bh->b_end_io = handler;
bh->b_private = private;
}
+EXPORT_SYMBOL(init_buffer);
static int sync_buffer(void *word)
{
smp_mb__after_clear_bit();
wake_up_bit(&bh->b_state, BH_Lock);
}
+EXPORT_SYMBOL(unlock_buffer);
/*
* Block until a buffer comes unlocked. This doesn't stop it
{
wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE);
}
+EXPORT_SYMBOL(__wait_on_buffer);
static void
__clear_page_buffers(struct page *page)
__end_buffer_read_notouch(bh, uptodate);
put_bh(bh);
}
+EXPORT_SYMBOL(end_buffer_read_sync);
void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
{
unlock_buffer(bh);
put_bh(bh);
}
+EXPORT_SYMBOL(end_buffer_write_sync);
/*
* Various filesystems appear to want __find_get_block to be non-blocking.
head = page_buffers(page);
bh = head;
do {
- if (bh->b_blocknr == block) {
+ if (!buffer_mapped(bh))
+ all_mapped = 0;
+ else if (bh->b_blocknr == block) {
ret = bh;
get_bh(bh);
goto out_unlock;
}
- if (!buffer_mapped(bh))
- all_mapped = 0;
bh = bh->b_this_page;
} while (bh != head);
invalidate_bh_lrus();
invalidate_mapping_pages(mapping, 0, -1);
}
+EXPORT_SYMBOL(invalidate_bdev);
/*
- * Kick pdflush then try to free up some ZONE_NORMAL memory.
+ * Kick the writeback threads then try to free up some ZONE_NORMAL memory.
*/
static void free_more_memory(void)
{
struct zone *zone;
int nid;
- wakeup_pdflush(1024);
+ wakeup_flusher_threads(1024);
yield();
for_each_online_node(nid) {
&zone);
if (zone)
try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
- GFP_NOFS);
+ GFP_NOFS, NULL);
}
}
* Completion handler for block_write_full_page() - pages which are unlocked
* during I/O, and which have PageWriteback cleared upon I/O completion.
*/
-static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
+void end_buffer_async_write(struct buffer_head *bh, int uptodate)
{
char b[BDEVNAME_SIZE];
unsigned long flags;
local_irq_restore(flags);
return;
}
+EXPORT_SYMBOL(end_buffer_async_write);
/*
* If a page's buffers are under async readin (end_buffer_async_read
set_buffer_async_read(bh);
}
-void mark_buffer_async_write(struct buffer_head *bh)
+static void mark_buffer_async_write_endio(struct buffer_head *bh,
+ bh_end_io_t *handler)
{
- bh->b_end_io = end_buffer_async_write;
+ bh->b_end_io = handler;
set_buffer_async_write(bh);
}
+
+void mark_buffer_async_write(struct buffer_head *bh)
+{
+ mark_buffer_async_write_endio(bh, end_buffer_async_write);
+}
EXPORT_SYMBOL(mark_buffer_async_write);
return err;
}
+static void do_thaw_all(struct work_struct *work)
+{
+ struct super_block *sb;
+ char b[BDEVNAME_SIZE];
+
+ spin_lock(&sb_lock);
+restart:
+ list_for_each_entry(sb, &super_blocks, s_list) {
+ sb->s_count++;
+ spin_unlock(&sb_lock);
+ down_read(&sb->s_umount);
+ while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+ printk(KERN_WARNING "Emergency Thaw on %s\n",
+ bdevname(sb->s_bdev, b));
+ up_read(&sb->s_umount);
+ spin_lock(&sb_lock);
+ if (__put_super_and_need_restart(sb))
+ goto restart;
+ }
+ spin_unlock(&sb_lock);
+ kfree(work);
+ printk(KERN_WARNING "Emergency Thaw complete\n");
+}
+
+/**
+ * emergency_thaw_all -- forcibly thaw every frozen filesystem
+ *
+ * Used for emergency unfreeze of all filesystems via SysRq
+ */
+void emergency_thaw_all(void)
+{
+ struct work_struct *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work) {
+ INIT_WORK(work, do_thaw_all);
+ schedule_work(work);
+ }
+}
+
/**
* sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
* @mapping: the mapping which wants those buffers written
spin_lock_irq(&mapping->tree_lock);
if (page->mapping) { /* Race with truncate? */
WARN_ON_ONCE(warn && !PageUptodate(page));
-
- if (mapping_cap_account_dirty(mapping)) {
- __inc_zone_page_state(page, NR_FILE_DIRTY);
- __inc_bdi_stat(mapping->backing_dev_info,
- BDI_RECLAIMABLE);
- task_dirty_inc(current);
- task_io_account_write(PAGE_CACHE_SIZE);
- }
+ account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
{
struct buffer_head *bh;
struct list_head tmp;
- struct address_space *mapping;
+ struct address_space *mapping, *prev_mapping = NULL;
int err = 0, err2;
INIT_LIST_HEAD(&tmp);
* contents - it is a noop if I/O is still in
* flight on potentially older contents.
*/
- ll_rw_block(SWRITE_SYNC, 1, &bh);
+ ll_rw_block(SWRITE_SYNC_PLUG, 1, &bh);
+
+ /*
+ * Kick off IO for the previous mapping. Note
+ * that we will not run the very last mapping,
+ * wait_on_buffer() will do that for us
+ * through sync_buffer().
+ */
+ if (prev_mapping && prev_mapping != mapping)
+ blk_run_address_space(prev_mapping);
+ prev_mapping = mapping;
+
brelse(bh);
spin_lock(lock);
}
__getblk_slow(struct block_device *bdev, sector_t block, int size)
{
/* Size must be multiple of hard sectorsize */
- if (unlikely(size & (bdev_hardsect_size(bdev)-1) ||
+ if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
(size < 512 || size > PAGE_SIZE))) {
printk(KERN_ERR "getblk(): invalid block size %d requested\n",
size);
- printk(KERN_ERR "hardsect size: %d\n",
- bdev_hardsect_size(bdev));
+ printk(KERN_ERR "logical block size: %d\n",
+ bdev_logical_block_size(bdev));
dump_stack();
return NULL;
if (!test_set_buffer_dirty(bh)) {
struct page *page = bh->b_page;
- if (!TestSetPageDirty(page))
- __set_page_dirty(page, page_mapping(page), 0);
+ if (!TestSetPageDirty(page)) {
+ struct address_space *mapping = page_mapping(page);
+ if (mapping)
+ __set_page_dirty(page, mapping, 0);
+ }
}
}
+EXPORT_SYMBOL(mark_buffer_dirty);
/*
* Decrement a buffer_head's reference count. If all buffers against a page
}
WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
}
+EXPORT_SYMBOL(__brelse);
/*
* bforget() is like brelse(), except it discards any
}
__brelse(bh);
}
+EXPORT_SYMBOL(__bforget);
static struct buffer_head *__bread_slow(struct buffer_head *bh)
{
* locked buffer. This only can happen if someone has written the buffer
* directly, with submit_bh(). At the address_space level PageWriteback
* prevents this contention from occurring.
+ *
+ * If block_write_full_page() is called with wbc->sync_mode ==
+ * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this
+ * causes the writes to be flagged as synchronous writes, but the
+ * block device queue will NOT be unplugged, since usually many pages
+ * will be pushed to the out before the higher-level caller actually
+ * waits for the writes to be completed. The various wait functions,
+ * such as wait_on_writeback_range() will ultimately call sync_page()
+ * which will ultimately call blk_run_backing_dev(), which will end up
+ * unplugging the device queue.
*/
static int __block_write_full_page(struct inode *inode, struct page *page,
- get_block_t *get_block, struct writeback_control *wbc)
+ get_block_t *get_block, struct writeback_control *wbc,
+ bh_end_io_t *handler)
{
int err;
sector_t block;
struct buffer_head *bh, *head;
const unsigned blocksize = 1 << inode->i_blkbits;
int nr_underway = 0;
+ int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
+ WRITE_SYNC_PLUG : WRITE);
BUG_ON(!PageLocked(page));
/*
* If it's a fully non-blocking write attempt and we cannot
* lock the buffer then redirty the page. Note that this can
- * potentially cause a busy-wait loop from pdflush and kswapd
- * activity, but those code paths have their own higher-level
- * throttling.
+ * potentially cause a busy-wait loop from writeback threads
+ * and kswapd activity, but those code paths have their own
+ * higher-level throttling.
*/
if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
lock_buffer(bh);
continue;
}
if (test_clear_buffer_dirty(bh)) {
- mark_buffer_async_write(bh);
+ mark_buffer_async_write_endio(bh, handler);
} else {
unlock_buffer(bh);
}
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh(WRITE, bh);
+ submit_bh(write_op, bh);
nr_underway++;
}
bh = next;
if (buffer_mapped(bh) && buffer_dirty(bh) &&
!buffer_delay(bh)) {
lock_buffer(bh);
- mark_buffer_async_write(bh);
+ mark_buffer_async_write_endio(bh, handler);
} else {
/*
* The buffer may have been set dirty during
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh(WRITE, bh);
+ submit_bh(write_op, bh);
nr_underway++;
}
bh = next;
}
return 0;
}
+EXPORT_SYMBOL(block_read_full_page);
/* utility function for filesystems that need to do work on expanding
* truncates. Uses filesystem pagecache writes to allow the filesystem to
struct address_space *mapping = inode->i_mapping;
struct page *page;
void *fsdata;
- unsigned long limit;
int err;
- err = -EFBIG;
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && size > (loff_t)limit) {
- send_sig(SIGXFSZ, current, 0);
- goto out;
- }
- if (size > inode->i_sb->s_maxbytes)
+ err = inode_newsize_ok(inode, size);
+ if (err)
goto out;
err = pagecache_write_begin(NULL, mapping, size, 0,
out:
return err;
}
+EXPORT_SYMBOL(generic_cont_expand_simple);
static int cont_expand_zero(struct file *file, struct address_space *mapping,
loff_t pos, loff_t *bytes)
out:
return err;
}
+EXPORT_SYMBOL(cont_write_begin);
int block_prepare_write(struct page *page, unsigned from, unsigned to,
get_block_t *get_block)
ClearPageUptodate(page);
return err;
}
+EXPORT_SYMBOL(block_prepare_write);
int block_commit_write(struct page *page, unsigned from, unsigned to)
{
__block_commit_write(inode,page,from,to);
return 0;
}
+EXPORT_SYMBOL(block_commit_write);
/*
* block_page_mkwrite() is not allowed to change the file size as it gets
* unlock the page.
*/
int
-block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
+block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
+ struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
unsigned long end;
loff_t size;
- int ret = -EINVAL;
+ int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
lock_page(page);
size = i_size_read(inode);
if ((page->mapping != inode->i_mapping) ||
(page_offset(page) > size)) {
/* page got truncated out from underneath us */
- goto out_unlock;
+ unlock_page(page);
+ goto out;
}
/* page is wholly or partially inside EOF */
if (!ret)
ret = block_commit_write(page, 0, end);
-out_unlock:
- unlock_page(page);
+ if (unlikely(ret)) {
+ unlock_page(page);
+ if (ret == -ENOMEM)
+ ret = VM_FAULT_OOM;
+ else /* -ENOSPC, -EIO, etc */
+ ret = VM_FAULT_SIGBUS;
+ } else
+ ret = VM_FAULT_LOCKED;
+
+out:
return ret;
}
+EXPORT_SYMBOL(block_page_mkwrite);
/*
* nobh_write_begin()'s prereads are special: the buffer_heads are freed
out:
ret = mpage_writepage(page, get_block, wbc);
if (ret == -EAGAIN)
- ret = __block_write_full_page(inode, page, get_block, wbc);
+ ret = __block_write_full_page(inode, page, get_block, wbc,
+ end_buffer_async_write);
return ret;
}
EXPORT_SYMBOL(nobh_writepage);
pos += blocksize;
}
+ map_bh.b_size = blocksize;
+ map_bh.b_state = 0;
err = get_block(inode, iblock, &map_bh, 0);
if (err)
goto unlock;
out:
return err;
}
+EXPORT_SYMBOL(block_truncate_page);
/*
* The generic ->writepage function for buffer-backed address_spaces
+ * this form passes in the end_io handler used to finish the IO.
*/
-int block_write_full_page(struct page *page, get_block_t *get_block,
- struct writeback_control *wbc)
+int block_write_full_page_endio(struct page *page, get_block_t *get_block,
+ struct writeback_control *wbc, bh_end_io_t *handler)
{
struct inode * const inode = page->mapping->host;
loff_t i_size = i_size_read(inode);
/* Is the page fully inside i_size? */
if (page->index < end_index)
- return __block_write_full_page(inode, page, get_block, wbc);
+ return __block_write_full_page(inode, page, get_block, wbc,
+ handler);
/* Is the page fully outside i_size? (truncate in progress) */
offset = i_size & (PAGE_CACHE_SIZE-1);
/*
* The page straddles i_size. It must be zeroed out on each and every
- * writepage invokation because it may be mmapped. "A file is mapped
+ * writepage invocation because it may be mmapped. "A file is mapped
* in multiples of the page size. For a file that is not a multiple of
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
- return __block_write_full_page(inode, page, get_block, wbc);
+ return __block_write_full_page(inode, page, get_block, wbc, handler);
+}
+EXPORT_SYMBOL(block_write_full_page_endio);
+
+/*
+ * The generic ->writepage function for buffer-backed address_spaces
+ */
+int block_write_full_page(struct page *page, get_block_t *get_block,
+ struct writeback_control *wbc)
+{
+ return block_write_full_page_endio(page, get_block, wbc,
+ end_buffer_async_write);
}
+EXPORT_SYMBOL(block_write_full_page);
sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
get_block_t *get_block)
get_block(inode, block, &tmp, 0);
return tmp.b_blocknr;
}
+EXPORT_SYMBOL(generic_block_bmap);
static void end_bio_bh_io_sync(struct bio *bio, int err)
{
BUG_ON(!buffer_locked(bh));
BUG_ON(!buffer_mapped(bh));
BUG_ON(!bh->b_end_io);
+ BUG_ON(buffer_delay(bh));
+ BUG_ON(buffer_unwritten(bh));
/*
* Mask in barrier bit for a write (could be either a WRITE or a
bio_put(bio);
return ret;
}
+EXPORT_SYMBOL(submit_bh);
/**
* ll_rw_block: low-level access to block devices (DEPRECATED)
for (i = 0; i < nr; i++) {
struct buffer_head *bh = bhs[i];
- if (rw == SWRITE || rw == SWRITE_SYNC)
+ if (rw == SWRITE || rw == SWRITE_SYNC || rw == SWRITE_SYNC_PLUG)
lock_buffer(bh);
else if (!trylock_buffer(bh))
continue;
- if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
+ if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC ||
+ rw == SWRITE_SYNC_PLUG) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
unlock_buffer(bh);
}
}
+EXPORT_SYMBOL(ll_rw_block);
/*
* For a data-integrity writeout, we need to wait upon any in-progress I/O
if (test_clear_buffer_dirty(bh)) {
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(WRITE, bh);
+ ret = submit_bh(WRITE_SYNC, bh);
wait_on_buffer(bh);
if (buffer_eopnotsupp(bh)) {
clear_buffer_eopnotsupp(bh);
}
return ret;
}
+EXPORT_SYMBOL(sync_dirty_buffer);
/*
* try_to_free_buffers() checks if all the buffers on this particular page
if (mapping)
blk_run_backing_dev(mapping->backing_dev_info, page);
}
+EXPORT_SYMBOL(block_sync_page);
/*
* There are no bdflush tunables left. But distributions are
* still running obsolete flush daemons, so we terminate them here.
*
* Use of bdflush() is deprecated and will be removed in a future kernel.
- * The `pdflush' kernel threads fully replace bdflush daemons and this call.
+ * The `flush-X' kernel threads fully replace bdflush daemons and this call.
*/
SYSCALL_DEFINE2(bdflush, int, func, long, data)
{
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
{
- struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags);
+ struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
if (ret) {
INIT_LIST_HEAD(&ret->b_assoc_buffers);
get_cpu_var(bh_accounting).nr++;
}
EXPORT_SYMBOL(bh_submit_read);
-static void
-init_buffer_head(void *data)
-{
- struct buffer_head *bh = data;
-
- memset(bh, 0, sizeof(*bh));
- INIT_LIST_HEAD(&bh->b_assoc_buffers);
-}
-
void __init buffer_init(void)
{
int nrpages;
sizeof(struct buffer_head), 0,
(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
SLAB_MEM_SPREAD),
- init_buffer_head);
+ NULL);
/*
* Limit the bh occupancy to 10% of ZONE_NORMAL
max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head));
hotcpu_notifier(buffer_cpu_notify, 0);
}
-
-EXPORT_SYMBOL(__bforget);
-EXPORT_SYMBOL(__brelse);
-EXPORT_SYMBOL(__wait_on_buffer);
-EXPORT_SYMBOL(block_commit_write);
-EXPORT_SYMBOL(block_prepare_write);
-EXPORT_SYMBOL(block_page_mkwrite);
-EXPORT_SYMBOL(block_read_full_page);
-EXPORT_SYMBOL(block_sync_page);
-EXPORT_SYMBOL(block_truncate_page);
-EXPORT_SYMBOL(block_write_full_page);
-EXPORT_SYMBOL(cont_write_begin);
-EXPORT_SYMBOL(end_buffer_read_sync);
-EXPORT_SYMBOL(end_buffer_write_sync);
-EXPORT_SYMBOL(file_fsync);
-EXPORT_SYMBOL(fsync_bdev);
-EXPORT_SYMBOL(generic_block_bmap);
-EXPORT_SYMBOL(generic_cont_expand_simple);
-EXPORT_SYMBOL(init_buffer);
-EXPORT_SYMBOL(invalidate_bdev);
-EXPORT_SYMBOL(ll_rw_block);
-EXPORT_SYMBOL(mark_buffer_dirty);
-EXPORT_SYMBOL(submit_bh);
-EXPORT_SYMBOL(sync_dirty_buffer);
-EXPORT_SYMBOL(unlock_buffer);
Code Review / linux-2.6.git / blobdiff