#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/writeback.h>
#include <linux/hash.h>
#include <linux/suspend.h>
}
EXPORT_SYMBOL(init_buffer);
-static int sync_buffer(void *word)
+static int sleep_on_buffer(void *word)
{
- struct block_device *bd;
- struct buffer_head *bh
- = container_of(word, struct buffer_head, b_state);
-
- smp_mb();
- bd = bh->b_bdev;
- if (bd)
- blk_run_address_space(bd->bd_inode->i_mapping);
io_schedule();
return 0;
}
void __lock_buffer(struct buffer_head *bh)
{
- wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer,
+ wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_buffer);
*/
void __wait_on_buffer(struct buffer_head * bh)
{
- wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE);
+ wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__wait_on_buffer);
* elsewhere, don't buffer_error if we had some unmapped buffers
*/
if (all_mapped) {
+ char b[BDEVNAME_SIZE];
+
printk("__find_get_block_slow() failed. "
"block=%llu, b_blocknr=%llu\n",
(unsigned long long)block,
(unsigned long long)bh->b_blocknr);
printk("b_state=0x%08lx, b_size=%zu\n",
bh->b_state, bh->b_size);
- printk("device blocksize: %d\n", 1 << bd_inode->i_blkbits);
+ printk("device %s blocksize: %d\n", bdevname(bdev, b),
+ 1 << bd_inode->i_blkbits);
}
out_unlock:
spin_unlock(&bd_mapping->private_lock);
return ret;
}
-/* If invalidate_buffers() will trash dirty buffers, it means some kind
- of fs corruption is going on. Trashing dirty data always imply losing
- information that was supposed to be just stored on the physical layer
- by the user.
-
- Thus invalidate_buffers in general usage is not allwowed to trash
- dirty buffers. For example ioctl(FLSBLKBUF) expects dirty data to
- be preserved. These buffers are simply skipped.
-
- We also skip buffers which are still in use. For example this can
- happen if a userspace program is reading the block device.
-
- NOTE: In the case where the user removed a removable-media-disk even if
- there's still dirty data not synced on disk (due a bug in the device driver
- or due an error of the user), by not destroying the dirty buffers we could
- generate corruption also on the next media inserted, thus a parameter is
- necessary to handle this case in the most safe way possible (trying
- to not corrupt also the new disk inserted with the data belonging to
- the old now corrupted disk). Also for the ramdisk the natural thing
- to do in order to release the ramdisk memory is to destroy dirty buffers.
-
- These are two special cases. Normal usage imply the device driver
- to issue a sync on the device (without waiting I/O completion) and
- then an invalidate_buffers call that doesn't trash dirty buffers.
-
- For handling cache coherency with the blkdev pagecache the 'update' case
- is been introduced. It is needed to re-read from disk any pinned
- buffer. NOTE: re-reading from disk is destructive so we can do it only
- when we assume nobody is changing the buffercache under our I/O and when
- we think the disk contains more recent information than the buffercache.
- The update == 1 pass marks the buffers we need to update, the update == 2
- pass does the actual I/O. */
-void invalidate_bdev(struct block_device *bdev)
-{
- struct address_space *mapping = bdev->bd_inode->i_mapping;
-
- if (mapping->nrpages == 0)
- return;
-
- invalidate_bh_lrus();
- lru_add_drain_all(); /* make sure all lru add caches are flushed */
- invalidate_mapping_pages(mapping, 0, -1);
-}
-EXPORT_SYMBOL(invalidate_bdev);
-
/*
* Kick the writeback threads then try to free up some ZONE_NORMAL memory.
*/
struct zone *zone;
int nid;
- wakeup_flusher_threads(1024);
+ wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM);
yield();
for_each_online_node(nid) {
{
struct buffer_head *bh;
struct list_head tmp;
- struct address_space *mapping, *prev_mapping = NULL;
+ struct address_space *mapping;
int err = 0, err2;
+ struct blk_plug plug;
INIT_LIST_HEAD(&tmp);
+ blk_start_plug(&plug);
spin_lock(lock);
while (!list_empty(list)) {
* still in flight on potentially older
* contents.
*/
- write_dirty_buffer(bh, WRITE_SYNC_PLUG);
+ write_dirty_buffer(bh, WRITE_SYNC);
/*
* Kick off IO for the previous mapping. Note
* 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);
}
}
}
+ spin_unlock(lock);
+ blk_finish_plug(&plug);
+ spin_lock(lock);
+
while (!list_empty(&tmp)) {
bh = BH_ENTRY(tmp.prev);
get_bh(bh);
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
int uptodate = PageUptodate(page);
+ sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode));
do {
if (!buffer_mapped(bh)) {
bh->b_blocknr = block;
if (uptodate)
set_buffer_uptodate(bh);
- set_buffer_mapped(bh);
+ if (block < end_block)
+ set_buffer_mapped(bh);
}
block++;
bh = bh->b_this_page;
return page;
failed:
- BUG();
unlock_page(page);
page_cache_release(page);
return NULL;
* inode list.
*
* mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock,
- * mapping->tree_lock and the global inode_lock.
+ * mapping->tree_lock and mapping->host->i_lock.
*/
void mark_buffer_dirty(struct buffer_head *bh)
{
static void bh_lru_install(struct buffer_head *bh)
{
struct buffer_head *evictee = NULL;
- struct bh_lru *lru;
check_irqs_on();
bh_lru_lock();
- lru = &__get_cpu_var(bh_lrus);
- if (lru->bhs[0] != bh) {
+ if (__this_cpu_read(bh_lrus.bhs[0]) != bh) {
struct buffer_head *bhs[BH_LRU_SIZE];
int in;
int out = 0;
get_bh(bh);
bhs[out++] = bh;
for (in = 0; in < BH_LRU_SIZE; in++) {
- struct buffer_head *bh2 = lru->bhs[in];
+ struct buffer_head *bh2 =
+ __this_cpu_read(bh_lrus.bhs[in]);
if (bh2 == bh) {
__brelse(bh2);
}
while (out < BH_LRU_SIZE)
bhs[out++] = NULL;
- memcpy(lru->bhs, bhs, sizeof(bhs));
+ memcpy(__this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs));
}
bh_lru_unlock();
lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *ret = NULL;
- struct bh_lru *lru;
unsigned int i;
check_irqs_on();
bh_lru_lock();
- lru = &__get_cpu_var(bh_lrus);
for (i = 0; i < BH_LRU_SIZE; i++) {
- struct buffer_head *bh = lru->bhs[i];
+ struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
if (bh && bh->b_bdev == bdev &&
bh->b_blocknr == block && bh->b_size == size) {
if (i) {
while (i) {
- lru->bhs[i] = lru->bhs[i - 1];
+ __this_cpu_write(bh_lrus.bhs[i],
+ __this_cpu_read(bh_lrus.bhs[i - 1]));
i--;
}
- lru->bhs[0] = bh;
+ __this_cpu_write(bh_lrus.bhs[0], bh);
}
get_bh(bh);
ret = bh;
}
put_cpu_var(bh_lrus);
}
+
+static bool has_bh_in_lru(int cpu, void *dummy)
+{
+ struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
+ int i;
+ for (i = 0; i < BH_LRU_SIZE; i++) {
+ if (b->bhs[i])
+ return 1;
+ }
+
+ return 0;
+}
+
void invalidate_bh_lrus(void)
{
- on_each_cpu(invalidate_bh_lru, NULL, 1);
+ on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
}
/**
- * block_invalidatepage - invalidate part of all of a buffer-backed page
+ * block_invalidatepage - invalidate part or all of a buffer-backed page
*
* @page: the page which is affected
* @offset: the index of the truncation point
*
* block_invalidatepage() is called when all or part of the page has become
- * invalidatedby a truncate operation.
+ * invalidated by a truncate operation.
*
* block_invalidatepage() does not have to release all buffers, but it must
* ensure that no dirty buffer is left outside @offset and that no I/O
* 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.
+ * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this
+ * causes the writes to be flagged as synchronous writes.
*/
static int __block_write_full_page(struct inode *inode, struct page *page,
get_block_t *get_block, struct writeback_control *wbc,
const unsigned blocksize = 1 << inode->i_blkbits;
int nr_underway = 0;
int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
- WRITE_SYNC_PLUG : WRITE);
+ WRITE_SYNC : WRITE);
BUG_ON(!PageLocked(page));
if (!buffer_uptodate(*wait_bh))
err = -EIO;
}
- if (unlikely(err)) {
+ if (unlikely(err))
page_zero_new_buffers(page, from, to);
- ClearPageUptodate(page);
- }
return err;
}
EXPORT_SYMBOL(__block_write_begin);
* page lock we can determine safely if the page is beyond EOF. If it is not
* beyond EOF, then the page is guaranteed safe against truncation until we
* unlock the page.
+ *
+ * Direct callers of this function should call vfs_check_frozen() so that page
+ * fault does not busyloop until the fs is thawed.
*/
-int
-block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block)
+int __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 = VM_FAULT_NOPAGE; /* make the VM retry the fault */
+ int ret;
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 */
- unlock_page(page);
- goto out;
+ /* We overload EFAULT to mean page got truncated */
+ ret = -EFAULT;
+ goto out_unlock;
}
/* page is wholly or partially inside EOF */
if (!ret)
ret = block_commit_write(page, 0, end);
- 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:
+ if (unlikely(ret < 0))
+ goto out_unlock;
+ /*
+ * Freezing in progress? We check after the page is marked dirty and
+ * with page lock held so if the test here fails, we are sure freezing
+ * code will wait during syncing until the page fault is done - at that
+ * point page will be dirty and unlocked so freezing code will write it
+ * and writeprotect it again.
+ */
+ set_page_dirty(page);
+ if (inode->i_sb->s_frozen != SB_UNFROZEN) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
+ wait_on_page_writeback(page);
+ return 0;
+out_unlock:
+ unlock_page(page);
return ret;
}
+EXPORT_SYMBOL(__block_page_mkwrite);
+
+int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+ get_block_t get_block)
+{
+ int ret;
+ struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
+
+ /*
+ * This check is racy but catches the common case. The check in
+ * __block_page_mkwrite() is reliable.
+ */
+ vfs_check_frozen(sb, SB_FREEZE_WRITE);
+ ret = __block_page_mkwrite(vma, vmf, get_block);
+ return block_page_mkwrite_return(ret);
+}
EXPORT_SYMBOL(block_page_mkwrite);
/*
}
EXPORT_SYMBOL(try_to_free_buffers);
-void block_sync_page(struct page *page)
-{
- struct address_space *mapping;
-
- smp_mb();
- mapping = page_mapping(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.
int i;
int tot = 0;
- if (__get_cpu_var(bh_accounting).ratelimit++ < 4096)
+ if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096)
return;
- __get_cpu_var(bh_accounting).ratelimit = 0;
+ __this_cpu_write(bh_accounting.ratelimit, 0);
for_each_online_cpu(i)
tot += per_cpu(bh_accounting, i).nr;
buffer_heads_over_limit = (tot > max_buffer_heads);
}
-
+
struct buffer_head *alloc_buffer_head(gfp_t 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++;
+ preempt_disable();
+ __this_cpu_inc(bh_accounting.nr);
recalc_bh_state();
- put_cpu_var(bh_accounting);
+ preempt_enable();
}
return ret;
}
{
BUG_ON(!list_empty(&bh->b_assoc_buffers));
kmem_cache_free(bh_cachep, bh);
- get_cpu_var(bh_accounting).nr--;
+ preempt_disable();
+ __this_cpu_dec(bh_accounting.nr);
recalc_bh_state();
- put_cpu_var(bh_accounting);
+ preempt_enable();
}
EXPORT_SYMBOL(free_buffer_head);
brelse(b->bhs[i]);
b->bhs[i] = NULL;
}
- get_cpu_var(bh_accounting).nr += per_cpu(bh_accounting, cpu).nr;
+ this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr);
per_cpu(bh_accounting, cpu).nr = 0;
- put_cpu_var(bh_accounting);
}
static int buffer_cpu_notify(struct notifier_block *self,