#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/page-flags.h>
+#include <linux/sched/mm.h>
#include <linux/spinlock.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
#include "subpage.h"
#include "zoned.h"
#include "block-group.h"
+#include "compression.h"
static struct kmem_cache *extent_state_cache;
static struct kmem_cache *extent_buffer_cache;
if (!fs_info->allocated_ebs.next)
return;
+ WARN_ON(!list_empty(&fs_info->allocated_ebs));
spin_lock_irqsave(&fs_info->eb_leak_lock, flags);
while (!list_empty(&fs_info->allocated_ebs)) {
eb = list_first_entry(&fs_info->allocated_ebs,
struct rb_node rb_node;
};
+/*
+ * Structure to record info about the bio being assembled, and other info like
+ * how many bytes are there before stripe/ordered extent boundary.
+ */
+struct btrfs_bio_ctrl {
+ struct bio *bio;
+ enum btrfs_compression_type compress_type;
+ u32 len_to_stripe_boundary;
+ u32 len_to_oe_boundary;
+};
+
struct extent_page_data {
struct btrfs_bio_ctrl bio_ctrl;
/* tells writepage not to lock the state bits for this range
return ret;
}
-int __must_check submit_one_bio(struct bio *bio, int mirror_num,
- unsigned long bio_flags)
+static void submit_one_bio(struct bio *bio, int mirror_num,
+ enum btrfs_compression_type compress_type)
{
- blk_status_t ret = 0;
struct extent_io_tree *tree = bio->bi_private;
bio->bi_private = NULL;
/* Caller should ensure the bio has at least some range added */
ASSERT(bio->bi_iter.bi_size);
+
if (is_data_inode(tree->private_data))
- ret = btrfs_submit_data_bio(tree->private_data, bio, mirror_num,
- bio_flags);
+ btrfs_submit_data_bio(tree->private_data, bio, mirror_num,
+ compress_type);
else
- ret = btrfs_submit_metadata_bio(tree->private_data, bio,
- mirror_num, bio_flags);
-
- return blk_status_to_errno(ret);
+ btrfs_submit_metadata_bio(tree->private_data, bio, mirror_num);
+ /*
+ * Above submission hooks will handle the error by ending the bio,
+ * which will do the cleanup properly. So here we should not return
+ * any error, or the caller of submit_extent_page() will do cleanup
+ * again, causing problems.
+ */
}
/* Cleanup unsubmitted bios */
* Return 0 if everything is OK.
* Return <0 for error.
*/
-static int __must_check flush_write_bio(struct extent_page_data *epd)
+static void flush_write_bio(struct extent_page_data *epd)
{
- int ret = 0;
struct bio *bio = epd->bio_ctrl.bio;
if (bio) {
- ret = submit_one_bio(bio, 0, 0);
+ submit_one_bio(bio, 0, 0);
/*
* Clean up of epd->bio is handled by its endio function.
* And endio is either triggered by successful bio execution
*/
epd->bio_ctrl.bio = NULL;
}
- return ret;
}
int __init extent_state_cache_init(void)
u64 length, u64 logical, struct page *page,
unsigned int pg_offset, int mirror_num)
{
- struct bio *bio;
struct btrfs_device *dev;
+ struct bio_vec bvec;
+ struct bio bio;
u64 map_length = 0;
u64 sector;
struct btrfs_io_context *bioc = NULL;
- int ret;
+ int ret = 0;
ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
BUG_ON(!mirror_num);
if (btrfs_repair_one_zone(fs_info, logical))
return 0;
- bio = btrfs_bio_alloc(1);
- bio->bi_iter.bi_size = 0;
map_length = length;
/*
*/
ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
&map_length, &bioc, 0);
- if (ret) {
- btrfs_bio_counter_dec(fs_info);
- bio_put(bio);
- return -EIO;
- }
+ if (ret)
+ goto out_counter_dec;
ASSERT(bioc->mirror_num == 1);
} else {
ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
&map_length, &bioc, mirror_num);
- if (ret) {
- btrfs_bio_counter_dec(fs_info);
- bio_put(bio);
- return -EIO;
- }
+ if (ret)
+ goto out_counter_dec;
BUG_ON(mirror_num != bioc->mirror_num);
}
sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
- bio->bi_iter.bi_sector = sector;
dev = bioc->stripes[bioc->mirror_num - 1].dev;
btrfs_put_bioc(bioc);
+
if (!dev || !dev->bdev ||
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
- btrfs_bio_counter_dec(fs_info);
- bio_put(bio);
- return -EIO;
+ ret = -EIO;
+ goto out_counter_dec;
}
- bio_set_dev(bio, dev->bdev);
- bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
- bio_add_page(bio, page, length, pg_offset);
- if (btrfsic_submit_bio_wait(bio)) {
+ bio_init(&bio, dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC);
+ bio.bi_iter.bi_sector = sector;
+ __bio_add_page(&bio, page, length, pg_offset);
+
+ btrfsic_check_bio(&bio);
+ ret = submit_bio_wait(&bio);
+ if (ret) {
/* try to remap that extent elsewhere? */
- btrfs_bio_counter_dec(fs_info);
- bio_put(bio);
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
- return -EIO;
+ goto out_bio_uninit;
}
btrfs_info_rl_in_rcu(fs_info,
"read error corrected: ino %llu off %llu (dev %s sector %llu)",
ino, start,
rcu_str_deref(dev->name), sector);
+ ret = 0;
+
+out_bio_uninit:
+ bio_uninit(&bio);
+out_counter_dec:
btrfs_bio_counter_dec(fs_info);
- bio_put(bio);
- return 0;
+ return ret;
}
int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num)
failrec->start = start;
failrec->len = sectorsize;
failrec->this_mirror = 0;
- failrec->bio_flags = 0;
+ failrec->compress_type = BTRFS_COMPRESS_NONE;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, failrec->len);
logical = em->block_start + logical;
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
logical = em->block_start;
- failrec->bio_flags = EXTENT_BIO_COMPRESSED;
- extent_set_compress_type(&failrec->bio_flags, em->compress_type);
+ failrec->compress_type = em->compress_type;
}
btrfs_debug(fs_info,
* will be handled by the endio on the repair_bio, so we can't return an
* error here.
*/
- submit_bio_hook(inode, repair_bio, failrec->this_mirror, failrec->bio_flags);
+ submit_bio_hook(inode, repair_bio, failrec->this_mirror, failrec->compress_type);
return BLK_STS_OK;
}
btrfs_page_set_error(fs_info, page, start, len);
}
- if (fs_info->sectorsize == PAGE_SIZE)
+ if (!btrfs_is_subpage(fs_info, page))
unlock_page(page);
else
btrfs_subpage_end_reader(fs_info, page, start, len);
}
-static blk_status_t submit_read_repair(struct inode *inode,
- struct bio *failed_bio, u32 bio_offset,
- struct page *page, unsigned int pgoff,
- u64 start, u64 end, int failed_mirror,
- unsigned int error_bitmap,
- submit_bio_hook_t *submit_bio_hook)
+static blk_status_t submit_data_read_repair(struct inode *inode,
+ struct bio *failed_bio,
+ u32 bio_offset, struct page *page,
+ unsigned int pgoff,
+ u64 start, u64 end,
+ int failed_mirror,
+ unsigned int error_bitmap)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
const u32 sectorsize = fs_info->sectorsize;
BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
+ /* This repair is only for data */
+ ASSERT(is_data_inode(inode));
+
/* We're here because we had some read errors or csum mismatch */
ASSERT(error_bitmap);
ret = btrfs_repair_one_sector(inode, failed_bio,
bio_offset + offset,
page, pgoff + offset, start + offset,
- failed_mirror, submit_bio_hook);
+ failed_mirror, btrfs_submit_data_bio);
if (!ret) {
/*
* We have submitted the read repair, the page release
static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
{
ASSERT(PageLocked(page));
- if (fs_info->sectorsize == PAGE_SIZE)
+ if (!btrfs_is_subpage(fs_info, page))
return;
ASSERT(PagePrivate(page));
}
/*
- * Find extent buffer for a givne bytenr.
+ * Find extent buffer for a given bytenr.
*
* This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
* in endio context.
* For regular sectorsize, we can use page->private to grab extent
* buffer
*/
- if (fs_info->sectorsize == PAGE_SIZE) {
+ if (fs_info->nodesize >= PAGE_SIZE) {
ASSERT(PagePrivate(page) && page->private);
return (struct extent_buffer *)page->private;
}
- /* For subpage case, we need to lookup buffer radix tree */
- rcu_read_lock();
- eb = radix_tree_lookup(&fs_info->buffer_radix,
- bytenr >> fs_info->sectorsize_bits);
- rcu_read_unlock();
+ /* For subpage case, we need to lookup extent buffer xarray */
+ eb = xa_load(&fs_info->extent_buffers,
+ bytenr >> fs_info->sectorsize_bits);
ASSERT(eb);
return eb;
}
goto readpage_ok;
/*
- * btrfs_submit_read_repair() will handle all the good
+ * submit_data_read_repair() will handle all the good
* and bad sectors, we just continue to the next bvec.
*/
- submit_read_repair(inode, bio, bio_offset, page,
- start - page_offset(page), start,
- end, mirror, error_bitmap,
- btrfs_submit_data_bio);
+ submit_data_read_repair(inode, bio, bio_offset, page,
+ start - page_offset(page),
+ start, end, mirror,
+ error_bitmap);
ASSERT(bio_offset + len > bio_offset);
bio_offset += len;
bio_put(bio);
}
+/**
+ * Populate every free slot in a provided array with pages.
+ *
+ * @nr_pages: number of pages to allocate
+ * @page_array: the array to fill with pages; any existing non-null entries in
+ * the array will be skipped
+ *
+ * Return: 0 if all pages were able to be allocated;
+ * -ENOMEM otherwise, and the caller is responsible for freeing all
+ * non-null page pointers in the array.
+ */
+int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
+{
+ unsigned int allocated;
+
+ for (allocated = 0; allocated < nr_pages;) {
+ unsigned int last = allocated;
+
+ allocated = alloc_pages_bulk_array(GFP_NOFS, nr_pages, page_array);
+
+ if (allocated == nr_pages)
+ return 0;
+
+ /*
+ * During this iteration, no page could be allocated, even
+ * though alloc_pages_bulk_array() falls back to alloc_page()
+ * if it could not bulk-allocate. So we must be out of memory.
+ */
+ if (allocated == last)
+ return -ENOMEM;
+
+ memalloc_retry_wait(GFP_NOFS);
+ }
+ return 0;
+}
+
/*
* Initialize the members up to but not including 'bio'. Use after allocating a
* new bio by bio_alloc_bioset as it does not initialize the bytes outside of
return bio;
}
-struct bio *btrfs_bio_clone(struct bio *bio)
+struct bio *btrfs_bio_clone(struct block_device *bdev, struct bio *bio)
{
struct btrfs_bio *bbio;
struct bio *new;
/* Bio allocation backed by a bioset does not fail */
- new = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOFS, &btrfs_bioset);
+ new = bio_alloc_clone(bdev, bio, GFP_NOFS, &btrfs_bioset);
bbio = btrfs_bio(new);
btrfs_bio_init(bbio);
bbio->iter = bio->bi_iter;
* a contiguous page to the previous one
* @size: portion of page that we want to write
* @pg_offset: starting offset in the page
- * @bio_flags: flags of the current bio to see if we can merge them
+ * @compress_type: compression type of the current bio to see if we can merge them
*
* Attempt to add a page to bio considering stripe alignment etc.
*
struct page *page,
u64 disk_bytenr, unsigned int size,
unsigned int pg_offset,
- unsigned long bio_flags)
+ enum btrfs_compression_type compress_type)
{
struct bio *bio = bio_ctrl->bio;
u32 bio_size = bio->bi_iter.bi_size;
ASSERT(bio);
/* The limit should be calculated when bio_ctrl->bio is allocated */
ASSERT(bio_ctrl->len_to_oe_boundary && bio_ctrl->len_to_stripe_boundary);
- if (bio_ctrl->bio_flags != bio_flags)
+ if (bio_ctrl->compress_type != compress_type)
return 0;
- if (bio_ctrl->bio_flags & EXTENT_BIO_COMPRESSED)
+ if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
contig = bio->bi_iter.bi_sector == sector;
else
contig = bio_end_sector(bio) == sector;
* The split happens for real compressed bio, which happens in
* btrfs_submit_compressed_read/write().
*/
- if (bio_ctrl->bio_flags & EXTENT_BIO_COMPRESSED) {
+ if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) {
bio_ctrl->len_to_oe_boundary = U32_MAX;
bio_ctrl->len_to_stripe_boundary = U32_MAX;
return 0;
unsigned int opf,
bio_end_io_t end_io_func,
u64 disk_bytenr, u32 offset, u64 file_offset,
- unsigned long bio_flags)
+ enum btrfs_compression_type compress_type)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct bio *bio;
* For compressed page range, its disk_bytenr is always @disk_bytenr
* passed in, no matter if we have added any range into previous bio.
*/
- if (bio_flags & EXTENT_BIO_COMPRESSED)
+ if (compress_type != BTRFS_COMPRESS_NONE)
bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
else
bio->bi_iter.bi_sector = (disk_bytenr + offset) >> SECTOR_SHIFT;
bio_ctrl->bio = bio;
- bio_ctrl->bio_flags = bio_flags;
+ bio_ctrl->compress_type = compress_type;
bio->bi_end_io = end_io_func;
bio->bi_private = &inode->io_tree;
bio->bi_opf = opf;
* @end_io_func: end_io callback for new bio
* @mirror_num: desired mirror to read/write
* @prev_bio_flags: flags of previous bio to see if we can merge the current one
- * @bio_flags: flags of the current bio to see if we can merge them
+ * @compress_type: compress type for current bio
*/
static int submit_extent_page(unsigned int opf,
struct writeback_control *wbc,
size_t size, unsigned long pg_offset,
bio_end_io_t end_io_func,
int mirror_num,
- unsigned long bio_flags,
+ enum btrfs_compression_type compress_type,
bool force_bio_submit)
{
int ret = 0;
ASSERT(pg_offset < PAGE_SIZE && size <= PAGE_SIZE &&
pg_offset + size <= PAGE_SIZE);
if (force_bio_submit && bio_ctrl->bio) {
- ret = submit_one_bio(bio_ctrl->bio, mirror_num, bio_ctrl->bio_flags);
+ submit_one_bio(bio_ctrl->bio, mirror_num, bio_ctrl->compress_type);
bio_ctrl->bio = NULL;
- if (ret < 0)
- return ret;
}
while (cur < pg_offset + size) {
ret = alloc_new_bio(inode, bio_ctrl, wbc, opf,
end_io_func, disk_bytenr, offset,
page_offset(page) + cur,
- bio_flags);
+ compress_type);
if (ret < 0)
return ret;
}
* We must go through btrfs_bio_add_page() to ensure each
* page range won't cross various boundaries.
*/
- if (bio_flags & EXTENT_BIO_COMPRESSED)
+ if (compress_type != BTRFS_COMPRESS_NONE)
added = btrfs_bio_add_page(bio_ctrl, page, disk_bytenr,
size - offset, pg_offset + offset,
- bio_flags);
+ compress_type);
else
added = btrfs_bio_add_page(bio_ctrl, page,
disk_bytenr + offset, size - offset,
- pg_offset + offset, bio_flags);
+ pg_offset + offset, compress_type);
/* Metadata page range should never be split */
if (!is_data_inode(&inode->vfs_inode))
if (added < size - offset) {
/* The bio should contain some page(s) */
ASSERT(bio_ctrl->bio->bi_iter.bi_size);
- ret = submit_one_bio(bio_ctrl->bio, mirror_num,
- bio_ctrl->bio_flags);
+ submit_one_bio(bio_ctrl->bio, mirror_num, bio_ctrl->compress_type);
bio_ctrl->bio = NULL;
- if (ret < 0)
- return ret;
}
cur += added;
}
if (page->mapping)
lockdep_assert_held(&page->mapping->private_lock);
- if (fs_info->sectorsize == PAGE_SIZE) {
+ if (fs_info->nodesize >= PAGE_SIZE) {
if (!PagePrivate(page))
attach_page_private(page, eb);
else
fs_info = btrfs_sb(page->mapping->host->i_sb);
- if (fs_info->sectorsize < PAGE_SIZE)
+ if (btrfs_is_subpage(fs_info, page))
return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA);
attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE);
return;
fs_info = btrfs_sb(page->mapping->host->i_sb);
- if (fs_info->sectorsize < PAGE_SIZE)
+ if (btrfs_is_subpage(fs_info, page))
return btrfs_detach_subpage(fs_info, page);
detach_page_private(page);
* XXX JDM: This needs looking at to ensure proper page locking
* return 0 on success, otherwise return error
*/
-int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
+static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
struct btrfs_bio_ctrl *bio_ctrl,
unsigned int read_flags, u64 *prev_em_start)
{
BUG_ON(extent_map_end(em) <= cur);
BUG_ON(end < cur);
- if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
- this_bio_flag |= EXTENT_BIO_COMPRESSED;
- extent_set_compress_type(&this_bio_flag,
- em->compress_type);
- }
+ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+ this_bio_flag = em->compress_type;
iosize = min(extent_map_end(em) - cur, end - cur + 1);
cur_end = min(extent_map_end(em) - 1, end);
iosize = ALIGN(iosize, blocksize);
- if (this_bio_flag & EXTENT_BIO_COMPRESSED)
+ if (this_bio_flag != BTRFS_COMPRESS_NONE)
disk_bytenr = em->block_start;
else
disk_bytenr = em->block_start + extent_offset;
this_bio_flag,
force_bio_submit);
if (ret) {
- unlock_extent(tree, cur, cur + iosize - 1);
- end_page_read(page, false, cur, iosize);
+ /*
+ * We have to unlock the remaining range, or the page
+ * will never be unlocked.
+ */
+ unlock_extent(tree, cur, end);
+ end_page_read(page, false, cur, end + 1 - cur);
goto out;
}
cur = cur + iosize;
return ret;
}
+int btrfs_read_folio(struct file *file, struct folio *folio)
+{
+ struct page *page = &folio->page;
+ struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
+ u64 start = page_offset(page);
+ u64 end = start + PAGE_SIZE - 1;
+ struct btrfs_bio_ctrl bio_ctrl = { 0 };
+ int ret;
+
+ btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
+
+ ret = btrfs_do_readpage(page, NULL, &bio_ctrl, 0, NULL);
+ /*
+ * If btrfs_do_readpage() failed we will want to submit the assembled
+ * bio to do the cleanup.
+ */
+ if (bio_ctrl.bio)
+ submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.compress_type);
+ return ret;
+}
+
static inline void contiguous_readpages(struct page *pages[], int nr_pages,
u64 start, u64 end,
struct extent_map **em_cached,
}
}
-static void update_nr_written(struct writeback_control *wbc,
- unsigned long nr_written)
-{
- wbc->nr_to_write -= nr_written;
-}
-
/*
* helper for __extent_writepage, doing all of the delayed allocation setup.
*
* For regular sector size == page size case, since one page only
* contains one sector, we return the page offset directly.
*/
- if (fs_info->sectorsize == PAGE_SIZE) {
+ if (!btrfs_is_subpage(fs_info, page)) {
*start = page_offset(page);
*end = page_offset(page) + PAGE_SIZE;
return;
u64 extent_offset;
u64 block_start;
struct extent_map *em;
+ int saved_ret = 0;
int ret = 0;
int nr = 0;
u32 opf = REQ_OP_WRITE;
const unsigned int write_flags = wbc_to_write_flags(wbc);
+ bool has_error = false;
bool compressed;
ret = btrfs_writepage_cow_fixup(page);
* we don't want to touch the inode after unlocking the page,
* so we update the mapping writeback index now
*/
- update_nr_written(wbc, 1);
+ wbc->nr_to_write--;
while (cur <= end) {
u64 disk_bytenr;
if (IS_ERR(em)) {
btrfs_page_set_error(fs_info, page, cur, end - cur + 1);
ret = PTR_ERR_OR_ZERO(em);
+ has_error = true;
+ if (!saved_ret)
+ saved_ret = ret;
break;
}
end_bio_extent_writepage,
0, 0, false);
if (ret) {
+ has_error = true;
+ if (!saved_ret)
+ saved_ret = ret;
+
btrfs_page_set_error(fs_info, page, cur, iosize);
if (PageWriteback(page))
btrfs_page_clear_writeback(fs_info, page, cur,
* If we finish without problem, we should not only clear page dirty,
* but also empty subpage dirty bits
*/
- if (!ret)
+ if (!has_error)
btrfs_page_assert_not_dirty(fs_info, page);
+ else
+ ret = saved_ret;
*nr_ret = nr;
return ret;
}
static void end_extent_buffer_writeback(struct extent_buffer *eb)
{
- if (test_bit(EXTENT_BUFFER_ZONE_FINISH, &eb->bflags))
- btrfs_zone_finish_endio(eb->fs_info, eb->start, eb->len);
-
clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
smp_mb__after_atomic();
wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
struct extent_page_data *epd)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
- int i, num_pages, failed_page_nr;
+ int i, num_pages;
int flush = 0;
int ret = 0;
if (!btrfs_try_tree_write_lock(eb)) {
- ret = flush_write_bio(epd);
- if (ret < 0)
- return ret;
+ flush_write_bio(epd);
flush = 1;
btrfs_tree_lock(eb);
}
if (!epd->sync_io)
return 0;
if (!flush) {
- ret = flush_write_bio(epd);
- if (ret < 0)
- return ret;
+ flush_write_bio(epd);
flush = 1;
}
while (1) {
* Subpage metadata doesn't use page locking at all, so we can skip
* the page locking.
*/
- if (!ret || fs_info->sectorsize < PAGE_SIZE)
+ if (!ret || fs_info->nodesize < PAGE_SIZE)
return ret;
num_pages = num_extent_pages(eb);
if (!trylock_page(p)) {
if (!flush) {
- int err;
-
- err = flush_write_bio(epd);
- if (err < 0) {
- ret = err;
- failed_page_nr = i;
- goto err_unlock;
- }
+ flush_write_bio(epd);
flush = 1;
}
lock_page(p);
}
}
- return ret;
-err_unlock:
- /* Unlock already locked pages */
- for (i = 0; i < failed_page_nr; i++)
- unlock_page(eb->pages[i]);
- /*
- * Clear EXTENT_BUFFER_WRITEBACK and wake up anyone waiting on it.
- * Also set back EXTENT_BUFFER_DIRTY so future attempts to this eb can
- * be made and undo everything done before.
- */
- btrfs_tree_lock(eb);
- spin_lock(&eb->refs_lock);
- set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
- end_extent_buffer_writeback(eb);
- spin_unlock(&eb->refs_lock);
- percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, eb->len,
- fs_info->dirty_metadata_batch);
- btrfs_clear_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
- btrfs_tree_unlock(eb);
return ret;
}
struct extent_buffer *eb;
rcu_read_lock();
- eb = radix_tree_lookup(&fs_info->buffer_radix,
- start >> fs_info->sectorsize_bits);
+ eb = xa_load(&fs_info->extent_buffers,
+ start >> fs_info->sectorsize_bits);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
return eb;
struct bvec_iter_all iter_all;
fs_info = btrfs_sb(bio_first_page_all(bio)->mapping->host->i_sb);
- ASSERT(fs_info->sectorsize < PAGE_SIZE);
+ ASSERT(fs_info->nodesize < PAGE_SIZE);
ASSERT(!bio_flagged(bio, BIO_CLONED));
bio_for_each_segment_all(bvec, bio, iter_all) {
* dirty anymore, we have submitted a page. Update nr_written in wbc.
*/
if (no_dirty_ebs)
- update_nr_written(wbc, 1);
+ wbc->nr_to_write--;
return ret;
}
break;
}
disk_bytenr += PAGE_SIZE;
- update_nr_written(wbc, 1);
+ wbc->nr_to_write--;
unlock_page(p);
}
if (!PagePrivate(page))
return 0;
- if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE)
+ if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
return submit_eb_subpage(page, wbc, epd);
spin_lock(&mapping->private_lock);
/*
* Implies write in zoned mode. Mark the last eb in a block group.
*/
- if (cache->seq_zone && eb->start + eb->len == cache->zone_capacity)
- set_bit(EXTENT_BUFFER_ZONE_FINISH, &eb->bflags);
+ btrfs_schedule_zone_finish_bg(cache, eb);
btrfs_put_block_group(cache);
}
ret = write_one_eb(eb, wbc, epd);
* if the fs already has error.
*/
if (!BTRFS_FS_ERROR(fs_info)) {
- ret = flush_write_bio(&epd);
+ flush_write_bio(&epd);
} else {
ret = -EROFS;
end_write_bio(&epd, ret);
}
out:
btrfs_zoned_meta_io_unlock(fs_info);
+ /*
+ * We can get ret > 0 from submit_extent_page() indicating how many ebs
+ * were submitted. Reset it to 0 to avoid false alerts for the caller.
+ */
+ if (ret > 0)
+ ret = 0;
return ret;
}
* tmpfs file mapping
*/
if (!trylock_page(page)) {
- ret = flush_write_bio(epd);
- BUG_ON(ret < 0);
+ flush_write_bio(epd);
lock_page(page);
}
}
if (wbc->sync_mode != WB_SYNC_NONE) {
- if (PageWriteback(page)) {
- ret = flush_write_bio(epd);
- BUG_ON(ret < 0);
- }
+ if (PageWriteback(page))
+ flush_write_bio(epd);
wait_on_page_writeback(page);
}
* page in our current bio, and thus deadlock, so flush the
* write bio here.
*/
- ret = flush_write_bio(epd);
- if (!ret)
- goto retry;
+ flush_write_bio(epd);
+ goto retry;
}
if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
return ret;
}
- ret = flush_write_bio(&epd);
- ASSERT(ret <= 0);
+ flush_write_bio(&epd);
return ret;
}
}
if (!found_error)
- ret = flush_write_bio(&epd);
+ flush_write_bio(&epd);
else
end_write_bio(&epd, ret);
end_write_bio(&epd, ret);
return ret;
}
- ret = flush_write_bio(&epd);
+ flush_write_bio(&epd);
return ret;
}
if (em_cached)
free_extent_map(em_cached);
- if (bio_ctrl.bio) {
- if (submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.bio_flags))
- return;
- }
+ if (bio_ctrl.bio)
+ submit_one_bio(bio_ctrl.bio, 0, bio_ctrl.compress_type);
}
/*
return;
}
- if (fs_info->sectorsize == PAGE_SIZE) {
+ if (fs_info->nodesize >= PAGE_SIZE) {
/*
* We do this since we'll remove the pages after we've
* removed the eb from the radix tree, so we could race
struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
{
int i;
- struct page *p;
struct extent_buffer *new;
int num_pages = num_extent_pages(src);
+ int ret;
new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
if (new == NULL)
*/
set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
+ memset(new->pages, 0, sizeof(*new->pages) * num_pages);
+ ret = btrfs_alloc_page_array(num_pages, new->pages);
+ if (ret) {
+ btrfs_release_extent_buffer(new);
+ return NULL;
+ }
+
for (i = 0; i < num_pages; i++) {
int ret;
+ struct page *p = new->pages[i];
- p = alloc_page(GFP_NOFS);
- if (!p) {
- btrfs_release_extent_buffer(new);
- return NULL;
- }
ret = attach_extent_buffer_page(new, p, NULL);
if (ret < 0) {
- put_page(p);
btrfs_release_extent_buffer(new);
return NULL;
}
WARN_ON(PageDirty(p));
- new->pages[i] = p;
copy_page(page_address(p), page_address(src->pages[i]));
}
set_extent_buffer_uptodate(new);
struct extent_buffer *eb;
int num_pages;
int i;
+ int ret;
eb = __alloc_extent_buffer(fs_info, start, len);
if (!eb)
return NULL;
num_pages = num_extent_pages(eb);
+ ret = btrfs_alloc_page_array(num_pages, eb->pages);
+ if (ret)
+ goto err;
+
for (i = 0; i < num_pages; i++) {
- int ret;
+ struct page *p = eb->pages[i];
- eb->pages[i] = alloc_page(GFP_NOFS);
- if (!eb->pages[i])
- goto err;
- ret = attach_extent_buffer_page(eb, eb->pages[i], NULL);
+ ret = attach_extent_buffer_page(eb, p, NULL);
if (ret < 0)
goto err;
}
+
set_extent_buffer_uptodate(eb);
btrfs_set_header_nritems(eb, 0);
set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
return eb;
err:
- for (; i > 0; i--) {
- detach_extent_buffer_page(eb, eb->pages[i - 1]);
- __free_page(eb->pages[i - 1]);
+ for (i = 0; i < num_pages; i++) {
+ if (eb->pages[i]) {
+ detach_extent_buffer_page(eb, eb->pages[i]);
+ __free_page(eb->pages[i]);
+ }
}
__free_extent_buffer(eb);
return NULL;
if (!eb)
return ERR_PTR(-ENOMEM);
eb->fs_info = fs_info;
-again:
- ret = radix_tree_preload(GFP_NOFS);
- if (ret) {
- exists = ERR_PTR(ret);
- goto free_eb;
- }
- spin_lock(&fs_info->buffer_lock);
- ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> fs_info->sectorsize_bits, eb);
- spin_unlock(&fs_info->buffer_lock);
- radix_tree_preload_end();
- if (ret == -EEXIST) {
- exists = find_extent_buffer(fs_info, start);
- if (exists)
+
+ do {
+ ret = xa_insert(&fs_info->extent_buffers,
+ start >> fs_info->sectorsize_bits,
+ eb, GFP_NOFS);
+ if (ret == -ENOMEM) {
+ exists = ERR_PTR(ret);
goto free_eb;
- else
- goto again;
- }
+ }
+ if (ret == -EBUSY) {
+ exists = find_extent_buffer(fs_info, start);
+ if (exists)
+ goto free_eb;
+ }
+ } while (ret);
+
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
* don't try to insert two ebs for the same bytenr. So here we always
* return NULL and just continue.
*/
- if (fs_info->sectorsize < PAGE_SIZE)
+ if (fs_info->nodesize < PAGE_SIZE)
return NULL;
/* Page not yet attached to an extent buffer */
return NULL;
}
+static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
+{
+ if (!IS_ALIGNED(start, fs_info->sectorsize)) {
+ btrfs_err(fs_info, "bad tree block start %llu", start);
+ return -EINVAL;
+ }
+
+ if (fs_info->nodesize < PAGE_SIZE &&
+ offset_in_page(start) + fs_info->nodesize > PAGE_SIZE) {
+ btrfs_err(fs_info,
+ "tree block crosses page boundary, start %llu nodesize %u",
+ start, fs_info->nodesize);
+ return -EINVAL;
+ }
+ if (fs_info->nodesize >= PAGE_SIZE &&
+ !IS_ALIGNED(start, PAGE_SIZE)) {
+ btrfs_err(fs_info,
+ "tree block is not page aligned, start %llu nodesize %u",
+ start, fs_info->nodesize);
+ return -EINVAL;
+ }
+ return 0;
+}
+
struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, u64 owner_root, int level)
{
int uptodate = 1;
int ret;
- if (!IS_ALIGNED(start, fs_info->sectorsize)) {
- btrfs_err(fs_info, "bad tree block start %llu", start);
+ if (check_eb_alignment(fs_info, start))
return ERR_PTR(-EINVAL);
- }
#if BITS_PER_LONG == 32
if (start >= MAX_LFS_FILESIZE) {
btrfs_warn_32bit_limit(fs_info);
#endif
- if (fs_info->sectorsize < PAGE_SIZE &&
- offset_in_page(start) + len > PAGE_SIZE) {
- btrfs_err(fs_info,
- "tree block crosses page boundary, start %llu nodesize %lu",
- start, len);
- return ERR_PTR(-EINVAL);
- }
-
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
* page, but it may change in the future for 16K page size
* support, so we still preallocate the memory in the loop.
*/
- if (fs_info->sectorsize < PAGE_SIZE) {
+ if (fs_info->nodesize < PAGE_SIZE) {
prealloc = btrfs_alloc_subpage(fs_info, BTRFS_SUBPAGE_METADATA);
if (IS_ERR(prealloc)) {
ret = PTR_ERR(prealloc);
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-again:
- ret = radix_tree_preload(GFP_NOFS);
- if (ret) {
- exists = ERR_PTR(ret);
- goto free_eb;
- }
-
- spin_lock(&fs_info->buffer_lock);
- ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> fs_info->sectorsize_bits, eb);
- spin_unlock(&fs_info->buffer_lock);
- radix_tree_preload_end();
- if (ret == -EEXIST) {
- exists = find_extent_buffer(fs_info, start);
- if (exists)
+
+ do {
+ ret = xa_insert(&fs_info->extent_buffers,
+ start >> fs_info->sectorsize_bits,
+ eb, GFP_NOFS);
+ if (ret == -ENOMEM) {
+ exists = ERR_PTR(ret);
goto free_eb;
- else
- goto again;
- }
+ }
+ if (ret == -EBUSY) {
+ exists = find_extent_buffer(fs_info, start);
+ if (exists)
+ goto free_eb;
+ }
+ } while (ret);
+
/* add one reference for the tree */
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
spin_unlock(&eb->refs_lock);
- spin_lock(&fs_info->buffer_lock);
- radix_tree_delete(&fs_info->buffer_radix,
- eb->start >> fs_info->sectorsize_bits);
- spin_unlock(&fs_info->buffer_lock);
+ xa_erase(&fs_info->extent_buffers,
+ eb->start >> fs_info->sectorsize_bits);
} else {
spin_unlock(&eb->refs_lock);
}
int num_pages;
struct page *page;
- if (eb->fs_info->sectorsize < PAGE_SIZE)
+ if (eb->fs_info->nodesize < PAGE_SIZE)
return clear_subpage_extent_buffer_dirty(eb);
num_pages = num_extent_pages(eb);
WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
if (!was_dirty) {
- bool subpage = eb->fs_info->sectorsize < PAGE_SIZE;
+ bool subpage = eb->fs_info->nodesize < PAGE_SIZE;
/*
* For subpage case, we can have other extent buffers in the
num_pages = num_extent_pages(eb);
for (i = 0; i < num_pages; i++) {
page = eb->pages[i];
- if (page)
- btrfs_page_clear_uptodate(fs_info, page,
- eb->start, eb->len);
+ if (!page)
+ continue;
+
+ /*
+ * This is special handling for metadata subpage, as regular
+ * btrfs_is_subpage() can not handle cloned/dummy metadata.
+ */
+ if (fs_info->nodesize >= PAGE_SIZE)
+ ClearPageUptodate(page);
+ else
+ btrfs_subpage_clear_uptodate(fs_info, page, eb->start,
+ eb->len);
}
}
num_pages = num_extent_pages(eb);
for (i = 0; i < num_pages; i++) {
page = eb->pages[i];
- btrfs_page_set_uptodate(fs_info, page, eb->start, eb->len);
+
+ /*
+ * This is special handling for metadata subpage, as regular
+ * btrfs_is_subpage() can not handle cloned/dummy metadata.
+ */
+ if (fs_info->nodesize >= PAGE_SIZE)
+ SetPageUptodate(page);
+ else
+ btrfs_subpage_set_uptodate(fs_info, page, eb->start,
+ eb->len);
}
}
atomic_dec(&eb->io_pages);
}
if (bio_ctrl.bio) {
- int tmp;
-
- tmp = submit_one_bio(bio_ctrl.bio, mirror_num, 0);
+ submit_one_bio(bio_ctrl.bio, mirror_num, 0);
bio_ctrl.bio = NULL;
- if (tmp < 0)
- return tmp;
}
if (ret || wait != WAIT_COMPLETE)
return ret;
if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)))
return -EIO;
- if (eb->fs_info->sectorsize < PAGE_SIZE)
+ if (eb->fs_info->nodesize < PAGE_SIZE)
return read_extent_buffer_subpage(eb, wait, mirror_num);
num_pages = num_extent_pages(eb);
}
if (bio_ctrl.bio) {
- err = submit_one_bio(bio_ctrl.bio, mirror_num, bio_ctrl.bio_flags);
+ submit_one_bio(bio_ctrl.bio, mirror_num, bio_ctrl.compress_type);
bio_ctrl.bio = NULL;
- if (err)
- return err;
}
if (ret || wait != WAIT_COMPLETE)
* would have !PageUptodate && !PageError, as we clear PageError before
* reading.
*/
- if (fs_info->sectorsize < PAGE_SIZE) {
+ if (fs_info->nodesize < PAGE_SIZE) {
bool uptodate, error;
uptodate = btrfs_subpage_test_uptodate(fs_info, page,
ASSERT(dst->len == src->len);
- if (dst->fs_info->sectorsize == PAGE_SIZE) {
+ if (dst->fs_info->nodesize >= PAGE_SIZE) {
num_pages = num_extent_pages(dst);
for (i = 0; i < num_pages; i++)
copy_page(page_address(dst->pages[i]),
size_t src_offset = get_eb_offset_in_page(src, 0);
size_t dst_offset = get_eb_offset_in_page(dst, 0);
- ASSERT(src->fs_info->sectorsize < PAGE_SIZE);
+ ASSERT(src->fs_info->nodesize < PAGE_SIZE);
memcpy(page_address(dst->pages[0]) + dst_offset,
page_address(src->pages[0]) + src_offset,
src->len);
}
}
-#define GANG_LOOKUP_SIZE 16
static struct extent_buffer *get_next_extent_buffer(
struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
{
- struct extent_buffer *gang[GANG_LOOKUP_SIZE];
- struct extent_buffer *found = NULL;
+ struct extent_buffer *eb;
+ unsigned long index;
u64 page_start = page_offset(page);
- u64 cur = page_start;
ASSERT(in_range(bytenr, page_start, PAGE_SIZE));
lockdep_assert_held(&fs_info->buffer_lock);
- while (cur < page_start + PAGE_SIZE) {
- int ret;
- int i;
-
- ret = radix_tree_gang_lookup(&fs_info->buffer_radix,
- (void **)gang, cur >> fs_info->sectorsize_bits,
- min_t(unsigned int, GANG_LOOKUP_SIZE,
- PAGE_SIZE / fs_info->nodesize));
- if (ret == 0)
- goto out;
- for (i = 0; i < ret; i++) {
- /* Already beyond page end */
- if (gang[i]->start >= page_start + PAGE_SIZE)
- goto out;
- /* Found one */
- if (gang[i]->start >= bytenr) {
- found = gang[i];
- goto out;
- }
- }
- cur = gang[ret - 1]->start + gang[ret - 1]->len;
+ xa_for_each_start(&fs_info->extent_buffers, index, eb,
+ page_start >> fs_info->sectorsize_bits) {
+ if (in_range(eb->start, page_start, PAGE_SIZE))
+ return eb;
+ else if (eb->start >= page_start + PAGE_SIZE)
+ /* Already beyond page end */
+ return NULL;
}
-out:
- return found;
+ return NULL;
}
static int try_release_subpage_extent_buffer(struct page *page)
{
struct extent_buffer *eb;
- if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE)
+ if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
return try_release_subpage_extent_buffer(page);
/*