#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/aio.h>
+#include <linux/capability.h>
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/syscalls.h>
+#include <linux/cpuset.h>
#include "filemap.h"
+#include "internal.h"
+
/*
* FIXME: remove all knowledge of the buffer layer from the core VM
*/
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
*
- * ->i_sem
+ * ->i_mutex
* ->i_mmap_lock (truncate->unmap_mapping_range)
*
* ->mmap_sem
* ->lock_page (access_process_vm)
*
* ->mmap_sem
- * ->i_sem (msync)
+ * ->i_mutex (msync)
*
- * ->i_sem
+ * ->i_mutex
* ->i_alloc_sem (various)
*
* ->inode_lock
* ->private_lock (try_to_unmap_one)
* ->tree_lock (try_to_unmap_one)
* ->zone.lru_lock (follow_page->mark_page_accessed)
+ * ->zone.lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->tree_lock (page_remove_rmap->set_page_dirty)
* ->inode_lock (page_remove_rmap->set_page_dirty)
* dirty pages that lie within the byte offsets <start, end>
* @mapping: address space structure to write
* @start: offset in bytes where the range starts
- * @end: offset in bytes where the range ends
+ * @end: offset in bytes where the range ends (inclusive)
* @sync_mode: enable synchronous operation
*
* If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
* these two operations is that if a dirty page/buffer is encountered, it must
* be waited upon, and not just skipped over.
*/
-static int __filemap_fdatawrite_range(struct address_space *mapping,
- loff_t start, loff_t end, int sync_mode)
+int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+ loff_t end, int sync_mode)
{
int ret;
struct writeback_control wbc = {
}
EXPORT_SYMBOL(filemap_fdatawrite);
-static int filemap_fdatawrite_range(struct address_space *mapping,
- loff_t start, loff_t end)
+static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+ loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
* Wait for writeback to complete against pages indexed by start->end
* inclusive
*/
-static int wait_on_page_writeback_range(struct address_space *mapping,
+int wait_on_page_writeback_range(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
struct pagevec pvec;
* integrity" operation. It waits upon in-flight writeout before starting and
* waiting upon new writeout. If there was an IO error, return it.
*
- * We need to re-take i_sem during the generic_osync_inode list walk because
+ * We need to re-take i_mutex during the generic_osync_inode list walk because
* it is otherwise livelockable.
*/
int sync_page_range(struct inode *inode, struct address_space *mapping,
- loff_t pos, size_t count)
+ loff_t pos, loff_t count)
{
pgoff_t start = pos >> PAGE_CACHE_SHIFT;
pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
return 0;
ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
if (ret == 0) {
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
}
if (ret == 0)
ret = wait_on_page_writeback_range(mapping, start, end);
EXPORT_SYMBOL(sync_page_range);
/*
- * Note: Holding i_sem across sync_page_range_nolock is not a good idea
+ * Note: Holding i_mutex across sync_page_range_nolock is not a good idea
* as it forces O_SYNC writers to different parts of the same file
* to be serialised right until io completion.
*/
-static int sync_page_range_nolock(struct inode *inode,
- struct address_space *mapping,
- loff_t pos, size_t count)
+int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
+ loff_t pos, loff_t count)
{
pgoff_t start = pos >> PAGE_CACHE_SHIFT;
pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
ret = wait_on_page_writeback_range(mapping, start, end);
return ret;
}
+EXPORT_SYMBOL(sync_page_range_nolock);
/**
* filemap_fdatawait - walk the list of under-writeback pages of the given
int filemap_write_and_wait(struct address_space *mapping)
{
- int retval = 0;
+ int err = 0;
if (mapping->nrpages) {
- retval = filemap_fdatawrite(mapping);
- if (retval == 0)
- retval = filemap_fdatawait(mapping);
+ err = filemap_fdatawrite(mapping);
+ /*
+ * Even if the above returned error, the pages may be
+ * written partially (e.g. -ENOSPC), so we wait for it.
+ * But the -EIO is special case, it may indicate the worst
+ * thing (e.g. bug) happened, so we avoid waiting for it.
+ */
+ if (err != -EIO) {
+ int err2 = filemap_fdatawait(mapping);
+ if (!err)
+ err = err2;
+ }
}
- return retval;
+ return err;
}
+EXPORT_SYMBOL(filemap_write_and_wait);
+/*
+ * Write out and wait upon file offsets lstart->lend, inclusive.
+ *
+ * Note that `lend' is inclusive (describes the last byte to be written) so
+ * that this function can be used to write to the very end-of-file (end = -1).
+ */
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
- int retval = 0;
+ int err = 0;
if (mapping->nrpages) {
- retval = __filemap_fdatawrite_range(mapping, lstart, lend,
- WB_SYNC_ALL);
- if (retval == 0)
- retval = wait_on_page_writeback_range(mapping,
- lstart >> PAGE_CACHE_SHIFT,
- lend >> PAGE_CACHE_SHIFT);
+ err = __filemap_fdatawrite_range(mapping, lstart, lend,
+ WB_SYNC_ALL);
+ /* See comment of filemap_write_and_wait() */
+ if (err != -EIO) {
+ int err2 = wait_on_page_writeback_range(mapping,
+ lstart >> PAGE_CACHE_SHIFT,
+ lend >> PAGE_CACHE_SHIFT);
+ if (!err)
+ err = err2;
+ }
}
- return retval;
+ return err;
}
/*
return ret;
}
+#ifdef CONFIG_NUMA
+struct page *page_cache_alloc(struct address_space *x)
+{
+ if (cpuset_do_page_mem_spread()) {
+ int n = cpuset_mem_spread_node();
+ return alloc_pages_node(n, mapping_gfp_mask(x), 0);
+ }
+ return alloc_pages(mapping_gfp_mask(x), 0);
+}
+EXPORT_SYMBOL(page_cache_alloc);
+
+struct page *page_cache_alloc_cold(struct address_space *x)
+{
+ if (cpuset_do_page_mem_spread()) {
+ int n = cpuset_mem_spread_node();
+ return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0);
+ }
+ return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0);
+}
+EXPORT_SYMBOL(page_cache_alloc_cold);
+#endif
+
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
page_cache_get(page);
if (TestSetPageLocked(page)) {
read_unlock_irq(&mapping->tree_lock);
- lock_page(page);
+ __lock_page(page);
read_lock_irq(&mapping->tree_lock);
/* Has the page been truncated while we slept? */
- if (page->mapping != mapping || page->index != offset) {
+ if (unlikely(page->mapping != mapping ||
+ page->index != offset)) {
unlock_page(page);
page_cache_release(page);
goto repeat;
/* Start the actual read. The read will unlock the page. */
error = mapping->a_ops->readpage(filp, page);
- if (unlikely(error))
+ if (unlikely(error)) {
+ if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto find_page;
+ }
goto readpage_error;
+ }
if (!PageUptodate(page)) {
lock_page(page);
{
struct address_space *mapping = file->f_mapping;
struct page *page;
- int error;
+ int ret;
- page = page_cache_alloc_cold(mapping);
- if (!page)
- return -ENOMEM;
+ do {
+ page = page_cache_alloc_cold(mapping);
+ if (!page)
+ return -ENOMEM;
+
+ ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
+ if (ret == 0)
+ ret = mapping->a_ops->readpage(file, page);
+ else if (ret == -EEXIST)
+ ret = 0; /* losing race to add is OK */
- error = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
- if (!error) {
- error = mapping->a_ops->readpage(file, page);
page_cache_release(page);
- return error;
- }
- /*
- * We arrive here in the unlikely event that someone
- * raced with us and added our page to the cache first
- * or we are out of memory for radix-tree nodes.
- */
- page_cache_release(page);
- return error == -EEXIST ? 0 : error;
+ } while (ret == AOP_TRUNCATED_PAGE);
+
+ return ret;
}
#define MMAP_LOTSAMISS (100)
goto success;
}
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
goto success;
}
ClearPageError(page);
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
goto success;
}
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
}
ClearPageError(page);
- if (!mapping->a_ops->readpage(file, page)) {
+ error = mapping->a_ops->readpage(file, page);
+ if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
+ } else if (error == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ goto retry_find;
}
/*
/*
* Sync the fs metadata but not the minor inode changes and
* of course not the data as we did direct DMA for the IO.
- * i_sem is held, which protects generic_osync_inode() from
+ * i_mutex is held, which protects generic_osync_inode() from
* livelocking.
*/
if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
status = a_ops->prepare_write(file, page, offset, offset+bytes);
if (unlikely(status)) {
loff_t isize = i_size_read(inode);
+
+ if (status != AOP_TRUNCATED_PAGE)
+ unlock_page(page);
+ page_cache_release(page);
+ if (status == AOP_TRUNCATED_PAGE)
+ continue;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
- unlock_page(page);
- page_cache_release(page);
if (pos + bytes > isize)
vmtruncate(inode, isize);
break;
cur_iov, iov_base, bytes);
flush_dcache_page(page);
status = a_ops->commit_write(file, page, offset, offset+bytes);
+ if (status == AOP_TRUNCATED_PAGE) {
+ page_cache_release(page);
+ continue;
+ }
if (likely(copied > 0)) {
if (!status)
status = copied;
if (err)
goto out;
- inode_update_time(inode, 1);
+ file_update_time(file);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
BUG_ON(iocb->ki_pos != pos);
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1,
&iocb->ki_pos);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
ssize_t err;
struct iovec local_iov = { .iov_base = (void __user *)buf,
.iov_len = count };
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = __generic_file_write_nolock(file, &local_iov, 1, ppos);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
ssize_t err;
struct inode *inode = mapping->host;
ssize_t ret;
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
ret = __generic_file_write_nolock(file, iov, nr_segs, ppos);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
int err;
EXPORT_SYMBOL(generic_file_writev);
/*
- * Called under i_sem for writes to S_ISREG files. Returns -EIO if something
+ * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something
* went wrong during pagecache shootdown.
*/
static ssize_t