iw_cxgb4: Support the new memory registration API

Support the new memory registration API by allocating a
private page list array in c4iw_mr and populate it when
c4iw_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating build_fastreg just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (c4iw_mr)
- key, access flags (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -386,6 +386,10 @@ struct c4iw_mr {
 	struct c4iw_dev *rhp;
 	u64 kva;
 	struct tpt_attributes attr;
+	u64 *mpl;
+	dma_addr_t mpl_addr;
+	u32 max_mpl_len;
+	u32 mpl_len;
 };
 
 static inline struct c4iw_mr *to_c4iw_mr(struct ib_mr *ibmr)
@@ -973,6 +977,9 @@ struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(
 struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 			    enum ib_mr_type mr_type,
 			    u32 max_num_sg);
+int c4iw_map_mr_sg(struct ib_mr *ibmr,
+		   struct scatterlist *sg,
+		   int sg_nents);
 int c4iw_dealloc_mw(struct ib_mw *mw);
 struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
 struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,

drivers/infiniband/hw/cxgb4/mem.c

@@ -863,6 +863,7 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 	u32 mmid;
 	u32 stag = 0;
 	int ret = 0;
+	int length = roundup(max_num_sg * sizeof(u64), 32);
 
 	if (mr_type != IB_MR_TYPE_MEM_REG ||
 	    max_num_sg > t4_max_fr_depth(use_dsgl))
@@ -876,6 +877,14 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 		goto err;
 	}
 
+	mhp->mpl = dma_alloc_coherent(&rhp->rdev.lldi.pdev->dev,
+				      length, &mhp->mpl_addr, GFP_KERNEL);
+	if (!mhp->mpl) {
+		ret = -ENOMEM;
+		goto err_mpl;
+	}
+	mhp->max_mpl_len = length;
+
 	mhp->rhp = rhp;
 	ret = alloc_pbl(mhp, max_num_sg);
 	if (ret)
@@ -905,11 +914,37 @@ err2:
 	c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
 			      mhp->attr.pbl_size << 3);
 err1:
+	dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev,
+			  mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr);
+err_mpl:
 	kfree(mhp);
 err:
 	return ERR_PTR(ret);
 }
 
+static int c4iw_set_page(struct ib_mr *ibmr, u64 addr)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
+
+	if (unlikely(mhp->mpl_len == mhp->max_mpl_len))
+		return -ENOMEM;
+
+	mhp->mpl[mhp->mpl_len++] = addr;
+
+	return 0;
+}
+
+int c4iw_map_mr_sg(struct ib_mr *ibmr,
+		   struct scatterlist *sg,
+		   int sg_nents)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
+
+	mhp->mpl_len = 0;
+
+	return ib_sg_to_pages(ibmr, sg, sg_nents, c4iw_set_page);
+}
+
 struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(struct ib_device *device,
 						     int page_list_len)
 {
@@ -970,6 +1005,9 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr)
 	rhp = mhp->rhp;
 	mmid = mhp->attr.stag >> 8;
 	remove_handle(rhp, &rhp->mmidr, mmid);
+	if (mhp->mpl)
+		dma_free_coherent(&mhp->rhp->rdev.lldi.pdev->dev,
+				  mhp->max_mpl_len, mhp->mpl, mhp->mpl_addr);
 	dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
 		       mhp->attr.pbl_addr);
 	if (mhp->attr.pbl_size)

drivers/infiniband/hw/cxgb4/provider.c

@@ -557,6 +557,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.bind_mw = c4iw_bind_mw;
 	dev->ibdev.dealloc_mw = c4iw_dealloc_mw;
 	dev->ibdev.alloc_mr = c4iw_alloc_mr;
+	dev->ibdev.map_mr_sg = c4iw_map_mr_sg;
 	dev->ibdev.alloc_fast_reg_page_list = c4iw_alloc_fastreg_pbl;
 	dev->ibdev.free_fast_reg_page_list = c4iw_free_fastreg_pbl;
 	dev->ibdev.attach_mcast = c4iw_multicast_attach;

drivers/infiniband/hw/cxgb4/qp.c

@@ -605,10 +605,76 @@ static int build_rdma_recv(struct c4iw_qp *qhp, union t4_recv_wr *wqe,
 	return 0;
 }
 
+static int build_memreg(struct t4_sq *sq, union t4_wr *wqe,
+			struct ib_reg_wr *wr, u8 *len16, u8 t5dev)
+{
+	struct c4iw_mr *mhp = to_c4iw_mr(wr->mr);
+	struct fw_ri_immd *imdp;
+	__be64 *p;
+	int i;
+	int pbllen = roundup(mhp->mpl_len * sizeof(u64), 32);
+	int rem;
+
+	if (mhp->mpl_len > t4_max_fr_depth(use_dsgl))
+		return -EINVAL;
+
+	wqe->fr.qpbinde_to_dcacpu = 0;
+	wqe->fr.pgsz_shift = ilog2(wr->mr->page_size) - 12;
+	wqe->fr.addr_type = FW_RI_VA_BASED_TO;
+	wqe->fr.mem_perms = c4iw_ib_to_tpt_access(wr->access);
+	wqe->fr.len_hi = 0;
+	wqe->fr.len_lo = cpu_to_be32(mhp->ibmr.length);
+	wqe->fr.stag = cpu_to_be32(wr->key);
+	wqe->fr.va_hi = cpu_to_be32(mhp->ibmr.iova >> 32);
+	wqe->fr.va_lo_fbo = cpu_to_be32(mhp->ibmr.iova &
+					0xffffffff);
+
+	if (t5dev && use_dsgl && (pbllen > max_fr_immd)) {
+		struct fw_ri_dsgl *sglp;
+
+		for (i = 0; i < mhp->mpl_len; i++)
+			mhp->mpl[i] = (__force u64)cpu_to_be64((u64)mhp->mpl[i]);
+
+		sglp = (struct fw_ri_dsgl *)(&wqe->fr + 1);
+		sglp->op = FW_RI_DATA_DSGL;
+		sglp->r1 = 0;
+		sglp->nsge = cpu_to_be16(1);
+		sglp->addr0 = cpu_to_be64(mhp->mpl_addr);
+		sglp->len0 = cpu_to_be32(pbllen);
+
+		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*sglp), 16);
+	} else {
+		imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
+		imdp->op = FW_RI_DATA_IMMD;
+		imdp->r1 = 0;
+		imdp->r2 = 0;
+		imdp->immdlen = cpu_to_be32(pbllen);
+		p = (__be64 *)(imdp + 1);
+		rem = pbllen;
+		for (i = 0; i < mhp->mpl_len; i++) {
+			*p = cpu_to_be64((u64)mhp->mpl[i]);
+			rem -= sizeof(*p);
+			if (++p == (__be64 *)&sq->queue[sq->size])
+				p = (__be64 *)sq->queue;
+		}
+		BUG_ON(rem < 0);
+		while (rem) {
+			*p = 0;
+			rem -= sizeof(*p);
+			if (++p == (__be64 *)&sq->queue[sq->size])
+				p = (__be64 *)sq->queue;
+		}
+		*len16 = DIV_ROUND_UP(sizeof(wqe->fr) + sizeof(*imdp)
+				      + pbllen, 16);
+	}
+	return 0;
+}
+
 static int build_fastreg(struct t4_sq *sq, union t4_wr *wqe,
 			 struct ib_send_wr *send_wr, u8 *len16, u8 t5dev)
 {
 	struct ib_fast_reg_wr *wr = fast_reg_wr(send_wr);
+
 	struct fw_ri_immd *imdp;
 	__be64 *p;
 	int i;
@@ -815,6 +881,14 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 					    qhp->rhp->rdev.lldi.adapter_type) ?
 					    1 : 0);
 			break;
+		case IB_WR_REG_MR:
+			fw_opcode = FW_RI_FR_NSMR_WR;
+			swsqe->opcode = FW_RI_FAST_REGISTER;
+			err = build_memreg(&qhp->wq.sq, wqe, reg_wr(wr), &len16,
+					   is_t5(
+					   qhp->rhp->rdev.lldi.adapter_type) ?
+					   1 : 0);
+			break;
 		case IB_WR_LOCAL_INV:
 			if (wr->send_flags & IB_SEND_FENCE)
 				fw_flags |= FW_RI_LOCAL_FENCE_FLAG;