#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/capability.h>
#include <linux/blkdev.h>
#include <linux/file.h>
#include <linux/bit_spinlock.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
-static void invalidate_bh_lrus(void);
#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
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, int destroy_dirty_buffers)
+void invalidate_bdev(struct block_device *bdev)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
return;
invalidate_bh_lrus();
- /*
- * FIXME: what about destroy_dirty_buffers?
- * We really want to use invalidate_inode_pages2() for
- * that, but not until that's cleaned up.
- */
invalidate_mapping_pages(mapping, 0, -1);
}
for_each_online_pgdat(pgdat) {
zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones;
if (*zones)
- try_to_free_pages(zones, GFP_NOFS);
+ try_to_free_pages(zones, 0, GFP_NOFS);
}
}
EXPORT_SYMBOL(mark_buffer_dirty_inode);
/*
+ * Mark the page dirty, and set it dirty in the radix tree, and mark the inode
+ * dirty.
+ *
+ * If warn is true, then emit a warning if the page is not uptodate and has
+ * not been truncated.
+ */
+static int __set_page_dirty(struct page *page,
+ struct address_space *mapping, int warn)
+{
+ if (unlikely(!mapping))
+ return !TestSetPageDirty(page);
+
+ if (TestSetPageDirty(page))
+ return 0;
+
+ write_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);
+ task_io_account_write(PAGE_CACHE_SIZE);
+ }
+ radix_tree_tag_set(&mapping->page_tree,
+ page_index(page), PAGECACHE_TAG_DIRTY);
+ }
+ write_unlock_irq(&mapping->tree_lock);
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+ return 1;
+}
+
+/*
* Add a page to the dirty page list.
*
* It is a sad fact of life that this function is called from several places
*/
int __set_page_dirty_buffers(struct page *page)
{
- struct address_space * const mapping = page_mapping(page);
+ struct address_space *mapping = page_mapping(page);
if (unlikely(!mapping))
return !TestSetPageDirty(page);
}
spin_unlock(&mapping->private_lock);
- if (TestSetPageDirty(page))
- return 0;
-
- write_lock_irq(&mapping->tree_lock);
- if (page->mapping) { /* Race with truncate? */
- if (mapping_cap_account_dirty(mapping)) {
- __inc_zone_page_state(page, NR_FILE_DIRTY);
- task_io_account_write(PAGE_CACHE_SIZE);
- }
- radix_tree_tag_set(&mapping->page_tree,
- page_index(page), PAGECACHE_TAG_DIRTY);
- }
- write_unlock_irq(&mapping->tree_lock);
- __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
- return 1;
+ return __set_page_dirty(page, mapping, 1);
}
EXPORT_SYMBOL(__set_page_dirty_buffers);
struct page *page;
struct buffer_head *bh;
- page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, index,
+ (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
if (!page)
return NULL;
/*
* Create buffers for the specified block device block's page. If
* that page was dirty, the buffers are set dirty also.
- *
- * Except that's a bug. Attaching dirty buffers to a dirty
- * blockdev's page can result in filesystem corruption, because
- * some of those buffers may be aliases of filesystem data.
- * grow_dev_page() will go BUG() if this happens.
*/
static int
grow_buffers(struct block_device *bdev, sector_t block, int size)
*/
void fastcall mark_buffer_dirty(struct buffer_head *bh)
{
+ WARN_ON_ONCE(!buffer_uptodate(bh));
if (!buffer_dirty(bh) && !test_set_buffer_dirty(bh))
- __set_page_dirty_nobuffers(bh->b_page);
+ __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
}
/*
* Look up the bh in this cpu's LRU. If it's there, move it to the head.
*/
static struct buffer_head *
-lookup_bh_lru(struct block_device *bdev, sector_t block, int size)
+lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *ret = NULL;
struct bh_lru *lru;
- int i;
+ unsigned int i;
check_irqs_on();
bh_lru_lock();
* NULL
*/
struct buffer_head *
-__find_get_block(struct block_device *bdev, sector_t block, int size)
+__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
* attempt is failing. FIXME, perhaps?
*/
struct buffer_head *
-__getblk(struct block_device *bdev, sector_t block, int size)
+__getblk(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = __find_get_block(bdev, block, size);
/*
* Do async read-ahead on a buffer..
*/
-void __breadahead(struct block_device *bdev, sector_t block, int size)
+void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = __getblk(bdev, block, size);
if (likely(bh)) {
* It returns NULL if the block was unreadable.
*/
struct buffer_head *
-__bread(struct block_device *bdev, sector_t block, int size)
+__bread(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = __getblk(bdev, block, size);
put_cpu_var(bh_lrus);
}
-static void invalidate_bh_lrus(void)
+void invalidate_bh_lrus(void)
{
on_each_cpu(invalidate_bh_lru, NULL, 1, 1);
}
* clean. Someone wrote them back by hand with
* ll_rw_block/submit_bh. A rare case.
*/
- int uptodate = 1;
- do {
- if (!buffer_uptodate(bh)) {
- uptodate = 0;
- break;
- }
- bh = bh->b_this_page;
- } while (bh != head);
- if (uptodate)
- SetPageUptodate(page);
end_page_writeback(page);
+
/*
* The page and buffer_heads can be released at any time from
* here on.
} while ((bh = bh->b_this_page) != head);
SetPageError(page);
BUG_ON(PageWriteback(page));
+ mapping_set_error(page->mapping, err);
set_page_writeback(page);
- unlock_page(page);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
}
bh = next;
} while (bh != head);
+ unlock_page(page);
goto done;
}
if (block_start >= to)
break;
if (buffer_new(bh)) {
- void *kaddr;
-
clear_buffer_new(bh);
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr+block_start, 0, bh->b_size);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, block_start, bh->b_size, KM_USER0);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
}
SetPageError(page);
}
if (!buffer_mapped(bh)) {
- void *kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + i * blocksize, 0, blocksize);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, i * blocksize, blocksize,
+ KM_USER0);
if (!err)
set_buffer_uptodate(bh);
continue;
long status;
unsigned zerofrom;
unsigned blocksize = 1 << inode->i_blkbits;
- void *kaddr;
while(page->index > (pgpos = *bytes>>PAGE_CACHE_SHIFT)) {
status = -ENOMEM;
PAGE_CACHE_SIZE, get_block);
if (status)
goto out_unmap;
- kaddr = kmap_atomic(new_page, KM_USER0);
- memset(kaddr+zerofrom, 0, PAGE_CACHE_SIZE-zerofrom);
- flush_dcache_page(new_page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(new_page, zerofrom, PAGE_CACHE_SIZE - zerofrom,
+ KM_USER0);
generic_commit_write(NULL, new_page, zerofrom, PAGE_CACHE_SIZE);
unlock_page(new_page);
page_cache_release(new_page);
if (status)
goto out1;
if (zerofrom < offset) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr+zerofrom, 0, offset-zerofrom);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, zerofrom, offset - zerofrom, KM_USER0);
__block_commit_write(inode, page, zerofrom, offset);
}
return 0;
return 0;
}
+/*
+ * block_page_mkwrite() is not allowed to change the file size as it gets
+ * called from a page fault handler when a page is first dirtied. Hence we must
+ * be careful to check for EOF conditions here. We set the page up correctly
+ * for a written page which means we get ENOSPC checking when writing into
+ * holes and correct delalloc and unwritten extent mapping on filesystems that
+ * support these features.
+ *
+ * We are not allowed to take the i_mutex here so we have to play games to
+ * protect against truncate races as the page could now be beyond EOF. Because
+ * vmtruncate() writes the inode size before removing pages, once we have the
+ * 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.
+ */
+int
+block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
+ get_block_t get_block)
+{
+ struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ unsigned long end;
+ loff_t size;
+ int ret = -EINVAL;
+
+ 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;
+ }
+
+ /* page is wholly or partially inside EOF */
+ if (((page->index + 1) << PAGE_CACHE_SHIFT) > size)
+ end = size & ~PAGE_CACHE_MASK;
+ else
+ end = PAGE_CACHE_SIZE;
+
+ ret = block_prepare_write(page, 0, end, get_block);
+ if (!ret)
+ ret = block_commit_write(page, 0, end);
+
+out_unlock:
+ unlock_page(page);
+ return ret;
+}
/*
* nobh_prepare_write()'s prereads are special: the buffer_heads are freed
int i;
int ret = 0;
int is_mapped_to_disk = 1;
- int dirtied_it = 0;
if (PageMappedToDisk(page))
return 0;
continue;
if (buffer_new(&map_bh) || !buffer_mapped(&map_bh)) {
kaddr = kmap_atomic(page, KM_USER0);
- if (block_start < from) {
+ if (block_start < from)
memset(kaddr+block_start, 0, from-block_start);
- dirtied_it = 1;
- }
- if (block_end > to) {
+ if (block_end > to)
memset(kaddr + to, 0, block_end - to);
- dirtied_it = 1;
- }
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
continue;
if (is_mapped_to_disk)
SetPageMappedToDisk(page);
- SetPageUptodate(page);
-
- /*
- * Setting the page dirty here isn't necessary for the prepare_write
- * function - commit_write will do that. But if/when this function is
- * used within the pagefault handler to ensure that all mmapped pages
- * have backing space in the filesystem, we will need to dirty the page
- * if its contents were altered.
- */
- if (dirtied_it)
- set_page_dirty(page);
return 0;
* Error recovery is pretty slack. Clear the page and mark it dirty
* so we'll later zero out any blocks which _were_ allocated.
*/
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr, 0, PAGE_CACHE_SIZE);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0);
SetPageUptodate(page);
set_page_dirty(page);
return ret;
}
EXPORT_SYMBOL(nobh_prepare_write);
+/*
+ * Make sure any changes to nobh_commit_write() are reflected in
+ * nobh_truncate_page(), since it doesn't call commit_write().
+ */
int nobh_commit_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct inode *inode = page->mapping->host;
loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ SetPageUptodate(page);
set_page_dirty(page);
if (pos > inode->i_size) {
i_size_write(inode, pos);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
unsigned offset;
- void *kaddr;
int ret;
/* Is the page fully inside i_size? */
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0);
out:
ret = mpage_writepage(page, get_block, wbc);
if (ret == -EAGAIN)
unsigned to;
struct page *page;
const struct address_space_operations *a_ops = mapping->a_ops;
- char *kaddr;
int ret = 0;
if ((offset & (blocksize - 1)) == 0)
to = (offset + blocksize) & ~(blocksize - 1);
ret = a_ops->prepare_write(NULL, page, offset, to);
if (ret == 0) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, PAGE_CACHE_SIZE - offset,
+ KM_USER0);
+ /*
+ * It would be more correct to call aops->commit_write()
+ * here, but this is more efficient.
+ */
+ SetPageUptodate(page);
set_page_dirty(page);
}
unlock_page(page);
struct inode *inode = mapping->host;
struct page *page;
struct buffer_head *bh;
- void *kaddr;
int err;
blocksize = 1 << inode->i_blkbits;
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);
mark_buffer_dirty(bh);
err = 0;
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
unsigned offset;
- void *kaddr;
/* Is the page fully inside i_size? */
if (page->index < end_index)
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0);
return __block_write_full_page(inode, page, get_block, wbc);
}
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++;
recalc_bh_state();
put_cpu_var(bh_accounting);
}
EXPORT_SYMBOL(free_buffer_head);
-static void
-init_buffer_head(void *data, struct kmem_cache *cachep, unsigned long flags)
-{
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR) {
- struct buffer_head * bh = (struct buffer_head *)data;
-
- memset(bh, 0, sizeof(*bh));
- INIT_LIST_HEAD(&bh->b_assoc_buffers);
- }
-}
-
static void buffer_exit_cpu(int cpu)
{
int i;
static int buffer_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
- if (action == CPU_DEAD)
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
buffer_exit_cpu((unsigned long)hcpu);
return NOTIFY_OK;
}
{
int nrpages;
- bh_cachep = kmem_cache_create("buffer_head",
- sizeof(struct buffer_head), 0,
- (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
- SLAB_MEM_SPREAD),
- init_buffer_head,
- NULL);
+ bh_cachep = KMEM_CACHE(buffer_head,
+ SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD);
/*
* Limit the bh occupancy to 10% of ZONE_NORMAL
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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff