diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
index 510e922..84c8e52 100644
--- a/fs/erofs/compress.h
+++ b/fs/erofs/compress.h
@@ -23,8 +23,8 @@ struct z_erofs_decompress_req {
 struct z_erofs_decompressor {
 	int (*config)(struct super_block *sb, struct erofs_super_block *dsb,
 		      void *data, int size);
-	int (*decompress)(struct z_erofs_decompress_req *rq,
-			  struct page **pagepool);
+	const char *(*decompress)(struct z_erofs_decompress_req *rq,
+				  struct page **pagepool);
 	int (*init)(void);
 	void (*exit)(void);
 	char *name;
@@ -70,10 +70,10 @@ struct z_erofs_stream_dctx {
 	bool bounced;			/* is the bounce buffer used now? */
 };
 
-int z_erofs_stream_switch_bufs(struct z_erofs_stream_dctx *dctx, void **dst,
-			       void **src, struct page **pgpl);
-int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf,
-			 unsigned int padbufsize);
+const char *z_erofs_stream_switch_bufs(struct z_erofs_stream_dctx *dctx,
+				void **dst, void **src, struct page **pgpl);
+const char *z_erofs_fixup_insize(struct z_erofs_decompress_req *rq,
+				 const char *padbuf, unsigned int padbufsize);
 int __init z_erofs_init_decompressor(void);
 void z_erofs_exit_decompressor(void);
 int z_erofs_crypto_decompress(struct z_erofs_decompress_req *rq,
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 354762c..d5d0902 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -105,44 +105,58 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq,
 	return kaddr ? 1 : 0;
 }
 
-static void *z_erofs_lz4_handle_overlap(struct z_erofs_decompress_req *rq,
+static void *z_erofs_lz4_handle_overlap(const struct z_erofs_decompress_req *rq,
 			void *inpage, void *out, unsigned int *inputmargin,
 			int *maptype, bool may_inplace)
 {
-	unsigned int oend, omargin, total, i;
+	unsigned int oend, omargin, cnt, i;
 	struct page **in;
-	void *src, *tmp;
-
-	if (rq->inplace_io) {
-		oend = rq->pageofs_out + rq->outputsize;
-		omargin = PAGE_ALIGN(oend) - oend;
-		if (rq->partial_decoding || !may_inplace ||
-		    omargin < LZ4_DECOMPRESS_INPLACE_MARGIN(rq->inputsize))
-			goto docopy;
+	void *src;
 
+	/*
+	 * If in-place I/O isn't used, for example, the bounce compressed cache
+	 * can hold data for incomplete read requests. Just map the compressed
+	 * buffer as well and decompress directly.
+	 */
+	if (!rq->inplace_io) {
+		if (rq->inpages <= 1) {
+			*maptype = 0;
+			return inpage;
+		}
+		kunmap_local(inpage);
+		src = erofs_vm_map_ram(rq->in, rq->inpages);
+		if (!src)
+			return ERR_PTR(-ENOMEM);
+		*maptype = 1;
+		return src;
+	}
+	/*
+	 * Then, deal with in-place I/Os. The reasons why in-place I/O is useful
+	 * are: (1) It minimizes memory footprint during the I/O submission,
+	 * which is useful for slow storage (including network devices and
+	 * low-end HDDs/eMMCs) but with a lot inflight I/Os; (2) If in-place
+	 * decompression can also be applied, it will reuse the unique buffer so
+	 * that no extra CPU D-cache is polluted with temporary compressed data
+	 * for extreme performance.
+	 */
+	oend = rq->pageofs_out + rq->outputsize;
+	omargin = PAGE_ALIGN(oend) - oend;
+	if (!rq->partial_decoding && may_inplace &&
+	    omargin >= LZ4_DECOMPRESS_INPLACE_MARGIN(rq->inputsize)) {
 		for (i = 0; i < rq->inpages; ++i)
 			if (rq->out[rq->outpages - rq->inpages + i] !=
 			    rq->in[i])
-				goto docopy;
-		kunmap_local(inpage);
-		*maptype = 3;
-		return out + ((rq->outpages - rq->inpages) << PAGE_SHIFT);
-	}
-
-	if (rq->inpages <= 1) {
-		*maptype = 0;
-		return inpage;
+				break;
+		if (i >= rq->inpages) {
+			kunmap_local(inpage);
+			*maptype = 3;
+			return out + ((rq->outpages - rq->inpages) << PAGE_SHIFT);
+		}
 	}
-	kunmap_local(inpage);
-	src = erofs_vm_map_ram(rq->in, rq->inpages);
-	if (!src)
-		return ERR_PTR(-ENOMEM);
-	*maptype = 1;
-	return src;
-
-docopy:
-	/* Or copy compressed data which can be overlapped to per-CPU buffer */
-	in = rq->in;
+	/*
+	 * If in-place decompression can't be applied, copy compressed data that
+	 * may potentially overlap during decompression to a per-CPU buffer.
+	 */
 	src = z_erofs_get_gbuf(rq->inpages);
 	if (!src) {
 		DBG_BUGON(1);
@@ -150,20 +164,13 @@ docopy:
 		return ERR_PTR(-EFAULT);
 	}
 
-	tmp = src;
-	total = rq->inputsize;
-	while (total) {
-		unsigned int page_copycnt =
-			min_t(unsigned int, total, PAGE_SIZE - *inputmargin);
-
+	for (i = 0, in = rq->in; i < rq->inputsize; i += cnt, ++in) {
+		cnt = min_t(u32, rq->inputsize - i, PAGE_SIZE - *inputmargin);
 		if (!inpage)
 			inpage = kmap_local_page(*in);
-		memcpy(tmp, inpage + *inputmargin, page_copycnt);
+		memcpy(src + i, inpage + *inputmargin, cnt);
 		kunmap_local(inpage);
 		inpage = NULL;
-		tmp += page_copycnt;
-		total -= page_copycnt;
-		++in;
 		*inputmargin = 0;
 	}
 	*maptype = 2;
@@ -171,21 +178,21 @@ docopy:
 }
 
 /*
- * Get the exact inputsize with zero_padding feature.
- *  - For LZ4, it should work if zero_padding feature is on (5.3+);
- *  - For MicroLZMA, it'd be enabled all the time.
+ * Get the exact on-disk size of the compressed data:
+ *  - For LZ4, it should apply if the zero_padding feature is on (5.3+);
+ *  - For others, zero_padding is enabled all the time.
  */
-int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf,
-			 unsigned int padbufsize)
+const char *z_erofs_fixup_insize(struct z_erofs_decompress_req *rq,
+				 const char *padbuf, unsigned int padbufsize)
 {
 	const char *padend;
 
 	padend = memchr_inv(padbuf, 0, padbufsize);
 	if (!padend)
-		return -EFSCORRUPTED;
+		return "compressed data start not found";
 	rq->inputsize -= padend - padbuf;
 	rq->pageofs_in += padend - padbuf;
-	return 0;
+	return NULL;
 }
 
 static int z_erofs_lz4_decompress_mem(struct z_erofs_decompress_req *rq, u8 *dst)
@@ -193,6 +200,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_decompress_req *rq, u8 *dst
 	bool support_0padding = false, may_inplace = false;
 	unsigned int inputmargin;
 	u8 *out, *headpage, *src;
+	const char *reason;
 	int ret, maptype;
 
 	DBG_BUGON(*rq->in == NULL);
@@ -201,12 +209,12 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_decompress_req *rq, u8 *dst
 	/* LZ4 decompression inplace is only safe if zero_padding is enabled */
 	if (erofs_sb_has_zero_padding(EROFS_SB(rq->sb))) {
 		support_0padding = true;
-		ret = z_erofs_fixup_insize(rq, headpage + rq->pageofs_in,
+		reason = z_erofs_fixup_insize(rq, headpage + rq->pageofs_in,
 				min_t(unsigned int, rq->inputsize,
 				      rq->sb->s_blocksize - rq->pageofs_in));
-		if (ret) {
+		if (reason) {
 			kunmap_local(headpage);
-			return ret;
+			return IS_ERR(reason) ? PTR_ERR(reason) : -EFSCORRUPTED;
 		}
 		may_inplace = !((rq->pageofs_in + rq->inputsize) &
 				(rq->sb->s_blocksize - 1));
@@ -228,8 +236,6 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_decompress_req *rq, u8 *dst
 					  rq->inputsize, rq->outputsize);
 
 	if (ret != rq->outputsize) {
-		erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
-			  ret, rq->inputsize, inputmargin, rq->outputsize);
 		if (ret >= 0)
 			memset(out + ret, 0, rq->outputsize - ret);
 		ret = -EFSCORRUPTED;
@@ -250,8 +256,8 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_decompress_req *rq, u8 *dst
 	return ret;
 }
 
-static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
-				  struct page **pagepool)
+static const char *z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
+					  struct page **pagepool)
 {
 	unsigned int dst_maptype;
 	void *dst;
@@ -266,14 +272,14 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
 		/* general decoding path which can be used for all cases */
 		ret = z_erofs_lz4_prepare_dstpages(rq, pagepool);
 		if (ret < 0)
-			return ret;
+			return ERR_PTR(ret);
 		if (ret > 0) {
 			dst = page_address(*rq->out);
 			dst_maptype = 1;
 		} else {
 			dst = erofs_vm_map_ram(rq->out, rq->outpages);
 			if (!dst)
-				return -ENOMEM;
+				return ERR_PTR(-ENOMEM);
 			dst_maptype = 2;
 		}
 	}
@@ -282,11 +288,11 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
 		kunmap_local(dst);
 	else if (dst_maptype == 2)
 		vm_unmap_ram(dst, rq->outpages);
-	return ret;
+	return ERR_PTR(ret);
 }
 
-static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
-				   struct page **pagepool)
+static const char *z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
+					   struct page **pagepool)
 {
 	const unsigned int nrpages_in = rq->inpages, nrpages_out = rq->outpages;
 	const unsigned int bs = rq->sb->s_blocksize;
@@ -294,7 +300,7 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 	u8 *kin;
 
 	if (rq->outputsize > rq->inputsize)
-		return -EOPNOTSUPP;
+		return ERR_PTR(-EOPNOTSUPP);
 	if (rq->alg == Z_EROFS_COMPRESSION_INTERLACED) {
 		cur = bs - (rq->pageofs_out & (bs - 1));
 		pi = (rq->pageofs_in + rq->inputsize - cur) & ~PAGE_MASK;
@@ -334,22 +340,19 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 		kunmap_local(kin);
 	}
 	DBG_BUGON(ni > nrpages_in);
-	return 0;
+	return NULL;
 }
 
-int z_erofs_stream_switch_bufs(struct z_erofs_stream_dctx *dctx, void **dst,
-			       void **src, struct page **pgpl)
+const char *z_erofs_stream_switch_bufs(struct z_erofs_stream_dctx *dctx,
+				void **dst, void **src, struct page **pgpl)
 {
 	struct z_erofs_decompress_req *rq = dctx->rq;
-	struct super_block *sb = rq->sb;
 	struct page **pgo, *tmppage;
 	unsigned int j;
 
 	if (!dctx->avail_out) {
-		if (++dctx->no >= rq->outpages || !rq->outputsize) {
-			erofs_err(sb, "insufficient space for decompressed data");
-			return -EFSCORRUPTED;
-		}
+		if (++dctx->no >= rq->outpages || !rq->outputsize)
+			return "insufficient space for decompressed data";
 
 		if (dctx->kout)
 			kunmap_local(dctx->kout);
@@ -360,7 +363,7 @@ int z_erofs_stream_switch_bufs(struct z_erofs_stream_dctx *dctx, void **dst,
 			*pgo = erofs_allocpage(pgpl, rq->gfp);
 			if (!*pgo) {
 				dctx->kout = NULL;
-				return -ENOMEM;
+				return ERR_PTR(-ENOMEM);
 			}
 			set_page_private(*pgo, Z_EROFS_SHORTLIVED_PAGE);
 		}
@@ -374,10 +377,8 @@ int z_erofs_stream_switch_bufs(struct z_erofs_stream_dctx *dctx, void **dst,
 	}
 
 	if (dctx->inbuf_pos == dctx->inbuf_sz && rq->inputsize) {
-		if (++dctx->ni >= rq->inpages) {
-			erofs_err(sb, "invalid compressed data");
-			return -EFSCORRUPTED;
-		}
+		if (++dctx->ni >= rq->inpages)
+			return "invalid compressed data";
 		if (dctx->kout) /* unlike kmap(), take care of the orders */
 			kunmap_local(dctx->kout);
 		kunmap_local(dctx->kin);
@@ -412,12 +413,12 @@ int z_erofs_stream_switch_bufs(struct z_erofs_stream_dctx *dctx, void **dst,
 			continue;
 		tmppage = erofs_allocpage(pgpl, rq->gfp);
 		if (!tmppage)
-			return -ENOMEM;
+			return ERR_PTR(-ENOMEM);
 		set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
 		copy_highpage(tmppage, rq->in[j]);
 		rq->in[j] = tmppage;
 	}
-	return 0;
+	return NULL;
 }
 
 const struct z_erofs_decompressor *z_erofs_decomp[] = {
diff --git a/fs/erofs/decompressor_crypto.c b/fs/erofs/decompressor_crypto.c
index 97b77ab..5ef6f71 100644
--- a/fs/erofs/decompressor_crypto.c
+++ b/fs/erofs/decompressor_crypto.c
@@ -9,16 +9,17 @@ static int __z_erofs_crypto_decompress(struct z_erofs_decompress_req *rq,
 	struct sg_table st_src, st_dst;
 	struct acomp_req *req;
 	struct crypto_wait wait;
+	const char *reason;
 	u8 *headpage;
 	int ret;
 
 	headpage = kmap_local_page(*rq->in);
-	ret = z_erofs_fixup_insize(rq, headpage + rq->pageofs_in,
+	reason = z_erofs_fixup_insize(rq, headpage + rq->pageofs_in,
 				min_t(unsigned int, rq->inputsize,
 				      rq->sb->s_blocksize - rq->pageofs_in));
 	kunmap_local(headpage);
-	if (ret)
-		return ret;
+	if (reason)
+		return IS_ERR(reason) ? PTR_ERR(reason) : -EFSCORRUPTED;
 
 	req = acomp_request_alloc(tfm);
 	if (!req)
diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c
index 6909b2d..3fb7300 100644
--- a/fs/erofs/decompressor_deflate.c
+++ b/fs/erofs/decompressor_deflate.c
@@ -97,21 +97,22 @@ failed:
 	return -ENOMEM;
 }
 
-static int __z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
-					struct page **pgpl)
+static const char *__z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
+						struct page **pgpl)
 {
 	struct super_block *sb = rq->sb;
 	struct z_erofs_stream_dctx dctx = { .rq = rq, .no = -1, .ni = 0 };
 	struct z_erofs_deflate *strm;
-	int zerr, err;
+	const char *reason;
+	int zerr;
 
 	/* 1. get the exact DEFLATE compressed size */
 	dctx.kin = kmap_local_page(*rq->in);
-	err = z_erofs_fixup_insize(rq, dctx.kin + rq->pageofs_in,
+	reason = z_erofs_fixup_insize(rq, dctx.kin + rq->pageofs_in,
 			min(rq->inputsize, sb->s_blocksize - rq->pageofs_in));
-	if (err) {
+	if (reason) {
 		kunmap_local(dctx.kin);
-		return err;
+		return reason;
 	}
 
 	/* 2. get an available DEFLATE context */
@@ -129,7 +130,7 @@ again:
 	/* 3. multi-call decompress */
 	zerr = zlib_inflateInit2(&strm->z, -MAX_WBITS);
 	if (zerr != Z_OK) {
-		err = -EIO;
+		reason = ERR_PTR(-EINVAL);
 		goto failed_zinit;
 	}
 
@@ -143,10 +144,10 @@ again:
 	while (1) {
 		dctx.avail_out = strm->z.avail_out;
 		dctx.inbuf_sz = strm->z.avail_in;
-		err = z_erofs_stream_switch_bufs(&dctx,
+		reason = z_erofs_stream_switch_bufs(&dctx,
 					(void **)&strm->z.next_out,
 					(void **)&strm->z.next_in, pgpl);
-		if (err)
+		if (reason)
 			break;
 		strm->z.avail_out = dctx.avail_out;
 		strm->z.avail_in = dctx.inbuf_sz;
@@ -157,14 +158,14 @@ again:
 				break;
 			if (zerr == Z_STREAM_END && !rq->outputsize)
 				break;
-			erofs_err(sb, "failed to decompress %d in[%u] out[%u]",
-				  zerr, rq->inputsize, rq->outputsize);
-			err = -EFSCORRUPTED;
+			reason = (zerr == Z_DATA_ERROR ?
+				"corrupted compressed data" :
+				"unexpected end of stream");
 			break;
 		}
 	}
-	if (zlib_inflateEnd(&strm->z) != Z_OK && !err)
-		err = -EIO;
+	if (zlib_inflateEnd(&strm->z) != Z_OK && !reason)
+		reason = ERR_PTR(-EIO);
 	if (dctx.kout)
 		kunmap_local(dctx.kout);
 failed_zinit:
@@ -175,11 +176,11 @@ failed_zinit:
 	z_erofs_deflate_head = strm;
 	spin_unlock(&z_erofs_deflate_lock);
 	wake_up(&z_erofs_deflate_wq);
-	return err;
+	return reason;
 }
 
-static int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
-				      struct page **pgpl)
+static const char *z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
+					      struct page **pgpl)
 {
 #ifdef CONFIG_EROFS_FS_ZIP_ACCEL
 	int err;
@@ -187,7 +188,7 @@ static int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
 	if (!rq->partial_decoding) {
 		err = z_erofs_crypto_decompress(rq, pgpl);
 		if (err != -EOPNOTSUPP)
-			return err;
+			return ERR_PTR(err);
 
 	}
 #endif
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 832cffb..b4ea697 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -146,23 +146,23 @@ again:
 	return err;
 }
 
-static int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
-				   struct page **pgpl)
+static const char *z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
+					   struct page **pgpl)
 {
 	struct super_block *sb = rq->sb;
 	struct z_erofs_stream_dctx dctx = { .rq = rq, .no = -1, .ni = 0 };
 	struct xz_buf buf = {};
 	struct z_erofs_lzma *strm;
 	enum xz_ret xz_err;
-	int err;
+	const char *reason;
 
 	/* 1. get the exact LZMA compressed size */
 	dctx.kin = kmap_local_page(*rq->in);
-	err = z_erofs_fixup_insize(rq, dctx.kin + rq->pageofs_in,
+	reason = z_erofs_fixup_insize(rq, dctx.kin + rq->pageofs_in,
 			min(rq->inputsize, sb->s_blocksize - rq->pageofs_in));
-	if (err) {
+	if (reason) {
 		kunmap_local(dctx.kin);
-		return err;
+		return reason;
 	}
 
 	/* 2. get an available lzma context */
@@ -188,9 +188,9 @@ again:
 		dctx.avail_out = buf.out_size - buf.out_pos;
 		dctx.inbuf_sz = buf.in_size;
 		dctx.inbuf_pos = buf.in_pos;
-		err = z_erofs_stream_switch_bufs(&dctx, (void **)&buf.out,
-						 (void **)&buf.in, pgpl);
-		if (err)
+		reason = z_erofs_stream_switch_bufs(&dctx, (void **)&buf.out,
+						    (void **)&buf.in, pgpl);
+		if (reason)
 			break;
 
 		if (buf.out_size == buf.out_pos) {
@@ -207,9 +207,9 @@ again:
 		if (xz_err != XZ_OK) {
 			if (xz_err == XZ_STREAM_END && !rq->outputsize)
 				break;
-			erofs_err(sb, "failed to decompress %d in[%u] out[%u]",
-				  xz_err, rq->inputsize, rq->outputsize);
-			err = -EFSCORRUPTED;
+			reason = (xz_err == XZ_DATA_ERROR ?
+				"corrupted compressed data" :
+				"unexpected end of stream");
 			break;
 		}
 	} while (1);
@@ -223,7 +223,7 @@ again:
 	z_erofs_lzma_head = strm;
 	spin_unlock(&z_erofs_lzma_lock);
 	wake_up(&z_erofs_lzma_wq);
-	return err;
+	return reason;
 }
 
 const struct z_erofs_decompressor z_erofs_lzma_decomp = {
diff --git a/fs/erofs/decompressor_zstd.c b/fs/erofs/decompressor_zstd.c
index e38d93b..beae491 100644
--- a/fs/erofs/decompressor_zstd.c
+++ b/fs/erofs/decompressor_zstd.c
@@ -135,8 +135,8 @@ static int z_erofs_load_zstd_config(struct super_block *sb,
 	return strm ? -ENOMEM : 0;
 }
 
-static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
-				   struct page **pgpl)
+static const char *z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
+					   struct page **pgpl)
 {
 	struct super_block *sb = rq->sb;
 	struct z_erofs_stream_dctx dctx = { .rq = rq, .no = -1, .ni = 0 };
@@ -144,15 +144,16 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
 	zstd_out_buffer out_buf = { NULL, 0, 0 };
 	struct z_erofs_zstd *strm;
 	zstd_dstream *stream;
-	int zerr, err;
+	const char *reason;
+	int zerr;
 
 	/* 1. get the exact compressed size */
 	dctx.kin = kmap_local_page(*rq->in);
-	err = z_erofs_fixup_insize(rq, dctx.kin + rq->pageofs_in,
+	reason = z_erofs_fixup_insize(rq, dctx.kin + rq->pageofs_in,
 			min(rq->inputsize, sb->s_blocksize - rq->pageofs_in));
-	if (err) {
+	if (reason) {
 		kunmap_local(dctx.kin);
-		return err;
+		return reason;
 	}
 
 	/* 2. get an available ZSTD context */
@@ -161,7 +162,7 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
 	/* 3. multi-call decompress */
 	stream = zstd_init_dstream(z_erofs_zstd_max_dictsize, strm->wksp, strm->wkspsz);
 	if (!stream) {
-		err = -EIO;
+		reason = ERR_PTR(-ENOMEM);
 		goto failed_zinit;
 	}
 
@@ -174,9 +175,9 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
 	do {
 		dctx.inbuf_sz = in_buf.size;
 		dctx.inbuf_pos = in_buf.pos;
-		err = z_erofs_stream_switch_bufs(&dctx, &out_buf.dst,
+		reason = z_erofs_stream_switch_bufs(&dctx, &out_buf.dst,
 						 (void **)&in_buf.src, pgpl);
-		if (err)
+		if (reason)
 			break;
 
 		if (out_buf.size == out_buf.pos) {
@@ -191,11 +192,8 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
 		if (zstd_is_error(zerr) ||
 		    ((rq->outputsize + dctx.avail_out) && (!zerr || (zerr > 0 &&
 				!(rq->inputsize + in_buf.size - in_buf.pos))))) {
-			erofs_err(sb, "failed to decompress in[%u] out[%u]: %s",
-				  rq->inputsize, rq->outputsize,
-				  zstd_is_error(zerr) ? zstd_get_error_name(zerr) :
-					"unexpected end of stream");
-			err = -EFSCORRUPTED;
+			reason = zstd_is_error(zerr) ? zstd_get_error_name(zerr) :
+					"unexpected end of stream";
 			break;
 		}
 	} while (rq->outputsize + dctx.avail_out);
@@ -210,7 +208,7 @@ failed_zinit:
 	z_erofs_zstd_head = strm;
 	spin_unlock(&z_erofs_zstd_lock);
 	wake_up(&z_erofs_zstd_wq);
-	return err;
+	return reason;
 }
 
 const struct z_erofs_decompressor z_erofs_zstd_decomp = {
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 3d5738f..e24268a 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-only OR Apache-2.0 */
+/* SPDX-License-Identifier: MIT */
 /*
  * EROFS (Enhanced ROM File System) on-disk format definition
  *
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index d279384..932e8b3 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -34,13 +34,13 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
 	if (rq->bio.bi_end_io) {
 		if (ret < 0 && !rq->bio.bi_status)
 			rq->bio.bi_status = errno_to_blk_status(ret);
-		rq->bio.bi_end_io(&rq->bio);
 	} else {
 		bio_for_each_folio_all(fi, &rq->bio) {
 			DBG_BUGON(folio_test_uptodate(fi.folio));
 			erofs_onlinefolio_end(fi.folio, ret, false);
 		}
 	}
+	bio_endio(&rq->bio);
 	bio_uninit(&rq->bio);
 	kfree(rq);
 }
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 362acf8..7a346e2 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -185,7 +185,7 @@ static void erofs_fscache_bio_endio(void *priv, ssize_t transferred_or_error)
 
 	if (IS_ERR_VALUE(transferred_or_error))
 		io->bio.bi_status = errno_to_blk_status(transferred_or_error);
-	io->bio.bi_end_io(&io->bio);
+	bio_endio(&io->bio);
 	BUILD_BUG_ON(offsetof(struct erofs_fscache_bio, io) != 0);
 	erofs_fscache_io_put(&io->io);
 }
@@ -216,7 +216,7 @@ void erofs_fscache_submit_bio(struct bio *bio)
 	if (!ret)
 		return;
 	bio->bi_status = errno_to_blk_status(ret);
-	bio->bi_end_io(bio);
+	bio_endio(bio);
 }
 
 static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index f3f8d8c..937a215 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -174,15 +174,15 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 		if (!erofs_is_fileio_mode(sbi)) {
 			dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file),
 					&dif->dax_part_off, NULL, NULL);
-			if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) {
-				erofs_info(sb, "DAX unsupported by %s. Turning off DAX.",
-					   dif->path);
-				clear_opt(&sbi->opt, DAX_ALWAYS);
-			}
 		} else if (!S_ISREG(file_inode(file)->i_mode)) {
 			fput(file);
 			return -EINVAL;
 		}
+		if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) {
+			erofs_info(sb, "DAX unsupported by %s. Turning off DAX.",
+				   dif->path);
+			clear_opt(&sbi->opt, DAX_ALWAYS);
+		}
 		dif->file = file;
 	}
 
@@ -215,13 +215,13 @@ static int erofs_scan_devices(struct super_block *sb,
 			  ondisk_extradevs, sbi->devs->extra_devices);
 		return -EINVAL;
 	}
-	if (!ondisk_extradevs) {
-		if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) {
-			erofs_info(sb, "DAX unsupported by block device. Turning off DAX.");
-			clear_opt(&sbi->opt, DAX_ALWAYS);
-		}
-		return 0;
+
+	if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) {
+		erofs_info(sb, "DAX unsupported by block device. Turning off DAX.");
+		clear_opt(&sbi->opt, DAX_ALWAYS);
 	}
+	if (!ondisk_extradevs)
+		return 0;
 
 	if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb))
 		sbi->devs->flatdev = true;
@@ -639,6 +639,22 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	sbi->blkszbits = PAGE_SHIFT;
 	if (!sb->s_bdev) {
+		/*
+		 * (File-backed mounts) EROFS claims it's safe to nest other
+		 * fs contexts (including its own) due to self-controlled RO
+		 * accesses/contexts and no side-effect changes that need to
+		 * context save & restore so it can reuse the current thread
+		 * context.  However, it still needs to bump `s_stack_depth` to
+		 * avoid kernel stack overflow from nested filesystems.
+		 */
+		if (erofs_is_fileio_mode(sbi)) {
+			sb->s_stack_depth =
+				file_inode(sbi->dif0.file)->i_sb->s_stack_depth + 1;
+			if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
+				erofs_err(sb, "maximum fs stacking depth exceeded");
+				return -ENOTBLK;
+			}
+		}
 		sb->s_blocksize = PAGE_SIZE;
 		sb->s_blocksize_bits = PAGE_SHIFT;
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index bc80cfe..461a929 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1267,12 +1267,13 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 	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 *decomp =
+	const struct z_erofs_decompressor *alg =
 				z_erofs_decomp[pcl->algorithmformat];
+	bool try_free = true;
 	int i, j, jtop, err2;
 	struct page *page;
 	bool overlapped;
-	bool try_free = true;
+	const char *reason;
 
 	mutex_lock(&pcl->lock);
 	be->nr_pages = PAGE_ALIGN(pcl->length + pcl->pageofs_out) >> PAGE_SHIFT;
@@ -1304,8 +1305,8 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 	err2 = z_erofs_parse_in_bvecs(be, &overlapped);
 	if (err2)
 		err = err2;
-	if (!err)
-		err = decomp->decompress(&(struct z_erofs_decompress_req) {
+	if (!err) {
+		reason = alg->decompress(&(struct z_erofs_decompress_req) {
 					.sb = be->sb,
 					.in = be->compressed_pages,
 					.out = be->decompressed_pages,
@@ -1322,6 +1323,18 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 					.gfp = pcl->besteffort ? GFP_KERNEL :
 						GFP_NOWAIT | __GFP_NORETRY
 				 }, be->pagepool);
+		if (IS_ERR(reason)) {
+			erofs_err(be->sb, "failed to decompress (%s) %ld @ pa %llu size %u => %u",
+				  alg->name, PTR_ERR(reason), pcl->pos,
+				  pcl->pclustersize, pcl->length);
+			err = PTR_ERR(reason);
+		} else if (unlikely(reason)) {
+			erofs_err(be->sb, "failed to decompress (%s) %s @ pa %llu size %u => %u",
+				  alg->name, reason, pcl->pos,
+				  pcl->pclustersize, pcl->length);
+			err = -EFSCORRUPTED;
+		}
+	}
 
 	/* must handle all compressed pages before actual file pages */
 	if (pcl->from_meta) {
