8ff8466d29
In btrfs_release_extent_buffer_pages(), we need to add extra handling for subpage. Introduce a helper, detach_extent_buffer_page(), to do different handling for regular and subpage cases. For subpage case, handle detaching page private. For unmapped (dummy or cloned) ebs, we can detach the page private immediately as the page can only be attached to one unmapped eb. For mapped ebs, we have to ensure there are no eb in the page range before we delete it, as page->private is shared between all ebs in the same page. But there is a subpage specific race, where we can race with extent buffer allocation, and clear the page private while new eb is still being utilized, like this: Extent buffer A is the new extent buffer which will be allocated, while extent buffer B is the last existing extent buffer of the page. T1 (eb A) | T2 (eb B) -------------------------------+------------------------------ alloc_extent_buffer() | btrfs_release_extent_buffer_pages() |- p = find_or_create_page() | | |- attach_extent_buffer_page() | | | | |- detach_extent_buffer_page() | | |- if (!page_range_has_eb()) | | | No new eb in the page range yet | | | As new eb A hasn't yet been | | | inserted into radix tree. | | |- btrfs_detach_subpage() | | |- detach_page_private(); |- radix_tree_insert() | Then we have a metadata eb whose page has no private bit. To avoid such race, we introduce a subpage metadata-specific member, btrfs_subpage::eb_refs. In alloc_extent_buffer() we increase eb_refs in the critical section of private_lock. Then page_range_has_eb() will return true for detach_extent_buffer_page(), and will not detach page private. The section is marked by: - btrfs_page_inc_eb_refs() - btrfs_page_dec_eb_refs() Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
104 lines
2.6 KiB
C
104 lines
2.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#include <linux/slab.h>
|
|
#include "ctree.h"
|
|
#include "subpage.h"
|
|
|
|
int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
|
|
struct page *page, enum btrfs_subpage_type type)
|
|
{
|
|
struct btrfs_subpage *subpage = NULL;
|
|
int ret;
|
|
|
|
/*
|
|
* We have cases like a dummy extent buffer page, which is not mappped
|
|
* and doesn't need to be locked.
|
|
*/
|
|
if (page->mapping)
|
|
ASSERT(PageLocked(page));
|
|
/* Either not subpage, or the page already has private attached */
|
|
if (fs_info->sectorsize == PAGE_SIZE || PagePrivate(page))
|
|
return 0;
|
|
|
|
ret = btrfs_alloc_subpage(fs_info, &subpage, type);
|
|
if (ret < 0)
|
|
return ret;
|
|
attach_page_private(page, subpage);
|
|
return 0;
|
|
}
|
|
|
|
void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info,
|
|
struct page *page)
|
|
{
|
|
struct btrfs_subpage *subpage;
|
|
|
|
/* Either not subpage, or already detached */
|
|
if (fs_info->sectorsize == PAGE_SIZE || !PagePrivate(page))
|
|
return;
|
|
|
|
subpage = (struct btrfs_subpage *)detach_page_private(page);
|
|
ASSERT(subpage);
|
|
btrfs_free_subpage(subpage);
|
|
}
|
|
|
|
int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info,
|
|
struct btrfs_subpage **ret,
|
|
enum btrfs_subpage_type type)
|
|
{
|
|
if (fs_info->sectorsize == PAGE_SIZE)
|
|
return 0;
|
|
|
|
*ret = kzalloc(sizeof(struct btrfs_subpage), GFP_NOFS);
|
|
if (!*ret)
|
|
return -ENOMEM;
|
|
spin_lock_init(&(*ret)->lock);
|
|
if (type == BTRFS_SUBPAGE_METADATA)
|
|
atomic_set(&(*ret)->eb_refs, 0);
|
|
return 0;
|
|
}
|
|
|
|
void btrfs_free_subpage(struct btrfs_subpage *subpage)
|
|
{
|
|
kfree(subpage);
|
|
}
|
|
|
|
/*
|
|
* Increase the eb_refs of current subpage.
|
|
*
|
|
* This is important for eb allocation, to prevent race with last eb freeing
|
|
* of the same page.
|
|
* With the eb_refs increased before the eb inserted into radix tree,
|
|
* detach_extent_buffer_page() won't detach the page private while we're still
|
|
* allocating the extent buffer.
|
|
*/
|
|
void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info,
|
|
struct page *page)
|
|
{
|
|
struct btrfs_subpage *subpage;
|
|
|
|
if (fs_info->sectorsize == PAGE_SIZE)
|
|
return;
|
|
|
|
ASSERT(PagePrivate(page) && page->mapping);
|
|
lockdep_assert_held(&page->mapping->private_lock);
|
|
|
|
subpage = (struct btrfs_subpage *)page->private;
|
|
atomic_inc(&subpage->eb_refs);
|
|
}
|
|
|
|
void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info,
|
|
struct page *page)
|
|
{
|
|
struct btrfs_subpage *subpage;
|
|
|
|
if (fs_info->sectorsize == PAGE_SIZE)
|
|
return;
|
|
|
|
ASSERT(PagePrivate(page) && page->mapping);
|
|
lockdep_assert_held(&page->mapping->private_lock);
|
|
|
|
subpage = (struct btrfs_subpage *)page->private;
|
|
ASSERT(atomic_read(&subpage->eb_refs));
|
|
atomic_dec(&subpage->eb_refs);
|
|
}
|