clear_inode(inode); /* We must guarantee clearing of inode... */
}
-static int ext3_alloc_block (handle_t *handle,
- struct inode * inode, unsigned long goal, int *err)
-{
- unsigned long result;
-
- result = ext3_new_block(handle, inode, goal, err);
- return result;
-}
-
-
typedef struct {
__le32 *p;
__le32 key;
ext3_warning (inode->i_sb, "ext3_block_to_path", "block > big");
}
if (boundary)
- *boundary = (i_block & (ptrs - 1)) == (final - 1);
+ *boundary = final - 1 - (i_block & (ptrs - 1));
return n;
}
return ext3_find_near(inode, partial);
}
+/**
+ * ext3_blks_to_allocate: Look up the block map and count the number
+ * of direct blocks need to be allocated for the given branch.
+ *
+ * @branch: chain of indirect blocks
+ * @k: number of blocks need for indirect blocks
+ * @blks: number of data blocks to be mapped.
+ * @blocks_to_boundary: the offset in the indirect block
+ *
+ * return the total number of blocks to be allocate, including the
+ * direct and indirect blocks.
+ */
+static int
+ext3_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
+ int blocks_to_boundary)
+{
+ unsigned long count = 0;
+
+ /*
+ * Simple case, [t,d]Indirect block(s) has not allocated yet
+ * then it's clear blocks on that path have not allocated
+ */
+ if (k > 0) {
+ /* right now don't hanel cross boundary allocation */
+ if (blks < blocks_to_boundary + 1)
+ count += blks;
+ else
+ count += blocks_to_boundary + 1;
+ return count;
+ }
+
+ count++;
+ while (count < blks && count <= blocks_to_boundary &&
+ le32_to_cpu(*(branch[0].p + count)) == 0) {
+ count++;
+ }
+ return count;
+}
+
+/**
+ * ext3_alloc_blocks: multiple allocate blocks needed for a branch
+ * @indirect_blks: the number of blocks need to allocate for indirect
+ * blocks
+ *
+ * @new_blocks: on return it will store the new block numbers for
+ * the indirect blocks(if needed) and the first direct block,
+ * @blks: on return it will store the total number of allocated
+ * direct blocks
+ */
+static int ext3_alloc_blocks(handle_t *handle, struct inode *inode,
+ unsigned long goal, int indirect_blks, int blks,
+ unsigned long long new_blocks[4], int *err)
+{
+ int target, i;
+ unsigned long count = 0;
+ int index = 0;
+ unsigned long 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)
+ */
+ target = blks + indirect_blks;
+
+ while (1) {
+ count = target;
+ /* allocating blocks for indirect blocks and direct blocks */
+ current_block = ext3_new_blocks(handle, inode, goal, &count, err);
+ if (*err)
+ goto failed_out;
+
+ target -= count;
+ /* allocate blocks for indirect blocks */
+ while (index < indirect_blks && count) {
+ new_blocks[index++] = current_block++;
+ count--;
+ }
+
+ if (count > 0)
+ break;
+ }
+
+ /* save the new block number for the first direct block */
+ new_blocks[index] = current_block;
+
+ /* total number of blocks allocated for direct blocks */
+ ret = count;
+ *err = 0;
+ return ret;
+failed_out:
+ for (i = 0; i <index; i++)
+ ext3_free_blocks(handle, inode, new_blocks[i], 1);
+ return ret;
+}
/**
* ext3_alloc_branch - allocate and set up a chain of blocks.
* @inode: owner
- * @num: depth of the chain (number of blocks to allocate)
+ * @indirect_blks: number of allocated indirect blocks
+ * @blks: number of allocated direct blocks
* @offsets: offsets (in the blocks) to store the pointers to next.
* @branch: place to store the chain in.
*
- * This function allocates @num blocks, zeroes out all but the last one,
+ * This function allocates blocks, zeroes out all but the last one,
* links them into chain and (if we are synchronous) writes them to disk.
* In other words, it prepares a branch that can be spliced onto the
* inode. It stores the information about that chain in the branch[], in
*/
static int ext3_alloc_branch(handle_t *handle, struct inode *inode,
- int num,
- unsigned long goal,
- int *offsets,
- Indirect *branch)
+ int indirect_blks, int *blks, unsigned long goal,
+ int *offsets, Indirect *branch)
{
int blocksize = inode->i_sb->s_blocksize;
- int n = 0, keys = 0;
+ int i, n = 0;
int err = 0;
- int i;
- int parent = ext3_alloc_block(handle, inode, goal, &err);
-
- branch[0].key = cpu_to_le32(parent);
- if (parent) {
- for (n = 1; n < num; n++) {
- struct buffer_head *bh;
- /* Allocate the next block */
- int nr = ext3_alloc_block(handle, inode, parent, &err);
- if (!nr)
- break;
- branch[n].key = cpu_to_le32(nr);
+ struct buffer_head *bh;
+ int num;
+ unsigned long long new_blocks[4];
+ unsigned long long current_block;
- /*
- * 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, parent);
- if (!bh)
- break;
- keys = n+1;
- branch[n].bh = bh;
- lock_buffer(bh);
- BUFFER_TRACE(bh, "call get_create_access");
- err = ext3_journal_get_create_access(handle, bh);
- if (err) {
- unlock_buffer(bh);
- brelse(bh);
- break;
- }
+ num = ext3_alloc_blocks(handle, inode, goal, indirect_blks,
+ *blks, new_blocks, &err);
+ if (err)
+ return err;
- memset(bh->b_data, 0, blocksize);
- branch[n].p = (__le32*) bh->b_data + offsets[n];
- *branch[n].p = branch[n].key;
- BUFFER_TRACE(bh, "marking uptodate");
- set_buffer_uptodate(bh);
+ branch[0].key = cpu_to_le32(new_blocks[0]);
+ /*
+ * metadata blocks and data blocks are allocated.
+ */
+ 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]);
+ branch[n].bh = bh;
+ lock_buffer(bh);
+ BUFFER_TRACE(bh, "call get_create_access");
+ err = ext3_journal_get_create_access(handle, bh);
+ if (err) {
unlock_buffer(bh);
+ brelse(bh);
+ goto failed;
+ }
- BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
- err = ext3_journal_dirty_metadata(handle, bh);
- if (err)
- break;
-
- parent = nr;
+ 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);
}
- }
- if (n == num)
- return 0;
+ BUFFER_TRACE(bh, "marking uptodate");
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
+ err = ext3_journal_dirty_metadata(handle, bh);
+ if (err)
+ goto failed;
+ }
+ *blks = num;
+ return err;
+failed:
/* Allocation failed, free what we already allocated */
- for (i = 1; i < keys; i++) {
+ for (i = 1; i <= n ; i++) {
BUFFER_TRACE(branch[i].bh, "call journal_forget");
ext3_journal_forget(handle, branch[i].bh);
}
- for (i = 0; i < keys; i++)
- ext3_free_blocks(handle, inode, le32_to_cpu(branch[i].key), 1);
+ for (i = 0; i <indirect_blks; i++)
+ ext3_free_blocks(handle, inode, new_blocks[i], 1);
+
+ ext3_free_blocks(handle, inode, new_blocks[i], num);
+
return err;
}
* @chain: chain of indirect blocks (with a missing link - see
* ext3_alloc_branch)
* @where: location of missing link
- * @num: number of blocks we are adding
+ * @num: number of indirect blocks we are adding
+ * @blks: number of direct blocks we are adding
*
* This function fills the missing link and does all housekeeping needed in
* inode (->i_blocks, etc.). In case of success we end up with the full
*/
static int ext3_splice_branch(handle_t *handle, struct inode *inode, long block,
- Indirect chain[4], Indirect *where, int num)
+ Indirect *where, int num, int blks)
{
int i;
int err = 0;
struct ext3_block_alloc_info *block_i = EXT3_I(inode)->i_block_alloc_info;
-
+ unsigned long current_block;
/*
* If we're splicing into a [td]indirect block (as opposed to the
* inode) then we need to get write access to the [td]indirect block
/* That's it */
*where->p = where->key;
+ /* update host bufferhead or inode to point to
+ * more just allocated direct blocks blocks */
+ if (num == 0 && blks > 1) {
+ current_block = le32_to_cpu(where->key + 1);
+ for (i = 1; i < blks; i++)
+ *(where->p + i ) = cpu_to_le32(current_block++);
+ }
/*
* update the most recently allocated logical & physical block
* allocation
*/
if (block_i) {
- block_i->last_alloc_logical_block = block;
- block_i->last_alloc_physical_block = le32_to_cpu(where[num-1].key);
+ block_i->last_alloc_logical_block = block + blks - 1;
+ block_i->last_alloc_physical_block = le32_to_cpu(where[num].key + blks - 1);
}
/* We are done with atomic stuff, now do the rest of housekeeping */
return err;
err_out:
- for (i = 1; i < num; i++) {
+ for (i = 1; i <= num; i++) {
BUFFER_TRACE(where[i].bh, "call journal_forget");
ext3_journal_forget(handle, where[i].bh);
+ ext3_free_blocks(handle, inode, le32_to_cpu(where[i-1].key), 1);
}
+ ext3_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks);
+
return err;
}
* akpm: `handle' can be NULL if create == 0.
*
* The BKL may not be held on entry here. Be sure to take it early.
+ * return > 0, # of blocks mapped or allocated.
+ * return = 0, if plain lookup failed.
+ * return < 0, error case.
*/
-static int
-ext3_get_block_handle(handle_t *handle, struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create, int extend_disksize)
+int
+ext3_get_blocks_handle(handle_t *handle, struct inode *inode, sector_t iblock,
+ unsigned long maxblocks, struct buffer_head *bh_result,
+ int create, int extend_disksize)
{
int err = -EIO;
int offsets[4];
Indirect chain[4];
Indirect *partial;
unsigned long goal;
- int left;
- int boundary = 0;
- const int depth = ext3_block_to_path(inode, iblock, offsets, &boundary);
+ int indirect_blks;
+ int blocks_to_boundary = 0;
+ int depth;
struct ext3_inode_info *ei = EXT3_I(inode);
+ int count = 0;
+ unsigned long first_block = 0;
+
J_ASSERT(handle != NULL || create == 0);
+ depth = ext3_block_to_path(inode, iblock, offsets, &blocks_to_boundary);
if (depth == 0)
goto out;
/* Simplest case - block found, no allocation needed */
if (!partial) {
+ first_block = chain[depth - 1].key;
clear_buffer_new(bh_result);
- goto got_it;
+ count++;
+ /*map more blocks*/
+ while (count < maxblocks && count <= blocks_to_boundary) {
+ if (!verify_chain(chain, partial)) {
+ /*
+ * Indirect block might be removed by
+ * truncate while we were reading it.
+ * Handling of that case: forget what we've
+ * got now. Flag the err as EAGAIN, so it
+ * will reread.
+ */
+ err = -EAGAIN;
+ count = 0;
+ break;
+ }
+ if (le32_to_cpu(*(chain[depth-1].p+count) ==
+ (first_block + count)))
+ count++;
+ else
+ break;
+ }
+ if (err != -EAGAIN)
+ goto got_it;
}
/* Next simple case - plain lookup or failed read of indirect block */
if (!create || err == -EIO)
goto cleanup;
- down(&ei->truncate_sem);
+ mutex_lock(&ei->truncate_mutex);
/*
* If the indirect block is missing while we are reading
}
partial = ext3_get_branch(inode, depth, offsets, chain, &err);
if (!partial) {
- up(&ei->truncate_sem);
+ count++;
+ mutex_unlock(&ei->truncate_mutex);
if (err)
goto cleanup;
clear_buffer_new(bh_result);
goal = ext3_find_goal(inode, iblock, chain, partial);
- left = (chain + depth) - partial;
+ /* the number of blocks need to allocate for [d,t]indirect blocks */
+ indirect_blks = (chain + depth) - partial - 1;
+ /*
+ * Next look up the indirect map to count the totoal number of
+ * direct blocks to allocate for this branch.
+ */
+ count = ext3_blks_to_allocate(partial, indirect_blks,
+ maxblocks, blocks_to_boundary);
/*
* Block out ext3_truncate while we alter the tree
*/
- err = ext3_alloc_branch(handle, inode, left, goal,
+ err = ext3_alloc_branch(handle, inode, indirect_blks, &count, goal,
offsets + (partial - chain), partial);
/*
* may need to return -EAGAIN upwards in the worst case. --sct
*/
if (!err)
- err = ext3_splice_branch(handle, inode, iblock, chain,
- partial, left);
+ err = ext3_splice_branch(handle, inode, iblock,
+ partial, indirect_blks, count);
/*
- * i_disksize growing is protected by truncate_sem. Don't forget to
+ * i_disksize growing is protected by truncate_mutex. Don't forget to
* protect it if you're about to implement concurrent
* ext3_get_block() -bzzz
*/
if (!err && extend_disksize && inode->i_size > ei->i_disksize)
ei->i_disksize = inode->i_size;
- up(&ei->truncate_sem);
+ mutex_unlock(&ei->truncate_mutex);
if (err)
goto cleanup;
set_buffer_new(bh_result);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
- if (boundary)
+ if (blocks_to_boundary == 0)
set_buffer_boundary(bh_result);
+ err = count;
/* Clean up and exit */
partial = chain + depth - 1; /* the whole chain */
cleanup:
return err;
}
-static int ext3_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- handle_t *handle = NULL;
- int ret;
-
- if (create) {
- handle = ext3_journal_current_handle();
- J_ASSERT(handle != 0);
- }
- ret = ext3_get_block_handle(handle, inode, iblock,
- bh_result, create, 1);
- return ret;
-}
-
#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32)
static int
ext3_direct_io_get_blocks(struct inode *inode, sector_t iblock,
- unsigned long max_blocks, struct buffer_head *bh_result,
- int create)
+ struct buffer_head *bh_result, int create)
{
handle_t *handle = journal_current_handle();
int ret = 0;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
- if (!handle)
+ if (!create)
goto get_block; /* A read */
+ if (max_blocks == 1)
+ goto get_block; /* A single block get */
+
if (handle->h_transaction->t_state == T_LOCKED) {
/*
* Huge direct-io writes can hold off commits for long
}
get_block:
- if (ret == 0)
- ret = ext3_get_block_handle(handle, inode, iblock,
- bh_result, create, 0);
- bh_result->b_size = (1 << inode->i_blkbits);
+ if (ret == 0) {
+ ret = ext3_get_blocks_handle(handle, inode, iblock,
+ max_blocks, bh_result, create, 0);
+ if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
+ }
+ }
return ret;
}
+static int ext3_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ return ext3_direct_io_get_blocks(inode, iblock, bh_result, create);
+}
+
/*
* `handle' can be NULL if create is zero
*/
dummy.b_state = 0;
dummy.b_blocknr = -1000;
buffer_trace_init(&dummy.b_history);
- *errp = ext3_get_block_handle(handle, inode, block, &dummy, create, 1);
- if (!*errp && buffer_mapped(&dummy)) {
+ err = ext3_get_blocks_handle(handle, inode, block, 1,
+ &dummy, create, 1);
+ if (err == 1) {
+ err = 0;
+ } else if (err >= 0) {
+ WARN_ON(1);
+ err = -EIO;
+ }
+ *errp = err;
+ if (!err && buffer_mapped(&dummy)) {
struct buffer_head *bh;
bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
if (!bh) {
* ext3_file_write() -> generic_file_write() -> __alloc_pages() -> ...
*
* Same applies to ext3_get_block(). We will deadlock on various things like
- * lock_journal and i_truncate_sem.
+ * lock_journal and i_truncate_mutex.
*
* Setting PF_MEMALLOC here doesn't work - too many internal memory
* allocations fail.
return mpage_readpages(mapping, pages, nr_pages, ext3_get_block);
}
-static int ext3_invalidatepage(struct page *page, unsigned long offset)
+static void ext3_invalidatepage(struct page *page, unsigned long offset)
{
journal_t *journal = EXT3_JOURNAL(page->mapping->host);
if (offset == 0)
ClearPageChecked(page);
- return journal_invalidatepage(journal, page, offset);
+ journal_invalidatepage(journal, page, offset);
}
static int ext3_releasepage(struct page *page, gfp_t wait)
* From here we block out all ext3_get_block() callers who want to
* modify the block allocation tree.
*/
- down(&ei->truncate_sem);
+ mutex_lock(&ei->truncate_mutex);
if (n == 1) { /* direct blocks */
ext3_free_data(handle, inode, NULL, i_data+offsets[0],
ext3_discard_reservation(inode);
- up(&ei->truncate_sem);
+ mutex_unlock(&ei->truncate_mutex);
inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
ext3_mark_inode_dirty(handle, inode);