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])
-					goto docopy;
-		}
+		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;
-	}
-
-	if (rq->out[0] == *rq->in) {
-		DBG_BUGON(rq->pageofs_out);
-		return 0;
+	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);
+			}
+			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;
 
-	pr_err("(device %s): %s: %pV", sb->s_id, func, &vaf);
+	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;
 
-	pr_info("(device %s): %pV", sb->s_id, &vaf);
+	if (sb)
+		pr_info("(device %s): %pV", sb->s_id, &vaf);
+	else
+		pr_info("%pV", &vaf);
 	va_end(args);
 }
 

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;