[PATCH v2 1/6] zram: handle multiple pages attached bio's bvec

[Minchan Kim]

Johannes Thumshirn reported system goes the panic when using NVMe over
Fabrics loopback target with zram.

The reason is zram expects each bvec in bio contains a single page
but nvme can attach a huge bulk of pages attached to the bio's bvec
so that zram's index arithmetic could be wrong so that out-of-bound
access makes system panic.

[1] in mainline solved solved the problem by limiting max_sectors with
SECTORS_PER_PAGE but it makes zram slow because bio should split with
each pages so this patch makes zram aware of multiple pages in a bvec
so it could solve without any regression(ie, bio split).

[1] 0bc315381fe9, zram: set physical queue limits to avoid array out of
    bounds accesses

* from v1
  * Do not exceed page boundary when set up bv.bv_len in make_request
  * change "remained" variable name with "unwritten"

Cc: Hannes Reinecke <hare@xxxxxxxx>
Reported-by: Johannes Thumshirn <jthumshirn@xxxxxxx>
Tested-by: Johannes Thumshirn <jthumshirn@xxxxxxx>
Reviewed-by: Johannes Thumshirn <jthumshirn@xxxxxxx>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
---
 drivers/block/zram/zram_drv.c | 38 +++++++++++---------------------------
 1 file changed, 11 insertions(+), 27 deletions(-)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 11cc8767af99..9c3f862b72f4 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -137,8 +137,7 @@ static inline bool valid_io_request(struct zram *zram,
 
 static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
 {
-	if (*offset + bvec->bv_len >= PAGE_SIZE)
-		(*index)++;
+	*index  += (*offset + bvec->bv_len) / PAGE_SIZE;
 	*offset = (*offset + bvec->bv_len) % PAGE_SIZE;
 }
 
@@ -838,34 +837,21 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 	}
 
 	bio_for_each_segment(bvec, bio, iter) {
-		int max_transfer_size = PAGE_SIZE - offset;
-
-		if (bvec.bv_len > max_transfer_size) {
-			/*
-			 * zram_bvec_rw() can only make operation on a single
-			 * zram page. Split the bio vector.
-			 */
-			struct bio_vec bv;
-
-			bv.bv_page = bvec.bv_page;
-			bv.bv_len = max_transfer_size;
-			bv.bv_offset = bvec.bv_offset;
+		struct bio_vec bv = bvec;
+		unsigned int unwritten = bvec.bv_len;
 
+		do {
+			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
+							unwritten);
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					 op_is_write(bio_op(bio))) < 0)
+					op_is_write(bio_op(bio))) < 0)
 				goto out;
 
-			bv.bv_len = bvec.bv_len - max_transfer_size;
-			bv.bv_offset += max_transfer_size;
-			if (zram_bvec_rw(zram, &bv, index + 1, 0,
-					 op_is_write(bio_op(bio))) < 0)
-				goto out;
-		} else
-			if (zram_bvec_rw(zram, &bvec, index, offset,
-					 op_is_write(bio_op(bio))) < 0)
-				goto out;
+			bv.bv_offset += bv.bv_len;
+			unwritten -= bv.bv_len;
 
-		update_position(&index, &offset, &bvec);
+			update_position(&index, &offset, &bv);
+		} while (unwritten);
 	}
 
 	bio_endio(bio);
@@ -882,8 +868,6 @@ static blk_qc_t zram_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct zram *zram = queue->queuedata;
 
-	blk_queue_split(queue, &bio, queue->bio_split);
-
 	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
 					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
-- 
2.7.4