RDMA/hns: Limit the size of extend sge of sq

The hip08 split two hardware version. The version id are 0x20 and 0x21
according to the PCI revison. The max size of extend sge of sq is limited
to 2M for 0x20 version and 8M for 0x21 version. It may be exceeded to 2M
according to the algorithm that compute the product of wqe count and
extend sge number of every wqe. But the product always less than 8M.
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -670,6 +670,7 @@ struct hns_roce_caps {
 	u32		max_sq_sg;	/* 2 */
 	u32		max_sq_inline;	/* 32 */
 	u32		max_rq_sg;	/* 2 */
+	u32		max_extend_sg;
 	int		num_qps;	/* 256k */
 	int             reserved_qps;
 	u32		max_wqes;	/* 16k */

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

@@ -1191,6 +1191,7 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 	caps->num_cqs		= HNS_ROCE_V2_MAX_CQ_NUM;
 	caps->max_cqes		= HNS_ROCE_V2_MAX_CQE_NUM;
 	caps->max_sq_sg		= HNS_ROCE_V2_MAX_SQ_SGE_NUM;
+	caps->max_extend_sg	= HNS_ROCE_V2_MAX_EXTEND_SGE_NUM;
 	caps->max_rq_sg		= HNS_ROCE_V2_MAX_RQ_SGE_NUM;
 	caps->max_sq_inline	= HNS_ROCE_V2_MAX_SQ_INLINE;
 	caps->num_uars		= HNS_ROCE_V2_UAR_NUM;

drivers/infiniband/hw/hns/hns_roce_hw_v2.h

@@ -50,6 +50,7 @@
 #define HNS_ROCE_V2_MAX_CQE_NUM			0x10000
 #define HNS_ROCE_V2_MAX_RQ_SGE_NUM		0x100
 #define HNS_ROCE_V2_MAX_SQ_SGE_NUM		0xff
+#define HNS_ROCE_V2_MAX_EXTEND_SGE_NUM		0x200000
 #define HNS_ROCE_V2_MAX_SQ_INLINE		0x20
 #define HNS_ROCE_V2_UAR_NUM			256
 #define HNS_ROCE_V2_PHY_UAR_NUM			1

drivers/infiniband/hw/hns/hns_roce_qp.c

@@ -31,6 +31,7 @@
  * SOFTWARE.
  */
 
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib_umem.h>
@@ -372,6 +373,16 @@ static int hns_roce_set_user_sq_size(struct hns_roce_dev *hr_dev,
 	if (hr_qp->sq.max_gs > 2)
 		hr_qp->sge.sge_cnt = roundup_pow_of_two(hr_qp->sq.wqe_cnt *
 							(hr_qp->sq.max_gs - 2));
+
+	if ((hr_qp->sq.max_gs > 2) && (hr_dev->pci_dev->revision == 0x20)) {
+		if (hr_qp->sge.sge_cnt > hr_dev->caps.max_extend_sg) {
+			dev_err(hr_dev->dev,
+				"The extended sge cnt error! sge_cnt=%d\n",
+				hr_qp->sge.sge_cnt);
+			return -EINVAL;
+		}
+	}
+
 	hr_qp->sge.sge_shift = 4;
 
 	/* Get buf size, SQ and RQ  are aligned to page_szie */
@@ -465,6 +476,14 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev,
 		hr_qp->sge.sge_shift = 4;
 	}
 
+	if ((hr_qp->sq.max_gs > 2) && hr_dev->pci_dev->revision == 0x20) {
+		if (hr_qp->sge.sge_cnt > hr_dev->caps.max_extend_sg) {
+			dev_err(dev, "The extended sge cnt error! sge_cnt=%d\n",
+				hr_qp->sge.sge_cnt);
+			return -EINVAL;
+		}
+	}
+
 	/* Get buf size, SQ and RQ are aligned to PAGE_SIZE */
 	page_size = 1 << (hr_dev->caps.mtt_buf_pg_sz + PAGE_SHIFT);
 	hr_qp->sq.offset = 0;