* (sct@redhat.com), 1993, 1998
*/
+#include <linux/aio.h>
#include "ext4_jbd2.h"
#include "truncate.h"
#include "ext4_extents.h" /* Needed for EXT_MAX_BLOCKS */
return count;
}
-/**
- * ext4_alloc_blocks: multiple allocate blocks needed for a branch
- * @handle: handle for this transaction
- * @inode: inode which needs allocated blocks
- * @iblock: the logical block to start allocated at
- * @goal: preferred physical block of allocation
- * @indirect_blks: the number of blocks need to allocate for indirect
- * blocks
- * @blks: number of desired blocks
- * @new_blocks: on return it will store the new block numbers for
- * the indirect blocks(if needed) and the first direct block,
- * @err: on return it will store the error code
- *
- * This function will return the number of blocks allocated as
- * requested by the passed-in parameters.
- */
-static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t iblock, ext4_fsblk_t goal,
- int indirect_blks, int blks,
- ext4_fsblk_t new_blocks[4], int *err)
-{
- struct ext4_allocation_request ar;
- int target, i;
- unsigned long count = 0, blk_allocated = 0;
- int index = 0;
- ext4_fsblk_t current_block = 0;
- int ret = 0;
-
- /*
- * Here we try to allocate the requested multiple blocks at once,
- * on a best-effort basis.
- * To build a branch, we should allocate blocks for
- * the indirect blocks(if not allocated yet), and at least
- * the first direct block of this branch. That's the
- * minimum number of blocks need to allocate(required)
- */
- /* first we try to allocate the indirect blocks */
- target = indirect_blks;
- while (target > 0) {
- count = target;
- /* allocating blocks for indirect blocks and direct blocks */
- current_block = ext4_new_meta_blocks(handle, inode, goal,
- 0, &count, err);
- if (*err)
- goto failed_out;
-
- if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) {
- EXT4_ERROR_INODE(inode,
- "current_block %llu + count %lu > %d!",
- current_block, count,
- EXT4_MAX_BLOCK_FILE_PHYS);
- *err = -EIO;
- goto failed_out;
- }
-
- target -= count;
- /* allocate blocks for indirect blocks */
- while (index < indirect_blks && count) {
- new_blocks[index++] = current_block++;
- count--;
- }
- if (count > 0) {
- /*
- * save the new block number
- * for the first direct block
- */
- new_blocks[index] = current_block;
- WARN(1, KERN_INFO "%s returned more blocks than "
- "requested\n", __func__);
- break;
- }
- }
-
- target = blks - count ;
- blk_allocated = count;
- if (!target)
- goto allocated;
- /* Now allocate data blocks */
- memset(&ar, 0, sizeof(ar));
- ar.inode = inode;
- ar.goal = goal;
- ar.len = target;
- ar.logical = iblock;
- if (S_ISREG(inode->i_mode))
- /* enable in-core preallocation only for regular files */
- ar.flags = EXT4_MB_HINT_DATA;
-
- current_block = ext4_mb_new_blocks(handle, &ar, err);
- if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) {
- EXT4_ERROR_INODE(inode,
- "current_block %llu + ar.len %d > %d!",
- current_block, ar.len,
- EXT4_MAX_BLOCK_FILE_PHYS);
- *err = -EIO;
- goto failed_out;
- }
-
- if (*err && (target == blks)) {
- /*
- * if the allocation failed and we didn't allocate
- * any blocks before
- */
- goto failed_out;
- }
- if (!*err) {
- if (target == blks) {
- /*
- * save the new block number
- * for the first direct block
- */
- new_blocks[index] = current_block;
- }
- blk_allocated += ar.len;
- }
-allocated:
- /* total number of blocks allocated for direct blocks */
- ret = blk_allocated;
- *err = 0;
- return ret;
-failed_out:
- for (i = 0; i < index; i++)
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
- return ret;
-}
-
/**
* ext4_alloc_branch - allocate and set up a chain of blocks.
* @handle: handle for this transaction
int *blks, ext4_fsblk_t goal,
ext4_lblk_t *offsets, Indirect *branch)
{
- int blocksize = inode->i_sb->s_blocksize;
- int i, n = 0;
- int err = 0;
- struct buffer_head *bh;
- int num;
- ext4_fsblk_t new_blocks[4];
- ext4_fsblk_t current_block;
+ struct ext4_allocation_request ar;
+ struct buffer_head * bh;
+ ext4_fsblk_t b, new_blocks[4];
+ __le32 *p;
+ int i, j, err, len = 1;
- num = ext4_alloc_blocks(handle, inode, iblock, goal, indirect_blks,
- *blks, new_blocks, &err);
- if (err)
- return err;
-
- branch[0].key = cpu_to_le32(new_blocks[0]);
/*
- * metadata blocks and data blocks are allocated.
+ * Set up for the direct block allocation
*/
- for (n = 1; n <= indirect_blks; n++) {
- /*
- * Get buffer_head for parent block, zero it out
- * and set the pointer to new one, then send
- * parent to disk.
- */
- bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+ memset(&ar, 0, sizeof(ar));
+ ar.inode = inode;
+ ar.len = *blks;
+ ar.logical = iblock;
+ if (S_ISREG(inode->i_mode))
+ ar.flags = EXT4_MB_HINT_DATA;
+
+ for (i = 0; i <= indirect_blks; i++) {
+ if (i == indirect_blks) {
+ ar.goal = goal;
+ new_blocks[i] = ext4_mb_new_blocks(handle, &ar, &err);
+ } else
+ goal = new_blocks[i] = ext4_new_meta_blocks(handle, inode,
+ goal, 0, NULL, &err);
+ if (err) {
+ i--;
+ goto failed;
+ }
+ branch[i].key = cpu_to_le32(new_blocks[i]);
+ if (i == 0)
+ continue;
+
+ bh = branch[i].bh = sb_getblk(inode->i_sb, new_blocks[i-1]);
if (unlikely(!bh)) {
err = -ENOMEM;
goto failed;
}
-
- branch[n].bh = bh;
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
err = ext4_journal_get_create_access(handle, bh);
if (err) {
- /* Don't brelse(bh) here; it's done in
- * ext4_journal_forget() below */
unlock_buffer(bh);
goto failed;
}
- memset(bh->b_data, 0, blocksize);
- branch[n].p = (__le32 *) bh->b_data + offsets[n];
- branch[n].key = cpu_to_le32(new_blocks[n]);
- *branch[n].p = branch[n].key;
- if (n == indirect_blks) {
- current_block = new_blocks[n];
- /*
- * End of chain, update the last new metablock of
- * the chain to point to the new allocated
- * data blocks numbers
- */
- for (i = 1; i < num; i++)
- *(branch[n].p + i) = cpu_to_le32(++current_block);
- }
+ memset(bh->b_data, 0, bh->b_size);
+ p = branch[i].p = (__le32 *) bh->b_data + offsets[i];
+ b = new_blocks[i];
+
+ if (i == indirect_blks)
+ len = ar.len;
+ for (j = 0; j < len; j++)
+ *p++ = cpu_to_le32(b++);
+
BUFFER_TRACE(bh, "marking uptodate");
set_buffer_uptodate(bh);
unlock_buffer(bh);
if (err)
goto failed;
}
- *blks = num;
- return err;
+ *blks = ar.len;
+ return 0;
failed:
- /* Allocation failed, free what we already allocated */
- ext4_free_blocks(handle, inode, NULL, 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.
- */
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
- EXT4_FREE_BLOCKS_FORGET);
+ for (; i >= 0; i--) {
+ if (i != indirect_blks && branch[i].bh)
+ ext4_forget(handle, 1, inode, branch[i].bh,
+ branch[i].bh->b_blocknr);
+ ext4_free_blocks(handle, inode, NULL, new_blocks[i],
+ (i == indirect_blks) ? ar.len : 1, 0);
}
- for (i = n+1; i < indirect_blks; i++)
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
-
- ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
-
return err;
}
return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
}
-int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+/*
+ * Calculate number of indirect blocks touched by mapping @nrblocks logically
+ * contiguous blocks
+ */
+int ext4_ind_trans_blocks(struct inode *inode, int nrblocks)
{
- int indirects;
-
- /* if nrblocks are contiguous */
- if (chunk) {
- /*
- * With N contiguous data blocks, we need at most
- * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
- * 2 dindirect blocks, and 1 tindirect block
- */
- return DIV_ROUND_UP(nrblocks,
- EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
- }
/*
- * if nrblocks are not contiguous, worse case, each block touch
- * a indirect block, and each indirect block touch a double indirect
- * block, plus a triple indirect block
+ * With N contiguous data blocks, we need at most
+ * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
+ * 2 dindirect blocks, and 1 tindirect block
*/
- indirects = nrblocks * 2 + 1;
- return indirects;
+ return DIV_ROUND_UP(nrblocks, EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
}
/*
* be able to restart the transaction at a conventient checkpoint to make
* sure we don't overflow the journal.
*
- * start_transaction gets us a new handle for a truncate transaction,
- * and extend_transaction tries to extend the existing one a bit. If
+ * Try to extend this transaction for the purposes of truncation. If
* extend fails, we need to propagate the failure up and restart the
* transaction in the top-level truncate loop. --sct
- */
-static handle_t *start_transaction(struct inode *inode)
-{
- handle_t *result;
-
- result = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
- ext4_blocks_for_truncate(inode));
- if (!IS_ERR(result))
- return result;
-
- ext4_std_error(inode->i_sb, PTR_ERR(result));
- return result;
-}
-
-/*
- * Try to extend this transaction for the purposes of truncation.
*
* Returns 0 if we managed to create more room. If we can't create more
* room, and the transaction must be restarted we return 1.
}
}
-void ext4_ind_truncate(struct inode *inode)
+void ext4_ind_truncate(handle_t *handle, struct inode *inode)
{
- handle_t *handle;
struct ext4_inode_info *ei = EXT4_I(inode);
__le32 *i_data = ei->i_data;
int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- struct address_space *mapping = inode->i_mapping;
ext4_lblk_t offsets[4];
Indirect chain[4];
Indirect *partial;
__le32 nr = 0;
int n = 0;
ext4_lblk_t last_block, max_block;
- loff_t page_len;
unsigned blocksize = inode->i_sb->s_blocksize;
- int err;
-
- handle = start_transaction(inode);
- if (IS_ERR(handle))
- return; /* AKPM: return what? */
last_block = (inode->i_size + blocksize-1)
>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
- if (inode->i_size % PAGE_CACHE_SIZE != 0) {
- page_len = PAGE_CACHE_SIZE -
- (inode->i_size & (PAGE_CACHE_SIZE - 1));
-
- err = ext4_discard_partial_page_buffers(handle,
- mapping, inode->i_size, page_len, 0);
-
- if (err)
- goto out_stop;
- }
-
if (last_block != max_block) {
n = ext4_block_to_path(inode, last_block, offsets, NULL);
if (n == 0)
- goto out_stop; /* error */
+ return;
}
- /*
- * OK. This truncate is going to happen. We add the inode to the
- * orphan list, so that if this truncate spans multiple transactions,
- * and we crash, we will resume the truncate when the filesystem
- * recovers. It also marks the inode dirty, to catch the new size.
- *
- * Implication: the file must always be in a sane, consistent
- * truncatable state while each transaction commits.
- */
- if (ext4_orphan_add(handle, inode))
- goto out_stop;
-
- /*
- * From here we block out all ext4_get_block() callers who want to
- * modify the block allocation tree.
- */
- down_write(&ei->i_data_sem);
-
- ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block);
/*
* It is unnecessary to free any data blocks if last_block is
* equal to the indirect block limit.
*/
- goto out_unlock;
+ return;
} else if (n == 1) { /* direct blocks */
ext4_free_data(handle, inode, NULL, i_data+offsets[0],
i_data + EXT4_NDIR_BLOCKS);
case EXT4_TIND_BLOCK:
;
}
-
-out_unlock:
- up_write(&ei->i_data_sem);
- inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
-
- /*
- * In a multi-transaction truncate, we only make the final transaction
- * synchronous
- */
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-out_stop:
- /*
- * If this was a simple ftruncate(), and the file will remain alive
- * then we need to clear up the orphan record which we created above.
- * However, if this was a real unlink then we were called by
- * ext4_delete_inode(), and we allow that function to clean up the
- * orphan info for us.
- */
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
-
- ext4_journal_stop(handle);
- trace_ext4_truncate_exit(inode);
}
static int free_hole_blocks(handle_t *handle, struct inode *inode,
return ret;
}
-static int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
- ext4_lblk_t first, ext4_lblk_t stop)
+int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
+ ext4_lblk_t first, ext4_lblk_t stop)
{
int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
int level, ret = 0;
return ret;
}
-int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length)
-{
- struct inode *inode = file_inode(file);
- struct super_block *sb = inode->i_sb;
- ext4_lblk_t first_block, stop_block;
- struct address_space *mapping = inode->i_mapping;
- handle_t *handle = NULL;
- loff_t first_page, last_page, page_len;
- loff_t first_page_offset, last_page_offset;
- int err = 0;
-
- /*
- * Write out all dirty pages to avoid race conditions
- * Then release them.
- */
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
- err = filemap_write_and_wait_range(mapping,
- offset, offset + length - 1);
- if (err)
- return err;
- }
-
- mutex_lock(&inode->i_mutex);
- /* It's not possible punch hole on append only file */
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
- err = -EPERM;
- goto out_mutex;
- }
- if (IS_SWAPFILE(inode)) {
- err = -ETXTBSY;
- goto out_mutex;
- }
-
- /* No need to punch hole beyond i_size */
- if (offset >= inode->i_size)
- goto out_mutex;
-
- /*
- * If the hole extents beyond i_size, set the hole
- * to end after the page that contains i_size
- */
- if (offset + length > inode->i_size) {
- length = inode->i_size +
- PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
- offset;
- }
-
- first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- last_page = (offset + length) >> PAGE_CACHE_SHIFT;
-
- first_page_offset = first_page << PAGE_CACHE_SHIFT;
- last_page_offset = last_page << PAGE_CACHE_SHIFT;
-
- /* Now release the pages */
- if (last_page_offset > first_page_offset) {
- truncate_pagecache_range(inode, first_page_offset,
- last_page_offset - 1);
- }
-
- /* Wait all existing dio works, newcomers will block on i_mutex */
- inode_dio_wait(inode);
-
- handle = start_transaction(inode);
- if (IS_ERR(handle))
- goto out_mutex;
-
- /*
- * Now we need to zero out the non-page-aligned data in the
- * pages at the start and tail of the hole, and unmap the buffer
- * heads for the block aligned regions of the page that were
- * completely zerod.
- */
- if (first_page > last_page) {
- /*
- * If the file space being truncated is contained within a page
- * just zero out and unmap the middle of that page
- */
- err = ext4_discard_partial_page_buffers(handle,
- mapping, offset, length, 0);
- if (err)
- goto out;
- } else {
- /*
- * Zero out and unmap the paritial page that contains
- * the start of the hole
- */
- page_len = first_page_offset - offset;
- if (page_len > 0) {
- err = ext4_discard_partial_page_buffers(handle, mapping,
- offset, page_len, 0);
- if (err)
- goto out;
- }
-
- /*
- * Zero out and unmap the partial page that contains
- * the end of the hole
- */
- page_len = offset + length - last_page_offset;
- if (page_len > 0) {
- err = ext4_discard_partial_page_buffers(handle, mapping,
- last_page_offset, page_len, 0);
- if (err)
- goto out;
- }
- }
-
- /*
- * If i_size contained in the last page, we need to
- * unmap and zero the paritial page after i_size
- */
- if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
- inode->i_size % PAGE_CACHE_SIZE != 0) {
- page_len = PAGE_CACHE_SIZE -
- (inode->i_size & (PAGE_CACHE_SIZE - 1));
- if (page_len > 0) {
- err = ext4_discard_partial_page_buffers(handle,
- mapping, inode->i_size, page_len, 0);
- if (err)
- goto out;
- }
- }
-
- first_block = (offset + sb->s_blocksize - 1) >>
- EXT4_BLOCK_SIZE_BITS(sb);
- stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
- if (first_block >= stop_block)
- goto out;
-
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
-
- err = ext4_es_remove_extent(inode, first_block,
- stop_block - first_block);
- err = ext4_free_hole_blocks(handle, inode, first_block, stop_block);
-
- ext4_discard_preallocations(inode);
-
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-
- up_write(&EXT4_I(inode)->i_data_sem);
-
-out:
- inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
- ext4_journal_stop(handle);
-
-out_mutex:
- mutex_unlock(&inode->i_mutex);
-
- return err;
-}
projects / ~andy / linux / blobdiff