mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-20 19:23:57 +08:00
92082d4097
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>
279 lines
8.4 KiB
C
279 lines
8.4 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);
|
|
else
|
|
atomic_set(&(*ret)->readers, 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);
|
|
}
|
|
|
|
static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
|
|
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);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
|
|
/*
|
|
* 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);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error);
|
|
|
|
/*
|
|
* 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); \
|
|
}
|
|
IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate,
|
|
PageUptodate);
|
|
IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError);
|