diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c
index 752060d7261c..33c1b6a0a738 100644
--- a/block/blk-mq-dma.c
+++ b/block/blk-mq-dma.c
@@ -4,8 +4,75 @@
  */
 #include <linux/blk-integrity.h>
 #include <linux/blk-mq-dma.h>
+#include <linux/scatterlist.h>
 #include "blk.h"
 
+static void dump_rq_mapping_debug(struct request *rq, struct scatterlist *sglist,
+				  int nsegs)
+{
+	struct scatterlist *sg;
+	struct bio *bio;
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	int i;
+
+	pr_err("=== __blk_rq_map_sg DEBUG DUMP ===\n");
+	pr_err("DISK: %s\n", rq->q->disk ? rq->q->disk->disk_name : "(null)");
+
+	/* Dump nsegs vs expected */
+	pr_err("nsegs=%d nr_phys_segments=%u\n",
+	       nsegs, blk_rq_nr_phys_segments(rq));
+
+	/* Dump request info */
+	pr_err("REQUEST: __data_len=%u __sector=%llu cmd_flags=0x%x "
+	       "rq_flags=0x%x nr_phys_segments=%u phys_gap_bit=%u\n",
+	       rq->__data_len, (unsigned long long)rq->__sector,
+	       rq->cmd_flags, (__force unsigned int)rq->rq_flags,
+	       rq->nr_phys_segments, rq->phys_gap_bit);
+
+	/* Dump each SG element */
+	pr_err("--- SG LIST (%d entries) ---\n", nsegs);
+	for_each_sg(sglist, sg, nsegs, i) {
+		pr_err("  sg[%d]: pfn=0x%lx offset=%u len=%u dma_addr=0x%llx\n",
+		       i, page_to_pfn(sg_page(sg)), sg->offset, sg->length,
+		       (unsigned long long)sg_dma_address(sg));
+	}
+
+	/* Dump each bio */
+	pr_err("--- BIO LIST ---\n");
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		pr_err("  BIO %p: bi_iter={sector=%llu size=%u idx=%u bvec_done=%u} "
+		       "bi_flags=0x%x bi_opf=0x%x bi_vcnt=%u bi_bvec_gap_bit=%u\n",
+		       bio,
+		       (unsigned long long)bio->bi_iter.bi_sector,
+		       bio->bi_iter.bi_size, bio->bi_iter.bi_idx,
+		       bio->bi_iter.bi_bvec_done,
+		       bio->bi_flags, bio->bi_opf, bio->bi_vcnt,
+		       bio->bi_bvec_gap_bit);
+
+		/* Dump each bvec in this bio */
+		pr_err("    --- BVECS (bi_vcnt=%u) ---\n", bio->bi_vcnt);
+		for (i = 0; i < bio->bi_vcnt; i++) {
+			struct bio_vec *bvp = &bio->bi_io_vec[i];
+
+			pr_err("      bvec[%d]: pfn=0x%lx len=%u offset=%u\n",
+			       i, page_to_pfn(bvp->bv_page), bvp->bv_len,
+			       bvp->bv_offset);
+		}
+
+		/* Also dump effective bvecs via iterator */
+		pr_err("    --- EFFECTIVE BVECS (via iter) ---\n");
+		i = 0;
+		bio_for_each_bvec(bv, bio, iter) {
+			pr_err("      eff_bvec[%d]: pfn=0x%lx len=%u offset=%u\n",
+			       i++, page_to_pfn(bv.bv_page), bv.bv_len,
+			       bv.bv_offset);
+		}
+	}
+
+	pr_err("=== END DEBUG DUMP ===\n");
+}
+
 static bool __blk_map_iter_next(struct blk_map_iter *iter)
 {
 	if (iter->iter.bi_size)
@@ -306,6 +373,8 @@ int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist,
 	 * Something must have been wrong if the figured number of
 	 * segment is bigger than number of req's physical segments
 	 */
+	if (nsegs > blk_rq_nr_phys_segments(rq))
+		dump_rq_mapping_debug(rq, sglist, nsegs);
 	WARN_ON(nsegs > blk_rq_nr_phys_segments(rq));
 
 	return nsegs;
diff --git a/block/blk.h b/block/blk.h
index 98f4dfd4ec75..980eef1f5690 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -380,7 +380,7 @@ static inline bool bio_may_need_split(struct bio *bio,
 		return true;
 
 	bv = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
-	if (bio->bi_iter.bi_size > bv->bv_len)
+	if (bio->bi_iter.bi_size > bv->bv_len - bio->bi_iter.bi_bvec_done)
 		return true;
 	return bv->bv_len + bv->bv_offset > lim->max_fast_segment_size;
 }