IB/mlx5: Support 4k UAR for libmlx5

Add fields to structs to convey to kernel an indication whether the
library supports multi UARs per page and return to the library the size
of a UAR based on the queried value.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

9 files changed, 42 insertions, 100 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 664067239de5..a191b9327b0c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -992,6 +992,12 @@ out:
 	return err;
 }
 
+static void print_lib_caps(struct mlx5_ib_dev *dev, u64 caps)
+{
+	mlx5_ib_dbg(dev, "MLX5_LIB_CAP_4K_UAR = %s\n",
+		    caps & MLX5_LIB_CAP_4K_UAR ? "y" : "n");
+}
+
 static int calc_total_bfregs(struct mlx5_ib_dev *dev, bool lib_uar_4k,
 			     struct mlx5_ib_alloc_ucontext_req_v2 *req,
 			     u32 *num_sys_pages)
@@ -1122,6 +1128,10 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	resp.cqe_version = min_t(__u8,
 				 (__u8)MLX5_CAP_GEN(dev->mdev, cqe_version),
 				 req.max_cqe_version);
+	resp.log_uar_size = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+				MLX5_ADAPTER_PAGE_SHIFT : PAGE_SHIFT;
+	resp.num_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+					MLX5_CAP_GEN(dev->mdev, num_of_uars_per_page) : 1;
 	resp.response_length = min(offsetof(typeof(resp), response_length) +
 				   sizeof(resp.response_length), udata->outlen);
 
@@ -1129,7 +1139,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (!context)
 		return ERR_PTR(-ENOMEM);
 
-	lib_uar_4k = false;
+	lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR;
 	bfregi = &context->bfregi;
 
 	/* updates req->total_num_bfregs */
@@ -1209,6 +1219,12 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 					sizeof(resp.reserved2);
 	}
 
+	if (field_avail(typeof(resp), log_uar_size, udata->outlen))
+		resp.response_length += sizeof(resp.log_uar_size);
+
+	if (field_avail(typeof(resp), num_uars_per_page, udata->outlen))
+		resp.response_length += sizeof(resp.num_uars_per_page);
+
 	err = ib_copy_to_udata(udata, &resp, resp.response_length);
 	if (err)
 		goto out_td;
@@ -1216,7 +1232,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	bfregi->ver = ver;
 	bfregi->num_low_latency_bfregs = req.num_low_latency_bfregs;
 	context->cqe_version = resp.cqe_version;
-	context->lib_caps = false;
+	context->lib_caps = req.lib_caps;
+	print_lib_caps(dev, context->lib_caps);
 
 	return &context->ibucontext;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 32d4af9b594d..336d4738b807 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -179,6 +179,8 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 		mlx5_core_dbg(dev, "failed adding CP 0x%x to debug file system\n",
 			      cq->cqn);
 
+	cq->uar = dev->priv.uar;
+
 	return 0;
 
 err_cmd:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3037631570b1..a473cea10c16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -465,7 +465,6 @@ struct mlx5e_sq {
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	u32                        dma_fifo_mask;
-	void __iomem              *uar_map;
 	struct netdev_queue       *txq;
 	u32                        sqn;
 	u16                        bf_buf_size;
@@ -479,7 +478,7 @@ struct mlx5e_sq {
 
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
-	struct mlx5_uar            uar;
+	struct mlx5_sq_bfreg	   bfreg;
 	struct mlx5e_channel      *channel;
 	int                        tc;
 	u32                        rate_limit;
@@ -806,7 +805,7 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
 				      struct mlx5_wqe_ctrl_seg *ctrl, int bf_sz)
 {
-	u16 ofst = MLX5_BF_OFFSET + sq->bf_offset;
+	u16 ofst = sq->bf_offset;
 
 	/* ensure wqe is visible to device before updating doorbell record */
 	dma_wmb();
@@ -818,9 +817,9 @@ static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
 	 */
 	wmb();
 	if (bf_sz)
-		__iowrite64_copy(sq->uar_map + ofst, ctrl, bf_sz);
+		__iowrite64_copy(sq->bfreg.map + ofst, ctrl, bf_sz);
 	else
-		mlx5_write64((__be32 *)ctrl, sq->uar_map + ofst, NULL);
+		mlx5_write64((__be32 *)ctrl, sq->bfreg.map + ofst, NULL);
 	/* flush the write-combining mapped buffer */
 	wmb();
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index f175518ff07a..bd898d8deda0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -89,16 +89,10 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	struct mlx5e_resources *res = &mdev->mlx5e_res;
 	int err;
 
-	err = mlx5_alloc_map_uar(mdev, &res->cq_uar, false);
-	if (err) {
-		mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err);
-		return err;
-	}
-
 	err = mlx5_core_alloc_pd(mdev, &res->pdn);
 	if (err) {
 		mlx5_core_err(mdev, "alloc pd failed, %d\n", err);
-		goto err_unmap_free_uar;
+		return err;
 	}
 
 	err = mlx5_core_alloc_transport_domain(mdev, &res->td.tdn);
@@ -121,9 +115,6 @@ err_dealloc_transport_domain:
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 err_dealloc_pd:
 	mlx5_core_dealloc_pd(mdev, res->pdn);
-err_unmap_free_uar:
-	mlx5_unmap_free_uar(mdev, &res->cq_uar);
-
 	return err;
 }
 
@@ -134,7 +125,6 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	mlx5_core_destroy_mkey(mdev, &res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 	mlx5_core_dealloc_pd(mdev, res->pdn);
-	mlx5_unmap_free_uar(mdev, &res->cq_uar);
 }
 
 int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5ff86f0ecb7b..c32754b1598e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -991,7 +991,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->tc        = tc;
 
-	err = mlx5_alloc_map_uar(mdev, &sq->uar, !!MLX5_CAP_GEN(mdev, bf));
+	err = mlx5_alloc_bfreg(mdev, &sq->bfreg, MLX5_CAP_GEN(mdev, bf), false);
 	if (err)
 		return err;
 
@@ -1003,12 +1003,9 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
 		goto err_unmap_free_uar;
 
 	sq->wq.db       = &sq->wq.db[MLX5_SND_DBR];
-	if (sq->uar.bf_map) {
+	if (sq->bfreg.wc)
 		set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state);
-		sq->uar_map = sq->uar.bf_map;
-	} else {
-		sq->uar_map = sq->uar.map;
-	}
+
 	sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
 	sq->max_inline  = param->max_inline;
 	sq->min_inline_mode =
@@ -1036,7 +1033,7 @@ err_sq_wq_destroy:
 	mlx5_wq_destroy(&sq->wq_ctrl);
 
 err_unmap_free_uar:
-	mlx5_unmap_free_uar(mdev, &sq->uar);
+	mlx5_free_bfreg(mdev, &sq->bfreg);
 
 	return err;
 }
@@ -1048,7 +1045,7 @@ static void mlx5e_destroy_sq(struct mlx5e_sq *sq)
 
 	mlx5e_free_sq_db(sq);
 	mlx5_wq_destroy(&sq->wq_ctrl);
-	mlx5_unmap_free_uar(priv->mdev, &sq->uar);
+	mlx5_free_bfreg(priv->mdev, &sq->bfreg);
 }
 
 static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
@@ -1082,7 +1079,7 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
 	MLX5_SET(sqc,  sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1);
 
 	MLX5_SET(wq,   wq, wq_type,       MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq,   wq, uar_page,      sq->uar.index);
+	MLX5_SET(wq,   wq, uar_page,      sq->bfreg.index);
 	MLX5_SET(wq,   wq, log_wq_pg_sz,  sq->wq_ctrl.buf.page_shift -
 					  MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq, dbr_addr,      sq->wq_ctrl.db.dma);
@@ -1240,7 +1237,6 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 	mcq->comp       = mlx5e_completion_event;
 	mcq->event      = mlx5e_cq_error_event;
 	mcq->irqn       = irqn;
-	mcq->uar        = &mdev->mlx5e_res.cq_uar;
 
 	for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
 		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
@@ -1289,7 +1285,7 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 
 	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
 	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
-	MLX5_SET(cqc,   cqc, uar_page,      mcq->uar->index);
+	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.frag_buf.page_shift -
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
@@ -1701,7 +1697,7 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
 {
 	void *cqc = param->cqc;
 
-	MLX5_SET(cqc, cqc, uar_page, priv->mdev->mlx5e_res.cq_uar.index);
+	MLX5_SET(cqc, cqc, uar_page, priv->mdev->priv.uar->index);
 }
 
 static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
@@ -2320,7 +2316,6 @@ static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
 	mcq->comp       = mlx5e_completion_event;
 	mcq->event      = mlx5e_cq_error_event;
 	mcq->irqn       = irqn;
-	mcq->uar        = &mdev->mlx5e_res.cq_uar;
 
 	cq->priv = priv;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 07b273cccc26..2e6b0f290ddc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -37,11 +37,6 @@
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
-enum {
-	NUM_DRIVER_UARS		= 4,
-	NUM_LOW_LAT_BFREGS	= 4,
-};
-
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn)
 {
 	u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {0};
@@ -67,57 +62,6 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn)
 }
 EXPORT_SYMBOL(mlx5_cmd_free_uar);
 
-int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar,
-		       bool map_wc)
-{
-	phys_addr_t pfn;
-	phys_addr_t uar_bar_start;
-	int err;
-
-	err = mlx5_cmd_alloc_uar(mdev, &uar->index);
-	if (err) {
-		mlx5_core_warn(mdev, "mlx5_cmd_alloc_uar() failed, %d\n", err);
-		return err;
-	}
-
-	uar_bar_start = pci_resource_start(mdev->pdev, 0);
-	pfn           = (uar_bar_start >> PAGE_SHIFT) + uar->index;
-
-	if (map_wc) {
-		uar->bf_map = ioremap_wc(pfn << PAGE_SHIFT, PAGE_SIZE);
-		if (!uar->bf_map) {
-			mlx5_core_warn(mdev, "ioremap_wc() failed\n");
-			uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
-			if (!uar->map)
-				goto err_free_uar;
-		}
-	} else {
-		uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
-		if (!uar->map)
-			goto err_free_uar;
-	}
-
-	return 0;
-
-err_free_uar:
-	mlx5_core_warn(mdev, "ioremap() failed\n");
-	err = -ENOMEM;
-	mlx5_cmd_free_uar(mdev, uar->index);
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_alloc_map_uar);
-
-void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar)
-{
-	if (uar->map)
-		iounmap(uar->map);
-	else
-		iounmap(uar->bf_map);
-	mlx5_cmd_free_uar(mdev, uar->index);
-}
-EXPORT_SYMBOL(mlx5_unmap_free_uar);
-
 static int uars_per_sys_page(struct mlx5_core_dev *mdev)
 {
 	if (MLX5_CAP_GEN(mdev, uar_4k))
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 996863381bc8..95898847c7d4 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -42,13 +42,13 @@ struct mlx5_core_cq {
 	int			cqe_sz;
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
+	struct mlx5_uars_page  *uar;
 	atomic_t		refcount;
 	struct completion	free;
 	unsigned		vector;
 	unsigned int		irqn;
 	void (*comp)		(struct mlx5_core_cq *);
 	void (*event)		(struct mlx5_core_cq *, enum mlx5_event);
-	struct mlx5_uar	       *uar;
 	u32			cons_index;
 	unsigned		arm_sn;
 	struct mlx5_rsc_debug	*dbg;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7e7394fef835..10e632588cd5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -467,12 +467,6 @@ struct mlx5_sq_bfreg {
 	unsigned int		offset;
 };
 
-struct mlx5_uar {
-	u32			index;
-	void __iomem	       *map;
-	void __iomem	       *bf_map;
-};
-
 struct mlx5_core_health {
 	struct health_buffer __iomem   *health;
 	__be32 __iomem		       *health_counter;
@@ -725,7 +719,6 @@ struct mlx5_td {
 };
 
 struct mlx5e_resources {
-	struct mlx5_uar            cq_uar;
 	u32                        pdn;
 	struct mlx5_td             td;
 	struct mlx5_core_mkey      mkey;
@@ -915,11 +908,6 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
-int mlx5_alloc_bfregs(struct mlx5_core_dev *dev, struct mlx5_bfreg_info *bfregi);
-int mlx5_free_bfregs(struct mlx5_core_dev *dev, struct mlx5_bfreg_info *bfregi);
-int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar,
-		       bool map_wc);
-void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 86a8f30060f3..85dc966ea70b 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -65,6 +65,10 @@ struct mlx5_ib_alloc_ucontext_req {
 	__u32	num_low_latency_bfregs;
 };
 
+enum mlx5_lib_caps {
+	MLX5_LIB_CAP_4K_UAR	= (u64)1 << 0,
+};
+
 struct mlx5_ib_alloc_ucontext_req_v2 {
 	__u32	total_num_bfregs;
 	__u32	num_low_latency_bfregs;
@@ -74,6 +78,7 @@ struct mlx5_ib_alloc_ucontext_req_v2 {
 	__u8	reserved0;
 	__u16	reserved1;
 	__u32	reserved2;
+	__u64	lib_caps;
 };
 
 enum mlx5_ib_alloc_ucontext_resp_mask {
@@ -103,6 +108,8 @@ struct mlx5_ib_alloc_ucontext_resp {
 	__u8	cmds_supp_uhw;
 	__u16	reserved2;
 	__u64	hca_core_clock_offset;
+	__u32	log_uar_size;
+	__u32	num_uars_per_page;
 };
 
 struct mlx5_ib_alloc_pd_resp {