erofs: refine z_erofs_transform_plain() for sub-page block support

Sub-page block support is still unusable even with previous commits if
interlaced PLAIN pclusters exist.  Such pclusters can be found if the
fragment feature is enabled.

This commit tries to handle "the head part" of interlaced PLAIN
pclusters first: it was once explained in commit fdffc091 ("erofs:
support interlaced uncompressed data for compressed files").

It uses a unique way for both shifted and interlaced PLAIN pclusters.
As an added bonus, PLAIN pclusters larger than the block size is also
supported now for the upcoming large lclusters.
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20231206091057.87027-5-hsiangkao@linux.alibaba.com

fs/erofs/decompressor.c

@@ -320,43 +320,58 @@ 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;
 }