[for-rc,1/4] RDMA/hns: Fix mapping error of zero-hop WQE buffer

Commit Message

Junxian Huang Dec. 20, 2024, 5:52 a.m. UTC

From: wenglianfa <[e-mail]>

Due to HW limitation, the three region of WQE buffer must be mapped
and set to HW in a fixed order: SQ buffer, SGE buffer, and RQ buffer.

Currently when one region is zero-hop while the other two are not,
the zero-hop region will not be mapped. This violate the limitation
above and leads to address error.

Fixes: 38389eaa4db1 ("RDMA/hns: Add mtr support for mixed multihop addressing")
Signed-off-by: wenglianfa <[e-mail]>
Signed-off-by: Junxian Huang <[e-mail]>
---
 drivers/infiniband/hw/hns/hns_roce_hem.c | 43 ++++++++++++++++--------
 drivers/infiniband/hw/hns/hns_roce_mr.c  |  5 ---
 2 files changed, 29 insertions(+), 19 deletions(-)

Patch

diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index f84521be3bea..605562122ecc 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -931,6 +931,7 @@  struct hns_roce_hem_item {
 	size_t count; /* max ba numbers */
 	int start; /* start buf offset in this hem */
 	int end; /* end buf offset in this hem */
+	bool exist_bt;
 };
 
 /* All HEM items are linked in a tree structure */
@@ -959,6 +960,7 @@  hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count,
 		}
 	}
 
+	hem->exist_bt = exist_bt;
 	hem->count = count;
 	hem->start = start;
 	hem->end = end;
@@ -969,22 +971,22 @@  hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count,
 }
 
 static void hem_list_free_item(struct hns_roce_dev *hr_dev,
-			       struct hns_roce_hem_item *hem, bool exist_bt)
+			       struct hns_roce_hem_item *hem)
 {
-	if (exist_bt)
+	if (hem->exist_bt)
 		dma_free_coherent(hr_dev->dev, hem->count * BA_BYTE_LEN,
 				  hem->addr, hem->dma_addr);
 	kfree(hem);
 }
 
 static void hem_list_free_all(struct hns_roce_dev *hr_dev,
-			      struct list_head *head, bool exist_bt)
+			      struct list_head *head)
 {
 	struct hns_roce_hem_item *hem, *temp_hem;
 
 	list_for_each_entry_safe(hem, temp_hem, head, list) {
 		list_del(&hem->list);
-		hem_list_free_item(hr_dev, hem, exist_bt);
+		hem_list_free_item(hr_dev, hem);
 	}
 }
 
@@ -1084,6 +1086,10 @@  int hns_roce_hem_list_calc_root_ba(const struct hns_roce_buf_region *regions,
 
 	for (i = 0; i < region_cnt; i++) {
 		r = (struct hns_roce_buf_region *)&regions[i];
+		/* when r->hopnum = 0, the region should not occupy root_ba. */
+		if (!r->hopnum)
+			continue;
+
 		if (r->hopnum > 1) {
 			step = hem_list_calc_ba_range(r->hopnum, 1, unit);
 			if (step > 0)
@@ -1177,7 +1183,7 @@  static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev,
 
 err_exit:
 	for (level = 1; level < hopnum; level++)
-		hem_list_free_all(hr_dev, &temp_list[level], true);
+		hem_list_free_all(hr_dev, &temp_list[level]);
 
 	return ret;
 }
@@ -1218,16 +1224,26 @@  static int alloc_fake_root_bt(struct hns_roce_dev *hr_dev, void *cpu_base,
 {
 	struct hns_roce_hem_item *hem;
 
+	/* This is on the has_mtt branch, if r->hopnum
+	 * is 0, there is no root_ba to reuse for the
+	 * region's fake hem, so a dma_alloc request is
+	 * necessary here.
+	 */
 	hem = hem_list_alloc_item(hr_dev, r->offset, r->offset + r->count - 1,
-				  r->count, false);
+				  r->count, !r->hopnum);
 	if (!hem)
 		return -ENOMEM;
 
-	hem_list_assign_bt(hem, cpu_base, phy_base);
+	/* The root_ba can be reused only when r->hopnum > 0. */
+	if (r->hopnum)
+		hem_list_assign_bt(hem, cpu_base, phy_base);
 	list_add(&hem->list, branch_head);
 	list_add(&hem->sibling, leaf_head);
 
-	return r->count;
+	/* If r->hopnum == 0, 0 is returned,
+	 * so that the root_bt entry is not occupied.
+	 */
+	return r->hopnum ? r->count : 0;
 }
 
 static int setup_middle_bt(struct hns_roce_dev *hr_dev, void *cpu_base,
@@ -1271,7 +1287,7 @@  setup_root_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem_list *hem_list,
 		return -ENOMEM;
 
 	total = 0;
-	for (i = 0; i < region_cnt && total < max_ba_num; i++) {
+	for (i = 0; i < region_cnt && total <= max_ba_num; i++) {
 		r = &regions[i];
 		if (!r->count)
 			continue;
@@ -1337,9 +1353,9 @@  static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev,
 			     region_cnt);
 	if (ret) {
 		for (i = 0; i < region_cnt; i++)
-			hem_list_free_all(hr_dev, &head.branch[i], false);
+			hem_list_free_all(hr_dev, &head.branch[i]);
 
-		hem_list_free_all(hr_dev, &head.root, true);
+		hem_list_free_all(hr_dev, &head.root);
 	}
 
 	return ret;
@@ -1402,10 +1418,9 @@  void hns_roce_hem_list_release(struct hns_roce_dev *hr_dev,
 
 	for (i = 0; i < HNS_ROCE_MAX_BT_REGION; i++)
 		for (j = 0; j < HNS_ROCE_MAX_BT_LEVEL; j++)
-			hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j],
-					  j != 0);
+			hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j]);
 
-	hem_list_free_all(hr_dev, &hem_list->root_bt, true);
+	hem_list_free_all(hr_dev, &hem_list->root_bt);
 	INIT_LIST_HEAD(&hem_list->btm_bt);
 	hem_list->root_ba = 0;
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index bf30b3a65a9b..55b9283bfc6f 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -814,11 +814,6 @@  int hns_roce_mtr_map(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 	for (i = 0, mapped_cnt = 0; i < mtr->hem_cfg.region_count &&
 	     mapped_cnt < page_cnt; i++) {
 		r = &mtr->hem_cfg.region[i];
-		/* if hopnum is 0, no need to map pages in this region */
-		if (!r->hopnum) {
-			mapped_cnt += r->count;
-			continue;
-		}
 
 		if (r->offset + r->count > page_cnt) {
 			ret = -EINVAL;