[RFC PATCH net-next v3 0/6] ethtool: Add ability to control transceiver modules' power mode

@@ -179,7 +179,7 @@ according to message purpose:
 
 Userspace to kernel:
 
-  ===================================== ================================
+  ===================================== =================================
   ``ETHTOOL_MSG_STRSET_GET``            get string set
   ``ETHTOOL_MSG_LINKINFO_GET``          get link settings
   ``ETHTOOL_MSG_LINKINFO_SET``          set link settings

@@ -213,7 +213,9 @@ Userspace to kernel:
   ``ETHTOOL_MSG_MODULE_EEPROM_GET``     read SFP module EEPROM
   ``ETHTOOL_MSG_STATS_GET``             get standard statistics
   ``ETHTOOL_MSG_PHC_VCLOCKS_GET``       get PHC virtual clocks info
-  ===================================== ================================
+  ``ETHTOOL_MSG_MODULE_SET``            set transceiver module parameters
+  ``ETHTOOL_MSG_MODULE_GET``            get transceiver module parameters
+  ===================================== =================================
 
 Kernel to userspace:
 

@@ -252,6 +254,7 @@ Kernel to userspace:
   ``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY``  read SFP module EEPROM
   ``ETHTOOL_MSG_STATS_GET_REPLY``          standard statistics
   ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY``    PHC virtual clocks info
+  ``ETHTOOL_MSG_MODULE_GET_REPLY``         transceiver module parameters
   ======================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device

@@ -1506,6 +1509,61 @@ Kernel response contents:
   ``ETHTOOL_A_PHC_VCLOCKS_INDEX``       s32     PHC index array
   ====================================  ======  ==========================
 
+MODULE_GET
+==========
+
+Gets transceiver module parameters.
+
+Request contents:
+
+  =====================================  ======  ==========================
+  ``ETHTOOL_A_MODULE_HEADER``            nested  request header
+  =====================================  ======  ==========================
+
+Kernel response contents:
+
+  ======================================  ======  ==========================
+  ``ETHTOOL_A_MODULE_HEADER``             nested  reply header
+  ``ETHTOOL_A_MODULE_POWER_MODE_POLICY``  u8      power mode policy
+  ``ETHTOOL_A_MODULE_POWER_MODE``         u8      operational power mode
+  ======================================  ======  ==========================
+
+The optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute encodes the
+transceiver module power mode policy enforced by the host. The default policy
+is driver-dependent and can be queried using this attribute.
+
+The optional ``ETHTHOOL_A_MODULE_POWER_MODE`` attribute encodes the operational
+power mode policy of the transceiver module. It is only reported when a module
+is plugged-in. Possible values are:
+
+.. kernel-doc:: include/uapi/linux/ethtool.h
+    :identifiers: ethtool_module_power_mode
+
+MODULE_SET
+==========
+
+Sets transceiver module parameters.
+
+Request contents:
+
+  ======================================  ======  ==========================
+  ``ETHTOOL_A_MODULE_HEADER``             nested  request header
+  ``ETHTOOL_A_MODULE_POWER_MODE_POLICY``  u8      power mode policy
+  ======================================  ======  ==========================
+
+When set, the optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute is used
+to set the transceiver module power policy enforced by the host. Possible
+values are:
+
+.. kernel-doc:: include/uapi/linux/ethtool.h
+    :identifiers: ethtool_module_power_mode_policy
+
+For SFF-8636 modules, low power mode is forced by the host according to table
+6-10 in revision 2.10a of the specification.
+
+For CMIS modules, low power mode is forced by the host according to table 6-12
+in revision 5.0 of the specification.
+
 Request translation
 ===================
 

@@ -1605,4 +1663,6 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT``
   n/a                                 ``ETHTOOL_MSG_TUNNEL_INFO_GET``
   n/a                                 ``ETHTOOL_MSG_PHC_VCLOCKS_GET``
+  n/a                                 ``ETHTOOL_MSG_MODULE_GET``
+  n/a                                 ``ETHTOOL_MSG_MODULE_SET``
   =================================== =====================================

@@ -405,6 +405,20 @@ struct ethtool_module_eeprom {
 	u8	*data;
 };
 
+/**
+ * struct ethtool_module_power_mode_params - module power mode parameters
+ * @policy: The power mode policy enforced by the host for the plug-in module.
+ * @mode: The operational power mode of the plug-in module. Should be filled by
+ * device drivers on get operations.
+ * @mode_valid: Indicates the validity of the @mode field. Should be set by
+ * device drivers on get operations when a module is plugged-in.
+ */
+struct ethtool_module_power_mode_params {
+	enum ethtool_module_power_mode_policy policy;
+	enum ethtool_module_power_mode mode;
+	u8 mode_valid:1;
+};
+
 /**
  * struct ethtool_ops - optional netdev operations
  * @cap_link_lanes_supported: indicates if the driver supports lanes

@@ -570,6 +584,11 @@ struct ethtool_module_eeprom {
  * @get_eth_ctrl_stats: Query some of the IEEE 802.3 MAC Ctrl statistics.
  * @get_rmon_stats: Query some of the RMON (RFC 2819) statistics.
  *	Set %ranges to a pointer to zero-terminated array of byte ranges.
+ * @get_module_power_mode: Get the power mode policy for the plug-in module
+ *	used by the network device and its operational power mode, if
+ *	plugged-in.
+ * @set_module_power_mode: Set the power mode policy for the plug-in module
+ *	used by the network device.
  *
  * All operations are optional (i.e. the function pointer may be set
  * to %NULL) and callers must take this into account.  Callers must

@@ -689,6 +708,12 @@ struct ethtool_ops {
 	void	(*get_rmon_stats)(struct net_device *dev,
 				  struct ethtool_rmon_stats *rmon_stats,
 				  const struct ethtool_rmon_hist_range **ranges);
+	int	(*get_module_power_mode)(struct net_device *dev,
+					 struct ethtool_module_power_mode_params *params,
+					 struct netlink_ext_ack *extack);
+	int	(*set_module_power_mode)(struct net_device *dev,
+					 const struct ethtool_module_power_mode_params *params,
+					 struct netlink_ext_ack *extack);
 };
 
 int ethtool_check_ops(const struct ethtool_ops *ops);

@@ -706,6 +706,29 @@ enum ethtool_stringset {
 	ETH_SS_COUNT
 };
 
+/**
+ * enum ethtool_module_power_mode_policy - plug-in module power mode policy
+ * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode.
+ * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host
+ *	to high power mode when the first port using it is put administratively
+ *	up and to low power mode when the last port using it is put
+ *	administratively down.
+ */
+enum ethtool_module_power_mode_policy {
+	ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH,
+	ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO,
+};
+
+/**
+ * enum ethtool_module_power_mode - plug-in module power mode
+ * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode.
+ * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode.
+ */
+enum ethtool_module_power_mode {
+	ETHTOOL_MODULE_POWER_MODE_LOW,
+	ETHTOOL_MODULE_POWER_MODE_HIGH,
+};
+
 /**
  * struct ethtool_gstrings - string set for data tagging
  * @cmd: Command number = %ETHTOOL_GSTRINGS

@@ -47,6 +47,8 @@ enum {
 	ETHTOOL_MSG_MODULE_EEPROM_GET,
 	ETHTOOL_MSG_STATS_GET,
 	ETHTOOL_MSG_PHC_VCLOCKS_GET,
+	ETHTOOL_MSG_MODULE_GET,
+	ETHTOOL_MSG_MODULE_SET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,

@@ -90,6 +92,8 @@ enum {
 	ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY,
 	ETHTOOL_MSG_STATS_GET_REPLY,
 	ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY,
+	ETHTOOL_MSG_MODULE_GET_REPLY,
+	ETHTOOL_MSG_MODULE_NTF,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,

@@ -831,6 +835,19 @@ enum {
 	ETHTOOL_A_STATS_RMON_MAX = (__ETHTOOL_A_STATS_RMON_CNT - 1)
 };
 
+/* MODULE */
+
+enum {
+	ETHTOOL_A_MODULE_UNSPEC,
+	ETHTOOL_A_MODULE_HEADER,		/* nest - _A_HEADER_* */
+	ETHTOOL_A_MODULE_POWER_MODE_POLICY,	/* u8 */
+	ETHTOOL_A_MODULE_POWER_MODE,		/* u8 */
+
+	/* add new constants above here */
+	__ETHTOOL_A_MODULE_CNT,
+	ETHTOOL_A_MODULE_MAX = (__ETHTOOL_A_MODULE_CNT - 1)
+};
+
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1

@@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK)	+= ethtool_nl.o
 ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
 		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
-		   tunnels.o fec.o eeprom.o stats.o phc_vclocks.o
+		   tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o

@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/ethtool.h>
+
+#include "netlink.h"
+#include "common.h"
+#include "bitset.h"
+
+struct module_req_info {
+	struct ethnl_req_info base;
+};
+
+struct module_reply_data {
+	struct ethnl_reply_data	base;
+	struct ethtool_module_power_mode_params power;
+	u8 power_valid:1;
+};
+
+#define MODULE_REPDATA(__reply_base) \
+	container_of(__reply_base, struct module_reply_data, base)
+
+/* MODULE_GET */
+
+const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1] = {
+	[ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+static int module_get_power_mode(struct net_device *dev,
+				 struct module_reply_data *data,
+				 struct netlink_ext_ack *extack)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	int ret;
+
+	if (!ops->get_module_power_mode)
+		return 0;
+
+	ret = ops->get_module_power_mode(dev, &data->power, extack);
+	if (ret < 0)
+		return ret;
+
+	data->power_valid = true;
+
+	return 0;
+}
+
+static int module_prepare_data(const struct ethnl_req_info *req_base,
+			       struct ethnl_reply_data *reply_base,
+			       struct genl_info *info)
+{
+	struct module_reply_data *data = MODULE_REPDATA(reply_base);
+	struct netlink_ext_ack *extack = info ? info->extack : NULL;
+	struct net_device *dev = reply_base->dev;
+	int ret;
+
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		return ret;
+
+	ret = module_get_power_mode(dev, data, extack);
+	if (ret < 0)
+		goto out_complete;
+
+out_complete:
+	ethnl_ops_complete(dev);
+	return ret;
+}
+
+static int module_reply_size(const struct ethnl_req_info *req_base,
+			     const struct ethnl_reply_data *reply_base)
+{
+	struct module_reply_data *data = MODULE_REPDATA(reply_base);
+	int len = 0;
+
+	if (data->power_valid)
+		len += nla_total_size(sizeof(u8));	/* _MODULE_POWER_MODE_POLICY */
+
+	if (data->power_valid && data->power.mode_valid)
+		len += nla_total_size(sizeof(u8));	/* _MODULE_POWER_MODE */
+
+	return len;
+}
+
+static int module_fill_reply(struct sk_buff *skb,
+			     const struct ethnl_req_info *req_base,
+			     const struct ethnl_reply_data *reply_base)
+{
+	const struct module_reply_data *data = MODULE_REPDATA(reply_base);
+
+	if (data->power_valid &&
+	    nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE_POLICY,
+		       data->power.policy))
+		return -EMSGSIZE;
+
+	if (data->power_valid && data->power.mode_valid &&
+	    nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE, data->power.mode))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+const struct ethnl_request_ops ethnl_module_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_MODULE_GET,
+	.reply_cmd		= ETHTOOL_MSG_MODULE_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_MODULE_HEADER,
+	.req_info_size		= sizeof(struct module_req_info),
+	.reply_data_size	= sizeof(struct module_reply_data),
+
+	.prepare_data		= module_prepare_data,
+	.reply_size		= module_reply_size,
+	.fill_reply		= module_fill_reply,
+};
+
+/* MODULE_SET */
+
+const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1] = {
+	[ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+	[ETHTOOL_A_MODULE_POWER_MODE_POLICY] =
+		NLA_POLICY_MAX(NLA_U8, ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO),
+};
+
+static int module_set_power_mode(struct net_device *dev, struct nlattr **tb,
+				 bool *p_mod, struct netlink_ext_ack *extack)
+{
+	struct ethtool_module_power_mode_params power = {};
+	struct ethtool_module_power_mode_params power_new;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	int ret;
+
+	if (!tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY])
+		return 0;
+
+	if (!ops->get_module_power_mode || !ops->set_module_power_mode) {
+		NL_SET_ERR_MSG_ATTR(extack,
+				    tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY],
+				    "Setting power mode policy is not supported by this device");
+		return -EOPNOTSUPP;
+	}
+
+	power_new.policy = nla_get_u8(tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]);
+	ret = ops->get_module_power_mode(dev, &power, extack);
+	if (ret < 0)
+		return ret;
+	*p_mod = power_new.policy != power.policy;
+
+	return ops->set_module_power_mode(dev, &power_new, extack);
+}
+
+int ethnl_set_module(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
+	struct net_device *dev;
+	bool mod = false;
+	int ret;
+
+	ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_MODULE_HEADER],
+					 genl_info_net(info), info->extack,
+					 true);
+	if (ret < 0)
+		return ret;
+	dev = req_info.dev;
+
+	rtnl_lock();
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		goto out_rtnl;
+
+	ret = module_set_power_mode(dev, tb, &mod, info->extack);
+	if (ret < 0)
+		goto out_ops;
+
+	if (!mod)
+		goto out_ops;
+
+	ethtool_notify(dev, ETHTOOL_MSG_MODULE_NTF, NULL);
+
+out_ops:
+	ethnl_ops_complete(dev);
+out_rtnl:
+	rtnl_unlock();
+	dev_put(dev);
+	return ret;
+}

@@ -282,6 +282,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_MODULE_EEPROM_GET]	= &ethnl_module_eeprom_request_ops,
 	[ETHTOOL_MSG_STATS_GET]		= &ethnl_stats_request_ops,
 	[ETHTOOL_MSG_PHC_VCLOCKS_GET]	= &ethnl_phc_vclocks_request_ops,
+	[ETHTOOL_MSG_MODULE_GET]	= &ethnl_module_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)

@@ -593,6 +594,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = {
 	[ETHTOOL_MSG_PAUSE_NTF]		= &ethnl_pause_request_ops,
 	[ETHTOOL_MSG_EEE_NTF]		= &ethnl_eee_request_ops,
 	[ETHTOOL_MSG_FEC_NTF]		= &ethnl_fec_request_ops,
+	[ETHTOOL_MSG_MODULE_NTF]	= &ethnl_module_request_ops,
 };
 
 /* default notification handler */

@@ -686,6 +688,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = {
 	[ETHTOOL_MSG_PAUSE_NTF]		= ethnl_default_notify,
 	[ETHTOOL_MSG_EEE_NTF]		= ethnl_default_notify,
 	[ETHTOOL_MSG_FEC_NTF]		= ethnl_default_notify,
+	[ETHTOOL_MSG_MODULE_NTF]	= ethnl_default_notify,
 };
 
 void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data)

@@ -999,6 +1002,22 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_phc_vclocks_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_MODULE_GET,
+		.doit	= ethnl_default_doit,
+		.start	= ethnl_default_start,
+		.dumpit	= ethnl_default_dumpit,
+		.done	= ethnl_default_done,
+		.policy = ethnl_module_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_module_get_policy) - 1,
+	},
+	{
+		.cmd	= ETHTOOL_MSG_MODULE_SET,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= ethnl_set_module,
+		.policy = ethnl_module_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_module_set_policy) - 1,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {

@@ -337,6 +337,7 @@ extern const struct ethnl_request_ops ethnl_fec_request_ops;
 extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops;
 extern const struct ethnl_request_ops ethnl_stats_request_ops;
 extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops;
+extern const struct ethnl_request_ops ethnl_module_request_ops;
 
 extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
 extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];

@@ -373,6 +374,8 @@ extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1];
 extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1];
 extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1];
 extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1];
+extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1];
+extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1];
 
 int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info);
 int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info);

@@ -391,6 +394,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_start(struct netlink_callback *cb);
 int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int ethnl_set_fec(struct sk_buff *skb, struct genl_info *info);
+int ethnl_set_module(struct sk_buff *skb, struct genl_info *info);
 
 extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN];
 extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN];

@@ -5946,6 +5946,49 @@ static inline void mlxsw_reg_pddr_pack(char *payload, u8 local_port,
 	mlxsw_reg_pddr_page_select_set(payload, page_select);
 }
 
+/* PMMP - Port Module Memory Map Properties Register
+ * -------------------------------------------------
+ * The PMMP register allows to override the module memory map advertisement.
+ * The register can only be set when the module is disabled by PMAOS register.
+ */
+#define MLXSW_REG_PMMP_ID 0x5044
+#define MLXSW_REG_PMMP_LEN 0x2C
+
+MLXSW_REG_DEFINE(pmmp, MLXSW_REG_PMMP_ID, MLXSW_REG_PMMP_LEN);
+
+/* reg_pmmp_module
+ * Module number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pmmp, module, 0x00, 16, 8);
+
+/* reg_pmmp_eeprom_override_mask
+ * Write mask bit (negative polarity).
+ * 0 - Allow write
+ * 1 - Ignore write
+ * On write, indicates which of the bits from eeprom_override field are
+ * updated.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, pmmp, eeprom_override_mask, 0x04, 16, 16);
+
+enum {
+	/* Set module to low power mode */
+	MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK = BIT(8),
+};
+
+/* reg_pmmp_eeprom_override
+ * Override / ignore EEPROM advertisement properties bitmask
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pmmp, eeprom_override, 0x04, 0, 16);
+
+static inline void mlxsw_reg_pmmp_pack(char *payload, u8 module)
+{
+	MLXSW_REG_ZERO(pmmp, payload);
+	mlxsw_reg_pmmp_module_set(payload, module);
+}
+
 /* PLLP - Port Local port to Label Port mapping Register
  * -----------------------------------------------------
  * The PLLP register returns the mapping from Local Port into Label Port.

@@ -12273,6 +12316,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(pmtdb),
 	MLXSW_REG(pmpe),
 	MLXSW_REG(pddr),
+	MLXSW_REG(pmmp),
 	MLXSW_REG(pllp),
 	MLXSW_REG(htgt),
 	MLXSW_REG(hpkt),

@@ -10321,6 +10321,39 @@ static inline void mlxsw_reg_mlcr_pack(char *payload, u8 local_port,
 					   MLXSW_REG_MLCR_DURATION_MAX : 0);
 }
 
+/* MCION - Management Cable IO and Notifications Register
+ * ------------------------------------------------------
+ * The MCION register is used to query transceiver modules' IO pins and other
+ * notifications.
+ */
+#define MLXSW_REG_MCION_ID 0x9052
+#define MLXSW_REG_MCION_LEN 0x18
+
+MLXSW_REG_DEFINE(mcion, MLXSW_REG_MCION_ID, MLXSW_REG_MCION_LEN);
+
+/* reg_mcion_module
+ * Module number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mcion, module, 0x00, 16, 8);
+
+enum {
+	MLXSW_REG_MCION_MODULE_STATUS_BITS_PRESENT_MASK = BIT(0),
+	MLXSW_REG_MCION_MODULE_STATUS_BITS_LOW_POWER_MASK = BIT(8),
+};
+
+/* reg_mcion_module_status_bits
+ * Module IO status as defined by SFF.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mcion, module_status_bits, 0x04, 0, 16);
+
+static inline void mlxsw_reg_mcion_pack(char *payload, u8 module)
+{
+	MLXSW_REG_ZERO(mcion, payload);
+	mlxsw_reg_mcion_module_set(payload, module);
+}
+
 /* MTPPS - Management Pulse Per Second Register
  * --------------------------------------------
  * This register provides the device PPS capabilities, configure the PPS in and

@@ -12364,6 +12397,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mgir),
 	MLXSW_REG(mrsr),
 	MLXSW_REG(mlcr),
+	MLXSW_REG(mcion),
 	MLXSW_REG(mtpps),
 	MLXSW_REG(mtutc),
 	MLXSW_REG(mpsc),

@@ -17,6 +17,7 @@ struct mlxsw_env_module_info {
 	bool is_overheat;
 	int num_ports_mapped;
 	int num_ports_up;
+	enum ethtool_module_power_mode_policy power_mode_policy;
 };
 
 struct mlxsw_env {

@@ -445,6 +446,153 @@ int mlxsw_env_reset_module(struct net_device *netdev,
 }
 EXPORT_SYMBOL(mlxsw_env_reset_module);
 
+int
+mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
+				struct ethtool_module_power_mode_params *params,
+				struct netlink_ext_ack *extack)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	char mcion_pl[MLXSW_REG_MCION_LEN];
+	u32 status_bits;
+	int err;
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+
+	params->policy = mlxsw_env->module_info[module].power_mode_policy;
+
+	mlxsw_reg_mcion_pack(mcion_pl, module);
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcion), mcion_pl);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to retrieve module's power mode");
+		goto out;
+	}
+
+	status_bits = mlxsw_reg_mcion_module_status_bits_get(mcion_pl);
+	if (!(status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_PRESENT_MASK))
+		goto out;
+
+	if (status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_LOW_POWER_MASK)
+		params->mode = ETHTOOL_MODULE_POWER_MODE_LOW;
+	else
+		params->mode = ETHTOOL_MODULE_POWER_MODE_HIGH;
+
+	params->mode_valid = true;
+
+out:
+	mutex_unlock(&mlxsw_env->module_info_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlxsw_env_get_module_power_mode);
+
+static int mlxsw_env_module_enable_set(struct mlxsw_core *mlxsw_core,
+				       u8 module, bool enable)
+{
+	enum mlxsw_reg_pmaos_admin_status admin_status;
+	char pmaos_pl[MLXSW_REG_PMAOS_LEN];
+
+	mlxsw_reg_pmaos_pack(pmaos_pl, module);
+	admin_status = enable ? MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED :
+				MLXSW_REG_PMAOS_ADMIN_STATUS_DISABLED;
+	mlxsw_reg_pmaos_admin_status_set(pmaos_pl, admin_status);
+	mlxsw_reg_pmaos_ase_set(pmaos_pl, true);
+
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
+}
+
+static int mlxsw_env_module_low_power_set(struct mlxsw_core *mlxsw_core,
+					  u8 module, bool low_power)
+{
+	u16 eeprom_override_mask, eeprom_override;
+	char pmmp_pl[MLXSW_REG_PMMP_LEN];
+
+	mlxsw_reg_pmmp_pack(pmmp_pl, module);
+	/* Mask all the bits except low power mode. */
+	eeprom_override_mask = ~MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK;
+	mlxsw_reg_pmmp_eeprom_override_mask_set(pmmp_pl, eeprom_override_mask);
+	eeprom_override = low_power ? MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK :
+				      0;
+	mlxsw_reg_pmmp_eeprom_override_set(pmmp_pl, eeprom_override);
+
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmmp), pmmp_pl);
+}
+
+static int __mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core,
+					     u8 module, bool low_power,
+					     struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = mlxsw_env_module_enable_set(mlxsw_core, module, false);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to disable module");
+		return err;
+	}
+
+	err = mlxsw_env_module_low_power_set(mlxsw_core, module, low_power);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set module's power mode");
+		goto err_module_low_power_set;
+	}
+
+	err = mlxsw_env_module_enable_set(mlxsw_core, module, true);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to enable module");
+		goto err_module_enable_set;
+	}
+
+	return 0;
+
+err_module_enable_set:
+	mlxsw_env_module_low_power_set(mlxsw_core, module, !low_power);
+err_module_low_power_set:
+	mlxsw_env_module_enable_set(mlxsw_core, module, true);
+	return err;
+}
+
+int
+mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
+				enum ethtool_module_power_mode_policy policy,
+				struct netlink_ext_ack *extack)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	bool low_power;
+	int err = 0;
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	if (policy != ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH &&
+	    policy != ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported power mode policy");
+		return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&mlxsw_env->module_info_lock);
+
+	if (mlxsw_env->module_info[module].power_mode_policy == policy)
+		goto out;
+
+	/* If any ports are up, we are already in high power mode. */
+	if (mlxsw_env->module_info[module].num_ports_up)
+		goto out_set_policy;
+
+	low_power = policy == ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO;
+	err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, low_power,
+						extack);
+	if (err)
+		goto out;
+
+out_set_policy:
+	mlxsw_env->module_info[module].power_mode_policy = policy;
+out:
+	mutex_unlock(&mlxsw_env->module_info_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlxsw_env_set_module_power_mode);
+
 static int mlxsw_env_module_has_temp_sensor(struct mlxsw_core *mlxsw_core,
 					    u8 module,
 					    bool *p_has_temp_sensor)

@@ -794,15 +942,33 @@ EXPORT_SYMBOL(mlxsw_env_module_port_unmap);
 int mlxsw_env_module_port_up(struct mlxsw_core *mlxsw_core, u8 module)
 {
 	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+	int err = 0;
 
 	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
 		return -EINVAL;
 
 	mutex_lock(&mlxsw_env->module_info_lock);
+
+	if (mlxsw_env->module_info[module].power_mode_policy !=
+	    ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO)
+		goto out_inc;
+
+	if (mlxsw_env->module_info[module].num_ports_up != 0)
+		goto out_inc;
+
+	/* Transition to high power mode following first port using the module
+	 * being put administratively up.
+	 */
+	err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, false,
+						NULL);
+	if (err)
+		goto out_unlock;
+
+out_inc:
 	mlxsw_env->module_info[module].num_ports_up++;
+out_unlock:
 	mutex_unlock(&mlxsw_env->module_info_lock);
-
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL(mlxsw_env_module_port_up);
 

@@ -814,7 +980,22 @@ void mlxsw_env_module_port_down(struct mlxsw_core *mlxsw_core, u8 module)
 		return;
 
 	mutex_lock(&mlxsw_env->module_info_lock);
+
 	mlxsw_env->module_info[module].num_ports_up--;
+
+	if (mlxsw_env->module_info[module].power_mode_policy !=
+	    ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO)
+		goto out_unlock;
+
+	if (mlxsw_env->module_info[module].num_ports_up != 0)
+		goto out_unlock;
+
+	/* Transition to low power mode following last port using the module
+	 * being put administratively down.
+	 */
+	__mlxsw_env_set_module_power_mode(mlxsw_core, module, true, NULL);
+
+out_unlock:
 	mutex_unlock(&mlxsw_env->module_info_lock);
 }
 EXPORT_SYMBOL(mlxsw_env_module_port_down);

@@ -824,7 +1005,7 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env)
 	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
 	struct mlxsw_env *env;
 	u8 module_count;
-	int err;
+	int i, err;
 
 	mlxsw_reg_mgpir_pack(mgpir_pl);
 	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgpir), mgpir_pl);

@@ -837,6 +1018,13 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env)
 	if (!env)
 		return -ENOMEM;
 
+	/* Firmware defaults to high power mode policy where modules are
+	 * transitioned to high power mode following plug-in.
+	 */
+	for (i = 0; i < module_count; i++)
+		env->module_info[i].power_mode_policy =
+			ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH;
+
 	mutex_init(&env->module_info_lock);
 	env->core = mlxsw_core;
 	env->module_count = module_count;

@@ -28,6 +28,16 @@ int mlxsw_env_reset_module(struct net_device *netdev,
 			   struct mlxsw_core *mlxsw_core, u8 module,
 			   u32 *flags);
 
+int
+mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
+				struct ethtool_module_power_mode_params *params,
+				struct netlink_ext_ack *extack);
+
+int
+mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
+				enum ethtool_module_power_mode_policy policy,
+				struct netlink_ext_ack *extack);
+
 int
 mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module,
 				      u64 *p_counter);

@@ -145,12 +145,38 @@ static int mlxsw_m_reset(struct net_device *netdev, u32 *flags)
 				      flags);
 }
 
+static int
+mlxsw_m_get_module_power_mode(struct net_device *netdev,
+			      struct ethtool_module_power_mode_params *params,
+			      struct netlink_ext_ack *extack)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+
+	return mlxsw_env_get_module_power_mode(core, mlxsw_m_port->module,
+					       params, extack);
+}
+
+static int
+mlxsw_m_set_module_power_mode(struct net_device *netdev,
+			      const struct ethtool_module_power_mode_params *params,
+			      struct netlink_ext_ack *extack)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+
+	return mlxsw_env_set_module_power_mode(core, mlxsw_m_port->module,
+					       params->policy, extack);
+}
+
 static const struct ethtool_ops mlxsw_m_port_ethtool_ops = {
 	.get_drvinfo		= mlxsw_m_module_get_drvinfo,
 	.get_module_info	= mlxsw_m_get_module_info,
 	.get_module_eeprom	= mlxsw_m_get_module_eeprom,
 	.get_module_eeprom_by_page = mlxsw_m_get_module_eeprom_by_page,
 	.reset			= mlxsw_m_reset,
+	.get_module_power_mode	= mlxsw_m_get_module_power_mode,
+	.set_module_power_mode	= mlxsw_m_set_module_power_mode,
 };
 
 static int

@@ -1206,6 +1206,32 @@ static int mlxsw_sp_reset(struct net_device *dev, u32 *flags)
 	return mlxsw_env_reset_module(dev, mlxsw_sp->core, module, flags);
 }
 
+static int
+mlxsw_sp_get_module_power_mode(struct net_device *dev,
+			       struct ethtool_module_power_mode_params *params,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 module = mlxsw_sp_port->mapping.module;
+
+	return mlxsw_env_get_module_power_mode(mlxsw_sp->core, module, params,
+					       extack);
+}
+
+static int
+mlxsw_sp_set_module_power_mode(struct net_device *dev,
+			       const struct ethtool_module_power_mode_params *params,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 module = mlxsw_sp_port->mapping.module;
+
+	return mlxsw_env_set_module_power_mode(mlxsw_sp->core, module,
+					       params->policy, extack);
+}
+
 const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
 	.cap_link_lanes_supported	= true,
 	.get_drvinfo			= mlxsw_sp_port_get_drvinfo,

@@ -1228,6 +1254,8 @@ const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
 	.get_eth_ctrl_stats		= mlxsw_sp_get_eth_ctrl_stats,
 	.get_rmon_stats			= mlxsw_sp_get_rmon_stats,
 	.reset				= mlxsw_sp_reset,
+	.get_module_power_mode		= mlxsw_sp_get_module_power_mode,
+	.set_module_power_mode		= mlxsw_sp_set_module_power_mode,
 };
 
 struct mlxsw_sp1_port_link_mode {

@@ -523,6 +523,8 @@ Link extended states:
                                                         power required from cable or module
 
   ``ETHTOOL_LINK_EXT_STATE_OVERHEAT``                   The module is overheated
+
+  ``ETHTOOL_LINK_EXT_STATE_MODULE``                     Transceiver module issue
   ================================================      ============================================
 
 Link extended substates:

@@ -616,6 +618,16 @@ Link extended substates:
   ``ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE``   Cable test failure
   ===================================================   ============================================
 
+  Transceiver module issue substates:
+
+  ===================================================   ============================================
+  ``ETHTOOL_LINK_EXT_SUBSTATE_MODULE_LOW_POWER_MODE``   The transceiver module is in low power mode
+
+  ``ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY``   The CMIS Module State Machine did not reach
+                                                        the ModuleReady state. For example, if the
+                                                        module is stuck at ModuleFault state
+  ===================================================   ============================================
+
 DEBUG_GET
 =========
 

@@ -93,6 +93,7 @@ struct ethtool_link_ext_state_info {
 		enum ethtool_link_ext_substate_link_logical_mismatch link_logical_mismatch;
 		enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity;
 		enum ethtool_link_ext_substate_cable_issue cable_issue;
+		enum ethtool_link_ext_substate_module module;
 		u8 __link_ext_substate;
 	};
 };

@@ -603,6 +603,7 @@ enum ethtool_link_ext_state {
 	ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE,
 	ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED,
 	ETHTOOL_LINK_EXT_STATE_OVERHEAT,
+	ETHTOOL_LINK_EXT_STATE_MODULE,
 };
 
 /* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */

@@ -649,6 +650,12 @@ enum ethtool_link_ext_substate_cable_issue {
 	ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,
 };
 
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */
+enum ethtool_link_ext_substate_module {
+	ETHTOOL_LINK_EXT_SUBSTATE_MODULE_LOW_POWER_MODE = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY,
+};
+
 #define ETH_GSTRING_LEN		32
 
 /**

@@ -96,6 +96,11 @@ mlxsw_sp_link_ext_state_opcode_map[] = {
 	{1032, ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, 0},
 
 	{1030, ETHTOOL_LINK_EXT_STATE_OVERHEAT, 0},
+
+	{1042, ETHTOOL_LINK_EXT_STATE_MODULE,
+	 ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY},
+	{2048, ETHTOOL_LINK_EXT_STATE_MODULE,
+	 ETHTOOL_LINK_EXT_SUBSTATE_MODULE_LOW_POWER_MODE},
 };
 
 static void

@@ -124,6 +129,10 @@ mlxsw_sp_port_set_link_ext_state(struct mlxsw_sp_ethtool_link_ext_state_opcode_m
 		link_ext_state_info->cable_issue =
 			link_ext_state_mapping.link_ext_substate;
 		break;
+	case ETHTOOL_LINK_EXT_STATE_MODULE:
+		link_ext_state_info->module =
+			link_ext_state_mapping.link_ext_substate;
+		break;
 	default:
 		break;
 	}

@@ -131,19 +140,46 @@ mlxsw_sp_port_set_link_ext_state(struct mlxsw_sp_ethtool_link_ext_state_opcode_m
 	link_ext_state_info->link_ext_state = link_ext_state_mapping.link_ext_state;
 }
 
+static int
+mlxsw_sp_port_status_opcode_drv_get(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u32 *p_status_opcode)
+{
+	struct ethtool_module_power_mode_params params = {};
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 module = mlxsw_sp_port->mapping.module;
+	int err;
+
+	*p_status_opcode = 0;
+
+	err = mlxsw_env_get_module_power_mode(mlxsw_sp->core, module, &params,
+					      NULL);
+	if (err)
+		return err;
+	if (params.mode_valid && params.mode == ETHTOOL_MODULE_POWER_MODE_LOW)
+		*p_status_opcode = 2048;
+
+	return 0;
+}
+
 static int
 mlxsw_sp_port_get_link_ext_state(struct net_device *dev,
 				 struct ethtool_link_ext_state_info *link_ext_state_info)
 {
 	struct mlxsw_sp_ethtool_link_ext_state_opcode_mapping link_ext_state_mapping;
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	u32 status_opcode, status_opcode_drv;
 	char pddr_pl[MLXSW_REG_PDDR_LEN];
 	int opcode, err, i;
-	u32 status_opcode;
 
 	if (netif_carrier_ok(dev))
 		return -ENODATA;
 
+	/* Opcodes 2048-3072 are reserved for driver use. */
+	err = mlxsw_sp_port_status_opcode_drv_get(mlxsw_sp_port,
+						  &status_opcode_drv);
+	if (err)
+		return err;
+
 	mlxsw_reg_pddr_pack(pddr_pl, mlxsw_sp_port->local_port,
 			    MLXSW_REG_PDDR_PAGE_SELECT_TROUBLESHOOTING_INFO);
 

@@ -156,9 +192,14 @@ mlxsw_sp_port_get_link_ext_state(struct net_device *dev,
 		return err;
 
 	status_opcode = mlxsw_reg_pddr_trblsh_status_opcode_get(pddr_pl);
-	if (!status_opcode)
+	if (!status_opcode && !status_opcode_drv)
 		return -ENODATA;
 
+	/* Allow driver-detected issues to take precedence, as it is likely
+	 * that they are more meaningful to user space.
+	 */
+	status_opcode = status_opcode_drv ? status_opcode_drv : status_opcode;
+
 	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_link_ext_state_opcode_map); i++) {
 		link_ext_state_mapping = mlxsw_sp_link_ext_state_opcode_map[i];
 		if (link_ext_state_mapping.status_opcode == status_opcode) {