IB/uverbs: Implement memory windows support in uverbs

The existing user/kernel uverbs API has IB_USER_VERBS_CMD_ALLOC/DEALLOC_MW.
Implement these calls, along with destroying user memory windows during
process cleanup.

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>

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 5bcb2af..0fcd7aa 100644 (file)
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -188,6 +188,8 @@ IB_UVERBS_DECLARE_CMD(alloc_pd);
 IB_UVERBS_DECLARE_CMD(dealloc_pd);
 IB_UVERBS_DECLARE_CMD(reg_mr);
 IB_UVERBS_DECLARE_CMD(dereg_mr);
+IB_UVERBS_DECLARE_CMD(alloc_mw);
+IB_UVERBS_DECLARE_CMD(dealloc_mw);
 IB_UVERBS_DECLARE_CMD(create_comp_channel);
 IB_UVERBS_DECLARE_CMD(create_cq);
 IB_UVERBS_DECLARE_CMD(resize_cq);

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 0cb0007..3983a05 100644 (file)
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -48,6 +48,7 @@ struct uverbs_lock_class {
 
 static struct uverbs_lock_class pd_lock_class  = { .name = "PD-uobj" };
 static struct uverbs_lock_class mr_lock_class  = { .name = "MR-uobj" };
+static struct uverbs_lock_class mw_lock_class  = { .name = "MW-uobj" };
 static struct uverbs_lock_class cq_lock_class  = { .name = "CQ-uobj" };
 static struct uverbs_lock_class qp_lock_class  = { .name = "QP-uobj" };
 static struct uverbs_lock_class ah_lock_class  = { .name = "AH-uobj" };
@@ -1049,6 +1050,126 @@ ssize_t ib_uverbs_dereg_mr(struct ib_uverbs_file *file,
        return in_len;
 }
 
+ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file,
+                        const char __user *buf, int in_len,
+                        int out_len)
+{
+       struct ib_uverbs_alloc_mw      cmd;
+       struct ib_uverbs_alloc_mw_resp resp;
+       struct ib_uobject             *uobj;
+       struct ib_pd                  *pd;
+       struct ib_mw                  *mw;
+       int                            ret;
+
+       if (out_len < sizeof(resp))
+               return -ENOSPC;
+
+       if (copy_from_user(&cmd, buf, sizeof(cmd)))
+               return -EFAULT;
+
+       uobj = kmalloc(sizeof(*uobj), GFP_KERNEL);
+       if (!uobj)
+               return -ENOMEM;
+
+       init_uobj(uobj, 0, file->ucontext, &mw_lock_class);
+       down_write(&uobj->mutex);
+
+       pd = idr_read_pd(cmd.pd_handle, file->ucontext);
+       if (!pd) {
+               ret = -EINVAL;
+               goto err_free;
+       }
+
+       mw = pd->device->alloc_mw(pd, cmd.mw_type);
+       if (IS_ERR(mw)) {
+               ret = PTR_ERR(mw);
+               goto err_put;
+       }
+
+       mw->device  = pd->device;
+       mw->pd      = pd;
+       mw->uobject = uobj;
+       atomic_inc(&pd->usecnt);
+
+       uobj->object = mw;
+       ret = idr_add_uobj(&ib_uverbs_mw_idr, uobj);
+       if (ret)
+               goto err_unalloc;
+
+       memset(&resp, 0, sizeof(resp));
+       resp.rkey      = mw->rkey;
+       resp.mw_handle = uobj->id;
+
+       if (copy_to_user((void __user *)(unsigned long)cmd.response,
+                        &resp, sizeof(resp))) {
+               ret = -EFAULT;
+               goto err_copy;
+       }
+
+       put_pd_read(pd);
+
+       mutex_lock(&file->mutex);
+       list_add_tail(&uobj->list, &file->ucontext->mw_list);
+       mutex_unlock(&file->mutex);
+
+       uobj->live = 1;
+
+       up_write(&uobj->mutex);
+
+       return in_len;
+
+err_copy:
+       idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
+
+err_unalloc:
+       ib_dealloc_mw(mw);
+
+err_put:
+       put_pd_read(pd);
+
+err_free:
+       put_uobj_write(uobj);
+       return ret;
+}
+
+ssize_t ib_uverbs_dealloc_mw(struct ib_uverbs_file *file,
+                          const char __user *buf, int in_len,
+                          int out_len)
+{
+       struct ib_uverbs_dealloc_mw cmd;
+       struct ib_mw               *mw;
+       struct ib_uobject          *uobj;
+       int                         ret = -EINVAL;
+
+       if (copy_from_user(&cmd, buf, sizeof(cmd)))
+               return -EFAULT;
+
+       uobj = idr_write_uobj(&ib_uverbs_mw_idr, cmd.mw_handle, file->ucontext);
+       if (!uobj)
+               return -EINVAL;
+
+       mw = uobj->object;
+
+       ret = ib_dealloc_mw(mw);
+       if (!ret)
+               uobj->live = 0;
+
+       put_uobj_write(uobj);
+
+       if (ret)
+               return ret;
+
+       idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
+
+       mutex_lock(&file->mutex);
+       list_del(&uobj->list);
+       mutex_unlock(&file->mutex);
+
+       put_uobj(uobj);
+
+       return in_len;
+}
+
 ssize_t ib_uverbs_create_comp_channel(struct ib_uverbs_file *file,
                                      const char __user *buf, int in_len,
                                      int out_len)

diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 6f2ce6f..2c6f0f2 100644 (file)
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -87,6 +87,8 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
        [IB_USER_VERBS_CMD_DEALLOC_PD]          = ib_uverbs_dealloc_pd,
        [IB_USER_VERBS_CMD_REG_MR]              = ib_uverbs_reg_mr,
        [IB_USER_VERBS_CMD_DEREG_MR]            = ib_uverbs_dereg_mr,
+       [IB_USER_VERBS_CMD_ALLOC_MW]            = ib_uverbs_alloc_mw,
+       [IB_USER_VERBS_CMD_DEALLOC_MW]          = ib_uverbs_dealloc_mw,
        [IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL] = ib_uverbs_create_comp_channel,
        [IB_USER_VERBS_CMD_CREATE_CQ]           = ib_uverbs_create_cq,
        [IB_USER_VERBS_CMD_RESIZE_CQ]           = ib_uverbs_resize_cq,
@@ -201,6 +203,15 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
                kfree(uobj);
        }
 
+       /* Remove MWs before QPs, in order to support type 2A MWs. */
+       list_for_each_entry_safe(uobj, tmp, &context->mw_list, list) {
+               struct ib_mw *mw = uobj->object;
+
+               idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
+               ib_dealloc_mw(mw);
+               kfree(uobj);
+       }
+
        list_for_each_entry_safe(uobj, tmp, &context->qp_list, list) {
                struct ib_qp *qp = uobj->object;
                struct ib_uqp_object *uqp =
@@ -240,8 +251,6 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
                kfree(uevent);
        }
 
-       /* XXX Free MWs */
-
        list_for_each_entry_safe(uobj, tmp, &context->mr_list, list) {
                struct ib_mr *mr = uobj->object;
 

diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 81aba3a..805711e 100644 (file)
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -261,6 +261,22 @@ struct ib_uverbs_dereg_mr {
        __u32 mr_handle;
 };
 
+struct ib_uverbs_alloc_mw {
+       __u64 response;
+       __u32 pd_handle;
+       __u8  mw_type;
+       __u8  reserved[3];
+};
+
+struct ib_uverbs_alloc_mw_resp {
+       __u32 mw_handle;
+       __u32 rkey;
+};
+
+struct ib_uverbs_dealloc_mw {
+       __u32 mw_handle;
+};
+
 struct ib_uverbs_create_comp_channel {
        __u64 response;
 };