diff options
Diffstat (limited to 'fs/iomap/buffered-io.c')
| -rw-r--r-- | fs/iomap/buffered-io.c | 2683 |
1 files changed, 1492 insertions, 1191 deletions
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index bcfc288dba3f..e5c1ca440d93 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1,403 +1,613 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. - * Copyright (C) 2016-2019 Christoph Hellwig. + * Copyright (C) 2016-2023 Christoph Hellwig. */ -#include <linux/module.h> -#include <linux/compiler.h> -#include <linux/fs.h> #include <linux/iomap.h> -#include <linux/pagemap.h> -#include <linux/uio.h> #include <linux/buffer_head.h> -#include <linux/dax.h> #include <linux/writeback.h> -#include <linux/list_sort.h> #include <linux/swap.h> -#include <linux/bio.h> -#include <linux/sched/signal.h> #include <linux/migrate.h> +#include "internal.h" #include "trace.h" #include "../internal.h" /* - * Structure allocated for each page when block size < PAGE_SIZE to track - * sub-page uptodate status and I/O completions. + * Structure allocated for each folio to track per-block uptodate, dirty state + * and I/O completions. */ -struct iomap_page { - atomic_t read_count; - atomic_t write_count; - spinlock_t uptodate_lock; - DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); +struct iomap_folio_state { + spinlock_t state_lock; + unsigned int read_bytes_pending; + atomic_t write_bytes_pending; + + /* + * Each block has two bits in this bitmap: + * Bits [0..blocks_per_folio) has the uptodate status. + * Bits [b_p_f...(2*b_p_f)) has the dirty status. + */ + unsigned long state[]; }; -static inline struct iomap_page *to_iomap_page(struct page *page) +static inline bool ifs_is_fully_uptodate(struct folio *folio, + struct iomap_folio_state *ifs) { - if (page_has_private(page)) - return (struct iomap_page *)page_private(page); - return NULL; + struct inode *inode = folio->mapping->host; + + return bitmap_full(ifs->state, i_blocks_per_folio(inode, folio)); } -static struct bio_set iomap_ioend_bioset; +/* + * Find the next uptodate block in the folio. end_blk is inclusive. + * If no uptodate block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_uptodate_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) +{ + struct iomap_folio_state *ifs = folio->private; + + return find_next_bit(ifs->state, end_blk + 1, start_blk); +} -static struct iomap_page * -iomap_page_create(struct inode *inode, struct page *page) +/* + * Find the next non-uptodate block in the folio. end_blk is inclusive. + * If no non-uptodate block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_nonuptodate_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) +{ + struct iomap_folio_state *ifs = folio->private; + + return find_next_zero_bit(ifs->state, end_blk + 1, start_blk); +} + +static bool ifs_set_range_uptodate(struct folio *folio, + struct iomap_folio_state *ifs, size_t off, size_t len) { - struct iomap_page *iop = to_iomap_page(page); + struct inode *inode = folio->mapping->host; + unsigned int first_blk = off >> inode->i_blkbits; + unsigned int last_blk = (off + len - 1) >> inode->i_blkbits; + unsigned int nr_blks = last_blk - first_blk + 1; - if (iop || i_blocksize(inode) == PAGE_SIZE) - return iop; + bitmap_set(ifs->state, first_blk, nr_blks); + return ifs_is_fully_uptodate(folio, ifs); +} + +static void iomap_set_range_uptodate(struct folio *folio, size_t off, + size_t len) +{ + struct iomap_folio_state *ifs = folio->private; + unsigned long flags; + bool uptodate = true; + + if (folio_test_uptodate(folio)) + return; + + if (ifs) { + spin_lock_irqsave(&ifs->state_lock, flags); + uptodate = ifs_set_range_uptodate(folio, ifs, off, len); + spin_unlock_irqrestore(&ifs->state_lock, flags); + } + + if (uptodate) + folio_mark_uptodate(folio); +} + +/* + * Find the next dirty block in the folio. end_blk is inclusive. + * If no dirty block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_dirty_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) +{ + struct iomap_folio_state *ifs = folio->private; + struct inode *inode = folio->mapping->host; + unsigned int blks = i_blocks_per_folio(inode, folio); + + return find_next_bit(ifs->state, blks + end_blk + 1, + blks + start_blk) - blks; +} + +/* + * Find the next clean block in the folio. end_blk is inclusive. + * If no clean block is found, this will return end_blk + 1. + */ +static unsigned ifs_next_clean_block(struct folio *folio, + unsigned start_blk, unsigned end_blk) +{ + struct iomap_folio_state *ifs = folio->private; + struct inode *inode = folio->mapping->host; + unsigned int blks = i_blocks_per_folio(inode, folio); - iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL); - atomic_set(&iop->read_count, 0); - atomic_set(&iop->write_count, 0); - spin_lock_init(&iop->uptodate_lock); - bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + return find_next_zero_bit(ifs->state, blks + end_blk + 1, + blks + start_blk) - blks; +} + +static unsigned ifs_find_dirty_range(struct folio *folio, + struct iomap_folio_state *ifs, u64 *range_start, u64 range_end) +{ + struct inode *inode = folio->mapping->host; + unsigned start_blk = + offset_in_folio(folio, *range_start) >> inode->i_blkbits; + unsigned end_blk = min_not_zero( + offset_in_folio(folio, range_end) >> inode->i_blkbits, + i_blocks_per_folio(inode, folio)) - 1; + unsigned nblks; + + start_blk = ifs_next_dirty_block(folio, start_blk, end_blk); + if (start_blk > end_blk) + return 0; + if (start_blk == end_blk) + nblks = 1; + else + nblks = ifs_next_clean_block(folio, start_blk + 1, end_blk) - + start_blk; + + *range_start = folio_pos(folio) + (start_blk << inode->i_blkbits); + return nblks << inode->i_blkbits; +} + +static unsigned iomap_find_dirty_range(struct folio *folio, u64 *range_start, + u64 range_end) +{ + struct iomap_folio_state *ifs = folio->private; + + if (*range_start >= range_end) + return 0; + + if (ifs) + return ifs_find_dirty_range(folio, ifs, range_start, range_end); + return range_end - *range_start; +} + +static void ifs_clear_range_dirty(struct folio *folio, + struct iomap_folio_state *ifs, size_t off, size_t len) +{ + struct inode *inode = folio->mapping->host; + unsigned int blks_per_folio = i_blocks_per_folio(inode, folio); + unsigned int first_blk = (off >> inode->i_blkbits); + unsigned int last_blk = (off + len - 1) >> inode->i_blkbits; + unsigned int nr_blks = last_blk - first_blk + 1; + unsigned long flags; + + spin_lock_irqsave(&ifs->state_lock, flags); + bitmap_clear(ifs->state, first_blk + blks_per_folio, nr_blks); + spin_unlock_irqrestore(&ifs->state_lock, flags); +} + +static void iomap_clear_range_dirty(struct folio *folio, size_t off, size_t len) +{ + struct iomap_folio_state *ifs = folio->private; + + if (ifs) + ifs_clear_range_dirty(folio, ifs, off, len); +} + +static void ifs_set_range_dirty(struct folio *folio, + struct iomap_folio_state *ifs, size_t off, size_t len) +{ + struct inode *inode = folio->mapping->host; + unsigned int blks_per_folio = i_blocks_per_folio(inode, folio); + unsigned int first_blk = (off >> inode->i_blkbits); + unsigned int last_blk = (off + len - 1) >> inode->i_blkbits; + unsigned int nr_blks = last_blk - first_blk + 1; + unsigned long flags; + + spin_lock_irqsave(&ifs->state_lock, flags); + bitmap_set(ifs->state, first_blk + blks_per_folio, nr_blks); + spin_unlock_irqrestore(&ifs->state_lock, flags); +} + +static void iomap_set_range_dirty(struct folio *folio, size_t off, size_t len) +{ + struct iomap_folio_state *ifs = folio->private; + + if (ifs) + ifs_set_range_dirty(folio, ifs, off, len); +} + +static struct iomap_folio_state *ifs_alloc(struct inode *inode, + struct folio *folio, unsigned int flags) +{ + struct iomap_folio_state *ifs = folio->private; + unsigned int nr_blocks = i_blocks_per_folio(inode, folio); + gfp_t gfp; + + if (ifs || nr_blocks <= 1) + return ifs; + + if (flags & IOMAP_NOWAIT) + gfp = GFP_NOWAIT; + else + gfp = GFP_NOFS | __GFP_NOFAIL; /* - * migrate_page_move_mapping() assumes that pages with private data have - * their count elevated by 1. + * ifs->state tracks two sets of state flags when the + * filesystem block size is smaller than the folio size. + * The first state tracks per-block uptodate and the + * second tracks per-block dirty state. */ - attach_page_private(page, iop); - return iop; + ifs = kzalloc(struct_size(ifs, state, + BITS_TO_LONGS(2 * nr_blocks)), gfp); + if (!ifs) + return ifs; + + spin_lock_init(&ifs->state_lock); + if (folio_test_uptodate(folio)) + bitmap_set(ifs->state, 0, nr_blocks); + if (folio_test_dirty(folio)) + bitmap_set(ifs->state, nr_blocks, nr_blocks); + folio_attach_private(folio, ifs); + + return ifs; } -static void -iomap_page_release(struct page *page) +static void ifs_free(struct folio *folio) { - struct iomap_page *iop = detach_page_private(page); + struct iomap_folio_state *ifs = folio_detach_private(folio); - if (!iop) + if (!ifs) return; - WARN_ON_ONCE(atomic_read(&iop->read_count)); - WARN_ON_ONCE(atomic_read(&iop->write_count)); - kfree(iop); + WARN_ON_ONCE(ifs->read_bytes_pending != 0); + WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending)); + WARN_ON_ONCE(ifs_is_fully_uptodate(folio, ifs) != + folio_test_uptodate(folio)); + kfree(ifs); } /* - * Calculate the range inside the page that we actually need to read. + * Calculate how many bytes to truncate based off the number of blocks to + * truncate and the end position to start truncating from. */ -static void -iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, - loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp) +static size_t iomap_bytes_to_truncate(loff_t end_pos, unsigned block_bits, + unsigned blocks_truncated) +{ + unsigned block_size = 1 << block_bits; + unsigned block_offset = end_pos & (block_size - 1); + + if (!block_offset) + return blocks_truncated << block_bits; + + return ((blocks_truncated - 1) << block_bits) + block_offset; +} + +/* + * Calculate the range inside the folio that we actually need to read. + */ +static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, + loff_t *pos, loff_t length, size_t *offp, size_t *lenp) { + struct iomap_folio_state *ifs = folio->private; loff_t orig_pos = *pos; loff_t isize = i_size_read(inode); unsigned block_bits = inode->i_blkbits; unsigned block_size = (1 << block_bits); - unsigned poff = offset_in_page(*pos); - unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); + size_t poff = offset_in_folio(folio, *pos); + size_t plen = min_t(loff_t, folio_size(folio) - poff, length); + size_t orig_plen = plen; unsigned first = poff >> block_bits; unsigned last = (poff + plen - 1) >> block_bits; /* - * If the block size is smaller than the page size we need to check the + * If the block size is smaller than the page size, we need to check the * per-block uptodate status and adjust the offset and length if needed * to avoid reading in already uptodate ranges. */ - if (iop) { - unsigned int i; - - /* move forward for each leading block marked uptodate */ - for (i = first; i <= last; i++) { - if (!test_bit(i, iop->uptodate)) - break; - *pos += block_size; - poff += block_size; - plen -= block_size; - first++; + if (ifs) { + unsigned int next, blocks_skipped; + + next = ifs_next_nonuptodate_block(folio, first, last); + blocks_skipped = next - first; + + if (blocks_skipped) { + unsigned long block_offset = *pos & (block_size - 1); + unsigned bytes_skipped = + (blocks_skipped << block_bits) - block_offset; + + *pos += bytes_skipped; + poff += bytes_skipped; + plen -= bytes_skipped; } + first = next; /* truncate len if we find any trailing uptodate block(s) */ - for ( ; i <= last; i++) { - if (test_bit(i, iop->uptodate)) { - plen -= (last - i + 1) * block_size; - last = i - 1; - break; + if (++next <= last) { + next = ifs_next_uptodate_block(folio, next, last); + if (next <= last) { + plen -= iomap_bytes_to_truncate(*pos + plen, + block_bits, last - next + 1); + last = next - 1; } } } /* - * If the extent spans the block that contains the i_size we need to + * If the extent spans the block that contains the i_size, we need to * handle both halves separately so that we properly zero data in the * page cache for blocks that are entirely outside of i_size. */ - if (orig_pos <= isize && orig_pos + length > isize) { - unsigned end = offset_in_page(isize - 1) >> block_bits; + if (orig_pos <= isize && orig_pos + orig_plen > isize) { + unsigned end = offset_in_folio(folio, isize - 1) >> block_bits; if (first <= end && last > end) - plen -= (last - end) * block_size; + plen -= iomap_bytes_to_truncate(*pos + plen, block_bits, + last - end); } *offp = poff; *lenp = plen; } -static void -iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len) +static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter, + loff_t pos) { - struct iomap_page *iop = to_iomap_page(page); - struct inode *inode = page->mapping->host; - unsigned first = off >> inode->i_blkbits; - unsigned last = (off + len - 1) >> inode->i_blkbits; - bool uptodate = true; - unsigned long flags; - unsigned int i; - - spin_lock_irqsave(&iop->uptodate_lock, flags); - for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) { - if (i >= first && i <= last) - set_bit(i, iop->uptodate); - else if (!test_bit(i, iop->uptodate)) - uptodate = false; - } + const struct iomap *srcmap = iomap_iter_srcmap(iter); - if (uptodate) - SetPageUptodate(page); - spin_unlock_irqrestore(&iop->uptodate_lock, flags); + return srcmap->type != IOMAP_MAPPED || + (srcmap->flags & IOMAP_F_NEW) || + pos >= i_size_read(iter->inode); } -static void -iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +/** + * iomap_read_inline_data - copy inline data into the page cache + * @iter: iteration structure + * @folio: folio to copy to + * + * Copy the inline data in @iter into @folio and zero out the rest of the folio. + * Only a single IOMAP_INLINE extent is allowed at the end of each file. + * Returns zero for success to complete the read, or the usual negative errno. + */ +static int iomap_read_inline_data(const struct iomap_iter *iter, + struct folio *folio) { - if (PageError(page)) - return; + const struct iomap *iomap = iomap_iter_srcmap(iter); + size_t size = i_size_read(iter->inode) - iomap->offset; + size_t offset = offset_in_folio(folio, iomap->offset); - if (page_has_private(page)) - iomap_iop_set_range_uptodate(page, off, len); - else - SetPageUptodate(page); -} + if (WARN_ON_ONCE(!iomap->inline_data)) + return -EIO; -static void -iomap_read_finish(struct iomap_page *iop, struct page *page) -{ - if (!iop || atomic_dec_and_test(&iop->read_count)) - unlock_page(page); + if (folio_test_uptodate(folio)) + return 0; + + if (WARN_ON_ONCE(size > iomap->length)) + return -EIO; + if (offset > 0) + ifs_alloc(iter->inode, folio, iter->flags); + + folio_fill_tail(folio, offset, iomap->inline_data, size); + iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset); + return 0; } -static void -iomap_read_page_end_io(struct bio_vec *bvec, int error) +void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len, + int error) { - struct page *page = bvec->bv_page; - struct iomap_page *iop = to_iomap_page(page); - - if (unlikely(error)) { - ClearPageUptodate(page); - SetPageError(page); - } else { - iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len); + struct iomap_folio_state *ifs = folio->private; + bool uptodate = !error; + bool finished = true; + + if (ifs) { + unsigned long flags; + + spin_lock_irqsave(&ifs->state_lock, flags); + if (!error) + uptodate = ifs_set_range_uptodate(folio, ifs, off, len); + ifs->read_bytes_pending -= len; + finished = !ifs->read_bytes_pending; + spin_unlock_irqrestore(&ifs->state_lock, flags); } - iomap_read_finish(iop, page); + if (finished) + folio_end_read(folio, uptodate); } +EXPORT_SYMBOL_GPL(iomap_finish_folio_read); -static void -iomap_read_end_io(struct bio *bio) +static void iomap_read_init(struct folio *folio) { - int error = blk_status_to_errno(bio->bi_status); - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct iomap_folio_state *ifs = folio->private; - bio_for_each_segment_all(bvec, bio, iter_all) - iomap_read_page_end_io(bvec, error); - bio_put(bio); -} + if (ifs) { + size_t len = folio_size(folio); -struct iomap_readpage_ctx { - struct page *cur_page; - bool cur_page_in_bio; - struct bio *bio; - struct readahead_control *rac; -}; + /* + * ifs->read_bytes_pending is used to track how many bytes are + * read in asynchronously by the IO helper. We need to track + * this so that we can know when the IO helper has finished + * reading in all the necessary ranges of the folio and can end + * the read. + * + * Increase ->read_bytes_pending by the folio size to start, and + * add a +1 bias. We'll subtract the bias and any uptodate / + * zeroed ranges that did not require IO in iomap_read_end() + * after we're done processing the folio. + * + * We do this because otherwise, we would have to increment + * ifs->read_bytes_pending every time a range in the folio needs + * to be read in, which can get expensive since the spinlock + * needs to be held whenever modifying ifs->read_bytes_pending. + * + * We add the bias to ensure the read has not been ended on the + * folio when iomap_read_end() is called, even if the IO helper + * has already finished reading in the entire folio. + */ + spin_lock_irq(&ifs->state_lock); + WARN_ON_ONCE(ifs->read_bytes_pending != 0); + ifs->read_bytes_pending = len + 1; + spin_unlock_irq(&ifs->state_lock); + } +} -static void -iomap_read_inline_data(struct inode *inode, struct page *page, - struct iomap *iomap) +/* + * This ends IO if no bytes were submitted to an IO helper. + * + * Otherwise, this calibrates ifs->read_bytes_pending to represent only the + * submitted bytes (see comment in iomap_read_init()). If all bytes submitted + * have already been completed by the IO helper, then this will end the read. + * Else the IO helper will end the read after all submitted ranges have been + * read. + */ +static void iomap_read_end(struct folio *folio, size_t bytes_submitted) { - size_t size = i_size_read(inode); - void *addr; + struct iomap_folio_state *ifs = folio->private; - if (PageUptodate(page)) - return; + if (ifs) { + bool end_read, uptodate; - BUG_ON(page->index); - BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data)); + spin_lock_irq(&ifs->state_lock); + if (!ifs->read_bytes_pending) { + WARN_ON_ONCE(bytes_submitted); + spin_unlock_irq(&ifs->state_lock); + folio_unlock(folio); + return; + } - addr = kmap_atomic(page); - memcpy(addr, iomap->inline_data, size); - memset(addr + size, 0, PAGE_SIZE - size); - kunmap_atomic(addr); - SetPageUptodate(page); -} + /* + * Subtract any bytes that were initially accounted to + * read_bytes_pending but skipped for IO. The +1 accounts for + * the bias we added in iomap_read_init(). + */ + ifs->read_bytes_pending -= + (folio_size(folio) + 1 - bytes_submitted); -static inline bool iomap_block_needs_zeroing(struct inode *inode, - struct iomap *iomap, loff_t pos) -{ - return iomap->type != IOMAP_MAPPED || - (iomap->flags & IOMAP_F_NEW) || - pos >= i_size_read(inode); + /* + * If !ifs->read_bytes_pending, this means all pending reads by + * the IO helper have already completed, which means we need to + * end the folio read here. If ifs->read_bytes_pending != 0, + * the IO helper will end the folio read. + */ + end_read = !ifs->read_bytes_pending; + if (end_read) + uptodate = ifs_is_fully_uptodate(folio, ifs); + spin_unlock_irq(&ifs->state_lock); + if (end_read) + folio_end_read(folio, uptodate); + } else if (!bytes_submitted) { + /* + * If there were no bytes submitted, this means we are + * responsible for unlocking the folio here, since no IO helper + * has taken ownership of it. If there were bytes submitted, + * then the IO helper will end the read via + * iomap_finish_folio_read(). + */ + folio_unlock(folio); + } } -static loff_t -iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap, struct iomap *srcmap) +static int iomap_read_folio_iter(struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, size_t *bytes_submitted) { - struct iomap_readpage_ctx *ctx = data; - struct page *page = ctx->cur_page; - struct iomap_page *iop = iomap_page_create(inode, page); - bool same_page = false, is_contig = false; - loff_t orig_pos = pos; - unsigned poff, plen; - sector_t sector; + const struct iomap *iomap = &iter->iomap; + loff_t pos = iter->pos; + loff_t length = iomap_length(iter); + struct folio *folio = ctx->cur_folio; + size_t poff, plen; + loff_t pos_diff; + int ret; if (iomap->type == IOMAP_INLINE) { - WARN_ON_ONCE(pos); - iomap_read_inline_data(inode, page, iomap); - return PAGE_SIZE; - } - - /* zero post-eof blocks as the page may be mapped */ - iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen); - if (plen == 0) - goto done; - - if (iomap_block_needs_zeroing(inode, iomap, pos)) { - zero_user(page, poff, plen); - iomap_set_range_uptodate(page, poff, plen); - goto done; + ret = iomap_read_inline_data(iter, folio); + if (ret) + return ret; + return iomap_iter_advance(iter, length); } - ctx->cur_page_in_bio = true; + ifs_alloc(iter->inode, folio, iter->flags); - /* - * Try to merge into a previous segment if we can. - */ - sector = iomap_sector(iomap, pos); - if (ctx->bio && bio_end_sector(ctx->bio) == sector) - is_contig = true; - - if (is_contig && - __bio_try_merge_page(ctx->bio, page, plen, poff, &same_page)) { - if (!same_page && iop) - atomic_inc(&iop->read_count); - goto done; - } + length = min_t(loff_t, length, + folio_size(folio) - offset_in_folio(folio, pos)); + while (length) { + iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, + &plen); - /* - * If we start a new segment we need to increase the read count, and we - * need to do so before submitting any previous full bio to make sure - * that we don't prematurely unlock the page. - */ - if (iop) - atomic_inc(&iop->read_count); + pos_diff = pos - iter->pos; + if (WARN_ON_ONCE(pos_diff + plen > length)) + return -EIO; - if (!ctx->bio || !is_contig || bio_full(ctx->bio, plen)) { - gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); - gfp_t orig_gfp = gfp; - int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; + ret = iomap_iter_advance(iter, pos_diff); + if (ret) + return ret; - if (ctx->bio) - submit_bio(ctx->bio); + if (plen == 0) + return 0; + + /* zero post-eof blocks as the page may be mapped */ + if (iomap_block_needs_zeroing(iter, pos)) { + folio_zero_range(folio, poff, plen); + iomap_set_range_uptodate(folio, poff, plen); + } else { + if (!*bytes_submitted) + iomap_read_init(folio); + ret = ctx->ops->read_folio_range(iter, ctx, plen); + if (ret) + return ret; + *bytes_submitted += plen; + } - if (ctx->rac) /* same as readahead_gfp_mask */ - gfp |= __GFP_NORETRY | __GFP_NOWARN; - ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs)); - /* - * If the bio_alloc fails, try it again for a single page to - * avoid having to deal with partial page reads. This emulates - * what do_mpage_readpage does. - */ - if (!ctx->bio) - ctx->bio = bio_alloc(orig_gfp, 1); - ctx->bio->bi_opf = REQ_OP_READ; - if (ctx->rac) - ctx->bio->bi_opf |= REQ_RAHEAD; - ctx->bio->bi_iter.bi_sector = sector; - bio_set_dev(ctx->bio, iomap->bdev); - ctx->bio->bi_end_io = iomap_read_end_io; + ret = iomap_iter_advance(iter, plen); + if (ret) + return ret; + length -= pos_diff + plen; + pos = iter->pos; } - - bio_add_page(ctx->bio, page, plen, poff); -done: - /* - * Move the caller beyond our range so that it keeps making progress. - * For that we have to include any leading non-uptodate ranges, but - * we can skip trailing ones as they will be handled in the next - * iteration. - */ - return pos - orig_pos + plen; + return 0; } -int -iomap_readpage(struct page *page, const struct iomap_ops *ops) +void iomap_read_folio(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx) { - struct iomap_readpage_ctx ctx = { .cur_page = page }; - struct inode *inode = page->mapping->host; - unsigned poff; - loff_t ret; - - trace_iomap_readpage(page->mapping->host, 1); - - for (poff = 0; poff < PAGE_SIZE; poff += ret) { - ret = iomap_apply(inode, page_offset(page) + poff, - PAGE_SIZE - poff, 0, ops, &ctx, - iomap_readpage_actor); - if (ret <= 0) { - WARN_ON_ONCE(ret == 0); - SetPageError(page); - break; - } - } + struct folio *folio = ctx->cur_folio; + struct iomap_iter iter = { + .inode = folio->mapping->host, + .pos = folio_pos(folio), + .len = folio_size(folio), + }; + size_t bytes_submitted = 0; + int ret; - if (ctx.bio) { - submit_bio(ctx.bio); - WARN_ON_ONCE(!ctx.cur_page_in_bio); - } else { - WARN_ON_ONCE(ctx.cur_page_in_bio); - unlock_page(page); - } + trace_iomap_readpage(iter.inode, 1); - /* - * Just like mpage_readahead and block_read_full_page we always - * return 0 and just mark the page as PageError on errors. This - * should be cleaned up all through the stack eventually. - */ - return 0; + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.status = iomap_read_folio_iter(&iter, ctx, + &bytes_submitted); + + if (ctx->ops->submit_read) + ctx->ops->submit_read(ctx); + + iomap_read_end(folio, bytes_submitted); } -EXPORT_SYMBOL_GPL(iomap_readpage); +EXPORT_SYMBOL_GPL(iomap_read_folio); -static loff_t -iomap_readahead_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap, struct iomap *srcmap) +static int iomap_readahead_iter(struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, size_t *cur_bytes_submitted) { - struct iomap_readpage_ctx *ctx = data; - loff_t done, ret; - - for (done = 0; done < length; done += ret) { - if (ctx->cur_page && offset_in_page(pos + done) == 0) { - if (!ctx->cur_page_in_bio) - unlock_page(ctx->cur_page); - put_page(ctx->cur_page); - ctx->cur_page = NULL; + int ret; + + while (iomap_length(iter)) { + if (ctx->cur_folio && + offset_in_folio(ctx->cur_folio, iter->pos) == 0) { + iomap_read_end(ctx->cur_folio, *cur_bytes_submitted); + ctx->cur_folio = NULL; } - if (!ctx->cur_page) { - ctx->cur_page = readahead_page(ctx->rac); - ctx->cur_page_in_bio = false; + if (!ctx->cur_folio) { + ctx->cur_folio = readahead_folio(ctx->rac); + if (WARN_ON_ONCE(!ctx->cur_folio)) + return -EINVAL; + *cur_bytes_submitted = 0; } - ret = iomap_readpage_actor(inode, pos + done, length - done, - ctx, iomap, srcmap); + ret = iomap_read_folio_iter(iter, ctx, cur_bytes_submitted); + if (ret) + return ret; } - return done; + return 0; } /** * iomap_readahead - Attempt to read pages from a file. - * @rac: Describes the pages to be read. * @ops: The operations vector for the filesystem. + * @ctx: The ctx used for issuing readahead. * * This function is for filesystems to call to implement their readahead * address_space operation. @@ -409,133 +619,126 @@ iomap_readahead_actor(struct inode *inode, loff_t pos, loff_t length, * function is called with memalloc_nofs set, so allocations will not cause * the filesystem to be reentered. */ -void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) +void iomap_readahead(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx) { - struct inode *inode = rac->mapping->host; - loff_t pos = readahead_pos(rac); - loff_t length = readahead_length(rac); - struct iomap_readpage_ctx ctx = { - .rac = rac, + struct readahead_control *rac = ctx->rac; + struct iomap_iter iter = { + .inode = rac->mapping->host, + .pos = readahead_pos(rac), + .len = readahead_length(rac), }; + size_t cur_bytes_submitted; - trace_iomap_readahead(inode, readahead_count(rac)); + trace_iomap_readahead(rac->mapping->host, readahead_count(rac)); - while (length > 0) { - loff_t ret = iomap_apply(inode, pos, length, 0, ops, - &ctx, iomap_readahead_actor); - if (ret <= 0) { - WARN_ON_ONCE(ret == 0); - break; - } - pos += ret; - length -= ret; - } + while (iomap_iter(&iter, ops) > 0) + iter.status = iomap_readahead_iter(&iter, ctx, + &cur_bytes_submitted); - if (ctx.bio) - submit_bio(ctx.bio); - if (ctx.cur_page) { - if (!ctx.cur_page_in_bio) - unlock_page(ctx.cur_page); - put_page(ctx.cur_page); - } + if (ctx->ops->submit_read) + ctx->ops->submit_read(ctx); + + if (ctx->cur_folio) + iomap_read_end(ctx->cur_folio, cur_bytes_submitted); } EXPORT_SYMBOL_GPL(iomap_readahead); /* - * iomap_is_partially_uptodate checks whether blocks within a page are + * iomap_is_partially_uptodate checks whether blocks within a folio are * uptodate or not. * - * Returns true if all blocks which correspond to a file portion - * we want to read within the page are uptodate. + * Returns true if all blocks which correspond to the specified part + * of the folio are uptodate. */ -int -iomap_is_partially_uptodate(struct page *page, unsigned long from, - unsigned long count) +bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { - struct iomap_page *iop = to_iomap_page(page); - struct inode *inode = page->mapping->host; - unsigned len, first, last; - unsigned i; + struct iomap_folio_state *ifs = folio->private; + struct inode *inode = folio->mapping->host; + unsigned first, last; - /* Limit range to one page */ - len = min_t(unsigned, PAGE_SIZE - from, count); + if (!ifs) + return false; - /* First and last blocks in range within page */ - first = from >> inode->i_blkbits; - last = (from + len - 1) >> inode->i_blkbits; + /* Caller's range may extend past the end of this folio */ + count = min(folio_size(folio) - from, count); - if (iop) { - for (i = first; i <= last; i++) - if (!test_bit(i, iop->uptodate)) - return 0; - return 1; - } + /* First and last blocks in range within folio */ + first = from >> inode->i_blkbits; + last = (from + count - 1) >> inode->i_blkbits; - return 0; + return ifs_next_nonuptodate_block(folio, first, last) > last; } EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); -int -iomap_releasepage(struct page *page, gfp_t gfp_mask) +/** + * iomap_get_folio - get a folio reference for writing + * @iter: iteration structure + * @pos: start offset of write + * @len: Suggested size of folio to create. + * + * Returns a locked reference to the folio at @pos, or an error pointer if the + * folio could not be obtained. + */ +struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len) +{ + fgf_t fgp = FGP_WRITEBEGIN | FGP_NOFS; + + if (iter->flags & IOMAP_NOWAIT) + fgp |= FGP_NOWAIT; + if (iter->flags & IOMAP_DONTCACHE) + fgp |= FGP_DONTCACHE; + fgp |= fgf_set_order(len); + + return __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, + fgp, mapping_gfp_mask(iter->inode->i_mapping)); +} +EXPORT_SYMBOL_GPL(iomap_get_folio); + +bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags) { - trace_iomap_releasepage(page->mapping->host, page_offset(page), - PAGE_SIZE); + trace_iomap_release_folio(folio->mapping->host, folio_pos(folio), + folio_size(folio)); /* - * mm accommodates an old ext3 case where clean pages might not have had - * the dirty bit cleared. Thus, it can send actual dirty pages to - * ->releasepage() via shrink_active_list(), skip those here. + * If the folio is dirty, we refuse to release our metadata because + * it may be partially dirty. Once we track per-block dirty state, + * we can release the metadata if every block is dirty. */ - if (PageDirty(page) || PageWriteback(page)) - return 0; - iomap_page_release(page); - return 1; + if (folio_test_dirty(folio)) + return false; + ifs_free(folio); + return true; } -EXPORT_SYMBOL_GPL(iomap_releasepage); +EXPORT_SYMBOL_GPL(iomap_release_folio); -void -iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len) +void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len) { - trace_iomap_invalidatepage(page->mapping->host, offset, len); + trace_iomap_invalidate_folio(folio->mapping->host, + folio_pos(folio) + offset, len); /* - * If we are invalidating the entire page, clear the dirty state from it - * and release it to avoid unnecessary buildup of the LRU. + * If we're invalidating the entire folio, clear the dirty state + * from it and release it to avoid unnecessary buildup of the LRU. */ - if (offset == 0 && len == PAGE_SIZE) { - WARN_ON_ONCE(PageWriteback(page)); - cancel_dirty_page(page); - iomap_page_release(page); + if (offset == 0 && len == folio_size(folio)) { + WARN_ON_ONCE(folio_test_writeback(folio)); + folio_cancel_dirty(folio); + ifs_free(folio); } } -EXPORT_SYMBOL_GPL(iomap_invalidatepage); +EXPORT_SYMBOL_GPL(iomap_invalidate_folio); -#ifdef CONFIG_MIGRATION -int -iomap_migrate_page(struct address_space *mapping, struct page *newpage, - struct page *page, enum migrate_mode mode) +bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio) { - int ret; - - ret = migrate_page_move_mapping(mapping, newpage, page, 0); - if (ret != MIGRATEPAGE_SUCCESS) - return ret; - - if (page_has_private(page)) - attach_page_private(newpage, detach_page_private(page)); + struct inode *inode = mapping->host; + size_t len = folio_size(folio); - if (mode != MIGRATE_SYNC_NO_COPY) - migrate_page_copy(newpage, page); - else - migrate_page_states(newpage, page); - return MIGRATEPAGE_SUCCESS; + ifs_alloc(inode, folio, 0); + iomap_set_range_dirty(folio, 0, len); + return filemap_dirty_folio(mapping, folio); } -EXPORT_SYMBOL_GPL(iomap_migrate_page); -#endif /* CONFIG_MIGRATION */ - -enum { - IOMAP_WRITE_F_UNSHARE = (1 << 0), -}; +EXPORT_SYMBOL_GPL(iomap_dirty_folio); static void iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) @@ -547,462 +750,875 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) * write started inside the existing inode size. */ if (pos + len > i_size) - truncate_pagecache_range(inode, max(pos, i_size), pos + len); + truncate_pagecache_range(inode, max(pos, i_size), + pos + len - 1); } -static int -iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff, - unsigned plen, struct iomap *iomap) +static int __iomap_write_begin(const struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, size_t len, + struct folio *folio) { - struct bio_vec bvec; - struct bio bio; - - bio_init(&bio, &bvec, 1); - bio.bi_opf = REQ_OP_READ; - bio.bi_iter.bi_sector = iomap_sector(iomap, block_start); - bio_set_dev(&bio, iomap->bdev); - __bio_add_page(&bio, page, plen, poff); - return submit_bio_wait(&bio); -} + struct iomap_folio_state *ifs; + loff_t pos = iter->pos; + loff_t block_size = i_blocksize(iter->inode); + loff_t block_start = round_down(pos, block_size); + loff_t block_end = round_up(pos + len, block_size); + unsigned int nr_blocks = i_blocks_per_folio(iter->inode, folio); + size_t from = offset_in_folio(folio, pos), to = from + len; + size_t poff, plen; -static int -__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, - struct page *page, struct iomap *srcmap) -{ - struct iomap_page *iop = iomap_page_create(inode, page); - loff_t block_size = i_blocksize(inode); - loff_t block_start = pos & ~(block_size - 1); - loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1); - unsigned from = offset_in_page(pos), to = from + len, poff, plen; - int status; + /* + * If the write or zeroing completely overlaps the current folio, then + * entire folio will be dirtied so there is no need for + * per-block state tracking structures to be attached to this folio. + * For the unshare case, we must read in the ondisk contents because we + * are not changing pagecache contents. + */ + if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) && + pos + len >= folio_next_pos(folio)) + return 0; + + ifs = ifs_alloc(iter->inode, folio, iter->flags); + if ((iter->flags & IOMAP_NOWAIT) && !ifs && nr_blocks > 1) + return -EAGAIN; - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) return 0; do { - iomap_adjust_read_range(inode, iop, &block_start, + iomap_adjust_read_range(iter->inode, folio, &block_start, block_end - block_start, &poff, &plen); if (plen == 0) break; - if (!(flags & IOMAP_WRITE_F_UNSHARE) && - (from <= poff || from >= poff + plen) && - (to <= poff || to >= poff + plen)) + /* + * If the read range will be entirely overwritten by the write, + * we can skip having to zero/read it in. + */ + if (!(iter->flags & IOMAP_UNSHARE) && from <= poff && + to >= poff + plen) continue; - if (iomap_block_needs_zeroing(inode, srcmap, block_start)) { - if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE)) + if (iomap_block_needs_zeroing(iter, block_start)) { + if (WARN_ON_ONCE(iter->flags & IOMAP_UNSHARE)) return -EIO; - zero_user_segments(page, poff, from, to, poff + plen); - iomap_set_range_uptodate(page, poff, plen); - continue; + folio_zero_segments(folio, poff, from, to, poff + plen); + } else { + int status; + + if (iter->flags & IOMAP_NOWAIT) + return -EAGAIN; + + if (write_ops && write_ops->read_folio_range) + status = write_ops->read_folio_range(iter, + folio, block_start, plen); + else + status = iomap_bio_read_folio_range_sync(iter, + folio, block_start, plen); + if (status) + return status; } - - status = iomap_read_page_sync(block_start, page, poff, plen, - srcmap); - if (status) - return status; + iomap_set_range_uptodate(folio, poff, plen); } while ((block_start += plen) < block_end); return 0; } -static int -iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, - struct page **pagep, struct iomap *iomap, struct iomap *srcmap) +static struct folio *__iomap_get_folio(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, size_t len) { - const struct iomap_page_ops *page_ops = iomap->page_ops; - struct page *page; + loff_t pos = iter->pos; + + if (!mapping_large_folio_support(iter->inode->i_mapping)) + len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); + + if (iter->fbatch) { + struct folio *folio = folio_batch_next(iter->fbatch); + + if (!folio) + return NULL; + + /* + * The folio mapping generally shouldn't have changed based on + * fs locks, but be consistent with filemap lookup and retry + * the iter if it does. + */ + folio_lock(folio); + if (unlikely(folio->mapping != iter->inode->i_mapping)) { + iter->iomap.flags |= IOMAP_F_STALE; + folio_unlock(folio); + return NULL; + } + + folio_get(folio); + return folio; + } + + if (write_ops && write_ops->get_folio) + return write_ops->get_folio(iter, pos, len); + return iomap_get_folio(iter, pos, len); +} + +static void __iomap_put_folio(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, size_t ret, + struct folio *folio) +{ + loff_t pos = iter->pos; + + if (write_ops && write_ops->put_folio) { + write_ops->put_folio(iter->inode, pos, ret, folio); + } else { + folio_unlock(folio); + folio_put(folio); + } +} + +/* trim pos and bytes to within a given folio */ +static loff_t iomap_trim_folio_range(struct iomap_iter *iter, + struct folio *folio, size_t *offset, u64 *bytes) +{ + loff_t pos = iter->pos; + size_t fsize = folio_size(folio); + + WARN_ON_ONCE(pos < folio_pos(folio)); + WARN_ON_ONCE(pos >= folio_pos(folio) + fsize); + + *offset = offset_in_folio(folio, pos); + *bytes = min(*bytes, fsize - *offset); + + return pos; +} + +static int iomap_write_begin_inline(const struct iomap_iter *iter, + struct folio *folio) +{ + /* needs more work for the tailpacking case; disable for now */ + if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0)) + return -EIO; + return iomap_read_inline_data(iter, folio); +} + +/* + * Grab and prepare a folio for write based on iter state. Returns the folio, + * offset, and length. Callers can optionally pass a max length *plen, + * otherwise init to zero. + */ +static int iomap_write_begin(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops, struct folio **foliop, + size_t *poffset, u64 *plen) +{ + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos; + u64 len = min_t(u64, SIZE_MAX, iomap_length(iter)); + struct folio *folio; int status = 0; - BUG_ON(pos + len > iomap->offset + iomap->length); - if (srcmap != iomap) - BUG_ON(pos + len > srcmap->offset + srcmap->length); + len = min_not_zero(len, *plen); + *foliop = NULL; + *plen = 0; if (fatal_signal_pending(current)) return -EINTR; - if (page_ops && page_ops->page_prepare) { - status = page_ops->page_prepare(inode, pos, len, iomap); - if (status) - return status; + folio = __iomap_get_folio(iter, write_ops, len); + if (IS_ERR(folio)) + return PTR_ERR(folio); + + /* + * No folio means we're done with a batch. We still have range to + * process so return and let the caller iterate and refill the batch. + */ + if (!folio) { + WARN_ON_ONCE(!iter->fbatch); + return 0; } - page = grab_cache_page_write_begin(inode->i_mapping, pos >> PAGE_SHIFT, - AOP_FLAG_NOFS); - if (!page) { - status = -ENOMEM; - goto out_no_page; + /* + * Now we have a locked folio, before we do anything with it we need to + * check that the iomap we have cached is not stale. The inode extent + * mapping can change due to concurrent IO in flight (e.g. + * IOMAP_UNWRITTEN state can change and memory reclaim could have + * reclaimed a previously partially written page at this index after IO + * completion before this write reaches this file offset) and hence we + * could do the wrong thing here (zero a page range incorrectly or fail + * to zero) and corrupt data. + */ + if (write_ops && write_ops->iomap_valid) { + bool iomap_valid = write_ops->iomap_valid(iter->inode, + &iter->iomap); + if (!iomap_valid) { + iter->iomap.flags |= IOMAP_F_STALE; + status = 0; + goto out_unlock; + } } + /* + * The folios in a batch may not be contiguous. If we've skipped + * forward, advance the iter to the pos of the current folio. If the + * folio starts beyond the end of the mapping, it may have been trimmed + * since the lookup for whatever reason. Return a NULL folio to + * terminate the op. + */ + if (folio_pos(folio) > iter->pos) { + len = min_t(u64, folio_pos(folio) - iter->pos, + iomap_length(iter)); + status = iomap_iter_advance(iter, len); + len = iomap_length(iter); + if (status || !len) + goto out_unlock; + } + + pos = iomap_trim_folio_range(iter, folio, poffset, &len); + if (srcmap->type == IOMAP_INLINE) - iomap_read_inline_data(inode, page, srcmap); - else if (iomap->flags & IOMAP_F_BUFFER_HEAD) - status = __block_write_begin_int(page, pos, len, NULL, srcmap); + status = iomap_write_begin_inline(iter, folio); + else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) + status = __block_write_begin_int(folio, pos, len, NULL, srcmap); else - status = __iomap_write_begin(inode, pos, len, flags, page, - srcmap); + status = __iomap_write_begin(iter, write_ops, len, folio); if (unlikely(status)) goto out_unlock; - *pagep = page; + *foliop = folio; + *plen = len; return 0; out_unlock: - unlock_page(page); - put_page(page); - iomap_write_failed(inode, pos, len); - -out_no_page: - if (page_ops && page_ops->page_done) - page_ops->page_done(inode, pos, 0, NULL, iomap); + __iomap_put_folio(iter, write_ops, 0, folio); return status; } -int -iomap_set_page_dirty(struct page *page) -{ - struct address_space *mapping = page_mapping(page); - int newly_dirty; - - if (unlikely(!mapping)) - return !TestSetPageDirty(page); - - /* - * Lock out page->mem_cgroup migration to keep PageDirty - * synchronized with per-memcg dirty page counters. - */ - lock_page_memcg(page); - newly_dirty = !TestSetPageDirty(page); - if (newly_dirty) - __set_page_dirty(page, mapping, 0); - unlock_page_memcg(page); - - if (newly_dirty) - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - return newly_dirty; -} -EXPORT_SYMBOL_GPL(iomap_set_page_dirty); - -static int -__iomap_write_end(struct inode *inode, loff_t pos, unsigned len, - unsigned copied, struct page *page) +static bool __iomap_write_end(struct inode *inode, loff_t pos, size_t len, + size_t copied, struct folio *folio) { - flush_dcache_page(page); + flush_dcache_folio(folio); /* * The blocks that were entirely written will now be uptodate, so we - * don't have to worry about a readpage reading them and overwriting a - * partial write. However if we have encountered a short write and only + * don't have to worry about a read_folio reading them and overwriting a + * partial write. However, if we've encountered a short write and only * partially written into a block, it will not be marked uptodate, so a - * readpage might come in and destroy our partial write. + * read_folio might come in and destroy our partial write. * - * Do the simplest thing, and just treat any short write to a non - * uptodate page as a zero-length write, and force the caller to redo - * the whole thing. + * Do the simplest thing and just treat any short write to a + * non-uptodate page as a zero-length write, and force the caller to + * redo the whole thing. */ - if (unlikely(copied < len && !PageUptodate(page))) - return 0; - iomap_set_range_uptodate(page, offset_in_page(pos), len); - iomap_set_page_dirty(page); - return copied; + if (unlikely(copied < len && !folio_test_uptodate(folio))) + return false; + iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len); + iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied); + filemap_dirty_folio(inode->i_mapping, folio); + return true; } -static int -iomap_write_end_inline(struct inode *inode, struct page *page, - struct iomap *iomap, loff_t pos, unsigned copied) +static bool iomap_write_end_inline(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t copied) { + const struct iomap *iomap = &iter->iomap; void *addr; - WARN_ON_ONCE(!PageUptodate(page)); - BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data)); + WARN_ON_ONCE(!folio_test_uptodate(folio)); + BUG_ON(!iomap_inline_data_valid(iomap)); + + if (WARN_ON_ONCE(!iomap->inline_data)) + return false; - addr = kmap_atomic(page); - memcpy(iomap->inline_data + pos, addr + pos, copied); - kunmap_atomic(addr); + flush_dcache_folio(folio); + addr = kmap_local_folio(folio, pos); + memcpy(iomap_inline_data(iomap, pos), addr, copied); + kunmap_local(addr); - mark_inode_dirty(inode); - return copied; + mark_inode_dirty(iter->inode); + return true; } -static int -iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, - struct page *page, struct iomap *iomap, struct iomap *srcmap) +/* + * Returns true if all copied bytes have been written to the pagecache, + * otherwise return false. + */ +static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied, + struct folio *folio) { - const struct iomap_page_ops *page_ops = iomap->page_ops; - loff_t old_size = inode->i_size; - int ret; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; - if (srcmap->type == IOMAP_INLINE) { - ret = iomap_write_end_inline(inode, page, iomap, pos, copied); - } else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { - ret = block_write_end(NULL, inode->i_mapping, pos, len, copied, - page, NULL); - } else { - ret = __iomap_write_end(inode, pos, len, copied, page); - } + if (srcmap->type == IOMAP_INLINE) + return iomap_write_end_inline(iter, folio, pos, copied); - /* - * Update the in-memory inode size after copying the data into the page - * cache. It's up to the file system to write the updated size to disk, - * preferably after I/O completion so that no stale data is exposed. - */ - if (pos + ret > old_size) { - i_size_write(inode, pos + ret); - iomap->flags |= IOMAP_F_SIZE_CHANGED; - } - unlock_page(page); + if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { + size_t bh_written; - if (old_size < pos) - pagecache_isize_extended(inode, old_size, pos); - if (page_ops && page_ops->page_done) - page_ops->page_done(inode, pos, ret, page, iomap); - put_page(page); + bh_written = block_write_end(pos, len, copied, folio); + WARN_ON_ONCE(bh_written != copied && bh_written != 0); + return bh_written == copied; + } - if (ret < len) - iomap_write_failed(inode, pos, len); - return ret; + return __iomap_write_end(iter->inode, pos, len, copied, folio); } -static loff_t -iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap, struct iomap *srcmap) +static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i, + const struct iomap_write_ops *write_ops) { - struct iov_iter *i = data; - long status = 0; - ssize_t written = 0; + ssize_t total_written = 0; + int status = 0; + struct address_space *mapping = iter->inode->i_mapping; + size_t chunk = mapping_max_folio_size(mapping); + unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0; do { - struct page *page; - unsigned long offset; /* Offset into pagecache page */ - unsigned long bytes; /* Bytes to write to page */ + struct folio *folio; + loff_t old_size; + size_t offset; /* Offset into folio */ + u64 bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ + u64 written; /* Bytes have been written */ + loff_t pos; + + bytes = iov_iter_count(i); +retry: + offset = iter->pos & (chunk - 1); + bytes = min(chunk - offset, bytes); + status = balance_dirty_pages_ratelimited_flags(mapping, + bdp_flags); + if (unlikely(status)) + break; - offset = offset_in_page(pos); - bytes = min_t(unsigned long, PAGE_SIZE - offset, - iov_iter_count(i)); -again: - if (bytes > length) - bytes = length; + if (bytes > iomap_length(iter)) + bytes = iomap_length(iter); /* - * Bring in the user page that we will copy from _first_. + * Bring in the user page that we'll copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * - * Not only is this an optimisation, but it is also required - * to check that the address is actually valid, when atomic - * usercopies are used, below. + * For async buffered writes the assumption is that the user + * page has already been faulted in. This can be optimized by + * faulting the user page. */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) { status = -EFAULT; break; } - status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, - srcmap); - if (unlikely(status)) + status = iomap_write_begin(iter, write_ops, &folio, &offset, + &bytes); + if (unlikely(status)) { + iomap_write_failed(iter->inode, iter->pos, bytes); + break; + } + if (iter->iomap.flags & IOMAP_F_STALE) break; - if (mapping_writably_mapped(inode->i_mapping)) - flush_dcache_page(page); + pos = iter->pos; - copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); + if (mapping_writably_mapped(mapping)) + flush_dcache_folio(folio); - flush_dcache_page(page); + copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); + written = iomap_write_end(iter, bytes, copied, folio) ? + copied : 0; - status = iomap_write_end(inode, pos, bytes, copied, page, iomap, - srcmap); - if (unlikely(status < 0)) - break; - copied = status; + /* + * Update the in-memory inode size after copying the data into + * the page cache. It's up to the file system to write the + * updated size to disk, preferably after I/O completion so that + * no stale data is exposed. Only once that's done can we + * unlock and release the folio. + */ + old_size = iter->inode->i_size; + if (pos + written > old_size) { + i_size_write(iter->inode, pos + written); + iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; + } + __iomap_put_folio(iter, write_ops, written, folio); - cond_resched(); + if (old_size < pos) + pagecache_isize_extended(iter->inode, old_size, pos); - iov_iter_advance(i, copied); - if (unlikely(copied == 0)) { + cond_resched(); + if (unlikely(written == 0)) { /* - * If we were unable to copy any data at all, we must - * fall back to a single segment length write. - * - * If we didn't fallback here, we could livelock - * because not all segments in the iov can be copied at - * once without a pagefault. + * A short copy made iomap_write_end() reject the + * thing entirely. Might be memory poisoning + * halfway through, might be a race with munmap, + * might be severe memory pressure. */ - bytes = min_t(unsigned long, PAGE_SIZE - offset, - iov_iter_single_seg_count(i)); - goto again; + iomap_write_failed(iter->inode, pos, bytes); + iov_iter_revert(i, copied); + + if (chunk > PAGE_SIZE) + chunk /= 2; + if (copied) { + bytes = copied; + goto retry; + } + } else { + total_written += written; + iomap_iter_advance(iter, written); } - pos += copied; - written += copied; - length -= copied; - - balance_dirty_pages_ratelimited(inode->i_mapping); - } while (iov_iter_count(i) && length); + } while (iov_iter_count(i) && iomap_length(iter)); - return written ? written : status; + return total_written ? 0 : status; } ssize_t -iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter, - const struct iomap_ops *ops) +iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private) { - struct inode *inode = iocb->ki_filp->f_mapping->host; - loff_t pos = iocb->ki_pos, ret = 0, written = 0; + struct iomap_iter iter = { + .inode = iocb->ki_filp->f_mapping->host, + .pos = iocb->ki_pos, + .len = iov_iter_count(i), + .flags = IOMAP_WRITE, + .private = private, + }; + ssize_t ret; + + if (iocb->ki_flags & IOCB_NOWAIT) + iter.flags |= IOMAP_NOWAIT; + if (iocb->ki_flags & IOCB_DONTCACHE) + iter.flags |= IOMAP_DONTCACHE; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.status = iomap_write_iter(&iter, i, write_ops); + + if (unlikely(iter.pos == iocb->ki_pos)) + return ret; + ret = iter.pos - iocb->ki_pos; + iocb->ki_pos = iter.pos; + return ret; +} +EXPORT_SYMBOL_GPL(iomap_file_buffered_write); + +static void iomap_write_delalloc_ifs_punch(struct inode *inode, + struct folio *folio, loff_t start_byte, loff_t end_byte, + struct iomap *iomap, iomap_punch_t punch) +{ + unsigned int first_blk, last_blk; + loff_t last_byte; + u8 blkbits = inode->i_blkbits; + struct iomap_folio_state *ifs; + + /* + * When we have per-block dirty tracking, there can be + * blocks within a folio which are marked uptodate + * but not dirty. In that case it is necessary to punch + * out such blocks to avoid leaking any delalloc blocks. + */ + ifs = folio->private; + if (!ifs) + return; + + last_byte = min_t(loff_t, end_byte - 1, folio_next_pos(folio) - 1); + first_blk = offset_in_folio(folio, start_byte) >> blkbits; + last_blk = offset_in_folio(folio, last_byte) >> blkbits; + while ((first_blk = ifs_next_clean_block(folio, first_blk, last_blk)) + <= last_blk) { + punch(inode, folio_pos(folio) + (first_blk << blkbits), + 1 << blkbits, iomap); + first_blk++; + } +} + +static void iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, + loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, + struct iomap *iomap, iomap_punch_t punch) +{ + if (!folio_test_dirty(folio)) + return; + + /* if dirty, punch up to offset */ + if (start_byte > *punch_start_byte) { + punch(inode, *punch_start_byte, start_byte - *punch_start_byte, + iomap); + } + + /* Punch non-dirty blocks within folio */ + iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, + iomap, punch); - while (iov_iter_count(iter)) { - ret = iomap_apply(inode, pos, iov_iter_count(iter), - IOMAP_WRITE, ops, iter, iomap_write_actor); - if (ret <= 0) + /* + * Make sure the next punch start is correctly bound to + * the end of this data range, not the end of the folio. + */ + *punch_start_byte = min_t(loff_t, end_byte, folio_next_pos(folio)); +} + +/* + * Scan the data range passed to us for dirty page cache folios. If we find a + * dirty folio, punch out the preceding range and update the offset from which + * the next punch will start from. + * + * We can punch out storage reservations under clean pages because they either + * contain data that has been written back - in which case the delalloc punch + * over that range is a no-op - or they have been read faults in which case they + * contain zeroes and we can remove the delalloc backing range and any new + * writes to those pages will do the normal hole filling operation... + * + * This makes the logic simple: we only need to keep the delalloc extents only + * over the dirty ranges of the page cache. + * + * This function uses [start_byte, end_byte) intervals (i.e. open ended) to + * simplify range iterations. + */ +static void iomap_write_delalloc_scan(struct inode *inode, + loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, + struct iomap *iomap, iomap_punch_t punch) +{ + while (start_byte < end_byte) { + struct folio *folio; + + /* grab locked page */ + folio = filemap_lock_folio(inode->i_mapping, + start_byte >> PAGE_SHIFT); + if (IS_ERR(folio)) { + start_byte = ALIGN_DOWN(start_byte, PAGE_SIZE) + + PAGE_SIZE; + continue; + } + + iomap_write_delalloc_punch(inode, folio, punch_start_byte, + start_byte, end_byte, iomap, punch); + + /* move offset to start of next folio in range */ + start_byte = folio_next_pos(folio); + folio_unlock(folio); + folio_put(folio); + } +} + +/* + * When a short write occurs, the filesystem might need to use ->iomap_end + * to remove space reservations created in ->iomap_begin. + * + * For filesystems that use delayed allocation, there can be dirty pages over + * the delalloc extent outside the range of a short write but still within the + * delalloc extent allocated for this iomap if the write raced with page + * faults. + * + * Punch out all the delalloc blocks in the range given except for those that + * have dirty data still pending in the page cache - those are going to be + * written and so must still retain the delalloc backing for writeback. + * + * The punch() callback *must* only punch delalloc extents in the range passed + * to it. It must skip over all other types of extents in the range and leave + * them completely unchanged. It must do this punch atomically with respect to + * other extent modifications. + * + * The punch() callback may be called with a folio locked to prevent writeback + * extent allocation racing at the edge of the range we are currently punching. + * The locked folio may or may not cover the range being punched, so it is not + * safe for the punch() callback to lock folios itself. + * + * Lock order is: + * + * inode->i_rwsem (shared or exclusive) + * inode->i_mapping->invalidate_lock (exclusive) + * folio_lock() + * ->punch + * internal filesystem allocation lock + * + * As we are scanning the page cache for data, we don't need to reimplement the + * wheel - mapping_seek_hole_data() does exactly what we need to identify the + * start and end of data ranges correctly even for sub-folio block sizes. This + * byte range based iteration is especially convenient because it means we + * don't have to care about variable size folios, nor where the start or end of + * the data range lies within a folio, if they lie within the same folio or even + * if there are multiple discontiguous data ranges within the folio. + * + * It should be noted that mapping_seek_hole_data() is not aware of EOF, and so + * can return data ranges that exist in the cache beyond EOF. e.g. a page fault + * spanning EOF will initialise the post-EOF data to zeroes and mark it up to + * date. A write page fault can then mark it dirty. If we then fail a write() + * beyond EOF into that up to date cached range, we allocate a delalloc block + * beyond EOF and then have to punch it out. Because the range is up to date, + * mapping_seek_hole_data() will return it, and we will skip the punch because + * the folio is dirty. THis is incorrect - we always need to punch out delalloc + * beyond EOF in this case as writeback will never write back and covert that + * delalloc block beyond EOF. Hence we limit the cached data scan range to EOF, + * resulting in always punching out the range from the EOF to the end of the + * range the iomap spans. + * + * Intervals are of the form [start_byte, end_byte) (i.e. open ended) because it + * matches the intervals returned by mapping_seek_hole_data(). i.e. SEEK_DATA + * returns the start of a data range (start_byte), and SEEK_HOLE(start_byte) + * returns the end of the data range (data_end). Using closed intervals would + * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose + * the code to subtle off-by-one bugs.... + */ +void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, + loff_t end_byte, unsigned flags, struct iomap *iomap, + iomap_punch_t punch) +{ + loff_t punch_start_byte = start_byte; + loff_t scan_end_byte = min(i_size_read(inode), end_byte); + + /* + * The caller must hold invalidate_lock to avoid races with page faults + * re-instantiating folios and dirtying them via ->page_mkwrite whilst + * we walk the cache and perform delalloc extent removal. Failing to do + * this can leave dirty pages with no space reservation in the cache. + */ + lockdep_assert_held_write(&inode->i_mapping->invalidate_lock); + + while (start_byte < scan_end_byte) { + loff_t data_end; + + start_byte = mapping_seek_hole_data(inode->i_mapping, + start_byte, scan_end_byte, SEEK_DATA); + /* + * If there is no more data to scan, all that is left is to + * punch out the remaining range. + * + * Note that mapping_seek_hole_data is only supposed to return + * either an offset or -ENXIO, so WARN on any other error as + * that would be an API change without updating the callers. + */ + if (start_byte == -ENXIO || start_byte == scan_end_byte) break; - pos += ret; - written += ret; + if (WARN_ON_ONCE(start_byte < 0)) + return; + WARN_ON_ONCE(start_byte < punch_start_byte); + WARN_ON_ONCE(start_byte > scan_end_byte); + + /* + * We find the end of this contiguous cached data range by + * seeking from start_byte to the beginning of the next hole. + */ + data_end = mapping_seek_hole_data(inode->i_mapping, start_byte, + scan_end_byte, SEEK_HOLE); + if (WARN_ON_ONCE(data_end < 0)) + return; + + /* + * If we race with post-direct I/O invalidation of the page cache, + * there might be no data left at start_byte. + */ + if (data_end == start_byte) + continue; + + WARN_ON_ONCE(data_end < start_byte); + WARN_ON_ONCE(data_end > scan_end_byte); + + iomap_write_delalloc_scan(inode, &punch_start_byte, start_byte, + data_end, iomap, punch); + + /* The next data search starts at the end of this one. */ + start_byte = data_end; } - return written ? written : ret; + if (punch_start_byte < end_byte) + punch(inode, punch_start_byte, end_byte - punch_start_byte, + iomap); } -EXPORT_SYMBOL_GPL(iomap_file_buffered_write); +EXPORT_SYMBOL_GPL(iomap_write_delalloc_release); -static loff_t -iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap, struct iomap *srcmap) +static int iomap_unshare_iter(struct iomap_iter *iter, + const struct iomap_write_ops *write_ops) { - long status = 0; - loff_t written = 0; + struct iomap *iomap = &iter->iomap; + u64 bytes = iomap_length(iter); + int status; - /* don't bother with blocks that are not shared to start with */ - if (!(iomap->flags & IOMAP_F_SHARED)) - return length; - /* don't bother with holes or unwritten extents */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) - return length; + if (!iomap_want_unshare_iter(iter)) + return iomap_iter_advance(iter, bytes); do { - unsigned long offset = offset_in_page(pos); - unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length); - struct page *page; + struct folio *folio; + size_t offset; + bool ret; - status = iomap_write_begin(inode, pos, bytes, - IOMAP_WRITE_F_UNSHARE, &page, iomap, srcmap); + bytes = min_t(u64, SIZE_MAX, bytes); + status = iomap_write_begin(iter, write_ops, &folio, &offset, + &bytes); if (unlikely(status)) return status; + if (iomap->flags & IOMAP_F_STALE) + break; - status = iomap_write_end(inode, pos, bytes, bytes, page, iomap, - srcmap); - if (unlikely(status <= 0)) { - if (WARN_ON_ONCE(status == 0)) - return -EIO; - return status; - } + ret = iomap_write_end(iter, bytes, bytes, folio); + __iomap_put_folio(iter, write_ops, bytes, folio); + if (WARN_ON_ONCE(!ret)) + return -EIO; cond_resched(); - pos += status; - written += status; - length -= status; + balance_dirty_pages_ratelimited(iter->inode->i_mapping); - balance_dirty_pages_ratelimited(inode->i_mapping); - } while (length); + status = iomap_iter_advance(iter, bytes); + if (status) + break; + } while ((bytes = iomap_length(iter)) > 0); - return written; + return status; } int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, - const struct iomap_ops *ops) + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops) { - loff_t ret; + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .flags = IOMAP_WRITE | IOMAP_UNSHARE, + }; + loff_t size = i_size_read(inode); + int ret; - while (len) { - ret = iomap_apply(inode, pos, len, IOMAP_WRITE, ops, NULL, - iomap_unshare_actor); - if (ret <= 0) - return ret; - pos += ret; - len -= ret; - } + if (pos < 0 || pos >= size) + return 0; - return 0; + iter.len = min(len, size - pos); + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.status = iomap_unshare_iter(&iter, write_ops); + return ret; } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset, - unsigned bytes, struct iomap *iomap, struct iomap *srcmap) +/* + * Flush the remaining range of the iter and mark the current mapping stale. + * This is used when zero range sees an unwritten mapping that may have had + * dirty pagecache over it. + */ +static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i) { - struct page *page; - int status; - - status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap); - if (status) - return status; + struct address_space *mapping = i->inode->i_mapping; + loff_t end = i->pos + i->len - 1; - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap); + i->iomap.flags |= IOMAP_F_STALE; + return filemap_write_and_wait_range(mapping, i->pos, end); } -static loff_t -iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, - void *data, struct iomap *iomap, struct iomap *srcmap) +static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, + const struct iomap_write_ops *write_ops) { - bool *did_zero = data; - loff_t written = 0; + u64 bytes = iomap_length(iter); int status; - /* already zeroed? we're done. */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) - return count; - do { - unsigned offset, bytes; + struct folio *folio; + size_t offset; + bool ret; - offset = offset_in_page(pos); - bytes = min_t(loff_t, PAGE_SIZE - offset, count); - - if (IS_DAX(inode)) - status = dax_iomap_zero(pos, offset, bytes, iomap); - else - status = iomap_zero(inode, pos, offset, bytes, iomap, - srcmap); - if (status < 0) + bytes = min_t(u64, SIZE_MAX, bytes); + status = iomap_write_begin(iter, write_ops, &folio, &offset, + &bytes); + if (status) return status; + if (iter->iomap.flags & IOMAP_F_STALE) + break; + + /* a NULL folio means we're done with a folio batch */ + if (!folio) { + status = iomap_iter_advance_full(iter); + break; + } + + /* warn about zeroing folios beyond eof that won't write back */ + WARN_ON_ONCE(folio_pos(folio) > iter->inode->i_size); + + trace_iomap_zero_iter(iter->inode, folio_pos(folio) + offset, + bytes); + + folio_zero_range(folio, offset, bytes); + folio_mark_accessed(folio); + + ret = iomap_write_end(iter, bytes, bytes, folio); + __iomap_put_folio(iter, write_ops, bytes, folio); + if (WARN_ON_ONCE(!ret)) + return -EIO; + + status = iomap_iter_advance(iter, bytes); + if (status) + break; + } while ((bytes = iomap_length(iter)) > 0); - pos += bytes; - count -= bytes; - written += bytes; - if (did_zero) - *did_zero = true; - } while (count > 0); + if (did_zero) + *did_zero = true; + return status; +} - return written; +loff_t +iomap_fill_dirty_folios( + struct iomap_iter *iter, + loff_t offset, + loff_t length) +{ + struct address_space *mapping = iter->inode->i_mapping; + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + length - 1) >> PAGE_SHIFT; + + iter->fbatch = kmalloc(sizeof(struct folio_batch), GFP_KERNEL); + if (!iter->fbatch) + return offset + length; + folio_batch_init(iter->fbatch); + + filemap_get_folios_dirty(mapping, &start, end, iter->fbatch); + return (start << PAGE_SHIFT); } +EXPORT_SYMBOL_GPL(iomap_fill_dirty_folios); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, - const struct iomap_ops *ops) + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private) { - loff_t ret; + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + .private = private, + }; + struct address_space *mapping = inode->i_mapping; + int ret; + bool range_dirty; - while (len > 0) { - ret = iomap_apply(inode, pos, len, IOMAP_ZERO, - ops, did_zero, iomap_zero_range_actor); - if (ret <= 0) - return ret; + /* + * To avoid an unconditional flush, check pagecache state and only flush + * if dirty and the fs returns a mapping that might convert on + * writeback. + */ + range_dirty = filemap_range_needs_writeback(mapping, iter.pos, + iter.pos + iter.len - 1); + while ((ret = iomap_iter(&iter, ops)) > 0) { + const struct iomap *srcmap = iomap_iter_srcmap(&iter); + + if (WARN_ON_ONCE(iter.fbatch && + srcmap->type != IOMAP_UNWRITTEN)) + return -EIO; + + if (!iter.fbatch && + (srcmap->type == IOMAP_HOLE || + srcmap->type == IOMAP_UNWRITTEN)) { + s64 status; + + if (range_dirty) { + range_dirty = false; + status = iomap_zero_iter_flush_and_stale(&iter); + } else { + status = iomap_iter_advance_full(&iter); + } + iter.status = status; + continue; + } - pos += ret; - len -= ret; + iter.status = iomap_zero_iter(&iter, did_zero, write_ops); } - - return 0; + return ret; } EXPORT_SYMBOL_GPL(iomap_zero_range); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - const struct iomap_ops *ops) + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private) { unsigned int blocksize = i_blocksize(inode); unsigned int off = pos & (blocksize - 1); @@ -1010,609 +1626,294 @@ iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, /* Block boundary? Nothing to do */ if (!off) return 0; - return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops); + return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops, + write_ops, private); } EXPORT_SYMBOL_GPL(iomap_truncate_page); -static loff_t -iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap, struct iomap *srcmap) +static int iomap_folio_mkwrite_iter(struct iomap_iter *iter, + struct folio *folio) { - struct page *page = data; + loff_t length = iomap_length(iter); int ret; - if (iomap->flags & IOMAP_F_BUFFER_HEAD) { - ret = __block_write_begin_int(page, pos, length, NULL, iomap); + if (iter->iomap.flags & IOMAP_F_BUFFER_HEAD) { + ret = __block_write_begin_int(folio, iter->pos, length, NULL, + &iter->iomap); if (ret) return ret; - block_commit_write(page, 0, length); + block_commit_write(folio, 0, length); } else { - WARN_ON_ONCE(!PageUptodate(page)); - iomap_page_create(inode, page); - set_page_dirty(page); + WARN_ON_ONCE(!folio_test_uptodate(folio)); + folio_mark_dirty(folio); } - return length; + return iomap_iter_advance(iter, length); } -vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops, + void *private) { - struct page *page = vmf->page; - struct inode *inode = file_inode(vmf->vma->vm_file); - unsigned long length; - loff_t offset; + struct iomap_iter iter = { + .inode = file_inode(vmf->vma->vm_file), + .flags = IOMAP_WRITE | IOMAP_FAULT, + .private = private, + }; + struct folio *folio = page_folio(vmf->page); ssize_t ret; - lock_page(page); - ret = page_mkwrite_check_truncate(page, inode); + folio_lock(folio); + ret = folio_mkwrite_check_truncate(folio, iter.inode); if (ret < 0) goto out_unlock; - length = ret; - - offset = page_offset(page); - while (length > 0) { - ret = iomap_apply(inode, offset, length, - IOMAP_WRITE | IOMAP_FAULT, ops, page, - iomap_page_mkwrite_actor); - if (unlikely(ret <= 0)) - goto out_unlock; - offset += ret; - length -= ret; - } + iter.pos = folio_pos(folio); + iter.len = ret; + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.status = iomap_folio_mkwrite_iter(&iter, folio); - wait_for_stable_page(page); + if (ret < 0) + goto out_unlock; + folio_wait_stable(folio); return VM_FAULT_LOCKED; out_unlock: - unlock_page(page); - return block_page_mkwrite_return(ret); + folio_unlock(folio); + return vmf_fs_error(ret); } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); -static void -iomap_finish_page_writeback(struct inode *inode, struct page *page, - int error) -{ - struct iomap_page *iop = to_iomap_page(page); - - if (error) { - SetPageError(page); - mapping_set_error(inode->i_mapping, -EIO); - } - - WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop); - WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0); - - if (!iop || atomic_dec_and_test(&iop->write_count)) - end_page_writeback(page); -} - -/* - * We're now finished for good with this ioend structure. Update the page - * state, release holds on bios, and finally free up memory. Do not use the - * ioend after this. - */ -static void -iomap_finish_ioend(struct iomap_ioend *ioend, int error) +static void iomap_writeback_init(struct inode *inode, struct folio *folio) { - struct inode *inode = ioend->io_inode; - struct bio *bio = &ioend->io_inline_bio; - struct bio *last = ioend->io_bio, *next; - u64 start = bio->bi_iter.bi_sector; - loff_t offset = ioend->io_offset; - bool quiet = bio_flagged(bio, BIO_QUIET); - - for (bio = &ioend->io_inline_bio; bio; bio = next) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct iomap_folio_state *ifs = folio->private; + WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); + if (ifs) { + WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0); /* - * For the last bio, bi_private points to the ioend, so we - * need to explicitly end the iteration here. + * Set this to the folio size. After processing the folio for + * writeback in iomap_writeback_folio(), we'll subtract any + * ranges not written back. + * + * We do this because otherwise, we would have to atomically + * increment ifs->write_bytes_pending every time a range in the + * folio needs to be written back. */ - if (bio == last) - next = NULL; - else - next = bio->bi_private; - - /* walk each page on bio, ending page IO on them */ - bio_for_each_segment_all(bv, bio, iter_all) - iomap_finish_page_writeback(inode, bv->bv_page, error); - bio_put(bio); - } - /* The ioend has been freed by bio_put() */ - - if (unlikely(error && !quiet)) { - printk_ratelimited(KERN_ERR -"%s: writeback error on inode %lu, offset %lld, sector %llu", - inode->i_sb->s_id, inode->i_ino, offset, start); + atomic_set(&ifs->write_bytes_pending, folio_size(folio)); } } -void -iomap_finish_ioends(struct iomap_ioend *ioend, int error) +void iomap_finish_folio_write(struct inode *inode, struct folio *folio, + size_t len) { - struct list_head tmp; + struct iomap_folio_state *ifs = folio->private; - list_replace_init(&ioend->io_list, &tmp); - iomap_finish_ioend(ioend, error); + WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); + WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0); - while (!list_empty(&tmp)) { - ioend = list_first_entry(&tmp, struct iomap_ioend, io_list); - list_del_init(&ioend->io_list); - iomap_finish_ioend(ioend, error); - } + if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending)) + folio_end_writeback(folio); } -EXPORT_SYMBOL_GPL(iomap_finish_ioends); +EXPORT_SYMBOL_GPL(iomap_finish_folio_write); -/* - * We can merge two adjacent ioends if they have the same set of work to do. - */ -static bool -iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next) +static int iomap_writeback_range(struct iomap_writepage_ctx *wpc, + struct folio *folio, u64 pos, u32 rlen, u64 end_pos, + size_t *bytes_submitted) { - if (ioend->io_bio->bi_status != next->io_bio->bi_status) - return false; - if ((ioend->io_flags & IOMAP_F_SHARED) ^ - (next->io_flags & IOMAP_F_SHARED)) - return false; - if ((ioend->io_type == IOMAP_UNWRITTEN) ^ - (next->io_type == IOMAP_UNWRITTEN)) - return false; - if (ioend->io_offset + ioend->io_size != next->io_offset) - return false; - return true; -} - -void -iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends, - void (*merge_private)(struct iomap_ioend *ioend, - struct iomap_ioend *next)) -{ - struct iomap_ioend *next; - - INIT_LIST_HEAD(&ioend->io_list); + do { + ssize_t ret; - while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend, - io_list))) { - if (!iomap_ioend_can_merge(ioend, next)) - break; - list_move_tail(&next->io_list, &ioend->io_list); - ioend->io_size += next->io_size; - if (next->io_private && merge_private) - merge_private(ioend, next); - } -} -EXPORT_SYMBOL_GPL(iomap_ioend_try_merge); + ret = wpc->ops->writeback_range(wpc, folio, pos, rlen, end_pos); + if (WARN_ON_ONCE(ret == 0 || ret > rlen)) + return -EIO; + if (ret < 0) + return ret; + rlen -= ret; + pos += ret; -static int -iomap_ioend_compare(void *priv, struct list_head *a, struct list_head *b) -{ - struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list); - struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list); + /* + * Holes are not written back by ->writeback_range, so track + * if we did handle anything that is not a hole here. + */ + if (wpc->iomap.type != IOMAP_HOLE) + *bytes_submitted += ret; + } while (rlen); - if (ia->io_offset < ib->io_offset) - return -1; - if (ia->io_offset > ib->io_offset) - return 1; return 0; } -void -iomap_sort_ioends(struct list_head *ioend_list) -{ - list_sort(NULL, ioend_list, iomap_ioend_compare); -} -EXPORT_SYMBOL_GPL(iomap_sort_ioends); - -static void iomap_writepage_end_bio(struct bio *bio) -{ - struct iomap_ioend *ioend = bio->bi_private; - - iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status)); -} - /* - * Submit the final bio for an ioend. + * Check interaction of the folio with the file end. * - * If @error is non-zero, it means that we have a situation where some part of - * the submission process has failed after we have marked paged for writeback - * and unlocked them. In this situation, we need to fail the bio instead of - * submitting it. This typically only happens on a filesystem shutdown. + * If the folio is entirely beyond i_size, return false. If it straddles + * i_size, adjust end_pos and zero all data beyond i_size. */ -static int -iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend, - int error) +static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode, + u64 *end_pos) { - ioend->io_bio->bi_private = ioend; - ioend->io_bio->bi_end_io = iomap_writepage_end_bio; + u64 isize = i_size_read(inode); + + if (*end_pos > isize) { + size_t poff = offset_in_folio(folio, isize); + pgoff_t end_index = isize >> PAGE_SHIFT; - if (wpc->ops->prepare_ioend) - error = wpc->ops->prepare_ioend(ioend, error); - if (error) { /* - * If we are failing the IO now, just mark the ioend with an - * error and finish it. This will run IO completion immediately - * as there is only one reference to the ioend at this point in - * time. + * If the folio is entirely ouside of i_size, skip it. + * + * This can happen due to a truncate operation that is in + * progress and in that case truncate will finish it off once + * we've dropped the folio lock. + * + * Note that the pgoff_t used for end_index is an unsigned long. + * If the given offset is greater than 16TB on a 32-bit system, + * then if we checked if the folio is fully outside i_size with + * "if (folio->index >= end_index + 1)", "end_index + 1" would + * overflow and evaluate to 0. Hence this folio would be + * redirtied and written out repeatedly, which would result in + * an infinite loop; the user program performing this operation + * would hang. Instead, we can detect this situation by + * checking if the folio is totally beyond i_size or if its + * offset is just equal to the EOF. */ - ioend->io_bio->bi_status = errno_to_blk_status(error); - bio_endio(ioend->io_bio); - return error; - } + if (folio->index > end_index || + (folio->index == end_index && poff == 0)) + return false; - submit_bio(ioend->io_bio); - return 0; -} - -static struct iomap_ioend * -iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, - loff_t offset, sector_t sector, struct writeback_control *wbc) -{ - struct iomap_ioend *ioend; - struct bio *bio; - - bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &iomap_ioend_bioset); - bio_set_dev(bio, wpc->iomap.bdev); - bio->bi_iter.bi_sector = sector; - bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); - bio->bi_write_hint = inode->i_write_hint; - wbc_init_bio(wbc, bio); - - ioend = container_of(bio, struct iomap_ioend, io_inline_bio); - INIT_LIST_HEAD(&ioend->io_list); - ioend->io_type = wpc->iomap.type; - ioend->io_flags = wpc->iomap.flags; - ioend->io_inode = inode; - ioend->io_size = 0; - ioend->io_offset = offset; - ioend->io_private = NULL; - ioend->io_bio = bio; - return ioend; -} - -/* - * Allocate a new bio, and chain the old bio to the new one. - * - * Note that we have to do perform the chaining in this unintuitive order - * so that the bi_private linkage is set up in the right direction for the - * traversal in iomap_finish_ioend(). - */ -static struct bio * -iomap_chain_bio(struct bio *prev) -{ - struct bio *new; - - new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); - bio_copy_dev(new, prev);/* also copies over blkcg information */ - new->bi_iter.bi_sector = bio_end_sector(prev); - new->bi_opf = prev->bi_opf; - new->bi_write_hint = prev->bi_write_hint; - - bio_chain(prev, new); - bio_get(prev); /* for iomap_finish_ioend */ - submit_bio(prev); - return new; -} + /* + * 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. + * + * Also adjust the end_pos to the end of file and skip writeback + * for all blocks entirely beyond i_size. + */ + folio_zero_segment(folio, poff, folio_size(folio)); + *end_pos = isize; + } -static bool -iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, - sector_t sector) -{ - if ((wpc->iomap.flags & IOMAP_F_SHARED) != - (wpc->ioend->io_flags & IOMAP_F_SHARED)) - return false; - if (wpc->iomap.type != wpc->ioend->io_type) - return false; - if (offset != wpc->ioend->io_offset + wpc->ioend->io_size) - return false; - if (sector != bio_end_sector(wpc->ioend->io_bio)) - return false; return true; } -/* - * Test to see if we have an existing ioend structure that we could append to - * first, otherwise finish off the current ioend and start another. - */ -static void -iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page, - struct iomap_page *iop, struct iomap_writepage_ctx *wpc, - struct writeback_control *wbc, struct list_head *iolist) +int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio) { - sector_t sector = iomap_sector(&wpc->iomap, offset); - unsigned len = i_blocksize(inode); - unsigned poff = offset & (PAGE_SIZE - 1); - bool merged, same_page = false; - - if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, offset, sector)) { - if (wpc->ioend) - list_add(&wpc->ioend->io_list, iolist); - wpc->ioend = iomap_alloc_ioend(inode, wpc, offset, sector, wbc); - } - - merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, - &same_page); - if (iop && !same_page) - atomic_inc(&iop->write_count); + struct iomap_folio_state *ifs = folio->private; + struct inode *inode = wpc->inode; + u64 pos = folio_pos(folio); + u64 end_pos = pos + folio_size(folio); + u64 end_aligned = 0; + size_t bytes_submitted = 0; + int error = 0; + u32 rlen; + + WARN_ON_ONCE(!folio_test_locked(folio)); + WARN_ON_ONCE(folio_test_dirty(folio)); + WARN_ON_ONCE(folio_test_writeback(folio)); + + trace_iomap_writeback_folio(inode, pos, folio_size(folio)); + + if (!iomap_writeback_handle_eof(folio, inode, &end_pos)) + return 0; + WARN_ON_ONCE(end_pos <= pos); - if (!merged) { - if (bio_full(wpc->ioend->io_bio, len)) { - wpc->ioend->io_bio = - iomap_chain_bio(wpc->ioend->io_bio); + if (i_blocks_per_folio(inode, folio) > 1) { + if (!ifs) { + ifs = ifs_alloc(inode, folio, 0); + iomap_set_range_dirty(folio, 0, end_pos - pos); } - bio_add_page(wpc->ioend->io_bio, page, len, poff); - } - - wpc->ioend->io_size += len; - wbc_account_cgroup_owner(wbc, page, len); -} -/* - * We implement an immediate ioend submission policy here to avoid needing to - * chain multiple ioends and hence nest mempool allocations which can violate - * forward progress guarantees we need to provide. The current ioend we are - * adding blocks to is cached on the writepage context, and if the new block - * does not append to the cached ioend it will create a new ioend and cache that - * instead. - * - * If a new ioend is created and cached, the old ioend is returned and queued - * locally for submission once the entire page is processed or an error has been - * detected. While ioends are submitted immediately after they are completed, - * batching optimisations are provided by higher level block plugging. - * - * At the end of a writeback pass, there will be a cached ioend remaining on the - * writepage context that the caller will need to submit. - */ -static int -iomap_writepage_map(struct iomap_writepage_ctx *wpc, - struct writeback_control *wbc, struct inode *inode, - struct page *page, u64 end_offset) -{ - struct iomap_page *iop = to_iomap_page(page); - struct iomap_ioend *ioend, *next; - unsigned len = i_blocksize(inode); - u64 file_offset; /* file offset of page */ - int error = 0, count = 0, i; - LIST_HEAD(submit_list); - - WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop); - WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0); + iomap_writeback_init(inode, folio); + } /* - * Walk through the page to find areas to write back. If we run off the - * end of the current map or find the current map invalid, grab a new - * one. + * Set the writeback bit ASAP, as the I/O completion for the single + * block per folio case happen hit as soon as we're submitting the bio. */ - for (i = 0, file_offset = page_offset(page); - i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset; - i++, file_offset += len) { - if (iop && !test_bit(i, iop->uptodate)) - continue; + folio_start_writeback(folio); - error = wpc->ops->map_blocks(wpc, inode, file_offset); + /* + * Walk through the folio to find dirty areas to write back. + */ + end_aligned = round_up(end_pos, i_blocksize(inode)); + while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { + error = iomap_writeback_range(wpc, folio, pos, rlen, end_pos, + &bytes_submitted); if (error) break; - if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE)) - continue; - if (wpc->iomap.type == IOMAP_HOLE) - continue; - iomap_add_to_ioend(inode, file_offset, page, iop, wpc, wbc, - &submit_list); - count++; + pos += rlen; } - WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); - WARN_ON_ONCE(!PageLocked(page)); - WARN_ON_ONCE(PageWriteback(page)); + if (bytes_submitted) + wpc->nr_folios++; /* - * We cannot cancel the ioend directly here on error. We may have - * already set other pages under writeback and hence we have to run I/O - * completion to mark the error state of the pages under writeback - * appropriately. + * We can have dirty bits set past end of file in page_mkwrite path + * while mapping the last partial folio. Hence it's better to clear + * all the dirty bits in the folio here. */ - if (unlikely(error)) { - if (!count) { - /* - * If the current page hasn't been added to ioend, it - * won't be affected by I/O completions and we must - * discard and unlock it right here. - */ - if (wpc->ops->discard_page) - wpc->ops->discard_page(page); - ClearPageUptodate(page); - unlock_page(page); - goto done; - } - - /* - * If the page was not fully cleaned, we need to ensure that the - * higher layers come back to it correctly. That means we need - * to keep the page dirty, and for WB_SYNC_ALL writeback we need - * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed - * so another attempt to write this page in this writeback sweep - * will be made. - */ - set_page_writeback_keepwrite(page); - } else { - clear_page_dirty_for_io(page); - set_page_writeback(page); - } - - unlock_page(page); + iomap_clear_range_dirty(folio, 0, folio_size(folio)); /* - * Preserve the original error if there was one, otherwise catch - * submission errors here and propagate into subsequent ioend - * submissions. + * Usually the writeback bit is cleared by the I/O completion handler. + * But we may end up either not actually writing any blocks, or (when + * there are multiple blocks in a folio) all I/O might have finished + * already at this point. In that case we need to clear the writeback + * bit ourselves right after unlocking the page. */ - list_for_each_entry_safe(ioend, next, &submit_list, io_list) { - int error2; - - list_del_init(&ioend->io_list); - error2 = iomap_submit_ioend(wpc, ioend, error); - if (error2 && !error) - error = error2; + if (ifs) { + /* + * Subtract any bytes that were initially accounted to + * write_bytes_pending but skipped for writeback. + */ + size_t bytes_not_submitted = folio_size(folio) - + bytes_submitted; + + if (bytes_not_submitted) + iomap_finish_folio_write(inode, folio, + bytes_not_submitted); + } else if (!bytes_submitted) { + folio_end_writeback(folio); } - /* - * We can end up here with no error and nothing to write only if we race - * with a partial page truncate on a sub-page block sized filesystem. - */ - if (!count) - end_page_writeback(page); -done: - mapping_set_error(page->mapping, error); + mapping_set_error(inode->i_mapping, error); return error; } +EXPORT_SYMBOL_GPL(iomap_writeback_folio); -/* - * Write out a dirty page. - * - * For delalloc space on the page we need to allocate space and flush it. - * For unwritten space on the page we need to start the conversion to - * regular allocated space. - */ -static int -iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) +int +iomap_writepages(struct iomap_writepage_ctx *wpc) { - struct iomap_writepage_ctx *wpc = data; - struct inode *inode = page->mapping->host; - pgoff_t end_index; - u64 end_offset; - loff_t offset; - - trace_iomap_writepage(inode, page_offset(page), PAGE_SIZE); + struct address_space *mapping = wpc->inode->i_mapping; + struct folio *folio = NULL; + int error; /* - * Refuse to write the page out if we are called from reclaim context. - * - * This avoids stack overflows when called from deeply used stacks in - * random callers for direct reclaim or memcg reclaim. We explicitly - * allow reclaim from kswapd as the stack usage there is relatively low. - * - * This should never happen except in the case of a VM regression so - * warn about it. + * Writeback from reclaim context should never happen except in the case + * of a VM regression so warn about it and refuse to write the data. */ - if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == + if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC | PF_KSWAPD)) == PF_MEMALLOC)) - goto redirty; + return -EIO; - /* - * Given that we do not allow direct reclaim to call us, we should - * never be called in a recursive filesystem reclaim context. - */ - if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) - goto redirty; + while ((folio = writeback_iter(mapping, wpc->wbc, folio, &error))) { + error = iomap_writeback_folio(wpc, folio); + folio_unlock(folio); + } /* - * Is this page beyond the end of the file? + * If @error is non-zero, it means that we have a situation where some + * part of the submission process has failed after we've marked pages + * for writeback. * - * The page index is less than the end_index, adjust the end_offset - * to the highest offset that this page should represent. - * ----------------------------------------------------- - * | file mapping | <EOF> | - * ----------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | | - * ^--------------------------------^----------|-------- - * | desired writeback range | see else | - * ---------------------------------^------------------| + * We cannot cancel the writeback directly in that case, so always call + * ->writeback_submit to run the I/O completion handler to clear the + * writeback bit and let the file system proess the errors. */ - offset = i_size_read(inode); - end_index = offset >> PAGE_SHIFT; - if (page->index < end_index) - end_offset = (loff_t)(page->index + 1) << PAGE_SHIFT; - else { - /* - * Check whether the page to write out is beyond or straddles - * i_size or not. - * ------------------------------------------------------- - * | file mapping | <EOF> | - * ------------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | Beyond | - * ^--------------------------------^-----------|--------- - * | | Straddles | - * ---------------------------------^-----------|--------| - */ - unsigned offset_into_page = offset & (PAGE_SIZE - 1); - - /* - * Skip the page if it is fully outside i_size, e.g. due to a - * truncate operation that is in progress. We must redirty the - * page so that reclaim stops reclaiming it. Otherwise - * iomap_vm_releasepage() is called on it and gets confused. - * - * Note that the end_index is unsigned long, it would overflow - * if the given offset is greater than 16TB on 32-bit system - * and if we do check the page is fully outside i_size or not - * via "if (page->index >= end_index + 1)" as "end_index + 1" - * will be evaluated to 0. Hence this page will be redirtied - * and be written out repeatedly which would result in an - * infinite loop, the user program that perform this operation - * will hang. Instead, we can verify this situation by checking - * if the page to write is totally beyond the i_size or if it's - * offset is just equal to the EOF. - */ - if (page->index > end_index || - (page->index == end_index && offset_into_page == 0)) - goto redirty; - - /* - * The page 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." - */ - zero_user_segment(page, offset_into_page, PAGE_SIZE); - - /* Adjust the end_offset to the end of file */ - end_offset = offset; - } - - return iomap_writepage_map(wpc, wbc, inode, page, end_offset); - -redirty: - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} - -int -iomap_writepage(struct page *page, struct writeback_control *wbc, - struct iomap_writepage_ctx *wpc, - const struct iomap_writeback_ops *ops) -{ - int ret; - - wpc->ops = ops; - ret = iomap_do_writepage(page, wbc, wpc); - if (!wpc->ioend) - return ret; - return iomap_submit_ioend(wpc, wpc->ioend, ret); -} -EXPORT_SYMBOL_GPL(iomap_writepage); - -int -iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, - struct iomap_writepage_ctx *wpc, - const struct iomap_writeback_ops *ops) -{ - int ret; - - wpc->ops = ops; - ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc); - if (!wpc->ioend) - return ret; - return iomap_submit_ioend(wpc, wpc->ioend, ret); + if (wpc->wb_ctx) + return wpc->ops->writeback_submit(wpc, error); + return error; } EXPORT_SYMBOL_GPL(iomap_writepages); - -static int __init iomap_init(void) -{ - return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), - offsetof(struct iomap_ioend, io_inline_bio), - BIOSET_NEED_BVECS); -} -fs_initcall(iomap_init); |