// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/page-io.c * * This contains the new page_io functions for ext4 * * Written by Theodore Ts'o, 2010.
*/
/* * Print an buffer I/O error compatible with the fs/buffer.c. This * provides compatibility with dmesg scrapers that look for a specific * buffer I/O error message. We really need a unified error reporting * structure to userspace ala Digital Unix's uerf system, but it's * probably not going to happen in my lifetime, due to LKML politics...
*/ staticvoid buffer_io_error(struct buffer_head *bh)
{
printk_ratelimited(KERN_ERR "Buffer I/O error on device %pg, logical block %llu\n",
bh->b_bdev,
(unsignedlonglong)bh->b_blocknr);
}
staticvoid ext4_finish_bio(struct bio *bio)
{ struct folio_iter fi;
if (fscrypt_is_bounce_folio(folio)) {
io_folio = folio;
folio = fscrypt_pagecache_folio(folio);
}
if (bio->bi_status) { int err = blk_status_to_errno(bio->bi_status);
mapping_set_error(folio->mapping, err);
}
bh = head = folio_buffers(folio); /* * We check all buffers in the folio under b_uptodate_lock * to avoid races with other end io clearing async_write flags
*/
spin_lock_irqsave(&head->b_uptodate_lock, flags); do { if (bh_offset(bh) < bio_start ||
bh_offset(bh) + bh->b_size > bio_end) { if (buffer_async_write(bh))
under_io++; continue;
}
clear_buffer_async_write(bh); if (bio->bi_status) {
set_buffer_write_io_error(bh);
buffer_io_error(bh);
}
} while ((bh = bh->b_this_page) != head);
spin_unlock_irqrestore(&head->b_uptodate_lock, flags); if (!under_io) {
fscrypt_free_bounce_page(&io_folio->page);
folio_end_writeback(folio);
}
}
}
staticvoid ext4_release_io_end(ext4_io_end_t *io_end)
{ struct bio *bio, *next_bio;
for (bio = io_end->bio; bio; bio = next_bio) {
next_bio = bio->bi_private;
ext4_finish_bio(bio);
bio_put(bio);
}
ext4_free_io_end_vec(io_end);
kmem_cache_free(io_end_cachep, io_end);
}
/* * On successful IO, check a range of space and convert unwritten extents to * written. On IO failure, check if journal abort is needed. Note that * we are protected from truncate touching same part of extent tree by the * fact that truncate code waits for all DIO to finish (thus exclusion from * direct IO is achieved) and also waits for PageWriteback bits. Thus we * cannot get to ext4_ext_truncate() before all IOs overlapping that range are * completed (happens from ext4_free_ioend()).
*/ staticint ext4_end_io_end(ext4_io_end_t *io_end)
{ struct inode *inode = io_end->inode;
handle_t *handle = io_end->handle; struct super_block *sb = inode->i_sb; int ret = 0;
/* * Do not convert the unwritten extents if data writeback fails, * or stale data may be exposed.
*/
io_end->handle = NULL; /* Following call will use up the handle */ if (unlikely(io_end->flag & EXT4_IO_END_FAILED)) {
ret = -EIO; if (handle)
jbd2_journal_free_reserved(handle);
if (test_opt(sb, DATA_ERR_ABORT))
jbd2_journal_abort(EXT4_SB(sb)->s_journal, ret);
} else {
ret = ext4_convert_unwritten_io_end_vec(handle, io_end);
} if (ret < 0 && !ext4_emergency_state(sb) &&
io_end->flag & EXT4_IO_END_UNWRITTEN) {
ext4_msg(sb, KERN_EMERG, "failed to convert unwritten extents to written " "extents -- potential data loss! " "(inode %lu, error %d)", inode->i_ino, ret);
}
err = ext4_end_io_end(io_end); if (unlikely(!ret && err))
ret = err;
} return ret;
}
/* * Used to convert unwritten extents to written extents upon IO completion, * or used to abort the journal upon IO errors.
*/ void ext4_end_io_rsv_work(struct work_struct *work)
{ struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
i_rsv_conversion_work);
ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list);
}
void ext4_put_io_end_defer(ext4_io_end_t *io_end)
{ if (refcount_dec_and_test(&io_end->count)) { if (ext4_io_end_defer_completion(io_end)) return ext4_add_complete_io(io_end);
ext4_release_io_end(io_end);
}
}
int ext4_put_io_end(ext4_io_end_t *io_end)
{ if (refcount_dec_and_test(&io_end->count)) { if (ext4_io_end_defer_completion(io_end)) return ext4_end_io_end(io_end);
if (ext4_io_end_defer_completion(io_end)) { /* * Link bio into list hanging from io_end. We have to do it * atomically as bio completions can be racing against each * other.
*/
bio->bi_private = xchg(&io_end->bio, bio);
ext4_put_io_end_defer(io_end);
} else { /* * Drop io_end reference early. Inode can get freed once * we finish the bio.
*/
ext4_put_io_end_defer(io_end);
ext4_finish_bio(bio);
bio_put(bio);
}
}
void ext4_io_submit(struct ext4_io_submit *io)
{ struct bio *bio = io->io_bio;
if (bio) { if (io->io_wbc->sync_mode == WB_SYNC_ALL)
io->io_bio->bi_opf |= REQ_SYNC;
submit_bio(io->io_bio);
}
io->io_bio = NULL;
}
/* * bio_alloc will _always_ be able to allocate a bio if * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset().
*/
bio = bio_alloc(bh->b_bdev, BIO_MAX_VECS, REQ_OP_WRITE, GFP_NOIO);
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_end_io = ext4_end_bio;
bio->bi_private = ext4_get_io_end(io->io_end);
io->io_bio = bio;
io->io_next_block = bh->b_blocknr;
wbc_init_bio(io->io_wbc, bio);
}
/* * Comments copied from block_write_full_folio: * * The folio straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file."
*/ if (len < folio_size(folio))
folio_zero_segment(folio, len, folio_size(folio)); /* * In the first loop we prepare and mark buffers to submit. We have to * mark all buffers in the folio before submitting so that * folio_end_writeback() cannot be called from ext4_end_bio() when IO * on the first buffer finishes and we are still working on submitting * the second buffer.
*/
bh = head = folio_buffers(folio); do {
block_start = bh_offset(bh); if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh); continue;
} if (!buffer_dirty(bh) || buffer_delay(bh) ||
!buffer_mapped(bh) || buffer_unwritten(bh)) { /* A hole? We can safely clear the dirty bit */ if (!buffer_mapped(bh))
clear_buffer_dirty(bh); /* * Keeping dirty some buffer we cannot write? Make sure * to redirty the folio and keep TOWRITE tag so that * racing WB_SYNC_ALL writeback does not skip the folio. * This happens e.g. when doing writeout for * transaction commit or when journalled data is not * yet committed.
*/ if (buffer_dirty(bh) ||
(buffer_jbd(bh) && buffer_jbddirty(bh))) { if (!folio_test_dirty(folio))
folio_redirty_for_writepage(wbc, folio);
keep_towrite = true;
} continue;
} if (buffer_new(bh))
clear_buffer_new(bh);
set_buffer_async_write(bh);
clear_buffer_dirty(bh);
nr_to_submit++;
} while ((bh = bh->b_this_page) != head);
/* Nothing to submit? Just unlock the folio... */ if (!nr_to_submit) return 0;
bh = head = folio_buffers(folio);
/* * If any blocks are being written to an encrypted file, encrypt them * into a bounce page. For simplicity, just encrypt until the last * block which might be needed. This may cause some unneeded blocks * (e.g. holes) to be unnecessarily encrypted, but this is rare and * can't happen in the common case of blocksize == PAGE_SIZE.
*/ if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
gfp_t gfp_flags = GFP_NOFS; unsignedint enc_bytes = round_up(len, i_blocksize(inode)); struct page *bounce_page;
/* * Since bounce page allocation uses a mempool, we can only use * a waiting mask (i.e. request guaranteed allocation) on the * first page of the bio. Otherwise it can deadlock.
*/ if (io->io_bio)
gfp_flags = GFP_NOWAIT;
retry_encrypt:
bounce_page = fscrypt_encrypt_pagecache_blocks(folio,
enc_bytes, 0, gfp_flags); if (IS_ERR(bounce_page)) {
ret = PTR_ERR(bounce_page); if (ret == -ENOMEM &&
(io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
gfp_t new_gfp_flags = GFP_NOFS; if (io->io_bio)
ext4_io_submit(io); else
new_gfp_flags |= __GFP_NOFAIL;
memalloc_retry_wait(gfp_flags);
gfp_flags = new_gfp_flags; goto retry_encrypt;
}
printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret);
folio_redirty_for_writepage(wbc, folio); do { if (buffer_async_write(bh)) {
clear_buffer_async_write(bh);
set_buffer_dirty(bh);
}
bh = bh->b_this_page;
} while (bh != head);
/* Now submit buffers to write */ do { if (!buffer_async_write(bh)) continue;
io_submit_add_bh(io, inode, folio, io_folio, bh);
} while ((bh = bh->b_this_page) != head);
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.