diff options
Diffstat (limited to 'fs/iomap')
| -rw-r--r-- | fs/iomap/Makefile | 17 | ||||
| -rw-r--r-- | fs/iomap/apply.c | 99 | ||||
| -rw-r--r-- | fs/iomap/buffered-io.c | 1573 | ||||
| -rw-r--r-- | fs/iomap/direct-io.c | 610 | ||||
| -rw-r--r-- | fs/iomap/fiemap.c | 140 | ||||
| -rw-r--r-- | fs/iomap/seek.c | 205 | ||||
| -rw-r--r-- | fs/iomap/swapfile.c | 195 | ||||
| -rw-r--r-- | fs/iomap/trace.c | 12 | ||||
| -rw-r--r-- | fs/iomap/trace.h | 187 |
9 files changed, 3038 insertions, 0 deletions
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile new file mode 100644 index 000000000..eef2722d9 --- /dev/null +++ b/fs/iomap/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# Copyright (c) 2019 Oracle. +# All Rights Reserved. +# + +ccflags-y += -I $(srctree)/$(src) # needed for trace events + +obj-$(CONFIG_FS_IOMAP) += iomap.o + +iomap-y += trace.o \ + apply.o \ + buffered-io.o \ + direct-io.o \ + fiemap.o \ + seek.o +iomap-$(CONFIG_SWAP) += swapfile.o diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c new file mode 100644 index 000000000..26ab65631 --- /dev/null +++ b/fs/iomap/apply.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010 Red Hat, Inc. + * Copyright (c) 2016-2018 Christoph Hellwig. + */ +#include <linux/module.h> +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/iomap.h> +#include "trace.h" + +/* + * Execute a iomap write on a segment of the mapping that spans a + * contiguous range of pages that have identical block mapping state. + * + * This avoids the need to map pages individually, do individual allocations + * for each page and most importantly avoid the need for filesystem specific + * locking per page. Instead, all the operations are amortised over the entire + * range of pages. It is assumed that the filesystems will lock whatever + * resources they require in the iomap_begin call, and release them in the + * iomap_end call. + */ +loff_t +iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, + const struct iomap_ops *ops, void *data, iomap_actor_t actor) +{ + struct iomap iomap = { .type = IOMAP_HOLE }; + struct iomap srcmap = { .type = IOMAP_HOLE }; + loff_t written = 0, ret; + u64 end; + + trace_iomap_apply(inode, pos, length, flags, ops, actor, _RET_IP_); + + /* + * Need to map a range from start position for length bytes. This can + * span multiple pages - it is only guaranteed to return a range of a + * single type of pages (e.g. all into a hole, all mapped or all + * unwritten). Failure at this point has nothing to undo. + * + * If allocation is required for this range, reserve the space now so + * that the allocation is guaranteed to succeed later on. Once we copy + * the data into the page cache pages, then we cannot fail otherwise we + * expose transient stale data. If the reserve fails, we can safely + * back out at this point as there is nothing to undo. + */ + ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap); + if (ret) + return ret; + if (WARN_ON(iomap.offset > pos)) { + written = -EIO; + goto out; + } + if (WARN_ON(iomap.length == 0)) { + written = -EIO; + goto out; + } + + trace_iomap_apply_dstmap(inode, &iomap); + if (srcmap.type != IOMAP_HOLE) + trace_iomap_apply_srcmap(inode, &srcmap); + + /* + * Cut down the length to the one actually provided by the filesystem, + * as it might not be able to give us the whole size that we requested. + */ + end = iomap.offset + iomap.length; + if (srcmap.type != IOMAP_HOLE) + end = min(end, srcmap.offset + srcmap.length); + if (pos + length > end) + length = end - pos; + + /* + * Now that we have guaranteed that the space allocation will succeed, + * we can do the copy-in page by page without having to worry about + * failures exposing transient data. + * + * To support COW operations, we read in data for partially blocks from + * the srcmap if the file system filled it in. In that case we the + * length needs to be limited to the earlier of the ends of the iomaps. + * If the file system did not provide a srcmap we pass in the normal + * iomap into the actors so that they don't need to have special + * handling for the two cases. + */ + written = actor(inode, pos, length, data, &iomap, + srcmap.type != IOMAP_HOLE ? &srcmap : &iomap); + +out: + /* + * Now the data has been copied, commit the range we've copied. This + * should not fail unless the filesystem has had a fatal error. + */ + if (ops->iomap_end) { + ret = ops->iomap_end(inode, pos, length, + written > 0 ? written : 0, + flags, &iomap); + } + + return written ? written : ret; +} diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c new file mode 100644 index 000000000..86297f59b --- /dev/null +++ b/fs/iomap/buffered-io.c @@ -0,0 +1,1573 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010 Red Hat, Inc. + * Copyright (C) 2016-2019 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 "trace.h" + +#include "../internal.h" + +/* + * Structure allocated for each page or THP when block size < page size + * to track sub-page uptodate status and I/O completions. + */ +struct iomap_page { + atomic_t read_bytes_pending; + atomic_t write_bytes_pending; + spinlock_t uptodate_lock; + unsigned long uptodate[]; +}; + +static inline struct iomap_page *to_iomap_page(struct page *page) +{ + /* + * per-block data is stored in the head page. Callers should + * not be dealing with tail pages (and if they are, they can + * call thp_head() first. + */ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + + if (page_has_private(page)) + return (struct iomap_page *)page_private(page); + return NULL; +} + +static struct bio_set iomap_ioend_bioset; + +static struct iomap_page * +iomap_page_create(struct inode *inode, struct page *page) +{ + struct iomap_page *iop = to_iomap_page(page); + unsigned int nr_blocks = i_blocks_per_page(inode, page); + + if (iop || nr_blocks <= 1) + return iop; + + iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)), + GFP_NOFS | __GFP_NOFAIL); + spin_lock_init(&iop->uptodate_lock); + if (PageUptodate(page)) + bitmap_fill(iop->uptodate, nr_blocks); + attach_page_private(page, iop); + return iop; +} + +static void +iomap_page_release(struct page *page) +{ + struct iomap_page *iop = detach_page_private(page); + unsigned int nr_blocks = i_blocks_per_page(page->mapping->host, page); + + if (!iop) + return; + WARN_ON_ONCE(atomic_read(&iop->read_bytes_pending)); + WARN_ON_ONCE(atomic_read(&iop->write_bytes_pending)); + WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) != + PageUptodate(page)); + kfree(iop); +} + +/* + * Calculate the range inside the page that we actually need to read. + */ +static void +iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, + loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp) +{ + 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); + 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 + * 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++; + } + + /* 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 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 (first <= end && last > end) + plen -= (last - end) * block_size; + } + + *offp = poff; + *lenp = plen; +} + +static void +iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len) +{ + 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; + unsigned long flags; + + spin_lock_irqsave(&iop->uptodate_lock, flags); + bitmap_set(iop->uptodate, first, last - first + 1); + if (bitmap_full(iop->uptodate, i_blocks_per_page(inode, page))) + SetPageUptodate(page); + spin_unlock_irqrestore(&iop->uptodate_lock, flags); +} + +static void +iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +{ + if (PageError(page)) + return; + + if (page_has_private(page)) + iomap_iop_set_range_uptodate(page, off, len); + else + SetPageUptodate(page); +} + +static void +iomap_read_page_end_io(struct bio_vec *bvec, 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); + } + + if (!iop || atomic_sub_and_test(bvec->bv_len, &iop->read_bytes_pending)) + unlock_page(page); +} + +static void +iomap_read_end_io(struct bio *bio) +{ + int error = blk_status_to_errno(bio->bi_status); + struct bio_vec *bvec; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bvec, bio, iter_all) + iomap_read_page_end_io(bvec, error); + bio_put(bio); +} + +struct iomap_readpage_ctx { + struct page *cur_page; + bool cur_page_in_bio; + struct bio *bio; + struct readahead_control *rac; +}; + +static void +iomap_read_inline_data(struct inode *inode, struct page *page, + struct iomap *iomap) +{ + size_t size = i_size_read(inode); + void *addr; + + if (PageUptodate(page)) + return; + + BUG_ON(page->index); + BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data)); + + addr = kmap_atomic(page); + memcpy(addr, iomap->inline_data, size); + memset(addr + size, 0, PAGE_SIZE - size); + kunmap_atomic(addr); + SetPageUptodate(page); +} + +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); +} + +static loff_t +iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, + struct iomap *iomap, struct iomap *srcmap) +{ + 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; + + 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; + } + + ctx->cur_page_in_bio = true; + if (iop) + atomic_add(plen, &iop->read_bytes_pending); + + /* Try to merge into a previous segment if we can */ + sector = iomap_sector(iomap, pos); + if (ctx->bio && bio_end_sector(ctx->bio) == sector) { + if (__bio_try_merge_page(ctx->bio, page, plen, poff, + &same_page)) + goto done; + is_contig = true; + } + + if (!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; + + if (ctx->bio) + submit_bio(ctx->bio); + + 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; + } + + 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; +} + +int +iomap_readpage(struct page *page, const struct iomap_ops *ops) +{ + 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; + } + } + + 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); + } + + /* + * 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; +} +EXPORT_SYMBOL_GPL(iomap_readpage); + +static loff_t +iomap_readahead_actor(struct inode *inode, loff_t pos, loff_t length, + void *data, struct iomap *iomap, struct iomap *srcmap) +{ + 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; + } + if (!ctx->cur_page) { + ctx->cur_page = readahead_page(ctx->rac); + ctx->cur_page_in_bio = false; + } + ret = iomap_readpage_actor(inode, pos + done, length - done, + ctx, iomap, srcmap); + } + + return done; +} + +/** + * iomap_readahead - Attempt to read pages from a file. + * @rac: Describes the pages to be read. + * @ops: The operations vector for the filesystem. + * + * This function is for filesystems to call to implement their readahead + * address_space operation. + * + * Context: The @ops callbacks may submit I/O (eg to read the addresses of + * blocks from disc), and may wait for it. The caller may be trying to + * access a different page, and so sleeping excessively should be avoided. + * It may allocate memory, but should avoid costly allocations. This + * 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) +{ + 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, + }; + + trace_iomap_readahead(inode, 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; + } + + 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); + } +} +EXPORT_SYMBOL_GPL(iomap_readahead); + +/* + * iomap_is_partially_uptodate checks whether blocks within a page are + * uptodate or not. + * + * Returns true if all blocks which correspond to a file portion + * we want to read within the page are uptodate. + */ +int +iomap_is_partially_uptodate(struct page *page, unsigned long from, + unsigned long count) +{ + struct iomap_page *iop = to_iomap_page(page); + struct inode *inode = page->mapping->host; + unsigned len, first, last; + unsigned i; + + /* Limit range to one page */ + len = min_t(unsigned, PAGE_SIZE - from, count); + + /* First and last blocks in range within page */ + first = from >> inode->i_blkbits; + last = (from + len - 1) >> inode->i_blkbits; + + if (iop) { + for (i = first; i <= last; i++) + if (!test_bit(i, iop->uptodate)) + return 0; + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); + +int +iomap_releasepage(struct page *page, gfp_t gfp_mask) +{ + trace_iomap_releasepage(page->mapping->host, page_offset(page), + PAGE_SIZE); + + /* + * 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 (PageDirty(page) || PageWriteback(page)) + return 0; + iomap_page_release(page); + return 1; +} +EXPORT_SYMBOL_GPL(iomap_releasepage); + +void +iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len) +{ + trace_iomap_invalidatepage(page->mapping->host, 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 (offset == 0 && len == PAGE_SIZE) { + WARN_ON_ONCE(PageWriteback(page)); + cancel_dirty_page(page); + iomap_page_release(page); + } +} +EXPORT_SYMBOL_GPL(iomap_invalidatepage); + +#ifdef CONFIG_MIGRATION +int +iomap_migrate_page(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ + 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)); + + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); + return MIGRATEPAGE_SUCCESS; +} +EXPORT_SYMBOL_GPL(iomap_migrate_page); +#endif /* CONFIG_MIGRATION */ + +enum { + IOMAP_WRITE_F_UNSHARE = (1 << 0), +}; + +static void +iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) +{ + loff_t i_size = i_size_read(inode); + + /* + * Only truncate newly allocated pages beyoned EOF, even if the + * write started inside the existing inode size. + */ + if (pos + len > i_size) + 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) +{ + 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); +} + +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 = round_down(pos, block_size); + loff_t block_end = round_up(pos + len, block_size); + unsigned from = offset_in_page(pos), to = from + len, poff, plen; + + if (PageUptodate(page)) + return 0; + ClearPageError(page); + + do { + iomap_adjust_read_range(inode, iop, &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)) + continue; + + if (iomap_block_needs_zeroing(inode, srcmap, block_start)) { + if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE)) + return -EIO; + zero_user_segments(page, poff, from, to, poff + plen); + } else { + int status = iomap_read_page_sync(block_start, page, + poff, plen, srcmap); + if (status) + return status; + } + iomap_set_range_uptodate(page, 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) +{ + const struct iomap_page_ops *page_ops = iomap->page_ops; + struct page *page; + int status = 0; + + BUG_ON(pos + len > iomap->offset + iomap->length); + if (srcmap != iomap) + BUG_ON(pos + len > srcmap->offset + srcmap->length); + + 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; + } + + page = grab_cache_page_write_begin(inode->i_mapping, pos >> PAGE_SHIFT, + AOP_FLAG_NOFS); + if (!page) { + status = -ENOMEM; + goto out_no_page; + } + + 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); + else + status = __iomap_write_begin(inode, pos, len, flags, page, + srcmap); + + if (unlikely(status)) + goto out_unlock; + + *pagep = page; + 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); + 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 size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, + size_t copied, struct page *page) +{ + flush_dcache_page(page); + + /* + * 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 + * partially written into a block, it will not be marked uptodate, so a + * readpage 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. + */ + 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; +} + +static size_t iomap_write_end_inline(struct inode *inode, struct page *page, + struct iomap *iomap, loff_t pos, size_t copied) +{ + void *addr; + + WARN_ON_ONCE(!PageUptodate(page)); + BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data)); + + flush_dcache_page(page); + addr = kmap_atomic(page); + memcpy(iomap->inline_data + pos, addr + pos, copied); + kunmap_atomic(addr); + + mark_inode_dirty(inode); + return copied; +} + +/* Returns the number of bytes copied. May be 0. Cannot be an errno. */ +static size_t iomap_write_end(struct inode *inode, loff_t pos, size_t len, + size_t copied, struct page *page, struct iomap *iomap, + struct iomap *srcmap) +{ + const struct iomap_page_ops *page_ops = iomap->page_ops; + loff_t old_size = inode->i_size; + size_t ret; + + 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); + } + + /* + * 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 (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); + + if (ret < len) + iomap_write_failed(inode, pos, len); + return ret; +} + +static loff_t +iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data, + struct iomap *iomap, struct iomap *srcmap) +{ + struct iov_iter *i = data; + long status = 0; + ssize_t written = 0; + + do { + struct page *page; + unsigned long offset; /* Offset into pagecache page */ + unsigned long bytes; /* Bytes to write to page */ + size_t copied; /* Bytes copied from user */ + + offset = offset_in_page(pos); + bytes = min_t(unsigned long, PAGE_SIZE - offset, + iov_iter_count(i)); +again: + if (bytes > length) + bytes = length; + + /* + * Bring in the user page that we will 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. + */ + if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + status = -EFAULT; + break; + } + + status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, + srcmap); + if (unlikely(status)) + break; + + if (mapping_writably_mapped(inode->i_mapping)) + flush_dcache_page(page); + + copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); + + copied = iomap_write_end(inode, pos, bytes, copied, page, iomap, + srcmap); + + cond_resched(); + + iov_iter_advance(i, copied); + if (unlikely(copied == 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. + */ + bytes = min_t(unsigned long, PAGE_SIZE - offset, + iov_iter_single_seg_count(i)); + goto again; + } + pos += copied; + written += copied; + length -= copied; + + balance_dirty_pages_ratelimited(inode->i_mapping); + } while (iov_iter_count(i) && length); + + return written ? written : status; +} + +ssize_t +iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter, + const struct iomap_ops *ops) +{ + struct inode *inode = iocb->ki_filp->f_mapping->host; + loff_t pos = iocb->ki_pos, ret = 0, written = 0; + + while (iov_iter_count(iter)) { + ret = iomap_apply(inode, pos, iov_iter_count(iter), + IOMAP_WRITE, ops, iter, iomap_write_actor); + if (ret <= 0) + break; + pos += ret; + written += ret; + } + + return written ? written : ret; +} +EXPORT_SYMBOL_GPL(iomap_file_buffered_write); + +static loff_t +iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, + struct iomap *iomap, struct iomap *srcmap) +{ + long status = 0; + loff_t written = 0; + + /* 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; + + do { + unsigned long offset = offset_in_page(pos); + unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length); + struct page *page; + + status = iomap_write_begin(inode, pos, bytes, + IOMAP_WRITE_F_UNSHARE, &page, iomap, srcmap); + if (unlikely(status)) + return status; + + status = iomap_write_end(inode, pos, bytes, bytes, page, iomap, + srcmap); + if (WARN_ON_ONCE(status == 0)) + return -EIO; + + cond_resched(); + + pos += status; + written += status; + length -= status; + + balance_dirty_pages_ratelimited(inode->i_mapping); + } while (length); + + return written; +} + +int +iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, + const struct iomap_ops *ops) +{ + loff_t 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; + } + + return 0; +} +EXPORT_SYMBOL_GPL(iomap_file_unshare); + +static s64 iomap_zero(struct inode *inode, loff_t pos, u64 length, + struct iomap *iomap, struct iomap *srcmap) +{ + struct page *page; + int status; + unsigned offset = offset_in_page(pos); + unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); + + status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap); + if (status) + return status; + + zero_user(page, offset, bytes); + mark_page_accessed(page); + + return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap); +} + +static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos, + loff_t length, void *data, struct iomap *iomap, + struct iomap *srcmap) +{ + bool *did_zero = data; + loff_t written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + s64 bytes; + + if (IS_DAX(inode)) + bytes = dax_iomap_zero(pos, length, iomap); + else + bytes = iomap_zero(inode, pos, length, iomap, srcmap); + if (bytes < 0) + return bytes; + + pos += bytes; + length -= bytes; + written += bytes; + if (did_zero) + *did_zero = true; + } while (length > 0); + + return written; +} + +int +iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + loff_t ret; + + while (len > 0) { + ret = iomap_apply(inode, pos, len, IOMAP_ZERO, + ops, did_zero, iomap_zero_range_actor); + if (ret <= 0) + return ret; + + pos += ret; + len -= ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(iomap_zero_range); + +int +iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops); +} +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) +{ + struct page *page = data; + int ret; + + if (iomap->flags & IOMAP_F_BUFFER_HEAD) { + ret = __block_write_begin_int(page, pos, length, NULL, iomap); + if (ret) + return ret; + block_commit_write(page, 0, length); + } else { + WARN_ON_ONCE(!PageUptodate(page)); + iomap_page_create(inode, page); + set_page_dirty(page); + } + + return length; +} + +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) +{ + struct page *page = vmf->page; + struct inode *inode = file_inode(vmf->vma->vm_file); + unsigned long length; + loff_t offset; + ssize_t ret; + + lock_page(page); + ret = page_mkwrite_check_truncate(page, 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; + } + + wait_for_stable_page(page); + return VM_FAULT_LOCKED; +out_unlock: + unlock_page(page); + return block_page_mkwrite_return(ret); +} +EXPORT_SYMBOL_GPL(iomap_page_mkwrite); + +static void +iomap_finish_page_writeback(struct inode *inode, struct page *page, + int error, unsigned int len) +{ + struct iomap_page *iop = to_iomap_page(page); + + if (error) { + SetPageError(page); + mapping_set_error(inode->i_mapping, error); + } + + WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop); + WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) <= 0); + + if (!iop || atomic_sub_and_test(len, &iop->write_bytes_pending)) + 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) +{ + 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; + + /* + * For the last bio, bi_private points to the ioend, so we + * need to explicitly end the iteration here. + */ + 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, + bv->bv_len); + 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); + } +} + +void +iomap_finish_ioends(struct iomap_ioend *ioend, int error) +{ + struct list_head tmp; + + list_replace_init(&ioend->io_list, &tmp); + iomap_finish_ioend(ioend, error); + + 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); + } +} +EXPORT_SYMBOL_GPL(iomap_finish_ioends); + +/* + * 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) +{ + 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); + + 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); + +static int +iomap_ioend_compare(void *priv, const struct list_head *a, + const 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); + + 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. + * + * 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. + */ +static int +iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend, + int error) +{ + ioend->io_bio->bi_private = ioend; + ioend->io_bio->bi_end_io = iomap_writepage_end_bio; + + 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. + */ + ioend->io_bio->bi_status = errno_to_blk_status(error); + bio_endio(ioend->io_bio); + return error; + } + + 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; +} + +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) +{ + 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) + atomic_add(len, &iop->write_bytes_pending); + + if (!merged) { + if (bio_full(wpc->ioend->io_bio, len)) { + wpc->ioend->io_bio = + iomap_chain_bio(wpc->ioend->io_bio); + } + 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_blocks_per_page(inode, page) > 1 && !iop); + WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0); + + /* + * 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. + */ + 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; + + error = wpc->ops->map_blocks(wpc, inode, file_offset); + 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++; + } + + WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); + WARN_ON_ONCE(!PageLocked(page)); + WARN_ON_ONCE(PageWriteback(page)); + WARN_ON_ONCE(PageDirty(page)); + + /* + * 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. + */ + if (unlikely(error)) { + /* + * Let the filesystem know what portion of the current page + * failed to map. If the page wasn't been added to ioend, it + * won't be affected by I/O completion and we must unlock it + * now. + */ + if (wpc->ops->discard_page) + wpc->ops->discard_page(page, file_offset); + if (!count) { + ClearPageUptodate(page); + unlock_page(page); + goto done; + } + } + + set_page_writeback(page); + unlock_page(page); + + /* + * Preserve the original error if there was one, otherwise catch + * submission errors here and propagate into subsequent ioend + * submissions. + */ + 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; + } + + /* + * 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); + return error; +} + +/* + * 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) +{ + 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); + + /* + * 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. + */ + if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == + PF_MEMALLOC)) + goto redirty; + + /* + * Is this page beyond the end of the file? + * + * 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 | + * ---------------------------------^------------------| + */ + 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); +} +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); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c new file mode 100644 index 000000000..933f234d5 --- /dev/null +++ b/fs/iomap/direct-io.c @@ -0,0 +1,610 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010 Red Hat, Inc. + * Copyright (c) 2016-2018 Christoph Hellwig. + */ +#include <linux/module.h> +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/iomap.h> +#include <linux/backing-dev.h> +#include <linux/uio.h> +#include <linux/task_io_accounting_ops.h> +#include "trace.h" + +#include "../internal.h" + +/* + * Private flags for iomap_dio, must not overlap with the public ones in + * iomap.h: + */ +#define IOMAP_DIO_WRITE_FUA (1 << 28) +#define IOMAP_DIO_NEED_SYNC (1 << 29) +#define IOMAP_DIO_WRITE (1 << 30) +#define IOMAP_DIO_DIRTY (1 << 31) + +struct iomap_dio { + struct kiocb *iocb; + const struct iomap_dio_ops *dops; + loff_t i_size; + loff_t size; + atomic_t ref; + unsigned flags; + int error; + bool wait_for_completion; + + union { + /* used during submission and for synchronous completion: */ + struct { + struct iov_iter *iter; + struct task_struct *waiter; + struct request_queue *last_queue; + blk_qc_t cookie; + } submit; + + /* used for aio completion: */ + struct { + struct work_struct work; + } aio; + }; +}; + +int iomap_dio_iopoll(struct kiocb *kiocb, bool spin) +{ + struct request_queue *q = READ_ONCE(kiocb->private); + + if (!q) + return 0; + return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin); +} +EXPORT_SYMBOL_GPL(iomap_dio_iopoll); + +static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap, + struct bio *bio, loff_t pos) +{ + atomic_inc(&dio->ref); + + if (dio->iocb->ki_flags & IOCB_HIPRI) + bio_set_polled(bio, dio->iocb); + + dio->submit.last_queue = bdev_get_queue(iomap->bdev); + if (dio->dops && dio->dops->submit_io) + dio->submit.cookie = dio->dops->submit_io( + file_inode(dio->iocb->ki_filp), + iomap, bio, pos); + else + dio->submit.cookie = submit_bio(bio); +} + +ssize_t iomap_dio_complete(struct iomap_dio *dio) +{ + const struct iomap_dio_ops *dops = dio->dops; + struct kiocb *iocb = dio->iocb; + struct inode *inode = file_inode(iocb->ki_filp); + loff_t offset = iocb->ki_pos; + ssize_t ret = dio->error; + + if (dops && dops->end_io) + ret = dops->end_io(iocb, dio->size, ret, dio->flags); + + if (likely(!ret)) { + ret = dio->size; + /* check for short read */ + if (offset + ret > dio->i_size && + !(dio->flags & IOMAP_DIO_WRITE)) + ret = dio->i_size - offset; + iocb->ki_pos += ret; + } + + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + * + * And this page cache invalidation has to be after ->end_io(), as some + * filesystems convert unwritten extents to real allocations in + * ->end_io() when necessary, otherwise a racing buffer read would cache + * zeros from unwritten extents. + */ + if (!dio->error && dio->size && + (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { + int err; + err = invalidate_inode_pages2_range(inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + dio->size - 1) >> PAGE_SHIFT); + if (err) + dio_warn_stale_pagecache(iocb->ki_filp); + } + + inode_dio_end(file_inode(iocb->ki_filp)); + /* + * If this is a DSYNC write, make sure we push it to stable storage now + * that we've written data. + */ + if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC)) + ret = generic_write_sync(iocb, ret); + + kfree(dio); + + return ret; +} +EXPORT_SYMBOL_GPL(iomap_dio_complete); + +static void iomap_dio_complete_work(struct work_struct *work) +{ + struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); + struct kiocb *iocb = dio->iocb; + + iocb->ki_complete(iocb, iomap_dio_complete(dio), 0); +} + +/* + * Set an error in the dio if none is set yet. We have to use cmpxchg + * as the submission context and the completion context(s) can race to + * update the error. + */ +static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret) +{ + cmpxchg(&dio->error, 0, ret); +} + +static void iomap_dio_bio_end_io(struct bio *bio) +{ + struct iomap_dio *dio = bio->bi_private; + bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); + + if (bio->bi_status) + iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status)); + + if (atomic_dec_and_test(&dio->ref)) { + if (dio->wait_for_completion) { + struct task_struct *waiter = dio->submit.waiter; + WRITE_ONCE(dio->submit.waiter, NULL); + blk_wake_io_task(waiter); + } else if (dio->flags & IOMAP_DIO_WRITE) { + struct inode *inode = file_inode(dio->iocb->ki_filp); + + INIT_WORK(&dio->aio.work, iomap_dio_complete_work); + queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work); + } else { + iomap_dio_complete_work(&dio->aio.work); + } + } + + if (should_dirty) { + bio_check_pages_dirty(bio); + } else { + bio_release_pages(bio, false); + bio_put(bio); + } +} + +static void +iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, + unsigned len) +{ + struct page *page = ZERO_PAGE(0); + int flags = REQ_SYNC | REQ_IDLE; + struct bio *bio; + + bio = bio_alloc(GFP_KERNEL, 1); + bio_set_dev(bio, iomap->bdev); + bio->bi_iter.bi_sector = iomap_sector(iomap, pos); + bio->bi_private = dio; + bio->bi_end_io = iomap_dio_bio_end_io; + + get_page(page); + __bio_add_page(bio, page, len, 0); + bio_set_op_attrs(bio, REQ_OP_WRITE, flags); + iomap_dio_submit_bio(dio, iomap, bio, pos); +} + +static loff_t +iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, + struct iomap_dio *dio, struct iomap *iomap) +{ + unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); + unsigned int fs_block_size = i_blocksize(inode), pad; + unsigned int align = iov_iter_alignment(dio->submit.iter); + struct bio *bio; + bool need_zeroout = false; + bool use_fua = false; + int nr_pages, ret = 0; + size_t copied = 0; + size_t orig_count; + + if ((pos | length | align) & ((1 << blkbits) - 1)) + return -EINVAL; + + if (iomap->type == IOMAP_UNWRITTEN) { + dio->flags |= IOMAP_DIO_UNWRITTEN; + need_zeroout = true; + } + + if (iomap->flags & IOMAP_F_SHARED) + dio->flags |= IOMAP_DIO_COW; + + if (iomap->flags & IOMAP_F_NEW) { + need_zeroout = true; + } else if (iomap->type == IOMAP_MAPPED) { + /* + * Use a FUA write if we need datasync semantics, this is a pure + * data IO that doesn't require any metadata updates (including + * after IO completion such as unwritten extent conversion) and + * the underlying device supports FUA. This allows us to avoid + * cache flushes on IO completion. + */ + if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && + (dio->flags & IOMAP_DIO_WRITE_FUA) && + blk_queue_fua(bdev_get_queue(iomap->bdev))) + use_fua = true; + } + + /* + * Save the original count and trim the iter to just the extent we + * are operating on right now. The iter will be re-expanded once + * we are done. + */ + orig_count = iov_iter_count(dio->submit.iter); + iov_iter_truncate(dio->submit.iter, length); + + nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES); + if (nr_pages <= 0) { + ret = nr_pages; + goto out; + } + + if (need_zeroout) { + /* zero out from the start of the block to the write offset */ + pad = pos & (fs_block_size - 1); + if (pad) + iomap_dio_zero(dio, iomap, pos - pad, pad); + } + + do { + size_t n; + if (dio->error) { + iov_iter_revert(dio->submit.iter, copied); + copied = ret = 0; + goto out; + } + + bio = bio_alloc(GFP_KERNEL, nr_pages); + bio_set_dev(bio, iomap->bdev); + bio->bi_iter.bi_sector = iomap_sector(iomap, pos); + bio->bi_write_hint = dio->iocb->ki_hint; + bio->bi_ioprio = dio->iocb->ki_ioprio; + bio->bi_private = dio; + bio->bi_end_io = iomap_dio_bio_end_io; + + ret = bio_iov_iter_get_pages(bio, dio->submit.iter); + if (unlikely(ret)) { + /* + * We have to stop part way through an IO. We must fall + * through to the sub-block tail zeroing here, otherwise + * this short IO may expose stale data in the tail of + * the block we haven't written data to. + */ + bio_put(bio); + goto zero_tail; + } + + n = bio->bi_iter.bi_size; + if (dio->flags & IOMAP_DIO_WRITE) { + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; + if (use_fua) + bio->bi_opf |= REQ_FUA; + else + dio->flags &= ~IOMAP_DIO_WRITE_FUA; + task_io_account_write(n); + } else { + bio->bi_opf = REQ_OP_READ; + if (dio->flags & IOMAP_DIO_DIRTY) + bio_set_pages_dirty(bio); + } + + dio->size += n; + copied += n; + + nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES); + iomap_dio_submit_bio(dio, iomap, bio, pos); + pos += n; + } while (nr_pages); + + /* + * We need to zeroout the tail of a sub-block write if the extent type + * requires zeroing or the write extends beyond EOF. If we don't zero + * the block tail in the latter case, we can expose stale data via mmap + * reads of the EOF block. + */ +zero_tail: + if (need_zeroout || + ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) { + /* zero out from the end of the write to the end of the block */ + pad = pos & (fs_block_size - 1); + if (pad) + iomap_dio_zero(dio, iomap, pos, fs_block_size - pad); + } +out: + /* Undo iter limitation to current extent */ + iov_iter_reexpand(dio->submit.iter, orig_count - copied); + if (copied) + return copied; + return ret; +} + +static loff_t +iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio) +{ + length = iov_iter_zero(length, dio->submit.iter); + dio->size += length; + return length; +} + +static loff_t +iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length, + struct iomap_dio *dio, struct iomap *iomap) +{ + struct iov_iter *iter = dio->submit.iter; + size_t copied; + + BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data)); + + if (dio->flags & IOMAP_DIO_WRITE) { + loff_t size = inode->i_size; + + if (pos > size) + memset(iomap->inline_data + size, 0, pos - size); + copied = copy_from_iter(iomap->inline_data + pos, length, iter); + if (copied) { + if (pos + copied > size) + i_size_write(inode, pos + copied); + mark_inode_dirty(inode); + } + } else { + copied = copy_to_iter(iomap->inline_data + pos, length, iter); + } + dio->size += copied; + return copied; +} + +static loff_t +iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, + void *data, struct iomap *iomap, struct iomap *srcmap) +{ + struct iomap_dio *dio = data; + + switch (iomap->type) { + case IOMAP_HOLE: + if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE)) + return -EIO; + return iomap_dio_hole_actor(length, dio); + case IOMAP_UNWRITTEN: + if (!(dio->flags & IOMAP_DIO_WRITE)) + return iomap_dio_hole_actor(length, dio); + return iomap_dio_bio_actor(inode, pos, length, dio, iomap); + case IOMAP_MAPPED: + return iomap_dio_bio_actor(inode, pos, length, dio, iomap); + case IOMAP_INLINE: + return iomap_dio_inline_actor(inode, pos, length, dio, iomap); + case IOMAP_DELALLOC: + /* + * DIO is not serialised against mmap() access at all, and so + * if the page_mkwrite occurs between the writeback and the + * iomap_apply() call in the DIO path, then it will see the + * DELALLOC block that the page-mkwrite allocated. + */ + pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n", + dio->iocb->ki_filp, current->comm); + return -EIO; + default: + WARN_ON_ONCE(1); + return -EIO; + } +} + +/* + * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO + * is being issued as AIO or not. This allows us to optimise pure data writes + * to use REQ_FUA rather than requiring generic_write_sync() to issue a + * REQ_FLUSH post write. This is slightly tricky because a single request here + * can be mapped into multiple disjoint IOs and only a subset of the IOs issued + * may be pure data writes. In that case, we still need to do a full data sync + * completion. + * + * Returns -ENOTBLK In case of a page invalidation invalidation failure for + * writes. The callers needs to fall back to buffered I/O in this case. + */ +struct iomap_dio * +__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, + const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + bool wait_for_completion) +{ + struct address_space *mapping = iocb->ki_filp->f_mapping; + struct inode *inode = file_inode(iocb->ki_filp); + size_t count = iov_iter_count(iter); + loff_t pos = iocb->ki_pos; + loff_t end = iocb->ki_pos + count - 1, ret = 0; + unsigned int flags = IOMAP_DIRECT; + struct blk_plug plug; + struct iomap_dio *dio; + + if (!count) + return NULL; + + if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion)) + return ERR_PTR(-EIO); + + dio = kmalloc(sizeof(*dio), GFP_KERNEL); + if (!dio) + return ERR_PTR(-ENOMEM); + + dio->iocb = iocb; + atomic_set(&dio->ref, 1); + dio->size = 0; + dio->i_size = i_size_read(inode); + dio->dops = dops; + dio->error = 0; + dio->flags = 0; + + dio->submit.iter = iter; + dio->submit.waiter = current; + dio->submit.cookie = BLK_QC_T_NONE; + dio->submit.last_queue = NULL; + + if (iov_iter_rw(iter) == READ) { + if (pos >= dio->i_size) + goto out_free_dio; + + if (iter_is_iovec(iter)) + dio->flags |= IOMAP_DIO_DIRTY; + } else { + flags |= IOMAP_WRITE; + dio->flags |= IOMAP_DIO_WRITE; + + /* for data sync or sync, we need sync completion processing */ + if (iocb->ki_flags & IOCB_DSYNC) + dio->flags |= IOMAP_DIO_NEED_SYNC; + + /* + * For datasync only writes, we optimistically try using FUA for + * this IO. Any non-FUA write that occurs will clear this flag, + * hence we know before completion whether a cache flush is + * necessary. + */ + if ((iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) == IOCB_DSYNC) + dio->flags |= IOMAP_DIO_WRITE_FUA; + } + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (filemap_range_has_page(mapping, pos, end)) { + ret = -EAGAIN; + goto out_free_dio; + } + flags |= IOMAP_NOWAIT; + } + + ret = filemap_write_and_wait_range(mapping, pos, end); + if (ret) + goto out_free_dio; + + if (iov_iter_rw(iter) == WRITE) { + /* + * Try to invalidate cache pages for the range we are writing. + * If this invalidation fails, let the caller fall back to + * buffered I/O. + */ + if (invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, + end >> PAGE_SHIFT)) { + trace_iomap_dio_invalidate_fail(inode, pos, count); + ret = -ENOTBLK; + goto out_free_dio; + } + + if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; + } + } + + inode_dio_begin(inode); + + blk_start_plug(&plug); + do { + ret = iomap_apply(inode, pos, count, flags, ops, dio, + iomap_dio_actor); + if (ret <= 0) { + /* magic error code to fall back to buffered I/O */ + if (ret == -ENOTBLK) { + wait_for_completion = true; + ret = 0; + } + break; + } + pos += ret; + + if (iov_iter_rw(iter) == READ && pos >= dio->i_size) { + /* + * We only report that we've read data up to i_size. + * Revert iter to a state corresponding to that as + * some callers (such as splice code) rely on it. + */ + iov_iter_revert(iter, pos - dio->i_size); + break; + } + } while ((count = iov_iter_count(iter)) > 0); + blk_finish_plug(&plug); + + if (ret < 0) + iomap_dio_set_error(dio, ret); + + /* + * If all the writes we issued were FUA, we don't need to flush the + * cache on IO completion. Clear the sync flag for this case. + */ + if (dio->flags & IOMAP_DIO_WRITE_FUA) + dio->flags &= ~IOMAP_DIO_NEED_SYNC; + + WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie); + WRITE_ONCE(iocb->private, dio->submit.last_queue); + + /* + * We are about to drop our additional submission reference, which + * might be the last reference to the dio. There are three different + * ways we can progress here: + * + * (a) If this is the last reference we will always complete and free + * the dio ourselves. + * (b) If this is not the last reference, and we serve an asynchronous + * iocb, we must never touch the dio after the decrement, the + * I/O completion handler will complete and free it. + * (c) If this is not the last reference, but we serve a synchronous + * iocb, the I/O completion handler will wake us up on the drop + * of the final reference, and we will complete and free it here + * after we got woken by the I/O completion handler. + */ + dio->wait_for_completion = wait_for_completion; + if (!atomic_dec_and_test(&dio->ref)) { + if (!wait_for_completion) + return ERR_PTR(-EIOCBQUEUED); + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (!READ_ONCE(dio->submit.waiter)) + break; + + if (!(iocb->ki_flags & IOCB_HIPRI) || + !dio->submit.last_queue || + !blk_poll(dio->submit.last_queue, + dio->submit.cookie, true)) + blk_io_schedule(); + } + __set_current_state(TASK_RUNNING); + } + + return dio; + +out_free_dio: + kfree(dio); + if (ret) + return ERR_PTR(ret); + return NULL; +} +EXPORT_SYMBOL_GPL(__iomap_dio_rw); + +ssize_t +iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, + const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + bool wait_for_completion) +{ + struct iomap_dio *dio; + + dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion); + if (IS_ERR_OR_NULL(dio)) + return PTR_ERR_OR_ZERO(dio); + return iomap_dio_complete(dio); +} +EXPORT_SYMBOL_GPL(iomap_dio_rw); diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c new file mode 100644 index 000000000..aab070df4 --- /dev/null +++ b/fs/iomap/fiemap.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2016-2018 Christoph Hellwig. + */ +#include <linux/module.h> +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/iomap.h> +#include <linux/fiemap.h> + +struct fiemap_ctx { + struct fiemap_extent_info *fi; + struct iomap prev; +}; + +static int iomap_to_fiemap(struct fiemap_extent_info *fi, + struct iomap *iomap, u32 flags) +{ + switch (iomap->type) { + case IOMAP_HOLE: + /* skip holes */ + return 0; + case IOMAP_DELALLOC: + flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN; + break; + case IOMAP_MAPPED: + break; + case IOMAP_UNWRITTEN: + flags |= FIEMAP_EXTENT_UNWRITTEN; + break; + case IOMAP_INLINE: + flags |= FIEMAP_EXTENT_DATA_INLINE; + break; + } + + if (iomap->flags & IOMAP_F_MERGED) + flags |= FIEMAP_EXTENT_MERGED; + if (iomap->flags & IOMAP_F_SHARED) + flags |= FIEMAP_EXTENT_SHARED; + + return fiemap_fill_next_extent(fi, iomap->offset, + iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0, + iomap->length, flags); +} + +static loff_t +iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, + struct iomap *iomap, struct iomap *srcmap) +{ + struct fiemap_ctx *ctx = data; + loff_t ret = length; + + if (iomap->type == IOMAP_HOLE) + return length; + + ret = iomap_to_fiemap(ctx->fi, &ctx->prev, 0); + ctx->prev = *iomap; + switch (ret) { + case 0: /* success */ + return length; + case 1: /* extent array full */ + return 0; + default: + return ret; + } +} + +int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, + u64 start, u64 len, const struct iomap_ops *ops) +{ + struct fiemap_ctx ctx; + loff_t ret; + + memset(&ctx, 0, sizeof(ctx)); + ctx.fi = fi; + ctx.prev.type = IOMAP_HOLE; + + ret = fiemap_prep(inode, fi, start, &len, 0); + if (ret) + return ret; + + while (len > 0) { + ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx, + iomap_fiemap_actor); + /* inode with no (attribute) mapping will give ENOENT */ + if (ret == -ENOENT) + break; + if (ret < 0) + return ret; + if (ret == 0) + break; + + start += ret; + len -= ret; + } + + if (ctx.prev.type != IOMAP_HOLE) { + ret = iomap_to_fiemap(fi, &ctx.prev, FIEMAP_EXTENT_LAST); + if (ret < 0) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(iomap_fiemap); + +static loff_t +iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length, + void *data, struct iomap *iomap, struct iomap *srcmap) +{ + sector_t *bno = data, addr; + + if (iomap->type == IOMAP_MAPPED) { + addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits; + *bno = addr; + } + return 0; +} + +/* legacy ->bmap interface. 0 is the error return (!) */ +sector_t +iomap_bmap(struct address_space *mapping, sector_t bno, + const struct iomap_ops *ops) +{ + struct inode *inode = mapping->host; + loff_t pos = bno << inode->i_blkbits; + unsigned blocksize = i_blocksize(inode); + int ret; + + if (filemap_write_and_wait(mapping)) + return 0; + + bno = 0; + ret = iomap_apply(inode, pos, blocksize, 0, ops, &bno, + iomap_bmap_actor); + if (ret) + return 0; + return bno; +} +EXPORT_SYMBOL_GPL(iomap_bmap); diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c new file mode 100644 index 000000000..220c30616 --- /dev/null +++ b/fs/iomap/seek.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2017 Red Hat, Inc. + * Copyright (c) 2018 Christoph Hellwig. + */ +#include <linux/module.h> +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/iomap.h> +#include <linux/pagemap.h> +#include <linux/pagevec.h> + +/* + * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff. + * Returns true if found and updates @lastoff to the offset in file. + */ +static bool +page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff, + int whence) +{ + const struct address_space_operations *ops = inode->i_mapping->a_ops; + unsigned int bsize = i_blocksize(inode), off; + bool seek_data = whence == SEEK_DATA; + loff_t poff = page_offset(page); + + if (WARN_ON_ONCE(*lastoff >= poff + PAGE_SIZE)) + return false; + + if (*lastoff < poff) { + /* + * Last offset smaller than the start of the page means we found + * a hole: + */ + if (whence == SEEK_HOLE) + return true; + *lastoff = poff; + } + + /* + * Just check the page unless we can and should check block ranges: + */ + if (bsize == PAGE_SIZE || !ops->is_partially_uptodate) + return PageUptodate(page) == seek_data; + + lock_page(page); + if (unlikely(page->mapping != inode->i_mapping)) + goto out_unlock_not_found; + + for (off = 0; off < PAGE_SIZE; off += bsize) { + if (offset_in_page(*lastoff) >= off + bsize) + continue; + if (ops->is_partially_uptodate(page, off, bsize) == seek_data) { + unlock_page(page); + return true; + } + *lastoff = poff + off + bsize; + } + +out_unlock_not_found: + unlock_page(page); + return false; +} + +/* + * Seek for SEEK_DATA / SEEK_HOLE in the page cache. + * + * Within unwritten extents, the page cache determines which parts are holes + * and which are data: uptodate buffer heads count as data; everything else + * counts as a hole. + * + * Returns the resulting offset on successs, and -ENOENT otherwise. + */ +static loff_t +page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length, + int whence) +{ + pgoff_t index = offset >> PAGE_SHIFT; + pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE); + loff_t lastoff = offset; + struct pagevec pvec; + + if (length <= 0) + return -ENOENT; + + pagevec_init(&pvec); + + do { + unsigned nr_pages, i; + + nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index, + end - 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + if (page_seek_hole_data(inode, page, &lastoff, whence)) + goto check_range; + lastoff = page_offset(page) + PAGE_SIZE; + } + pagevec_release(&pvec); + } while (index < end); + + /* When no page at lastoff and we are not done, we found a hole. */ + if (whence != SEEK_HOLE) + goto not_found; + +check_range: + if (lastoff < offset + length) + goto out; +not_found: + lastoff = -ENOENT; +out: + pagevec_release(&pvec); + return lastoff; +} + + +static loff_t +iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length, + void *data, struct iomap *iomap, struct iomap *srcmap) +{ + switch (iomap->type) { + case IOMAP_UNWRITTEN: + offset = page_cache_seek_hole_data(inode, offset, length, + SEEK_HOLE); + if (offset < 0) + return length; + fallthrough; + case IOMAP_HOLE: + *(loff_t *)data = offset; + return 0; + default: + return length; + } +} + +loff_t +iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) +{ + loff_t size = i_size_read(inode); + loff_t ret; + + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) + return -ENXIO; + + while (offset < size) { + ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT, + ops, &offset, iomap_seek_hole_actor); + if (ret < 0) + return ret; + if (ret == 0) + break; + offset += ret; + } + + return offset; +} +EXPORT_SYMBOL_GPL(iomap_seek_hole); + +static loff_t +iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length, + void *data, struct iomap *iomap, struct iomap *srcmap) +{ + switch (iomap->type) { + case IOMAP_HOLE: + return length; + case IOMAP_UNWRITTEN: + offset = page_cache_seek_hole_data(inode, offset, length, + SEEK_DATA); + if (offset < 0) + return length; + fallthrough; + default: + *(loff_t *)data = offset; + return 0; + } +} + +loff_t +iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops) +{ + loff_t size = i_size_read(inode); + loff_t ret; + + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) + return -ENXIO; + + while (offset < size) { + ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT, + ops, &offset, iomap_seek_data_actor); + if (ret < 0) + return ret; + if (ret == 0) + return offset; + offset += ret; + } + + /* We've reached the end of the file without finding data */ + return -ENXIO; +} +EXPORT_SYMBOL_GPL(iomap_seek_data); diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c new file mode 100644 index 000000000..2ceea45ae --- /dev/null +++ b/fs/iomap/swapfile.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#include <linux/module.h> +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/iomap.h> +#include <linux/swap.h> + +/* Swapfile activation */ + +struct iomap_swapfile_info { + struct iomap iomap; /* accumulated iomap */ + struct swap_info_struct *sis; + uint64_t lowest_ppage; /* lowest physical addr seen (pages) */ + uint64_t highest_ppage; /* highest physical addr seen (pages) */ + unsigned long nr_pages; /* number of pages collected */ + int nr_extents; /* extent count */ +}; + +/* + * Collect physical extents for this swap file. Physical extents reported to + * the swap code must be trimmed to align to a page boundary. The logical + * offset within the file is irrelevant since the swapfile code maps logical + * page numbers of the swap device to the physical page-aligned extents. + */ +static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi) +{ + struct iomap *iomap = &isi->iomap; + unsigned long nr_pages; + unsigned long max_pages; + uint64_t first_ppage; + uint64_t first_ppage_reported; + uint64_t next_ppage; + int error; + + if (unlikely(isi->nr_pages >= isi->sis->max)) + return 0; + max_pages = isi->sis->max - isi->nr_pages; + + /* + * Round the start up and the end down so that the physical + * extent aligns to a page boundary. + */ + first_ppage = ALIGN(iomap->addr, PAGE_SIZE) >> PAGE_SHIFT; + next_ppage = ALIGN_DOWN(iomap->addr + iomap->length, PAGE_SIZE) >> + PAGE_SHIFT; + + /* Skip too-short physical extents. */ + if (first_ppage >= next_ppage) + return 0; + nr_pages = next_ppage - first_ppage; + nr_pages = min(nr_pages, max_pages); + + /* + * Calculate how much swap space we're adding; the first page contains + * the swap header and doesn't count. The mm still wants that first + * page fed to add_swap_extent, however. + */ + first_ppage_reported = first_ppage; + if (iomap->offset == 0) + first_ppage_reported++; + if (isi->lowest_ppage > first_ppage_reported) + isi->lowest_ppage = first_ppage_reported; + if (isi->highest_ppage < (next_ppage - 1)) + isi->highest_ppage = next_ppage - 1; + + /* Add extent, set up for the next call. */ + error = add_swap_extent(isi->sis, isi->nr_pages, nr_pages, first_ppage); + if (error < 0) + return error; + isi->nr_extents += error; + isi->nr_pages += nr_pages; + return 0; +} + +/* + * Accumulate iomaps for this swap file. We have to accumulate iomaps because + * swap only cares about contiguous page-aligned physical extents and makes no + * distinction between written and unwritten extents. + */ +static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos, + loff_t count, void *data, struct iomap *iomap, + struct iomap *srcmap) +{ + struct iomap_swapfile_info *isi = data; + int error; + + switch (iomap->type) { + case IOMAP_MAPPED: + case IOMAP_UNWRITTEN: + /* Only real or unwritten extents. */ + break; + case IOMAP_INLINE: + /* No inline data. */ + pr_err("swapon: file is inline\n"); + return -EINVAL; + default: + pr_err("swapon: file has unallocated extents\n"); + return -EINVAL; + } + + /* No uncommitted metadata or shared blocks. */ + if (iomap->flags & IOMAP_F_DIRTY) { + pr_err("swapon: file is not committed\n"); + return -EINVAL; + } + if (iomap->flags & IOMAP_F_SHARED) { + pr_err("swapon: file has shared extents\n"); + return -EINVAL; + } + + /* Only one bdev per swap file. */ + if (iomap->bdev != isi->sis->bdev) { + pr_err("swapon: file is on multiple devices\n"); + return -EINVAL; + } + + if (isi->iomap.length == 0) { + /* No accumulated extent, so just store it. */ + memcpy(&isi->iomap, iomap, sizeof(isi->iomap)); + } else if (isi->iomap.addr + isi->iomap.length == iomap->addr) { + /* Append this to the accumulated extent. */ + isi->iomap.length += iomap->length; + } else { + /* Otherwise, add the retained iomap and store this one. */ + error = iomap_swapfile_add_extent(isi); + if (error) + return error; + memcpy(&isi->iomap, iomap, sizeof(isi->iomap)); + } + return count; +} + +/* + * Iterate a swap file's iomaps to construct physical extents that can be + * passed to the swapfile subsystem. + */ +int iomap_swapfile_activate(struct swap_info_struct *sis, + struct file *swap_file, sector_t *pagespan, + const struct iomap_ops *ops) +{ + struct iomap_swapfile_info isi = { + .sis = sis, + .lowest_ppage = (sector_t)-1ULL, + }; + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; + loff_t pos = 0; + loff_t len = ALIGN_DOWN(i_size_read(inode), PAGE_SIZE); + loff_t ret; + + /* + * Persist all file mapping metadata so that we won't have any + * IOMAP_F_DIRTY iomaps. + */ + ret = vfs_fsync(swap_file, 1); + if (ret) + return ret; + + while (len > 0) { + ret = iomap_apply(inode, pos, len, IOMAP_REPORT, + ops, &isi, iomap_swapfile_activate_actor); + if (ret <= 0) + return ret; + + pos += ret; + len -= ret; + } + + if (isi.iomap.length) { + ret = iomap_swapfile_add_extent(&isi); + if (ret) + return ret; + } + + /* + * If this swapfile doesn't contain even a single page-aligned + * contiguous range of blocks, reject this useless swapfile to + * prevent confusion later on. + */ + if (isi.nr_pages == 0) { + pr_warn("swapon: Cannot find a single usable page in file.\n"); + return -EINVAL; + } + + *pagespan = 1 + isi.highest_ppage - isi.lowest_ppage; + sis->max = isi.nr_pages; + sis->pages = isi.nr_pages - 1; + sis->highest_bit = isi.nr_pages - 1; + return isi.nr_extents; +} +EXPORT_SYMBOL_GPL(iomap_swapfile_activate); diff --git a/fs/iomap/trace.c b/fs/iomap/trace.c new file mode 100644 index 000000000..da217246b --- /dev/null +++ b/fs/iomap/trace.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Christoph Hellwig + */ +#include <linux/iomap.h> + +/* + * We include this last to have the helpers above available for the trace + * event implementations. + */ +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h new file mode 100644 index 000000000..fdc7ae388 --- /dev/null +++ b/fs/iomap/trace.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2009-2019 Christoph Hellwig + * + * NOTE: none of these tracepoints shall be consider a stable kernel ABI + * as they can change at any time. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM iomap + +#if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _IOMAP_TRACE_H + +#include <linux/tracepoint.h> + +struct inode; + +DECLARE_EVENT_CLASS(iomap_readpage_class, + TP_PROTO(struct inode *inode, int nr_pages), + TP_ARGS(inode, nr_pages), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, ino) + __field(int, nr_pages) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nr_pages = nr_pages; + ), + TP_printk("dev %d:%d ino 0x%llx nr_pages %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->nr_pages) +) + +#define DEFINE_READPAGE_EVENT(name) \ +DEFINE_EVENT(iomap_readpage_class, name, \ + TP_PROTO(struct inode *inode, int nr_pages), \ + TP_ARGS(inode, nr_pages)) +DEFINE_READPAGE_EVENT(iomap_readpage); +DEFINE_READPAGE_EVENT(iomap_readahead); + +DECLARE_EVENT_CLASS(iomap_range_class, + TP_PROTO(struct inode *inode, unsigned long off, unsigned int len), + TP_ARGS(inode, off, len), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, ino) + __field(loff_t, size) + __field(unsigned long, offset) + __field(unsigned int, length) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->size = i_size_read(inode); + __entry->offset = off; + __entry->length = len; + ), + TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset %lx " + "length %x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->size, + __entry->offset, + __entry->length) +) + +#define DEFINE_RANGE_EVENT(name) \ +DEFINE_EVENT(iomap_range_class, name, \ + TP_PROTO(struct inode *inode, unsigned long off, unsigned int len),\ + TP_ARGS(inode, off, len)) +DEFINE_RANGE_EVENT(iomap_writepage); +DEFINE_RANGE_EVENT(iomap_releasepage); +DEFINE_RANGE_EVENT(iomap_invalidatepage); +DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); + +#define IOMAP_TYPE_STRINGS \ + { IOMAP_HOLE, "HOLE" }, \ + { IOMAP_DELALLOC, "DELALLOC" }, \ + { IOMAP_MAPPED, "MAPPED" }, \ + { IOMAP_UNWRITTEN, "UNWRITTEN" }, \ + { IOMAP_INLINE, "INLINE" } + +#define IOMAP_FLAGS_STRINGS \ + { IOMAP_WRITE, "WRITE" }, \ + { IOMAP_ZERO, "ZERO" }, \ + { IOMAP_REPORT, "REPORT" }, \ + { IOMAP_FAULT, "FAULT" }, \ + { IOMAP_DIRECT, "DIRECT" }, \ + { IOMAP_NOWAIT, "NOWAIT" } + +#define IOMAP_F_FLAGS_STRINGS \ + { IOMAP_F_NEW, "NEW" }, \ + { IOMAP_F_DIRTY, "DIRTY" }, \ + { IOMAP_F_SHARED, "SHARED" }, \ + { IOMAP_F_MERGED, "MERGED" }, \ + { IOMAP_F_BUFFER_HEAD, "BH" }, \ + { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" } + +DECLARE_EVENT_CLASS(iomap_class, + TP_PROTO(struct inode *inode, struct iomap *iomap), + TP_ARGS(inode, iomap), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, ino) + __field(u64, addr) + __field(loff_t, offset) + __field(u64, length) + __field(u16, type) + __field(u16, flags) + __field(dev_t, bdev) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->addr = iomap->addr; + __entry->offset = iomap->offset; + __entry->length = iomap->length; + __entry->type = iomap->type; + __entry->flags = iomap->flags; + __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; + ), + TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr %lld offset %lld " + "length %llu type %s flags %s", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + MAJOR(__entry->bdev), MINOR(__entry->bdev), + __entry->addr, + __entry->offset, + __entry->length, + __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), + __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS)) +) + +#define DEFINE_IOMAP_EVENT(name) \ +DEFINE_EVENT(iomap_class, name, \ + TP_PROTO(struct inode *inode, struct iomap *iomap), \ + TP_ARGS(inode, iomap)) +DEFINE_IOMAP_EVENT(iomap_apply_dstmap); +DEFINE_IOMAP_EVENT(iomap_apply_srcmap); + +TRACE_EVENT(iomap_apply, + TP_PROTO(struct inode *inode, loff_t pos, loff_t length, + unsigned int flags, const void *ops, void *actor, + unsigned long caller), + TP_ARGS(inode, pos, length, flags, ops, actor, caller), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, ino) + __field(loff_t, pos) + __field(loff_t, length) + __field(unsigned int, flags) + __field(const void *, ops) + __field(void *, actor) + __field(unsigned long, caller) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pos = pos; + __entry->length = length; + __entry->flags = flags; + __entry->ops = ops; + __entry->actor = actor; + __entry->caller = caller; + ), + TP_printk("dev %d:%d ino 0x%llx pos %lld length %lld flags %s (0x%x) " + "ops %ps caller %pS actor %ps", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->pos, + __entry->length, + __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), + __entry->flags, + __entry->ops, + (void *)__entry->caller, + __entry->actor) +); + +#endif /* _IOMAP_TRACE_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace +#include <trace/define_trace.h> |