mlx4: Implement memory windows allocation and deallocation

Implement MW allocation and deallocation in mlx4_core and mlx4_ib.
Pass down the enable bind flag when registering memory regions.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

4 files changed, 178 insertions, 1 deletions

diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index cce5dde94bc1..9ba0aaf3a58e 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -116,6 +116,11 @@ struct mlx4_ib_mr {
         struct ib_umem         *umem;
 };
 
+struct mlx4_ib_mw {
+        struct ib_mw            ibmw;
+        struct mlx4_mw          mmw;
+};
+
 struct mlx4_ib_fast_reg_page_list {
         struct ib_fast_reg_page_list    ibfrpl;
         __be64                         *mapped_page_list;
@@ -533,6 +538,11 @@ static inline struct mlx4_ib_mr *to_mmr(struct ib_mr *ibmr)
         return container_of(ibmr, struct mlx4_ib_mr, ibmr);
 }
 
+static inline struct mlx4_ib_mw *to_mmw(struct ib_mw *ibmw)
+{
+        return container_of(ibmw, struct mlx4_ib_mw, ibmw);
+}
+
 static inline struct mlx4_ib_fast_reg_page_list *to_mfrpl(struct ib_fast_reg_page_list *ibfrpl)
 {
         return container_of(ibfrpl, struct mlx4_ib_fast_reg_page_list, ibfrpl);
@@ -581,6 +591,8 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
                                   u64 virt_addr, int access_flags,
                                   struct ib_udata *udata);
 int mlx4_ib_dereg_mr(struct ib_mr *mr);
+struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
+int mlx4_ib_dealloc_mw(struct ib_mw *mw);
 struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
                                         int max_page_list_len);
 struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 254e1cf26439..5adf4c47ee18 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -41,9 +41,19 @@ static u32 convert_access(int acc)
                (acc & IB_ACCESS_REMOTE_WRITE  ? MLX4_PERM_REMOTE_WRITE : 0) |
                (acc & IB_ACCESS_REMOTE_READ   ? MLX4_PERM_REMOTE_READ  : 0) |
                (acc & IB_ACCESS_LOCAL_WRITE   ? MLX4_PERM_LOCAL_WRITE  : 0) |
+               (acc & IB_ACCESS_MW_BIND       ? MLX4_PERM_BIND_MW      : 0) |
                MLX4_PERM_LOCAL_READ;
 }
 
+static enum mlx4_mw_type to_mlx4_type(enum ib_mw_type type)
+{
+        switch (type) {
+        case IB_MW_TYPE_1:      return MLX4_MW_TYPE_1;
+        case IB_MW_TYPE_2:      return MLX4_MW_TYPE_2;
+        default:                return -1;
+        }
+}
+
 struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
 {
         struct mlx4_ib_mr *mr;
@@ -189,6 +199,48 @@ int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
         return 0;
 }
 
+struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
+{
+        struct mlx4_ib_dev *dev = to_mdev(pd->device);
+        struct mlx4_ib_mw *mw;
+        int err;
+
+        mw = kmalloc(sizeof(*mw), GFP_KERNEL);
+        if (!mw)
+                return ERR_PTR(-ENOMEM);
+
+        err = mlx4_mw_alloc(dev->dev, to_mpd(pd)->pdn,
+                            to_mlx4_type(type), &mw->mmw);
+        if (err)
+                goto err_free;
+
+        err = mlx4_mw_enable(dev->dev, &mw->mmw);
+        if (err)
+                goto err_mw;
+
+        mw->ibmw.rkey = mw->mmw.key;
+
+        return &mw->ibmw;
+
+err_mw:
+        mlx4_mw_free(dev->dev, &mw->mmw);
+
+err_free:
+        kfree(mw);
+
+        return ERR_PTR(err);
+}
+
+int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
+{
+        struct mlx4_ib_mw *mw = to_mmw(ibmw);
+
+        mlx4_mw_free(to_mdev(ibmw->device)->dev, &mw->mmw);
+        kfree(mw);
+
+        return 0;
+}
+
 struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
                                         int max_page_list_len)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 5e785bdcc694..602ca9bf78e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -654,6 +654,101 @@ int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 }
 EXPORT_SYMBOL_GPL(mlx4_buf_write_mtt);
 
+int mlx4_mw_alloc(struct mlx4_dev *dev, u32 pd, enum mlx4_mw_type type,
+                  struct mlx4_mw *mw)
+{
+        u32 index;
+
+        if ((type == MLX4_MW_TYPE_1 &&
+             !(dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW)) ||
+             (type == MLX4_MW_TYPE_2 &&
+             !(dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)))
+                return -ENOTSUPP;
+
+        index = mlx4_mpt_reserve(dev);
+        if (index == -1)
+                return -ENOMEM;
+
+        mw->key     = hw_index_to_key(index);
+        mw->pd      = pd;
+        mw->type    = type;
+        mw->enabled = MLX4_MPT_DISABLED;
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_mw_alloc);
+
+int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw)
+{
+        struct mlx4_cmd_mailbox *mailbox;
+        struct mlx4_mpt_entry *mpt_entry;
+        int err;
+
+        err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key));
+        if (err)
+                return err;
+
+        mailbox = mlx4_alloc_cmd_mailbox(dev);
+        if (IS_ERR(mailbox)) {
+                err = PTR_ERR(mailbox);
+                goto err_table;
+        }
+        mpt_entry = mailbox->buf;
+
+        memset(mpt_entry, 0, sizeof(*mpt_entry));
+
+        /* Note that the MLX4_MPT_FLAG_REGION bit in mpt_entry->flags is turned
+         * off, thus creating a memory window and not a memory region.
+         */
+        mpt_entry->key         = cpu_to_be32(key_to_hw_index(mw->key));
+        mpt_entry->pd_flags    = cpu_to_be32(mw->pd);
+        if (mw->type == MLX4_MW_TYPE_2) {
+                mpt_entry->flags    |= cpu_to_be32(MLX4_MPT_FLAG_FREE);
+                mpt_entry->qpn       = cpu_to_be32(MLX4_MPT_QP_FLAG_BOUND_QP);
+                mpt_entry->pd_flags |= cpu_to_be32(MLX4_MPT_PD_FLAG_EN_INV);
+        }
+
+        err = mlx4_SW2HW_MPT(dev, mailbox,
+                             key_to_hw_index(mw->key) &
+                             (dev->caps.num_mpts - 1));
+        if (err) {
+                mlx4_warn(dev, "SW2HW_MPT failed (%d)\n", err);
+                goto err_cmd;
+        }
+        mw->enabled = MLX4_MPT_EN_HW;
+
+        mlx4_free_cmd_mailbox(dev, mailbox);
+
+        return 0;
+
+err_cmd:
+        mlx4_free_cmd_mailbox(dev, mailbox);
+
+err_table:
+        mlx4_mpt_free_icm(dev, key_to_hw_index(mw->key));
+        return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_mw_enable);
+
+void mlx4_mw_free(struct mlx4_dev *dev, struct mlx4_mw *mw)
+{
+        int err;
+
+        if (mw->enabled == MLX4_MPT_EN_HW) {
+                err = mlx4_HW2SW_MPT(dev, NULL,
+                                     key_to_hw_index(mw->key) &
+                                     (dev->caps.num_mpts - 1));
+                if (err)
+                        mlx4_warn(dev, "xxx HW2SW_MPT failed (%d)\n", err);
+
+                mw->enabled = MLX4_MPT_EN_SW;
+        }
+        if (mw->enabled)
+                mlx4_mpt_free_icm(dev, key_to_hw_index(mw->key));
+        mlx4_mpt_release(dev, key_to_hw_index(mw->key));
+}
+EXPORT_SYMBOL_GPL(mlx4_mw_free);
+
 int mlx4_init_mr_table(struct mlx4_dev *dev)
 {
         struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e9fe8caaf8bb..67b4695e5940 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -170,6 +170,7 @@ enum {
 #define MLX4_ATTR_EXTENDED_PORT_INFO    cpu_to_be16(0xff90)
 
 enum {
+        MLX4_BMME_FLAG_WIN_TYPE_2B      = 1 <<  1,
         MLX4_BMME_FLAG_LOCAL_INV        = 1 <<  6,
         MLX4_BMME_FLAG_REMOTE_INV       = 1 <<  7,
         MLX4_BMME_FLAG_TYPE_2_WIN       = 1 <<  9,
@@ -237,7 +238,8 @@ enum {
         MLX4_PERM_LOCAL_WRITE   = 1 << 11,
         MLX4_PERM_REMOTE_READ   = 1 << 12,
         MLX4_PERM_REMOTE_WRITE  = 1 << 13,
-        MLX4_PERM_ATOMIC        = 1 << 14
+        MLX4_PERM_ATOMIC        = 1 << 14,
+        MLX4_PERM_BIND_MW       = 1 << 15,
 };
 
 enum {
@@ -503,6 +505,18 @@ struct mlx4_mr {
         int                     enabled;
 };
 
+enum mlx4_mw_type {
+        MLX4_MW_TYPE_1 = 1,
+        MLX4_MW_TYPE_2 = 2,
+};
+
+struct mlx4_mw {
+        u32                     key;
+        u32                     pd;
+        enum mlx4_mw_type       type;
+        int                     enabled;
+};
+
 struct mlx4_fmr {
         struct mlx4_mr          mr;
         struct mlx4_mpt_entry  *mpt;
@@ -803,6 +817,10 @@ int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
                   int npages, int page_shift, struct mlx4_mr *mr);
 int mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr);
 int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr);
+int mlx4_mw_alloc(struct mlx4_dev *dev, u32 pd, enum mlx4_mw_type type,
+                  struct mlx4_mw *mw);
+void mlx4_mw_free(struct mlx4_dev *dev, struct mlx4_mw *mw);
+int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw);
 int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
                    int start_index, int npages, u64 *page_list);
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,