2021-01-26 16:33:47 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include "ctree.h"
|
|
|
|
#include "subpage.h"
|
|
|
|
|
2021-03-25 15:14:45 +08:00
|
|
|
/*
|
|
|
|
* Subpage (sectorsize < PAGE_SIZE) support overview:
|
|
|
|
*
|
|
|
|
* Limitations:
|
|
|
|
*
|
|
|
|
* - Only support 64K page size for now
|
|
|
|
* This is to make metadata handling easier, as 64K page would ensure
|
|
|
|
* all nodesize would fit inside one page, thus we don't need to handle
|
|
|
|
* cases where a tree block crosses several pages.
|
|
|
|
*
|
|
|
|
* - Only metadata read-write for now
|
|
|
|
* The data read-write part is in development.
|
|
|
|
*
|
|
|
|
* - Metadata can't cross 64K page boundary
|
|
|
|
* btrfs-progs and kernel have done that for a while, thus only ancient
|
|
|
|
* filesystems could have such problem. For such case, do a graceful
|
|
|
|
* rejection.
|
|
|
|
*
|
|
|
|
* Special behavior:
|
|
|
|
*
|
|
|
|
* - Metadata
|
|
|
|
* Metadata read is fully supported.
|
|
|
|
* Meaning when reading one tree block will only trigger the read for the
|
|
|
|
* needed range, other unrelated range in the same page will not be touched.
|
|
|
|
*
|
|
|
|
* Metadata write support is partial.
|
|
|
|
* The writeback is still for the full page, but we will only submit
|
|
|
|
* the dirty extent buffers in the page.
|
|
|
|
*
|
|
|
|
* This means, if we have a metadata page like this:
|
|
|
|
*
|
|
|
|
* Page offset
|
|
|
|
* 0 16K 32K 48K 64K
|
|
|
|
* |/////////| |///////////|
|
|
|
|
* \- Tree block A \- Tree block B
|
|
|
|
*
|
|
|
|
* Even if we just want to writeback tree block A, we will also writeback
|
|
|
|
* tree block B if it's also dirty.
|
|
|
|
*
|
|
|
|
* This may cause extra metadata writeback which results more COW.
|
|
|
|
*
|
|
|
|
* Implementation:
|
|
|
|
*
|
|
|
|
* - Common
|
|
|
|
* Both metadata and data will use a new structure, btrfs_subpage, to
|
|
|
|
* record the status of each sector inside a page. This provides the extra
|
|
|
|
* granularity needed.
|
|
|
|
*
|
|
|
|
* - Metadata
|
|
|
|
* Since we have multiple tree blocks inside one page, we can't rely on page
|
|
|
|
* locking anymore, or we will have greatly reduced concurrency or even
|
|
|
|
* deadlocks (hold one tree lock while trying to lock another tree lock in
|
|
|
|
* the same page).
|
|
|
|
*
|
|
|
|
* Thus for metadata locking, subpage support relies on io_tree locking only.
|
|
|
|
* This means a slightly higher tree locking latency.
|
|
|
|
*/
|
|
|
|
|
2021-01-26 16:33:47 +08:00
|
|
|
int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, enum btrfs_subpage_type type)
|
|
|
|
{
|
2021-01-26 16:33:48 +08:00
|
|
|
struct btrfs_subpage *subpage = NULL;
|
|
|
|
int ret;
|
2021-01-26 16:33:47 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
|
2021-01-26 16:33:48 +08:00
|
|
|
ret = btrfs_alloc_subpage(fs_info, &subpage, type);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
2021-01-26 16:33:47 +08:00
|
|
|
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);
|
2021-01-26 16:33:48 +08:00
|
|
|
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);
|
2021-05-31 16:50:44 +08:00
|
|
|
if (type == BTRFS_SUBPAGE_METADATA) {
|
btrfs: support subpage for extent buffer page release
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>
2021-01-26 16:33:50 +08:00
|
|
|
atomic_set(&(*ret)->eb_refs, 0);
|
2021-05-31 16:50:44 +08:00
|
|
|
} else {
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
atomic_set(&(*ret)->readers, 0);
|
2021-05-31 16:50:44 +08:00
|
|
|
atomic_set(&(*ret)->writers, 0);
|
|
|
|
}
|
2021-01-26 16:33:48 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_free_subpage(struct btrfs_subpage *subpage)
|
|
|
|
{
|
2021-01-26 16:33:47 +08:00
|
|
|
kfree(subpage);
|
|
|
|
}
|
btrfs: support subpage for extent buffer page release
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>
2021-01-26 16:33:50 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
}
|
2021-01-26 16:33:52 +08:00
|
|
|
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
|
2021-01-26 16:33:52 +08:00
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
/* Basic checks */
|
|
|
|
ASSERT(PagePrivate(page) && page->private);
|
|
|
|
ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
|
|
|
|
IS_ALIGNED(len, fs_info->sectorsize));
|
|
|
|
/*
|
|
|
|
* The range check only works for mapped page, we can still have
|
|
|
|
* unmapped page like dummy extent buffer pages.
|
|
|
|
*/
|
|
|
|
if (page->mapping)
|
|
|
|
ASSERT(page_offset(page) <= start &&
|
|
|
|
start + len <= page_offset(page) + PAGE_SIZE);
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const int nbits = len >> fs_info->sectorsize_bits;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
btrfs_subpage_assert(fs_info, page, start, len);
|
|
|
|
|
|
|
|
ret = atomic_add_return(nbits, &subpage->readers);
|
|
|
|
ASSERT(ret == nbits);
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const int nbits = len >> fs_info->sectorsize_bits;
|
|
|
|
|
|
|
|
btrfs_subpage_assert(fs_info, page, start, len);
|
|
|
|
ASSERT(atomic_read(&subpage->readers) >= nbits);
|
|
|
|
if (atomic_sub_and_test(nbits, &subpage->readers))
|
|
|
|
unlock_page(page);
|
|
|
|
}
|
|
|
|
|
2021-05-31 16:50:44 +08:00
|
|
|
static void btrfs_subpage_clamp_range(struct page *page, u64 *start, u32 *len)
|
|
|
|
{
|
|
|
|
u64 orig_start = *start;
|
|
|
|
u32 orig_len = *len;
|
|
|
|
|
|
|
|
*start = max_t(u64, page_offset(page), orig_start);
|
|
|
|
*len = min_t(u64, page_offset(page) + PAGE_SIZE,
|
|
|
|
orig_start + orig_len) - *start;
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const int nbits = (len >> fs_info->sectorsize_bits);
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
btrfs_subpage_assert(fs_info, page, start, len);
|
|
|
|
|
|
|
|
ASSERT(atomic_read(&subpage->readers) == 0);
|
|
|
|
ret = atomic_add_return(nbits, &subpage->writers);
|
|
|
|
ASSERT(ret == nbits);
|
|
|
|
}
|
|
|
|
|
|
|
|
bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const int nbits = (len >> fs_info->sectorsize_bits);
|
|
|
|
|
|
|
|
btrfs_subpage_assert(fs_info, page, start, len);
|
|
|
|
|
|
|
|
ASSERT(atomic_read(&subpage->writers) >= nbits);
|
|
|
|
return atomic_sub_and_test(nbits, &subpage->writers);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Lock a page for delalloc page writeback.
|
|
|
|
*
|
|
|
|
* Return -EAGAIN if the page is not properly initialized.
|
|
|
|
* Return 0 with the page locked, and writer counter updated.
|
|
|
|
*
|
|
|
|
* Even with 0 returned, the page still need extra check to make sure
|
|
|
|
* it's really the correct page, as the caller is using
|
|
|
|
* find_get_pages_contig(), which can race with page invalidating.
|
|
|
|
*/
|
|
|
|
int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) {
|
|
|
|
lock_page(page);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
lock_page(page);
|
|
|
|
if (!PagePrivate(page) || !page->private) {
|
|
|
|
unlock_page(page);
|
|
|
|
return -EAGAIN;
|
|
|
|
}
|
|
|
|
btrfs_subpage_clamp_range(page, &start, &len);
|
|
|
|
btrfs_subpage_start_writer(fs_info, page, start, len);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE)
|
|
|
|
return unlock_page(page);
|
|
|
|
btrfs_subpage_clamp_range(page, &start, &len);
|
|
|
|
if (btrfs_subpage_end_and_test_writer(fs_info, page, start, len))
|
|
|
|
unlock_page(page);
|
|
|
|
}
|
|
|
|
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
/*
|
|
|
|
* Convert the [start, start + len) range into a u16 bitmap
|
|
|
|
*
|
|
|
|
* For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0.
|
|
|
|
*/
|
|
|
|
static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits;
|
|
|
|
const int nbits = len >> fs_info->sectorsize_bits;
|
|
|
|
|
|
|
|
btrfs_subpage_assert(fs_info, page, start, len);
|
|
|
|
|
2021-01-26 16:33:52 +08:00
|
|
|
/*
|
|
|
|
* Here nbits can be 16, thus can go beyond u16 range. We make the
|
|
|
|
* first left shift to be calculate in unsigned long (at least u32),
|
|
|
|
* then truncate the result to u16.
|
|
|
|
*/
|
|
|
|
return (u16)(((1UL << nbits) - 1) << bit_start);
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->uptodate_bitmap |= tmp;
|
|
|
|
if (subpage->uptodate_bitmap == U16_MAX)
|
|
|
|
SetPageUptodate(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->uptodate_bitmap &= ~tmp;
|
|
|
|
ClearPageUptodate(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
|
|
|
|
2021-01-26 16:33:53 +08:00
|
|
|
void btrfs_subpage_set_error(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->error_bitmap |= tmp;
|
|
|
|
SetPageError(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_clear_error(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->error_bitmap &= ~tmp;
|
|
|
|
if (subpage->error_bitmap == 0)
|
|
|
|
ClearPageError(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
|
|
|
|
2021-03-25 15:14:37 +08:00
|
|
|
void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->dirty_bitmap |= tmp;
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
set_page_dirty(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Extra clear_and_test function for subpage dirty bitmap.
|
|
|
|
*
|
|
|
|
* Return true if we're the last bits in the dirty_bitmap and clear the
|
|
|
|
* dirty_bitmap.
|
|
|
|
* Return false otherwise.
|
|
|
|
*
|
|
|
|
* NOTE: Callers should manually clear page dirty for true case, as we have
|
|
|
|
* extra handling for tree blocks.
|
|
|
|
*/
|
|
|
|
bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
bool last = false;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->dirty_bitmap &= ~tmp;
|
|
|
|
if (subpage->dirty_bitmap == 0)
|
|
|
|
last = true;
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
return last;
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_clear_dirty(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
bool last;
|
|
|
|
|
|
|
|
last = btrfs_subpage_clear_and_test_dirty(fs_info, page, start, len);
|
|
|
|
if (last)
|
|
|
|
clear_page_dirty_for_io(page);
|
|
|
|
}
|
|
|
|
|
2021-03-25 15:14:38 +08:00
|
|
|
void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->writeback_bitmap |= tmp;
|
|
|
|
set_page_writeback(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_clear_writeback(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->writeback_bitmap &= ~tmp;
|
|
|
|
if (subpage->writeback_bitmap == 0)
|
|
|
|
end_page_writeback(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
|
|
|
|
2021-05-31 16:50:45 +08:00
|
|
|
void btrfs_subpage_set_ordered(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->ordered_bitmap |= tmp;
|
|
|
|
SetPageOrdered(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
void btrfs_subpage_clear_ordered(const struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len);
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
|
|
|
subpage->ordered_bitmap &= ~tmp;
|
|
|
|
if (subpage->ordered_bitmap == 0)
|
|
|
|
ClearPageOrdered(page);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
}
|
2021-01-26 16:33:52 +08:00
|
|
|
/*
|
|
|
|
* Unlike set/clear which is dependent on each page status, for test all bits
|
|
|
|
* are tested in the same way.
|
|
|
|
*/
|
|
|
|
#define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name) \
|
|
|
|
bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \
|
|
|
|
struct page *page, u64 start, u32 len) \
|
|
|
|
{ \
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; \
|
|
|
|
const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); \
|
|
|
|
unsigned long flags; \
|
|
|
|
bool ret; \
|
|
|
|
\
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags); \
|
|
|
|
ret = ((subpage->name##_bitmap & tmp) == tmp); \
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags); \
|
|
|
|
return ret; \
|
|
|
|
}
|
|
|
|
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate);
|
2021-01-26 16:33:53 +08:00
|
|
|
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error);
|
2021-03-25 15:14:37 +08:00
|
|
|
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(dirty);
|
2021-03-25 15:14:38 +08:00
|
|
|
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(writeback);
|
2021-05-31 16:50:45 +08:00
|
|
|
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(ordered);
|
2021-01-26 16:33:52 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Note that, in selftests (extent-io-tests), we can have empty fs_info passed
|
|
|
|
* in. We only test sectorsize == PAGE_SIZE cases so far, thus we can fall
|
|
|
|
* back to regular sectorsize branch.
|
|
|
|
*/
|
|
|
|
#define IMPLEMENT_BTRFS_PAGE_OPS(name, set_page_func, clear_page_func, \
|
|
|
|
test_page_func) \
|
|
|
|
void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \
|
|
|
|
struct page *page, u64 start, u32 len) \
|
|
|
|
{ \
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \
|
|
|
|
set_page_func(page); \
|
|
|
|
return; \
|
|
|
|
} \
|
|
|
|
btrfs_subpage_set_##name(fs_info, page, start, len); \
|
|
|
|
} \
|
|
|
|
void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \
|
|
|
|
struct page *page, u64 start, u32 len) \
|
|
|
|
{ \
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \
|
|
|
|
clear_page_func(page); \
|
|
|
|
return; \
|
|
|
|
} \
|
|
|
|
btrfs_subpage_clear_##name(fs_info, page, start, len); \
|
|
|
|
} \
|
|
|
|
bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \
|
|
|
|
struct page *page, u64 start, u32 len) \
|
|
|
|
{ \
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \
|
|
|
|
return test_page_func(page); \
|
|
|
|
return btrfs_subpage_test_##name(fs_info, page, start, len); \
|
2021-05-31 16:50:39 +08:00
|
|
|
} \
|
|
|
|
void btrfs_page_clamp_set_##name(const struct btrfs_fs_info *fs_info, \
|
|
|
|
struct page *page, u64 start, u32 len) \
|
|
|
|
{ \
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \
|
|
|
|
set_page_func(page); \
|
|
|
|
return; \
|
|
|
|
} \
|
|
|
|
btrfs_subpage_clamp_range(page, &start, &len); \
|
|
|
|
btrfs_subpage_set_##name(fs_info, page, start, len); \
|
|
|
|
} \
|
|
|
|
void btrfs_page_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \
|
|
|
|
struct page *page, u64 start, u32 len) \
|
|
|
|
{ \
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \
|
|
|
|
clear_page_func(page); \
|
|
|
|
return; \
|
|
|
|
} \
|
|
|
|
btrfs_subpage_clamp_range(page, &start, &len); \
|
|
|
|
btrfs_subpage_clear_##name(fs_info, page, start, len); \
|
|
|
|
} \
|
|
|
|
bool btrfs_page_clamp_test_##name(const struct btrfs_fs_info *fs_info, \
|
|
|
|
struct page *page, u64 start, u32 len) \
|
|
|
|
{ \
|
|
|
|
if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \
|
|
|
|
return test_page_func(page); \
|
|
|
|
btrfs_subpage_clamp_range(page, &start, &len); \
|
|
|
|
return btrfs_subpage_test_##name(fs_info, page, start, len); \
|
2021-01-26 16:33:52 +08:00
|
|
|
}
|
|
|
|
IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate,
|
|
|
|
PageUptodate);
|
2021-01-26 16:33:53 +08:00
|
|
|
IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError);
|
2021-03-25 15:14:37 +08:00
|
|
|
IMPLEMENT_BTRFS_PAGE_OPS(dirty, set_page_dirty, clear_page_dirty_for_io,
|
|
|
|
PageDirty);
|
2021-03-25 15:14:38 +08:00
|
|
|
IMPLEMENT_BTRFS_PAGE_OPS(writeback, set_page_writeback, end_page_writeback,
|
|
|
|
PageWriteback);
|
2021-05-31 16:50:45 +08:00
|
|
|
IMPLEMENT_BTRFS_PAGE_OPS(ordered, SetPageOrdered, ClearPageOrdered,
|
|
|
|
PageOrdered);
|