN 7
+
/*
* This function is called by ext4_ext_get_blocks() if someone tries to write
* to an uninitialized extent. It may result in splitting the uninitialized
ext4_lblk_t iblock,
unsigned long max_blocks)
{
- struct ext4_extent *ex, newex;
+ struct ext4_extent *ex, newex, orig_ex;
struct ext4_extent *ex1 = NULL;
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
allocated = ee_len - (iblock - ee_block);
newblock = iblock - ee_block + ext_pblock(ex);
ex2 = ex;
+ orig_ex.ee_block = ex->ee_block;
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+ /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
+ if (ee_len <= 2*EXT4_EXT_ZERO_LEN) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ return allocated;
+ }
/* ex1: ee_block to iblock - 1 : uninitialized */
if (iblock > ee_block) {
/* ex3: to ee_block + ee_len : uninitialised */
if (allocated > max_blocks) {
unsigned int newdepth;
+ /* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
+ if (allocated <= EXT4_EXT_ZERO_LEN) {
+ /* Mark first half uninitialized.
+ * Mark second half initialized and zero out the
+ * initialized extent
+ */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = cpu_to_le16(ee_len - allocated);
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+
+ ex3 = &newex;
+ ex3->ee_block = cpu_to_le32(iblock);
+ ext4_ext_store_pblock(ex3, newblock);
+ ex3->ee_len = cpu_to_le16(allocated);
+ err = ext4_ext_insert_extent(handle, inode, path, ex3);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ return allocated;
+
+ } else if (err)
+ goto fix_extent_len;
+
+ /*
+ * We need to zero out the second half because
+ * an fallocate request can update file size and
+ * converting the second half to initialized extent
+ * implies that we can leak some junk data to user
+ * space.
+ */
+ err = ext4_ext_zeroout(inode, ex3);
+ if (err) {
+ /*
+ * We should actually mark the
+ * second half as uninit and return error
+ * Insert would have changed the extent
+ */
+ depth = ext_depth(inode);
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode,
+ iblock, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ return err;
+ }
+ ex = path[depth].p_ext;
+ err = ext4_ext_get_access(handle, inode,
+ path + depth);
+ if (err)
+ return err;
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_dirty(handle, inode, path + depth);
+ return err;
+ }
+
+ /* zeroed the second half */
+ return allocated;
+ }
ex3 = &newex;
ex3->ee_block = cpu_to_le32(iblock + max_blocks);
ext4_ext_store_pblock(ex3, newblock + max_blocks);
ex3->ee_len = cpu_to_le16(allocated - max_blocks);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3);
- if (err)
- goto out;
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ return allocated;
+
+ } else if (err)
+ goto fix_extent_len;
/*
* The depth, and hence eh & ex might change
* as part of the insert above.
*/
newdepth = ext_depth(inode);
+ /*
+ * update the extent length after successfull insert of the
+ * split extent
+ */
+ orig_ex.ee_len = cpu_to_le16(ee_len -
+ ext4_ext_get_actual_len(ex3));
if (newdepth != depth) {
depth = newdepth;
- path = ext4_ext_find_extent(inode, iblock, NULL);
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode, iblock, path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
- path = NULL;
goto out;
}
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
if (ex2 != &newex)
ex2 = ex;
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
}
allocated = max_blocks;
+
+ /* If extent has less than EXT4_EXT_ZERO_LEN and we are trying
+ * to insert a extent in the middle zerout directly
+ * otherwise give the extent a chance to merge to left
+ */
+ if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
+ iblock != ee_block) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zero out the first half */
+ return allocated;
+ }
}
/*
* If there was a change of depth as part of the
ex2->ee_len = cpu_to_le16(allocated);
if (ex2 != ex)
goto insert;
- err = ext4_ext_get_access(handle, inode, path + depth);
- if (err)
- goto out;
/*
* New (initialized) extent starts from the first block
* in the current extent. i.e., ex2 == ex
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zero out the first half */
+ return allocated;
+ } else if (err)
+ goto fix_extent_len;
out:
return err ? err : allocated;
+
+fix_extent_len:
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_dirty(handle, inode, path + depth);
+ return err;
}
+/*
+ * Block allocation/map/preallocation routine for extents based files
+ *
+ *
+ * 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)
+ *
+ * return > 0, number of of blocks already mapped/allocated
+ * if create == 0 and these are pre-allocated blocks
+ * buffer head is unmapped
+ * otherwise blocks are mapped
+ *
+ * return = 0, if plain look up failed (blocks have not been allocated)
+ * buffer head is unmapped
+ *
+ * return < 0, error case.
+ */
int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock,
unsigned long max_blocks, struct buffer_head *bh_result,
ext4_fsblk_t goal, newblock;
int err = 0, depth, ret;
unsigned long allocated = 0;
+ struct ext4_allocation_request ar;
__clear_bit(BH_New, &bh_result->b_state);
ext_debug("blocks %u/%lu requested for inode %u\n",
iblock, max_blocks, inode->i_ino);
- mutex_lock(&EXT4_I(inode)->truncate_mutex);
/* check in cache */
goal = ext4_ext_in_cache(inode, iblock, &newex);
- le32_to_cpu(newex.ee_block)
+ ext_pblock(&newex);
/* number of remaining blocks in the extent */
- allocated = le16_to_cpu(newex.ee_len) -
+ allocated = ext4_ext_get_actual_len(&newex) -
(iblock - le32_to_cpu(newex.ee_block));
goto out;
} else {
}
if (create == EXT4_CREATE_UNINITIALIZED_EXT)
goto out;
- if (!create)
+ if (!create) {
+ /*
+ * We have blocks reserved already. We
+ * return allocated blocks so that delalloc
+ * won't do block reservation for us. But
+ * the buffer head will be unmapped so that
+ * a read from the block returns 0s.
+ */
+ if (allocated > max_blocks)
+ allocated = max_blocks;
+ /* mark the buffer unwritten */
+ __set_bit(BH_Unwritten, &bh_result->b_state);
goto out2;
+ }
ret = ext4_ext_convert_to_initialized(handle, inode,
path, iblock,
max_blocks);
- if (ret <= 0)
+ if (ret <= 0) {
+ err = ret;
goto out2;
- else
+ } else
allocated = ret;
goto outnew;
}
if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info))
ext4_init_block_alloc_info(inode);
- /* allocate new block */
- goal = ext4_ext_find_goal(inode, path, iblock);
+ /* find neighbour allocated blocks */
+ ar.lleft = iblock;
+ err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
+ if (err)
+ goto out2;
+ ar.lright = iblock;
+ err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
+ if (err)
+ goto out2;
/*
* See if request is beyond maximum number of blocks we can have in
newex.ee_len = cpu_to_le16(max_blocks);
err = ext4_ext_check_overlap(inode, &newex, path);
if (err)
- allocated = le16_to_cpu(newex.ee_len);
+ allocated = ext4_ext_get_actual_len(&newex);
else
allocated = max_blocks;
- newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err);
+
+ /* allocate new block */
+ ar.inode = inode;
+ ar.goal = ext4_ext_find_goal(inode, path, iblock);
+ ar.logical = iblock;
+ ar.len = allocated;
+ if (S_ISREG(inode->i_mode))
+ ar.flags = EXT4_MB_HINT_DATA;
+ else
+ /* disable in-core preallocation for non-regular files */
+ ar.flags = 0;
+ newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock);
- newex.ee_len = cpu_to_le16(allocated);
+ newex.ee_len = cpu_to_le16(ar.len);
if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */
ext4_ext_mark_uninitialized(&newex);
err = ext4_ext_insert_extent(handle, inode, path, &newex);
if (err) {
/* free data blocks we just allocated */
+ /* not a good idea to call discard here directly,
+ * but otherwise we'd need to call it every free() */
+ ext4_mb_discard_inode_preallocations(inode);
ext4_free_blocks(handle, inode, ext_pblock(&newex),
- le16_to_cpu(newex.ee_len));
+ ext4_ext_get_actual_len(&newex), 0);
goto out2;
}
/* previous routine could use block we allocated */
newblock = ext_pblock(&newex);
+ allocated = ext4_ext_get_actual_len(&newex);
outnew:
__set_bit(BH_New, &bh_result->b_state);
ext4_ext_drop_refs(path);
kfree(path);
}
- mutex_unlock(&EXT4_I(inode)->truncate_mutex);
-
return err ? err : allocated;
}
if (page)
ext4_block_truncate_page(handle, page, mapping, inode->i_size);
- mutex_lock(&EXT4_I(inode)->truncate_mutex);
+ down_write(&EXT4_I(inode)->i_data_sem);
ext4_ext_invalidate_cache(inode);
+ ext4_mb_discard_inode_preallocations(inode);
+
/*
* TODO: optimization is possible here.
* Probably we need not scan at all,
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
- mutex_unlock(&EXT4_I(inode)->truncate_mutex);
+ up_write(&EXT4_I(inode)->i_data_sem);
ext4_journal_stop(handle);
}
return needed;
}
+static void ext4_falloc_update_inode(struct inode *inode,
+ int mode, loff_t new_size, int update_ctime)
+{
+ struct timespec now;
+
+ if (update_ctime) {
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_ctime, &now))
+ inode->i_ctime = now;
+ }
+ /*
+ * Update only when preallocation was requested beyond
+ * the file size.
+ */
+ if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+ new_size > i_size_read(inode)) {
+ i_size_write(inode, new_size);
+ EXT4_I(inode)->i_disksize = new_size;
+ }
+
+}
+
/*
* preallocate space for a file. This implements ext4's fallocate inode
* operation, which gets called from sys_fallocate system call.
{
handle_t *handle;
ext4_lblk_t block;
+ loff_t new_size;
unsigned long max_blocks;
- ext4_fsblk_t nblocks = 0;
int ret = 0;
int ret2 = 0;
int retries = 0;
return -ENODEV;
block = offset >> blkbits;
+ /*
+ * We can't just convert len to max_blocks because
+ * If blocksize = 4096 offset = 3072 and len = 2048
+ */
max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
- - block;
-
+ - block;
/*
* credits to insert 1 extent into extent tree + buffers to be able to
* modify 1 super block, 1 block bitmap and 1 group descriptor.
*/
credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
+ mutex_lock(&inode->i_mutex);
retry:
while (ret >= 0 && ret < max_blocks) {
block = block + ret;
ret = PTR_ERR(handle);
break;
}
-
- ret = ext4_ext_get_blocks(handle, inode, block,
+ ret = ext4_get_blocks_wrap(handle, inode, block,
max_blocks, &map_bh,
EXT4_CREATE_UNINITIALIZED_EXT, 0);
- WARN_ON(!ret);
- if (!ret) {
- ext4_error(inode->i_sb, "ext4_fallocate",
- "ext4_ext_get_blocks returned 0! inode#%lu"
- ", block=%u, max_blocks=%lu",
- inode->i_ino, block, max_blocks);
- ret = -EIO;
+ if (ret <= 0) {
+#ifdef EXT4FS_DEBUG
+ WARN_ON(ret <= 0);
+ printk(KERN_ERR "%s: ext4_ext_get_blocks "
+ "returned error inode#%lu, block=%u, "
+ "max_blocks=%lu", __func__,
+ inode->i_ino, block, max_blocks);
+#endif
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
break;
}
- if (ret > 0) {
- /* check wrap through sign-bit/zero here */
- if ((block + ret) < 0 || (block + ret) < block) {
- ret = -EIO;
- ext4_mark_inode_dirty(handle, inode);
- ret2 = ext4_journal_stop(handle);
- break;
- }
- if (buffer_new(&map_bh) && ((block + ret) >
- (EXT4_BLOCK_ALIGN(i_size_read(inode), blkbits)
- >> blkbits)))
- nblocks = nblocks + ret;
- }
-
- /* Update ctime if new blocks get allocated */
- if (nblocks) {
- struct timespec now;
-
- now = current_fs_time(inode->i_sb);
- if (!timespec_equal(&inode->i_ctime, &now))
- inode->i_ctime = now;
- }
+ if ((block + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
+ blkbits) >> blkbits))
+ new_size = offset + len;
+ else
+ new_size = (block + ret) << blkbits;
+ ext4_falloc_update_inode(inode, mode, new_size,
+ buffer_new(&map_bh));
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
if (ret2)
break;
}
-
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries)) {
+ ret = 0;
goto retry;
-
- /*
- * Time to update the file size.
- * Update only when preallocation was requested beyond the file size.
- */
- if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- (offset + len) > i_size_read(inode)) {
- if (ret > 0) {
- /*
- * if no error, we assume preallocation succeeded
- * completely
- */
- mutex_lock(&inode->i_mutex);
- i_size_write(inode, offset + len);
- EXT4_I(inode)->i_disksize = i_size_read(inode);
- mutex_unlock(&inode->i_mutex);
- } else if (ret < 0 && nblocks) {
- /* Handle partial allocation scenario */
- loff_t newsize;
-
- mutex_lock(&inode->i_mutex);
- newsize = (nblocks << blkbits) + i_size_read(inode);
- i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits));
- EXT4_I(inode)->i_disksize = i_size_read(inode);
- mutex_unlock(&inode->i_mutex);
- }
}
-
+ mutex_unlock(&inode->i_mutex);
return ret > 0 ? ret2 : ret;
}
projects / linux-2.6-omap-h63xx.git / blobdiff