net/devlink: Add E-Switch mode control

Add the commands to set and show the mode of SRIOV E-Switch, two modes
are supported:

* legacy: operating in the "old" L2 based mode (DMAC --> VF vport)

* switchdev: the E-Switch is referred to as whitebox switch configured
using standard tools such as tc, bridge, openvswitch etc. To allow
working with the tools, for each VF, a VF representor netdevice is
created by the E-Switch manager vendor device driver instance (e.g PF).

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 98 insertions, 0 deletions

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 1d45b61cb320..c99ffe8cef3c 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -90,6 +90,9 @@ struct devlink_ops {
 				       u16 tc_index,
 				       enum devlink_sb_pool_type pool_type,
 				       u32 *p_cur, u32 *p_max);
+
+	int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode);
+	int (*eswitch_mode_set)(struct devlink *devlink, u16 mode);
 };
 
 static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index ba0073b26fa6..915bfa74458c 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -57,6 +57,8 @@ enum devlink_command {
 	DEVLINK_CMD_SB_OCC_SNAPSHOT,
 	DEVLINK_CMD_SB_OCC_MAX_CLEAR,
 
+	DEVLINK_CMD_ESWITCH_MODE_GET,
+	DEVLINK_CMD_ESWITCH_MODE_SET,
 	/* add new commands above here */
 
 	__DEVLINK_CMD_MAX,
@@ -95,6 +97,11 @@ enum devlink_sb_threshold_type {
 
 #define DEVLINK_SB_THRESHOLD_TO_ALPHA_MAX 20
 
+enum devlink_eswitch_mode {
+	DEVLINK_ESWITCH_MODE_LEGACY,
+	DEVLINK_ESWITCH_MODE_SWITCHDEV,
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -125,6 +132,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_SB_TC_INDEX,		/* u16 */
 	DEVLINK_ATTR_SB_OCC_CUR,		/* u32 */
 	DEVLINK_ATTR_SB_OCC_MAX,		/* u32 */
+	DEVLINK_ATTR_ESWITCH_MODE,		/* u16 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 933e8d4d3968..b2e592a198c0 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1394,6 +1394,78 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
 	return -EOPNOTSUPP;
 }
 
+static int devlink_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
+				enum devlink_command cmd, u32 portid,
+				u32 seq, int flags, u16 mode)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb,
+						struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const struct devlink_ops *ops = devlink->ops;
+	struct sk_buff *msg;
+	u16 mode;
+	int err;
+
+	if (!ops || !ops->eswitch_mode_get)
+		return -EOPNOTSUPP;
+
+	err = ops->eswitch_mode_get(devlink, &mode);
+	if (err)
+		return err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_MODE_GET,
+				   info->snd_portid, info->snd_seq, 0, mode);
+
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_eswitch_mode_set_doit(struct sk_buff *skb,
+						struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const struct devlink_ops *ops = devlink->ops;
+	u16 mode;
+
+	if (!info->attrs[DEVLINK_ATTR_ESWITCH_MODE])
+		return -EINVAL;
+
+	mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+
+	if (ops && ops->eswitch_mode_set)
+		return ops->eswitch_mode_set(devlink, mode);
+	return -EOPNOTSUPP;
+}
+
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -1407,6 +1479,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -1525,6 +1598,20 @@ static const struct genl_ops devlink_nl_ops[] = {
 				  DEVLINK_NL_FLAG_NEED_SB |
 				  DEVLINK_NL_FLAG_LOCK_PORTS,
 	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_MODE_GET,
+		.doit = devlink_nl_cmd_eswitch_mode_get_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_ESWITCH_MODE_SET,
+		.doit = devlink_nl_cmd_eswitch_mode_set_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 /**