RDMA v6.18 first rc pull request

Following fixes:
 
 - Memory leak in bnxt GSI qp path
 
 - Failure in irdma registering large MRs
 
 - Failure to clean out the right CQ table entry in irdma
 
 - Invalid vf_id in some cases
 
 - Incorrect error unwind in EFA CQ create
 
 - hns doesn't use the optimal cq/qp relationships for it's HW banks
 
 - hns reports the wrong SGE size to userspace for its QPs
 
 - Corruption of the hns work queue entries in some cases
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRRRCHOFoQz/8F5bUaFwuHvBreFYQUCaQoEZAAKCRCFwuHvBreF
 YbdjAP9MfjyZvmOu5H7yqwdIgCNeduANVWbEzSXUEU6j5LRCywD+O5UnkPbHQ9ko
 k+jo07V6Ra/FuTVmr1Wf/Nfa9JmPqwc=
 =dnEg
 -----END PGP SIGNATURE-----

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

Pull rdma fixes from Jason Gunthorpe:

 - Memory leak in bnxt GSI qp path

 - Failure in irdma registering large MRs

 - Failure to clean out the right CQ table entry in irdma

 - Invalid vf_id in some cases

 - Incorrect error unwind in EFA CQ create

 - hns doesn't use the optimal cq/qp relationships for it's HW banks

 - hns reports the wrong SGE size to userspace for its QPs

 - Corruption of the hns work queue entries in some cases

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  MAINTAINERS: Update irdma maintainers
  RDMA/irdma: Fix vf_id size to u16 to avoid overflow
  RDMA/hns: Remove an extra blank line
  RDMA/hns: Fix wrong WQE data when QP wraps around
  RDMA/hns: Fix the modification of max_send_sge
  RDMA/hns: Fix recv CQ and QP cache affinity
  RDMA/uverbs: Fix umem release in UVERBS_METHOD_CQ_CREATE
  RDMA/irdma: Set irdma_cq cq_num field during CQ create
  RDMA/irdma: Fix SD index calculation
  RDMA/bnxt_re: Fix a potential memory leak in destroy_gsi_sqp

MAINTAINERS

@@ -12521,6 +12521,7 @@ F:	include/linux/avf/virtchnl.h
 F:	include/linux/net/intel/*/
 
 INTEL ETHERNET PROTOCOL DRIVER FOR RDMA
+M:	Krzysztof Czurylo <krzysztof.czurylo@intel.com>
 M:	Tatyana Nikolova <tatyana.e.nikolova@intel.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported

drivers/infiniband/core/uverbs_std_types_cq.c

@@ -206,6 +206,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	return ret;
 
 err_free:
+	ib_umem_release(umem);
 	rdma_restrack_put(&cq->res);
 	kfree(cq);
 err_event_file:

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -913,7 +913,7 @@ void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp,
 	spin_unlock_irqrestore(&qp->scq->cq_lock, flags);
 }
 
-static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
+static void bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 {
 	struct bnxt_re_qp *gsi_sqp;
 	struct bnxt_re_ah *gsi_sah;
@@ -933,10 +933,9 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 
 	ibdev_dbg(&rdev->ibdev, "Destroy the shadow QP\n");
 	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &gsi_sqp->qplib_qp);
-	if (rc) {
+	if (rc)
 		ibdev_err(&rdev->ibdev, "Destroy Shadow QP failed");
-		goto fail;
+
-	}
 	bnxt_qplib_free_qp_res(&rdev->qplib_res, &gsi_sqp->qplib_qp);
 
 	/* remove from active qp list */
@@ -951,10 +950,6 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 	rdev->gsi_ctx.gsi_sqp = NULL;
 	rdev->gsi_ctx.gsi_sah = NULL;
 	rdev->gsi_ctx.sqp_tbl = NULL;
-
-	return 0;
-fail:
-	return rc;
 }
 
 static void bnxt_re_del_unique_gid(struct bnxt_re_dev *rdev)

drivers/infiniband/hw/efa/efa_verbs.c

@@ -1216,13 +1216,13 @@ int efa_create_cq_umem(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		if (umem->length < cq->size) {
 			ibdev_dbg(&dev->ibdev, "External memory too small\n");
 			err = -EINVAL;
-			goto err_free_mem;
+			goto err_out;
 		}
 
 		if (!ib_umem_is_contiguous(umem)) {
 			ibdev_dbg(&dev->ibdev, "Non contiguous CQ unsupported\n");
 			err = -EINVAL;
-			goto err_free_mem;
+			goto err_out;
 		}
 
 		cq->cpu_addr = NULL;
@@ -1251,7 +1251,7 @@ int efa_create_cq_umem(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 
 	err = efa_com_create_cq(&dev->edev, &params, &result);
 	if (err)
-		goto err_free_mem;
+		goto err_free_mapped;
 
 	resp.db_off = result.db_off;
 	resp.cq_idx = result.cq_idx;
@@ -1299,12 +1299,10 @@ int efa_create_cq_umem(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	efa_cq_user_mmap_entries_remove(cq);
 err_destroy_cq:
 	efa_destroy_cq_idx(dev, cq->cq_idx);
-err_free_mem:
+err_free_mapped:
-	if (umem)
+	if (!umem)
-		ib_umem_release(umem);
+		efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size,
-	else
+				DMA_FROM_DEVICE);
-		efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size, DMA_FROM_DEVICE);
-
 err_out:
 	atomic64_inc(&dev->stats.create_cq_err);
 	return err;

drivers/infiniband/hw/hns/hns_roce_cq.c

@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/pci.h>
 #include <rdma/ib_umem.h>
 #include <rdma/uverbs_ioctl.h>
 #include "hns_roce_device.h"
@@ -37,6 +38,43 @@
 #include "hns_roce_hem.h"
 #include "hns_roce_common.h"
 
+void hns_roce_put_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(uctx->ibucontext.device);
+	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
+
+	if (hr_dev->pci_dev->revision < PCI_REVISION_ID_HIP09)
+		return;
+
+	mutex_lock(&cq_table->bank_mutex);
+	cq_table->ctx_num[uctx->cq_bank_id]--;
+	mutex_unlock(&cq_table->bank_mutex);
+}
+
+void hns_roce_get_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(uctx->ibucontext.device);
+	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
+	u32 least_load = cq_table->ctx_num[0];
+	u8 bankid = 0;
+	u8 i;
+
+	if (hr_dev->pci_dev->revision < PCI_REVISION_ID_HIP09)
+		return;
+
+	mutex_lock(&cq_table->bank_mutex);
+	for (i = 1; i < HNS_ROCE_CQ_BANK_NUM; i++) {
+		if (cq_table->ctx_num[i] < least_load) {
+			least_load = cq_table->ctx_num[i];
+			bankid = i;
+		}
+	}
+	cq_table->ctx_num[bankid]++;
+	mutex_unlock(&cq_table->bank_mutex);
+
+	uctx->cq_bank_id = bankid;
+}
+
 static u8 get_least_load_bankid_for_cq(struct hns_roce_bank *bank)
 {
 	u32 least_load = bank[0].inuse;
@@ -55,7 +93,21 @@ static u8 get_least_load_bankid_for_cq(struct hns_roce_bank *bank)
 	return bankid;
 }
 
-static int alloc_cqn(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
+static u8 select_cq_bankid(struct hns_roce_dev *hr_dev,
+			   struct hns_roce_bank *bank, struct ib_udata *udata)
+{
+	struct hns_roce_ucontext *uctx = udata ?
+		rdma_udata_to_drv_context(udata, struct hns_roce_ucontext,
+					  ibucontext) : NULL;
+
+	if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
+		return uctx ? uctx->cq_bank_id : 0;
+
+	return get_least_load_bankid_for_cq(bank);
+}
+
+static int alloc_cqn(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
+		     struct ib_udata *udata)
 {
 	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
 	struct hns_roce_bank *bank;
@@ -63,7 +115,7 @@ static int alloc_cqn(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
 	int id;
 
 	mutex_lock(&cq_table->bank_mutex);
-	bankid = get_least_load_bankid_for_cq(cq_table->bank);
+	bankid = select_cq_bankid(hr_dev, cq_table->bank, udata);
 	bank = &cq_table->bank[bankid];
 
 	id = ida_alloc_range(&bank->ida, bank->min, bank->max, GFP_KERNEL);
@@ -396,7 +448,7 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 		goto err_cq_buf;
 	}
 
-	ret = alloc_cqn(hr_dev, hr_cq);
+	ret = alloc_cqn(hr_dev, hr_cq, udata);
 	if (ret) {
 		ibdev_err(ibdev, "failed to alloc CQN, ret = %d.\n", ret);
 		goto err_cq_db;

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -217,6 +217,7 @@ struct hns_roce_ucontext {
 	struct mutex		page_mutex;
 	struct hns_user_mmap_entry *db_mmap_entry;
 	u32			config;
+	u8 cq_bank_id;
 };
 
 struct hns_roce_pd {
@@ -495,6 +496,7 @@ struct hns_roce_cq_table {
 	struct hns_roce_hem_table	table;
 	struct hns_roce_bank bank[HNS_ROCE_CQ_BANK_NUM];
 	struct mutex			bank_mutex;
+	u32 ctx_num[HNS_ROCE_CQ_BANK_NUM];
 };
 
 struct hns_roce_srq_table {
@@ -1305,5 +1307,7 @@ hns_roce_user_mmap_entry_insert(struct ib_ucontext *ucontext, u64 address,
 				size_t length,
 				enum hns_roce_mmap_type mmap_type);
 bool check_sl_valid(struct hns_roce_dev *hr_dev, u8 sl);
+void hns_roce_put_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx);
+void hns_roce_get_cq_bankid_for_uctx(struct hns_roce_ucontext *uctx);
 
 #endif /* _HNS_ROCE_DEVICE_H */

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

@@ -165,6 +165,8 @@ static void set_frmr_seg(struct hns_roce_v2_rc_send_wqe *rc_sq_wqe,
 	hr_reg_write(fseg, FRMR_PBL_BUF_PG_SZ,
 		     to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.buf_pg_shift));
 	hr_reg_clear(fseg, FRMR_BLK_MODE);
+	hr_reg_clear(fseg, FRMR_BLOCK_SIZE);
+	hr_reg_clear(fseg, FRMR_ZBVA);
 }
 
 static void set_atomic_seg(const struct ib_send_wr *wr,
@@ -339,9 +341,6 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 	int j = 0;
 	int i;
 
-	hr_reg_write(rc_sq_wqe, RC_SEND_WQE_MSG_START_SGE_IDX,
-		     (*sge_ind) & (qp->sge.sge_cnt - 1));
-
 	hr_reg_write(rc_sq_wqe, RC_SEND_WQE_INLINE,
 		     !!(wr->send_flags & IB_SEND_INLINE));
 	if (wr->send_flags & IB_SEND_INLINE)
@@ -586,6 +585,9 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp,
 	hr_reg_write(rc_sq_wqe, RC_SEND_WQE_CQE,
 		     (wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0);
 
+	hr_reg_write(rc_sq_wqe, RC_SEND_WQE_MSG_START_SGE_IDX,
+		     curr_idx & (qp->sge.sge_cnt - 1));
+
 	if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP ||
 	    wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD) {
 		if (msg_len != ATOMIC_WR_LEN)
@@ -734,6 +736,9 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 		owner_bit =
 		       ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1);
 
+		/* RC and UD share the same DirectWQE field layout */
+		((struct hns_roce_v2_rc_send_wqe *)wqe)->byte_4 = 0;
+
 		/* Corresponding to the QP type, wqe process separately */
 		if (ibqp->qp_type == IB_QPT_RC)
 			ret = set_rc_wqe(qp, wr, wqe, &sge_idx, owner_bit);
@@ -7048,7 +7053,6 @@ static int __hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)
 		goto error_failed_roce_init;
 	}
 
-
 	handle->priv = hr_dev;
 
 	return 0;

drivers/infiniband/hw/hns/hns_roce_main.c

@@ -425,6 +425,8 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 	if (ret)
 		goto error_fail_copy_to_udata;
 
+	hns_roce_get_cq_bankid_for_uctx(context);
+
 	return 0;
 
 error_fail_copy_to_udata:
@@ -447,6 +449,8 @@ static void hns_roce_dealloc_ucontext(struct ib_ucontext *ibcontext)
 	struct hns_roce_ucontext *context = to_hr_ucontext(ibcontext);
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibcontext->device);
 
+	hns_roce_put_cq_bankid_for_uctx(context);
+
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_CQ_RECORD_DB ||
 	    hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_QP_RECORD_DB)
 		mutex_destroy(&context->page_mutex);

drivers/infiniband/hw/hns/hns_roce_qp.c

@@ -662,7 +662,6 @@ static int set_user_sq_size(struct hns_roce_dev *hr_dev,
 
 	hr_qp->sq.wqe_shift = ucmd->log_sq_stride;
 	hr_qp->sq.wqe_cnt = cnt;
-	cap->max_send_sge = hr_qp->sq.max_gs;
 
 	return 0;
 }
@@ -744,7 +743,6 @@ static int set_kernel_sq_size(struct hns_roce_dev *hr_dev,
 
 	/* sync the parameters of kernel QP to user's configuration */
 	cap->max_send_wr = cnt;
-	cap->max_send_sge = hr_qp->sq.max_gs;
 
 	return 0;
 }

drivers/infiniband/hw/irdma/pble.c

@@ -71,7 +71,7 @@ int irdma_hmc_init_pble(struct irdma_sc_dev *dev,
 static void get_sd_pd_idx(struct irdma_hmc_pble_rsrc *pble_rsrc,
 			  struct sd_pd_idx *idx)
 {
-	idx->sd_idx = (u32)pble_rsrc->next_fpm_addr / IRDMA_HMC_DIRECT_BP_SIZE;
+	idx->sd_idx = pble_rsrc->next_fpm_addr / IRDMA_HMC_DIRECT_BP_SIZE;
 	idx->pd_idx = (u32)(pble_rsrc->next_fpm_addr / IRDMA_HMC_PAGED_BP_SIZE);
 	idx->rel_pd_idx = (idx->pd_idx % IRDMA_HMC_PD_CNT_IN_SD);
 }

drivers/infiniband/hw/irdma/type.h

@@ -706,7 +706,7 @@ struct irdma_sc_dev {
 	u32 vchnl_ver;
 	u16 num_vfs;
 	u16 hmc_fn_id;
-	u8 vf_id;
+	u16 vf_id;
 	bool privileged:1;
 	bool vchnl_up:1;
 	bool ceq_valid:1;

drivers/infiniband/hw/irdma/verbs.c

@@ -2503,6 +2503,7 @@ static int irdma_create_cq(struct ib_cq *ibcq,
 	spin_lock_init(&iwcq->lock);
 	INIT_LIST_HEAD(&iwcq->resize_list);
 	INIT_LIST_HEAD(&iwcq->cmpl_generated);
+	iwcq->cq_num = cq_num;
 	info.dev = dev;
 	ukinfo->cq_size = max(entries, 4);
 	ukinfo->cq_id = cq_num;

drivers/infiniband/hw/irdma/verbs.h

@@ -140,7 +140,7 @@ struct irdma_srq {
 struct irdma_cq {
 	struct ib_cq ibcq;
 	struct irdma_sc_cq sc_cq;
-	u16 cq_num;
+	u32 cq_num;
 	bool user_mode;
 	atomic_t armed;
 	enum irdma_cmpl_notify last_notify;