1 files changed, 151 insertions, 83 deletions

diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 1e9c3c5bee68..6aa82fe9dd3d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -30,7 +30,7 @@
  * SOFTWARE.
  */
 
-#include <linux/platform_device.h>
+#include <linux/pci.h>
 #include <rdma/ib_umem.h>
 #include <rdma/uverbs_ioctl.h>
 #include "hns_roce_device.h"
@@ -38,6 +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;
@@ -56,7 +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;
@@ -64,7 +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);
@@ -101,20 +152,45 @@ static void free_cqn(struct hns_roce_dev *hr_dev, unsigned long cqn)
 	mutex_unlock(&cq_table->bank_mutex);
 }
 
+static int hns_roce_create_cqc(struct hns_roce_dev *hr_dev,
+			       struct hns_roce_cq *hr_cq,
+			       u64 *mtts, dma_addr_t dma_handle)
+{
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_cmd_mailbox *mailbox;
+	int ret;
+
+	mailbox = hns_roce_alloc_cmd_mailbox(hr_dev);
+	if (IS_ERR(mailbox)) {
+		ibdev_err(ibdev, "failed to alloc mailbox for CQC.\n");
+		return PTR_ERR(mailbox);
+	}
+
+	hr_dev->hw->write_cqc(hr_dev, hr_cq, mailbox->buf, mtts, dma_handle);
+
+	ret = hns_roce_create_hw_ctx(hr_dev, mailbox, HNS_ROCE_CMD_CREATE_CQC,
+				     hr_cq->cqn);
+	if (ret)
+		ibdev_err(ibdev,
+			  "failed to send create cmd for CQ(0x%lx), ret = %d.\n",
+			  hr_cq->cqn, ret);
+
+	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
+
+	return ret;
+}
+
 static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
 {
 	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
 	struct ib_device *ibdev = &hr_dev->ib_dev;
-	struct hns_roce_cmd_mailbox *mailbox;
-	u64 mtts[MTT_MIN_COUNT] = { 0 };
-	dma_addr_t dma_handle;
+	u64 mtts[MTT_MIN_COUNT] = {};
 	int ret;
 
-	ret = hns_roce_mtr_find(hr_dev, &hr_cq->mtr, 0, mtts, ARRAY_SIZE(mtts),
-				&dma_handle);
-	if (!ret) {
+	ret = hns_roce_mtr_find(hr_dev, &hr_cq->mtr, 0, mtts, ARRAY_SIZE(mtts));
+	if (ret) {
 		ibdev_err(ibdev, "failed to find CQ mtr, ret = %d.\n", ret);
-		return -EINVAL;
+		return ret;
 	}
 
 	/* Get CQC memory HEM(Hardware Entry Memory) table */
@@ -122,50 +198,27 @@ static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
 	if (ret) {
 		ibdev_err(ibdev, "failed to get CQ(0x%lx) context, ret = %d.\n",
 			  hr_cq->cqn, ret);
-		goto err_out;
+		return ret;
 	}
 
-	ret = xa_err(xa_store(&cq_table->array, hr_cq->cqn, hr_cq, GFP_KERNEL));
+	ret = xa_err(xa_store_irq(&cq_table->array, hr_cq->cqn, hr_cq, GFP_KERNEL));
 	if (ret) {
 		ibdev_err(ibdev, "failed to xa_store CQ, ret = %d.\n", ret);
 		goto err_put;
 	}
 
-	/* Allocate mailbox memory */
-	mailbox = hns_roce_alloc_cmd_mailbox(hr_dev);
-	if (IS_ERR(mailbox)) {
-		ret = PTR_ERR(mailbox);
-		goto err_xa;
-	}
-
-	hr_dev->hw->write_cqc(hr_dev, hr_cq, mailbox->buf, mtts, dma_handle);
-
-	/* Send mailbox to hw */
-	ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, hr_cq->cqn, 0,
-			HNS_ROCE_CMD_CREATE_CQC, HNS_ROCE_CMD_TIMEOUT_MSECS);
-	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
-	if (ret) {
-		ibdev_err(ibdev,
-			  "failed to send create cmd for CQ(0x%lx), ret = %d.\n",
-			  hr_cq->cqn, ret);
+	ret = hns_roce_create_cqc(hr_dev, hr_cq, mtts,
+				  hns_roce_get_mtr_ba(&hr_cq->mtr));
+	if (ret)
 		goto err_xa;
-	}
-
-	hr_cq->cons_index = 0;
-	hr_cq->arm_sn = 1;
-
-	refcount_set(&hr_cq->refcount, 1);
-	init_completion(&hr_cq->free);
 
 	return 0;
 
 err_xa:
-	xa_erase(&cq_table->array, hr_cq->cqn);
-
+	xa_erase_irq(&cq_table->array, hr_cq->cqn);
 err_put:
 	hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn);
 
-err_out:
 	return ret;
 }
 
@@ -175,14 +228,13 @@ static void free_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
 	struct device *dev = hr_dev->dev;
 	int ret;
 
-	ret = hns_roce_cmd_mbox(hr_dev, 0, 0, hr_cq->cqn, 1,
-				HNS_ROCE_CMD_DESTROY_CQC,
-				HNS_ROCE_CMD_TIMEOUT_MSECS);
+	ret = hns_roce_destroy_hw_ctx(hr_dev, HNS_ROCE_CMD_DESTROY_CQC,
+				      hr_cq->cqn);
 	if (ret)
-		dev_err(dev, "DESTROY_CQ failed (%d) for CQN %06lx\n", ret,
-			hr_cq->cqn);
+		dev_err_ratelimited(dev, "DESTROY_CQ failed (%d) for CQN %06lx\n",
+				    ret, hr_cq->cqn);
 
-	xa_erase(&cq_table->array, hr_cq->cqn);
+	xa_erase_irq(&cq_table->array, hr_cq->cqn);
 
 	/* Waiting interrupt process procedure carried out */
 	synchronize_irq(hr_dev->eq_table.eq[hr_cq->vector].irq);
@@ -326,52 +378,68 @@ static void set_cq_param(struct hns_roce_cq *hr_cq, u32 cq_entries, int vector,
 	INIT_LIST_HEAD(&hr_cq->rq_list);
 }
 
-static void set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
-			 struct hns_roce_ib_create_cq *ucmd)
+static int set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
+			struct hns_roce_ib_create_cq *ucmd)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device);
 
-	if (udata) {
-		if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size))
-			hr_cq->cqe_size = ucmd->cqe_size;
-		else
-			hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
-	} else {
+	if (!udata) {
 		hr_cq->cqe_size = hr_dev->caps.cqe_sz;
+		return 0;
 	}
+
+	if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size)) {
+		if (ucmd->cqe_size != HNS_ROCE_V2_CQE_SIZE &&
+		    ucmd->cqe_size != HNS_ROCE_V3_CQE_SIZE) {
+			ibdev_err(&hr_dev->ib_dev,
+				  "invalid cqe size %u.\n", ucmd->cqe_size);
+			return -EINVAL;
+		}
+
+		hr_cq->cqe_size = ucmd->cqe_size;
+	} else {
+		hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
+	}
+
+	return 0;
 }
 
 int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
-		       struct ib_udata *udata)
+		       struct uverbs_attr_bundle *attrs)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
+	struct ib_udata *udata = &attrs->driver_udata;
 	struct hns_roce_ib_create_cq_resp resp = {};
 	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	struct hns_roce_ib_create_cq ucmd = {};
 	int ret;
 
-	if (attr->flags)
-		return -EOPNOTSUPP;
+	if (attr->flags) {
+		ret = -EOPNOTSUPP;
+		goto err_out;
+	}
 
 	ret = verify_cq_create_attr(hr_dev, attr);
 	if (ret)
-		return ret;
+		goto err_out;
 
 	if (udata) {
 		ret = get_cq_ucmd(hr_cq, udata, &ucmd);
 		if (ret)
-			return ret;
+			goto err_out;
 	}
 
 	set_cq_param(hr_cq, attr->cqe, attr->comp_vector, &ucmd);
 
-	set_cqe_size(hr_cq, udata, &ucmd);
+	ret = set_cqe_size(hr_cq, udata, &ucmd);
+	if (ret)
+		goto err_out;
 
 	ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr);
 	if (ret) {
 		ibdev_err(ibdev, "failed to alloc CQ buf, ret = %d.\n", ret);
-		return ret;
+		goto err_out;
 	}
 
 	ret = alloc_cq_db(hr_dev, hr_cq, udata, ucmd.db_addr, &resp);
@@ -380,7 +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;
@@ -393,15 +461,6 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 		goto err_cqn;
 	}
 
-	/*
-	 * For the QP created by kernel space, tptr value should be initialized
-	 * to zero; For the QP created by user space, it will cause synchronous
-	 * problems if tptr is set to zero here, so we initialize it in user
-	 * space.
-	 */
-	if (!udata && hr_cq->tptr_addr)
-		*hr_cq->tptr_addr = 0;
-
 	if (udata) {
 		resp.cqn = hr_cq->cqn;
 		ret = ib_copy_to_udata(udata, &resp,
@@ -410,6 +469,11 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 			goto err_cqc;
 	}
 
+	hr_cq->cons_index = 0;
+	hr_cq->arm_sn = 1;
+	refcount_set(&hr_cq->refcount, 1);
+	init_completion(&hr_cq->free);
+
 	return 0;
 
 err_cqc:
@@ -420,6 +484,9 @@ err_cq_db:
 	free_cq_db(hr_dev, hr_cq, udata);
 err_cq_buf:
 	free_cq_buf(hr_dev, hr_cq);
+err_out:
+	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CQ_CREATE_ERR_CNT]);
+
 	return ret;
 }
 
@@ -428,9 +495,6 @@ int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
 	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
 
-	if (hr_dev->hw->destroy_cq)
-		hr_dev->hw->destroy_cq(ib_cq, udata);
-
 	free_cqc(hr_dev, hr_cq);
 	free_cqn(hr_dev, hr_cq->cqn);
 	free_cq_db(hr_dev, hr_cq, udata);
@@ -447,7 +511,7 @@ void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn)
 	hr_cq = xa_load(&hr_dev->cq_table.array,
 			cqn & (hr_dev->caps.num_cqs - 1));
 	if (!hr_cq) {
-		dev_warn(hr_dev->dev, "Completion event for bogus CQ 0x%06x\n",
+		dev_warn(hr_dev->dev, "completion event for bogus CQ 0x%06x\n",
 			 cqn);
 		return;
 	}
@@ -465,22 +529,24 @@ void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type)
 	struct ib_event event;
 	struct ib_cq *ibcq;
 
-	hr_cq = xa_load(&hr_dev->cq_table.array,
-			cqn & (hr_dev->caps.num_cqs - 1));
-	if (!hr_cq) {
-		dev_warn(dev, "Async event for bogus CQ 0x%06x\n", cqn);
-		return;
-	}
-
 	if (event_type != HNS_ROCE_EVENT_TYPE_CQ_ID_INVALID &&
 	    event_type != HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR &&
 	    event_type != HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW) {
-		dev_err(dev, "Unexpected event type 0x%x on CQ 0x%06x\n",
+		dev_err(dev, "unexpected event type 0x%x on CQ 0x%06x\n",
 			event_type, cqn);
 		return;
 	}
 
-	refcount_inc(&hr_cq->refcount);
+	xa_lock(&hr_dev->cq_table.array);
+	hr_cq = xa_load(&hr_dev->cq_table.array,
+			cqn & (hr_dev->caps.num_cqs - 1));
+	if (hr_cq)
+		refcount_inc(&hr_cq->refcount);
+	xa_unlock(&hr_dev->cq_table.array);
+	if (!hr_cq) {
+		dev_warn(dev, "async event for bogus CQ 0x%06x\n", cqn);
+		return;
+	}
 
 	ibcq = &hr_cq->ib_cq;
 	if (ibcq->event_handler) {
@@ -523,4 +589,6 @@ void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev)
 
 	for (i = 0; i < HNS_ROCE_CQ_BANK_NUM; i++)
 		ida_destroy(&hr_dev->cq_table.bank[i].ida);
+	xa_destroy(&hr_dev->cq_table.array);
+	mutex_destroy(&hr_dev->cq_table.bank_mutex);
 }