Merge tag 'erofs-for-6.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs

Pull erofs updates from Gao Xiang:
 "In this cycle, we'd like to enable basic sub-page compressed data
  support for Android ecosystem (for vendors to try out 16k page size
  with 4k-block images in their compatibility mode) as well as container
  images (so that 4k-block images can be parsed on arm64 cloud servers
  using 64k page size.)

  In addition, there are several bugfixes and cleanups as usual. All
  commits have been in -next for a while and no potential merge conflict
  is observed.

  Summary:

   - Add basic sub-page compressed data support

   - Fix a memory leak on MicroLZMA and DEFLATE compression

   - Fix a rare LZ4 inplace decompression issue on recent x86 CPUs

   - Fix a KASAN issue reported by syzbot around crafted images

   - Some cleanups"

* tag 'erofs-for-6.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs:
  erofs: make erofs_{err,info}() support NULL sb parameter
  erofs: avoid debugging output for (de)compressed data
  erofs: allow partially filled compressed bvecs
  erofs: enable sub-page compressed block support
  erofs: refine z_erofs_transform_plain() for sub-page block support
  erofs: fix ztailpacking for subpage compressed blocks
  erofs: fix up compacted indexes for block size < 4096
  erofs: record `pclustersize` in bytes instead of pages
  erofs: support I/O submission for sub-page compressed blocks
  erofs: fix lz4 inplace decompression
  erofs: fix memory leak on short-lived bounced pages

fs/erofs/decompressor.c

@@ -121,11 +121,11 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
 }
 
 static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
-			void *inpage, unsigned int *inputmargin, int *maptype,
-			bool may_inplace)
+			void *inpage, void *out, unsigned int *inputmargin,
+			int *maptype, bool may_inplace)
 {
 	struct z_erofs_decompress_req *rq = ctx->rq;
-	unsigned int omargin, total, i, j;
+	unsigned int omargin, total, i;
 	struct page **in;
 	void *src, *tmp;
 
@@ -135,12 +135,13 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
 		    omargin < LZ4_DECOMPRESS_INPLACE_MARGIN(rq->inputsize))
 			goto docopy;
 
-		for (i = 0; i < ctx->inpages; ++i) {
-			DBG_BUGON(rq->in[i] == NULL);
-			for (j = 0; j < ctx->outpages - ctx->inpages + i; ++j)
-				if (rq->out[j] == rq->in[i])
+		for (i = 0; i < ctx->inpages; ++i)
+			if (rq->out[ctx->outpages - ctx->inpages + i] !=
+			    rq->in[i])
 				goto docopy;
-		}
+		kunmap_local(inpage);
+		*maptype = 3;
+		return out + ((ctx->outpages - ctx->inpages) << PAGE_SHIFT);
 	}
 
 	if (ctx->inpages <= 1) {
@@ -148,7 +149,6 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
 		return inpage;
 	}
 	kunmap_local(inpage);
-	might_sleep();
 	src = erofs_vm_map_ram(rq->in, ctx->inpages);
 	if (!src)
 		return ERR_PTR(-ENOMEM);
@@ -204,12 +204,12 @@ int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf,
 }
 
 static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
-				      u8 *out)
+				      u8 *dst)
 {
 	struct z_erofs_decompress_req *rq = ctx->rq;
 	bool support_0padding = false, may_inplace = false;
 	unsigned int inputmargin;
-	u8 *headpage, *src;
+	u8 *out, *headpage, *src;
 	int ret, maptype;
 
 	DBG_BUGON(*rq->in == NULL);
@@ -230,11 +230,12 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 	}
 
 	inputmargin = rq->pageofs_in;
-	src = z_erofs_lz4_handle_overlap(ctx, headpage, &inputmargin,
+	src = z_erofs_lz4_handle_overlap(ctx, headpage, dst, &inputmargin,
 					 &maptype, may_inplace);
 	if (IS_ERR(src))
 		return PTR_ERR(src);
 
+	out = dst + rq->pageofs_out;
 	/* legacy format could compress extra data in a pcluster. */
 	if (rq->partial_decoding || !support_0padding)
 		ret = LZ4_decompress_safe_partial(src + inputmargin, out,
@@ -246,15 +247,9 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 	if (ret != rq->outputsize) {
 		erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
 			  ret, rq->inputsize, inputmargin, rq->outputsize);
-
-		print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
-			       16, 1, src + inputmargin, rq->inputsize, true);
-		print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
-			       16, 1, out, rq->outputsize, true);
-
 		if (ret >= 0)
 			memset(out + ret, 0, rq->outputsize - ret);
-		ret = -EIO;
+		ret = -EFSCORRUPTED;
 	} else {
 		ret = 0;
 	}
@@ -265,7 +260,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 		vm_unmap_ram(src, ctx->inpages);
 	} else if (maptype == 2) {
 		erofs_put_pcpubuf(src);
-	} else {
+	} else if (maptype != 3) {
 		DBG_BUGON(1);
 		return -EFAULT;
 	}
@@ -308,7 +303,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
 	}
 
 dstmap_out:
-	ret = z_erofs_lz4_decompress_mem(&ctx, dst + rq->pageofs_out);
+	ret = z_erofs_lz4_decompress_mem(&ctx, dst);
 	if (!dst_maptype)
 		kunmap_local(dst);
 	else if (dst_maptype == 2)
@@ -319,43 +314,58 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
 static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 				   struct page **pagepool)
 {
-	const unsigned int inpages = PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT;
-	const unsigned int outpages =
+	const unsigned int nrpages_in =
+		PAGE_ALIGN(rq->pageofs_in + rq->inputsize) >> PAGE_SHIFT;
+	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
-	const unsigned int righthalf = min_t(unsigned int, rq->outputsize,
-					     PAGE_SIZE - rq->pageofs_out);
-	const unsigned int lefthalf = rq->outputsize - righthalf;
-	const unsigned int interlaced_offset =
-		rq->alg == Z_EROFS_COMPRESSION_SHIFTED ? 0 : rq->pageofs_out;
-	u8 *src;
-
-	if (outpages > 2 && rq->alg == Z_EROFS_COMPRESSION_SHIFTED) {
-		DBG_BUGON(1);
-		return -EFSCORRUPTED;
+	const unsigned int bs = rq->sb->s_blocksize;
+	unsigned int cur = 0, ni = 0, no, pi, po, insz, cnt;
+	u8 *kin;
+
+	DBG_BUGON(rq->outputsize > rq->inputsize);
+	if (rq->alg == Z_EROFS_COMPRESSION_INTERLACED) {
+		cur = bs - (rq->pageofs_out & (bs - 1));
+		pi = (rq->pageofs_in + rq->inputsize - cur) & ~PAGE_MASK;
+		cur = min(cur, rq->outputsize);
+		if (cur && rq->out[0]) {
+			kin = kmap_local_page(rq->in[nrpages_in - 1]);
+			if (rq->out[0] == rq->in[nrpages_in - 1]) {
+				memmove(kin + rq->pageofs_out, kin + pi, cur);
+				flush_dcache_page(rq->out[0]);
+			} else {
+				memcpy_to_page(rq->out[0], rq->pageofs_out,
+					       kin + pi, cur);
 			}
-
-	if (rq->out[0] == *rq->in) {
-		DBG_BUGON(rq->pageofs_out);
-		return 0;
+			kunmap_local(kin);
+		}
+		rq->outputsize -= cur;
 	}
 
-	src = kmap_local_page(rq->in[inpages - 1]) + rq->pageofs_in;
-	if (rq->out[0])
-		memcpy_to_page(rq->out[0], rq->pageofs_out,
-			       src + interlaced_offset, righthalf);
-
-	if (outpages > inpages) {
-		DBG_BUGON(!rq->out[outpages - 1]);
-		if (rq->out[outpages - 1] != rq->in[inpages - 1]) {
-			memcpy_to_page(rq->out[outpages - 1], 0, src +
-					(interlaced_offset ? 0 : righthalf),
-				       lefthalf);
-		} else if (!interlaced_offset) {
-			memmove(src, src + righthalf, lefthalf);
-			flush_dcache_page(rq->in[inpages - 1]);
+	for (; rq->outputsize; rq->pageofs_in = 0, cur += PAGE_SIZE, ni++) {
+		insz = min(PAGE_SIZE - rq->pageofs_in, rq->outputsize);
+		rq->outputsize -= insz;
+		if (!rq->in[ni])
+			continue;
+		kin = kmap_local_page(rq->in[ni]);
+		pi = 0;
+		do {
+			no = (rq->pageofs_out + cur + pi) >> PAGE_SHIFT;
+			po = (rq->pageofs_out + cur + pi) & ~PAGE_MASK;
+			DBG_BUGON(no >= nrpages_out);
+			cnt = min(insz - pi, PAGE_SIZE - po);
+			if (rq->out[no] == rq->in[ni]) {
+				memmove(kin + po,
+					kin + rq->pageofs_in + pi, cnt);
+				flush_dcache_page(rq->out[no]);
+			} else if (rq->out[no]) {
+				memcpy_to_page(rq->out[no], po,
+					       kin + rq->pageofs_in + pi, cnt);
 			}
+			pi += cnt;
+		} while (pi < insz);
+		kunmap_local(kin);
 	}
-	kunmap_local(src);
+	DBG_BUGON(ni > nrpages_in);
 	return 0;
 }
 

fs/erofs/decompressor_deflate.c

@@ -70,7 +70,7 @@ int __init z_erofs_deflate_init(void)
 	return 0;
 
 out_failed:
-	pr_err("failed to allocate zlib workspace\n");
+	erofs_err(NULL, "failed to allocate zlib workspace");
 	z_erofs_deflate_exit();
 	return -ENOMEM;
 }

fs/erofs/inode.c

@@ -259,8 +259,10 @@ static int erofs_fill_inode(struct inode *inode)
 
 	if (erofs_inode_is_data_compressed(vi->datalayout)) {
 #ifdef CONFIG_EROFS_FS_ZIP
-		if (!erofs_is_fscache_mode(inode->i_sb) &&
-		    inode->i_sb->s_blocksize_bits == PAGE_SHIFT) {
+		if (!erofs_is_fscache_mode(inode->i_sb)) {
+			DO_ONCE_LITE_IF(inode->i_sb->s_blocksize != PAGE_SIZE,
+				  erofs_info, inode->i_sb,
+				  "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
 			inode->i_mapping->a_ops = &z_erofs_aops;
 			err = 0;
 			goto out_unlock;

fs/erofs/super.c

@@ -27,7 +27,10 @@ void _erofs_err(struct super_block *sb, const char *func, const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	if (sb)
 		pr_err("(device %s): %s: %pV", sb->s_id, func, &vaf);
+	else
+		pr_err("%s: %pV", func, &vaf);
 	va_end(args);
 }
 
@@ -41,7 +44,10 @@ void _erofs_info(struct super_block *sb, const char *func, const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	if (sb)
 		pr_info("(device %s): %pV", sb->s_id, &vaf);
+	else
+		pr_info("%pV", &vaf);
 	va_end(args);
 }
 

fs/erofs/zdata.c

@@ -56,6 +56,9 @@ struct z_erofs_pcluster {
 	/* L: total number of bvecs */
 	unsigned int vcnt;
 
+	/* I: pcluster size (compressed size) in bytes */
+	unsigned int pclustersize;
+
 	/* I: page offset of start position of decompression */
 	unsigned short pageofs_out;
 
@@ -70,14 +73,6 @@ struct z_erofs_pcluster {
 		struct rcu_head rcu;
 	};
 
-	union {
-		/* I: physical cluster size in pages */
-		unsigned short pclusterpages;
-
-		/* I: tailpacking inline compressed size */
-		unsigned short tailpacking_size;
-	};
-
 	/* I: compression algorithm format */
 	unsigned char algorithmformat;
 
@@ -115,9 +110,7 @@ static inline bool z_erofs_is_inline_pcluster(struct z_erofs_pcluster *pcl)
 
 static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl)
 {
-	if (z_erofs_is_inline_pcluster(pcl))
-		return 1;
-	return pcl->pclusterpages;
+	return PAGE_ALIGN(pcl->pclustersize) >> PAGE_SHIFT;
 }
 
 /*
@@ -298,12 +291,12 @@ static int z_erofs_create_pcluster_pool(void)
 	return 0;
 }
 
-static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
+static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int size)
 {
-	int i;
+	unsigned int nrpages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct z_erofs_pcluster_slab *pcs = pcluster_pool;
 
-	for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
-		struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
+	for (; pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) {
 		struct z_erofs_pcluster *pcl;
 
 		if (nrpages > pcs->maxpages)
@@ -312,7 +305,7 @@ static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
 		pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
 		if (!pcl)
 			return ERR_PTR(-ENOMEM);
-		pcl->pclusterpages = nrpages;
+		pcl->pclustersize = size;
 		return pcl;
 	}
 	return ERR_PTR(-EINVAL);
@@ -559,6 +552,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 {
 	struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode));
 	struct z_erofs_pcluster *pcl = fe->pcl;
+	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	bool shouldalloc = z_erofs_should_alloc_cache(fe);
 	bool standalone = true;
 	/*
@@ -569,13 +563,14 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
 	unsigned int i;
 
+	if (i_blocksize(fe->inode) != PAGE_SIZE)
+		return;
 	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
 		return;
 
-	for (i = 0; i < pcl->pclusterpages; ++i) {
-		struct page *page;
+	for (i = 0; i < pclusterpages; ++i) {
+		struct page *page, *newpage;
 		void *t;	/* mark pages just found for debugging */
-		struct page *newpage = NULL;
 
 		/* the compressed page was loaded before */
 		if (READ_ONCE(pcl->compressed_bvecs[i].page))
@@ -585,6 +580,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 
 		if (page) {
 			t = (void *)((unsigned long)page | 1);
+			newpage = NULL;
 		} else {
 			/* I/O is needed, no possible to decompress directly */
 			standalone = false;
@@ -592,9 +588,8 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 				continue;
 
 			/*
-			 * try to use cached I/O if page allocation
-			 * succeeds or fallback to in-place I/O instead
-			 * to avoid any direct reclaim.
+			 * Try cached I/O if allocation succeeds or fallback to
+			 * in-place I/O instead to avoid any direct reclaim.
 			 */
 			newpage = erofs_allocpage(&fe->pagepool, gfp);
 			if (!newpage)
@@ -626,6 +621,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 {
 	struct z_erofs_pcluster *const pcl =
 		container_of(grp, struct z_erofs_pcluster, obj);
+	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	int i;
 
 	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
@@ -633,7 +629,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 	 * refcount of workgroup is now freezed as 0,
 	 * therefore no need to worry about available decompression users.
 	 */
-	for (i = 0; i < pcl->pclusterpages; ++i) {
+	for (i = 0; i < pclusterpages; ++i) {
 		struct page *page = pcl->compressed_bvecs[i].page;
 
 		if (!page)
@@ -657,6 +653,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
 {
 	struct z_erofs_pcluster *pcl = folio_get_private(folio);
+	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	bool ret;
 	int i;
 
@@ -669,7 +666,7 @@ static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
 		goto out;
 
 	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
-	for (i = 0; i < pcl->pclusterpages; ++i) {
+	for (i = 0; i < pclusterpages; ++i) {
 		if (pcl->compressed_bvecs[i].page == &folio->page) {
 			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
 			ret = true;
@@ -778,20 +775,20 @@ static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)
 static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
 {
 	struct erofs_map_blocks *map = &fe->map;
+	struct super_block *sb = fe->inode->i_sb;
 	bool ztailpacking = map->m_flags & EROFS_MAP_META;
 	struct z_erofs_pcluster *pcl;
 	struct erofs_workgroup *grp;
 	int err;
 
 	if (!(map->m_flags & EROFS_MAP_ENCODED) ||
-	    (!ztailpacking && !(map->m_pa >> PAGE_SHIFT))) {
+	    (!ztailpacking && !erofs_blknr(sb, map->m_pa))) {
 		DBG_BUGON(1);
 		return -EFSCORRUPTED;
 	}
 
 	/* no available pcluster, let's allocate one */
-	pcl = z_erofs_alloc_pcluster(ztailpacking ? 1 :
-				     map->m_plen >> PAGE_SHIFT);
+	pcl = z_erofs_alloc_pcluster(map->m_plen);
 	if (IS_ERR(pcl))
 		return PTR_ERR(pcl);
 
@@ -815,10 +812,8 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
 
 	if (ztailpacking) {
 		pcl->obj.index = 0;	/* which indicates ztailpacking */
-		pcl->pageofs_in = erofs_blkoff(fe->inode->i_sb, map->m_pa);
-		pcl->tailpacking_size = map->m_plen;
 	} else {
-		pcl->obj.index = map->m_pa >> PAGE_SHIFT;
+		pcl->obj.index = erofs_blknr(sb, map->m_pa);
 
 		grp = erofs_insert_workgroup(fe->inode->i_sb, &pcl->obj);
 		if (IS_ERR(grp)) {
@@ -893,6 +888,7 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe)
 		}
 		get_page(map->buf.page);
 		WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, map->buf.page);
+		fe->pcl->pageofs_in = map->m_pa & ~PAGE_MASK;
 		fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
 	}
 	/* file-backed inplace I/O pages are traversed in reverse order */
@@ -973,12 +969,12 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
 	struct inode *const inode = fe->inode;
 	struct erofs_map_blocks *const map = &fe->map;
 	const loff_t offset = page_offset(page);
+	const unsigned int bs = i_blocksize(inode);
 	bool tight = true, exclusive;
 	unsigned int cur, end, len, split;
 	int err = 0;
 
 	z_erofs_onlinepage_init(page);
-
 	split = 0;
 	end = PAGE_SIZE;
 repeat:
@@ -1027,7 +1023,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
 	 * for inplace I/O or bvpage (should be processed in a strict order.)
 	 */
 	tight &= (fe->mode > Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE);
-	exclusive = (!cur && ((split <= 1) || tight));
+	exclusive = (!cur && ((split <= 1) || (tight && bs == PAGE_SIZE)));
 	if (cur)
 		tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED);
 
@@ -1206,34 +1202,27 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
 		struct z_erofs_bvec *bvec = &pcl->compressed_bvecs[i];
 		struct page *page = bvec->page;
 
-		/* compressed pages ought to be present before decompressing */
+		/* compressed data ought to be valid before decompressing */
 		if (!page) {
-			DBG_BUGON(1);
+			err = -EIO;
 			continue;
 		}
 		be->compressed_pages[i] = page;
 
-		if (z_erofs_is_inline_pcluster(pcl)) {
+		if (z_erofs_is_inline_pcluster(pcl) ||
+		    erofs_page_is_managed(EROFS_SB(be->sb), page)) {
 			if (!PageUptodate(page))
 				err = -EIO;
 			continue;
 		}
 
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
-		if (!z_erofs_is_shortlived_page(page)) {
-			if (erofs_page_is_managed(EROFS_SB(be->sb), page)) {
-				if (!PageUptodate(page))
-					err = -EIO;
+		if (z_erofs_is_shortlived_page(page))
 			continue;
-			}
 		z_erofs_do_decompressed_bvec(be, bvec);
 		*overlapped = true;
 	}
-	}
-
-	if (err)
 	return err;
-	return 0;
 }
 
 static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
@@ -1242,10 +1231,9 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	struct erofs_sb_info *const sbi = EROFS_SB(be->sb);
 	struct z_erofs_pcluster *pcl = be->pcl;
 	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
-	const struct z_erofs_decompressor *decompressor =
+	const struct z_erofs_decompressor *decomp =
 				&erofs_decompressors[pcl->algorithmformat];
-	unsigned int i, inputsize;
-	int err2;
+	int i, err2;
 	struct page *page;
 	bool overlapped;
 
@@ -1279,21 +1267,14 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	err2 = z_erofs_parse_in_bvecs(be, &overlapped);
 	if (err2)
 		err = err2;
-	if (err)
-		goto out;
-
-	if (z_erofs_is_inline_pcluster(pcl))
-		inputsize = pcl->tailpacking_size;
-	else
-		inputsize = pclusterpages * PAGE_SIZE;
-
-	err = decompressor->decompress(&(struct z_erofs_decompress_req) {
+	if (!err)
+		err = decomp->decompress(&(struct z_erofs_decompress_req) {
 					.sb = be->sb,
 					.in = be->compressed_pages,
 					.out = be->decompressed_pages,
 					.pageofs_in = pcl->pageofs_in,
 					.pageofs_out = pcl->pageofs_out,
-					.inputsize = inputsize,
+					.inputsize = pcl->pclustersize,
 					.outputsize = pcl->length,
 					.alg = pcl->algorithmformat,
 					.inplace_io = overlapped,
@@ -1301,7 +1282,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 					.fillgaps = pcl->multibases,
 				 }, be->pagepool);
 
-out:
 	/* must handle all compressed pages before actual file pages */
 	if (z_erofs_is_inline_pcluster(pcl)) {
 		page = pcl->compressed_bvecs[0].page;
@@ -1309,12 +1289,11 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 		put_page(page);
 	} else {
 		for (i = 0; i < pclusterpages; ++i) {
-			page = pcl->compressed_bvecs[i].page;
+			/* consider shortlived pages added when decompressing */
+			page = be->compressed_pages[i];
 
-			if (erofs_page_is_managed(sbi, page))
+			if (!page || erofs_page_is_managed(sbi, page))
 				continue;
-
-			/* recycle all individual short-lived pages */
 			(void)z_erofs_put_shortlivedpage(be->pagepool, page);
 			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
 		}
@@ -1436,86 +1415,85 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
 	z_erofs_decompressqueue_work(&io->u.work);
 }
 
-static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
+static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
+				 struct z_erofs_decompress_frontend *f,
+				 struct z_erofs_pcluster *pcl,
 				 unsigned int nr,
-					       struct page **pagepool,
 				 struct address_space *mc)
 {
-	const pgoff_t index = pcl->obj.index;
 	gfp_t gfp = mapping_gfp_mask(mc);
 	bool tocache = false;
-
+	struct z_erofs_bvec *zbv = pcl->compressed_bvecs + nr;
 	struct address_space *mapping;
-	struct page *oldpage, *page;
-	int justfound;
+	struct page *page, *oldpage;
+	int justfound, bs = i_blocksize(f->inode);
 
+	/* Except for inplace pages, the entire page can be used for I/Os */
+	bvec->bv_offset = 0;
+	bvec->bv_len = PAGE_SIZE;
 repeat:
-	page = READ_ONCE(pcl->compressed_bvecs[nr].page);
-	oldpage = page;
-
-	if (!page)
+	oldpage = READ_ONCE(zbv->page);
+	if (!oldpage)
 		goto out_allocpage;
 
-	justfound = (unsigned long)page & 1UL;
-	page = (struct page *)((unsigned long)page & ~1UL);
+	justfound = (unsigned long)oldpage & 1UL;
+	page = (struct page *)((unsigned long)oldpage & ~1UL);
+	bvec->bv_page = page;
 
+	DBG_BUGON(z_erofs_is_shortlived_page(page));
 	/*
-	 * preallocated cached pages, which is used to avoid direct reclaim
-	 * otherwise, it will go inplace I/O path instead.
+	 * Handle preallocated cached pages.  We tried to allocate such pages
+	 * without triggering direct reclaim.  If allocation failed, inplace
+	 * file-backed pages will be used instead.
 	 */
 	if (page->private == Z_EROFS_PREALLOCATED_PAGE) {
-		WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
 		set_page_private(page, 0);
+		WRITE_ONCE(zbv->page, page);
 		tocache = true;
 		goto out_tocache;
 	}
-	mapping = READ_ONCE(page->mapping);
 
+	mapping = READ_ONCE(page->mapping);
 	/*
-	 * file-backed online pages in plcuster are all locked steady,
-	 * therefore it is impossible for `mapping' to be NULL.
+	 * File-backed pages for inplace I/Os are all locked steady,
+	 * therefore it is impossible for `mapping` to be NULL.
 	 */
-	if (mapping && mapping != mc)
-		/* ought to be unmanaged pages */
-		goto out;
-
-	/* directly return for shortlived page as well */
-	if (z_erofs_is_shortlived_page(page))
-		goto out;
+	if (mapping && mapping != mc) {
+		if (zbv->offset < 0)
+			bvec->bv_offset = round_up(-zbv->offset, bs);
+		bvec->bv_len = round_up(zbv->end, bs) - bvec->bv_offset;
+		return;
+	}
 
 	lock_page(page);
-
 	/* only true if page reclaim goes wrong, should never happen */
 	DBG_BUGON(justfound && PagePrivate(page));
 
-	/* the page is still in manage cache */
+	/* the cached page is still in managed cache */
 	if (page->mapping == mc) {
-		WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
-
-		if (!PagePrivate(page)) {
+		WRITE_ONCE(zbv->page, page);
 		/*
-			 * impossible to be !PagePrivate(page) for
-			 * the current restriction as well if
-			 * the page is already in compressed_bvecs[].
+		 * The cached page is still available but without a valid
+		 * `->private` pcluster hint.  Let's reconnect them.
 		 */
+		if (!PagePrivate(page)) {
 			DBG_BUGON(!justfound);
-
-			justfound = 0;
-			set_page_private(page, (unsigned long)pcl);
-			SetPagePrivate(page);
+			/* compressed_bvecs[] already takes a ref */
+			attach_page_private(page, pcl);
+			put_page(page);
 		}
 
-		/* no need to submit io if it is already up-to-date */
+		/* no need to submit if it is already up-to-date */
 		if (PageUptodate(page)) {
 			unlock_page(page);
-			page = NULL;
+			bvec->bv_page = NULL;
 		}
-		goto out;
+		return;
 	}
 
 	/*
-	 * the managed page has been truncated, it's unsafe to
-	 * reuse this one, let's allocate a new cache-managed page.
+	 * It has been truncated, so it's unsafe to reuse this one. Let's
+	 * allocate a new page for compressed data.
 	 */
 	DBG_BUGON(page->mapping);
 	DBG_BUGON(!justfound);
@@ -1524,25 +1502,23 @@ static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
 	unlock_page(page);
 	put_page(page);
 out_allocpage:
-	page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL);
-	if (oldpage != cmpxchg(&pcl->compressed_bvecs[nr].page,
-			       oldpage, page)) {
-		erofs_pagepool_add(pagepool, page);
+	page = erofs_allocpage(&f->pagepool, gfp | __GFP_NOFAIL);
+	if (oldpage != cmpxchg(&zbv->page, oldpage, page)) {
+		erofs_pagepool_add(&f->pagepool, page);
 		cond_resched();
 		goto repeat;
 	}
+	bvec->bv_page = page;
 out_tocache:
-	if (!tocache || add_to_page_cache_lru(page, mc, index + nr, gfp)) {
-		/* turn into temporary page if fails (1 ref) */
+	if (!tocache || bs != PAGE_SIZE ||
+	    add_to_page_cache_lru(page, mc, pcl->obj.index + nr, gfp)) {
+		/* turn into a temporary shortlived page (1 ref) */
 		set_page_private(page, Z_EROFS_SHORTLIVED_PAGE);
-		goto out;
+		return;
 	}
 	attach_page_private(page, pcl);
-	/* drop a refcount added by allocpage (then we have 2 refs here) */
+	/* drop a refcount added by allocpage (then 2 refs in total here) */
 	put_page(page);
-
-out:	/* the only exit (for tracing and debugging) */
-	return page;
 }
 
 static struct z_erofs_decompressqueue *jobqueue_init(struct super_block *sb,
@@ -1597,7 +1573,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
 	qtail[JQ_BYPASS] = &pcl->next;
 }
 
-static void z_erofs_decompressqueue_endio(struct bio *bio)
+static void z_erofs_submissionqueue_endio(struct bio *bio)
 {
 	struct z_erofs_decompressqueue *q = bio->bi_private;
 	blk_status_t err = bio->bi_status;
@@ -1609,7 +1585,6 @@ static void z_erofs_decompressqueue_endio(struct bio *bio)
 
 		DBG_BUGON(PageUptodate(page));
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
-
 		if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
 			if (!err)
 				SetPageUptodate(page);
@@ -1632,17 +1607,14 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
 	z_erofs_next_pcluster_t owned_head = f->owned_head;
 	/* bio is NULL initially, so no need to initialize last_{index,bdev} */
-	pgoff_t last_index;
+	erofs_off_t last_pa;
 	struct block_device *last_bdev;
 	unsigned int nr_bios = 0;
 	struct bio *bio = NULL;
 	unsigned long pflags;
 	int memstall = 0;
 
-	/*
-	 * if managed cache is enabled, bypass jobqueue is needed,
-	 * no need to read from device for all pclusters in this queue.
-	 */
+	/* No need to read from device for pclusters in the bypass queue. */
 	q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, NULL);
 	q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, force_fg);
 
@@ -1655,7 +1627,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	do {
 		struct erofs_map_dev mdev;
 		struct z_erofs_pcluster *pcl;
-		pgoff_t cur, end;
+		erofs_off_t cur, end;
+		struct bio_vec bvec;
 		unsigned int i = 0;
 		bool bypass = true;
 
@@ -1674,18 +1647,14 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 		};
 		(void)erofs_map_dev(sb, &mdev);
 
-		cur = erofs_blknr(sb, mdev.m_pa);
-		end = cur + pcl->pclusterpages;
-
+		cur = mdev.m_pa;
+		end = cur + pcl->pclustersize;
 		do {
-			struct page *page;
-
-			page = pickup_page_for_submission(pcl, i++,
-					&f->pagepool, mc);
-			if (!page)
+			z_erofs_fill_bio_vec(&bvec, f, pcl, i++, mc);
+			if (!bvec.bv_page)
 				continue;
 
-			if (bio && (cur != last_index + 1 ||
+			if (bio && (cur != last_pa ||
 				    last_bdev != mdev.m_bdev)) {
 submit_bio_retry:
 				submit_bio(bio);
@@ -1696,7 +1665,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 				bio = NULL;
 			}
 
-			if (unlikely(PageWorkingset(page)) && !memstall) {
+			if (unlikely(PageWorkingset(bvec.bv_page)) &&
+			    !memstall) {
 				psi_memstall_enter(&pflags);
 				memstall = 1;
 			}
@@ -1704,23 +1674,24 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 			if (!bio) {
 				bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
 						REQ_OP_READ, GFP_NOIO);
-				bio->bi_end_io = z_erofs_decompressqueue_endio;
-
-				last_bdev = mdev.m_bdev;
-				bio->bi_iter.bi_sector = (sector_t)cur <<
-					(sb->s_blocksize_bits - 9);
+				bio->bi_end_io = z_erofs_submissionqueue_endio;
+				bio->bi_iter.bi_sector = cur >> 9;
 				bio->bi_private = q[JQ_SUBMIT];
 				if (readahead)
 					bio->bi_opf |= REQ_RAHEAD;
 				++nr_bios;
+				last_bdev = mdev.m_bdev;
 			}
 
-			if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
+			if (cur + bvec.bv_len > end)
+				bvec.bv_len = end - cur;
+			if (!bio_add_page(bio, bvec.bv_page, bvec.bv_len,
+					  bvec.bv_offset))
 				goto submit_bio_retry;
 
-			last_index = cur;
+			last_pa = cur + bvec.bv_len;
 			bypass = false;
-		} while (++cur < end);
+		} while ((cur += bvec.bv_len) < end);
 
 		if (!bypass)
 			qtail[JQ_SUBMIT] = &pcl->next;

fs/erofs/zmap.c

@@ -82,29 +82,26 @@ static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m,
 }
 
 static unsigned int decode_compactedbits(unsigned int lobits,
-					 unsigned int lomask,
 					 u8 *in, unsigned int pos, u8 *type)
 {
 	const unsigned int v = get_unaligned_le32(in + pos / 8) >> (pos & 7);
-	const unsigned int lo = v & lomask;
+	const unsigned int lo = v & ((1 << lobits) - 1);
 
 	*type = (v >> lobits) & 3;
 	return lo;
 }
 
-static int get_compacted_la_distance(unsigned int lclusterbits,
+static int get_compacted_la_distance(unsigned int lobits,
 				     unsigned int encodebits,
 				     unsigned int vcnt, u8 *in, int i)
 {
-	const unsigned int lomask = (1 << lclusterbits) - 1;
 	unsigned int lo, d1 = 0;
 	u8 type;
 
 	DBG_BUGON(i >= vcnt);
 
 	do {
-		lo = decode_compactedbits(lclusterbits, lomask,
-					  in, encodebits * i, &type);
+		lo = decode_compactedbits(lobits, in, encodebits * i, &type);
 
 		if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 			return d1;
@@ -123,15 +120,14 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 {
 	struct erofs_inode *const vi = EROFS_I(m->inode);
 	const unsigned int lclusterbits = vi->z_logical_clusterbits;
-	const unsigned int lomask = (1 << lclusterbits) - 1;
-	unsigned int vcnt, base, lo, encodebits, nblk, eofs;
+	unsigned int vcnt, base, lo, lobits, encodebits, nblk, eofs;
 	int i;
 	u8 *in, type;
 	bool big_pcluster;
 
 	if (1 << amortizedshift == 4 && lclusterbits <= 14)
 		vcnt = 2;
-	else if (1 << amortizedshift == 2 && lclusterbits == 12)
+	else if (1 << amortizedshift == 2 && lclusterbits <= 12)
 		vcnt = 16;
 	else
 		return -EOPNOTSUPP;
@@ -140,6 +136,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	m->nextpackoff = round_down(pos, vcnt << amortizedshift) +
 			 (vcnt << amortizedshift);
 	big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
+	lobits = max(lclusterbits, ilog2(Z_EROFS_LI_D0_CBLKCNT) + 1U);
 	encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
 	eofs = erofs_blkoff(m->inode->i_sb, pos);
 	base = round_down(eofs, vcnt << amortizedshift);
@@ -147,15 +144,14 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 
 	i = (eofs - base) >> amortizedshift;
 
-	lo = decode_compactedbits(lclusterbits, lomask,
-				  in, encodebits * i, &type);
+	lo = decode_compactedbits(lobits, in, encodebits * i, &type);
 	m->type = type;
 	if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) {
 		m->clusterofs = 1 << lclusterbits;
 
 		/* figure out lookahead_distance: delta[1] if needed */
 		if (lookahead)
-			m->delta[1] = get_compacted_la_distance(lclusterbits,
+			m->delta[1] = get_compacted_la_distance(lobits,
 						encodebits, vcnt, in, i);
 		if (lo & Z_EROFS_LI_D0_CBLKCNT) {
 			if (!big_pcluster) {
@@ -174,8 +170,8 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 		 * of which lo saves delta[1] rather than delta[0].
 		 * Hence, get delta[0] by the previous lcluster indirectly.
 		 */
-		lo = decode_compactedbits(lclusterbits, lomask,
-					  in, encodebits * (i - 1), &type);
+		lo = decode_compactedbits(lobits, in,
+					  encodebits * (i - 1), &type);
 		if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 			lo = 0;
 		else if (lo & Z_EROFS_LI_D0_CBLKCNT)
@@ -190,8 +186,8 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 		nblk = 1;
 		while (i > 0) {
 			--i;
-			lo = decode_compactedbits(lclusterbits, lomask,
-						  in, encodebits * i, &type);
+			lo = decode_compactedbits(lobits, in,
+						  encodebits * i, &type);
 			if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD)
 				i -= lo;
 
@@ -202,8 +198,8 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 		nblk = 0;
 		while (i > 0) {
 			--i;
-			lo = decode_compactedbits(lclusterbits, lomask,
-						  in, encodebits * i, &type);
+			lo = decode_compactedbits(lobits, in,
+						  encodebits * i, &type);
 			if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) {
 				if (lo & Z_EROFS_LI_D0_CBLKCNT) {
 					--i;