1 files changed, 221 insertions, 194 deletions

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 3787a5fb0a42..9db829715652 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -2,35 +2,13 @@
 /*
  * Copyright (C) 2017-2018 HUAWEI, Inc.
  *             https://www.huawei.com/
+ * Copyright (C) 2021, Alibaba Cloud
  */
 #include "internal.h"
 #include <linux/prefetch.h>
-
+#include <linux/dax.h>
 #include <trace/events/erofs.h>
 
-static void erofs_readendio(struct bio *bio)
-{
-	struct bio_vec *bvec;
-	blk_status_t err = bio->bi_status;
-	struct bvec_iter_all iter_all;
-
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
-
-		/* page is already locked */
-		DBG_BUGON(PageUptodate(page));
-
-		if (err)
-			SetPageError(page);
-		else
-			SetPageUptodate(page);
-
-		unlock_page(page);
-		/* page could be reclaimed now */
-	}
-	bio_put(bio);
-}
-
 struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr)
 {
 	struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping;
@@ -59,13 +37,6 @@ static int erofs_map_blocks_flatmode(struct inode *inode,
 	nblocks = DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
 	lastblk = nblocks - tailendpacking;
 
-	if (offset >= inode->i_size) {
-		/* leave out-of-bound access unmapped */
-		map->m_flags = 0;
-		map->m_plen = 0;
-		goto out;
-	}
-
 	/* there is no hole in flatmode */
 	map->m_flags = EROFS_MAP_MAPPED;
 
@@ -100,217 +71,273 @@ static int erofs_map_blocks_flatmode(struct inode *inode,
 		goto err_out;
 	}
 
-out:
 	map->m_llen = map->m_plen;
-
 err_out:
 	trace_erofs_map_blocks_flatmode_exit(inode, map, flags, 0);
 	return err;
 }
 
-static inline struct bio *erofs_read_raw_page(struct bio *bio,
-					      struct address_space *mapping,
-					      struct page *page,
-					      erofs_off_t *last_block,
-					      unsigned int nblocks,
-					      unsigned int *eblks,
-					      bool ra)
+static int erofs_map_blocks(struct inode *inode,
+			    struct erofs_map_blocks *map, int flags)
 {
-	struct inode *const inode = mapping->host;
-	struct super_block *const sb = inode->i_sb;
-	erofs_off_t current_block = (erofs_off_t)page->index;
-	int err;
-
-	DBG_BUGON(!nblocks);
-
-	if (PageUptodate(page)) {
-		err = 0;
-		goto has_updated;
-	}
+	struct super_block *sb = inode->i_sb;
+	struct erofs_inode *vi = EROFS_I(inode);
+	struct erofs_inode_chunk_index *idx;
+	struct page *page;
+	u64 chunknr;
+	unsigned int unit;
+	erofs_off_t pos;
+	int err = 0;
 
-	/* note that for readpage case, bio also equals to NULL */
-	if (bio &&
-	    (*last_block + 1 != current_block || !*eblks)) {
-submit_bio_retry:
-		submit_bio(bio);
-		bio = NULL;
+	if (map->m_la >= inode->i_size) {
+		/* leave out-of-bound access unmapped */
+		map->m_flags = 0;
+		map->m_plen = 0;
+		goto out;
 	}
 
-	if (!bio) {
-		struct erofs_map_blocks map = {
-			.m_la = blknr_to_addr(current_block),
-		};
-		erofs_blk_t blknr;
-		unsigned int blkoff;
-
-		err = erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW);
-		if (err)
-			goto err_out;
-
-		/* zero out the holed page */
-		if (!(map.m_flags & EROFS_MAP_MAPPED)) {
-			zero_user_segment(page, 0, PAGE_SIZE);
-			SetPageUptodate(page);
-
-			/* imply err = 0, see erofs_map_blocks */
-			goto has_updated;
-		}
-
-		/* for RAW access mode, m_plen must be equal to m_llen */
-		DBG_BUGON(map.m_plen != map.m_llen);
-
-		blknr = erofs_blknr(map.m_pa);
-		blkoff = erofs_blkoff(map.m_pa);
-
-		/* deal with inline page */
-		if (map.m_flags & EROFS_MAP_META) {
-			void *vsrc, *vto;
-			struct page *ipage;
+	if (vi->datalayout != EROFS_INODE_CHUNK_BASED)
+		return erofs_map_blocks_flatmode(inode, map, flags);
 
-			DBG_BUGON(map.m_plen > PAGE_SIZE);
+	if (vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)
+		unit = sizeof(*idx);			/* chunk index */
+	else
+		unit = EROFS_BLOCK_MAP_ENTRY_SIZE;	/* block map */
 
-			ipage = erofs_get_meta_page(inode->i_sb, blknr);
+	chunknr = map->m_la >> vi->chunkbits;
+	pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
+		    vi->xattr_isize, unit) + unit * chunknr;
 
-			if (IS_ERR(ipage)) {
-				err = PTR_ERR(ipage);
-				goto err_out;
-			}
+	page = erofs_get_meta_page(inode->i_sb, erofs_blknr(pos));
+	if (IS_ERR(page))
+		return PTR_ERR(page);
 
-			vsrc = kmap_atomic(ipage);
-			vto = kmap_atomic(page);
-			memcpy(vto, vsrc + blkoff, map.m_plen);
-			memset(vto + map.m_plen, 0, PAGE_SIZE - map.m_plen);
-			kunmap_atomic(vto);
-			kunmap_atomic(vsrc);
-			flush_dcache_page(page);
+	map->m_la = chunknr << vi->chunkbits;
+	map->m_plen = min_t(erofs_off_t, 1UL << vi->chunkbits,
+			    roundup(inode->i_size - map->m_la, EROFS_BLKSIZ));
 
-			SetPageUptodate(page);
-			/* TODO: could we unlock the page earlier? */
-			unlock_page(ipage);
-			put_page(ipage);
+	/* handle block map */
+	if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) {
+		__le32 *blkaddr = page_address(page) + erofs_blkoff(pos);
 
-			/* imply err = 0, see erofs_map_blocks */
-			goto has_updated;
+		if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) {
+			map->m_flags = 0;
+		} else {
+			map->m_pa = blknr_to_addr(le32_to_cpu(*blkaddr));
+			map->m_flags = EROFS_MAP_MAPPED;
 		}
+		goto out_unlock;
+	}
+	/* parse chunk indexes */
+	idx = page_address(page) + erofs_blkoff(pos);
+	switch (le32_to_cpu(idx->blkaddr)) {
+	case EROFS_NULL_ADDR:
+		map->m_flags = 0;
+		break;
+	default:
+		/* only one device is supported for now */
+		if (idx->device_id) {
+			erofs_err(sb, "invalid device id %u @ %llu for nid %llu",
+				  le16_to_cpu(idx->device_id),
+				  chunknr, vi->nid);
+			err = -EFSCORRUPTED;
+			goto out_unlock;
+		}
+		map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr));
+		map->m_flags = EROFS_MAP_MAPPED;
+		break;
+	}
+out_unlock:
+	unlock_page(page);
+	put_page(page);
+out:
+	map->m_llen = map->m_plen;
+	return err;
+}
 
-		/* pa must be block-aligned for raw reading */
-		DBG_BUGON(erofs_blkoff(map.m_pa));
+static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
+{
+	int ret;
+	struct erofs_map_blocks map;
+
+	map.m_la = offset;
+	map.m_llen = length;
+
+	ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
+	if (ret < 0)
+		return ret;
+
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->dax_dev = EROFS_I_SB(inode)->dax_dev;
+	iomap->offset = map.m_la;
+	iomap->length = map.m_llen;
+	iomap->flags = 0;
+	iomap->private = NULL;
+
+	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
+		iomap->type = IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
+		if (!iomap->length)
+			iomap->length = length;
+		return 0;
+	}
 
-		/* max # of continuous pages */
-		if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
-			nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
+	if (map.m_flags & EROFS_MAP_META) {
+		struct page *ipage;
+
+		iomap->type = IOMAP_INLINE;
+		ipage = erofs_get_meta_page(inode->i_sb,
+					    erofs_blknr(map.m_pa));
+		if (IS_ERR(ipage))
+			return PTR_ERR(ipage);
+		iomap->inline_data = page_address(ipage) +
+					erofs_blkoff(map.m_pa);
+		iomap->private = ipage;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->addr = map.m_pa;
+	}
+	return 0;
+}
 
-		*eblks = bio_max_segs(nblocks);
-		bio = bio_alloc(GFP_NOIO, *eblks);
+static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length,
+		ssize_t written, unsigned int flags, struct iomap *iomap)
+{
+	struct page *ipage = iomap->private;
 
-		bio->bi_end_io = erofs_readendio;
-		bio_set_dev(bio, sb->s_bdev);
-		bio->bi_iter.bi_sector = (sector_t)blknr <<
-			LOG_SECTORS_PER_BLOCK;
-		bio->bi_opf = REQ_OP_READ | (ra ? REQ_RAHEAD : 0);
+	if (ipage) {
+		DBG_BUGON(iomap->type != IOMAP_INLINE);
+		unlock_page(ipage);
+		put_page(ipage);
+	} else {
+		DBG_BUGON(iomap->type == IOMAP_INLINE);
 	}
+	return written;
+}
 
-	err = bio_add_page(bio, page, PAGE_SIZE, 0);
-	/* out of the extent or bio is full */
-	if (err < PAGE_SIZE)
-		goto submit_bio_retry;
-	--*eblks;
-	*last_block = current_block;
-	return bio;
+static const struct iomap_ops erofs_iomap_ops = {
+	.iomap_begin = erofs_iomap_begin,
+	.iomap_end = erofs_iomap_end,
+};
 
-err_out:
-	/* for sync reading, set page error immediately */
-	if (!ra) {
-		SetPageError(page);
-		ClearPageUptodate(page);
+int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		 u64 start, u64 len)
+{
+	if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
+#ifdef CONFIG_EROFS_FS_ZIP
+		return iomap_fiemap(inode, fieinfo, start, len,
+				    &z_erofs_iomap_report_ops);
+#else
+		return -EOPNOTSUPP;
+#endif
 	}
-has_updated:
-	unlock_page(page);
-
-	/* if updated manually, continuous pages has a gap */
-	if (bio)
-		submit_bio(bio);
-	return err ? ERR_PTR(err) : NULL;
+	return iomap_fiemap(inode, fieinfo, start, len, &erofs_iomap_ops);
 }
 
 /*
  * since we dont have write or truncate flows, so no inode
  * locking needs to be held at the moment.
  */
-static int erofs_raw_access_readpage(struct file *file, struct page *page)
+static int erofs_readpage(struct file *file, struct page *page)
 {
-	erofs_off_t last_block;
-	unsigned int eblks;
-	struct bio *bio;
-
-	trace_erofs_readpage(page, true);
+	return iomap_readpage(page, &erofs_iomap_ops);
+}
 
-	bio = erofs_read_raw_page(NULL, page->mapping,
-				  page, &last_block, 1, &eblks, false);
+static void erofs_readahead(struct readahead_control *rac)
+{
+	return iomap_readahead(rac, &erofs_iomap_ops);
+}
 
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
+static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
+{
+	return iomap_bmap(mapping, block, &erofs_iomap_ops);
+}
 
-	if (bio)
-		submit_bio(bio);
+static int erofs_prepare_dio(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	loff_t align = iocb->ki_pos | iov_iter_count(to) |
+		iov_iter_alignment(to);
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	unsigned int blksize_mask;
+
+	if (bdev)
+		blksize_mask = (1 << ilog2(bdev_logical_block_size(bdev))) - 1;
+	else
+		blksize_mask = (1 << inode->i_blkbits) - 1;
+
+	if (align & blksize_mask)
+		return -EINVAL;
 	return 0;
 }
 
-static void erofs_raw_access_readahead(struct readahead_control *rac)
+static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	erofs_off_t last_block;
-	unsigned int eblks;
-	struct bio *bio = NULL;
-	struct page *page;
-
-	trace_erofs_readpages(rac->mapping->host, readahead_index(rac),
-			readahead_count(rac), true);
-
-	while ((page = readahead_page(rac))) {
-		prefetchw(&page->flags);
-
-		bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
-				readahead_count(rac), &eblks, true);
-
-		/* all the page errors are ignored when readahead */
-		if (IS_ERR(bio)) {
-			pr_err("%s, readahead error at page %lu of nid %llu\n",
-			       __func__, page->index,
-			       EROFS_I(rac->mapping->host)->nid);
-
-			bio = NULL;
-		}
-
-		put_page(page);
+	/* no need taking (shared) inode lock since it's a ro filesystem */
+	if (!iov_iter_count(to))
+		return 0;
+
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(iocb->ki_filp->f_mapping->host))
+		return dax_iomap_rw(iocb, to, &erofs_iomap_ops);
+#endif
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		int err = erofs_prepare_dio(iocb, to);
+
+		if (!err)
+			return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
+					    NULL, 0);
+		if (err < 0)
+			return err;
 	}
+	return filemap_read(iocb, to, 0);
+}
+
+/* for uncompressed (aligned) files and raw access for other files */
+const struct address_space_operations erofs_raw_access_aops = {
+	.readpage = erofs_readpage,
+	.readahead = erofs_readahead,
+	.bmap = erofs_bmap,
+	.direct_IO = noop_direct_IO,
+};
 
-	if (bio)
-		submit_bio(bio);
+#ifdef CONFIG_FS_DAX
+static vm_fault_t erofs_dax_huge_fault(struct vm_fault *vmf,
+		enum page_entry_size pe_size)
+{
+	return dax_iomap_fault(vmf, pe_size, NULL, NULL, &erofs_iomap_ops);
 }
 
-static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
+static vm_fault_t erofs_dax_fault(struct vm_fault *vmf)
 {
-	struct inode *inode = mapping->host;
-	struct erofs_map_blocks map = {
-		.m_la = blknr_to_addr(block),
-	};
+	return erofs_dax_huge_fault(vmf, PE_SIZE_PTE);
+}
 
-	if (EROFS_I(inode)->datalayout == EROFS_INODE_FLAT_INLINE) {
-		erofs_blk_t blks = i_size_read(inode) >> LOG_BLOCK_SIZE;
+static const struct vm_operations_struct erofs_dax_vm_ops = {
+	.fault		= erofs_dax_fault,
+	.huge_fault	= erofs_dax_huge_fault,
+};
 
-		if (block >> LOG_SECTORS_PER_BLOCK >= blks)
-			return 0;
-	}
+static int erofs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!IS_DAX(file_inode(file)))
+		return generic_file_readonly_mmap(file, vma);
 
-	if (!erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW))
-		return erofs_blknr(map.m_pa);
+	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
+		return -EINVAL;
 
+	vma->vm_ops = &erofs_dax_vm_ops;
+	vma->vm_flags |= VM_HUGEPAGE;
 	return 0;
 }
-
-/* for uncompressed (aligned) files and raw access for other files */
-const struct address_space_operations erofs_raw_access_aops = {
-	.readpage = erofs_raw_access_readpage,
-	.readahead = erofs_raw_access_readahead,
-	.bmap = erofs_bmap,
+#else
+#define erofs_file_mmap	generic_file_readonly_mmap
+#endif
+
+const struct file_operations erofs_file_fops = {
+	.llseek		= generic_file_llseek,
+	.read_iter	= erofs_file_read_iter,
+	.mmap		= erofs_file_mmap,
+	.splice_read	= generic_file_splice_read,
 };