Merge branch 'ethtool-mac-merge'

Vladimir Oltean says:

====================
ethtool support for IEEE 802.3 MAC Merge layer

Change log
----------

v3->v4:
- add missing opening bracket in ocelot_port_mm_irq()
- moved cfg.verify_time range checking so that it actually takes place
  for the updated rather than old value
v3 at:
https://patchwork.kernel.org/project/netdevbpf/cover/20230117085947.2176464-1-vladimir.oltean@nxp.com/

v2->v3:
- made get_mm return int instead of void
- deleted ETHTOOL_A_MM_SUPPORTED
- renamed ETHTOOL_A_MM_ADD_FRAG_SIZE to ETHTOOL_A_MM_TX_MIN_FRAG_SIZE
- introduced ETHTOOL_A_MM_RX_MIN_FRAG_SIZE
- cleaned up documentation
- rebased on top of PLCA changes
- renamed ETHTOOL_STATS_SRC_* to ETHTOOL_MAC_STATS_SRC_*
v2 at:
https://patchwork.kernel.org/project/netdevbpf/cover/20230111161706.1465242-1-vladimir.oltean@nxp.com/

v1->v2:
I've decided to focus just on the MAC Merge layer for now, which is why
I am able to submit this patch set as non-RFC.
v1 (RFC) at:
https://patchwork.kernel.org/project/netdevbpf/cover/20220816222920.1952936-1-vladimir.oltean@nxp.com/

What is being introduced
------------------------

TL;DR: a MAC Merge layer as defined by IEEE 802.3-2018, clause 99
(interspersing of express traffic). This is controlled through ethtool
netlink (ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET). The raw ethtool
commands are posted here:
https://patchwork.kernel.org/project/netdevbpf/cover/20230111153638.1454687-1-vladimir.oltean@nxp.com/

The MAC Merge layer has its own statistics counters
(ethtool --include-statistics --show-mm swp0) as well as two member
MACs, the statistics of which can be queried individually, through a new
ethtool netlink attribute, corresponding to:

$ ethtool -I --show-pause eno2 --src aggregate
$ ethtool -S eno2 --groups eth-mac eth-phy eth-ctrl rmon -- --src pmac

The core properties of the MAC Merge layer are described in great detail
in patches 02/12 and 03/12. They can be viewed in "make htmldocs" format.

Devices for which the API is supported
--------------------------------------

I decided to start with the Ethernet switch on NXP LS1028A (Felix)
because of the smaller patch set. I also have support for the ENETC
controller pending.

I would like to get confirmation that the UAPI being proposed here will
not restrict any use cases known by other hardware vendors.

Why is support for preemptible traffic classes not here?
--------------------------------------------------------

There is legitimate concern whether the 802.1Q portion of the standard
(which traffic classes go to the eMAC and which to the pMAC) should be
modeled in Linux using tc or using another UAPI. I think that is
stalling the entire series, but should be discussed separately instead.
Removing FP adminStatus support makes me confident enough to submit this
patch set without an RFC tag (meaning: I wouldn't mind if it was merged
as is).

What is submitted here is sufficient for an LLDP daemon to do its job.
I've patched openlldp to advertise and configure frame preemption:
https://github.com/vladimiroltean/openlldp/tree/frame-preemption-v3

In case someone wants to try it out, here are some commands I've used.

 # Configure the interfaces to receive and transmit LLDP Data Units
 lldptool -L -i eno0 adminStatus=rxtx
 lldptool -L -i swp0 adminStatus=rxtx
 # Enable the transmission of certain TLVs on switch's interface
 lldptool -T -i eno0 -V addEthCap enableTx=yes
 lldptool -T -i swp0 -V addEthCap enableTx=yes
 # Query LLDP statistics on switch's interface
 lldptool -S -i swp0
 # Query the received neighbor TLVs
 lldptool -i swp0 -t -n -V addEthCap
 Additional Ethernet Capabilities TLV
         Preemption capability supported
         Preemption capability enabled
         Preemption capability active
         Additional fragment size: 60 octets

So using this patch set, lldpad will be able to advertise and configure
frame preemption, but still, no data packet will be sent as preemptible
over the link, because there is no UAPI to control which traffic classes
are sent as preemptible and which as express.

Preemptable or preemptible?
---------------------------

IEEE 802.3 uses "preemptable" throughout. IEEE 802.1Q uses "preemptible"
throughout. Because the definition of "preemptible" falls under 802.1Q's
jurisdiction and 802.3 just references it, I went with the 802.1Q naming
even where supporting an 802.3 feature. Also, checkpatch agrees with this.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 271 insertions, 0 deletions

diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c
new file mode 100644
index 000000000000..809d196665c6
--- /dev/null
+++ b/net/ethtool/mm.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2022-2023 NXP
+ */
+#include "common.h"
+#include "netlink.h"
+
+struct mm_req_info {
+	struct ethnl_req_info		base;
+};
+
+struct mm_reply_data {
+	struct ethnl_reply_data		base;
+	struct ethtool_mm_state		state;
+	struct ethtool_mm_stats		stats;
+};
+
+#define MM_REPDATA(__reply_base) \
+	container_of(__reply_base, struct mm_reply_data, base)
+
+#define ETHTOOL_MM_STAT_CNT \
+	(__ETHTOOL_A_MM_STAT_CNT - (ETHTOOL_A_MM_STAT_PAD + 1))
+
+const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1] = {
+	[ETHTOOL_A_MM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats),
+};
+
+static int mm_prepare_data(const struct ethnl_req_info *req_base,
+			   struct ethnl_reply_data *reply_base,
+			   struct genl_info *info)
+{
+	struct mm_reply_data *data = MM_REPDATA(reply_base);
+	struct net_device *dev = reply_base->dev;
+	const struct ethtool_ops *ops;
+	int ret;
+
+	ops = dev->ethtool_ops;
+
+	if (!ops->get_mm)
+		return -EOPNOTSUPP;
+
+	ethtool_stats_init((u64 *)&data->stats,
+			   sizeof(data->stats) / sizeof(u64));
+
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		return ret;
+
+	ret = ops->get_mm(dev, &data->state);
+	if (ret)
+		goto out_complete;
+
+	if (ops->get_mm_stats && (req_base->flags & ETHTOOL_FLAG_STATS))
+		ops->get_mm_stats(dev, &data->stats);
+
+out_complete:
+	ethnl_ops_complete(dev);
+
+	return 0;
+}
+
+static int mm_reply_size(const struct ethnl_req_info *req_base,
+			 const struct ethnl_reply_data *reply_base)
+{
+	int len = 0;
+
+	len += nla_total_size(sizeof(u8)); /* _MM_PMAC_ENABLED */
+	len += nla_total_size(sizeof(u8)); /* _MM_TX_ENABLED */
+	len += nla_total_size(sizeof(u8)); /* _MM_TX_ACTIVE */
+	len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_ENABLED */
+	len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_STATUS */
+	len += nla_total_size(sizeof(u32)); /* _MM_VERIFY_TIME */
+	len += nla_total_size(sizeof(u32)); /* _MM_MAX_VERIFY_TIME */
+	len += nla_total_size(sizeof(u32)); /* _MM_TX_MIN_FRAG_SIZE */
+	len += nla_total_size(sizeof(u32)); /* _MM_RX_MIN_FRAG_SIZE */
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS)
+		len += nla_total_size(0) + /* _MM_STATS */
+		       nla_total_size_64bit(sizeof(u64)) * ETHTOOL_MM_STAT_CNT;
+
+	return len;
+}
+
+static int mm_put_stat(struct sk_buff *skb, u64 val, u16 attrtype)
+{
+	if (val == ETHTOOL_STAT_NOT_SET)
+		return 0;
+	if (nla_put_u64_64bit(skb, attrtype, val, ETHTOOL_A_MM_STAT_PAD))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int mm_put_stats(struct sk_buff *skb,
+			const struct ethtool_mm_stats *stats)
+{
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, ETHTOOL_A_MM_STATS);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (mm_put_stat(skb, stats->MACMergeFrameAssErrorCount,
+			ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS) ||
+	    mm_put_stat(skb, stats->MACMergeFrameSmdErrorCount,
+			ETHTOOL_A_MM_STAT_SMD_ERRORS) ||
+	    mm_put_stat(skb, stats->MACMergeFrameAssOkCount,
+			ETHTOOL_A_MM_STAT_REASSEMBLY_OK) ||
+	    mm_put_stat(skb, stats->MACMergeFragCountRx,
+			ETHTOOL_A_MM_STAT_RX_FRAG_COUNT) ||
+	    mm_put_stat(skb, stats->MACMergeFragCountTx,
+			ETHTOOL_A_MM_STAT_TX_FRAG_COUNT) ||
+	    mm_put_stat(skb, stats->MACMergeHoldCount,
+			ETHTOOL_A_MM_STAT_HOLD_COUNT))
+		goto err_cancel;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+err_cancel:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int mm_fill_reply(struct sk_buff *skb,
+			 const struct ethnl_req_info *req_base,
+			 const struct ethnl_reply_data *reply_base)
+{
+	const struct mm_reply_data *data = MM_REPDATA(reply_base);
+	const struct ethtool_mm_state *state = &data->state;
+
+	if (nla_put_u8(skb, ETHTOOL_A_MM_TX_ENABLED, state->tx_enabled) ||
+	    nla_put_u8(skb, ETHTOOL_A_MM_TX_ACTIVE, state->tx_active) ||
+	    nla_put_u8(skb, ETHTOOL_A_MM_PMAC_ENABLED, state->pmac_enabled) ||
+	    nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_ENABLED, state->verify_enabled) ||
+	    nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_STATUS, state->verify_status) ||
+	    nla_put_u32(skb, ETHTOOL_A_MM_VERIFY_TIME, state->verify_time) ||
+	    nla_put_u32(skb, ETHTOOL_A_MM_MAX_VERIFY_TIME, state->max_verify_time) ||
+	    nla_put_u32(skb, ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, state->tx_min_frag_size) ||
+	    nla_put_u32(skb, ETHTOOL_A_MM_RX_MIN_FRAG_SIZE, state->rx_min_frag_size))
+		return -EMSGSIZE;
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    mm_put_stats(skb, &data->stats))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+const struct ethnl_request_ops ethnl_mm_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_MM_GET,
+	.reply_cmd		= ETHTOOL_MSG_MM_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_MM_HEADER,
+	.req_info_size		= sizeof(struct mm_req_info),
+	.reply_data_size	= sizeof(struct mm_reply_data),
+
+	.prepare_data		= mm_prepare_data,
+	.reply_size		= mm_reply_size,
+	.fill_reply		= mm_fill_reply,
+};
+
+const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1] = {
+	[ETHTOOL_A_MM_HEADER]		= NLA_POLICY_NESTED(ethnl_header_policy),
+	[ETHTOOL_A_MM_VERIFY_ENABLED]	= NLA_POLICY_MAX(NLA_U8, 1),
+	[ETHTOOL_A_MM_VERIFY_TIME]	= NLA_POLICY_RANGE(NLA_U32, 1, 128),
+	[ETHTOOL_A_MM_TX_ENABLED]	= NLA_POLICY_MAX(NLA_U8, 1),
+	[ETHTOOL_A_MM_PMAC_ENABLED]	= NLA_POLICY_MAX(NLA_U8, 1),
+	[ETHTOOL_A_MM_TX_MIN_FRAG_SIZE]	= NLA_POLICY_RANGE(NLA_U32, 60, 252),
+};
+
+static void mm_state_to_cfg(const struct ethtool_mm_state *state,
+			    struct ethtool_mm_cfg *cfg)
+{
+	/* We could also compare state->verify_status against
+	 * ETHTOOL_MM_VERIFY_STATUS_DISABLED, but state->verify_enabled
+	 * is more like an administrative state which should be seen in
+	 * ETHTOOL_MSG_MM_GET replies. For example, a port with verification
+	 * disabled might be in the ETHTOOL_MM_VERIFY_STATUS_INITIAL
+	 * if it's down.
+	 */
+	cfg->verify_enabled = state->verify_enabled;
+	cfg->verify_time = state->verify_time;
+	cfg->tx_enabled = state->tx_enabled;
+	cfg->pmac_enabled = state->pmac_enabled;
+	cfg->tx_min_frag_size = state->tx_min_frag_size;
+}
+
+int ethnl_set_mm(struct sk_buff *skb, struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct ethnl_req_info req_info = {};
+	struct ethtool_mm_state state = {};
+	struct nlattr **tb = info->attrs;
+	struct ethtool_mm_cfg cfg = {};
+	const struct ethtool_ops *ops;
+	struct net_device *dev;
+	bool mod = false;
+	int ret;
+
+	ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_MM_HEADER],
+					 genl_info_net(info), extack, true);
+	if (ret)
+		return ret;
+
+	dev = req_info.dev;
+	ops = dev->ethtool_ops;
+
+	if (!ops->get_mm || !ops->set_mm) {
+		ret = -EOPNOTSUPP;
+		goto out_dev_put;
+	}
+
+	rtnl_lock();
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		goto out_rtnl_unlock;
+
+	ret = ops->get_mm(dev, &state);
+	if (ret)
+		goto out_complete;
+
+	mm_state_to_cfg(&state, &cfg);
+
+	ethnl_update_bool(&cfg.verify_enabled, tb[ETHTOOL_A_MM_VERIFY_ENABLED],
+			  &mod);
+	ethnl_update_u32(&cfg.verify_time, tb[ETHTOOL_A_MM_VERIFY_TIME], &mod);
+	ethnl_update_bool(&cfg.tx_enabled, tb[ETHTOOL_A_MM_TX_ENABLED], &mod);
+	ethnl_update_bool(&cfg.pmac_enabled, tb[ETHTOOL_A_MM_PMAC_ENABLED],
+			  &mod);
+	ethnl_update_u32(&cfg.tx_min_frag_size,
+			 tb[ETHTOOL_A_MM_TX_MIN_FRAG_SIZE], &mod);
+
+	if (!mod)
+		goto out_complete;
+
+	if (cfg.verify_time > state.max_verify_time) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MM_VERIFY_TIME],
+				    "verifyTime exceeds device maximum");
+		ret = -ERANGE;
+		goto out_complete;
+	}
+
+	ret = ops->set_mm(dev, &cfg, extack);
+	if (ret)
+		goto out_complete;
+
+	ethtool_notify(dev, ETHTOOL_MSG_MM_NTF, NULL);
+
+out_complete:
+	ethnl_ops_complete(dev);
+out_rtnl_unlock:
+	rtnl_unlock();
+out_dev_put:
+	ethnl_parse_header_dev_put(&req_info);
+	return ret;
+}
+
+/* Returns whether a given device supports the MAC merge layer
+ * (has an eMAC and a pMAC). Must be called under rtnl_lock() and
+ * ethnl_ops_begin().
+ */
+bool __ethtool_dev_mm_supported(struct net_device *dev)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_mm_state state = {};
+	int ret = -EOPNOTSUPP;
+
+	if (ops && ops->get_mm)
+		ret = ops->get_mm(dev, &state);
+
+	return !!ret;
+}