page->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
-
- if (shadow) {
- mapping->nrexceptional += nr;
- /*
- * Make sure the nrexceptional update is committed before
- * the nrpages update so that final truncate racing
- * with reclaim does not see both counters 0 at the
- * same time and miss a shadow entry.
- */
- smp_wmb();
- }
mapping->nrpages -= nr;
}
/* Returns true if writeback might be needed or already in progress. */
static bool mapping_needs_writeback(struct address_space *mapping)
{
- if (dax_mapping(mapping))
- return mapping->nrexceptional;
-
return mapping->nrpages;
}
+/**
+ * filemap_range_needs_writeback - check if range potentially needs writeback
+ * @mapping: address space within which to check
+ * @start_byte: offset in bytes where the range starts
+ * @end_byte: offset in bytes where the range ends (inclusive)
+ *
+ * Find at least one page in the range supplied, usually used to check if
+ * direct writing in this range will trigger a writeback. Used by O_DIRECT
+ * read/write with IOCB_NOWAIT, to see if the caller needs to do
+ * filemap_write_and_wait_range() before proceeding.
+ *
+ * Return: %true if the caller should do filemap_write_and_wait_range() before
+ * doing O_DIRECT to a page in this range, %false otherwise.
+ */
+bool filemap_range_needs_writeback(struct address_space *mapping,
+ loff_t start_byte, loff_t end_byte)
+{
+ XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
+ pgoff_t max = end_byte >> PAGE_SHIFT;
+ struct page *page;
+
+ if (!mapping_needs_writeback(mapping))
+ return false;
+ if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
+ !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+ return false;
+ if (end_byte < start_byte)
+ return false;
+
+ rcu_read_lock();
+ xas_for_each(&xas, page, max) {
+ if (xas_retry(&xas, page))
+ continue;
+ if (xa_is_value(page))
+ continue;
+ if (PageDirty(page) || PageLocked(page) || PageWriteback(page))
+ break;
+ }
+ rcu_read_unlock();
+ return page != NULL;
+}
+EXPORT_SYMBOL_GPL(filemap_range_needs_writeback);
+
/**
* filemap_write_and_wait_range - write out & wait on a file range
* @mapping: the address_space for the pages
page->index = offset;
if (!huge) {
- error = mem_cgroup_charge(page, current->mm, gfp);
+ error = mem_cgroup_charge(page, NULL, gfp);
if (error)
goto error;
charged = true;
if (xas_error(&xas))
goto unlock;
- if (old)
- mapping->nrexceptional--;
mapping->nrpages++;
/* hugetlb pages do not participate in page cache accounting */
}
EXPORT_SYMBOL(unlock_page);
+/**
+ * end_page_private_2 - Clear PG_private_2 and release any waiters
+ * @page: The page
+ *
+ * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for
+ * this. The page ref held for PG_private_2 being set is released.
+ *
+ * This is, for example, used when a netfs page is being written to a local
+ * disk cache, thereby allowing writes to the cache for the same page to be
+ * serialised.
+ */
+void end_page_private_2(struct page *page)
+{
+ page = compound_head(page);
+ VM_BUG_ON_PAGE(!PagePrivate2(page), page);
+ clear_bit_unlock(PG_private_2, &page->flags);
+ wake_up_page_bit(page, PG_private_2);
+ put_page(page);
+}
+EXPORT_SYMBOL(end_page_private_2);
+
+/**
+ * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page
+ * @page: The page to wait on
+ *
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page.
+ */
+void wait_on_page_private_2(struct page *page)
+{
+ page = compound_head(page);
+ while (PagePrivate2(page))
+ wait_on_page_bit(page, PG_private_2);
+}
+EXPORT_SYMBOL(wait_on_page_private_2);
+
+/**
+ * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page
+ * @page: The page to wait on
+ *
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a
+ * fatal signal is received by the calling task.
+ *
+ * Return:
+ * - 0 if successful.
+ * - -EINTR if a fatal signal was encountered.
+ */
+int wait_on_page_private_2_killable(struct page *page)
+{
+ int ret = 0;
+
+ page = compound_head(page);
+ while (PagePrivate2(page)) {
+ ret = wait_on_page_bit_killable(page, PG_private_2);
+ if (ret < 0)
+ break;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(wait_on_page_private_2_killable);
+
/**
* end_page_writeback - end writeback against a page
* @page: the page
* @mapping: the address_space to search
* @index: The page cache index.
*
- * Looks up the page cache slot at @mapping & @offset. If there is a
+ * Looks up the page cache slot at @mapping & @index. If there is a
* page cache page, the head page is returned with an increased refcount.
*
* If the slot holds a shadow entry of a previously evicted page, or a
return error;
if (PageUptodate(page))
return 0;
- if (!page->mapping) /* page truncated */
- return AOP_TRUNCATED_PAGE;
shrink_readahead_size_eio(&file->f_ra);
return -EIO;
}
size = i_size_read(inode);
if (iocb->ki_flags & IOCB_NOWAIT) {
- if (filemap_range_has_page(mapping, iocb->ki_pos,
- iocb->ki_pos + count - 1))
+ if (filemap_range_needs_writeback(mapping, iocb->ki_pos,
+ iocb->ki_pos + count - 1))
return -EAGAIN;
} else {
retval = filemap_write_and_wait_range(mapping,
* entirely memory-based such as tmpfs, and filesystems which support
* unwritten extents.
*
- * Return: The requested offset on successs, or -ENXIO if @whence specifies
+ * Return: The requested offset on success, or -ENXIO if @whence specifies
* SEEK_DATA and there is no data after @start. There is an implicit hole
* after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start
* and @end contain data.
struct file *file = vmf->vma->vm_file;
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
- DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff);
+ DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
struct file *fpin = NULL;
unsigned int mmap_miss;
if (vmf->vma->vm_flags & VM_SEQ_READ) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- page_cache_sync_ra(&ractl, ra, ra->ra_pages);
+ page_cache_sync_ra(&ractl, ra->ra_pages);
return fpin;
}
struct file *file = vmf->vma->vm_file;
struct file *fpin = NULL;
struct address_space *mapping = file->f_mapping;
- struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
pgoff_t offset = vmf->pgoff;
pgoff_t max_off;
* because there really aren't any performance issues here
* and we need to check for errors.
*/
- ClearPageError(page);
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- error = mapping->a_ops->readpage(file, page);
- if (!error) {
- wait_on_page_locked(page);
- if (!PageUptodate(page))
- error = -EIO;
- }
+ error = filemap_read_page(file, mapping, page);
if (fpin)
goto out_retry;
put_page(page);
if (!error || error == AOP_TRUNCATED_PAGE)
goto retry_find;
- shrink_readahead_size_eio(ra);
return VM_FAULT_SIGBUS;
out_retry:
/* This is used for a general mmap of a disk file */
-int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
+int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct address_space *mapping = file->f_mapping;
{
return VM_FAULT_SIGBUS;
}
-int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
+int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
{
return -ENOSYS;
}
-int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
+int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
return -ENOSYS;
}
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
- *
- * Not only is this an optimisation, but it is also required
- * to check that the address is actually valid, when atomic
- * usercopies are used, below.
*/
if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
status = -EFAULT;
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
- copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
+ copied = copy_page_from_iter_atomic(page, offset, bytes, i);
flush_dcache_page(page);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
page, fsdata);
- if (unlikely(status < 0))
- break;
- copied = status;
-
+ if (unlikely(status != copied)) {
+ iov_iter_revert(i, copied - max(status, 0L));
+ if (unlikely(status < 0))
+ break;
+ }
cond_resched();
- iov_iter_advance(i, copied);
- if (unlikely(copied == 0)) {
+ if (unlikely(status == 0)) {
/*
- * If we were unable to copy any data at all, we must
- * fall back to a single segment length write.
- *
- * If we didn't fallback here, we could livelock
- * because not all segments in the iov can be copied at
- * once without a pagefault.
+ * A short copy made ->write_end() reject the
+ * thing entirely. Might be memory poisoning
+ * halfway through, might be a race with munmap,
+ * might be severe memory pressure.
*/
- bytes = min_t(unsigned long, PAGE_SIZE - offset,
- iov_iter_single_seg_count(i));
+ if (copied)
+ bytes = copied;
goto again;
}
- pos += copied;
- written += copied;
+ pos += status;
+ written += status;
balance_dirty_pages_ratelimited(mapping);
} while (iov_iter_count(i));
ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
- struct address_space * mapping = file->f_mapping;
+ struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t written = 0;
ssize_t err;