@@ -1361,6 +1361,11 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev,
return ret;
}
+/* This is the bottom bt pages number of a 100G MR on 4K OS, assuming
+ * the bt page size is not expanded by cal_best_bt_pg_sz()
+ */
+#define RESCHED_LOOP_CNT_THRESHOLD_ON_4K 12800
+
/* construct the base address table and link them by address hop config */
int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
struct hns_roce_hem_list *hem_list,
@@ -1369,6 +1374,7 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
{
const struct hns_roce_buf_region *r;
int ofs, end;
+ int loop;
int unit;
int ret;
int i;
@@ -1386,7 +1392,10 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
continue;
end = r->offset + r->count;
- for (ofs = r->offset; ofs < end; ofs += unit) {
+ for (ofs = r->offset, loop = 1; ofs < end; ofs += unit, loop++) {
+ if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+ cond_resched();
+
ret = hem_list_alloc_mid_bt(hr_dev, r, unit, ofs,
hem_list->mid_bt[i],
&hem_list->btm_bt);
@@ -1443,9 +1452,14 @@ void *hns_roce_hem_list_find_mtt(struct hns_roce_dev *hr_dev,
struct list_head *head = &hem_list->btm_bt;
struct hns_roce_hem_item *hem, *temp_hem;
void *cpu_base = NULL;
+ int loop = 1;
int nr = 0;
list_for_each_entry_safe(hem, temp_hem, head, sibling) {
+ if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+ cond_resched();
+ loop++;
+
if (hem_list_page_is_in_range(hem, offset)) {
nr = offset - hem->start;
cpu_base = hem->addr + nr * BA_BYTE_LEN;
Driver runs a for-loop when allocating bt pages and mapping them with buffer pages. When a large buffer (e.g. MR over 100GB) is being allocated, it may require a considerable loop count. This will lead to soft lockup: watchdog: BUG: soft lockup - CPU#27 stuck for 22s! ... Call trace: hem_list_alloc_mid_bt+0x124/0x394 [hns_roce_hw_v2] hns_roce_hem_list_request+0xf8/0x160 [hns_roce_hw_v2] hns_roce_mtr_create+0x2e4/0x360 [hns_roce_hw_v2] alloc_mr_pbl+0xd4/0x17c [hns_roce_hw_v2] hns_roce_reg_user_mr+0xf8/0x190 [hns_roce_hw_v2] ib_uverbs_reg_mr+0x118/0x290 watchdog: BUG: soft lockup - CPU#35 stuck for 23s! ... Call trace: hns_roce_hem_list_find_mtt+0x7c/0xb0 [hns_roce_hw_v2] mtr_map_bufs+0xc4/0x204 [hns_roce_hw_v2] hns_roce_mtr_create+0x31c/0x3c4 [hns_roce_hw_v2] alloc_mr_pbl+0xb0/0x160 [hns_roce_hw_v2] hns_roce_reg_user_mr+0x108/0x1c0 [hns_roce_hw_v2] ib_uverbs_reg_mr+0x120/0x2bc Add a cond_resched() to fix soft lockup during these loops. In order not to affect the allocation performance of normal-size buffer, set the loop count of a 100GB MR as the threshold to call cond_resched(). Fixes: 38389eaa4db1 ("RDMA/hns: Add mtr support for mixed multihop addressing") Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com> --- drivers/infiniband/hw/hns/hns_roce_hem.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)