Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma fixes from Jason Gunthorpe:
 "Many bug fixes in several drivers:

   - Fix misuse of the DMA API in rtrs

   - Several irdma issues: hung task due to SQ flushing, incorrect
     capability reporting to userspace, improper error handling for MW
     corners, touching an uninitialized SGL for during invalidation.

   - hns was using the wrong page size limits for the HW, an incorrect
     calculation of wqe_shift causing WQE corruption, and mis computed a
     timer id.

   - Fix a crash in SRP triggered by blktests

   - Fix compiler errors by calling virt_to_page() with the proper type
     in siw

   - Userspace triggerable deadlock in ODP

   - mlx5 could use the wrong profile due to some driver loading races,
     counters were not working in some device configurations, and a
     crash on error unwind"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/irdma: Report RNR NAK generation in device caps
  RDMA/irdma: Use s/g array in post send only when its valid
  RDMA/irdma: Return correct WC error for bind operation failure
  RDMA/irdma: Return error on MR deregister CQP failure
  RDMA/irdma: Report the correct max cqes from query device
  MAINTAINERS: Update maintainers of HiSilicon RoCE
  RDMA/mlx5: Fix UMR cleanup on error flow of driver init
  RDMA/mlx5: Set local port to one when accessing counters
  RDMA/mlx5: Rely on RoCE fw cap instead of devlink when setting profile
  IB/core: Fix a nested dead lock as part of ODP flow
  RDMA/siw: Pass a pointer to virt_to_page()
  RDMA/srp: Set scmnd->result only when scmnd is not NULL
  RDMA/hns: Remove the num_qpc_timer variable
  RDMA/hns: Fix wrong fixed value of qp->rq.wqe_shift
  RDMA/hns: Fix supported page size
  RDMA/cma: Fix arguments order in net device validation
  RDMA/irdma: Fix drain SQ hang with no completion
  RDMA/rtrs-srv: Pass the correct number of entries for dma mapped SGL
  RDMA/rtrs-clt: Use the right sg_cnt after ib_dma_map_sg

MAINTAINERS

@@ -9208,8 +9208,8 @@ F:	Documentation/ABI/testing/debugfs-hisi-zip
 F:	drivers/crypto/hisilicon/zip/
 
 HISILICON ROCE DRIVER
+M:	Haoyue Xu <xuhaoyue1@hisilicon.com>
 M:	Wenpeng Liang <liangwenpeng@huawei.com>
-M:	Weihang Li <liweihang@huawei.com>
 L:	linux-rdma@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt

drivers/infiniband/core/cma.c

@@ -1841,8 +1841,8 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 		}
 
 		if (!validate_net_dev(*net_dev,
-				 (struct sockaddr *)&req->listen_addr_storage,
-				 (struct sockaddr *)&req->src_addr_storage)) {
+				 (struct sockaddr *)&req->src_addr_storage,
+				 (struct sockaddr *)&req->listen_addr_storage)) {
 			id_priv = ERR_PTR(-EHOSTUNREACH);
 			goto err;
 		}

drivers/infiniband/core/umem_odp.c

@@ -462,7 +462,7 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 		mutex_unlock(&umem_odp->umem_mutex);
 
 out_put_mm:
-	mmput(owning_mm);
+	mmput_async(owning_mm);
 out_put_task:
 	if (owning_process)
 		put_task_struct(owning_process);

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -730,7 +730,6 @@ struct hns_roce_caps {
 	u32		num_qps;
 	u32		num_pi_qps;
 	u32		reserved_qps;
-	int		num_qpc_timer;
 	u32		num_srqs;
 	u32		max_wqes;
 	u32		max_srq_wrs;

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

@@ -1977,7 +1977,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
 
 	caps->num_mtpts		= HNS_ROCE_V2_MAX_MTPT_NUM;
 	caps->num_pds		= HNS_ROCE_V2_MAX_PD_NUM;
-	caps->num_qpc_timer	= HNS_ROCE_V2_MAX_QPC_TIMER_NUM;
+	caps->qpc_timer_bt_num	= HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM;
 	caps->cqc_timer_bt_num	= HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM;
 
 	caps->max_qp_init_rdma	= HNS_ROCE_V2_MAX_QP_INIT_RDMA;
@@ -2273,7 +2273,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
 	caps->max_rq_sg		     = le16_to_cpu(resp_a->max_rq_sg);
 	caps->max_rq_sg = roundup_pow_of_two(caps->max_rq_sg);
 	caps->max_extend_sg	     = le32_to_cpu(resp_a->max_extend_sg);
-	caps->num_qpc_timer	     = le16_to_cpu(resp_a->num_qpc_timer);
 	caps->max_srq_sges	     = le16_to_cpu(resp_a->max_srq_sges);
 	caps->max_srq_sges = roundup_pow_of_two(caps->max_srq_sges);
 	caps->num_aeq_vectors	     = resp_a->num_aeq_vectors;

drivers/infiniband/hw/hns/hns_roce_hw_v2.h

@@ -36,11 +36,11 @@
 #include <linux/bitops.h>
 
 #define HNS_ROCE_V2_MAX_QP_NUM			0x1000
-#define HNS_ROCE_V2_MAX_QPC_TIMER_NUM		0x200
 #define HNS_ROCE_V2_MAX_WQE_NUM			0x8000
 #define HNS_ROCE_V2_MAX_SRQ_WR			0x8000
 #define HNS_ROCE_V2_MAX_SRQ_SGE			64
 #define HNS_ROCE_V2_MAX_CQ_NUM			0x100000
+#define HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM	0x100
 #define HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM	0x100
 #define HNS_ROCE_V2_MAX_SRQ_NUM			0x100000
 #define HNS_ROCE_V2_MAX_CQE_NUM			0x400000
@@ -83,7 +83,7 @@
 
 #define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ		PAGE_SIZE
 #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		PAGE_SIZE
-#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
+#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFF000
 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
 #define HNS_ROCE_INVALID_LKEY			0x0
 #define HNS_ROCE_INVALID_SGE_LENGTH		0x80000000

drivers/infiniband/hw/hns/hns_roce_main.c

@@ -725,7 +725,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
 		ret = hns_roce_init_hem_table(hr_dev, &hr_dev->qpc_timer_table,
 					      HEM_TYPE_QPC_TIMER,
 					      hr_dev->caps.qpc_timer_entry_sz,
-					      hr_dev->caps.num_qpc_timer, 1);
+					      hr_dev->caps.qpc_timer_bt_num, 1);
 		if (ret) {
 			dev_err(dev,
 				"Failed to init QPC timer memory, aborting.\n");

drivers/infiniband/hw/hns/hns_roce_qp.c

@@ -462,11 +462,8 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 	hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) +
 					      hr_qp->rq.rsv_sge);
 
-	if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE)
-		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz);
-	else
-		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz *
-					    hr_qp->rq.max_gs);
+	hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz *
+				    hr_qp->rq.max_gs);
 
 	hr_qp->rq.wqe_cnt = cnt;
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE &&

drivers/infiniband/hw/irdma/uk.c

@@ -497,7 +497,8 @@ int irdma_uk_send(struct irdma_qp_uk *qp, struct irdma_post_sq_info *info,
 			      FIELD_PREP(IRDMAQPSQ_IMMDATA, info->imm_data));
 		i = 0;
 	} else {
-		qp->wqe_ops.iw_set_fragment(wqe, 0, op_info->sg_list,
+		qp->wqe_ops.iw_set_fragment(wqe, 0,
+					    frag_cnt ? op_info->sg_list : NULL,
 					    qp->swqe_polarity);
 		i = 1;
 	}
@@ -1005,6 +1006,7 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq,
 	int ret_code;
 	bool move_cq_head = true;
 	u8 polarity;
+	u8 op_type;
 	bool ext_valid;
 	__le64 *ext_cqe;
 
@@ -1187,7 +1189,6 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq,
 			do {
 				__le64 *sw_wqe;
 				u64 wqe_qword;
-				u8 op_type;
 				u32 tail;
 
 				tail = qp->sq_ring.tail;
@@ -1204,6 +1205,8 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq,
 					break;
 				}
 			} while (1);
+			if (op_type == IRDMA_OP_TYPE_BIND_MW && info->minor_err == FLUSH_PROT_ERR)
+				info->minor_err = FLUSH_MW_BIND_ERR;
 			qp->sq_flush_seen = true;
 			if (!IRDMA_RING_MORE_WORK(qp->sq_ring))
 				qp->sq_flush_complete = true;

drivers/infiniband/hw/irdma/utils.c

@@ -590,11 +590,14 @@ static int irdma_wait_event(struct irdma_pci_f *rf,
 	cqp_error = cqp_request->compl_info.error;
 	if (cqp_error) {
 		err_code = -EIO;
-		if (cqp_request->compl_info.maj_err_code == 0xFFFF &&
-		    cqp_request->compl_info.min_err_code == 0x8029) {
-			if (!rf->reset) {
-				rf->reset = true;
-				rf->gen_ops.request_reset(rf);
+		if (cqp_request->compl_info.maj_err_code == 0xFFFF) {
+			if (cqp_request->compl_info.min_err_code == 0x8002)
+				err_code = -EBUSY;
+			else if (cqp_request->compl_info.min_err_code == 0x8029) {
+				if (!rf->reset) {
+					rf->reset = true;
+					rf->gen_ops.request_reset(rf);
+				}
 			}
 		}
 	}
@@ -2598,7 +2601,7 @@ void irdma_generate_flush_completions(struct irdma_qp *iwqp)
 		spin_unlock_irqrestore(&iwqp->lock, flags2);
 		spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1);
 		if (compl_generated)
-			irdma_comp_handler(iwqp->iwrcq);
+			irdma_comp_handler(iwqp->iwscq);
 	} else {
 		spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1);
 		mod_delayed_work(iwqp->iwdev->cleanup_wq, &iwqp->dwork_flush,

drivers/infiniband/hw/irdma/verbs.c

@@ -39,15 +39,18 @@ static int irdma_query_device(struct ib_device *ibdev,
 	props->max_send_sge = hw_attrs->uk_attrs.max_hw_wq_frags;
 	props->max_recv_sge = hw_attrs->uk_attrs.max_hw_wq_frags;
 	props->max_cq = rf->max_cq - rf->used_cqs;
-	props->max_cqe = rf->max_cqe;
+	props->max_cqe = rf->max_cqe - 1;
 	props->max_mr = rf->max_mr - rf->used_mrs;
 	props->max_mw = props->max_mr;
 	props->max_pd = rf->max_pd - rf->used_pds;
 	props->max_sge_rd = hw_attrs->uk_attrs.max_hw_read_sges;
 	props->max_qp_rd_atom = hw_attrs->max_hw_ird;
 	props->max_qp_init_rd_atom = hw_attrs->max_hw_ord;
-	if (rdma_protocol_roce(ibdev, 1))
+	if (rdma_protocol_roce(ibdev, 1)) {
+		props->device_cap_flags |= IB_DEVICE_RC_RNR_NAK_GEN;
 		props->max_pkeys = IRDMA_PKEY_TBL_SZ;
+	}
+
 	props->max_ah = rf->max_ah;
 	props->max_mcast_grp = rf->max_mcg;
 	props->max_mcast_qp_attach = IRDMA_MAX_MGS_PER_CTX;
@@ -3009,6 +3012,7 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
 	struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc;
 	struct irdma_cqp_request *cqp_request;
 	struct cqp_cmds_info *cqp_info;
+	int status;
 
 	if (iwmr->type != IRDMA_MEMREG_TYPE_MEM) {
 		if (iwmr->region) {
@@ -3039,8 +3043,11 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
 	cqp_info->post_sq = 1;
 	cqp_info->in.u.dealloc_stag.dev = &iwdev->rf->sc_dev;
 	cqp_info->in.u.dealloc_stag.scratch = (uintptr_t)cqp_request;
-	irdma_handle_cqp_op(iwdev->rf, cqp_request);
+	status = irdma_handle_cqp_op(iwdev->rf, cqp_request);
 	irdma_put_cqp_request(&iwdev->rf->cqp, cqp_request);
+	if (status)
+		return status;
+
 	irdma_free_stag(iwdev, iwmr->stag);
 done:
 	if (iwpbl->pbl_allocated)

drivers/infiniband/hw/mlx5/mad.c

@@ -166,6 +166,12 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num,
 		mdev = dev->mdev;
 		mdev_port_num = 1;
 	}
+	if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) {
+		/* set local port to one for Function-Per-Port HCA. */
+		mdev = dev->mdev;
+		mdev_port_num = 1;
+	}
+
 	/* Declaring support of extended counters */
 	if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) {
 		struct ib_class_port_info cpi = {};

drivers/infiniband/hw/mlx5/main.c

@@ -4336,7 +4336,7 @@ static int mlx5r_probe(struct auxiliary_device *adev,
 	dev->mdev = mdev;
 	dev->num_ports = num_ports;
 
-	if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_is_roce_init_enabled(mdev))
+	if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_get_roce_state(mdev))
 		profile = &raw_eth_profile;
 	else
 		profile = &pf_profile;

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -708,6 +708,7 @@ struct mlx5_ib_umr_context {
 };
 
 enum {
+	MLX5_UMR_STATE_UNINIT,
 	MLX5_UMR_STATE_ACTIVE,
 	MLX5_UMR_STATE_RECOVER,
 	MLX5_UMR_STATE_ERR,

drivers/infiniband/hw/mlx5/umr.c

@@ -177,6 +177,7 @@ int mlx5r_umr_resource_init(struct mlx5_ib_dev *dev)
 
 	sema_init(&dev->umrc.sem, MAX_UMR_WR);
 	mutex_init(&dev->umrc.lock);
+	dev->umrc.state = MLX5_UMR_STATE_ACTIVE;
 
 	return 0;
 
@@ -191,6 +192,8 @@ int mlx5r_umr_resource_init(struct mlx5_ib_dev *dev)
 
 void mlx5r_umr_resource_cleanup(struct mlx5_ib_dev *dev)
 {
+	if (dev->umrc.state == MLX5_UMR_STATE_UNINIT)
+		return;
 	ib_destroy_qp(dev->umrc.qp);
 	ib_free_cq(dev->umrc.cq);
 	ib_dealloc_pd(dev->umrc.pd);

drivers/infiniband/sw/siw/siw_qp_tx.c

@@ -29,7 +29,7 @@ static struct page *siw_get_pblpage(struct siw_mem *mem, u64 addr, int *idx)
 	dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx);
 
 	if (paddr)
-		return virt_to_page(paddr);
+		return virt_to_page((void *)paddr);
 
 	return NULL;
 }
@@ -533,13 +533,23 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 					kunmap_local(kaddr);
 				}
 			} else {
-				u64 va = sge->laddr + sge_off;
+				/*
+				 * Cast to an uintptr_t to preserve all 64 bits
+				 * in sge->laddr.
+				 */
+				uintptr_t va = (uintptr_t)(sge->laddr + sge_off);
 
-				page_array[seg] = virt_to_page(va & PAGE_MASK);
+				/*
+				 * virt_to_page() takes a (void *) pointer
+				 * so cast to a (void *) meaning it will be 64
+				 * bits on a 64 bit platform and 32 bits on a
+				 * 32 bit platform.
+				 */
+				page_array[seg] = virt_to_page((void *)(va & PAGE_MASK));
 				if (do_crc)
 					crypto_shash_update(
 						c_tx->mpa_crc_hd,
-						(void *)(uintptr_t)va,
+						(void *)va,
 						plen);
 			}
 

drivers/infiniband/ulp/rtrs/rtrs-clt.c

@@ -1004,7 +1004,8 @@ rtrs_clt_get_copy_req(struct rtrs_clt_path *alive_path,
 static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con,
 				   struct rtrs_clt_io_req *req,
 				   struct rtrs_rbuf *rbuf, bool fr_en,
-				   u32 size, u32 imm, struct ib_send_wr *wr,
+				   u32 count, u32 size, u32 imm,
+				   struct ib_send_wr *wr,
 				   struct ib_send_wr *tail)
 {
 	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
@@ -1024,12 +1025,12 @@ static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con,
 		num_sge = 2;
 		ptail = tail;
 	} else {
-		for_each_sg(req->sglist, sg, req->sg_cnt, i) {
+		for_each_sg(req->sglist, sg, count, i) {
 			sge[i].addr   = sg_dma_address(sg);
 			sge[i].length = sg_dma_len(sg);
 			sge[i].lkey   = clt_path->s.dev->ib_pd->local_dma_lkey;
 		}
-		num_sge = 1 + req->sg_cnt;
+		num_sge = 1 + count;
 	}
 	sge[i].addr   = req->iu->dma_addr;
 	sge[i].length = size;
@@ -1142,7 +1143,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 	 */
 	rtrs_clt_update_all_stats(req, WRITE);
 
-	ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en,
+	ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en, count,
 				      req->usr_len + sizeof(*msg),
 				      imm, wr, &inv_wr);
 	if (ret) {

drivers/infiniband/ulp/rtrs/rtrs-srv.c

@@ -595,7 +595,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path)
 		struct sg_table *sgt = &srv_mr->sgt;
 		struct scatterlist *s;
 		struct ib_mr *mr;
-		int nr, chunks;
+		int nr, nr_sgt, chunks;
 
 		chunks = chunks_per_mr * mri;
 		if (!always_invalidate)
@@ -610,19 +610,19 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path)
 			sg_set_page(s, srv->chunks[chunks + i],
 				    max_chunk_size, 0);
 
-		nr = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl,
+		nr_sgt = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl,
 				   sgt->nents, DMA_BIDIRECTIONAL);
-		if (nr < sgt->nents) {
-			err = nr < 0 ? nr : -EINVAL;
+		if (!nr_sgt) {
+			err = -EINVAL;
 			goto free_sg;
 		}
 		mr = ib_alloc_mr(srv_path->s.dev->ib_pd, IB_MR_TYPE_MEM_REG,
-				 sgt->nents);
+				 nr_sgt);
 		if (IS_ERR(mr)) {
 			err = PTR_ERR(mr);
 			goto unmap_sg;
 		}
-		nr = ib_map_mr_sg(mr, sgt->sgl, sgt->nents,
+		nr = ib_map_mr_sg(mr, sgt->sgl, nr_sgt,
 				  NULL, max_chunk_size);
 		if (nr < 0 || nr < sgt->nents) {
 			err = nr < 0 ? nr : -EINVAL;
@@ -641,7 +641,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path)
 			}
 		}
 		/* Eventually dma addr for each chunk can be cached */
-		for_each_sg(sgt->sgl, s, sgt->orig_nents, i)
+		for_each_sg(sgt->sgl, s, nr_sgt, i)
 			srv_path->dma_addr[chunks + i] = sg_dma_address(s);
 
 		ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey));

drivers/infiniband/ulp/srp/ib_srp.c

@@ -1961,7 +1961,8 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp)
 		if (scmnd) {
 			req = scsi_cmd_priv(scmnd);
 			scmnd = srp_claim_req(ch, req, NULL, scmnd);
-		} else {
+		}
+		if (!scmnd) {
 			shost_printk(KERN_ERR, target->scsi_host,
 				     "Null scmnd for RSP w/tag %#016llx received on ch %td / QP %#x\n",
 				     rsp->tag, ch - target->ch, ch->qp->qp_num);

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -494,6 +494,24 @@ static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
 	return err;
 }
 
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+						 &val);
+
+	if (!err)
+		return val.vbool;
+
+	mlx5_core_dbg(dev, "Failed to get param. err = %d\n", err);
+	return MLX5_CAP_GEN(dev, roce);
+}
+EXPORT_SYMBOL(mlx5_is_roce_on);
+
 static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	void *set_hca_cap;
@@ -597,7 +615,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 			 MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
 
 	if (MLX5_CAP_GEN(dev, roce_rw_supported))
-		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
+		MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
+			 mlx5_is_roce_on(dev));
 
 	max_uc_list = max_uc_list_get_devlink_param(dev);
 	if (max_uc_list > 0)
@@ -623,7 +642,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
  */
 static bool is_roce_fw_disabled(struct mlx5_core_dev *dev)
 {
-	return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) ||
+	return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_on(dev)) ||
 		(!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce));
 }
 

include/linux/mlx5/driver.h

@@ -1280,16 +1280,17 @@ enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
 
-static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev)
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev);
+
+static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 {
-	struct devlink *devlink = priv_to_devlink(dev);
-	union devlink_param_value val;
-	int err;
-
-	err = devlink_param_driverinit_value_get(devlink,
-						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
-						 &val);
-	return err ? MLX5_CAP_GEN(dev, roce) : val.vbool;
+	if (MLX5_CAP_GEN(dev, roce_rw_supported))
+		return MLX5_CAP_GEN(dev, roce);
+
+	/* If RoCE cap is read-only in FW, get RoCE state from devlink
+	 * in order to support RoCE enable/disable feature
+	 */
+	return mlx5_is_roce_on(dev);
 }
 
 #endif /* MLX5_DRIVER_H */

kernel/fork.c

@@ -1225,6 +1225,7 @@ void mmput_async(struct mm_struct *mm)
 		schedule_work(&mm->async_put_work);
 	}
 }
+EXPORT_SYMBOL_GPL(mmput_async);
 #endif
 
 /**