* Copyright (C) 1991, 1992 Linus Torvalds
*
* Goal-directed block allocation by Stephen Tweedie
- * (sct@redhat.com), 1993, 1998
+ * (sct@redhat.com), 1993, 1998
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
* 64-bit file support on 64-bit platforms by Jakub Jelinek
- * (jj@sunsite.ms.mff.cuni.cz)
+ * (jj@sunsite.ms.mff.cuni.cz)
*
* Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000
*/
#include <linux/time.h>
#include <linux/ext3_jbd.h>
#include <linux/jbd.h>
-#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/uio.h>
+#include <linux/bio.h>
#include "xattr.h"
#include "acl.h"
/*
* Test whether an inode is a fast symlink.
*/
-static inline int ext3_inode_is_fast_symlink(struct inode *inode)
+static int ext3_inode_is_fast_symlink(struct inode *inode)
{
int ea_blocks = EXT3_I(inode)->i_file_acl ?
(inode->i_sb->s_blocksize >> 9) : 0;
- return (S_ISLNK(inode->i_mode) &&
- inode->i_blocks - ea_blocks == 0);
+ return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
-/* The ext3 forget function must perform a revoke if we are freeing data
+/*
+ * The ext3 forget function must perform a revoke if we are freeing data
* which has been journaled. Metadata (eg. indirect blocks) must be
- * revoked in all cases.
+ * revoked in all cases.
*
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
*/
-
-int ext3_forget(handle_t *handle, int is_metadata,
- struct inode *inode, struct buffer_head *bh,
- int blocknr)
+int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode,
+ struct buffer_head *bh, ext3_fsblk_t blocknr)
{
int err;
}
/*
- * Work out how many blocks we need to progress with the next chunk of a
+ * Work out how many blocks we need to proceed with the next chunk of a
* truncate transaction.
*/
-
-static unsigned long blocks_for_truncate(struct inode *inode)
+static unsigned long blocks_for_truncate(struct inode *inode)
{
unsigned long needed;
/* But we need to bound the transaction so we don't overflow the
* journal. */
- if (needed > EXT3_MAX_TRANS_DATA)
+ if (needed > EXT3_MAX_TRANS_DATA)
needed = EXT3_MAX_TRANS_DATA;
return EXT3_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
}
-/*
+/*
* Truncate transactions can be complex and absolutely huge. So we need to
* 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
* extend fails, we need to propagate the failure up and restart the
- * transaction in the top-level truncate loop. --sct
+ * transaction in the top-level truncate loop. --sct
*/
-
-static handle_t *start_transaction(struct inode *inode)
+static handle_t *start_transaction(struct inode *inode)
{
handle_t *result;
handle = start_transaction(inode);
if (IS_ERR(handle)) {
- /* If we're going to skip the normal cleanup, we still
- * need to make sure that the in-core orphan linked list
- * is properly cleaned up. */
+ /*
+ * If we're going to skip the normal cleanup, we still need to
+ * make sure that the in-core orphan linked list is properly
+ * cleaned up.
+ */
ext3_orphan_del(NULL, inode);
goto no_delete;
}
ext3_orphan_del(handle, inode);
EXT3_I(inode)->i_dtime = get_seconds();
- /*
+ /*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
- * fails.
+ * fails.
*/
if (ext3_mark_inode_dirty(handle, inode))
/* If that failed, just do the required in-core inode clear. */
p->bh = bh;
}
-static inline int verify_chain(Indirect *from, Indirect *to)
+static int verify_chain(Indirect *from, Indirect *to)
{
while (from <= to && from->key == *from->p)
from++;
offsets[n++] = i_block & (ptrs - 1);
final = ptrs;
} else {
- ext3_warning (inode->i_sb, "ext3_block_to_path", "block > big");
+ ext3_warning(inode->i_sb, "ext3_block_to_path", "block > big");
}
if (boundary)
*boundary = final - 1 - (i_block & (ptrs - 1));
* + if there is a block to the left of our position - allocate near it.
* + if pointer will live in indirect block - allocate near that block.
* + if pointer will live in inode - allocate in the same
- * cylinder group.
+ * cylinder group.
*
* In the latter case we colour the starting block by the callers PID to
* prevent it from clashing with concurrent allocations for a different inode
*
* Caller must make sure that @ind is valid and will stay that way.
*/
-
-static unsigned long ext3_find_near(struct inode *inode, Indirect *ind)
+static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind)
{
struct ext3_inode_info *ei = EXT3_I(inode);
__le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
__le32 *p;
- unsigned long bg_start;
- unsigned long colour;
+ ext3_fsblk_t bg_start;
+ ext3_grpblk_t colour;
/* Try to find previous block */
- for (p = ind->p - 1; p >= start; p--)
+ for (p = ind->p - 1; p >= start; p--) {
if (*p)
return le32_to_cpu(*p);
+ }
/* No such thing, so let's try location of indirect block */
if (ind->bh)
return ind->bh->b_blocknr;
/*
- * It is going to be refered from inode itself? OK, just put it into
- * the same cylinder group then.
+ * It is going to be referred to from the inode itself? OK, just put it
+ * into the same cylinder group then.
*/
- bg_start = (ei->i_block_group * EXT3_BLOCKS_PER_GROUP(inode->i_sb)) +
- le32_to_cpu(EXT3_SB(inode->i_sb)->s_es->s_first_data_block);
+ bg_start = ext3_group_first_block_no(inode->i_sb, ei->i_block_group);
colour = (current->pid % 16) *
(EXT3_BLOCKS_PER_GROUP(inode->i_sb) / 16);
return bg_start + colour;
* stores it in *@goal and returns zero.
*/
-static unsigned long ext3_find_goal(struct inode *inode, long block,
+static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block,
Indirect chain[4], Indirect *partial)
{
- struct ext3_block_alloc_info *block_i = EXT3_I(inode)->i_block_alloc_info;
+ struct ext3_block_alloc_info *block_i;
+
+ block_i = EXT3_I(inode)->i_block_alloc_info;
/*
* try the heuristic for sequential allocation,
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
+ * @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,
+static int ext3_blks_to_allocate(Indirect *branch, int k, unsigned long blks,
int blocks_to_boundary)
{
unsigned long count = 0;
* then it's clear blocks on that path have not allocated
*/
if (k > 0) {
- /* right now don't hanel cross boundary allocation */
+ /* right now we don't handle cross boundary allocation */
if (blks < blocks_to_boundary + 1)
count += blks;
else
* 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)
+ ext3_fsblk_t goal, int indirect_blks, int blks,
+ ext3_fsblk_t new_blocks[4], int *err)
{
int target, i;
unsigned long count = 0;
int index = 0;
- unsigned long current_block = 0;
+ ext3_fsblk_t current_block = 0;
int ret = 0;
/*
while (1) {
count = target;
/* allocating blocks for indirect blocks and direct blocks */
- current_block = ext3_new_blocks(handle, inode, goal, &count, err);
+ current_block = ext3_new_blocks(handle,inode,goal,&count,err);
if (*err)
goto failed_out;
* ext3_alloc_block() (normally -ENOSPC). Otherwise we set the chain
* as described above and return 0.
*/
-
static int ext3_alloc_branch(handle_t *handle, struct inode *inode,
- int indirect_blks, int *blks, unsigned long goal,
+ int indirect_blks, int *blks, ext3_fsblk_t goal,
int *offsets, Indirect *branch)
{
int blocksize = inode->i_sb->s_blocksize;
int err = 0;
struct buffer_head *bh;
int num;
- unsigned long long new_blocks[4];
- unsigned long long current_block;
+ ext3_fsblk_t new_blocks[4];
+ ext3_fsblk_t current_block;
num = ext3_alloc_blocks(handle, inode, goal, indirect_blks,
*blks, new_blocks, &err);
}
/**
- * ext3_splice_branch - splice the allocated branch onto inode.
- * @inode: owner
- * @block: (logical) number of block we are adding
- * @chain: chain of indirect blocks (with a missing link - see
- * ext3_alloc_branch)
- * @where: location of missing link
- * @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
- * chain to new block and return 0.
+ * ext3_splice_branch - splice the allocated branch onto inode.
+ * @inode: owner
+ * @block: (logical) number of block we are adding
+ * @chain: chain of indirect blocks (with a missing link - see
+ * ext3_alloc_branch)
+ * @where: location of missing link
+ * @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
+ * chain to new block and return 0.
*/
-
-static int ext3_splice_branch(handle_t *handle, struct inode *inode, long block,
- Indirect *where, int num, int blks)
+static int ext3_splice_branch(handle_t *handle, struct inode *inode,
+ long block, 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;
+ struct ext3_block_alloc_info *block_i;
+ ext3_fsblk_t current_block;
+
+ block_i = EXT3_I(inode)->i_block_alloc_info;
/*
* 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 */
+
+ /*
+ * Update the host buffer_head or inode to point to more just allocated
+ * direct blocks blocks
+ */
if (num == 0 && blks > 1) {
- current_block = le32_to_cpu(where->key + 1);
+ current_block = le32_to_cpu(where->key) + 1;
for (i = 1; i < blks; i++)
*(where->p + i ) = cpu_to_le32(current_block++);
}
*/
if (block_i) {
block_i->last_alloc_logical_block = block + blks - 1;
- block_i->last_alloc_physical_block = le32_to_cpu(where[num].key + 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 */
/* had we spliced it onto indirect block? */
if (where->bh) {
/*
- * akpm: If we spliced it onto an indirect block, we haven't
+ * If we spliced it onto an indirect block, we haven't
* altered the inode. Note however that if it is being spliced
* onto an indirect block at the very end of the file (the
* file is growing) then we *will* alter the inode to reflect
jbd_debug(5, "splicing indirect only\n");
BUFFER_TRACE(where->bh, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, where->bh);
- if (err)
+ if (err)
goto err_out;
} else {
/*
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[i-1].key),1);
}
ext3_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks);
* allocations is needed - we simply release blocks and do not touch anything
* reachable from inode.
*
- * akpm: `handle' can be NULL if create == 0.
+ * `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.
*/
-
-int
-ext3_get_blocks_handle(handle_t *handle, struct inode *inode, sector_t iblock,
- unsigned long maxblocks, struct buffer_head *bh_result,
+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;
+ ext3_fsblk_t goal;
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;
+ ext3_fsblk_t first_block = 0;
J_ASSERT(handle != NULL || create == 0);
- depth = ext3_block_to_path(inode, iblock, offsets, &blocks_to_boundary);
+ 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;
+ 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) {
+ ext3_fsblk_t blk;
+
if (!verify_chain(chain, partial)) {
/*
* Indirect block might be removed by
count = 0;
break;
}
- if (le32_to_cpu(*(chain[depth-1].p+count) ==
- (first_block + count)))
+ blk = le32_to_cpu(*(chain[depth-1].p + count));
+
+ if (blk == first_block + count)
count++;
else
break;
set_buffer_new(bh_result);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
- if (blocks_to_boundary == 0)
+ if (count > blocks_to_boundary)
set_buffer_boundary(bh_result);
err = count;
/* Clean up and exit */
#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32)
-static int
-ext3_direct_io_get_blocks(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+static int ext3_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
{
- handle_t *handle = journal_current_handle();
+ handle_t *handle = ext3_journal_current_handle();
int ret = 0;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
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
*/
-struct buffer_head *ext3_getblk(handle_t *handle, struct inode * inode,
- long block, int create, int * errp)
+struct buffer_head *ext3_getblk(handle_t *handle, struct inode *inode,
+ long block, int create, int *errp)
{
struct buffer_head dummy;
int fatal = 0, err;
buffer_trace_init(&dummy.b_history);
err = ext3_get_blocks_handle(handle, inode, block, 1,
&dummy, create, 1);
- if (err == 1) {
+ /*
+ * ext3_get_blocks_handle() returns number of blocks
+ * mapped. 0 in case of a HOLE.
+ */
+ if (err > 0) {
+ if (err > 1)
+ WARN_ON(1);
err = 0;
- } else if (err >= 0) {
- WARN_ON(1);
- err = -EIO;
}
*errp = err;
if (!err && buffer_mapped(&dummy)) {
J_ASSERT(create != 0);
J_ASSERT(handle != 0);
- /* 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
- ext3_get_block instead, so it's not a
- problem. */
+ /*
+ * 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 ext3_get_block instead, so it's not a
+ * problem.
+ */
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
fatal = ext3_journal_get_create_access(handle, bh);
if (!fatal && !buffer_uptodate(bh)) {
- memset(bh->b_data, 0, inode->i_sb->s_blocksize);
+ memset(bh->b_data,0,inode->i_sb->s_blocksize);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
return NULL;
}
-struct buffer_head *ext3_bread(handle_t *handle, struct inode * inode,
+struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode,
int block, int create, int *err)
{
struct buffer_head * bh;
return bh;
if (buffer_uptodate(bh))
return bh;
- ll_rw_block(READ, 1, &bh);
+ ll_rw_block(READ_META, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
for ( bh = head, block_start = 0;
ret == 0 && (bh != head || !block_start);
- block_start = block_end, bh = next)
+ block_start = block_end, bh = next)
{
next = bh->b_this_page;
block_end = block_start + blocksize;
* So what we do is to rely on the fact that journal_stop/journal_start
* will _not_ run commit under these circumstances because handle->h_ref
* is elevated. We'll still have enough credits for the tiny quotafile
- * write.
+ * write.
*/
-
-static int do_journal_get_write_access(handle_t *handle,
- struct buffer_head *bh)
+static int do_journal_get_write_access(handle_t *handle,
+ struct buffer_head *bh)
{
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
ret = PTR_ERR(handle);
goto out;
}
- if (test_opt(inode->i_sb, NOBH))
+ if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
ret = nobh_prepare_write(page, from, to, ext3_get_block);
else
ret = block_prepare_write(page, from, to, ext3_get_block);
return ret;
}
-int
-ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
+int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
{
int err = journal_dirty_data(handle, bh);
if (err)
* ext3 never places buffers on inode->i_mapping->private_list. metadata
* buffers are managed internally.
*/
-
static int ext3_ordered_commit_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
if (new_i_size > EXT3_I(inode)->i_disksize)
EXT3_I(inode)->i_disksize = new_i_size;
- if (test_opt(inode->i_sb, NOBH))
+ if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
ret = nobh_commit_write(file, page, from, to);
else
ret = generic_commit_write(file, page, from, to);
if (inode->i_size > EXT3_I(inode)->i_disksize) {
EXT3_I(inode)->i_disksize = inode->i_size;
ret2 = ext3_mark_inode_dirty(handle, inode);
- if (!ret)
+ if (!ret)
ret = ret2;
}
ret2 = ext3_journal_stop(handle);
return ret;
}
-/*
+/*
* bmap() is special. It gets used by applications such as lilo and by
* the swapper to find the on-disk block of a specific piece of data.
*
* filesystem and enables swap, then they may get a nasty shock when the
* data getting swapped to that swapfile suddenly gets overwritten by
* the original zero's written out previously to the journal and
- * awaiting writeback in the kernel's buffer cache.
+ * awaiting writeback in the kernel's buffer cache.
*
* So, if we see any bmap calls here on a modified, data-journaled file,
- * take extra steps to flush any blocks which might be in the cache.
+ * take extra steps to flush any blocks which might be in the cache.
*/
static sector_t ext3_bmap(struct address_space *mapping, sector_t block)
{
int err;
if (EXT3_I(inode)->i_state & EXT3_STATE_JDATA) {
- /*
+ /*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
* only if we run lilo or swapon on a freshly made file
- * do we expect this to happen.
+ * do we expect this to happen.
*
* (bmap requires CAP_SYS_RAWIO so this does not
* represent an unprivileged user DOS attack --- we'd be
* in trouble if mortal users could trigger this path at
- * will.)
+ * will.)
*
* NB. EXT3_STATE_JDATA is not set on files other than
* regular files. If somebody wants to bmap a directory
* we don't need to open a transaction here.
*/
static int ext3_ordered_writepage(struct page *page,
- struct writeback_control *wbc)
+ struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct buffer_head *page_bufs;
*/
/*
- * And attach them to the current transaction. But only if
+ * And attach them to the current transaction. But only if
* block_write_full_page() succeeded. Otherwise they are unmapped,
* and generally junk.
*/
goto out_fail;
}
- if (test_opt(inode->i_sb, NOBH))
+ if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
ret = nobh_writepage(page, ext3_get_block, wbc);
else
ret = block_write_full_page(page, ext3_get_block, wbc);
}
}
- ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs,
- ext3_direct_io_get_blocks, NULL);
+ ext3_get_block, NULL);
/*
- * Reacquire the handle: ext3_direct_io_get_block() can restart the
- * transaction
+ * Reacquire the handle: ext3_get_block() can restart the transaction
*/
- handle = journal_current_handle();
+ handle = ext3_journal_current_handle();
out_stop:
if (handle) {
return __set_page_dirty_nobuffers(page);
}
-static struct address_space_operations ext3_ordered_aops = {
+static const struct address_space_operations ext3_ordered_aops = {
.readpage = ext3_readpage,
.readpages = ext3_readpages,
.writepage = ext3_ordered_writepage,
.migratepage = buffer_migrate_page,
};
-static struct address_space_operations ext3_writeback_aops = {
+static const struct address_space_operations ext3_writeback_aops = {
.readpage = ext3_readpage,
.readpages = ext3_readpages,
.writepage = ext3_writeback_writepage,
.migratepage = buffer_migrate_page,
};
-static struct address_space_operations ext3_journalled_aops = {
+static const struct address_space_operations ext3_journalled_aops = {
.readpage = ext3_readpage,
.readpages = ext3_readpages,
.writepage = ext3_journalled_writepage,
static int ext3_block_truncate_page(handle_t *handle, struct page *page,
struct address_space *mapping, loff_t from)
{
- unsigned long index = from >> PAGE_CACHE_SHIFT;
+ ext3_fsblk_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned blocksize, iblock, length, pos;
struct inode *inode = mapping->host;
struct buffer_head *bh;
int err = 0;
- void *kaddr;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
*/
if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
ext3_should_writeback_data(inode) && PageUptodate(page)) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, length, KM_USER0);
set_page_dirty(page);
goto unlock;
}
goto unlock;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
-
+ zero_user_page(page, offset, length, KM_USER0);
BUFFER_TRACE(bh, "zeroed end of block");
err = 0;
* c) free the subtrees growing from the inode past the @chain[0].
* (no partially truncated stuff there). */
-static Indirect *ext3_find_shared(struct inode *inode,
- int depth,
- int offsets[4],
- Indirect chain[4],
- __le32 *top)
+static Indirect *ext3_find_shared(struct inode *inode, int depth,
+ int offsets[4], Indirect chain[4], __le32 *top)
{
Indirect *partial, *p;
int k, err;
}
/* Writer: end */
- while(partial > p)
- {
+ while(partial > p) {
brelse(partial->bh);
partial--;
}
* We release `count' blocks on disk, but (last - first) may be greater
* than `count' because there can be holes in there.
*/
-static void
-ext3_clear_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh,
- unsigned long block_to_free, unsigned long count,
- __le32 *first, __le32 *last)
+static void ext3_clear_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext3_fsblk_t block_to_free,
+ unsigned long count, __le32 *first, __le32 *last)
{
__le32 *p;
if (try_to_extend_transaction(handle, inode)) {
struct buffer_head *this_bh,
__le32 *first, __le32 *last)
{
- unsigned long block_to_free = 0; /* Starting block # of a run */
- unsigned long count = 0; /* Number of blocks in the run */
+ ext3_fsblk_t block_to_free = 0; /* Starting block # of a run */
+ unsigned long count = 0; /* Number of blocks in the run */
__le32 *block_to_free_p = NULL; /* Pointer into inode/ind
corresponding to
block_to_free */
- unsigned long nr; /* Current block # */
+ ext3_fsblk_t nr; /* Current block # */
__le32 *p; /* Pointer into inode/ind
for current block */
int err;
} else if (nr == block_to_free + count) {
count++;
} else {
- ext3_clear_blocks(handle, inode, this_bh,
+ ext3_clear_blocks(handle, inode, this_bh,
block_to_free,
count, block_to_free_p, p);
block_to_free = nr;
struct buffer_head *parent_bh,
__le32 *first, __le32 *last, int depth)
{
- unsigned long nr;
+ ext3_fsblk_t nr;
__le32 *p;
if (is_handle_aborted(handle))
*/
if (!bh) {
ext3_error(inode->i_sb, "ext3_free_branches",
- "Read failure, inode=%ld, block=%ld",
+ "Read failure, inode=%lu, block="E3FSBLK,
inode->i_ino, nr);
continue;
}
*p = 0;
BUFFER_TRACE(parent_bh,
"call ext3_journal_dirty_metadata");
- ext3_journal_dirty_metadata(handle,
+ ext3_journal_dirty_metadata(handle,
parent_bh);
}
}
* that's fine - as long as they are linked from the inode, the post-crash
* ext3_truncate() run will find them and release them.
*/
-
-void ext3_truncate(struct inode * inode)
+void ext3_truncate(struct inode *inode)
{
handle_t *handle;
struct ext3_inode_info *ei = EXT3_I(inode);
do_indirects:
/* Kill the remaining (whole) subtrees */
switch (offsets[0]) {
- default:
- nr = i_data[EXT3_IND_BLOCK];
- if (nr) {
- ext3_free_branches(handle, inode, NULL,
- &nr, &nr+1, 1);
- i_data[EXT3_IND_BLOCK] = 0;
- }
- case EXT3_IND_BLOCK:
- nr = i_data[EXT3_DIND_BLOCK];
- if (nr) {
- ext3_free_branches(handle, inode, NULL,
- &nr, &nr+1, 2);
- i_data[EXT3_DIND_BLOCK] = 0;
- }
- case EXT3_DIND_BLOCK:
- nr = i_data[EXT3_TIND_BLOCK];
- if (nr) {
- ext3_free_branches(handle, inode, NULL,
- &nr, &nr+1, 3);
- i_data[EXT3_TIND_BLOCK] = 0;
- }
- case EXT3_TIND_BLOCK:
- ;
+ default:
+ nr = i_data[EXT3_IND_BLOCK];
+ if (nr) {
+ ext3_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
+ i_data[EXT3_IND_BLOCK] = 0;
+ }
+ case EXT3_IND_BLOCK:
+ nr = i_data[EXT3_DIND_BLOCK];
+ if (nr) {
+ ext3_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
+ i_data[EXT3_DIND_BLOCK] = 0;
+ }
+ case EXT3_DIND_BLOCK:
+ nr = i_data[EXT3_TIND_BLOCK];
+ if (nr) {
+ ext3_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
+ i_data[EXT3_TIND_BLOCK] = 0;
+ }
+ case EXT3_TIND_BLOCK:
+ ;
}
ext3_discard_reservation(inode);
inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
ext3_mark_inode_dirty(handle, inode);
- /* In a multi-transaction truncate, we only make the final
- * transaction synchronous */
+ /*
+ * In a multi-transaction truncate, we only make the final transaction
+ * synchronous
+ */
if (IS_SYNC(inode))
handle->h_sync = 1;
out_stop:
ext3_journal_stop(handle);
}
-static unsigned long ext3_get_inode_block(struct super_block *sb,
+static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb,
unsigned long ino, struct ext3_iloc *iloc)
{
unsigned long desc, group_desc, block_group;
- unsigned long offset, block;
+ unsigned long offset;
+ ext3_fsblk_t block;
struct buffer_head *bh;
struct ext3_group_desc * gdp;
-
- if ((ino != EXT3_ROOT_INO &&
- ino != EXT3_JOURNAL_INO &&
- ino != EXT3_RESIZE_INO &&
- ino < EXT3_FIRST_INO(sb)) ||
- ino > le32_to_cpu(
- EXT3_SB(sb)->s_es->s_inodes_count)) {
- ext3_error (sb, "ext3_get_inode_block",
- "bad inode number: %lu", ino);
+ if (!ext3_valid_inum(sb, ino)) {
+ /*
+ * This error is already checked for in namei.c unless we are
+ * looking at an NFS filehandle, in which case no error
+ * report is needed
+ */
return 0;
}
+
block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
if (block_group >= EXT3_SB(sb)->s_groups_count) {
- ext3_error (sb, "ext3_get_inode_block",
- "group >= groups count");
+ ext3_error(sb,"ext3_get_inode_block","group >= groups count");
return 0;
}
smp_rmb();
return 0;
}
- gdp = (struct ext3_group_desc *) bh->b_data;
+ gdp = (struct ext3_group_desc *)bh->b_data;
/*
* Figure out the offset within the block group inode table
*/
static int __ext3_get_inode_loc(struct inode *inode,
struct ext3_iloc *iloc, int in_mem)
{
- unsigned long block;
+ ext3_fsblk_t block;
struct buffer_head *bh;
block = ext3_get_inode_block(inode->i_sb, inode->i_ino, iloc);
if (!bh) {
ext3_error (inode->i_sb, "ext3_get_inode_loc",
"unable to read inode block - "
- "inode=%lu, block=%lu", inode->i_ino, block);
+ "inode=%lu, block="E3FSBLK,
+ inode->i_ino, block);
return -EIO;
}
if (!buffer_uptodate(bh)) {
*/
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(READ, bh);
+ submit_bh(READ_META, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
ext3_error(inode->i_sb, "ext3_get_inode_loc",
"unable to read inode block - "
- "inode=%lu, block=%lu",
+ "inode=%lu, block="E3FSBLK,
inode->i_ino, block);
brelse(bh);
return -EIO;
inode->i_flags |= S_DIRSYNC;
}
+/* Propagate flags from i_flags to EXT3_I(inode)->i_flags */
+void ext3_get_inode_flags(struct ext3_inode_info *ei)
+{
+ unsigned int flags = ei->vfs_inode.i_flags;
+
+ ei->i_flags &= ~(EXT3_SYNC_FL|EXT3_APPEND_FL|
+ EXT3_IMMUTABLE_FL|EXT3_NOATIME_FL|EXT3_DIRSYNC_FL);
+ if (flags & S_SYNC)
+ ei->i_flags |= EXT3_SYNC_FL;
+ if (flags & S_APPEND)
+ ei->i_flags |= EXT3_APPEND_FL;
+ if (flags & S_IMMUTABLE)
+ ei->i_flags |= EXT3_IMMUTABLE_FL;
+ if (flags & S_NOATIME)
+ ei->i_flags |= EXT3_NOATIME_FL;
+ if (flags & S_DIRSYNC)
+ ei->i_flags |= EXT3_DIRSYNC_FL;
+}
+
void ext3_read_inode(struct inode * inode)
{
struct ext3_iloc iloc;
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime);
- inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime);
+ inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
+ inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
+ inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0;
ei->i_state = 0;
* recovery code: that's fine, we're about to complete
* the process of deleting those. */
}
- inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size
- * (for stat), not the fs block
- * size */
inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
#ifdef EXT3_FRAGMENTS
if (raw_inode->i_block[0])
init_special_inode(inode, inode->i_mode,
old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
- else
+ else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
}
*
* The caller must have write access to iloc->bh.
*/
-static int ext3_do_update_inode(handle_t *handle,
- struct inode *inode,
+static int ext3_do_update_inode(handle_t *handle,
+ struct inode *inode,
struct ext3_iloc *iloc)
{
struct ext3_inode *raw_inode = ext3_raw_inode(iloc);
if (ei->i_state & EXT3_STATE_NEW)
memset(raw_inode, 0, EXT3_SB(inode->i_sb)->s_inode_size);
+ ext3_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if(!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
* commit will leave the blocks being flushed in an unused state on
* disk. (On recovery, the inode will get truncated and the blocks will
* be freed, so we have a strong guarantee that no future commit will
- * leave these blocks visible to the user.)
+ * leave these blocks visible to the user.)
*
* Called with inode->sem down.
*/
/*
- * akpm: how many blocks doth make a writepage()?
+ * How many blocks doth make a writepage()?
*
* With N blocks per page, it may be:
* N data blocks
return err;
}
-/*
+/*
* On success, We end up with an outstanding reference count against
- * iloc->bh. This _must_ be cleaned up later.
+ * iloc->bh. This _must_ be cleaned up later.
*/
int
-ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
+ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext3_iloc *iloc)
{
int err = 0;
}
/*
- * akpm: What we do here is to mark the in-core inode as clean
- * with respect to inode dirtiness (it may still be data-dirty).
+ * What we do here is to mark the in-core inode as clean with respect to inode
+ * dirtiness (it may still be data-dirty).
* This means that the in-core inode may be reaped by prune_icache
* without having to perform any I/O. This is a very good thing,
* because *any* task may call prune_icache - even ones which
}
/*
- * akpm: ext3_dirty_inode() is called from __mark_inode_dirty()
+ * ext3_dirty_inode() is called from __mark_inode_dirty()
*
* We're really interested in the case where a file is being extended.
* i_size has been changed by generic_commit_write() and we thus need
return;
}
-#ifdef AKPM
-/*
+#if 0
+/*
* Bind an inode's backing buffer_head into this transaction, to prevent
* it from being flushed to disk early. Unlike
* ext3_reserve_inode_write, this leaves behind no bh reference and
* returns no iloc structure, so the caller needs to repeat the iloc
* lookup to mark the inode dirty later.
*/
-static inline int
-ext3_pin_inode(handle_t *handle, struct inode *inode)
+static int ext3_pin_inode(handle_t *handle, struct inode *inode)
{
struct ext3_iloc iloc;
BUFFER_TRACE(iloc.bh, "get_write_access");
err = journal_get_write_access(handle, iloc.bh);
if (!err)
- err = ext3_journal_dirty_metadata(handle,
+ err = ext3_journal_dirty_metadata(handle,
iloc.bh);
brelse(iloc.bh);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff