IB/uverbs: Introduce RWQ Indirection table

User applications that want to spread traffic on several WQs, need to
create an indirection table, by using already created WQs.

Adding uverbs API in order to create and destroy this table.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>

5 files changed, 253 insertions, 0 deletions

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 74776c6531f4..6c2292397cd6 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -186,6 +186,7 @@ extern struct idr ib_uverbs_srq_idr;
 extern struct idr ib_uverbs_xrcd_idr;
 extern struct idr ib_uverbs_rule_idr;
 extern struct idr ib_uverbs_wq_idr;
+extern struct idr ib_uverbs_rwq_ind_tbl_idr;
 
 void idr_remove_uobj(struct idr *idp, struct ib_uobject *uobj);
 
@@ -284,5 +285,7 @@ IB_UVERBS_DECLARE_EX_CMD(create_qp);
 IB_UVERBS_DECLARE_EX_CMD(create_wq);
 IB_UVERBS_DECLARE_EX_CMD(modify_wq);
 IB_UVERBS_DECLARE_EX_CMD(destroy_wq);
+IB_UVERBS_DECLARE_EX_CMD(create_rwq_ind_table);
+IB_UVERBS_DECLARE_EX_CMD(destroy_rwq_ind_table);
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 22e617391657..327a56cccc27 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -58,6 +58,7 @@ static struct uverbs_lock_class srq_lock_class	= { .name = "SRQ-uobj" };
 static struct uverbs_lock_class xrcd_lock_class = { .name = "XRCD-uobj" };
 static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" };
 static struct uverbs_lock_class wq_lock_class = { .name = "WQ-uobj" };
+static struct uverbs_lock_class rwq_ind_table_lock_class = { .name = "IND_TBL-uobj" };
 
 /*
  * The ib_uobject locking scheme is as follows:
@@ -338,6 +339,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	INIT_LIST_HEAD(&ucontext->srq_list);
 	INIT_LIST_HEAD(&ucontext->ah_list);
 	INIT_LIST_HEAD(&ucontext->wq_list);
+	INIT_LIST_HEAD(&ucontext->rwq_ind_tbl_list);
 	INIT_LIST_HEAD(&ucontext->xrcd_list);
 	INIT_LIST_HEAD(&ucontext->rule_list);
 	rcu_read_lock();
@@ -3299,6 +3301,214 @@ int ib_uverbs_ex_modify_wq(struct ib_uverbs_file *file,
 	return ret;
 }
 
+int ib_uverbs_ex_create_rwq_ind_table(struct ib_uverbs_file *file,
+				      struct ib_device *ib_dev,
+				      struct ib_udata *ucore,
+				      struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_create_rwq_ind_table	  cmd = {};
+	struct ib_uverbs_ex_create_rwq_ind_table_resp  resp = {};
+	struct ib_uobject		  *uobj;
+	int err = 0;
+	struct ib_rwq_ind_table_init_attr init_attr = {};
+	struct ib_rwq_ind_table *rwq_ind_tbl;
+	struct ib_wq	**wqs = NULL;
+	u32 *wqs_handles = NULL;
+	struct ib_wq	*wq = NULL;
+	int i, j, num_read_wqs;
+	u32 num_wq_handles;
+	u32 expected_in_size;
+	size_t required_cmd_sz_header;
+	size_t required_resp_len;
+
+	required_cmd_sz_header = offsetof(typeof(cmd), log_ind_tbl_size) + sizeof(cmd.log_ind_tbl_size);
+	required_resp_len = offsetof(typeof(resp), ind_tbl_num) + sizeof(resp.ind_tbl_num);
+
+	if (ucore->inlen < required_cmd_sz_header)
+		return -EINVAL;
+
+	if (ucore->outlen < required_resp_len)
+		return -ENOSPC;
+
+	err = ib_copy_from_udata(&cmd, ucore, required_cmd_sz_header);
+	if (err)
+		return err;
+
+	ucore->inbuf += required_cmd_sz_header;
+	ucore->inlen -= required_cmd_sz_header;
+
+	if (cmd.comp_mask)
+		return -EOPNOTSUPP;
+
+	if (cmd.log_ind_tbl_size > IB_USER_VERBS_MAX_LOG_IND_TBL_SIZE)
+		return -EINVAL;
+
+	num_wq_handles = 1 << cmd.log_ind_tbl_size;
+	expected_in_size = num_wq_handles * sizeof(__u32);
+	if (num_wq_handles == 1)
+		/* input size for wq handles is u64 aligned */
+		expected_in_size += sizeof(__u32);
+
+	if (ucore->inlen < expected_in_size)
+		return -EINVAL;
+
+	if (ucore->inlen > expected_in_size &&
+	    !ib_is_udata_cleared(ucore, expected_in_size,
+				 ucore->inlen - expected_in_size))
+		return -EOPNOTSUPP;
+
+	wqs_handles = kcalloc(num_wq_handles, sizeof(*wqs_handles),
+			      GFP_KERNEL);
+	if (!wqs_handles)
+		return -ENOMEM;
+
+	err = ib_copy_from_udata(wqs_handles, ucore,
+				 num_wq_handles * sizeof(__u32));
+	if (err)
+		goto err_free;
+
+	wqs = kcalloc(num_wq_handles, sizeof(*wqs), GFP_KERNEL);
+	if (!wqs) {
+		err = -ENOMEM;
+		goto  err_free;
+	}
+
+	for (num_read_wqs = 0; num_read_wqs < num_wq_handles;
+			num_read_wqs++) {
+		wq = idr_read_wq(wqs_handles[num_read_wqs], file->ucontext);
+		if (!wq) {
+			err = -EINVAL;
+			goto put_wqs;
+		}
+
+		wqs[num_read_wqs] = wq;
+	}
+
+	uobj = kmalloc(sizeof(*uobj), GFP_KERNEL);
+	if (!uobj) {
+		err = -ENOMEM;
+		goto put_wqs;
+	}
+
+	init_uobj(uobj, 0, file->ucontext, &rwq_ind_table_lock_class);
+	down_write(&uobj->mutex);
+	init_attr.log_ind_tbl_size = cmd.log_ind_tbl_size;
+	init_attr.ind_tbl = wqs;
+	rwq_ind_tbl = ib_dev->create_rwq_ind_table(ib_dev, &init_attr, uhw);
+
+	if (IS_ERR(rwq_ind_tbl)) {
+		err = PTR_ERR(rwq_ind_tbl);
+		goto err_uobj;
+	}
+
+	rwq_ind_tbl->ind_tbl = wqs;
+	rwq_ind_tbl->log_ind_tbl_size = init_attr.log_ind_tbl_size;
+	rwq_ind_tbl->uobject = uobj;
+	uobj->object = rwq_ind_tbl;
+	rwq_ind_tbl->device = ib_dev;
+	atomic_set(&rwq_ind_tbl->usecnt, 0);
+
+	for (i = 0; i < num_wq_handles; i++)
+		atomic_inc(&wqs[i]->usecnt);
+
+	err = idr_add_uobj(&ib_uverbs_rwq_ind_tbl_idr, uobj);
+	if (err)
+		goto destroy_ind_tbl;
+
+	resp.ind_tbl_handle = uobj->id;
+	resp.ind_tbl_num = rwq_ind_tbl->ind_tbl_num;
+	resp.response_length = required_resp_len;
+
+	err = ib_copy_to_udata(ucore,
+			       &resp, resp.response_length);
+	if (err)
+		goto err_copy;
+
+	kfree(wqs_handles);
+
+	for (j = 0; j < num_read_wqs; j++)
+		put_wq_read(wqs[j]);
+
+	mutex_lock(&file->mutex);
+	list_add_tail(&uobj->list, &file->ucontext->rwq_ind_tbl_list);
+	mutex_unlock(&file->mutex);
+
+	uobj->live = 1;
+
+	up_write(&uobj->mutex);
+	return 0;
+
+err_copy:
+	idr_remove_uobj(&ib_uverbs_rwq_ind_tbl_idr, uobj);
+destroy_ind_tbl:
+	ib_destroy_rwq_ind_table(rwq_ind_tbl);
+err_uobj:
+	put_uobj_write(uobj);
+put_wqs:
+	for (j = 0; j < num_read_wqs; j++)
+		put_wq_read(wqs[j]);
+err_free:
+	kfree(wqs_handles);
+	kfree(wqs);
+	return err;
+}
+
+int ib_uverbs_ex_destroy_rwq_ind_table(struct ib_uverbs_file *file,
+				       struct ib_device *ib_dev,
+				       struct ib_udata *ucore,
+				       struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_destroy_rwq_ind_table	cmd = {};
+	struct ib_rwq_ind_table *rwq_ind_tbl;
+	struct ib_uobject		*uobj;
+	int			ret;
+	struct ib_wq	**ind_tbl;
+	size_t required_cmd_sz;
+
+	required_cmd_sz = offsetof(typeof(cmd), ind_tbl_handle) + sizeof(cmd.ind_tbl_handle);
+
+	if (ucore->inlen < required_cmd_sz)
+		return -EINVAL;
+
+	if (ucore->inlen > sizeof(cmd) &&
+	    !ib_is_udata_cleared(ucore, sizeof(cmd),
+				 ucore->inlen - sizeof(cmd)))
+		return -EOPNOTSUPP;
+
+	ret = ib_copy_from_udata(&cmd, ucore, min(sizeof(cmd), ucore->inlen));
+	if (ret)
+		return ret;
+
+	if (cmd.comp_mask)
+		return -EOPNOTSUPP;
+
+	uobj = idr_write_uobj(&ib_uverbs_rwq_ind_tbl_idr, cmd.ind_tbl_handle,
+			      file->ucontext);
+	if (!uobj)
+		return -EINVAL;
+	rwq_ind_tbl = uobj->object;
+	ind_tbl = rwq_ind_tbl->ind_tbl;
+
+	ret = ib_destroy_rwq_ind_table(rwq_ind_tbl);
+	if (!ret)
+		uobj->live = 0;
+
+	put_uobj_write(uobj);
+
+	if (ret)
+		return ret;
+
+	idr_remove_uobj(&ib_uverbs_rwq_ind_tbl_idr, uobj);
+
+	mutex_lock(&file->mutex);
+	list_del(&uobj->list);
+	mutex_unlock(&file->mutex);
+
+	put_uobj(uobj);
+	kfree(ind_tbl);
+	return ret;
+}
+
 int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 			     struct ib_device *ib_dev,
 			     struct ib_udata *ucore,
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 91cb36f66ea7..426e0ac203fc 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -77,6 +77,7 @@ DEFINE_IDR(ib_uverbs_srq_idr);
 DEFINE_IDR(ib_uverbs_xrcd_idr);
 DEFINE_IDR(ib_uverbs_rule_idr);
 DEFINE_IDR(ib_uverbs_wq_idr);
+DEFINE_IDR(ib_uverbs_rwq_ind_tbl_idr);
 
 static DEFINE_SPINLOCK(map_lock);
 static DECLARE_BITMAP(dev_map, IB_UVERBS_MAX_DEVICES);
@@ -134,6 +135,8 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_EX_CMD_CREATE_WQ]        = ib_uverbs_ex_create_wq,
 	[IB_USER_VERBS_EX_CMD_MODIFY_WQ]        = ib_uverbs_ex_modify_wq,
 	[IB_USER_VERBS_EX_CMD_DESTROY_WQ]       = ib_uverbs_ex_destroy_wq,
+	[IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL] = ib_uverbs_ex_create_rwq_ind_table,
+	[IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL] = ib_uverbs_ex_destroy_rwq_ind_table,
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
@@ -269,6 +272,16 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 		kfree(uqp);
 	}
 
+	list_for_each_entry_safe(uobj, tmp, &context->rwq_ind_tbl_list, list) {
+		struct ib_rwq_ind_table *rwq_ind_tbl = uobj->object;
+		struct ib_wq **ind_tbl = rwq_ind_tbl->ind_tbl;
+
+		idr_remove_uobj(&ib_uverbs_rwq_ind_tbl_idr, uobj);
+		ib_destroy_rwq_ind_table(rwq_ind_tbl);
+		kfree(ind_tbl);
+		kfree(uobj);
+	}
+
 	list_for_each_entry_safe(uobj, tmp, &context->wq_list, list) {
 		struct ib_wq *wq = uobj->object;
 		struct ib_uwq_object *uwq =
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fa2e0184dcc5..e305c9a36663 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1326,6 +1326,7 @@ struct ib_ucontext {
 	struct list_head	xrcd_list;
 	struct list_head	rule_list;
 	struct list_head	wq_list;
+	struct list_head	rwq_ind_tbl_list;
 	int			closing;
 
 	struct pid             *tgid;
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index c9470e511e03..2cf7c95860d8 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -98,6 +98,8 @@ enum {
 	IB_USER_VERBS_EX_CMD_CREATE_WQ,
 	IB_USER_VERBS_EX_CMD_MODIFY_WQ,
 	IB_USER_VERBS_EX_CMD_DESTROY_WQ,
+	IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL,
+	IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL
 };
 
 /*
@@ -987,4 +989,28 @@ struct ib_uverbs_ex_modify_wq  {
 	__u32 curr_wq_state;
 };
 
+/* Prevent memory allocation rather than max expected size */
+#define IB_USER_VERBS_MAX_LOG_IND_TBL_SIZE 0x0d
+struct ib_uverbs_ex_create_rwq_ind_table  {
+	__u32 comp_mask;
+	__u32 log_ind_tbl_size;
+	/* Following are the wq handles according to log_ind_tbl_size
+	 * wq_handle1
+	 * wq_handle2
+	 */
+	__u32 wq_handles[0];
+};
+
+struct ib_uverbs_ex_create_rwq_ind_table_resp {
+	__u32 comp_mask;
+	__u32 response_length;
+	__u32 ind_tbl_handle;
+	__u32 ind_tbl_num;
+};
+
+struct ib_uverbs_ex_destroy_rwq_ind_table  {
+	__u32 comp_mask;
+	__u32 ind_tbl_handle;
+};
+
 #endif /* IB_USER_VERBS_H */