Merge tag 'v5.12-rc7' into driver-core-next

We need the driver core fix in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

18 files changed, 173 insertions, 71 deletions

diff --git a/include/dt-bindings/bus/moxtet.h b/include/dt-bindings/bus/moxtet.h
index dc9345440ebe..10528de7b3ef 100644
--- a/include/dt-bindings/bus/moxtet.h
+++ b/include/dt-bindings/bus/moxtet.h
@@ -2,7 +2,7 @@
 /*
  * Constant for device tree bindings for Turris Mox module configuration bus
  *
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
  */
 
 #ifndef _DT_BINDINGS_BUS_MOXTET_H
diff --git a/include/linux/armada-37xx-rwtm-mailbox.h b/include/linux/armada-37xx-rwtm-mailbox.h
index 57bb54f6767a..ef4bd705eb65 100644
--- a/include/linux/armada-37xx-rwtm-mailbox.h
+++ b/include/linux/armada-37xx-rwtm-mailbox.h
@@ -2,7 +2,7 @@
 /*
  * rWTM BIU Mailbox driver for Armada 37xx
  *
- * Author: Marek Behun <marek.behun@nic.cz>
+ * Author: Marek Behún <kabel@kernel.org>
  */
 
 #ifndef _LINUX_ARMADA_37XX_RWTM_MAILBOX_H_
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 40bad71865ea..532bcbfc4716 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -476,7 +476,6 @@ struct virtchnl_rss_key {
 	u16 vsi_id;
 	u16 key_len;
 	u8 key[1];         /* RSS hash key, packed bytes */
-	u8 pad[1];
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key);
@@ -485,7 +484,6 @@ struct virtchnl_rss_lut {
 	u16 vsi_id;
 	u16 lut_entries;
 	u8 lut[1];        /* RSS lookup table */
-	u8 pad[1];
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3625f019767d..fdac0534ce79 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_local_storage;
 struct bpf_local_storage_map;
 struct kobject;
 struct mem_cgroup;
+struct module;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -623,6 +624,7 @@ struct bpf_trampoline {
 	/* Executable image of trampoline */
 	struct bpf_tramp_image *cur_image;
 	u64 selector;
+	struct module *mod;
 };
 
 struct bpf_attach_target_info {
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index ec4cd3921c67..cdca84e6dd6b 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -87,9 +87,7 @@ u32 ethtool_op_get_link(struct net_device *dev);
 int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti);
 
 
-/**
- * struct ethtool_link_ext_state_info - link extended state and substate.
- */
+/* Link extended state and substate. */
 struct ethtool_link_ext_state_info {
 	enum ethtool_link_ext_state link_ext_state;
 	union {
@@ -129,7 +127,6 @@ struct ethtool_link_ksettings {
 		__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising);
 	} link_modes;
 	u32	lanes;
-	enum ethtool_link_mode_bit_indices link_mode;
 };
 
 /**
@@ -292,6 +289,9 @@ struct ethtool_pause_stats {
  *	do not attach ext_substate attribute to netlink message). If link_ext_state
  *	and link_ext_substate are unknown, return -ENODATA. If not implemented,
  *	link_ext_state and link_ext_substate will not be sent to userspace.
+ * @get_eeprom_len: Read range of EEPROM addresses for validation of
+ *	@get_eeprom and @set_eeprom requests.
+ *	Returns 0 if device does not support EEPROM access.
  * @get_eeprom: Read data from the device EEPROM.
  *	Should fill in the magic field.  Don't need to check len for zero
  *	or wraparound.  Fill in the data argument with the eeprom values
@@ -384,6 +384,8 @@ struct ethtool_pause_stats {
  * @get_module_eeprom: Get the eeprom information from the plug-in module
  * @get_eee: Get Energy-Efficient (EEE) supported and status.
  * @set_eee: Set EEE status (enable/disable) as well as LPI timers.
+ * @get_tunable: Read the value of a driver / device tunable.
+ * @set_tunable: Set the value of a driver / device tunable.
  * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue.
  *	It must check that the given queue number is valid. If neither a RX nor
  *	a TX queue has this number, return -EINVAL. If only a RX queue or a TX
@@ -547,8 +549,8 @@ struct phy_tdr_config;
  * @get_sset_count: Get number of strings that @get_strings will write.
  * @get_strings: Return a set of strings that describe the requested objects
  * @get_stats: Return extended statistics about the PHY device.
- * @start_cable_test - Start a cable test
- * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test
+ * @start_cable_test: Start a cable test
+ * @start_cable_test_tdr: Start a Time Domain Reflectometry cable test
  *
  * All operations are optional (i.e. the function pointer may be set to %NULL)
  * and callers must take this into account. Callers must hold the RTNL lock.
@@ -571,4 +573,12 @@ struct ethtool_phy_ops {
  */
 void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops);
 
+/*
+ * ethtool_params_from_link_mode - Derive link parameters from a given link mode
+ * @link_ksettings: Link parameters to be derived from the link mode
+ * @link_mode: Link mode
+ */
+void
+ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings,
+			      enum ethtool_link_mode_bit_indices link_mode);
 #endif /* _LINUX_ETHTOOL_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index df5d91c8b2d4..9c68b2da14c6 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -437,11 +437,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         reserved_at_60[0x18];
 	u8         log_max_ft_num[0x8];
 
-	u8         reserved_at_80[0x18];
+	u8         reserved_at_80[0x10];
+	u8         log_max_flow_counter[0x8];
 	u8         log_max_destination[0x8];
 
-	u8         log_max_flow_counter[0x8];
-	u8         reserved_at_a8[0x10];
+	u8         reserved_at_a0[0x18];
 	u8         log_max_flow[0x8];
 
 	u8         reserved_at_c0[0x40];
@@ -8835,6 +8835,8 @@ struct mlx5_ifc_pplm_reg_bits {
 
 	u8         fec_override_admin_100g_2x[0x10];
 	u8         fec_override_admin_50g_1x[0x10];
+
+	u8         reserved_at_140[0x140];
 };
 
 struct mlx5_ifc_ppcnt_reg_bits {
@@ -10198,7 +10200,7 @@ struct mlx5_ifc_pbmc_reg_bits {
 
 	struct mlx5_ifc_bufferx_reg_bits buffer[10];
 
-	u8         reserved_at_2e0[0x40];
+	u8         reserved_at_2e0[0x80];
 };
 
 struct mlx5_ifc_qtct_reg_bits {
diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h
index 490db6886dcc..79184948fab4 100644
--- a/include/linux/moxtet.h
+++ b/include/linux/moxtet.h
@@ -2,7 +2,7 @@
 /*
  * Turris Mox module configuration bus driver
  *
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
  */
 
 #ifndef __LINUX_MOXTET_H
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 8edbbf5f2f93..822c048934e3 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -349,8 +349,13 @@ static inline void sk_psock_update_proto(struct sock *sk,
 static inline void sk_psock_restore_proto(struct sock *sk,
 					  struct sk_psock *psock)
 {
-	sk->sk_prot->unhash = psock->saved_unhash;
 	if (inet_csk_has_ulp(sk)) {
+		/* TLS does not have an unhash proto in SW cases, but we need
+		 * to ensure we stop using the sock_map unhash routine because
+		 * the associated psock is being removed. So use the original
+		 * unhash handler.
+		 */
+		WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
 		tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
 	} else {
 		sk->sk_write_space = psock->saved_write_space;
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 6b5fcfa1e555..b465f8f3e554 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -62,15 +62,21 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			return -EINVAL;
 	}
 
+	skb_reset_mac_header(skb);
+
 	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
-		u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+		u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
+		u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+		u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
+
+		if (!pskb_may_pull(skb, needed))
+			return -EINVAL;
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
 		p_off = skb_transport_offset(skb) + thlen;
-		if (p_off > skb_headlen(skb))
+		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
@@ -100,14 +106,14 @@ retry:
 			}
 
 			p_off = keys.control.thoff + thlen;
-			if (p_off > skb_headlen(skb) ||
+			if (!pskb_may_pull(skb, p_off) ||
 			    keys.basic.ip_proto != ip_proto)
 				return -EINVAL;
 
 			skb_set_transport_header(skb, keys.control.thoff);
 		} else if (gso_type) {
 			p_off = thlen;
-			if (p_off > skb_headlen(skb))
+			if (!pskb_may_pull(skb, p_off))
 				return -EINVAL;
 		}
 	}
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 2bf3092ae7ec..086b291e9530 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -170,12 +170,7 @@ void tcf_idr_insert_many(struct tc_action *actions[]);
 void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 			struct tc_action **a, int bind);
-int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
-
-static inline int tcf_idr_release(struct tc_action *a, bool bind)
-{
-	return __tcf_idr_release(a, bind, false);
-}
+int tcf_idr_release(struct tc_action *a, bool bind);
 
 int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
 int tcf_unregister_action(struct tc_action_ops *a,
@@ -185,7 +180,7 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 		    int nr_actions, struct tcf_result *res);
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct tc_action *actions[], size_t *attr_size,
+		    struct tc_action *actions[], int init_res[], size_t *attr_size,
 		    bool rtnl_held, struct netlink_ext_ack *extack);
 struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla,
 					 bool rtnl_held,
@@ -193,7 +188,8 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla,
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
-				    struct tc_action_ops *ops, bool rtnl_held,
+				    struct tc_action_ops *a_o, int *init_res,
+				    bool rtnl_held,
 				    struct netlink_ext_ack *extack);
 int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
 		    int ref, bool terse);
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 59f45b1e9dac..e816b6a3ef2b 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -72,7 +72,9 @@ struct netns_xfrm {
 #if IS_ENABLED(CONFIG_IPV6)
 	struct dst_ops		xfrm6_dst_ops;
 #endif
-	spinlock_t xfrm_state_lock;
+	spinlock_t		xfrm_state_lock;
+	seqcount_spinlock_t	xfrm_state_hash_generation;
+
 	spinlock_t xfrm_policy_lock;
 	struct mutex xfrm_cfg_mutex;
 };
diff --git a/include/net/red.h b/include/net/red.h
index 0b39eff1d50a..be11dbd26492 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -171,9 +171,9 @@ static inline void red_set_vars(struct red_vars *v)
 static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog,
 				    u8 Scell_log, u8 *stab)
 {
-	if (fls(qth_min) + Wlog > 32)
+	if (fls(qth_min) + Wlog >= 32)
 		return false;
-	if (fls(qth_max) + Wlog > 32)
+	if (fls(qth_max) + Wlog >= 32)
 		return false;
 	if (Scell_log >= 32)
 		return false;
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 4da61c950e93..479f60ef54c0 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -147,8 +147,8 @@ struct rtnl_af_ops {
 	int			(*validate_link_af)(const struct net_device *dev,
 						    const struct nlattr *attr);
 	int			(*set_link_af)(struct net_device *dev,
-					       const struct nlattr *attr);
-
+					       const struct nlattr *attr,
+					       struct netlink_ext_ack *extack);
 	int			(*fill_stats_af)(struct sk_buff *skb,
 						 const struct net_device *dev);
 	size_t			(*get_stats_af_size)(const struct net_device *dev);
diff --git a/include/net/sock.h b/include/net/sock.h
index 0b6266fd6bf6..8487f58da36d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -934,9 +934,13 @@ static inline void sk_acceptq_added(struct sock *sk)
 	WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1);
 }
 
+/* Note: If you think the test should be:
+ *	return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog);
+ * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.")
+ */
 static inline bool sk_acceptq_is_full(const struct sock *sk)
 {
-	return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog);
+	return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog);
 }
 
 /*
@@ -2221,6 +2225,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
+static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
+{
+	if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
+		skb_orphan(skb);
+		skb->destructor = sock_efree;
+		skb->sk = sk;
+	}
+}
+
 void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 		    unsigned long expires);
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b2a06f10b62c..c58a6d4eb610 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1097,7 +1097,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 		return __xfrm_policy_check(sk, ndir, skb, family);
 
 	return	(!net->xfrm.policy_count[dir] && !secpath_exists(skb)) ||
-		(skb_dst(skb)->flags & DST_NOPOLICY) ||
+		(skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) ||
 		__xfrm_policy_check(sk, ndir, skb, family);
 }
 
@@ -1557,7 +1557,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 int xfrm_trans_queue(struct sk_buff *skb,
 		     int (*finish)(struct net *, struct sock *,
 				   struct sk_buff *));
-int xfrm_output_resume(struct sk_buff *skb, int err);
+int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err);
 int xfrm_output(struct sock *sk, struct sk_buff *skb);
 
 #if IS_ENABLED(CONFIG_NET_PKTGEN)
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index f75238ac6dce..c7535352fef6 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -113,7 +113,7 @@ struct can_frame {
 		 */
 		__u8 len;
 		__u8 can_dlc; /* deprecated */
-	};
+	} __attribute__((packed)); /* disable padding added in some ABIs */
 	__u8 __pad; /* padding */
 	__u8 __res0; /* reserved / padding */
 	__u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index cde753bb2093..5afea692a3f7 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -26,6 +26,14 @@
  * have the same layout for 32-bit and 64-bit userland.
  */
 
+/* Note on reserved space.
+ * Reserved fields must not be accessed directly by user space because
+ * they may be replaced by a different field in the future. They must
+ * be initialized to zero before making the request, e.g. via memset
+ * of the entire structure or implicitly by not being set in a structure
+ * initializer.
+ */
+
 /**
  * struct ethtool_cmd - DEPRECATED, link control and status
  * This structure is DEPRECATED, please use struct ethtool_link_settings.
@@ -67,6 +75,7 @@
  *	and other link features that the link partner advertised
  *	through autonegotiation; 0 if unknown or not applicable.
  *	Read-only.
+ * @reserved: Reserved for future use; see the note on reserved space.
  *
  * The link speed in Mbps is split between @speed and @speed_hi.  Use
  * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to
@@ -155,6 +164,7 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep)
  * @bus_info: Device bus address.  This should match the dev_name()
  *	string for the underlying bus device, if there is one.  May be
  *	an empty string.
+ * @reserved2: Reserved for future use; see the note on reserved space.
  * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
  *	%ETHTOOL_SPFLAGS commands; also the number of strings in the
  *	%ETH_SS_PRIV_FLAGS set
@@ -356,6 +366,7 @@ struct ethtool_eeprom {
  * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting
  *	its tx lpi (after reaching 'idle' state). Effective only when eee
  *	was negotiated and tx_lpi_enabled was set.
+ * @reserved: Reserved for future use; see the note on reserved space.
  */
 struct ethtool_eee {
 	__u32	cmd;
@@ -374,6 +385,7 @@ struct ethtool_eee {
  * @cmd: %ETHTOOL_GMODULEINFO
  * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx
  * @eeprom_len: Length of the eeprom
+ * @reserved: Reserved for future use; see the note on reserved space.
  *
  * This structure is used to return the information to
  * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM.
@@ -579,9 +591,7 @@ struct ethtool_pauseparam {
 	__u32	tx_pause;
 };
 
-/**
- * enum ethtool_link_ext_state - link extended state
- */
+/* Link extended state */
 enum ethtool_link_ext_state {
 	ETHTOOL_LINK_EXT_STATE_AUTONEG,
 	ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
@@ -595,10 +605,7 @@ enum ethtool_link_ext_state {
 	ETHTOOL_LINK_EXT_STATE_OVERHEAT,
 };
 
-/**
- * enum ethtool_link_ext_substate_autoneg - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_AUTONEG.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */
 enum ethtool_link_ext_substate_autoneg {
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED,
@@ -608,9 +615,7 @@ enum ethtool_link_ext_substate_autoneg {
 	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD,
 };
 
-/**
- * enum ethtool_link_ext_substate_link_training - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
  */
 enum ethtool_link_ext_substate_link_training {
 	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1,
@@ -619,9 +624,7 @@ enum ethtool_link_ext_substate_link_training {
 	ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT,
 };
 
-/**
- * enum ethtool_link_ext_substate_logical_mismatch - more information in addition
- * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
  */
 enum ethtool_link_ext_substate_link_logical_mismatch {
 	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1,
@@ -631,19 +634,14 @@ enum ethtool_link_ext_substate_link_logical_mismatch {
 	ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED,
 };
 
-/**
- * enum ethtool_link_ext_substate_bad_signal_integrity - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
  */
 enum ethtool_link_ext_substate_bad_signal_integrity {
 	ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE,
 };
 
-/**
- * enum ethtool_link_ext_substate_cable_issue - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */
 enum ethtool_link_ext_substate_cable_issue {
 	ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1,
 	ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,
@@ -661,6 +659,7 @@ enum ethtool_link_ext_substate_cable_issue {
  *	now deprecated
  * @ETH_SS_FEATURES: Device feature names
  * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
+ * @ETH_SS_TUNABLES: tunable names
  * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS
  * @ETH_SS_PHY_TUNABLES: PHY tunable names
  * @ETH_SS_LINK_MODES: link mode names
@@ -670,6 +669,8 @@ enum ethtool_link_ext_substate_cable_issue {
  * @ETH_SS_TS_TX_TYPES: timestamping Tx types
  * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters
  * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types
+ *
+ * @ETH_SS_COUNT: number of defined string sets
  */
 enum ethtool_stringset {
 	ETH_SS_TEST		= 0,
@@ -715,6 +716,7 @@ struct ethtool_gstrings {
 /**
  * struct ethtool_sset_info - string set information
  * @cmd: Command number = %ETHTOOL_GSSET_INFO
+ * @reserved: Reserved for future use; see the note on reserved space.
  * @sset_mask: On entry, a bitmask of string sets to query, with bits
  *	numbered according to &enum ethtool_stringset.  On return, a
  *	bitmask of those string sets queried that are supported.
@@ -759,6 +761,7 @@ enum ethtool_test_flags {
  * @flags: A bitmask of flags from &enum ethtool_test_flags.  Some
  *	flags may be set by the user on entry; others may be set by
  *	the driver on return.
+ * @reserved: Reserved for future use; see the note on reserved space.
  * @len: On return, the number of test results
  * @data: Array of test results
  *
@@ -959,6 +962,7 @@ union ethtool_flow_union {
  * @vlan_etype: VLAN EtherType
  * @vlan_tci: VLAN tag control information
  * @data: user defined data
+ * @padding: Reserved for future use; see the note on reserved space.
  *
  * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT
  * is set in &struct ethtool_rx_flow_spec @flow_type.
@@ -1134,7 +1138,8 @@ struct ethtool_rxfh_indir {
  *	hardware hash key.
  * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
  *	Valid values are one of the %ETH_RSS_HASH_*.
- * @rsvd:	Reserved for future extensions.
+ * @rsvd8: Reserved for future use; see the note on reserved space.
+ * @rsvd32: Reserved for future use; see the note on reserved space.
  * @rss_config: RX ring/queue index for each hash value i.e., indirection table
  *	of @indir_size __u32 elements, followed by hash key of @key_size
  *	bytes.
@@ -1302,7 +1307,9 @@ struct ethtool_sfeatures {
  * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
  * @phc_index: device index of the associated PHC, or -1 if there is none
  * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
+ * @tx_reserved: Reserved for future use; see the note on reserved space.
  * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
+ * @rx_reserved: Reserved for future use; see the note on reserved space.
  *
  * The bits in the 'tx_types' and 'rx_filters' fields correspond to
  * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values,
@@ -1958,6 +1965,11 @@ enum ethtool_reset_flags {
  *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  * @transceiver: Used to distinguish different possible PHY types,
  *	reported consistently by PHYLIB.  Read-only.
+ * @master_slave_cfg: Master/slave port mode.
+ * @master_slave_state: Master/slave port state.
+ * @reserved: Reserved for future use; see the note on reserved space.
+ * @reserved1: Reserved for future use; see the note on reserved space.
+ * @link_mode_masks: Variable length bitmaps.
  *
  * If autonegotiation is disabled, the speed and @duplex represent the
  * fixed link mode and are writable if the driver supports multiple
diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h
index 03e8af87b364..9b77cfc42efa 100644
--- a/include/uapi/linux/rfkill.h
+++ b/include/uapi/linux/rfkill.h
@@ -86,34 +86,90 @@ enum rfkill_hard_block_reasons {
  * @op: operation code
  * @hard: hard state (0/1)
  * @soft: soft state (0/1)
+ *
+ * Structure used for userspace communication on /dev/rfkill,
+ * used for events from the kernel and control to the kernel.
+ */
+struct rfkill_event {
+	__u32 idx;
+	__u8  type;
+	__u8  op;
+	__u8  soft;
+	__u8  hard;
+} __attribute__((packed));
+
+/**
+ * struct rfkill_event_ext - events for userspace on /dev/rfkill
+ * @idx: index of dev rfkill
+ * @type: type of the rfkill struct
+ * @op: operation code
+ * @hard: hard state (0/1)
+ * @soft: soft state (0/1)
  * @hard_block_reasons: valid if hard is set. One or several reasons from
  *	&enum rfkill_hard_block_reasons.
  *
  * Structure used for userspace communication on /dev/rfkill,
  * used for events from the kernel and control to the kernel.
+ *
+ * See the extensibility docs below.
  */
-struct rfkill_event {
+struct rfkill_event_ext {
 	__u32 idx;
 	__u8  type;
 	__u8  op;
 	__u8  soft;
 	__u8  hard;
+
+	/*
+	 * older kernels will accept/send only up to this point,
+	 * and if extended further up to any chunk marked below
+	 */
+
 	__u8  hard_block_reasons;
 } __attribute__((packed));
 
-/*
- * We are planning to be backward and forward compatible with changes
- * to the event struct, by adding new, optional, members at the end.
- * When reading an event (whether the kernel from userspace or vice
- * versa) we need to accept anything that's at least as large as the
- * version 1 event size, but might be able to accept other sizes in
- * the future.
+/**
+ * DOC: Extensibility
+ *
+ * Originally, we had planned to allow backward and forward compatible
+ * changes by just adding fields at the end of the structure that are
+ * then not reported on older kernels on read(), and not written to by
+ * older kernels on write(), with the kernel reporting the size it did
+ * accept as the result.
+ *
+ * This would have allowed userspace to detect on read() and write()
+ * which kernel structure version it was dealing with, and if was just
+ * recompiled it would have gotten the new fields, but obviously not
+ * accessed them, but things should've continued to work.
+ *
+ * Unfortunately, while actually exercising this mechanism to add the
+ * hard block reasons field, we found that userspace (notably systemd)
+ * did all kinds of fun things not in line with this scheme:
+ *
+ * 1. treat the (expected) short writes as an error;
+ * 2. ask to read sizeof(struct rfkill_event) but then compare the
+ *    actual return value to RFKILL_EVENT_SIZE_V1 and treat any
+ *    mismatch as an error.
+ *
+ * As a consequence, just recompiling with a new struct version caused
+ * things to no longer work correctly on old and new kernels.
+ *
+ * Hence, we've rolled back &struct rfkill_event to the original version
+ * and added &struct rfkill_event_ext. This effectively reverts to the
+ * old behaviour for all userspace, unless it explicitly opts in to the
+ * rules outlined here by using the new &struct rfkill_event_ext.
+ *
+ * Userspace using &struct rfkill_event_ext must adhere to the following
+ * rules
  *
- * One exception is the kernel -- we already have two event sizes in
- * that we've made the 'hard' member optional since our only option
- * is to ignore it anyway.
+ * 1. accept short writes, optionally using them to detect that it's
+ *    running on an older kernel;
+ * 2. accept short reads, knowing that this means it's running on an
+ *    older kernel;
+ * 3. treat reads that are as long as requested as acceptable, not
+ *    checking against RFKILL_EVENT_SIZE_V1 or such.
  */
-#define RFKILL_EVENT_SIZE_V1	8
+#define RFKILL_EVENT_SIZE_V1	sizeof(struct rfkill_event)
 
 /* ioctl for turning off rfkill-input (if present) */
 #define RFKILL_IOC_MAGIC	'R'