From 40cbfa90218bc570a7959b436b9d48a18c361041 Mon Sep 17 00:00:00 2001
From: Srinivas Dasari <dasaris@qti.qualcomm.com>
Date: Thu, 25 Jan 2018 17:13:38 +0200
Subject: cfg80211/nl80211: Optional authentication offload to userspace

This interface allows the host driver to offload the authentication to
user space. This is exclusively defined for host drivers that do not
define separate commands for authentication and association, but rely on
userspace SME (e.g., in wpa_supplicant for the ~WPA_DRIVER_FLAGS_SME
case) for the authentication to happen. This can be used to implement
SAE without full implementation in the kernel/firmware while still being
able to use NL80211_CMD_CONNECT with driver-based BSS selection.

Host driver sends NL80211_CMD_EXTERNAL_AUTH event to start/abort
authentication to the port on which connect is triggered and status
of authentication is further indicated by user space to host
driver through the same command response interface.

User space entities advertise this capability through the
NL80211_ATTR_EXTERNAL_AUTH_SUPP flag in the NL80211_CMD_CONNECT request.
Host drivers shall look at this capability to offload the authentication.

Signed-off-by: Srinivas Dasari <dasaris@qti.qualcomm.com>
Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
[add socket connection ownership check]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 51 insertions(+), 3 deletions(-)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 81174f9b8d14..68def3e5b013 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1905,11 +1905,16 @@ struct cfg80211_auth_request {
  * @ASSOC_REQ_DISABLE_HT:  Disable HT (802.11n)
  * @ASSOC_REQ_DISABLE_VHT:  Disable VHT
  * @ASSOC_REQ_USE_RRM: Declare RRM capability in this association
+ * @CONNECT_REQ_EXTERNAL_AUTH_SUPPORT: User space indicates external
+ *	authentication capability. Drivers can offload authentication to
+ *	userspace if this flag is set. Only applicable for cfg80211_connect()
+ *	request (connect callback).
  */
 enum cfg80211_assoc_req_flags {
-	ASSOC_REQ_DISABLE_HT		= BIT(0),
-	ASSOC_REQ_DISABLE_VHT		= BIT(1),
-	ASSOC_REQ_USE_RRM		= BIT(2),
+	ASSOC_REQ_DISABLE_HT			= BIT(0),
+	ASSOC_REQ_DISABLE_VHT			= BIT(1),
+	ASSOC_REQ_USE_RRM			= BIT(2),
+	CONNECT_REQ_EXTERNAL_AUTH_SUPPORT	= BIT(3),
 };
 
 /**
@@ -2600,6 +2605,33 @@ struct cfg80211_pmk_conf {
 	const u8 *pmk_r0_name;
 };
 
+/**
+ * struct cfg80211_external_auth_params - Trigger External authentication.
+ *
+ * Commonly used across the external auth request and event interfaces.
+ *
+ * @action: action type / trigger for external authentication. Only significant
+ *	for the authentication request event interface (driver to user space).
+ * @bssid: BSSID of the peer with which the authentication has
+ *	to happen. Used by both the authentication request event and
+ *	authentication response command interface.
+ * @ssid: SSID of the AP.  Used by both the authentication request event and
+ *	authentication response command interface.
+ * @key_mgmt_suite: AKM suite of the respective authentication. Used by the
+ *	authentication request event interface.
+ * @status: status code, %WLAN_STATUS_SUCCESS for successful authentication,
+ *	use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space cannot give you
+ *	the real status code for failures. Used only for the authentication
+ *	response command interface (user space to driver).
+ */
+struct cfg80211_external_auth_params {
+	enum nl80211_external_auth_action action;
+	u8 bssid[ETH_ALEN] __aligned(2);
+	struct cfg80211_ssid ssid;
+	unsigned int key_mgmt_suite;
+	u16 status;
+};
+
 /**
  * struct cfg80211_ops - backend description for wireless configuration
  *
@@ -2923,6 +2955,9 @@ struct cfg80211_pmk_conf {
  *	(invoked with the wireless_dev mutex held)
  * @del_pmk: delete the previously configured PMK for the given authenticator.
  *	(invoked with the wireless_dev mutex held)
+ *
+ * @external_auth: indicates result of offloaded authentication processing from
+ *     user space
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -3216,6 +3251,8 @@ struct cfg80211_ops {
 			   const struct cfg80211_pmk_conf *conf);
 	int	(*del_pmk)(struct wiphy *wiphy, struct net_device *dev,
 			   const u8 *aa);
+	int     (*external_auth)(struct wiphy *wiphy, struct net_device *dev,
+				 struct cfg80211_external_auth_params *params);
 };
 
 /*
@@ -6202,6 +6239,17 @@ void cfg80211_nan_func_terminated(struct wireless_dev *wdev,
 /* ethtool helper */
 void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info);
 
+/**
+ * cfg80211_external_auth_request - userspace request for authentication
+ * @netdev: network device
+ * @params: External authentication parameters
+ * @gfp: allocation flags
+ * Returns: 0 on success, < 0 on error
+ */
+int cfg80211_external_auth_request(struct net_device *netdev,
+				   struct cfg80211_external_auth_params *params,
+				   gfp_t gfp);
+
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
 
 /* wiphy_printk helpers, similar to dev_printk */
-- 
cgit v1.2.3


From 466b9936bf93b7ec3bce1dcd493262ff0a8a4f44 Mon Sep 17 00:00:00 2001
From: "tamizhr@codeaurora.org" <tamizhr@codeaurora.org>
Date: Wed, 31 Jan 2018 16:24:49 +0530
Subject: cfg80211: Add support to notify station's opmode change to userspace

ht/vht action frames will be sent to AP from station to notify
change of its ht/vht opmode(max bandwidth, smps mode or nss) modified
values. Currently these valuse used by driver/firmware for rate control
algorithm. This patch introduces NL80211_CMD_STA_OPMODE_CHANGED
command to notify those modified/current supported values(max bandwidth,
smps mode, max nss) to userspace application. This will be useful for the
application like steering, which closely monitoring station's capability
changes. Since the application has taken these values during station
association.

Signed-off-by: Tamizh chelvam <tamizhr@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 43 ++++++++++++++++++++++++++++++++++
 include/uapi/linux/nl80211.h | 12 ++++++++++
 net/wireless/nl80211.c       | 55 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 110 insertions(+)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 68def3e5b013..7d49cd0cf92d 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3553,6 +3553,35 @@ enum wiphy_vendor_command_flags {
 	WIPHY_VENDOR_CMD_NEED_RUNNING = BIT(2),
 };
 
+/**
+ * enum wiphy_opmode_flag - Station's ht/vht operation mode information flags
+ *
+ * @STA_OPMODE_MAX_BW_CHANGED: Max Bandwidth changed
+ * @STA_OPMODE_SMPS_MODE_CHANGED: SMPS mode changed
+ * @STA_OPMODE_N_SS_CHANGED: max N_SS (number of spatial streams) changed
+ *
+ */
+enum wiphy_opmode_flag {
+	STA_OPMODE_MAX_BW_CHANGED	= BIT(0),
+	STA_OPMODE_SMPS_MODE_CHANGED	= BIT(1),
+	STA_OPMODE_N_SS_CHANGED		= BIT(2),
+};
+
+/**
+ * struct sta_opmode_info - Station's ht/vht operation mode information
+ * @changed: contains value from &enum wiphy_opmode_flag
+ * @smps_mode: New SMPS mode of a station
+ * @bw: new max bandwidth value of a station
+ * @rx_nss: new rx_nss value of a station
+ */
+
+struct sta_opmode_info {
+	u32 changed;
+	u8 smps_mode;
+	u8 bw;
+	u8 rx_nss;
+};
+
 /**
  * struct wiphy_vendor_command - vendor command definition
  * @info: vendor command identifying information, as used in nl80211
@@ -5721,6 +5750,20 @@ void cfg80211_cqm_beacon_loss_notify(struct net_device *dev, gfp_t gfp);
 void cfg80211_radar_event(struct wiphy *wiphy,
 			  struct cfg80211_chan_def *chandef, gfp_t gfp);
 
+/**
+ * cfg80211_sta_opmode_change_notify - STA's ht/vht operation mode change event
+ * @dev: network device
+ * @mac: MAC address of a station which opmode got modified
+ * @sta_opmode: station's current opmode value
+ * @gfp: context flags
+ *
+ * Driver should call this function when station's opmode modified via action
+ * frame.
+ */
+void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac,
+				       struct sta_opmode_info *sta_opmode,
+				       gfp_t gfp);
+
 /**
  * cfg80211_cac_event - Channel availability check (CAC) event
  * @netdev: network device
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index c2342456cf16..ca3d5a613fc0 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1013,6 +1013,11 @@
  *	user space through the connect result as the user space would have
  *	initiated the connection through the connect request.
  *
+ * @NL80211_CMD_STA_OPMODE_CHANGED: An event that notify station's
+ *	ht opmode or vht opmode changes using any of &NL80211_ATTR_SMPS_MODE,
+ *	&NL80211_ATTR_CHANNEL_WIDTH,&NL80211_ATTR_NSS attributes with its
+ *	address(specified in &NL80211_ATTR_MAC).
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -1221,6 +1226,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_EXTERNAL_AUTH,
 
+	NL80211_CMD_STA_OPMODE_CHANGED,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -2186,6 +2193,9 @@ enum nl80211_commands {
  *     authentication processing to user space if this capability is indicated
  *     in NL80211_CMD_CONNECT requests from the user space.
  *
+ * @NL80211_ATTR_NSS: Station's New/updated  RX_NSS value notified using this
+ *	u8 attribute. This is used with %NL80211_CMD_STA_OPMODE_CHANGED.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2615,6 +2625,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_EXTERNAL_AUTH_ACTION,
 	NL80211_ATTR_EXTERNAL_AUTH_SUPPORT,
 
+	NL80211_ATTR_NSS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index bdb70fe74e3c..cc6ec5bab676 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -14950,6 +14950,61 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 	nlmsg_free(msg);
 }
 
+void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac,
+				       struct sta_opmode_info *sta_opmode,
+				       gfp_t gfp)
+{
+	struct sk_buff *msg;
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	void *hdr;
+
+	if (WARN_ON(!mac))
+		return;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_STA_OPMODE_CHANGED);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
+		goto nla_put_failure;
+
+	if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac))
+		goto nla_put_failure;
+
+	if ((sta_opmode->changed & STA_OPMODE_SMPS_MODE_CHANGED) &&
+	    nla_put_u8(msg, NL80211_ATTR_SMPS_MODE, sta_opmode->smps_mode))
+		goto nla_put_failure;
+
+	if ((sta_opmode->changed & STA_OPMODE_MAX_BW_CHANGED) &&
+	    nla_put_u8(msg, NL80211_ATTR_CHANNEL_WIDTH, sta_opmode->bw))
+		goto nla_put_failure;
+
+	if ((sta_opmode->changed & STA_OPMODE_N_SS_CHANGED) &&
+	    nla_put_u8(msg, NL80211_ATTR_NSS, sta_opmode->rx_nss))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
+				NL80211_MCGRP_MLME, gfp);
+
+	return;
+
+nla_put_failure:
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_sta_opmode_change_notify);
+
 void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 			   u64 cookie, bool acked, gfp_t gfp)
 {
-- 
cgit v1.2.3


From 9b2c45d479d0fb8647c9e83359df69162b5fbe5f Mon Sep 17 00:00:00 2001
From: Denys Vlasenko <dvlasenk@redhat.com>
Date: Mon, 12 Feb 2018 20:00:20 +0100
Subject: net: make getname() functions return length rather than use int*
 parameter

Changes since v1:
Added changes in these files:
    drivers/infiniband/hw/usnic/usnic_transport.c
    drivers/staging/lustre/lnet/lnet/lib-socket.c
    drivers/target/iscsi/iscsi_target_login.c
    drivers/vhost/net.c
    fs/dlm/lowcomms.c
    fs/ocfs2/cluster/tcp.c
    security/tomoyo/network.c

Before:
All these functions either return a negative error indicator,
or store length of sockaddr into "int *socklen" parameter
and return zero on success.

"int *socklen" parameter is awkward. For example, if caller does not
care, it still needs to provide on-stack storage for the value
it does not need.

None of the many FOO_getname() functions of various protocols
ever used old value of *socklen. They always just overwrite it.

This change drops this parameter, and makes all these functions, on success,
return length of sockaddr. It's always >= 0 and can be differentiated
from an error.

Tests in callers are changed from "if (err)" to "if (err < 0)", where needed.

rpc_sockname() lost "int buflen" parameter, since its only use was
to be passed to kernel_getsockname() as &buflen and subsequently
not used in any way.

Userspace API is not changed.

    text    data     bss      dec     hex filename
30108430 2633624  873672 33615726 200ef6e vmlinux.before.o
30108109 2633612  873672 33615393 200ee21 vmlinux.o

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: David S. Miller <davem@davemloft.net>
CC: linux-kernel@vger.kernel.org
CC: netdev@vger.kernel.org
CC: linux-bluetooth@vger.kernel.org
CC: linux-decnet-user@lists.sourceforge.net
CC: linux-wireless@vger.kernel.org
CC: linux-rdma@vger.kernel.org
CC: linux-sctp@vger.kernel.org
CC: linux-nfs@vger.kernel.org
CC: linux-x25@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/usnic/usnic_transport.c |  5 ++--
 drivers/isdn/mISDN/socket.c                   |  5 ++--
 drivers/net/ppp/pppoe.c                       |  6 ++---
 drivers/net/ppp/pptp.c                        |  6 ++---
 drivers/scsi/iscsi_tcp.c                      | 14 +++++------
 drivers/soc/qcom/qmi_interface.c              |  3 +--
 drivers/staging/ipx/af_ipx.c                  |  6 ++---
 drivers/staging/irda/net/af_irda.c            |  8 +++---
 drivers/staging/lustre/lnet/lnet/lib-socket.c |  7 +++---
 drivers/target/iscsi/iscsi_target_login.c     | 18 +++++++-------
 drivers/vhost/net.c                           |  7 +++---
 fs/dlm/lowcomms.c                             |  7 +++---
 fs/ocfs2/cluster/tcp.c                        |  6 ++---
 include/linux/net.h                           |  8 +++---
 include/net/inet_common.h                     |  2 +-
 include/net/ipv6.h                            |  2 +-
 include/net/sock.h                            |  2 +-
 net/appletalk/ddp.c                           |  5 ++--
 net/atm/pvc.c                                 |  5 ++--
 net/atm/svc.c                                 |  5 ++--
 net/ax25/af_ax25.c                            |  4 +--
 net/bluetooth/hci_sock.c                      |  4 +--
 net/bluetooth/l2cap_sock.c                    |  5 ++--
 net/bluetooth/rfcomm/sock.c                   |  5 ++--
 net/bluetooth/sco.c                           |  5 ++--
 net/can/raw.c                                 |  6 ++---
 net/core/sock.c                               |  5 ++--
 net/decnet/af_decnet.c                        |  6 ++---
 net/ipv4/af_inet.c                            |  5 ++--
 net/ipv6/af_inet6.c                           |  5 ++--
 net/iucv/af_iucv.c                            |  5 ++--
 net/l2tp/l2tp_ip.c                            |  5 ++--
 net/l2tp/l2tp_ip6.c                           |  5 ++--
 net/l2tp/l2tp_ppp.c                           |  5 ++--
 net/llc/af_llc.c                              |  5 ++--
 net/netlink/af_netlink.c                      |  5 ++--
 net/netrom/af_netrom.c                        |  9 ++++---
 net/nfc/llcp_sock.c                           |  5 ++--
 net/packet/af_packet.c                        | 10 +++-----
 net/phonet/socket.c                           |  5 ++--
 net/qrtr/qrtr.c                               |  5 ++--
 net/rds/af_rds.c                              |  5 ++--
 net/rds/tcp.c                                 |  7 ++----
 net/rose/af_rose.c                            |  5 ++--
 net/sctp/ipv6.c                               |  8 +++---
 net/smc/af_smc.c                              | 11 ++++-----
 net/socket.c                                  | 35 +++++++++++++--------------
 net/sunrpc/clnt.c                             |  6 ++---
 net/sunrpc/svcsock.c                          | 13 ++++++----
 net/sunrpc/xprtsock.c                         |  3 +--
 net/tipc/socket.c                             |  5 ++--
 net/unix/af_unix.c                            | 10 ++++----
 net/vmw_vsock/af_vsock.c                      |  4 +--
 net/x25/af_x25.c                              |  4 +--
 security/tomoyo/network.c                     |  5 ++--
 55 files changed, 159 insertions(+), 203 deletions(-)

(limited to 'include/net')

diff --git a/drivers/infiniband/hw/usnic/usnic_transport.c b/drivers/infiniband/hw/usnic/usnic_transport.c
index de318389a301..67de94343cb4 100644
--- a/drivers/infiniband/hw/usnic/usnic_transport.c
+++ b/drivers/infiniband/hw/usnic/usnic_transport.c
@@ -174,14 +174,13 @@ void usnic_transport_put_socket(struct socket *sock)
 int usnic_transport_sock_get_addr(struct socket *sock, int *proto,
 					uint32_t *addr, uint16_t *port)
 {
-	int len;
 	int err;
 	struct sockaddr_in sock_addr;
 
 	err = sock->ops->getname(sock,
 				(struct sockaddr *)&sock_addr,
-				&len, 0);
-	if (err)
+				0);
+	if (err < 0)
 		return err;
 
 	if (sock_addr.sin_family != AF_INET)
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index c5603d1a07d6..1f8f489b4167 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -560,7 +560,7 @@ done:
 
 static int
 data_sock_getname(struct socket *sock, struct sockaddr *addr,
-		  int *addr_len, int peer)
+		  int peer)
 {
 	struct sockaddr_mISDN	*maddr = (struct sockaddr_mISDN *) addr;
 	struct sock		*sk = sock->sk;
@@ -570,14 +570,13 @@ data_sock_getname(struct socket *sock, struct sockaddr *addr,
 
 	lock_sock(sk);
 
-	*addr_len = sizeof(*maddr);
 	maddr->family = AF_ISDN;
 	maddr->dev = _pms(sk)->dev->id;
 	maddr->channel = _pms(sk)->ch.nr;
 	maddr->sapi = _pms(sk)->ch.addr & 0xff;
 	maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xff;
 	release_sock(sk);
-	return 0;
+	return sizeof(*maddr);
 }
 
 static const struct proto_ops data_sock_ops = {
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5aa59f41bf8c..bd89d1c559ce 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -714,7 +714,7 @@ err_put:
 }
 
 static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr,
-		  int *usockaddr_len, int peer)
+		  int peer)
 {
 	int len = sizeof(struct sockaddr_pppox);
 	struct sockaddr_pppox sp;
@@ -726,9 +726,7 @@ static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr,
 
 	memcpy(uaddr, &sp, len);
 
-	*usockaddr_len = len;
-
-	return 0;
+	return len;
 }
 
 static int pppoe_ioctl(struct socket *sock, unsigned int cmd,
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 6dde9a0cfe76..8249d46a7844 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -483,7 +483,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 }
 
 static int pptp_getname(struct socket *sock, struct sockaddr *uaddr,
-	int *usockaddr_len, int peer)
+	int peer)
 {
 	int len = sizeof(struct sockaddr_pppox);
 	struct sockaddr_pppox sp;
@@ -496,9 +496,7 @@ static int pptp_getname(struct socket *sock, struct sockaddr *uaddr,
 
 	memcpy(uaddr, &sp, len);
 
-	*usockaddr_len = len;
-
-	return 0;
+	return len;
 }
 
 static int pptp_release(struct socket *sock)
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 6198559abbd8..0ad00dbf912d 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -732,7 +732,7 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn,
 	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
 	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
 	struct sockaddr_in6 addr;
-	int rc, len;
+	int rc;
 
 	switch(param) {
 	case ISCSI_PARAM_CONN_PORT:
@@ -745,12 +745,12 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn,
 		}
 		if (param == ISCSI_PARAM_LOCAL_PORT)
 			rc = kernel_getsockname(tcp_sw_conn->sock,
-						(struct sockaddr *)&addr, &len);
+						(struct sockaddr *)&addr);
 		else
 			rc = kernel_getpeername(tcp_sw_conn->sock,
-						(struct sockaddr *)&addr, &len);
+						(struct sockaddr *)&addr);
 		spin_unlock_bh(&conn->session->frwd_lock);
-		if (rc)
+		if (rc < 0)
 			return rc;
 
 		return iscsi_conn_get_addr_param((struct sockaddr_storage *)
@@ -771,7 +771,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost,
 	struct iscsi_tcp_conn *tcp_conn;
 	struct iscsi_sw_tcp_conn *tcp_sw_conn;
 	struct sockaddr_in6 addr;
-	int rc, len;
+	int rc;
 
 	switch (param) {
 	case ISCSI_HOST_PARAM_IPADDRESS:
@@ -793,9 +793,9 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost,
 		}
 
 		rc = kernel_getsockname(tcp_sw_conn->sock,
-					(struct sockaddr *)&addr, &len);
+					(struct sockaddr *)&addr);
 		spin_unlock_bh(&session->frwd_lock);
-		if (rc)
+		if (rc < 0)
 			return rc;
 
 		return iscsi_conn_get_addr_param((struct sockaddr_storage *)
diff --git a/drivers/soc/qcom/qmi_interface.c b/drivers/soc/qcom/qmi_interface.c
index 877611d5c42b..321982277697 100644
--- a/drivers/soc/qcom/qmi_interface.c
+++ b/drivers/soc/qcom/qmi_interface.c
@@ -586,7 +586,6 @@ static struct socket *qmi_sock_create(struct qmi_handle *qmi,
 				      struct sockaddr_qrtr *sq)
 {
 	struct socket *sock;
-	int sl = sizeof(*sq);
 	int ret;
 
 	ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM,
@@ -594,7 +593,7 @@ static struct socket *qmi_sock_create(struct qmi_handle *qmi,
 	if (ret < 0)
 		return ERR_PTR(ret);
 
-	ret = kernel_getsockname(sock, (struct sockaddr *)sq, &sl);
+	ret = kernel_getsockname(sock, (struct sockaddr *)sq);
 	if (ret < 0) {
 		sock_release(sock);
 		return ERR_PTR(ret);
diff --git a/drivers/staging/ipx/af_ipx.c b/drivers/staging/ipx/af_ipx.c
index d21a9d128d3e..5703dd176787 100644
--- a/drivers/staging/ipx/af_ipx.c
+++ b/drivers/staging/ipx/af_ipx.c
@@ -1577,7 +1577,7 @@ out:
 
 
 static int ipx_getname(struct socket *sock, struct sockaddr *uaddr,
-			int *uaddr_len, int peer)
+			int peer)
 {
 	struct ipx_address *addr;
 	struct sockaddr_ipx sipx;
@@ -1585,8 +1585,6 @@ static int ipx_getname(struct socket *sock, struct sockaddr *uaddr,
 	struct ipx_sock *ipxs = ipx_sk(sk);
 	int rc;
 
-	*uaddr_len = sizeof(struct sockaddr_ipx);
-
 	lock_sock(sk);
 	if (peer) {
 		rc = -ENOTCONN;
@@ -1620,7 +1618,7 @@ static int ipx_getname(struct socket *sock, struct sockaddr *uaddr,
 	sipx.sipx_zero	 = 0;
 	memcpy(uaddr, &sipx, sizeof(sipx));
 
-	rc = 0;
+	rc = sizeof(struct sockaddr_ipx);
 out:
 	release_sock(sk);
 	return rc;
diff --git a/drivers/staging/irda/net/af_irda.c b/drivers/staging/irda/net/af_irda.c
index 2f1e9ab3d6d0..c13553a9ee11 100644
--- a/drivers/staging/irda/net/af_irda.c
+++ b/drivers/staging/irda/net/af_irda.c
@@ -697,7 +697,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name)
  *
  */
 static int irda_getname(struct socket *sock, struct sockaddr *uaddr,
-			int *uaddr_len, int peer)
+			int peer)
 {
 	struct sockaddr_irda saddr;
 	struct sock *sk = sock->sk;
@@ -720,11 +720,9 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr,
 	pr_debug("%s(), tsap_sel = %#x\n", __func__, saddr.sir_lsap_sel);
 	pr_debug("%s(), addr = %08x\n", __func__, saddr.sir_addr);
 
-	/* uaddr_len come to us uninitialised */
-	*uaddr_len = sizeof (struct sockaddr_irda);
-	memcpy(uaddr, &saddr, *uaddr_len);
+	memcpy(uaddr, &saddr, sizeof (struct sockaddr_irda));
 
-	return 0;
+	return sizeof (struct sockaddr_irda);
 }
 
 /*
diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c
index ce93806eefca..1bee667802b0 100644
--- a/drivers/staging/lustre/lnet/lnet/lib-socket.c
+++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c
@@ -448,14 +448,13 @@ int
 lnet_sock_getaddr(struct socket *sock, bool remote, __u32 *ip, int *port)
 {
 	struct sockaddr_in sin;
-	int len = sizeof(sin);
 	int rc;
 
 	if (remote)
-		rc = kernel_getpeername(sock, (struct sockaddr *)&sin, &len);
+		rc = kernel_getpeername(sock, (struct sockaddr *)&sin);
 	else
-		rc = kernel_getsockname(sock, (struct sockaddr *)&sin, &len);
-	if (rc) {
+		rc = kernel_getsockname(sock, (struct sockaddr *)&sin);
+	if (rc < 0) {
 		CERROR("Error %d getting sock %s IP/port\n",
 		       rc, remote ? "peer" : "local");
 		return rc;
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 64c5a57b92e4..99501785cdc1 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1020,7 +1020,7 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	struct socket *new_sock, *sock = np->np_socket;
 	struct sockaddr_in sock_in;
 	struct sockaddr_in6 sock_in6;
-	int rc, err;
+	int rc;
 
 	rc = kernel_accept(sock, &new_sock, 0);
 	if (rc < 0)
@@ -1033,8 +1033,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 		memset(&sock_in6, 0, sizeof(struct sockaddr_in6));
 
 		rc = conn->sock->ops->getname(conn->sock,
-				(struct sockaddr *)&sock_in6, &err, 1);
-		if (!rc) {
+				(struct sockaddr *)&sock_in6, 1);
+		if (rc >= 0) {
 			if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) {
 				memcpy(&conn->login_sockaddr, &sock_in6, sizeof(sock_in6));
 			} else {
@@ -1047,8 +1047,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 		}
 
 		rc = conn->sock->ops->getname(conn->sock,
-				(struct sockaddr *)&sock_in6, &err, 0);
-		if (!rc) {
+				(struct sockaddr *)&sock_in6, 0);
+		if (rc >= 0) {
 			if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) {
 				memcpy(&conn->local_sockaddr, &sock_in6, sizeof(sock_in6));
 			} else {
@@ -1063,13 +1063,13 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 		memset(&sock_in, 0, sizeof(struct sockaddr_in));
 
 		rc = conn->sock->ops->getname(conn->sock,
-				(struct sockaddr *)&sock_in, &err, 1);
-		if (!rc)
+				(struct sockaddr *)&sock_in, 1);
+		if (rc >= 0)
 			memcpy(&conn->login_sockaddr, &sock_in, sizeof(sock_in));
 
 		rc = conn->sock->ops->getname(conn->sock,
-				(struct sockaddr *)&sock_in, &err, 0);
-		if (!rc)
+				(struct sockaddr *)&sock_in, 0);
+		if (rc >= 0)
 			memcpy(&conn->local_sockaddr, &sock_in, sizeof(sock_in));
 	}
 
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 610cba276d47..b5fb56b822fd 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1038,7 +1038,7 @@ static struct socket *get_raw_socket(int fd)
 		struct sockaddr_ll sa;
 		char  buf[MAX_ADDR_LEN];
 	} uaddr;
-	int uaddr_len = sizeof uaddr, r;
+	int r;
 	struct socket *sock = sockfd_lookup(fd, &r);
 
 	if (!sock)
@@ -1050,9 +1050,8 @@ static struct socket *get_raw_socket(int fd)
 		goto err;
 	}
 
-	r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa,
-			       &uaddr_len, 0);
-	if (r)
+	r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0);
+	if (r < 0)
 		goto err;
 
 	if (uaddr.sa.sll_family != AF_PACKET) {
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index cff79ea0c01d..5243989a60cc 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -482,7 +482,6 @@ static void lowcomms_error_report(struct sock *sk)
 {
 	struct connection *con;
 	struct sockaddr_storage saddr;
-	int buflen;
 	void (*orig_report)(struct sock *) = NULL;
 
 	read_lock_bh(&sk->sk_callback_lock);
@@ -492,7 +491,7 @@ static void lowcomms_error_report(struct sock *sk)
 
 	orig_report = listen_sock.sk_error_report;
 	if (con->sock == NULL ||
-	    kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) {
+	    kernel_getpeername(con->sock, (struct sockaddr *)&saddr) < 0) {
 		printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
 				   "sending to node %d, port %d, "
 				   "sk_err=%d/%d\n", dlm_our_nodeid(),
@@ -757,8 +756,8 @@ static int tcp_accept_from_sock(struct connection *con)
 
 	/* Get the connected socket's peer */
 	memset(&peeraddr, 0, sizeof(peeraddr));
-	if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr,
-				  &len, 2)) {
+	len = newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, 2);
+	if (len < 0) {
 		result = -ECONNABORTED;
 		goto accept_err;
 	}
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index eac5140aac47..e5076185cc1e 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1819,7 +1819,7 @@ int o2net_register_hb_callbacks(void)
 
 static int o2net_accept_one(struct socket *sock, int *more)
 {
-	int ret, slen;
+	int ret;
 	struct sockaddr_in sin;
 	struct socket *new_sock = NULL;
 	struct o2nm_node *node = NULL;
@@ -1864,9 +1864,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 		goto out;
 	}
 
-	slen = sizeof(sin);
-	ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin,
-				       &slen, 1);
+	ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, 1);
 	if (ret < 0)
 		goto out;
 
diff --git a/include/linux/net.h b/include/linux/net.h
index 91216b16feb7..000d1aada74f 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -146,7 +146,7 @@ struct proto_ops {
 				      struct socket *newsock, int flags, bool kern);
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
-				      int *sockaddr_len, int peer);
+				      int peer);
 	__poll_t	(*poll)	     (struct file *file, struct socket *sock,
 				      struct poll_table_struct *wait);
 	int		(*ioctl)     (struct socket *sock, unsigned int cmd,
@@ -294,10 +294,8 @@ int kernel_listen(struct socket *sock, int backlog);
 int kernel_accept(struct socket *sock, struct socket **newsock, int flags);
 int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
 		   int flags);
-int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
-		       int *addrlen);
-int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
-		       int *addrlen);
+int kernel_getsockname(struct socket *sock, struct sockaddr *addr);
+int kernel_getpeername(struct socket *sock, struct sockaddr *addr);
 int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval,
 		      int *optlen);
 int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval,
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 5a54c9570977..500f81375200 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -32,7 +32,7 @@ int inet_shutdown(struct socket *sock, int how);
 int inet_listen(struct socket *sock, int backlog);
 void inet_sock_destruct(struct sock *sk);
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
-int inet_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len,
+int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 		 int peer);
 int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int inet_ctl_sock_create(struct sock **sk, unsigned short family,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8606c9113d3f..7a98cd583c73 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1056,7 +1056,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);
 
 int inet6_release(struct socket *sock);
 int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
-int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len,
+int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		  int peer);
 int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 169c92afcafa..3aa7b7d6e6c7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1584,7 +1584,7 @@ int sock_no_bind(struct socket *, struct sockaddr *, int);
 int sock_no_connect(struct socket *, struct sockaddr *, int, int);
 int sock_no_socketpair(struct socket *, struct socket *);
 int sock_no_accept(struct socket *, struct socket *, int, bool);
-int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
+int sock_no_getname(struct socket *, struct sockaddr *, int);
 __poll_t sock_no_poll(struct file *, struct socket *,
 			  struct poll_table_struct *);
 int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 03a9fc0771c0..9b6bc5abe946 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1238,7 +1238,7 @@ out:
  * fields into the sockaddr.
  */
 static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
-			 int *uaddr_len, int peer)
+			 int peer)
 {
 	struct sockaddr_at sat;
 	struct sock *sk = sock->sk;
@@ -1251,7 +1251,6 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
 		if (atalk_autobind(sk) < 0)
 			goto out;
 
-	*uaddr_len = sizeof(struct sockaddr_at);
 	memset(&sat, 0, sizeof(sat));
 
 	if (peer) {
@@ -1268,9 +1267,9 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
 		sat.sat_port	    = at->src_port;
 	}
 
-	err = 0;
 	sat.sat_family = AF_APPLETALK;
 	memcpy(uaddr, &sat, sizeof(sat));
+	err = sizeof(struct sockaddr_at);
 
 out:
 	release_sock(sk);
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index e1140b3bdcaa..2cb10af16afc 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -87,21 +87,20 @@ static int pvc_getsockopt(struct socket *sock, int level, int optname,
 }
 
 static int pvc_getname(struct socket *sock, struct sockaddr *sockaddr,
-		       int *sockaddr_len, int peer)
+		       int peer)
 {
 	struct sockaddr_atmpvc *addr;
 	struct atm_vcc *vcc = ATM_SD(sock);
 
 	if (!vcc->dev || !test_bit(ATM_VF_ADDR, &vcc->flags))
 		return -ENOTCONN;
-	*sockaddr_len = sizeof(struct sockaddr_atmpvc);
 	addr = (struct sockaddr_atmpvc *)sockaddr;
 	memset(addr, 0, sizeof(*addr));
 	addr->sap_family = AF_ATMPVC;
 	addr->sap_addr.itf = vcc->dev->number;
 	addr->sap_addr.vpi = vcc->vpi;
 	addr->sap_addr.vci = vcc->vci;
-	return 0;
+	return sizeof(struct sockaddr_atmpvc);
 }
 
 static const struct proto_ops pvc_proto_ops = {
diff --git a/net/atm/svc.c b/net/atm/svc.c
index c458adcbc177..2f91b766ac42 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -419,15 +419,14 @@ out:
 }
 
 static int svc_getname(struct socket *sock, struct sockaddr *sockaddr,
-		       int *sockaddr_len, int peer)
+		       int peer)
 {
 	struct sockaddr_atmsvc *addr;
 
-	*sockaddr_len = sizeof(struct sockaddr_atmsvc);
 	addr = (struct sockaddr_atmsvc *) sockaddr;
 	memcpy(addr, peer ? &ATM_SD(sock)->remote : &ATM_SD(sock)->local,
 	       sizeof(struct sockaddr_atmsvc));
-	return 0;
+	return sizeof(struct sockaddr_atmsvc);
 }
 
 int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos)
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 47fdd399626b..c8319ed48485 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1388,7 +1388,7 @@ out:
 }
 
 static int ax25_getname(struct socket *sock, struct sockaddr *uaddr,
-	int *uaddr_len, int peer)
+	int peer)
 {
 	struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)uaddr;
 	struct sock *sk = sock->sk;
@@ -1427,7 +1427,7 @@ static int ax25_getname(struct socket *sock, struct sockaddr *uaddr,
 			fsa->fsa_digipeater[0] = null_ax25_address;
 		}
 	}
-	*uaddr_len = sizeof (struct full_sockaddr_ax25);
+	err = sizeof (struct full_sockaddr_ax25);
 
 out:
 	release_sock(sk);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 923e9a271872..1506e1632394 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1340,7 +1340,7 @@ done:
 }
 
 static int hci_sock_getname(struct socket *sock, struct sockaddr *addr,
-			    int *addr_len, int peer)
+			    int peer)
 {
 	struct sockaddr_hci *haddr = (struct sockaddr_hci *)addr;
 	struct sock *sk = sock->sk;
@@ -1360,10 +1360,10 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr,
 		goto done;
 	}
 
-	*addr_len = sizeof(*haddr);
 	haddr->hci_family = AF_BLUETOOTH;
 	haddr->hci_dev    = hdev->id;
 	haddr->hci_channel= hci_pi(sk)->channel;
+	err = sizeof(*haddr);
 
 done:
 	release_sock(sk);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 67a8642f57ea..686bdc6b35b0 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -358,7 +358,7 @@ done:
 }
 
 static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr,
-			      int *len, int peer)
+			      int peer)
 {
 	struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr;
 	struct sock *sk = sock->sk;
@@ -373,7 +373,6 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr,
 
 	memset(la, 0, sizeof(struct sockaddr_l2));
 	addr->sa_family = AF_BLUETOOTH;
-	*len = sizeof(struct sockaddr_l2);
 
 	la->l2_psm = chan->psm;
 
@@ -387,7 +386,7 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr,
 		la->l2_bdaddr_type = chan->src_type;
 	}
 
-	return 0;
+	return sizeof(struct sockaddr_l2);
 }
 
 static int l2cap_sock_getsockopt_old(struct socket *sock, int optname,
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 1aaccf637479..93a3b219db09 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -533,7 +533,7 @@ done:
 	return err;
 }
 
-static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer)
+static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int peer)
 {
 	struct sockaddr_rc *sa = (struct sockaddr_rc *) addr;
 	struct sock *sk = sock->sk;
@@ -552,8 +552,7 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *
 	else
 		bacpy(&sa->rc_bdaddr, &rfcomm_pi(sk)->src);
 
-	*len = sizeof(struct sockaddr_rc);
-	return 0;
+	return sizeof(struct sockaddr_rc);
 }
 
 static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg,
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 08df57665e1f..413b8ee49fec 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -680,7 +680,7 @@ done:
 }
 
 static int sco_sock_getname(struct socket *sock, struct sockaddr *addr,
-			    int *len, int peer)
+			    int peer)
 {
 	struct sockaddr_sco *sa = (struct sockaddr_sco *) addr;
 	struct sock *sk = sock->sk;
@@ -688,14 +688,13 @@ static int sco_sock_getname(struct socket *sock, struct sockaddr *addr,
 	BT_DBG("sock %p, sk %p", sock, sk);
 
 	addr->sa_family = AF_BLUETOOTH;
-	*len = sizeof(struct sockaddr_sco);
 
 	if (peer)
 		bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst);
 	else
 		bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src);
 
-	return 0;
+	return sizeof(struct sockaddr_sco);
 }
 
 static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
diff --git a/net/can/raw.c b/net/can/raw.c
index f2ecc43376a1..1051eee82581 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -470,7 +470,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 }
 
 static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
-		       int *len, int peer)
+		       int peer)
 {
 	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
 	struct sock *sk = sock->sk;
@@ -483,9 +483,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr,
 	addr->can_family  = AF_CAN;
 	addr->can_ifindex = ro->ifindex;
 
-	*len = sizeof(*addr);
-
-	return 0;
+	return sizeof(*addr);
 }
 
 static int raw_setsockopt(struct socket *sock, int level, int optname,
diff --git a/net/core/sock.c b/net/core/sock.c
index c501499a04fe..04e5e27c9b81 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1274,7 +1274,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	{
 		char address[128];
 
-		if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
+		lv = sock->ops->getname(sock, (struct sockaddr *)address, 2);
+		if (lv < 0)
 			return -ENOTCONN;
 		if (lv < len)
 			return -EINVAL;
@@ -2497,7 +2498,7 @@ int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
 EXPORT_SYMBOL(sock_no_accept);
 
 int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
-		    int *len, int peer)
+		    int peer)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 91dd09f79808..45cb5bea884b 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1180,14 +1180,12 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags,
 }
 
 
-static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len,int peer)
+static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer)
 {
 	struct sockaddr_dn *sa = (struct sockaddr_dn *)uaddr;
 	struct sock *sk = sock->sk;
 	struct dn_scp *scp = DN_SK(sk);
 
-	*uaddr_len = sizeof(struct sockaddr_dn);
-
 	lock_sock(sk);
 
 	if (peer) {
@@ -1205,7 +1203,7 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len
 
 	release_sock(sk);
 
-	return 0;
+	return sizeof(struct sockaddr_dn);
 }
 
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e4329e161943..f98e2f0db841 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -723,7 +723,7 @@ EXPORT_SYMBOL(inet_accept);
  *	This does both peername and sockname.
  */
 int inet_getname(struct socket *sock, struct sockaddr *uaddr,
-			int *uaddr_len, int peer)
+			int peer)
 {
 	struct sock *sk		= sock->sk;
 	struct inet_sock *inet	= inet_sk(sk);
@@ -745,8 +745,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 		sin->sin_addr.s_addr = addr;
 	}
 	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
-	*uaddr_len = sizeof(*sin);
-	return 0;
+	return sizeof(*sin);
 }
 EXPORT_SYMBOL(inet_getname);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 416917719a6f..c1e292db04db 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -470,7 +470,7 @@ EXPORT_SYMBOL_GPL(inet6_destroy_sock);
  */
 
 int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
-		 int *uaddr_len, int peer)
+		 int peer)
 {
 	struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr;
 	struct sock *sk = sock->sk;
@@ -500,8 +500,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 	}
 	sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr,
 						 sk->sk_bound_dev_if);
-	*uaddr_len = sizeof(*sin);
-	return 0;
+	return sizeof(*sin);
 }
 EXPORT_SYMBOL(inet6_getname);
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 1e8cc7bcbca3..81ce15ffb878 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -989,14 +989,13 @@ done:
 }
 
 static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr,
-			     int *len, int peer)
+			     int peer)
 {
 	struct sockaddr_iucv *siucv = (struct sockaddr_iucv *) addr;
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
 
 	addr->sa_family = AF_IUCV;
-	*len = sizeof(struct sockaddr_iucv);
 
 	if (peer) {
 		memcpy(siucv->siucv_user_id, iucv->dst_user_id, 8);
@@ -1009,7 +1008,7 @@ static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr,
 	memset(&siucv->siucv_addr, 0, sizeof(siucv->siucv_addr));
 	memset(&siucv->siucv_nodeid, 0, sizeof(siucv->siucv_nodeid));
 
-	return 0;
+	return sizeof(struct sockaddr_iucv);
 }
 
 /**
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ff61124fdf59..4614585e1720 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -349,7 +349,7 @@ static int l2tp_ip_disconnect(struct sock *sk, int flags)
 }
 
 static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
-			   int *uaddr_len, int peer)
+			   int peer)
 {
 	struct sock *sk		= sock->sk;
 	struct inet_sock *inet	= inet_sk(sk);
@@ -370,8 +370,7 @@ static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
 		lsa->l2tp_conn_id = lsk->conn_id;
 		lsa->l2tp_addr.s_addr = addr;
 	}
-	*uaddr_len = sizeof(*lsa);
-	return 0;
+	return sizeof(*lsa);
 }
 
 static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 192344688c06..efea58b66295 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -421,7 +421,7 @@ static int l2tp_ip6_disconnect(struct sock *sk, int flags)
 }
 
 static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
-			    int *uaddr_len, int peer)
+			    int peer)
 {
 	struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr;
 	struct sock *sk = sock->sk;
@@ -449,8 +449,7 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
 	}
 	if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
 		lsa->l2tp_scope_id = sk->sk_bound_dev_if;
-	*uaddr_len = sizeof(*lsa);
-	return 0;
+	return sizeof(*lsa);
 }
 
 static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 59f246d7b290..99a03c72db4f 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -870,7 +870,7 @@ err:
 /* getname() support.
  */
 static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
-			    int *usockaddr_len, int peer)
+			    int peer)
 {
 	int len = 0;
 	int error = 0;
@@ -969,8 +969,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 		memcpy(uaddr, &sp, len);
 	}
 
-	*usockaddr_len = len;
-	error = 0;
+	error = len;
 
 	sock_put(sk);
 end:
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c38d16f22d2a..01dcc0823d1f 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -971,7 +971,7 @@ release:
  *	Return the address information of a socket.
  */
 static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr,
-			  int *uaddrlen, int peer)
+			  int peer)
 {
 	struct sockaddr_llc sllc;
 	struct sock *sk = sock->sk;
@@ -982,7 +982,6 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr,
 	lock_sock(sk);
 	if (sock_flag(sk, SOCK_ZAPPED))
 		goto out;
-	*uaddrlen = sizeof(sllc);
 	if (peer) {
 		rc = -ENOTCONN;
 		if (sk->sk_state != TCP_ESTABLISHED)
@@ -1003,9 +1002,9 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr,
 			       IFHWADDRLEN);
 		}
 	}
-	rc = 0;
 	sllc.sllc_family = AF_LLC;
 	memcpy(uaddr, &sllc, sizeof(sllc));
+	rc = sizeof(sllc);
 out:
 	release_sock(sk);
 	return rc;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2ad445c1d27c..3c8af14330b5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1105,7 +1105,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 }
 
 static int netlink_getname(struct socket *sock, struct sockaddr *addr,
-			   int *addr_len, int peer)
+			   int peer)
 {
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -1113,7 +1113,6 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
 
 	nladdr->nl_family = AF_NETLINK;
 	nladdr->nl_pad = 0;
-	*addr_len = sizeof(*nladdr);
 
 	if (peer) {
 		nladdr->nl_pid = nlk->dst_portid;
@@ -1124,7 +1123,7 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
 		nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0;
 		netlink_unlock_table();
 	}
-	return 0;
+	return sizeof(*nladdr);
 }
 
 static int netlink_ioctl(struct socket *sock, unsigned int cmd,
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 9ba30c63be3d..35bb6807927f 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -829,11 +829,12 @@ out_release:
 }
 
 static int nr_getname(struct socket *sock, struct sockaddr *uaddr,
-	int *uaddr_len, int peer)
+	int peer)
 {
 	struct full_sockaddr_ax25 *sax = (struct full_sockaddr_ax25 *)uaddr;
 	struct sock *sk = sock->sk;
 	struct nr_sock *nr = nr_sk(sk);
+	int uaddr_len;
 
 	memset(&sax->fsa_ax25, 0, sizeof(struct sockaddr_ax25));
 
@@ -848,16 +849,16 @@ static int nr_getname(struct socket *sock, struct sockaddr *uaddr,
 		sax->fsa_ax25.sax25_call   = nr->user_addr;
 		memset(sax->fsa_digipeater, 0, sizeof(sax->fsa_digipeater));
 		sax->fsa_digipeater[0]     = nr->dest_addr;
-		*uaddr_len = sizeof(struct full_sockaddr_ax25);
+		uaddr_len = sizeof(struct full_sockaddr_ax25);
 	} else {
 		sax->fsa_ax25.sax25_family = AF_NETROM;
 		sax->fsa_ax25.sax25_ndigis = 0;
 		sax->fsa_ax25.sax25_call   = nr->source_addr;
-		*uaddr_len = sizeof(struct sockaddr_ax25);
+		uaddr_len = sizeof(struct sockaddr_ax25);
 	}
 	release_sock(sk);
 
-	return 0;
+	return uaddr_len;
 }
 
 int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 376040092142..ea0c0c6f1874 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -497,7 +497,7 @@ error:
 }
 
 static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr,
-			     int *len, int peer)
+			     int peer)
 {
 	struct sock *sk = sock->sk;
 	struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk);
@@ -510,7 +510,6 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr,
 		 llcp_sock->dsap, llcp_sock->ssap);
 
 	memset(llcp_addr, 0, sizeof(*llcp_addr));
-	*len = sizeof(struct sockaddr_nfc_llcp);
 
 	lock_sock(sk);
 	if (!llcp_sock->dev) {
@@ -528,7 +527,7 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr,
 	       llcp_addr->service_name_len);
 	release_sock(sk);
 
-	return 0;
+	return sizeof(struct sockaddr_nfc_llcp);
 }
 
 static inline __poll_t llcp_accept_poll(struct sock *parent)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e0f3f4aeeb4f..616cb9c18f88 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3409,7 +3409,7 @@ out:
 }
 
 static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
-			       int *uaddr_len, int peer)
+			       int peer)
 {
 	struct net_device *dev;
 	struct sock *sk	= sock->sk;
@@ -3424,13 +3424,12 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
 	if (dev)
 		strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data));
 	rcu_read_unlock();
-	*uaddr_len = sizeof(*uaddr);
 
-	return 0;
+	return sizeof(*uaddr);
 }
 
 static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
-			  int *uaddr_len, int peer)
+			  int peer)
 {
 	struct net_device *dev;
 	struct sock *sk = sock->sk;
@@ -3455,9 +3454,8 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
 		sll->sll_halen = 0;
 	}
 	rcu_read_unlock();
-	*uaddr_len = offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen;
 
-	return 0;
+	return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen;
 }
 
 static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i,
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index fffcd69f63ff..f9b40e6a18a5 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -326,7 +326,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock,
 }
 
 static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
-				int *sockaddr_len, int peer)
+				int peer)
 {
 	struct sock *sk = sock->sk;
 	struct pn_sock *pn = pn_sk(sk);
@@ -337,8 +337,7 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
 		pn_sockaddr_set_object((struct sockaddr_pn *)addr,
 					pn->sobject);
 
-	*sockaddr_len = sizeof(struct sockaddr_pn);
-	return 0;
+	return sizeof(struct sockaddr_pn);
 }
 
 static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 5fb3929e3d7d..b33e5aeb4c06 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -893,7 +893,7 @@ static int qrtr_connect(struct socket *sock, struct sockaddr *saddr,
 }
 
 static int qrtr_getname(struct socket *sock, struct sockaddr *saddr,
-			int *len, int peer)
+			int peer)
 {
 	struct qrtr_sock *ipc = qrtr_sk(sock->sk);
 	struct sockaddr_qrtr qaddr;
@@ -912,12 +912,11 @@ static int qrtr_getname(struct socket *sock, struct sockaddr *saddr,
 	}
 	release_sock(sk);
 
-	*len = sizeof(qaddr);
 	qaddr.sq_family = AF_QIPCRTR;
 
 	memcpy(saddr, &qaddr, sizeof(qaddr));
 
-	return 0;
+	return sizeof(qaddr);
 }
 
 static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 744c637c86b0..0a8eefd256b3 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -110,7 +110,7 @@ void rds_wake_sk_sleep(struct rds_sock *rs)
 }
 
 static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
-		       int *uaddr_len, int peer)
+		       int peer)
 {
 	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
 	struct rds_sock *rs = rds_sk_to_rs(sock->sk);
@@ -131,8 +131,7 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
 
 	sin->sin_family = AF_INET;
 
-	*uaddr_len = sizeof(*sin);
-	return 0;
+	return sizeof(*sin);
 }
 
 /*
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 44c4652721af..08230a145042 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -227,7 +227,6 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 	struct rds_tcp_connection *tc;
 	unsigned long flags;
 	struct sockaddr_in sin;
-	int sinlen;
 	struct socket *sock;
 
 	spin_lock_irqsave(&rds_tcp_tc_list_lock, flags);
@@ -239,12 +238,10 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 
 		sock = tc->t_sock;
 		if (sock) {
-			sock->ops->getname(sock, (struct sockaddr *)&sin,
-					   &sinlen, 0);
+			sock->ops->getname(sock, (struct sockaddr *)&sin, 0);
 			tsinfo.local_addr = sin.sin_addr.s_addr;
 			tsinfo.local_port = sin.sin_port;
-			sock->ops->getname(sock, (struct sockaddr *)&sin,
-					   &sinlen, 1);
+			sock->ops->getname(sock, (struct sockaddr *)&sin, 1);
 			tsinfo.peer_addr = sin.sin_addr.s_addr;
 			tsinfo.peer_port = sin.sin_port;
 		}
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 083bd251406f..5170373b797c 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -938,7 +938,7 @@ out_release:
 }
 
 static int rose_getname(struct socket *sock, struct sockaddr *uaddr,
-	int *uaddr_len, int peer)
+	int peer)
 {
 	struct full_sockaddr_rose *srose = (struct full_sockaddr_rose *)uaddr;
 	struct sock *sk = sock->sk;
@@ -964,8 +964,7 @@ static int rose_getname(struct socket *sock, struct sockaddr *uaddr,
 			srose->srose_digis[n] = rose->source_digis[n];
 	}
 
-	*uaddr_len = sizeof(struct full_sockaddr_rose);
-	return 0;
+	return sizeof(struct full_sockaddr_rose);
 }
 
 int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct rose_neigh *neigh, unsigned int lci)
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e35d4f73d2df..0d873c58e516 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -952,16 +952,16 @@ static int sctp_inet6_supported_addrs(const struct sctp_sock *opt,
 
 /* Handle SCTP_I_WANT_MAPPED_V4_ADDR for getpeername() and getsockname() */
 static int sctp_getname(struct socket *sock, struct sockaddr *uaddr,
-			int *uaddr_len, int peer)
+			int peer)
 {
 	int rc;
 
-	rc = inet6_getname(sock, uaddr, uaddr_len, peer);
+	rc = inet6_getname(sock, uaddr, peer);
 
-	if (rc != 0)
+	if (rc < 0)
 		return rc;
 
-	*uaddr_len = sctp_v6_addr_to_user(sctp_sk(sock->sk),
+	rc = sctp_v6_addr_to_user(sctp_sk(sock->sk),
 					  (union sctp_addr *)uaddr);
 
 	return rc;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index da1a5cdefd13..38ae22b65e77 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -281,7 +281,6 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock,
 	struct in_device *in_dev;
 	struct sockaddr_in addr;
 	int rc = -ENOENT;
-	int len;
 
 	if (!dst) {
 		rc = -ENOTCONN;
@@ -293,7 +292,7 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock,
 	}
 
 	/* get address to which the internal TCP socket is bound */
-	kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len);
+	kernel_getsockname(clcsock, (struct sockaddr *)&addr);
 	/* analyze IPv4 specific data of net_device belonging to TCP socket */
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(dst->dev);
@@ -771,7 +770,7 @@ static void smc_listen_work(struct work_struct *work)
 	u8 buf[SMC_CLC_MAX_LEN];
 	struct smc_link *link;
 	int reason_code = 0;
-	int rc = 0, len;
+	int rc = 0;
 	__be32 subnet;
 	u8 prefix_len;
 	u8 ibport;
@@ -824,7 +823,7 @@ static void smc_listen_work(struct work_struct *work)
 	}
 
 	/* get address of the peer connected to the internal TCP socket */
-	kernel_getpeername(newclcsock, (struct sockaddr *)&peeraddr, &len);
+	kernel_getpeername(newclcsock, (struct sockaddr *)&peeraddr);
 
 	/* allocate connection / link group */
 	mutex_lock(&smc_create_lgr_pending);
@@ -1075,7 +1074,7 @@ out:
 }
 
 static int smc_getname(struct socket *sock, struct sockaddr *addr,
-		       int *len, int peer)
+		       int peer)
 {
 	struct smc_sock *smc;
 
@@ -1085,7 +1084,7 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr,
 
 	smc = smc_sk(sock->sk);
 
-	return smc->clcsock->ops->getname(smc->clcsock, addr, len, peer);
+	return smc->clcsock->ops->getname(smc->clcsock, addr, peer);
 }
 
 static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
diff --git a/net/socket.c b/net/socket.c
index a93c99b518ca..fac8246a8ae8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1573,8 +1573,9 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
 		goto out_fd;
 
 	if (upeer_sockaddr) {
-		if (newsock->ops->getname(newsock, (struct sockaddr *)&address,
-					  &len, 2) < 0) {
+		len = newsock->ops->getname(newsock,
+					(struct sockaddr *)&address, 2);
+		if (len < 0) {
 			err = -ECONNABORTED;
 			goto out_fd;
 		}
@@ -1654,7 +1655,7 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
 {
 	struct socket *sock;
 	struct sockaddr_storage address;
-	int len, err, fput_needed;
+	int err, fput_needed;
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
@@ -1664,10 +1665,11 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
 	if (err)
 		goto out_put;
 
-	err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0);
-	if (err)
+	err = sock->ops->getname(sock, (struct sockaddr *)&address, 0);
+	if (err < 0)
 		goto out_put;
-	err = move_addr_to_user(&address, len, usockaddr, usockaddr_len);
+        /* "err" is actually length in this case */
+	err = move_addr_to_user(&address, err, usockaddr, usockaddr_len);
 
 out_put:
 	fput_light(sock->file, fput_needed);
@@ -1685,7 +1687,7 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
 {
 	struct socket *sock;
 	struct sockaddr_storage address;
-	int len, err, fput_needed;
+	int err, fput_needed;
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock != NULL) {
@@ -1695,11 +1697,10 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
 			return err;
 		}
 
-		err =
-		    sock->ops->getname(sock, (struct sockaddr *)&address, &len,
-				       1);
-		if (!err)
-			err = move_addr_to_user(&address, len, usockaddr,
+		err = sock->ops->getname(sock, (struct sockaddr *)&address, 1);
+		if (err >= 0)
+			/* "err" is actually length in this case */
+			err = move_addr_to_user(&address, err, usockaddr,
 						usockaddr_len);
 		fput_light(sock->file, fput_needed);
 	}
@@ -3166,17 +3167,15 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
 }
 EXPORT_SYMBOL(kernel_connect);
 
-int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
-			 int *addrlen)
+int kernel_getsockname(struct socket *sock, struct sockaddr *addr)
 {
-	return sock->ops->getname(sock, addr, addrlen, 0);
+	return sock->ops->getname(sock, addr, 0);
 }
 EXPORT_SYMBOL(kernel_getsockname);
 
-int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
-			 int *addrlen)
+int kernel_getpeername(struct socket *sock, struct sockaddr *addr)
 {
-	return sock->ops->getname(sock, addr, addrlen, 1);
+	return sock->ops->getname(sock, addr, 1);
 }
 EXPORT_SYMBOL(kernel_getpeername);
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 6e432ecd7f99..806395687bb6 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1231,7 +1231,7 @@ static const struct sockaddr_in6 rpc_in6addr_loopback = {
  * negative errno is returned.
  */
 static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen,
-			struct sockaddr *buf, int buflen)
+			struct sockaddr *buf)
 {
 	struct socket *sock;
 	int err;
@@ -1269,7 +1269,7 @@ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen,
 		goto out_release;
 	}
 
-	err = kernel_getsockname(sock, buf, &buflen);
+	err = kernel_getsockname(sock, buf);
 	if (err < 0) {
 		dprintk("RPC:       getsockname failed (%d)\n", err);
 		goto out_release;
@@ -1353,7 +1353,7 @@ int rpc_localaddr(struct rpc_clnt *clnt, struct sockaddr *buf, size_t buflen)
 	rcu_read_unlock();
 
 	rpc_set_port(sap, 0);
-	err = rpc_sockname(net, sap, salen, buf, buflen);
+	err = rpc_sockname(net, sap, salen, buf);
 	put_net(net);
 	if (err != 0)
 		/* Couldn't discover local address, return ANYADDR */
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 943f2a745cd5..08cd951aaeea 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -832,12 +832,13 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	}
 	set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
 
-	err = kernel_getpeername(newsock, sin, &slen);
+	err = kernel_getpeername(newsock, sin);
 	if (err < 0) {
 		net_warn_ratelimited("%s: peername failed (err %d)!\n",
 				     serv->sv_name, -err);
 		goto failed;		/* aborted connection or whatever */
 	}
+	slen = err;
 
 	/* Ideally, we would want to reject connections from unauthorized
 	 * hosts here, but when we get encryption, the IP of the host won't
@@ -866,7 +867,8 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	if (IS_ERR(newsvsk))
 		goto failed;
 	svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen);
-	err = kernel_getsockname(newsock, sin, &slen);
+	err = kernel_getsockname(newsock, sin);
+	slen = err;
 	if (unlikely(err < 0)) {
 		dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err);
 		slen = offsetof(struct sockaddr, sa_data);
@@ -1465,7 +1467,8 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
 		err = PTR_ERR(svsk);
 		goto out;
 	}
-	if (kernel_getsockname(svsk->sk_sock, sin, &salen) == 0)
+	salen = kernel_getsockname(svsk->sk_sock, sin);
+	if (salen >= 0)
 		svc_xprt_set_local(&svsk->sk_xprt, sin, salen);
 	svc_add_new_perm_xprt(serv, &svsk->sk_xprt);
 	return svc_one_sock_name(svsk, name_return, len);
@@ -1539,10 +1542,10 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	if (error < 0)
 		goto bummer;
 
-	newlen = len;
-	error = kernel_getsockname(sock, newsin, &newlen);
+	error = kernel_getsockname(sock, newsin);
 	if (error < 0)
 		goto bummer;
+	newlen = error;
 
 	if (protocol == IPPROTO_TCP) {
 		if ((error = kernel_listen(sock, 64)) < 0)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index a6b8c1f8f92a..956e29c1438d 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1794,10 +1794,9 @@ static void xs_sock_set_reuseport(struct socket *sock)
 static unsigned short xs_sock_getport(struct socket *sock)
 {
 	struct sockaddr_storage buf;
-	int buflen;
 	unsigned short port = 0;
 
-	if (kernel_getsockname(sock, (struct sockaddr *)&buf, &buflen) < 0)
+	if (kernel_getsockname(sock, (struct sockaddr *)&buf) < 0)
 		goto out;
 	switch (buf.ss_family) {
 	case AF_INET6:
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b0323ec7971e..f93477187a90 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -665,7 +665,7 @@ exit:
  *       a completely predictable manner).
  */
 static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
-			int *uaddr_len, int peer)
+			int peer)
 {
 	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
 	struct sock *sk = sock->sk;
@@ -684,13 +684,12 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 		addr->addr.id.node = tn->own_addr;
 	}
 
-	*uaddr_len = sizeof(*addr);
 	addr->addrtype = TIPC_ADDR_ID;
 	addr->family = AF_TIPC;
 	addr->scope = 0;
 	addr->addr.name.domain = 0;
 
-	return 0;
+	return sizeof(*addr);
 }
 
 /**
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d545e1d0dea2..723698416242 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -637,7 +637,7 @@ static int unix_stream_connect(struct socket *, struct sockaddr *,
 			       int addr_len, int flags);
 static int unix_socketpair(struct socket *, struct socket *);
 static int unix_accept(struct socket *, struct socket *, int, bool);
-static int unix_getname(struct socket *, struct sockaddr *, int *, int);
+static int unix_getname(struct socket *, struct sockaddr *, int);
 static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
 static __poll_t unix_dgram_poll(struct file *, struct socket *,
 				    poll_table *);
@@ -1453,7 +1453,7 @@ out:
 }
 
 
-static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer)
+static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 {
 	struct sock *sk = sock->sk;
 	struct unix_sock *u;
@@ -1476,12 +1476,12 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_
 	if (!u->addr) {
 		sunaddr->sun_family = AF_UNIX;
 		sunaddr->sun_path[0] = 0;
-		*uaddr_len = sizeof(short);
+		err = sizeof(short);
 	} else {
 		struct unix_address *addr = u->addr;
 
-		*uaddr_len = addr->len;
-		memcpy(sunaddr, addr->name, *uaddr_len);
+		err = addr->len;
+		memcpy(sunaddr, addr->name, addr->len);
 	}
 	unix_state_unlock(sk);
 	sock_put(sk);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index e0fc84daed94..aac9b8f6552e 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -759,7 +759,7 @@ vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 }
 
 static int vsock_getname(struct socket *sock,
-			 struct sockaddr *addr, int *addr_len, int peer)
+			 struct sockaddr *addr, int peer)
 {
 	int err;
 	struct sock *sk;
@@ -794,7 +794,7 @@ static int vsock_getname(struct socket *sock,
 	 */
 	BUILD_BUG_ON(sizeof(*vm_addr) > 128);
 	memcpy(addr, vm_addr, sizeof(*vm_addr));
-	*addr_len = sizeof(*vm_addr);
+	err = sizeof(*vm_addr);
 
 out:
 	release_sock(sk);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 562cc11131f6..d49aa79b7997 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -896,7 +896,7 @@ out:
 }
 
 static int x25_getname(struct socket *sock, struct sockaddr *uaddr,
-		       int *uaddr_len, int peer)
+		       int peer)
 {
 	struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)uaddr;
 	struct sock *sk = sock->sk;
@@ -913,7 +913,7 @@ static int x25_getname(struct socket *sock, struct sockaddr *uaddr,
 		sx25->sx25_addr = x25->source_addr;
 
 	sx25->sx25_family = AF_X25;
-	*uaddr_len = sizeof(*sx25);
+	rc = sizeof(*sx25);
 
 out:
 	return rc;
diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c
index cd6932e5225c..9094f4b3b367 100644
--- a/security/tomoyo/network.c
+++ b/security/tomoyo/network.c
@@ -655,10 +655,11 @@ int tomoyo_socket_listen_permission(struct socket *sock)
 		return 0;
 	{
 		const int error = sock->ops->getname(sock, (struct sockaddr *)
-						     &addr, &addr_len, 0);
+						     &addr, 0);
 
-		if (error)
+		if (error < 0)
 			return error;
+		addr_len = error;
 	}
 	address.protocol = type;
 	address.operation = TOMOYO_NETWORK_LISTEN;
-- 
cgit v1.2.3


From 447cd7a0d7d1e5b4486e99cce289654fec9951e3 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Tue, 13 Feb 2018 12:26:44 +0300
Subject: net: Allow pernet_operations to be executed in parallel

This adds new pernet_operations::async flag to indicate operations,
which ->init(), ->exit() and ->exit_batch() methods are allowed
to be executed in parallel with the methods of any other pernet_operations.

When there are only asynchronous pernet_operations in the system,
net_mutex won't be taken for a net construction and destruction.

Also, remove BUG_ON(mutex_is_locked()) from net_assign_generic()
without replacing with the equivalent net_sem check, as there is
one more lockdep assert below.

v3: Add comment near net_mutex.

Suggested-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h |  6 ++++++
 net/core/net_namespace.c    | 30 ++++++++++++++++++++----------
 2 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include/net')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index f306b2aa15a4..9158ec1ad06f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -313,6 +313,12 @@ struct pernet_operations {
 	void (*exit_batch)(struct list_head *net_exit_list);
 	unsigned int *id;
 	size_t size;
+	/*
+	 * Indicates above methods are allowed to be executed in parallel
+	 * with methods of any other pernet_operations, i.e. they are not
+	 * need synchronization via net_mutex.
+	 */
+	bool async;
 };
 
 /*
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index f8453c438798..2a01ff32d9c7 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -29,6 +29,7 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
+/* Used only if there are !async pernet_operations registered */
 DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
@@ -41,8 +42,9 @@ struct net init_net = {
 EXPORT_SYMBOL(init_net);
 
 static bool init_net_initialized;
+static unsigned nr_sync_pernet_ops;
 /*
- * net_sem: protects: pernet_list, net_generic_ids,
+ * net_sem: protects: pernet_list, net_generic_ids, nr_sync_pernet_ops,
  * init_net_initialized and first_device pointer.
  */
 DECLARE_RWSEM(net_sem);
@@ -70,11 +72,10 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data)
 {
 	struct net_generic *ng, *old_ng;
 
-	BUG_ON(!mutex_is_locked(&net_mutex));
 	BUG_ON(id < MIN_PERNET_OPS_ID);
 
 	old_ng = rcu_dereference_protected(net->gen,
-					   lockdep_is_held(&net_mutex));
+					   lockdep_is_held(&net_sem));
 	if (old_ng->s.len > id) {
 		old_ng->ptr[id] = data;
 		return 0;
@@ -426,11 +427,14 @@ struct net *copy_net_ns(unsigned long flags,
 	rv = down_read_killable(&net_sem);
 	if (rv < 0)
 		goto put_userns;
-	rv = mutex_lock_killable(&net_mutex);
-	if (rv < 0)
-		goto up_read;
+	if (nr_sync_pernet_ops) {
+		rv = mutex_lock_killable(&net_mutex);
+		if (rv < 0)
+			goto up_read;
+	}
 	rv = setup_net(net, user_ns);
-	mutex_unlock(&net_mutex);
+	if (nr_sync_pernet_ops)
+		mutex_unlock(&net_mutex);
 up_read:
 	up_read(&net_sem);
 	if (rv < 0) {
@@ -487,7 +491,8 @@ static void cleanup_net(struct work_struct *work)
 	spin_unlock_irq(&cleanup_list_lock);
 
 	down_read(&net_sem);
-	mutex_lock(&net_mutex);
+	if (nr_sync_pernet_ops)
+		mutex_lock(&net_mutex);
 
 	/* Don't let anyone else find us. */
 	rtnl_lock();
@@ -522,7 +527,8 @@ static void cleanup_net(struct work_struct *work)
 	list_for_each_entry_reverse(ops, &pernet_list, list)
 		ops_exit_list(ops, &net_exit_list);
 
-	mutex_unlock(&net_mutex);
+	if (nr_sync_pernet_ops)
+		mutex_unlock(&net_mutex);
 
 	/* Free the net generic variables */
 	list_for_each_entry_reverse(ops, &pernet_list, list)
@@ -994,6 +1000,9 @@ again:
 		rcu_barrier();
 		if (ops->id)
 			ida_remove(&net_generic_ids, *ops->id);
+	} else if (!ops->async) {
+		pr_info_once("Pernet operations %ps are sync.\n", ops);
+		nr_sync_pernet_ops++;
 	}
 
 	return error;
@@ -1001,7 +1010,8 @@ again:
 
 static void unregister_pernet_operations(struct pernet_operations *ops)
 {
-	
+	if (!ops->async)
+		BUG_ON(nr_sync_pernet_ops-- == 0);
 	__unregister_pernet_operations(ops);
 	rcu_barrier();
 	if (ops->id)
-- 
cgit v1.2.3


From 19ff13f2a411d99af67d8e51867d54b86e1bf017 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 13 Feb 2018 08:52:01 -0800
Subject: net: Make ax25_ptr depend on CONFIG_AX25

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 ++
 include/net/ax25.h        | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include/net')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d2ef35e00626..936dc2c9dca1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1804,7 +1804,9 @@ struct net_device {
 	struct dn_dev __rcu     *dn_ptr;
 #endif
 	struct inet6_dev __rcu	*ip6_ptr;
+#if IS_ENABLED(CONFIG_AX25)
 	void			*ax25_ptr;
+#endif
 	struct wireless_dev	*ieee80211_ptr;
 	struct wpan_dev		*ieee802154_ptr;
 #if IS_ENABLED(CONFIG_MPLS_ROUTING)
diff --git a/include/net/ax25.h b/include/net/ax25.h
index 76fb39c272a7..c91bc87931c7 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -318,10 +318,12 @@ void ax25_digi_invert(const ax25_digi *, ax25_digi *);
 extern ax25_dev *ax25_dev_list;
 extern spinlock_t ax25_dev_lock;
 
+#if IS_ENABLED(CONFIG_AX25)
 static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev)
 {
 	return dev->ax25_ptr;
 }
+#endif
 
 ax25_dev *ax25_addr_ax25dev(ax25_address *);
 void ax25_dev_device_up(struct net_device *);
-- 
cgit v1.2.3


From e0f9759f530bf789e984961dce79f525b151ecf3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 13 Feb 2018 06:14:12 -0800
Subject: tcp: try to keep packet if SYN_RCV race is lost
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

배석진 reported that in some situations, packets for a given 5-tuple
end up being processed by different CPUS.

This involves RPS, and fragmentation.

배석진 is seeing packet drops when a SYN_RECV request socket is
moved into ESTABLISH state. Other states are protected by socket lock.

This is caused by a CPU losing the race, and simply not caring enough.

Since this seems to occur frequently, we can do better and perform
a second lookup.

Note that all needed memory barriers are already in the existing code,
thanks to the spin_lock()/spin_unlock() pair in inet_ehash_insert()
and reqsk_put(). The second lookup must find the new socket,
unless it has already been accepted and closed by another cpu.

Note that the fragmentation could be avoided in the first place by
use of a correct TCP MSS option in the SYN{ACK} packet, but this
does not mean we can not be more robust.

Many thanks to 배석진 for a very detailed analysis.

Reported-by: 배석진 <soukjin.bae@samsung.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        |  3 ++-
 net/ipv4/tcp_input.c     |  4 +++-
 net/ipv4/tcp_ipv4.c      | 13 ++++++++++++-
 net/ipv4/tcp_minisocks.c |  3 ++-
 net/ipv6/tcp_ipv6.c      | 13 ++++++++++++-
 5 files changed, 31 insertions(+), 5 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e3fc667f9ac2..92b06c6e7732 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -374,7 +374,8 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
 					      struct sk_buff *skb,
 					      const struct tcphdr *th);
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
-			   struct request_sock *req, bool fastopen);
+			   struct request_sock *req, bool fastopen,
+			   bool *lost_race);
 int tcp_child_process(struct sock *parent, struct sock *child,
 		      struct sk_buff *skb);
 void tcp_enter_loss(struct sock *sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 575d3c1fb6e8..a6b48f6253e3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5870,10 +5870,12 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	tp->rx_opt.saw_tstamp = 0;
 	req = tp->fastopen_rsk;
 	if (req) {
+		bool req_stolen;
+
 		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
 		    sk->sk_state != TCP_FIN_WAIT1);
 
-		if (!tcp_check_req(sk, skb, req, true))
+		if (!tcp_check_req(sk, skb, req, true, &req_stolen))
 			goto discard;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ac16795486ea..f3e52bc98980 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1672,6 +1672,7 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
+		bool req_stolen = false;
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
@@ -1694,10 +1695,20 @@ process:
 			th = (const struct tcphdr *)skb->data;
 			iph = ip_hdr(skb);
 			tcp_v4_fill_cb(skb, iph, th);
-			nsk = tcp_check_req(sk, skb, req, false);
+			nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
 		}
 		if (!nsk) {
 			reqsk_put(req);
+			if (req_stolen) {
+				/* Another cpu got exclusive access to req
+				 * and created a full blown socket.
+				 * Try to feed this packet to this socket
+				 * instead of discarding it.
+				 */
+				tcp_v4_restore_cb(skb);
+				sock_put(sk);
+				goto lookup;
+			}
 			goto discard_and_relse;
 		}
 		if (nsk == sk) {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a8384b0c11f8..e7e36433cdb5 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -578,7 +578,7 @@ EXPORT_SYMBOL(tcp_create_openreq_child);
 
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req,
-			   bool fastopen)
+			   bool fastopen, bool *req_stolen)
 {
 	struct tcp_options_received tmp_opt;
 	struct sock *child;
@@ -785,6 +785,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	sock_rps_save_rxhash(child, skb);
 	tcp_synack_rtt_meas(child, req);
+	*req_stolen = !own_req;
 	return inet_csk_complete_hashdance(sk, child, req, own_req);
 
 listen_overflow:
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 412139f4eccd..883df0ad5bfe 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1451,6 +1451,7 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
+		bool req_stolen = false;
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
@@ -1470,10 +1471,20 @@ process:
 			th = (const struct tcphdr *)skb->data;
 			hdr = ipv6_hdr(skb);
 			tcp_v6_fill_cb(skb, hdr, th);
-			nsk = tcp_check_req(sk, skb, req, false);
+			nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
 		}
 		if (!nsk) {
 			reqsk_put(req);
+			if (req_stolen) {
+				/* Another cpu got exclusive access to req
+				 * and created a full blown socket.
+				 * Try to feed this packet to this socket
+				 * instead of discarding it.
+				 */
+				tcp_v6_restore_cb(skb);
+				sock_put(sk);
+				goto lookup;
+			}
 			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-- 
cgit v1.2.3


From 0336369d3a4d65c9332476b618ff3bb9b41045e1 Mon Sep 17 00:00:00 2001
From: Brandon Streiff <brandon.streiff@ni.com>
Date: Wed, 14 Feb 2018 01:07:48 +0100
Subject: net: dsa: forward hardware timestamping ioctls to switch driver

This patch adds support to the dsa slave network device so that
switch drivers can implement the SIOC[GS]HWTSTAMP ioctls and the
ethtool timestamp-info interface.

Signed-off-by: Brandon Streiff <brandon.streiff@ni.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 15 +++++++++++++++
 net/dsa/slave.c   | 29 +++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)

(limited to 'include/net')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 6cb602dd970c..4c0df83dddaf 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -19,6 +19,7 @@
 #include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/ethtool.h>
+#include <linux/net_tstamp.h>
 #include <net/devlink.h>
 #include <net/switchdev.h>
 
@@ -367,6 +368,12 @@ struct dsa_switch_ops {
 	int	(*set_wol)(struct dsa_switch *ds, int port,
 			   struct ethtool_wolinfo *w);
 
+	/*
+	 * ethtool timestamp info
+	 */
+	int	(*get_ts_info)(struct dsa_switch *ds, int port,
+			       struct ethtool_ts_info *ts);
+
 	/*
 	 * Suspend and resume
 	 */
@@ -469,6 +476,14 @@ struct dsa_switch_ops {
 					 int port, struct net_device *br);
 	void	(*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index,
 					  int port, struct net_device *br);
+
+	/*
+	 * PTP functionality
+	 */
+	int	(*port_hwtstamp_get)(struct dsa_switch *ds, int port,
+				     struct ifreq *ifr);
+	int	(*port_hwtstamp_set)(struct dsa_switch *ds, int port,
+				     struct ifreq *ifr);
 };
 
 struct dsa_switch_driver {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index f52307296de4..935d93f0d36c 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -255,6 +255,22 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 
 static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->dp->ds;
+	int port = p->dp->index;
+
+	/* Pass through to switch driver if it supports timestamping */
+	switch (cmd) {
+	case SIOCGHWTSTAMP:
+		if (ds->ops->port_hwtstamp_get)
+			return ds->ops->port_hwtstamp_get(ds, port, ifr);
+		break;
+	case SIOCSHWTSTAMP:
+		if (ds->ops->port_hwtstamp_set)
+			return ds->ops->port_hwtstamp_set(ds, port, ifr);
+		break;
+	}
+
 	if (!dev->phydev)
 		return -ENODEV;
 
@@ -918,6 +934,18 @@ static int dsa_slave_set_rxnfc(struct net_device *dev,
 	return ds->ops->set_rxnfc(ds, dp->index, nfc);
 }
 
+static int dsa_slave_get_ts_info(struct net_device *dev,
+				 struct ethtool_ts_info *ts)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->dp->ds;
+
+	if (!ds->ops->get_ts_info)
+		return -EOPNOTSUPP;
+
+	return ds->ops->get_ts_info(ds, p->dp->index, ts);
+}
+
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_drvinfo		= dsa_slave_get_drvinfo,
 	.get_regs_len		= dsa_slave_get_regs_len,
@@ -938,6 +966,7 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.get_rxnfc		= dsa_slave_get_rxnfc,
 	.set_rxnfc		= dsa_slave_set_rxnfc,
+	.get_ts_info		= dsa_slave_get_ts_info,
 };
 
 /* legacy way, bypassing the bridge *****************************************/
-- 
cgit v1.2.3


From 90af1059c52c0031f3bfd8279c9ede153ca83275 Mon Sep 17 00:00:00 2001
From: Brandon Streiff <brandon.streiff@ni.com>
Date: Wed, 14 Feb 2018 01:07:49 +0100
Subject: net: dsa: forward timestamping callbacks to switch drivers

Forward the rx/tx timestamp machinery from the dsa infrastructure to the
switch driver.

On the rx side, defer delivery of skbs until we have an rx timestamp.
This mimicks the behavior of skb_defer_rx_timestamp.

On the tx side, identify PTP packets, clone them, and pass them to the
underlying switch driver before we transmit. This mimicks the behavior
of skb_tx_timestamp.

Adjusted txstamp API to keep the allocation and freeing of the clone
in the same central function by Richard Cochran

Signed-off-by: Brandon Streiff <brandon.streiff@ni.com>
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  5 +++++
 net/dsa/dsa.c     | 36 ++++++++++++++++++++++++++++++++++++
 net/dsa/slave.c   | 30 ++++++++++++++++++++++++++++++
 3 files changed, 71 insertions(+)

(limited to 'include/net')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 4c0df83dddaf..0ad17b63684d 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -102,6 +102,7 @@ struct dsa_platform_data {
 };
 
 struct packet_type;
+struct dsa_switch;
 
 struct dsa_device_ops {
 	struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev);
@@ -484,6 +485,10 @@ struct dsa_switch_ops {
 				     struct ifreq *ifr);
 	int	(*port_hwtstamp_set)(struct dsa_switch *ds, int port,
 				     struct ifreq *ifr);
+	bool	(*port_txtstamp)(struct dsa_switch *ds, int port,
+				 struct sk_buff *clone, unsigned int type);
+	bool	(*port_rxtstamp)(struct dsa_switch *ds, int port,
+				 struct sk_buff *skb, unsigned int type);
 };
 
 struct dsa_switch_driver {
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 6a9d0f50fbee..e63c554e0623 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -23,6 +23,7 @@
 #include <linux/netdevice.h>
 #include <linux/sysfs.h>
 #include <linux/phy_fixed.h>
+#include <linux/ptp_classify.h>
 #include <linux/gpio/consumer.h>
 #include <linux/etherdevice.h>
 
@@ -122,6 +123,38 @@ struct net_device *dsa_dev_to_net_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dsa_dev_to_net_device);
 
+/* Determine if we should defer delivery of skb until we have a rx timestamp.
+ *
+ * Called from dsa_switch_rcv. For now, this will only work if tagging is
+ * enabled on the switch. Normally the MAC driver would retrieve the hardware
+ * timestamp when it reads the packet out of the hardware. However in a DSA
+ * switch, the DSA driver owning the interface to which the packet is
+ * delivered is never notified unless we do so here.
+ */
+static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p,
+				       struct sk_buff *skb)
+{
+	struct dsa_switch *ds = p->dp->ds;
+	unsigned int type;
+
+	if (skb_headroom(skb) < ETH_HLEN)
+		return false;
+
+	__skb_push(skb, ETH_HLEN);
+
+	type = ptp_classify_raw(skb);
+
+	__skb_pull(skb, ETH_HLEN);
+
+	if (type == PTP_CLASS_NONE)
+		return false;
+
+	if (likely(ds->ops->port_rxtstamp))
+		return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type);
+
+	return false;
+}
+
 static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 			  struct packet_type *pt, struct net_device *unused)
 {
@@ -157,6 +190,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 	s->rx_bytes += skb->len;
 	u64_stats_update_end(&s->syncp);
 
+	if (dsa_skb_defer_rx_timestamp(p, skb))
+		return 0;
+
 	netif_receive_skb(skb);
 
 	return 0;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 935d93f0d36c..3376dad6dcfd 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -21,6 +21,7 @@
 #include <net/tc_act/tc_mirred.h>
 #include <linux/if_bridge.h>
 #include <linux/netpoll.h>
+#include <linux/ptp_classify.h>
 
 #include "dsa_priv.h"
 
@@ -401,6 +402,30 @@ static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev,
 	return NETDEV_TX_OK;
 }
 
+static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p,
+				 struct sk_buff *skb)
+{
+	struct dsa_switch *ds = p->dp->ds;
+	struct sk_buff *clone;
+	unsigned int type;
+
+	type = ptp_classify_raw(skb);
+	if (type == PTP_CLASS_NONE)
+		return;
+
+	if (!ds->ops->port_txtstamp)
+		return;
+
+	clone = skb_clone_sk(skb);
+	if (!clone)
+		return;
+
+	if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type))
+		return;
+
+	kfree_skb(clone);
+}
+
 static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -413,6 +438,11 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 	s->tx_bytes += skb->len;
 	u64_stats_update_end(&s->syncp);
 
+	/* Identify PTP protocol packets, clone them, and pass them to the
+	 * switch driver
+	 */
+	dsa_skb_tx_timestamp(p, skb);
+
 	/* Transmit function may have to reallocate the original SKB,
 	 * in which case it must have freed it. Only free it here on error.
 	 */
-- 
cgit v1.2.3


From 9942895b5ee4b0db53f32fbcb4a51360607aac1b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 13 Feb 2018 20:32:04 -0800
Subject: net: Move ipv4 set_lwt_redirect helper to lwtunnel

IPv4 uses set_lwt_redirect to set the lwtunnel redirect functions as
needed. Move it to lwtunnel.h as lwtunnel_set_redirect and change
IPv6 to also use it.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/lwtunnel.h | 15 +++++++++++++++
 net/ipv4/route.c       | 17 ++---------------
 net/ipv6/route.c       |  9 +--------
 3 files changed, 18 insertions(+), 23 deletions(-)

(limited to 'include/net')

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index d747ef975cd8..33fd9ba7e0e5 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -127,6 +127,17 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int lwtunnel_input(struct sk_buff *skb);
 int lwtunnel_xmit(struct sk_buff *skb);
 
+static inline void lwtunnel_set_redirect(struct dst_entry *dst)
+{
+	if (lwtunnel_output_redirect(dst->lwtstate)) {
+		dst->lwtstate->orig_output = dst->output;
+		dst->output = lwtunnel_output;
+	}
+	if (lwtunnel_input_redirect(dst->lwtstate)) {
+		dst->lwtstate->orig_input = dst->input;
+		dst->input = lwtunnel_input;
+	}
+}
 #else
 
 static inline void lwtstate_free(struct lwtunnel_state *lws)
@@ -158,6 +169,10 @@ static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)
 	return false;
 }
 
+static inline void lwtunnel_set_redirect(struct dst_entry *dst)
+{
+}
+
 static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,
 					     unsigned int mtu)
 {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b0ef4cc3e875..6ce623e3e2ab 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1645,19 +1645,6 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 	spin_unlock_bh(&fnhe_lock);
 }
 
-static void set_lwt_redirect(struct rtable *rth)
-{
-	if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
-		rth->dst.lwtstate->orig_output = rth->dst.output;
-		rth->dst.output = lwtunnel_output;
-	}
-
-	if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
-		rth->dst.lwtstate->orig_input = rth->dst.input;
-		rth->dst.input = lwtunnel_input;
-	}
-}
-
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1748,7 +1735,7 @@ rt_cache:
 
 	rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag,
 		       do_cache);
-	set_lwt_redirect(rth);
+	lwtunnel_set_redirect(&rth->dst);
 	skb_dst_set(skb, &rth->dst);
 out:
 	err = 0;
@@ -2267,7 +2254,7 @@ add:
 	}
 
 	rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache);
-	set_lwt_redirect(rth);
+	lwtunnel_set_redirect(&rth->dst);
 
 	return rth;
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9dcfadddd800..f0baae26db8f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2671,14 +2671,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
 		if (err)
 			goto out;
 		rt->dst.lwtstate = lwtstate_get(lwtstate);
-		if (lwtunnel_output_redirect(rt->dst.lwtstate)) {
-			rt->dst.lwtstate->orig_output = rt->dst.output;
-			rt->dst.output = lwtunnel_output;
-		}
-		if (lwtunnel_input_redirect(rt->dst.lwtstate)) {
-			rt->dst.lwtstate->orig_input = rt->dst.input;
-			rt->dst.input = lwtunnel_input;
-		}
+		lwtunnel_set_redirect(&rt->dst);
 	}
 
 	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
-- 
cgit v1.2.3


From 68e813aa43071377b698c662bc0214f2a833bcbb Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 14 Feb 2018 14:24:28 -0800
Subject: net/ipv4: Remove fib table id from rtable

Remove rt_table_id from rtable. It was added for getroute to return the
table id that was hit in the lookup. With the changes for fibmatch the
table id can be extracted from the fib_info returned in the fib_result
so it no longer needs to be in rtable directly.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c       | 1 -
 include/net/route.h     | 2 --
 net/ipv4/route.c        | 9 +--------
 net/ipv4/xfrm4_policy.c | 1 -
 4 files changed, 1 insertion(+), 12 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 139c61c8244a..239c78c53e58 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -736,7 +736,6 @@ static int vrf_rtable_create(struct net_device *dev)
 		return -ENOMEM;
 
 	rth->dst.output	= vrf_output;
-	rth->rt_table_id = vrf->tb_id;
 
 	rcu_assign_pointer(vrf->rth, rth);
 
diff --git a/include/net/route.h b/include/net/route.h
index 1eb9ce470e25..158833ea7988 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -65,8 +65,6 @@ struct rtable {
 	/* Miscellaneous cached information */
 	u32			rt_pmtu;
 
-	u32			rt_table_id;
-
 	struct list_head	rt_uncached;
 	struct uncached_list	*rt_uncached_list;
 };
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6ce623e3e2ab..5ca7415cd48c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1509,7 +1509,6 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 		rt->rt_pmtu = 0;
 		rt->rt_gateway = 0;
 		rt->rt_uses_gateway = 0;
-		rt->rt_table_id = 0;
 		INIT_LIST_HEAD(&rt->rt_uncached);
 
 		rt->dst.output = ip_output;
@@ -1727,8 +1726,6 @@ rt_cache:
 	}
 
 	rth->rt_is_input = 1;
-	if (res->table)
-		rth->rt_table_id = res->table->tb_id;
 	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;
@@ -2001,8 +1998,6 @@ local_input:
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_is_input = 1;
-	if (res->table)
-		rth->rt_table_id = res->table->tb_id;
 
 	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res->type == RTN_UNREACHABLE) {
@@ -2231,8 +2226,6 @@ add:
 		return ERR_PTR(-ENOBUFS);
 
 	rth->rt_iif = orig_oif;
-	if (res->table)
-		rth->rt_table_id = res->table->tb_id;
 
 	RT_CACHE_STAT_INC(out_slow_tot);
 
@@ -2762,7 +2755,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		rt->rt_flags |= RTCF_NOTIFY;
 
 	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
-		table_id = rt->rt_table_id;
+		table_id = res.table ? res.table->tb_id : 0;
 
 	if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
 		if (!res.fi) {
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 753f526cf9db..796ac4115485 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,7 +100,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt.rt_gateway = rt->rt_gateway;
 	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
-	xdst->u.rt.rt_table_id = rt->rt_table_id;
 	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
 
 	return 0;
-- 
cgit v1.2.3


From b7b347fa3cd496ad5b4cbcc8ea2931847c4d0d78 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:53 -0500
Subject: net: sched: act: fix code style

This patch is used by subsequent patches. It fixes code style issues
caught by checkpatch.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h  |  5 +++--
 net/sched/act_api.c    | 12 ++++++------
 net/sched/act_mirred.c |  6 +++---
 3 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 6ed9692f20bd..32ef544f4ddc 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -87,12 +87,13 @@ struct tc_action_ops {
 		       struct tcf_result *);
 	int     (*dump)(struct sk_buff *, struct tc_action *, int, int);
 	void	(*cleanup)(struct tc_action *);
-	int     (*lookup)(struct net *, struct tc_action **, u32);
+	int     (*lookup)(struct net *net, struct tc_action **a, u32 index);
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
 			int bind);
 	int     (*walk)(struct net *, struct sk_buff *,
-			struct netlink_callback *, int, const struct tc_action_ops *);
+			struct netlink_callback *, int,
+			const struct tc_action_ops *);
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
 	struct net_device *(*get_dev)(const struct tc_action *a);
 };
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 624995564e5a..a32e6c2edbf6 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -621,7 +621,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			goto err_out;
 		err = -EINVAL;
 		kind = tb[TCA_ACT_KIND];
-		if (kind == NULL)
+		if (!kind)
 			goto err_out;
 		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ)
 			goto err_out;
@@ -822,7 +822,7 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
 	t->tca__pad2 = 0;
 
 	nest = nla_nest_start(skb, TCA_ACT_TAB);
-	if (nest == NULL)
+	if (!nest)
 		goto out_nlmsg_trim;
 
 	if (tcf_action_dump(skb, actions, bind, ref) < 0)
@@ -934,7 +934,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	t->tca__pad2 = 0;
 
 	nest = nla_nest_start(skb, TCA_ACT_TAB);
-	if (nest == NULL)
+	if (!nest)
 		goto out_module_put;
 
 	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
@@ -1007,10 +1007,10 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 		return ret;
 
 	if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) {
-		if (tb[1] != NULL)
+		if (tb[1])
 			return tca_action_flush(net, tb[1], n, portid);
-		else
-			return -EINVAL;
+
+		return -EINVAL;
 	}
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index e6ff88f72900..abcd5f12b913 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -80,12 +80,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	bool exists = false;
 	int ret;
 
-	if (nla == NULL)
+	if (!nla)
 		return -EINVAL;
 	ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, NULL);
 	if (ret < 0)
 		return ret;
-	if (tb[TCA_MIRRED_PARMS] == NULL)
+	if (!tb[TCA_MIRRED_PARMS])
 		return -EINVAL;
 	parm = nla_data(tb[TCA_MIRRED_PARMS]);
 
@@ -117,7 +117,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		if (dev == NULL)
+		if (!dev)
 			return -EINVAL;
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_mirred_ops, bind, true);
-- 
cgit v1.2.3


From 10defbd29e6218c1cab5c217a9d808fc05e3938a Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:54 -0500
Subject: net: sched: act: add extack to init

This patch adds extack to tcf_action_init and tcf_action_init_1
functions. These are necessary to make individual extack handling in
each act implementation.

Based on work by David Ahern <dsahern@gmail.com>

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  5 +++--
 net/sched/act_api.c   | 17 +++++++++++------
 net/sched/cls_api.c   |  4 ++--
 3 files changed, 16 insertions(+), 10 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 32ef544f4ddc..41d95930ffbc 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -163,10 +163,11 @@ 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 list_head *actions);
+		    struct list_head *actions, struct netlink_ext_ack *extack);
 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);
+				    char *name, int ovr, int bind,
+				    struct netlink_ext_ack *extack);
 int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a32e6c2edbf6..662574646256 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -605,7 +605,8 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 
 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)
+				    char *name, int ovr, int bind,
+				    struct netlink_ext_ack *extack)
 {
 	struct tc_action *a;
 	struct tc_action_ops *a_o;
@@ -726,7 +727,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
 
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct list_head *actions)
+		    struct list_head *actions, struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
@@ -738,7 +739,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		return err;
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
-		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind);
+		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
+					extack);
 		if (IS_ERR(act)) {
 			err = PTR_ERR(act);
 			goto err;
@@ -1062,12 +1064,14 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
 }
 
 static int tcf_action_add(struct net *net, struct nlattr *nla,
-			  struct nlmsghdr *n, u32 portid, int ovr)
+			  struct nlmsghdr *n, u32 portid, int ovr,
+			  struct netlink_ext_ack *extack)
 {
 	int ret = 0;
 	LIST_HEAD(actions);
 
-	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions);
+	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
+			      extack);
 	if (ret)
 		return ret;
 
@@ -1115,7 +1119,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 		if (n->nlmsg_flags & NLM_F_REPLACE)
 			ovr = 1;
 replay:
-		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr);
+		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
+				     extack);
 		if (ret == -EAGAIN)
 			goto replay;
 		break;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2bc1bc23d42e..f21610c5da1a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1434,7 +1434,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 		if (exts->police && tb[exts->police]) {
 			act = tcf_action_init_1(net, tp, tb[exts->police],
 						rate_tlv, "police", ovr,
-						TCA_ACT_BIND);
+						TCA_ACT_BIND, extack);
 			if (IS_ERR(act))
 				return PTR_ERR(act);
 
@@ -1447,7 +1447,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 
 			err = tcf_action_init(net, tp, tb[exts->action],
 					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
-					      &actions);
+					      &actions, extack);
 			if (err)
 				return err;
 			list_for_each_entry(act, &actions, list)
-- 
cgit v1.2.3


From ee99b2d8bf4ad6d03046a8c2f25bad7cfd9de64a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 16 Feb 2018 16:03:39 -0500
Subject: net: Revert sched action extack support series.

It was mis-applied and the changes had rejects.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h  | 10 ++++------
 net/sched/act_api.c    | 29 ++++++++++++-----------------
 net/sched/act_mirred.c |  6 +++---
 net/sched/cls_api.c    |  4 ++--
 4 files changed, 21 insertions(+), 28 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 41d95930ffbc..6ed9692f20bd 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -87,13 +87,12 @@ struct tc_action_ops {
 		       struct tcf_result *);
 	int     (*dump)(struct sk_buff *, struct tc_action *, int, int);
 	void	(*cleanup)(struct tc_action *);
-	int     (*lookup)(struct net *net, struct tc_action **a, u32 index);
+	int     (*lookup)(struct net *, struct tc_action **, u32);
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
 			int bind);
 	int     (*walk)(struct net *, struct sk_buff *,
-			struct netlink_callback *, int,
-			const struct tc_action_ops *);
+			struct netlink_callback *, int, const struct tc_action_ops *);
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
 	struct net_device *(*get_dev)(const struct tc_action *a);
 };
@@ -163,11 +162,10 @@ 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 list_head *actions, struct netlink_ext_ack *extack);
+		    struct list_head *actions);
 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 netlink_ext_ack *extack);
+				    char *name, int ovr, int bind);
 int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 662574646256..624995564e5a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -605,8 +605,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 
 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 netlink_ext_ack *extack)
+				    char *name, int ovr, int bind)
 {
 	struct tc_action *a;
 	struct tc_action_ops *a_o;
@@ -622,7 +621,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			goto err_out;
 		err = -EINVAL;
 		kind = tb[TCA_ACT_KIND];
-		if (!kind)
+		if (kind == NULL)
 			goto err_out;
 		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ)
 			goto err_out;
@@ -727,7 +726,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
 
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct list_head *actions, struct netlink_ext_ack *extack)
+		    struct list_head *actions)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
@@ -739,8 +738,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		return err;
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
-		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
-					extack);
+		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind);
 		if (IS_ERR(act)) {
 			err = PTR_ERR(act);
 			goto err;
@@ -824,7 +822,7 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
 	t->tca__pad2 = 0;
 
 	nest = nla_nest_start(skb, TCA_ACT_TAB);
-	if (!nest)
+	if (nest == NULL)
 		goto out_nlmsg_trim;
 
 	if (tcf_action_dump(skb, actions, bind, ref) < 0)
@@ -936,7 +934,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	t->tca__pad2 = 0;
 
 	nest = nla_nest_start(skb, TCA_ACT_TAB);
-	if (!nest)
+	if (nest == NULL)
 		goto out_module_put;
 
 	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
@@ -1009,10 +1007,10 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 		return ret;
 
 	if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) {
-		if (tb[1])
+		if (tb[1] != NULL)
 			return tca_action_flush(net, tb[1], n, portid);
-
-		return -EINVAL;
+		else
+			return -EINVAL;
 	}
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
@@ -1064,14 +1062,12 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
 }
 
 static int tcf_action_add(struct net *net, struct nlattr *nla,
-			  struct nlmsghdr *n, u32 portid, int ovr,
-			  struct netlink_ext_ack *extack)
+			  struct nlmsghdr *n, u32 portid, int ovr)
 {
 	int ret = 0;
 	LIST_HEAD(actions);
 
-	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
-			      extack);
+	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions);
 	if (ret)
 		return ret;
 
@@ -1119,8 +1115,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 		if (n->nlmsg_flags & NLM_F_REPLACE)
 			ovr = 1;
 replay:
-		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
-				     extack);
+		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr);
 		if (ret == -EAGAIN)
 			goto replay;
 		break;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index abcd5f12b913..e6ff88f72900 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -80,12 +80,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	bool exists = false;
 	int ret;
 
-	if (!nla)
+	if (nla == NULL)
 		return -EINVAL;
 	ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, NULL);
 	if (ret < 0)
 		return ret;
-	if (!tb[TCA_MIRRED_PARMS])
+	if (tb[TCA_MIRRED_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_MIRRED_PARMS]);
 
@@ -117,7 +117,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		if (!dev)
+		if (dev == NULL)
 			return -EINVAL;
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_mirred_ops, bind, true);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f21610c5da1a..2bc1bc23d42e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1434,7 +1434,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 		if (exts->police && tb[exts->police]) {
 			act = tcf_action_init_1(net, tp, tb[exts->police],
 						rate_tlv, "police", ovr,
-						TCA_ACT_BIND, extack);
+						TCA_ACT_BIND);
 			if (IS_ERR(act))
 				return PTR_ERR(act);
 
@@ -1447,7 +1447,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 
 			err = tcf_action_init(net, tp, tb[exts->action],
 					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
-					      &actions, extack);
+					      &actions);
 			if (err)
 				return err;
 			list_for_each_entry(act, &actions, list)
-- 
cgit v1.2.3


From 1af85155813622767d223af6d4dff283ebeea7a7 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:53 -0500
Subject: net: sched: act: fix code style

This patch is used by subsequent patches. It fixes code style issues
caught by checkpatch.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h  |  5 +++--
 net/sched/act_api.c    | 12 ++++++------
 net/sched/act_mirred.c |  6 +++---
 3 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 6ed9692f20bd..32ef544f4ddc 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -87,12 +87,13 @@ struct tc_action_ops {
 		       struct tcf_result *);
 	int     (*dump)(struct sk_buff *, struct tc_action *, int, int);
 	void	(*cleanup)(struct tc_action *);
-	int     (*lookup)(struct net *, struct tc_action **, u32);
+	int     (*lookup)(struct net *net, struct tc_action **a, u32 index);
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
 			int bind);
 	int     (*walk)(struct net *, struct sk_buff *,
-			struct netlink_callback *, int, const struct tc_action_ops *);
+			struct netlink_callback *, int,
+			const struct tc_action_ops *);
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
 	struct net_device *(*get_dev)(const struct tc_action *a);
 };
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 624995564e5a..a32e6c2edbf6 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -621,7 +621,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			goto err_out;
 		err = -EINVAL;
 		kind = tb[TCA_ACT_KIND];
-		if (kind == NULL)
+		if (!kind)
 			goto err_out;
 		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ)
 			goto err_out;
@@ -822,7 +822,7 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
 	t->tca__pad2 = 0;
 
 	nest = nla_nest_start(skb, TCA_ACT_TAB);
-	if (nest == NULL)
+	if (!nest)
 		goto out_nlmsg_trim;
 
 	if (tcf_action_dump(skb, actions, bind, ref) < 0)
@@ -934,7 +934,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	t->tca__pad2 = 0;
 
 	nest = nla_nest_start(skb, TCA_ACT_TAB);
-	if (nest == NULL)
+	if (!nest)
 		goto out_module_put;
 
 	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
@@ -1007,10 +1007,10 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 		return ret;
 
 	if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) {
-		if (tb[1] != NULL)
+		if (tb[1])
 			return tca_action_flush(net, tb[1], n, portid);
-		else
-			return -EINVAL;
+
+		return -EINVAL;
 	}
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index e6ff88f72900..abcd5f12b913 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -80,12 +80,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	bool exists = false;
 	int ret;
 
-	if (nla == NULL)
+	if (!nla)
 		return -EINVAL;
 	ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, NULL);
 	if (ret < 0)
 		return ret;
-	if (tb[TCA_MIRRED_PARMS] == NULL)
+	if (!tb[TCA_MIRRED_PARMS])
 		return -EINVAL;
 	parm = nla_data(tb[TCA_MIRRED_PARMS]);
 
@@ -117,7 +117,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		if (dev == NULL)
+		if (!dev)
 			return -EINVAL;
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_mirred_ops, bind, true);
-- 
cgit v1.2.3


From aea0d727899140820a631bac78f36e9d9ef15ef6 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:54 -0500
Subject: net: sched: act: add extack to init

This patch adds extack to tcf_action_init and tcf_action_init_1
functions. These are necessary to make individual extack handling in
each act implementation.

Based on work by David Ahern <dsahern@gmail.com>

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  5 +++--
 net/sched/act_api.c   | 17 +++++++++++------
 net/sched/cls_api.c   |  4 ++--
 3 files changed, 16 insertions(+), 10 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 32ef544f4ddc..41d95930ffbc 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -163,10 +163,11 @@ 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 list_head *actions);
+		    struct list_head *actions, struct netlink_ext_ack *extack);
 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);
+				    char *name, int ovr, int bind,
+				    struct netlink_ext_ack *extack);
 int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a32e6c2edbf6..662574646256 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -605,7 +605,8 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 
 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)
+				    char *name, int ovr, int bind,
+				    struct netlink_ext_ack *extack)
 {
 	struct tc_action *a;
 	struct tc_action_ops *a_o;
@@ -726,7 +727,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
 
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct list_head *actions)
+		    struct list_head *actions, struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
@@ -738,7 +739,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		return err;
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
-		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind);
+		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
+					extack);
 		if (IS_ERR(act)) {
 			err = PTR_ERR(act);
 			goto err;
@@ -1062,12 +1064,14 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
 }
 
 static int tcf_action_add(struct net *net, struct nlattr *nla,
-			  struct nlmsghdr *n, u32 portid, int ovr)
+			  struct nlmsghdr *n, u32 portid, int ovr,
+			  struct netlink_ext_ack *extack)
 {
 	int ret = 0;
 	LIST_HEAD(actions);
 
-	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions);
+	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
+			      extack);
 	if (ret)
 		return ret;
 
@@ -1115,7 +1119,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 		if (n->nlmsg_flags & NLM_F_REPLACE)
 			ovr = 1;
 replay:
-		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr);
+		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
+				     extack);
 		if (ret == -EAGAIN)
 			goto replay;
 		break;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2bc1bc23d42e..f21610c5da1a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1434,7 +1434,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 		if (exts->police && tb[exts->police]) {
 			act = tcf_action_init_1(net, tp, tb[exts->police],
 						rate_tlv, "police", ovr,
-						TCA_ACT_BIND);
+						TCA_ACT_BIND, extack);
 			if (IS_ERR(act))
 				return PTR_ERR(act);
 
@@ -1447,7 +1447,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 
 			err = tcf_action_init(net, tp, tb[exts->action],
 					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
-					      &actions);
+					      &actions, extack);
 			if (err)
 				return err;
 			list_for_each_entry(act, &actions, list)
-- 
cgit v1.2.3


From 589dad6d71a72dd7912e5070c63f6bf1f561b5cf Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:56 -0500
Subject: net: sched: act: add extack to init callback

This patch adds extack support for act init callback api. This
prepares to handle extack support inside each specific act
implementation.

Based on work by David Ahern <dsahern@gmail.com>

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      | 2 +-
 net/sched/act_api.c        | 5 +++--
 net/sched/act_bpf.c        | 2 +-
 net/sched/act_connmark.c   | 3 ++-
 net/sched/act_csum.c       | 2 +-
 net/sched/act_gact.c       | 2 +-
 net/sched/act_ife.c        | 2 +-
 net/sched/act_ipt.c        | 4 ++--
 net/sched/act_mirred.c     | 2 +-
 net/sched/act_nat.c        | 3 ++-
 net/sched/act_pedit.c      | 2 +-
 net/sched/act_police.c     | 3 ++-
 net/sched/act_sample.c     | 2 +-
 net/sched/act_simple.c     | 2 +-
 net/sched/act_skbedit.c    | 2 +-
 net/sched/act_skbmod.c     | 2 +-
 net/sched/act_tunnel_key.c | 2 +-
 net/sched/act_vlan.c       | 2 +-
 18 files changed, 24 insertions(+), 20 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 41d95930ffbc..3717e0f2bb1b 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -90,7 +90,7 @@ struct tc_action_ops {
 	int     (*lookup)(struct net *net, struct tc_action **a, u32 index);
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
-			int bind);
+			int bind, struct netlink_ext_ack *extack);
 	int     (*walk)(struct net *, struct sk_buff *,
 			struct netlink_callback *, int,
 			const struct tc_action_ops *);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8e77ddd9f0ad..576a0c311e5e 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -680,9 +680,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 
 	/* backward compatibility for policer */
 	if (name == NULL)
-		err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind);
+		err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
+				extack);
 	else
-		err = a_o->init(net, nla, est, &a, ovr, bind);
+		err = a_o->init(net, nla, est, &a, ovr, bind, extack);
 	if (err < 0)
 		goto err_mod;
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index b3f2c15affa7..b3ebfa9598e2 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -272,7 +272,7 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
 
 static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act,
-			int replace, int bind)
+			int replace, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 2b15ba84e0c8..20e0215360b5 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -96,7 +96,8 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
 
 static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 			     struct nlattr *est, struct tc_action **a,
-			     int ovr, int bind)
+			     int ovr, int bind,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
 	struct nlattr *tb[TCA_CONNMARK_MAX + 1];
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index b7ba9b06b147..3b8c48bb2683 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -46,7 +46,7 @@ static struct tc_action_ops act_csum_ops;
 
 static int tcf_csum_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a, int ovr,
-			 int bind)
+			 int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 	struct tcf_csum_params *params_old, *params_new;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index b56986d41c87..912f3398f1c1 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -56,7 +56,7 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = {
 
 static int tcf_gact_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
-			 int ovr, int bind)
+			 int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 	struct nlattr *tb[TCA_GACT_MAX + 1];
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 5954e992685a..e5127d400737 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -447,7 +447,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 
 static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a,
-			int ovr, int bind)
+			int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 	struct nlattr *tb[TCA_IFE_MAX + 1];
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 06e380ae0928..6894cfa83863 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -193,7 +193,7 @@ err1:
 
 static int tcf_ipt_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a, int ovr,
-			int bind)
+			int bind, struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
 			      bind);
@@ -201,7 +201,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla,
 
 static int tcf_xt_init(struct net *net, struct nlattr *nla,
 		       struct nlattr *est, struct tc_action **a, int ovr,
-		       int bind)
+		       int bind, struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
 			      bind);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index abcd5f12b913..7ccd4c71179f 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -69,7 +69,7 @@ static struct tc_action_ops act_mirred_ops;
 
 static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a, int ovr,
-			   int bind)
+			   int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 	struct nlattr *tb[TCA_MIRRED_MAX + 1];
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 98c6a4b2f523..7e5ebd7f52a6 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -37,7 +37,8 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
 };
 
 static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
-			struct tc_action **a, int ovr, int bind)
+			struct tc_action **a, int ovr, int bind,
+			struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 	struct nlattr *tb[TCA_NAT_MAX + 1];
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 349beaffb29e..bb2c35ed6f10 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -132,7 +132,7 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
 
 static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
-			  int ovr, int bind)
+			  int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 	struct nlattr *tb[TCA_PEDIT_MAX + 1];
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 95d3c9097b25..6b6facbe251b 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -74,7 +74,8 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 
 static int tcf_act_police_init(struct net *net, struct nlattr *nla,
 			       struct nlattr *est, struct tc_action **a,
-			       int ovr, int bind)
+			       int ovr, int bind,
+			       struct netlink_ext_ack *extack)
 {
 	int ret = 0, err;
 	struct nlattr *tb[TCA_POLICE_MAX + 1];
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 1ba0df238756..f4579ceba1f6 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -37,7 +37,7 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
 
 static int tcf_sample_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a, int ovr,
-			   int bind)
+			   int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 425eac11f6da..b0346347c5f0 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -79,7 +79,7 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = {
 
 static int tcf_simp_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
-			 int ovr, int bind)
+			 int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 	struct nlattr *tb[TCA_DEF_MAX + 1];
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 5a3f691bb545..7651c9d2182d 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -66,7 +66,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 			    struct nlattr *est, struct tc_action **a,
-			    int ovr, int bind)
+			    int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 	struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index fa975262dbac..1266449aa8ea 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -84,7 +84,7 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
 
 static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
-			   int ovr, int bind)
+			   int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 	struct nlattr *tb[TCA_SKBMOD_MAX + 1];
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 0e23aac09ad6..dde01eca7ed0 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -70,7 +70,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
-			   int ovr, int bind)
+			   int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 	struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index e1a1b3f3983a..6c387310b1b6 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -109,7 +109,7 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
 
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
-			 int ovr, int bind)
+			 int ovr, int bind, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
-- 
cgit v1.2.3


From 331a9295de23a9428adb7f593d0701d393a2079e Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:57 -0500
Subject: net: sched: act: add extack for lookup callback

This patch adds extack support for act lookup callback api. This
prepares to handle extack support inside each specific act
implementation.

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      | 3 ++-
 net/sched/act_api.c        | 2 +-
 net/sched/act_bpf.c        | 3 ++-
 net/sched/act_connmark.c   | 3 ++-
 net/sched/act_csum.c       | 3 ++-
 net/sched/act_gact.c       | 3 ++-
 net/sched/act_ife.c        | 3 ++-
 net/sched/act_ipt.c        | 6 ++++--
 net/sched/act_mirred.c     | 3 ++-
 net/sched/act_nat.c        | 3 ++-
 net/sched/act_pedit.c      | 3 ++-
 net/sched/act_police.c     | 3 ++-
 net/sched/act_sample.c     | 3 ++-
 net/sched/act_simple.c     | 3 ++-
 net/sched/act_skbedit.c    | 3 ++-
 net/sched/act_skbmod.c     | 3 ++-
 net/sched/act_tunnel_key.c | 3 ++-
 net/sched/act_vlan.c       | 3 ++-
 18 files changed, 37 insertions(+), 19 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3717e0f2bb1b..0bd65db506ba 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -87,7 +87,8 @@ struct tc_action_ops {
 		       struct tcf_result *);
 	int     (*dump)(struct sk_buff *, struct tc_action *, int, int);
 	void	(*cleanup)(struct tc_action *);
-	int     (*lookup)(struct net *net, struct tc_action **a, u32 index);
+	int     (*lookup)(struct net *net, struct tc_action **a, u32 index,
+			  struct netlink_ext_ack *extack);
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
 			int bind, struct netlink_ext_ack *extack);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 576a0c311e5e..74ed1e288e57 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -901,7 +901,7 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla,
 		goto err_out;
 	}
 	err = -ENOENT;
-	if (ops->lookup(net, &a, index) == 0)
+	if (ops->lookup(net, &a, index, extack) == 0)
 		goto err_mod;
 
 	module_put(ops->owner);
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index b3ebfa9598e2..d9654b863347 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -374,7 +374,8 @@ static int tcf_bpf_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 20e0215360b5..0504b7600fb6 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -184,7 +184,8 @@ static int tcf_connmark_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index,
+			       struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 3b8c48bb2683..bdd17b9ef034 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -638,7 +638,8 @@ static int tcf_csum_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 912f3398f1c1..e1e69e38f4b0 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -208,7 +208,8 @@ static int tcf_gact_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index e5127d400737..0b70fb0cc609 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -831,7 +831,8 @@ static int tcf_ife_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 6894cfa83863..f29af79a2d1f 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -310,7 +310,8 @@ static int tcf_ipt_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ipt_net_id);
 
@@ -358,7 +359,8 @@ static int tcf_xt_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, xt_net_id);
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 7ccd4c71179f..9980c6affb5e 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -272,7 +272,8 @@ static int tcf_mirred_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 7e5ebd7f52a6..6f6d7667ef9a 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -285,7 +285,8 @@ static int tcf_nat_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index bb2c35ed6f10..308b2680a6d9 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -426,7 +426,8 @@ static int tcf_pedit_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index,
+			    struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 6b6facbe251b..1292f880eab0 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -305,7 +305,8 @@ nla_put_failure:
 	return -1;
 }
 
-static int tcf_police_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_police_search(struct net *net, struct tc_action **a, u32 index,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index f4579ceba1f6..22379b2cfd1a 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -209,7 +209,8 @@ static int tcf_sample_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index b0346347c5f0..3ebf71470977 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -177,7 +177,8 @@ static int tcf_simp_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 7651c9d2182d..ff1970e14016 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -215,7 +215,8 @@ static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index,
+			      struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 1266449aa8ea..110d7c1f823d 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -239,7 +239,8 @@ static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index dde01eca7ed0..65a19928f1a9 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -298,7 +298,8 @@ static int tunnel_key_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index)
+static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 6c387310b1b6..03dcbbc5ffd2 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -274,7 +274,8 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops);
 }
 
-static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 
-- 
cgit v1.2.3


From 417801055b8cb4c052e989289ccf24a673178bbc Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:58 -0500
Subject: net: sched: act: add extack for walk callback

This patch adds extack support for act walker callback api. This
prepares to handle extack support inside each specific act
implementation.

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      | 3 ++-
 net/sched/act_api.c        | 4 ++--
 net/sched/act_bpf.c        | 3 ++-
 net/sched/act_connmark.c   | 3 ++-
 net/sched/act_csum.c       | 3 ++-
 net/sched/act_gact.c       | 3 ++-
 net/sched/act_ife.c        | 3 ++-
 net/sched/act_ipt.c        | 6 ++++--
 net/sched/act_mirred.c     | 3 ++-
 net/sched/act_nat.c        | 3 ++-
 net/sched/act_pedit.c      | 3 ++-
 net/sched/act_police.c     | 3 ++-
 net/sched/act_sample.c     | 3 ++-
 net/sched/act_simple.c     | 3 ++-
 net/sched/act_skbedit.c    | 3 ++-
 net/sched/act_skbmod.c     | 3 ++-
 net/sched/act_tunnel_key.c | 3 ++-
 net/sched/act_vlan.c       | 3 ++-
 18 files changed, 38 insertions(+), 20 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 0bd65db506ba..ab3529255377 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -94,7 +94,8 @@ struct tc_action_ops {
 			int bind, struct netlink_ext_ack *extack);
 	int     (*walk)(struct net *, struct sk_buff *,
 			struct netlink_callback *, int,
-			const struct tc_action_ops *);
+			const struct tc_action_ops *,
+			struct netlink_ext_ack *);
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
 	struct net_device *(*get_dev)(const struct tc_action *a);
 };
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 74ed1e288e57..ab107997b259 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -963,7 +963,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 		goto out_module_put;
 	}
 
-	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
+	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops, extack);
 	if (err <= 0) {
 		nla_nest_cancel(skb, nest);
 		goto out_module_put;
@@ -1255,7 +1255,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
 	if (nest == NULL)
 		goto out_module_put;
 
-	ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o);
+	ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o, NULL);
 	if (ret < 0)
 		goto out_module_put;
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index d9654b863347..7e01e2c710c4 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -367,7 +367,8 @@ static void tcf_bpf_cleanup(struct tc_action *act)
 
 static int tcf_bpf_walker(struct net *net, struct sk_buff *skb,
 			  struct netlink_callback *cb, int type,
-			  const struct tc_action_ops *ops)
+			  const struct tc_action_ops *ops,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 0504b7600fb6..cb722da0bb15 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -177,7 +177,8 @@ nla_put_failure:
 
 static int tcf_connmark_walker(struct net *net, struct sk_buff *skb,
 			       struct netlink_callback *cb, int type,
-			       const struct tc_action_ops *ops)
+			       const struct tc_action_ops *ops,
+			       struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index bdd17b9ef034..3e8efadb750f 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -631,7 +631,8 @@ static void tcf_csum_cleanup(struct tc_action *a)
 
 static int tcf_csum_walker(struct net *net, struct sk_buff *skb,
 			   struct netlink_callback *cb, int type,
-			   const struct tc_action_ops *ops)
+			   const struct tc_action_ops *ops,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e1e69e38f4b0..d96ebe4bb65a 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -201,7 +201,8 @@ nla_put_failure:
 
 static int tcf_gact_walker(struct net *net, struct sk_buff *skb,
 			   struct netlink_callback *cb, int type,
-			   const struct tc_action_ops *ops)
+			   const struct tc_action_ops *ops,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 0b70fb0cc609..b777e381e0dd 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -824,7 +824,8 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a,
 
 static int tcf_ife_walker(struct net *net, struct sk_buff *skb,
 			  struct netlink_callback *cb, int type,
-			  const struct tc_action_ops *ops)
+			  const struct tc_action_ops *ops,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index f29af79a2d1f..f33a8cc5dee6 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -303,7 +303,8 @@ nla_put_failure:
 
 static int tcf_ipt_walker(struct net *net, struct sk_buff *skb,
 			  struct netlink_callback *cb, int type,
-			  const struct tc_action_ops *ops)
+			  const struct tc_action_ops *ops,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ipt_net_id);
 
@@ -352,7 +353,8 @@ static struct pernet_operations ipt_net_ops = {
 
 static int tcf_xt_walker(struct net *net, struct sk_buff *skb,
 			 struct netlink_callback *cb, int type,
-			 const struct tc_action_ops *ops)
+			 const struct tc_action_ops *ops,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, xt_net_id);
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 9980c6affb5e..3dcd295ea6a7 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -265,7 +265,8 @@ nla_put_failure:
 
 static int tcf_mirred_walker(struct net *net, struct sk_buff *skb,
 			     struct netlink_callback *cb, int type,
-			     const struct tc_action_ops *ops)
+			     const struct tc_action_ops *ops,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 6f6d7667ef9a..67243cdc0588 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -278,7 +278,8 @@ nla_put_failure:
 
 static int tcf_nat_walker(struct net *net, struct sk_buff *skb,
 			  struct netlink_callback *cb, int type,
-			  const struct tc_action_ops *ops)
+			  const struct tc_action_ops *ops,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 308b2680a6d9..6d6481f6bffa 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -419,7 +419,8 @@ nla_put_failure:
 
 static int tcf_pedit_walker(struct net *net, struct sk_buff *skb,
 			    struct netlink_callback *cb, int type,
-			    const struct tc_action_ops *ops)
+			    const struct tc_action_ops *ops,
+			    struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 1292f880eab0..ff803414a736 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -58,7 +58,8 @@ static struct tc_action_ops act_police_ops;
 
 static int tcf_act_police_walker(struct net *net, struct sk_buff *skb,
 				 struct netlink_callback *cb, int type,
-				 const struct tc_action_ops *ops)
+				 const struct tc_action_ops *ops,
+				 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 22379b2cfd1a..7a2b6a33f239 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -202,7 +202,8 @@ nla_put_failure:
 
 static int tcf_sample_walker(struct net *net, struct sk_buff *skb,
 			     struct netlink_callback *cb, int type,
-			     const struct tc_action_ops *ops)
+			     const struct tc_action_ops *ops,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 3ebf71470977..3f5474d20702 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -170,7 +170,8 @@ nla_put_failure:
 
 static int tcf_simp_walker(struct net *net, struct sk_buff *skb,
 			   struct netlink_callback *cb, int type,
-			   const struct tc_action_ops *ops)
+			   const struct tc_action_ops *ops,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index ff1970e14016..d99b6f1f5181 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -208,7 +208,8 @@ nla_put_failure:
 
 static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb,
 			      struct netlink_callback *cb, int type,
-			      const struct tc_action_ops *ops)
+			      const struct tc_action_ops *ops,
+			      struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 110d7c1f823d..369ea85d0f02 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -232,7 +232,8 @@ nla_put_failure:
 
 static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb,
 			     struct netlink_callback *cb, int type,
-			     const struct tc_action_ops *ops)
+			     const struct tc_action_ops *ops,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 65a19928f1a9..bced6fd00d43 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -291,7 +291,8 @@ nla_put_failure:
 
 static int tunnel_key_walker(struct net *net, struct sk_buff *skb,
 			     struct netlink_callback *cb, int type,
-			     const struct tc_action_ops *ops)
+			     const struct tc_action_ops *ops,
+			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 03dcbbc5ffd2..7cf409443d02 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -267,7 +267,8 @@ nla_put_failure:
 
 static int tcf_vlan_walker(struct net *net, struct sk_buff *skb,
 			   struct netlink_callback *cb, int type,
-			   const struct tc_action_ops *ops)
+			   const struct tc_action_ops *ops,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 
-- 
cgit v1.2.3


From b36201455aa0749e8708ef97ed9c1c9ece29a113 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Thu, 15 Feb 2018 10:54:59 -0500
Subject: net: sched: act: handle extack in tcf_generic_walker

This patch adds extack handling for a common used TC act function
"tcf_generic_walker()" to add an extack message on failures.
The tcf_generic_walker() function can fail if get a invalid command
different than DEL and GET. The naming "action" here is wrong, the
correct naming would be command.

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      | 3 ++-
 net/sched/act_api.c        | 6 ++++--
 net/sched/act_bpf.c        | 2 +-
 net/sched/act_connmark.c   | 2 +-
 net/sched/act_csum.c       | 2 +-
 net/sched/act_gact.c       | 2 +-
 net/sched/act_ife.c        | 2 +-
 net/sched/act_ipt.c        | 4 ++--
 net/sched/act_mirred.c     | 2 +-
 net/sched/act_nat.c        | 2 +-
 net/sched/act_pedit.c      | 2 +-
 net/sched/act_police.c     | 2 +-
 net/sched/act_sample.c     | 2 +-
 net/sched/act_simple.c     | 2 +-
 net/sched/act_skbedit.c    | 2 +-
 net/sched/act_skbmod.c     | 2 +-
 net/sched/act_tunnel_key.c | 2 +-
 net/sched/act_vlan.c       | 2 +-
 18 files changed, 23 insertions(+), 20 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index ab3529255377..9c2f22695025 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -140,7 +140,8 @@ static inline void tc_action_net_exit(struct list_head *net_list,
 
 int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 		       struct netlink_callback *cb, int type,
-		       const struct tc_action_ops *ops);
+		       const struct tc_action_ops *ops,
+		       struct netlink_ext_ack *extack);
 int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index);
 bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
 		    int bind);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index ab107997b259..1f65d6ada9ff 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -202,7 +202,8 @@ nla_put_failure:
 
 int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 		       struct netlink_callback *cb, int type,
-		       const struct tc_action_ops *ops)
+		       const struct tc_action_ops *ops,
+		       struct netlink_ext_ack *extack)
 {
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
 
@@ -211,7 +212,8 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 	} else if (type == RTM_GETACTION) {
 		return tcf_dump_walker(idrinfo, skb, cb);
 	} else {
-		WARN(1, "tcf_generic_walker: unknown action %d\n", type);
+		WARN(1, "tcf_generic_walker: unknown command %d\n", type);
+		NL_SET_ERR_MSG(extack, "tcf_generic_walker: unknown command");
 		return -EINVAL;
 	}
 }
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 7e01e2c710c4..cb3c5d403c88 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -372,7 +372,7 @@ static int tcf_bpf_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index cb722da0bb15..e4b880fa51fe 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -182,7 +182,7 @@ static int tcf_connmark_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 3e8efadb750f..d5c2e528d150 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -636,7 +636,7 @@ static int tcf_csum_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index d96ebe4bb65a..f072bcf33760 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -206,7 +206,7 @@ static int tcf_gact_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index b777e381e0dd..a5994cf0512b 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -829,7 +829,7 @@ static int tcf_ife_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index f33a8cc5dee6..9784629090ad 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -308,7 +308,7 @@ static int tcf_ipt_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, ipt_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index,
@@ -358,7 +358,7 @@ static int tcf_xt_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, xt_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 3dcd295ea6a7..05c2ebe92eca 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -270,7 +270,7 @@ static int tcf_mirred_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 67243cdc0588..4b5848b6c252 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -283,7 +283,7 @@ static int tcf_nat_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 6d6481f6bffa..094303c27c5e 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -424,7 +424,7 @@ static int tcf_pedit_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index ff803414a736..ff55bd6c7db0 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -63,7 +63,7 @@ static int tcf_act_police_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 7a2b6a33f239..9765145aaf40 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -207,7 +207,7 @@ static int tcf_sample_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 3f5474d20702..8244e221fe4f 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -175,7 +175,7 @@ static int tcf_simp_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index d99b6f1f5181..ddf69fc01bdf 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -213,7 +213,7 @@ static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 369ea85d0f02..a406f191cb84 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -237,7 +237,7 @@ static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index bced6fd00d43..41ff9d0e5c62 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -296,7 +296,7 @@ static int tunnel_key_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index,
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 7cf409443d02..71411a255f04 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -272,7 +272,7 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb,
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
 static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index,
-- 
cgit v1.2.3


From c4b50cd31d25c3d17886ffc47ca4a9a12c6dc9bf Mon Sep 17 00:00:00 2001
From: Venkateswara Naralasetty <vnaralas@codeaurora.org>
Date: Tue, 13 Feb 2018 11:03:06 +0530
Subject: cfg80211: send ack_signal to user in probe client response

This patch provides support to get ack signal in probe client response
and in station info from user.

Signed-off-by: Venkateswara Naralasetty <vnaralas@codeaurora.org>
[squash in compilation fixes]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/wil6210/cfg80211.c | 3 ++-
 include/net/cfg80211.h                      | 7 ++++++-
 include/uapi/linux/nl80211.h                | 3 +++
 net/mac80211/status.c                       | 2 +-
 net/wireless/nl80211.c                      | 8 ++++++--
 5 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 768f63f38341..b799a5384abb 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -1599,7 +1599,8 @@ static void wil_probe_client_handle(struct wil6210_priv *wil,
 	 */
 	bool alive = (sta->status == wil_sta_connected);
 
-	cfg80211_probe_status(ndev, sta->addr, req->cookie, alive, GFP_KERNEL);
+	cfg80211_probe_status(ndev, sta->addr, req->cookie, alive,
+			      0, false, GFP_KERNEL);
 }
 
 static struct list_head *next_probe_client(struct wil6210_priv *wil)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 7d49cd0cf92d..56e905cd4b07 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1147,6 +1147,7 @@ struct cfg80211_tid_stats {
  * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer
  * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last
  *	(IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs.
+ * @ack_signal: signal strength (in dBm) of the last ACK frame.
  */
 struct station_info {
 	u64 filled;
@@ -1191,6 +1192,7 @@ struct station_info {
 	u64 rx_duration;
 	u8 rx_beacon_signal_avg;
 	struct cfg80211_tid_stats pertid[IEEE80211_NUM_TIDS + 1];
+	s8 ack_signal;
 };
 
 #if IS_ENABLED(CONFIG_CFG80211)
@@ -5838,10 +5840,13 @@ bool cfg80211_rx_unexpected_4addr_frame(struct net_device *dev,
  * @addr: the address of the peer
  * @cookie: the cookie filled in @probe_client previously
  * @acked: indicates whether probe was acked or not
+ * @ack_signal: signal strength (in dBm) of the ACK frame.
+ * @is_valid_ack_signal: indicates the ack_signal is valid or not.
  * @gfp: allocation flags
  */
 void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
-			   u64 cookie, bool acked, gfp_t gfp);
+			   u64 cookie, bool acked, s32 ack_signal,
+			   bool is_valid_ack_signal, gfp_t gfp);
 
 /**
  * cfg80211_report_obss_beacon - report beacon from other APs
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index ca3d5a613fc0..c13c84304be3 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2626,6 +2626,7 @@ enum nl80211_attrs {
 	NL80211_ATTR_EXTERNAL_AUTH_SUPPORT,
 
 	NL80211_ATTR_NSS,
+	NL80211_ATTR_ACK_SIGNAL,
 
 	/* add attributes here, update the policy in nl80211.c */
 
@@ -2947,6 +2948,7 @@ enum nl80211_sta_bss_param {
  * @NL80211_STA_INFO_RX_DURATION: aggregate PPDU duration for all frames
  *	received from the station (u64, usec)
  * @NL80211_STA_INFO_PAD: attribute used for padding for 64-bit alignment
+ * @NL80211_STA_INFO_ACK_SIGNAL: signal strength of the last ACK frame(u8, dBm)
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -2985,6 +2987,7 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_TID_STATS,
 	NL80211_STA_INFO_RX_DURATION,
 	NL80211_STA_INFO_PAD,
+	NL80211_STA_INFO_ACK_SIGNAL,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index da7427a41529..d74d44e65bd7 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -486,7 +486,7 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local,
 			if (ieee80211_is_nullfunc(hdr->frame_control) ||
 			    ieee80211_is_qos_nullfunc(hdr->frame_control))
 				cfg80211_probe_status(sdata->dev, hdr->addr1,
-						      cookie, acked,
+						      cookie, acked, 0, false,
 						      GFP_ATOMIC);
 			else
 				cfg80211_mgmt_tx_status(&sdata->wdev, cookie,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c6f256b29c73..050ff61b06a3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4486,6 +4486,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO_U64(RX_DROP_MISC, rx_dropped_misc);
 	PUT_SINFO_U64(BEACON_RX, rx_beacon);
 	PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8);
+	PUT_SINFO(ACK_SIGNAL, ack_signal, u8);
 
 #undef PUT_SINFO
 #undef PUT_SINFO_U64
@@ -14984,7 +14985,8 @@ nla_put_failure:
 EXPORT_SYMBOL(cfg80211_sta_opmode_change_notify);
 
 void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
-			   u64 cookie, bool acked, gfp_t gfp)
+			   u64 cookie, bool acked, s32 ack_signal,
+			   bool is_valid_ack_signal, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
@@ -15009,7 +15011,9 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) ||
 	    nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, cookie,
 			      NL80211_ATTR_PAD) ||
-	    (acked && nla_put_flag(msg, NL80211_ATTR_ACK)))
+	    (acked && nla_put_flag(msg, NL80211_ATTR_ACK)) ||
+	    (is_valid_ack_signal && nla_put_s32(msg, NL80211_ATTR_ACK_SIGNAL,
+						ack_signal)))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
-- 
cgit v1.2.3


From a78b26fffd2368fcd079802897f4c97f9baea833 Mon Sep 17 00:00:00 2001
From: Venkateswara Naralasetty <vnaralas@codeaurora.org>
Date: Tue, 13 Feb 2018 11:04:46 +0530
Subject: mac80211: Add tx ack signal support in sta info

This allows users to get ack signal strength of
last transmitted frame.

Signed-off-by: Venkateswara Naralasetty <vnaralas@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h  |  1 +
 net/mac80211/sta_info.c |  6 ++++++
 net/mac80211/sta_info.h |  2 ++
 net/mac80211/status.c   | 13 +++++++++++--
 4 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include/net')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 906e90223066..854037b8163e 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -934,6 +934,7 @@ struct ieee80211_tx_info {
 			u8 ampdu_len;
 			u8 antenna;
 			u16 tx_time;
+			bool is_valid_ack_signal;
 			void *status_driver_data[19 / sizeof(void *)];
 		} status;
 		struct {
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 0c5627f8a104..0bc40c719a55 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2287,6 +2287,12 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT);
 		sinfo->expected_throughput = thr;
 	}
+
+	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL)) &&
+	    sta->status_stats.ack_signal_filled) {
+		sinfo->ack_signal = sta->status_stats.last_ack_signal;
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL);
+	}
 }
 
 u32 sta_get_expected_throughput(struct sta_info *sta)
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index cd53619435b6..f64eb86ca64b 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -548,6 +548,8 @@ struct sta_info {
 		u64 msdu_retries[IEEE80211_NUM_TIDS + 1];
 		u64 msdu_failed[IEEE80211_NUM_TIDS + 1];
 		unsigned long last_ack;
+		s8 last_ack_signal;
+		bool ack_signal_filled;
 	} status_stats;
 
 	/* Updated from TX path only, no locking requirements */
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index d74d44e65bd7..743e89c5926c 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -187,9 +187,16 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb)
 	struct ieee80211_mgmt *mgmt = (void *) skb->data;
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb);
 
-	if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
+	if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
 		sta->status_stats.last_ack = jiffies;
+		if (txinfo->status.is_valid_ack_signal) {
+			sta->status_stats.last_ack_signal =
+					 (s8)txinfo->status.ack_signal;
+			sta->status_stats.ack_signal_filled = true;
+		}
+	}
 
 	if (ieee80211_is_data_qos(mgmt->frame_control)) {
 		struct ieee80211_hdr *hdr = (void *) skb->data;
@@ -486,7 +493,9 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local,
 			if (ieee80211_is_nullfunc(hdr->frame_control) ||
 			    ieee80211_is_qos_nullfunc(hdr->frame_control))
 				cfg80211_probe_status(sdata->dev, hdr->addr1,
-						      cookie, acked, 0, false,
+						      cookie, acked,
+						      info->status.ack_signal,
+						      info->status.is_valid_ack_signal,
 						      GFP_ATOMIC);
 			else
 				cfg80211_mgmt_tx_status(&sdata->wdev, cookie,
-- 
cgit v1.2.3


From 19efbd93e6fb05eab81856b4fc8d64211dd37088 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 19 Feb 2018 12:58:38 +0300
Subject: net: Kill net_mutex

We take net_mutex, when there are !async pernet_operations
registered, and read locking of net_sem is not enough. But
we may get rid of taking the mutex, and just change the logic
to write lock net_sem in such cases. This obviously reduces
the number of lock operations, we do.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rtnetlink.h   |  1 -
 include/net/net_namespace.h | 11 ++++++----
 net/core/net_namespace.c    | 53 +++++++++++++++++++++++++++------------------
 3 files changed, 39 insertions(+), 26 deletions(-)

(limited to 'include/net')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index e9ee9ad0a681..3573b4bf2fdf 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -35,7 +35,6 @@ extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
 
 extern wait_queue_head_t netdev_unregistering_wq;
-extern struct mutex net_mutex;
 extern struct rw_semaphore net_sem;
 
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 9158ec1ad06f..115b01b92f4d 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -60,8 +60,11 @@ struct net {
 
 	struct list_head	list;		/* list of network namespaces */
 	struct list_head	cleanup_list;	/* namespaces on death row */
-	struct list_head	exit_list;	/* Use only net_mutex */
-
+	struct list_head	exit_list;	/* To linked to call pernet exit
+						 * methods on dead net (net_sem
+						 * read locked), or to unregister
+						 * pernet ops (net_sem wr locked).
+						 */
 	struct user_namespace   *user_ns;	/* Owning user namespace */
 	struct ucounts		*ucounts;
 	spinlock_t		nsid_lock;
@@ -89,7 +92,7 @@ struct net {
 	/* core fib_rules */
 	struct list_head	rules_ops;
 
-	struct list_head	fib_notifier_ops;  /* protected by net_mutex */
+	struct list_head	fib_notifier_ops;  /* protected by net_sem */
 
 	struct net_device       *loopback_dev;          /* The loopback */
 	struct netns_core	core;
@@ -316,7 +319,7 @@ struct pernet_operations {
 	/*
 	 * Indicates above methods are allowed to be executed in parallel
 	 * with methods of any other pernet_operations, i.e. they are not
-	 * need synchronization via net_mutex.
+	 * need write locked net_sem.
 	 */
 	bool async;
 };
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index bcab9a938d6f..e89a516620dd 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -29,8 +29,6 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
-/* Used only if there are !async pernet_operations registered */
-DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
@@ -407,6 +405,7 @@ struct net *copy_net_ns(unsigned long flags,
 {
 	struct ucounts *ucounts;
 	struct net *net;
+	unsigned write;
 	int rv;
 
 	if (!(flags & CLONE_NEWNET))
@@ -424,20 +423,26 @@ struct net *copy_net_ns(unsigned long flags,
 	refcount_set(&net->passive, 1);
 	net->ucounts = ucounts;
 	get_user_ns(user_ns);
-
-	rv = down_read_killable(&net_sem);
+again:
+	write = READ_ONCE(nr_sync_pernet_ops);
+	if (write)
+		rv = down_write_killable(&net_sem);
+	else
+		rv = down_read_killable(&net_sem);
 	if (rv < 0)
 		goto put_userns;
-	if (nr_sync_pernet_ops) {
-		rv = mutex_lock_killable(&net_mutex);
-		if (rv < 0)
-			goto up_read;
+
+	if (!write && unlikely(READ_ONCE(nr_sync_pernet_ops))) {
+		up_read(&net_sem);
+		goto again;
 	}
 	rv = setup_net(net, user_ns);
-	if (nr_sync_pernet_ops)
-		mutex_unlock(&net_mutex);
-up_read:
-	up_read(&net_sem);
+
+	if (write)
+		up_write(&net_sem);
+	else
+		up_read(&net_sem);
+
 	if (rv < 0) {
 put_userns:
 		put_user_ns(user_ns);
@@ -485,15 +490,23 @@ static void cleanup_net(struct work_struct *work)
 	struct net *net, *tmp, *last;
 	struct list_head net_kill_list;
 	LIST_HEAD(net_exit_list);
+	unsigned write;
 
 	/* Atomically snapshot the list of namespaces to cleanup */
 	spin_lock_irq(&cleanup_list_lock);
 	list_replace_init(&cleanup_list, &net_kill_list);
 	spin_unlock_irq(&cleanup_list_lock);
+again:
+	write = READ_ONCE(nr_sync_pernet_ops);
+	if (write)
+		down_write(&net_sem);
+	else
+		down_read(&net_sem);
 
-	down_read(&net_sem);
-	if (nr_sync_pernet_ops)
-		mutex_lock(&net_mutex);
+	if (!write && unlikely(READ_ONCE(nr_sync_pernet_ops))) {
+		up_read(&net_sem);
+		goto again;
+	}
 
 	/* Don't let anyone else find us. */
 	rtnl_lock();
@@ -528,14 +541,14 @@ static void cleanup_net(struct work_struct *work)
 	list_for_each_entry_reverse(ops, &pernet_list, list)
 		ops_exit_list(ops, &net_exit_list);
 
-	if (nr_sync_pernet_ops)
-		mutex_unlock(&net_mutex);
-
 	/* Free the net generic variables */
 	list_for_each_entry_reverse(ops, &pernet_list, list)
 		ops_free_list(ops, &net_exit_list);
 
-	up_read(&net_sem);
+	if (write)
+		up_write(&net_sem);
+	else
+		up_read(&net_sem);
 
 	/* Ensure there are no outstanding rcu callbacks using this
 	 * network namespace.
@@ -563,8 +576,6 @@ static void cleanup_net(struct work_struct *work)
 void net_ns_barrier(void)
 {
 	down_write(&net_sem);
-	mutex_lock(&net_mutex);
-	mutex_unlock(&net_mutex);
 	up_write(&net_sem);
 }
 EXPORT_SYMBOL(net_ns_barrier);
-- 
cgit v1.2.3


From 65b7b5b90fcd17b25ef43b0cd02bda47bf286675 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 19 Feb 2018 12:58:45 +0300
Subject: net: Make cleanup_list and net::cleanup_list of llist type

This simplifies cleanup queueing and makes cleanup lists
to use llist primitives. Since llist has its own cmpxchg()
ordering, cleanup_list_lock is not more need.

Also, struct llist_node is smaller, than struct list_head,
so we save some bytes in struct net with this patch.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h |  3 ++-
 net/core/net_namespace.c    | 20 ++++++--------------
 2 files changed, 8 insertions(+), 15 deletions(-)

(limited to 'include/net')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 115b01b92f4d..d4417495773a 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -59,12 +59,13 @@ struct net {
 	atomic64_t		cookie_gen;
 
 	struct list_head	list;		/* list of network namespaces */
-	struct list_head	cleanup_list;	/* namespaces on death row */
 	struct list_head	exit_list;	/* To linked to call pernet exit
 						 * methods on dead net (net_sem
 						 * read locked), or to unregister
 						 * pernet ops (net_sem wr locked).
 						 */
+	struct llist_node	cleanup_list;	/* namespaces on death row */
+
 	struct user_namespace   *user_ns;	/* Owning user namespace */
 	struct ucounts		*ucounts;
 	spinlock_t		nsid_lock;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index e89a516620dd..abf8a46e94e2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -481,21 +481,18 @@ static void unhash_nsid(struct net *net, struct net *last)
 	spin_unlock_bh(&net->nsid_lock);
 }
 
-static DEFINE_SPINLOCK(cleanup_list_lock);
-static LIST_HEAD(cleanup_list);  /* Must hold cleanup_list_lock to touch */
+static LLIST_HEAD(cleanup_list);
 
 static void cleanup_net(struct work_struct *work)
 {
 	const struct pernet_operations *ops;
 	struct net *net, *tmp, *last;
-	struct list_head net_kill_list;
+	struct llist_node *net_kill_list;
 	LIST_HEAD(net_exit_list);
 	unsigned write;
 
 	/* Atomically snapshot the list of namespaces to cleanup */
-	spin_lock_irq(&cleanup_list_lock);
-	list_replace_init(&cleanup_list, &net_kill_list);
-	spin_unlock_irq(&cleanup_list_lock);
+	net_kill_list = llist_del_all(&cleanup_list);
 again:
 	write = READ_ONCE(nr_sync_pernet_ops);
 	if (write)
@@ -510,7 +507,7 @@ again:
 
 	/* Don't let anyone else find us. */
 	rtnl_lock();
-	list_for_each_entry(net, &net_kill_list, cleanup_list)
+	llist_for_each_entry(net, net_kill_list, cleanup_list)
 		list_del_rcu(&net->list);
 	/* Cache last net. After we unlock rtnl, no one new net
 	 * added to net_namespace_list can assign nsid pointer
@@ -525,7 +522,7 @@ again:
 	last = list_last_entry(&net_namespace_list, struct net, list);
 	rtnl_unlock();
 
-	list_for_each_entry(net, &net_kill_list, cleanup_list) {
+	llist_for_each_entry(net, net_kill_list, cleanup_list) {
 		unhash_nsid(net, last);
 		list_add_tail(&net->exit_list, &net_exit_list);
 	}
@@ -585,12 +582,7 @@ static DECLARE_WORK(net_cleanup_work, cleanup_net);
 void __put_net(struct net *net)
 {
 	/* Cleanup the network namespace in process context */
-	unsigned long flags;
-
-	spin_lock_irqsave(&cleanup_list_lock, flags);
-	list_add(&net->cleanup_list, &cleanup_list);
-	spin_unlock_irqrestore(&cleanup_list_lock, flags);
-
+	llist_add(&net->cleanup_list, &cleanup_list);
 	queue_work(netns_wq, &net_cleanup_work);
 }
 EXPORT_SYMBOL_GPL(__put_net);
-- 
cgit v1.2.3


From 4f4bbf7c4e3d4bd14987a13041c6b5b1ea59e21f Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Tue, 20 Feb 2018 08:44:21 +0100
Subject: devlink: Perform cleanup of resource_set cb

After adding size validation logic into core cleanup is required.

Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 83 +-------------------------
 include/net/devlink.h                          |  4 --
 2 files changed, 3 insertions(+), 84 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5e8ea712caa2..39196625ae8e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3798,70 +3798,6 @@ static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
 	.resource_query_enable		= 1,
 };
 
-static bool
-mlxsw_sp_resource_kvd_granularity_validate(struct netlink_ext_ack *extack,
-					   u64 size)
-{
-	const struct mlxsw_config_profile *profile;
-
-	profile = &mlxsw_sp_config_profile;
-	if (size % profile->kvd_hash_granularity) {
-		NL_SET_ERR_MSG_MOD(extack, "resource set with wrong granularity");
-		return false;
-	}
-	return true;
-}
-
-static int
-mlxsw_sp_resource_kvd_size_validate(struct devlink *devlink, u64 size,
-				    struct netlink_ext_ack *extack)
-{
-	NL_SET_ERR_MSG_MOD(extack, "kvd size cannot be changed");
-	return -EINVAL;
-}
-
-static int
-mlxsw_sp_resource_kvd_linear_size_validate(struct devlink *devlink, u64 size,
-					   struct netlink_ext_ack *extack)
-{
-	if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int
-mlxsw_sp_resource_kvd_hash_single_size_validate(struct devlink *devlink, u64 size,
-						struct netlink_ext_ack *extack)
-{
-	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
-
-	if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size))
-		return -EINVAL;
-
-	if (size < MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE)) {
-		NL_SET_ERR_MSG_MOD(extack, "hash single size is smaller than minimum");
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int
-mlxsw_sp_resource_kvd_hash_double_size_validate(struct devlink *devlink, u64 size,
-						struct netlink_ext_ack *extack)
-{
-	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
-
-	if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size))
-		return -EINVAL;
-
-	if (size < MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE)) {
-		NL_SET_ERR_MSG_MOD(extack, "hash double size is smaller than minimum");
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static u64 mlxsw_sp_resource_kvd_linear_occ_get(struct devlink *devlink)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
@@ -3870,23 +3806,10 @@ static u64 mlxsw_sp_resource_kvd_linear_occ_get(struct devlink *devlink)
 	return mlxsw_sp_kvdl_occ_get(mlxsw_sp);
 }
 
-static struct devlink_resource_ops mlxsw_sp_resource_kvd_ops = {
-	.size_validate = mlxsw_sp_resource_kvd_size_validate,
-};
-
 static struct devlink_resource_ops mlxsw_sp_resource_kvd_linear_ops = {
-	.size_validate = mlxsw_sp_resource_kvd_linear_size_validate,
 	.occ_get = mlxsw_sp_resource_kvd_linear_occ_get,
 };
 
-static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_single_ops = {
-	.size_validate = mlxsw_sp_resource_kvd_hash_single_size_validate,
-};
-
-static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_double_ops = {
-	.size_validate = mlxsw_sp_resource_kvd_hash_double_size_validate,
-};
-
 static struct devlink_resource_size_params mlxsw_sp_kvd_size_params;
 static struct devlink_resource_size_params mlxsw_sp_linear_size_params;
 static struct devlink_resource_size_params mlxsw_sp_hash_single_size_params;
@@ -3948,7 +3871,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 					MLXSW_SP_RESOURCE_KVD,
 					DEVLINK_RESOURCE_ID_PARENT_TOP,
 					&mlxsw_sp_kvd_size_params,
-					&mlxsw_sp_resource_kvd_ops);
+					NULL);
 	if (err)
 		return err;
 
@@ -3972,7 +3895,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 					MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE,
 					MLXSW_SP_RESOURCE_KVD,
 					&mlxsw_sp_hash_double_size_params,
-					&mlxsw_sp_resource_kvd_hash_double_ops);
+					NULL);
 	if (err)
 		return err;
 
@@ -3982,7 +3905,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 					MLXSW_SP_RESOURCE_KVD_HASH_SINGLE,
 					MLXSW_SP_RESOURCE_KVD,
 					&mlxsw_sp_hash_single_size_params,
-					&mlxsw_sp_resource_kvd_hash_single_ops);
+					NULL);
 	if (err)
 		return err;
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 6545b03e97f7..8d1c3f276dea 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -234,13 +234,9 @@ struct devlink_dpipe_headers {
 /**
  * struct devlink_resource_ops - resource ops
  * @occ_get: get the occupied size
- * @size_validate: validate the size of the resource before update, reload
- *                 is needed for changes to take place
  */
 struct devlink_resource_ops {
 	u64 (*occ_get)(struct devlink *devlink);
-	int (*size_validate)(struct devlink *devlink, u64 size,
-			     struct netlink_ext_ack *extack);
 };
 
 /**
-- 
cgit v1.2.3


From 494a973e22954249d35152cce1dcfba6d10c52e4 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Sun, 18 Feb 2018 21:39:17 -0500
Subject: net/mac8390: Convert to nubus_driver

This resolves an old bug that constrained this driver to no more than
one card.

Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Space.c                 |   3 -
 drivers/net/ethernet/8390/mac8390.c | 139 +++++++++++++++++-------------------
 include/net/Space.h                 |   1 -
 3 files changed, 67 insertions(+), 76 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/Space.c b/drivers/net/Space.c
index 11fe71278f40..64333ec999ac 100644
--- a/drivers/net/Space.c
+++ b/drivers/net/Space.c
@@ -114,9 +114,6 @@ static struct devprobe2 m68k_probes[] __initdata = {
 #ifdef CONFIG_MVME147_NET	/* MVME147 internal Ethernet */
 	{mvme147lance_probe, 0},
 #endif
-#ifdef CONFIG_MAC8390           /* NuBus NS8390-based cards */
-	{mac8390_probe, 0},
-#endif
 #ifdef CONFIG_MAC89x0
 	{mac89x0_probe, 0},
 #endif
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index abe50338b9f7..8042dd73eb6a 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -123,8 +123,7 @@ enum mac8390_access {
 };
 
 extern int mac8390_memtest(struct net_device *dev);
-static int mac8390_initdev(struct net_device *dev,
-			   struct nubus_rsrc *ndev,
+static int mac8390_initdev(struct net_device *dev, struct nubus_board *board,
 			   enum mac8390_type type);
 
 static int mac8390_open(struct net_device *dev);
@@ -169,7 +168,7 @@ static void slow_sane_block_output(struct net_device *dev, int count,
 static void word_memcpy_tocard(unsigned long tp, const void *fp, int count);
 static void word_memcpy_fromcard(void *tp, unsigned long fp, int count);
 
-static enum mac8390_type __init mac8390_ident(struct nubus_rsrc *fres)
+static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres)
 {
 	switch (fres->dr_sw) {
 	case NUBUS_DRSW_3COM:
@@ -235,7 +234,7 @@ static enum mac8390_type __init mac8390_ident(struct nubus_rsrc *fres)
 	return MAC8390_NONE;
 }
 
-static enum mac8390_access __init mac8390_testio(volatile unsigned long membase)
+static enum mac8390_access mac8390_testio(unsigned long membase)
 {
 	unsigned long outdata = 0xA5A0B5B0;
 	unsigned long indata =  0x00000000;
@@ -253,7 +252,7 @@ static enum mac8390_access __init mac8390_testio(volatile unsigned long membase)
 	return ACCESS_UNKNOWN;
 }
 
-static int __init mac8390_memsize(unsigned long membase)
+static int mac8390_memsize(unsigned long membase)
 {
 	unsigned long flags;
 	int i, j;
@@ -289,28 +288,28 @@ static int __init mac8390_memsize(unsigned long membase)
 	return i * 0x1000;
 }
 
-static bool __init mac8390_init(struct net_device *dev,
-				struct nubus_rsrc *ndev,
-				enum mac8390_type cardtype)
+static bool mac8390_rsrc_init(struct net_device *dev,
+			      struct nubus_rsrc *fres,
+			      enum mac8390_type cardtype)
 {
+	struct nubus_board *board = fres->board;
 	struct nubus_dir dir;
 	struct nubus_dirent ent;
 	int offset;
 	volatile unsigned short *i;
 
-	dev->irq = SLOT2IRQ(ndev->board->slot);
+	dev->irq = SLOT2IRQ(board->slot);
 	/* This is getting to be a habit */
-	dev->base_addr = (ndev->board->slot_addr |
-			  ((ndev->board->slot & 0xf) << 20));
+	dev->base_addr = board->slot_addr | ((board->slot & 0xf) << 20);
 
 	/*
 	 * Get some Nubus info - we will trust the card's idea
 	 * of where its memory and registers are.
 	 */
 
-	if (nubus_get_func_dir(ndev, &dir) == -1) {
+	if (nubus_get_func_dir(fres, &dir) == -1) {
 		pr_err("%s: Unable to get Nubus functional directory for slot %X!\n",
-		       dev->name, ndev->board->slot);
+		       dev->name, board->slot);
 		return false;
 	}
 
@@ -327,7 +326,7 @@ static bool __init mac8390_init(struct net_device *dev,
 		if (nubus_find_rsrc(&dir, NUBUS_RESID_MINOR_BASEOS,
 				    &ent) == -1) {
 			pr_err("%s: Memory offset resource for slot %X not found!\n",
-			       dev->name, ndev->board->slot);
+			       dev->name, board->slot);
 			return false;
 		}
 		nubus_get_rsrc_mem(&offset, &ent, 4);
@@ -338,7 +337,7 @@ static bool __init mac8390_init(struct net_device *dev,
 		if (nubus_find_rsrc(&dir, NUBUS_RESID_MINOR_LENGTH,
 				    &ent) == -1) {
 			pr_info("%s: Memory length resource for slot %X not found, probing\n",
-				dev->name, ndev->board->slot);
+				dev->name, board->slot);
 			offset = mac8390_memsize(dev->mem_start);
 		} else {
 			nubus_get_rsrc_mem(&offset, &ent, 4);
@@ -348,25 +347,25 @@ static bool __init mac8390_init(struct net_device *dev,
 		switch (cardtype) {
 		case MAC8390_KINETICS:
 		case MAC8390_DAYNA: /* it's the same */
-			dev->base_addr = (int)(ndev->board->slot_addr +
+			dev->base_addr = (int)(board->slot_addr +
 					       DAYNA_8390_BASE);
-			dev->mem_start = (int)(ndev->board->slot_addr +
+			dev->mem_start = (int)(board->slot_addr +
 					       DAYNA_8390_MEM);
 			dev->mem_end = dev->mem_start +
 				       mac8390_memsize(dev->mem_start);
 			break;
 		case MAC8390_INTERLAN:
-			dev->base_addr = (int)(ndev->board->slot_addr +
+			dev->base_addr = (int)(board->slot_addr +
 					       INTERLAN_8390_BASE);
-			dev->mem_start = (int)(ndev->board->slot_addr +
+			dev->mem_start = (int)(board->slot_addr +
 					       INTERLAN_8390_MEM);
 			dev->mem_end = dev->mem_start +
 				       mac8390_memsize(dev->mem_start);
 			break;
 		case MAC8390_CABLETRON:
-			dev->base_addr = (int)(ndev->board->slot_addr +
+			dev->base_addr = (int)(board->slot_addr +
 					       CABLETRON_8390_BASE);
-			dev->mem_start = (int)(ndev->board->slot_addr +
+			dev->mem_start = (int)(board->slot_addr +
 					       CABLETRON_8390_MEM);
 			/* The base address is unreadable if 0x00
 			 * has been written to the command register
@@ -382,7 +381,7 @@ static bool __init mac8390_init(struct net_device *dev,
 
 		default:
 			pr_err("Card type %s is unsupported, sorry\n",
-			       ndev->board->name);
+			       board->name);
 			return false;
 		}
 	}
@@ -390,86 +389,83 @@ static bool __init mac8390_init(struct net_device *dev,
 	return true;
 }
 
-struct net_device * __init mac8390_probe(int unit)
+static int mac8390_device_probe(struct nubus_board *board)
 {
 	struct net_device *dev;
-	struct nubus_rsrc *ndev = NULL;
 	int err = -ENODEV;
-	static unsigned int slots;
-
-	enum mac8390_type cardtype;
-
-	/* probably should check for Nubus instead */
-
-	if (!MACH_IS_MAC)
-		return ERR_PTR(-ENODEV);
+	struct nubus_rsrc *fres;
+	enum mac8390_type cardtype = MAC8390_NONE;
 
 	dev = ____alloc_ei_netdev(0);
 	if (!dev)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	if (unit >= 0)
-		sprintf(dev->name, "eth%d", unit);
+	SET_NETDEV_DEV(dev, &board->dev);
 
-	for_each_func_rsrc(ndev) {
-		if (ndev->category != NUBUS_CAT_NETWORK ||
-		    ndev->type != NUBUS_TYPE_ETHERNET)
+	for_each_board_func_rsrc(board, fres) {
+		if (fres->category != NUBUS_CAT_NETWORK ||
+		    fres->type != NUBUS_TYPE_ETHERNET)
 			continue;
 
-		/* Have we seen it already? */
-		if (slots & (1 << ndev->board->slot))
-			continue;
-		slots |= 1 << ndev->board->slot;
-
-		cardtype = mac8390_ident(ndev);
+		cardtype = mac8390_ident(fres);
 		if (cardtype == MAC8390_NONE)
 			continue;
 
-		if (!mac8390_init(dev, ndev, cardtype))
-			continue;
-
-		/* Do the nasty 8390 stuff */
-		if (!mac8390_initdev(dev, ndev, cardtype))
+		if (mac8390_rsrc_init(dev, fres, cardtype))
 			break;
 	}
+	if (!fres)
+		goto out;
 
-	if (!ndev)
+	err = mac8390_initdev(dev, board, cardtype);
+	if (err)
 		goto out;
 
 	err = register_netdev(dev);
 	if (err)
 		goto out;
-	return dev;
+
+	nubus_set_drvdata(board, dev);
+	return 0;
 
 out:
 	free_netdev(dev);
-	return ERR_PTR(err);
+	return err;
 }
 
-#ifdef MODULE
+static int mac8390_device_remove(struct nubus_board *board)
+{
+	struct net_device *dev = nubus_get_drvdata(board);
+
+	unregister_netdev(dev);
+	free_netdev(dev);
+	return 0;
+}
+
+static struct nubus_driver mac8390_driver = {
+	.probe = mac8390_device_probe,
+	.remove = mac8390_device_remove,
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.owner = THIS_MODULE,
+	}
+};
+
 MODULE_AUTHOR("David Huggins-Daines <dhd@debian.org> and others");
 MODULE_DESCRIPTION("Macintosh NS8390-based Nubus Ethernet driver");
 MODULE_LICENSE("GPL");
 
-static struct net_device *dev_mac8390;
-
-int __init init_module(void)
+static int __init mac8390_init(void)
 {
-	dev_mac8390 = mac8390_probe(-1);
-	if (IS_ERR(dev_mac8390)) {
-		pr_warn("mac8390: No card found\n");
-		return PTR_ERR(dev_mac8390);
-	}
-	return 0;
+	return nubus_driver_register(&mac8390_driver);
 }
+module_init(mac8390_init);
 
-void __exit cleanup_module(void)
+static void __exit mac8390_exit(void)
 {
-	unregister_netdev(dev_mac8390);
-	free_netdev(dev_mac8390);
+	nubus_driver_unregister(&mac8390_driver);
 }
-
-#endif /* MODULE */
+module_exit(mac8390_exit);
 
 static const struct net_device_ops mac8390_netdev_ops = {
 	.ndo_open 		= mac8390_open,
@@ -485,9 +481,8 @@ static const struct net_device_ops mac8390_netdev_ops = {
 #endif
 };
 
-static int __init mac8390_initdev(struct net_device *dev,
-				  struct nubus_rsrc *ndev,
-				  enum mac8390_type type)
+static int mac8390_initdev(struct net_device *dev, struct nubus_board *board,
+			   enum mac8390_type type)
 {
 	static u32 fwrd4_offsets[16] = {
 		0,      4,      8,      12,
@@ -605,7 +600,7 @@ static int __init mac8390_initdev(struct net_device *dev,
 
 	default:
 		pr_err("Card type %s is unsupported, sorry\n",
-		       ndev->board->name);
+		       board->name);
 		return -ENODEV;
 	}
 
@@ -613,7 +608,7 @@ static int __init mac8390_initdev(struct net_device *dev,
 
 	/* Good, done, now spit out some messages */
 	pr_info("%s: %s in slot %X (type %s)\n",
-		dev->name, ndev->board->name, ndev->board->slot,
+		dev->name, board->name, board->slot,
 		cardname[type]);
 	pr_info("MAC %pM IRQ %d, %d KB shared memory at %#lx, %d-bit access.\n",
 		dev->dev_addr, dev->irq,
diff --git a/include/net/Space.h b/include/net/Space.h
index 27fb5c937c4f..336da258885a 100644
--- a/include/net/Space.h
+++ b/include/net/Space.h
@@ -20,7 +20,6 @@ struct net_device *cs89x0_probe(int unit);
 struct net_device *mvme147lance_probe(int unit);
 struct net_device *tc515_probe(int unit);
 struct net_device *lance_probe(int unit);
-struct net_device *mac8390_probe(int unit);
 struct net_device *mac89x0_probe(int unit);
 struct net_device *cops_probe(int unit);
 struct net_device *ltpc_probe(void);
-- 
cgit v1.2.3


From 0a6b2a1dc2a2105f178255fe495eb914b09cb37a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 19 Feb 2018 11:56:47 -0800
Subject: tcp: switch to GSO being always on

Oleksandr Natalenko reported performance issues with BBR without FQ
packet scheduler that were root caused to lack of SG and GSO/TSO on
his configuration.

In this mode, TCP internal pacing has to setup a high resolution timer
for each MSS sent.

We could implement in TCP a strategy similar to the one adopted
in commit fefa569a9d4b ("net_sched: sch_fq: account for schedule/timers drifts")
or decide to finally switch TCP stack to a GSO only mode.

This has many benefits :

1) Most TCP developments are done with TSO in mind.
2) Less high-resolution timers needs to be armed for TCP-pacing
3) GSO can benefit of xmit_more hint
4) Receiver GRO is more effective (as if TSO was used for real on sender)
   -> Lower ACK traffic
5) Write queues have less overhead (one skb holds about 64KB of payload)
6) SACK coalescing just works.
7) rtx rb-tree contains less packets, SACK is cheaper.

This patch implements the minimum patch, but we can remove some legacy
code as follow ups.

Tested:

On 40Gbit link, one netperf -t TCP_STREAM

BBR+fq:
sg on:  26 Gbits/sec
sg off: 15.7 Gbits/sec   (was 2.3 Gbit before patch)

BBR+pfifo_fast:
sg on:  24.2 Gbits/sec
sg off: 14.9 Gbits/sec  (was 0.66 Gbit before patch !!! )

BBR+fq_codel:
sg on:  24.4 Gbits/sec
sg off: 15 Gbits/sec  (was 0.66 Gbit before patch !!! )

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 1 +
 net/core/sock.c    | 2 +-
 net/ipv4/tcp.c     | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index 3aa7b7d6e6c7..f0f576ff5603 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -417,6 +417,7 @@ struct sock {
 	struct page_frag	sk_frag;
 	netdev_features_t	sk_route_caps;
 	netdev_features_t	sk_route_nocaps;
+	netdev_features_t	sk_route_forced_caps;
 	int			sk_gso_type;
 	unsigned int		sk_gso_max_size;
 	gfp_t			sk_allocation;
diff --git a/net/core/sock.c b/net/core/sock.c
index a1fa4a548f1b..507d8c6c4319 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1777,7 +1777,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 	u32 max_segs = 1;
 
 	sk_dst_set(sk, dst);
-	sk->sk_route_caps = dst->dev->features;
+	sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
 	if (sk->sk_route_caps & NETIF_F_GSO)
 		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
 	sk->sk_route_caps &= ~sk->sk_route_nocaps;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 48636aee23c3..4b46a2ae46e3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -453,6 +453,7 @@ void tcp_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
 
 	sk_sockets_allocated_inc(sk);
+	sk->sk_route_forced_caps = NETIF_F_GSO;
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
-- 
cgit v1.2.3


From dead7cdb0daec58490891e59f4fae0c5c76fa5f3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 19 Feb 2018 11:56:49 -0800
Subject: tcp: remove sk_check_csum_caps()

Since TCP relies on GSO, we do not need this helper anymore.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |  9 ---------
 net/ipv4/tcp.c     | 11 +++--------
 2 files changed, 3 insertions(+), 17 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index f0f576ff5603..b9624581d639 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1863,15 +1863,6 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
 	sk->sk_route_caps &= ~flags;
 }
 
-static inline bool sk_check_csum_caps(struct sock *sk)
-{
-	return (sk->sk_route_caps & NETIF_F_HW_CSUM) ||
-	       (sk->sk_family == PF_INET &&
-		(sk->sk_route_caps & NETIF_F_IP_CSUM)) ||
-	       (sk->sk_family == PF_INET6 &&
-		(sk->sk_route_caps & NETIF_F_IPV6_CSUM));
-}
-
 static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
 					   struct iov_iter *from, char *to,
 					   int copy, int offset)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6f35c12af85a..7c4140271887 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1063,8 +1063,7 @@ EXPORT_SYMBOL_GPL(do_tcp_sendpages);
 int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
 			size_t size, int flags)
 {
-	if (!(sk->sk_route_caps & NETIF_F_SG) ||
-	    !sk_check_csum_caps(sk))
+	if (!(sk->sk_route_caps & NETIF_F_SG))
 		return sock_no_sendpage_locked(sk, page, offset, size, flags);
 
 	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */
@@ -1190,7 +1189,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			goto out_err;
 		}
 
-		zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG;
+		zc = sk->sk_route_caps & NETIF_F_SG;
 		if (!zc)
 			uarg->zerocopy = 0;
 	}
@@ -1287,11 +1286,7 @@ new_segment:
 				goto wait_for_memory;
 
 			process_backlog = true;
-			/*
-			 * Check whether we can use HW checksum.
-			 */
-			if (sk_check_csum_caps(sk))
-				skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->ip_summed = CHECKSUM_PARTIAL;
 
 			skb_entail(sk, skb);
 			copy = size_goal;
-- 
cgit v1.2.3


From a823fed03b5d940e4d57271222a0b959fc2ab201 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Tue, 20 Feb 2018 21:28:31 +0800
Subject: tcp: remove the hardcode in the definition of TCPF Macro

TCPF_ macro depends on the definition of TCP_ macro.
So it is better to define them with TCP_ marco.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp_states.h | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h
index 50e78a74d0df..2875e169d744 100644
--- a/include/net/tcp_states.h
+++ b/include/net/tcp_states.h
@@ -32,21 +32,21 @@ enum {
 
 #define TCP_STATE_MASK	0xF
 
-#define TCP_ACTION_FIN	(1 << 7)
+#define TCP_ACTION_FIN	(1 << TCP_CLOSE)
 
 enum {
-	TCPF_ESTABLISHED = (1 << 1),
-	TCPF_SYN_SENT	 = (1 << 2),
-	TCPF_SYN_RECV	 = (1 << 3),
-	TCPF_FIN_WAIT1	 = (1 << 4),
-	TCPF_FIN_WAIT2	 = (1 << 5),
-	TCPF_TIME_WAIT	 = (1 << 6),
-	TCPF_CLOSE	 = (1 << 7),
-	TCPF_CLOSE_WAIT	 = (1 << 8),
-	TCPF_LAST_ACK	 = (1 << 9),
-	TCPF_LISTEN	 = (1 << 10),
-	TCPF_CLOSING	 = (1 << 11),
-	TCPF_NEW_SYN_RECV = (1 << 12),
+	TCPF_ESTABLISHED = (1 << TCP_ESTABLISHED),
+	TCPF_SYN_SENT	 = (1 << TCP_SYN_SENT),
+	TCPF_SYN_RECV	 = (1 << TCP_SYN_RECV),
+	TCPF_FIN_WAIT1	 = (1 << TCP_FIN_WAIT1),
+	TCPF_FIN_WAIT2	 = (1 << TCP_FIN_WAIT2),
+	TCPF_TIME_WAIT	 = (1 << TCP_TIME_WAIT),
+	TCPF_CLOSE	 = (1 << TCP_CLOSE),
+	TCPF_CLOSE_WAIT	 = (1 << TCP_CLOSE_WAIT),
+	TCPF_LAST_ACK	 = (1 << TCP_LAST_ACK),
+	TCPF_LISTEN	 = (1 << TCP_LISTEN),
+	TCPF_CLOSING	 = (1 << TCP_CLOSING),
+	TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV),
 };
 
 #endif	/* _LINUX_TCP_STATES_H */
-- 
cgit v1.2.3


From cac56209a66ea3b0be67aa2966b2c628b944da1e Mon Sep 17 00:00:00 2001
From: Donald Sharp <sharpd@cumulusnetworks.com>
Date: Tue, 20 Feb 2018 08:55:58 -0500
Subject: net: Allow a rule to track originating protocol

Allow a rule that is being added/deleted/modified or
dumped to contain the originating protocol's id.

The protocol is handled just like a routes originating
protocol is.  This is especially useful because there
is starting to be a plethora of different user space
programs adding rules.

Allow the vrf device to specify that the kernel is the originator
of the rule created for this device.

Signed-off-by: Donald Sharp <sharpd@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c              | 1 +
 include/net/fib_rules.h        | 3 ++-
 include/uapi/linux/fib_rules.h | 2 +-
 net/core/fib_rules.c           | 7 ++++++-
 4 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 239c78c53e58..951a4b42cb29 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1174,6 +1174,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 	memset(frh, 0, sizeof(*frh));
 	frh->family = family;
 	frh->action = FR_ACT_TO_TBL;
+	frh->proto = RTPROT_KERNEL;
 
 	if (nla_put_u8(skb, FRA_L3MDEV, 1))
 		goto nla_put_failure;
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 648caf90ec07..b166ef07e6d4 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -26,7 +26,8 @@ struct fib_rule {
 	u32			table;
 	u8			action;
 	u8			l3mdev;
-	/* 2 bytes hole, try to use */
+	u8                      proto;
+	/* 1 byte hole, try to use */
 	u32			target;
 	__be64			tun_id;
 	struct fib_rule __rcu	*ctarget;
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 2b642bf9b5a0..925539172d5b 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -23,8 +23,8 @@ struct fib_rule_hdr {
 	__u8		tos;
 
 	__u8		table;
+	__u8		proto;
 	__u8		res1;	/* reserved */
-	__u8		res2;	/* reserved */
 	__u8		action;
 
 	__u32		flags;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index cb071b8e8d17..88298f18cbae 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -51,6 +51,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->pref = pref;
 	r->table = table;
 	r->flags = flags;
+	r->proto = RTPROT_KERNEL;
 	r->fr_net = ops->fro_net;
 	r->uid_range = fib_kuid_range_unset;
 
@@ -465,6 +466,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 	refcount_set(&rule->refcnt, 1);
 	rule->fr_net = net;
+	rule->proto = frh->proto;
 
 	rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY])
 	                              : fib_default_rule_pref(ops);
@@ -664,6 +666,9 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	list_for_each_entry(rule, &ops->rules_list, list) {
+		if (frh->proto && (frh->proto != rule->proto))
+			continue;
+
 		if (frh->action && (frh->action != rule->action))
 			continue;
 
@@ -808,9 +813,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
 		goto nla_put_failure;
 	frh->res1 = 0;
-	frh->res2 = 0;
 	frh->action = rule->action;
 	frh->flags = rule->flags;
+	frh->proto = rule->proto;
 
 	if (rule->action == FR_ACT_GOTO &&
 	    rcu_access_pointer(rule->ctarget) == NULL)
-- 
cgit v1.2.3


From 7299d6f7bfd1921c0cfb5e202155f1a5cfdb57d0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 19 Feb 2018 14:48:39 +0200
Subject: mac80211: support reporting A-MPDU EOF bit value/known

Support getting the EOF bit value reported from hardware
and writing it out to radiotap.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/ieee80211_radiotap.h | 2 ++
 include/net/mac80211.h           | 5 +++++
 net/mac80211/rx.c                | 4 ++++
 3 files changed, 11 insertions(+)

(limited to 'include/net')

diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index d91f9e7f4d71..960236fb1681 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -149,6 +149,8 @@ enum ieee80211_radiotap_ampdu_flags {
 	IEEE80211_RADIOTAP_AMPDU_IS_LAST = 0x0008,
 	IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_ERR = 0x0010,
 	IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_KNOWN = 0x0020,
+	IEEE80211_RADIOTAP_AMPDU_EOF = 0x0040,
+	IEEE80211_RADIOTAP_AMPDU_EOF_KNOWN = 0x0080,
 };
 
 /* for IEEE80211_RADIOTAP_VHT */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 854037b8163e..649f073eb6df 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1099,6 +1099,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	the first subframe.
  * @RX_FLAG_ICV_STRIPPED: The ICV is stripped from this frame. CRC checking must
  *	be done in the hardware.
+ * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this
+ *	frame
+ * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known
  */
 enum mac80211_rx_flags {
 	RX_FLAG_MMIC_ERROR		= BIT(0),
@@ -1125,6 +1128,8 @@ enum mac80211_rx_flags {
 	RX_FLAG_MIC_STRIPPED		= BIT(21),
 	RX_FLAG_ALLOW_SAME_PN		= BIT(22),
 	RX_FLAG_ICV_STRIPPED		= BIT(23),
+	RX_FLAG_AMPDU_EOF_BIT		= BIT(24),
+	RX_FLAG_AMPDU_EOF_BIT_KNOWN	= BIT(25),
 };
 
 /**
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index e755f93ad735..478a9c735edb 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -439,6 +439,10 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 			flags |= IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_ERR;
 		if (status->flag & RX_FLAG_AMPDU_DELIM_CRC_KNOWN)
 			flags |= IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_KNOWN;
+		if (status->flag & RX_FLAG_AMPDU_EOF_BIT_KNOWN)
+			flags |= IEEE80211_RADIOTAP_AMPDU_EOF_KNOWN;
+		if (status->flag & RX_FLAG_AMPDU_EOF_BIT)
+			flags |= IEEE80211_RADIOTAP_AMPDU_EOF;
 		put_unaligned_le16(flags, pos);
 		pos += 2;
 		if (status->flag & RX_FLAG_AMPDU_DELIM_CRC_KNOWN)
-- 
cgit v1.2.3


From 94ba92713f8329c96e0a8e2880b3c1a785d1c95c Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Mon, 19 Feb 2018 14:48:41 +0200
Subject: mac80211: Call mgd_prep_tx before transmitting deauthentication

In multi channel scenarios, when disassociating from the AP before a
beacon was heard from the AP, it is not guaranteed that the virtual
interface is granted air time for the transmission of the
deauthentication frame. This in turn can lead to various issues as
the AP might never get the deauthentication frame.

To mitigate such possible issues, add a HW flag indicating that the
driver requires mac80211 to call the mgd_prep_tx() driver callback
to make sure that the virtual interface is granted immediate airtime
to be able to transmit the frame, in case that no beacon was heard
from the AP.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 13 +++++++++++++
 net/mac80211/debugfs.c |  1 +
 net/mac80211/mlme.c    | 16 +++++++++++++++-
 3 files changed, 29 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 649f073eb6df..dc3e9d9c3527 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6,6 +6,7 @@
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018        Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -2069,6 +2070,14 @@ struct ieee80211_txq {
  * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on
  *	TDLS links.
  *
+ * @IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP: The driver requires the
+ *	mgd_prepare_tx() callback to be called before transmission of a
+ *	deauthentication frame in case the association was completed but no
+ *	beacon was heard. This is required in multi-channel scenarios, where the
+ *	virtual interface might not be given air time for the transmission of
+ *	the frame, as it is not synced with the AP/P2P GO yet, and thus the
+ *	deauthentication frame might not be transmitted.
+ *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
 enum ieee80211_hw_flags {
@@ -2112,6 +2121,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_REPORTS_LOW_ACK,
 	IEEE80211_HW_SUPPORTS_TX_FRAG,
 	IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA,
+	IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
@@ -3356,6 +3366,9 @@ enum ieee80211_reconfig_type {
  *	management frame prior to having successfully associated to allow the
  *	driver to give it channel time for the transmission, to get a response
  *	and to be able to synchronize with the GO.
+ *	For drivers that set %IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, mac80211
+ *	would also call this function before transmitting a deauthentication
+ *	frame in case that no beacon was heard from the AP/P2P GO.
  *	The callback will be called before each transmission and upon return
  *	mac80211 will transmit the frame right away.
  *	The callback is optional and can (should!) sleep.
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 1f466d12a6bc..a75653affbf7 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -212,6 +212,7 @@ static const char *hw_flag_names[] = {
 	FLAG(REPORTS_LOW_ACK),
 	FLAG(SUPPORTS_TX_FRAG),
 	FLAG(SUPPORTS_TDLS_BUFFER_STA),
+	FLAG(DEAUTH_NEED_MGD_TX_PREP),
 #undef FLAG
 };
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 010b127a3937..0024eff9bb84 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7,6 +7,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018        Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -2008,9 +2009,22 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 		ieee80211_flush_queues(local, sdata, true);
 
 	/* deauthenticate/disassociate now */
-	if (tx || frame_buf)
+	if (tx || frame_buf) {
+		struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+
+		/*
+		 * In multi channel scenarios guarantee that the virtual
+		 * interface is granted immediate airtime to transmit the
+		 * deauthentication frame by calling mgd_prepare_tx, if the
+		 * driver requested so.
+		 */
+		if (ieee80211_hw_check(&local->hw, DEAUTH_NEED_MGD_TX_PREP) &&
+		    !ifmgd->have_beacon)
+			drv_mgd_prepare_tx(sdata->local, sdata);
+
 		ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype,
 					       reason, tx, frame_buf);
+	}
 
 	/* flush out frame - make sure the deauth was actually sent */
 	if (tx)
-- 
cgit v1.2.3


From 1b71af6053af1bd2f849e9fda4f71c1e3f145dcf Mon Sep 17 00:00:00 2001
From: Donald Sharp <sharpd@cumulusnetworks.com>
Date: Fri, 23 Feb 2018 14:01:52 -0500
Subject: net: fib_rules: Add new attribute to set protocol

For ages iproute2 has used `struct rtmsg` as the ancillary header for
FIB rules and in the process set the protocol value to RTPROT_BOOT.
Until ca56209a66 ("net: Allow a rule to track originating protocol")
the kernel rules code ignored the protocol value sent from userspace
and always returned 0 in notifications. To avoid incompatibility with
existing iproute2, send the protocol as a new attribute.

Fixes: cac56209a66 ("net: Allow a rule to track originating protocol")
Signed-off-by: Donald Sharp <sharpd@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c              |  5 ++++-
 include/net/fib_rules.h        |  3 ++-
 include/uapi/linux/fib_rules.h |  5 +++--
 net/core/fib_rules.c           | 15 +++++++++++----
 4 files changed, 20 insertions(+), 8 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 951a4b42cb29..9ce0182223a0 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1145,6 +1145,7 @@ static inline size_t vrf_fib_rule_nl_size(void)
 	sz  = NLMSG_ALIGN(sizeof(struct fib_rule_hdr));
 	sz += nla_total_size(sizeof(u8));	/* FRA_L3MDEV */
 	sz += nla_total_size(sizeof(u32));	/* FRA_PRIORITY */
+	sz += nla_total_size(sizeof(u8));       /* FRA_PROTOCOL */
 
 	return sz;
 }
@@ -1174,7 +1175,9 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 	memset(frh, 0, sizeof(*frh));
 	frh->family = family;
 	frh->action = FR_ACT_TO_TBL;
-	frh->proto = RTPROT_KERNEL;
+
+	if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL))
+		goto nla_put_failure;
 
 	if (nla_put_u8(skb, FRA_L3MDEV, 1))
 		goto nla_put_failure;
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index b166ef07e6d4..b3d216249240 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -109,7 +109,8 @@ struct fib_rule_notifier_info {
 	[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
 	[FRA_GOTO]	= { .type = NLA_U32 }, \
 	[FRA_L3MDEV]	= { .type = NLA_U8 }, \
-	[FRA_UID_RANGE]	= { .len = sizeof(struct fib_rule_uid_range) }
+	[FRA_UID_RANGE]	= { .len = sizeof(struct fib_rule_uid_range) }, \
+	[FRA_PROTOCOL]  = { .type = NLA_U8 }
 
 static inline void fib_rule_get(struct fib_rule *rule)
 {
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 925539172d5b..77d90ae38114 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -23,8 +23,8 @@ struct fib_rule_hdr {
 	__u8		tos;
 
 	__u8		table;
-	__u8		proto;
-	__u8		res1;	/* reserved */
+	__u8		res1;   /* reserved */
+	__u8		res2;	/* reserved */
 	__u8		action;
 
 	__u32		flags;
@@ -58,6 +58,7 @@ enum {
 	FRA_PAD,
 	FRA_L3MDEV,	/* iif or oif is l3mdev goto its table */
 	FRA_UID_RANGE,	/* UID range */
+	FRA_PROTOCOL,   /* Originator of the rule */
 	__FRA_MAX
 };
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 88298f18cbae..a6aea805a0a2 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -466,11 +466,13 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 	refcount_set(&rule->refcnt, 1);
 	rule->fr_net = net;
-	rule->proto = frh->proto;
 
 	rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY])
 	                              : fib_default_rule_pref(ops);
 
+	rule->proto = tb[FRA_PROTOCOL] ?
+		nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC;
+
 	if (tb[FRA_IIFNAME]) {
 		struct net_device *dev;
 
@@ -666,7 +668,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	list_for_each_entry(rule, &ops->rules_list, list) {
-		if (frh->proto && (frh->proto != rule->proto))
+		if (tb[FRA_PROTOCOL] &&
+		    (rule->proto != nla_get_u8(tb[FRA_PROTOCOL])))
 			continue;
 
 		if (frh->action && (frh->action != rule->action))
@@ -786,7 +789,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(4) /* FRA_FWMARK */
 			 + nla_total_size(4) /* FRA_FWMASK */
 			 + nla_total_size_64bit(8) /* FRA_TUN_ID */
-			 + nla_total_size(sizeof(struct fib_kuid_range));
+			 + nla_total_size(sizeof(struct fib_kuid_range))
+			 + nla_total_size(1); /* FRA_PROTOCOL */
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);
@@ -813,9 +817,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
 		goto nla_put_failure;
 	frh->res1 = 0;
+	frh->res2 = 0;
 	frh->action = rule->action;
 	frh->flags = rule->flags;
-	frh->proto = rule->proto;
+
+	if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto))
+		goto nla_put_failure;
 
 	if (rule->action == FR_ACT_GOTO &&
 	    rcu_access_pointer(rule->ctarget) == NULL)
-- 
cgit v1.2.3


From 24bba078eca099b5bd25e17e97b485f013589f8c Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Feb 2018 13:03:07 +0100
Subject: mac80211: support A-MSDU in fast-rx

Only works if the IV was stripped from packets. Create a smaller
variant of ieee80211_rx_h_amsdu, which bypasses checks already done
within the fast-rx context.

In order to do so, update cfg80211's ieee80211_data_to_8023_exthdr()
to take the offset between header and snap.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |   6 ++-
 net/mac80211/rx.c      | 124 +++++++++++++++++++++++++++++--------------------
 net/wireless/util.c    |   5 +-
 3 files changed, 80 insertions(+), 55 deletions(-)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 56e905cd4b07..fc40843baed3 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4410,10 +4410,12 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr);
  *	of it being pushed into the SKB
  * @addr: the device MAC address
  * @iftype: the virtual interface type
+ * @data_offset: offset of payload after the 802.11 header
  * Return: 0 on success. Non-zero on error.
  */
 int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
-				  const u8 *addr, enum nl80211_iftype iftype);
+				  const u8 *addr, enum nl80211_iftype iftype,
+				  u8 data_offset);
 
 /**
  * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3
@@ -4425,7 +4427,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 					 enum nl80211_iftype iftype)
 {
-	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype);
+	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0);
 }
 
 /**
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 2783c5cd7de7..de7d10732fd5 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2353,39 +2353,17 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 }
 
 static ieee80211_rx_result debug_noinline
-ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
+__ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset)
 {
 	struct net_device *dev = rx->sdata->dev;
 	struct sk_buff *skb = rx->skb;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	__le16 fc = hdr->frame_control;
 	struct sk_buff_head frame_list;
-	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
 	struct ethhdr ethhdr;
 	const u8 *check_da = ethhdr.h_dest, *check_sa = ethhdr.h_source;
 
-	if (unlikely(!ieee80211_is_data(fc)))
-		return RX_CONTINUE;
-
-	if (unlikely(!ieee80211_is_data_present(fc)))
-		return RX_DROP_MONITOR;
-
-	if (!(status->rx_flags & IEEE80211_RX_AMSDU))
-		return RX_CONTINUE;
-
 	if (unlikely(ieee80211_has_a4(hdr->frame_control))) {
-		switch (rx->sdata->vif.type) {
-		case NL80211_IFTYPE_AP_VLAN:
-			if (!rx->sdata->u.vlan.sta)
-				return RX_DROP_UNUSABLE;
-			break;
-		case NL80211_IFTYPE_STATION:
-			if (!rx->sdata->u.mgd.use_4addr)
-				return RX_DROP_UNUSABLE;
-			break;
-		default:
-			return RX_DROP_UNUSABLE;
-		}
 		check_da = NULL;
 		check_sa = NULL;
 	} else switch (rx->sdata->vif.type) {
@@ -2405,15 +2383,13 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
 			break;
 	}
 
-	if (is_multicast_ether_addr(hdr->addr1))
-		return RX_DROP_UNUSABLE;
-
 	skb->dev = dev;
 	__skb_queue_head_init(&frame_list);
 
 	if (ieee80211_data_to_8023_exthdr(skb, &ethhdr,
 					  rx->sdata->vif.addr,
-					  rx->sdata->vif.type))
+					  rx->sdata->vif.type,
+					  data_offset))
 		return RX_DROP_UNUSABLE;
 
 	ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr,
@@ -2435,6 +2411,44 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
 	return RX_QUEUED;
 }
 
+static ieee80211_rx_result debug_noinline
+ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
+{
+	struct sk_buff *skb = rx->skb;
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	__le16 fc = hdr->frame_control;
+
+	if (!(status->rx_flags & IEEE80211_RX_AMSDU))
+		return RX_CONTINUE;
+
+	if (unlikely(!ieee80211_is_data(fc)))
+		return RX_CONTINUE;
+
+	if (unlikely(!ieee80211_is_data_present(fc)))
+		return RX_DROP_MONITOR;
+
+	if (unlikely(ieee80211_has_a4(hdr->frame_control))) {
+		switch (rx->sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+			if (!rx->sdata->u.vlan.sta)
+				return RX_DROP_UNUSABLE;
+			break;
+		case NL80211_IFTYPE_STATION:
+			if (!rx->sdata->u.mgd.use_4addr)
+				return RX_DROP_UNUSABLE;
+			break;
+		default:
+			return RX_DROP_UNUSABLE;
+		}
+	}
+
+	if (is_multicast_ether_addr(hdr->addr1))
+		return RX_DROP_UNUSABLE;
+
+	return __ieee80211_rx_h_amsdu(rx, 0);
+}
+
 #ifdef CONFIG_MAC80211_MESH
 static ieee80211_rx_result
 ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
@@ -3898,7 +3912,8 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	struct sta_info *sta = rx->sta;
 	int orig_len = skb->len;
-	int snap_offs = ieee80211_hdrlen(hdr->frame_control);
+	int hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	int snap_offs = hdrlen;
 	struct {
 		u8 snap[sizeof(rfc1042_header)];
 		__be16 proto;
@@ -3929,10 +3944,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 	    (status->flag & FAST_RX_CRYPT_FLAGS) != FAST_RX_CRYPT_FLAGS)
 		return false;
 
-	/* we don't deal with A-MSDU deaggregation here */
-	if (status->rx_flags & IEEE80211_RX_AMSDU)
-		return false;
-
 	if (unlikely(!ieee80211_is_data_present(hdr->frame_control)))
 		return false;
 
@@ -3964,21 +3975,24 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 		snap_offs += IEEE80211_CCMP_HDR_LEN;
 	}
 
-	if (!pskb_may_pull(skb, snap_offs + sizeof(*payload)))
-		goto drop;
-	payload = (void *)(skb->data + snap_offs);
+	if (!(status->rx_flags & IEEE80211_RX_AMSDU)) {
+		if (!pskb_may_pull(skb, snap_offs + sizeof(*payload)))
+			goto drop;
 
-	if (!ether_addr_equal(payload->snap, fast_rx->rfc1042_hdr))
-		return false;
+		payload = (void *)(skb->data + snap_offs);
 
-	/* Don't handle these here since they require special code.
-	 * Accept AARP and IPX even though they should come with a
-	 * bridge-tunnel header - but if we get them this way then
-	 * there's little point in discarding them.
-	 */
-	if (unlikely(payload->proto == cpu_to_be16(ETH_P_TDLS) ||
-		     payload->proto == fast_rx->control_port_protocol))
-		return false;
+		if (!ether_addr_equal(payload->snap, fast_rx->rfc1042_hdr))
+			return false;
+
+		/* Don't handle these here since they require special code.
+		 * Accept AARP and IPX even though they should come with a
+		 * bridge-tunnel header - but if we get them this way then
+		 * there's little point in discarding them.
+		 */
+		if (unlikely(payload->proto == cpu_to_be16(ETH_P_TDLS) ||
+			     payload->proto == fast_rx->control_port_protocol))
+			return false;
+	}
 
 	/* after this point, don't punt to the slowpath! */
 
@@ -3992,12 +4006,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 	}
 
 	/* statistics part of ieee80211_rx_h_sta_process() */
-	stats->last_rx = jiffies;
-	stats->last_rate = sta_stats_encode_rate(status);
-
-	stats->fragments++;
-	stats->packets++;
-
 	if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) {
 		stats->last_signal = status->signal;
 		if (!fast_rx->uses_rss)
@@ -4026,6 +4034,20 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 	if (rx->key && !ieee80211_has_protected(hdr->frame_control))
 		goto drop;
 
+	if (status->rx_flags & IEEE80211_RX_AMSDU) {
+		if (__ieee80211_rx_h_amsdu(rx, snap_offs - hdrlen) !=
+		    RX_QUEUED)
+			goto drop;
+
+		return true;
+	}
+
+	stats->last_rx = jiffies;
+	stats->last_rate = sta_stats_encode_rate(status);
+
+	stats->fragments++;
+	stats->packets++;
+
 	/* do the header conversion - first grab the addresses */
 	ether_addr_copy(addrs.da, skb->data + fast_rx->da_offs);
 	ether_addr_copy(addrs.sa, skb->data + fast_rx->sa_offs);
diff --git a/net/wireless/util.c b/net/wireless/util.c
index c69160694b6c..d112e9a89364 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -420,7 +420,8 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr)
 EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen);
 
 int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
-				  const u8 *addr, enum nl80211_iftype iftype)
+				  const u8 *addr, enum nl80211_iftype iftype,
+				  u8 data_offset)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	struct {
@@ -434,7 +435,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 	if (unlikely(!ieee80211_is_data_present(hdr->frame_control)))
 		return -1;
 
-	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	hdrlen = ieee80211_hdrlen(hdr->frame_control) + data_offset;
 	if (skb->len < hdrlen + 8)
 		return -1;
 
-- 
cgit v1.2.3


From d1b2a6c4bed99fc7e8a11e7abcff19293d1974f5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 27 Feb 2018 14:53:37 +0100
Subject: net: GRE: Add is_gretap_dev, is_ip6gretap_dev

Determining whether a device is a GRE device is easily done by
inspecting struct net_device.type. However, for the tap variants, the
type is just ARPHRD_ETHER.

Therefore introduce two predicate functions that use netdev_ops to tell
the tap devices.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gre.h  | 3 +++
 net/ipv4/ip_gre.c  | 6 ++++++
 net/ipv6/ip6_gre.c | 6 ++++++
 3 files changed, 15 insertions(+)

(limited to 'include/net')

diff --git a/include/net/gre.h b/include/net/gre.h
index f90585decbce..797142eee9cd 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -37,6 +37,9 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		     bool *csum_err, __be16 proto, int nhs);
 
+bool is_gretap_dev(const struct net_device *dev);
+bool is_ip6gretap_dev(const struct net_device *dev);
+
 static inline int gre_calc_hlen(__be16 o_flags)
 {
 	int addend = 4;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e496afa47709..0fe1d69b5df4 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1323,6 +1323,12 @@ static void ipgre_tap_setup(struct net_device *dev)
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
+bool is_gretap_dev(const struct net_device *dev)
+{
+	return dev->netdev_ops == &gre_tap_netdev_ops;
+}
+EXPORT_SYMBOL_GPL(is_gretap_dev);
+
 static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[],
 			 struct netlink_ext_ack *extack)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3026662a6413..4f150a394387 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1785,6 +1785,12 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 }
 
+bool is_ip6gretap_dev(const struct net_device *dev)
+{
+	return dev->netdev_ops == &ip6gre_tap_netdev_ops;
+}
+EXPORT_SYMBOL_GPL(is_ip6gretap_dev);
+
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
 				       struct ip_tunnel_encap *ipencap)
 {
-- 
cgit v1.2.3


From b0066da52ea53bae2b4ceed3f47d488df27dab66 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 27 Feb 2018 14:53:38 +0100
Subject: ip_tunnel: Rename & publish init_tunnel_flow

Initializing struct flowi4 is useful for drivers that need to emulate
routing decisions made by a tunnel interface. Publish the
function (appropriately renamed) so that the drivers in question don't
need to cut'n'paste it around.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h | 16 ++++++++++++++++
 net/ipv4/ip_tunnel.c     | 40 ++++++++++++----------------------------
 2 files changed, 28 insertions(+), 28 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 1f16773cfd76..cbe5addb9293 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -254,6 +254,22 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id)
 
 #ifdef CONFIG_INET
 
+static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
+				       int proto,
+				       __be32 daddr, __be32 saddr,
+				       __be32 key, __u8 tos, int oif,
+				       __u32 mark)
+{
+	memset(fl4, 0, sizeof(*fl4));
+	fl4->flowi4_oif = oif;
+	fl4->daddr = daddr;
+	fl4->saddr = saddr;
+	fl4->flowi4_tos = tos;
+	fl4->flowi4_proto = proto;
+	fl4->fl4_gre_key = key;
+	fl4->flowi4_mark = mark;
+}
+
 int ip_tunnel_init(struct net_device *dev);
 void ip_tunnel_uninit(struct net_device *dev);
 void  ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d786a8441bce..b2117d89bc83 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -290,22 +290,6 @@ failed:
 	return ERR_PTR(err);
 }
 
-static inline void init_tunnel_flow(struct flowi4 *fl4,
-				    int proto,
-				    __be32 daddr, __be32 saddr,
-				    __be32 key, __u8 tos, int oif,
-				    __u32 mark)
-{
-	memset(fl4, 0, sizeof(*fl4));
-	fl4->flowi4_oif = oif;
-	fl4->daddr = daddr;
-	fl4->saddr = saddr;
-	fl4->flowi4_tos = tos;
-	fl4->flowi4_proto = proto;
-	fl4->fl4_gre_key = key;
-	fl4->flowi4_mark = mark;
-}
-
 static int ip_tunnel_bind_dev(struct net_device *dev)
 {
 	struct net_device *tdev = NULL;
@@ -322,10 +306,10 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 		struct flowi4 fl4;
 		struct rtable *rt;
 
-		init_tunnel_flow(&fl4, iph->protocol, iph->daddr,
-				 iph->saddr, tunnel->parms.o_key,
-				 RT_TOS(iph->tos), tunnel->parms.link,
-				 tunnel->fwmark);
+		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
+				    iph->saddr, tunnel->parms.o_key,
+				    RT_TOS(iph->tos), tunnel->parms.link,
+				    tunnel->fwmark);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
 		if (!IS_ERR(rt)) {
@@ -581,8 +565,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 		else if (skb->protocol == htons(ETH_P_IPV6))
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 	}
-	init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
-			 RT_TOS(tos), tunnel->parms.link, tunnel->fwmark);
+	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
+			    RT_TOS(tos), tunnel->parms.link, tunnel->fwmark);
 	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
 		goto tx_error;
 	rt = ip_route_output_key(tunnel->net, &fl4);
@@ -711,14 +695,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (tunnel->fwmark) {
-		init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
-				 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
-				 tunnel->fwmark);
+		ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
+				    tunnel->parms.o_key, RT_TOS(tos),
+				    tunnel->parms.link, tunnel->fwmark);
 	}
 	else {
-		init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
-				 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
-				 skb->mark);
+		ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
+				    tunnel->parms.o_key, RT_TOS(tos),
+				    tunnel->parms.link, skb->mark);
 	}
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
-- 
cgit v1.2.3


From 82695b30ffeeab665f41416c6f5015dea3147bd5 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 27 Feb 2018 15:48:21 -0800
Subject: inet: whitespace cleanup

Ran simple script to find/remove trailing whitespace and blank lines
at EOF because that kind of stuff git whines about and editors leave
behind.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ethoc.h                |  1 -
 include/net/flow.h                 |  2 +-
 include/net/inet_connection_sock.h | 10 +++++-----
 include/net/ip.h                   | 12 ++++++------
 include/net/ip_fib.h               |  2 +-
 include/net/ipv6.h                 | 10 +++++-----
 include/net/xfrm.h                 | 14 +++++++-------
 net/ipv4/fib_semantics.c           |  2 +-
 net/ipv4/proc.c                    |  1 -
 net/ipv4/tunnel4.c                 |  2 +-
 net/ipv4/xfrm4_policy.c            |  1 -
 net/ipv6/anycast.c                 |  1 -
 net/ipv6/exthdrs_core.c            |  1 -
 net/ipv6/ipv6_sockglue.c           |  1 -
 net/ipv6/proc.c                    |  1 -
 net/ipv6/xfrm6_state.c             |  1 -
 16 files changed, 27 insertions(+), 35 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ethoc.h b/include/net/ethoc.h
index bb7f467da7fc..29ba069a1d93 100644
--- a/include/net/ethoc.h
+++ b/include/net/ethoc.h
@@ -21,4 +21,3 @@ struct ethoc_platform_data {
 };
 
 #endif /* !LINUX_NET_ETHOC_H */
-
diff --git a/include/net/flow.h b/include/net/flow.h
index f1624fd5b1d0..64e7ee9cb980 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -125,7 +125,7 @@ static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __u8 tos,
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
 }
-				      
+
 
 struct flowi6 {
 	struct flowi_common	__fl_common;
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c1a93ce35e62..b68fea022a82 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -49,9 +49,9 @@ struct inet_connection_sock_af_ops {
 	u16	    net_header_len;
 	u16	    net_frag_header_len;
 	u16	    sockaddr_len;
-	int	    (*setsockopt)(struct sock *sk, int level, int optname, 
+	int	    (*setsockopt)(struct sock *sk, int level, int optname,
 				  char __user *optval, unsigned int optlen);
-	int	    (*getsockopt)(struct sock *sk, int level, int optname, 
+	int	    (*getsockopt)(struct sock *sk, int level, int optname,
 				  char __user *optval, int __user *optlen);
 #ifdef CONFIG_COMPAT
 	int	    (*compat_setsockopt)(struct sock *sk,
@@ -67,7 +67,7 @@ struct inet_connection_sock_af_ops {
 
 /** inet_connection_sock - INET connection oriented sock
  *
- * @icsk_accept_queue:	   FIFO of established children 
+ * @icsk_accept_queue:	   FIFO of established children
  * @icsk_bind_hash:	   Bind node
  * @icsk_timeout:	   Timeout
  * @icsk_retransmit_timer: Resend (no ack)
@@ -122,7 +122,7 @@ struct inet_connection_sock {
 		unsigned long	  timeout;	 /* Currently scheduled timeout		   */
 		__u32		  lrcvtime;	 /* timestamp of last received data packet */
 		__u16		  last_seg_size; /* Size of last incoming segment	   */
-		__u16		  rcv_mss;	 /* MSS used for delayed ACK decisions	   */ 
+		__u16		  rcv_mss;	 /* MSS used for delayed ACK decisions	   */
 	} icsk_ack;
 	struct {
 		int		  enabled;
@@ -201,7 +201,7 @@ extern const char inet_csk_timer_bug_msg[];
 static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	
+
 	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
 		icsk->icsk_pending = 0;
 #ifdef INET_CSK_CLEAR_TIMERS
diff --git a/include/net/ip.h b/include/net/ip.h
index 746abff9ce51..fe63ba95d12b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -186,15 +186,15 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 void ip4_datagram_release_cb(struct sock *sk);
 
 struct ip_reply_arg {
-	struct kvec iov[1];   
+	struct kvec iov[1];
 	int	    flags;
 	__wsum 	    csum;
 	int	    csumoffset; /* u16 offset of csum in iov[0].iov_base */
-				/* -1 if not needed */ 
+				/* -1 if not needed */
 	int	    bound_dev_if;
 	u8  	    tos;
 	kuid_t	    uid;
-}; 
+};
 
 #define IP_REPLY_ARG_NOSRCCHECK 1
 
@@ -577,13 +577,13 @@ int ip_frag_mem(struct net *net);
 /*
  *	Functions provided by ip_forward.c
  */
- 
+
 int ip_forward(struct sk_buff *skb);
- 
+
 /*
  *	Functions provided by ip_options.c
  */
- 
+
 void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
 		      __be32 daddr, struct rtable *rt, int is_frag);
 
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index f80524396c06..15e19c5c6f26 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -157,7 +157,7 @@ struct fib_result_nl {
 	unsigned char	nh_sel;
 	unsigned char	type;
 	unsigned char	scope;
-	int             err;      
+	int             err;
 };
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 7a98cd583c73..cabd3cdd4015 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -105,8 +105,8 @@
 
 #define IPV6_ADDR_ANY		0x0000U
 
-#define IPV6_ADDR_UNICAST      	0x0001U	
-#define IPV6_ADDR_MULTICAST    	0x0002U	
+#define IPV6_ADDR_UNICAST	0x0001U
+#define IPV6_ADDR_MULTICAST	0x0002U
 
 #define IPV6_ADDR_LOOPBACK	0x0010U
 #define IPV6_ADDR_LINKLOCAL	0x0020U
@@ -447,7 +447,7 @@ ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m,
 #endif
 }
 
-static inline void ipv6_addr_prefix(struct in6_addr *pfx, 
+static inline void ipv6_addr_prefix(struct in6_addr *pfx,
 				    const struct in6_addr *addr,
 				    int plen)
 {
@@ -496,7 +496,7 @@ static inline void __ipv6_addr_set_half(__be32 *addr,
 	addr[1] = wl;
 }
 
-static inline void ipv6_addr_set(struct in6_addr *addr, 
+static inline void ipv6_addr_set(struct in6_addr *addr,
 				     __be32 w1, __be32 w2,
 				     __be32 w3, __be32 w4)
 {
@@ -732,7 +732,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int
 	}
 
 	/*
-	 *	we should *never* get to this point since that 
+	 *	we should *never* get to this point since that
 	 *	would mean the addrs are equal
 	 *
 	 *	However, we do get to it 8) And exacly, when
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 7d2077665c0b..aa027ba1d032 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1267,12 +1267,12 @@ static inline void xfrm_sk_free_policy(struct sock *sk)
 
 static inline void xfrm_sk_free_policy(struct sock *sk) {}
 static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; }
-static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; }  
-static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } 
+static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; }
+static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; }
 static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
-{ 
-	return 1; 
-} 
+{
+	return 1;
+}
 static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb)
 {
 	return 1;
@@ -1356,7 +1356,7 @@ __xfrm6_state_addr_check(const struct xfrm_state *x,
 {
 	if (ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) &&
 	    (ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr) ||
-	     ipv6_addr_any((struct in6_addr *)saddr) || 
+	     ipv6_addr_any((struct in6_addr *)saddr) ||
 	     ipv6_addr_any((struct in6_addr *)&x->props.saddr)))
 		return 1;
 	return 0;
@@ -1666,7 +1666,7 @@ int xfrm_user_policy(struct sock *sk, int optname,
 static inline int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
 {
  	return -ENOPROTOOPT;
-} 
+}
 
 static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index cd46d7666598..f31e6575ab91 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -171,7 +171,7 @@ static void free_nh_exceptions(struct fib_nh *nh)
 		fnhe = rcu_dereference_protected(hash[i].chain, 1);
 		while (fnhe) {
 			struct fib_nh_exception *next;
-			
+
 			next = rcu_dereference_protected(fnhe->fnhe_next, 1);
 
 			rt_fibinfo_free(&fnhe->fnhe_rth_input);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index fdabc70283b6..d97e83b2dd33 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -556,4 +556,3 @@ int __init ip_misc_proc_init(void)
 {
 	return register_pernet_subsys(&ip_proc_ops);
 }
-
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index ec35eaa5c029..c0630013c1ae 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -90,7 +90,7 @@ EXPORT_SYMBOL(xfrm4_tunnel_deregister);
 	for (handler = rcu_dereference(head);		\
 	     handler != NULL;				\
 	     handler = rcu_dereference(handler->next))	\
-	
+
 static int tunnel4_rcv(struct sk_buff *skb)
 {
 	struct xfrm_tunnel *handler;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 796ac4115485..0c752dc3f93b 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -379,4 +379,3 @@ void __init xfrm4_init(void)
 	xfrm4_protocol_init();
 	register_pernet_subsys(&xfrm4_net_ops);
 }
-
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 8e085cc05aeb..d7d0abc7fd0e 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -552,4 +552,3 @@ void ac6_proc_exit(struct net *net)
 	remove_proc_entry("anycast6", net->proc_net);
 }
 #endif
-
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 11025f8d124b..b643f5ce6c80 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -279,4 +279,3 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 	return nexthdr;
 }
 EXPORT_SYMBOL(ipv6_find_hdr);
-
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 24535169663d..4d780c7f0130 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1415,4 +1415,3 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 }
 EXPORT_SYMBOL(compat_ipv6_getsockopt);
 #endif
-
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index b8858c546f41..1678cf037688 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -355,4 +355,3 @@ void ipv6_misc_proc_exit(void)
 {
 	unregister_pernet_subsys(&ipv6_proc_ops);
 }
-
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index b15075a5c227..16f434791763 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -196,4 +196,3 @@ void xfrm6_state_fini(void)
 {
 	xfrm_state_unregister_afinfo(&xfrm6_state_afinfo);
 }
-
-- 
cgit v1.2.3


From b9c7a7acc749f3d0667a2ab44ea38110d5a1f286 Mon Sep 17 00:00:00 2001
From: Nogah Frankel <nogahf@mellanox.com>
Date: Wed, 28 Feb 2018 10:45:06 +0100
Subject: net: sch: prio: Add offload ability for grafting a child

Offload sch_prio graft command for capable drivers.
Warn in case of a failure, unless the graft was done as part of a destroy
operation (the new qdisc is a noop) or if all the qdiscs (the parent, the
old child, and the new one) are not offloaded.

Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h |  8 ++++++++
 net/sched/sch_prio.c  | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

(limited to 'include/net')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 87406252f0a3..e828d31be5da 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -806,6 +806,7 @@ enum tc_prio_command {
 	TC_PRIO_REPLACE,
 	TC_PRIO_DESTROY,
 	TC_PRIO_STATS,
+	TC_PRIO_GRAFT,
 };
 
 struct tc_prio_qopt_offload_params {
@@ -818,6 +819,11 @@ struct tc_prio_qopt_offload_params {
 	struct gnet_stats_queue *qstats;
 };
 
+struct tc_prio_qopt_offload_graft_params {
+	u8 band;
+	u32 child_handle;
+};
+
 struct tc_prio_qopt_offload {
 	enum tc_prio_command command;
 	u32 handle;
@@ -825,6 +831,8 @@ struct tc_prio_qopt_offload {
 	union {
 		struct tc_prio_qopt_offload_params replace_params;
 		struct tc_qopt_offload_stats stats;
+		struct tc_prio_qopt_offload_graft_params graft_params;
 	};
 };
+
 #endif
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index ba2d6d17d95a..222e53d3d27a 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -308,12 +308,44 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 		      struct Qdisc **old, struct netlink_ext_ack *extack)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
+	struct tc_prio_qopt_offload graft_offload;
+	struct net_device *dev = qdisc_dev(sch);
 	unsigned long band = arg - 1;
+	bool any_qdisc_is_offloaded;
+	int err;
 
 	if (new == NULL)
 		new = &noop_qdisc;
 
 	*old = qdisc_replace(sch, new, &q->queues[band]);
+
+	if (!tc_can_offload(dev))
+		return 0;
+
+	graft_offload.handle = sch->handle;
+	graft_offload.parent = sch->parent;
+	graft_offload.graft_params.band = band;
+	graft_offload.graft_params.child_handle = new->handle;
+	graft_offload.command = TC_PRIO_GRAFT;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO,
+					    &graft_offload);
+
+	/* Don't report error if the graft is part of destroy operation. */
+	if (err && new != &noop_qdisc) {
+		/* Don't report error if the parent, the old child and the new
+		 * one are not offloaded.
+		 */
+		any_qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED;
+		any_qdisc_is_offloaded |= new->flags & TCQ_F_OFFLOADED;
+		if (*old)
+			any_qdisc_is_offloaded |= (*old)->flags &
+						   TCQ_F_OFFLOADED;
+
+		if (any_qdisc_is_offloaded)
+			NL_SET_ERR_MSG(extack, "Offloading graft operation failed.");
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From bfff4862653bb96001ab57c1edd6d03f48e5f035 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 28 Feb 2018 22:40:16 -0500
Subject: net: fib_rules: support for match on ip_proto, sport and dport

uapi for ip_proto, sport and dport range match
in fib rules.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fib_rules.h        | 36 ++++++++++++++++-
 include/uapi/linux/fib_rules.h |  8 ++++
 net/core/fib_rules.c           | 92 +++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 133 insertions(+), 3 deletions(-)

(limited to 'include/net')

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index b3d216249240..6dd0a00653ae 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -27,7 +27,7 @@ struct fib_rule {
 	u8			action;
 	u8			l3mdev;
 	u8                      proto;
-	/* 1 byte hole, try to use */
+	u8			ip_proto;
 	u32			target;
 	__be64			tun_id;
 	struct fib_rule __rcu	*ctarget;
@@ -40,6 +40,8 @@ struct fib_rule {
 	char			iifname[IFNAMSIZ];
 	char			oifname[IFNAMSIZ];
 	struct fib_kuid_range	uid_range;
+	struct fib_rule_port_range	sport_range;
+	struct fib_rule_port_range	dport_range;
 	struct rcu_head		rcu;
 };
 
@@ -144,6 +146,38 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
 	return frh->table;
 }
 
+static inline bool fib_rule_port_range_set(const struct fib_rule_port_range *range)
+{
+	return range->start != 0 && range->end != 0;
+}
+
+static inline bool fib_rule_port_inrange(const struct fib_rule_port_range *a,
+					 __be16 port)
+{
+	return ntohs(port) >= a->start &&
+		ntohs(port) <= a->end;
+}
+
+static inline bool fib_rule_port_range_valid(const struct fib_rule_port_range *a)
+{
+	return a->start != 0 && a->end != 0 && a->end < 0xffff &&
+		a->start <= a->end;
+}
+
+static inline bool fib_rule_port_range_compare(struct fib_rule_port_range *a,
+					       struct fib_rule_port_range *b)
+{
+	return a->start == b->start &&
+		a->end == b->end;
+}
+
+static inline bool fib_rule_requires_fldissect(struct fib_rule *rule)
+{
+	return rule->ip_proto ||
+		fib_rule_port_range_set(&rule->sport_range) ||
+		fib_rule_port_range_set(&rule->dport_range);
+}
+
 struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *,
 					 struct net *);
 void fib_rules_unregister(struct fib_rules_ops *);
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 77d90ae38114..232df14e1287 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -35,6 +35,11 @@ struct fib_rule_uid_range {
 	__u32		end;
 };
 
+struct fib_rule_port_range {
+	__u16		start;
+	__u16		end;
+};
+
 enum {
 	FRA_UNSPEC,
 	FRA_DST,	/* destination address */
@@ -59,6 +64,9 @@ enum {
 	FRA_L3MDEV,	/* iif or oif is l3mdev goto its table */
 	FRA_UID_RANGE,	/* UID range */
 	FRA_PROTOCOL,   /* Originator of the rule */
+	FRA_IP_PROTO,	/* ip proto */
+	FRA_SPORT_RANGE, /* sport */
+	FRA_DPORT_RANGE, /* dport */
 	__FRA_MAX
 };
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index a6aea805a0a2..f6f04fc0f629 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -33,6 +33,10 @@ bool fib_rule_matchall(const struct fib_rule *rule)
 	if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
 	    !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
 		return false;
+	if (fib_rule_port_range_set(&rule->sport_range))
+		return false;
+	if (fib_rule_port_range_set(&rule->dport_range))
+		return false;
 	return true;
 }
 EXPORT_SYMBOL_GPL(fib_rule_matchall);
@@ -221,6 +225,26 @@ static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range)
 	return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);
 }
 
+static int nla_get_port_range(struct nlattr *pattr,
+			      struct fib_rule_port_range *port_range)
+{
+	const struct fib_rule_port_range *pr = nla_data(pattr);
+
+	if (!fib_rule_port_range_valid(pr))
+		return -EINVAL;
+
+	port_range->start = pr->start;
+	port_range->end = pr->end;
+
+	return 0;
+}
+
+static int nla_put_port_range(struct sk_buff *skb, int attrtype,
+			      struct fib_rule_port_range *range)
+{
+	return nla_put(skb, attrtype, sizeof(*range), range);
+}
+
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 			  struct flowi *fl, int flags,
 			  struct fib_lookup_arg *arg)
@@ -425,6 +449,17 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
 		    !uid_eq(r->uid_range.end, rule->uid_range.end))
 			continue;
 
+		if (r->ip_proto != rule->ip_proto)
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->sport_range,
+						 &rule->sport_range))
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->dport_range,
+						 &rule->dport_range))
+			continue;
+
 		if (!ops->compare(r, frh, tb))
 			continue;
 		return 1;
@@ -569,6 +604,23 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		rule->uid_range = fib_kuid_range_unset;
 	}
 
+	if (tb[FRA_IP_PROTO])
+		rule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]);
+
+	if (tb[FRA_SPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_SPORT_RANGE],
+					 &rule->sport_range);
+		if (err)
+			goto errout_free;
+	}
+
+	if (tb[FRA_DPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_DPORT_RANGE],
+					 &rule->dport_range);
+		if (err)
+			goto errout_free;
+	}
+
 	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
 	    rule_exists(ops, frh, tb, rule)) {
 		err = -EEXIST;
@@ -634,6 +686,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
+	struct fib_rule_port_range sprange = {0, 0};
+	struct fib_rule_port_range dprange = {0, 0};
 	struct fib_rules_ops *ops = NULL;
 	struct fib_rule *rule, *r;
 	struct nlattr *tb[FRA_MAX+1];
@@ -667,6 +721,20 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		range = fib_kuid_range_unset;
 	}
 
+	if (tb[FRA_SPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_SPORT_RANGE],
+					 &sprange);
+		if (err)
+			goto errout;
+	}
+
+	if (tb[FRA_DPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_DPORT_RANGE],
+					 &dprange);
+		if (err)
+			goto errout;
+	}
+
 	list_for_each_entry(rule, &ops->rules_list, list) {
 		if (tb[FRA_PROTOCOL] &&
 		    (rule->proto != nla_get_u8(tb[FRA_PROTOCOL])))
@@ -712,6 +780,18 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		     !uid_eq(rule->uid_range.end, range.end)))
 			continue;
 
+		if (tb[FRA_IP_PROTO] &&
+		    (rule->ip_proto != nla_get_u8(tb[FRA_IP_PROTO])))
+			continue;
+
+		if (fib_rule_port_range_set(&sprange) &&
+		    !fib_rule_port_range_compare(&rule->sport_range, &sprange))
+			continue;
+
+		if (fib_rule_port_range_set(&dprange) &&
+		    !fib_rule_port_range_compare(&rule->dport_range, &dprange))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 
@@ -790,7 +870,10 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(4) /* FRA_FWMASK */
 			 + nla_total_size_64bit(8) /* FRA_TUN_ID */
 			 + nla_total_size(sizeof(struct fib_kuid_range))
-			 + nla_total_size(1); /* FRA_PROTOCOL */
+			 + nla_total_size(1) /* FRA_PROTOCOL */
+			 + nla_total_size(1) /* FRA_IP_PROTO */
+			 + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */
+			 + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);
@@ -855,7 +938,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    (rule->l3mdev &&
 	     nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) ||
 	    (uid_range_set(&rule->uid_range) &&
-	     nla_put_uid_range(skb, &rule->uid_range)))
+	     nla_put_uid_range(skb, &rule->uid_range)) ||
+	    (fib_rule_port_range_set(&rule->sport_range) &&
+	     nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) ||
+	    (fib_rule_port_range_set(&rule->dport_range) &&
+	     nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) ||
+	    (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {
-- 
cgit v1.2.3


From e37b1e978bec5334dc379d8c2423d063af207430 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 28 Feb 2018 22:42:41 -0500
Subject: ipv6: route: dissect flow in input path if fib rules need it

Dissect flow in fwd path if fib rules require it. Controlled by
a flag to avoid penatly for the common case. Flag is set when fib
rules with sport, dport and proto match that require flow dissect
are installed. Also passes the dissected hash keys to the multipath
hash function when applicable to avoid dissecting the flow again.
icmp packets will continue to use inner header for hash
calculations (Thanks to Nikolay Aleksandrov for some review here).

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 27 ++++++++++++++++++++++++++-
 include/net/netns/ipv4.h |  1 +
 net/ipv4/fib_rules.c     |  8 ++++++++
 net/ipv4/fib_semantics.c |  2 +-
 net/ipv4/route.c         | 43 +++++++++++++++++++++++++++++--------------
 5 files changed, 65 insertions(+), 16 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 15e19c5c6f26..8812582a94d5 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -293,6 +293,13 @@ static inline unsigned int fib4_rules_seq_read(struct net *net)
 	return 0;
 }
 
+static inline bool fib4_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi4 *fl4,
+						 struct flow_keys *flkeys)
+{
+	return false;
+}
 #else /* CONFIG_IP_MULTIPLE_TABLES */
 int __net_init fib4_rules_init(struct net *net);
 void __net_exit fib4_rules_exit(struct net *net);
@@ -341,6 +348,24 @@ bool fib4_rule_default(const struct fib_rule *rule);
 int fib4_rules_dump(struct net *net, struct notifier_block *nb);
 unsigned int fib4_rules_seq_read(struct net *net);
 
+static inline bool fib4_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi4 *fl4,
+						 struct flow_keys *flkeys)
+{
+	unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+
+	if (!net->ipv4.fib_rules_require_fldissect)
+		return false;
+
+	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	fl4->fl4_sport = flkeys->ports.src;
+	fl4->fl4_dport = flkeys->ports.dst;
+	fl4->flowi4_proto = flkeys->basic.ip_proto;
+
+	return true;
+}
+
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 /* Exported by fib_frontend.c */
@@ -371,7 +396,7 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
-		       const struct sk_buff *skb);
+		       const struct sk_buff *skb, struct flow_keys *flkeys);
 #endif
 void fib_select_multipath(struct fib_result *res, int hash);
 void fib_select_path(struct net *net, struct fib_result *res,
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 44668c29701a..3a970e429ab6 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -52,6 +52,7 @@ struct netns_ipv4 {
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	struct fib_rules_ops	*rules_ops;
 	bool			fib_has_custom_rules;
+	unsigned int		fib_rules_require_fldissect;
 	struct fib_table __rcu	*fib_main;
 	struct fib_table __rcu	*fib_default;
 #endif
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 16083b82954b..737d11bc8838 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -255,6 +255,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	}
 #endif
 
+	if (fib_rule_requires_fldissect(rule))
+		net->ipv4.fib_rules_require_fldissect++;
+
 	rule4->src_len = frh->src_len;
 	rule4->srcmask = inet_make_mask(rule4->src_len);
 	rule4->dst_len = frh->dst_len;
@@ -283,6 +286,10 @@ static int fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
+
+	if (net->ipv4.fib_rules_require_fldissect &&
+	    fib_rule_requires_fldissect(rule))
+		net->ipv4.fib_rules_require_fldissect--;
 errout:
 	return err;
 }
@@ -400,6 +407,7 @@ int __net_init fib4_rules_init(struct net *net)
 		goto fail;
 	net->ipv4.rules_ops = ops;
 	net->ipv4.fib_has_custom_rules = false;
+	net->ipv4.fib_rules_require_fldissect = 0;
 	return 0;
 
 fail:
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f31e6575ab91..181b0d8d589c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1770,7 +1770,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, fl4, skb);
+		int h = fib_multipath_hash(res->fi, fl4, skb, NULL);
 
 		fib_select_multipath(res, h);
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 26eefa2eaa44..3bb686dac273 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1783,7 +1783,7 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb,
 
 /* if skb is set it will be used and fl4 can be NULL */
 int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
-		       const struct sk_buff *skb)
+		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
 	struct net *net = fi->fib_net;
 	struct flow_keys hash_keys;
@@ -1810,14 +1810,23 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 			if (skb->l4_hash)
 				return skb_get_hash_raw(skb) >> 1;
 			memset(&hash_keys, 0, sizeof(hash_keys));
-			skb_flow_dissect_flow_keys(skb, &keys, flag);
 
-			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
-			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
-			hash_keys.ports.src = keys.ports.src;
-			hash_keys.ports.dst = keys.ports.dst;
-			hash_keys.basic.ip_proto = keys.basic.ip_proto;
+			if (flkeys) {
+				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+				hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src;
+				hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst;
+				hash_keys.ports.src = flkeys->ports.src;
+				hash_keys.ports.dst = flkeys->ports.dst;
+				hash_keys.basic.ip_proto = flkeys->basic.ip_proto;
+			} else {
+				skb_flow_dissect_flow_keys(skb, &keys, flag);
+				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+				hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+				hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+				hash_keys.ports.src = keys.ports.src;
+				hash_keys.ports.dst = keys.ports.dst;
+				hash_keys.basic.ip_proto = keys.basic.ip_proto;
+			}
 		} else {
 			memset(&hash_keys, 0, sizeof(hash_keys));
 			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -1838,11 +1847,12 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 static int ip_mkroute_input(struct sk_buff *skb,
 			    struct fib_result *res,
 			    struct in_device *in_dev,
-			    __be32 daddr, __be32 saddr, u32 tos)
+			    __be32 daddr, __be32 saddr, u32 tos,
+			    struct flow_keys *hkeys)
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, NULL, skb);
+		int h = fib_multipath_hash(res->fi, NULL, skb, hkeys);
 
 		fib_select_multipath(res, h);
 	}
@@ -1868,13 +1878,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			       struct fib_result *res)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	struct flow_keys *flkeys = NULL, _flkeys;
+	struct net    *net = dev_net(dev);
 	struct ip_tunnel_info *tun_info;
-	struct flowi4	fl4;
+	int		err = -EINVAL;
 	unsigned int	flags = 0;
 	u32		itag = 0;
 	struct rtable	*rth;
-	int		err = -EINVAL;
-	struct net    *net = dev_net(dev);
+	struct flowi4	fl4;
 	bool do_cache;
 
 	/* IP on this device is disabled. */
@@ -1933,6 +1944,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+
+	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys))
+		flkeys = &_flkeys;
+
 	err = fib_lookup(net, &fl4, res, 0);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
@@ -1958,7 +1973,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (res->type != RTN_UNICAST)
 		goto martian_destination;
 
-	err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos);
+	err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys);
 out:	return err;
 
 brd_input:
-- 
cgit v1.2.3


From 5e5d6fed374155ba1a7a5ca5f12fbec2285d06a2 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 28 Feb 2018 22:43:22 -0500
Subject: ipv6: route: dissect flow in input path if fib rules need it

Dissect flow in fwd path if fib rules require it. Controlled by
a flag to avoid penatly for the common case. Flag is set when fib
rules with sport, dport and proto match that require flow dissect
are installed. Also passes the dissected hash keys to the multipath
hash function when applicable to avoid dissecting the flow again.
icmp packets will continue to use inner header for hash
calculations.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h    | 25 +++++++++++++++++++++++++
 include/net/ip6_route.h  |  4 +++-
 include/net/netns/ipv6.h |  3 ++-
 net/ipv6/fib6_rules.c    | 16 ++++++++++++++++
 net/ipv6/icmp.c          |  2 +-
 net/ipv6/route.c         | 34 +++++++++++++++++++++++++---------
 6 files changed, 72 insertions(+), 12 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 34ec321d6a03..8d906a35b534 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -415,6 +415,24 @@ void fib6_rules_cleanup(void);
 bool fib6_rule_default(const struct fib_rule *rule);
 int fib6_rules_dump(struct net *net, struct notifier_block *nb);
 unsigned int fib6_rules_seq_read(struct net *net);
+
+static inline bool fib6_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi6 *fl6,
+						 struct flow_keys *flkeys)
+{
+	unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+
+	if (!net->ipv6.fib6_rules_require_fldissect)
+		return false;
+
+	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	fl6->fl6_sport = flkeys->ports.src;
+	fl6->fl6_dport = flkeys->ports.dst;
+	fl6->flowi6_proto = flkeys->basic.ip_proto;
+
+	return true;
+}
 #else
 static inline int               fib6_rules_init(void)
 {
@@ -436,5 +454,12 @@ static inline unsigned int fib6_rules_seq_read(struct net *net)
 {
 	return 0;
 }
+static inline bool fib6_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi6 *fl6,
+						 struct flow_keys *flkeys)
+{
+	return false;
+}
 #endif
 #endif
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 27d23a65f3cd..da2bde5fda8f 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -127,7 +127,8 @@ static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
 
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif, int flags);
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb);
+u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
+		       struct flow_keys *hkeys);
 
 struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
 
@@ -266,4 +267,5 @@ static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
 	       ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
 	       !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
 }
+
 #endif
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 987cc4569cb8..2b9194229a56 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -71,7 +71,8 @@ struct netns_ipv6 {
 	unsigned int		 ip6_rt_gc_expire;
 	unsigned long		 ip6_rt_last_gc;
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	bool			 fib6_has_custom_rules;
+	unsigned int		fib6_rules_require_fldissect;
+	bool			fib6_has_custom_rules;
 	struct rt6_info         *ip6_prohibit_entry;
 	struct rt6_info         *ip6_blk_hole_entry;
 	struct fib6_table       *fib6_local_tbl;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index bcd1f22ac7b1..04e5f523e50f 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -269,12 +269,26 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule6->dst.plen = frh->dst_len;
 	rule6->tclass = frh->tos;
 
+	if (fib_rule_requires_fldissect(rule))
+		net->ipv6.fib6_rules_require_fldissect++;
+
 	net->ipv6.fib6_has_custom_rules = true;
 	err = 0;
 errout:
 	return err;
 }
 
+static int fib6_rule_delete(struct fib_rule *rule)
+{
+	struct net *net = rule->fr_net;
+
+	if (net->ipv6.fib6_rules_require_fldissect &&
+	    fib_rule_requires_fldissect(rule))
+		net->ipv6.fib6_rules_require_fldissect--;
+
+	return 0;
+}
+
 static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 			     struct nlattr **tb)
 {
@@ -334,6 +348,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = {
 	.match			= fib6_rule_match,
 	.suppress		= fib6_rule_suppress,
 	.configure		= fib6_rule_configure,
+	.delete			= fib6_rule_delete,
 	.compare		= fib6_rule_compare,
 	.fill			= fib6_rule_fill,
 	.nlmsg_payload		= fib6_rule_nlmsg_payload,
@@ -361,6 +376,7 @@ static int __net_init fib6_rules_net_init(struct net *net)
 		goto out_fib6_rules_ops;
 
 	net->ipv6.fib6_rules_ops = ops;
+	net->ipv6.fib6_rules_require_fldissect = 0;
 out:
 	return err;
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4fa4f1b150a4..b0778d323b6e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -522,7 +522,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
-	fl6.mp_hash = rt6_multipath_hash(&fl6, skb);
+	fl6.mp_hash = rt6_multipath_hash(&fl6, skb, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index aa709b644945..e2bb40824c85 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -460,7 +460,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
 	if (!fl6->mp_hash)
-		fl6->mp_hash = rt6_multipath_hash(fl6, NULL);
+		fl6->mp_hash = rt6_multipath_hash(fl6, NULL, NULL);
 
 	if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound))
 		return match;
@@ -1786,10 +1786,12 @@ struct dst_entry *ip6_route_input_lookup(struct net *net,
 EXPORT_SYMBOL_GPL(ip6_route_input_lookup);
 
 static void ip6_multipath_l3_keys(const struct sk_buff *skb,
-				  struct flow_keys *keys)
+				  struct flow_keys *keys,
+				  struct flow_keys *flkeys)
 {
 	const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
 	const struct ipv6hdr *key_iph = outer_iph;
+	struct flow_keys *_flkeys = flkeys;
 	const struct ipv6hdr *inner_iph;
 	const struct icmp6hdr *icmph;
 	struct ipv6hdr _inner_iph;
@@ -1811,22 +1813,31 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
 		goto out;
 
 	key_iph = inner_iph;
+	_flkeys = NULL;
 out:
 	memset(keys, 0, sizeof(*keys));
 	keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
-	keys->addrs.v6addrs.src = key_iph->saddr;
-	keys->addrs.v6addrs.dst = key_iph->daddr;
-	keys->tags.flow_label = ip6_flowinfo(key_iph);
-	keys->basic.ip_proto = key_iph->nexthdr;
+	if (_flkeys) {
+		keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src;
+		keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst;
+		keys->tags.flow_label = _flkeys->tags.flow_label;
+		keys->basic.ip_proto = _flkeys->basic.ip_proto;
+	} else {
+		keys->addrs.v6addrs.src = key_iph->saddr;
+		keys->addrs.v6addrs.dst = key_iph->daddr;
+		keys->tags.flow_label = ip6_flowinfo(key_iph);
+		keys->basic.ip_proto = key_iph->nexthdr;
+	}
 }
 
 /* if skb is set it will be used and fl6 can be NULL */
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb)
+u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
+		       struct flow_keys *flkeys)
 {
 	struct flow_keys hash_keys;
 
 	if (skb) {
-		ip6_multipath_l3_keys(skb, &hash_keys);
+		ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
 		return flow_hash_from_keys(&hash_keys) >> 1;
 	}
 
@@ -1847,12 +1858,17 @@ void ip6_route_input(struct sk_buff *skb)
 		.flowi6_mark = skb->mark,
 		.flowi6_proto = iph->nexthdr,
 	};
+	struct flow_keys *flkeys = NULL, _flkeys;
 
 	tun_info = skb_tunnel_info(skb);
 	if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX))
 		fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id;
+
+	if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys))
+		flkeys = &_flkeys;
+
 	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
-		fl6.mp_hash = rt6_multipath_hash(&fl6, skb);
+		fl6.mp_hash = rt6_multipath_hash(&fl6, skb, flkeys);
 	skb_dst_drop(skb);
 	skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
 }
-- 
cgit v1.2.3


From b70432f7319eb75b24ca57dde8146c5e27244780 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Wed, 28 Feb 2018 23:29:32 +0200
Subject: mroute*: Make mr_table a common struct

Following previous changes to ip6mr, mr_table and mr6_table are
basically the same [up to mr6_table having additional '6' suffixes to
its variable names].
Move the common structure definition into a common header; This
requires renaming all references in ip6mr to variables that had the
distinct suffix.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mroute.h      |  21 ----
 include/linux/mroute6.h     |   1 -
 include/linux/mroute_base.h |  46 +++++++
 include/net/netns/ipv6.h    |   2 +-
 net/ipv4/ipmr.c             |   2 -
 net/ipv6/ip6mr.c            | 301 ++++++++++++++++++++------------------------
 6 files changed, 186 insertions(+), 187 deletions(-)

(limited to 'include/net')

diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index b8aadffe6237..8688c5d03a24 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -4,8 +4,6 @@
 
 #include <linux/in.h>
 #include <linux/pim.h>
-#include <linux/rhashtable.h>
-#include <net/sock.h>
 #include <net/fib_rules.h>
 #include <net/fib_notifier.h>
 #include <uapi/linux/mroute.h>
@@ -67,25 +65,6 @@ struct vif_entry_notifier_info {
 
 #define VIFF_STATIC 0x8000
 
-#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
-
-struct mr_table {
-	struct list_head	list;
-	possible_net_t		net;
-	u32			id;
-	struct sock __rcu	*mroute_sk;
-	struct timer_list	ipmr_expire_timer;
-	struct list_head	mfc_unres_queue;
-	struct vif_device	vif_table[MAXVIFS];
-	struct rhltable		mfc_hash;
-	struct list_head	mfc_cache_list;
-	int			maxvif;
-	atomic_t		cache_resolve_queue_len;
-	bool			mroute_do_assert;
-	bool			mroute_do_pim;
-	int			mroute_reg_vif_num;
-};
-
 /* mfc_flags:
  * MFC_STATIC - the entry was added statically (not by a routing daemon)
  * MFC_OFFLOAD - the entry was offloaded to the hardware
diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index e2dac199861e..d5c8dc155a42 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -8,7 +8,6 @@
 #include <net/net_namespace.h>
 #include <uapi/linux/mroute6.h>
 #include <linux/mroute_base.h>
-#include <linux/rhashtable.h>
 
 #ifdef CONFIG_IPV6_MROUTE
 static inline int ip6_mroute_opt(int opt)
diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index 0de651e15f27..1cc944a14df5 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -2,6 +2,9 @@
 #define __LINUX_MROUTE_BASE_H
 
 #include <linux/netdevice.h>
+#include <linux/rhashtable.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
 
 /**
  * struct vif_device - interface representor for multicast routing
@@ -32,6 +35,49 @@ struct vif_device {
 	__be32 local, remote;
 };
 
+#ifndef MAXVIFS
+/* This one is nasty; value is defined in uapi using different symbols for
+ * mroute and morute6 but both map into same 32.
+ */
+#define MAXVIFS	32
+#endif
+
+#define VIF_EXISTS(_mrt, _idx) (!!((_mrt)->vif_table[_idx].dev))
+
+/**
+ * struct mr_table - a multicast routing table
+ * @list: entry within a list of multicast routing tables
+ * @net: net where this table belongs
+ * @id: identifier of the table
+ * @mroute_sk: socket associated with the table
+ * @ipmr_expire_timer: timer for handling unresolved routes
+ * @mfc_unres_queue: list of unresolved MFC entries
+ * @vif_table: array containing all possible vifs
+ * @mfc_hash: Hash table of all resolved routes for easy lookup
+ * @mfc_cache_list: list of resovled routes for possible traversal
+ * @maxvif: Identifier of highest value vif currently in use
+ * @cache_resolve_queue_len: current size of unresolved queue
+ * @mroute_do_assert: Whether to inform userspace on wrong ingress
+ * @mroute_do_pim: Whether to receive IGMP PIMv1
+ * @mroute_reg_vif_num: PIM-device vif index
+ */
+struct mr_table {
+	struct list_head	list;
+	possible_net_t		net;
+	u32			id;
+	struct sock __rcu	*mroute_sk;
+	struct timer_list	ipmr_expire_timer;
+	struct list_head	mfc_unres_queue;
+	struct vif_device	vif_table[MAXVIFS];
+	struct rhltable		mfc_hash;
+	struct list_head	mfc_cache_list;
+	int			maxvif;
+	atomic_t		cache_resolve_queue_len;
+	bool			mroute_do_assert;
+	bool			mroute_do_pim;
+	int			mroute_reg_vif_num;
+};
+
 #ifdef CONFIG_IP_MROUTE_COMMON
 void vif_device_init(struct vif_device *v,
 		     struct net_device *dev,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 2b9194229a56..e286fda09fcf 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -85,7 +85,7 @@ struct netns_ipv6 {
 	struct sock		*mc_autojoin_sk;
 #ifdef CONFIG_IPV6_MROUTE
 #ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
-	struct mr6_table	*mrt6;
+	struct mr_table		*mrt6;
 #else
 	struct list_head	mr6_tables;
 	struct fib_rules_ops	*mr6_rules_ops;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1370edad64bf..a1bf0020cad1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -31,7 +31,6 @@
 #include <linux/cache.h>
 #include <linux/capability.h>
 #include <linux/errno.h>
-#include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/kernel.h>
 #include <linux/fcntl.h>
@@ -53,7 +52,6 @@
 #include <net/protocol.h>
 #include <linux/skbuff.h>
 #include <net/route.h>
-#include <net/sock.h>
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/raw.h>
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6f0b7f4894b2..adbb826ca8fd 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -20,7 +20,6 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
-#include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/kernel.h>
 #include <linux/fcntl.h>
@@ -36,7 +35,6 @@
 #include <linux/compat.h>
 #include <net/protocol.h>
 #include <linux/skbuff.h>
-#include <net/sock.h>
 #include <net/raw.h>
 #include <linux/notifier.h>
 #include <linux/if_arp.h>
@@ -54,31 +52,12 @@
 #include <net/ip6_checksum.h>
 #include <linux/netconf.h>
 
-struct mr6_table {
-	struct list_head	list;
-	possible_net_t		net;
-	u32			id;
-	struct sock __rcu	*mroute6_sk;
-	struct timer_list	ipmr_expire_timer;
-	struct list_head	mfc6_unres_queue;
-	struct vif_device	vif6_table[MAXMIFS];
-	struct rhltable		mfc6_hash;
-	struct list_head	mfc6_cache_list;
-	int			maxvif;
-	atomic_t		cache_resolve_queue_len;
-	bool			mroute_do_assert;
-	bool			mroute_do_pim;
-#ifdef CONFIG_IPV6_PIMSM_V2
-	int			mroute_reg_vif_num;
-#endif
-};
-
 struct ip6mr_rule {
 	struct fib_rule		common;
 };
 
 struct ip6mr_result {
-	struct mr6_table	*mrt;
+	struct mr_table	*mrt;
 };
 
 /* Big lock, protecting vif table, mrt cache and mroute socket state.
@@ -87,11 +66,7 @@ struct ip6mr_result {
 
 static DEFINE_RWLOCK(mrt_lock);
 
-/*
- *	Multicast router control variables
- */
-
-#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL)
+/* Multicast router control variables */
 
 /* Special spinlock for queue of unresolved entries */
 static DEFINE_SPINLOCK(mfc_unres_lock);
@@ -106,30 +81,30 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
 
 static struct kmem_cache *mrt_cachep __read_mostly;
 
-static struct mr6_table *ip6mr_new_table(struct net *net, u32 id);
-static void ip6mr_free_table(struct mr6_table *mrt);
+static struct mr_table *ip6mr_new_table(struct net *net, u32 id);
+static void ip6mr_free_table(struct mr_table *mrt);
 
-static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
+static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
 			   struct sk_buff *skb, struct mfc6_cache *cache);
-static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
+static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
 			      mifi_t mifi, int assert);
-static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
+static int __ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			       struct mfc6_cache *c, struct rtmsg *rtm);
-static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
+static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
 			      int cmd);
-static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt);
+static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt);
 static int ip6mr_rtm_dumproute(struct sk_buff *skb,
 			       struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt, bool all);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
 static void ipmr_expire_process(struct timer_list *t);
 
 #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
 #define ip6mr_for_each_table(mrt, net) \
 	list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list)
 
-static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
+static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
 {
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	ip6mr_for_each_table(mrt, net) {
 		if (mrt->id == id)
@@ -139,7 +114,7 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
 }
 
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
-			    struct mr6_table **mrt)
+			    struct mr_table **mrt)
 {
 	int err;
 	struct ip6mr_result res;
@@ -160,7 +135,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
 			     int flags, struct fib_lookup_arg *arg)
 {
 	struct ip6mr_result *res = arg->result;
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	switch (rule->action) {
 	case FR_ACT_TO_TBL:
@@ -228,7 +203,7 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = {
 static int __net_init ip6mr_rules_init(struct net *net)
 {
 	struct fib_rules_ops *ops;
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	int err;
 
 	ops = fib_rules_register(&ip6mr_rules_ops_template, net);
@@ -259,7 +234,7 @@ err1:
 
 static void __net_exit ip6mr_rules_exit(struct net *net)
 {
-	struct mr6_table *mrt, *next;
+	struct mr_table *mrt, *next;
 
 	rtnl_lock();
 	list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) {
@@ -273,13 +248,13 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
 #define ip6mr_for_each_table(mrt, net) \
 	for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
 
-static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
+static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
 {
 	return net->ipv6.mrt6;
 }
 
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
-			    struct mr6_table **mrt)
+			    struct mr_table **mrt)
 {
 	*mrt = net->ipv6.mrt6;
 	return 0;
@@ -320,9 +295,9 @@ static const struct rhashtable_params ip6mr_rht_params = {
 	.automatic_shrinking = true,
 };
 
-static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
+static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
 {
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	mrt = ip6mr_get_table(net, id);
 	if (mrt)
@@ -334,9 +309,9 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 	mrt->id = id;
 	write_pnet(&mrt->net, net);
 
-	rhltable_init(&mrt->mfc6_hash, &ip6mr_rht_params);
-	INIT_LIST_HEAD(&mrt->mfc6_cache_list);
-	INIT_LIST_HEAD(&mrt->mfc6_unres_queue);
+	rhltable_init(&mrt->mfc_hash, &ip6mr_rht_params);
+	INIT_LIST_HEAD(&mrt->mfc_cache_list);
+	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
 
 	timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0);
 
@@ -349,11 +324,11 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 	return mrt;
 }
 
-static void ip6mr_free_table(struct mr6_table *mrt)
+static void ip6mr_free_table(struct mr_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, true);
-	rhltable_destroy(&mrt->mfc6_hash);
+	rhltable_destroy(&mrt->mfc_hash);
 	kfree(mrt);
 }
 
@@ -361,7 +336,7 @@ static void ip6mr_free_table(struct mr6_table *mrt)
 
 struct ipmr_mfc_iter {
 	struct seq_net_private p;
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct list_head *cache;
 };
 
@@ -369,18 +344,18 @@ struct ipmr_mfc_iter {
 static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net,
 					   struct ipmr_mfc_iter *it, loff_t pos)
 {
-	struct mr6_table *mrt = it->mrt;
+	struct mr_table *mrt = it->mrt;
 	struct mfc6_cache *mfc;
 
 	rcu_read_lock();
-	it->cache = &mrt->mfc6_cache_list;
-	list_for_each_entry_rcu(mfc, &mrt->mfc6_cache_list, list)
+	it->cache = &mrt->mfc_cache_list;
+	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
 		if (pos-- == 0)
 			return mfc;
 	rcu_read_unlock();
 
 	spin_lock_bh(&mfc_unres_lock);
-	it->cache = &mrt->mfc6_unres_queue;
+	it->cache = &mrt->mfc_unres_queue;
 	list_for_each_entry(mfc, it->cache, list)
 		if (pos-- == 0)
 			return mfc;
@@ -396,7 +371,7 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net,
 
 struct ipmr_vif_iter {
 	struct seq_net_private p;
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	int ct;
 };
 
@@ -404,13 +379,13 @@ static struct vif_device *ip6mr_vif_seq_idx(struct net *net,
 					    struct ipmr_vif_iter *iter,
 					    loff_t pos)
 {
-	struct mr6_table *mrt = iter->mrt;
+	struct mr_table *mrt = iter->mrt;
 
 	for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
-		if (!MIF_EXISTS(mrt, iter->ct))
+		if (!VIF_EXISTS(mrt, iter->ct))
 			continue;
 		if (pos-- == 0)
-			return &mrt->vif6_table[iter->ct];
+			return &mrt->vif_table[iter->ct];
 	}
 	return NULL;
 }
@@ -420,7 +395,7 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct ipmr_vif_iter *iter = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
 	if (!mrt)
@@ -437,16 +412,16 @@ static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ipmr_vif_iter *iter = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct mr6_table *mrt = iter->mrt;
+	struct mr_table *mrt = iter->mrt;
 
 	++*pos;
 	if (v == SEQ_START_TOKEN)
 		return ip6mr_vif_seq_idx(net, iter, 0);
 
 	while (++iter->ct < mrt->maxvif) {
-		if (!MIF_EXISTS(mrt, iter->ct))
+		if (!VIF_EXISTS(mrt, iter->ct))
 			continue;
-		return &mrt->vif6_table[iter->ct];
+		return &mrt->vif_table[iter->ct];
 	}
 	return NULL;
 }
@@ -460,7 +435,7 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v)
 static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
 {
 	struct ipmr_vif_iter *iter = seq->private;
-	struct mr6_table *mrt = iter->mrt;
+	struct mr_table *mrt = iter->mrt;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -471,7 +446,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
 
 		seq_printf(seq,
 			   "%2td %-10s %8ld %7ld  %8ld %7ld %05X\n",
-			   vif - mrt->vif6_table,
+			   vif - mrt->vif_table,
 			   name, vif->bytes_in, vif->pkt_in,
 			   vif->bytes_out, vif->pkt_out,
 			   vif->flags);
@@ -503,7 +478,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct ipmr_mfc_iter *it = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
 	if (!mrt)
@@ -520,7 +495,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	struct mfc6_cache *mfc = v;
 	struct ipmr_mfc_iter *it = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct mr6_table *mrt = it->mrt;
+	struct mr_table *mrt = it->mrt;
 
 	++*pos;
 
@@ -530,12 +505,12 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	if (mfc->list.next != it->cache)
 		return list_entry(mfc->list.next, struct mfc6_cache, list);
 
-	if (it->cache == &mrt->mfc6_unres_queue)
+	if (it->cache == &mrt->mfc_unres_queue)
 		goto end_of_list;
 
 	/* exhausted cache_array, show unresolved */
 	rcu_read_unlock();
-	it->cache = &mrt->mfc6_unres_queue;
+	it->cache = &mrt->mfc_unres_queue;
 
 	spin_lock_bh(&mfc_unres_lock);
 	if (!list_empty(it->cache))
@@ -551,11 +526,11 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 {
 	struct ipmr_mfc_iter *it = seq->private;
-	struct mr6_table *mrt = it->mrt;
+	struct mr_table *mrt = it->mrt;
 
-	if (it->cache == &mrt->mfc6_unres_queue)
+	if (it->cache == &mrt->mfc_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == &mrt->mfc6_cache_list)
+	else if (it->cache == &mrt->mfc_cache_list)
 		rcu_read_unlock();
 }
 
@@ -571,20 +546,20 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
 	} else {
 		const struct mfc6_cache *mfc = v;
 		const struct ipmr_mfc_iter *it = seq->private;
-		struct mr6_table *mrt = it->mrt;
+		struct mr_table *mrt = it->mrt;
 
 		seq_printf(seq, "%pI6 %pI6 %-3hd",
 			   &mfc->mf6c_mcastgrp, &mfc->mf6c_origin,
 			   mfc->mf6c_parent);
 
-		if (it->cache != &mrt->mfc6_unres_queue) {
+		if (it->cache != &mrt->mfc_unres_queue) {
 			seq_printf(seq, " %8lu %8lu %8lu",
 				   mfc->mfc_un.res.pkt,
 				   mfc->mfc_un.res.bytes,
 				   mfc->mfc_un.res.wrong_if);
 			for (n = mfc->mfc_un.res.minvif;
 			     n < mfc->mfc_un.res.maxvif; n++) {
-				if (MIF_EXISTS(mrt, n) &&
+				if (VIF_EXISTS(mrt, n) &&
 				    mfc->mfc_un.res.ttls[n] < 255)
 					seq_printf(seq,
 						   " %2d:%-3d",
@@ -630,7 +605,7 @@ static int pim6_rcv(struct sk_buff *skb)
 	struct ipv6hdr   *encap;
 	struct net_device  *reg_dev = NULL;
 	struct net *net = dev_net(skb->dev);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct flowi6 fl6 = {
 		.flowi6_iif	= skb->dev->ifindex,
 		.flowi6_mark	= skb->mark,
@@ -664,7 +639,7 @@ static int pim6_rcv(struct sk_buff *skb)
 
 	read_lock(&mrt_lock);
 	if (reg_vif_num >= 0)
-		reg_dev = mrt->vif6_table[reg_vif_num].dev;
+		reg_dev = mrt->vif_table[reg_vif_num].dev;
 	if (reg_dev)
 		dev_hold(reg_dev);
 	read_unlock(&mrt_lock);
@@ -699,7 +674,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct flowi6 fl6 = {
 		.flowi6_oif	= dev->ifindex,
 		.flowi6_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
@@ -742,7 +717,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
-static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
+static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
 {
 	struct net_device *dev;
 	char name[IFNAMSIZ];
@@ -779,7 +754,7 @@ failure:
  *	Delete a VIF entry
  */
 
-static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
+static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
 		       struct list_head *head)
 {
 	struct vif_device *v;
@@ -789,7 +764,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
 	if (vifi < 0 || vifi >= mrt->maxvif)
 		return -EADDRNOTAVAIL;
 
-	v = &mrt->vif6_table[vifi];
+	v = &mrt->vif_table[vifi];
 
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
@@ -808,7 +783,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
 	if (vifi + 1 == mrt->maxvif) {
 		int tmp;
 		for (tmp = vifi - 1; tmp >= 0; tmp--) {
-			if (MIF_EXISTS(mrt, tmp))
+			if (VIF_EXISTS(mrt, tmp))
 				break;
 		}
 		mrt->maxvif = tmp + 1;
@@ -849,7 +824,7 @@ static inline void ip6mr_cache_free(struct mfc6_cache *c)
    and reporting error to netlink readers.
  */
 
-static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
+static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c)
 {
 	struct net *net = read_pnet(&mrt->net);
 	struct sk_buff *skb;
@@ -875,13 +850,13 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
 
 /* Timer process for all the unresolved queue. */
 
-static void ipmr_do_expire_process(struct mr6_table *mrt)
+static void ipmr_do_expire_process(struct mr_table *mrt)
 {
 	unsigned long now = jiffies;
 	unsigned long expires = 10 * HZ;
 	struct mfc6_cache *c, *next;
 
-	list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) {
+	list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
 		if (time_after(c->mfc_un.unres.expires, now)) {
 			/* not yet... */
 			unsigned long interval = c->mfc_un.unres.expires - now;
@@ -895,20 +870,20 @@ static void ipmr_do_expire_process(struct mr6_table *mrt)
 		ip6mr_destroy_unres(mrt, c);
 	}
 
-	if (!list_empty(&mrt->mfc6_unres_queue))
+	if (!list_empty(&mrt->mfc_unres_queue))
 		mod_timer(&mrt->ipmr_expire_timer, jiffies + expires);
 }
 
 static void ipmr_expire_process(struct timer_list *t)
 {
-	struct mr6_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
+	struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
 
 	if (!spin_trylock(&mfc_unres_lock)) {
 		mod_timer(&mrt->ipmr_expire_timer, jiffies + 1);
 		return;
 	}
 
-	if (!list_empty(&mrt->mfc6_unres_queue))
+	if (!list_empty(&mrt->mfc_unres_queue))
 		ipmr_do_expire_process(mrt);
 
 	spin_unlock(&mfc_unres_lock);
@@ -916,7 +891,8 @@ static void ipmr_expire_process(struct timer_list *t)
 
 /* Fill oifs list. It is called under write locked mrt_lock. */
 
-static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache,
+static void ip6mr_update_thresholds(struct mr_table *mrt,
+				    struct mfc6_cache *cache,
 				    unsigned char *ttls)
 {
 	int vifi;
@@ -926,7 +902,7 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca
 	memset(cache->mfc_un.res.ttls, 255, MAXMIFS);
 
 	for (vifi = 0; vifi < mrt->maxvif; vifi++) {
-		if (MIF_EXISTS(mrt, vifi) &&
+		if (VIF_EXISTS(mrt, vifi) &&
 		    ttls[vifi] && ttls[vifi] < 255) {
 			cache->mfc_un.res.ttls[vifi] = ttls[vifi];
 			if (cache->mfc_un.res.minvif > vifi)
@@ -938,17 +914,17 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca
 	cache->mfc_un.res.lastuse = jiffies;
 }
 
-static int mif6_add(struct net *net, struct mr6_table *mrt,
+static int mif6_add(struct net *net, struct mr_table *mrt,
 		    struct mif6ctl *vifc, int mrtsock)
 {
 	int vifi = vifc->mif6c_mifi;
-	struct vif_device *v = &mrt->vif6_table[vifi];
+	struct vif_device *v = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct inet6_dev *in6_dev;
 	int err;
 
 	/* Is vif busy ? */
-	if (MIF_EXISTS(mrt, vifi))
+	if (VIF_EXISTS(mrt, vifi))
 		return -EADDRINUSE;
 
 	switch (vifc->mif6c_flags) {
@@ -1011,7 +987,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
 	return 0;
 }
 
-static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt,
+static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt,
 					   const struct in6_addr *origin,
 					   const struct in6_addr *mcastgrp)
 {
@@ -1022,7 +998,7 @@ static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt,
 	struct rhlist_head *tmp, *list;
 	struct mfc6_cache *c;
 
-	list = rhltable_lookup(&mrt->mfc6_hash, &arg, ip6mr_rht_params);
+	list = rhltable_lookup(&mrt->mfc_hash, &arg, ip6mr_rht_params);
 	rhl_for_each_entry_rcu(c, tmp, list, mnode)
 		return c;
 
@@ -1030,7 +1006,7 @@ static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt,
 }
 
 /* Look for a (*,*,oif) entry */
-static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt,
+static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr_table *mrt,
 						      mifi_t mifi)
 {
 	struct mfc6_cache_cmp_arg arg = {
@@ -1040,7 +1016,7 @@ static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt,
 	struct rhlist_head *tmp, *list;
 	struct mfc6_cache *c;
 
-	list = rhltable_lookup(&mrt->mfc6_hash, &arg, ip6mr_rht_params);
+	list = rhltable_lookup(&mrt->mfc_hash, &arg, ip6mr_rht_params);
 	rhl_for_each_entry_rcu(c, tmp, list, mnode)
 		if (c->mfc_un.res.ttls[mifi] < 255)
 			return c;
@@ -1049,7 +1025,7 @@ static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt,
 }
 
 /* Look for a (*,G) entry */
-static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt,
+static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt,
 					       struct in6_addr *mcastgrp,
 					       mifi_t mifi)
 {
@@ -1063,7 +1039,7 @@ static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt,
 	if (ipv6_addr_any(mcastgrp))
 		goto skip;
 
-	list = rhltable_lookup(&mrt->mfc6_hash, &arg, ip6mr_rht_params);
+	list = rhltable_lookup(&mrt->mfc_hash, &arg, ip6mr_rht_params);
 	rhl_for_each_entry_rcu(c, tmp, list, mnode) {
 		if (c->mfc_un.res.ttls[mifi] < 255)
 			return c;
@@ -1080,7 +1056,7 @@ skip:
 
 /* Look for a (S,G,iif) entry if parent != -1 */
 static struct mfc6_cache *
-ip6mr_cache_find_parent(struct mr6_table *mrt,
+ip6mr_cache_find_parent(struct mr_table *mrt,
 			const struct in6_addr *origin,
 			const struct in6_addr *mcastgrp,
 			int parent)
@@ -1092,7 +1068,7 @@ ip6mr_cache_find_parent(struct mr6_table *mrt,
 	struct rhlist_head *tmp, *list;
 	struct mfc6_cache *c;
 
-	list = rhltable_lookup(&mrt->mfc6_hash, &arg, ip6mr_rht_params);
+	list = rhltable_lookup(&mrt->mfc_hash, &arg, ip6mr_rht_params);
 	rhl_for_each_entry_rcu(c, tmp, list, mnode)
 		if (parent == -1 || parent == c->mf6c_parent)
 			return c;
@@ -1127,7 +1103,7 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
  *	A cache entry has gone into a resolved state from queued
  */
 
-static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
+static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt,
 				struct mfc6_cache *uc, struct mfc6_cache *c)
 {
 	struct sk_buff *skb;
@@ -1161,7 +1137,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
  *	Called under mrt_lock.
  */
 
-static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
+static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
 			      mifi_t mifi, int assert)
 {
 	struct sock *mroute6_sk;
@@ -1235,7 +1211,7 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
 	}
 
 	rcu_read_lock();
-	mroute6_sk = rcu_dereference(mrt->mroute6_sk);
+	mroute6_sk = rcu_dereference(mrt->mroute_sk);
 	if (!mroute6_sk) {
 		rcu_read_unlock();
 		kfree_skb(skb);
@@ -1260,14 +1236,14 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
  */
 
 static int
-ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
+ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi, struct sk_buff *skb)
 {
 	bool found = false;
 	int err;
 	struct mfc6_cache *c;
 
 	spin_lock_bh(&mfc_unres_lock);
-	list_for_each_entry(c, &mrt->mfc6_unres_queue, list) {
+	list_for_each_entry(c, &mrt->mfc_unres_queue, list) {
 		if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) &&
 		    ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) {
 			found = true;
@@ -1311,7 +1287,7 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
 		}
 
 		atomic_inc(&mrt->cache_resolve_queue_len);
-		list_add(&c->list, &mrt->mfc6_unres_queue);
+		list_add(&c->list, &mrt->mfc_unres_queue);
 		mr6_netlink_event(mrt, c, RTM_NEWROUTE);
 
 		ipmr_do_expire_process(mrt);
@@ -1336,7 +1312,7 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
  *	MFC6 cache manipulation by user space
  */
 
-static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc,
+static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc,
 			    int parent)
 {
 	struct mfc6_cache *c;
@@ -1348,7 +1324,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc,
 	rcu_read_unlock();
 	if (!c)
 		return -ENOENT;
-	rhltable_remove(&mrt->mfc6_hash, &c->mnode, ip6mr_rht_params);
+	rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
 	list_del_rcu(&c->list);
 
 	mr6_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1361,7 +1337,7 @@ static int ip6mr_device_event(struct notifier_block *this,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct vif_device *v;
 	int ct;
 
@@ -1369,7 +1345,7 @@ static int ip6mr_device_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	ip6mr_for_each_table(mrt, net) {
-		v = &mrt->vif6_table[0];
+		v = &mrt->vif_table[0];
 		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 			if (v->dev == dev)
 				mif6_delete(mrt, ct, 1, NULL);
@@ -1483,7 +1459,7 @@ void ip6_mr_cleanup(void)
 	kmem_cache_destroy(mrt_cachep);
 }
 
-static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
+static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
 			 struct mf6cctl *mfc, int mrtsock, int parent)
 {
 	unsigned char ttls[MAXMIFS];
@@ -1531,21 +1507,21 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
 	if (!mrtsock)
 		c->mfc_flags |= MFC_STATIC;
 
-	err = rhltable_insert_key(&mrt->mfc6_hash, &c->cmparg, &c->mnode,
+	err = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->mnode,
 				  ip6mr_rht_params);
 	if (err) {
 		pr_err("ip6mr: rhtable insert error %d\n", err);
 		ip6mr_cache_free(c);
 		return err;
 	}
-	list_add_tail_rcu(&c->list, &mrt->mfc6_cache_list);
+	list_add_tail_rcu(&c->list, &mrt->mfc_cache_list);
 
 	/* Check to see if we resolved a queued list. If so we
 	 * need to send on the frames and tidy up.
 	 */
 	found = false;
 	spin_lock_bh(&mfc_unres_lock);
-	list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) {
+	list_for_each_entry(uc, &mrt->mfc_unres_queue, list) {
 		if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) &&
 		    ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) {
 			list_del(&uc->list);
@@ -1554,7 +1530,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
 			break;
 		}
 	}
-	if (list_empty(&mrt->mfc6_unres_queue))
+	if (list_empty(&mrt->mfc_unres_queue))
 		del_timer(&mrt->ipmr_expire_timer);
 	spin_unlock_bh(&mfc_unres_lock);
 
@@ -1570,7 +1546,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr6_table *mrt, bool all)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
 	struct mfc6_cache *c, *tmp;
 	LIST_HEAD(list);
@@ -1578,17 +1554,17 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 
 	/* Shut down all active vif entries */
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+		if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
 			continue;
 		mif6_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
 	/* Wipe the cache */
-	list_for_each_entry_safe(c, tmp, &mrt->mfc6_cache_list, list) {
+	list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
 		if (!all && (c->mfc_flags & MFC_STATIC))
 			continue;
-		rhltable_remove(&mrt->mfc6_hash, &c->mnode, ip6mr_rht_params);
+		rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
 		list_del_rcu(&c->list);
 		mr6_netlink_event(mrt, c, RTM_DELROUTE);
 		ip6mr_cache_free(c);
@@ -1596,7 +1572,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 
 	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
 		spin_lock_bh(&mfc_unres_lock);
-		list_for_each_entry_safe(c, tmp, &mrt->mfc6_unres_queue, list) {
+		list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
 			list_del(&c->list);
 			mr6_netlink_event(mrt, c, RTM_DELROUTE);
 			ip6mr_destroy_unres(mrt, c);
@@ -1605,17 +1581,17 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 	}
 }
 
-static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
+static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk)
 {
 	int err = 0;
 	struct net *net = sock_net(sk);
 
 	rtnl_lock();
 	write_lock_bh(&mrt_lock);
-	if (rtnl_dereference(mrt->mroute6_sk)) {
+	if (rtnl_dereference(mrt->mroute_sk)) {
 		err = -EADDRINUSE;
 	} else {
-		rcu_assign_pointer(mrt->mroute6_sk, sk);
+		rcu_assign_pointer(mrt->mroute_sk, sk);
 		net->ipv6.devconf_all->mc_forwarding++;
 	}
 	write_unlock_bh(&mrt_lock);
@@ -1634,7 +1610,7 @@ int ip6mr_sk_done(struct sock *sk)
 {
 	int err = -EACCES;
 	struct net *net = sock_net(sk);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	if (sk->sk_type != SOCK_RAW ||
 	    inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
@@ -1642,9 +1618,9 @@ int ip6mr_sk_done(struct sock *sk)
 
 	rtnl_lock();
 	ip6mr_for_each_table(mrt, net) {
-		if (sk == rtnl_dereference(mrt->mroute6_sk)) {
+		if (sk == rtnl_dereference(mrt->mroute_sk)) {
 			write_lock_bh(&mrt_lock);
-			RCU_INIT_POINTER(mrt->mroute6_sk, NULL);
+			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
 			net->ipv6.devconf_all->mc_forwarding--;
 			write_unlock_bh(&mrt_lock);
 			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
@@ -1665,7 +1641,7 @@ int ip6mr_sk_done(struct sock *sk)
 
 bool mroute6_is_socket(struct net *net, struct sk_buff *skb)
 {
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct flowi6 fl6 = {
 		.flowi6_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
 		.flowi6_oif	= skb->dev->ifindex,
@@ -1675,7 +1651,7 @@ bool mroute6_is_socket(struct net *net, struct sk_buff *skb)
 	if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
 		return NULL;
 
-	return rcu_access_pointer(mrt->mroute6_sk);
+	return rcu_access_pointer(mrt->mroute_sk);
 }
 EXPORT_SYMBOL(mroute6_is_socket);
 
@@ -1693,7 +1669,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 	struct mf6cctl mfc;
 	mifi_t mifi;
 	struct net *net = sock_net(sk);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	if (sk->sk_type != SOCK_RAW ||
 	    inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
@@ -1704,7 +1680,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		return -ENOENT;
 
 	if (optname != MRT6_INIT) {
-		if (sk != rcu_access_pointer(mrt->mroute6_sk) &&
+		if (sk != rcu_access_pointer(mrt->mroute_sk) &&
 		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EACCES;
 	}
@@ -1728,7 +1704,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 			return -ENFILE;
 		rtnl_lock();
 		ret = mif6_add(net, mrt, &vif,
-			       sk == rtnl_dereference(mrt->mroute6_sk));
+			       sk == rtnl_dereference(mrt->mroute_sk));
 		rtnl_unlock();
 		return ret;
 
@@ -1764,7 +1740,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		else
 			ret = ip6mr_mfc_add(net, mrt, &mfc,
 					    sk ==
-					    rtnl_dereference(mrt->mroute6_sk),
+					    rtnl_dereference(mrt->mroute_sk),
 					    parent);
 		rtnl_unlock();
 		return ret;
@@ -1817,7 +1793,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		/* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */
 		if (v != RT_TABLE_DEFAULT && v >= 100000000)
 			return -EINVAL;
-		if (sk == rcu_access_pointer(mrt->mroute6_sk))
+		if (sk == rcu_access_pointer(mrt->mroute_sk))
 			return -EBUSY;
 
 		rtnl_lock();
@@ -1848,7 +1824,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
 	int olr;
 	int val;
 	struct net *net = sock_net(sk);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	if (sk->sk_type != SOCK_RAW ||
 	    inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
@@ -1899,7 +1875,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
 	struct vif_device *vif;
 	struct mfc6_cache *c;
 	struct net *net = sock_net(sk);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
 	if (!mrt)
@@ -1912,8 +1888,8 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
 		if (vr.mifi >= mrt->maxvif)
 			return -EINVAL;
 		read_lock(&mrt_lock);
-		vif = &mrt->vif6_table[vr.mifi];
-		if (MIF_EXISTS(mrt, vr.mifi)) {
+		vif = &mrt->vif_table[vr.mifi];
+		if (VIF_EXISTS(mrt, vr.mifi)) {
 			vr.icount = vif->pkt_in;
 			vr.ocount = vif->pkt_out;
 			vr.ibytes = vif->bytes_in;
@@ -1973,7 +1949,7 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 	struct vif_device *vif;
 	struct mfc6_cache *c;
 	struct net *net = sock_net(sk);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 
 	mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
 	if (!mrt)
@@ -1986,8 +1962,8 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 		if (vr.mifi >= mrt->maxvif)
 			return -EINVAL;
 		read_lock(&mrt_lock);
-		vif = &mrt->vif6_table[vr.mifi];
-		if (MIF_EXISTS(mrt, vr.mifi)) {
+		vif = &mrt->vif_table[vr.mifi];
+		if (VIF_EXISTS(mrt, vr.mifi)) {
 			vr.icount = vif->pkt_in;
 			vr.ocount = vif->pkt_out;
 			vr.ibytes = vif->bytes_in;
@@ -2037,11 +2013,11 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct
  *	Processing handlers for ip6mr_forward
  */
 
-static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
+static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
 			  struct sk_buff *skb, struct mfc6_cache *c, int vifi)
 {
 	struct ipv6hdr *ipv6h;
-	struct vif_device *vif = &mrt->vif6_table[vifi];
+	struct vif_device *vif = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct dst_entry *dst;
 	struct flowi6 fl6;
@@ -2111,18 +2087,18 @@ out_free:
 	return 0;
 }
 
-static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev)
+static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev)
 {
 	int ct;
 
 	for (ct = mrt->maxvif - 1; ct >= 0; ct--) {
-		if (mrt->vif6_table[ct].dev == dev)
+		if (mrt->vif_table[ct].dev == dev)
 			break;
 	}
 	return ct;
 }
 
-static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
+static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
 			   struct sk_buff *skb, struct mfc6_cache *cache)
 {
 	int psend = -1;
@@ -2153,7 +2129,7 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
 	/*
 	 * Wrong interface: drop packet and (maybe) send PIM assert.
 	 */
-	if (mrt->vif6_table[vif].dev != skb->dev) {
+	if (mrt->vif_table[vif].dev != skb->dev) {
 		cache->mfc_un.res.wrong_if++;
 
 		if (true_vifi >= 0 && mrt->mroute_do_assert &&
@@ -2173,8 +2149,8 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
 	}
 
 forward:
-	mrt->vif6_table[vif].pkt_in++;
-	mrt->vif6_table[vif].bytes_in += skb->len;
+	mrt->vif_table[vif].pkt_in++;
+	mrt->vif_table[vif].bytes_in += skb->len;
 
 	/*
 	 *	Forward the frame
@@ -2225,7 +2201,7 @@ int ip6_mr_input(struct sk_buff *skb)
 {
 	struct mfc6_cache *cache;
 	struct net *net = dev_net(skb->dev);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct flowi6 fl6 = {
 		.flowi6_iif	= skb->dev->ifindex,
 		.flowi6_mark	= skb->mark,
@@ -2276,7 +2252,7 @@ int ip6_mr_input(struct sk_buff *skb)
 }
 
 
-static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
+static int __ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			       struct mfc6_cache *c, struct rtmsg *rtm)
 {
 	struct rta_mfc_stats mfcs;
@@ -2291,15 +2267,16 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 		return -ENOENT;
 	}
 
-	if (MIF_EXISTS(mrt, c->mf6c_parent) &&
-	    nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0)
+	if (VIF_EXISTS(mrt, c->mf6c_parent) &&
+	    nla_put_u32(skb, RTA_IIF,
+			mrt->vif_table[c->mf6c_parent].dev->ifindex) < 0)
 		return -EMSGSIZE;
 	mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
 	if (!mp_attr)
 		return -EMSGSIZE;
 
 	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
-		if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
+		if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
 			nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
 			if (!nhp) {
 				nla_nest_cancel(skb, mp_attr);
@@ -2308,7 +2285,7 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 
 			nhp->rtnh_flags = 0;
 			nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
-			nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex;
+			nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex;
 			nhp->rtnh_len = sizeof(*nhp);
 		}
 	}
@@ -2334,7 +2311,7 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
 		    u32 portid)
 {
 	int err;
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct mfc6_cache *cache;
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
 
@@ -2403,7 +2380,7 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
 	return err;
 }
 
-static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
+static int ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			     u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
 			     int flags)
 {
@@ -2468,7 +2445,7 @@ static int mr6_msgsize(bool unresolved, int maxvif)
 	return len;
 }
 
-static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
+static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
 			      int cmd)
 {
 	struct net *net = read_pnet(&mrt->net);
@@ -2510,7 +2487,7 @@ static size_t mrt6msg_netlink_msgsize(size_t payloadlen)
 	return len;
 }
 
-static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt)
+static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt)
 {
 	struct net *net = read_pnet(&mrt->net);
 	struct nlmsghdr *nlh;
@@ -2561,7 +2538,7 @@ errout:
 static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
-	struct mr6_table *mrt;
+	struct mr_table *mrt;
 	struct mfc6_cache *mfc;
 	unsigned int t = 0, s_t;
 	unsigned int e = 0, s_e;
@@ -2573,7 +2550,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 	ip6mr_for_each_table(mrt, net) {
 		if (t < s_t)
 			goto next_table;
-		list_for_each_entry_rcu(mfc, &mrt->mfc6_cache_list, list) {
+		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
 			if (e < s_e)
 				goto next_entry;
 			if (ip6mr_fill_mroute(mrt, skb,
@@ -2589,7 +2566,7 @@ next_entry:
 		s_e = 0;
 
 		spin_lock_bh(&mfc_unres_lock);
-		list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) {
+		list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
 			if (e < s_e)
 				goto next_entry2;
 			if (ip6mr_fill_mroute(mrt, skb,
-- 
cgit v1.2.3


From 3a053b1a30dcb4e39569bcce2f4357509260db75 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 28 Feb 2018 15:59:15 +0200
Subject: net: Fix spelling mistake "greater then" -> "greater than"

Fix trivial spelling mistake "greater then" -> "greater than".

Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 2 +-
 net/core/dev.c            | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e2ab13687fb9..d4907b584b38 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -540,7 +540,7 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb)
 	return false;
 }
 
-/* Reset all TX qdiscs greater then index of a device.  */
+/* Reset all TX qdiscs greater than index of a device.  */
 static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
 {
 	struct Qdisc *qdisc;
diff --git a/net/core/dev.c b/net/core/dev.c
index 5bdcc5a161fe..40fb3aed5df2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2378,7 +2378,7 @@ EXPORT_SYMBOL(netdev_set_num_tc);
 
 /*
  * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
- * greater then real_num_tx_queues stale skbs on the qdisc must be flushed.
+ * greater than real_num_tx_queues stale skbs on the qdisc must be flushed.
  */
 int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 {
-- 
cgit v1.2.3


From 5f6f845b608a3fa13e5da0584eea5803710cf708 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Thu, 1 Mar 2018 17:55:37 -0800
Subject: fib_rules: FRA_GENERIC_POLICY updates for ip proto, sport and dport
 attrs

Fixes: bfff4862653b ("net: fib_rules: support for match on ip_proto, sport and dport")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fib_rules.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 6dd0a00653ae..1c9e17c11953 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -112,7 +112,11 @@ struct fib_rule_notifier_info {
 	[FRA_GOTO]	= { .type = NLA_U32 }, \
 	[FRA_L3MDEV]	= { .type = NLA_U8 }, \
 	[FRA_UID_RANGE]	= { .len = sizeof(struct fib_rule_uid_range) }, \
-	[FRA_PROTOCOL]  = { .type = NLA_U8 }
+	[FRA_PROTOCOL]  = { .type = NLA_U8 }, \
+	[FRA_IP_PROTO]  = { .type = NLA_U8 }, \
+	[FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, \
+	[FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }
+
 
 static inline void fib_rule_get(struct fib_rule *rule)
 {
-- 
cgit v1.2.3


From 43bf2e6d69dd6c2cea7a28763893a3dff34b7873 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 1 Mar 2018 18:29:28 -0500
Subject: net/mac89x0: Convert to platform_driver

Apparently these Dayna cards don't have a pseudoslot declaration ROM
which means they can't be probed like NuBus cards.

Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/m68k/mac/config.c                |  4 +++
 drivers/net/Space.c                   |  3 --
 drivers/net/ethernet/cirrus/mac89x0.c | 68 +++++++++++++++--------------------
 include/net/Space.h                   |  1 -
 4 files changed, 33 insertions(+), 43 deletions(-)

(limited to 'include/net')

diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index d3d435248a24..c73eb8209555 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -1088,6 +1088,10 @@ int __init mac_platform_init(void)
 	    macintosh_config->expansion_type == MAC_EXP_PDS_COMM)
 		platform_device_register_simple("macsonic", -1, NULL, 0);
 
+	if (macintosh_config->expansion_type == MAC_EXP_PDS ||
+	    macintosh_config->expansion_type == MAC_EXP_PDS_COMM)
+		platform_device_register_simple("mac89x0", -1, NULL, 0);
+
 	if (macintosh_config->ether_type == MAC_ETHER_MACE)
 		platform_device_register_simple("macmace", -1, NULL, 0);
 
diff --git a/drivers/net/Space.c b/drivers/net/Space.c
index 64333ec999ac..3afda6561434 100644
--- a/drivers/net/Space.c
+++ b/drivers/net/Space.c
@@ -113,9 +113,6 @@ static struct devprobe2 m68k_probes[] __initdata = {
 #endif
 #ifdef CONFIG_MVME147_NET	/* MVME147 internal Ethernet */
 	{mvme147lance_probe, 0},
-#endif
-#ifdef CONFIG_MAC89x0
-	{mac89x0_probe, 0},
 #endif
 	{NULL, 0},
 };
diff --git a/drivers/net/ethernet/cirrus/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c
index 4fe0ae93ab36..911139abbe20 100644
--- a/drivers/net/ethernet/cirrus/mac89x0.c
+++ b/drivers/net/ethernet/cirrus/mac89x0.c
@@ -93,6 +93,7 @@ static const char version[] =
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/netdevice.h>
+#include <linux/platform_device.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 #include <linux/delay.h>
@@ -105,6 +106,10 @@ static const char version[] =
 
 #include "cs89x0.h"
 
+static int debug;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "CS89[02]0 debug level (0-5)");
+
 static unsigned int net_debug = NET_DEBUG;
 
 /* Information that need to be kept for each board. */
@@ -167,10 +172,9 @@ static const struct net_device_ops mac89x0_netdev_ops = {
 
 /* Probe for the CS8900 card in slot E.  We won't bother looking
    anywhere else until we have a really good reason to do so. */
-struct net_device * __init mac89x0_probe(int unit)
+static int mac89x0_device_probe(struct platform_device *pdev)
 {
 	struct net_device *dev;
-	static int once_is_enough;
 	struct net_local *lp;
 	static unsigned version_printed;
 	int i, slot;
@@ -180,21 +184,11 @@ struct net_device * __init mac89x0_probe(int unit)
 	int err = -ENODEV;
 	struct nubus_rsrc *fres;
 
-	if (!MACH_IS_MAC)
-		return ERR_PTR(-ENODEV);
+	net_debug = debug;
 
 	dev = alloc_etherdev(sizeof(struct net_local));
 	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	if (unit >= 0) {
-		sprintf(dev->name, "eth%d", unit);
-		netdev_boot_setup_check(dev);
-	}
-
-	if (once_is_enough)
-		goto out;
-	once_is_enough = 1;
+		return -ENOMEM;
 
 	/* We might have to parameterize this later */
 	slot = 0xE;
@@ -221,6 +215,8 @@ struct net_device * __init mac89x0_probe(int unit)
 	if (sig != swab16(CHIP_EISA_ID_SIG))
 		goto out;
 
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
 	/* Initialize the net_device structure. */
 	lp = netdev_priv(dev);
 
@@ -280,12 +276,14 @@ struct net_device * __init mac89x0_probe(int unit)
 	err = register_netdev(dev);
 	if (err)
 		goto out1;
-	return NULL;
+
+	platform_set_drvdata(pdev, dev);
+	return 0;
 out1:
 	nubus_writew(0, dev->base_addr + ADD_PORT);
 out:
 	free_netdev(dev);
-	return ERR_PTR(err);
+	return err;
 }
 
 /* Open/initialize the board.  This is called (in the current kernel)
@@ -571,32 +569,24 @@ static int set_mac_address(struct net_device *dev, void *addr)
 	return 0;
 }
 
-#ifdef MODULE
-
-static struct net_device *dev_cs89x0;
-static int debug;
-
-module_param(debug, int, 0);
-MODULE_PARM_DESC(debug, "CS89[02]0 debug level (0-5)");
 MODULE_LICENSE("GPL");
 
-int __init
-init_module(void)
+static int mac89x0_device_remove(struct platform_device *pdev)
 {
-	net_debug = debug;
-        dev_cs89x0 = mac89x0_probe(-1);
-	if (IS_ERR(dev_cs89x0)) {
-                printk(KERN_WARNING "mac89x0.c: No card found\n");
-		return PTR_ERR(dev_cs89x0);
-	}
+	struct net_device *dev = platform_get_drvdata(pdev);
+
+	unregister_netdev(dev);
+	nubus_writew(0, dev->base_addr + ADD_PORT);
+	free_netdev(dev);
 	return 0;
 }
 
-void
-cleanup_module(void)
-{
-	unregister_netdev(dev_cs89x0);
-	nubus_writew(0, dev_cs89x0->base_addr + ADD_PORT);
-	free_netdev(dev_cs89x0);
-}
-#endif /* MODULE */
+static struct platform_driver mac89x0_platform_driver = {
+	.probe = mac89x0_device_probe,
+	.remove = mac89x0_device_remove,
+	.driver = {
+		.name = "mac89x0",
+	},
+};
+
+module_platform_driver(mac89x0_platform_driver);
diff --git a/include/net/Space.h b/include/net/Space.h
index 336da258885a..9cce0d80d37a 100644
--- a/include/net/Space.h
+++ b/include/net/Space.h
@@ -20,7 +20,6 @@ struct net_device *cs89x0_probe(int unit);
 struct net_device *mvme147lance_probe(int unit);
 struct net_device *tc515_probe(int unit);
 struct net_device *lance_probe(int unit);
-struct net_device *mac89x0_probe(int unit);
 struct net_device *cops_probe(int unit);
 struct net_device *ltpc_probe(void);
 
-- 
cgit v1.2.3


From dcb8c9b4373a583451b1b8a3e916d33de273633d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 28 Feb 2018 14:40:46 -0800
Subject: tcp_bbr: better deal with suboptimal GSO (II)

This is second part of dealing with suboptimal device gso parameters.
In first patch (350c9f484bde "tcp_bbr: better deal with suboptimal GSO")
we dealt with devices having low gso_max_segs

Some devices lower gso_max_size from 64KB to 16 KB (r8152 is an example)

In order to probe an optimal cwnd, we want BBR being not sensitive
to whatever GSO constraint a device can have.

This patch removes tso_segs_goal() CC callback in favor of
min_tso_segs() for CC wanting to override sysctl_tcp_min_tso_segs

Next patch will remove bbr->tso_segs_goal since it does not have
to be persistent.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  6 ++----
 net/ipv4/tcp_bbr.c    | 23 +++++++++++++----------
 net/ipv4/tcp_output.c | 15 ++++++++-------
 3 files changed, 23 insertions(+), 21 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 92b06c6e7732..9c9b3768b350 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -511,8 +511,6 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss);
 #endif
 /* tcp_output.c */
 
-u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
-		     int min_tso_segs);
 void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
 			       int nonagle);
 int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
@@ -981,8 +979,8 @@ struct tcp_congestion_ops {
 	u32  (*undo_cwnd)(struct sock *sk);
 	/* hook for packet ack accounting (optional) */
 	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
-	/* suggest number of segments for each skb to transmit (optional) */
-	u32 (*tso_segs_goal)(struct sock *sk);
+	/* override sysctl_tcp_min_tso_segs */
+	u32 (*min_tso_segs)(struct sock *sk);
 	/* returns the multiplier used in tcp_sndbuf_expand (optional) */
 	u32 (*sndbuf_expand)(struct sock *sk);
 	/* call when packets are delivered to update cwnd and pacing rate,
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index a471f696e13c..afc0567b8a98 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -261,23 +261,26 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 		sk->sk_pacing_rate = rate;
 }
 
-/* Return count of segments we want in the skbs we send, or 0 for default. */
-static u32 bbr_tso_segs_goal(struct sock *sk)
+/* override sysctl_tcp_min_tso_segs */
+static u32 bbr_min_tso_segs(struct sock *sk)
 {
-	struct bbr *bbr = inet_csk_ca(sk);
-
-	return bbr->tso_segs_goal;
+	return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2;
 }
 
 static void bbr_set_tso_segs_goal(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u32 min_segs;
+	u32 segs, bytes;
+
+	/* Sort of tcp_tso_autosize() but ignoring
+	 * driver provided sk_gso_max_size.
+	 */
+	bytes = min_t(u32, sk->sk_pacing_rate >> sk->sk_pacing_shift,
+		      GSO_MAX_SIZE - 1 - MAX_TCP_HEADER);
+	segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
 
-	min_segs = sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2;
-	bbr->tso_segs_goal = min(tcp_tso_autosize(sk, tp->mss_cache, min_segs),
-				 0x7FU);
+	bbr->tso_segs_goal = min(segs, 0x7FU);
 }
 
 /* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */
@@ -936,7 +939,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = {
 	.undo_cwnd	= bbr_undo_cwnd,
 	.cwnd_event	= bbr_cwnd_event,
 	.ssthresh	= bbr_ssthresh,
-	.tso_segs_goal	= bbr_tso_segs_goal,
+	.min_tso_segs	= bbr_min_tso_segs,
 	.get_info	= bbr_get_info,
 	.set_state	= bbr_set_state,
 };
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 49d043de3476..383cac0ff0ec 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1703,8 +1703,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
 /* Return how many segs we'd like on a TSO packet,
  * to send one TSO packet per ms
  */
-u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
-		     int min_tso_segs)
+static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
+			    int min_tso_segs)
 {
 	u32 bytes, segs;
 
@@ -1720,7 +1720,6 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 
 	return segs;
 }
-EXPORT_SYMBOL(tcp_tso_autosize);
 
 /* Return the number of segments we want in the skb we are transmitting.
  * See if congestion control module wants to decide; otherwise, autosize.
@@ -1728,11 +1727,13 @@ EXPORT_SYMBOL(tcp_tso_autosize);
 static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 {
 	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
-	u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
+	u32 min_tso, tso_segs;
 
-	if (!tso_segs)
-		tso_segs = tcp_tso_autosize(sk, mss_now,
-				sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+	min_tso = ca_ops->min_tso_segs ?
+			ca_ops->min_tso_segs(sk) :
+			sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+
+	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
 	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
 }
 
-- 
cgit v1.2.3


From 7efc0b6b666d757e07417f59397e7f5f340e74e0 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 2 Mar 2018 08:32:12 -0800
Subject: net/ipv4: Pass net to fib_multipath_hash instead of fib_info

fib_multipath_hash only needs net struct to check a sysctl. Make it
clear by passing net instead of fib_info. In the end this allows
alignment between the ipv4 and ipv6 versions.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 2 +-
 net/ipv4/fib_semantics.c | 2 +-
 net/ipv4/route.c         | 5 ++---
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 8812582a94d5..7c7522e8585b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -395,7 +395,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local);
 int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 		       const struct sk_buff *skb, struct flow_keys *flkeys);
 #endif
 void fib_select_multipath(struct fib_result *res, int hash);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 181b0d8d589c..e7c602c600ac 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1770,7 +1770,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, fl4, skb, NULL);
+		int h = fib_multipath_hash(net, fl4, skb, NULL);
 
 		fib_select_multipath(res, h);
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3bb686dac273..1689c569bbc3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1782,10 +1782,9 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb,
 }
 
 /* if skb is set it will be used and fl4 can be NULL */
-int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
-	struct net *net = fi->fib_net;
 	struct flow_keys hash_keys;
 	u32 mhash;
 
@@ -1852,7 +1851,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, NULL, skb, hkeys);
+		int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);
 
 		fib_select_multipath(res, h);
 	}
-- 
cgit v1.2.3


From 3192dac64c73d8c0eb4274a3da23d829fb5177af Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 2 Mar 2018 08:32:16 -0800
Subject: net: Rename NETEVENT_MULTIPATH_HASH_UPDATE

Rename NETEVENT_MULTIPATH_HASH_UPDATE to
NETEVENT_IPV4_MPATH_HASH_UPDATE to denote it relates to a change
in the IPv4 hash policy.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 include/net/netevent.h                                | 2 +-
 net/ipv4/sysctl_net_ipv4.c                            | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 69f16c605b9d..93d48c1b2bf8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2430,7 +2430,7 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 		mlxsw_core_schedule_work(&net_work->work);
 		mlxsw_sp_port_dev_put(mlxsw_sp_port);
 		break;
-	case NETEVENT_MULTIPATH_HASH_UPDATE:
+	case NETEVENT_IPV4_MPATH_HASH_UPDATE:
 		net = ptr;
 
 		if (!net_eq(net, &init_net))
diff --git a/include/net/netevent.h b/include/net/netevent.h
index 40e7bab68490..baee605a94ab 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -26,7 +26,7 @@ enum netevent_notif_type {
 	NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
 	NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
-	NETEVENT_MULTIPATH_HASH_UPDATE, /* arg is struct net ptr */
+	NETEVENT_IPV4_MPATH_HASH_UPDATE, /* arg is struct net ptr */
 };
 
 int register_netevent_notifier(struct notifier_block *nb);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 89683d868b37..011de9a20ec6 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -400,7 +400,7 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (write && ret == 0)
-		call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net);
+		call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net);
 
 	return ret;
 }
-- 
cgit v1.2.3


From b75cc8f90f07342467b3bd51dbc0054f185032c9 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 2 Mar 2018 08:32:17 -0800
Subject: net/ipv6: Pass skb to route lookup

IPv6 does path selection for multipath routes deep in the lookup
functions. The next patch adds L4 hash option and needs the skb
for the forward path. To get the skb to the relevant FIB lookup
functions it needs to go through the fib rules layer, so add a
lookup_data argument to the fib_lookup_arg struct.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/cma.c      |  2 +-
 drivers/net/ipvlan/ipvlan_core.c   |  3 +-
 drivers/net/vrf.c                  |  7 ++--
 include/net/fib_rules.h            |  1 +
 include/net/ip6_fib.h              |  4 ++-
 include/net/ip6_route.h            | 11 +++---
 net/ipv6/anycast.c                 |  2 +-
 net/ipv6/fib6_rules.c              |  8 +++--
 net/ipv6/icmp.c                    |  3 +-
 net/ipv6/ip6_fib.c                 |  3 +-
 net/ipv6/ip6_gre.c                 |  2 +-
 net/ipv6/ip6_tunnel.c              |  4 +--
 net/ipv6/ip6_vti.c                 |  2 +-
 net/ipv6/mcast.c                   |  4 +--
 net/ipv6/netfilter/ip6t_rpfilter.c |  2 +-
 net/ipv6/netfilter/nft_fib_ipv6.c  |  3 +-
 net/ipv6/route.c                   | 72 +++++++++++++++++++++++---------------
 net/ipv6/seg6_local.c              |  4 +--
 18 files changed, 83 insertions(+), 54 deletions(-)

(limited to 'include/net')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 3ae32d1ddd27..915bbd867b61 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1334,7 +1334,7 @@ static bool validate_ipv6_net_dev(struct net_device *net_dev,
 			   IPV6_ADDR_LINKLOCAL;
 	struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr,
 					 &src_addr->sin6_addr, net_dev->ifindex,
-					 strict);
+					 NULL, strict);
 	bool ret;
 
 	if (!rt)
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 17daebd19e65..1a8132eb2a3e 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -817,7 +817,8 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb,
 		};
 
 		skb_dst_drop(skb);
-		dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, flags);
+		dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6,
+					     skb, flags);
 		skb_dst_set(skb, dst);
 		break;
 	}
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index e459e601c57f..c6be49d3a9eb 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -941,6 +941,7 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
 					     const struct net_device *dev,
 					     struct flowi6 *fl6,
 					     int ifindex,
+					     const struct sk_buff *skb,
 					     int flags)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
@@ -959,7 +960,7 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
 	if (!table)
 		return NULL;
 
-	return ip6_pol_route(net, table, ifindex, fl6, flags);
+	return ip6_pol_route(net, table, ifindex, fl6, skb, flags);
 }
 
 static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
@@ -977,7 +978,7 @@ static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
 	struct net *net = dev_net(vrf_dev);
 	struct rt6_info *rt6;
 
-	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex,
+	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb,
 				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
 	if (unlikely(!rt6))
 		return;
@@ -1110,7 +1111,7 @@ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev,
 	if (!ipv6_addr_any(&fl6->saddr))
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 
-	rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, flags);
+	rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags);
 	if (rt)
 		dst = &rt->dst;
 
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 1c9e17c11953..e5cfcfc7dd93 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -47,6 +47,7 @@ struct fib_rule {
 
 struct fib_lookup_arg {
 	void			*lookup_ptr;
+	const void		*lookup_data;
 	void			*result;
 	struct fib_rule		*rule;
 	u32			table;
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 8d906a35b534..5e86fd9dc857 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -350,7 +350,8 @@ struct fib6_table {
 
 typedef struct rt6_info *(*pol_lookup_t)(struct net *,
 					 struct fib6_table *,
-					 struct flowi6 *, int);
+					 struct flowi6 *,
+					 const struct sk_buff *, int);
 
 struct fib6_entry_notifier_info {
 	struct fib_notifier_info info; /* must be first */
@@ -364,6 +365,7 @@ struct fib6_entry_notifier_info {
 struct fib6_table *fib6_get_table(struct net *net, u32 id);
 struct fib6_table *fib6_new_table(struct net *net, u32 id);
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup);
 
 struct fib6_node *fib6_lookup(struct fib6_node *root,
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index da2bde5fda8f..9594f9317952 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -75,7 +75,8 @@ static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt)
 void ip6_route_input(struct sk_buff *skb);
 struct dst_entry *ip6_route_input_lookup(struct net *net,
 					 struct net_device *dev,
-					 struct flowi6 *fl6, int flags);
+					 struct flowi6 *fl6,
+					 const struct sk_buff *skb, int flags);
 
 struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 					 struct flowi6 *fl6, int flags);
@@ -88,9 +89,10 @@ static inline struct dst_entry *ip6_route_output(struct net *net,
 }
 
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
-				   int flags);
+				   const struct sk_buff *skb, int flags);
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
-			       int ifindex, struct flowi6 *fl6, int flags);
+			       int ifindex, struct flowi6 *fl6,
+			       const struct sk_buff *skb, int flags);
 
 void ip6_route_init_special_entries(void);
 int ip6_route_init(void);
@@ -126,7 +128,8 @@ static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
 }
 
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
-			    const struct in6_addr *saddr, int oif, int flags);
+			    const struct in6_addr *saddr, int oif,
+			    const struct sk_buff *skb, int flags);
 u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
 		       struct flow_keys *hkeys);
 
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index d7d0abc7fd0e..c61718dba2e6 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -78,7 +78,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 
-		rt = rt6_lookup(net, addr, NULL, 0, 0);
+		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
 		if (rt) {
 			dev = rt->dst.dev;
 			ip6_rt_put(rt);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 04e5f523e50f..00ef9467f3c0 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -61,11 +61,13 @@ unsigned int fib6_rules_seq_read(struct net *net)
 }
 
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup)
 {
 	if (net->ipv6.fib6_has_custom_rules) {
 		struct fib_lookup_arg arg = {
 			.lookup_ptr = lookup,
+			.lookup_data = skb,
 			.flags = FIB_LOOKUP_NOREF,
 		};
 
@@ -80,11 +82,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	} else {
 		struct rt6_info *rt;
 
-		rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, flags);
+		rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, skb, flags);
 		if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN)
 			return &rt->dst;
 		ip6_rt_put(rt);
-		rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
+		rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
 		if (rt->dst.error != -EAGAIN)
 			return &rt->dst;
 		ip6_rt_put(rt);
@@ -130,7 +132,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 		goto out;
 	}
 
-	rt = lookup(net, table, flp6, flags);
+	rt = lookup(net, table, flp6, arg->lookup_data, flags);
 	if (rt != net->ipv6.ip6_null_entry) {
 		struct fib6_rule *r = (struct fib6_rule *)rule;
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index b0778d323b6e..a5d929223820 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -629,7 +629,8 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
 	skb_pull(skb2, nhs);
 	skb_reset_network_header(skb2);
 
-	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0,
+			skb, 0);
 
 	if (rt && rt->dst.dev)
 		skb2->dev = rt->dst.dev;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cab95cf3b39f..2f995e9e3050 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -299,11 +299,12 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id)
 }
 
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup)
 {
 	struct rt6_info *rt;
 
-	rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
+	rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
 	if (rt->dst.error == -EAGAIN) {
 		ip6_rt_put(rt);
 		rt = net->ipv6.ip6_null_entry;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4f150a394387..83c7766c8c75 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1053,7 +1053,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 
 		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
-						 p->link, strict);
+						 p->link, NULL, strict);
 
 		if (!rt)
 			return;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 869e2e6750f7..1124f310df5a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -679,7 +679,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 		/* Try to guess incoming interface */
 		rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr,
-				NULL, 0, 0);
+				NULL, 0, skb2, 0);
 
 		if (rt && rt->dst.dev)
 			skb2->dev = rt->dst.dev;
@@ -1444,7 +1444,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 
 		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
-						 p->link, strict);
+						 p->link, NULL, strict);
 
 		if (!rt)
 			return;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index c617ea17faa8..a482b854eeea 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -645,7 +645,7 @@ static void vti6_link_config(struct ip6_tnl *t)
 			      (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
 		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
-						 p->link, strict);
+						 p->link, NULL, strict);
 
 		if (rt)
 			tdev = rt->dst.dev;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index d9bb933dd5c4..d1a0cefac273 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -165,7 +165,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	if (ifindex == 0) {
 		struct rt6_info *rt;
-		rt = rt6_lookup(net, addr, NULL, 0, 0);
+		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
 		if (rt) {
 			dev = rt->dst.dev;
 			ip6_rt_put(rt);
@@ -254,7 +254,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
 	struct inet6_dev *idev = NULL;
 
 	if (ifindex == 0) {
-		struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, 0);
+		struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, NULL, 0);
 
 		if (rt) {
 			dev = rt->dst.dev;
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index 94deb69bbbda..910a27318f58 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -53,7 +53,7 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 		lookup_flags |= RT6_LOOKUP_F_IFACE;
 	}
 
-	rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags);
+	rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags);
 	if (rt->dst.error)
 		goto out;
 
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index cc5174c7254c..3230b3d7b11b 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -181,7 +181,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	*dest = 0;
  again:
-	rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags);
+	rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb,
+				      lookup_flags);
 	if (rt->dst.error)
 		goto put_rt_err;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5c89af2c54f4..d2b8368663cb 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -452,6 +452,7 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 
 static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 					     struct flowi6 *fl6, int oif,
+					     const struct sk_buff *skb,
 					     int strict)
 {
 	struct rt6_info *sibling, *next_sibling;
@@ -460,7 +461,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
 	if (!fl6->mp_hash)
-		fl6->mp_hash = rt6_multipath_hash(fl6, NULL, NULL);
+		fl6->mp_hash = rt6_multipath_hash(fl6, skb, NULL);
 
 	if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound))
 		return match;
@@ -914,7 +915,9 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
 
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     struct fib6_table *table,
-					     struct flowi6 *fl6, int flags)
+					     struct flowi6 *fl6,
+					     const struct sk_buff *skb,
+					     int flags)
 {
 	struct rt6_info *rt, *rt_cache;
 	struct fib6_node *fn;
@@ -929,8 +932,8 @@ restart:
 		rt = rt6_device_match(net, rt, &fl6->saddr,
 				      fl6->flowi6_oif, flags);
 		if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
-			rt = rt6_multipath_select(rt, fl6,
-						  fl6->flowi6_oif, flags);
+			rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif,
+						  skb, flags);
 	}
 	if (rt == net->ipv6.ip6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
@@ -954,14 +957,15 @@ restart:
 }
 
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
-				    int flags)
+				   const struct sk_buff *skb, int flags)
 {
-	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup);
+	return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup);
 }
 EXPORT_SYMBOL_GPL(ip6_route_lookup);
 
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
-			    const struct in6_addr *saddr, int oif, int strict)
+			    const struct in6_addr *saddr, int oif,
+			    const struct sk_buff *skb, int strict)
 {
 	struct flowi6 fl6 = {
 		.flowi6_oif = oif,
@@ -975,7 +979,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 	}
 
-	dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup);
+	dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup);
 	if (dst->error == 0)
 		return (struct rt6_info *) dst;
 
@@ -1647,7 +1651,8 @@ void rt6_age_exceptions(struct rt6_info *rt,
 }
 
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
-			       int oif, struct flowi6 *fl6, int flags)
+			       int oif, struct flowi6 *fl6,
+			       const struct sk_buff *skb, int flags)
 {
 	struct fib6_node *fn, *saved_fn;
 	struct rt6_info *rt, *rt_cache;
@@ -1669,7 +1674,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 redo_rt6_select:
 	rt = rt6_select(net, fn, oif, strict);
 	if (rt->rt6i_nsiblings)
-		rt = rt6_multipath_select(rt, fl6, oif, strict);
+		rt = rt6_multipath_select(rt, fl6, oif, skb, strict);
 	if (rt == net->ipv6.ip6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
@@ -1768,20 +1773,25 @@ uncached_rt_out:
 }
 EXPORT_SYMBOL_GPL(ip6_pol_route);
 
-static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
-					    struct flowi6 *fl6, int flags)
+static struct rt6_info *ip6_pol_route_input(struct net *net,
+					    struct fib6_table *table,
+					    struct flowi6 *fl6,
+					    const struct sk_buff *skb,
+					    int flags)
 {
-	return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags);
+	return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags);
 }
 
 struct dst_entry *ip6_route_input_lookup(struct net *net,
 					 struct net_device *dev,
-					 struct flowi6 *fl6, int flags)
+					 struct flowi6 *fl6,
+					 const struct sk_buff *skb,
+					 int flags)
 {
 	if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG)
 		flags |= RT6_LOOKUP_F_IFACE;
 
-	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input);
+	return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input);
 }
 EXPORT_SYMBOL_GPL(ip6_route_input_lookup);
 
@@ -1876,13 +1886,17 @@ void ip6_route_input(struct sk_buff *skb)
 	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
 		fl6.mp_hash = rt6_multipath_hash(&fl6, skb, flkeys);
 	skb_dst_drop(skb);
-	skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
+	skb_dst_set(skb,
+		    ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags));
 }
 
-static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
-					     struct flowi6 *fl6, int flags)
+static struct rt6_info *ip6_pol_route_output(struct net *net,
+					     struct fib6_table *table,
+					     struct flowi6 *fl6,
+					     const struct sk_buff *skb,
+					     int flags)
 {
-	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
+	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags);
 }
 
 struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
@@ -1910,7 +1924,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 	else if (sk)
 		flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
 
-	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
+	return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output);
 }
 EXPORT_SYMBOL_GPL(ip6_route_output_flags);
 
@@ -2159,6 +2173,7 @@ struct ip6rd_flowi {
 static struct rt6_info *__ip6_route_redirect(struct net *net,
 					     struct fib6_table *table,
 					     struct flowi6 *fl6,
+					     const struct sk_buff *skb,
 					     int flags)
 {
 	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
@@ -2232,8 +2247,9 @@ out:
 };
 
 static struct dst_entry *ip6_route_redirect(struct net *net,
-					const struct flowi6 *fl6,
-					const struct in6_addr *gateway)
+					    const struct flowi6 *fl6,
+					    const struct sk_buff *skb,
+					    const struct in6_addr *gateway)
 {
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
 	struct ip6rd_flowi rdfl;
@@ -2241,7 +2257,7 @@ static struct dst_entry *ip6_route_redirect(struct net *net,
 	rdfl.fl6 = *fl6;
 	rdfl.gateway = *gateway;
 
-	return fib6_rule_lookup(net, &rdfl.fl6,
+	return fib6_rule_lookup(net, &rdfl.fl6, skb,
 				flags, __ip6_route_redirect);
 }
 
@@ -2261,7 +2277,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
 	fl6.flowlabel = ip6_flowinfo(iph);
 	fl6.flowi6_uid = uid;
 
-	dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr);
+	dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr);
 	rt6_do_redirect(dst, NULL, skb);
 	dst_release(dst);
 }
@@ -2283,7 +2299,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
 	fl6.saddr = iph->daddr;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
 
-	dst = ip6_route_redirect(net, &fl6, &iph->saddr);
+	dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr);
 	rt6_do_redirect(dst, NULL, skb);
 	dst_release(dst);
 }
@@ -2485,7 +2501,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 
 	flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE;
-	rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, flags);
+	rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, NULL, flags);
 
 	/* if table lookup failed, fall back to full lookup */
 	if (rt == net->ipv6.ip6_null_entry) {
@@ -2548,7 +2564,7 @@ static int ip6_route_check_nh(struct net *net,
 	}
 
 	if (!grt)
-		grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1);
+		grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, NULL, 1);
 
 	if (!grt)
 		goto out;
@@ -4613,7 +4629,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		if (!ipv6_addr_any(&fl6.saddr))
 			flags |= RT6_LOOKUP_F_HAS_SADDR;
 
-		dst = ip6_route_input_lookup(net, dev, &fl6, flags);
+		dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags);
 
 		rcu_read_unlock();
 	} else {
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index ba3767ef5e93..45722327375a 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -161,7 +161,7 @@ static void lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 		fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
 
 	if (!tbl_id) {
-		dst = ip6_route_input_lookup(net, skb->dev, &fl6, flags);
+		dst = ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags);
 	} else {
 		struct fib6_table *table;
 
@@ -169,7 +169,7 @@ static void lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 		if (!table)
 			goto out;
 
-		rt = ip6_pol_route(net, table, 0, &fl6, flags);
+		rt = ip6_pol_route(net, table, 0, &fl6, skb, flags);
 		dst = &rt->dst;
 	}
 
-- 
cgit v1.2.3


From b4bac172e90ce4a93df8adf44eb70d91b9d611eb Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 2 Mar 2018 08:32:18 -0800
Subject: net/ipv6: Add support for path selection using hash of 5-tuple

Some operators prefer IPv6 path selection to use a standard 5-tuple
hash rather than just an L3 hash with the flow the label. To that end
add support to IPv6 for multipath hash policy similar to bf4e0a3db97eb
("net: ipv4: add support for ECMP hash policy choice"). The default
is still L3 which covers source and destination addresses along with
flow label and IPv6 protocol.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  7 ++++
 include/net/ip6_route.h                |  4 +-
 include/net/netevent.h                 |  1 +
 include/net/netns/ipv6.h               |  1 +
 net/ipv6/icmp.c                        |  2 +-
 net/ipv6/route.c                       | 68 ++++++++++++++++++++++++++--------
 net/ipv6/sysctl_net_ipv6.c             | 27 ++++++++++++++
 7 files changed, 91 insertions(+), 19 deletions(-)

(limited to 'include/net')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a553d4e4a0fb..783675a730e5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1363,6 +1363,13 @@ flowlabel_reflect - BOOLEAN
 	FALSE: disabled
 	Default: FALSE
 
+fib_multipath_hash_policy - INTEGER
+	Controls which hash policy to use for multipath routes.
+	Default: 0 (Layer 3)
+	Possible values:
+	0 - Layer 3 (source and destination addresses plus flow label)
+	1 - Layer 4 (standard 5-tuple)
+
 anycast_src_echo_reply - BOOLEAN
 	Controls the use of anycast addresses as source addresses for ICMPv6
 	echo reply
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 9594f9317952..ce2abc0ff102 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -130,8 +130,8 @@ static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif,
 			    const struct sk_buff *skb, int flags);
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
-		       struct flow_keys *hkeys);
+u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
+		       const struct sk_buff *skb, struct flow_keys *hkeys);
 
 struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
 
diff --git a/include/net/netevent.h b/include/net/netevent.h
index baee605a94ab..d9918261701c 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -27,6 +27,7 @@ enum netevent_notif_type {
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
 	NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
 	NETEVENT_IPV4_MPATH_HASH_UPDATE, /* arg is struct net ptr */
+	NETEVENT_IPV6_MPATH_HASH_UPDATE, /* arg is struct net ptr */
 };
 
 int register_netevent_notifier(struct notifier_block *nb);
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index e286fda09fcf..5b51110435fc 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -28,6 +28,7 @@ struct netns_sysctl_ipv6 {
 	int ip6_rt_gc_elasticity;
 	int ip6_rt_mtu_expires;
 	int ip6_rt_min_advmss;
+	int multipath_hash_policy;
 	int flowlabel_consistency;
 	int auto_flowlabels;
 	int icmpv6_time;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index a5d929223820..6f84668be6ea 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -522,7 +522,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
-	fl6.mp_hash = rt6_multipath_hash(&fl6, skb, NULL);
+	fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d2b8368663cb..f0ae58424c45 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -450,7 +450,8 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
-static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
+static struct rt6_info *rt6_multipath_select(const struct net *net,
+					     struct rt6_info *match,
 					     struct flowi6 *fl6, int oif,
 					     const struct sk_buff *skb,
 					     int strict)
@@ -461,7 +462,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
 	if (!fl6->mp_hash)
-		fl6->mp_hash = rt6_multipath_hash(fl6, skb, NULL);
+		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
 	if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound))
 		return match;
@@ -932,7 +933,7 @@ restart:
 		rt = rt6_device_match(net, rt, &fl6->saddr,
 				      fl6->flowi6_oif, flags);
 		if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
-			rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif,
+			rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif,
 						  skb, flags);
 	}
 	if (rt == net->ipv6.ip6_null_entry) {
@@ -1674,7 +1675,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 redo_rt6_select:
 	rt = rt6_select(net, fn, oif, strict);
 	if (rt->rt6i_nsiblings)
-		rt = rt6_multipath_select(rt, fl6, oif, skb, strict);
+		rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict);
 	if (rt == net->ipv6.ip6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
@@ -1839,21 +1840,56 @@ out:
 }
 
 /* if skb is set it will be used and fl6 can be NULL */
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
-		       struct flow_keys *flkeys)
+u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
+		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
 	struct flow_keys hash_keys;
 	u32 mhash;
 
-	memset(&hash_keys, 0, sizeof(hash_keys));
-	hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
-	if (skb) {
-		ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
-	} else {
-		hash_keys.addrs.v6addrs.src = fl6->saddr;
-		hash_keys.addrs.v6addrs.dst = fl6->daddr;
-		hash_keys.tags.flow_label = (__force u32)fl6->flowlabel;
-		hash_keys.basic.ip_proto = fl6->flowi6_proto;
+	switch (net->ipv6.sysctl.multipath_hash_policy) {
+	case 0:
+		memset(&hash_keys, 0, sizeof(hash_keys));
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		if (skb) {
+			ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
+		} else {
+			hash_keys.addrs.v6addrs.src = fl6->saddr;
+			hash_keys.addrs.v6addrs.dst = fl6->daddr;
+			hash_keys.tags.flow_label = (__force u32)fl6->flowlabel;
+			hash_keys.basic.ip_proto = fl6->flowi6_proto;
+		}
+		break;
+	case 1:
+		if (skb) {
+			unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+			struct flow_keys keys;
+
+			/* short-circuit if we already have L4 hash present */
+			if (skb->l4_hash)
+				return skb_get_hash_raw(skb) >> 1;
+
+			memset(&hash_keys, 0, sizeof(hash_keys));
+
+                        if (!flkeys) {
+				skb_flow_dissect_flow_keys(skb, &keys, flag);
+				flkeys = &keys;
+			}
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+			hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src;
+			hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst;
+			hash_keys.ports.src = flkeys->ports.src;
+			hash_keys.ports.dst = flkeys->ports.dst;
+			hash_keys.basic.ip_proto = flkeys->basic.ip_proto;
+		} else {
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+			hash_keys.addrs.v6addrs.src = fl6->saddr;
+			hash_keys.addrs.v6addrs.dst = fl6->daddr;
+			hash_keys.ports.src = fl6->fl6_sport;
+			hash_keys.ports.dst = fl6->fl6_dport;
+			hash_keys.basic.ip_proto = fl6->flowi6_proto;
+		}
+		break;
 	}
 	mhash = flow_hash_from_keys(&hash_keys);
 
@@ -1884,7 +1920,7 @@ void ip6_route_input(struct sk_buff *skb)
 		flkeys = &_flkeys;
 
 	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
-		fl6.mp_hash = rt6_multipath_hash(&fl6, skb, flkeys);
+		fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys);
 	skb_dst_drop(skb);
 	skb_dst_set(skb,
 		    ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags));
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 262f791f1b9b..966c42af92f4 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -16,14 +16,31 @@
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 #include <net/inet_frag.h>
+#include <net/netevent.h>
 #ifdef CONFIG_NETLABEL
 #include <net/calipso.h>
 #endif
 
+static int zero;
 static int one = 1;
 static int auto_flowlabels_min;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
 
+static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
+					  void __user *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	struct net *net;
+	int ret;
+
+	net = container_of(table->data, struct net,
+			   ipv6.sysctl.multipath_hash_policy);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net);
+
+	return ret;
+}
 
 static struct ctl_table ipv6_table_template[] = {
 	{
@@ -126,6 +143,15 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "fib_multipath_hash_policy",
+		.data		= &init_net.ipv6.sysctl.multipath_hash_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler   = proc_rt6_multipath_hash_policy,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
@@ -190,6 +216,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
 	ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt;
 	ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len;
 	ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len;
+	ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy,
 
 	ipv6_route_table = ipv6_route_sysctl_init(net);
 	if (!ipv6_route_table)
-- 
cgit v1.2.3


From de7a0f871fabe74fff7481caf7d3efe03b58fe58 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 2 Mar 2018 08:32:20 -0800
Subject: net: Remove unused get_hash_from_flow functions

__get_hash_from_flowi6 is still used for flowlabels, but the IPv4
variant and the wrappers to both are not used. Remove them.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h        | 16 ----------------
 net/core/flow_dissector.c | 16 ----------------
 2 files changed, 32 deletions(-)

(limited to 'include/net')

diff --git a/include/net/flow.h b/include/net/flow.h
index 64e7ee9cb980..8ce21793094e 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -222,20 +222,4 @@ static inline unsigned int flow_key_size(u16 family)
 
 __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys);
 
-static inline __u32 get_hash_from_flowi6(const struct flowi6 *fl6)
-{
-	struct flow_keys keys;
-
-	return __get_hash_from_flowi6(fl6, &keys);
-}
-
-__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys);
-
-static inline __u32 get_hash_from_flowi4(const struct flowi4 *fl4)
-{
-	struct flow_keys keys;
-
-	return __get_hash_from_flowi4(fl4, &keys);
-}
-
 #endif
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 559db9ea8d86..d29f09bc5ff9 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1341,22 +1341,6 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys)
 }
 EXPORT_SYMBOL(__get_hash_from_flowi6);
 
-__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys)
-{
-	memset(keys, 0, sizeof(*keys));
-
-	keys->addrs.v4addrs.src = fl4->saddr;
-	keys->addrs.v4addrs.dst = fl4->daddr;
-	keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-	keys->ports.src = fl4->fl4_sport;
-	keys->ports.dst = fl4->fl4_dport;
-	keys->keyid.keyid = fl4->fl4_gre_key;
-	keys->basic.ip_proto = fl4->flowi4_proto;
-
-	return flow_hash_from_keys(keys);
-}
-EXPORT_SYMBOL(__get_hash_from_flowi4);
-
 static const struct flow_dissector_key flow_keys_dissector_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
-- 
cgit v1.2.3


From 88c060549a4c555d59965801d1e811b71614c2b7 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 1 Mar 2018 02:02:27 +0100
Subject: dsa: Pass the port to get_sset_count()

By passing the port, we allow different ports to have different
statistics. This is useful since some ports have SERDES interfaces
with their own statistic counters.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c       | 2 +-
 drivers/net/dsa/b53/b53_priv.h         | 2 +-
 drivers/net/dsa/dsa_loop.c             | 2 +-
 drivers/net/dsa/lan9303-core.c         | 2 +-
 drivers/net/dsa/microchip/ksz_common.c | 2 +-
 drivers/net/dsa/mt7530.c               | 2 +-
 drivers/net/dsa/mv88e6xxx/chip.c       | 2 +-
 drivers/net/dsa/qca8k.c                | 2 +-
 include/net/dsa.h                      | 2 +-
 net/dsa/master.c                       | 4 ++--
 net/dsa/slave.c                        | 2 +-
 11 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index db830a1141d9..cd16067265dd 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -852,7 +852,7 @@ void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
 }
 EXPORT_SYMBOL(b53_get_ethtool_stats);
 
-int b53_get_sset_count(struct dsa_switch *ds)
+int b53_get_sset_count(struct dsa_switch *ds, int port)
 {
 	struct b53_device *dev = ds->priv;
 
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index d954cf36ecd8..1187ebd79287 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -288,7 +288,7 @@ void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port);
 int b53_configure_vlan(struct dsa_switch *ds);
 void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data);
 void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
-int b53_get_sset_count(struct dsa_switch *ds);
+int b53_get_sset_count(struct dsa_switch *ds, int port);
 int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge);
 void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge);
 void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state);
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index 7aa84ee4e771..f77be9f85cb3 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -86,7 +86,7 @@ static int dsa_loop_setup(struct dsa_switch *ds)
 	return 0;
 }
 
-static int dsa_loop_get_sset_count(struct dsa_switch *ds)
+static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port)
 {
 	return __DSA_LOOP_CNT_MAX;
 }
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
index 6171c0853ff1..fefa454f3e56 100644
--- a/drivers/net/dsa/lan9303-core.c
+++ b/drivers/net/dsa/lan9303-core.c
@@ -1007,7 +1007,7 @@ static void lan9303_get_ethtool_stats(struct dsa_switch *ds, int port,
 	}
 }
 
-static int lan9303_get_sset_count(struct dsa_switch *ds)
+static int lan9303_get_sset_count(struct dsa_switch *ds, int port)
 {
 	return ARRAY_SIZE(lan9303_mib);
 }
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 663b0d5b982b..bcb3e6c734f2 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -439,7 +439,7 @@ static void ksz_disable_port(struct dsa_switch *ds, int port,
 	ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_MAC_LOOPBACK, true);
 }
 
-static int ksz_sset_count(struct dsa_switch *ds)
+static int ksz_sset_count(struct dsa_switch *ds, int port)
 {
 	return TOTAL_SWITCH_COUNTER_NUM;
 }
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 8a0bb000d056..511ca134f13f 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -604,7 +604,7 @@ mt7530_get_ethtool_stats(struct dsa_switch *ds, int port,
 }
 
 static int
-mt7530_get_sset_count(struct dsa_switch *ds)
+mt7530_get_sset_count(struct dsa_switch *ds, int port)
 {
 	return ARRAY_SIZE(mt7530_mib);
 }
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 24486f96dd39..8c9a30d1b06f 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -754,7 +754,7 @@ static int mv88e6320_stats_get_sset_count(struct mv88e6xxx_chip *chip)
 					      STATS_TYPE_BANK1);
 }
 
-static int mv88e6xxx_get_sset_count(struct dsa_switch *ds)
+static int mv88e6xxx_get_sset_count(struct dsa_switch *ds, int port)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 9df22ebee822..600d5ad1fbde 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -631,7 +631,7 @@ qca8k_get_ethtool_stats(struct dsa_switch *ds, int port,
 }
 
 static int
-qca8k_get_sset_count(struct dsa_switch *ds)
+qca8k_get_sset_count(struct dsa_switch *ds, int port)
 {
 	return ARRAY_SIZE(ar8327_mib);
 }
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 0ad17b63684d..60fb4ec8ba61 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -359,7 +359,7 @@ struct dsa_switch_ops {
 	void	(*get_strings)(struct dsa_switch *ds, int port, uint8_t *data);
 	void	(*get_ethtool_stats)(struct dsa_switch *ds,
 				     int port, uint64_t *data);
-	int	(*get_sset_count)(struct dsa_switch *ds);
+	int	(*get_sset_count)(struct dsa_switch *ds, int port);
 
 	/*
 	 * ethtool Wake-on-LAN
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 00589147f042..90e6df0351eb 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -42,7 +42,7 @@ static int dsa_master_get_sset_count(struct net_device *dev, int sset)
 		count += ops->get_sset_count(dev, sset);
 
 	if (sset == ETH_SS_STATS && ds->ops->get_sset_count)
-		count += ds->ops->get_sset_count(ds);
+		count += ds->ops->get_sset_count(ds, cpu_dp->index);
 
 	return count;
 }
@@ -76,7 +76,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset,
 		 * constructed earlier
 		 */
 		ds->ops->get_strings(ds, port, ndata);
-		count = ds->ops->get_sset_count(ds);
+		count = ds->ops->get_sset_count(ds, port);
 		for (i = 0; i < count; i++) {
 			memmove(ndata + (i * len + sizeof(pfx)),
 				ndata + i * len, len - sizeof(pfx));
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 3376dad6dcfd..18561af7a8f1 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -605,7 +605,7 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
 
 		count = 4;
 		if (ds->ops->get_sset_count)
-			count += ds->ops->get_sset_count(ds);
+			count += ds->ops->get_sset_count(ds, dp->index);
 
 		return count;
 	}
-- 
cgit v1.2.3


From 76b12974a3981db2a1ae60d62f55dd839d07ac85 Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Sun, 4 Mar 2018 03:29:51 +0100
Subject: net: core: dst_cache: Fix a typo in a comment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst_cache.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index 72fd5067c353..844906fbf8c9 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -71,7 +71,7 @@ struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache,
  *	dst_cache_reset - invalidate the cache contents
  *	@dst_cache: the cache
  *
- *	This do not free the cached dst to avoid races and contentions.
+ *	This does not free the cached dst to avoid races and contentions.
  *	the dst will be freed on later cache lookup.
  */
 static inline void dst_cache_reset(struct dst_cache *dst_cache)
-- 
cgit v1.2.3


From 4c1342d967cb556ea1c0f34271b125deeb25f0f8 Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Sun, 4 Mar 2018 03:29:52 +0100
Subject: net: core: dst_cache_set_ip6: Rename 'addr' parameter to 'saddr' for
 consistency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The other dst_cache_{get,set}_ip{4,6} functions, and the doc comment for
dst_cache_set_ip6 use 'saddr' for their source address parameter. Rename
the parameter to increase consistency.

This fixes the following kernel-doc warnings:

./include/net/dst_cache.h:58: warning: Function parameter or member 'addr' not described in 'dst_cache_set_ip6'
./include/net/dst_cache.h:58: warning: Excess function parameter 'saddr' description in 'dst_cache_set_ip6'

Fixes: 911362c70df5 ("net: add dst_cache support")
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst_cache.h | 2 +-
 net/core/dst_cache.c    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/net')

diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index 844906fbf8c9..67634675e919 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -54,7 +54,7 @@ void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst,
  *	local BH must be disabled.
  */
 void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
-		       const struct in6_addr *addr);
+		       const struct in6_addr *saddr);
 
 /**
  *	dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address
diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
index 554d36449231..64cef977484a 100644
--- a/net/core/dst_cache.c
+++ b/net/core/dst_cache.c
@@ -107,7 +107,7 @@ EXPORT_SYMBOL_GPL(dst_cache_set_ip4);
 
 #if IS_ENABLED(CONFIG_IPV6)
 void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
-		       const struct in6_addr *addr)
+		       const struct in6_addr *saddr)
 {
 	struct dst_cache_pcpu *idst;
 
@@ -117,7 +117,7 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
 	idst = this_cpu_ptr(dst_cache->cache);
 	dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst,
 				  rt6_get_cookie((struct rt6_info *)dst));
-	idst->in6_saddr = *addr;
+	idst->in6_saddr = *saddr;
 }
 EXPORT_SYMBOL_GPL(dst_cache_set_ip6);
 
-- 
cgit v1.2.3


From 8eb1a8590f5ca114fabf16ebb26a4bce0255ace9 Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Sun, 4 Mar 2018 03:29:53 +0100
Subject: net: core: dst: Add kernel-doc for 'net' parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes the following kernel-doc warning:

./include/net/dst.h:366: warning: Function parameter or member 'net' not described in 'skb_tunnel_rx'

Fixes: ea23192e8e57 ("tunnels: harmonize cleanup done on skb on rx path")
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/net')

diff --git a/include/net/dst.h b/include/net/dst.h
index c63d2c37f6e9..b3219cd8a5a1 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -356,6 +356,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
  *	skb_tunnel_rx - prepare skb for rx reinsert
  *	@skb: buffer
  *	@dev: tunnel device
+ *	@net: netns for packet i/o
  *
  *	After decapsulation, packet is going to re-enter (netif_rx()) our stack,
  *	so make some cleanups, and perform accounting.
-- 
cgit v1.2.3


From 433029ecc62788296cacca50ceb24db90c17a4a2 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 11 Feb 2018 23:28:18 +0900
Subject: netfilter: nf_conntrack_broadcast: remove useless parameter

parameter protoff in nf_conntrack_broadcast_help is not used anywhere.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_helper.h | 3 +--
 net/netfilter/nf_conntrack_broadcast.c      | 1 -
 net/netfilter/nf_conntrack_netbios_ns.c     | 5 +++--
 net/netfilter/nf_conntrack_snmp.c           | 5 +++--
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index fc39bbaf107c..32c2a94a219d 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -132,8 +132,7 @@ void nf_conntrack_helper_pernet_fini(struct net *net);
 int nf_conntrack_helper_init(void);
 void nf_conntrack_helper_fini(void);
 
-int nf_conntrack_broadcast_help(struct sk_buff *skb, unsigned int protoff,
-				struct nf_conn *ct,
+int nf_conntrack_broadcast_help(struct sk_buff *skb, struct nf_conn *ct,
 				enum ip_conntrack_info ctinfo,
 				unsigned int timeout);
 
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index ecc3ab784633..a1086bdec242 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -20,7 +20,6 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 
 int nf_conntrack_broadcast_help(struct sk_buff *skb,
-				unsigned int protoff,
 				struct nf_conn *ct,
 				enum ip_conntrack_info ctinfo,
 				unsigned int timeout)
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index 496ce173f0c1..a4a59dc7cf17 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -41,9 +41,10 @@ static struct nf_conntrack_expect_policy exp_policy = {
 };
 
 static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff,
-		   struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+			   struct nf_conn *ct,
+			   enum ip_conntrack_info ctinfo)
 {
-	return nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+	return nf_conntrack_broadcast_help(skb, ct, ctinfo, timeout);
 }
 
 static struct nf_conntrack_helper helper __read_mostly = {
diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c
index 87b95a2c270c..2d0f8e010821 100644
--- a/net/netfilter/nf_conntrack_snmp.c
+++ b/net/netfilter/nf_conntrack_snmp.c
@@ -36,11 +36,12 @@ int (*nf_nat_snmp_hook)(struct sk_buff *skb,
 EXPORT_SYMBOL_GPL(nf_nat_snmp_hook);
 
 static int snmp_conntrack_help(struct sk_buff *skb, unsigned int protoff,
-		struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+			       struct nf_conn *ct,
+			       enum ip_conntrack_info ctinfo)
 {
 	typeof(nf_nat_snmp_hook) nf_nat_snmp;
 
-	nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+	nf_conntrack_broadcast_help(skb, ct, ctinfo, timeout);
 
 	nf_nat_snmp = rcu_dereference(nf_nat_snmp_hook);
 	if (nf_nat_snmp && ct->status & IPS_NAT_MASK)
-- 
cgit v1.2.3


From 3427b2ab63faccafe774ea997fc2da7faf690c5a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 1 Mar 2018 18:58:38 -0800
Subject: netfilter: make xt_rateest hash table per net

As suggested by Eric, we need to make the xt_rateest
hash table and its lock per netns to reduce lock
contentions.

Cc: Florian Westphal <fw@strlen.de>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/xt_rateest.h |  4 +-
 net/netfilter/xt_RATEEST.c         | 91 +++++++++++++++++++++++++++-----------
 net/netfilter/xt_rateest.c         | 10 ++---
 3 files changed, 72 insertions(+), 33 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h
index b1db13772554..832ab69efda5 100644
--- a/include/net/netfilter/xt_rateest.h
+++ b/include/net/netfilter/xt_rateest.h
@@ -21,7 +21,7 @@ struct xt_rateest {
 	struct net_rate_estimator __rcu *rate_est;
 };
 
-struct xt_rateest *xt_rateest_lookup(const char *name);
-void xt_rateest_put(struct xt_rateest *est);
+struct xt_rateest *xt_rateest_lookup(struct net *net, const char *name);
+void xt_rateest_put(struct net *net, struct xt_rateest *est);
 
 #endif /* _XT_RATEEST_H */
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 141c295191f6..dec843cadf46 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -14,15 +14,21 @@
 #include <linux/slab.h>
 #include <net/gen_stats.h>
 #include <net/netlink.h>
+#include <net/netns/generic.h>
 
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_RATEEST.h>
 #include <net/netfilter/xt_rateest.h>
 
-static DEFINE_MUTEX(xt_rateest_mutex);
-
 #define RATEEST_HSIZE	16
-static struct hlist_head rateest_hash[RATEEST_HSIZE] __read_mostly;
+
+struct xt_rateest_net {
+	struct mutex hash_lock;
+	struct hlist_head hash[RATEEST_HSIZE];
+};
+
+static unsigned int xt_rateest_id;
+
 static unsigned int jhash_rnd __read_mostly;
 
 static unsigned int xt_rateest_hash(const char *name)
@@ -31,21 +37,23 @@ static unsigned int xt_rateest_hash(const char *name)
 	       (RATEEST_HSIZE - 1);
 }
 
-static void xt_rateest_hash_insert(struct xt_rateest *est)
+static void xt_rateest_hash_insert(struct xt_rateest_net *xn,
+				   struct xt_rateest *est)
 {
 	unsigned int h;
 
 	h = xt_rateest_hash(est->name);
-	hlist_add_head(&est->list, &rateest_hash[h]);
+	hlist_add_head(&est->list, &xn->hash[h]);
 }
 
-static struct xt_rateest *__xt_rateest_lookup(const char *name)
+static struct xt_rateest *__xt_rateest_lookup(struct xt_rateest_net *xn,
+					      const char *name)
 {
 	struct xt_rateest *est;
 	unsigned int h;
 
 	h = xt_rateest_hash(name);
-	hlist_for_each_entry(est, &rateest_hash[h], list) {
+	hlist_for_each_entry(est, &xn->hash[h], list) {
 		if (strcmp(est->name, name) == 0) {
 			est->refcnt++;
 			return est;
@@ -55,20 +63,23 @@ static struct xt_rateest *__xt_rateest_lookup(const char *name)
 	return NULL;
 }
 
-struct xt_rateest *xt_rateest_lookup(const char *name)
+struct xt_rateest *xt_rateest_lookup(struct net *net, const char *name)
 {
+	struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
 	struct xt_rateest *est;
 
-	mutex_lock(&xt_rateest_mutex);
-	est = __xt_rateest_lookup(name);
-	mutex_unlock(&xt_rateest_mutex);
+	mutex_lock(&xn->hash_lock);
+	est = __xt_rateest_lookup(xn, name);
+	mutex_unlock(&xn->hash_lock);
 	return est;
 }
 EXPORT_SYMBOL_GPL(xt_rateest_lookup);
 
-void xt_rateest_put(struct xt_rateest *est)
+void xt_rateest_put(struct net *net, struct xt_rateest *est)
 {
-	mutex_lock(&xt_rateest_mutex);
+	struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
+
+	mutex_lock(&xn->hash_lock);
 	if (--est->refcnt == 0) {
 		hlist_del(&est->list);
 		gen_kill_estimator(&est->rate_est);
@@ -78,7 +89,7 @@ void xt_rateest_put(struct xt_rateest *est)
 		 */
 		kfree_rcu(est, rcu);
 	}
-	mutex_unlock(&xt_rateest_mutex);
+	mutex_unlock(&xn->hash_lock);
 }
 EXPORT_SYMBOL_GPL(xt_rateest_put);
 
@@ -98,6 +109,7 @@ xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
 static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 {
+	struct xt_rateest_net *xn = net_generic(par->net, xt_rateest_id);
 	struct xt_rateest_target_info *info = par->targinfo;
 	struct xt_rateest *est;
 	struct {
@@ -108,10 +120,10 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 
 	net_get_random_once(&jhash_rnd, sizeof(jhash_rnd));
 
-	mutex_lock(&xt_rateest_mutex);
-	est = __xt_rateest_lookup(info->name);
+	mutex_lock(&xn->hash_lock);
+	est = __xt_rateest_lookup(xn, info->name);
 	if (est) {
-		mutex_unlock(&xt_rateest_mutex);
+		mutex_unlock(&xn->hash_lock);
 		/*
 		 * If estimator parameters are specified, they must match the
 		 * existing estimator.
@@ -119,7 +131,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 		if ((!info->interval && !info->ewma_log) ||
 		    (info->interval != est->params.interval ||
 		     info->ewma_log != est->params.ewma_log)) {
-			xt_rateest_put(est);
+			xt_rateest_put(par->net, est);
 			return -EINVAL;
 		}
 		info->est = est;
@@ -148,14 +160,14 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 		goto err2;
 
 	info->est = est;
-	xt_rateest_hash_insert(est);
-	mutex_unlock(&xt_rateest_mutex);
+	xt_rateest_hash_insert(xn, est);
+	mutex_unlock(&xn->hash_lock);
 	return 0;
 
 err2:
 	kfree(est);
 err1:
-	mutex_unlock(&xt_rateest_mutex);
+	mutex_unlock(&xn->hash_lock);
 	return ret;
 }
 
@@ -163,7 +175,7 @@ static void xt_rateest_tg_destroy(const struct xt_tgdtor_param *par)
 {
 	struct xt_rateest_target_info *info = par->targinfo;
 
-	xt_rateest_put(info->est);
+	xt_rateest_put(par->net, info->est);
 }
 
 static struct xt_target xt_rateest_tg_reg __read_mostly = {
@@ -178,19 +190,46 @@ static struct xt_target xt_rateest_tg_reg __read_mostly = {
 	.me         = THIS_MODULE,
 };
 
-static int __init xt_rateest_tg_init(void)
+static __net_init int xt_rateest_net_init(struct net *net)
+{
+	struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
+	int i;
+
+	mutex_init(&xn->hash_lock);
+	for (i = 0; i < ARRAY_SIZE(xn->hash); i++)
+		INIT_HLIST_HEAD(&xn->hash[i]);
+	return 0;
+}
+
+static void __net_exit xt_rateest_net_exit(struct net *net)
 {
-	unsigned int i;
+	struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(xn->hash); i++)
+		WARN_ON_ONCE(!hlist_empty(&xn->hash[i]));
+}
 
-	for (i = 0; i < ARRAY_SIZE(rateest_hash); i++)
-		INIT_HLIST_HEAD(&rateest_hash[i]);
+static struct pernet_operations xt_rateest_net_ops = {
+	.init = xt_rateest_net_init,
+	.exit = xt_rateest_net_exit,
+	.id   = &xt_rateest_id,
+	.size = sizeof(struct xt_rateest_net),
+};
+
+static int __init xt_rateest_tg_init(void)
+{
+	int err = register_pernet_subsys(&xt_rateest_net_ops);
 
+	if (err)
+		return err;
 	return xt_register_target(&xt_rateest_tg_reg);
 }
 
 static void __exit xt_rateest_tg_fini(void)
 {
 	xt_unregister_target(&xt_rateest_tg_reg);
+	unregister_pernet_subsys(&xt_rateest_net_ops);
 }
 
 
diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c
index 755d2f6693a2..bf77326861af 100644
--- a/net/netfilter/xt_rateest.c
+++ b/net/netfilter/xt_rateest.c
@@ -95,13 +95,13 @@ static int xt_rateest_mt_checkentry(const struct xt_mtchk_param *par)
 	}
 
 	ret  = -ENOENT;
-	est1 = xt_rateest_lookup(info->name1);
+	est1 = xt_rateest_lookup(par->net, info->name1);
 	if (!est1)
 		goto err1;
 
 	est2 = NULL;
 	if (info->flags & XT_RATEEST_MATCH_REL) {
-		est2 = xt_rateest_lookup(info->name2);
+		est2 = xt_rateest_lookup(par->net, info->name2);
 		if (!est2)
 			goto err2;
 	}
@@ -111,7 +111,7 @@ static int xt_rateest_mt_checkentry(const struct xt_mtchk_param *par)
 	return 0;
 
 err2:
-	xt_rateest_put(est1);
+	xt_rateest_put(par->net, est1);
 err1:
 	return ret;
 }
@@ -120,9 +120,9 @@ static void xt_rateest_mt_destroy(const struct xt_mtdtor_param *par)
 {
 	struct xt_rateest_match_info *info = par->matchinfo;
 
-	xt_rateest_put(info->est1);
+	xt_rateest_put(par->net, info->est1);
 	if (info->est2)
-		xt_rateest_put(info->est2);
+		xt_rateest_put(par->net, info->est2);
 }
 
 static struct xt_match xt_rateest_mt_reg __read_mostly = {
-- 
cgit v1.2.3


From ed63afb8a318f6b3558d76afba7809daee4f28e5 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 5 Mar 2018 20:44:18 +0800
Subject: sctp: add support for PR-SCTP Information for sendmsg

This patch is to add support for PR-SCTP Information for sendmsg,
as described in section 5.3.7 of RFC6458.

With this option, you can specify pr_policy and pr_value for user
data in sendmsg.

It's also a necessary send info for sctp_sendv.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  1 +
 include/uapi/linux/sctp.h  | 15 +++++++++++++++
 net/sctp/socket.c          | 31 ++++++++++++++++++++++++++++++-
 3 files changed, 46 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 03e92dda1813..d40a2a329888 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2112,6 +2112,7 @@ struct sctp_cmsgs {
 	struct sctp_initmsg *init;
 	struct sctp_sndrcvinfo *srinfo;
 	struct sctp_sndinfo *sinfo;
+	struct sctp_prinfo *prinfo;
 };
 
 /* Structure for tracking memory objects */
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 4c4db14786bd..0dd1f82a4fa8 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -260,6 +260,19 @@ struct sctp_nxtinfo {
 	sctp_assoc_t nxt_assoc_id;
 };
 
+/* 5.3.7 SCTP PR-SCTP Information Structure (SCTP_PRINFO)
+ *
+ *   This cmsghdr structure specifies SCTP options for sendmsg().
+ *
+ *   cmsg_level    cmsg_type      cmsg_data[]
+ *   ------------  ------------   -------------------
+ *   IPPROTO_SCTP  SCTP_PRINFO    struct sctp_prinfo
+ */
+struct sctp_prinfo {
+	__u16 pr_policy;
+	__u32 pr_value;
+};
+
 /*
  *  sinfo_flags: 16 bits (unsigned integer)
  *
@@ -293,6 +306,8 @@ typedef enum sctp_cmsg_type {
 #define SCTP_RCVINFO	SCTP_RCVINFO
 	SCTP_NXTINFO,		/* 5.3.6 SCTP Next Receive Information Structure */
 #define SCTP_NXTINFO	SCTP_NXTINFO
+	SCTP_PRINFO,		/* 5.3.7 SCTP PR-SCTP Information Structure */
+#define SCTP_PRINFO	SCTP_PRINFO
 } sctp_cmsg_t;
 
 /*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 7fa76031bb08..fdde697b37e7 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1644,6 +1644,12 @@ static int sctp_sendmsg_parse(struct sock *sk, struct sctp_cmsgs *cmsgs,
 		srinfo->sinfo_assoc_id = cmsgs->sinfo->snd_assoc_id;
 	}
 
+	if (cmsgs->prinfo) {
+		srinfo->sinfo_timetolive = cmsgs->prinfo->pr_value;
+		SCTP_PR_SET_POLICY(srinfo->sinfo_flags,
+				   cmsgs->prinfo->pr_policy);
+	}
+
 	sflags = srinfo->sinfo_flags;
 	if (!sflags && msg_len)
 		return 0;
@@ -1901,9 +1907,12 @@ static void sctp_sendmsg_update_sinfo(struct sctp_association *asoc,
 		sinfo->sinfo_ppid = asoc->default_ppid;
 		sinfo->sinfo_context = asoc->default_context;
 		sinfo->sinfo_assoc_id = sctp_assoc2id(asoc);
+
+		if (!cmsgs->prinfo)
+			sinfo->sinfo_flags = asoc->default_flags;
 	}
 
-	if (!cmsgs->srinfo)
+	if (!cmsgs->srinfo && !cmsgs->prinfo)
 		sinfo->sinfo_timetolive = asoc->default_timetolive;
 }
 
@@ -7749,6 +7758,26 @@ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs)
 			      SCTP_ABORT | SCTP_EOF))
 				return -EINVAL;
 			break;
+		case SCTP_PRINFO:
+			/* SCTP Socket API Extension
+			 * 5.3.7 SCTP PR-SCTP Information Structure (SCTP_PRINFO)
+			 *
+			 * This cmsghdr structure specifies SCTP options for sendmsg().
+			 *
+			 * cmsg_level    cmsg_type      cmsg_data[]
+			 * ------------  ------------   ---------------------
+			 * IPPROTO_SCTP  SCTP_PRINFO    struct sctp_prinfo
+			 */
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_prinfo)))
+				return -EINVAL;
+
+			cmsgs->prinfo = CMSG_DATA(cmsg);
+			if (cmsgs->prinfo->pr_policy & ~SCTP_PR_SCTP_MASK)
+				return -EINVAL;
+
+			if (cmsgs->prinfo->pr_policy == SCTP_PR_SCTP_NONE)
+				cmsgs->prinfo->pr_value = 0;
+			break;
 		default:
 			return -EINVAL;
 		}
-- 
cgit v1.2.3


From 2c0dbaa0c43d04d8d6daf52adb724c5789676b15 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 5 Mar 2018 20:44:19 +0800
Subject: sctp: add support for SCTP_DSTADDRV4/6 Information for sendmsg

This patch is to add support for Destination IPv4/6 Address options
for sendmsg, as described in section 5.3.9/10 of RFC6458.

With this option, you can provide more than one destination addrs
to sendmsg when creating asoc, like sctp_connectx.

It's also a necessary send info for sctp_sendv.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  1 +
 include/uapi/linux/sctp.h  |  6 ++++
 net/sctp/socket.c          | 77 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 84 insertions(+)

(limited to 'include/net')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index d40a2a329888..ec6e46b7e119 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2113,6 +2113,7 @@ struct sctp_cmsgs {
 	struct sctp_sndrcvinfo *srinfo;
 	struct sctp_sndinfo *sinfo;
 	struct sctp_prinfo *prinfo;
+	struct msghdr *addrs_msg;
 };
 
 /* Structure for tracking memory objects */
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 0dd1f82a4fa8..a1bc35098033 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -308,6 +308,12 @@ typedef enum sctp_cmsg_type {
 #define SCTP_NXTINFO	SCTP_NXTINFO
 	SCTP_PRINFO,		/* 5.3.7 SCTP PR-SCTP Information Structure */
 #define SCTP_PRINFO	SCTP_PRINFO
+	SCTP_AUTHINFO,		/* 5.3.8 SCTP AUTH Information Structure (RESERVED) */
+#define SCTP_AUTHINFO	SCTP_AUTHINFO
+	SCTP_DSTADDRV4,		/* 5.3.9 SCTP Destination IPv4 Address Structure */
+#define SCTP_DSTADDRV4	SCTP_DSTADDRV4
+	SCTP_DSTADDRV6,		/* 5.3.10 SCTP Destination IPv6 Address Structure */
+#define SCTP_DSTADDRV6	SCTP_DSTADDRV6
 } sctp_cmsg_t;
 
 /*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fdde697b37e7..067b57a330b1 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1676,6 +1676,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 	struct net *net = sock_net(sk);
 	struct sctp_association *asoc;
 	enum sctp_scope scope;
+	struct cmsghdr *cmsg;
 	int err = -EINVAL;
 
 	*tp = NULL;
@@ -1741,6 +1742,67 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 		goto free;
 	}
 
+	if (!cmsgs->addrs_msg)
+		return 0;
+
+	/* sendv addr list parse */
+	for_each_cmsghdr(cmsg, cmsgs->addrs_msg) {
+		struct sctp_transport *transport;
+		struct sctp_association *old;
+		union sctp_addr _daddr;
+		int dlen;
+
+		if (cmsg->cmsg_level != IPPROTO_SCTP ||
+		    (cmsg->cmsg_type != SCTP_DSTADDRV4 &&
+		     cmsg->cmsg_type != SCTP_DSTADDRV6))
+			continue;
+
+		daddr = &_daddr;
+		memset(daddr, 0, sizeof(*daddr));
+		dlen = cmsg->cmsg_len - sizeof(struct cmsghdr);
+		if (cmsg->cmsg_type == SCTP_DSTADDRV4) {
+			if (dlen < sizeof(struct in_addr))
+				goto free;
+
+			dlen = sizeof(struct in_addr);
+			daddr->v4.sin_family = AF_INET;
+			daddr->v4.sin_port = htons(asoc->peer.port);
+			memcpy(&daddr->v4.sin_addr, CMSG_DATA(cmsg), dlen);
+		} else {
+			if (dlen < sizeof(struct in6_addr))
+				goto free;
+
+			dlen = sizeof(struct in6_addr);
+			daddr->v6.sin6_family = AF_INET6;
+			daddr->v6.sin6_port = htons(asoc->peer.port);
+			memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen);
+		}
+		err = sctp_verify_addr(sk, daddr, sizeof(*daddr));
+		if (err)
+			goto free;
+
+		old = sctp_endpoint_lookup_assoc(ep, daddr, &transport);
+		if (old && old != asoc) {
+			if (old->state >= SCTP_STATE_ESTABLISHED)
+				err = -EISCONN;
+			else
+				err = -EALREADY;
+			goto free;
+		}
+
+		if (sctp_endpoint_is_peeled_off(ep, daddr)) {
+			err = -EADDRNOTAVAIL;
+			goto free;
+		}
+
+		transport = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL,
+						SCTP_UNKNOWN);
+		if (!transport) {
+			err = -ENOMEM;
+			goto free;
+		}
+	}
+
 	return 0;
 
 free:
@@ -7778,6 +7840,21 @@ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs)
 			if (cmsgs->prinfo->pr_policy == SCTP_PR_SCTP_NONE)
 				cmsgs->prinfo->pr_value = 0;
 			break;
+		case SCTP_DSTADDRV4:
+		case SCTP_DSTADDRV6:
+			/* SCTP Socket API Extension
+			 * 5.3.9/10 SCTP Destination IPv4/6 Address Structure (SCTP_DSTADDRV4/6)
+			 *
+			 * This cmsghdr structure specifies SCTP options for sendmsg().
+			 *
+			 * cmsg_level    cmsg_type         cmsg_data[]
+			 * ------------  ------------   ---------------------
+			 * IPPROTO_SCTP  SCTP_DSTADDRV4 struct in_addr
+			 * ------------  ------------   ---------------------
+			 * IPPROTO_SCTP  SCTP_DSTADDRV6 struct in6_addr
+			 */
+			cmsgs->addrs_msg = my_msg;
+			break;
 		default:
 			return -EINVAL;
 		}
-- 
cgit v1.2.3


From 79134e6ce2c9d1a00eab4d98cb48f975dd2474cb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 8 Mar 2018 12:51:41 -0800
Subject: net: do not create fallback tunnels for non-default namespaces

fallback tunnels (like tunl0, gre0, gretap0, erspan0, sit0,
ip6tnl0, ip6gre0) are automatically created when the corresponding
module is loaded.

These tunnels are also automatically created when a new network
namespace is created, at a great cost.

In many cases, netns are used for isolation purposes, and these
extra network devices are a waste of resources. We are using
thousands of netns per host, and hit the netns creation/delete
bottleneck a lot. (Many thanks to Kirill for recent work on this)

Add a new sysctl so that we can opt-out from this automatic creation.

Note that these tunnels are still created for the initial namespace,
to be the least intrusive for typical setups.

Tested:
lpk43:~# cat add_del_unshare.sh
for i in `seq 1 40`
do
 (for j in `seq 1 100` ; do  unshare -n /bin/true >/dev/null ; done) &
done
wait

lpk43:~# echo 0 >/proc/sys/net/core/fb_tunnels_only_for_init_net
lpk43:~# time ./add_del_unshare.sh

real	0m37.521s
user	0m0.886s
sys	7m7.084s
lpk43:~# echo 1 >/proc/sys/net/core/fb_tunnels_only_for_init_net
lpk43:~# time ./add_del_unshare.sh

real	0m4.761s
user	0m0.851s
sys	1m8.343s
lpk43:~#

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/sysctl/net.txt | 12 ++++++++++++
 include/linux/netdevice.h    |  7 +++++++
 include/net/ip_tunnels.h     |  2 ++
 net/core/sysctl_net_core.c   | 12 ++++++++++++
 net/ipv4/ip_tunnel.c         | 20 ++++++++++++--------
 net/ipv6/ip6_gre.c           |  4 +++-
 net/ipv6/ip6_tunnel.c        |  2 ++
 net/ipv6/sit.c               |  5 ++++-
 8 files changed, 54 insertions(+), 10 deletions(-)

(limited to 'include/net')

diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 35c62f522754..5992602469d8 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -270,6 +270,18 @@ optmem_max
 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
 of struct cmsghdr structures with appended data.
 
+fb_tunnels_only_for_init_net
+----------------------------
+
+Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0,
+sit0, ip6tnl0, ip6gre0) are automatically created when a new
+network namespace is created, if corresponding tunnel is present
+in initial network namespace.
+If set to 1, these devices are not automatically created, and
+user space is responsible for creating them if needed.
+
+Default : 0  (for compatibility reasons)
+
 2. /proc/sys/net/unix - Parameters for Unix domain sockets
 -------------------------------------------------------
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 95a613a7cc1c..9711108c3916 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -585,6 +585,13 @@ struct netdev_queue {
 #endif
 } ____cacheline_aligned_in_smp;
 
+extern int sysctl_fb_tunnels_only_for_init_net;
+
+static inline bool net_has_fallback_tunnels(const struct net *net)
+{
+	return net == &init_net || !sysctl_fb_tunnels_only_for_init_net;
+}
+
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
 {
 #if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index cbe5addb9293..540a4b4417bf 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -180,8 +180,10 @@ struct tnl_ptk_info {
 
 struct ip_tunnel_net {
 	struct net_device *fb_tunnel_dev;
+	struct rtnl_link_ops *rtnl_link_ops;
 	struct hlist_head tunnels[IP_TNL_HASH_SIZE];
 	struct ip_tunnel __rcu *collect_md_tun;
+	int type;
 };
 
 static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index d714f65782b7..4f47f92459cc 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -32,6 +32,9 @@ static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
+int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0;
+EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net);
+
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -513,6 +516,15 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 	},
+	{
+		.procname	= "fb_tunnels_only_for_init_net",
+		.data		= &sysctl_fb_tunnels_only_for_init_net,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 602597dfc395..5fcb17cb426b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -347,8 +347,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	struct net_device *dev;
 	int t_hlen;
 
-	BUG_ON(!itn->fb_tunnel_dev);
-	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
+	dev = __ip_tunnel_create(net, itn->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
 		return ERR_CAST(dev);
 
@@ -822,7 +821,6 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 	struct net *net = t->net;
 	struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id);
 
-	BUG_ON(!itn->fb_tunnel_dev);
 	switch (cmd) {
 	case SIOCGETTUNNEL:
 		if (dev == itn->fb_tunnel_dev) {
@@ -847,7 +845,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 				p->o_key = 0;
 		}
 
-		t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+		t = ip_tunnel_find(itn, p, itn->type);
 
 		if (cmd == SIOCADDTUNNEL) {
 			if (!t) {
@@ -991,10 +989,15 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 	struct ip_tunnel_parm parms;
 	unsigned int i;
 
+	itn->rtnl_link_ops = ops;
 	for (i = 0; i < IP_TNL_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&itn->tunnels[i]);
 
-	if (!ops) {
+	if (!ops || !net_has_fallback_tunnels(net)) {
+		struct ip_tunnel_net *it_init_net;
+
+		it_init_net = net_generic(&init_net, ip_tnl_net_id);
+		itn->type = it_init_net->type;
 		itn->fb_tunnel_dev = NULL;
 		return 0;
 	}
@@ -1012,6 +1015,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
+		itn->type = itn->fb_tunnel_dev->type;
 	}
 	rtnl_unlock();
 
@@ -1019,10 +1023,10 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
 
-static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
+static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn,
+			      struct list_head *head,
 			      struct rtnl_link_ops *ops)
 {
-	struct net *net = dev_net(itn->fb_tunnel_dev);
 	struct net_device *dev, *aux;
 	int h;
 
@@ -1054,7 +1058,7 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
 	rtnl_lock();
 	list_for_each_entry(net, net_list, exit_list) {
 		itn = net_generic(net, id);
-		ip_tunnel_destroy(itn, &list, ops);
+		ip_tunnel_destroy(net, itn, &list, ops);
 	}
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 18a3dfbd0300..7d8775c9570d 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -236,7 +236,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 		return t;
 
 	dev = ign->fb_tunnel_dev;
-	if (dev->flags & IFF_UP)
+	if (dev && dev->flags & IFF_UP)
 		return netdev_priv(dev);
 
 	return NULL;
@@ -1472,6 +1472,8 @@ static int __net_init ip6gre_init_net(struct net *net)
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	int err;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
 	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
 					  NET_NAME_UNKNOWN,
 					  ip6gre_tunnel_setup);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 56c4967f1868..5c045fa407da 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2205,6 +2205,8 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	ip6n->tnls[0] = ip6n->tnls_wc;
 	ip6n->tnls[1] = ip6n->tnls_r_l;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
 	err = -ENOMEM;
 	ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0",
 					NET_NAME_UNKNOWN, ip6_tnl_dev_setup);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a9c4ac6efe22..8a4f8fddd812 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -182,7 +182,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel *t = netdev_priv(dev);
 
-	if (dev == sitn->fb_tunnel_dev) {
+	if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) {
 		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
 		t->ip6rd.relay_prefix = 0;
 		t->ip6rd.prefixlen = 16;
@@ -1835,6 +1835,9 @@ static int __net_init sit_init_net(struct net *net)
 	sitn->tunnels[2] = sitn->tunnels_r;
 	sitn->tunnels[3] = sitn->tunnels_r_l;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
+
 	sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
 					   NET_NAME_UNKNOWN,
 					   ipip6_tunnel_setup);
-- 
cgit v1.2.3


From d04e6990c948a3315ea8eca5979ebea48cda56f4 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Thu, 8 Mar 2018 16:59:17 -0500
Subject: net sched actions: update Add/Delete action API with new argument

Introduce a new function argument to carry total attributes size for
correct allocation of skb in event messages.

Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  3 ++-
 net/sched/act_api.c   | 21 +++++++++++++--------
 net/sched/cls_api.c   |  3 ++-
 3 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 9c2f22695025..88c1f99bae46 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -166,7 +166,8 @@ 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 list_head *actions, struct netlink_ext_ack *extack);
+		    struct list_head *actions, size_t *attr_size,
+		    struct netlink_ext_ack *extack);
 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,
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a54fa7b8c217..3de0e0610200 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -741,7 +741,8 @@ static void cleanup_a(struct list_head *actions, int ovr)
 
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct list_head *actions, struct netlink_ext_ack *extack)
+		    struct list_head *actions, size_t *attr_size,
+		    struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
@@ -994,12 +995,13 @@ err_out:
 
 static int
 tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
-	       u32 portid, struct netlink_ext_ack *extack)
+	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
 {
 	int ret;
 	struct sk_buff *skb;
 
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
+			GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
 
@@ -1032,6 +1034,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	int i, ret;
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
+	size_t attr_size = 0;
 	LIST_HEAD(actions);
 
 	ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
@@ -1059,7 +1062,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	if (event == RTM_GETACTION)
 		ret = tcf_get_notify(net, portid, n, &actions, event, extack);
 	else { /* delete */
-		ret = tcf_del_notify(net, n, &actions, portid, extack);
+		ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
 		if (ret)
 			goto err;
 		return ret;
@@ -1072,12 +1075,13 @@ err:
 
 static int
 tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
-	       u32 portid, struct netlink_ext_ack *extack)
+	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
 {
 	struct sk_buff *skb;
 	int err = 0;
 
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
+			GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
 
@@ -1099,15 +1103,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 			  struct nlmsghdr *n, u32 portid, int ovr,
 			  struct netlink_ext_ack *extack)
 {
+	size_t attr_size = 0;
 	int ret = 0;
 	LIST_HEAD(actions);
 
 	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
-			      extack);
+			      &attr_size, extack);
 	if (ret)
 		return ret;
 
-	return tcf_add_notify(net, n, &actions, portid, extack);
+	return tcf_add_notify(net, n, &actions, portid, attr_size, extack);
 }
 
 static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 19f9f421d5b7..ec5fe8ec0c3e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1433,6 +1433,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 #ifdef CONFIG_NET_CLS_ACT
 	{
 		struct tc_action *act;
+		size_t attr_size = 0;
 
 		if (exts->police && tb[exts->police]) {
 			act = tcf_action_init_1(net, tp, tb[exts->police],
@@ -1450,7 +1451,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 
 			err = tcf_action_init(net, tp, tb[exts->action],
 					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
-					      &actions, extack);
+					      &actions, &attr_size, extack);
 			if (err)
 				return err;
 			list_for_each_entry(act, &actions, list)
-- 
cgit v1.2.3


From a03b91b17684023c45d39b836c85579d5e535983 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Thu, 8 Mar 2018 16:59:18 -0500
Subject: net sched actions: add new tc_action_ops callback

Add a new callback in tc_action_ops, it will be needed by the tc actions
to compute its size when a ADD/DELETE notification message is constructed.
This routine has to take into account optional/variable size TLVs specific
per action.

Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 88c1f99bae46..e0a9c2003b24 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -97,6 +97,7 @@ struct tc_action_ops {
 			const struct tc_action_ops *,
 			struct netlink_ext_ack *);
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
+	size_t  (*get_fill_size)(const struct tc_action *act);
 	struct net_device *(*get_dev)(const struct tc_action *a);
 };
 
-- 
cgit v1.2.3


From 918ee5073b0e253649083d731a88588b5c1723a3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 11 Mar 2018 09:45:47 +0200
Subject: net: ipv6: Introduce ip6_multipath_hash_policy()

In order to abstract away access to the
ipv6.sysctl.multipath_hash_policy variable, which is not available on
systems compiled without IPv6 support, introduce a wrapper function
ip6_multipath_hash_policy() that falls back to 0 on non-IPv6 systems.

Use this wrapper from mlxsw/spectrum_router instead of a direct
reference.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c |  2 +-
 include/net/ipv6.h                                    | 11 +++++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index a8a578610a7b..921bd1075edf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -7031,7 +7031,7 @@ static void mlxsw_sp_mp4_hash_init(char *recr2_pl)
 
 static void mlxsw_sp_mp6_hash_init(char *recr2_pl)
 {
-	bool only_l3 = !init_net.ipv6.sysctl.multipath_hash_policy;
+	bool only_l3 = !ip6_multipath_hash_policy(&init_net);
 
 	mlxsw_sp_mp_hash_header_set(recr2_pl,
 				    MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index cabd3cdd4015..50a6f0ddb878 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -888,6 +888,17 @@ static inline int ip6_default_np_autolabel(struct net *net)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int ip6_multipath_hash_policy(const struct net *net)
+{
+	return net->ipv6.sysctl.multipath_hash_policy;
+}
+#else
+static inline int ip6_multipath_hash_policy(const struct net *net)
+{
+	return 0;
+}
+#endif
 
 /*
  *	Header manipulation
-- 
cgit v1.2.3


From 6056415d3a513846f774e7bbee0de0460b1c15df Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Tue, 13 Mar 2018 13:55:55 +0300
Subject: net: Add comment about pernet_operations methods and synchronization

Make locking scheme be visible for users, and provide
a comment what for we are need exit_batch() methods,
and when it should be used.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include/net')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index d4417495773a..71abc8d79178 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -312,6 +312,20 @@ struct net *get_net_ns_by_id(struct net *net, int id);
 
 struct pernet_operations {
 	struct list_head list;
+	/*
+	 * Below methods are called without any exclusive locks.
+	 * More than one net may be constructed and destructed
+	 * in parallel on several cpus. Every pernet_operations
+	 * have to keep in mind all other pernet_operations and
+	 * to introduce a locking, if they share common resources.
+	 *
+	 * Exit methods using blocking RCU primitives, such as
+	 * synchronize_rcu(), should be implemented via exit_batch.
+	 * Then, destruction of a group of net requires single
+	 * synchronize_rcu() related to these pernet_operations,
+	 * instead of separate synchronize_rcu() for every net.
+	 * Please, avoid synchronize_rcu() at all, where it's possible.
+	 */
 	int (*init)(struct net *net);
 	void (*exit)(struct net *net);
 	void (*exit_batch)(struct list_head *net_exit_list);
-- 
cgit v1.2.3


From 4c10d56a76bb1d40ea6bede579d1522cbcdc438e Mon Sep 17 00:00:00 2001
From: Prameela Rani Garnepudi <prameela.j04cs@gmail.com>
Date: Tue, 27 Feb 2018 19:56:13 +0530
Subject: rsi: add header file rsi_91x

The common parameters used by wlan and bt modules are add
to a new header file "rsi_91x.h" defined in 'include/net'

Signed-off-by: Prameela Rani Garnepudi <prameela.j04cs@gmail.com>
Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Amitkumar Karwar <amit.karwar@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_main.h | 12 ++----------
 include/net/rsi_91x.h               | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 10 deletions(-)
 create mode 100644 include/net/rsi_91x.h

(limited to 'include/net')

diff --git a/drivers/net/wireless/rsi/rsi_main.h b/drivers/net/wireless/rsi/rsi_main.h
index ee469dc66562..b0f4e2cce0ec 100644
--- a/drivers/net/wireless/rsi/rsi_main.h
+++ b/drivers/net/wireless/rsi/rsi_main.h
@@ -20,6 +20,7 @@
 #include <linux/string.h>
 #include <linux/skbuff.h>
 #include <net/mac80211.h>
+#include <net/rsi_91x.h>
 
 struct rsi_sta {
 	struct ieee80211_sta *sta;
@@ -85,10 +86,6 @@ extern __printf(2, 3) void rsi_dbg(u32 zone, const char *fmt, ...);
 #define MGMT_HW_Q			10
 #define BEACON_HW_Q			11
 
-/* Queue information */
-#define RSI_COEX_Q			0x0
-#define RSI_WIFI_MGMT_Q                 0x4
-#define RSI_WIFI_DATA_Q                 0x5
 #define IEEE80211_MGMT_FRAME            0x00
 #define IEEE80211_CTL_FRAME             0x04
 
@@ -293,11 +290,6 @@ struct rsi_common {
 	struct ieee80211_vif *roc_vif;
 };
 
-enum host_intf {
-	RSI_HOST_INTF_SDIO = 0,
-	RSI_HOST_INTF_USB
-};
-
 struct eepromrw_info {
 	u32 offset;
 	u32 length;
@@ -322,7 +314,7 @@ struct rsi_hw {
 	struct device *device;
 	u8 sc_nvifs;
 
-	enum host_intf rsi_host_intf;
+	enum rsi_host_intf rsi_host_intf;
 	u16 block_size;
 	enum ps_state ps_state;
 	struct rsi_ps_info ps_info;
diff --git a/include/net/rsi_91x.h b/include/net/rsi_91x.h
new file mode 100644
index 000000000000..16a447b46119
--- /dev/null
+++ b/include/net/rsi_91x.h
@@ -0,0 +1,34 @@
+/**
+ * Copyright (c) 2017 Redpine Signals Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __RSI_HEADER_H__
+#define __RSI_HEADER_H__
+
+/* HAL queue information */
+#define RSI_COEX_Q			0x0
+#define RSI_BT_Q			0x2
+#define RSI_WLAN_Q                      0x3
+#define RSI_WIFI_MGMT_Q                 0x4
+#define RSI_WIFI_DATA_Q                 0x5
+#define RSI_BT_MGMT_Q			0x6
+#define RSI_BT_DATA_Q			0x7
+
+enum rsi_host_intf {
+	RSI_HOST_INTF_SDIO = 0,
+	RSI_HOST_INTF_USB
+};
+
+#endif
-- 
cgit v1.2.3


From 2108df3c4b1856588ca2e7f641900c2bbf38467e Mon Sep 17 00:00:00 2001
From: Prameela Rani Garnepudi <prameela.j04cs@gmail.com>
Date: Tue, 27 Feb 2018 19:56:14 +0530
Subject: rsi: add coex support

With BT support, driver has to handle two streams of data
(i.e. wlan and BT). Actual coex implementation is in firmware.
Coex module just schedule the packets to firmware by taking them
from the corresponding paths.

Structures for module and protocol operations are introduced for
this purpose. Protocol operations structure is global structure
which can be shared among different modules. Move initialization
of coex and operating mode values to rsi_91x_init().

Signed-off-by: Prameela Rani Garnepudi <prameela.j04cs@gmail.com>
Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Amitkumar Karwar <amit.karwar@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/Kconfig        |   9 ++
 drivers/net/wireless/rsi/Makefile       |   1 +
 drivers/net/wireless/rsi/rsi_91x_coex.c | 177 ++++++++++++++++++++++++++++++++
 drivers/net/wireless/rsi/rsi_91x_hal.c  |  17 +--
 drivers/net/wireless/rsi/rsi_91x_main.c |  38 ++++++-
 drivers/net/wireless/rsi/rsi_91x_mgmt.c |   2 +-
 drivers/net/wireless/rsi/rsi_91x_sdio.c |   1 +
 drivers/net/wireless/rsi/rsi_91x_usb.c  |   2 +
 drivers/net/wireless/rsi/rsi_coex.h     |  37 +++++++
 drivers/net/wireless/rsi/rsi_main.h     |   6 ++
 drivers/net/wireless/rsi/rsi_mgmt.h     |   3 +
 include/net/rsi_91x.h                   |  20 ++++
 12 files changed, 303 insertions(+), 10 deletions(-)
 create mode 100644 drivers/net/wireless/rsi/rsi_91x_coex.c
 create mode 100644 drivers/net/wireless/rsi/rsi_coex.h

(limited to 'include/net')

diff --git a/drivers/net/wireless/rsi/Kconfig b/drivers/net/wireless/rsi/Kconfig
index 7c5e4ca4e3d0..e6135ee35213 100644
--- a/drivers/net/wireless/rsi/Kconfig
+++ b/drivers/net/wireless/rsi/Kconfig
@@ -42,4 +42,13 @@ config RSI_USB
 	  This option enables the USB bus support in rsi drivers.
 	  Select M (recommended), if you have a RSI 1x1 wireless module.
 
+config RSI_COEX
+	bool "Redpine Signals WLAN BT Coexistence support"
+	depends on BT_HCIRSI && RSI_91X
+	default y
+	---help---
+	  This option enables the WLAN BT coex support in rsi drivers.
+	  Select M (recommended), if you have want to use this feature
+	  and you have RS9113 module.
+
 endif # WLAN_VENDOR_RSI
diff --git a/drivers/net/wireless/rsi/Makefile b/drivers/net/wireless/rsi/Makefile
index 47c45908d894..ff87121a5928 100644
--- a/drivers/net/wireless/rsi/Makefile
+++ b/drivers/net/wireless/rsi/Makefile
@@ -5,6 +5,7 @@ rsi_91x-y			+= rsi_91x_mac80211.o
 rsi_91x-y			+= rsi_91x_mgmt.o
 rsi_91x-y			+= rsi_91x_hal.o
 rsi_91x-y			+= rsi_91x_ps.o
+rsi_91x-$(CONFIG_RSI_COEX)	+= rsi_91x_coex.o
 rsi_91x-$(CONFIG_RSI_DEBUGFS)	+= rsi_91x_debugfs.o
 
 rsi_usb-y			+= rsi_91x_usb.o rsi_91x_usb_ops.o
diff --git a/drivers/net/wireless/rsi/rsi_91x_coex.c b/drivers/net/wireless/rsi/rsi_91x_coex.c
new file mode 100644
index 000000000000..c07e839017ea
--- /dev/null
+++ b/drivers/net/wireless/rsi/rsi_91x_coex.c
@@ -0,0 +1,177 @@
+/**
+ * Copyright (c) 2018 Redpine Signals Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "rsi_main.h"
+#include "rsi_coex.h"
+#include "rsi_mgmt.h"
+#include "rsi_hal.h"
+
+static enum rsi_coex_queues rsi_coex_determine_coex_q
+			(struct rsi_coex_ctrl_block *coex_cb)
+{
+	enum rsi_coex_queues q_num = RSI_COEX_Q_INVALID;
+
+	if (skb_queue_len(&coex_cb->coex_tx_qs[RSI_COEX_Q_COMMON]) > 0)
+		q_num = RSI_COEX_Q_COMMON;
+	if (skb_queue_len(&coex_cb->coex_tx_qs[RSI_COEX_Q_BT]) > 0)
+		q_num = RSI_COEX_Q_BT;
+	if (skb_queue_len(&coex_cb->coex_tx_qs[RSI_COEX_Q_WLAN]) > 0)
+		q_num = RSI_COEX_Q_WLAN;
+
+	return q_num;
+}
+
+static void rsi_coex_sched_tx_pkts(struct rsi_coex_ctrl_block *coex_cb)
+{
+	enum rsi_coex_queues coex_q = RSI_COEX_Q_INVALID;
+	struct sk_buff *skb;
+
+	do {
+		coex_q = rsi_coex_determine_coex_q(coex_cb);
+		rsi_dbg(INFO_ZONE, "queue = %d\n", coex_q);
+
+		if (coex_q == RSI_COEX_Q_BT)
+			skb = skb_dequeue(&coex_cb->coex_tx_qs[RSI_COEX_Q_BT]);
+	} while (coex_q != RSI_COEX_Q_INVALID);
+}
+
+static void rsi_coex_scheduler_thread(struct rsi_common *common)
+{
+	struct rsi_coex_ctrl_block *coex_cb =
+		(struct rsi_coex_ctrl_block *)common->coex_cb;
+	u32 timeout = EVENT_WAIT_FOREVER;
+
+	do {
+		rsi_wait_event(&coex_cb->coex_tx_thread.event, timeout);
+		rsi_reset_event(&coex_cb->coex_tx_thread.event);
+
+		rsi_coex_sched_tx_pkts(coex_cb);
+	} while (atomic_read(&coex_cb->coex_tx_thread.thread_done) == 0);
+
+	complete_and_exit(&coex_cb->coex_tx_thread.completion, 0);
+}
+
+int rsi_coex_recv_pkt(struct rsi_common *common, u8 *msg)
+{
+	u8 msg_type = msg[RSI_RX_DESC_MSG_TYPE_OFFSET];
+
+	switch (msg_type) {
+	case COMMON_CARD_READY_IND:
+		rsi_dbg(INFO_ZONE, "common card ready received\n");
+		rsi_handle_card_ready(common, msg);
+		break;
+	case SLEEP_NOTIFY_IND:
+		rsi_dbg(INFO_ZONE, "sleep notify received\n");
+		rsi_mgmt_pkt_recv(common, msg);
+		break;
+	}
+
+	return 0;
+}
+
+static inline int rsi_map_coex_q(u8 hal_queue)
+{
+	switch (hal_queue) {
+	case RSI_COEX_Q:
+		return RSI_COEX_Q_COMMON;
+	case RSI_WLAN_Q:
+		return RSI_COEX_Q_WLAN;
+	case RSI_BT_Q:
+		return RSI_COEX_Q_BT;
+	}
+	return RSI_COEX_Q_INVALID;
+}
+
+int rsi_coex_send_pkt(void *priv, struct sk_buff *skb, u8 hal_queue)
+{
+	struct rsi_common *common = (struct rsi_common *)priv;
+	struct rsi_coex_ctrl_block *coex_cb =
+		(struct rsi_coex_ctrl_block *)common->coex_cb;
+	struct skb_info *tx_params = NULL;
+	enum rsi_coex_queues coex_q;
+	int status;
+
+	coex_q = rsi_map_coex_q(hal_queue);
+	if (coex_q == RSI_COEX_Q_INVALID) {
+		rsi_dbg(ERR_ZONE, "Invalid coex queue\n");
+		return -EINVAL;
+	}
+	if (coex_q != RSI_COEX_Q_COMMON &&
+	    coex_q != RSI_COEX_Q_WLAN) {
+		skb_queue_tail(&coex_cb->coex_tx_qs[coex_q], skb);
+		rsi_set_event(&coex_cb->coex_tx_thread.event);
+		return 0;
+	}
+	if (common->iface_down) {
+		tx_params =
+			(struct skb_info *)&IEEE80211_SKB_CB(skb)->driver_data;
+
+		if (!(tx_params->flags & INTERNAL_MGMT_PKT)) {
+			rsi_indicate_tx_status(common->priv, skb, -EINVAL);
+			return 0;
+		}
+	}
+
+	/* Send packet to hal */
+	if (skb->priority == MGMT_SOFT_Q)
+		status = rsi_send_mgmt_pkt(common, skb);
+	else
+		status = rsi_send_data_pkt(common, skb);
+
+	return status;
+}
+
+int rsi_coex_attach(struct rsi_common *common)
+{
+	struct rsi_coex_ctrl_block *coex_cb;
+	int cnt;
+
+	coex_cb = kzalloc(sizeof(*coex_cb), GFP_KERNEL);
+	if (!coex_cb)
+		return -ENOMEM;
+
+	common->coex_cb = (void *)coex_cb;
+	coex_cb->priv = common;
+
+	/* Initialize co-ex queues */
+	for (cnt = 0; cnt < NUM_COEX_TX_QUEUES; cnt++)
+		skb_queue_head_init(&coex_cb->coex_tx_qs[cnt]);
+	rsi_init_event(&coex_cb->coex_tx_thread.event);
+
+	/* Initialize co-ex thread */
+	if (rsi_create_kthread(common,
+			       &coex_cb->coex_tx_thread,
+			       rsi_coex_scheduler_thread,
+			       "Coex-Tx-Thread")) {
+		rsi_dbg(ERR_ZONE, "%s: Unable to init tx thrd\n", __func__);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+void rsi_coex_detach(struct rsi_common *common)
+{
+	struct rsi_coex_ctrl_block *coex_cb =
+		(struct rsi_coex_ctrl_block *)common->coex_cb;
+	int cnt;
+
+	rsi_kill_thread(&coex_cb->coex_tx_thread);
+
+	for (cnt = 0; cnt < NUM_COEX_TX_QUEUES; cnt++)
+		skb_queue_purge(&coex_cb->coex_tx_qs[cnt]);
+
+	kfree(coex_cb);
+}
diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 1176de646942..151d228a6167 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -31,8 +31,15 @@ int rsi_send_pkt_to_bus(struct rsi_common *common, struct sk_buff *skb)
 	struct rsi_hw *adapter = common->priv;
 	int status;
 
+	if (common->coex_mode > 1)
+		mutex_lock(&common->tx_bus_mutex);
+
 	status = adapter->host_intf_ops->write_pkt(common->priv,
 						   skb->data, skb->len);
+
+	if (common->coex_mode > 1)
+		mutex_unlock(&common->tx_bus_mutex);
+
 	return status;
 }
 
@@ -296,8 +303,7 @@ int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb)
 	if (status)
 		goto err;
 
-	status = adapter->host_intf_ops->write_pkt(common->priv, skb->data,
-						   skb->len);
+	status = rsi_send_pkt_to_bus(common, skb);
 	if (status)
 		rsi_dbg(ERR_ZONE, "%s: Failed to write pkt\n", __func__);
 
@@ -342,8 +348,7 @@ int rsi_send_mgmt_pkt(struct rsi_common *common,
 		goto err;
 
 	rsi_prepare_mgmt_desc(common, skb);
-	status = adapter->host_intf_ops->write_pkt(common->priv,
-						   (u8 *)skb->data, skb->len);
+	status = rsi_send_pkt_to_bus(common, skb);
 	if (status)
 		rsi_dbg(ERR_ZONE, "%s: Failed to write the packet\n", __func__);
 
@@ -926,10 +931,6 @@ int rsi_hal_device_init(struct rsi_hw *adapter)
 {
 	struct rsi_common *common = adapter->priv;
 
-	common->coex_mode = RSI_DEV_COEX_MODE_WIFI_ALONE;
-	common->oper_mode = RSI_DEV_OPMODE_WIFI_ALONE;
-	adapter->device_model = RSI_DEV_9113;
-
 	switch (adapter->device_model) {
 	case RSI_DEV_9113:
 		if (rsi_load_firmware(adapter)) {
diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c
index 0413af88cd25..641c388b5666 100644
--- a/drivers/net/wireless/rsi/rsi_91x_main.c
+++ b/drivers/net/wireless/rsi/rsi_91x_main.c
@@ -20,6 +20,7 @@
 #include <linux/firmware.h>
 #include "rsi_mgmt.h"
 #include "rsi_common.h"
+#include "rsi_coex.h"
 #include "rsi_hal.h"
 
 u32 rsi_zone_enabled = /* INFO_ZONE |
@@ -160,8 +161,15 @@ int rsi_read_pkt(struct rsi_common *common, u8 *rx_pkt, s32 rcv_pkt_len)
 
 		switch (queueno) {
 		case RSI_COEX_Q:
-			rsi_mgmt_pkt_recv(common, (frame_desc + offset));
+#ifdef CONFIG_RSI_COEX
+			if (common->coex_mode > 1)
+				rsi_coex_recv_pkt(common, frame_desc + offset);
+			else
+#endif
+				rsi_mgmt_pkt_recv(common,
+						  (frame_desc + offset));
 			break;
+
 		case RSI_WIFI_DATA_Q:
 			skb = rsi_prepare_skb(common,
 					      (frame_desc + offset),
@@ -217,6 +225,15 @@ static void rsi_tx_scheduler_thread(struct rsi_common *common)
 	complete_and_exit(&common->tx_thread.completion, 0);
 }
 
+#ifdef CONFIG_RSI_COEX
+enum rsi_host_intf rsi_get_host_intf(void *priv)
+{
+	struct rsi_common *common = (struct rsi_common *)priv;
+
+	return common->priv->rsi_host_intf;
+}
+#endif
+
 /**
  * rsi_91x_init() - This function initializes os interface operations.
  * @void: Void.
@@ -251,6 +268,7 @@ struct rsi_hw *rsi_91x_init(void)
 	mutex_init(&common->mutex);
 	mutex_init(&common->tx_lock);
 	mutex_init(&common->rx_lock);
+	mutex_init(&common->tx_bus_mutex);
 
 	if (rsi_create_kthread(common,
 			       &common->tx_thread,
@@ -265,6 +283,19 @@ struct rsi_hw *rsi_91x_init(void)
 	timer_setup(&common->roc_timer, rsi_roc_timeout, 0);
 	init_completion(&common->wlan_init_completion);
 	common->init_done = true;
+
+	common->coex_mode = RSI_DEV_COEX_MODE_WIFI_ALONE;
+	common->oper_mode = RSI_DEV_OPMODE_WIFI_ALONE;
+	adapter->device_model = RSI_DEV_9113;
+#ifdef CONFIG_RSI_COEX
+	if (common->coex_mode > 1) {
+		if (rsi_coex_attach(common)) {
+			rsi_dbg(ERR_ZONE, "Failed to init coex module\n");
+			goto err;
+		}
+	}
+#endif
+
 	return adapter;
 
 err:
@@ -294,6 +325,11 @@ void rsi_91x_deinit(struct rsi_hw *adapter)
 
 	common->init_done = false;
 
+#ifdef CONFIG_RSI_COEX
+	if (common->coex_mode > 1)
+		rsi_coex_detach(common);
+#endif
+
 	kfree(common);
 	kfree(adapter->rsi_dev);
 	kfree(adapter);
diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index 46c9d5470dfb..c21fca750fd4 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -1791,7 +1791,7 @@ out:
 	return -EINVAL;
 }
 
-static int rsi_handle_card_ready(struct rsi_common *common, u8 *msg)
+int rsi_handle_card_ready(struct rsi_common *common, u8 *msg)
 {
 	switch (common->fsm_state) {
 	case FSM_CARD_NOT_READY:
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index b0cf41195051..ba38c6d00128 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include "rsi_sdio.h"
 #include "rsi_common.h"
+#include "rsi_coex.h"
 #include "rsi_hal.h"
 
 /**
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index 9ab86fb1da28..b33a05f057ba 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -16,8 +16,10 @@
  */
 
 #include <linux/module.h>
+#include <net/rsi_91x.h>
 #include "rsi_usb.h"
 #include "rsi_hal.h"
+#include "rsi_coex.h"
 
 /**
  * rsi_usb_card_write() - This function writes to the USB Card.
diff --git a/drivers/net/wireless/rsi/rsi_coex.h b/drivers/net/wireless/rsi/rsi_coex.h
new file mode 100644
index 000000000000..0fdc67f37a56
--- /dev/null
+++ b/drivers/net/wireless/rsi/rsi_coex.h
@@ -0,0 +1,37 @@
+/**
+ * Copyright (c) 2018 Redpine Signals Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __RSI_COEX_H__
+#define __RSI_COEX_H__
+
+#include "rsi_common.h"
+
+#ifdef CONFIG_RSI_COEX
+#define COMMON_CARD_READY_IND           0
+#define NUM_COEX_TX_QUEUES              5
+
+struct rsi_coex_ctrl_block {
+	struct rsi_common *priv;
+	struct sk_buff_head coex_tx_qs[NUM_COEX_TX_QUEUES];
+	struct rsi_thread coex_tx_thread;
+};
+
+int rsi_coex_attach(struct rsi_common *common);
+void rsi_coex_detach(struct rsi_common *common);
+int rsi_coex_send_pkt(void *priv, struct sk_buff *skb, u8 proto_type);
+int rsi_coex_recv_pkt(struct rsi_common *common, u8 *msg);
+#endif
+#endif
diff --git a/drivers/net/wireless/rsi/rsi_main.h b/drivers/net/wireless/rsi/rsi_main.h
index b0f4e2cce0ec..99a00a3ccaa4 100644
--- a/drivers/net/wireless/rsi/rsi_main.h
+++ b/drivers/net/wireless/rsi/rsi_main.h
@@ -206,6 +206,7 @@ struct rsi_common {
 	struct rsi_hw *priv;
 	struct vif_priv vif_info[RSI_MAX_VIFS];
 
+	void *coex_cb;
 	bool mgmt_q_block;
 	struct version_info lmac_ver;
 
@@ -270,6 +271,8 @@ struct rsi_common {
 	u8 obm_ant_sel_val;
 	int tx_power;
 	u8 ant_in_use;
+	/* Mutex used for writing packet to bus */
+	struct mutex tx_bus_mutex;
 	bool hibernate_resume;
 	bool reinit_hw;
 	u8 wow_flags;
@@ -359,4 +362,7 @@ struct rsi_host_intf_ops {
 				      u8 *fw);
 	int (*reinit_device)(struct rsi_hw *adapter);
 };
+
+enum rsi_host_intf rsi_get_host_intf(void *priv);
+
 #endif
diff --git a/drivers/net/wireless/rsi/rsi_mgmt.h b/drivers/net/wireless/rsi/rsi_mgmt.h
index 389094a3f91c..cf6567ae5bbe 100644
--- a/drivers/net/wireless/rsi/rsi_mgmt.h
+++ b/drivers/net/wireless/rsi/rsi_mgmt.h
@@ -57,12 +57,14 @@
 #define WOW_PATTERN_SIZE 256
 
 /* Receive Frame Types */
+#define RSI_RX_DESC_MSG_TYPE_OFFSET	2
 #define TA_CONFIRM_TYPE                 0x01
 #define RX_DOT11_MGMT                   0x02
 #define TX_STATUS_IND                   0x04
 #define BEACON_EVENT_IND		0x08
 #define PROBEREQ_CONFIRM                2
 #define CARD_READY_IND                  0x00
+#define SLEEP_NOTIFY_IND                0x06
 
 #define RSI_DELETE_PEER                 0x0
 #define RSI_ADD_PEER                    0x1
@@ -638,6 +640,7 @@ static inline void rsi_set_len_qno(__le16 *addr, u16 len, u8 qno)
 	*addr = cpu_to_le16(len | ((qno & 7) << 12));
 }
 
+int rsi_handle_card_ready(struct rsi_common *common, u8 *msg);
 int rsi_mgmt_pkt_recv(struct rsi_common *common, u8 *msg);
 int rsi_set_vap_capabilities(struct rsi_common *common, enum opmode mode,
 			     u8 *mac_addr, u8 vap_id, u8 vap_status);
diff --git a/include/net/rsi_91x.h b/include/net/rsi_91x.h
index 16a447b46119..737ab4e01e3b 100644
--- a/include/net/rsi_91x.h
+++ b/include/net/rsi_91x.h
@@ -17,6 +17,8 @@
 #ifndef __RSI_HEADER_H__
 #define __RSI_HEADER_H__
 
+#include <linux/skbuff.h>
+
 /* HAL queue information */
 #define RSI_COEX_Q			0x0
 #define RSI_BT_Q			0x2
@@ -26,9 +28,27 @@
 #define RSI_BT_MGMT_Q			0x6
 #define RSI_BT_DATA_Q			0x7
 
+enum rsi_coex_queues {
+	RSI_COEX_Q_INVALID = -1,
+	RSI_COEX_Q_COMMON = 0,
+	RSI_COEX_Q_BT,
+	RSI_COEX_Q_WLAN
+};
+
 enum rsi_host_intf {
 	RSI_HOST_INTF_SDIO = 0,
 	RSI_HOST_INTF_USB
 };
 
+struct rsi_proto_ops {
+	int (*coex_send_pkt)(void *priv, struct sk_buff *skb, u8 hal_queue);
+	enum rsi_host_intf (*get_host_intf)(void *priv);
+	void (*set_bt_context)(void *priv, void *context);
+};
+
+struct rsi_mod_ops {
+	int (*attach)(void *priv, struct rsi_proto_ops *ops);
+	void (*detach)(void *priv);
+	int (*recv_pkt)(void *priv, u8 *msg);
+};
 #endif
-- 
cgit v1.2.3


From 38aa4da504837ba8b9c04941e843642f129661eb Mon Sep 17 00:00:00 2001
From: Prameela Rani Garnepudi <prameela.j04cs@gmail.com>
Date: Tue, 27 Feb 2018 19:56:15 +0530
Subject: Bluetooth: btrsi: add new rsi bluetooth driver

Redpine bluetooth driver is a thin driver which depends on
'rsi_91x' driver for transmitting and receiving packets
to/from device. It creates hci interface when attach() is
called from 'rsi_91x' module.

Signed-off-by: Prameela Rani Garnepudi <prameela.j04cs@gmail.com>
Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Reviewed-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Amitkumar Karwar <amit.karwar@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/bluetooth/Kconfig  |  12 +++
 drivers/bluetooth/Makefile |   2 +
 drivers/bluetooth/btrsi.c  | 188 +++++++++++++++++++++++++++++++++++++++++++++
 include/net/rsi_91x.h      |   4 +-
 4 files changed, 205 insertions(+), 1 deletion(-)
 create mode 100644 drivers/bluetooth/btrsi.c

(limited to 'include/net')

diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 07e55cd8f8c8..d8bbd661dbdb 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -392,4 +392,16 @@ config BT_QCOMSMD
 	  Say Y here to compile support for HCI over Qualcomm SMD into the
 	  kernel or say M to compile as a module.
 
+config BT_HCIRSI
+	tristate "Redpine HCI support"
+	default n
+	select RSI_COEX
+	help
+	  Redpine BT driver.
+	  This driver handles BT traffic from upper layers and pass
+	  to the RSI_91x coex module for further scheduling to device
+
+	  Say Y here to compile support for HCI over Redpine into the
+	  kernel or say M to compile as a module.
+
 endmenu
diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile
index 4e4e44d09796..03cfc1b20c4a 100644
--- a/drivers/bluetooth/Makefile
+++ b/drivers/bluetooth/Makefile
@@ -28,6 +28,8 @@ obj-$(CONFIG_BT_QCA)		+= btqca.o
 
 obj-$(CONFIG_BT_HCIUART_NOKIA)	+= hci_nokia.o
 
+obj-$(CONFIG_BT_HCIRSI)		+= btrsi.o
+
 btmrvl-y			:= btmrvl_main.o
 btmrvl-$(CONFIG_DEBUG_FS)	+= btmrvl_debugfs.o
 
diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c
new file mode 100644
index 000000000000..5034325e417c
--- /dev/null
+++ b/drivers/bluetooth/btrsi.c
@@ -0,0 +1,188 @@
+/**
+ * Copyright (c) 2017 Redpine Signals Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+#include <asm/unaligned.h>
+#include <net/rsi_91x.h>
+#include <net/genetlink.h>
+
+#define RSI_HEADROOM_FOR_BT_HAL	16
+#define RSI_FRAME_DESC_SIZE	16
+
+struct rsi_hci_adapter {
+	void *priv;
+	struct rsi_proto_ops *proto_ops;
+	struct hci_dev *hdev;
+};
+
+static int rsi_hci_open(struct hci_dev *hdev)
+{
+	return 0;
+}
+
+static int rsi_hci_close(struct hci_dev *hdev)
+{
+	return 0;
+}
+
+static int rsi_hci_flush(struct hci_dev *hdev)
+{
+	return 0;
+}
+
+static int rsi_hci_send_pkt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct rsi_hci_adapter *h_adapter = hci_get_drvdata(hdev);
+	struct sk_buff *new_skb = NULL;
+
+	switch (hci_skb_pkt_type(skb)) {
+	case HCI_COMMAND_PKT:
+		hdev->stat.cmd_tx++;
+		break;
+	case HCI_ACLDATA_PKT:
+		hdev->stat.acl_tx++;
+		break;
+	case HCI_SCODATA_PKT:
+		hdev->stat.sco_tx++;
+		break;
+	}
+
+	if (skb_headroom(skb) < RSI_HEADROOM_FOR_BT_HAL) {
+		/* Insufficient skb headroom - allocate a new skb */
+		new_skb = skb_realloc_headroom(skb, RSI_HEADROOM_FOR_BT_HAL);
+		if (unlikely(!new_skb))
+			return -ENOMEM;
+		bt_cb(new_skb)->pkt_type = hci_skb_pkt_type(skb);
+		kfree_skb(skb);
+		skb = new_skb;
+	}
+
+	return h_adapter->proto_ops->coex_send_pkt(h_adapter->priv, skb,
+						   RSI_BT_Q);
+}
+
+static int rsi_hci_recv_pkt(void *priv, const u8 *pkt)
+{
+	struct rsi_hci_adapter *h_adapter = priv;
+	struct hci_dev *hdev = h_adapter->hdev;
+	struct sk_buff *skb;
+	int pkt_len = get_unaligned_le16(pkt) & 0x0fff;
+
+	skb = dev_alloc_skb(pkt_len);
+	if (!skb)
+		return -ENOMEM;
+
+	memcpy(skb->data, pkt + RSI_FRAME_DESC_SIZE, pkt_len);
+	skb_put(skb, pkt_len);
+	h_adapter->hdev->stat.byte_rx += skb->len;
+
+	hci_skb_pkt_type(skb) = pkt[14];
+
+	return hci_recv_frame(hdev, skb);
+}
+
+static int rsi_hci_attach(void *priv, struct rsi_proto_ops *ops)
+{
+	struct rsi_hci_adapter *h_adapter = NULL;
+	struct hci_dev *hdev;
+	int err = 0;
+
+	h_adapter = kzalloc(sizeof(*h_adapter), GFP_KERNEL);
+	if (!h_adapter)
+		return -ENOMEM;
+
+	h_adapter->priv = priv;
+	ops->set_bt_context(priv, h_adapter);
+	h_adapter->proto_ops = ops;
+
+	hdev = hci_alloc_dev();
+	if (!hdev) {
+		BT_ERR("Failed to alloc HCI device");
+		goto err;
+	}
+
+	h_adapter->hdev = hdev;
+
+	if (ops->get_host_intf(priv) == RSI_HOST_INTF_SDIO)
+		hdev->bus = HCI_SDIO;
+	else
+		hdev->bus = HCI_USB;
+
+	hci_set_drvdata(hdev, h_adapter);
+	hdev->dev_type = HCI_PRIMARY;
+	hdev->open = rsi_hci_open;
+	hdev->close = rsi_hci_close;
+	hdev->flush = rsi_hci_flush;
+	hdev->send = rsi_hci_send_pkt;
+
+	err = hci_register_dev(hdev);
+	if (err < 0) {
+		BT_ERR("HCI registration failed with errcode %d", err);
+		hci_free_dev(hdev);
+		goto err;
+	}
+
+	return 0;
+err:
+	h_adapter->hdev = NULL;
+	kfree(h_adapter);
+	return -EINVAL;
+}
+
+static void rsi_hci_detach(void *priv)
+{
+	struct rsi_hci_adapter *h_adapter = priv;
+	struct hci_dev *hdev;
+
+	if (!h_adapter)
+		return;
+
+	hdev = h_adapter->hdev;
+	if (hdev) {
+		hci_unregister_dev(hdev);
+		hci_free_dev(hdev);
+		h_adapter->hdev = NULL;
+	}
+
+	kfree(h_adapter);
+}
+
+const struct rsi_mod_ops rsi_bt_ops = {
+	.attach	= rsi_hci_attach,
+	.detach	= rsi_hci_detach,
+	.recv_pkt = rsi_hci_recv_pkt,
+};
+EXPORT_SYMBOL(rsi_bt_ops);
+
+static int rsi_91x_bt_module_init(void)
+{
+	return 0;
+}
+
+static void rsi_91x_bt_module_exit(void)
+{
+	return;
+}
+
+module_init(rsi_91x_bt_module_init);
+module_exit(rsi_91x_bt_module_exit);
+MODULE_AUTHOR("Redpine Signals Inc");
+MODULE_DESCRIPTION("RSI BT driver");
+MODULE_SUPPORTED_DEVICE("RSI-BT");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/include/net/rsi_91x.h b/include/net/rsi_91x.h
index 737ab4e01e3b..040f07b47f1f 100644
--- a/include/net/rsi_91x.h
+++ b/include/net/rsi_91x.h
@@ -49,6 +49,8 @@ struct rsi_proto_ops {
 struct rsi_mod_ops {
 	int (*attach)(void *priv, struct rsi_proto_ops *ops);
 	void (*detach)(void *priv);
-	int (*recv_pkt)(void *priv, u8 *msg);
+	int (*recv_pkt)(void *priv, const u8 *msg);
 };
+
+extern const struct rsi_mod_ops rsi_bt_ops;
 #endif
-- 
cgit v1.2.3


From 1b1e0bc9947427ae58bbe7de0ce9cfd591b589b9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 14 Mar 2018 19:05:30 +0800
Subject: sctp: add refcnt support for sh_key

With refcnt support for sh_key, chunks auth sh_keys can be decided
before enqueuing it. Changing the active key later will not affect
the chunks already enqueued.

Furthermore, this is necessary when adding the support for authinfo
for sendmsg in next patch.

Note that struct sctp_chunk can't be grown due to that performance
drop issue on slow cpu, so it just reuses head_skb memory for shkey
in sctp_chunk.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/auth.h    |  9 +++--
 include/net/sctp/sm.h      |  3 +-
 include/net/sctp/structs.h |  9 +++--
 net/sctp/auth.c            | 86 +++++++++++++++++++++++-----------------------
 net/sctp/chunk.c           |  5 +++
 net/sctp/output.c          | 18 ++++++++--
 net/sctp/sm_make_chunk.c   | 15 ++++++--
 net/sctp/sm_statefuns.c    | 11 +++---
 net/sctp/socket.c          |  6 ++++
 9 files changed, 104 insertions(+), 58 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h
index e5c57d0a082d..017c1aa3a2c9 100644
--- a/include/net/sctp/auth.h
+++ b/include/net/sctp/auth.h
@@ -62,8 +62,9 @@ struct sctp_auth_bytes {
 /* Definition for a shared key, weather endpoint or association */
 struct sctp_shared_key {
 	struct list_head key_list;
-	__u16 key_id;
 	struct sctp_auth_bytes *key;
+	refcount_t refcnt;
+	__u16 key_id;
 };
 
 #define key_for_each(__key, __list_head) \
@@ -103,8 +104,10 @@ int sctp_auth_send_cid(enum sctp_cid chunk,
 int sctp_auth_recv_cid(enum sctp_cid chunk,
 		       const struct sctp_association *asoc);
 void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
-			    struct sk_buff *skb,
-			    struct sctp_auth_chunk *auth, gfp_t gfp);
+			      struct sk_buff *skb, struct sctp_auth_chunk *auth,
+			      struct sctp_shared_key *ep_key, gfp_t gfp);
+void sctp_auth_shkey_release(struct sctp_shared_key *sh_key);
+void sctp_auth_shkey_hold(struct sctp_shared_key *sh_key);
 
 /* API Helpers */
 int sctp_auth_ep_add_chunkid(struct sctp_endpoint *ep, __u8 chunk_id);
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 2883c43c5258..2d0e782c9055 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -263,7 +263,8 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
 struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc,
 				    __u32 new_cum_tsn, size_t nstreams,
 				    struct sctp_fwdtsn_skip *skiplist);
-struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc);
+struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc,
+				  __u16 key_id);
 struct sctp_chunk *sctp_make_strreset_req(const struct sctp_association *asoc,
 					  __u16 stream_num, __be16 *stream_list,
 					  bool out, bool in);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ec6e46b7e119..49ad67bbdbb5 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -577,8 +577,12 @@ struct sctp_chunk {
 	/* This points to the sk_buff containing the actual data.  */
 	struct sk_buff *skb;
 
-	/* In case of GSO packets, this will store the head one */
-	struct sk_buff *head_skb;
+	union {
+		/* In case of GSO packets, this will store the head one */
+		struct sk_buff *head_skb;
+		/* In case of auth enabled, this will point to the shkey */
+		struct sctp_shared_key *shkey;
+	};
 
 	/* These are the SCTP headers by reverse order in a packet.
 	 * Note that some of these may happen more than once.  In that
@@ -1995,6 +1999,7 @@ struct sctp_association {
 	 * The current generated assocaition shared key (secret)
 	 */
 	struct sctp_auth_bytes *asoc_shared_key;
+	struct sctp_shared_key *shkey;
 
 	/* SCTP AUTH: hmac id of the first peer requested algorithm
 	 * that we support.
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 00667c50efa7..e5214fd7f650 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -101,13 +101,14 @@ struct sctp_shared_key *sctp_auth_shkey_create(__u16 key_id, gfp_t gfp)
 		return NULL;
 
 	INIT_LIST_HEAD(&new->key_list);
+	refcount_set(&new->refcnt, 1);
 	new->key_id = key_id;
 
 	return new;
 }
 
 /* Free the shared key structure */
-static void sctp_auth_shkey_free(struct sctp_shared_key *sh_key)
+static void sctp_auth_shkey_destroy(struct sctp_shared_key *sh_key)
 {
 	BUG_ON(!list_empty(&sh_key->key_list));
 	sctp_auth_key_put(sh_key->key);
@@ -115,6 +116,17 @@ static void sctp_auth_shkey_free(struct sctp_shared_key *sh_key)
 	kfree(sh_key);
 }
 
+void sctp_auth_shkey_release(struct sctp_shared_key *sh_key)
+{
+	if (refcount_dec_and_test(&sh_key->refcnt))
+		sctp_auth_shkey_destroy(sh_key);
+}
+
+void sctp_auth_shkey_hold(struct sctp_shared_key *sh_key)
+{
+	refcount_inc(&sh_key->refcnt);
+}
+
 /* Destroy the entire key list.  This is done during the
  * associon and endpoint free process.
  */
@@ -128,7 +140,7 @@ void sctp_auth_destroy_keys(struct list_head *keys)
 
 	key_for_each_safe(ep_key, tmp, keys) {
 		list_del_init(&ep_key->key_list);
-		sctp_auth_shkey_free(ep_key);
+		sctp_auth_shkey_release(ep_key);
 	}
 }
 
@@ -409,13 +421,19 @@ int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
 
 	sctp_auth_key_put(asoc->asoc_shared_key);
 	asoc->asoc_shared_key = secret;
+	asoc->shkey = ep_key;
 
 	/* Update send queue in case any chunk already in there now
 	 * needs authenticating
 	 */
 	list_for_each_entry(chunk, &asoc->outqueue.out_chunk_list, list) {
-		if (sctp_auth_send_cid(chunk->chunk_hdr->type, asoc))
+		if (sctp_auth_send_cid(chunk->chunk_hdr->type, asoc)) {
 			chunk->auth = 1;
+			if (!chunk->shkey) {
+				chunk->shkey = asoc->shkey;
+				sctp_auth_shkey_hold(chunk->shkey);
+			}
+		}
 	}
 
 	return 0;
@@ -703,16 +721,15 @@ int sctp_auth_recv_cid(enum sctp_cid chunk, const struct sctp_association *asoc)
  *    after the AUTH chunk in the SCTP packet.
  */
 void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
-			      struct sk_buff *skb,
-			      struct sctp_auth_chunk *auth,
-			      gfp_t gfp)
+			      struct sk_buff *skb, struct sctp_auth_chunk *auth,
+			      struct sctp_shared_key *ep_key, gfp_t gfp)
 {
-	struct crypto_shash *tfm;
 	struct sctp_auth_bytes *asoc_key;
+	struct crypto_shash *tfm;
 	__u16 key_id, hmac_id;
-	__u8 *digest;
 	unsigned char *end;
 	int free_key = 0;
+	__u8 *digest;
 
 	/* Extract the info we need:
 	 * - hmac id
@@ -724,12 +741,7 @@ void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
 	if (key_id == asoc->active_key_id)
 		asoc_key = asoc->asoc_shared_key;
 	else {
-		struct sctp_shared_key *ep_key;
-
-		ep_key = sctp_auth_get_shkey(asoc, key_id);
-		if (!ep_key)
-			return;
-
+		/* ep_key can't be NULL here */
 		asoc_key = sctp_auth_asoc_create_secret(asoc, ep_key, gfp);
 		if (!asoc_key)
 			return;
@@ -829,7 +841,7 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
 		      struct sctp_association *asoc,
 		      struct sctp_authkey *auth_key)
 {
-	struct sctp_shared_key *cur_key = NULL;
+	struct sctp_shared_key *cur_key, *shkey;
 	struct sctp_auth_bytes *key;
 	struct list_head *sh_keys;
 	int replace = 0;
@@ -842,46 +854,34 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
 	else
 		sh_keys = &ep->endpoint_shared_keys;
 
-	key_for_each(cur_key, sh_keys) {
-		if (cur_key->key_id == auth_key->sca_keynumber) {
+	key_for_each(shkey, sh_keys) {
+		if (shkey->key_id == auth_key->sca_keynumber) {
 			replace = 1;
 			break;
 		}
 	}
 
-	/* If we are not replacing a key id, we need to allocate
-	 * a shared key.
-	 */
-	if (!replace) {
-		cur_key = sctp_auth_shkey_create(auth_key->sca_keynumber,
-						 GFP_KERNEL);
-		if (!cur_key)
-			return -ENOMEM;
-	}
+	cur_key = sctp_auth_shkey_create(auth_key->sca_keynumber, GFP_KERNEL);
+	if (!cur_key)
+		return -ENOMEM;
 
 	/* Create a new key data based on the info passed in */
 	key = sctp_auth_create_key(auth_key->sca_keylength, GFP_KERNEL);
-	if (!key)
-		goto nomem;
+	if (!key) {
+		kfree(cur_key);
+		return -ENOMEM;
+	}
 
 	memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength);
+	cur_key->key = key;
 
-	/* If we are replacing, remove the old keys data from the
-	 * key id.  If we are adding new key id, add it to the
-	 * list.
-	 */
-	if (replace)
-		sctp_auth_key_put(cur_key->key);
-	else
-		list_add(&cur_key->key_list, sh_keys);
+	if (replace) {
+		list_del_init(&shkey->key_list);
+		sctp_auth_shkey_release(shkey);
+	}
+	list_add(&cur_key->key_list, sh_keys);
 
-	cur_key->key = key;
 	return 0;
-nomem:
-	if (!replace)
-		sctp_auth_shkey_free(cur_key);
-
-	return -ENOMEM;
 }
 
 int sctp_auth_set_active_key(struct sctp_endpoint *ep,
@@ -952,7 +952,7 @@ int sctp_auth_del_key_id(struct sctp_endpoint *ep,
 
 	/* Delete the shared key */
 	list_del_init(&key->key_list);
-	sctp_auth_shkey_free(key);
+	sctp_auth_shkey_release(key);
 
 	return 0;
 }
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 991a530c6b31..9f28a9aae976 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -168,6 +168,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 {
 	size_t len, first_len, max_data, remaining;
 	size_t msg_len = iov_iter_count(from);
+	struct sctp_shared_key *shkey = NULL;
 	struct list_head *pos, *temp;
 	struct sctp_chunk *chunk;
 	struct sctp_datamsg *msg;
@@ -204,6 +205,8 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 		if (hmac_desc)
 			max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) +
 					      hmac_desc->hmac_len);
+
+		shkey = asoc->shkey;
 	}
 
 	/* Check what's our max considering the above */
@@ -275,6 +278,8 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 		if (err < 0)
 			goto errout_chunk_free;
 
+		chunk->shkey = shkey;
+
 		/* Put the chunk->skb back into the form expected by send.  */
 		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr -
 				       chunk->skb->data);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 01a26ee051e3..d6e1c90cc09a 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -241,10 +241,13 @@ static enum sctp_xmit sctp_packet_bundle_auth(struct sctp_packet *pkt,
 	if (!chunk->auth)
 		return retval;
 
-	auth = sctp_make_auth(asoc);
+	auth = sctp_make_auth(asoc, chunk->shkey->key_id);
 	if (!auth)
 		return retval;
 
+	auth->shkey = chunk->shkey;
+	sctp_auth_shkey_hold(auth->shkey);
+
 	retval = __sctp_packet_append_chunk(pkt, auth);
 
 	if (retval != SCTP_XMIT_OK)
@@ -490,7 +493,8 @@ merge:
 		}
 
 		if (auth) {
-			sctp_auth_calculate_hmac(tp->asoc, nskb, auth, gfp);
+			sctp_auth_calculate_hmac(tp->asoc, nskb, auth,
+						 packet->auth->shkey, gfp);
 			/* free auth if no more chunks, or add it back */
 			if (list_empty(&packet->chunk_list))
 				sctp_chunk_free(packet->auth);
@@ -770,6 +774,16 @@ static enum sctp_xmit sctp_packet_will_fit(struct sctp_packet *packet,
 	enum sctp_xmit retval = SCTP_XMIT_OK;
 	size_t psize, pmtu, maxsize;
 
+	/* Don't bundle in this packet if this chunk's auth key doesn't
+	 * match other chunks already enqueued on this packet. Also,
+	 * don't bundle the chunk with auth key if other chunks in this
+	 * packet don't have auth key.
+	 */
+	if ((packet->auth && chunk->shkey != packet->auth->shkey) ||
+	    (!packet->auth && chunk->shkey &&
+	     chunk->chunk_hdr->type != SCTP_CID_AUTH))
+		return SCTP_XMIT_PMTU_FULL;
+
 	psize = packet->size;
 	if (packet->transport->asoc)
 		pmtu = packet->transport->asoc->pathmtu;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index d01475f5f710..10f071cdf188 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -87,7 +87,10 @@ static void  *sctp_addto_chunk_fixed(struct sctp_chunk *, int len,
 /* Control chunk destructor */
 static void sctp_control_release_owner(struct sk_buff *skb)
 {
-	/*TODO: do memory release */
+	struct sctp_chunk *chunk = skb_shinfo(skb)->destructor_arg;
+
+	if (chunk->shkey)
+		sctp_auth_shkey_release(chunk->shkey);
 }
 
 static void sctp_control_set_owner_w(struct sctp_chunk *chunk)
@@ -102,7 +105,12 @@ static void sctp_control_set_owner_w(struct sctp_chunk *chunk)
 	 *
 	 *  For now don't do anything for now.
 	 */
+	if (chunk->auth) {
+		chunk->shkey = asoc->shkey;
+		sctp_auth_shkey_hold(chunk->shkey);
+	}
 	skb->sk = asoc ? asoc->base.sk : NULL;
+	skb_shinfo(skb)->destructor_arg = chunk;
 	skb->destructor = sctp_control_release_owner;
 }
 
@@ -1271,7 +1279,8 @@ nodata:
 	return retval;
 }
 
-struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc)
+struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc,
+				  __u16 key_id)
 {
 	struct sctp_authhdr auth_hdr;
 	struct sctp_hmac *hmac_desc;
@@ -1289,7 +1298,7 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc)
 		return NULL;
 
 	auth_hdr.hmac_id = htons(hmac_desc->hmac_id);
-	auth_hdr.shkey_id = htons(asoc->active_key_id);
+	auth_hdr.shkey_id = htons(key_id);
 
 	retval->subh.auth_hdr = sctp_addto_chunk(retval, sizeof(auth_hdr),
 						 &auth_hdr);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index eb7905ffe5f2..792e0e2be320 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -4114,6 +4114,7 @@ static enum sctp_ierror sctp_sf_authenticate(
 					const union sctp_subtype type,
 					struct sctp_chunk *chunk)
 {
+	struct sctp_shared_key *sh_key = NULL;
 	struct sctp_authhdr *auth_hdr;
 	__u8 *save_digest, *digest;
 	struct sctp_hmac *hmac;
@@ -4135,9 +4136,11 @@ static enum sctp_ierror sctp_sf_authenticate(
 	 * configured
 	 */
 	key_id = ntohs(auth_hdr->shkey_id);
-	if (key_id != asoc->active_key_id && !sctp_auth_get_shkey(asoc, key_id))
-		return SCTP_IERROR_AUTH_BAD_KEYID;
-
+	if (key_id != asoc->active_key_id) {
+		sh_key = sctp_auth_get_shkey(asoc, key_id);
+		if (!sh_key)
+			return SCTP_IERROR_AUTH_BAD_KEYID;
+	}
 
 	/* Make sure that the length of the signature matches what
 	 * we expect.
@@ -4166,7 +4169,7 @@ static enum sctp_ierror sctp_sf_authenticate(
 
 	sctp_auth_calculate_hmac(asoc, chunk->skb,
 				 (struct sctp_auth_chunk *)chunk->chunk_hdr,
-				 GFP_ATOMIC);
+				 sh_key, GFP_ATOMIC);
 
 	/* Discard the packet if the digests do not match */
 	if (memcmp(save_digest, digest, sig_len)) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index af5cf29b0c65..003a4ad89c01 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -156,6 +156,9 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 	/* The sndbuf space is tracked per association.  */
 	sctp_association_hold(asoc);
 
+	if (chunk->shkey)
+		sctp_auth_shkey_hold(chunk->shkey);
+
 	skb_set_owner_w(chunk->skb, sk);
 
 	chunk->skb->destructor = sctp_wfree;
@@ -8109,6 +8112,9 @@ static void sctp_wfree(struct sk_buff *skb)
 	sk->sk_wmem_queued   -= skb->truesize;
 	sk_mem_uncharge(sk, skb->truesize);
 
+	if (chunk->shkey)
+		sctp_auth_shkey_release(chunk->shkey);
+
 	sock_wfree(skb);
 	sctp_wake_up_waiters(sk, asoc);
 
-- 
cgit v1.2.3


From 3ff547c06a7d75d72d37dae2c064fcf0672e56c0 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 14 Mar 2018 19:05:31 +0800
Subject: sctp: add support for SCTP AUTH Information for sendmsg

This patch is to add support for SCTP AUTH Information for sendmsg,
as described in section 5.3.8 of RFC6458.

With this option, you can provide shared key identifier used for
sending the user message.

It's also a necessary send info for sctp_sendv.

Note that it reuses sinfo->sinfo_tsn to indicate if this option is
set and sinfo->sinfo_ssn to save the shkey ID which can be 0.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  1 +
 include/uapi/linux/sctp.h  | 14 +++++++++++++-
 net/sctp/chunk.c           | 11 ++++++++++-
 net/sctp/socket.c          | 23 +++++++++++++++++++++++
 4 files changed, 47 insertions(+), 2 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 49ad67bbdbb5..012fb3e2f4cf 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2118,6 +2118,7 @@ struct sctp_cmsgs {
 	struct sctp_sndrcvinfo *srinfo;
 	struct sctp_sndinfo *sinfo;
 	struct sctp_prinfo *prinfo;
+	struct sctp_authinfo *authinfo;
 	struct msghdr *addrs_msg;
 };
 
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index e94b6d297ad9..47e781ebde05 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -273,6 +273,18 @@ struct sctp_prinfo {
 	__u32 pr_value;
 };
 
+/* 5.3.8 SCTP AUTH Information Structure (SCTP_AUTHINFO)
+ *
+ *   This cmsghdr structure specifies SCTP options for sendmsg().
+ *
+ *   cmsg_level    cmsg_type      cmsg_data[]
+ *   ------------  ------------   -------------------
+ *   IPPROTO_SCTP  SCTP_AUTHINFO  struct sctp_authinfo
+ */
+struct sctp_authinfo {
+	__u16 auth_keynumber;
+};
+
 /*
  *  sinfo_flags: 16 bits (unsigned integer)
  *
@@ -310,7 +322,7 @@ typedef enum sctp_cmsg_type {
 #define SCTP_NXTINFO	SCTP_NXTINFO
 	SCTP_PRINFO,		/* 5.3.7 SCTP PR-SCTP Information Structure */
 #define SCTP_PRINFO	SCTP_PRINFO
-	SCTP_AUTHINFO,		/* 5.3.8 SCTP AUTH Information Structure (RESERVED) */
+	SCTP_AUTHINFO,		/* 5.3.8 SCTP AUTH Information Structure */
 #define SCTP_AUTHINFO	SCTP_AUTHINFO
 	SCTP_DSTADDRV4,		/* 5.3.9 SCTP Destination IPv4 Address Structure */
 #define SCTP_DSTADDRV4	SCTP_DSTADDRV4
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 9f28a9aae976..f889a84f264d 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -206,7 +206,16 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 			max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) +
 					      hmac_desc->hmac_len);
 
-		shkey = asoc->shkey;
+		if (sinfo->sinfo_tsn &&
+		    sinfo->sinfo_ssn != asoc->active_key_id) {
+			shkey = sctp_auth_get_shkey(asoc, sinfo->sinfo_ssn);
+			if (!shkey) {
+				err = -EINVAL;
+				goto errout;
+			}
+		} else {
+			shkey = asoc->shkey;
+		}
 	}
 
 	/* Check what's our max considering the above */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 003a4ad89c01..9ffdecbc3531 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1987,6 +1987,14 @@ static void sctp_sendmsg_update_sinfo(struct sctp_association *asoc,
 
 	if (!cmsgs->srinfo && !cmsgs->prinfo)
 		sinfo->sinfo_timetolive = asoc->default_timetolive;
+
+	if (cmsgs->authinfo) {
+		/* Reuse sinfo_tsn to indicate that authinfo was set and
+		 * sinfo_ssn to save the keyid on tx path.
+		 */
+		sinfo->sinfo_tsn = 1;
+		sinfo->sinfo_ssn = cmsgs->authinfo->auth_keynumber;
+	}
 }
 
 static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
@@ -7874,6 +7882,21 @@ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs)
 			if (cmsgs->prinfo->pr_policy == SCTP_PR_SCTP_NONE)
 				cmsgs->prinfo->pr_value = 0;
 			break;
+		case SCTP_AUTHINFO:
+			/* SCTP Socket API Extension
+			 * 5.3.8 SCTP AUTH Information Structure (SCTP_AUTHINFO)
+			 *
+			 * This cmsghdr structure specifies SCTP options for sendmsg().
+			 *
+			 * cmsg_level    cmsg_type      cmsg_data[]
+			 * ------------  ------------   ---------------------
+			 * IPPROTO_SCTP  SCTP_AUTHINFO  struct sctp_authinfo
+			 */
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_authinfo)))
+				return -EINVAL;
+
+			cmsgs->authinfo = CMSG_DATA(cmsg);
+			break;
 		case SCTP_DSTADDRV4:
 		case SCTP_DSTADDRV6:
 			/* SCTP Socket API Extension
-- 
cgit v1.2.3


From 601590ec155aadf5daa17a6f63a06d1bba5b5ce9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 14 Mar 2018 19:05:32 +0800
Subject: sctp: add sockopt SCTP_AUTH_DEACTIVATE_KEY

This patch is to add sockopt SCTP_AUTH_DEACTIVATE_KEY, as described in
section 8.3.4 of RFC6458.

This set option indicates that the application will no longer send user
messages using the indicated key identifier.

Note that RFC requires that only deactivated keys that are no longer used
by an association can be deleted, but for the backward compatibility, it
is not to check deactivated when deleting or replacing one sh_key.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/auth.h   | 12 ++++++------
 include/uapi/linux/sctp.h |  1 +
 net/sctp/auth.c           | 46 +++++++++++++++++++++++++++++++++++++++++++---
 net/sctp/socket.c         | 31 +++++++++++++++++++++++++++++++
 4 files changed, 81 insertions(+), 9 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h
index 017c1aa3a2c9..687e7f80037d 100644
--- a/include/net/sctp/auth.h
+++ b/include/net/sctp/auth.h
@@ -65,6 +65,7 @@ struct sctp_shared_key {
 	struct sctp_auth_bytes *key;
 	refcount_t refcnt;
 	__u16 key_id;
+	__u8 deactivated;
 };
 
 #define key_for_each(__key, __list_head) \
@@ -113,14 +114,13 @@ void sctp_auth_shkey_hold(struct sctp_shared_key *sh_key);
 int sctp_auth_ep_add_chunkid(struct sctp_endpoint *ep, __u8 chunk_id);
 int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
 			    struct sctp_hmacalgo *hmacs);
-int sctp_auth_set_key(struct sctp_endpoint *ep,
-		      struct sctp_association *asoc,
+int sctp_auth_set_key(struct sctp_endpoint *ep, struct sctp_association *asoc,
 		      struct sctp_authkey *auth_key);
 int sctp_auth_set_active_key(struct sctp_endpoint *ep,
-		      struct sctp_association *asoc,
-		      __u16 key_id);
+			     struct sctp_association *asoc, __u16 key_id);
 int sctp_auth_del_key_id(struct sctp_endpoint *ep,
-		      struct sctp_association *asoc,
-		      __u16 key_id);
+			 struct sctp_association *asoc, __u16 key_id);
+int sctp_auth_deact_key_id(struct sctp_endpoint *ep,
+			   struct sctp_association *asoc, __u16 key_id);
 
 #endif
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 47e781ebde05..08fc313829f4 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -99,6 +99,7 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_RECVRCVINFO	32
 #define SCTP_RECVNXTINFO	33
 #define SCTP_DEFAULT_SNDINFO	34
+#define SCTP_AUTH_DEACTIVATE_KEY	35
 
 /* Internal Socket Options. Some of the sctp library functions are
  * implemented using these socket options.
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index e5214fd7f650..a073123fc485 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -449,8 +449,11 @@ struct sctp_shared_key *sctp_auth_get_shkey(
 
 	/* First search associations set of endpoint pair shared keys */
 	key_for_each(key, &asoc->endpoint_shared_keys) {
-		if (key->key_id == key_id)
-			return key;
+		if (key->key_id == key_id) {
+			if (!key->deactivated)
+				return key;
+			break;
+		}
 	}
 
 	return NULL;
@@ -905,7 +908,7 @@ int sctp_auth_set_active_key(struct sctp_endpoint *ep,
 		}
 	}
 
-	if (!found)
+	if (!found || key->deactivated)
 		return -EINVAL;
 
 	if (asoc) {
@@ -956,3 +959,40 @@ int sctp_auth_del_key_id(struct sctp_endpoint *ep,
 
 	return 0;
 }
+
+int sctp_auth_deact_key_id(struct sctp_endpoint *ep,
+			   struct sctp_association *asoc, __u16  key_id)
+{
+	struct sctp_shared_key *key;
+	struct list_head *sh_keys;
+	int found = 0;
+
+	/* The key identifier MUST NOT be the current active key
+	 * The key identifier MUST correst to an existing key
+	 */
+	if (asoc) {
+		if (asoc->active_key_id == key_id)
+			return -EINVAL;
+
+		sh_keys = &asoc->endpoint_shared_keys;
+	} else {
+		if (ep->active_key_id == key_id)
+			return -EINVAL;
+
+		sh_keys = &ep->endpoint_shared_keys;
+	}
+
+	key_for_each(key, sh_keys) {
+		if (key->key_id == key_id) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return -EINVAL;
+
+	key->deactivated = 1;
+
+	return 0;
+}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9ffdecbc3531..65cc354c520f 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3646,6 +3646,33 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 
 }
 
+/*
+ * 8.3.4  Deactivate a Shared Key (SCTP_AUTH_DEACTIVATE_KEY)
+ *
+ * This set option will deactivate a shared secret key.
+ */
+static int sctp_setsockopt_deactivate_key(struct sock *sk, char __user *optval,
+					  unsigned int optlen)
+{
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
+	struct sctp_authkeyid val;
+	struct sctp_association *asoc;
+
+	if (!ep->auth_enable)
+		return -EACCES;
+
+	if (optlen != sizeof(struct sctp_authkeyid))
+		return -EINVAL;
+	if (copy_from_user(&val, optval, optlen))
+		return -EFAULT;
+
+	asoc = sctp_id2assoc(sk, val.scact_assoc_id);
+	if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
+		return -EINVAL;
+
+	return sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber);
+}
+
 /*
  * 8.1.23 SCTP_AUTO_ASCONF
  *
@@ -4238,6 +4265,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_AUTH_DELETE_KEY:
 		retval = sctp_setsockopt_del_key(sk, optval, optlen);
 		break;
+	case SCTP_AUTH_DEACTIVATE_KEY:
+		retval = sctp_setsockopt_deactivate_key(sk, optval, optlen);
+		break;
 	case SCTP_AUTO_ASCONF:
 		retval = sctp_setsockopt_auto_asconf(sk, optval, optlen);
 		break;
@@ -7212,6 +7242,7 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_AUTH_KEY:
 	case SCTP_AUTH_CHUNK:
 	case SCTP_AUTH_DELETE_KEY:
+	case SCTP_AUTH_DEACTIVATE_KEY:
 		retval = -EOPNOTSUPP;
 		break;
 	case SCTP_HMAC_IDENT:
-- 
cgit v1.2.3


From 30f6ebf65bc46161c5aaff1db2e6e7c76aa4a06b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 14 Mar 2018 19:05:34 +0800
Subject: sctp: add SCTP_AUTH_NO_AUTH type for AUTHENTICATION_EVENT

This patch is to add SCTP_AUTH_NO_AUTH type for AUTHENTICATION_EVENT,
as described in section 6.1.8 of RFC6458.

      SCTP_AUTH_NO_AUTH:  This report indicates that the peer does not
         support SCTP authentication as defined in [RFC4895].

Note that the implementation is quite similar as that of
SCTP_ADAPTATION_INDICATION.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/command.h |  1 +
 include/uapi/linux/sctp.h  |  1 +
 net/sctp/sm_sideeffect.c   | 13 +++++++++++++
 net/sctp/sm_statefuns.c    | 43 +++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 56 insertions(+), 2 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index b55c6a48a206..6640f84fe536 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -100,6 +100,7 @@ enum sctp_verb {
 	SCTP_CMD_SET_SK_ERR,	 /* Set sk_err */
 	SCTP_CMD_ASSOC_CHANGE,	 /* generate and send assoc_change event */
 	SCTP_CMD_ADAPTATION_IND, /* generate and send adaptation event */
+	SCTP_CMD_PEER_NO_AUTH,   /* generate and send authentication event */
 	SCTP_CMD_ASSOC_SHKEY,    /* generate the association shared keys */
 	SCTP_CMD_T1_RETRAN,	 /* Mark for retransmission after T1 timeout  */
 	SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 18ebbfeee4af..afd4346386e0 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -522,6 +522,7 @@ enum {
 	SCTP_AUTH_NEW_KEY,
 #define	SCTP_AUTH_NEWKEY	SCTP_AUTH_NEW_KEY /* compatible with before */
 	SCTP_AUTH_FREE_KEY,
+	SCTP_AUTH_NO_AUTH,
 };
 
 /*
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index b71e7fb0a20a..298112ca8c06 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1049,6 +1049,16 @@ static void sctp_cmd_assoc_change(struct sctp_cmd_seq *commands,
 		asoc->stream.si->enqueue_event(&asoc->ulpq, ev);
 }
 
+static void sctp_cmd_peer_no_auth(struct sctp_cmd_seq *commands,
+				  struct sctp_association *asoc)
+{
+	struct sctp_ulpevent *ev;
+
+	ev = sctp_ulpevent_make_authkey(asoc, 0, SCTP_AUTH_NO_AUTH, GFP_ATOMIC);
+	if (ev)
+		asoc->stream.si->enqueue_event(&asoc->ulpq, ev);
+}
+
 /* Helper function to generate an adaptation indication event */
 static void sctp_cmd_adaptation_ind(struct sctp_cmd_seq *commands,
 				    struct sctp_association *asoc)
@@ -1755,6 +1765,9 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 		case SCTP_CMD_ADAPTATION_IND:
 			sctp_cmd_adaptation_ind(commands, asoc);
 			break;
+		case SCTP_CMD_PEER_NO_AUTH:
+			sctp_cmd_peer_no_auth(commands, asoc);
+			break;
 
 		case SCTP_CMD_ASSOC_SHKEY:
 			error = sctp_auth_asoc_init_active_key(asoc,
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 1e41dee70b51..cc56a67dbb4d 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -659,7 +659,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 					 void *arg,
 					 struct sctp_cmd_seq *commands)
 {
-	struct sctp_ulpevent *ev, *ai_ev = NULL;
+	struct sctp_ulpevent *ev, *ai_ev = NULL, *auth_ev = NULL;
 	struct sctp_association *new_asoc;
 	struct sctp_init_chunk *peer_init;
 	struct sctp_chunk *chunk = arg;
@@ -820,6 +820,14 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 			goto nomem_aiev;
 	}
 
+	if (!new_asoc->peer.auth_capable) {
+		auth_ev = sctp_ulpevent_make_authkey(new_asoc, 0,
+						     SCTP_AUTH_NO_AUTH,
+						     GFP_ATOMIC);
+		if (!auth_ev)
+			goto nomem_authev;
+	}
+
 	/* Add all the state machine commands now since we've created
 	 * everything.  This way we don't introduce memory corruptions
 	 * during side-effect processing and correclty count established
@@ -847,8 +855,14 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 		sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
 				SCTP_ULPEVENT(ai_ev));
 
+	if (auth_ev)
+		sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
+				SCTP_ULPEVENT(auth_ev));
+
 	return SCTP_DISPOSITION_CONSUME;
 
+nomem_authev:
+	sctp_ulpevent_free(ai_ev);
 nomem_aiev:
 	sctp_ulpevent_free(ev);
 nomem_ev:
@@ -953,6 +967,15 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net,
 				SCTP_ULPEVENT(ev));
 	}
 
+	if (!asoc->peer.auth_capable) {
+		ev = sctp_ulpevent_make_authkey(asoc, 0, SCTP_AUTH_NO_AUTH,
+						GFP_ATOMIC);
+		if (!ev)
+			goto nomem;
+		sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
+				SCTP_ULPEVENT(ev));
+	}
+
 	return SCTP_DISPOSITION_CONSUME;
 nomem:
 	return SCTP_DISPOSITION_NOMEM;
@@ -1908,6 +1931,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_b(
 	if (asoc->peer.adaptation_ind)
 		sctp_add_cmd_sf(commands, SCTP_CMD_ADAPTATION_IND, SCTP_NULL());
 
+	if (!asoc->peer.auth_capable)
+		sctp_add_cmd_sf(commands, SCTP_CMD_PEER_NO_AUTH, SCTP_NULL());
+
 	return SCTP_DISPOSITION_CONSUME;
 
 nomem:
@@ -1954,7 +1980,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 					struct sctp_cmd_seq *commands,
 					struct sctp_association *new_asoc)
 {
-	struct sctp_ulpevent *ev = NULL, *ai_ev = NULL;
+	struct sctp_ulpevent *ev = NULL, *ai_ev = NULL, *auth_ev = NULL;
 	struct sctp_chunk *repl;
 
 	/* Clarification from Implementor's Guide:
@@ -2001,6 +2027,14 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 				goto nomem;
 
 		}
+
+		if (!asoc->peer.auth_capable) {
+			auth_ev = sctp_ulpevent_make_authkey(asoc, 0,
+							     SCTP_AUTH_NO_AUTH,
+							     GFP_ATOMIC);
+			if (!auth_ev)
+				goto nomem;
+		}
 	}
 
 	repl = sctp_make_cookie_ack(new_asoc, chunk);
@@ -2015,10 +2049,15 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 	if (ai_ev)
 		sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
 					SCTP_ULPEVENT(ai_ev));
+	if (auth_ev)
+		sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
+				SCTP_ULPEVENT(auth_ev));
 
 	return SCTP_DISPOSITION_CONSUME;
 
 nomem:
+	if (auth_ev)
+		sctp_ulpevent_free(auth_ev);
 	if (ai_ev)
 		sctp_ulpevent_free(ai_ev);
 	if (ev)
-- 
cgit v1.2.3


From 232378e8db4780bc7145d7a0ee47f5f80a41ad6b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 13 Mar 2018 08:29:37 -0700
Subject: net/ipv6: Change address check to always take a device argument

ipv6_chk_addr_and_flags determines if an address is a local address and
optionally if it is an address on a specific device. For example, it is
called by ip6_route_info_create to determine if a given gateway address
is a local address. The address check currently does not consider L3
domains and as a result does not allow a route to be added in one VRF
if the nexthop points to an address in a second VRF. e.g.,

    $ ip route add 2001:db8:1::/64 vrf r2 via 2001:db8:102::23
    Error: Invalid gateway address.

where 2001:db8:102::23 is an address on an interface in vrf r1.

ipv6_chk_addr_and_flags needs to allow callers to always pass in a device
with a separate argument to not limit the address to the specific device.
The device is used used to determine the L3 domain of interest.

To that end add an argument to skip the device check and update callers
to always pass a device where possible and use the new argument to mean
any address in the domain.

Update a handful of users of ipv6_chk_addr with a NULL dev argument. This
patch handles the change to these callers without adding the domain check.

ip6_validate_gw needs to handle 2 cases - one where the device is given
as part of the nexthop spec and the other where the device is resolved.
There is at least 1 VRF case where deferring the check to only after
the route lookup has resolved the device fails with an unintuitive error
"RTNETLINK answers: No route to host" as opposed to the preferred
"Error: Gateway can not be a local address." The 'no route to host'
error is because of the fallback to a full lookup. The check is done
twice to avoid this error.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  4 ++--
 net/ipv6/addrconf.c    | 11 ++++++++---
 net/ipv6/anycast.c     |  9 ++++++---
 net/ipv6/datagram.c    |  5 +++--
 net/ipv6/ip6_tunnel.c  | 12 ++++++++----
 net/ipv6/ndisc.c       |  2 +-
 net/ipv6/route.c       | 19 +++++++++++++++----
 7 files changed, 43 insertions(+), 19 deletions(-)

(limited to 'include/net')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index c4185a7b0e90..132e5b95167a 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -69,8 +69,8 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg);
 int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		  const struct net_device *dev, int strict);
 int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
-			    const struct net_device *dev, int strict,
-			    u32 banned_flags);
+			    const struct net_device *dev, bool skip_dev_check,
+			    int strict, u32 banned_flags);
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b5fd116c046a..0677b9732d56 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1851,19 +1851,24 @@ static int ipv6_count_addresses(const struct inet6_dev *idev)
 int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		  const struct net_device *dev, int strict)
 {
-	return ipv6_chk_addr_and_flags(net, addr, dev, strict, IFA_F_TENTATIVE);
+	return ipv6_chk_addr_and_flags(net, addr, dev, !dev,
+				       strict, IFA_F_TENTATIVE);
 }
 EXPORT_SYMBOL(ipv6_chk_addr);
 
 int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
-			    const struct net_device *dev, int strict,
-			    u32 banned_flags)
+			    const struct net_device *dev, bool skip_dev_check,
+			    int strict, u32 banned_flags)
 {
 	unsigned int hash = inet6_addr_hash(net, addr);
 	struct inet6_ifaddr *ifp;
 	u32 ifp_flags;
 
 	rcu_read_lock();
+
+	if (skip_dev_check)
+		dev = NULL;
+
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index c61718dba2e6..d580d4d456a5 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -66,7 +66,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		return -EPERM;
 	if (ipv6_addr_is_multicast(addr))
 		return -EINVAL;
-	if (ipv6_chk_addr(net, addr, NULL, 0))
+
+	if (ifindex)
+		dev = __dev_get_by_index(net, ifindex);
+
+	if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE))
 		return -EINVAL;
 
 	pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL);
@@ -90,8 +94,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			dev = __dev_get_by_flags(net, IFF_UP,
 						 IFF_UP | IFF_LOOPBACK);
 		}
-	} else
-		dev = __dev_get_by_index(net, ifindex);
+	}
 
 	if (!dev) {
 		err = -ENODEV;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index fbf08ce3f5ab..b27333d7b099 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -801,8 +801,9 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			if (addr_type != IPV6_ADDR_ANY) {
 				int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
 				if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
-				    !ipv6_chk_addr(net, &src_info->ipi6_addr,
-						   strict ? dev : NULL, 0) &&
+				    !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr,
+							     dev, !strict, 0,
+							     IFA_F_TENTATIVE) &&
 				    !ipv6_chk_acast_addr_src(net, dev,
 							     &src_info->ipi6_addr))
 					err = -EINVAL;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5c045fa407da..456fcf942f95 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -758,9 +758,11 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
 			ldev = dev_get_by_index_rcu(net, p->link);
 
 		if ((ipv6_addr_is_multicast(laddr) ||
-		     likely(ipv6_chk_addr(net, laddr, ldev, 0))) &&
+		     likely(ipv6_chk_addr_and_flags(net, laddr, ldev, false,
+						    0, IFA_F_TENTATIVE))) &&
 		    ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) ||
-		     likely(!ipv6_chk_addr(net, raddr, NULL, 0))))
+		     likely(!ipv6_chk_addr_and_flags(net, raddr, ldev, true,
+						     0, IFA_F_TENTATIVE))))
 			ret = 1;
 	}
 	return ret;
@@ -990,12 +992,14 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t,
 		if (p->link)
 			ldev = dev_get_by_index_rcu(net, p->link);
 
-		if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0)))
+		if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false,
+						      0, IFA_F_TENTATIVE)))
 			pr_warn("%s xmit: Local address not yet configured!\n",
 				p->name);
 		else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) &&
 			 !ipv6_addr_is_multicast(raddr) &&
-			 unlikely(ipv6_chk_addr(net, raddr, NULL, 0)))
+			 unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev,
+							  true, 0, IFA_F_TENTATIVE)))
 			pr_warn("%s xmit: Routing loop! Remote address found on this node!\n",
 				p->name);
 		else
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 8af5eef464c1..10024eb0c521 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -707,7 +707,7 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
 	int probes = atomic_read(&neigh->probes);
 
 	if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr,
-					   dev, 1,
+					   dev, false, 1,
 					   IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))
 		saddr = &ipv6_hdr(skb)->saddr;
 	probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 23ced851fdb1..939d122e71b4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2632,7 +2632,9 @@ static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
 {
 	const struct in6_addr *gw_addr = &cfg->fc_gateway;
 	int gwa_type = ipv6_addr_type(gw_addr);
+	bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true;
 	const struct net_device *dev = *_dev;
+	bool need_addr_check = !dev;
 	int err = -EINVAL;
 
 	/* if gw_addr is local we will fail to detect this in case
@@ -2640,10 +2642,9 @@ static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
 	 * will return already-added prefix route via interface that
 	 * prefix route was assigned to, which might be non-loopback.
 	 */
-	if (ipv6_chk_addr_and_flags(net, gw_addr,
-				    gwa_type & IPV6_ADDR_LINKLOCAL ?
-				    dev : NULL, 0, 0)) {
-		NL_SET_ERR_MSG(extack, "Invalid gateway address");
+	if (dev &&
+	    ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) {
+		NL_SET_ERR_MSG(extack, "Gateway can not be a local address");
 		goto out;
 	}
 
@@ -2683,6 +2684,16 @@ static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
 			       "Egress device can not be loopback device for this route");
 		goto out;
 	}
+
+	/* if we did not check gw_addr above, do so now that the
+	 * egress device has been resolved.
+	 */
+	if (need_addr_check &&
+	    ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) {
+		NL_SET_ERR_MSG(extack, "Gateway can not be a local address");
+		goto out;
+	}
+
 	err = 0;
 out:
 	return err;
-- 
cgit v1.2.3


From 1e8029515816f771b9b3751f24f19fe6df4c72ae Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Tue, 13 Mar 2018 21:57:16 -0700
Subject: udp: Move the udp sysctl to namespace.

This patch moves the udp_rmem_min, udp_wmem_min
to namespace and init the udp_l3mdev_accept explicitly.

The udp_rmem_min/udp_wmem_min affect udp rx/tx queue,
with this patch namespaces can set them differently.

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h   |  3 ++
 net/ipv4/sysctl_net_ipv4.c | 32 ++++++++---------
 net/ipv4/udp.c             | 86 +++++++++++++++++++++++++++-------------------
 net/ipv6/udp.c             | 52 ++++++++++++++--------------
 4 files changed, 96 insertions(+), 77 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 3a970e429ab6..382bfd7583cf 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -168,6 +168,9 @@ struct netns_ipv4 {
 	atomic_t tfo_active_disable_times;
 	unsigned long tfo_active_disable_stamp;
 
+	int sysctl_udp_wmem_min;
+	int sysctl_udp_rmem_min;
+
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	int sysctl_udp_l3mdev_accept;
 #endif
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 011de9a20ec6..5b72d97693f8 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -520,22 +520,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
-	{
-		.procname	= "udp_rmem_min",
-		.data		= &sysctl_udp_rmem_min,
-		.maxlen		= sizeof(sysctl_udp_rmem_min),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one
-	},
-	{
-		.procname	= "udp_wmem_min",
-		.data		= &sysctl_udp_wmem_min,
-		.maxlen		= sizeof(sysctl_udp_wmem_min),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one
-	},
 	{ }
 };
 
@@ -1167,6 +1151,22 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &one,
 	},
+	{
+		.procname	= "udp_rmem_min",
+		.data		= &init_net.ipv4.sysctl_udp_rmem_min,
+		.maxlen		= sizeof(init_net.ipv4.sysctl_udp_rmem_min),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one
+	},
+	{
+		.procname	= "udp_wmem_min",
+		.data		= &init_net.ipv4.sysctl_udp_wmem_min,
+		.maxlen		= sizeof(init_net.ipv4.sysctl_udp_wmem_min),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one
+	},
 	{ }
 };
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3013404d0935..908fc02fb4f8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -122,12 +122,6 @@ EXPORT_SYMBOL(udp_table);
 long sysctl_udp_mem[3] __read_mostly;
 EXPORT_SYMBOL(sysctl_udp_mem);
 
-int sysctl_udp_rmem_min __read_mostly;
-EXPORT_SYMBOL(sysctl_udp_rmem_min);
-
-int sysctl_udp_wmem_min __read_mostly;
-EXPORT_SYMBOL(sysctl_udp_wmem_min);
-
 atomic_long_t udp_memory_allocated;
 EXPORT_SYMBOL(udp_memory_allocated);
 
@@ -2533,35 +2527,35 @@ int udp_abort(struct sock *sk, int err)
 EXPORT_SYMBOL_GPL(udp_abort);
 
 struct proto udp_prot = {
-	.name		   = "UDP",
-	.owner		   = THIS_MODULE,
-	.close		   = udp_lib_close,
-	.connect	   = ip4_datagram_connect,
-	.disconnect	   = udp_disconnect,
-	.ioctl		   = udp_ioctl,
-	.init		   = udp_init_sock,
-	.destroy	   = udp_destroy_sock,
-	.setsockopt	   = udp_setsockopt,
-	.getsockopt	   = udp_getsockopt,
-	.sendmsg	   = udp_sendmsg,
-	.recvmsg	   = udp_recvmsg,
-	.sendpage	   = udp_sendpage,
-	.release_cb	   = ip4_datagram_release_cb,
-	.hash		   = udp_lib_hash,
-	.unhash		   = udp_lib_unhash,
-	.rehash		   = udp_v4_rehash,
-	.get_port	   = udp_v4_get_port,
-	.memory_allocated  = &udp_memory_allocated,
-	.sysctl_mem	   = sysctl_udp_mem,
-	.sysctl_wmem	   = &sysctl_udp_wmem_min,
-	.sysctl_rmem	   = &sysctl_udp_rmem_min,
-	.obj_size	   = sizeof(struct udp_sock),
-	.h.udp_table	   = &udp_table,
+	.name			= "UDP",
+	.owner			= THIS_MODULE,
+	.close			= udp_lib_close,
+	.connect		= ip4_datagram_connect,
+	.disconnect		= udp_disconnect,
+	.ioctl			= udp_ioctl,
+	.init			= udp_init_sock,
+	.destroy		= udp_destroy_sock,
+	.setsockopt		= udp_setsockopt,
+	.getsockopt		= udp_getsockopt,
+	.sendmsg		= udp_sendmsg,
+	.recvmsg		= udp_recvmsg,
+	.sendpage		= udp_sendpage,
+	.release_cb		= ip4_datagram_release_cb,
+	.hash			= udp_lib_hash,
+	.unhash			= udp_lib_unhash,
+	.rehash			= udp_v4_rehash,
+	.get_port		= udp_v4_get_port,
+	.memory_allocated	= &udp_memory_allocated,
+	.sysctl_mem		= sysctl_udp_mem,
+	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_udp_wmem_min),
+	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_udp_rmem_min),
+	.obj_size		= sizeof(struct udp_sock),
+	.h.udp_table		= &udp_table,
 #ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_udp_setsockopt,
-	.compat_getsockopt = compat_udp_getsockopt,
+	.compat_setsockopt	= compat_udp_setsockopt,
+	.compat_getsockopt	= compat_udp_getsockopt,
 #endif
-	.diag_destroy	   = udp_abort,
+	.diag_destroy		= udp_abort,
 };
 EXPORT_SYMBOL(udp_prot);
 
@@ -2831,6 +2825,26 @@ u32 udp_flow_hashrnd(void)
 }
 EXPORT_SYMBOL(udp_flow_hashrnd);
 
+static void __udp_sysctl_init(struct net *net)
+{
+	net->ipv4.sysctl_udp_rmem_min = SK_MEM_QUANTUM;
+	net->ipv4.sysctl_udp_wmem_min = SK_MEM_QUANTUM;
+
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	net->ipv4.sysctl_udp_l3mdev_accept = 0;
+#endif
+}
+
+static int __net_init udp_sysctl_init(struct net *net)
+{
+	__udp_sysctl_init(net);
+	return 0;
+}
+
+static struct pernet_operations __net_initdata udp_sysctl_ops = {
+	.init       = udp_sysctl_init,
+};
+
 void __init udp_init(void)
 {
 	unsigned long limit;
@@ -2843,8 +2857,7 @@ void __init udp_init(void)
 	sysctl_udp_mem[1] = limit;
 	sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2;
 
-	sysctl_udp_rmem_min = SK_MEM_QUANTUM;
-	sysctl_udp_wmem_min = SK_MEM_QUANTUM;
+	__udp_sysctl_init(&init_net);
 
 	/* 16 spinlocks per cpu */
 	udp_busylocks_log = ilog2(nr_cpu_ids) + 4;
@@ -2854,4 +2867,7 @@ void __init udp_init(void)
 		panic("UDP: failed to alloc udp_busylocks\n");
 	for (i = 0; i < (1U << udp_busylocks_log); i++)
 		spin_lock_init(udp_busylocks + i);
+
+	if (register_pernet_subsys(&udp_sysctl_ops))
+		panic("UDP: failed to init sysctl parameters.\n");
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 52e3ea0e6f50..ad30f5e31969 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1509,34 +1509,34 @@ void udp6_proc_exit(struct net *net)
 /* ------------------------------------------------------------------------ */
 
 struct proto udpv6_prot = {
-	.name		   = "UDPv6",
-	.owner		   = THIS_MODULE,
-	.close		   = udp_lib_close,
-	.connect	   = ip6_datagram_connect,
-	.disconnect	   = udp_disconnect,
-	.ioctl		   = udp_ioctl,
-	.init		   = udp_init_sock,
-	.destroy	   = udpv6_destroy_sock,
-	.setsockopt	   = udpv6_setsockopt,
-	.getsockopt	   = udpv6_getsockopt,
-	.sendmsg	   = udpv6_sendmsg,
-	.recvmsg	   = udpv6_recvmsg,
-	.release_cb	   = ip6_datagram_release_cb,
-	.hash		   = udp_lib_hash,
-	.unhash		   = udp_lib_unhash,
-	.rehash		   = udp_v6_rehash,
-	.get_port	   = udp_v6_get_port,
-	.memory_allocated  = &udp_memory_allocated,
-	.sysctl_mem	   = sysctl_udp_mem,
-	.sysctl_wmem	   = &sysctl_udp_wmem_min,
-	.sysctl_rmem	   = &sysctl_udp_rmem_min,
-	.obj_size	   = sizeof(struct udp6_sock),
-	.h.udp_table	   = &udp_table,
+	.name			= "UDPv6",
+	.owner			= THIS_MODULE,
+	.close			= udp_lib_close,
+	.connect		= ip6_datagram_connect,
+	.disconnect		= udp_disconnect,
+	.ioctl			= udp_ioctl,
+	.init			= udp_init_sock,
+	.destroy		= udpv6_destroy_sock,
+	.setsockopt		= udpv6_setsockopt,
+	.getsockopt		= udpv6_getsockopt,
+	.sendmsg		= udpv6_sendmsg,
+	.recvmsg		= udpv6_recvmsg,
+	.release_cb		= ip6_datagram_release_cb,
+	.hash			= udp_lib_hash,
+	.unhash			= udp_lib_unhash,
+	.rehash			= udp_v6_rehash,
+	.get_port		= udp_v6_get_port,
+	.memory_allocated	= &udp_memory_allocated,
+	.sysctl_mem		= sysctl_udp_mem,
+	.sysctl_wmem_offset     = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
+	.sysctl_rmem_offset     = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
+	.obj_size		= sizeof(struct udp6_sock),
+	.h.udp_table		= &udp_table,
 #ifdef CONFIG_COMPAT
-	.compat_setsockopt = compat_udpv6_setsockopt,
-	.compat_getsockopt = compat_udpv6_getsockopt,
+	.compat_setsockopt	= compat_udpv6_setsockopt,
+	.compat_getsockopt	= compat_udpv6_getsockopt,
 #endif
-	.diag_destroy      = udp_abort,
+	.diag_destroy		= udp_abort,
 };
 
 static struct inet_protosw udpv6_protosw = {
-- 
cgit v1.2.3


From d47d08c8ca052df3d9fde7cfff518660335b16e7 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@ZenIV.linux.org.uk>
Date: Fri, 16 Mar 2018 23:32:51 +0000
Subject: sctp: use proc_remove_subtree()

use proc_remove_subtree() for subtree removal, both on setup failure
halfway through and on teardown.  No need to make simple things
complex...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 11 +-----
 net/sctp/objcnt.c       |  8 -----
 net/sctp/proc.c         | 90 ++++++++++++-------------------------------------
 net/sctp/protocol.c     | 59 ++++----------------------------
 4 files changed, 28 insertions(+), 140 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index f7ae6b0a21d0..72c5b8fc3232 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -180,14 +180,7 @@ struct sctp_transport *sctp_epaddr_lookup_transport(
 /*
  * sctp/proc.c
  */
-int sctp_snmp_proc_init(struct net *net);
-void sctp_snmp_proc_exit(struct net *net);
-int sctp_eps_proc_init(struct net *net);
-void sctp_eps_proc_exit(struct net *net);
-int sctp_assocs_proc_init(struct net *net);
-void sctp_assocs_proc_exit(struct net *net);
-int sctp_remaddr_proc_init(struct net *net);
-void sctp_remaddr_proc_exit(struct net *net);
+int __net_init sctp_proc_init(struct net *net);
 
 /*
  * sctp/offload.c
@@ -318,7 +311,6 @@ atomic_t sctp_dbg_objcnt_## name = ATOMIC_INIT(0)
 {.label= #name, .counter= &sctp_dbg_objcnt_## name}
 
 void sctp_dbg_objcnt_init(struct net *);
-void sctp_dbg_objcnt_exit(struct net *);
 
 #else
 
@@ -326,7 +318,6 @@ void sctp_dbg_objcnt_exit(struct net *);
 #define SCTP_DBG_OBJCNT_DEC(name)
 
 static inline void sctp_dbg_objcnt_init(struct net *net) { return; }
-static inline void sctp_dbg_objcnt_exit(struct net *net) { return; }
 
 #endif /* CONFIG_SCTP_DBG_OBJCOUNT */
 
diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c
index aeea6da81441..fd2684ad94c8 100644
--- a/net/sctp/objcnt.c
+++ b/net/sctp/objcnt.c
@@ -130,11 +130,3 @@ void sctp_dbg_objcnt_init(struct net *net)
 	if (!ent)
 		pr_warn("sctp_dbg_objcnt: Unable to create /proc entry.\n");
 }
-
-/* Cleanup the objcount entry in the proc filesystem.  */
-void sctp_dbg_objcnt_exit(struct net *net)
-{
-	remove_proc_entry("sctp_dbg_objcnt", net->sctp.proc_net_sctp);
-}
-
-
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 537545ebcb0e..17d0155d9de3 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -101,25 +101,6 @@ static const struct file_operations sctp_snmp_seq_fops = {
 	.release = single_release_net,
 };
 
-/* Set up the proc fs entry for 'snmp' object. */
-int __net_init sctp_snmp_proc_init(struct net *net)
-{
-	struct proc_dir_entry *p;
-
-	p = proc_create("snmp", S_IRUGO, net->sctp.proc_net_sctp,
-			&sctp_snmp_seq_fops);
-	if (!p)
-		return -ENOMEM;
-
-	return 0;
-}
-
-/* Cleanup the proc fs entry for 'snmp' object. */
-void sctp_snmp_proc_exit(struct net *net)
-{
-	remove_proc_entry("snmp", net->sctp.proc_net_sctp);
-}
-
 /* Dump local addresses of an association/endpoint. */
 static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_common *epb)
 {
@@ -259,25 +240,6 @@ static const struct file_operations sctp_eps_seq_fops = {
 	.release = seq_release_net,
 };
 
-/* Set up the proc fs entry for 'eps' object. */
-int __net_init sctp_eps_proc_init(struct net *net)
-{
-	struct proc_dir_entry *p;
-
-	p = proc_create("eps", S_IRUGO, net->sctp.proc_net_sctp,
-			&sctp_eps_seq_fops);
-	if (!p)
-		return -ENOMEM;
-
-	return 0;
-}
-
-/* Cleanup the proc fs entry for 'eps' object. */
-void sctp_eps_proc_exit(struct net *net)
-{
-	remove_proc_entry("eps", net->sctp.proc_net_sctp);
-}
-
 struct sctp_ht_iter {
 	struct seq_net_private p;
 	struct rhashtable_iter hti;
@@ -390,25 +352,6 @@ static const struct file_operations sctp_assocs_seq_fops = {
 	.release = seq_release_net,
 };
 
-/* Set up the proc fs entry for 'assocs' object. */
-int __net_init sctp_assocs_proc_init(struct net *net)
-{
-	struct proc_dir_entry *p;
-
-	p = proc_create("assocs", S_IRUGO, net->sctp.proc_net_sctp,
-			&sctp_assocs_seq_fops);
-	if (!p)
-		return -ENOMEM;
-
-	return 0;
-}
-
-/* Cleanup the proc fs entry for 'assocs' object. */
-void sctp_assocs_proc_exit(struct net *net)
-{
-	remove_proc_entry("assocs", net->sctp.proc_net_sctp);
-}
-
 static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 {
 	struct sctp_association *assoc;
@@ -488,12 +431,6 @@ static const struct seq_operations sctp_remaddr_ops = {
 	.show  = sctp_remaddr_seq_show,
 };
 
-/* Cleanup the proc fs entry for 'remaddr' object. */
-void sctp_remaddr_proc_exit(struct net *net)
-{
-	remove_proc_entry("remaddr", net->sctp.proc_net_sctp);
-}
-
 static int sctp_remaddr_seq_open(struct inode *inode, struct file *file)
 {
 	return seq_open_net(inode, file, &sctp_remaddr_ops,
@@ -507,13 +444,28 @@ static const struct file_operations sctp_remaddr_seq_fops = {
 	.release = seq_release_net,
 };
 
-int __net_init sctp_remaddr_proc_init(struct net *net)
+/* Set up the proc fs entry for the SCTP protocol. */
+int __net_init sctp_proc_init(struct net *net)
 {
-	struct proc_dir_entry *p;
-
-	p = proc_create("remaddr", S_IRUGO, net->sctp.proc_net_sctp,
-			&sctp_remaddr_seq_fops);
-	if (!p)
+	net->sctp.proc_net_sctp = proc_net_mkdir(net, "sctp", net->proc_net);
+	if (!net->sctp.proc_net_sctp)
 		return -ENOMEM;
+	if (!proc_create("snmp", S_IRUGO, net->sctp.proc_net_sctp,
+			&sctp_snmp_seq_fops))
+		goto cleanup;
+	if (!proc_create("eps", S_IRUGO, net->sctp.proc_net_sctp,
+			&sctp_eps_seq_fops))
+		goto cleanup;
+	if (!proc_create("assocs", S_IRUGO, net->sctp.proc_net_sctp,
+			&sctp_assocs_seq_fops))
+		goto cleanup;
+	if (!proc_create("remaddr", S_IRUGO, net->sctp.proc_net_sctp,
+			&sctp_remaddr_seq_fops))
+		goto cleanup;
 	return 0;
+
+cleanup:
+	remove_proc_subtree("sctp", net->proc_net);
+	net->sctp.proc_net_sctp = NULL;
+	return -ENOMEM;
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 606361ee9e4a..493b817f6a2a 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -80,56 +80,6 @@ long sysctl_sctp_mem[3];
 int sysctl_sctp_rmem[3];
 int sysctl_sctp_wmem[3];
 
-/* Set up the proc fs entry for the SCTP protocol. */
-static int __net_init sctp_proc_init(struct net *net)
-{
-#ifdef CONFIG_PROC_FS
-	net->sctp.proc_net_sctp = proc_net_mkdir(net, "sctp", net->proc_net);
-	if (!net->sctp.proc_net_sctp)
-		goto out_proc_net_sctp;
-	if (sctp_snmp_proc_init(net))
-		goto out_snmp_proc_init;
-	if (sctp_eps_proc_init(net))
-		goto out_eps_proc_init;
-	if (sctp_assocs_proc_init(net))
-		goto out_assocs_proc_init;
-	if (sctp_remaddr_proc_init(net))
-		goto out_remaddr_proc_init;
-
-	return 0;
-
-out_remaddr_proc_init:
-	sctp_assocs_proc_exit(net);
-out_assocs_proc_init:
-	sctp_eps_proc_exit(net);
-out_eps_proc_init:
-	sctp_snmp_proc_exit(net);
-out_snmp_proc_init:
-	remove_proc_entry("sctp", net->proc_net);
-	net->sctp.proc_net_sctp = NULL;
-out_proc_net_sctp:
-	return -ENOMEM;
-#endif /* CONFIG_PROC_FS */
-	return 0;
-}
-
-/* Clean up the proc fs entry for the SCTP protocol.
- * Note: Do not make this __exit as it is used in the init error
- * path.
- */
-static void sctp_proc_exit(struct net *net)
-{
-#ifdef CONFIG_PROC_FS
-	sctp_snmp_proc_exit(net);
-	sctp_eps_proc_exit(net);
-	sctp_assocs_proc_exit(net);
-	sctp_remaddr_proc_exit(net);
-
-	remove_proc_entry("sctp", net->proc_net);
-	net->sctp.proc_net_sctp = NULL;
-#endif
-}
-
 /* Private helper to extract ipv4 address and stash them in
  * the protocol structure.
  */
@@ -1285,10 +1235,12 @@ static int __net_init sctp_defaults_init(struct net *net)
 	if (status)
 		goto err_init_mibs;
 
+#ifdef CONFIG_PROC_FS
 	/* Initialize proc fs directory.  */
 	status = sctp_proc_init(net);
 	if (status)
 		goto err_init_proc;
+#endif
 
 	sctp_dbg_objcnt_init(net);
 
@@ -1320,9 +1272,10 @@ static void __net_exit sctp_defaults_exit(struct net *net)
 	sctp_free_addr_wq(net);
 	sctp_free_local_addr_list(net);
 
-	sctp_dbg_objcnt_exit(net);
-
-	sctp_proc_exit(net);
+#ifdef CONFIG_PROC_FS
+	remove_proc_subtree("sctp", net->proc_net);
+	net->sctp.proc_net_sctp = NULL;
+#endif
 	cleanup_sctp_mibs(net);
 	sctp_sysctl_net_unregister(net);
 }
-- 
cgit v1.2.3


From 2c3682f0be97a5f57c6c8b40fa154dfc77efb461 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 18 Mar 2018 12:56:49 -0700
Subject: sock: make static tls function alloc_sg generic sock helper

The TLS ULP module builds scatterlists from a sock using
page_frag_refill(). This is going to be useful for other ULPs
so move it into sock file for more general use.

In the process remove useless goto at end of while loop.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/sock.h |  4 ++++
 net/core/sock.c    | 56 ++++++++++++++++++++++++++++++++++++++++++++
 net/tls/tls_sw.c   | 69 ++++++------------------------------------------------
 3 files changed, 67 insertions(+), 62 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index b9624581d639..447150c51feb 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2141,6 +2141,10 @@ static inline struct page_frag *sk_page_frag(struct sock *sk)
 
 bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
 
+int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
+		int *sg_num_elem, unsigned int *sg_size,
+		int first_coalesce);
+
 /*
  *	Default write policy as shown to user space via poll/select/SIGIO
  */
diff --git a/net/core/sock.c b/net/core/sock.c
index 27f218bba43f..f68dff0d7bc4 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2239,6 +2239,62 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 }
 EXPORT_SYMBOL(sk_page_frag_refill);
 
+int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
+		int *sg_num_elem, unsigned int *sg_size,
+		int first_coalesce)
+{
+	struct page_frag *pfrag;
+	unsigned int size = *sg_size;
+	int num_elem = *sg_num_elem, use = 0, rc = 0;
+	struct scatterlist *sge;
+	unsigned int orig_offset;
+
+	len -= size;
+	pfrag = sk_page_frag(sk);
+
+	while (len > 0) {
+		if (!sk_page_frag_refill(sk, pfrag)) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		use = min_t(int, len, pfrag->size - pfrag->offset);
+
+		if (!sk_wmem_schedule(sk, use)) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		sk_mem_charge(sk, use);
+		size += use;
+		orig_offset = pfrag->offset;
+		pfrag->offset += use;
+
+		sge = sg + num_elem - 1;
+		if (num_elem > first_coalesce && sg_page(sg) == pfrag->page &&
+		    sg->offset + sg->length == orig_offset) {
+			sg->length += use;
+		} else {
+			sge++;
+			sg_unmark_end(sge);
+			sg_set_page(sge, pfrag->page, use, orig_offset);
+			get_page(pfrag->page);
+			++num_elem;
+			if (num_elem == MAX_SKB_FRAGS) {
+				rc = -ENOSPC;
+				break;
+			}
+		}
+
+		len -= use;
+	}
+out:
+	*sg_size = size;
+	*sg_num_elem = num_elem;
+	return rc;
+}
+EXPORT_SYMBOL(sk_alloc_sg);
+
 static void __lock_sock(struct sock *sk)
 	__releases(&sk->sk_lock.slock)
 	__acquires(&sk->sk_lock.slock)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f26376e954ae..0fc8a24c6473 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -87,71 +87,16 @@ static void trim_both_sgl(struct sock *sk, int target_size)
 		target_size);
 }
 
-static int alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
-		    int *sg_num_elem, unsigned int *sg_size,
-		    int first_coalesce)
-{
-	struct page_frag *pfrag;
-	unsigned int size = *sg_size;
-	int num_elem = *sg_num_elem, use = 0, rc = 0;
-	struct scatterlist *sge;
-	unsigned int orig_offset;
-
-	len -= size;
-	pfrag = sk_page_frag(sk);
-
-	while (len > 0) {
-		if (!sk_page_frag_refill(sk, pfrag)) {
-			rc = -ENOMEM;
-			goto out;
-		}
-
-		use = min_t(int, len, pfrag->size - pfrag->offset);
-
-		if (!sk_wmem_schedule(sk, use)) {
-			rc = -ENOMEM;
-			goto out;
-		}
-
-		sk_mem_charge(sk, use);
-		size += use;
-		orig_offset = pfrag->offset;
-		pfrag->offset += use;
-
-		sge = sg + num_elem - 1;
-		if (num_elem > first_coalesce && sg_page(sg) == pfrag->page &&
-		    sg->offset + sg->length == orig_offset) {
-			sg->length += use;
-		} else {
-			sge++;
-			sg_unmark_end(sge);
-			sg_set_page(sge, pfrag->page, use, orig_offset);
-			get_page(pfrag->page);
-			++num_elem;
-			if (num_elem == MAX_SKB_FRAGS) {
-				rc = -ENOSPC;
-				break;
-			}
-		}
-
-		len -= use;
-	}
-	goto out;
-
-out:
-	*sg_size = size;
-	*sg_num_elem = num_elem;
-	return rc;
-}
-
 static int alloc_encrypted_sg(struct sock *sk, int len)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 	int rc = 0;
 
-	rc = alloc_sg(sk, len, ctx->sg_encrypted_data,
-		      &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0);
+	rc = sk_alloc_sg(sk, len,
+			 ctx->sg_encrypted_data,
+			 &ctx->sg_encrypted_num_elem,
+			 &ctx->sg_encrypted_size, 0);
 
 	return rc;
 }
@@ -162,9 +107,9 @@ static int alloc_plaintext_sg(struct sock *sk, int len)
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 	int rc = 0;
 
-	rc = alloc_sg(sk, len, ctx->sg_plaintext_data,
-		      &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size,
-		      tls_ctx->pending_open_record_frags);
+	rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data,
+			 &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size,
+			 tls_ctx->pending_open_record_frags);
 
 	return rc;
 }
-- 
cgit v1.2.3


From 8c05dbf04b2882c3c0bc43fe7668c720210877f3 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 18 Mar 2018 12:57:05 -0700
Subject: net: generalize sk_alloc_sg to work with scatterlist rings

The current implementation of sk_alloc_sg expects scatterlist to always
start at entry 0 and complete at entry MAX_SKB_FRAGS.

Future patches will want to support starting at arbitrary offset into
scatterlist so add an additional sg_start parameters and then default
to the current values in TLS code paths.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/sock.h |  2 +-
 net/core/sock.c    | 27 ++++++++++++++++-----------
 net/tls/tls_sw.c   |  4 ++--
 3 files changed, 19 insertions(+), 14 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index 447150c51feb..b7c75e024e37 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2142,7 +2142,7 @@ static inline struct page_frag *sk_page_frag(struct sock *sk)
 bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
 
 int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
-		int *sg_num_elem, unsigned int *sg_size,
+		int sg_start, int *sg_curr, unsigned int *sg_size,
 		int first_coalesce);
 
 /*
diff --git a/net/core/sock.c b/net/core/sock.c
index f68dff0d7bc4..4f92c2910200 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2240,19 +2240,20 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 EXPORT_SYMBOL(sk_page_frag_refill);
 
 int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
-		int *sg_num_elem, unsigned int *sg_size,
+		int sg_start, int *sg_curr_index, unsigned int *sg_curr_size,
 		int first_coalesce)
 {
+	int sg_curr = *sg_curr_index, use = 0, rc = 0;
+	unsigned int size = *sg_curr_size;
 	struct page_frag *pfrag;
-	unsigned int size = *sg_size;
-	int num_elem = *sg_num_elem, use = 0, rc = 0;
 	struct scatterlist *sge;
-	unsigned int orig_offset;
 
 	len -= size;
 	pfrag = sk_page_frag(sk);
 
 	while (len > 0) {
+		unsigned int orig_offset;
+
 		if (!sk_page_frag_refill(sk, pfrag)) {
 			rc = -ENOMEM;
 			goto out;
@@ -2270,17 +2271,21 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
 		orig_offset = pfrag->offset;
 		pfrag->offset += use;
 
-		sge = sg + num_elem - 1;
-		if (num_elem > first_coalesce && sg_page(sg) == pfrag->page &&
+		sge = sg + sg_curr - 1;
+		if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
 		    sg->offset + sg->length == orig_offset) {
 			sg->length += use;
 		} else {
-			sge++;
+			sge = sg + sg_curr;
 			sg_unmark_end(sge);
 			sg_set_page(sge, pfrag->page, use, orig_offset);
 			get_page(pfrag->page);
-			++num_elem;
-			if (num_elem == MAX_SKB_FRAGS) {
+			sg_curr++;
+
+			if (sg_curr == MAX_SKB_FRAGS)
+				sg_curr = 0;
+
+			if (sg_curr == sg_start) {
 				rc = -ENOSPC;
 				break;
 			}
@@ -2289,8 +2294,8 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
 		len -= use;
 	}
 out:
-	*sg_size = size;
-	*sg_num_elem = num_elem;
+	*sg_curr_size = size;
+	*sg_curr_index = sg_curr;
 	return rc;
 }
 EXPORT_SYMBOL(sk_alloc_sg);
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 0fc8a24c6473..057a558ed6d7 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -94,7 +94,7 @@ static int alloc_encrypted_sg(struct sock *sk, int len)
 	int rc = 0;
 
 	rc = sk_alloc_sg(sk, len,
-			 ctx->sg_encrypted_data,
+			 ctx->sg_encrypted_data, 0,
 			 &ctx->sg_encrypted_num_elem,
 			 &ctx->sg_encrypted_size, 0);
 
@@ -107,7 +107,7 @@ static int alloc_plaintext_sg(struct sock *sk, int len)
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 	int rc = 0;
 
-	rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data,
+	rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data, 0,
 			 &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size,
 			 tls_ctx->pending_open_record_frags);
 
-- 
cgit v1.2.3


From 6aec208786c2a54cbf6135a0242b224e845bef98 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Sun, 4 Mar 2018 15:29:51 -0800
Subject: netfilter: Refactor nf_conncount

Remove parameter 'family' in nf_conncount_count() and count_tree().
It is because the parameter is not useful after commit 625c556118f3
("netfilter: connlimit: split xt_connlimit into front and backend").

Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_count.h | 1 -
 net/netfilter/nf_conncount.c               | 4 +---
 net/netfilter/xt_connlimit.c               | 4 ++--
 3 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index adf8db44cf86..e61184fbfb71 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -11,7 +11,6 @@ void nf_conncount_destroy(struct net *net, unsigned int family,
 unsigned int nf_conncount_count(struct net *net,
 				struct nf_conncount_data *data,
 				const u32 *key,
-				unsigned int family,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 #endif
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 6d65389e308f..9305a08b4422 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -158,7 +158,6 @@ static void tree_nodes_free(struct rb_root *root,
 static unsigned int
 count_tree(struct net *net, struct rb_root *root,
 	   const u32 *key, u8 keylen,
-	   u8 family,
 	   const struct nf_conntrack_tuple *tuple,
 	   const struct nf_conntrack_zone *zone)
 {
@@ -246,7 +245,6 @@ count_tree(struct net *net, struct rb_root *root,
 unsigned int nf_conncount_count(struct net *net,
 				struct nf_conncount_data *data,
 				const u32 *key,
-				unsigned int family,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone)
 {
@@ -259,7 +257,7 @@ unsigned int nf_conncount_count(struct net *net,
 
 	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
 
-	count = count_tree(net, root, key, data->keylen, family, tuple, zone);
+	count = count_tree(net, root, key, data->keylen, tuple, zone);
 
 	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
 
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index b1b17b9353e1..6275106ccf50 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -67,8 +67,8 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		key[1] = zone->id;
 	}
 
-	connections = nf_conncount_count(net, info->data, key,
-					 xt_family(par), tuple_ptr, zone);
+	connections = nf_conncount_count(net, info->data, key, tuple_ptr,
+					 zone);
 	if (connections == 0)
 		/* kmalloc failed, drop it entirely */
 		goto hotdrop;
-- 
cgit v1.2.3


From 94e5e3087a67c765be98592b36d8d187566478d5 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Mon, 19 Mar 2018 13:17:30 +0100
Subject: net: add uevent socket member

This commit adds struct uevent_sock to struct net. Since struct uevent_sock
records the position of the uevent socket in the uevent socket list we can
trivially remove it from the uevent socket list during cleanup. This speeds
up the old removal codepath.
Note, list_del() will hit __list_del_entry_valid() in its call chain which
will validate that the element is a member of the list. If it isn't it will
take care that the list is not modified.

Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h |  4 +++-
 lib/kobject_uevent.c        | 17 +++++++----------
 2 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include/net')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 71abc8d79178..09e30bdc7876 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -40,7 +40,7 @@ struct net_device;
 struct sock;
 struct ctl_table_header;
 struct net_generic;
-struct sock;
+struct uevent_sock;
 struct netns_ipvs;
 
 
@@ -83,6 +83,8 @@ struct net {
 	struct sock 		*rtnl;			/* rtnetlink socket */
 	struct sock		*genl_sock;
 
+	struct uevent_sock	*uevent_sock;		/* uevent socket */
+
 	struct list_head 	dev_base_head;
 	struct hlist_head 	*dev_name_head;
 	struct hlist_head	*dev_index_head;
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 9539d7ab3ea8..54cfbaeb3a4e 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -32,11 +32,13 @@ u64 uevent_seqnum;
 #ifdef CONFIG_UEVENT_HELPER
 char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH;
 #endif
-#ifdef CONFIG_NET
+
 struct uevent_sock {
 	struct list_head list;
 	struct sock *sk;
 };
+
+#ifdef CONFIG_NET
 static LIST_HEAD(uevent_sock_list);
 #endif
 
@@ -621,6 +623,9 @@ static int uevent_net_init(struct net *net)
 		kfree(ue_sk);
 		return -ENODEV;
 	}
+
+	net->uevent_sock = ue_sk;
+
 	mutex_lock(&uevent_sock_mutex);
 	list_add_tail(&ue_sk->list, &uevent_sock_list);
 	mutex_unlock(&uevent_sock_mutex);
@@ -629,17 +634,9 @@ static int uevent_net_init(struct net *net)
 
 static void uevent_net_exit(struct net *net)
 {
-	struct uevent_sock *ue_sk;
+	struct uevent_sock *ue_sk = net->uevent_sock;
 
 	mutex_lock(&uevent_sock_mutex);
-	list_for_each_entry(ue_sk, &uevent_sock_list, list) {
-		if (sock_net(ue_sk->sk) == net)
-			goto found;
-	}
-	mutex_unlock(&uevent_sock_mutex);
-	return;
-
-found:
 	list_del(&ue_sk->list);
 	mutex_unlock(&uevent_sock_mutex);
 
-- 
cgit v1.2.3


From 145307460ba9c11489807de7acd3f4c7395f60b7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 20 Mar 2018 19:31:14 -0700
Subject: devlink: Remove top_hierarchy arg to devlink_resource_register

top_hierarchy arg can be determined by comparing parent_resource_id to
DEVLINK_RESOURCE_ID_PARENT_TOP so it does not need to be a separate
argument.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c      | 9 ++++-----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c | 6 +++---
 include/net/devlink.h                               | 1 -
 net/core/devlink.c                                  | 4 +++-
 4 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/net')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index a120602bca26..83886a9df206 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3876,8 +3876,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 
 	kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE);
 	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD,
-					true, kvd_size,
-					MLXSW_SP_RESOURCE_KVD,
+					kvd_size, MLXSW_SP_RESOURCE_KVD,
 					DEVLINK_RESOURCE_ID_PARENT_TOP,
 					&kvd_size_params,
 					NULL);
@@ -3886,7 +3885,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 
 	linear_size = profile->kvd_linear_size;
 	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR,
-					false, linear_size,
+					linear_size,
 					MLXSW_SP_RESOURCE_KVD_LINEAR,
 					MLXSW_SP_RESOURCE_KVD,
 					&linear_size_params,
@@ -3904,7 +3903,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 		       profile->kvd_hash_single_parts;
 	double_size = rounddown(double_size, profile->kvd_hash_granularity);
 	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_HASH_DOUBLE,
-					false, double_size,
+					double_size,
 					MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE,
 					MLXSW_SP_RESOURCE_KVD,
 					&hash_double_size_params,
@@ -3914,7 +3913,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 
 	single_size = kvd_size - double_size - linear_size;
 	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_HASH_SINGLE,
-					false, single_size,
+					single_size,
 					MLXSW_SP_RESOURCE_KVD_HASH_SINGLE,
 					MLXSW_SP_RESOURCE_KVD,
 					&hash_single_size_params,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index 4c9bff2fa055..85503e93b93f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -459,7 +459,7 @@ int mlxsw_sp_kvdl_resources_register(struct devlink *devlink)
 
 	mlxsw_sp_kvdl_resource_size_params_prepare(devlink);
 	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES,
-					false, MLXSW_SP_KVDL_SINGLE_SIZE,
+					MLXSW_SP_KVDL_SINGLE_SIZE,
 					MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
 					MLXSW_SP_RESOURCE_KVD_LINEAR,
 					&mlxsw_sp_kvdl_single_size_params,
@@ -468,7 +468,7 @@ int mlxsw_sp_kvdl_resources_register(struct devlink *devlink)
 		return err;
 
 	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS,
-					false, MLXSW_SP_KVDL_CHUNKS_SIZE,
+					MLXSW_SP_KVDL_CHUNKS_SIZE,
 					MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
 					MLXSW_SP_RESOURCE_KVD_LINEAR,
 					&mlxsw_sp_kvdl_chunks_size_params,
@@ -477,7 +477,7 @@ int mlxsw_sp_kvdl_resources_register(struct devlink *devlink)
 		return err;
 
 	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS,
-					false, MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE,
+					MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE,
 					MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
 					MLXSW_SP_RESOURCE_KVD_LINEAR,
 					&mlxsw_sp_kvdl_large_chunks_size_params,
diff --git a/include/net/devlink.h b/include/net/devlink.h
index c83125ad20ff..d5b707375e48 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -406,7 +406,6 @@ extern struct devlink_dpipe_header devlink_dpipe_header_ipv6;
 
 int devlink_resource_register(struct devlink *devlink,
 			      const char *resource_name,
-			      bool top_hierarchy,
 			      u64 resource_size,
 			      u64 resource_id,
 			      u64 parent_resource_id,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index f23e5ed7c90f..d03b96f87c25 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3174,7 +3174,6 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister);
  */
 int devlink_resource_register(struct devlink *devlink,
 			      const char *resource_name,
-			      bool top_hierarchy,
 			      u64 resource_size,
 			      u64 resource_id,
 			      u64 parent_resource_id,
@@ -3183,8 +3182,11 @@ int devlink_resource_register(struct devlink *devlink,
 {
 	struct devlink_resource *resource;
 	struct list_head *resource_list;
+	bool top_hierarchy;
 	int err = 0;
 
+	top_hierarchy = parent_resource_id == DEVLINK_RESOURCE_ID_PARENT_TOP;
+
 	mutex_lock(&devlink->lock);
 	resource = devlink_resource_find(devlink, NULL, resource_id);
 	if (resource) {
-- 
cgit v1.2.3


From 5796ef75ec7b6019eac88f66751d663d537a5cd3 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Thu, 22 Mar 2018 12:45:32 +0300
Subject: net: Make ip_ra_chain per struct net

This is optimization, which makes ip_call_ra_chain()
iterate less sockets to find the sockets it's looking for.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h         | 13 +++++++++++--
 include/net/netns/ipv4.h |  1 +
 net/ipv4/ip_input.c      |  5 ++---
 net/ipv4/ip_sockglue.c   | 15 ++-------------
 4 files changed, 16 insertions(+), 18 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ip.h b/include/net/ip.h
index fe63ba95d12b..d53b5a9eae34 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -91,6 +91,17 @@ static inline int inet_sdif(struct sk_buff *skb)
 	return 0;
 }
 
+/* Special input handler for packets caught by router alert option.
+   They are selected only by protocol field, and then processed likely
+   local ones; but only if someone wants them! Otherwise, router
+   not running rsvpd will kill RSVP.
+
+   It is user level problem, what it will make with them.
+   I have no idea, how it will masquearde or NAT them (it is joke, joke :-)),
+   but receiver should be enough clever f.e. to forward mtrace requests,
+   sent to multicast group to reach destination designated router.
+ */
+
 struct ip_ra_chain {
 	struct ip_ra_chain __rcu *next;
 	struct sock		*sk;
@@ -101,8 +112,6 @@ struct ip_ra_chain {
 	struct rcu_head		rcu;
 };
 
-extern struct ip_ra_chain __rcu *ip_ra_chain;
-
 /* IP flags. */
 #define IP_CE		0x8000		/* Flag: "Congestion"		*/
 #define IP_DF		0x4000		/* Flag: "Don't Fragment"	*/
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 382bfd7583cf..97d7ee6667c7 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -49,6 +49,7 @@ struct netns_ipv4 {
 #endif
 	struct ipv4_devconf	*devconf_all;
 	struct ipv4_devconf	*devconf_dflt;
+	struct ip_ra_chain __rcu *ra_chain;
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	struct fib_rules_ops	*rules_ops;
 	bool			fib_has_custom_rules;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 57fc13c6ab2b..7582713dd18f 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -159,7 +159,7 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	struct net *net = dev_net(dev);
 
-	for (ra = rcu_dereference(ip_ra_chain); ra; ra = rcu_dereference(ra->next)) {
+	for (ra = rcu_dereference(net->ipv4.ra_chain); ra; ra = rcu_dereference(ra->next)) {
 		struct sock *sk = ra->sk;
 
 		/* If socket is bound to an interface, only report
@@ -167,8 +167,7 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 		 */
 		if (sk && inet_sk(sk)->inet_num == protocol &&
 		    (!sk->sk_bound_dev_if ||
-		     sk->sk_bound_dev_if == dev->ifindex) &&
-		    net_eq(sock_net(sk), net)) {
+		     sk->sk_bound_dev_if == dev->ifindex)) {
 			if (ip_is_fragment(ip_hdr(skb))) {
 				if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN))
 					return true;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index bf5f44b27b7e..f36d35fe924b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -322,18 +322,6 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 	return 0;
 }
 
-
-/* Special input handler for packets caught by router alert option.
-   They are selected only by protocol field, and then processed likely
-   local ones; but only if someone wants them! Otherwise, router
-   not running rsvpd will kill RSVP.
-
-   It is user level problem, what it will make with them.
-   I have no idea, how it will masquearde or NAT them (it is joke, joke :-)),
-   but receiver should be enough clever f.e. to forward mtrace requests,
-   sent to multicast group to reach destination designated router.
- */
-struct ip_ra_chain __rcu *ip_ra_chain;
 static DEFINE_SPINLOCK(ip_ra_lock);
 
 
@@ -350,6 +338,7 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 {
 	struct ip_ra_chain *ra, *new_ra;
 	struct ip_ra_chain __rcu **rap;
+	struct net *net = sock_net(sk);
 
 	if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW)
 		return -EINVAL;
@@ -357,7 +346,7 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 	new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
 
 	spin_lock_bh(&ip_ra_lock);
-	for (rap = &ip_ra_chain;
+	for (rap = &net->ipv4.ra_chain;
 	     (ra = rcu_dereference_protected(*rap,
 			lockdep_is_held(&ip_ra_lock))) != NULL;
 	     rap = &ra->next) {
-- 
cgit v1.2.3


From d9ff3049739e349b5380b96226f9ad766741773d Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Thu, 22 Mar 2018 12:45:40 +0300
Subject: net: Replace ip_ra_lock with per-net mutex

Since ra_chain is per-net, we may use per-net mutexes
to protect them in ip_ra_control(). This improves
scalability.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h |  1 +
 net/core/net_namespace.c |  1 +
 net/ipv4/ip_sockglue.c   | 15 ++++++---------
 3 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 97d7ee6667c7..8491bc9c86b1 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -50,6 +50,7 @@ struct netns_ipv4 {
 	struct ipv4_devconf	*devconf_all;
 	struct ipv4_devconf	*devconf_dflt;
 	struct ip_ra_chain __rcu *ra_chain;
+	struct mutex		ra_mutex;
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	struct fib_rules_ops	*rules_ops;
 	bool			fib_has_custom_rules;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index c340d5cfbdec..95ba2c53bd9a 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -301,6 +301,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);
 	spin_lock_init(&net->nsid_lock);
+	mutex_init(&net->ipv4.ra_mutex);
 
 	list_for_each_entry(ops, &pernet_list, list) {
 		error = ops_init(ops, net);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index f36d35fe924b..5ad2d8ed3a3f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -322,9 +322,6 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 	return 0;
 }
 
-static DEFINE_SPINLOCK(ip_ra_lock);
-
-
 static void ip_ra_destroy_rcu(struct rcu_head *head)
 {
 	struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu);
@@ -345,21 +342,21 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 
 	new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
 
-	spin_lock_bh(&ip_ra_lock);
+	mutex_lock(&net->ipv4.ra_mutex);
 	for (rap = &net->ipv4.ra_chain;
 	     (ra = rcu_dereference_protected(*rap,
-			lockdep_is_held(&ip_ra_lock))) != NULL;
+			lockdep_is_held(&net->ipv4.ra_mutex))) != NULL;
 	     rap = &ra->next) {
 		if (ra->sk == sk) {
 			if (on) {
-				spin_unlock_bh(&ip_ra_lock);
+				mutex_unlock(&net->ipv4.ra_mutex);
 				kfree(new_ra);
 				return -EADDRINUSE;
 			}
 			/* dont let ip_call_ra_chain() use sk again */
 			ra->sk = NULL;
 			RCU_INIT_POINTER(*rap, ra->next);
-			spin_unlock_bh(&ip_ra_lock);
+			mutex_unlock(&net->ipv4.ra_mutex);
 
 			if (ra->destructor)
 				ra->destructor(sk);
@@ -374,7 +371,7 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 		}
 	}
 	if (!new_ra) {
-		spin_unlock_bh(&ip_ra_lock);
+		mutex_unlock(&net->ipv4.ra_mutex);
 		return -ENOBUFS;
 	}
 	new_ra->sk = sk;
@@ -383,7 +380,7 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 	RCU_INIT_POINTER(new_ra->next, ra);
 	rcu_assign_pointer(*rap, new_ra);
 	sock_hold(sk);
-	spin_unlock_bh(&ip_ra_lock);
+	mutex_unlock(&net->ipv4.ra_mutex);
 
 	return 0;
 }
-- 
cgit v1.2.3


From dcbe73ca55a42712bfd0e9966cd2d5a48355ace3 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Date: Thu, 22 Mar 2018 12:18:03 -0700
Subject: mac80211: notify driver for change in multicast rates

With drivers implementing rate control in driver or firmware
rate_control_send_low() may not get called, and thus the
driver needs to know about changes in the multicast rate.

Add and use a new BSS change flag for this.

Signed-off-by: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
[rewrite commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 3 +++
 net/mac80211/cfg.c     | 2 ++
 net/mac80211/ibss.c    | 2 +-
 net/mac80211/mesh.c    | 3 ++-
 net/mac80211/util.c    | 3 ++-
 5 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include/net')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 2fd59ed3be00..d39fd6838f41 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -302,6 +302,8 @@ struct ieee80211_vif_chanctx_switch {
  * @BSS_CHANGED_MU_GROUPS: VHT MU-MIMO group id or user position changed
  * @BSS_CHANGED_KEEP_ALIVE: keep alive options (idle period or protected
  *	keep alive) changed.
+ * @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface
+ *
  */
 enum ieee80211_bss_change {
 	BSS_CHANGED_ASSOC		= 1<<0,
@@ -329,6 +331,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_OCB                 = 1<<22,
 	BSS_CHANGED_MU_GROUPS		= 1<<23,
 	BSS_CHANGED_KEEP_ALIVE		= 1<<24,
+	BSS_CHANGED_MCAST_RATE		= 1<<25,
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index fd68f6fb02d7..5c4b105ca398 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2313,6 +2313,8 @@ static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev,
 	memcpy(sdata->vif.bss_conf.mcast_rate, rate,
 	       sizeof(int) * NUM_NL80211_BANDS);
 
+	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_MCAST_RATE);
+
 	return 0;
 }
 
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index db07e0de9a03..dc582aa35c89 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1839,7 +1839,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 		  IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED
 		| IEEE80211_HT_PARAM_RIFS_MODE;
 
-	changed |= BSS_CHANGED_HT;
+	changed |= BSS_CHANGED_HT | BSS_CHANGED_MCAST_RATE;
 	ieee80211_bss_info_change_notify(sdata, changed);
 
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 6a381cbe1e33..d51da26e9c18 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -880,7 +880,8 @@ int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
 		      BSS_CHANGED_BEACON_ENABLED |
 		      BSS_CHANGED_HT |
 		      BSS_CHANGED_BASIC_RATES |
-		      BSS_CHANGED_BEACON_INT;
+		      BSS_CHANGED_BEACON_INT |
+		      BSS_CHANGED_MCAST_RATE;
 
 	local->fif_other_bss++;
 	/* mesh ifaces must set allmulti to forward mcast traffic */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 1f82191ce601..55cd2922627a 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1968,7 +1968,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			  BSS_CHANGED_CQM |
 			  BSS_CHANGED_QOS |
 			  BSS_CHANGED_IDLE |
-			  BSS_CHANGED_TXPOWER;
+			  BSS_CHANGED_TXPOWER |
+			  BSS_CHANGED_MCAST_RATE;
 
 		if (sdata->vif.mu_mimo_owner)
 			changed |= BSS_CHANGED_MU_GROUPS;
-- 
cgit v1.2.3


From e9de0018d1fa97f8db9a39fcb69b55266c52835b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 23 Mar 2018 08:09:48 -0700
Subject: devlink: Remove top_hierarchy arg for DEVLINK disabled path

Earlier change missed the path where CONFIG_NET_DEVLINK is disabled.
Thanks to Jiri for spotting.

Fixes: 145307460ba9 ("devlink: Remove top_hierarchy arg to devlink_resource_register")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index d5b707375e48..e21d8cadd480 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -559,7 +559,6 @@ devlink_dpipe_match_put(struct sk_buff *skb,
 static inline int
 devlink_resource_register(struct devlink *devlink,
 			  const char *resource_name,
-			  bool top_hierarchy,
 			  u64 resource_size,
 			  u64 resource_id,
 			  u64 parent_resource_id,
-- 
cgit v1.2.3


From dbe425599ba05c7415f632e6f5f018453098eb69 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Thu, 22 Mar 2018 10:10:06 -0700
Subject: tls: Move cipher info to a separate struct

Separate tx crypto parameters to a separate cipher_context struct.
The same parameters will be used for rx using the same struct.

tls_advance_record_sn is modified to only take the cipher info.

Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  | 26 +++++++++++++-----------
 net/tls/tls_main.c |  8 ++++----
 net/tls/tls_sw.c   | 58 ++++++++++++++++++++++++++++--------------------------
 3 files changed, 49 insertions(+), 43 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tls.h b/include/net/tls.h
index 4913430ab807..019e52db1817 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -81,6 +81,16 @@ enum {
 	TLS_PENDING_CLOSED_RECORD
 };
 
+struct cipher_context {
+	u16 prepend_size;
+	u16 tag_size;
+	u16 overhead_size;
+	u16 iv_size;
+	char *iv;
+	u16 rec_seq_size;
+	char *rec_seq;
+};
+
 struct tls_context {
 	union {
 		struct tls_crypto_info crypto_send;
@@ -91,13 +101,7 @@ struct tls_context {
 
 	u8 tx_conf:2;
 
-	u16 prepend_size;
-	u16 tag_size;
-	u16 overhead_size;
-	u16 iv_size;
-	char *iv;
-	u16 rec_seq_size;
-	char *rec_seq;
+	struct cipher_context tx;
 
 	struct scatterlist *partially_sent_record;
 	u16 partially_sent_offset;
@@ -190,7 +194,7 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len)
 }
 
 static inline void tls_advance_record_sn(struct sock *sk,
-					 struct tls_context *ctx)
+					 struct cipher_context *ctx)
 {
 	if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size))
 		tls_err_abort(sk);
@@ -203,9 +207,9 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
 			     size_t plaintext_len,
 			     unsigned char record_type)
 {
-	size_t pkt_len, iv_size = ctx->iv_size;
+	size_t pkt_len, iv_size = ctx->tx.iv_size;
 
-	pkt_len = plaintext_len + iv_size + ctx->tag_size;
+	pkt_len = plaintext_len + iv_size + ctx->tx.tag_size;
 
 	/* we cover nonce explicit here as well, so buf should be of
 	 * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE
@@ -217,7 +221,7 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
 	buf[3] = pkt_len >> 8;
 	buf[4] = pkt_len & 0xFF;
 	memcpy(buf + TLS_NONCE_OFFSET,
-	       ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size);
+	       ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size);
 }
 
 static inline void tls_make_aad(char *buf,
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index d824d548447e..c671560b832b 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -259,8 +259,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		}
 	}
 
-	kfree(ctx->rec_seq);
-	kfree(ctx->iv);
+	kfree(ctx->tx.rec_seq);
+	kfree(ctx->tx.iv);
 
 	if (ctx->tx_conf == TLS_SW_TX)
 		tls_sw_free_tx_resources(sk);
@@ -319,9 +319,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
 		}
 		lock_sock(sk);
 		memcpy(crypto_info_aes_gcm_128->iv,
-		       ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+		       ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
 		       TLS_CIPHER_AES_GCM_128_IV_SIZE);
-		memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->rec_seq,
+		memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->tx.rec_seq,
 		       TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE);
 		release_sock(sk);
 		if (copy_to_user(optval,
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index ca1d20de3d2c..338d743bcc21 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -79,7 +79,7 @@ static void trim_both_sgl(struct sock *sk, int target_size)
 		target_size);
 
 	if (target_size > 0)
-		target_size += tls_ctx->overhead_size;
+		target_size += tls_ctx->tx.overhead_size;
 
 	trim_sg(sk, ctx->sg_encrypted_data,
 		&ctx->sg_encrypted_num_elem,
@@ -152,21 +152,21 @@ static int tls_do_encryption(struct tls_context *tls_ctx,
 	if (!aead_req)
 		return -ENOMEM;
 
-	ctx->sg_encrypted_data[0].offset += tls_ctx->prepend_size;
-	ctx->sg_encrypted_data[0].length -= tls_ctx->prepend_size;
+	ctx->sg_encrypted_data[0].offset += tls_ctx->tx.prepend_size;
+	ctx->sg_encrypted_data[0].length -= tls_ctx->tx.prepend_size;
 
 	aead_request_set_tfm(aead_req, ctx->aead_send);
 	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
 	aead_request_set_crypt(aead_req, ctx->sg_aead_in, ctx->sg_aead_out,
-			       data_len, tls_ctx->iv);
+			       data_len, tls_ctx->tx.iv);
 
 	aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				  crypto_req_done, &ctx->async_wait);
 
 	rc = crypto_wait_req(crypto_aead_encrypt(aead_req), &ctx->async_wait);
 
-	ctx->sg_encrypted_data[0].offset -= tls_ctx->prepend_size;
-	ctx->sg_encrypted_data[0].length += tls_ctx->prepend_size;
+	ctx->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size;
+	ctx->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size;
 
 	kfree(aead_req);
 	return rc;
@@ -183,7 +183,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1);
 
 	tls_make_aad(ctx->aad_space, ctx->sg_plaintext_size,
-		     tls_ctx->rec_seq, tls_ctx->rec_seq_size,
+		     tls_ctx->tx.rec_seq, tls_ctx->tx.rec_seq_size,
 		     record_type);
 
 	tls_fill_prepend(tls_ctx,
@@ -216,7 +216,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	if (rc < 0 && rc != -EAGAIN)
 		tls_err_abort(sk);
 
-	tls_advance_record_sn(sk, tls_ctx);
+	tls_advance_record_sn(sk, &tls_ctx->tx);
 	return rc;
 }
 
@@ -357,7 +357,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		}
 
 		required_size = ctx->sg_plaintext_size + try_to_copy +
-				tls_ctx->overhead_size;
+				tls_ctx->tx.overhead_size;
 
 		if (!sk_stream_memory_free(sk))
 			goto wait_for_sndbuf;
@@ -420,7 +420,7 @@ alloc_plaintext:
 				&ctx->sg_encrypted_num_elem,
 				&ctx->sg_encrypted_size,
 				ctx->sg_plaintext_size +
-				tls_ctx->overhead_size);
+				tls_ctx->tx.overhead_size);
 		}
 
 		ret = memcopy_from_iter(sk, &msg->msg_iter, try_to_copy);
@@ -512,7 +512,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 			full_record = true;
 		}
 		required_size = ctx->sg_plaintext_size + copy +
-			      tls_ctx->overhead_size;
+			      tls_ctx->tx.overhead_size;
 
 		if (!sk_stream_memory_free(sk))
 			goto wait_for_sndbuf;
@@ -644,24 +644,26 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 		goto free_priv;
 	}
 
-	ctx->prepend_size = TLS_HEADER_SIZE + nonce_size;
-	ctx->tag_size = tag_size;
-	ctx->overhead_size = ctx->prepend_size + ctx->tag_size;
-	ctx->iv_size = iv_size;
-	ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL);
-	if (!ctx->iv) {
+	ctx->tx.prepend_size = TLS_HEADER_SIZE + nonce_size;
+	ctx->tx.tag_size = tag_size;
+	ctx->tx.overhead_size = ctx->tx.prepend_size + ctx->tx.tag_size;
+	ctx->tx.iv_size = iv_size;
+	ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			     GFP_KERNEL);
+	if (!ctx->tx.iv) {
 		rc = -ENOMEM;
 		goto free_priv;
 	}
-	memcpy(ctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
-	memcpy(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
-	ctx->rec_seq_size = rec_seq_size;
-	ctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
-	if (!ctx->rec_seq) {
+	memcpy(ctx->tx.iv, gcm_128_info->salt,
+	       TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+	memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
+	ctx->tx.rec_seq_size = rec_seq_size;
+	ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
+	if (!ctx->tx.rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
 	}
-	memcpy(ctx->rec_seq, rec_seq, rec_seq_size);
+	memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size);
 
 	sg_init_table(sw_ctx->sg_encrypted_data,
 		      ARRAY_SIZE(sw_ctx->sg_encrypted_data));
@@ -697,7 +699,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 	if (rc)
 		goto free_aead;
 
-	rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tag_size);
+	rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tx.tag_size);
 	if (!rc)
 		return 0;
 
@@ -705,11 +707,11 @@ free_aead:
 	crypto_free_aead(sw_ctx->aead_send);
 	sw_ctx->aead_send = NULL;
 free_rec_seq:
-	kfree(ctx->rec_seq);
-	ctx->rec_seq = NULL;
+	kfree(ctx->tx.rec_seq);
+	ctx->tx.rec_seq = NULL;
 free_iv:
-	kfree(ctx->iv);
-	ctx->iv = NULL;
+	kfree(ctx->tx.iv);
+	ctx->tx.iv = NULL;
 free_priv:
 	kfree(ctx->priv_ctx);
 	ctx->priv_ctx = NULL;
-- 
cgit v1.2.3


From f4a8e43f1f0abc0e93ed5ee132288ee4142afde1 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Thu, 22 Mar 2018 10:10:15 -0700
Subject: tls: Pass error code explicitly to tls_err_abort

Pass EBADMSG explicitly to tls_err_abort.  Receive path will
pass additional codes - EMSGSIZE if framing is larger than max
TLS record size, EINVAL if TLS version mismatch.

Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h | 6 +++---
 net/tls/tls_sw.c  | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tls.h b/include/net/tls.h
index 019e52db1817..6b44875a78e5 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -174,9 +174,9 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx)
 	return tls_ctx->pending_open_record_frags;
 }
 
-static inline void tls_err_abort(struct sock *sk)
+static inline void tls_err_abort(struct sock *sk, int err)
 {
-	sk->sk_err = EBADMSG;
+	sk->sk_err = err;
 	sk->sk_error_report(sk);
 }
 
@@ -197,7 +197,7 @@ static inline void tls_advance_record_sn(struct sock *sk,
 					 struct cipher_context *ctx)
 {
 	if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size))
-		tls_err_abort(sk);
+		tls_err_abort(sk, EBADMSG);
 	tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
 			     ctx->iv_size);
 }
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 338d743bcc21..1c79d9ad1731 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -214,7 +214,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	/* Only pass through MSG_DONTWAIT and MSG_NOSIGNAL flags */
 	rc = tls_push_sg(sk, tls_ctx, ctx->sg_encrypted_data, 0, flags);
 	if (rc < 0 && rc != -EAGAIN)
-		tls_err_abort(sk);
+		tls_err_abort(sk, EBADMSG);
 
 	tls_advance_record_sn(sk, &tls_ctx->tx);
 	return rc;
-- 
cgit v1.2.3


From 583715853a25b4f2720b847e4fb8e37727299152 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Thu, 22 Mar 2018 10:10:26 -0700
Subject: tls: Refactor variable names

Several config variables are prefixed with tx, drop the prefix
since these will be used for both tx and rx.

Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  |  2 +-
 net/tls/tls_main.c | 26 +++++++++++++-------------
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tls.h b/include/net/tls.h
index 6b44875a78e5..095b72283861 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -99,7 +99,7 @@ struct tls_context {
 
 	void *priv_ctx;
 
-	u8 tx_conf:2;
+	u8 conf:2;
 
 	struct cipher_context tx;
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index c671560b832b..c405beeda765 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -52,7 +52,7 @@ enum {
 };
 
 enum {
-	TLS_BASE_TX,
+	TLS_BASE,
 	TLS_SW_TX,
 	TLS_NUM_CONFIG,
 };
@@ -65,7 +65,7 @@ static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 {
 	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
 
-	sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf];
+	sk->sk_prot = &tls_prots[ip_ver][ctx->conf];
 }
 
 int wait_on_pending_writer(struct sock *sk, long *timeo)
@@ -238,7 +238,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	lock_sock(sk);
 	sk_proto_close = ctx->sk_proto_close;
 
-	if (ctx->tx_conf == TLS_BASE_TX) {
+	if (ctx->conf == TLS_BASE) {
 		kfree(ctx);
 		goto skip_tx_cleanup;
 	}
@@ -262,7 +262,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	kfree(ctx->tx.rec_seq);
 	kfree(ctx->tx.iv);
 
-	if (ctx->tx_conf == TLS_SW_TX)
+	if (ctx->conf == TLS_SW_TX)
 		tls_sw_free_tx_resources(sk);
 
 skip_tx_cleanup:
@@ -371,7 +371,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	struct tls_crypto_info *crypto_info;
 	struct tls_context *ctx = tls_get_ctx(sk);
 	int rc = 0;
-	int tx_conf;
+	int conf;
 
 	if (!optval || (optlen < sizeof(*crypto_info))) {
 		rc = -EINVAL;
@@ -418,11 +418,11 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 
 	/* currently SW is default, we will have ethtool in future */
 	rc = tls_set_sw_offload(sk, ctx);
-	tx_conf = TLS_SW_TX;
+	conf = TLS_SW_TX;
 	if (rc)
 		goto err_crypto_info;
 
-	ctx->tx_conf = tx_conf;
+	ctx->conf = conf;
 	update_sk_prot(sk, ctx);
 	ctx->sk_write_space = sk->sk_write_space;
 	sk->sk_write_space = tls_write_space;
@@ -465,12 +465,12 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
 
 static void build_protos(struct proto *prot, struct proto *base)
 {
-	prot[TLS_BASE_TX] = *base;
-	prot[TLS_BASE_TX].setsockopt	= tls_setsockopt;
-	prot[TLS_BASE_TX].getsockopt	= tls_getsockopt;
-	prot[TLS_BASE_TX].close		= tls_sk_proto_close;
+	prot[TLS_BASE] = *base;
+	prot[TLS_BASE].setsockopt	= tls_setsockopt;
+	prot[TLS_BASE].getsockopt	= tls_getsockopt;
+	prot[TLS_BASE].close		= tls_sk_proto_close;
 
-	prot[TLS_SW_TX] = prot[TLS_BASE_TX];
+	prot[TLS_SW_TX] = prot[TLS_BASE];
 	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
 	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
 }
@@ -513,7 +513,7 @@ static int tls_init(struct sock *sk)
 		mutex_unlock(&tcpv6_prot_mutex);
 	}
 
-	ctx->tx_conf = TLS_BASE_TX;
+	ctx->conf = TLS_BASE;
 	update_sk_prot(sk, ctx);
 out:
 	return rc;
-- 
cgit v1.2.3


From c46234ebb4d1eee5e09819f49169e51cfc6eb909 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Thu, 22 Mar 2018 10:10:35 -0700
Subject: tls: RX path for ktls

Add rx path for tls software implementation.

recvmsg, splice_read, and poll implemented.

An additional sockopt TLS_RX is added, with the same interface as
TLS_TX.  Either TLX_RX or TLX_TX may be provided separately, or
together (with two different setsockopt calls with appropriate keys).

Control messages are passed via CMSG in a similar way to transmit.
If no cmsg buffer is passed, then only application data records
will be passed to userspace, and EIO is returned for other types of
alerts.

EBADMSG is passed for decryption errors, and EMSGSIZE is passed for
framing too big, and EBADMSG for framing too small (matching openssl
semantics). EINVAL is returned for TLS versions that do not match the
original setsockopt call.  All are unrecoverable.

strparser is used to parse TLS framing.   Decryption is done directly
in to userspace buffers if they are large enough to support it, otherwise
sk_cow_data is called (similar to ipsec), and buffers are decrypted in
place and copied.  splice_read always decrypts in place, since no
buffers are provided to decrypt in to.

sk_poll is overridden, and only returns POLLIN if a full TLS message is
received.  Otherwise we wait for strparser to finish reading a full frame.
Actual decryption is only done during recvmsg or splice_read calls.

Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h        |  27 ++-
 include/uapi/linux/tls.h |   2 +
 net/tls/Kconfig          |   1 +
 net/tls/tls_main.c       |  62 ++++-
 net/tls/tls_sw.c         | 587 ++++++++++++++++++++++++++++++++++++++++++-----
 5 files changed, 609 insertions(+), 70 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tls.h b/include/net/tls.h
index 095b72283861..437a746300bf 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -40,6 +40,7 @@
 #include <linux/socket.h>
 #include <linux/tcp.h>
 #include <net/tcp.h>
+#include <net/strparser.h>
 
 #include <uapi/linux/tls.h>
 
@@ -58,8 +59,18 @@
 
 struct tls_sw_context {
 	struct crypto_aead *aead_send;
+	struct crypto_aead *aead_recv;
 	struct crypto_wait async_wait;
 
+	/* Receive context */
+	struct strparser strp;
+	void (*saved_data_ready)(struct sock *sk);
+	unsigned int (*sk_poll)(struct file *file, struct socket *sock,
+				struct poll_table_struct *wait);
+	struct sk_buff *recv_pkt;
+	u8 control;
+	bool decrypted;
+
 	/* Sending context */
 	char aad_space[TLS_AAD_SPACE_SIZE];
 
@@ -96,12 +107,17 @@ struct tls_context {
 		struct tls_crypto_info crypto_send;
 		struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128;
 	};
+	union {
+		struct tls_crypto_info crypto_recv;
+		struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128;
+	};
 
 	void *priv_ctx;
 
 	u8 conf:2;
 
 	struct cipher_context tx;
+	struct cipher_context rx;
 
 	struct scatterlist *partially_sent_record;
 	u16 partially_sent_offset;
@@ -128,12 +144,19 @@ int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
 		  unsigned int optlen);
 
 
-int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx);
+int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_sw_sendpage(struct sock *sk, struct page *page,
 		    int offset, size_t size, int flags);
 void tls_sw_close(struct sock *sk, long timeout);
-void tls_sw_free_tx_resources(struct sock *sk);
+void tls_sw_free_resources(struct sock *sk);
+int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		   int nonblock, int flags, int *addr_len);
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait);
+ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
+			   struct pipe_inode_info *pipe,
+			   size_t len, unsigned int flags);
 
 void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
 void tls_icsk_clean_acked(struct sock *sk);
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
index 293b2cdad88d..c6633e97eca4 100644
--- a/include/uapi/linux/tls.h
+++ b/include/uapi/linux/tls.h
@@ -38,6 +38,7 @@
 
 /* TLS socket options */
 #define TLS_TX			1	/* Set transmit parameters */
+#define TLS_RX			2	/* Set receive parameters */
 
 /* Supported versions */
 #define TLS_VERSION_MINOR(ver)	((ver) & 0xFF)
@@ -59,6 +60,7 @@
 #define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE		8
 
 #define TLS_SET_RECORD_TYPE	1
+#define TLS_GET_RECORD_TYPE	2
 
 struct tls_crypto_info {
 	__u16 version;
diff --git a/net/tls/Kconfig b/net/tls/Kconfig
index eb583038c67e..89b8745a986f 100644
--- a/net/tls/Kconfig
+++ b/net/tls/Kconfig
@@ -7,6 +7,7 @@ config TLS
 	select CRYPTO
 	select CRYPTO_AES
 	select CRYPTO_GCM
+	select STREAM_PARSER
 	default n
 	---help---
 	Enable kernel support for TLS protocol. This allows symmetric
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index c405beeda765..6f5c1146da4a 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -54,12 +54,15 @@ enum {
 enum {
 	TLS_BASE,
 	TLS_SW_TX,
+	TLS_SW_RX,
+	TLS_SW_RXTX,
 	TLS_NUM_CONFIG,
 };
 
 static struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG];
+static struct proto_ops tls_sw_proto_ops;
 
 static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 {
@@ -261,9 +264,14 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 
 	kfree(ctx->tx.rec_seq);
 	kfree(ctx->tx.iv);
+	kfree(ctx->rx.rec_seq);
+	kfree(ctx->rx.iv);
 
-	if (ctx->conf == TLS_SW_TX)
-		tls_sw_free_tx_resources(sk);
+	if (ctx->conf == TLS_SW_TX ||
+	    ctx->conf == TLS_SW_RX ||
+	    ctx->conf == TLS_SW_RXTX) {
+		tls_sw_free_resources(sk);
+	}
 
 skip_tx_cleanup:
 	release_sock(sk);
@@ -365,8 +373,8 @@ static int tls_getsockopt(struct sock *sk, int level, int optname,
 	return do_tls_getsockopt(sk, optname, optval, optlen);
 }
 
-static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
-				unsigned int optlen)
+static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
+				  unsigned int optlen, int tx)
 {
 	struct tls_crypto_info *crypto_info;
 	struct tls_context *ctx = tls_get_ctx(sk);
@@ -378,7 +386,11 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 		goto out;
 	}
 
-	crypto_info = &ctx->crypto_send;
+	if (tx)
+		crypto_info = &ctx->crypto_send;
+	else
+		crypto_info = &ctx->crypto_recv;
+
 	/* Currently we don't support set crypto info more than one time */
 	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
 		rc = -EBUSY;
@@ -417,15 +429,31 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	}
 
 	/* currently SW is default, we will have ethtool in future */
-	rc = tls_set_sw_offload(sk, ctx);
-	conf = TLS_SW_TX;
+	if (tx) {
+		rc = tls_set_sw_offload(sk, ctx, 1);
+		if (ctx->conf == TLS_SW_RX)
+			conf = TLS_SW_RXTX;
+		else
+			conf = TLS_SW_TX;
+	} else {
+		rc = tls_set_sw_offload(sk, ctx, 0);
+		if (ctx->conf == TLS_SW_TX)
+			conf = TLS_SW_RXTX;
+		else
+			conf = TLS_SW_RX;
+	}
+
 	if (rc)
 		goto err_crypto_info;
 
 	ctx->conf = conf;
 	update_sk_prot(sk, ctx);
-	ctx->sk_write_space = sk->sk_write_space;
-	sk->sk_write_space = tls_write_space;
+	if (tx) {
+		ctx->sk_write_space = sk->sk_write_space;
+		sk->sk_write_space = tls_write_space;
+	} else {
+		sk->sk_socket->ops = &tls_sw_proto_ops;
+	}
 	goto out;
 
 err_crypto_info:
@@ -441,8 +469,10 @@ static int do_tls_setsockopt(struct sock *sk, int optname,
 
 	switch (optname) {
 	case TLS_TX:
+	case TLS_RX:
 		lock_sock(sk);
-		rc = do_tls_setsockopt_tx(sk, optval, optlen);
+		rc = do_tls_setsockopt_conf(sk, optval, optlen,
+					    optname == TLS_TX);
 		release_sock(sk);
 		break;
 	default:
@@ -473,6 +503,14 @@ static void build_protos(struct proto *prot, struct proto *base)
 	prot[TLS_SW_TX] = prot[TLS_BASE];
 	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
 	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
+
+	prot[TLS_SW_RX] = prot[TLS_BASE];
+	prot[TLS_SW_RX].recvmsg		= tls_sw_recvmsg;
+	prot[TLS_SW_RX].close		= tls_sk_proto_close;
+
+	prot[TLS_SW_RXTX] = prot[TLS_SW_TX];
+	prot[TLS_SW_RXTX].recvmsg	= tls_sw_recvmsg;
+	prot[TLS_SW_RXTX].close		= tls_sk_proto_close;
 }
 
 static int tls_init(struct sock *sk)
@@ -531,6 +569,10 @@ static int __init tls_register(void)
 {
 	build_protos(tls_prots[TLSV4], &tcp_prot);
 
+	tls_sw_proto_ops = inet_stream_ops;
+	tls_sw_proto_ops.poll = tls_sw_poll;
+	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
+
 	tcp_register_ulp(&tcp_tls_ulp_ops);
 
 	return 0;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1c79d9ad1731..4dc766b03f00 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -34,11 +34,60 @@
  * SOFTWARE.
  */
 
+#include <linux/sched/signal.h>
 #include <linux/module.h>
 #include <crypto/aead.h>
 
+#include <net/strparser.h>
 #include <net/tls.h>
 
+static int tls_do_decryption(struct sock *sk,
+			     struct scatterlist *sgin,
+			     struct scatterlist *sgout,
+			     char *iv_recv,
+			     size_t data_len,
+			     struct sk_buff *skb,
+			     gfp_t flags)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm = strp_msg(skb);
+	struct aead_request *aead_req;
+
+	int ret;
+	unsigned int req_size = sizeof(struct aead_request) +
+		crypto_aead_reqsize(ctx->aead_recv);
+
+	aead_req = kzalloc(req_size, flags);
+	if (!aead_req)
+		return -ENOMEM;
+
+	aead_request_set_tfm(aead_req, ctx->aead_recv);
+	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
+	aead_request_set_crypt(aead_req, sgin, sgout,
+			       data_len + tls_ctx->rx.tag_size,
+			       (u8 *)iv_recv);
+	aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  crypto_req_done, &ctx->async_wait);
+
+	ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait);
+
+	if (ret < 0)
+		goto out;
+
+	rxm->offset += tls_ctx->rx.prepend_size;
+	rxm->full_len -= tls_ctx->rx.overhead_size;
+	tls_advance_record_sn(sk, &tls_ctx->rx);
+
+	ctx->decrypted = true;
+
+	ctx->saved_data_ready(sk);
+
+out:
+	kfree(aead_req);
+	return ret;
+}
+
 static void trim_sg(struct sock *sk, struct scatterlist *sg,
 		    int *sg_num_elem, unsigned int *sg_size, int target_size)
 {
@@ -581,13 +630,404 @@ sendpage_end:
 	return ret;
 }
 
-void tls_sw_free_tx_resources(struct sock *sk)
+static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
+				     long timeo, int *err)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct sk_buff *skb;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	while (!(skb = ctx->recv_pkt)) {
+		if (sk->sk_err) {
+			*err = sock_error(sk);
+			return NULL;
+		}
+
+		if (sock_flag(sk, SOCK_DONE))
+			return NULL;
+
+		if ((flags & MSG_DONTWAIT) || !timeo) {
+			*err = -EAGAIN;
+			return NULL;
+		}
+
+		add_wait_queue(sk_sleep(sk), &wait);
+		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+		sk_wait_event(sk, &timeo, ctx->recv_pkt != skb, &wait);
+		sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+		remove_wait_queue(sk_sleep(sk), &wait);
+
+		/* Handle signals */
+		if (signal_pending(current)) {
+			*err = sock_intr_errno(timeo);
+			return NULL;
+		}
+	}
+
+	return skb;
+}
+
+static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
+		       struct scatterlist *sgout)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + tls_ctx->rx.iv_size];
+	struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2];
+	struct scatterlist *sgin = &sgin_arr[0];
+	struct strp_msg *rxm = strp_msg(skb);
+	int ret, nsg = ARRAY_SIZE(sgin_arr);
+	char aad_recv[TLS_AAD_SPACE_SIZE];
+	struct sk_buff *unused;
+
+	ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
+			    iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			    tls_ctx->rx.iv_size);
+	if (ret < 0)
+		return ret;
+
+	memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+	if (!sgout) {
+		nsg = skb_cow_data(skb, 0, &unused) + 1;
+		sgin = kmalloc_array(nsg, sizeof(*sgin), sk->sk_allocation);
+		if (!sgout)
+			sgout = sgin;
+	}
+
+	sg_init_table(sgin, nsg);
+	sg_set_buf(&sgin[0], aad_recv, sizeof(aad_recv));
+
+	nsg = skb_to_sgvec(skb, &sgin[1],
+			   rxm->offset + tls_ctx->rx.prepend_size,
+			   rxm->full_len - tls_ctx->rx.prepend_size);
+
+	tls_make_aad(aad_recv,
+		     rxm->full_len - tls_ctx->rx.overhead_size,
+		     tls_ctx->rx.rec_seq,
+		     tls_ctx->rx.rec_seq_size,
+		     ctx->control);
+
+	ret = tls_do_decryption(sk, sgin, sgout, iv,
+				rxm->full_len - tls_ctx->rx.overhead_size,
+				skb, sk->sk_allocation);
+
+	if (sgin != &sgin_arr[0])
+		kfree(sgin);
+
+	return ret;
+}
+
+static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb,
+			       unsigned int len)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm = strp_msg(skb);
+
+	if (len < rxm->full_len) {
+		rxm->offset += len;
+		rxm->full_len -= len;
+
+		return false;
+	}
+
+	/* Finished with message */
+	ctx->recv_pkt = NULL;
+	kfree_skb(skb);
+	strp_unpause(&ctx->strp);
+
+	return true;
+}
+
+int tls_sw_recvmsg(struct sock *sk,
+		   struct msghdr *msg,
+		   size_t len,
+		   int nonblock,
+		   int flags,
+		   int *addr_len)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	unsigned char control;
+	struct strp_msg *rxm;
+	struct sk_buff *skb;
+	ssize_t copied = 0;
+	bool cmsg = false;
+	int err = 0;
+	long timeo;
+
+	flags |= nonblock;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR);
+
+	lock_sock(sk);
+
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+	do {
+		bool zc = false;
+		int chunk = 0;
+
+		skb = tls_wait_data(sk, flags, timeo, &err);
+		if (!skb)
+			goto recv_end;
+
+		rxm = strp_msg(skb);
+		if (!cmsg) {
+			int cerr;
+
+			cerr = put_cmsg(msg, SOL_TLS, TLS_GET_RECORD_TYPE,
+					sizeof(ctx->control), &ctx->control);
+			cmsg = true;
+			control = ctx->control;
+			if (ctx->control != TLS_RECORD_TYPE_DATA) {
+				if (cerr || msg->msg_flags & MSG_CTRUNC) {
+					err = -EIO;
+					goto recv_end;
+				}
+			}
+		} else if (control != ctx->control) {
+			goto recv_end;
+		}
+
+		if (!ctx->decrypted) {
+			int page_count;
+			int to_copy;
+
+			page_count = iov_iter_npages(&msg->msg_iter,
+						     MAX_SKB_FRAGS);
+			to_copy = rxm->full_len - tls_ctx->rx.overhead_size;
+			if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
+			    likely(!(flags & MSG_PEEK)))  {
+				struct scatterlist sgin[MAX_SKB_FRAGS + 1];
+				char unused[21];
+				int pages = 0;
+
+				zc = true;
+				sg_init_table(sgin, MAX_SKB_FRAGS + 1);
+				sg_set_buf(&sgin[0], unused, 13);
+
+				err = zerocopy_from_iter(sk, &msg->msg_iter,
+							 to_copy, &pages,
+							 &chunk, &sgin[1],
+							 MAX_SKB_FRAGS,	false);
+				if (err < 0)
+					goto fallback_to_reg_recv;
+
+				err = decrypt_skb(sk, skb, sgin);
+				for (; pages > 0; pages--)
+					put_page(sg_page(&sgin[pages]));
+				if (err < 0) {
+					tls_err_abort(sk, EBADMSG);
+					goto recv_end;
+				}
+			} else {
+fallback_to_reg_recv:
+				err = decrypt_skb(sk, skb, NULL);
+				if (err < 0) {
+					tls_err_abort(sk, EBADMSG);
+					goto recv_end;
+				}
+			}
+			ctx->decrypted = true;
+		}
+
+		if (!zc) {
+			chunk = min_t(unsigned int, rxm->full_len, len);
+			err = skb_copy_datagram_msg(skb, rxm->offset, msg,
+						    chunk);
+			if (err < 0)
+				goto recv_end;
+		}
+
+		copied += chunk;
+		len -= chunk;
+		if (likely(!(flags & MSG_PEEK))) {
+			u8 control = ctx->control;
+
+			if (tls_sw_advance_skb(sk, skb, chunk)) {
+				/* Return full control message to
+				 * userspace before trying to parse
+				 * another message type
+				 */
+				msg->msg_flags |= MSG_EOR;
+				if (control != TLS_RECORD_TYPE_DATA)
+					goto recv_end;
+			}
+		}
+	} while (len);
+
+recv_end:
+	release_sock(sk);
+	return copied ? : err;
+}
+
+ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
+			   struct pipe_inode_info *pipe,
+			   size_t len, unsigned int flags)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sock->sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm = NULL;
+	struct sock *sk = sock->sk;
+	struct sk_buff *skb;
+	ssize_t copied = 0;
+	int err = 0;
+	long timeo;
+	int chunk;
+
+	lock_sock(sk);
+
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+
+	skb = tls_wait_data(sk, flags, timeo, &err);
+	if (!skb)
+		goto splice_read_end;
+
+	/* splice does not support reading control messages */
+	if (ctx->control != TLS_RECORD_TYPE_DATA) {
+		err = -ENOTSUPP;
+		goto splice_read_end;
+	}
+
+	if (!ctx->decrypted) {
+		err = decrypt_skb(sk, skb, NULL);
+
+		if (err < 0) {
+			tls_err_abort(sk, EBADMSG);
+			goto splice_read_end;
+		}
+		ctx->decrypted = true;
+	}
+	rxm = strp_msg(skb);
+
+	chunk = min_t(unsigned int, rxm->full_len, len);
+	copied = skb_splice_bits(skb, sk, rxm->offset, pipe, chunk, flags);
+	if (copied < 0)
+		goto splice_read_end;
+
+	if (likely(!(flags & MSG_PEEK)))
+		tls_sw_advance_skb(sk, skb, copied);
+
+splice_read_end:
+	release_sock(sk);
+	return copied ? : err;
+}
+
+unsigned int tls_sw_poll(struct file *file, struct socket *sock,
+			 struct poll_table_struct *wait)
+{
+	unsigned int ret;
+	struct sock *sk = sock->sk;
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+
+	/* Grab POLLOUT and POLLHUP from the underlying socket */
+	ret = ctx->sk_poll(file, sock, wait);
+
+	/* Clear POLLIN bits, and set based on recv_pkt */
+	ret &= ~(POLLIN | POLLRDNORM);
+	if (ctx->recv_pkt)
+		ret |= POLLIN | POLLRDNORM;
+
+	return ret;
+}
+
+static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	char header[tls_ctx->rx.prepend_size];
+	struct strp_msg *rxm = strp_msg(skb);
+	size_t cipher_overhead;
+	size_t data_len = 0;
+	int ret;
+
+	/* Verify that we have a full TLS header, or wait for more data */
+	if (rxm->offset + tls_ctx->rx.prepend_size > skb->len)
+		return 0;
+
+	/* Linearize header to local buffer */
+	ret = skb_copy_bits(skb, rxm->offset, header, tls_ctx->rx.prepend_size);
+
+	if (ret < 0)
+		goto read_failure;
+
+	ctx->control = header[0];
+
+	data_len = ((header[4] & 0xFF) | (header[3] << 8));
+
+	cipher_overhead = tls_ctx->rx.tag_size + tls_ctx->rx.iv_size;
+
+	if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead) {
+		ret = -EMSGSIZE;
+		goto read_failure;
+	}
+	if (data_len < cipher_overhead) {
+		ret = -EBADMSG;
+		goto read_failure;
+	}
+
+	if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) ||
+	    header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) {
+		ret = -EINVAL;
+		goto read_failure;
+	}
+
+	return data_len + TLS_HEADER_SIZE;
+
+read_failure:
+	tls_err_abort(strp->sk, ret);
+
+	return ret;
+}
+
+static void tls_queue(struct strparser *strp, struct sk_buff *skb)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct strp_msg *rxm;
+
+	rxm = strp_msg(skb);
+
+	ctx->decrypted = false;
+
+	ctx->recv_pkt = skb;
+	strp_pause(strp);
+
+	strp->sk->sk_state_change(strp->sk);
+}
+
+static void tls_data_ready(struct sock *sk)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+
+	strp_data_ready(&ctx->strp);
+}
+
+void tls_sw_free_resources(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 
 	if (ctx->aead_send)
 		crypto_free_aead(ctx->aead_send);
+	if (ctx->aead_recv) {
+		if (ctx->recv_pkt) {
+			kfree_skb(ctx->recv_pkt);
+			ctx->recv_pkt = NULL;
+		}
+		crypto_free_aead(ctx->aead_recv);
+		strp_stop(&ctx->strp);
+		write_lock_bh(&sk->sk_callback_lock);
+		sk->sk_data_ready = ctx->saved_data_ready;
+		write_unlock_bh(&sk->sk_callback_lock);
+		release_sock(sk);
+		strp_done(&ctx->strp);
+		lock_sock(sk);
+	}
 
 	tls_free_both_sg(sk);
 
@@ -595,12 +1035,15 @@ void tls_sw_free_tx_resources(struct sock *sk)
 	kfree(tls_ctx);
 }
 
-int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
+int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 {
 	char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
 	struct tls_crypto_info *crypto_info;
 	struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
 	struct tls_sw_context *sw_ctx;
+	struct cipher_context *cctx;
+	struct crypto_aead **aead;
+	struct strp_callbacks cb;
 	u16 nonce_size, tag_size, iv_size, rec_seq_size;
 	char *iv, *rec_seq;
 	int rc = 0;
@@ -610,22 +1053,29 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 		goto out;
 	}
 
-	if (ctx->priv_ctx) {
-		rc = -EEXIST;
-		goto out;
-	}
-
-	sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL);
-	if (!sw_ctx) {
-		rc = -ENOMEM;
-		goto out;
+	if (!ctx->priv_ctx) {
+		sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL);
+		if (!sw_ctx) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		crypto_init_wait(&sw_ctx->async_wait);
+	} else {
+		sw_ctx = ctx->priv_ctx;
 	}
 
-	crypto_init_wait(&sw_ctx->async_wait);
-
 	ctx->priv_ctx = (struct tls_offload_context *)sw_ctx;
 
-	crypto_info = &ctx->crypto_send;
+	if (tx) {
+		crypto_info = &ctx->crypto_send;
+		cctx = &ctx->tx;
+		aead = &sw_ctx->aead_send;
+	} else {
+		crypto_info = &ctx->crypto_recv;
+		cctx = &ctx->rx;
+		aead = &sw_ctx->aead_recv;
+	}
+
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128: {
 		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
@@ -644,48 +1094,49 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 		goto free_priv;
 	}
 
-	ctx->tx.prepend_size = TLS_HEADER_SIZE + nonce_size;
-	ctx->tx.tag_size = tag_size;
-	ctx->tx.overhead_size = ctx->tx.prepend_size + ctx->tx.tag_size;
-	ctx->tx.iv_size = iv_size;
-	ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
-			     GFP_KERNEL);
-	if (!ctx->tx.iv) {
+	cctx->prepend_size = TLS_HEADER_SIZE + nonce_size;
+	cctx->tag_size = tag_size;
+	cctx->overhead_size = cctx->prepend_size + cctx->tag_size;
+	cctx->iv_size = iv_size;
+	cctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			   GFP_KERNEL);
+	if (!cctx->iv) {
 		rc = -ENOMEM;
 		goto free_priv;
 	}
-	memcpy(ctx->tx.iv, gcm_128_info->salt,
-	       TLS_CIPHER_AES_GCM_128_SALT_SIZE);
-	memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
-	ctx->tx.rec_seq_size = rec_seq_size;
-	ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
-	if (!ctx->tx.rec_seq) {
+	memcpy(cctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+	memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
+	cctx->rec_seq_size = rec_seq_size;
+	cctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
+	if (!cctx->rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
 	}
-	memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size);
-
-	sg_init_table(sw_ctx->sg_encrypted_data,
-		      ARRAY_SIZE(sw_ctx->sg_encrypted_data));
-	sg_init_table(sw_ctx->sg_plaintext_data,
-		      ARRAY_SIZE(sw_ctx->sg_plaintext_data));
-
-	sg_init_table(sw_ctx->sg_aead_in, 2);
-	sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space,
-		   sizeof(sw_ctx->aad_space));
-	sg_unmark_end(&sw_ctx->sg_aead_in[1]);
-	sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data);
-	sg_init_table(sw_ctx->sg_aead_out, 2);
-	sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space,
-		   sizeof(sw_ctx->aad_space));
-	sg_unmark_end(&sw_ctx->sg_aead_out[1]);
-	sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data);
-
-	if (!sw_ctx->aead_send) {
-		sw_ctx->aead_send = crypto_alloc_aead("gcm(aes)", 0, 0);
-		if (IS_ERR(sw_ctx->aead_send)) {
-			rc = PTR_ERR(sw_ctx->aead_send);
-			sw_ctx->aead_send = NULL;
+	memcpy(cctx->rec_seq, rec_seq, rec_seq_size);
+
+	if (tx) {
+		sg_init_table(sw_ctx->sg_encrypted_data,
+			      ARRAY_SIZE(sw_ctx->sg_encrypted_data));
+		sg_init_table(sw_ctx->sg_plaintext_data,
+			      ARRAY_SIZE(sw_ctx->sg_plaintext_data));
+
+		sg_init_table(sw_ctx->sg_aead_in, 2);
+		sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space,
+			   sizeof(sw_ctx->aad_space));
+		sg_unmark_end(&sw_ctx->sg_aead_in[1]);
+		sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data);
+		sg_init_table(sw_ctx->sg_aead_out, 2);
+		sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space,
+			   sizeof(sw_ctx->aad_space));
+		sg_unmark_end(&sw_ctx->sg_aead_out[1]);
+		sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data);
+	}
+
+	if (!*aead) {
+		*aead = crypto_alloc_aead("gcm(aes)", 0, 0);
+		if (IS_ERR(*aead)) {
+			rc = PTR_ERR(*aead);
+			*aead = NULL;
 			goto free_rec_seq;
 		}
 	}
@@ -694,21 +1145,41 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 
 	memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
 
-	rc = crypto_aead_setkey(sw_ctx->aead_send, keyval,
+	rc = crypto_aead_setkey(*aead, keyval,
 				TLS_CIPHER_AES_GCM_128_KEY_SIZE);
 	if (rc)
 		goto free_aead;
 
-	rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tx.tag_size);
-	if (!rc)
-		return 0;
+	rc = crypto_aead_setauthsize(*aead, cctx->tag_size);
+	if (rc)
+		goto free_aead;
+
+	if (!tx) {
+		/* Set up strparser */
+		memset(&cb, 0, sizeof(cb));
+		cb.rcv_msg = tls_queue;
+		cb.parse_msg = tls_read_size;
+
+		strp_init(&sw_ctx->strp, sk, &cb);
+
+		write_lock_bh(&sk->sk_callback_lock);
+		sw_ctx->saved_data_ready = sk->sk_data_ready;
+		sk->sk_data_ready = tls_data_ready;
+		write_unlock_bh(&sk->sk_callback_lock);
+
+		sw_ctx->sk_poll = sk->sk_socket->ops->poll;
+
+		strp_check_rcv(&sw_ctx->strp);
+	}
+
+	goto out;
 
 free_aead:
-	crypto_free_aead(sw_ctx->aead_send);
-	sw_ctx->aead_send = NULL;
+	crypto_free_aead(*aead);
+	*aead = NULL;
 free_rec_seq:
-	kfree(ctx->tx.rec_seq);
-	ctx->tx.rec_seq = NULL;
+	kfree(cctx->rec_seq);
+	cctx->rec_seq = NULL;
 free_iv:
 	kfree(ctx->tx.iv);
 	ctx->tx.iv = NULL;
-- 
cgit v1.2.3


From affaa0c724c14c914625647efe7b95dfbe8d08f2 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 23 Mar 2018 19:09:39 +0100
Subject: net/sched: remove tcf_idr_cleanup()

tcf_idr_cleanup() is no more used, so remove it.

Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h | 1 -
 net/sched/act_api.c   | 8 --------
 2 files changed, 9 deletions(-)

(limited to 'include/net')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index e0a9c2003b24..9e59ebfded62 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -149,7 +149,6 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
 int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		   struct tc_action **a, const struct tc_action_ops *ops,
 		   int bind, bool cpustats);
-void tcf_idr_cleanup(struct tc_action *a, struct nlattr *est);
 void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
 
 int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 57cf37145282..7bd1b964f021 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -296,14 +296,6 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
 }
 EXPORT_SYMBOL(tcf_idr_check);
 
-void tcf_idr_cleanup(struct tc_action *a, struct nlattr *est)
-{
-	if (est)
-		gen_kill_estimator(&a->tcfa_rate_est);
-	free_tcf(a);
-}
-EXPORT_SYMBOL(tcf_idr_cleanup);
-
 int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		   struct tc_action **a, const struct tc_action_ops *ops,
 		   int bind, bool cpustats)
-- 
cgit v1.2.3


From 088aa3eec2ce340b5d0f0f54430f5706223d5e45 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Mon, 26 Mar 2018 15:01:34 +0300
Subject: ip6mr: Support fib notifications

In similar fashion to ipmr, support fib notifications for ip6mr mfc and
vif related events. This would later allow drivers to react to said
notifications and offload the IPv6 mroutes.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv6.h |   2 +
 net/ipv6/ip6mr.c         | 112 +++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 106 insertions(+), 8 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 5b51110435fc..c29f09cfc9d7 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -96,6 +96,8 @@ struct netns_ipv6 {
 	atomic_t		fib6_sernum;
 	struct seg6_pernet_data *seg6_data;
 	struct fib_notifier_ops	*notifier_ops;
+	struct fib_notifier_ops	*ip6mr_notifier_ops;
+	unsigned int ipmr_seq; /* protected by rtnl_mutex */
 	struct {
 		struct hlist_head head;
 		spinlock_t	lock;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 7345bd6c4b7d..0be2f333e168 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -258,6 +258,16 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
 	fib_rules_unregister(net->ipv6.mr6_rules_ops);
 	rtnl_unlock();
 }
+
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR);
+}
+
+static unsigned int ip6mr_rules_seq_read(struct net *net)
+{
+	return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR);
+}
 #else
 #define ip6mr_for_each_table(mrt, net) \
 	for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
@@ -295,6 +305,16 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
 	net->ipv6.mrt6 = NULL;
 	rtnl_unlock();
 }
+
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+	return 0;
+}
+
+static unsigned int ip6mr_rules_seq_read(struct net *net)
+{
+	return 0;
+}
 #endif
 
 static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -653,10 +673,25 @@ failure:
 }
 #endif
 
-/*
- *	Delete a VIF entry
- */
+static int call_ip6mr_vif_entry_notifiers(struct net *net,
+					  enum fib_event_type event_type,
+					  struct vif_device *vif,
+					  mifi_t vif_index, u32 tb_id)
+{
+	return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
+				     vif, vif_index, tb_id,
+				     &net->ipv6.ipmr_seq);
+}
 
+static int call_ip6mr_mfc_entry_notifiers(struct net *net,
+					  enum fib_event_type event_type,
+					  struct mfc6_cache *mfc, u32 tb_id)
+{
+	return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
+				     &mfc->_c, tb_id, &net->ipv6.ipmr_seq);
+}
+
+/* Delete a VIF entry */
 static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
 		       struct list_head *head)
 {
@@ -669,6 +704,11 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
 
 	v = &mrt->vif_table[vifi];
 
+	if (VIF_EXISTS(mrt, vifi))
+		call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net),
+					       FIB_EVENT_VIF_DEL, v, vifi,
+					       mrt->id);
+
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
 	v->dev = NULL;
@@ -887,6 +927,8 @@ static int mif6_add(struct net *net, struct mr_table *mrt,
 	if (vifi + 1 > mrt->maxvif)
 		mrt->maxvif = vifi + 1;
 	write_unlock_bh(&mrt_lock);
+	call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD,
+				       v, vifi, mrt->id);
 	return 0;
 }
 
@@ -1175,6 +1217,8 @@ static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc,
 	rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params);
 	list_del_rcu(&c->_c.list);
 
+	call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+				       FIB_EVENT_ENTRY_DEL, c, mrt->id);
 	mr6_netlink_event(mrt, c, RTM_DELROUTE);
 	ip6mr_cache_free(c);
 	return 0;
@@ -1203,21 +1247,63 @@ static int ip6mr_device_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
+static unsigned int ip6mr_seq_read(struct net *net)
+{
+	ASSERT_RTNL();
+
+	return net->ipv6.ipmr_seq + ip6mr_rules_seq_read(net);
+}
+
+static int ip6mr_dump(struct net *net, struct notifier_block *nb)
+{
+	return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump,
+		       ip6mr_mr_table_iter, &mrt_lock);
+}
+
 static struct notifier_block ip6_mr_notifier = {
 	.notifier_call = ip6mr_device_event
 };
 
-/*
- *	Setup for IP multicast routing
- */
+static const struct fib_notifier_ops ip6mr_notifier_ops_template = {
+	.family		= RTNL_FAMILY_IP6MR,
+	.fib_seq_read	= ip6mr_seq_read,
+	.fib_dump	= ip6mr_dump,
+	.owner		= THIS_MODULE,
+};
+
+static int __net_init ip6mr_notifier_init(struct net *net)
+{
+	struct fib_notifier_ops *ops;
+
+	net->ipv6.ipmr_seq = 0;
 
+	ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	net->ipv6.ip6mr_notifier_ops = ops;
+
+	return 0;
+}
+
+static void __net_exit ip6mr_notifier_exit(struct net *net)
+{
+	fib_notifier_ops_unregister(net->ipv6.ip6mr_notifier_ops);
+	net->ipv6.ip6mr_notifier_ops = NULL;
+}
+
+/* Setup for IP multicast routing */
 static int __net_init ip6mr_net_init(struct net *net)
 {
 	int err;
 
+	err = ip6mr_notifier_init(net);
+	if (err)
+		return err;
+
 	err = ip6mr_rules_init(net);
 	if (err < 0)
-		goto fail;
+		goto ip6mr_rules_fail;
 
 #ifdef CONFIG_PROC_FS
 	err = -ENOMEM;
@@ -1235,7 +1321,8 @@ proc_cache_fail:
 proc_vif_fail:
 	ip6mr_rules_exit(net);
 #endif
-fail:
+ip6mr_rules_fail:
+	ip6mr_notifier_exit(net);
 	return err;
 }
 
@@ -1246,6 +1333,7 @@ static void __net_exit ip6mr_net_exit(struct net *net)
 	remove_proc_entry("ip6_mr_vif", net->proc_net);
 #endif
 	ip6mr_rules_exit(net);
+	ip6mr_notifier_exit(net);
 }
 
 static struct pernet_operations ip6mr_net_ops = {
@@ -1337,6 +1425,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
 		if (!mrtsock)
 			c->_c.mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
+		call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
+					       c, mrt->id);
 		mr6_netlink_event(mrt, c, RTM_NEWROUTE);
 		return 0;
 	}
@@ -1388,6 +1478,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
 		ip6mr_cache_resolve(net, mrt, uc, c);
 		ip6mr_cache_free(uc);
 	}
+	call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD,
+				       c, mrt->id);
 	mr6_netlink_event(mrt, c, RTM_NEWROUTE);
 	return 0;
 }
@@ -1424,6 +1516,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 		spin_lock_bh(&mfc_unres_lock);
 		list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
 			list_del(&c->list);
+			call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+						       FIB_EVENT_ENTRY_DEL,
+						       (struct mfc6_cache *)c,
+						       mrt->id);
 			mr6_netlink_event(mrt, (struct mfc6_cache *)c,
 					  RTM_DELROUTE);
 			ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
-- 
cgit v1.2.3


From 5306653850b444452937834adc5a5ac63bae275e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 16:55:00 +0800
Subject: sctp: remove unnecessary asoc in sctp_has_association

After Commit dae399d7fdee ("sctp: hold transport instead of assoc
when lookup assoc in rx path"), it put transport instead of asoc
in sctp_has_association. Variable 'asoc' is not used any more.

So this patch is to remove it, while at it,  it also changes the
return type of sctp_has_association to bool, and does the same
for it's caller sctp_endpoint_is_peeled_off.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  8 ++++----
 net/sctp/endpointola.c     |  8 ++++----
 net/sctp/input.c           | 13 ++++++-------
 3 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 012fb3e2f4cf..c63249ea34c3 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1341,12 +1341,12 @@ struct sctp_association *sctp_endpoint_lookup_assoc(
 	const struct sctp_endpoint *ep,
 	const union sctp_addr *paddr,
 	struct sctp_transport **);
-int sctp_endpoint_is_peeled_off(struct sctp_endpoint *,
-				const union sctp_addr *);
+bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
+				 const union sctp_addr *paddr);
 struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *,
 					struct net *, const union sctp_addr *);
-int sctp_has_association(struct net *net, const union sctp_addr *laddr,
-			 const union sctp_addr *paddr);
+bool sctp_has_association(struct net *net, const union sctp_addr *laddr,
+			  const union sctp_addr *paddr);
 
 int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
 		     const struct sctp_association *asoc,
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 8b3146816519..e2f5a3ee41a7 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -349,8 +349,8 @@ out:
 /* Look for any peeled off association from the endpoint that matches the
  * given peer address.
  */
-int sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
-				const union sctp_addr *paddr)
+bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
+				 const union sctp_addr *paddr)
 {
 	struct sctp_sockaddr_entry *addr;
 	struct sctp_bind_addr *bp;
@@ -362,10 +362,10 @@ int sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
 	 */
 	list_for_each_entry(addr, &bp->address_list, list) {
 		if (sctp_has_association(net, &addr->a, paddr))
-			return 1;
+			return true;
 	}
 
-	return 0;
+	return false;
 }
 
 /* Do delayed input processing.  This is scheduled by sctp_rcv().
diff --git a/net/sctp/input.c b/net/sctp/input.c
index b381d78548ac..ba8a6e6c36fa 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -1010,19 +1010,18 @@ struct sctp_association *sctp_lookup_association(struct net *net,
 }
 
 /* Is there an association matching the given local and peer addresses? */
-int sctp_has_association(struct net *net,
-			 const union sctp_addr *laddr,
-			 const union sctp_addr *paddr)
+bool sctp_has_association(struct net *net,
+			  const union sctp_addr *laddr,
+			  const union sctp_addr *paddr)
 {
-	struct sctp_association *asoc;
 	struct sctp_transport *transport;
 
-	if ((asoc = sctp_lookup_association(net, laddr, paddr, &transport))) {
+	if (sctp_lookup_association(net, laddr, paddr, &transport)) {
 		sctp_transport_put(transport);
-		return 1;
+		return true;
 	}
 
-	return 0;
+	return false;
 }
 
 /*
-- 
cgit v1.2.3


From 2f635ceeb22ba13c307236d69795fbb29cfa3e7c Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Tue, 27 Mar 2018 18:02:13 +0300
Subject: net: Drop pernet_operations::async

Synchronous pernet_operations are not allowed anymore.
All are asynchronous. So, drop the structure member.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/cma.c                  | 1 -
 drivers/net/bonding/bond_main.c                | 1 -
 drivers/net/geneve.c                           | 1 -
 drivers/net/gtp.c                              | 1 -
 drivers/net/ipvlan/ipvlan_main.c               | 1 -
 drivers/net/loopback.c                         | 1 -
 drivers/net/ppp/ppp_generic.c                  | 1 -
 drivers/net/ppp/pppoe.c                        | 1 -
 drivers/net/vrf.c                              | 1 -
 drivers/net/vxlan.c                            | 1 -
 drivers/net/wireless/mac80211_hwsim.c          | 1 -
 fs/lockd/svc.c                                 | 1 -
 fs/nfs/blocklayout/rpc_pipefs.c                | 1 -
 fs/nfs/dns_resolve.c                           | 1 -
 fs/nfs/inode.c                                 | 1 -
 fs/nfs_common/grace.c                          | 1 -
 fs/nfsd/nfsctl.c                               | 1 -
 fs/proc/proc_net.c                             | 1 -
 include/net/net_namespace.h                    | 6 ------
 kernel/audit.c                                 | 1 -
 lib/kobject_uevent.c                           | 1 -
 net/8021q/vlan.c                               | 1 -
 net/bridge/br.c                                | 1 -
 net/bridge/br_netfilter_hooks.c                | 1 -
 net/bridge/netfilter/ebtable_broute.c          | 1 -
 net/bridge/netfilter/ebtable_filter.c          | 1 -
 net/bridge/netfilter/ebtable_nat.c             | 1 -
 net/bridge/netfilter/nf_log_bridge.c           | 1 -
 net/caif/caif_dev.c                            | 1 -
 net/can/af_can.c                               | 1 -
 net/can/bcm.c                                  | 1 -
 net/can/gw.c                                   | 1 -
 net/core/dev.c                                 | 2 --
 net/core/fib_notifier.c                        | 1 -
 net/core/fib_rules.c                           | 1 -
 net/core/net-procfs.c                          | 2 --
 net/core/net_namespace.c                       | 2 --
 net/core/pktgen.c                              | 1 -
 net/core/rtnetlink.c                           | 1 -
 net/core/sock.c                                | 2 --
 net/core/sock_diag.c                           | 1 -
 net/core/sysctl_net_core.c                     | 1 -
 net/dccp/ipv4.c                                | 1 -
 net/dccp/ipv6.c                                | 1 -
 net/ieee802154/6lowpan/reassembly.c            | 1 -
 net/ieee802154/core.c                          | 1 -
 net/ipv4/af_inet.c                             | 2 --
 net/ipv4/arp.c                                 | 1 -
 net/ipv4/devinet.c                             | 1 -
 net/ipv4/fib_frontend.c                        | 1 -
 net/ipv4/fou.c                                 | 1 -
 net/ipv4/icmp.c                                | 1 -
 net/ipv4/igmp.c                                | 1 -
 net/ipv4/ip_fragment.c                         | 1 -
 net/ipv4/ip_gre.c                              | 3 ---
 net/ipv4/ip_vti.c                              | 1 -
 net/ipv4/ipip.c                                | 1 -
 net/ipv4/ipmr.c                                | 1 -
 net/ipv4/netfilter/arp_tables.c                | 1 -
 net/ipv4/netfilter/arptable_filter.c           | 1 -
 net/ipv4/netfilter/ip_tables.c                 | 1 -
 net/ipv4/netfilter/ipt_CLUSTERIP.c             | 1 -
 net/ipv4/netfilter/iptable_filter.c            | 1 -
 net/ipv4/netfilter/iptable_mangle.c            | 1 -
 net/ipv4/netfilter/iptable_nat.c               | 1 -
 net/ipv4/netfilter/iptable_raw.c               | 1 -
 net/ipv4/netfilter/iptable_security.c          | 1 -
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 1 -
 net/ipv4/netfilter/nf_defrag_ipv4.c            | 1 -
 net/ipv4/netfilter/nf_log_arp.c                | 1 -
 net/ipv4/netfilter/nf_log_ipv4.c               | 1 -
 net/ipv4/ping.c                                | 1 -
 net/ipv4/proc.c                                | 1 -
 net/ipv4/raw.c                                 | 1 -
 net/ipv4/route.c                               | 4 ----
 net/ipv4/sysctl_net_ipv4.c                     | 1 -
 net/ipv4/tcp_ipv4.c                            | 2 --
 net/ipv4/tcp_metrics.c                         | 1 -
 net/ipv4/udp.c                                 | 2 --
 net/ipv4/udplite.c                             | 1 -
 net/ipv4/xfrm4_policy.c                        | 1 -
 net/ipv6/addrconf.c                            | 2 --
 net/ipv6/addrlabel.c                           | 1 -
 net/ipv6/af_inet6.c                            | 1 -
 net/ipv6/fib6_rules.c                          | 1 -
 net/ipv6/icmp.c                                | 1 -
 net/ipv6/ila/ila_xlat.c                        | 1 -
 net/ipv6/ip6_fib.c                             | 1 -
 net/ipv6/ip6_flowlabel.c                       | 1 -
 net/ipv6/ip6_gre.c                             | 1 -
 net/ipv6/ip6_tunnel.c                          | 1 -
 net/ipv6/ip6_vti.c                             | 1 -
 net/ipv6/ip6mr.c                               | 1 -
 net/ipv6/mcast.c                               | 1 -
 net/ipv6/ndisc.c                               | 1 -
 net/ipv6/netfilter/ip6_tables.c                | 1 -
 net/ipv6/netfilter/ip6table_filter.c           | 1 -
 net/ipv6/netfilter/ip6table_mangle.c           | 1 -
 net/ipv6/netfilter/ip6table_nat.c              | 1 -
 net/ipv6/netfilter/ip6table_raw.c              | 1 -
 net/ipv6/netfilter/ip6table_security.c         | 1 -
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 1 -
 net/ipv6/netfilter/nf_conntrack_reasm.c        | 1 -
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      | 1 -
 net/ipv6/netfilter/nf_log_ipv6.c               | 1 -
 net/ipv6/ping.c                                | 1 -
 net/ipv6/proc.c                                | 1 -
 net/ipv6/raw.c                                 | 1 -
 net/ipv6/reassembly.c                          | 1 -
 net/ipv6/route.c                               | 3 ---
 net/ipv6/seg6.c                                | 1 -
 net/ipv6/sit.c                                 | 1 -
 net/ipv6/sysctl_net_ipv6.c                     | 1 -
 net/ipv6/tcp_ipv6.c                            | 1 -
 net/ipv6/udplite.c                             | 1 -
 net/ipv6/xfrm6_policy.c                        | 1 -
 net/ipv6/xfrm6_tunnel.c                        | 1 -
 net/kcm/kcmproc.c                              | 1 -
 net/kcm/kcmsock.c                              | 1 -
 net/key/af_key.c                               | 1 -
 net/l2tp/l2tp_core.c                           | 1 -
 net/l2tp/l2tp_ppp.c                            | 1 -
 net/mpls/af_mpls.c                             | 1 -
 net/netfilter/core.c                           | 1 -
 net/netfilter/ipset/ip_set_core.c              | 1 -
 net/netfilter/ipvs/ip_vs_core.c                | 2 --
 net/netfilter/ipvs/ip_vs_ftp.c                 | 1 -
 net/netfilter/ipvs/ip_vs_lblc.c                | 1 -
 net/netfilter/ipvs/ip_vs_lblcr.c               | 1 -
 net/netfilter/nf_conntrack_netlink.c           | 1 -
 net/netfilter/nf_conntrack_proto_gre.c         | 1 -
 net/netfilter/nf_conntrack_standalone.c        | 1 -
 net/netfilter/nf_log.c                         | 1 -
 net/netfilter/nf_log_netdev.c                  | 1 -
 net/netfilter/nf_synproxy_core.c               | 1 -
 net/netfilter/nf_tables_api.c                  | 1 -
 net/netfilter/nfnetlink.c                      | 1 -
 net/netfilter/nfnetlink_acct.c                 | 1 -
 net/netfilter/nfnetlink_cttimeout.c            | 1 -
 net/netfilter/nfnetlink_log.c                  | 1 -
 net/netfilter/nfnetlink_queue.c                | 1 -
 net/netfilter/x_tables.c                       | 1 -
 net/netfilter/xt_hashlimit.c                   | 1 -
 net/netfilter/xt_recent.c                      | 1 -
 net/netlink/af_netlink.c                       | 2 --
 net/netlink/genetlink.c                        | 1 -
 net/openvswitch/datapath.c                     | 1 -
 net/packet/af_packet.c                         | 1 -
 net/phonet/pn_dev.c                            | 1 -
 net/rds/tcp.c                                  | 1 -
 net/rxrpc/net_ns.c                             | 1 -
 net/sched/act_api.c                            | 1 -
 net/sched/act_bpf.c                            | 1 -
 net/sched/act_connmark.c                       | 1 -
 net/sched/act_csum.c                           | 1 -
 net/sched/act_gact.c                           | 1 -
 net/sched/act_ife.c                            | 1 -
 net/sched/act_ipt.c                            | 2 --
 net/sched/act_mirred.c                         | 1 -
 net/sched/act_nat.c                            | 1 -
 net/sched/act_pedit.c                          | 1 -
 net/sched/act_police.c                         | 1 -
 net/sched/act_sample.c                         | 1 -
 net/sched/act_simple.c                         | 1 -
 net/sched/act_skbedit.c                        | 1 -
 net/sched/act_skbmod.c                         | 1 -
 net/sched/act_tunnel_key.c                     | 1 -
 net/sched/act_vlan.c                           | 1 -
 net/sched/cls_api.c                            | 1 -
 net/sched/sch_api.c                            | 1 -
 net/sctp/protocol.c                            | 2 --
 net/sunrpc/auth_gss/auth_gss.c                 | 1 -
 net/sunrpc/sunrpc_syms.c                       | 1 -
 net/sysctl_net.c                               | 1 -
 net/tipc/core.c                                | 1 -
 net/unix/af_unix.c                             | 1 -
 net/wireless/core.c                            | 1 -
 net/wireless/wext-core.c                       | 1 -
 net/xfrm/xfrm_policy.c                         | 1 -
 net/xfrm/xfrm_user.c                           | 1 -
 security/selinux/hooks.c                       | 1 -
 security/smack/smack_netfilter.c               | 1 -
 182 files changed, 206 deletions(-)

(limited to 'include/net')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 66f203730e80..6ab1059fed66 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4554,7 +4554,6 @@ static struct pernet_operations cma_pernet_operations = {
 	.exit = cma_exit_net,
 	.id = &cma_pernet_id,
 	.size = sizeof(struct cma_pernet),
-	.async = true,
 };
 
 static int __init cma_init(void)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4c19d23dd282..c669554d70bb 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4791,7 +4791,6 @@ static struct pernet_operations bond_net_ops = {
 	.exit = bond_net_exit,
 	.id   = &bond_net_id,
 	.size = sizeof(struct bond_net),
-	.async = true,
 };
 
 static int __init bonding_init(void)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 516dd59249d7..b919e89a9b93 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1694,7 +1694,6 @@ static struct pernet_operations geneve_net_ops = {
 	.exit_batch = geneve_exit_batch_net,
 	.id   = &geneve_net_id,
 	.size = sizeof(struct geneve_net),
-	.async = true,
 };
 
 static int __init geneve_init_module(void)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 127edd23018f..f38e32a7ec9c 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1325,7 +1325,6 @@ static struct pernet_operations gtp_net_ops = {
 	.exit	= gtp_net_exit,
 	.id	= &gtp_net_id,
 	.size	= sizeof(struct gtp_net),
-	.async	= true,
 };
 
 static int __init gtp_init(void)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 743d37fb034a..450eec264a5e 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -1040,7 +1040,6 @@ static struct pernet_operations ipvlan_net_ops = {
 	.id = &ipvlan_netid,
 	.size = sizeof(struct ipvlan_netns),
 	.exit = ipvlan_ns_exit,
-	.async = true,
 };
 
 static int __init ipvlan_init_module(void)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index b97a907ea5aa..30612497643c 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -230,5 +230,4 @@ out:
 /* Registered in net/core/dev.c */
 struct pernet_operations __net_initdata loopback_net_ops = {
 	.init = loopback_net_init,
-	.async = true,
 };
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 22fcff3c7a9a..dc7c7ec43202 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -970,7 +970,6 @@ static struct pernet_operations ppp_net_ops = {
 	.exit = ppp_exit_net,
 	.id   = &ppp_net_id,
 	.size = sizeof(struct ppp_net),
-	.async = true,
 };
 
 static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set)
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index f9552a400271..1483bc7b01e1 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1161,7 +1161,6 @@ static struct pernet_operations pppoe_net_ops = {
 	.exit = pppoe_exit_net,
 	.id   = &pppoe_net_id,
 	.size = sizeof(struct pppoe_net),
-	.async = true,
 };
 
 static int __init pppoe_init(void)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index c6be49d3a9eb..102582459bef 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1435,7 +1435,6 @@ static struct pernet_operations vrf_net_ops __net_initdata = {
 	.init = vrf_netns_init,
 	.id   = &vrf_net_id,
 	.size = sizeof(bool),
-	.async = true,
 };
 
 static int __init vrf_init_module(void)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index aa5f034d6ad1..fab7a4db249e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3752,7 +3752,6 @@ static struct pernet_operations vxlan_net_ops = {
 	.exit_batch = vxlan_exit_batch_net,
 	.id   = &vxlan_net_id,
 	.size = sizeof(struct vxlan_net),
-	.async = true,
 };
 
 static int __init vxlan_init_module(void)
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 100cf42db65d..a37f4b1d9d30 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3542,7 +3542,6 @@ static struct pernet_operations hwsim_net_ops = {
 	.exit = hwsim_exit_net,
 	.id   = &hwsim_net_id,
 	.size = sizeof(struct hwsim_net),
-	.async = true,
 };
 
 static void hwsim_exit_netlink(void)
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 2dee4e03ff1c..9c36d614bf89 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -709,7 +709,6 @@ static struct pernet_operations lockd_net_ops = {
 	.exit = lockd_exit_net,
 	.id = &lockd_net_id,
 	.size = sizeof(struct lockd_net),
-	.async = true,
 };
 
 
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index ef9fa111b009..9fb067a6f7e0 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -261,7 +261,6 @@ static void nfs4blocklayout_net_exit(struct net *net)
 static struct pernet_operations nfs4blocklayout_net_ops = {
 	.init = nfs4blocklayout_net_init,
 	.exit = nfs4blocklayout_net_exit,
-	.async = true,
 };
 
 int __init bl_init_pipefs(void)
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index e90bd69ab653..060c658eab66 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -410,7 +410,6 @@ static void nfs4_dns_net_exit(struct net *net)
 static struct pernet_operations nfs4_dns_resolver_ops = {
 	.init = nfs4_dns_net_init,
 	.exit = nfs4_dns_net_exit,
-	.async = true,
 };
 
 static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 6c3083c992e5..7d893543cf3b 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2122,7 +2122,6 @@ static struct pernet_operations nfs_net_ops = {
 	.exit = nfs_net_exit,
 	.id   = &nfs_net_id,
 	.size = sizeof(struct nfs_net),
-	.async = true,
 };
 
 /*
diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c
index 8c743a405df6..5be08f02a76b 100644
--- a/fs/nfs_common/grace.c
+++ b/fs/nfs_common/grace.c
@@ -118,7 +118,6 @@ static struct pernet_operations grace_net_ops = {
 	.exit = grace_exit_net,
 	.id   = &grace_net_id,
 	.size = sizeof(struct list_head),
-	.async = true,
 };
 
 static int __init
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 1e3824e6cce0..d107b4426f7e 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1263,7 +1263,6 @@ static struct pernet_operations nfsd_net_ops = {
 	.exit = nfsd_exit_net,
 	.id   = &nfsd_net_id,
 	.size = sizeof(struct nfsd_net),
-	.async = true,
 };
 
 static int __init init_nfsd(void)
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index da6f8733c9c5..68c06ae7888c 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -237,7 +237,6 @@ static __net_exit void proc_net_ns_exit(struct net *net)
 static struct pernet_operations __net_initdata proc_net_ns_ops = {
 	.init = proc_net_ns_init,
 	.exit = proc_net_ns_exit,
-	.async = true,
 };
 
 int __init proc_net_init(void)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 09e30bdc7876..37bcf8382b61 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -333,12 +333,6 @@ struct pernet_operations {
 	void (*exit_batch)(struct list_head *net_exit_list);
 	unsigned int *id;
 	size_t size;
-	/*
-	 * Indicates above methods are allowed to be executed in parallel
-	 * with methods of any other pernet_operations, i.e. they are not
-	 * need write locked net_sem.
-	 */
-	bool async;
 };
 
 /*
diff --git a/kernel/audit.c b/kernel/audit.c
index 5e49b614d0e6..227db99b0f19 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1526,7 +1526,6 @@ static struct pernet_operations audit_net_ops __net_initdata = {
 	.exit = audit_net_exit,
 	.id = &audit_net_id,
 	.size = sizeof(struct audit_net),
-	.async = true,
 };
 
 /* Initialize audit support at boot time. */
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index fa10ad8e9b17..15ea216a67ce 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -724,7 +724,6 @@ static void uevent_net_exit(struct net *net)
 static struct pernet_operations uevent_net_ops = {
 	.init	= uevent_net_init,
 	.exit	= uevent_net_exit,
-	.async  = true,
 };
 
 static int __init kobject_uevent_init(void)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index bd0ed39f65fb..bad01b14a4ad 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -729,7 +729,6 @@ static struct pernet_operations vlan_net_ops = {
 	.exit = vlan_exit_net,
 	.id   = &vlan_net_id,
 	.size = sizeof(struct vlan_net),
-	.async = true,
 };
 
 static int __init vlan_proto_init(void)
diff --git a/net/bridge/br.c b/net/bridge/br.c
index a3f95ab9d6a3..26e1616b2c90 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -188,7 +188,6 @@ static void __net_exit br_net_exit(struct net *net)
 
 static struct pernet_operations br_net_ops = {
 	.exit	= br_net_exit,
-	.async	= true,
 };
 
 static const struct stp_proto br_stp_proto = {
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index c2120eb889a9..9b16eaf33819 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -969,7 +969,6 @@ static struct pernet_operations brnf_net_ops __read_mostly = {
 	.exit = brnf_exit_net,
 	.id   = &brnf_net_id,
 	.size = sizeof(struct brnf_net),
-	.async = true,
 };
 
 static struct notifier_block brnf_notifier __read_mostly = {
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index f070b5e5b9dd..276b60262981 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -77,7 +77,6 @@ static void __net_exit broute_net_exit(struct net *net)
 static struct pernet_operations broute_net_ops = {
 	.init = broute_net_init,
 	.exit = broute_net_exit,
-	.async = true,
 };
 
 static int __init ebtable_broute_init(void)
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 4151afc8efcc..c41da5fac84f 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -105,7 +105,6 @@ static void __net_exit frame_filter_net_exit(struct net *net)
 static struct pernet_operations frame_filter_net_ops = {
 	.init = frame_filter_net_init,
 	.exit = frame_filter_net_exit,
-	.async = true,
 };
 
 static int __init ebtable_filter_init(void)
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index b8da2dfe2ec5..08df7406ecb3 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -105,7 +105,6 @@ static void __net_exit frame_nat_net_exit(struct net *net)
 static struct pernet_operations frame_nat_net_ops = {
 	.init = frame_nat_net_init,
 	.exit = frame_nat_net_exit,
-	.async = true,
 };
 
 static int __init ebtable_nat_init(void)
diff --git a/net/bridge/netfilter/nf_log_bridge.c b/net/bridge/netfilter/nf_log_bridge.c
index 91bfc2ac055a..bd2b3c78f59b 100644
--- a/net/bridge/netfilter/nf_log_bridge.c
+++ b/net/bridge/netfilter/nf_log_bridge.c
@@ -48,7 +48,6 @@ static void __net_exit nf_log_bridge_net_exit(struct net *net)
 static struct pernet_operations nf_log_bridge_net_ops = {
 	.init = nf_log_bridge_net_init,
 	.exit = nf_log_bridge_net_exit,
-	.async = true,
 };
 
 static int __init nf_log_bridge_init(void)
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 7a78268cc572..e0adcd123f48 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -544,7 +544,6 @@ static struct pernet_operations caif_net_ops = {
 	.exit = caif_exit_net,
 	.id   = &caif_net_id,
 	.size = sizeof(struct caif_net),
-	.async = true,
 };
 
 /* Initialize Caif devices list */
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 2f0d0a72e4b5..1684ba5b51eb 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -954,7 +954,6 @@ static struct notifier_block can_netdev_notifier __read_mostly = {
 static struct pernet_operations can_pernet_ops __read_mostly = {
 	.init = can_pernet_init,
 	.exit = can_pernet_exit,
-	.async = true,
 };
 
 static __init int can_init(void)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 26730d39e048..ac5e5e34fee3 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1717,7 +1717,6 @@ static void canbcm_pernet_exit(struct net *net)
 static struct pernet_operations canbcm_pernet_ops __read_mostly = {
 	.init = canbcm_pernet_init,
 	.exit = canbcm_pernet_exit,
-	.async = true,
 };
 
 static int __init bcm_module_init(void)
diff --git a/net/can/gw.c b/net/can/gw.c
index 8d71e199d5b3..faa3da88a127 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -1010,7 +1010,6 @@ static void __net_exit cangw_pernet_exit(struct net *net)
 static struct pernet_operations cangw_pernet_ops = {
 	.init = cangw_pernet_init,
 	.exit = cangw_pernet_exit,
-	.async = true,
 };
 
 static __init int cgw_module_init(void)
diff --git a/net/core/dev.c b/net/core/dev.c
index 97a96df4b6da..e13807b5c84d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8883,7 +8883,6 @@ static void __net_exit netdev_exit(struct net *net)
 static struct pernet_operations __net_initdata netdev_net_ops = {
 	.init = netdev_init,
 	.exit = netdev_exit,
-	.async = true,
 };
 
 static void __net_exit default_device_exit(struct net *net)
@@ -8984,7 +8983,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 static struct pernet_operations __net_initdata default_device_ops = {
 	.exit = default_device_exit,
 	.exit_batch = default_device_exit_batch,
-	.async = true,
 };
 
 /*
diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c
index 5ace0705a3f9..0c048bdeb016 100644
--- a/net/core/fib_notifier.c
+++ b/net/core/fib_notifier.c
@@ -171,7 +171,6 @@ static void __net_exit fib_notifier_net_exit(struct net *net)
 static struct pernet_operations fib_notifier_net_ops = {
 	.init = fib_notifier_net_init,
 	.exit = fib_notifier_net_exit,
-	.async = true,
 };
 
 static int __init fib_notifier_init(void)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index f6f04fc0f629..9d87ce868402 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -1130,7 +1130,6 @@ static void __net_exit fib_rules_net_exit(struct net *net)
 static struct pernet_operations fib_rules_net_ops = {
 	.init = fib_rules_net_init,
 	.exit = fib_rules_net_exit,
-	.async = true,
 };
 
 static int __init fib_rules_init(void)
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index dd6ae431d038..9737302907b1 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -349,7 +349,6 @@ static void __net_exit dev_proc_net_exit(struct net *net)
 static struct pernet_operations __net_initdata dev_proc_ops = {
 	.init = dev_proc_net_init,
 	.exit = dev_proc_net_exit,
-	.async = true,
 };
 
 static int dev_mc_seq_show(struct seq_file *seq, void *v)
@@ -406,7 +405,6 @@ static void __net_exit dev_mc_net_exit(struct net *net)
 static struct pernet_operations __net_initdata dev_mc_net_ops = {
 	.init = dev_mc_net_init,
 	.exit = dev_mc_net_exit,
-	.async = true,
 };
 
 int __init dev_proc_init(void)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 0f614523a13f..eef17ad29dea 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -338,7 +338,6 @@ static int __net_init net_defaults_init_net(struct net *net)
 
 static struct pernet_operations net_defaults_ops = {
 	.init = net_defaults_init_net,
-	.async = true,
 };
 
 static __init int net_defaults_init(void)
@@ -628,7 +627,6 @@ static __net_exit void net_ns_net_exit(struct net *net)
 static struct pernet_operations __net_initdata net_ns_ops = {
 	.init = net_ns_net_init,
 	.exit = net_ns_net_exit,
-	.async = true,
 };
 
 static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 545cf08cd558..7e4ede34cc52 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3852,7 +3852,6 @@ static struct pernet_operations pg_net_ops = {
 	.exit = pg_net_exit,
 	.id   = &pg_net_id,
 	.size = sizeof(struct pktgen_net),
-	.async = true,
 };
 
 static int __init pg_init(void)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 87079eaa871b..31438b63d4b4 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4730,7 +4730,6 @@ static void __net_exit rtnetlink_net_exit(struct net *net)
 static struct pernet_operations rtnetlink_net_ops = {
 	.init = rtnetlink_net_init,
 	.exit = rtnetlink_net_exit,
-	.async = true,
 };
 
 void __init rtnetlink_init(void)
diff --git a/net/core/sock.c b/net/core/sock.c
index 8cee2920a47f..6444525f610c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3175,7 +3175,6 @@ static void __net_exit sock_inuse_exit_net(struct net *net)
 static struct pernet_operations net_inuse_ops = {
 	.init = sock_inuse_init_net,
 	.exit = sock_inuse_exit_net,
-	.async = true,
 };
 
 static __init int net_inuse_init(void)
@@ -3470,7 +3469,6 @@ static __net_exit void proto_exit_net(struct net *net)
 static __net_initdata struct pernet_operations proto_net_ops = {
 	.init = proto_init_net,
 	.exit = proto_exit_net,
-	.async = true,
 };
 
 static int __init proto_init(void)
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a3392a8f9276..c37b5be7c5e4 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -324,7 +324,6 @@ static void __net_exit diag_net_exit(struct net *net)
 static struct pernet_operations diag_net_ops = {
 	.init = diag_net_init,
 	.exit = diag_net_exit,
-	.async = true,
 };
 
 static int __init sock_diag_init(void)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 4f47f92459cc..b3b609f0eeb5 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -584,7 +584,6 @@ static __net_exit void sysctl_core_net_exit(struct net *net)
 static __net_initdata struct pernet_operations sysctl_core_ops = {
 	.init = sysctl_core_net_init,
 	.exit = sysctl_core_net_exit,
-	.async = true,
 };
 
 static __init int sysctl_core_init(void)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 13ad28ab1e79..e65fcb45c3f6 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -1031,7 +1031,6 @@ static struct pernet_operations dccp_v4_ops = {
 	.init	= dccp_v4_init_net,
 	.exit	= dccp_v4_exit_net,
 	.exit_batch = dccp_v4_exit_batch,
-	.async	= true,
 };
 
 static int __init dccp_v4_init(void)
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 2f48c020f8c3..5df7857fc0f3 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1116,7 +1116,6 @@ static struct pernet_operations dccp_v6_ops = {
 	.init   = dccp_v6_init_net,
 	.exit   = dccp_v6_exit_net,
 	.exit_batch = dccp_v6_exit_batch,
-	.async	= true,
 };
 
 static int __init dccp_v6_init(void)
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index a9ccb1322f69..85bf86ad6b18 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -603,7 +603,6 @@ static void __net_exit lowpan_frags_exit_net(struct net *net)
 static struct pernet_operations lowpan_frags_ops = {
 	.init = lowpan_frags_init_net,
 	.exit = lowpan_frags_exit_net,
-	.async = true,
 };
 
 int __init lowpan_net_frag_init(void)
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 9104943c15ba..cb7176cd4cd6 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -345,7 +345,6 @@ static void __net_exit cfg802154_pernet_exit(struct net *net)
 
 static struct pernet_operations cfg802154_pernet_ops = {
 	.exit = cfg802154_pernet_exit,
-	.async = true,
 };
 
 static int __init wpan_phy_class_init(void)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e8c7fad8c329..f98e2f0db841 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1735,7 +1735,6 @@ static __net_exit void ipv4_mib_exit_net(struct net *net)
 static __net_initdata struct pernet_operations ipv4_mib_ops = {
 	.init = ipv4_mib_init_net,
 	.exit = ipv4_mib_exit_net,
-	.async = true,
 };
 
 static int __init init_ipv4_mibs(void)
@@ -1789,7 +1788,6 @@ static __net_exit void inet_exit_net(struct net *net)
 static __net_initdata struct pernet_operations af_inet_ops = {
 	.init = inet_init_net,
 	.exit = inet_exit_net,
-	.async = true,
 };
 
 static int __init init_inet_pernet_ops(void)
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 4c6ba0fb2630..be4c595edccb 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1447,7 +1447,6 @@ static void __net_exit arp_net_exit(struct net *net)
 static struct pernet_operations arp_net_ops = {
 	.init = arp_net_init,
 	.exit = arp_net_exit,
-	.async = true,
 };
 
 static int __init arp_proc_init(void)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5ae0d1f097ca..40f001782c1b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2469,7 +2469,6 @@ static __net_exit void devinet_exit_net(struct net *net)
 static __net_initdata struct pernet_operations devinet_ops = {
 	.init = devinet_init_net,
 	.exit = devinet_exit_net,
-	.async = true,
 };
 
 static struct rtnl_af_ops inet_af_ops __read_mostly = {
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index ac71c3d496c0..f05afaf3235c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1362,7 +1362,6 @@ static void __net_exit fib_net_exit(struct net *net)
 static struct pernet_operations fib_net_ops = {
 	.init = fib_net_init,
 	.exit = fib_net_exit,
-	.async = true,
 };
 
 void __init ip_fib_init(void)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index d3e1a9af478b..1540db65241a 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -1081,7 +1081,6 @@ static struct pernet_operations fou_net_ops = {
 	.exit = fou_exit_net,
 	.id   = &fou_net_id,
 	.size = sizeof(struct fou_net),
-	.async = true,
 };
 
 static int __init fou_init(void)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index cc56efa64d5c..1617604c9284 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1257,7 +1257,6 @@ fail:
 static struct pernet_operations __net_initdata icmp_sk_ops = {
        .init = icmp_sk_init,
        .exit = icmp_sk_exit,
-       .async = true,
 };
 
 int __init icmp_init(void)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index f17cd83ba164..b26a81a7de42 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -3028,7 +3028,6 @@ static void __net_exit igmp_net_exit(struct net *net)
 static struct pernet_operations igmp_net_ops = {
 	.init = igmp_net_init,
 	.exit = igmp_net_exit,
-	.async = true,
 };
 #endif
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 5e843ae5e468..bbf1b94942c0 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -885,7 +885,6 @@ static void __net_exit ipv4_frags_exit_net(struct net *net)
 static struct pernet_operations ip4_frags_ops = {
 	.init = ipv4_frags_init_net,
 	.exit = ipv4_frags_exit_net,
-	.async = true,
 };
 
 void __init ipfrag_init(void)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 9ab1aa2f7660..a8772a978224 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1044,7 +1044,6 @@ static struct pernet_operations ipgre_net_ops = {
 	.exit_batch = ipgre_exit_batch_net,
 	.id   = &ipgre_net_id,
 	.size = sizeof(struct ip_tunnel_net),
-	.async = true,
 };
 
 static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -1628,7 +1627,6 @@ static struct pernet_operations ipgre_tap_net_ops = {
 	.exit_batch = ipgre_tap_exit_batch_net,
 	.id   = &gre_tap_net_id,
 	.size = sizeof(struct ip_tunnel_net),
-	.async = true,
 };
 
 static int __net_init erspan_init_net(struct net *net)
@@ -1647,7 +1645,6 @@ static struct pernet_operations erspan_net_ops = {
 	.exit_batch = erspan_exit_batch_net,
 	.id   = &erspan_net_id,
 	.size = sizeof(struct ip_tunnel_net),
-	.async = true,
 };
 
 static int __init ipgre_init(void)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index b10bf563afd9..51b1669334fe 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -454,7 +454,6 @@ static struct pernet_operations vti_net_ops = {
 	.exit_batch = vti_exit_batch_net,
 	.id   = &vti_net_id,
 	.size = sizeof(struct ip_tunnel_net),
-	.async = true,
 };
 
 static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 9c5a4d164f09..c891235b4966 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -669,7 +669,6 @@ static struct pernet_operations ipip_net_ops = {
 	.exit_batch = ipip_exit_batch_net,
 	.id   = &ipip_net_id,
 	.size = sizeof(struct ip_tunnel_net),
-	.async = true,
 };
 
 static int __init ipip_init(void)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index e79211a8537c..2fb4de3f7f66 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -3009,7 +3009,6 @@ static void __net_exit ipmr_net_exit(struct net *net)
 static struct pernet_operations ipmr_net_ops = {
 	.init = ipmr_net_init,
 	.exit = ipmr_net_exit,
-	.async = true,
 };
 
 int __init ip_mr_init(void)
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index c36ffce3c812..e3e420f3ba7b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1635,7 +1635,6 @@ static void __net_exit arp_tables_net_exit(struct net *net)
 static struct pernet_operations arp_tables_net_ops = {
 	.init = arp_tables_net_init,
 	.exit = arp_tables_net_exit,
-	.async = true,
 };
 
 static int __init arp_tables_init(void)
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index 49c2490193ae..8f8713b4388f 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -65,7 +65,6 @@ static void __net_exit arptable_filter_net_exit(struct net *net)
 
 static struct pernet_operations arptable_filter_net_ops = {
 	.exit = arptable_filter_net_exit,
-	.async = true,
 };
 
 static int __init arptable_filter_init(void)
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index d4f7584d2dbe..e38395a8dcf2 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1916,7 +1916,6 @@ static void __net_exit ip_tables_net_exit(struct net *net)
 static struct pernet_operations ip_tables_net_ops = {
 	.init = ip_tables_net_init,
 	.exit = ip_tables_net_exit,
-	.async = true,
 };
 
 static int __init ip_tables_init(void)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 31b4cca588d0..2c8d313ae216 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -845,7 +845,6 @@ static struct pernet_operations clusterip_net_ops = {
 	.exit = clusterip_net_exit,
 	.id   = &clusterip_net_id,
 	.size = sizeof(struct clusterip_net),
-	.async = true,
 };
 
 static int __init clusterip_tg_init(void)
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index c1c136a93911..9ac92ea7b93c 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -87,7 +87,6 @@ static void __net_exit iptable_filter_net_exit(struct net *net)
 static struct pernet_operations iptable_filter_net_ops = {
 	.init = iptable_filter_net_init,
 	.exit = iptable_filter_net_exit,
-	.async = true,
 };
 
 static int __init iptable_filter_init(void)
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index f6074059531a..dea138ca8925 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -113,7 +113,6 @@ static void __net_exit iptable_mangle_net_exit(struct net *net)
 
 static struct pernet_operations iptable_mangle_net_ops = {
 	.exit = iptable_mangle_net_exit,
-	.async = true,
 };
 
 static int __init iptable_mangle_init(void)
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index b771af74be79..0f7255cc65ee 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -129,7 +129,6 @@ static void __net_exit iptable_nat_net_exit(struct net *net)
 
 static struct pernet_operations iptable_nat_net_ops = {
 	.exit	= iptable_nat_net_exit,
-	.async	= true,
 };
 
 static int __init iptable_nat_init(void)
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 963753e50842..960625aabf04 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -76,7 +76,6 @@ static void __net_exit iptable_raw_net_exit(struct net *net)
 
 static struct pernet_operations iptable_raw_net_ops = {
 	.exit = iptable_raw_net_exit,
-	.async = true,
 };
 
 static int __init iptable_raw_init(void)
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index c40d6b3d8b6a..e5379fe57b64 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -76,7 +76,6 @@ static void __net_exit iptable_security_net_exit(struct net *net)
 
 static struct pernet_operations iptable_security_net_ops = {
 	.exit = iptable_security_net_exit,
-	.async = true,
 };
 
 static int __init iptable_security_init(void)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 6531f69db010..b50721d9d30e 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -399,7 +399,6 @@ static struct pernet_operations ipv4_net_ops = {
 	.exit = ipv4_net_exit,
 	.id = &conntrack4_net_id,
 	.size = sizeof(struct conntrack4_net),
-	.async = true,
 };
 
 static int __init nf_conntrack_l3proto_ipv4_init(void)
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 57244b62a4fc..a0d3ad60a411 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -118,7 +118,6 @@ static void __net_exit defrag4_net_exit(struct net *net)
 
 static struct pernet_operations defrag4_net_ops = {
 	.exit = defrag4_net_exit,
-	.async = true,
 };
 
 static int __init nf_defrag_init(void)
diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index 162293469ac2..df5c2a2061a4 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/net/ipv4/netfilter/nf_log_arp.c
@@ -122,7 +122,6 @@ static void __net_exit nf_log_arp_net_exit(struct net *net)
 static struct pernet_operations nf_log_arp_net_ops = {
 	.init = nf_log_arp_net_init,
 	.exit = nf_log_arp_net_exit,
-	.async = true,
 };
 
 static int __init nf_log_arp_init(void)
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 7a06de140f3c..4388de0e5380 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -358,7 +358,6 @@ static void __net_exit nf_log_ipv4_net_exit(struct net *net)
 static struct pernet_operations nf_log_ipv4_net_ops = {
 	.init = nf_log_ipv4_net_init,
 	.exit = nf_log_ipv4_net_exit,
-	.async = true,
 };
 
 static int __init nf_log_ipv4_init(void)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 1f24bc8273a0..05e47d777009 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -1204,7 +1204,6 @@ static void __net_exit ping_v4_proc_exit_net(struct net *net)
 static struct pernet_operations ping_v4_net_ops = {
 	.init = ping_v4_proc_init_net,
 	.exit = ping_v4_proc_exit_net,
-	.async = true,
 };
 
 int __init ping_proc_init(void)
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 80de2e659dcb..adfb75340275 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -549,7 +549,6 @@ static __net_exit void ip_proc_exit_net(struct net *net)
 static __net_initdata struct pernet_operations ip_proc_ops = {
 	.init = ip_proc_init_net,
 	.exit = ip_proc_exit_net,
-	.async = true,
 };
 
 int __init ip_misc_proc_init(void)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 0ee2501a9027..1b4d3355624a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1154,7 +1154,6 @@ static __net_exit void raw_exit_net(struct net *net)
 static __net_initdata struct pernet_operations raw_net_ops = {
 	.init = raw_init_net,
 	.exit = raw_exit_net,
-	.async = true,
 };
 
 int __init raw_proc_init(void)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ce9bd5380d21..8322e479f299 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -418,7 +418,6 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net)
 static struct pernet_operations ip_rt_proc_ops __net_initdata =  {
 	.init = ip_rt_do_proc_init,
 	.exit = ip_rt_do_proc_exit,
-	.async = true,
 };
 
 static int __init ip_rt_proc_init(void)
@@ -3017,7 +3016,6 @@ static __net_exit void sysctl_route_net_exit(struct net *net)
 static __net_initdata struct pernet_operations sysctl_route_ops = {
 	.init = sysctl_route_net_init,
 	.exit = sysctl_route_net_exit,
-	.async = true,
 };
 #endif
 
@@ -3031,7 +3029,6 @@ static __net_init int rt_genid_init(struct net *net)
 
 static __net_initdata struct pernet_operations rt_genid_ops = {
 	.init = rt_genid_init,
-	.async = true,
 };
 
 static int __net_init ipv4_inetpeer_init(struct net *net)
@@ -3057,7 +3054,6 @@ static void __net_exit ipv4_inetpeer_exit(struct net *net)
 static __net_initdata struct pernet_operations ipv4_inetpeer_ops = {
 	.init	=	ipv4_inetpeer_init,
 	.exit	=	ipv4_inetpeer_exit,
-	.async	=	true,
 };
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 5b72d97693f8..4b195bac8ac0 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1219,7 +1219,6 @@ static __net_exit void ipv4_sysctl_exit_net(struct net *net)
 static __net_initdata struct pernet_operations ipv4_sysctl_ops = {
 	.init = ipv4_sysctl_init_net,
 	.exit = ipv4_sysctl_exit_net,
-	.async = true,
 };
 
 static __init int sysctl_ipv4_init(void)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fec8b1fd7b63..9639334ebb7c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2391,7 +2391,6 @@ static void __net_exit tcp4_proc_exit_net(struct net *net)
 static struct pernet_operations tcp4_net_ops = {
 	.init = tcp4_proc_init_net,
 	.exit = tcp4_proc_exit_net,
-	.async = true,
 };
 
 int __init tcp4_proc_init(void)
@@ -2578,7 +2577,6 @@ static struct pernet_operations __net_initdata tcp_sk_ops = {
        .init	   = tcp_sk_init,
        .exit	   = tcp_sk_exit,
        .exit_batch = tcp_sk_exit_batch,
-       .async	   = true,
 };
 
 void __init tcp_v4_init(void)
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index aa6fea9f3328..03b51cdcc731 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -1024,7 +1024,6 @@ static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_lis
 static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
 	.init		=	tcp_net_metrics_init,
 	.exit_batch	=	tcp_net_metrics_exit_batch,
-	.async		=	true,
 };
 
 void __init tcp_metrics_init(void)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index fb8f3a36bd14..f49e14cd3891 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2756,7 +2756,6 @@ static void __net_exit udp4_proc_exit_net(struct net *net)
 static struct pernet_operations udp4_net_ops = {
 	.init = udp4_proc_init_net,
 	.exit = udp4_proc_exit_net,
-	.async = true,
 };
 
 int __init udp4_proc_init(void)
@@ -2843,7 +2842,6 @@ static int __net_init udp_sysctl_init(struct net *net)
 
 static struct pernet_operations __net_initdata udp_sysctl_ops = {
 	.init	= udp_sysctl_init,
-	.async	= true,
 };
 
 void __init udp_init(void)
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 72f2c3806408..f96614e9b9a5 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -104,7 +104,6 @@ static void __net_exit udplite4_proc_exit_net(struct net *net)
 static struct pernet_operations udplite4_net_ops = {
 	.init = udplite4_proc_init_net,
 	.exit = udplite4_proc_exit_net,
-	.async = true,
 };
 
 static __init int udplite4_proc_init(void)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 6c76a757fa4a..d73a6d6652f6 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -367,7 +367,6 @@ static void __net_exit xfrm4_net_exit(struct net *net)
 static struct pernet_operations __net_initdata xfrm4_net_ops = {
 	.init	= xfrm4_net_init,
 	.exit	= xfrm4_net_exit,
-	.async	= true,
 };
 
 static void __init xfrm4_policy_init(void)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 189eac80f4ef..78cef00c9596 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4282,7 +4282,6 @@ static void __net_exit if6_proc_net_exit(struct net *net)
 static struct pernet_operations if6_proc_net_ops = {
 	.init = if6_proc_net_init,
 	.exit = if6_proc_net_exit,
-	.async = true,
 };
 
 int __init if6_proc_init(void)
@@ -6592,7 +6591,6 @@ static void __net_exit addrconf_exit_net(struct net *net)
 static struct pernet_operations addrconf_ops = {
 	.init = addrconf_init_net,
 	.exit = addrconf_exit_net,
-	.async = true,
 };
 
 static struct rtnl_af_ops inet6_ops __read_mostly = {
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index ba2e63633370..1d6ced37ad71 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -344,7 +344,6 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net)
 static struct pernet_operations ipv6_addr_label_ops = {
 	.init = ip6addrlbl_net_init,
 	.exit = ip6addrlbl_net_exit,
-	.async = true,
 };
 
 int __init ipv6_addr_label_init(void)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index dbbe04018813..c1e292db04db 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -857,7 +857,6 @@ static void __net_exit inet6_net_exit(struct net *net)
 static struct pernet_operations inet6_net_ops = {
 	.init = inet6_net_init,
 	.exit = inet6_net_exit,
-	.async = true,
 };
 
 static const struct ipv6_stub ipv6_stub_impl = {
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 00ef9467f3c0..df113c7b5fc8 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -397,7 +397,6 @@ static void __net_exit fib6_rules_net_exit(struct net *net)
 static struct pernet_operations fib6_rules_net_ops = {
 	.init = fib6_rules_net_init,
 	.exit = fib6_rules_net_exit,
-	.async = true,
 };
 
 int __init fib6_rules_init(void)
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 6f84668be6ea..d8c4b6374377 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -998,7 +998,6 @@ static void __net_exit icmpv6_sk_exit(struct net *net)
 static struct pernet_operations icmpv6_sk_ops = {
 	.init = icmpv6_sk_init,
 	.exit = icmpv6_sk_exit,
-	.async = true,
 };
 
 int __init icmpv6_init(void)
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index e438699f000f..44c39c5f0638 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -613,7 +613,6 @@ static struct pernet_operations ila_net_ops = {
 	.exit = ila_exit_net,
 	.id   = &ila_net_id,
 	.size = sizeof(struct ila_net),
-	.async = true,
 };
 
 static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 2f995e9e3050..908b8e5b615a 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2161,7 +2161,6 @@ static void fib6_net_exit(struct net *net)
 static struct pernet_operations fib6_net_ops = {
 	.init = fib6_net_init,
 	.exit = fib6_net_exit,
-	.async = true,
 };
 
 int __init fib6_init(void)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index f75b06ba8325..c05c4e82a7ca 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -873,7 +873,6 @@ static void __net_exit ip6_flowlabel_net_exit(struct net *net)
 static struct pernet_operations ip6_flowlabel_net_ops = {
 	.init = ip6_flowlabel_proc_init,
 	.exit = ip6_flowlabel_net_exit,
-	.async = true,
 };
 
 int ip6_flowlabel_init(void)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3a98c694da5f..22e86557aca4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1528,7 +1528,6 @@ static struct pernet_operations ip6gre_net_ops = {
 	.exit_batch = ip6gre_exit_batch_net,
 	.id   = &ip6gre_net_id,
 	.size = sizeof(struct ip6gre_net),
-	.async = true,
 };
 
 static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 456fcf942f95..df4c29f7d59f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2260,7 +2260,6 @@ static struct pernet_operations ip6_tnl_net_ops = {
 	.exit_batch = ip6_tnl_exit_batch_net,
 	.id   = &ip6_tnl_net_id,
 	.size = sizeof(struct ip6_tnl_net),
-	.async = true,
 };
 
 /**
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index a482b854eeea..60b771f49fb5 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1148,7 +1148,6 @@ static struct pernet_operations vti6_net_ops = {
 	.exit_batch = vti6_exit_batch_net,
 	.id   = &vti6_net_id,
 	.size = sizeof(struct vti6_net),
-	.async = true,
 };
 
 static struct xfrm6_protocol vti_esp6_protocol __read_mostly = {
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 1c8fa29d155a..298fd8b6ed17 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1348,7 +1348,6 @@ static void __net_exit ip6mr_net_exit(struct net *net)
 static struct pernet_operations ip6mr_net_ops = {
 	.init = ip6mr_net_init,
 	.exit = ip6mr_net_exit,
-	.async = true,
 };
 
 int __init ip6_mr_init(void)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 1e4c2b6ebd78..793159d77d8a 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2997,7 +2997,6 @@ static void __net_exit igmp6_net_exit(struct net *net)
 static struct pernet_operations igmp6_net_ops = {
 	.init = igmp6_net_init,
 	.exit = igmp6_net_exit,
-	.async = true,
 };
 
 int __init igmp6_init(void)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index d1d0b2fa7a07..9de4dfb126ba 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1883,7 +1883,6 @@ static void __net_exit ndisc_net_exit(struct net *net)
 static struct pernet_operations ndisc_net_ops = {
 	.init = ndisc_net_init,
 	.exit = ndisc_net_exit,
-	.async = true,
 };
 
 int __init ndisc_init(void)
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 4de8ac1e5af4..62358b93bbac 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1928,7 +1928,6 @@ static void __net_exit ip6_tables_net_exit(struct net *net)
 static struct pernet_operations ip6_tables_net_ops = {
 	.init = ip6_tables_net_init,
 	.exit = ip6_tables_net_exit,
-	.async = true,
 };
 
 static int __init ip6_tables_init(void)
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 06561c84c0bc..1343077dde93 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -87,7 +87,6 @@ static void __net_exit ip6table_filter_net_exit(struct net *net)
 static struct pernet_operations ip6table_filter_net_ops = {
 	.init = ip6table_filter_net_init,
 	.exit = ip6table_filter_net_exit,
-	.async = true,
 };
 
 static int __init ip6table_filter_init(void)
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index a11e25936b45..b0524b18c4fb 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -107,7 +107,6 @@ static void __net_exit ip6table_mangle_net_exit(struct net *net)
 
 static struct pernet_operations ip6table_mangle_net_ops = {
 	.exit = ip6table_mangle_net_exit,
-	.async = true,
 };
 
 static int __init ip6table_mangle_init(void)
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 4475fd300bb6..47306e45a80a 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -131,7 +131,6 @@ static void __net_exit ip6table_nat_net_exit(struct net *net)
 
 static struct pernet_operations ip6table_nat_net_ops = {
 	.exit	= ip6table_nat_net_exit,
-	.async	= true,
 };
 
 static int __init ip6table_nat_init(void)
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index a88f3b1995b1..710fa0806c37 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -75,7 +75,6 @@ static void __net_exit ip6table_raw_net_exit(struct net *net)
 
 static struct pernet_operations ip6table_raw_net_ops = {
 	.exit = ip6table_raw_net_exit,
-	.async = true,
 };
 
 static int __init ip6table_raw_init(void)
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 320048c008dc..cf26ccb04056 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -74,7 +74,6 @@ static void __net_exit ip6table_security_net_exit(struct net *net)
 
 static struct pernet_operations ip6table_security_net_ops = {
 	.exit = ip6table_security_net_exit,
-	.async = true,
 };
 
 static int __init ip6table_security_init(void)
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index ba54bb3bd1e4..663827ee3cf8 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -401,7 +401,6 @@ static struct pernet_operations ipv6_net_ops = {
 	.exit = ipv6_net_exit,
 	.id = &conntrack6_net_id,
 	.size = sizeof(struct conntrack6_net),
-	.async = true,
 };
 
 static int __init nf_conntrack_l3proto_ipv6_init(void)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 34136fe80ed5..b84ce3e6d728 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -646,7 +646,6 @@ static void nf_ct_net_exit(struct net *net)
 static struct pernet_operations nf_ct_net_ops = {
 	.init = nf_ct_net_init,
 	.exit = nf_ct_net_exit,
-	.async = true,
 };
 
 int nf_ct_frag6_init(void)
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index 32f98bc06900..c87b48359e8f 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -103,7 +103,6 @@ static void __net_exit defrag6_net_exit(struct net *net)
 
 static struct pernet_operations defrag6_net_ops = {
 	.exit = defrag6_net_exit,
-	.async = true,
 };
 
 static int __init nf_defrag_init(void)
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index 0220e584589c..b397a8fe88b9 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -390,7 +390,6 @@ static void __net_exit nf_log_ipv6_net_exit(struct net *net)
 static struct pernet_operations nf_log_ipv6_net_ops = {
 	.init = nf_log_ipv6_net_init,
 	.exit = nf_log_ipv6_net_exit,
-	.async = true,
 };
 
 static int __init nf_log_ipv6_init(void)
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 318c6e914234..d12c55dad7d1 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -240,7 +240,6 @@ static void __net_init ping_v6_proc_exit_net(struct net *net)
 static struct pernet_operations ping_v6_net_ops = {
 	.init = ping_v6_proc_init_net,
 	.exit = ping_v6_proc_exit_net,
-	.async = true,
 };
 #endif
 
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index f9891fa672f3..6e57028d2e91 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -343,7 +343,6 @@ static void __net_exit ipv6_proc_exit_net(struct net *net)
 static struct pernet_operations ipv6_proc_ops = {
 	.init = ipv6_proc_init_net,
 	.exit = ipv6_proc_exit_net,
-	.async = true,
 };
 
 int __init ipv6_misc_proc_init(void)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index b5e5de732494..5eb9b08947ed 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1332,7 +1332,6 @@ static void __net_exit raw6_exit_net(struct net *net)
 static struct pernet_operations raw6_net_ops = {
 	.init = raw6_init_net,
 	.exit = raw6_exit_net,
-	.async = true,
 };
 
 int __init raw6_proc_init(void)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index b5da69c83123..afbc000ad4f2 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -733,7 +733,6 @@ static void __net_exit ipv6_frags_exit_net(struct net *net)
 static struct pernet_operations ip6_frags_ops = {
 	.init = ipv6_frags_init_net,
 	.exit = ipv6_frags_exit_net,
-	.async = true,
 };
 
 int __init ipv6_frag_init(void)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1d0eaa69874d..ba8d5df50ebe 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5083,7 +5083,6 @@ static void __net_exit ip6_route_net_exit_late(struct net *net)
 static struct pernet_operations ip6_route_net_ops = {
 	.init = ip6_route_net_init,
 	.exit = ip6_route_net_exit,
-	.async = true,
 };
 
 static int __net_init ipv6_inetpeer_init(struct net *net)
@@ -5109,13 +5108,11 @@ static void __net_exit ipv6_inetpeer_exit(struct net *net)
 static struct pernet_operations ipv6_inetpeer_ops = {
 	.init	=	ipv6_inetpeer_init,
 	.exit	=	ipv6_inetpeer_exit,
-	.async	=	true,
 };
 
 static struct pernet_operations ip6_route_net_late_ops = {
 	.init = ip6_route_net_init_late,
 	.exit = ip6_route_net_exit_late,
-	.async = true,
 };
 
 static struct notifier_block ip6_route_dev_notifier = {
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index c3f13c3bd8a9..7f5621d09571 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -395,7 +395,6 @@ static void __net_exit seg6_net_exit(struct net *net)
 static struct pernet_operations ip6_segments_ops = {
 	.init = seg6_net_init,
 	.exit = seg6_net_exit,
-	.async = true,
 };
 
 static const struct genl_ops seg6_genl_ops[] = {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 8a4f8fddd812..1522bcfd253f 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1888,7 +1888,6 @@ static struct pernet_operations sit_net_ops = {
 	.exit_batch = sit_exit_batch_net,
 	.id   = &sit_net_id,
 	.size = sizeof(struct sit_net),
-	.async = true,
 };
 
 static void __exit sit_cleanup(void)
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 966c42af92f4..6fbdef630152 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -278,7 +278,6 @@ static void __net_exit ipv6_sysctl_net_exit(struct net *net)
 static struct pernet_operations ipv6_sysctl_net_ops = {
 	.init = ipv6_sysctl_net_init,
 	.exit = ipv6_sysctl_net_exit,
-	.async = true,
 };
 
 static struct ctl_table_header *ip6_header;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5425d7b100ee..883df0ad5bfe 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2007,7 +2007,6 @@ static struct pernet_operations tcpv6_net_ops = {
 	.init	    = tcpv6_net_init,
 	.exit	    = tcpv6_net_exit,
 	.exit_batch = tcpv6_net_exit_batch,
-	.async	    = true,
 };
 
 int __init tcpv6_init(void)
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index f3839780dc31..14ae32bb1f3d 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -123,7 +123,6 @@ static void __net_exit udplite6_proc_exit_net(struct net *net)
 static struct pernet_operations udplite6_net_ops = {
 	.init = udplite6_proc_init_net,
 	.exit = udplite6_proc_exit_net,
-	.async = true,
 };
 
 int __init udplite6_proc_init(void)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index cbb270bd81b0..416fe67271a9 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -400,7 +400,6 @@ static void __net_exit xfrm6_net_exit(struct net *net)
 static struct pernet_operations xfrm6_net_ops = {
 	.init	= xfrm6_net_init,
 	.exit	= xfrm6_net_exit,
-	.async	= true,
 };
 
 int __init xfrm6_init(void)
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index a9673619e0e9..f85f0d7480ac 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -353,7 +353,6 @@ static struct pernet_operations xfrm6_tunnel_net_ops = {
 	.exit	= xfrm6_tunnel_net_exit,
 	.id	= &xfrm6_tunnel_net_id,
 	.size	= sizeof(struct xfrm6_tunnel_net),
-	.async	= true,
 };
 
 static int __init xfrm6_tunnel_init(void)
diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
index 4c2e9907f254..1fac92543094 100644
--- a/net/kcm/kcmproc.c
+++ b/net/kcm/kcmproc.c
@@ -433,7 +433,6 @@ static void kcm_proc_exit_net(struct net *net)
 static struct pernet_operations kcm_net_ops = {
 	.init = kcm_proc_init_net,
 	.exit = kcm_proc_exit_net,
-	.async = true,
 };
 
 int __init kcm_proc_init(void)
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 516cfad71b85..dc76bc346829 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -2028,7 +2028,6 @@ static struct pernet_operations kcm_net_ops = {
 	.exit = kcm_exit_net,
 	.id   = &kcm_net_id,
 	.size = sizeof(struct kcm_net),
-	.async = true,
 };
 
 static int __init kcm_init(void)
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 3ac08ab26207..7e2e7188e7f4 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3863,7 +3863,6 @@ static struct pernet_operations pfkey_net_ops = {
 	.exit = pfkey_net_exit,
 	.id   = &pfkey_net_id,
 	.size = sizeof(struct netns_pfkey),
-	.async = true,
 };
 
 static void __exit ipsec_pfkey_exit(void)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index b86868da50d4..14b67dfacc4b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1789,7 +1789,6 @@ static struct pernet_operations l2tp_net_ops = {
 	.exit = l2tp_exit_net,
 	.id   = &l2tp_net_id,
 	.size = sizeof(struct l2tp_net),
-	.async = true,
 };
 
 static int __init l2tp_init(void)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index f24504efe729..d6deca11da19 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1762,7 +1762,6 @@ static struct pernet_operations pppol2tp_net_ops = {
 	.init = pppol2tp_init_net,
 	.exit = pppol2tp_exit_net,
 	.id   = &pppol2tp_net_id,
-	.async = true,
 };
 
 /*****************************************************************************
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index d4a89a8be013..7a4de6d618b1 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -2488,7 +2488,6 @@ static void mpls_net_exit(struct net *net)
 static struct pernet_operations mpls_net_ops = {
 	.init = mpls_net_init,
 	.exit = mpls_net_exit,
-	.async = true,
 };
 
 static struct rtnl_af_ops mpls_af_ops __read_mostly = {
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index d72cc786c7b7..0f6b8172fb9a 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -629,7 +629,6 @@ static void __net_exit netfilter_net_exit(struct net *net)
 static struct pernet_operations netfilter_net_ops = {
 	.init = netfilter_net_init,
 	.exit = netfilter_net_exit,
-	.async = true,
 };
 
 int __init netfilter_init(void)
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 2523ebe2b3cc..bc4bd247bb7d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -2095,7 +2095,6 @@ static struct pernet_operations ip_set_net_ops = {
 	.exit   = ip_set_net_exit,
 	.id	= &ip_set_net_id,
 	.size	= sizeof(struct ip_set_net),
-	.async	= true,
 };
 
 static int __init
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 6a6cb9db030b..5f6f73cf2174 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2289,12 +2289,10 @@ static struct pernet_operations ipvs_core_ops = {
 	.exit = __ip_vs_cleanup,
 	.id   = &ip_vs_net_id,
 	.size = sizeof(struct netns_ipvs),
-	.async = true,
 };
 
 static struct pernet_operations ipvs_core_dev_ops = {
 	.exit = __ip_vs_dev_cleanup,
-	.async = true,
 };
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 8b25aab41928..58d5d05aec24 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -479,7 +479,6 @@ static void __ip_vs_ftp_exit(struct net *net)
 static struct pernet_operations ip_vs_ftp_ops = {
 	.init = __ip_vs_ftp_init,
 	.exit = __ip_vs_ftp_exit,
-	.async = true,
 };
 
 static int __init ip_vs_ftp_init(void)
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 6a340c94c4b8..d625179de485 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -604,7 +604,6 @@ static void __net_exit __ip_vs_lblc_exit(struct net *net) { }
 static struct pernet_operations ip_vs_lblc_ops = {
 	.init = __ip_vs_lblc_init,
 	.exit = __ip_vs_lblc_exit,
-	.async = true,
 };
 
 static int __init ip_vs_lblc_init(void)
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 0627881128da..84c57b62a588 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -789,7 +789,6 @@ static void __net_exit __ip_vs_lblcr_exit(struct net *net) { }
 static struct pernet_operations ip_vs_lblcr_ops = {
 	.init = __ip_vs_lblcr_init,
 	.exit = __ip_vs_lblcr_exit,
-	.async = true,
 };
 
 static int __init ip_vs_lblcr_init(void)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 8884d302d33a..dd177ebee9aa 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3417,7 +3417,6 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
 static struct pernet_operations ctnetlink_net_ops = {
 	.init		= ctnetlink_net_init,
 	.exit_batch	= ctnetlink_net_exit_batch,
-	.async		= true,
 };
 
 static int __init ctnetlink_init(void)
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 9bcd72fe91f9..d049ea5a3770 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -406,7 +406,6 @@ static struct pernet_operations proto_gre_net_ops = {
 	.exit = proto_gre_net_exit,
 	.id   = &proto_gre_net_id,
 	.size = sizeof(struct netns_proto_gre),
-	.async = true,
 };
 
 static int __init nf_ct_proto_gre_init(void)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 98844c87d01e..037fec54c850 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -705,7 +705,6 @@ static void nf_conntrack_pernet_exit(struct list_head *net_exit_list)
 static struct pernet_operations nf_conntrack_net_ops = {
 	.init		= nf_conntrack_pernet_init,
 	.exit_batch	= nf_conntrack_pernet_exit,
-	.async		= true,
 };
 
 static int __init nf_conntrack_standalone_init(void)
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index a964e4d356cc..6d0357817cda 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -577,7 +577,6 @@ static void __net_exit nf_log_net_exit(struct net *net)
 static struct pernet_operations nf_log_net_ops = {
 	.init = nf_log_net_init,
 	.exit = nf_log_net_exit,
-	.async = true,
 };
 
 int __init netfilter_log_init(void)
diff --git a/net/netfilter/nf_log_netdev.c b/net/netfilter/nf_log_netdev.c
index 254c2c6bde48..350eb147754d 100644
--- a/net/netfilter/nf_log_netdev.c
+++ b/net/netfilter/nf_log_netdev.c
@@ -47,7 +47,6 @@ static void __net_exit nf_log_netdev_net_exit(struct net *net)
 static struct pernet_operations nf_log_netdev_net_ops = {
 	.init = nf_log_netdev_net_init,
 	.exit = nf_log_netdev_net_exit,
-	.async = true,
 };
 
 static int __init nf_log_netdev_init(void)
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 8f16fd27132d..6039b350abbe 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -398,7 +398,6 @@ static struct pernet_operations synproxy_net_ops = {
 	.exit		= synproxy_net_exit,
 	.id		= &synproxy_net_id,
 	.size		= sizeof(struct synproxy_net),
-	.async		= true,
 };
 
 static int __init synproxy_core_init(void)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fd13d28e4ca7..c4acc7340eb1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6597,7 +6597,6 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 static struct pernet_operations nf_tables_net_ops = {
 	.init	= nf_tables_init_net,
 	.exit	= nf_tables_exit_net,
-	.async	= true,
 };
 
 static int __init nf_tables_module_init(void)
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 84fc4954862d..03ead8a9e90c 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -566,7 +566,6 @@ static void __net_exit nfnetlink_net_exit_batch(struct list_head *net_exit_list)
 static struct pernet_operations nfnetlink_net_ops = {
 	.init		= nfnetlink_net_init,
 	.exit_batch	= nfnetlink_net_exit_batch,
-	.async		= true,
 };
 
 static int __init nfnetlink_init(void)
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 8d9f18bb8840..88d427f9f9e6 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -515,7 +515,6 @@ static void __net_exit nfnl_acct_net_exit(struct net *net)
 static struct pernet_operations nfnl_acct_ops = {
         .init   = nfnl_acct_net_init,
         .exit   = nfnl_acct_net_exit,
-	.async	= true,
 };
 
 static int __init nfnl_acct_init(void)
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 6819300f7fb7..95b04702a655 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -586,7 +586,6 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 static struct pernet_operations cttimeout_ops = {
 	.init	= cttimeout_net_init,
 	.exit	= cttimeout_net_exit,
-	.async	= true,
 };
 
 static int __init cttimeout_init(void)
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index b21ef79849a1..7b46aa4c478d 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1108,7 +1108,6 @@ static struct pernet_operations nfnl_log_net_ops = {
 	.exit	= nfnl_log_net_exit,
 	.id	= &nfnl_log_net_id,
 	.size	= sizeof(struct nfnl_log_net),
-	.async	= true,
 };
 
 static int __init nfnetlink_log_init(void)
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 9f572ed56208..0b839c38800f 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1525,7 +1525,6 @@ static struct pernet_operations nfnl_queue_net_ops = {
 	.exit_batch	= nfnl_queue_net_exit_batch,
 	.id		= &nfnl_queue_net_id,
 	.size		= sizeof(struct nfnl_queue_net),
-	.async		= true,
 };
 
 static int __init nfnetlink_queue_init(void)
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 6de1f6a4cb80..4aa01c90e9d1 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1789,7 +1789,6 @@ static void __net_exit xt_net_exit(struct net *net)
 static struct pernet_operations xt_net_ops = {
 	.init = xt_net_init,
 	.exit = xt_net_exit,
-	.async = true,
 };
 
 static int __init xt_init(void)
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index ef65b7a9173e..3360f13dc208 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -1349,7 +1349,6 @@ static struct pernet_operations hashlimit_net_ops = {
 	.exit	= hashlimit_net_exit,
 	.id	= &hashlimit_net_id,
 	.size	= sizeof(struct hashlimit_net),
-	.async	= true,
 };
 
 static int __init hashlimit_mt_init(void)
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 434e35ce940b..9bbfc17ce3ec 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -687,7 +687,6 @@ static struct pernet_operations recent_net_ops = {
 	.exit	= recent_net_exit,
 	.id	= &recent_net_id,
 	.size	= sizeof(struct recent_net),
-	.async	= true,
 };
 
 static struct xt_match recent_mt_reg[] __read_mostly = {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5d10dcfe6411..f1b02d87e336 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -253,7 +253,6 @@ static struct pernet_operations netlink_tap_net_ops = {
 	.exit = netlink_tap_exit_net,
 	.id   = &netlink_tap_net_id,
 	.size = sizeof(struct netlink_tap_net),
-	.async = true,
 };
 
 static bool netlink_filter_tap(const struct sk_buff *skb)
@@ -2726,7 +2725,6 @@ static void __init netlink_add_usersock_entry(void)
 static struct pernet_operations __net_initdata netlink_net_ops = {
 	.init = netlink_net_init,
 	.exit = netlink_net_exit,
-	.async = true,
 };
 
 static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index af51b8c0a2cb..b9ce82c9440f 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1035,7 +1035,6 @@ static void __net_exit genl_pernet_exit(struct net *net)
 static struct pernet_operations genl_pernet_ops = {
 	.init = genl_pernet_init,
 	.exit = genl_pernet_exit,
-	.async = true,
 };
 
 static int __init genl_init(void)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 100191df0371..ef38e5aecd28 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2384,7 +2384,6 @@ static struct pernet_operations ovs_net_ops = {
 	.exit = ovs_exit_net,
 	.id   = &ovs_net_id,
 	.size = sizeof(struct ovs_net),
-	.async = true,
 };
 
 static int __init dp_init(void)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2c5a6fe5d749..616cb9c18f88 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4557,7 +4557,6 @@ static void __net_exit packet_net_exit(struct net *net)
 static struct pernet_operations packet_net_ops = {
 	.init = packet_net_init,
 	.exit = packet_net_exit,
-	.async = true,
 };
 
 
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 9454e8393793..77787512fc32 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -342,7 +342,6 @@ static struct pernet_operations phonet_net_ops = {
 	.exit = phonet_exit_net,
 	.id   = &phonet_net_id,
 	.size = sizeof(struct phonet_net),
-	.async = true,
 };
 
 /* Initialize Phonet devices list */
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 4f3a32c38bf5..351a28474667 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -530,7 +530,6 @@ static struct pernet_operations rds_tcp_net_ops = {
 	.exit = rds_tcp_exit_net,
 	.id = &rds_tcp_netid,
 	.size = sizeof(struct rds_tcp_net),
-	.async = true,
 };
 
 void *rds_tcp_listen_sock_def_readable(struct net *net)
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 5fd939dabf41..f18c9248e0d4 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -106,5 +106,4 @@ struct pernet_operations rxrpc_net_ops = {
 	.exit	= rxrpc_exit_net,
 	.id	= &rxrpc_net_id,
 	.size	= sizeof(struct rxrpc_net),
-	.async	= true,
 };
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 7bd1b964f021..0d78b58e1898 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1533,7 +1533,6 @@ static struct pernet_operations tcf_action_net_ops = {
 	.exit = tcf_action_net_exit,
 	.id = &tcf_action_net_id,
 	.size = sizeof(struct tcf_action_net),
-	.async = true,
 };
 
 static int __init tc_action_init(void)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 5cb9b268e8ff..9092531d45d8 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -413,7 +413,6 @@ static struct pernet_operations bpf_net_ops = {
 	.exit_batch = bpf_exit_net,
 	.id   = &bpf_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int __init bpf_init_module(void)
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 371e5e4ab3e2..e4b880fa51fe 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -222,7 +222,6 @@ static struct pernet_operations connmark_net_ops = {
 	.exit_batch = connmark_exit_net,
 	.id   = &connmark_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int __init connmark_init_module(void)
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index a527e287c086..7e28b2ce1437 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -678,7 +678,6 @@ static struct pernet_operations csum_net_ops = {
 	.exit_batch = csum_exit_net,
 	.id   = &csum_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_DESCRIPTION("Checksum updating actions");
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 88fbb8403565..4dc4f153cad8 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -261,7 +261,6 @@ static struct pernet_operations gact_net_ops = {
 	.exit_batch = gact_exit_net,
 	.id   = &gact_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_AUTHOR("Jamal Hadi Salim(2002-4)");
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 555b1caeff72..a5994cf0512b 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -870,7 +870,6 @@ static struct pernet_operations ife_net_ops = {
 	.exit_batch = ife_exit_net,
 	.id   = &ife_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int __init ife_init_module(void)
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index b5e8565b89c7..14c312d7908f 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -352,7 +352,6 @@ static struct pernet_operations ipt_net_ops = {
 	.exit_batch = ipt_exit_net,
 	.id   = &ipt_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int tcf_xt_walker(struct net *net, struct sk_buff *skb,
@@ -403,7 +402,6 @@ static struct pernet_operations xt_net_ops = {
 	.exit_batch = xt_exit_net,
 	.id   = &xt_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_AUTHOR("Jamal Hadi Salim(2002-13)");
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 64c86579c3d9..fd34015331ab 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -353,7 +353,6 @@ static struct pernet_operations mirred_net_ops = {
 	.exit_batch = mirred_exit_net,
 	.id   = &mirred_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_AUTHOR("Jamal Hadi Salim(2002)");
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index b1bc757f6491..4b5848b6c252 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -323,7 +323,6 @@ static struct pernet_operations nat_net_ops = {
 	.exit_batch = nat_exit_net,
 	.id   = &nat_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_DESCRIPTION("Stateless NAT actions");
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index f392ccaaa0d8..8a925c72db5f 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -465,7 +465,6 @@ static struct pernet_operations pedit_net_ops = {
 	.exit_batch = pedit_exit_net,
 	.id   = &pedit_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_AUTHOR("Jamal Hadi Salim(2002-4)");
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 7081ec75e696..4e72bc2a0dfb 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -347,7 +347,6 @@ static struct pernet_operations police_net_ops = {
 	.exit_batch = police_exit_net,
 	.id   = &police_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int __init police_init_module(void)
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 3a89f98f17e6..5db358497c9e 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -249,7 +249,6 @@ static struct pernet_operations sample_net_ops = {
 	.exit_batch = sample_exit_net,
 	.id   = &sample_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int __init sample_init_module(void)
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index e84768ae610a..9618b4a83cee 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -216,7 +216,6 @@ static struct pernet_operations simp_net_ops = {
 	.exit_batch = simp_exit_net,
 	.id   = &simp_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_AUTHOR("Jamal Hadi Salim(2005)");
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 7971510fe61b..ddf69fc01bdf 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -253,7 +253,6 @@ static struct pernet_operations skbedit_net_ops = {
 	.exit_batch = skbedit_exit_net,
 	.id   = &skbedit_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>");
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 142a996ac776..bbcbdce732cc 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -279,7 +279,6 @@ static struct pernet_operations skbmod_net_ops = {
 	.exit_batch = skbmod_exit_net,
 	.id   = &skbmod_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>");
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index a1c8dd406a04..626dac81a48a 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -339,7 +339,6 @@ static struct pernet_operations tunnel_key_net_ops = {
 	.exit_batch = tunnel_key_exit_net,
 	.id   = &tunnel_key_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int __init tunnel_key_init_module(void)
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 41a66effeb5f..853604685965 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -314,7 +314,6 @@ static struct pernet_operations vlan_net_ops = {
 	.exit_batch = vlan_exit_net,
 	.id   = &vlan_net_id,
 	.size = sizeof(struct tc_action_net),
-	.async = true,
 };
 
 static int __init vlan_init_module(void)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ec5fe8ec0c3e..b66754f52a9f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1619,7 +1619,6 @@ static struct pernet_operations tcf_net_ops = {
 	.exit = tcf_net_exit,
 	.id   = &tcf_net_id,
 	.size = sizeof(struct tcf_net),
-	.async = true,
 };
 
 static int __init tc_filter_init(void)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 68f9d942bed4..106dae7e4818 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -2133,7 +2133,6 @@ static void __net_exit psched_net_exit(struct net *net)
 static struct pernet_operations psched_net_ops = {
 	.init = psched_net_init,
 	.exit = psched_net_exit,
-	.async = true,
 };
 
 static int __init pktsched_init(void)
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 493b817f6a2a..84a09f599131 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1283,7 +1283,6 @@ static void __net_exit sctp_defaults_exit(struct net *net)
 static struct pernet_operations sctp_defaults_ops = {
 	.init = sctp_defaults_init,
 	.exit = sctp_defaults_exit,
-	.async = true,
 };
 
 static int __net_init sctp_ctrlsock_init(struct net *net)
@@ -1307,7 +1306,6 @@ static void __net_init sctp_ctrlsock_exit(struct net *net)
 static struct pernet_operations sctp_ctrlsock_ops = {
 	.init = sctp_ctrlsock_init,
 	.exit = sctp_ctrlsock_exit,
-	.async = true,
 };
 
 /* Initialize the universe into something sensible.  */
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 44f939cb6bc8..9463af4b32e8 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -2063,7 +2063,6 @@ static __net_exit void rpcsec_gss_exit_net(struct net *net)
 static struct pernet_operations rpcsec_gss_net_ops = {
 	.init = rpcsec_gss_init_net,
 	.exit = rpcsec_gss_exit_net,
-	.async = true,
 };
 
 /*
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 68287e921847..56f9eff74150 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -79,7 +79,6 @@ static struct pernet_operations sunrpc_net_ops = {
 	.exit = sunrpc_exit_net,
 	.id = &sunrpc_net_id,
 	.size = sizeof(struct sunrpc_net),
-	.async = true,
 };
 
 static int __init
diff --git a/net/sysctl_net.c b/net/sysctl_net.c
index f424539829b7..9aed6fe1bf1a 100644
--- a/net/sysctl_net.c
+++ b/net/sysctl_net.c
@@ -89,7 +89,6 @@ static void __net_exit sysctl_net_exit(struct net *net)
 static struct pernet_operations sysctl_pernet_ops = {
 	.init = sysctl_net_init,
 	.exit = sysctl_net_exit,
-	.async = true,
 };
 
 static struct ctl_table_header *net_header;
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 52dfc51ac4d5..5b38f5164281 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -109,7 +109,6 @@ static struct pernet_operations tipc_net_ops = {
 	.exit = tipc_exit_net,
 	.id   = &tipc_net_id,
 	.size = sizeof(struct tipc_net),
-	.async = true,
 };
 
 static int __init tipc_init(void)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index bc2970a8e7f3..aded82da1aea 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2913,7 +2913,6 @@ static void __net_exit unix_net_exit(struct net *net)
 static struct pernet_operations unix_net_ops = {
 	.init = unix_net_init,
 	.exit = unix_net_exit,
-	.async = true,
 };
 
 static int __init af_unix_init(void)
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 670aa229168a..a6f3cac8c640 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1340,7 +1340,6 @@ static void __net_exit cfg80211_pernet_exit(struct net *net)
 
 static struct pernet_operations cfg80211_pernet_ops = {
 	.exit = cfg80211_pernet_exit,
-	.async = true,
 };
 
 static int __init cfg80211_init(void)
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index bc7064486b15..9efbfc753347 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -390,7 +390,6 @@ static void __net_exit wext_pernet_exit(struct net *net)
 static struct pernet_operations wext_pernet_ops = {
 	.init = wext_pernet_init,
 	.exit = wext_pernet_exit,
-	.async = true,
 };
 
 static int __init wireless_nlevent_init(void)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index cb3bb9ae4407..625b3fca5704 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2985,7 +2985,6 @@ static void __net_exit xfrm_net_exit(struct net *net)
 static struct pernet_operations __net_initdata xfrm_net_ops = {
 	.init = xfrm_net_init,
 	.exit = xfrm_net_exit,
-	.async = true,
 };
 
 void __init xfrm_init(void)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index e92b8c019c88..080035f056d9 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3253,7 +3253,6 @@ static void __net_exit xfrm_user_net_exit(struct list_head *net_exit_list)
 static struct pernet_operations xfrm_user_net_ops = {
 	.init	    = xfrm_user_net_init,
 	.exit_batch = xfrm_user_net_exit,
-	.async	    = true,
 };
 
 static int __init xfrm_user_init(void)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b4d7b6242a40..8644d864e3c1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6743,7 +6743,6 @@ static void __net_exit selinux_nf_unregister(struct net *net)
 static struct pernet_operations selinux_net_ops = {
 	.init = selinux_nf_register,
 	.exit = selinux_nf_unregister,
-	.async = true,
 };
 
 static int __init selinux_nf_ip_init(void)
diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c
index 3f29c03162ca..e36d17835d4f 100644
--- a/security/smack/smack_netfilter.c
+++ b/security/smack/smack_netfilter.c
@@ -89,7 +89,6 @@ static void __net_exit smack_nf_unregister(struct net *net)
 static struct pernet_operations smack_net_ops = {
 	.init = smack_nf_register,
 	.exit = smack_nf_unregister,
-	.async = true,
 };
 
 static int __init smack_nf_ip_init(void)
-- 
cgit v1.2.3


From 4420bf21fb6c0306e36ad58ade1e741fba57ce65 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Tue, 27 Mar 2018 18:02:23 +0300
Subject: net: Rename net_sem to pernet_ops_rwsem

net_sem is some undefined area name, so it will be better
to make the area more defined.

Rename it to pernet_ops_rwsem for better readability and
better intelligibility.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rtnetlink.h   |  2 +-
 include/net/net_namespace.h | 12 +++++++-----
 net/core/net_namespace.c    | 40 ++++++++++++++++++++--------------------
 net/core/rtnetlink.c        |  4 ++--
 4 files changed, 30 insertions(+), 28 deletions(-)

(limited to 'include/net')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 562a175c35a9..c7d1e4689325 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -36,7 +36,7 @@ extern int rtnl_is_locked(void);
 extern int rtnl_lock_killable(void);
 
 extern wait_queue_head_t netdev_unregistering_wq;
-extern struct rw_semaphore net_sem;
+extern struct rw_semaphore pernet_ops_rwsem;
 
 #ifdef CONFIG_PROVE_LOCKING
 extern bool lockdep_rtnl_is_held(void);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 37bcf8382b61..922e8b6fb422 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -60,9 +60,10 @@ struct net {
 
 	struct list_head	list;		/* list of network namespaces */
 	struct list_head	exit_list;	/* To linked to call pernet exit
-						 * methods on dead net (net_sem
-						 * read locked), or to unregister
-						 * pernet ops (net_sem wr locked).
+						 * methods on dead net (
+						 * pernet_ops_rwsem read locked),
+						 * or to unregister pernet ops
+						 * (pernet_ops_rwsem write locked).
 						 */
 	struct llist_node	cleanup_list;	/* namespaces on death row */
 
@@ -95,8 +96,9 @@ struct net {
 	/* core fib_rules */
 	struct list_head	rules_ops;
 
-	struct list_head	fib_notifier_ops;  /* protected by net_sem */
-
+	struct list_head	fib_notifier_ops;  /* Populated by
+						    * register_pernet_subsys()
+						    */
 	struct net_device       *loopback_dev;          /* The loopback */
 	struct netns_core	core;
 	struct netns_mib	mib;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index eef17ad29dea..9e8ee4640451 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -41,10 +41,10 @@ EXPORT_SYMBOL(init_net);
 
 static bool init_net_initialized;
 /*
- * net_sem: protects: pernet_list, net_generic_ids,
+ * pernet_ops_rwsem: protects: pernet_list, net_generic_ids,
  * init_net_initialized and first_device pointer.
  */
-DECLARE_RWSEM(net_sem);
+DECLARE_RWSEM(pernet_ops_rwsem);
 
 #define MIN_PERNET_OPS_ID	\
 	((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *))
@@ -72,7 +72,7 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data)
 	BUG_ON(id < MIN_PERNET_OPS_ID);
 
 	old_ng = rcu_dereference_protected(net->gen,
-					   lockdep_is_held(&net_sem));
+					   lockdep_is_held(&pernet_ops_rwsem));
 	if (old_ng->s.len > id) {
 		old_ng->ptr[id] = data;
 		return 0;
@@ -289,7 +289,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
  */
 static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 {
-	/* Must be called with net_sem held */
+	/* Must be called with pernet_ops_rwsem held */
 	const struct pernet_operations *ops, *saved_ops;
 	int error = 0;
 	LIST_HEAD(net_exit_list);
@@ -422,13 +422,13 @@ struct net *copy_net_ns(unsigned long flags,
 	net->ucounts = ucounts;
 	get_user_ns(user_ns);
 
-	rv = down_read_killable(&net_sem);
+	rv = down_read_killable(&pernet_ops_rwsem);
 	if (rv < 0)
 		goto put_userns;
 
 	rv = setup_net(net, user_ns);
 
-	up_read(&net_sem);
+	up_read(&pernet_ops_rwsem);
 
 	if (rv < 0) {
 put_userns:
@@ -480,7 +480,7 @@ static void cleanup_net(struct work_struct *work)
 	/* Atomically snapshot the list of namespaces to cleanup */
 	net_kill_list = llist_del_all(&cleanup_list);
 
-	down_read(&net_sem);
+	down_read(&pernet_ops_rwsem);
 
 	/* Don't let anyone else find us. */
 	rtnl_lock();
@@ -519,7 +519,7 @@ static void cleanup_net(struct work_struct *work)
 	list_for_each_entry_reverse(ops, &pernet_list, list)
 		ops_free_list(ops, &net_exit_list);
 
-	up_read(&net_sem);
+	up_read(&pernet_ops_rwsem);
 
 	/* Ensure there are no outstanding rcu callbacks using this
 	 * network namespace.
@@ -546,8 +546,8 @@ static void cleanup_net(struct work_struct *work)
  */
 void net_ns_barrier(void)
 {
-	down_write(&net_sem);
-	up_write(&net_sem);
+	down_write(&pernet_ops_rwsem);
+	up_write(&pernet_ops_rwsem);
 }
 EXPORT_SYMBOL(net_ns_barrier);
 
@@ -869,12 +869,12 @@ static int __init net_ns_init(void)
 
 	rcu_assign_pointer(init_net.gen, ng);
 
-	down_write(&net_sem);
+	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
 		panic("Could not setup the initial network namespace");
 
 	init_net_initialized = true;
-	up_write(&net_sem);
+	up_write(&pernet_ops_rwsem);
 
 	register_pernet_subsys(&net_ns_ops);
 
@@ -1013,9 +1013,9 @@ static void unregister_pernet_operations(struct pernet_operations *ops)
 int register_pernet_subsys(struct pernet_operations *ops)
 {
 	int error;
-	down_write(&net_sem);
+	down_write(&pernet_ops_rwsem);
 	error =  register_pernet_operations(first_device, ops);
-	up_write(&net_sem);
+	up_write(&pernet_ops_rwsem);
 	return error;
 }
 EXPORT_SYMBOL_GPL(register_pernet_subsys);
@@ -1031,9 +1031,9 @@ EXPORT_SYMBOL_GPL(register_pernet_subsys);
  */
 void unregister_pernet_subsys(struct pernet_operations *ops)
 {
-	down_write(&net_sem);
+	down_write(&pernet_ops_rwsem);
 	unregister_pernet_operations(ops);
-	up_write(&net_sem);
+	up_write(&pernet_ops_rwsem);
 }
 EXPORT_SYMBOL_GPL(unregister_pernet_subsys);
 
@@ -1059,11 +1059,11 @@ EXPORT_SYMBOL_GPL(unregister_pernet_subsys);
 int register_pernet_device(struct pernet_operations *ops)
 {
 	int error;
-	down_write(&net_sem);
+	down_write(&pernet_ops_rwsem);
 	error = register_pernet_operations(&pernet_list, ops);
 	if (!error && (first_device == &pernet_list))
 		first_device = &ops->list;
-	up_write(&net_sem);
+	up_write(&pernet_ops_rwsem);
 	return error;
 }
 EXPORT_SYMBOL_GPL(register_pernet_device);
@@ -1079,11 +1079,11 @@ EXPORT_SYMBOL_GPL(register_pernet_device);
  */
 void unregister_pernet_device(struct pernet_operations *ops)
 {
-	down_write(&net_sem);
+	down_write(&pernet_ops_rwsem);
 	if (&ops->list == first_device)
 		first_device = first_device->next;
 	unregister_pernet_operations(ops);
-	up_write(&net_sem);
+	up_write(&pernet_ops_rwsem);
 }
 EXPORT_SYMBOL_GPL(unregister_pernet_device);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 31438b63d4b4..73011a60434c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -460,11 +460,11 @@ static void rtnl_lock_unregistering_all(void)
 void rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
 	/* Close the race with cleanup_net() */
-	down_write(&net_sem);
+	down_write(&pernet_ops_rwsem);
 	rtnl_lock_unregistering_all();
 	__rtnl_link_unregister(ops);
 	rtnl_unlock();
-	up_write(&net_sem);
+	up_write(&pernet_ops_rwsem);
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 
-- 
cgit v1.2.3


From 8518e9bb98b602eca0717d5aaad63ccbe56539d2 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Tue, 27 Mar 2018 18:02:32 +0300
Subject: net: Add more comments

This adds comments to different places to improve
readability.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 4 ++++
 net/core/net_namespace.c    | 2 ++
 net/core/rtnetlink.c        | 2 +-
 3 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 922e8b6fb422..1ab4f920f109 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -323,6 +323,10 @@ struct pernet_operations {
 	 * have to keep in mind all other pernet_operations and
 	 * to introduce a locking, if they share common resources.
 	 *
+	 * The only time they are called with exclusive lock is
+	 * from register_pernet_subsys(), unregister_pernet_subsys()
+	 * register_pernet_device() and unregister_pernet_device().
+	 *
 	 * Exit methods using blocking RCU primitives, such as
 	 * synchronize_rcu(), should be implemented via exit_batch.
 	 * Then, destruction of a group of net requires single
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 9e8ee4640451..b5796d17a302 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -43,6 +43,8 @@ static bool init_net_initialized;
 /*
  * pernet_ops_rwsem: protects: pernet_list, net_generic_ids,
  * init_net_initialized and first_device pointer.
+ * This is internal net namespace object. Please, don't use it
+ * outside.
  */
 DECLARE_RWSEM(pernet_ops_rwsem);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 73011a60434c..2d3949789cef 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -459,7 +459,7 @@ static void rtnl_lock_unregistering_all(void)
  */
 void rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
-	/* Close the race with cleanup_net() */
+	/* Close the race with setup_net() and cleanup_net() */
 	down_write(&pernet_ops_rwsem);
 	rtnl_lock_unregistering_all();
 	__rtnl_link_unregister(ops);
-- 
cgit v1.2.3


From a25e21f0bcd25673b91b97b9805db33350feec0f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 27 Mar 2018 23:03:00 +0100
Subject: rxrpc, afs: Use debug_ids rather than pointers in traces

In rxrpc and afs, use the debug_ids that are monotonically allocated to
various objects as they're allocated rather than pointers as kernel
pointers are now hashed making them less useful.  Further, the debug ids
aren't reused anywhere nearly as quickly.

In addition, allow kernel services that use rxrpc, such as afs, to take
numbers from the rxrpc counter, assign them to their own call struct and
pass them in to rxrpc for both client and service calls so that the trace
lines for each will have the same ID tag.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/afs/internal.h            |   1 +
 fs/afs/rxrpc.c               |  12 ++--
 include/net/af_rxrpc.h       |  11 ++-
 include/trace/events/afs.h   |  69 +++++++++----------
 include/trace/events/rxrpc.h | 155 ++++++++++++++++++++++---------------------
 net/rxrpc/af_rxrpc.c         |   7 +-
 net/rxrpc/ar-internal.h      |   8 +--
 net/rxrpc/call_accept.c      |  18 +++--
 net/rxrpc/call_object.c      |  15 +++--
 net/rxrpc/conn_event.c       |   3 +-
 net/rxrpc/input.c            |   6 +-
 net/rxrpc/sendmsg.c          |   3 +-
 12 files changed, 163 insertions(+), 145 deletions(-)

(limited to 'include/net')

diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index f38d6a561a84..72217170b155 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -118,6 +118,7 @@ struct afs_call {
 	bool			ret_reply0;	/* T if should return reply[0] on success */
 	bool			upgrade;	/* T to request service upgrade */
 	u16			service_id;	/* Actual service ID (after upgrade) */
+	unsigned int		debug_id;	/* Trace ID */
 	u32			operation_ID;	/* operation ID for an incoming call */
 	u32			count;		/* count for use in unmarshalling */
 	__be32			tmp;		/* place to extract temporary data */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index e1126659f043..b819900916e6 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -131,6 +131,7 @@ static struct afs_call *afs_alloc_call(struct afs_net *net,
 
 	call->type = type;
 	call->net = net;
+	call->debug_id = atomic_inc_return(&rxrpc_debug_id);
 	atomic_set(&call->usage, 1);
 	INIT_WORK(&call->async_work, afs_process_async_call);
 	init_waitqueue_head(&call->waitq);
@@ -169,11 +170,12 @@ void afs_put_call(struct afs_call *call)
 		afs_put_server(call->net, call->cm_server);
 		afs_put_cb_interest(call->net, call->cbi);
 		kfree(call->request);
-		kfree(call);
 
-		o = atomic_dec_return(&net->nr_outstanding_calls);
 		trace_afs_call(call, afs_call_trace_free, 0, o,
 			       __builtin_return_address(0));
+		kfree(call);
+
+		o = atomic_dec_return(&net->nr_outstanding_calls);
 		if (o == 0)
 			wake_up_atomic_t(&net->nr_outstanding_calls);
 	}
@@ -378,7 +380,8 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
 					 (async ?
 					  afs_wake_up_async_call :
 					  afs_wake_up_call_waiter),
-					 call->upgrade);
+					 call->upgrade,
+					 call->debug_id);
 	if (IS_ERR(rxcall)) {
 		ret = PTR_ERR(rxcall);
 		goto error_kill_call;
@@ -727,7 +730,8 @@ void afs_charge_preallocation(struct work_struct *work)
 					       afs_wake_up_async_call,
 					       afs_rx_attach,
 					       (unsigned long)call,
-					       GFP_KERNEL) < 0)
+					       GFP_KERNEL,
+					       call->debug_id) < 0)
 			break;
 		call = NULL;
 	}
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 2b3a6eec4570..8ae8ee004258 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -31,6 +31,11 @@ enum rxrpc_call_completion {
 	NR__RXRPC_CALL_COMPLETIONS
 };
 
+/*
+ * Debug ID counter for tracing.
+ */
+extern atomic_t rxrpc_debug_id;
+
 typedef void (*rxrpc_notify_rx_t)(struct sock *, struct rxrpc_call *,
 				  unsigned long);
 typedef void (*rxrpc_notify_end_tx_t)(struct sock *, struct rxrpc_call *,
@@ -50,7 +55,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *,
 					   s64,
 					   gfp_t,
 					   rxrpc_notify_rx_t,
-					   bool);
+					   bool,
+					   unsigned int);
 int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
 			   struct msghdr *, size_t,
 			   rxrpc_notify_end_tx_t);
@@ -63,7 +69,8 @@ void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
 			   struct sockaddr_rxrpc *);
 u64 rxrpc_kernel_get_rtt(struct socket *, struct rxrpc_call *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
-			       rxrpc_user_attach_call_t, unsigned long, gfp_t);
+			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
+			       unsigned int);
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
 int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *,
 			    struct sockaddr_rxrpc *, struct key *);
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 6b59c63a8e51..63815f66b274 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -133,8 +133,7 @@ TRACE_EVENT(afs_recv_data,
 	    TP_ARGS(call, count, offset, want_more, ret),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	rxcall		)
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(enum afs_call_state,	state		)
 		    __field(unsigned int,		count		)
 		    __field(unsigned int,		offset		)
@@ -144,8 +143,7 @@ TRACE_EVENT(afs_recv_data,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->rxcall	= call->rxcall;
-		    __entry->call	= call;
+		    __entry->call	= call->debug_id;
 		    __entry->state	= call->state;
 		    __entry->unmarshall	= call->unmarshall;
 		    __entry->count	= count;
@@ -154,8 +152,7 @@ TRACE_EVENT(afs_recv_data,
 		    __entry->ret	= ret;
 			   ),
 
-	    TP_printk("c=%p ac=%p s=%u u=%u %u/%u wm=%u ret=%d",
-		      __entry->rxcall,
+	    TP_printk("c=%08x s=%u u=%u %u/%u wm=%u ret=%d",
 		      __entry->call,
 		      __entry->state, __entry->unmarshall,
 		      __entry->offset, __entry->count,
@@ -168,21 +165,18 @@ TRACE_EVENT(afs_notify_call,
 	    TP_ARGS(rxcall, call),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	rxcall		)
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(enum afs_call_state,	state		)
 		    __field(unsigned short,		unmarshall	)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->rxcall	= rxcall;
-		    __entry->call	= call;
+		    __entry->call	= call->debug_id;
 		    __entry->state	= call->state;
 		    __entry->unmarshall	= call->unmarshall;
 			   ),
 
-	    TP_printk("c=%p ac=%p s=%u u=%u",
-		      __entry->rxcall,
+	    TP_printk("c=%08x s=%u u=%u",
 		      __entry->call,
 		      __entry->state, __entry->unmarshall)
 	    );
@@ -193,21 +187,18 @@ TRACE_EVENT(afs_cb_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	rxcall		)
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(const char *,		name		)
 		    __field(u32,			op		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->rxcall	= call->rxcall;
-		    __entry->call	= call;
+		    __entry->call	= call->debug_id;
 		    __entry->name	= call->type->name;
 		    __entry->op		= call->operation_ID;
 			   ),
 
-	    TP_printk("c=%p ac=%p %s o=%u",
-		      __entry->rxcall,
+	    TP_printk("c=%08x %s o=%u",
 		      __entry->call,
 		      __entry->name,
 		      __entry->op)
@@ -220,7 +211,7 @@ TRACE_EVENT(afs_call,
 	    TP_ARGS(call, op, usage, outstanding, where),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(int,			op		)
 		    __field(int,			usage		)
 		    __field(int,			outstanding	)
@@ -228,14 +219,14 @@ TRACE_EVENT(afs_call,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->outstanding = outstanding;
 		    __entry->where = where;
 			   ),
 
-	    TP_printk("c=%p %s u=%d o=%d sp=%pSR",
+	    TP_printk("c=%08x %s u=%d o=%d sp=%pSR",
 		      __entry->call,
 		      __print_symbolic(__entry->op, afs_call_traces),
 		      __entry->usage,
@@ -249,13 +240,13 @@ TRACE_EVENT(afs_make_fs_call,
 	    TP_ARGS(call, fid),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(enum afs_fs_operation,	op		)
 		    __field_struct(struct afs_fid,	fid		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->op = call->operation_ID;
 		    if (fid) {
 			    __entry->fid = *fid;
@@ -266,7 +257,7 @@ TRACE_EVENT(afs_make_fs_call,
 		    }
 			   ),
 
-	    TP_printk("c=%p %06x:%06x:%06x %s",
+	    TP_printk("c=%08x %06x:%06x:%06x %s",
 		      __entry->call,
 		      __entry->fid.vid,
 		      __entry->fid.vnode,
@@ -280,16 +271,16 @@ TRACE_EVENT(afs_make_vl_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(enum afs_vl_operation,	op		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->op = call->operation_ID;
 			   ),
 
-	    TP_printk("c=%p %s",
+	    TP_printk("c=%08x %s",
 		      __entry->call,
 		      __print_symbolic(__entry->op, afs_vl_operations))
 	    );
@@ -300,20 +291,20 @@ TRACE_EVENT(afs_call_done,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(struct rxrpc_call *,	rx_call		)
 		    __field(int,			ret		)
 		    __field(u32,			abort_code	)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->rx_call = call->rxcall;
 		    __entry->ret = call->error;
 		    __entry->abort_code = call->abort_code;
 			   ),
 
-	    TP_printk("   c=%p ret=%d ab=%d [%p]",
+	    TP_printk("   c=%08x ret=%d ab=%d [%p]",
 		      __entry->call,
 		      __entry->ret,
 		      __entry->abort_code,
@@ -327,7 +318,7 @@ TRACE_EVENT(afs_send_pages,
 	    TP_ARGS(call, msg, first, last, offset),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(pgoff_t,			first		)
 		    __field(pgoff_t,			last		)
 		    __field(unsigned int,		nr		)
@@ -337,7 +328,7 @@ TRACE_EVENT(afs_send_pages,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->first = first;
 		    __entry->last = last;
 		    __entry->nr = msg->msg_iter.nr_segs;
@@ -346,7 +337,7 @@ TRACE_EVENT(afs_send_pages,
 		    __entry->flags = msg->msg_flags;
 			   ),
 
-	    TP_printk(" c=%p %lx-%lx-%lx b=%x o=%x f=%x",
+	    TP_printk(" c=%08x %lx-%lx-%lx b=%x o=%x f=%x",
 		      __entry->call,
 		      __entry->first, __entry->first + __entry->nr - 1, __entry->last,
 		      __entry->bytes, __entry->offset,
@@ -360,7 +351,7 @@ TRACE_EVENT(afs_sent_pages,
 	    TP_ARGS(call, first, last, cursor, ret),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(pgoff_t,			first		)
 		    __field(pgoff_t,			last		)
 		    __field(pgoff_t,			cursor		)
@@ -368,14 +359,14 @@ TRACE_EVENT(afs_sent_pages,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->first = first;
 		    __entry->last = last;
 		    __entry->cursor = cursor;
 		    __entry->ret = ret;
 			   ),
 
-	    TP_printk(" c=%p %lx-%lx c=%lx r=%d",
+	    TP_printk(" c=%08x %lx-%lx c=%lx r=%d",
 		      __entry->call,
 		      __entry->first, __entry->last,
 		      __entry->cursor, __entry->ret)
@@ -450,7 +441,7 @@ TRACE_EVENT(afs_call_state,
 	    TP_ARGS(call, from, to, ret, remote_abort),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_call *,		call		)
+		    __field(unsigned int,		call		)
 		    __field(enum afs_call_state,	from		)
 		    __field(enum afs_call_state,	to		)
 		    __field(int,			ret		)
@@ -458,14 +449,14 @@ TRACE_EVENT(afs_call_state,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->from = from;
 		    __entry->to = to;
 		    __entry->ret = ret;
 		    __entry->abort = remote_abort;
 			   ),
 
-	    TP_printk("c=%p %u->%u r=%d ab=%d",
+	    TP_printk("c=%08x %u->%u r=%d ab=%d",
 		      __entry->call,
 		      __entry->from, __entry->to,
 		      __entry->ret, __entry->abort)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 41979f907575..4d2c2d35c5cb 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -439,20 +439,20 @@ TRACE_EVENT(rxrpc_conn,
 	    TP_ARGS(conn, op, usage, where),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_connection *,	conn		)
-		    __field(int,			op		)
-		    __field(int,			usage		)
-		    __field(const void *,		where		)
+		    __field(unsigned int,	conn		)
+		    __field(int,		op		)
+		    __field(int,		usage		)
+		    __field(const void *,	where		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->conn = conn;
+		    __entry->conn = conn->debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->where = where;
 			   ),
 
-	    TP_printk("C=%p %s u=%d sp=%pSR",
+	    TP_printk("C=%08x %s u=%d sp=%pSR",
 		      __entry->conn,
 		      __print_symbolic(__entry->op, rxrpc_conn_traces),
 		      __entry->usage,
@@ -466,7 +466,7 @@ TRACE_EVENT(rxrpc_client,
 	    TP_ARGS(conn, channel, op),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_connection *,	conn		)
+		    __field(unsigned int,		conn		)
 		    __field(u32,			cid		)
 		    __field(int,			channel		)
 		    __field(int,			usage		)
@@ -475,7 +475,7 @@ TRACE_EVENT(rxrpc_client,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->conn = conn;
+		    __entry->conn = conn->debug_id;
 		    __entry->channel = channel;
 		    __entry->usage = atomic_read(&conn->usage);
 		    __entry->op = op;
@@ -483,7 +483,7 @@ TRACE_EVENT(rxrpc_client,
 		    __entry->cs = conn->cache_state;
 			   ),
 
-	    TP_printk("C=%p h=%2d %s %s i=%08x u=%d",
+	    TP_printk("C=%08x h=%2d %s %s i=%08x u=%d",
 		      __entry->conn,
 		      __entry->channel,
 		      __print_symbolic(__entry->op, rxrpc_client_traces),
@@ -499,7 +499,7 @@ TRACE_EVENT(rxrpc_call,
 	    TP_ARGS(call, op, usage, where, aux),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(int,			op		)
 		    __field(int,			usage		)
 		    __field(const void *,		where		)
@@ -507,14 +507,14 @@ TRACE_EVENT(rxrpc_call,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->where = where;
 		    __entry->aux = aux;
 			   ),
 
-	    TP_printk("c=%p %s u=%d sp=%pSR a=%p",
+	    TP_printk("c=%08x %s u=%d sp=%pSR a=%p",
 		      __entry->call,
 		      __print_symbolic(__entry->op, rxrpc_call_traces),
 		      __entry->usage,
@@ -593,12 +593,13 @@ TRACE_EVENT(rxrpc_rx_done,
 	    );
 
 TRACE_EVENT(rxrpc_abort,
-	    TP_PROTO(const char *why, u32 cid, u32 call_id, rxrpc_seq_t seq,
-		     int abort_code, int error),
+	    TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id,
+		     rxrpc_seq_t seq, int abort_code, int error),
 
-	    TP_ARGS(why, cid, call_id, seq, abort_code, error),
+	    TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error),
 
 	    TP_STRUCT__entry(
+		    __field(unsigned int,		call_nr		)
 		    __array(char,			why, 4		)
 		    __field(u32,			cid		)
 		    __field(u32,			call_id		)
@@ -609,6 +610,7 @@ TRACE_EVENT(rxrpc_abort,
 
 	    TP_fast_assign(
 		    memcpy(__entry->why, why, 4);
+		    __entry->call_nr = call_nr;
 		    __entry->cid = cid;
 		    __entry->call_id = call_id;
 		    __entry->abort_code = abort_code;
@@ -616,7 +618,8 @@ TRACE_EVENT(rxrpc_abort,
 		    __entry->seq = seq;
 			   ),
 
-	    TP_printk("%08x:%08x s=%u a=%d e=%d %s",
+	    TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s",
+		      __entry->call_nr,
 		      __entry->cid, __entry->call_id, __entry->seq,
 		      __entry->abort_code, __entry->error, __entry->why)
 	    );
@@ -627,7 +630,7 @@ TRACE_EVENT(rxrpc_transmit,
 	    TP_ARGS(call, why),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_transmit_trace,	why		)
 		    __field(rxrpc_seq_t,		tx_hard_ack	)
 		    __field(rxrpc_seq_t,		tx_top		)
@@ -635,14 +638,14 @@ TRACE_EVENT(rxrpc_transmit,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->why = why;
 		    __entry->tx_hard_ack = call->tx_hard_ack;
 		    __entry->tx_top = call->tx_top;
 		    __entry->tx_winsize = call->tx_winsize;
 			   ),
 
-	    TP_printk("c=%p %s f=%08x n=%u/%u",
+	    TP_printk("c=%08x %s f=%08x n=%u/%u",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_transmit_traces),
 		      __entry->tx_hard_ack + 1,
@@ -657,7 +660,7 @@ TRACE_EVENT(rxrpc_rx_data,
 	    TP_ARGS(call, seq, serial, flags, anno),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_seq_t,		seq		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(u8,				flags		)
@@ -665,14 +668,14 @@ TRACE_EVENT(rxrpc_rx_data,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->seq = seq;
 		    __entry->serial = serial;
 		    __entry->flags = flags;
 		    __entry->anno = anno;
 			   ),
 
-	    TP_printk("c=%p DATA %08x q=%08x fl=%02x a=%02x",
+	    TP_printk("c=%08x DATA %08x q=%08x fl=%02x a=%02x",
 		      __entry->call,
 		      __entry->serial,
 		      __entry->seq,
@@ -688,7 +691,7 @@ TRACE_EVENT(rxrpc_rx_ack,
 	    TP_ARGS(call, serial, ack_serial, first, prev, reason, n_acks),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(rxrpc_serial_t,		ack_serial	)
 		    __field(rxrpc_seq_t,		first		)
@@ -698,7 +701,7 @@ TRACE_EVENT(rxrpc_rx_ack,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->serial = serial;
 		    __entry->ack_serial = ack_serial;
 		    __entry->first = first;
@@ -707,7 +710,7 @@ TRACE_EVENT(rxrpc_rx_ack,
 		    __entry->n_acks = n_acks;
 			   ),
 
-	    TP_printk("c=%p %08x %s r=%08x f=%08x p=%08x n=%u",
+	    TP_printk("c=%08x %08x %s r=%08x f=%08x p=%08x n=%u",
 		      __entry->call,
 		      __entry->serial,
 		      __print_symbolic(__entry->reason, rxrpc_ack_names),
@@ -724,18 +727,18 @@ TRACE_EVENT(rxrpc_rx_abort,
 	    TP_ARGS(call, serial, abort_code),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(u32,			abort_code	)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->serial = serial;
 		    __entry->abort_code = abort_code;
 			   ),
 
-	    TP_printk("c=%p ABORT %08x ac=%d",
+	    TP_printk("c=%08x ABORT %08x ac=%d",
 		      __entry->call,
 		      __entry->serial,
 		      __entry->abort_code)
@@ -748,20 +751,20 @@ TRACE_EVENT(rxrpc_rx_rwind_change,
 	    TP_ARGS(call, serial, rwind, wake),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(u32,			rwind		)
 		    __field(bool,			wake		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->serial = serial;
 		    __entry->rwind = rwind;
 		    __entry->wake = wake;
 			   ),
 
-	    TP_printk("c=%p %08x rw=%u%s",
+	    TP_printk("c=%08x %08x rw=%u%s",
 		      __entry->call,
 		      __entry->serial,
 		      __entry->rwind,
@@ -775,7 +778,7 @@ TRACE_EVENT(rxrpc_tx_data,
 	    TP_ARGS(call, seq, serial, flags, retrans, lose),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_seq_t,		seq		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(u8,				flags		)
@@ -784,7 +787,7 @@ TRACE_EVENT(rxrpc_tx_data,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->seq = seq;
 		    __entry->serial = serial;
 		    __entry->flags = flags;
@@ -792,7 +795,7 @@ TRACE_EVENT(rxrpc_tx_data,
 		    __entry->lose = lose;
 			   ),
 
-	    TP_printk("c=%p DATA %08x q=%08x fl=%02x%s%s",
+	    TP_printk("c=%08x DATA %08x q=%08x fl=%02x%s%s",
 		      __entry->call,
 		      __entry->serial,
 		      __entry->seq,
@@ -809,7 +812,7 @@ TRACE_EVENT(rxrpc_tx_ack,
 	    TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(rxrpc_seq_t,		ack_first	)
 		    __field(rxrpc_serial_t,		ack_serial	)
@@ -818,7 +821,7 @@ TRACE_EVENT(rxrpc_tx_ack,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call ? call->debug_id : 0;
 		    __entry->serial = serial;
 		    __entry->ack_first = ack_first;
 		    __entry->ack_serial = ack_serial;
@@ -826,7 +829,7 @@ TRACE_EVENT(rxrpc_tx_ack,
 		    __entry->n_acks = n_acks;
 			   ),
 
-	    TP_printk(" c=%p ACK  %08x %s f=%08x r=%08x n=%u",
+	    TP_printk(" c=%08x ACK  %08x %s f=%08x r=%08x n=%u",
 		      __entry->call,
 		      __entry->serial,
 		      __print_symbolic(__entry->reason, rxrpc_ack_names),
@@ -842,7 +845,7 @@ TRACE_EVENT(rxrpc_receive,
 	    TP_ARGS(call, why, serial, seq),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_receive_trace,	why		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(rxrpc_seq_t,		seq		)
@@ -851,7 +854,7 @@ TRACE_EVENT(rxrpc_receive,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->why = why;
 		    __entry->serial = serial;
 		    __entry->seq = seq;
@@ -859,7 +862,7 @@ TRACE_EVENT(rxrpc_receive,
 		    __entry->top = call->rx_top;
 			   ),
 
-	    TP_printk("c=%p %s r=%08x q=%08x w=%08x-%08x",
+	    TP_printk("c=%08x %s r=%08x q=%08x w=%08x-%08x",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_receive_traces),
 		      __entry->serial,
@@ -876,7 +879,7 @@ TRACE_EVENT(rxrpc_recvmsg,
 	    TP_ARGS(call, why, seq, offset, len, ret),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_recvmsg_trace,	why		)
 		    __field(rxrpc_seq_t,		seq		)
 		    __field(unsigned int,		offset		)
@@ -885,7 +888,7 @@ TRACE_EVENT(rxrpc_recvmsg,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->why = why;
 		    __entry->seq = seq;
 		    __entry->offset = offset;
@@ -893,7 +896,7 @@ TRACE_EVENT(rxrpc_recvmsg,
 		    __entry->ret = ret;
 			   ),
 
-	    TP_printk("c=%p %s q=%08x o=%u l=%u ret=%d",
+	    TP_printk("c=%08x %s q=%08x o=%u l=%u ret=%d",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_recvmsg_traces),
 		      __entry->seq,
@@ -909,18 +912,18 @@ TRACE_EVENT(rxrpc_rtt_tx,
 	    TP_ARGS(call, why, send_serial),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_rtt_tx_trace,	why		)
 		    __field(rxrpc_serial_t,		send_serial	)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->why = why;
 		    __entry->send_serial = send_serial;
 			   ),
 
-	    TP_printk("c=%p %s sr=%08x",
+	    TP_printk("c=%08x %s sr=%08x",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_rtt_tx_traces),
 		      __entry->send_serial)
@@ -934,7 +937,7 @@ TRACE_EVENT(rxrpc_rtt_rx,
 	    TP_ARGS(call, why, send_serial, resp_serial, rtt, nr, avg),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_rtt_rx_trace,	why		)
 		    __field(u8,				nr		)
 		    __field(rxrpc_serial_t,		send_serial	)
@@ -944,7 +947,7 @@ TRACE_EVENT(rxrpc_rtt_rx,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->why = why;
 		    __entry->send_serial = send_serial;
 		    __entry->resp_serial = resp_serial;
@@ -953,7 +956,7 @@ TRACE_EVENT(rxrpc_rtt_rx,
 		    __entry->avg = avg;
 			   ),
 
-	    TP_printk("c=%p %s sr=%08x rr=%08x rtt=%lld nr=%u avg=%lld",
+	    TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%lld nr=%u avg=%lld",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_rtt_rx_traces),
 		      __entry->send_serial,
@@ -970,7 +973,7 @@ TRACE_EVENT(rxrpc_timer,
 	    TP_ARGS(call, why, now),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,		call		)
+		    __field(unsigned int,			call		)
 		    __field(enum rxrpc_timer_trace,		why		)
 		    __field(long,				now		)
 		    __field(long,				ack_at		)
@@ -984,7 +987,7 @@ TRACE_EVENT(rxrpc_timer,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call		= call;
+		    __entry->call		= call->debug_id;
 		    __entry->why		= why;
 		    __entry->now		= now;
 		    __entry->ack_at		= call->ack_at;
@@ -996,7 +999,7 @@ TRACE_EVENT(rxrpc_timer,
 		    __entry->timer		= call->timer.expires;
 			   ),
 
-	    TP_printk("c=%p %s a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld",
+	    TP_printk("c=%08x %s a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_timer_traces),
 		      __entry->ack_at - __entry->now,
@@ -1039,7 +1042,7 @@ TRACE_EVENT(rxrpc_propose_ack,
 		    outcome),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,		call		)
+		    __field(unsigned int,			call		)
 		    __field(enum rxrpc_propose_ack_trace,	why		)
 		    __field(rxrpc_serial_t,			serial		)
 		    __field(u8,					ack_reason	)
@@ -1049,7 +1052,7 @@ TRACE_EVENT(rxrpc_propose_ack,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call	= call;
+		    __entry->call	= call->debug_id;
 		    __entry->why	= why;
 		    __entry->serial	= serial;
 		    __entry->ack_reason	= ack_reason;
@@ -1058,7 +1061,7 @@ TRACE_EVENT(rxrpc_propose_ack,
 		    __entry->outcome	= outcome;
 			   ),
 
-	    TP_printk("c=%p %s %s r=%08x i=%u b=%u%s",
+	    TP_printk("c=%08x %s %s r=%08x i=%u b=%u%s",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_propose_ack_traces),
 		      __print_symbolic(__entry->ack_reason, rxrpc_ack_names),
@@ -1075,20 +1078,20 @@ TRACE_EVENT(rxrpc_retransmit,
 	    TP_ARGS(call, seq, annotation, expiry),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_seq_t,		seq		)
 		    __field(u8,				annotation	)
 		    __field(s64,			expiry		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->seq = seq;
 		    __entry->annotation = annotation;
 		    __entry->expiry = expiry;
 			   ),
 
-	    TP_printk("c=%p q=%x a=%02x xp=%lld",
+	    TP_printk("c=%08x q=%x a=%02x xp=%lld",
 		      __entry->call,
 		      __entry->seq,
 		      __entry->annotation,
@@ -1102,7 +1105,7 @@ TRACE_EVENT(rxrpc_congest,
 	    TP_ARGS(call, summary, ack_serial, change),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,		call		)
+		    __field(unsigned int,			call		)
 		    __field(enum rxrpc_congest_change,		change		)
 		    __field(rxrpc_seq_t,			hard_ack	)
 		    __field(rxrpc_seq_t,			top		)
@@ -1112,7 +1115,7 @@ TRACE_EVENT(rxrpc_congest,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call	= call;
+		    __entry->call	= call->debug_id;
 		    __entry->change	= change;
 		    __entry->hard_ack	= call->tx_hard_ack;
 		    __entry->top	= call->tx_top;
@@ -1121,7 +1124,7 @@ TRACE_EVENT(rxrpc_congest,
 		    memcpy(&__entry->sum, summary, sizeof(__entry->sum));
 			   ),
 
-	    TP_printk("c=%p r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
+	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
 		      __entry->call,
 		      __entry->ack_serial,
 		      __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
@@ -1146,16 +1149,16 @@ TRACE_EVENT(rxrpc_disconnect_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(u32,			abort_code	)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->abort_code = call->abort_code;
 			   ),
 
-	    TP_printk("c=%p ab=%08x",
+	    TP_printk("c=%08x ab=%08x",
 		      __entry->call,
 		      __entry->abort_code)
 	    );
@@ -1166,16 +1169,16 @@ TRACE_EVENT(rxrpc_improper_term,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(u32,			abort_code	)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->abort_code = call->abort_code;
 			   ),
 
-	    TP_printk("c=%p ab=%08x",
+	    TP_printk("c=%08x ab=%08x",
 		      __entry->call,
 		      __entry->abort_code)
 	    );
@@ -1187,18 +1190,18 @@ TRACE_EVENT(rxrpc_rx_eproto,
 	    TP_ARGS(call, serial, why),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(const char *,		why		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->serial = serial;
 		    __entry->why = why;
 			   ),
 
-	    TP_printk("c=%p EPROTO %08x %s",
+	    TP_printk("c=%08x EPROTO %08x %s",
 		      __entry->call,
 		      __entry->serial,
 		      __entry->why)
@@ -1210,20 +1213,20 @@ TRACE_EVENT(rxrpc_connect_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(unsigned long,		user_call_ID	)
 		    __field(u32,			cid		)
 		    __field(u32,			call_id		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->user_call_ID = call->user_call_ID;
 		    __entry->cid = call->cid;
 		    __entry->call_id = call->call_id;
 			   ),
 
-	    TP_printk("c=%p u=%p %08x:%08x",
+	    TP_printk("c=%08x u=%p %08x:%08x",
 		      __entry->call,
 		      (void *)__entry->user_call_ID,
 		      __entry->cid,
@@ -1236,18 +1239,18 @@ TRACE_EVENT(rxrpc_resend,
 	    TP_ARGS(call, ix),
 
 	    TP_STRUCT__entry(
-		    __field(struct rxrpc_call *,	call		)
+		    __field(unsigned int,		call		)
 		    __field(int,			ix		)
 		    __array(u8,				anno, 64	)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call;
+		    __entry->call = call->debug_id;
 		    __entry->ix = ix;
 		    memcpy(__entry->anno, call->rxtx_annotations, 64);
 			   ),
 
-	    TP_printk("c=%p ix=%u a=%64phN",
+	    TP_printk("c=%08x ix=%u a=%64phN",
 		      __entry->call,
 		      __entry->ix,
 		      __entry->anno)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 9e1c2c6b6a67..ec5ec68be1aa 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -40,6 +40,7 @@ static const struct proto_ops rxrpc_rpc_ops;
 
 /* current debugging ID */
 atomic_t rxrpc_debug_id;
+EXPORT_SYMBOL(rxrpc_debug_id);
 
 /* count of skbs currently in use */
 atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs;
@@ -267,6 +268,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * @gfp: The allocation constraints
  * @notify_rx: Where to send notifications instead of socket queue
  * @upgrade: Request service upgrade for call
+ * @debug_id: The debug ID for tracing to be assigned to the call
  *
  * Allow a kernel service to begin a call on the nominated socket.  This just
  * sets up all the internal tracking structures and allocates connection and
@@ -282,7 +284,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   s64 tx_total_len,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx,
-					   bool upgrade)
+					   bool upgrade,
+					   unsigned int debug_id)
 {
 	struct rxrpc_conn_parameters cp;
 	struct rxrpc_call_params p;
@@ -314,7 +317,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	cp.exclusive		= false;
 	cp.upgrade		= upgrade;
 	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp);
+	call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp, debug_id);
 	/* The socket has been unlocked. */
 	if (!IS_ERR(call)) {
 		call->notify_rx = notify_rx;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 416688381eb7..9c9817ddafc5 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -691,7 +691,6 @@ struct rxrpc_send_params {
  * af_rxrpc.c
  */
 extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs;
-extern atomic_t rxrpc_debug_id;
 extern struct workqueue_struct *rxrpc_workqueue;
 
 /*
@@ -732,11 +731,12 @@ extern unsigned int rxrpc_max_call_lifetime;
 extern struct kmem_cache *rxrpc_call_jar;
 
 struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long);
-struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t);
+struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int);
 struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
 					 struct rxrpc_conn_parameters *,
 					 struct sockaddr_rxrpc *,
-					 struct rxrpc_call_params *, gfp_t);
+					 struct rxrpc_call_params *, gfp_t,
+					 unsigned int);
 int rxrpc_retry_client_call(struct rxrpc_sock *,
 			    struct rxrpc_call *,
 			    struct rxrpc_conn_parameters *,
@@ -822,7 +822,7 @@ static inline bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call,
 				      rxrpc_seq_t seq,
 				      u32 abort_code, int error)
 {
-	trace_rxrpc_abort(why, call->cid, call->call_id, seq,
+	trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
 			  abort_code, error);
 	return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
 					   abort_code, error);
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 3028298ca561..92ebd1d7e0bb 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -34,7 +34,8 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 				      struct rxrpc_backlog *b,
 				      rxrpc_notify_rx_t notify_rx,
 				      rxrpc_user_attach_call_t user_attach_call,
-				      unsigned long user_call_ID, gfp_t gfp)
+				      unsigned long user_call_ID, gfp_t gfp,
+				      unsigned int debug_id)
 {
 	const void *here = __builtin_return_address(0);
 	struct rxrpc_call *call;
@@ -94,7 +95,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 	/* Now it gets complicated, because calls get registered with the
 	 * socket here, particularly if a user ID is preassigned by the user.
 	 */
-	call = rxrpc_alloc_call(rx, gfp);
+	call = rxrpc_alloc_call(rx, gfp, debug_id);
 	if (!call)
 		return -ENOMEM;
 	call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
@@ -174,7 +175,8 @@ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp)
 	if (rx->discard_new_call)
 		return 0;
 
-	while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp) == 0)
+	while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp,
+					  atomic_inc_return(&rxrpc_debug_id)) == 0)
 		;
 
 	return 0;
@@ -347,7 +349,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 		   service_id == rx->second_service))
 		goto found_service;
 
-	trace_rxrpc_abort("INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+	trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
 			  RX_INVALID_OPERATION, EOPNOTSUPP);
 	skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
 	skb->priority = RX_INVALID_OPERATION;
@@ -358,7 +360,7 @@ found_service:
 	spin_lock(&rx->incoming_lock);
 	if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
 	    rx->sk.sk_state == RXRPC_CLOSE) {
-		trace_rxrpc_abort("CLS", sp->hdr.cid, sp->hdr.callNumber,
+		trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
 				  sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
 		skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
 		skb->priority = RX_INVALID_OPERATION;
@@ -635,6 +637,7 @@ out_discard:
  * @user_attach_call: Func to attach call to user_call_ID
  * @user_call_ID: The tag to attach to the preallocated call
  * @gfp: The allocation conditions.
+ * @debug_id: The tracing debug ID.
  *
  * Charge up the socket with preallocated calls, each with a user ID.  A
  * function should be provided to effect the attachment from the user's side.
@@ -645,7 +648,8 @@ out_discard:
 int rxrpc_kernel_charge_accept(struct socket *sock,
 			       rxrpc_notify_rx_t notify_rx,
 			       rxrpc_user_attach_call_t user_attach_call,
-			       unsigned long user_call_ID, gfp_t gfp)
+			       unsigned long user_call_ID, gfp_t gfp,
+			       unsigned int debug_id)
 {
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	struct rxrpc_backlog *b = rx->backlog;
@@ -655,6 +659,6 @@ int rxrpc_kernel_charge_accept(struct socket *sock,
 
 	return rxrpc_service_prealloc_one(rx, b, notify_rx,
 					  user_attach_call, user_call_ID,
-					  gfp);
+					  gfp, debug_id);
 }
 EXPORT_SYMBOL(rxrpc_kernel_charge_accept);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 0b2db38dd32d..147657dfe757 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -99,7 +99,8 @@ found_extant_call:
 /*
  * allocate a new call
  */
-struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp)
+struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
+				    unsigned int debug_id)
 {
 	struct rxrpc_call *call;
 
@@ -138,7 +139,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp)
 	spin_lock_init(&call->notify_lock);
 	rwlock_init(&call->state_lock);
 	atomic_set(&call->usage, 1);
-	call->debug_id = atomic_inc_return(&rxrpc_debug_id);
+	call->debug_id = debug_id;
 	call->tx_total_len = -1;
 	call->next_rx_timo = 20 * HZ;
 	call->next_req_timo = 1 * HZ;
@@ -166,14 +167,15 @@ nomem:
  */
 static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
 						  struct sockaddr_rxrpc *srx,
-						  gfp_t gfp)
+						  gfp_t gfp,
+						  unsigned int debug_id)
 {
 	struct rxrpc_call *call;
 	ktime_t now;
 
 	_enter("");
 
-	call = rxrpc_alloc_call(rx, gfp);
+	call = rxrpc_alloc_call(rx, gfp, debug_id);
 	if (!call)
 		return ERR_PTR(-ENOMEM);
 	call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
@@ -214,7 +216,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 					 struct rxrpc_conn_parameters *cp,
 					 struct sockaddr_rxrpc *srx,
 					 struct rxrpc_call_params *p,
-					 gfp_t gfp)
+					 gfp_t gfp,
+					 unsigned int debug_id)
 	__releases(&rx->sk.sk_lock.slock)
 {
 	struct rxrpc_call *call, *xcall;
@@ -225,7 +228,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 
 	_enter("%p,%lx", rx, p->user_call_ID);
 
-	call = rxrpc_alloc_client_call(rx, srx, gfp);
+	call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
 	if (IS_ERR(call)) {
 		release_sock(&rx->sk);
 		_leave(" = %ld", PTR_ERR(call));
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index b1dfae107431..d2ec3fd593e8 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -160,7 +160,8 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
 			lockdep_is_held(&conn->channel_lock));
 		if (call) {
 			if (compl == RXRPC_CALL_LOCALLY_ABORTED)
-				trace_rxrpc_abort("CON", call->cid,
+				trace_rxrpc_abort(call->debug_id,
+						  "CON", call->cid,
 						  call->call_id, 0,
 						  abort_code, error);
 			if (rxrpc_set_call_completion(call, compl,
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 6fc61400337f..2a868fdab0ae 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1307,21 +1307,21 @@ out_unlock:
 
 wrong_security:
 	rcu_read_unlock();
-	trace_rxrpc_abort("SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+	trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
 			  RXKADINCONSISTENCY, EBADMSG);
 	skb->priority = RXKADINCONSISTENCY;
 	goto post_abort;
 
 reupgrade:
 	rcu_read_unlock();
-	trace_rxrpc_abort("UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+	trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
 			  RX_PROTOCOL_ERROR, EBADMSG);
 	goto protocol_error;
 
 bad_message_unlock:
 	rcu_read_unlock();
 bad_message:
-	trace_rxrpc_abort("BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+	trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
 			  RX_PROTOCOL_ERROR, EBADMSG);
 protocol_error:
 	skb->priority = RX_PROTOCOL_ERROR;
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 09f2a3e05221..8503f279b467 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -579,7 +579,8 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 	cp.exclusive		= rx->exclusive | p->exclusive;
 	cp.upgrade		= p->upgrade;
 	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL);
+	call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL,
+				     atomic_inc_return(&rxrpc_debug_id));
 	/* The socket is now unlocked */
 
 	_leave(" = %p\n", call);
-- 
cgit v1.2.3


From 5e78abd075e562fd5748ac3bfb067941e8baf6c7 Mon Sep 17 00:00:00 2001
From: "tamizhr@codeaurora.org" <tamizhr@codeaurora.org>
Date: Tue, 27 Mar 2018 19:16:15 +0530
Subject: cfg80211: fix data type of sta_opmode_info parameter

Currently bw and smps_mode are u8 type value in sta_opmode_info
structure. This values filled in mac80211 from ieee80211_sta_rx_bandwidth
and ieee80211_smps_mode. These enum values are specific to mac80211 and
userspace/cfg80211 doesn't know about that. This will lead to incorrect
result/assumption by the user space application.
Change bw and smps_mode parameters to their respective enums in nl80211.

Signed-off-by: Tamizh chelvam <tamizhr@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index fc40843baed3..4341508bc6a4 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3572,15 +3572,15 @@ enum wiphy_opmode_flag {
 /**
  * struct sta_opmode_info - Station's ht/vht operation mode information
  * @changed: contains value from &enum wiphy_opmode_flag
- * @smps_mode: New SMPS mode of a station
- * @bw: new max bandwidth value of a station
+ * @smps_mode: New SMPS mode value from &enum nl80211_smps_mode of a station
+ * @bw: new max bandwidth value from &enum nl80211_chan_width of a station
  * @rx_nss: new rx_nss value of a station
  */
 
 struct sta_opmode_info {
 	u32 changed;
-	u8 smps_mode;
-	u8 bw;
+	enum nl80211_smps_mode smps_mode;
+	enum nl80211_chan_width bw;
 	u8 rx_nss;
 };
 
-- 
cgit v1.2.3


From 230ebaa189af44d50dccb4a1846e39ca594e347b Mon Sep 17 00:00:00 2001
From: Haim Dreyfuss <haim.dreyfuss@intel.com>
Date: Wed, 28 Mar 2018 13:24:09 +0300
Subject: cfg80211: read wmm rules from regulatory database

ETSI EN 301 893 v2.1.1 (2017-05) standard defines a new channel access
mechanism that all devices (WLAN and LAA) need to comply with.
The regulatory database can now be loaded into the kernel and also
has the option to load optional data.
In order to be able to comply with ETSI standard, we add wmm_rule into
regulatory rule and add the option to read its value from the regulatory
database.

Signed-off-by: Haim Dreyfuss <haim.dreyfuss@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
[johannes: fix memory leak in error path]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/regulatory.h |  28 +++++++++
 net/wireless/reg.c       | 148 ++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 169 insertions(+), 7 deletions(-)

(limited to 'include/net')

diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index f83cacce3308..60f8cc86a447 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -4,6 +4,7 @@
  * regulatory support structures
  *
  * Copyright 2008-2009	Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
+ * Copyright (C) 2018 Intel Corporation
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -188,9 +189,35 @@ struct ieee80211_power_rule {
 	u32 max_eirp;
 };
 
+/**
+ * struct ieee80211_wmm_ac - used to store per ac wmm regulatory limitation
+ *
+ * The information provided in this structure is required for QoS
+ * transmit queue configuration. Cf. IEEE 802.11 7.3.2.29.
+ *
+ * @cw_min: minimum contention window [a value of the form
+ *      2^n-1 in the range 1..32767]
+ * @cw_max: maximum contention window [like @cw_min]
+ * @cot: maximum burst time in units of 32 usecs, 0 meaning disabled
+ * @aifsn: arbitration interframe space [0..255]
+ *
+ */
+struct ieee80211_wmm_ac {
+	u16 cw_min;
+	u16 cw_max;
+	u16 cot;
+	u8 aifsn;
+};
+
+struct ieee80211_wmm_rule {
+	struct ieee80211_wmm_ac client[IEEE80211_NUM_ACS];
+	struct ieee80211_wmm_ac ap[IEEE80211_NUM_ACS];
+};
+
 struct ieee80211_reg_rule {
 	struct ieee80211_freq_range freq_range;
 	struct ieee80211_power_rule power_rule;
+	struct ieee80211_wmm_rule *wmm_rule;
 	u32 flags;
 	u32 dfs_cac_ms;
 };
@@ -198,6 +225,7 @@ struct ieee80211_reg_rule {
 struct ieee80211_regdomain {
 	struct rcu_head rcu_head;
 	u32 n_reg_rules;
+	u32 n_wmm_rules;
 	char alpha2[3];
 	enum nl80211_dfs_regions dfs_region;
 	struct ieee80211_reg_rule reg_rules[];
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 7b42f0bacfd8..eddc834f6358 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -5,6 +5,7 @@
  * Copyright 2008-2011	Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright      2017  Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -424,23 +425,36 @@ static const struct ieee80211_regdomain *
 reg_copy_regd(const struct ieee80211_regdomain *src_regd)
 {
 	struct ieee80211_regdomain *regd;
-	int size_of_regd;
+	int size_of_regd, size_of_wmms;
 	unsigned int i;
+	struct ieee80211_wmm_rule *d_wmm, *s_wmm;
 
 	size_of_regd =
 		sizeof(struct ieee80211_regdomain) +
 		src_regd->n_reg_rules * sizeof(struct ieee80211_reg_rule);
+	size_of_wmms = src_regd->n_wmm_rules *
+		sizeof(struct ieee80211_wmm_rule);
 
-	regd = kzalloc(size_of_regd, GFP_KERNEL);
+	regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL);
 	if (!regd)
 		return ERR_PTR(-ENOMEM);
 
 	memcpy(regd, src_regd, sizeof(struct ieee80211_regdomain));
 
-	for (i = 0; i < src_regd->n_reg_rules; i++)
+	d_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd);
+	s_wmm = (struct ieee80211_wmm_rule *)((u8 *)src_regd + size_of_regd);
+	memcpy(d_wmm, s_wmm, size_of_wmms);
+
+	for (i = 0; i < src_regd->n_reg_rules; i++) {
 		memcpy(&regd->reg_rules[i], &src_regd->reg_rules[i],
 		       sizeof(struct ieee80211_reg_rule));
+		if (!src_regd->reg_rules[i].wmm_rule)
+			continue;
 
+		regd->reg_rules[i].wmm_rule = d_wmm +
+			(src_regd->reg_rules[i].wmm_rule - s_wmm) /
+			sizeof(struct ieee80211_wmm_rule);
+	}
 	return regd;
 }
 
@@ -595,6 +609,17 @@ enum fwdb_flags {
 	FWDB_FLAG_AUTO_BW	= BIT(4),
 };
 
+struct fwdb_wmm_ac {
+	u8 ecw;
+	u8 aifsn;
+	__be16 cot;
+} __packed;
+
+struct fwdb_wmm_rule {
+	struct fwdb_wmm_ac client[IEEE80211_NUM_ACS];
+	struct fwdb_wmm_ac ap[IEEE80211_NUM_ACS];
+} __packed;
+
 struct fwdb_rule {
 	u8 len;
 	u8 flags;
@@ -602,6 +627,7 @@ struct fwdb_rule {
 	__be32 start, end, max_bw;
 	/* start of optional data */
 	__be16 cac_timeout;
+	__be16 wmm_ptr;
 } __packed __aligned(4);
 
 #define FWDB_MAGIC 0x52474442
@@ -613,6 +639,31 @@ struct fwdb_header {
 	struct fwdb_country country[];
 } __packed __aligned(4);
 
+static int ecw2cw(int ecw)
+{
+	return (1 << ecw) - 1;
+}
+
+static bool valid_wmm(struct fwdb_wmm_rule *rule)
+{
+	struct fwdb_wmm_ac *ac = (struct fwdb_wmm_ac *)rule;
+	int i;
+
+	for (i = 0; i < IEEE80211_NUM_ACS * 2; i++) {
+		u16 cw_min = ecw2cw((ac[i].ecw & 0xf0) >> 4);
+		u16 cw_max = ecw2cw(ac[i].ecw & 0x0f);
+		u8 aifsn = ac[i].aifsn;
+
+		if (cw_min >= cw_max)
+			return false;
+
+		if (aifsn < 1)
+			return false;
+	}
+
+	return true;
+}
+
 static bool valid_rule(const u8 *data, unsigned int size, u16 rule_ptr)
 {
 	struct fwdb_rule *rule = (void *)(data + (rule_ptr << 2));
@@ -623,7 +674,18 @@ static bool valid_rule(const u8 *data, unsigned int size, u16 rule_ptr)
 	/* mandatory fields */
 	if (rule->len < offsetofend(struct fwdb_rule, max_bw))
 		return false;
+	if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) {
+		u32 wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2;
+		struct fwdb_wmm_rule *wmm;
 
+		if (wmm_ptr + sizeof(struct fwdb_wmm_rule) > size)
+			return false;
+
+		wmm = (void *)(data + wmm_ptr);
+
+		if (!valid_wmm(wmm))
+			return false;
+	}
 	return true;
 }
 
@@ -798,23 +860,64 @@ static bool valid_regdb(const u8 *data, unsigned int size)
 	return true;
 }
 
+static void set_wmm_rule(struct ieee80211_wmm_rule *rule,
+			 struct fwdb_wmm_rule *wmm)
+{
+	unsigned int i;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		rule->client[i].cw_min =
+			ecw2cw((wmm->client[i].ecw & 0xf0) >> 4);
+		rule->client[i].cw_max = ecw2cw(wmm->client[i].ecw & 0x0f);
+		rule->client[i].aifsn =  wmm->client[i].aifsn;
+		rule->client[i].cot = 1000 * be16_to_cpu(wmm->client[i].cot);
+		rule->ap[i].cw_min = ecw2cw((wmm->ap[i].ecw & 0xf0) >> 4);
+		rule->ap[i].cw_max = ecw2cw(wmm->ap[i].ecw & 0x0f);
+		rule->ap[i].aifsn = wmm->ap[i].aifsn;
+		rule->ap[i].cot = 1000 * be16_to_cpu(wmm->ap[i].cot);
+	}
+}
+
+struct wmm_ptrs {
+	struct ieee80211_wmm_rule *rule;
+	u32 ptr;
+};
+
+static struct ieee80211_wmm_rule *find_wmm_ptr(struct wmm_ptrs *wmm_ptrs,
+					       u32 wmm_ptr, int n_wmms)
+{
+	int i;
+
+	for (i = 0; i < n_wmms; i++) {
+		if (wmm_ptrs[i].ptr == wmm_ptr)
+			return wmm_ptrs[i].rule;
+	}
+	return NULL;
+}
+
 static int regdb_query_country(const struct fwdb_header *db,
 			       const struct fwdb_country *country)
 {
 	unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2;
 	struct fwdb_collection *coll = (void *)((u8 *)db + ptr);
 	struct ieee80211_regdomain *regdom;
-	unsigned int size_of_regd;
-	unsigned int i;
+	struct ieee80211_regdomain *tmp_rd;
+	unsigned int size_of_regd, i, n_wmms = 0;
+	struct wmm_ptrs *wmm_ptrs;
 
-	size_of_regd =
-		sizeof(struct ieee80211_regdomain) +
+	size_of_regd = sizeof(struct ieee80211_regdomain) +
 		coll->n_rules * sizeof(struct ieee80211_reg_rule);
 
 	regdom = kzalloc(size_of_regd, GFP_KERNEL);
 	if (!regdom)
 		return -ENOMEM;
 
+	wmm_ptrs = kcalloc(coll->n_rules, sizeof(*wmm_ptrs), GFP_KERNEL);
+	if (!wmm_ptrs) {
+		kfree(regdom);
+		return -ENOMEM;
+	}
+
 	regdom->n_reg_rules = coll->n_rules;
 	regdom->alpha2[0] = country->alpha2[0];
 	regdom->alpha2[1] = country->alpha2[1];
@@ -851,7 +954,38 @@ static int regdb_query_country(const struct fwdb_header *db,
 		if (rule->len >= offsetofend(struct fwdb_rule, cac_timeout))
 			rrule->dfs_cac_ms =
 				1000 * be16_to_cpu(rule->cac_timeout);
+		if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) {
+			u32 wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2;
+			struct ieee80211_wmm_rule *wmm_pos =
+				find_wmm_ptr(wmm_ptrs, wmm_ptr, n_wmms);
+			struct fwdb_wmm_rule *wmm;
+			struct ieee80211_wmm_rule *wmm_rule;
+
+			if (wmm_pos) {
+				rrule->wmm_rule = wmm_pos;
+				continue;
+			}
+			wmm = (void *)((u8 *)db + wmm_ptr);
+			tmp_rd = krealloc(regdom, size_of_regd + (n_wmms + 1) *
+					  sizeof(struct ieee80211_wmm_rule),
+					  GFP_KERNEL);
+
+			if (!tmp_rd) {
+				kfree(regdom);
+				return -ENOMEM;
+			}
+			regdom = tmp_rd;
+
+			wmm_rule = (struct ieee80211_wmm_rule *)
+				((u8 *)regdom + size_of_regd + n_wmms *
+				sizeof(struct ieee80211_wmm_rule));
+
+			set_wmm_rule(wmm_rule, wmm);
+			wmm_ptrs[n_wmms].ptr = wmm_ptr;
+			wmm_ptrs[n_wmms++].rule = wmm_rule;
+		}
 	}
+	kfree(wmm_ptrs);
 
 	return reg_schedule_apply(regdom);
 }
-- 
cgit v1.2.3


From 19d3577e35e0cbb42694811b096e749a0f89a824 Mon Sep 17 00:00:00 2001
From: Haim Dreyfuss <haim.dreyfuss@intel.com>
Date: Wed, 28 Mar 2018 13:24:11 +0300
Subject: cfg80211: Add API to allow querying regdb for wmm_rule

In general regulatory self managed devices maintain their own
regulatory profiles thus it doesn't have to query the regulatory database
on country change.

ETSI has recently introduced a new channel access mechanism for 5GHz
that all wlan devices need to comply with.
These values are stored in the regulatory database.
There are self managed devices which can't maintain these
values on their own. Add API to allow self managed regulatory devices
to query the regulatory database for high band wmm rule.

Signed-off-by: Haim Dreyfuss <haim.dreyfuss@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
[johannes: fix documentation]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 28 ++++++++++++++++++++++++++
 net/wireless/reg.c     | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 4341508bc6a4..bfe174896fcf 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -6,6 +6,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014 Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -4657,6 +4658,33 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
  */
 const char *reg_initiator_name(enum nl80211_reg_initiator initiator);
 
+/**
+ * DOC: Internal regulatory db functions
+ *
+ */
+
+/**
+ * reg_query_regdb_wmm -  Query internal regulatory db for wmm rule
+ * Regulatory self-managed driver can use it to proactively
+ *
+ * @alpha2: the ISO/IEC 3166 alpha2 wmm rule to be queried.
+ * @freq: the freqency(in MHz) to be queried.
+ * @ptr: pointer where the regdb wmm data is to be stored (or %NULL if
+ *	irrelevant). This can be used later for deduplication.
+ * @rule: pointer to store the wmm rule from the regulatory db.
+ *
+ * Self-managed wireless drivers can use this function to  query
+ * the internal regulatory database to check whether the given
+ * ISO/IEC 3166 alpha2 country and freq have wmm rule limitations.
+ *
+ * Drivers should check the return value, its possible you can get
+ * an -ENODATA.
+ *
+ * Return: 0 on success. -ENODATA.
+ */
+int reg_query_regdb_wmm(char *alpha2, int freq, u32 *ptr,
+			struct ieee80211_wmm_rule *rule);
+
 /*
  * callbacks for asynchronous cfg80211 methods, notification
  * functions and BSS handling helpers
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index e352a0d1c438..16c7e4ef5820 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -878,6 +878,60 @@ static void set_wmm_rule(struct ieee80211_wmm_rule *rule,
 	}
 }
 
+static int __regdb_query_wmm(const struct fwdb_header *db,
+			     const struct fwdb_country *country, int freq,
+			     u32 *dbptr, struct ieee80211_wmm_rule *rule)
+{
+	unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2;
+	struct fwdb_collection *coll = (void *)((u8 *)db + ptr);
+	int i;
+
+	for (i = 0; i < coll->n_rules; i++) {
+		__be16 *rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2));
+		unsigned int rule_ptr = be16_to_cpu(rules_ptr[i]) << 2;
+		struct fwdb_rule *rrule = (void *)((u8 *)db + rule_ptr);
+		struct fwdb_wmm_rule *wmm;
+		unsigned int wmm_ptr;
+
+		if (rrule->len < offsetofend(struct fwdb_rule, wmm_ptr))
+			continue;
+
+		if (freq >= KHZ_TO_MHZ(be32_to_cpu(rrule->start)) &&
+		    freq <= KHZ_TO_MHZ(be32_to_cpu(rrule->end))) {
+			wmm_ptr = be16_to_cpu(rrule->wmm_ptr) << 2;
+			wmm = (void *)((u8 *)db + wmm_ptr);
+			set_wmm_rule(rule, wmm);
+			if (dbptr)
+				*dbptr = wmm_ptr;
+			return 0;
+		}
+	}
+
+	return -ENODATA;
+}
+
+int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr,
+			struct ieee80211_wmm_rule *rule)
+{
+	const struct fwdb_header *hdr = regdb;
+	const struct fwdb_country *country;
+
+	if (IS_ERR(regdb))
+		return PTR_ERR(regdb);
+
+	country = &hdr->country[0];
+	while (country->coll_ptr) {
+		if (alpha2_equal(alpha2, country->alpha2))
+			return __regdb_query_wmm(regdb, country, freq, dbptr,
+						 rule);
+
+		country++;
+	}
+
+	return -ENODATA;
+}
+EXPORT_SYMBOL(reg_query_regdb_wmm);
+
 struct wmm_ptrs {
 	struct ieee80211_wmm_rule *rule;
 	u32 ptr;
-- 
cgit v1.2.3


From 6a671a50f8199b3e1fe49fa8afff0fc8335da79c Mon Sep 17 00:00:00 2001
From: Denis Kenzior <denkenz@gmail.com>
Date: Mon, 26 Mar 2018 12:52:41 -0500
Subject: nl80211: Add CMD_CONTROL_PORT_FRAME API

This commit also adds cfg80211_rx_control_port function.  This is used
to generate a CMD_CONTROL_PORT_FRAME event out to userspace.  The
conn_owner_nlportid is used as the unicast destination.  This means that
userspace must specify NL80211_ATTR_SOCKET_OWNER flag if control port
over nl80211 routing is requested in NL80211_CMD_CONNECT,
NL80211_CMD_ASSOCIATE, NL80211_CMD_START_AP or IBSS/mesh join.

Signed-off-by: Denis Kenzior <denkenz@gmail.com>
[johannes: fix return value of cfg80211_rx_control_port()]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 22 +++++++++++++++++
 include/uapi/linux/nl80211.h | 13 ++++++++++
 net/wireless/nl80211.c       | 58 ++++++++++++++++++++++++++++++++++++++++++++
 net/wireless/trace.h         | 21 ++++++++++++++++
 4 files changed, 114 insertions(+)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bfe174896fcf..df145f76adad 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5721,6 +5721,28 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 			     const u8 *buf, size_t len, bool ack, gfp_t gfp);
 
 
+/**
+ * cfg80211_rx_control_port - notification about a received control port frame
+ * @dev: The device the frame matched to
+ * @buf: control port frame
+ * @len: length of the frame data
+ * @addr: The peer from which the frame was received
+ * @proto: frame protocol, typically PAE or Pre-authentication
+ * @unencrypted: Whether the frame was received unencrypted
+ *
+ * This function is used to inform userspace about a received control port
+ * frame.  It should only be used if userspace indicated it wants to receive
+ * control port frames over nl80211.
+ *
+ * The frame is the data portion of the 802.3 or 802.11 data frame with all
+ * network layer headers removed (e.g. the raw EAPoL frame).
+ *
+ * Return: %true if the frame was passed to userspace
+ */
+bool cfg80211_rx_control_port(struct net_device *dev,
+			      const u8 *buf, size_t len,
+			      const u8 *addr, u16 proto, bool unencrypted);
+
 /**
  * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event
  * @dev: network device
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 9ea3d6039eca..6a3cc7a635b5 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -990,6 +990,17 @@
  *	&NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed
  *	&NL80211_CMD_DISCONNECT should be indicated instead.
  *
+ * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request
+ *	and RX notification.  This command is used both as a request to transmit
+ *	a control port frame and as a notification that a control port frame
+ *	has been received. %NL80211_ATTR_FRAME is used to specify the
+ *	frame contents.  The frame is the raw EAPoL data, without ethernet or
+ *	802.11 headers.
+ *	When used as an event indication %NL80211_ATTR_CONTROL_PORT_ETHERTYPE,
+ *	%NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT and %NL80211_ATTR_MAC are added
+ *	indicating the protocol type of the received frame; whether the frame
+ *	was received unencrypted and the MAC address of the peer respectively.
+ *
  * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded.
  *
  * @NL80211_CMD_EXTERNAL_AUTH: This interface is exclusively defined for host
@@ -1228,6 +1239,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_STA_OPMODE_CHANGED,
 
+	NL80211_CMD_CONTROL_PORT_FRAME,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index cfaf2aeb9783..0870447fbd55 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -14553,6 +14553,64 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 }
 EXPORT_SYMBOL(cfg80211_mgmt_tx_status);
 
+static int __nl80211_rx_control_port(struct net_device *dev,
+				     const u8 *buf, size_t len,
+				     const u8 *addr, u16 proto,
+				     bool unencrypted, gfp_t gfp)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct sk_buff *msg;
+	void *hdr;
+	u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid);
+
+	if (!nlportid)
+		return -ENOENT;
+
+	msg = nlmsg_new(100 + len, gfp);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_CONTROL_PORT_FRAME);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return -ENOBUFS;
+	}
+
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
+	    nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev),
+			      NL80211_ATTR_PAD) ||
+	    nla_put(msg, NL80211_ATTR_FRAME, len, buf) ||
+	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) ||
+	    nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) ||
+	    (unencrypted && nla_put_flag(msg,
+					 NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT)))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid);
+
+ nla_put_failure:
+	nlmsg_free(msg);
+	return -ENOBUFS;
+}
+
+bool cfg80211_rx_control_port(struct net_device *dev,
+			      const u8 *buf, size_t len,
+			      const u8 *addr, u16 proto, bool unencrypted)
+{
+	int ret;
+
+	trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted);
+	ret = __nl80211_rx_control_port(dev, buf, len, addr, proto,
+					unencrypted, GFP_ATOMIC);
+	trace_cfg80211_return_bool(ret == 0);
+	return ret == 0;
+}
+EXPORT_SYMBOL(cfg80211_rx_control_port);
+
 static struct sk_buff *cfg80211_prepare_cqm(struct net_device *dev,
 					    const char *mac, gfp_t gfp)
 {
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 5152938b358d..42fd338f879e 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2600,6 +2600,27 @@ TRACE_EVENT(cfg80211_mgmt_tx_status,
 		  WDEV_PR_ARG, __entry->cookie, BOOL_TO_STR(__entry->ack))
 );
 
+TRACE_EVENT(cfg80211_rx_control_port,
+	TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len,
+		 const u8 *addr, u16 proto, bool unencrypted),
+	TP_ARGS(netdev, buf, len, addr, proto, unencrypted),
+	TP_STRUCT__entry(
+		NETDEV_ENTRY
+		MAC_ENTRY(addr)
+		__field(u16, proto)
+		__field(bool, unencrypted)
+	),
+	TP_fast_assign(
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(addr, addr);
+		__entry->proto = proto;
+		__entry->unencrypted = unencrypted;
+	),
+	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s",
+		  NETDEV_PR_ARG, MAC_PR_ARG(addr),
+		  __entry->proto, BOOL_TO_STR(__entry->unencrypted))
+);
+
 TRACE_EVENT(cfg80211_cqm_rssi_notify,
 	TP_PROTO(struct net_device *netdev,
 		 enum nl80211_cqm_rssi_threshold_event rssi_event,
-- 
cgit v1.2.3


From 2576a9ace47eba28a682d249d1d6402f891808c9 Mon Sep 17 00:00:00 2001
From: Denis Kenzior <denkenz@gmail.com>
Date: Mon, 26 Mar 2018 12:52:42 -0500
Subject: nl80211: Implement TX of control port frames

This commit implements the TX side of NL80211_CMD_CONTROL_PORT_FRAME.
Userspace provides the raw EAPoL frame using NL80211_ATTR_FRAME.
Userspace should also provide the destination address and the protocol
type to use when sending the frame.  This is used to implement TX of
Pre-authentication frames.  If CONTROL_PORT_ETHERTYPE_NO_ENCRYPT is
specified, then the driver will be asked not to encrypt the outgoing
frame.

A new EXT_FEATURE flag is introduced so that nl80211 code can check
whether a given wiphy has capability to pass EAPoL frames over nl80211.

Signed-off-by: Denis Kenzior <denkenz@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  9 ++++++
 include/uapi/linux/nl80211.h |  3 ++
 net/wireless/nl80211.c       | 71 +++++++++++++++++++++++++++++++++++++++++++-
 net/wireless/rdev-ops.h      | 15 ++++++++++
 net/wireless/trace.h         | 26 ++++++++++++++++
 5 files changed, 123 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index df145f76adad..de2894a4ad10 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2961,6 +2961,9 @@ struct cfg80211_external_auth_params {
  *
  * @external_auth: indicates result of offloaded authentication processing from
  *     user space
+ *
+ * @tx_control_port: TX a control port frame (EAPoL).  The noencrypt parameter
+ *	tells the driver that the frame should not be encrypted.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -3256,6 +3259,12 @@ struct cfg80211_ops {
 			   const u8 *aa);
 	int     (*external_auth)(struct wiphy *wiphy, struct net_device *dev,
 				 struct cfg80211_external_auth_params *params);
+
+	int	(*tx_control_port)(struct wiphy *wiphy,
+				   struct net_device *dev,
+				   const u8 *buf, size_t len,
+				   const u8 *dest, const __be16 proto,
+				   const bool noencrypt);
 };
 
 /*
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 6a3cc7a635b5..3167d6f7fc68 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -5024,6 +5024,8 @@ enum nl80211_feature_flags {
  *	channel change triggered by radar detection event.
  *	No need to start CAC from user-space, no need to react to
  *	"radar detected" event.
+ * @NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211: Driver supports sending and
+ *	receiving control port frames over nl80211 instead of the netdevice.
  *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
@@ -5055,6 +5057,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_LOW_POWER_SCAN,
 	NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN,
 	NL80211_EXT_FEATURE_DFS_OFFLOAD,
+	NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0870447fbd55..6eb286784924 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -12535,6 +12535,68 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info)
 	return rdev_external_auth(rdev, dev, &params);
 }
 
+static int nl80211_tx_control_port(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	const u8 *buf;
+	size_t len;
+	u8 *dest;
+	u16 proto;
+	bool noencrypt;
+	int err;
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211))
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->tx_control_port)
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[NL80211_ATTR_FRAME] ||
+	    !info->attrs[NL80211_ATTR_MAC] ||
+	    !info->attrs[NL80211_ATTR_CONTROL_PORT_ETHERTYPE]) {
+		GENL_SET_ERR_MSG(info, "Frame, MAC or ethertype missing");
+		return -EINVAL;
+	}
+
+	wdev_lock(wdev);
+
+	switch (wdev->iftype) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_MESH_POINT:
+		break;
+	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		if (wdev->current_bss)
+			break;
+		err = -ENOTCONN;
+		goto out;
+	default:
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	wdev_unlock(wdev);
+
+	buf = nla_data(info->attrs[NL80211_ATTR_FRAME]);
+	len = nla_len(info->attrs[NL80211_ATTR_FRAME]);
+	dest = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	proto = nla_get_u16(info->attrs[NL80211_ATTR_CONTROL_PORT_ETHERTYPE]);
+	noencrypt =
+		nla_get_flag(info->attrs[NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT]);
+
+	return rdev_tx_control_port(rdev, dev, buf, len,
+				    dest, cpu_to_be16(proto), noencrypt);
+
+ out:
+	wdev_unlock(wdev);
+	return err;
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -13438,7 +13500,14 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
-
+	{
+		.cmd = NL80211_CMD_CONTROL_PORT_FRAME,
+		.doit = nl80211_tx_control_port,
+		.policy = nl80211_policy,
+		.flags = GENL_UNS_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 84f23ae015fc..87479a53411b 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -714,6 +714,21 @@ static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_tx_control_port(struct cfg80211_registered_device *rdev,
+				       struct net_device *dev,
+				       const void *buf, size_t len,
+				       const u8 *dest, __be16 proto,
+				       const bool noencrypt)
+{
+	int ret;
+	trace_rdev_tx_control_port(&rdev->wiphy, dev, buf, len,
+				   dest, proto, noencrypt);
+	ret = rdev->ops->tx_control_port(&rdev->wiphy, dev, buf, len,
+					 dest, proto, noencrypt);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
 static inline int
 rdev_mgmt_tx_cancel_wait(struct cfg80211_registered_device *rdev,
 			 struct wireless_dev *wdev, u64 cookie)
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 42fd338f879e..a64291ae52a6 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1882,6 +1882,32 @@ TRACE_EVENT(rdev_mgmt_tx,
 		  BOOL_TO_STR(__entry->dont_wait_for_ack))
 );
 
+TRACE_EVENT(rdev_tx_control_port,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const u8 *buf, size_t len, const u8 *dest, __be16 proto,
+		 bool unencrypted),
+	TP_ARGS(wiphy, netdev, buf, len, dest, proto, unencrypted),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(dest)
+		__field(__be16, proto)
+		__field(bool, unencrypted)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(dest, dest);
+		__entry->proto = proto;
+		__entry->unencrypted = unencrypted;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ","
+		  " proto: 0x%x, unencrypted: %s",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(dest),
+		  be16_to_cpu(__entry->proto),
+		  BOOL_TO_STR(__entry->unencrypted))
+);
+
 TRACE_EVENT(rdev_set_noack_map,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
 		 u16 noack_map),
-- 
cgit v1.2.3


From 64bf3d4bc2b0725b3c5ffadd982a9746bfc738b7 Mon Sep 17 00:00:00 2001
From: Denis Kenzior <denkenz@gmail.com>
Date: Mon, 26 Mar 2018 12:52:43 -0500
Subject: nl80211: Add CONTROL_PORT_OVER_NL80211 attribute

Signed-off-by: Denis Kenzior <denkenz@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  3 +++
 include/uapi/linux/nl80211.h | 14 +++++++++++++-
 net/wireless/nl80211.c       | 26 ++++++++++++++++++++++++++
 3 files changed, 42 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index de2894a4ad10..0bd957b37208 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -647,6 +647,8 @@ struct survey_info {
  *	allowed through even on unauthorized ports
  * @control_port_no_encrypt: TRUE to prevent encryption of control port
  *	protocol frames.
+ * @control_port_over_nl80211: TRUE if userspace expects to exchange control
+ *	port frames over NL80211 instead of the network interface.
  * @wep_keys: static WEP keys, if not NULL points to an array of
  *	CFG80211_MAX_WEP_KEYS WEP keys
  * @wep_tx_key: key index (0..3) of the default TX static WEP key
@@ -662,6 +664,7 @@ struct cfg80211_crypto_settings {
 	bool control_port;
 	__be16 control_port_ethertype;
 	bool control_port_no_encrypt;
+	bool control_port_over_nl80211;
 	struct key_params *wep_keys;
 	int wep_tx_key;
 	const u8 *psk;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 3167d6f7fc68..15daf5e2638d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -542,7 +542,8 @@
  *	IEs in %NL80211_ATTR_IE, %NL80211_ATTR_AUTH_TYPE, %NL80211_ATTR_USE_MFP,
  *	%NL80211_ATTR_MAC, %NL80211_ATTR_WIPHY_FREQ, %NL80211_ATTR_CONTROL_PORT,
  *	%NL80211_ATTR_CONTROL_PORT_ETHERTYPE,
- *	%NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT, %NL80211_ATTR_MAC_HINT, and
+ *	%NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT,
+ *	%NL80211_ATTR_CONTROL_PORT_OVER_NL80211, %NL80211_ATTR_MAC_HINT, and
  *	%NL80211_ATTR_WIPHY_FREQ_HINT.
  *	If included, %NL80211_ATTR_MAC and %NL80211_ATTR_WIPHY_FREQ are
  *	restrictions on BSS selection, i.e., they effectively prevent roaming
@@ -1488,6 +1489,15 @@ enum nl80211_commands {
  * @NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT: When included along with
  *	%NL80211_ATTR_CONTROL_PORT_ETHERTYPE, indicates that the custom
  *	ethertype frames used for key negotiation must not be encrypted.
+ * @NL80211_ATTR_CONTROL_PORT_OVER_NL80211: A flag indicating whether control
+ *	port frames (e.g. of type given in %NL80211_ATTR_CONTROL_PORT_ETHERTYPE)
+ *	will be sent directly to the network interface or sent via the NL80211
+ *	socket.  If this attribute is missing, then legacy behavior of sending
+ *	control port frames directly to the network interface is used.  If the
+ *	flag is included, then control port frames are sent over NL80211 instead
+ *	using %CMD_CONTROL_PORT_FRAME.  If control port routing over NL80211 is
+ *	to be used then userspace must also use the %NL80211_ATTR_SOCKET_OWNER
+ *	flag.
  *
  * @NL80211_ATTR_TESTDATA: Testmode data blob, passed through to the driver.
  *	We recommend using nested, driver-specific attributes within this.
@@ -2647,6 +2657,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_NSS,
 	NL80211_ATTR_ACK_SIGNAL,
 
+	NL80211_ATTR_CONTROL_PORT_OVER_NL80211,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 6eb286784924..d3b14d9d002a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -287,6 +287,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_CONTROL_PORT] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CONTROL_PORT_ETHERTYPE] = { .type = NLA_U16 },
 	[NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG },
+	[NL80211_ATTR_CONTROL_PORT_OVER_NL80211] = { .type = NLA_FLAG },
 	[NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 },
 	[NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 },
@@ -8211,6 +8212,22 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+static int validate_pae_over_nl80211(struct cfg80211_registered_device *rdev,
+				     struct genl_info *info)
+{
+	if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) {
+		GENL_SET_ERR_MSG(info, "SOCKET_OWNER not set");
+		return -EINVAL;
+	}
+
+	if (!rdev->ops->tx_control_port ||
+	    !wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 				   struct genl_info *info,
 				   struct cfg80211_crypto_settings *settings,
@@ -8234,6 +8251,15 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 	} else
 		settings->control_port_ethertype = cpu_to_be16(ETH_P_PAE);
 
+	if (info->attrs[NL80211_ATTR_CONTROL_PORT_OVER_NL80211]) {
+		int r = validate_pae_over_nl80211(rdev, info);
+
+		if (r < 0)
+			return r;
+
+		settings->control_port_over_nl80211 = true;
+	}
+
 	if (info->attrs[NL80211_ATTR_CIPHER_SUITES_PAIRWISE]) {
 		void *data;
 		int len, i;
-- 
cgit v1.2.3


From c3bfe1f6fc98e7185ff5ee9279ba259fe484597c Mon Sep 17 00:00:00 2001
From: Denis Kenzior <denkenz@gmail.com>
Date: Mon, 26 Mar 2018 12:52:48 -0500
Subject: nl80211: Add control_port_over_nl80211 for ibss

Signed-off-by: Denis Kenzior <denkenz@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 3 +++
 net/wireless/nl80211.c | 9 +++++++++
 2 files changed, 12 insertions(+)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 0bd957b37208..ed2773f8558e 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2034,6 +2034,8 @@ struct cfg80211_disassoc_request {
  *	sets/clears %NL80211_STA_FLAG_AUTHORIZED. If true, the driver is
  *	required to assume that the port is unauthorized until authorized by
  *	user space. Otherwise, port is marked authorized by default.
+ * @control_port_over_nl80211: TRUE if userspace expects to exchange control
+ *	port frames over NL80211 instead of the network interface.
  * @userspace_handles_dfs: whether user space controls DFS operation, i.e.
  *	changes the channel when a radar is detected. This is required
  *	to operate on DFS channels.
@@ -2057,6 +2059,7 @@ struct cfg80211_ibss_params {
 	bool channel_fixed;
 	bool privacy;
 	bool control_port;
+	bool control_port_over_nl80211;
 	bool userspace_handles_dfs;
 	int mcast_rate[NUM_NL80211_BANDS];
 	struct ieee80211_ht_cap ht_capa;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d3b14d9d002a..f8e10408f2b3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -8705,6 +8705,15 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 	ibss.control_port =
 		nla_get_flag(info->attrs[NL80211_ATTR_CONTROL_PORT]);
 
+	if (info->attrs[NL80211_ATTR_CONTROL_PORT_OVER_NL80211]) {
+		int r = validate_pae_over_nl80211(rdev, info);
+
+		if (r < 0)
+			return r;
+
+		ibss.control_port_over_nl80211 = true;
+	}
+
 	ibss.userspace_handles_dfs =
 		nla_get_flag(info->attrs[NL80211_ATTR_HANDLE_DFS]);
 
-- 
cgit v1.2.3


From 1224f5831a22977f30c1842874be12c58608cee7 Mon Sep 17 00:00:00 2001
From: Denis Kenzior <denkenz@gmail.com>
Date: Mon, 26 Mar 2018 12:52:49 -0500
Subject: nl80211: Add control_port_over_nl80211 to mesh_setup

Signed-off-by: Denis Kenzior <denkenz@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 3 +++
 net/wireless/nl80211.c | 9 +++++++++
 2 files changed, 12 insertions(+)

(limited to 'include/net')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ed2773f8558e..250dac390806 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1454,6 +1454,8 @@ struct mesh_config {
  * @userspace_handles_dfs: whether user space controls DFS operation, i.e.
  *	changes the channel when a radar is detected. This is required
  *	to operate on DFS channels.
+ * @control_port_over_nl80211: TRUE if userspace expects to exchange control
+ *	port frames over NL80211 instead of the network interface.
  *
  * These parameters are fixed when the mesh is created.
  */
@@ -1476,6 +1478,7 @@ struct mesh_setup {
 	u32 basic_rates;
 	struct cfg80211_bitrate_mask beacon_rate;
 	bool userspace_handles_dfs;
+	bool control_port_over_nl80211;
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f8e10408f2b3..ff28f8feeb09 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10168,6 +10168,15 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
 	setup.userspace_handles_dfs =
 		nla_get_flag(info->attrs[NL80211_ATTR_HANDLE_DFS]);
 
+	if (info->attrs[NL80211_ATTR_CONTROL_PORT_OVER_NL80211]) {
+		int r = validate_pae_over_nl80211(rdev, info);
+
+		if (r < 0)
+			return r;
+
+		setup.control_port_over_nl80211 = true;
+	}
+
 	wdev_lock(dev->ieee80211_ptr);
 	err = __cfg80211_join_mesh(rdev, dev, &setup, &cfg);
 	if (!err && info->attrs[NL80211_ATTR_SOCKET_OWNER])
-- 
cgit v1.2.3


From f0b07bb151b098d291fd1fd71ef7a2df56fb124a Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Thu, 29 Mar 2018 19:20:32 +0300
Subject: net: Introduce net_rwsem to protect net_namespace_list

rtnl_lock() is used everywhere, and contention is very high.
When someone wants to iterate over alive net namespaces,
he/she has no a possibility to do that without exclusive lock.
But the exclusive rtnl_lock() in such places is overkill,
and it just increases the contention. Yes, there is already
for_each_net_rcu() in kernel, but it requires rcu_read_lock(),
and this can't be sleepable. Also, sometimes it may be need
really prevent net_namespace_list growth, so for_each_net_rcu()
is not fit there.

This patch introduces new rw_semaphore, which will be used
instead of rtnl_mutex to protect net_namespace_list. It is
sleepable and allows not-exclusive iterations over net
namespaces list. It allows to stop using rtnl_lock()
in several places (what is made in next patches) and makes
less the time, we keep rtnl_mutex. Here we just add new lock,
while the explanation of we can remove rtnl_lock() there are
in next patches.

Fine grained locks generally are better, then one big lock,
so let's do that with net_namespace_list, while the situation
allows that.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/roce_gid_mgmt.c |  2 ++
 include/linux/rtnetlink.h               |  1 +
 include/net/net_namespace.h             |  1 +
 net/core/dev.c                          |  5 +++++
 net/core/fib_notifier.c                 |  2 ++
 net/core/net_namespace.c                | 18 +++++++++++++-----
 net/core/rtnetlink.c                    |  5 +++++
 net/netfilter/nf_conntrack_core.c       |  2 ++
 net/openvswitch/datapath.c              |  2 ++
 net/wireless/wext-core.c                |  2 ++
 security/selinux/include/xfrm.h         |  2 ++
 11 files changed, 37 insertions(+), 5 deletions(-)

(limited to 'include/net')

diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index 5a52ec77940a..cc2966380c0c 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -403,10 +403,12 @@ static void enum_all_gids_of_dev_cb(struct ib_device *ib_dev,
 	 * our feet
 	 */
 	rtnl_lock();
+	down_read(&net_rwsem);
 	for_each_net(net)
 		for_each_netdev(net, ndev)
 			if (is_eth_port_of_netdev(ib_dev, port, rdma_ndev, ndev))
 				add_netdev_ips(ib_dev, port, rdma_ndev, ndev);
+	up_read(&net_rwsem);
 	rtnl_unlock();
 }
 
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index c7d1e4689325..5225832bd6ff 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -37,6 +37,7 @@ extern int rtnl_lock_killable(void);
 
 extern wait_queue_head_t netdev_unregistering_wq;
 extern struct rw_semaphore pernet_ops_rwsem;
+extern struct rw_semaphore net_rwsem;
 
 #ifdef CONFIG_PROVE_LOCKING
 extern bool lockdep_rtnl_is_held(void);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 1ab4f920f109..47e35cce3b64 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -291,6 +291,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet)
 #endif
 }
 
+/* Protected by net_rwsem */
 #define for_each_net(VAR)				\
 	list_for_each_entry(VAR, &net_namespace_list, list)
 
diff --git a/net/core/dev.c b/net/core/dev.c
index e13807b5c84d..eca5458b2753 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1629,6 +1629,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
 		goto unlock;
 	if (dev_boot_phase)
 		goto unlock;
+	down_read(&net_rwsem);
 	for_each_net(net) {
 		for_each_netdev(net, dev) {
 			err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
@@ -1642,6 +1643,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
 			call_netdevice_notifier(nb, NETDEV_UP, dev);
 		}
 	}
+	up_read(&net_rwsem);
 
 unlock:
 	rtnl_unlock();
@@ -1664,6 +1666,7 @@ rollback:
 	}
 
 outroll:
+	up_read(&net_rwsem);
 	raw_notifier_chain_unregister(&netdev_chain, nb);
 	goto unlock;
 }
@@ -1694,6 +1697,7 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
 	if (err)
 		goto unlock;
 
+	down_read(&net_rwsem);
 	for_each_net(net) {
 		for_each_netdev(net, dev) {
 			if (dev->flags & IFF_UP) {
@@ -1704,6 +1708,7 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
 			call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
 		}
 	}
+	up_read(&net_rwsem);
 unlock:
 	rtnl_unlock();
 	return err;
diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c
index 0c048bdeb016..614b985c92a4 100644
--- a/net/core/fib_notifier.c
+++ b/net/core/fib_notifier.c
@@ -33,6 +33,7 @@ static unsigned int fib_seq_sum(void)
 	struct net *net;
 
 	rtnl_lock();
+	down_read(&net_rwsem);
 	for_each_net(net) {
 		rcu_read_lock();
 		list_for_each_entry_rcu(ops, &net->fib_notifier_ops, list) {
@@ -43,6 +44,7 @@ static unsigned int fib_seq_sum(void)
 		}
 		rcu_read_unlock();
 	}
+	up_read(&net_rwsem);
 	rtnl_unlock();
 
 	return fib_seq;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b5796d17a302..7fdf321d4997 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -33,6 +33,10 @@ static struct list_head *first_device = &pernet_list;
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
 
+/* Protects net_namespace_list. Nests iside rtnl_lock() */
+DECLARE_RWSEM(net_rwsem);
+EXPORT_SYMBOL_GPL(net_rwsem);
+
 struct net init_net = {
 	.count		= REFCOUNT_INIT(1),
 	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
@@ -309,9 +313,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 		if (error < 0)
 			goto out_undo;
 	}
-	rtnl_lock();
+	down_write(&net_rwsem);
 	list_add_tail_rcu(&net->list, &net_namespace_list);
-	rtnl_unlock();
+	up_write(&net_rwsem);
 out:
 	return error;
 
@@ -450,7 +454,7 @@ static void unhash_nsid(struct net *net, struct net *last)
 	 * and this work is the only process, that may delete
 	 * a net from net_namespace_list. So, when the below
 	 * is executing, the list may only grow. Thus, we do not
-	 * use for_each_net_rcu() or rtnl_lock().
+	 * use for_each_net_rcu() or net_rwsem.
 	 */
 	for_each_net(tmp) {
 		int id;
@@ -485,7 +489,7 @@ static void cleanup_net(struct work_struct *work)
 	down_read(&pernet_ops_rwsem);
 
 	/* Don't let anyone else find us. */
-	rtnl_lock();
+	down_write(&net_rwsem);
 	llist_for_each_entry(net, net_kill_list, cleanup_list)
 		list_del_rcu(&net->list);
 	/* Cache last net. After we unlock rtnl, no one new net
@@ -499,7 +503,7 @@ static void cleanup_net(struct work_struct *work)
 	 * useless anyway, as netns_ids are destroyed there.
 	 */
 	last = list_last_entry(&net_namespace_list, struct net, list);
-	rtnl_unlock();
+	up_write(&net_rwsem);
 
 	llist_for_each_entry(net, net_kill_list, cleanup_list) {
 		unhash_nsid(net, last);
@@ -900,6 +904,9 @@ static int __register_pernet_operations(struct list_head *list,
 
 	list_add_tail(&ops->list, list);
 	if (ops->init || (ops->id && ops->size)) {
+		/* We held write locked pernet_ops_rwsem, and parallel
+		 * setup_net() and cleanup_net() are not possible.
+		 */
 		for_each_net(net) {
 			error = ops_init(ops, net);
 			if (error)
@@ -923,6 +930,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops)
 	LIST_HEAD(net_exit_list);
 
 	list_del(&ops->list);
+	/* See comment in __register_pernet_operations() */
 	for_each_net(net)
 		list_add_tail(&net->exit_list, &net_exit_list);
 	ops_exit_list(ops, &net_exit_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2d3949789cef..e86b28482ca7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -418,9 +418,11 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
 	struct net *net;
 
+	down_read(&net_rwsem);
 	for_each_net(net) {
 		__rtnl_kill_links(net, ops);
 	}
+	up_read(&net_rwsem);
 	list_del(&ops->list);
 }
 EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
@@ -438,6 +440,9 @@ static void rtnl_lock_unregistering_all(void)
 	for (;;) {
 		unregistering = false;
 		rtnl_lock();
+		/* We held write locked pernet_ops_rwsem, and parallel
+		 * setup_net() and cleanup_net() are not possible.
+		 */
 		for_each_net(net) {
 			if (net->dev_unreg_count > 0) {
 				unregistering = true;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 705198de671d..370f9b7f051b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1764,12 +1764,14 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data)
 	struct net *net;
 
 	rtnl_lock();
+	down_read(&net_rwsem);
 	for_each_net(net) {
 		if (atomic_read(&net->ct.count) == 0)
 			continue;
 		__nf_ct_unconfirmed_destroy(net);
 		nf_queue_nf_hook_drop(net);
 	}
+	up_read(&net_rwsem);
 	rtnl_unlock();
 
 	/* Need to wait for netns cleanup worker to finish, if its
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index ef38e5aecd28..9746ee30a99b 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2364,8 +2364,10 @@ static void __net_exit ovs_exit_net(struct net *dnet)
 		__dp_destroy(dp);
 
 	rtnl_lock();
+	down_read(&net_rwsem);
 	for_each_net(net)
 		list_vports_from_net(net, dnet, &head);
+	up_read(&net_rwsem);
 	rtnl_unlock();
 
 	/* Detach all vports from given namespace. */
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 9efbfc753347..544d7b62d7ca 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -349,11 +349,13 @@ void wireless_nlevent_flush(void)
 
 	ASSERT_RTNL();
 
+	down_read(&net_rwsem);
 	for_each_net(net) {
 		while ((skb = skb_dequeue(&net->wext_nlevents)))
 			rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
 				    GFP_KERNEL);
 	}
+	up_read(&net_rwsem);
 }
 EXPORT_SYMBOL_GPL(wireless_nlevent_flush);
 
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 1f173a7a4daa..31d66431be1e 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -48,8 +48,10 @@ static inline void selinux_xfrm_notify_policyload(void)
 	struct net *net;
 
 	rtnl_lock();
+	down_read(&net_rwsem);
 	for_each_net(net)
 		rt_genid_bump_all(net);
+	up_read(&net_rwsem);
 	rtnl_unlock();
 }
 #else
-- 
cgit v1.2.3


From 8934ce2fd08171e8605f7fada91ee7619fe17ab8 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Wed, 28 Mar 2018 12:49:15 -0700
Subject: bpf: sockmap redirect ingress support

Add support for the BPF_F_INGRESS flag in sk_msg redirect helper.
To do this add a scatterlist ring for receiving socks to check
before calling into regular recvmsg call path. Additionally, because
the poll wakeup logic only checked the skb recv queue we need to
add a hook in TCP stack (similar to write side) so that we have
a way to wake up polling socks when a scatterlist is redirected
to that sock.

After this all that is needed is for the redirect helper to
push the scatterlist into the psock receive queue.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/filter.h |   1 +
 include/net/sock.h     |   1 +
 kernel/bpf/sockmap.c   | 198 ++++++++++++++++++++++++++++++++++++++++++++++++-
 net/core/filter.c      |   2 +-
 net/ipv4/tcp.c         |  10 ++-
 5 files changed, 207 insertions(+), 5 deletions(-)

(limited to 'include/net')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index c2f167db8bd5..961cc5d53956 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -521,6 +521,7 @@ struct sk_msg_buff {
 	__u32 key;
 	__u32 flags;
 	struct bpf_map *map;
+	struct list_head list;
 };
 
 /* Compute the linear packet data range [data, data_end) which
diff --git a/include/net/sock.h b/include/net/sock.h
index 709311132d4c..b8ff435fa96e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1085,6 +1085,7 @@ struct proto {
 #endif
 
 	bool			(*stream_memory_free)(const struct sock *sk);
+	bool			(*stream_memory_read)(const struct sock *sk);
 	/* Memory pressure */
 	void			(*enter_memory_pressure)(struct sock *sk);
 	void			(*leave_memory_pressure)(struct sock *sk);
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 69c5bccabd22..402e15466e9f 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -41,6 +41,8 @@
 #include <linux/mm.h>
 #include <net/strparser.h>
 #include <net/tcp.h>
+#include <linux/ptr_ring.h>
+#include <net/inet_common.h>
 
 #define SOCK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -82,6 +84,7 @@ struct smap_psock {
 	int sg_size;
 	int eval;
 	struct sk_msg_buff *cork;
+	struct list_head ingress;
 
 	struct strparser strp;
 	struct bpf_prog *bpf_tx_msg;
@@ -103,6 +106,8 @@ struct smap_psock {
 };
 
 static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
+static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			   int nonblock, int flags, int *addr_len);
 static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
 			    int offset, size_t size, int flags);
@@ -112,6 +117,21 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
 	return rcu_dereference_sk_user_data(sk);
 }
 
+static bool bpf_tcp_stream_read(const struct sock *sk)
+{
+	struct smap_psock *psock;
+	bool empty = true;
+
+	rcu_read_lock();
+	psock = smap_psock_sk(sk);
+	if (unlikely(!psock))
+		goto out;
+	empty = list_empty(&psock->ingress);
+out:
+	rcu_read_unlock();
+	return !empty;
+}
+
 static struct proto tcp_bpf_proto;
 static int bpf_tcp_init(struct sock *sk)
 {
@@ -135,6 +155,8 @@ static int bpf_tcp_init(struct sock *sk)
 	if (psock->bpf_tx_msg) {
 		tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
 		tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
+		tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
+		tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
 	}
 
 	sk->sk_prot = &tcp_bpf_proto;
@@ -170,6 +192,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 {
 	void (*close_fun)(struct sock *sk, long timeout);
 	struct smap_psock_map_entry *e, *tmp;
+	struct sk_msg_buff *md, *mtmp;
 	struct smap_psock *psock;
 	struct sock *osk;
 
@@ -188,6 +211,12 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 	close_fun = psock->save_close;
 
 	write_lock_bh(&sk->sk_callback_lock);
+	list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
+		list_del(&md->list);
+		free_start_sg(psock->sock, md);
+		kfree(md);
+	}
+
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
 		osk = cmpxchg(e->entry, sk, NULL);
 		if (osk == sk) {
@@ -468,6 +497,72 @@ verdict:
 	return _rc;
 }
 
+static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
+			   struct smap_psock *psock,
+			   struct sk_msg_buff *md, int flags)
+{
+	bool apply = apply_bytes;
+	size_t size, copied = 0;
+	struct sk_msg_buff *r;
+	int err = 0, i;
+
+	r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_KERNEL);
+	if (unlikely(!r))
+		return -ENOMEM;
+
+	lock_sock(sk);
+	r->sg_start = md->sg_start;
+	i = md->sg_start;
+
+	do {
+		r->sg_data[i] = md->sg_data[i];
+
+		size = (apply && apply_bytes < md->sg_data[i].length) ?
+			apply_bytes : md->sg_data[i].length;
+
+		if (!sk_wmem_schedule(sk, size)) {
+			if (!copied)
+				err = -ENOMEM;
+			break;
+		}
+
+		sk_mem_charge(sk, size);
+		r->sg_data[i].length = size;
+		md->sg_data[i].length -= size;
+		md->sg_data[i].offset += size;
+		copied += size;
+
+		if (md->sg_data[i].length) {
+			get_page(sg_page(&r->sg_data[i]));
+			r->sg_end = (i + 1) == MAX_SKB_FRAGS ? 0 : i + 1;
+		} else {
+			i++;
+			if (i == MAX_SKB_FRAGS)
+				i = 0;
+			r->sg_end = i;
+		}
+
+		if (apply) {
+			apply_bytes -= size;
+			if (!apply_bytes)
+				break;
+		}
+	} while (i != md->sg_end);
+
+	md->sg_start = i;
+
+	if (!err) {
+		list_add_tail(&r->list, &psock->ingress);
+		sk->sk_data_ready(sk);
+	} else {
+		free_start_sg(sk, r);
+		kfree(r);
+	}
+
+	release_sock(sk);
+	return err;
+}
+
 static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 				       struct sk_msg_buff *md,
 				       int flags)
@@ -475,6 +570,7 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 	struct smap_psock *psock;
 	struct scatterlist *sg;
 	int i, err, free = 0;
+	bool ingress = !!(md->flags & BPF_F_INGRESS);
 
 	sg = md->sg_data;
 
@@ -487,9 +583,14 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 		goto out_rcu;
 
 	rcu_read_unlock();
-	lock_sock(sk);
-	err = bpf_tcp_push(sk, send, md, flags, false);
-	release_sock(sk);
+
+	if (ingress) {
+		err = bpf_tcp_ingress(sk, send, psock, md, flags);
+	} else {
+		lock_sock(sk);
+		err = bpf_tcp_push(sk, send, md, flags, false);
+		release_sock(sk);
+	}
 	smap_release_sock(psock, sk);
 	if (unlikely(err))
 		goto out;
@@ -623,6 +724,89 @@ out_err:
 	return err;
 }
 
+static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			   int nonblock, int flags, int *addr_len)
+{
+	struct iov_iter *iter = &msg->msg_iter;
+	struct smap_psock *psock;
+	int copied = 0;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
+	rcu_read_lock();
+	psock = smap_psock_sk(sk);
+	if (unlikely(!psock))
+		goto out;
+
+	if (unlikely(!refcount_inc_not_zero(&psock->refcnt)))
+		goto out;
+	rcu_read_unlock();
+
+	if (!skb_queue_empty(&sk->sk_receive_queue))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+
+	lock_sock(sk);
+	while (copied != len) {
+		struct scatterlist *sg;
+		struct sk_msg_buff *md;
+		int i;
+
+		md = list_first_entry_or_null(&psock->ingress,
+					      struct sk_msg_buff, list);
+		if (unlikely(!md))
+			break;
+		i = md->sg_start;
+		do {
+			struct page *page;
+			int n, copy;
+
+			sg = &md->sg_data[i];
+			copy = sg->length;
+			page = sg_page(sg);
+
+			if (copied + copy > len)
+				copy = len - copied;
+
+			n = copy_page_to_iter(page, sg->offset, copy, iter);
+			if (n != copy) {
+				md->sg_start = i;
+				release_sock(sk);
+				smap_release_sock(psock, sk);
+				return -EFAULT;
+			}
+
+			copied += copy;
+			sg->offset += copy;
+			sg->length -= copy;
+			sk_mem_uncharge(sk, copy);
+
+			if (!sg->length) {
+				i++;
+				if (i == MAX_SKB_FRAGS)
+					i = 0;
+				put_page(page);
+			}
+			if (copied == len)
+				break;
+		} while (i != md->sg_end);
+		md->sg_start = i;
+
+		if (!sg->length && md->sg_start == md->sg_end) {
+			list_del(&md->list);
+			kfree(md);
+		}
+	}
+
+	release_sock(sk);
+	smap_release_sock(psock, sk);
+	return copied;
+out:
+	rcu_read_unlock();
+	return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+}
+
+
 static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS;
@@ -1107,6 +1291,7 @@ static void sock_map_remove_complete(struct bpf_stab *stab)
 static void smap_gc_work(struct work_struct *w)
 {
 	struct smap_psock_map_entry *e, *tmp;
+	struct sk_msg_buff *md, *mtmp;
 	struct smap_psock *psock;
 
 	psock = container_of(w, struct smap_psock, gc_work);
@@ -1131,6 +1316,12 @@ static void smap_gc_work(struct work_struct *w)
 		kfree(psock->cork);
 	}
 
+	list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
+		list_del(&md->list);
+		free_start_sg(psock->sock, md);
+		kfree(md);
+	}
+
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
 		list_del(&e->list);
 		kfree(e);
@@ -1160,6 +1351,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock,
 	INIT_WORK(&psock->tx_work, smap_tx_work);
 	INIT_WORK(&psock->gc_work, smap_gc_work);
 	INIT_LIST_HEAD(&psock->maps);
+	INIT_LIST_HEAD(&psock->ingress);
 	refcount_set(&psock->refcnt, 1);
 
 	rcu_assign_sk_user_data(sock, psock);
diff --git a/net/core/filter.c b/net/core/filter.c
index afd825534ac4..a5a995e5b380 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1894,7 +1894,7 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg,
 	   struct bpf_map *, map, u32, key, u64, flags)
 {
 	/* If user passes invalid input drop the packet. */
-	if (unlikely(flags))
+	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
 
 	msg->key = key;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0c31be306572..bccc4c270087 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -485,6 +485,14 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 	}
 }
 
+static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
+					  int target, struct sock *sk)
+{
+	return (tp->rcv_nxt - tp->copied_seq >= target) ||
+		(sk->sk_prot->stream_memory_read ?
+		sk->sk_prot->stream_memory_read(sk) : false);
+}
+
 /*
  *	Wait for a TCP event.
  *
@@ -554,7 +562,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		    tp->urg_data)
 			target++;
 
-		if (tp->rcv_nxt - tp->copied_seq >= target)
+		if (tcp_stream_is_readable(tp, target, sk))
 			mask |= EPOLLIN | EPOLLRDNORM;
 
 		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
-- 
cgit v1.2.3


From 32537e91847a5686d57d3811c075a46b2d9b6434 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 27 Mar 2018 11:53:05 +0200
Subject: netfilter: nf_tables: rename struct nf_chain_type

Use nft_ prefix. By when I added chain types, I forgot to use the
nftables prefix. Rename enum nft_chain_type to enum nft_chain_types too,
otherwise there is an overlap.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h         | 16 ++++++++--------
 net/bridge/netfilter/nf_tables_bridge.c   |  2 +-
 net/ipv4/netfilter/nf_tables_arp.c        |  2 +-
 net/ipv4/netfilter/nf_tables_ipv4.c       |  2 +-
 net/ipv4/netfilter/nft_chain_nat_ipv4.c   |  2 +-
 net/ipv4/netfilter/nft_chain_route_ipv4.c |  2 +-
 net/ipv6/netfilter/nf_tables_ipv6.c       |  2 +-
 net/ipv6/netfilter/nft_chain_nat_ipv6.c   |  2 +-
 net/ipv6/netfilter/nft_chain_route_ipv6.c |  2 +-
 net/netfilter/nf_tables_api.c             | 18 +++++++++---------
 net/netfilter/nf_tables_inet.c            |  2 +-
 net/netfilter/nf_tables_netdev.c          |  2 +-
 12 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 663b015dace5..4a304997c304 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -868,7 +868,7 @@ struct nft_chain {
 	char				*name;
 };
 
-enum nft_chain_type {
+enum nft_chain_types {
 	NFT_CHAIN_T_DEFAULT = 0,
 	NFT_CHAIN_T_ROUTE,
 	NFT_CHAIN_T_NAT,
@@ -876,7 +876,7 @@ enum nft_chain_type {
 };
 
 /**
- * 	struct nf_chain_type - nf_tables chain type info
+ * 	struct nft_chain_type - nf_tables chain type info
  *
  * 	@name: name of the type
  * 	@type: numeric identifier
@@ -885,9 +885,9 @@ enum nft_chain_type {
  * 	@hook_mask: mask of valid hooks
  * 	@hooks: array of hook functions
  */
-struct nf_chain_type {
+struct nft_chain_type {
 	const char			*name;
-	enum nft_chain_type		type;
+	enum nft_chain_types		type;
 	int				family;
 	struct module			*owner;
 	unsigned int			hook_mask;
@@ -895,7 +895,7 @@ struct nf_chain_type {
 };
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
-				  enum nft_chain_type type);
+				  enum nft_chain_types type);
 int nft_chain_validate_hooks(const struct nft_chain *chain,
                              unsigned int hook_flags);
 
@@ -917,7 +917,7 @@ struct nft_stats {
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops;
-	const struct nf_chain_type	*type;
+	const struct nft_chain_type	*type;
 	u8				policy;
 	u8				flags;
 	struct nft_stats __percpu	*stats;
@@ -970,8 +970,8 @@ struct nft_table {
 	char				*name;
 };
 
-int nft_register_chain_type(const struct nf_chain_type *);
-void nft_unregister_chain_type(const struct nf_chain_type *);
+int nft_register_chain_type(const struct nft_chain_type *);
+void nft_unregister_chain_type(const struct nft_chain_type *);
 
 int nft_register_expr(struct nft_expr_type *);
 void nft_unregister_expr(struct nft_expr_type *);
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
index 5160cf614176..73a1ec556a0a 100644
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -42,7 +42,7 @@ nft_do_chain_bridge(void *priv,
 	return nft_do_chain(&pkt, priv);
 }
 
-static const struct nf_chain_type filter_bridge = {
+static const struct nft_chain_type filter_bridge = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_BRIDGE,
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
index 036c074736b0..5b0be2a10b69 100644
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -27,7 +27,7 @@ nft_do_chain_arp(void *priv,
 	return nft_do_chain(&pkt, priv);
 }
 
-static const struct nf_chain_type filter_arp = {
+static const struct nft_chain_type filter_arp = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_ARP,
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index 96f955496d5f..13bae5cfa257 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -30,7 +30,7 @@ static unsigned int nft_do_chain_ipv4(void *priv,
 	return nft_do_chain(&pkt, priv);
 }
 
-static const struct nf_chain_type filter_ipv4 = {
+static const struct nft_chain_type filter_ipv4 = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_IPV4,
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index f2a490981594..167f377eb1cb 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -67,7 +67,7 @@ static unsigned int nft_nat_ipv4_local_fn(void *priv,
 	return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain);
 }
 
-static const struct nf_chain_type nft_chain_nat_ipv4 = {
+static const struct nft_chain_type nft_chain_nat_ipv4 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
 	.family		= NFPROTO_IPV4,
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index d965c225b9f6..48cf1f892314 100644
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -58,7 +58,7 @@ static unsigned int nf_route_table_hook(void *priv,
 	return ret;
 }
 
-static const struct nf_chain_type nft_chain_route_ipv4 = {
+static const struct nft_chain_type nft_chain_route_ipv4 = {
 	.name		= "route",
 	.type		= NFT_CHAIN_T_ROUTE,
 	.family		= NFPROTO_IPV4,
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index 17e03589331c..d99f9ac6f1b6 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -28,7 +28,7 @@ static unsigned int nft_do_chain_ipv6(void *priv,
 	return nft_do_chain(&pkt, priv);
 }
 
-static const struct nf_chain_type filter_ipv6 = {
+static const struct nft_chain_type filter_ipv6 = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_IPV6,
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index 73fe2bd13fcf..c498aaa8056b 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -65,7 +65,7 @@ static unsigned int nft_nat_ipv6_local_fn(void *priv,
 	return nf_nat_ipv6_local_fn(priv, skb, state, nft_nat_do_chain);
 }
 
-static const struct nf_chain_type nft_chain_nat_ipv6 = {
+static const struct nft_chain_type nft_chain_nat_ipv6 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
 	.family		= NFPROTO_IPV6,
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index 11d3c3b9aa18..d5c7fdc34256 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -60,7 +60,7 @@ static unsigned int nf_route_table_hook(void *priv,
 	return ret;
 }
 
-static const struct nf_chain_type nft_chain_route_ipv6 = {
+static const struct nft_chain_type nft_chain_route_ipv6 = {
 	.name		= "route",
 	.type		= NFT_CHAIN_T_ROUTE,
 	.family		= NFPROTO_IPV6,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 92f5606b0dea..bf564f491085 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -384,9 +384,9 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table)
 	return ++table->hgenerator;
 }
 
-static const struct nf_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX];
+static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX];
 
-static const struct nf_chain_type *
+static const struct nft_chain_type *
 __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
 {
 	int i;
@@ -399,10 +399,10 @@ __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
 	return NULL;
 }
 
-static const struct nf_chain_type *
+static const struct nft_chain_type *
 nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family, bool autoload)
 {
-	const struct nf_chain_type *type;
+	const struct nft_chain_type *type;
 
 	type = __nf_tables_chain_type_lookup(nla, family);
 	if (type != NULL)
@@ -859,7 +859,7 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
 	kfree(ctx->table);
 }
 
-int nft_register_chain_type(const struct nf_chain_type *ctype)
+int nft_register_chain_type(const struct nft_chain_type *ctype)
 {
 	int err = 0;
 
@@ -878,7 +878,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(nft_register_chain_type);
 
-void nft_unregister_chain_type(const struct nf_chain_type *ctype)
+void nft_unregister_chain_type(const struct nft_chain_type *ctype)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
 	chain_type[ctype->family][ctype->type] = NULL;
@@ -1239,7 +1239,7 @@ static void nf_tables_chain_destroy(struct nft_chain *chain)
 struct nft_chain_hook {
 	u32				num;
 	s32				priority;
-	const struct nf_chain_type	*type;
+	const struct nft_chain_type	*type;
 	struct net_device		*dev;
 };
 
@@ -1249,7 +1249,7 @@ static int nft_chain_parse_hook(struct net *net,
 				bool create)
 {
 	struct nlattr *ha[NFTA_HOOK_MAX + 1];
-	const struct nf_chain_type *type;
+	const struct nft_chain_type *type;
 	struct net_device *dev;
 	int err;
 
@@ -6000,7 +6000,7 @@ static const struct nfnetlink_subsystem nf_tables_subsys = {
 };
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
-				  enum nft_chain_type type)
+				  enum nft_chain_types type)
 {
 	const struct nft_base_chain *basechain;
 
diff --git a/net/netfilter/nf_tables_inet.c b/net/netfilter/nf_tables_inet.c
index e30c7da09d0d..0aefe66ce558 100644
--- a/net/netfilter/nf_tables_inet.c
+++ b/net/netfilter/nf_tables_inet.c
@@ -38,7 +38,7 @@ static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb,
 	return nft_do_chain(&pkt, priv);
 }
 
-static const struct nf_chain_type filter_inet = {
+static const struct nft_chain_type filter_inet = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_INET,
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
index 4041fafca934..88ea959211ac 100644
--- a/net/netfilter/nf_tables_netdev.c
+++ b/net/netfilter/nf_tables_netdev.c
@@ -38,7 +38,7 @@ nft_do_chain_netdev(void *priv, struct sk_buff *skb,
 	return nft_do_chain(&pkt, priv);
 }
 
-static const struct nf_chain_type nft_filter_chain_netdev = {
+static const struct nft_chain_type nft_filter_chain_netdev = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_NETDEV,
-- 
cgit v1.2.3


From cc07eeb0e5ee18895241460bdccf91a4952731f9 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 27 Mar 2018 11:53:06 +0200
Subject: netfilter: nf_tables: nft_register_chain_type() returns void

Use WARN_ON() instead since it should not happen that neither family
goes over NFPROTO_NUMPROTO nor there is already a chain of this type
already registered.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h         |  2 +-
 net/bridge/netfilter/nf_tables_bridge.c   |  4 +++-
 net/ipv4/netfilter/nf_tables_arp.c        |  4 +++-
 net/ipv4/netfilter/nf_tables_ipv4.c       |  4 +++-
 net/ipv4/netfilter/nft_chain_nat_ipv4.c   |  6 +-----
 net/ipv4/netfilter/nft_chain_route_ipv4.c |  4 +++-
 net/ipv6/netfilter/nf_tables_ipv6.c       |  4 +++-
 net/ipv6/netfilter/nft_chain_nat_ipv6.c   |  6 +-----
 net/ipv6/netfilter/nft_chain_route_ipv6.c |  4 +++-
 net/netfilter/nf_tables_api.c             | 14 +++++---------
 net/netfilter/nf_tables_inet.c            |  4 +++-
 net/netfilter/nf_tables_netdev.c          |  4 +---
 12 files changed, 30 insertions(+), 30 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4a304997c304..1f7148fe0504 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -970,7 +970,7 @@ struct nft_table {
 	char				*name;
 };
 
-int nft_register_chain_type(const struct nft_chain_type *);
+void nft_register_chain_type(const struct nft_chain_type *);
 void nft_unregister_chain_type(const struct nft_chain_type *);
 
 int nft_register_expr(struct nft_expr_type *);
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
index 73a1ec556a0a..ffb8580dfdac 100644
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -63,7 +63,9 @@ static const struct nft_chain_type filter_bridge = {
 
 static int __init nf_tables_bridge_init(void)
 {
-	return nft_register_chain_type(&filter_bridge);
+	nft_register_chain_type(&filter_bridge);
+
+	return 0;
 }
 
 static void __exit nf_tables_bridge_exit(void)
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
index 5b0be2a10b69..c2ee64208743 100644
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -42,7 +42,9 @@ static const struct nft_chain_type filter_arp = {
 
 static int __init nf_tables_arp_init(void)
 {
-	return nft_register_chain_type(&filter_arp);
+	nft_register_chain_type(&filter_arp);
+
+	return 0;
 }
 
 static void __exit nf_tables_arp_exit(void)
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index 13bae5cfa257..c09667de0d68 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -51,7 +51,9 @@ static const struct nft_chain_type filter_ipv4 = {
 
 static int __init nf_tables_ipv4_init(void)
 {
-	return nft_register_chain_type(&filter_ipv4);
+	nft_register_chain_type(&filter_ipv4);
+
+	return 0;
 }
 
 static void __exit nf_tables_ipv4_exit(void)
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index 167f377eb1cb..9864f5b3279c 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -86,11 +86,7 @@ static const struct nft_chain_type nft_chain_nat_ipv4 = {
 
 static int __init nft_chain_nat_init(void)
 {
-	int err;
-
-	err = nft_register_chain_type(&nft_chain_nat_ipv4);
-	if (err < 0)
-		return err;
+	nft_register_chain_type(&nft_chain_nat_ipv4);
 
 	return 0;
 }
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index 48cf1f892314..7d82934c46f4 100644
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -71,7 +71,9 @@ static const struct nft_chain_type nft_chain_route_ipv4 = {
 
 static int __init nft_chain_route_init(void)
 {
-	return nft_register_chain_type(&nft_chain_route_ipv4);
+	nft_register_chain_type(&nft_chain_route_ipv4);
+
+	return 0;
 }
 
 static void __exit nft_chain_route_exit(void)
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index d99f9ac6f1b6..496f69453457 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -49,7 +49,9 @@ static const struct nft_chain_type filter_ipv6 = {
 
 static int __init nf_tables_ipv6_init(void)
 {
-	return nft_register_chain_type(&filter_ipv6);
+	nft_register_chain_type(&filter_ipv6);
+
+	return 0;
 }
 
 static void __exit nf_tables_ipv6_exit(void)
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index c498aaa8056b..c95d9a97d425 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -84,11 +84,7 @@ static const struct nft_chain_type nft_chain_nat_ipv6 = {
 
 static int __init nft_chain_nat_ipv6_init(void)
 {
-	int err;
-
-	err = nft_register_chain_type(&nft_chain_nat_ipv6);
-	if (err < 0)
-		return err;
+	nft_register_chain_type(&nft_chain_nat_ipv6);
 
 	return 0;
 }
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index d5c7fdc34256..da3f1f8cb325 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -73,7 +73,9 @@ static const struct nft_chain_type nft_chain_route_ipv6 = {
 
 static int __init nft_chain_route_init(void)
 {
-	return nft_register_chain_type(&nft_chain_route_ipv6);
+	nft_register_chain_type(&nft_chain_route_ipv6);
+
+	return 0;
 }
 
 static void __exit nft_chain_route_exit(void)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index bf564f491085..9e4b1614ee39 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -859,22 +859,18 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
 	kfree(ctx->table);
 }
 
-int nft_register_chain_type(const struct nft_chain_type *ctype)
+void nft_register_chain_type(const struct nft_chain_type *ctype)
 {
-	int err = 0;
-
 	if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO))
-		return -EINVAL;
+		return;
 
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	if (chain_type[ctype->family][ctype->type] != NULL) {
-		err = -EBUSY;
-		goto out;
+	if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) {
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		return;
 	}
 	chain_type[ctype->family][ctype->type] = ctype;
-out:
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-	return err;
 }
 EXPORT_SYMBOL_GPL(nft_register_chain_type);
 
diff --git a/net/netfilter/nf_tables_inet.c b/net/netfilter/nf_tables_inet.c
index 0aefe66ce558..202c4219969b 100644
--- a/net/netfilter/nf_tables_inet.c
+++ b/net/netfilter/nf_tables_inet.c
@@ -59,7 +59,9 @@ static const struct nft_chain_type filter_inet = {
 
 static int __init nf_tables_inet_init(void)
 {
-	return nft_register_chain_type(&filter_inet);
+	nft_register_chain_type(&filter_inet);
+
+	return 0;
 }
 
 static void __exit nf_tables_inet_exit(void)
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
index 88ea959211ac..4c3835bca63e 100644
--- a/net/netfilter/nf_tables_netdev.c
+++ b/net/netfilter/nf_tables_netdev.c
@@ -112,9 +112,7 @@ static int __init nf_tables_netdev_init(void)
 {
 	int ret;
 
-	ret = nft_register_chain_type(&nft_filter_chain_netdev);
-	if (ret)
-		return ret;
+	nft_register_chain_type(&nft_filter_chain_netdev);
 
 	ret = register_netdevice_notifier(&nf_tables_netdev_notifier);
 	if (ret)
-- 
cgit v1.2.3


From 02c7b25e5f54321b9063e18d4f52cce07f8e081d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 27 Mar 2018 11:53:07 +0200
Subject: netfilter: nf_tables: build-in filter chain type

One module per supported filter chain family type takes too much memory
for very little code - too much modularization - place all chain filter
definitions in one single file.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h       |   3 +
 net/bridge/netfilter/Kconfig            |   2 +-
 net/bridge/netfilter/Makefile           |   1 -
 net/bridge/netfilter/nf_tables_bridge.c |  81 -------
 net/ipv4/netfilter/Kconfig              |   4 +-
 net/ipv4/netfilter/Makefile             |   2 -
 net/ipv4/netfilter/nf_tables_arp.c      |  60 -----
 net/ipv4/netfilter/nf_tables_ipv4.c     |  69 ------
 net/ipv6/netfilter/Kconfig              |   2 +-
 net/ipv6/netfilter/Makefile             |   1 -
 net/ipv6/netfilter/nf_tables_ipv6.c     |  67 ------
 net/netfilter/Kconfig                   |   4 +-
 net/netfilter/Makefile                  |   9 +-
 net/netfilter/nf_tables_api.c           |   3 +
 net/netfilter/nf_tables_inet.c          |  77 ------
 net/netfilter/nf_tables_netdev.c        | 140 -----------
 net/netfilter/nft_chain_filter.c        | 398 ++++++++++++++++++++++++++++++++
 17 files changed, 414 insertions(+), 509 deletions(-)
 delete mode 100644 net/bridge/netfilter/nf_tables_bridge.c
 delete mode 100644 net/ipv4/netfilter/nf_tables_arp.c
 delete mode 100644 net/ipv4/netfilter/nf_tables_ipv4.c
 delete mode 100644 net/ipv6/netfilter/nf_tables_ipv6.c
 delete mode 100644 net/netfilter/nf_tables_inet.c
 delete mode 100644 net/netfilter/nf_tables_netdev.c
 create mode 100644 net/netfilter/nft_chain_filter.c

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1f7148fe0504..77c3c04c27ac 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1345,4 +1345,7 @@ struct nft_trans_flowtable {
 #define nft_trans_flowtable(trans)	\
 	(((struct nft_trans_flowtable *)trans->data)->flowtable)
 
+int __init nft_chain_filter_init(void);
+void __exit nft_chain_filter_fini(void);
+
 #endif /* _NET_NF_TABLES_H */
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 225d1668dfdd..f212447794bd 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -5,7 +5,7 @@
 menuconfig NF_TABLES_BRIDGE
 	depends on BRIDGE && NETFILTER && NF_TABLES
 	select NETFILTER_FAMILY_BRIDGE
-	tristate "Ethernet Bridge nf_tables support"
+	bool "Ethernet Bridge nf_tables support"
 
 if NF_TABLES_BRIDGE
 
diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile
index 2f28e16de6c7..4bc758dd4a8c 100644
--- a/net/bridge/netfilter/Makefile
+++ b/net/bridge/netfilter/Makefile
@@ -3,7 +3,6 @@
 # Makefile for the netfilter modules for Link Layer filtering on a bridge.
 #
 
-obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o
 obj-$(CONFIG_NFT_BRIDGE_META)  += nft_meta_bridge.o
 obj-$(CONFIG_NFT_BRIDGE_REJECT)  += nft_reject_bridge.o
 
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
deleted file mode 100644
index ffb8580dfdac..000000000000
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2013 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/netfilter_bridge.h>
-#include <net/netfilter/nf_tables.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-
-static unsigned int
-nft_do_chain_bridge(void *priv,
-		    struct sk_buff *skb,
-		    const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-
-	switch (eth_hdr(skb)->h_proto) {
-	case htons(ETH_P_IP):
-		nft_set_pktinfo_ipv4_validate(&pkt, skb);
-		break;
-	case htons(ETH_P_IPV6):
-		nft_set_pktinfo_ipv6_validate(&pkt, skb);
-		break;
-	default:
-		nft_set_pktinfo_unspec(&pkt, skb);
-		break;
-	}
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static const struct nft_chain_type filter_bridge = {
-	.name		= "filter",
-	.type		= NFT_CHAIN_T_DEFAULT,
-	.family		= NFPROTO_BRIDGE,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_BR_PRE_ROUTING) |
-			  (1 << NF_BR_LOCAL_IN) |
-			  (1 << NF_BR_FORWARD) |
-			  (1 << NF_BR_LOCAL_OUT) |
-			  (1 << NF_BR_POST_ROUTING),
-	.hooks		= {
-		[NF_BR_PRE_ROUTING]	= nft_do_chain_bridge,
-		[NF_BR_LOCAL_IN]	= nft_do_chain_bridge,
-		[NF_BR_FORWARD]		= nft_do_chain_bridge,
-		[NF_BR_LOCAL_OUT]	= nft_do_chain_bridge,
-		[NF_BR_POST_ROUTING]	= nft_do_chain_bridge,
-	},
-};
-
-static int __init nf_tables_bridge_init(void)
-{
-	nft_register_chain_type(&filter_bridge);
-
-	return 0;
-}
-
-static void __exit nf_tables_bridge_exit(void)
-{
-	nft_unregister_chain_type(&filter_bridge);
-}
-
-module_init(nf_tables_bridge_init);
-module_exit(nf_tables_bridge_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_BRIDGE, "filter");
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index dfe6fa4ea554..280048e1e395 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -34,7 +34,7 @@ config NF_SOCKET_IPV4
 if NF_TABLES
 
 config NF_TABLES_IPV4
-	tristate "IPv4 nf_tables support"
+	bool "IPv4 nf_tables support"
 	help
 	  This option enables the IPv4 support for nf_tables.
 
@@ -71,7 +71,7 @@ config NFT_FIB_IPV4
 endif # NF_TABLES_IPV4
 
 config NF_TABLES_ARP
-	tristate "ARP nf_tables support"
+	bool "ARP nf_tables support"
 	select NETFILTER_FAMILY_ARP
 	help
 	  This option enables the ARP support for nf_tables.
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 2dad20eefd26..62ede5e3a3de 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -39,7 +39,6 @@ obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
 
-obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
@@ -47,7 +46,6 @@ obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o
 obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
 obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
 obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
-obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # flow table support
 obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
deleted file mode 100644
index c2ee64208743..000000000000
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * Copyright (c) 2008-2010 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2013 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/netfilter_arp.h>
-#include <net/netfilter/nf_tables.h>
-
-static unsigned int
-nft_do_chain_arp(void *priv,
-		  struct sk_buff *skb,
-		  const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_unspec(&pkt, skb);
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static const struct nft_chain_type filter_arp = {
-	.name		= "filter",
-	.type		= NFT_CHAIN_T_DEFAULT,
-	.family		= NFPROTO_ARP,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_ARP_IN) |
-			  (1 << NF_ARP_OUT),
-	.hooks		= {
-		[NF_ARP_IN]		= nft_do_chain_arp,
-		[NF_ARP_OUT]		= nft_do_chain_arp,
-	},
-};
-
-static int __init nf_tables_arp_init(void)
-{
-	nft_register_chain_type(&filter_arp);
-
-	return 0;
-}
-
-static void __exit nf_tables_arp_exit(void)
-{
-	nft_unregister_chain_type(&filter_arp);
-}
-
-module_init(nf_tables_arp_init);
-module_exit(nf_tables_arp_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(3, "filter"); /* NFPROTO_ARP */
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
deleted file mode 100644
index c09667de0d68..000000000000
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012-2013 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/ip.h>
-#include <linux/netfilter_ipv4.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/net_namespace.h>
-#include <net/ip.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-
-static unsigned int nft_do_chain_ipv4(void *priv,
-				      struct sk_buff *skb,
-				      const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv4(&pkt, skb);
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static const struct nft_chain_type filter_ipv4 = {
-	.name		= "filter",
-	.type		= NFT_CHAIN_T_DEFAULT,
-	.family		= NFPROTO_IPV4,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
-			  (1 << NF_INET_LOCAL_OUT) |
-			  (1 << NF_INET_FORWARD) |
-			  (1 << NF_INET_PRE_ROUTING) |
-			  (1 << NF_INET_POST_ROUTING),
-	.hooks		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv4,
-		[NF_INET_LOCAL_OUT]	= nft_do_chain_ipv4,
-		[NF_INET_FORWARD]	= nft_do_chain_ipv4,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv4,
-		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv4,
-	},
-};
-
-static int __init nf_tables_ipv4_init(void)
-{
-	nft_register_chain_type(&filter_ipv4);
-
-	return 0;
-}
-
-static void __exit nf_tables_ipv4_exit(void)
-{
-	nft_unregister_chain_type(&filter_ipv4);
-}
-
-module_init(nf_tables_ipv4_init);
-module_exit(nf_tables_ipv4_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET, "filter");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index d395d1590699..ccbfa83e4bb0 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -34,7 +34,7 @@ config NF_SOCKET_IPV6
 if NF_TABLES
 
 config NF_TABLES_IPV6
-	tristate "IPv6 nf_tables support"
+	bool "IPv6 nf_tables support"
 	help
 	  This option enables the IPv6 support for nf_tables.
 
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index d984057b8395..44273d6f03a5 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -36,7 +36,6 @@ obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o
 obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o
 
 # nf_tables
-obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
deleted file mode 100644
index 496f69453457..000000000000
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012-2013 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/ipv6.h>
-#include <linux/netfilter_ipv6.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-
-static unsigned int nft_do_chain_ipv6(void *priv,
-				      struct sk_buff *skb,
-				      const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv6(&pkt, skb);
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static const struct nft_chain_type filter_ipv6 = {
-	.name		= "filter",
-	.type		= NFT_CHAIN_T_DEFAULT,
-	.family		= NFPROTO_IPV6,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
-			  (1 << NF_INET_LOCAL_OUT) |
-			  (1 << NF_INET_FORWARD) |
-			  (1 << NF_INET_PRE_ROUTING) |
-			  (1 << NF_INET_POST_ROUTING),
-	.hooks		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv6,
-		[NF_INET_LOCAL_OUT]	= nft_do_chain_ipv6,
-		[NF_INET_FORWARD]	= nft_do_chain_ipv6,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv6,
-		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv6,
-	},
-};
-
-static int __init nf_tables_ipv6_init(void)
-{
-	nft_register_chain_type(&filter_ipv6);
-
-	return 0;
-}
-
-static void __exit nf_tables_ipv6_exit(void)
-{
-	nft_unregister_chain_type(&filter_ipv6);
-}
-
-module_init(nf_tables_ipv6_init);
-module_exit(nf_tables_ipv6_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET6, "filter");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index d3220b43c832..704b3832dbad 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -465,12 +465,12 @@ config NF_TABLES_INET
 	depends on IPV6
 	select NF_TABLES_IPV4
 	select NF_TABLES_IPV6
-	tristate "Netfilter nf_tables mixed IPv4/IPv6 tables support"
+	bool "Netfilter nf_tables mixed IPv4/IPv6 tables support"
 	help
 	  This option enables support for a mixed IPv4/IPv6 "inet" table.
 
 config NF_TABLES_NETDEV
-	tristate "Netfilter nf_tables netdev tables support"
+	bool "Netfilter nf_tables netdev tables support"
 	help
 	  This option enables support for the "netdev" table.
 
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 5d9b8b959e58..fd32bd2c9521 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -73,13 +73,12 @@ obj-$(CONFIG_NETFILTER_CONNCOUNT) += nf_conncount.o
 obj-$(CONFIG_NF_DUP_NETDEV)	+= nf_dup_netdev.o
 
 # nf_tables
-nf_tables-objs := nf_tables_core.o nf_tables_api.o nf_tables_trace.o \
-		  nft_immediate.o nft_cmp.o nft_range.o nft_bitwise.o \
-		  nft_byteorder.o nft_payload.o nft_lookup.o nft_dynset.o
+nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
+		  nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \
+		  nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
+		  nft_dynset.o
 
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
-obj-$(CONFIG_NF_TABLES_INET)	+= nf_tables_inet.o
-obj-$(CONFIG_NF_TABLES_NETDEV)	+= nf_tables_netdev.o
 obj-$(CONFIG_NFT_COMPAT)	+= nft_compat.o
 obj-$(CONFIG_NFT_EXTHDR)	+= nft_exthdr.o
 obj-$(CONFIG_NFT_META)		+= nft_meta.o
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9e4b1614ee39..97ec1c388bfe 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6584,6 +6584,8 @@ static int __init nf_tables_module_init(void)
 {
 	int err;
 
+	nft_chain_filter_init();
+
 	info = kmalloc(sizeof(struct nft_expr_info) * NFT_RULE_MAXEXPRS,
 		       GFP_KERNEL);
 	if (info == NULL) {
@@ -6618,6 +6620,7 @@ static void __exit nf_tables_module_exit(void)
 	rcu_barrier();
 	nf_tables_core_module_exit();
 	kfree(info);
+	nft_chain_filter_fini();
 }
 
 module_init(nf_tables_module_init);
diff --git a/net/netfilter/nf_tables_inet.c b/net/netfilter/nf_tables_inet.c
deleted file mode 100644
index 202c4219969b..000000000000
--- a/net/netfilter/nf_tables_inet.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * Copyright (c) 2012-2014 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter_ipv6.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-#include <net/ip.h>
-
-static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb,
-				      const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-
-	switch (state->pf) {
-	case NFPROTO_IPV4:
-		nft_set_pktinfo_ipv4(&pkt, skb);
-		break;
-	case NFPROTO_IPV6:
-		nft_set_pktinfo_ipv6(&pkt, skb);
-		break;
-	default:
-		break;
-	}
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static const struct nft_chain_type filter_inet = {
-	.name		= "filter",
-	.type		= NFT_CHAIN_T_DEFAULT,
-	.family		= NFPROTO_INET,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
-			  (1 << NF_INET_LOCAL_OUT) |
-			  (1 << NF_INET_FORWARD) |
-			  (1 << NF_INET_PRE_ROUTING) |
-			  (1 << NF_INET_POST_ROUTING),
-	.hooks		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain_inet,
-		[NF_INET_LOCAL_OUT]	= nft_do_chain_inet,
-		[NF_INET_FORWARD]	= nft_do_chain_inet,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain_inet,
-		[NF_INET_POST_ROUTING]	= nft_do_chain_inet,
-        },
-};
-
-static int __init nf_tables_inet_init(void)
-{
-	nft_register_chain_type(&filter_inet);
-
-	return 0;
-}
-
-static void __exit nf_tables_inet_exit(void)
-{
-	nft_unregister_chain_type(&filter_inet);
-}
-
-module_init(nf_tables_inet_init);
-module_exit(nf_tables_inet_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(1, "filter");
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
deleted file mode 100644
index 4c3835bca63e..000000000000
--- a/net/netfilter/nf_tables_netdev.c
+++ /dev/null
@@ -1,140 +0,0 @@
-/*
- * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <net/netfilter/nf_tables.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-
-static unsigned int
-nft_do_chain_netdev(void *priv, struct sk_buff *skb,
-		    const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-		nft_set_pktinfo_ipv4_validate(&pkt, skb);
-		break;
-	case htons(ETH_P_IPV6):
-		nft_set_pktinfo_ipv6_validate(&pkt, skb);
-		break;
-	default:
-		nft_set_pktinfo_unspec(&pkt, skb);
-		break;
-	}
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static const struct nft_chain_type nft_filter_chain_netdev = {
-	.name		= "filter",
-	.type		= NFT_CHAIN_T_DEFAULT,
-	.family		= NFPROTO_NETDEV,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_NETDEV_INGRESS),
-	.hooks		= {
-		[NF_NETDEV_INGRESS]	= nft_do_chain_netdev,
-	},
-};
-
-static void nft_netdev_event(unsigned long event, struct net_device *dev,
-			     struct nft_ctx *ctx)
-{
-	struct nft_base_chain *basechain = nft_base_chain(ctx->chain);
-
-	switch (event) {
-	case NETDEV_UNREGISTER:
-		if (strcmp(basechain->dev_name, dev->name) != 0)
-			return;
-
-		__nft_release_basechain(ctx);
-		break;
-	case NETDEV_CHANGENAME:
-		if (dev->ifindex != basechain->ops.dev->ifindex)
-			return;
-
-		strncpy(basechain->dev_name, dev->name, IFNAMSIZ);
-		break;
-	}
-}
-
-static int nf_tables_netdev_event(struct notifier_block *this,
-				  unsigned long event, void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct nft_table *table;
-	struct nft_chain *chain, *nr;
-	struct nft_ctx ctx = {
-		.net	= dev_net(dev),
-	};
-
-	if (event != NETDEV_UNREGISTER &&
-	    event != NETDEV_CHANGENAME)
-		return NOTIFY_DONE;
-
-	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_for_each_entry(table, &ctx.net->nft.tables, list) {
-		if (table->family != NFPROTO_NETDEV)
-			continue;
-
-		ctx.family = table->family;
-		ctx.table = table;
-		list_for_each_entry_safe(chain, nr, &table->chains, list) {
-			if (!nft_is_base_chain(chain))
-				continue;
-
-			ctx.chain = chain;
-			nft_netdev_event(event, dev, &ctx);
-		}
-	}
-	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block nf_tables_netdev_notifier = {
-	.notifier_call	= nf_tables_netdev_event,
-};
-
-static int __init nf_tables_netdev_init(void)
-{
-	int ret;
-
-	nft_register_chain_type(&nft_filter_chain_netdev);
-
-	ret = register_netdevice_notifier(&nf_tables_netdev_notifier);
-	if (ret)
-		goto err_register_netdevice_notifier;
-
-	return 0;
-
-err_register_netdevice_notifier:
-	nft_unregister_chain_type(&nft_filter_chain_netdev);
-
-	return ret;
-}
-
-static void __exit nf_tables_netdev_exit(void)
-{
-	unregister_netdevice_notifier(&nf_tables_netdev_notifier);
-	nft_unregister_chain_type(&nft_filter_chain_netdev);
-}
-
-module_init(nf_tables_netdev_init);
-module_exit(nf_tables_netdev_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
-MODULE_ALIAS_NFT_CHAIN(5, "filter"); /* NFPROTO_NETDEV */
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
new file mode 100644
index 000000000000..84c902477a91
--- /dev/null
+++ b/net/netfilter/nft_chain_filter.c
@@ -0,0 +1,398 @@
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <net/net_namespace.h>
+#include <net/netfilter/nf_tables.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_arp.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+
+#ifdef CONFIG_NF_TABLES_IPV4
+static unsigned int nft_do_chain_ipv4(void *priv,
+				      struct sk_buff *skb,
+				      const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, skb, state);
+	nft_set_pktinfo_ipv4(&pkt, skb);
+
+	return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_filter_ipv4 = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_IPV4,
+	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_FORWARD) |
+			  (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING),
+	.hooks		= {
+		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv4,
+		[NF_INET_LOCAL_OUT]	= nft_do_chain_ipv4,
+		[NF_INET_FORWARD]	= nft_do_chain_ipv4,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv4,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv4,
+	},
+};
+
+static void nft_chain_filter_ipv4_init(void)
+{
+	nft_register_chain_type(&nft_chain_filter_ipv4);
+}
+static void nft_chain_filter_ipv4_fini(void)
+{
+	nft_unregister_chain_type(&nft_chain_filter_ipv4);
+}
+
+#else
+static inline void nft_chain_filter_ipv4_init(void) {}
+static inline void nft_chain_filter_ipv4_fini(void) {}
+#endif /* CONFIG_NF_TABLES_IPV4 */
+
+#ifdef CONFIG_NF_TABLES_ARP
+static unsigned int nft_do_chain_arp(void *priv, struct sk_buff *skb,
+				     const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, skb, state);
+	nft_set_pktinfo_unspec(&pkt, skb);
+
+	return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_filter_arp = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_ARP,
+	.owner		= THIS_MODULE,
+	.hook_mask	= (1 << NF_ARP_IN) |
+			  (1 << NF_ARP_OUT),
+	.hooks		= {
+		[NF_ARP_IN]		= nft_do_chain_arp,
+		[NF_ARP_OUT]		= nft_do_chain_arp,
+	},
+};
+
+static void nft_chain_filter_arp_init(void)
+{
+	nft_register_chain_type(&nft_chain_filter_arp);
+}
+
+static void nft_chain_filter_arp_fini(void)
+{
+	nft_unregister_chain_type(&nft_chain_filter_arp);
+}
+#else
+static inline void nft_chain_filter_arp_init(void) {}
+static inline void nft_chain_filter_arp_fini(void) {}
+#endif /* CONFIG_NF_TABLES_ARP */
+
+#ifdef CONFIG_NF_TABLES_IPV6
+static unsigned int nft_do_chain_ipv6(void *priv,
+				      struct sk_buff *skb,
+				      const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, skb, state);
+	nft_set_pktinfo_ipv6(&pkt, skb);
+
+	return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_filter_ipv6 = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_IPV6,
+	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_FORWARD) |
+			  (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING),
+	.hooks		= {
+		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv6,
+		[NF_INET_LOCAL_OUT]	= nft_do_chain_ipv6,
+		[NF_INET_FORWARD]	= nft_do_chain_ipv6,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv6,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv6,
+	},
+};
+
+static void nft_chain_filter_ipv6_init(void)
+{
+	nft_register_chain_type(&nft_chain_filter_ipv6);
+}
+
+static void nft_chain_filter_ipv6_fini(void)
+{
+	nft_unregister_chain_type(&nft_chain_filter_ipv6);
+}
+#else
+static inline void nft_chain_filter_ipv6_init(void) {}
+static inline void nft_chain_filter_ipv6_fini(void) {}
+#endif /* CONFIG_NF_TABLES_IPV6 */
+
+#ifdef CONFIG_NF_TABLES_INET
+static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb,
+				      const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, skb, state);
+
+	switch (state->pf) {
+	case NFPROTO_IPV4:
+		nft_set_pktinfo_ipv4(&pkt, skb);
+		break;
+	case NFPROTO_IPV6:
+		nft_set_pktinfo_ipv6(&pkt, skb);
+		break;
+	default:
+		break;
+	}
+
+	return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_filter_inet = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_INET,
+	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_FORWARD) |
+			  (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING),
+	.hooks		= {
+		[NF_INET_LOCAL_IN]	= nft_do_chain_inet,
+		[NF_INET_LOCAL_OUT]	= nft_do_chain_inet,
+		[NF_INET_FORWARD]	= nft_do_chain_inet,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_inet,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_inet,
+        },
+};
+
+static void nft_chain_filter_inet_init(void)
+{
+	nft_register_chain_type(&nft_chain_filter_inet);
+}
+
+static void nft_chain_filter_inet_fini(void)
+{
+	nft_unregister_chain_type(&nft_chain_filter_inet);
+}
+#else
+static inline void nft_chain_filter_inet_init(void) {}
+static inline void nft_chain_filter_inet_fini(void) {}
+#endif /* CONFIG_NF_TABLES_IPV6 */
+
+#ifdef CONFIG_NF_TABLES_BRIDGE
+static unsigned int
+nft_do_chain_bridge(void *priv,
+		    struct sk_buff *skb,
+		    const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, skb, state);
+
+	switch (eth_hdr(skb)->h_proto) {
+	case htons(ETH_P_IP):
+		nft_set_pktinfo_ipv4_validate(&pkt, skb);
+		break;
+	case htons(ETH_P_IPV6):
+		nft_set_pktinfo_ipv6_validate(&pkt, skb);
+		break;
+	default:
+		nft_set_pktinfo_unspec(&pkt, skb);
+		break;
+	}
+
+	return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_filter_bridge = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_BRIDGE,
+	.hook_mask	= (1 << NF_BR_PRE_ROUTING) |
+			  (1 << NF_BR_LOCAL_IN) |
+			  (1 << NF_BR_FORWARD) |
+			  (1 << NF_BR_LOCAL_OUT) |
+			  (1 << NF_BR_POST_ROUTING),
+	.hooks		= {
+		[NF_BR_PRE_ROUTING]	= nft_do_chain_bridge,
+		[NF_BR_LOCAL_IN]	= nft_do_chain_bridge,
+		[NF_BR_FORWARD]		= nft_do_chain_bridge,
+		[NF_BR_LOCAL_OUT]	= nft_do_chain_bridge,
+		[NF_BR_POST_ROUTING]	= nft_do_chain_bridge,
+	},
+};
+
+static void nft_chain_filter_bridge_init(void)
+{
+	nft_register_chain_type(&nft_chain_filter_bridge);
+}
+
+static void nft_chain_filter_bridge_fini(void)
+{
+	nft_unregister_chain_type(&nft_chain_filter_bridge);
+}
+#else
+static inline void nft_chain_filter_bridge_init(void) {}
+static inline void nft_chain_filter_bridge_fini(void) {}
+#endif /* CONFIG_NF_TABLES_BRIDGE */
+
+#ifdef CONFIG_NF_TABLES_NETDEV
+static unsigned int nft_do_chain_netdev(void *priv, struct sk_buff *skb,
+					const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, skb, state);
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		nft_set_pktinfo_ipv4_validate(&pkt, skb);
+		break;
+	case htons(ETH_P_IPV6):
+		nft_set_pktinfo_ipv6_validate(&pkt, skb);
+		break;
+	default:
+		nft_set_pktinfo_unspec(&pkt, skb);
+		break;
+	}
+
+	return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_filter_netdev = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_NETDEV,
+	.hook_mask	= (1 << NF_NETDEV_INGRESS),
+	.hooks		= {
+		[NF_NETDEV_INGRESS]	= nft_do_chain_netdev,
+	},
+};
+
+static void nft_netdev_event(unsigned long event, struct net_device *dev,
+			     struct nft_ctx *ctx)
+{
+	struct nft_base_chain *basechain = nft_base_chain(ctx->chain);
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		if (strcmp(basechain->dev_name, dev->name) != 0)
+			return;
+
+		__nft_release_basechain(ctx);
+		break;
+	case NETDEV_CHANGENAME:
+		if (dev->ifindex != basechain->ops.dev->ifindex)
+			return;
+
+		strncpy(basechain->dev_name, dev->name, IFNAMSIZ);
+		break;
+	}
+}
+
+static int nf_tables_netdev_event(struct notifier_block *this,
+				  unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct nft_table *table;
+	struct nft_chain *chain, *nr;
+	struct nft_ctx ctx = {
+		.net	= dev_net(dev),
+	};
+
+	if (event != NETDEV_UNREGISTER &&
+	    event != NETDEV_CHANGENAME)
+		return NOTIFY_DONE;
+
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_for_each_entry(table, &ctx.net->nft.tables, list) {
+		if (table->family != NFPROTO_NETDEV)
+			continue;
+
+		ctx.family = table->family;
+		ctx.table = table;
+		list_for_each_entry_safe(chain, nr, &table->chains, list) {
+			if (!nft_is_base_chain(chain))
+				continue;
+
+			ctx.chain = chain;
+			nft_netdev_event(event, dev, &ctx);
+		}
+	}
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nf_tables_netdev_notifier = {
+	.notifier_call	= nf_tables_netdev_event,
+};
+
+static int nft_chain_filter_netdev_init(void)
+{
+	int err;
+
+	nft_register_chain_type(&nft_chain_filter_netdev);
+
+	err = register_netdevice_notifier(&nf_tables_netdev_notifier);
+	if (err)
+		goto err_register_netdevice_notifier;
+
+	return 0;
+
+err_register_netdevice_notifier:
+	nft_unregister_chain_type(&nft_chain_filter_netdev);
+
+	return err;
+}
+
+static void nft_chain_filter_netdev_fini(void)
+{
+	nft_unregister_chain_type(&nft_chain_filter_netdev);
+	unregister_netdevice_notifier(&nf_tables_netdev_notifier);
+}
+#else
+static inline int nft_chain_filter_netdev_init(void) { return 0; }
+static inline void nft_chain_filter_netdev_fini(void) {}
+#endif /* CONFIG_NF_TABLES_NETDEV */
+
+int __init nft_chain_filter_init(void)
+{
+	int err;
+
+	err = nft_chain_filter_netdev_init();
+	if (err < 0)
+		return err;
+
+	nft_chain_filter_ipv4_init();
+	nft_chain_filter_ipv6_init();
+	nft_chain_filter_arp_init();
+	nft_chain_filter_inet_init();
+	nft_chain_filter_bridge_init();
+
+	return 0;
+}
+
+void __exit nft_chain_filter_fini(void)
+{
+	nft_chain_filter_bridge_fini();
+	nft_chain_filter_inet_fini();
+	nft_chain_filter_arp_fini();
+	nft_chain_filter_ipv6_fini();
+	nft_chain_filter_ipv4_fini();
+	nft_chain_filter_netdev_fini();
+}
-- 
cgit v1.2.3


From 43a605f2f722b6e08addedae8545b490fca252c4 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 27 Mar 2018 11:53:08 +0200
Subject: netfilter: nf_tables: enable conntrack if NAT chain is registered

Register conntrack hooks if the user adds NAT chains. Users get confused
with the existing behaviour since they will see no packets hitting this
chain until they add the first rule that refers to conntrack.

This patch adds new ->init() and ->free() indirections to chain types
that can be used by NAT chains to invoke the conntrack dependency.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h       |  4 ++++
 net/ipv4/netfilter/nft_chain_nat_ipv4.c | 12 ++++++++++++
 net/ipv6/netfilter/nft_chain_nat_ipv6.c | 12 ++++++++++++
 net/netfilter/nf_tables_api.c           | 24 +++++++++++++++++-------
 4 files changed, 45 insertions(+), 7 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 77c3c04c27ac..e26b94a61a99 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -884,6 +884,8 @@ enum nft_chain_types {
  * 	@owner: module owner
  * 	@hook_mask: mask of valid hooks
  * 	@hooks: array of hook functions
+ *	@init: chain initialization function
+ *	@free: chain release function
  */
 struct nft_chain_type {
 	const char			*name;
@@ -892,6 +894,8 @@ struct nft_chain_type {
 	struct module			*owner;
 	unsigned int			hook_mask;
 	nf_hookfn			*hooks[NF_MAX_HOOKS];
+	int				(*init)(struct nft_ctx *ctx);
+	void				(*free)(struct nft_ctx *ctx);
 };
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index 9864f5b3279c..b5464a3f253b 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -67,6 +67,16 @@ static unsigned int nft_nat_ipv4_local_fn(void *priv,
 	return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain);
 }
 
+static int nft_nat_ipv4_init(struct nft_ctx *ctx)
+{
+	return nf_ct_netns_get(ctx->net, ctx->family);
+}
+
+static void nft_nat_ipv4_free(struct nft_ctx *ctx)
+{
+	nf_ct_netns_put(ctx->net, ctx->family);
+}
+
 static const struct nft_chain_type nft_chain_nat_ipv4 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
@@ -82,6 +92,8 @@ static const struct nft_chain_type nft_chain_nat_ipv4 = {
 		[NF_INET_LOCAL_OUT]	= nft_nat_ipv4_local_fn,
 		[NF_INET_LOCAL_IN]	= nft_nat_ipv4_fn,
 	},
+	.init		= nft_nat_ipv4_init,
+	.free		= nft_nat_ipv4_free,
 };
 
 static int __init nft_chain_nat_init(void)
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index c95d9a97d425..3557b114446c 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -65,6 +65,16 @@ static unsigned int nft_nat_ipv6_local_fn(void *priv,
 	return nf_nat_ipv6_local_fn(priv, skb, state, nft_nat_do_chain);
 }
 
+static int nft_nat_ipv6_init(struct nft_ctx *ctx)
+{
+	return nf_ct_netns_get(ctx->net, ctx->family);
+}
+
+static void nft_nat_ipv6_free(struct nft_ctx *ctx)
+{
+	nf_ct_netns_put(ctx->net, ctx->family);
+}
+
 static const struct nft_chain_type nft_chain_nat_ipv6 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
@@ -80,6 +90,8 @@ static const struct nft_chain_type nft_chain_nat_ipv6 = {
 		[NF_INET_LOCAL_OUT]	= nft_nat_ipv6_local_fn,
 		[NF_INET_LOCAL_IN]	= nft_nat_ipv6_fn,
 	},
+	.init		= nft_nat_ipv6_init,
+	.free		= nft_nat_ipv6_free,
 };
 
 static int __init nft_chain_nat_ipv6_init(void)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 97ec1c388bfe..af8b6a7488bd 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1211,13 +1211,17 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain,
 		rcu_assign_pointer(chain->stats, newstats);
 }
 
-static void nf_tables_chain_destroy(struct nft_chain *chain)
+static void nf_tables_chain_destroy(struct nft_ctx *ctx)
 {
+	struct nft_chain *chain = ctx->chain;
+
 	BUG_ON(chain->use > 0);
 
 	if (nft_is_base_chain(chain)) {
 		struct nft_base_chain *basechain = nft_base_chain(chain);
 
+		if (basechain->type->free)
+			basechain->type->free(ctx);
 		module_put(basechain->type->owner);
 		free_percpu(basechain->stats);
 		if (basechain->stats)
@@ -1354,6 +1358,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		}
 
 		basechain->type = hook.type;
+		if (basechain->type->init)
+			basechain->type->init(ctx);
+
 		chain = &basechain->chain;
 
 		ops		= &basechain->ops;
@@ -1374,6 +1381,8 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		if (chain == NULL)
 			return -ENOMEM;
 	}
+	ctx->chain = chain;
+
 	INIT_LIST_HEAD(&chain->rules);
 	chain->handle = nf_tables_alloc_handle(table);
 	chain->table = table;
@@ -1387,7 +1396,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	if (err < 0)
 		goto err1;
 
-	ctx->chain = chain;
 	err = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
 	if (err < 0)
 		goto err2;
@@ -1399,7 +1407,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 err2:
 	nf_tables_unregister_hook(net, table, chain);
 err1:
-	nf_tables_chain_destroy(chain);
+	nf_tables_chain_destroy(ctx);
 
 	return err;
 }
@@ -5678,7 +5686,7 @@ static void nf_tables_commit_release(struct nft_trans *trans)
 		nf_tables_table_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_DELCHAIN:
-		nf_tables_chain_destroy(trans->ctx.chain);
+		nf_tables_chain_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_DELRULE:
 		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
@@ -5849,7 +5857,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 		nf_tables_table_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_NEWCHAIN:
-		nf_tables_chain_destroy(trans->ctx.chain);
+		nf_tables_chain_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_NEWRULE:
 		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
@@ -6499,7 +6507,7 @@ int __nft_release_basechain(struct nft_ctx *ctx)
 	}
 	list_del(&ctx->chain->list);
 	ctx->table->use--;
-	nf_tables_chain_destroy(ctx->chain);
+	nf_tables_chain_destroy(ctx);
 
 	return 0;
 }
@@ -6515,6 +6523,7 @@ static void __nft_release_tables(struct net *net)
 	struct nft_set *set, *ns;
 	struct nft_ctx ctx = {
 		.net	= net,
+		.family	= NFPROTO_NETDEV,
 	};
 
 	list_for_each_entry_safe(table, nt, &net->nft.tables, list) {
@@ -6551,9 +6560,10 @@ static void __nft_release_tables(struct net *net)
 			nft_obj_destroy(obj);
 		}
 		list_for_each_entry_safe(chain, nc, &table->chains, list) {
+			ctx.chain = chain;
 			list_del(&chain->list);
 			table->use--;
-			nf_tables_chain_destroy(chain);
+			nf_tables_chain_destroy(&ctx);
 		}
 		list_del(&table->list);
 		nf_tables_table_destroy(&ctx);
-- 
cgit v1.2.3


From 10659cbab72b7bfee1a886018d1915a9549b6378 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 28 Mar 2018 12:06:49 +0200
Subject: netfilter: nf_tables: rename to nft_set_lookup_global()

To prepare shorter introduction of shorter function prefix.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 10 +++++-----
 net/netfilter/nf_tables_api.c     | 12 ++++++------
 net/netfilter/nft_dynset.c        |  5 +++--
 net/netfilter/nft_lookup.c        |  4 ++--
 net/netfilter/nft_objref.c        |  5 +++--
 5 files changed, 19 insertions(+), 17 deletions(-)

(limited to 'include/net')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index e26b94a61a99..bd2a18d66189 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -434,11 +434,11 @@ static inline struct nft_set *nft_set_container_of(const void *priv)
 	return (void *)priv - offsetof(struct nft_set, data);
 }
 
-struct nft_set *nft_set_lookup(const struct net *net,
-			       const struct nft_table *table,
-			       const struct nlattr *nla_set_name,
-			       const struct nlattr *nla_set_id,
-			       u8 genmask);
+struct nft_set *nft_set_lookup_global(const struct net *net,
+				      const struct nft_table *table,
+				      const struct nlattr *nla_set_name,
+				      const struct nlattr *nla_set_id,
+				      u8 genmask);
 
 static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
 {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index af8b6a7488bd..769d84015073 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2633,11 +2633,11 @@ static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
 	return ERR_PTR(-ENOENT);
 }
 
-struct nft_set *nft_set_lookup(const struct net *net,
-			       const struct nft_table *table,
-			       const struct nlattr *nla_set_name,
-			       const struct nlattr *nla_set_id,
-			       u8 genmask)
+struct nft_set *nft_set_lookup_global(const struct net *net,
+				      const struct nft_table *table,
+				      const struct nlattr *nla_set_name,
+				      const struct nlattr *nla_set_id,
+				      u8 genmask)
 {
 	struct nft_set *set;
 
@@ -2650,7 +2650,7 @@ struct nft_set *nft_set_lookup(const struct net *net,
 	}
 	return set;
 }
-EXPORT_SYMBOL_GPL(nft_set_lookup);
+EXPORT_SYMBOL_GPL(nft_set_lookup_global);
 
 static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 				    const char *name)
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index fc83e29d6634..04863fad05dd 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -132,8 +132,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 			priv->invert = true;
 	}
 
-	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME],
-			     tb[NFTA_DYNSET_SET_ID], genmask);
+	set = nft_set_lookup_global(ctx->net, ctx->table,
+				    tb[NFTA_DYNSET_SET_NAME],
+				    tb[NFTA_DYNSET_SET_ID], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 475570e89ede..f52da5e2199f 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -71,8 +71,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	    tb[NFTA_LOOKUP_SREG] == NULL)
 		return -EINVAL;
 
-	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET],
-			     tb[NFTA_LOOKUP_SET_ID], genmask);
+	set = nft_set_lookup_global(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET],
+				    tb[NFTA_LOOKUP_SET_ID], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 7bcdc48f3d73..0b02407773ad 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -117,8 +117,9 @@ static int nft_objref_map_init(const struct nft_ctx *ctx,
 	struct nft_set *set;
 	int err;
 
-	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME],
-			     tb[NFTA_OBJREF_SET_ID], genmask);
+	set = nft_set_lookup_global(ctx->net, ctx->table,
+				    tb[NFTA_OBJREF_SET_NAME],
+				    tb[NFTA_OBJREF_SET_ID], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
-- 
cgit v1.2.3


From e9a441b6e729e16092fcc18e3962b952a01d1e3c Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Thu, 29 Mar 2018 17:03:25 +0300
Subject: xfrm: Register xfrm_dev_notifier in appropriate place

Currently, driver registers it from pernet_operations::init method,
and this breaks modularity, because initialization of net namespace
and netdevice notifiers are orthogonal actions. We don't have
per-namespace netdevice notifiers; all of them are global for all
devices in all namespaces.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 2 +-
 net/xfrm/xfrm_device.c | 2 +-
 net/xfrm/xfrm_policy.c | 3 +--
 3 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/net')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index aa027ba1d032..a872379b69da 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1894,7 +1894,7 @@ static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb)
 #endif
 }
 
-void __net_init xfrm_dev_init(void);
+void __init xfrm_dev_init(void);
 
 #ifdef CONFIG_XFRM_OFFLOAD
 void xfrm_dev_resume(struct sk_buff *skb);
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index e87d6c4dd5b6..175941e15a6e 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -350,7 +350,7 @@ static struct notifier_block xfrm_dev_notifier = {
 	.notifier_call	= xfrm_dev_event,
 };
 
-void __net_init xfrm_dev_init(void)
+void __init xfrm_dev_init(void)
 {
 	register_netdevice_notifier(&xfrm_dev_notifier);
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0e065db6c7c0..40b54cc64243 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2895,8 +2895,6 @@ static int __net_init xfrm_policy_init(struct net *net)
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
 	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
-	if (net_eq(net, &init_net))
-		xfrm_dev_init();
 	return 0;
 
 out_bydst:
@@ -2999,6 +2997,7 @@ void __init xfrm_init(void)
 		INIT_WORK(&xfrm_pcpu_work[i], xfrm_pcpu_work_fn);
 
 	register_pernet_subsys(&xfrm_net_ops);
+	xfrm_dev_init();
 	seqcount_init(&xfrm_policy_hash_generation);
 	xfrm_input_init();
 }
-- 
cgit v1.2.3


From 3679d585bbc07a1ac4448d5b478b492cad3587ce Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 30 Mar 2018 15:08:04 -0700
Subject: net: Introduce __inet_bind() and __inet6_bind

Refactor `bind()` code to make it ready to be called from BPF helper
function `bpf_bind()` (will be added soon). Implementation of
`inet_bind()` and `inet6_bind()` is separated into `__inet_bind()` and
`__inet6_bind()` correspondingly. These function can be used from both
`sk_prot->bind` and `bpf_bind()` contexts.

New functions have two additional arguments.

`force_bind_address_no_port` forces binding to IP only w/o checking
`inet_sock.bind_address_no_port` field. It'll allow to bind local end of
a connection to desired IP in `bpf_bind()` w/o changing
`bind_address_no_port` field of a socket. It's useful since `bpf_bind()`
can return an error and we'd need to restore original value of
`bind_address_no_port` in that case if we changed this before calling to
the helper.

`with_lock` specifies whether to lock socket when working with `struct
sk` or not. The argument is set to `true` for `sk_prot->bind`, i.e. old
behavior is preserved. But it will be set to `false` for `bpf_bind()`
use-case. The reason is all call-sites, where `bpf_bind()` will be
called, already hold that socket lock.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/inet_common.h |  2 ++
 include/net/ipv6.h        |  2 ++
 net/ipv4/af_inet.c        | 39 ++++++++++++++++++++++++---------------
 net/ipv6/af_inet6.c       | 37 ++++++++++++++++++++++++-------------
 4 files changed, 52 insertions(+), 28 deletions(-)

(limited to 'include/net')

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 500f81375200..384b90c62c0b 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -32,6 +32,8 @@ int inet_shutdown(struct socket *sock, int how);
 int inet_listen(struct socket *sock, int backlog);
 void inet_sock_destruct(struct sock *sk);
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+		bool force_bind_address_no_port, bool with_lock);
 int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 		 int peer);
 int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 50a6f0ddb878..2e5fedc56e59 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1066,6 +1066,8 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);
 void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);
 
 int inet6_release(struct socket *sock);
+int __inet6_bind(struct sock *sock, struct sockaddr *uaddr, int addr_len,
+		 bool force_bind_address_no_port, bool with_lock);
 int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
 int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		  int peer);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 2dec266507dc..e203a39d6988 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -432,30 +432,37 @@ EXPORT_SYMBOL(inet_release);
 
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
-	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
 	struct sock *sk = sock->sk;
-	struct inet_sock *inet = inet_sk(sk);
-	struct net *net = sock_net(sk);
-	unsigned short snum;
-	int chk_addr_ret;
-	u32 tb_id = RT_TABLE_LOCAL;
 	int err;
 
 	/* If the socket has its own bind function then use it. (RAW) */
 	if (sk->sk_prot->bind) {
-		err = sk->sk_prot->bind(sk, uaddr, addr_len);
-		goto out;
+		return sk->sk_prot->bind(sk, uaddr, addr_len);
 	}
-	err = -EINVAL;
 	if (addr_len < sizeof(struct sockaddr_in))
-		goto out;
+		return -EINVAL;
 
 	/* BPF prog is run before any checks are done so that if the prog
 	 * changes context in a wrong way it will be caught.
 	 */
 	err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr);
 	if (err)
-		goto out;
+		return err;
+
+	return __inet_bind(sk, uaddr, addr_len, false, true);
+}
+EXPORT_SYMBOL(inet_bind);
+
+int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+		bool force_bind_address_no_port, bool with_lock)
+{
+	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
+	struct inet_sock *inet = inet_sk(sk);
+	struct net *net = sock_net(sk);
+	unsigned short snum;
+	int chk_addr_ret;
+	u32 tb_id = RT_TABLE_LOCAL;
+	int err;
 
 	if (addr->sin_family != AF_INET) {
 		/* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
@@ -499,7 +506,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	 *      would be illegal to use them (multicast/broadcast) in
 	 *      which case the sending device address is used.
 	 */
-	lock_sock(sk);
+	if (with_lock)
+		lock_sock(sk);
 
 	/* Check these errors (active socket, double bind). */
 	err = -EINVAL;
@@ -511,7 +519,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		inet->inet_saddr = 0;  /* Use device */
 
 	/* Make sure we are allowed to bind here. */
-	if ((snum || !inet->bind_address_no_port) &&
+	if ((snum || !(inet->bind_address_no_port ||
+		       force_bind_address_no_port)) &&
 	    sk->sk_prot->get_port(sk, snum)) {
 		inet->inet_saddr = inet->inet_rcv_saddr = 0;
 		err = -EADDRINUSE;
@@ -528,11 +537,11 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	sk_dst_reset(sk);
 	err = 0;
 out_release_sock:
-	release_sock(sk);
+	if (with_lock)
+		release_sock(sk);
 out:
 	return err;
 }
-EXPORT_SYMBOL(inet_bind);
 
 int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
 		       int addr_len, int flags)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fa24e3f06ac6..13110bee5c14 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -277,15 +277,7 @@ out_rcu_unlock:
 /* bind for INET6 API */
 int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
-	struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr;
 	struct sock *sk = sock->sk;
-	struct inet_sock *inet = inet_sk(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct net *net = sock_net(sk);
-	__be32 v4addr = 0;
-	unsigned short snum;
-	bool saved_ipv6only;
-	int addr_type = 0;
 	int err = 0;
 
 	/* If the socket has its own bind function then use it. */
@@ -302,11 +294,28 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (err)
 		return err;
 
+	return __inet6_bind(sk, uaddr, addr_len, false, true);
+}
+EXPORT_SYMBOL(inet6_bind);
+
+int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+		 bool force_bind_address_no_port, bool with_lock)
+{
+	struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr;
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net *net = sock_net(sk);
+	__be32 v4addr = 0;
+	unsigned short snum;
+	bool saved_ipv6only;
+	int addr_type = 0;
+	int err = 0;
+
 	if (addr->sin6_family != AF_INET6)
 		return -EAFNOSUPPORT;
 
 	addr_type = ipv6_addr_type(&addr->sin6_addr);
-	if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM)
+	if ((addr_type & IPV6_ADDR_MULTICAST) && sk->sk_type == SOCK_STREAM)
 		return -EINVAL;
 
 	snum = ntohs(addr->sin6_port);
@@ -314,7 +323,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	    !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
 		return -EACCES;
 
-	lock_sock(sk);
+	if (with_lock)
+		lock_sock(sk);
 
 	/* Check these errors (active socket, double bind). */
 	if (sk->sk_state != TCP_CLOSE || inet->inet_num) {
@@ -402,7 +412,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		sk->sk_ipv6only = 1;
 
 	/* Make sure we are allowed to bind here. */
-	if ((snum || !inet->bind_address_no_port) &&
+	if ((snum || !(inet->bind_address_no_port ||
+		       force_bind_address_no_port)) &&
 	    sk->sk_prot->get_port(sk, snum)) {
 		sk->sk_ipv6only = saved_ipv6only;
 		inet_reset_saddr(sk);
@@ -418,13 +429,13 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	inet->inet_dport = 0;
 	inet->inet_daddr = 0;
 out:
-	release_sock(sk);
+	if (with_lock)
+		release_sock(sk);
 	return err;
 out_unlock:
 	rcu_read_unlock();
 	goto out;
 }
-EXPORT_SYMBOL(inet6_bind);
 
 int inet6_release(struct socket *sock)
 {
-- 
cgit v1.2.3


From d74bad4e74ee373787a9ae24197c17b7cdc428d5 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 30 Mar 2018 15:08:05 -0700
Subject: bpf: Hooks for sys_connect

== The problem ==

See description of the problem in the initial patch of this patch set.

== The solution ==

The patch provides much more reliable in-kernel solution for the 2nd
part of the problem: making outgoing connecttion from desired IP.

It adds new attach types `BPF_CGROUP_INET4_CONNECT` and
`BPF_CGROUP_INET6_CONNECT` for program type
`BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that can be used to override both
source and destination of a connection at connect(2) time.

Local end of connection can be bound to desired IP using newly
introduced BPF-helper `bpf_bind()`. It allows to bind to only IP though,
and doesn't support binding to port, i.e. leverages
`IP_BIND_ADDRESS_NO_PORT` socket option. There are two reasons for this:
* looking for a free port is expensive and can affect performance
  significantly;
* there is no use-case for port.

As for remote end (`struct sockaddr *` passed by user), both parts of it
can be overridden, remote IP and remote port. It's useful if an
application inside cgroup wants to connect to another application inside
same cgroup or to itself, but knows nothing about IP assigned to the
cgroup.

Support is added for IPv4 and IPv6, for TCP and UDP.

IPv4 and IPv6 have separate attach types for same reason as sys_bind
hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields
when user passes sockaddr_in since it'd be out-of-bound.

== Implementation notes ==

The patch introduces new field in `struct proto`: `pre_connect` that is
a pointer to a function with same signature as `connect` but is called
before it. The reason is in some cases BPF hooks should be called way
before control is passed to `sk->sk_prot->connect`. Specifically
`inet_dgram_connect` autobinds socket before calling
`sk->sk_prot->connect` and there is no way to call `bpf_bind()` from
hooks from e.g. `ip4_datagram_connect` or `ip6_datagram_connect` since
it'd cause double-bind. On the other hand `proto.pre_connect` provides a
flexible way to add BPF hooks for connect only for necessary `proto` and
call them at desired time before `connect`. Since `bpf_bind()` is
allowed to bind only to IP and autobind in `inet_dgram_connect` binds
only port there is no chance of double-bind.

bpf_bind() sets `force_bind_address_no_port` to bind to only IP despite
of value of `bind_address_no_port` socket field.

bpf_bind() sets `with_lock` to `false` when calling to __inet_bind()
and __inet6_bind() since all call-sites, where bpf_bind() is called,
already hold socket lock.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf-cgroup.h | 31 +++++++++++++++++++++++++
 include/net/addrconf.h     |  7 ++++++
 include/net/sock.h         |  3 +++
 include/net/udp.h          |  1 +
 include/uapi/linux/bpf.h   | 12 +++++++++-
 kernel/bpf/syscall.c       |  8 +++++++
 net/core/filter.c          | 57 ++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/af_inet.c         | 13 +++++++++++
 net/ipv4/tcp_ipv4.c        | 16 +++++++++++++
 net/ipv4/udp.c             | 14 ++++++++++++
 net/ipv6/af_inet6.c        |  5 ++++
 net/ipv6/tcp_ipv6.c        | 16 +++++++++++++
 net/ipv6/udp.c             | 20 ++++++++++++++++
 13 files changed, 202 insertions(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 67dc4a6471ad..c6ab295e6dcb 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -116,12 +116,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 	__ret;								       \
 })
 
+#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)	{					       \
+		lock_sock(sk);						       \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type);    \
+		release_sock(sk);					       \
+	}								       \
+	__ret;								       \
+})
+
 #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr)			       \
 	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_BIND)
 
 #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr)			       \
 	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_BIND)
 
+#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \
+					    sk->sk_prot->pre_connect)
+
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr)		       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr)		       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT)
+
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops)				       \
 ({									       \
 	int __ret = 0;							       \
@@ -151,11 +177,16 @@ struct cgroup_bpf {};
 static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 
+#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
 
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 132e5b95167a..378d601258be 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -231,6 +231,13 @@ struct ipv6_stub {
 };
 extern const struct ipv6_stub *ipv6_stub __read_mostly;
 
+/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */
+struct ipv6_bpf_stub {
+	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+			  bool force_bind_address_no_port, bool with_lock);
+};
+extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
+
 /*
  * identify MLD packets for MLD filter exceptions
  */
diff --git a/include/net/sock.h b/include/net/sock.h
index b8ff435fa96e..49bd2c1796b0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1026,6 +1026,9 @@ static inline void sk_prot_clear_nulls(struct sock *sk, int size)
 struct proto {
 	void			(*close)(struct sock *sk,
 					long timeout);
+	int			(*pre_connect)(struct sock *sk,
+					struct sockaddr *uaddr,
+					int addr_len);
 	int			(*connect)(struct sock *sk,
 					struct sockaddr *uaddr,
 					int addr_len);
diff --git a/include/net/udp.h b/include/net/udp.h
index 850a8e581cce..0676b272f6ac 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -273,6 +273,7 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
 int udp_rcv(struct sk_buff *skb);
 int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int udp_init_sock(struct sock *sk);
+int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int __udp_disconnect(struct sock *sk, int flags);
 int udp_disconnect(struct sock *sk, int flags);
 __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ce3e69e3c793..77afaf1ba556 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -150,6 +150,8 @@ enum bpf_attach_type {
 	BPF_SK_MSG_VERDICT,
 	BPF_CGROUP_INET4_BIND,
 	BPF_CGROUP_INET6_BIND,
+	BPF_CGROUP_INET4_CONNECT,
+	BPF_CGROUP_INET6_CONNECT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -744,6 +746,13 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: SK_PASS
  *
+ * int bpf_bind(ctx, addr, addr_len)
+ *     Bind socket to address. Only binding to IP is supported, no port can be
+ *     set in addr.
+ *     @ctx: pointer to context of type bpf_sock_addr
+ *     @addr: pointer to struct sockaddr to bind socket to
+ *     @addr_len: length of sockaddr structure
+ *     Return: 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -809,7 +818,8 @@ union bpf_attr {
 	FN(msg_redirect_map),		\
 	FN(msg_apply_bytes),		\
 	FN(msg_cork_bytes),		\
-	FN(msg_pull_data),
+	FN(msg_pull_data),		\
+	FN(bind),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2cad66a4cacb..cf1b29bc0ab8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1180,6 +1180,8 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 		switch (expected_attach_type) {
 		case BPF_CGROUP_INET4_BIND:
 		case BPF_CGROUP_INET6_BIND:
+		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_INET6_CONNECT:
 			return 0;
 		default:
 			return -EINVAL;
@@ -1491,6 +1493,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		break;
 	case BPF_CGROUP_INET4_BIND:
 	case BPF_CGROUP_INET6_BIND:
+	case BPF_CGROUP_INET4_CONNECT:
+	case BPF_CGROUP_INET6_CONNECT:
 		ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 		break;
 	case BPF_CGROUP_SOCK_OPS:
@@ -1557,6 +1561,8 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		break;
 	case BPF_CGROUP_INET4_BIND:
 	case BPF_CGROUP_INET6_BIND:
+	case BPF_CGROUP_INET4_CONNECT:
+	case BPF_CGROUP_INET6_CONNECT:
 		ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 		break;
 	case BPF_CGROUP_SOCK_OPS:
@@ -1610,6 +1616,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET_SOCK_CREATE:
 	case BPF_CGROUP_INET4_BIND:
 	case BPF_CGROUP_INET6_BIND:
+	case BPF_CGROUP_INET4_CONNECT:
+	case BPF_CGROUP_INET6_CONNECT:
 	case BPF_CGROUP_SOCK_OPS:
 	case BPF_CGROUP_DEVICE:
 		break;
diff --git a/net/core/filter.c b/net/core/filter.c
index c08e5b121558..bdb9cadd4d27 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -33,6 +33,7 @@
 #include <linux/if_packet.h>
 #include <linux/if_arp.h>
 #include <linux/gfp.h>
+#include <net/inet_common.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/netlink.h>
@@ -3656,6 +3657,52 @@ static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
+EXPORT_SYMBOL_GPL(ipv6_bpf_stub);
+
+BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr,
+	   int, addr_len)
+{
+#ifdef CONFIG_INET
+	struct sock *sk = ctx->sk;
+	int err;
+
+	/* Binding to port can be expensive so it's prohibited in the helper.
+	 * Only binding to IP is supported.
+	 */
+	err = -EINVAL;
+	if (addr->sa_family == AF_INET) {
+		if (addr_len < sizeof(struct sockaddr_in))
+			return err;
+		if (((struct sockaddr_in *)addr)->sin_port != htons(0))
+			return err;
+		return __inet_bind(sk, addr, addr_len, true, false);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (addr->sa_family == AF_INET6) {
+		if (addr_len < SIN6_LEN_RFC2133)
+			return err;
+		if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
+			return err;
+		/* ipv6_bpf_stub cannot be NULL, since it's called from
+		 * bpf_cgroup_inet6_connect hook and ipv6 is already loaded
+		 */
+		return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, true, false);
+#endif /* CONFIG_IPV6 */
+	}
+#endif /* CONFIG_INET */
+
+	return -EAFNOSUPPORT;
+}
+
+static const struct bpf_func_proto bpf_bind_proto = {
+	.func		= bpf_bind,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -3707,6 +3754,14 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	 */
 	case BPF_FUNC_get_current_uid_gid:
 		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_bind:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_INET6_CONNECT:
+			return &bpf_bind_proto;
+		default:
+			return NULL;
+		}
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -4213,6 +4268,7 @@ static bool sock_addr_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
 		switch (prog->expected_attach_type) {
 		case BPF_CGROUP_INET4_BIND:
+		case BPF_CGROUP_INET4_CONNECT:
 			break;
 		default:
 			return false;
@@ -4221,6 +4277,7 @@ static bool sock_addr_is_valid_access(int off, int size,
 	case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]):
 		switch (prog->expected_attach_type) {
 		case BPF_CGROUP_INET6_BIND:
+		case BPF_CGROUP_INET6_CONNECT:
 			break;
 		default:
 			return false;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e203a39d6988..488fe26ac8e5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -547,12 +547,19 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
 		       int addr_len, int flags)
 {
 	struct sock *sk = sock->sk;
+	int err;
 
 	if (addr_len < sizeof(uaddr->sa_family))
 		return -EINVAL;
 	if (uaddr->sa_family == AF_UNSPEC)
 		return sk->sk_prot->disconnect(sk, flags);
 
+	if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) {
+		err = sk->sk_prot->pre_connect(sk, uaddr, addr_len);
+		if (err)
+			return err;
+	}
+
 	if (!inet_sk(sk)->inet_num && inet_autobind(sk))
 		return -EAGAIN;
 	return sk->sk_prot->connect(sk, uaddr, addr_len);
@@ -633,6 +640,12 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		if (sk->sk_state != TCP_CLOSE)
 			goto out;
 
+		if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) {
+			err = sk->sk_prot->pre_connect(sk, uaddr, addr_len);
+			if (err)
+				goto out;
+		}
+
 		err = sk->sk_prot->connect(sk, uaddr, addr_len);
 		if (err < 0)
 			goto out;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2c6aec2643e8..3c11d992d784 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -140,6 +140,21 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 }
 EXPORT_SYMBOL_GPL(tcp_twsk_unique);
 
+static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr,
+			      int addr_len)
+{
+	/* This check is replicated from tcp_v4_connect() and intended to
+	 * prevent BPF program called below from accessing bytes that are out
+	 * of the bound specified by user in addr_len.
+	 */
+	if (addr_len < sizeof(struct sockaddr_in))
+		return -EINVAL;
+
+	sock_owned_by_me(sk);
+
+	return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr);
+}
+
 /* This will initiate an outgoing connection. */
 int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
@@ -2409,6 +2424,7 @@ struct proto tcp_prot = {
 	.name			= "TCP",
 	.owner			= THIS_MODULE,
 	.close			= tcp_close,
+	.pre_connect		= tcp_v4_pre_connect,
 	.connect		= tcp_v4_connect,
 	.disconnect		= tcp_disconnect,
 	.accept			= inet_csk_accept,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 908fc02fb4f8..9c6c77fec963 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1658,6 +1658,19 @@ csum_copy_err:
 	goto try_again;
 }
 
+int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	/* This check is replicated from __ip4_datagram_connect() and
+	 * intended to prevent BPF program called below from accessing bytes
+	 * that are out of the bound specified by user in addr_len.
+	 */
+	if (addr_len < sizeof(struct sockaddr_in))
+		return -EINVAL;
+
+	return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr);
+}
+EXPORT_SYMBOL(udp_pre_connect);
+
 int __udp_disconnect(struct sock *sk, int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -2530,6 +2543,7 @@ struct proto udp_prot = {
 	.name			= "UDP",
 	.owner			= THIS_MODULE,
 	.close			= udp_lib_close,
+	.pre_connect		= udp_pre_connect,
 	.connect		= ip4_datagram_connect,
 	.disconnect		= udp_disconnect,
 	.ioctl			= udp_ioctl,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 13110bee5c14..566cec0e0a44 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -887,6 +887,10 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.nd_tbl	= &nd_tbl,
 };
 
+static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
+	.inet6_bind = __inet6_bind,
+};
+
 static int __init inet6_init(void)
 {
 	struct list_head *r;
@@ -1043,6 +1047,7 @@ static int __init inet6_init(void)
 	/* ensure that ipv6 stubs are visible only after ipv6 is ready */
 	wmb();
 	ipv6_stub = &ipv6_stub_impl;
+	ipv6_bpf_stub = &ipv6_bpf_stub_impl;
 out:
 	return err;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5425d7b100ee..6469b741cf5a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -117,6 +117,21 @@ static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb)
 				   ipv6_hdr(skb)->saddr.s6_addr32);
 }
 
+static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
+			      int addr_len)
+{
+	/* This check is replicated from tcp_v6_connect() and intended to
+	 * prevent BPF program called below from accessing bytes that are out
+	 * of the bound specified by user in addr_len.
+	 */
+	if (addr_len < SIN6_LEN_RFC2133)
+		return -EINVAL;
+
+	sock_owned_by_me(sk);
+
+	return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr);
+}
+
 static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			  int addr_len)
 {
@@ -1925,6 +1940,7 @@ struct proto tcpv6_prot = {
 	.name			= "TCPv6",
 	.owner			= THIS_MODULE,
 	.close			= tcp_close,
+	.pre_connect		= tcp_v6_pre_connect,
 	.connect		= tcp_v6_connect,
 	.disconnect		= tcp_disconnect,
 	.accept			= inet_csk_accept,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index ad30f5e31969..6861ed479469 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -957,6 +957,25 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
 	}
 }
 
+static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
+			     int addr_len)
+{
+	/* The following checks are replicated from __ip6_datagram_connect()
+	 * and intended to prevent BPF program called below from accessing
+	 * bytes that are out of the bound specified by user in addr_len.
+	 */
+	if (uaddr->sa_family == AF_INET) {
+		if (__ipv6_only_sock(sk))
+			return -EAFNOSUPPORT;
+		return udp_pre_connect(sk, uaddr, addr_len);
+	}
+
+	if (addr_len < SIN6_LEN_RFC2133)
+		return -EINVAL;
+
+	return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr);
+}
+
 /**
  *	udp6_hwcsum_outgoing  -  handle outgoing HW checksumming
  *	@sk:	socket we are sending on
@@ -1512,6 +1531,7 @@ struct proto udpv6_prot = {
 	.name			= "UDPv6",
 	.owner			= THIS_MODULE,
 	.close			= udp_lib_close,
+	.pre_connect		= udpv6_pre_connect,
 	.connect		= ip6_datagram_connect,
 	.disconnect		= udp_disconnect,
 	.ioctl			= udp_ioctl,
-- 
cgit v1.2.3


From c22af22cbdc206a0273d0e6d773bd3dfc99d2b02 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:42 -0700
Subject: ipv6: frag: remove unused field

csum field in struct frag_queue is not used, remove it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 50a6f0ddb878..5c18836672e9 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -603,7 +603,6 @@ struct frag_queue {
 	struct in6_addr		daddr;
 
 	int			iif;
-	unsigned int		csum;
 	__u16			nhoffset;
 	u8			ecn;
 };
-- 
cgit v1.2.3


From 787bea7748a76130566f881c2342a0be4127d182 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:43 -0700
Subject: inet: frags: change inet_frags_init_net() return value

We will soon initialize one rhashtable per struct netns_frags
in inet_frags_init_net().

This patch changes the return value to eventually propagate an
error.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 |  3 ++-
 net/ieee802154/6lowpan/reassembly.c     | 11 ++++++++---
 net/ipv4/ip_fragment.c                  | 12 +++++++++---
 net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++++++++---
 net/ipv6/reassembly.c                   | 11 +++++++++--
 5 files changed, 37 insertions(+), 12 deletions(-)

(limited to 'include/net')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 351f0c3cdcd9..b1d62176f3b4 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -104,9 +104,10 @@ struct inet_frags {
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline void inet_frags_init_net(struct netns_frags *nf)
+static inline int inet_frags_init_net(struct netns_frags *nf)
 {
 	atomic_set(&nf->mem, 0);
+	return 0;
 }
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 85bf86ad6b18..2aaab4bba429 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -581,14 +581,19 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
+	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	inet_frags_init_net(&ieee802154_lowpan->frags);
-
-	return lowpan_frags_ns_sysctl_register(net);
+	res = inet_frags_init_net(&ieee802154_lowpan->frags);
+	if (res < 0)
+		return res;
+	res = lowpan_frags_ns_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+	return res;
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbf1b94942c0..e0b39d4ecbd4 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -846,6 +846,8 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
+	int res;
+
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -871,9 +873,13 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 
 	net->ipv4.frags.max_dist = 64;
 
-	inet_frags_init_net(&net->ipv4.frags);
-
-	return ip4_frags_ns_ctl_register(net);
+	res = inet_frags_init_net(&net->ipv4.frags);
+	if (res < 0)
+		return res;
+	res = ip4_frags_ns_ctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+	return res;
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index b84ce3e6d728..6ff41569134a 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -629,12 +629,18 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
+	int res;
+
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	inet_frags_init_net(&net->nf_frag.frags);
-
-	return nf_ct_frag6_sysctl_register(net);
+	res = inet_frags_init_net(&net->nf_frag.frags);
+	if (res < 0)
+		return res;
+	res = nf_ct_frag6_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+	return res;
 }
 
 static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 08a139f14d0f..a8f7a5f0251a 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -711,13 +711,20 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
+	int res;
+
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	inet_frags_init_net(&net->ipv6.frags);
+	res = inet_frags_init_net(&net->ipv6.frags);
+	if (res < 0)
+		return res;
 
-	return ip6_frags_ns_sysctl_register(net);
+	res = ip6_frags_ns_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+	return res;
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)
-- 
cgit v1.2.3


From 093ba72914b696521e4885756a68a3332782c8de Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:44 -0700
Subject: inet: frags: add a pointer to struct netns_frags

In order to simplify the API, add a pointer to struct inet_frags.
This will allow us to make things less complex.

These functions no longer have a struct inet_frags parameter :

inet_frag_destroy(struct inet_frag_queue *q  /*, struct inet_frags *f */)
inet_frag_put(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frag_kill(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frags_exit_net(struct netns_frags *nf /*, struct inet_frags *f */)
ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 | 11 ++++++-----
 include/net/ipv6.h                      |  3 +--
 net/ieee802154/6lowpan/reassembly.c     | 13 +++++++------
 net/ipv4/inet_fragment.c                | 17 ++++++++++-------
 net/ipv4/ip_fragment.c                  |  9 +++++----
 net/ipv6/netfilter/nf_conntrack_reasm.c | 16 +++++++++-------
 net/ipv6/reassembly.c                   | 20 ++++++++++----------
 7 files changed, 48 insertions(+), 41 deletions(-)

(limited to 'include/net')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index b1d62176f3b4..69e531ed8189 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -10,6 +10,7 @@ struct netns_frags {
 	int			high_thresh;
 	int			low_thresh;
 	int			max_dist;
+	struct inet_frags	*f;
 };
 
 /**
@@ -109,20 +110,20 @@ static inline int inet_frags_init_net(struct netns_frags *nf)
 	atomic_set(&nf->mem, 0);
 	return 0;
 }
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
+void inet_frags_exit_net(struct netns_frags *nf);
 
-void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f);
+void inet_frag_kill(struct inet_frag_queue *q);
+void inet_frag_destroy(struct inet_frag_queue *q);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 		struct inet_frags *f, void *key, unsigned int hash);
 
 void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
 				   const char *prefix);
 
-static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
+static inline void inet_frag_put(struct inet_frag_queue *q)
 {
 	if (refcount_dec_and_test(&q->refcnt))
-		inet_frag_destroy(q, f);
+		inet_frag_destroy(q);
 }
 
 static inline bool inet_frag_evicting(struct inet_frag_queue *q)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 5c18836672e9..57b7fe43d2ab 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -607,8 +607,7 @@ struct frag_queue {
 	u8			ecn;
 };
 
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
-			   struct inet_frags *frags);
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
 
 static inline bool ipv6_addr_any(const struct in6_addr *a)
 {
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 2aaab4bba429..6badc055555b 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -94,10 +94,10 @@ static void lowpan_frag_expire(struct timer_list *t)
 	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
-	inet_frag_kill(&fq->q, &lowpan_frags);
+	inet_frag_kill(&fq->q);
 out:
 	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q, &lowpan_frags);
+	inet_frag_put(&fq->q);
 }
 
 static inline struct lowpan_frag_queue *
@@ -230,7 +230,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
 	struct sk_buff *fp, *head = fq->q.fragments;
 	int sum_truesize;
 
-	inet_frag_kill(&fq->q, &lowpan_frags);
+	inet_frag_kill(&fq->q);
 
 	/* Make the one we just received the head. */
 	if (prev) {
@@ -438,7 +438,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 		ret = lowpan_frag_queue(fq, skb, frag_type);
 		spin_unlock(&fq->q.lock);
 
-		inet_frag_put(&fq->q, &lowpan_frags);
+		inet_frag_put(&fq->q);
 		return ret;
 	}
 
@@ -586,13 +586,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+	ieee802154_lowpan->frags.f = &lowpan_frags;
 
 	res = inet_frags_init_net(&ieee802154_lowpan->frags);
 	if (res < 0)
 		return res;
 	res = lowpan_frags_ns_sysctl_register(net);
 	if (res < 0)
-		inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+		inet_frags_exit_net(&ieee802154_lowpan->frags);
 	return res;
 }
 
@@ -602,7 +603,7 @@ static void __net_exit lowpan_frags_exit_net(struct net *net)
 		net_ieee802154_lowpan(net);
 
 	lowpan_frags_ns_sysctl_unregister(net);
-	inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+	inet_frags_exit_net(&ieee802154_lowpan->frags);
 }
 
 static struct pernet_operations lowpan_frags_ops = {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index e8ec28999f5c..1ac69f65d0de 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -219,8 +219,9 @@ void inet_frags_fini(struct inet_frags *f)
 }
 EXPORT_SYMBOL(inet_frags_fini);
 
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
+void inet_frags_exit_net(struct netns_frags *nf)
 {
+	struct inet_frags *f =nf->f;
 	unsigned int seq;
 	int i;
 
@@ -264,33 +265,34 @@ __acquires(hb->chain_lock)
 	return hb;
 }
 
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+static inline void fq_unlink(struct inet_frag_queue *fq)
 {
 	struct inet_frag_bucket *hb;
 
-	hb = get_frag_bucket_locked(fq, f);
+	hb = get_frag_bucket_locked(fq, fq->net->f);
 	hlist_del(&fq->list);
 	fq->flags |= INET_FRAG_COMPLETE;
 	spin_unlock(&hb->chain_lock);
 }
 
-void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frag_kill(struct inet_frag_queue *fq)
 {
 	if (del_timer(&fq->timer))
 		refcount_dec(&fq->refcnt);
 
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
-		fq_unlink(fq, f);
+		fq_unlink(fq);
 		refcount_dec(&fq->refcnt);
 	}
 }
 EXPORT_SYMBOL(inet_frag_kill);
 
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
+void inet_frag_destroy(struct inet_frag_queue *q)
 {
 	struct sk_buff *fp;
 	struct netns_frags *nf;
 	unsigned int sum, sum_truesize = 0;
+	struct inet_frags *f;
 
 	WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
 	WARN_ON(del_timer(&q->timer) != 0);
@@ -298,6 +300,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 	/* Release all fragment data. */
 	fp = q->fragments;
 	nf = q->net;
+	f = nf->f;
 	while (fp) {
 		struct sk_buff *xp = fp->next;
 
@@ -333,7 +336,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
 			refcount_inc(&qp->refcnt);
 			spin_unlock(&hb->chain_lock);
 			qp_in->flags |= INET_FRAG_COMPLETE;
-			inet_frag_put(qp_in, f);
+			inet_frag_put(qp_in);
 			return qp;
 		}
 	}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index e0b39d4ecbd4..cd2b4c9419fc 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -168,7 +168,7 @@ static void ip4_frag_free(struct inet_frag_queue *q)
 
 static void ipq_put(struct ipq *ipq)
 {
-	inet_frag_put(&ipq->q, &ip4_frags);
+	inet_frag_put(&ipq->q);
 }
 
 /* Kill ipq entry. It is not destroyed immediately,
@@ -176,7 +176,7 @@ static void ipq_put(struct ipq *ipq)
  */
 static void ipq_kill(struct ipq *ipq)
 {
-	inet_frag_kill(&ipq->q, &ip4_frags);
+	inet_frag_kill(&ipq->q);
 }
 
 static bool frag_expire_skip_icmp(u32 user)
@@ -872,20 +872,21 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 	net->ipv4.frags.timeout = IP_FRAG_TIME;
 
 	net->ipv4.frags.max_dist = 64;
+	net->ipv4.frags.f = &ip4_frags;
 
 	res = inet_frags_init_net(&net->ipv4.frags);
 	if (res < 0)
 		return res;
 	res = ip4_frags_ns_ctl_register(net);
 	if (res < 0)
-		inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+		inet_frags_exit_net(&net->ipv4.frags);
 	return res;
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
 {
 	ip4_frags_ns_ctl_unregister(net);
-	inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+	inet_frags_exit_net(&net->ipv4.frags);
 }
 
 static struct pernet_operations ip4_frags_ops = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6ff41569134a..c4b40fdee838 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -178,7 +178,7 @@ static void nf_ct_frag6_expire(struct timer_list *t)
 	fq = container_of(frag, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, nf_frag.frags);
 
-	ip6_expire_frag_queue(net, fq, &nf_frags);
+	ip6_expire_frag_queue(net, fq);
 }
 
 /* Creation primitives. */
@@ -264,7 +264,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 			 * this case. -DaveM
 			 */
 			pr_debug("end of fragment not rounded to 8 bytes.\n");
-			inet_frag_kill(&fq->q, &nf_frags);
+			inet_frag_kill(&fq->q);
 			return -EPROTO;
 		}
 		if (end > fq->q.len) {
@@ -357,7 +357,7 @@ found:
 	return 0;
 
 discard_fq:
-	inet_frag_kill(&fq->q, &nf_frags);
+	inet_frag_kill(&fq->q);
 err:
 	return -EINVAL;
 }
@@ -379,7 +379,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 	int    payload_len;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q, &nf_frags);
+	inet_frag_kill(&fq->q);
 
 	WARN_ON(head == NULL);
 	WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
@@ -622,7 +622,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 
 out_unlock:
 	spin_unlock_bh(&fq->q.lock);
-	inet_frag_put(&fq->q, &nf_frags);
+	inet_frag_put(&fq->q);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
@@ -634,19 +634,21 @@ static int nf_ct_net_init(struct net *net)
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
+	net->nf_frag.frags.f = &nf_frags;
+
 	res = inet_frags_init_net(&net->nf_frag.frags);
 	if (res < 0)
 		return res;
 	res = nf_ct_frag6_sysctl_register(net);
 	if (res < 0)
-		inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+		inet_frags_exit_net(&net->nf_frag.frags);
 	return res;
 }
 
 static void nf_ct_net_exit(struct net *net)
 {
 	nf_ct_frags6_sysctl_unregister(net);
-	inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+	inet_frags_exit_net(&net->nf_frag.frags);
 }
 
 static struct pernet_operations nf_ct_net_ops = {
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index a8f7a5f0251a..4855de6f673a 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -128,8 +128,7 @@ void ip6_frag_init(struct inet_frag_queue *q, const void *a)
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
-			   struct inet_frags *frags)
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
 {
 	struct net_device *dev = NULL;
 
@@ -138,7 +137,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
 	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
-	inet_frag_kill(&fq->q, frags);
+	inet_frag_kill(&fq->q);
 
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, fq->iif);
@@ -166,7 +165,7 @@ out_rcu_unlock:
 	rcu_read_unlock();
 out:
 	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q, frags);
+	inet_frag_put(&fq->q);
 }
 EXPORT_SYMBOL(ip6_expire_frag_queue);
 
@@ -179,7 +178,7 @@ static void ip6_frag_expire(struct timer_list *t)
 	fq = container_of(frag, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, ipv6.frags);
 
-	ip6_expire_frag_queue(net, fq, &ip6_frags);
+	ip6_expire_frag_queue(net, fq);
 }
 
 static struct frag_queue *
@@ -364,7 +363,7 @@ found:
 	return -1;
 
 discard_fq:
-	inet_frag_kill(&fq->q, &ip6_frags);
+	inet_frag_kill(&fq->q);
 err:
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			IPSTATS_MIB_REASMFAILS);
@@ -391,7 +390,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	int sum_truesize;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q, &ip6_frags);
+	inet_frag_kill(&fq->q);
 
 	ecn = ip_frag_ecn_table[fq->ecn];
 	if (unlikely(ecn == 0xff))
@@ -569,7 +568,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
 
 		spin_unlock(&fq->q.lock);
-		inet_frag_put(&fq->q, &ip6_frags);
+		inet_frag_put(&fq->q);
 		return ret;
 	}
 
@@ -716,6 +715,7 @@ static int __net_init ipv6_frags_init_net(struct net *net)
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+	net->ipv6.frags.f = &ip6_frags;
 
 	res = inet_frags_init_net(&net->ipv6.frags);
 	if (res < 0)
@@ -723,14 +723,14 @@ static int __net_init ipv6_frags_init_net(struct net *net)
 
 	res = ip6_frags_ns_sysctl_register(net);
 	if (res < 0)
-		inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+		inet_frags_exit_net(&net->ipv6.frags);
 	return res;
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)
 {
 	ip6_frags_ns_sysctl_unregister(net);
-	inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+	inet_frags_exit_net(&net->ipv6.frags);
 }
 
 static struct pernet_operations ip6_frags_ops = {
-- 
cgit v1.2.3


From 648700f76b03b7e8149d13cc2bdb3355035258a9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:49 -0700
Subject: inet: frags: use rhashtables for reassembly units

Some applications still rely on IP fragmentation, and to be fair linux
reassembly unit is not working under any serious load.

It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!)

A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.

This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.

Then there is the problem of sharing this hash table for all netns.

It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.

Lookup is now using RCU. A followup patch will even remove
the refcount hold/release left from prior implementation and save
a couple of atomic operations.

Before this patch, 16 cpus (16 RX queue NIC) could not handle more
than 1 Mpps frags DDOS.

After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB
of storage for the fragments (exact number depends on frags being evicted
after timeout)

$ grep FRAG /proc/net/sockstat
FRAG: inuse 1966916 memory 2140004608

A followup patch will change the limits for 64bit arches.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Florian Westphal <fw@strlen.de>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt  |   7 +-
 include/net/inet_frag.h                 |  81 ++++----
 include/net/ipv6.h                      |  16 +-
 net/ieee802154/6lowpan/6lowpan_i.h      |  26 +--
 net/ieee802154/6lowpan/reassembly.c     |  91 ++++-----
 net/ipv4/inet_fragment.c                | 344 ++++++--------------------------
 net/ipv4/ip_fragment.c                  | 112 +++++------
 net/ipv6/netfilter/nf_conntrack_reasm.c |  51 ++---
 net/ipv6/reassembly.c                   | 110 +++++-----
 9 files changed, 265 insertions(+), 573 deletions(-)

(limited to 'include/net')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 33f35f049ad5..6f2a3670e44b 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -134,13 +134,10 @@ min_adv_mss - INTEGER
 IP Fragmentation:
 
 ipfrag_high_thresh - INTEGER
-	Maximum memory used to reassemble IP fragments. When
-	ipfrag_high_thresh bytes of memory is allocated for this purpose,
-	the fragment handler will toss packets until ipfrag_low_thresh
-	is reached. This also serves as a maximum limit to namespaces
-	different from the initial one.
+	Maximum memory used to reassemble IP fragments.
 
 ipfrag_low_thresh - INTEGER
+	(Obsolete since linux-4.17)
 	Maximum memory used to reassemble IP fragments before the kernel
 	begins to remove incomplete fragment queues to free up resources.
 	The kernel still accepts new fragments for defragmentation.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 69e531ed8189..3fec0d3a0d01 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -2,7 +2,11 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
+#include <linux/rhashtable.h>
+
 struct netns_frags {
+	struct rhashtable       rhashtable ____cacheline_aligned_in_smp;
+
 	/* Keep atomic mem on separate cachelines in structs that include it */
 	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
@@ -26,12 +30,30 @@ enum {
 	INET_FRAG_COMPLETE	= BIT(2),
 };
 
+struct frag_v4_compare_key {
+	__be32		saddr;
+	__be32		daddr;
+	u32		user;
+	u32		vif;
+	__be16		id;
+	u16		protocol;
+};
+
+struct frag_v6_compare_key {
+	struct in6_addr	saddr;
+	struct in6_addr	daddr;
+	u32		user;
+	__be32		id;
+	u32		iif;
+};
+
 /**
  * struct inet_frag_queue - fragment queue
  *
- * @lock: spinlock protecting the queue
+ * @node: rhash node
+ * @key: keys identifying this frag.
  * @timer: queue expiration timer
- * @list: hash bucket list
+ * @lock: spinlock protecting this frag
  * @refcnt: reference count of the queue
  * @fragments: received fragments head
  * @fragments_tail: received fragments tail
@@ -41,12 +63,16 @@ enum {
  * @flags: fragment queue flags
  * @max_size: maximum received fragment size
  * @net: namespace that this frag belongs to
- * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
+ * @rcu: rcu head for freeing deferall
  */
 struct inet_frag_queue {
-	spinlock_t		lock;
+	struct rhash_head	node;
+	union {
+		struct frag_v4_compare_key v4;
+		struct frag_v6_compare_key v6;
+	} key;
 	struct timer_list	timer;
-	struct hlist_node	list;
+	spinlock_t		lock;
 	refcount_t		refcnt;
 	struct sk_buff		*fragments;
 	struct sk_buff		*fragments_tail;
@@ -55,51 +81,20 @@ struct inet_frag_queue {
 	int			meat;
 	__u8			flags;
 	u16			max_size;
-	struct netns_frags	*net;
-	struct hlist_node	list_evictor;
-};
-
-#define INETFRAGS_HASHSZ	1024
-
-/* averaged:
- * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
- *	       rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
- *	       struct frag_queue))
- */
-#define INETFRAGS_MAXDEPTH	128
-
-struct inet_frag_bucket {
-	struct hlist_head	chain;
-	spinlock_t		chain_lock;
+	struct netns_frags      *net;
+	struct rcu_head		rcu;
 };
 
 struct inet_frags {
-	struct inet_frag_bucket	hash[INETFRAGS_HASHSZ];
-
-	struct work_struct	frags_work;
-	unsigned int next_bucket;
-	unsigned long last_rebuild_jiffies;
-	bool rebuild;
-
-	/* The first call to hashfn is responsible to initialize
-	 * rnd. This is best done with net_get_random_once.
-	 *
-	 * rnd_seqlock is used to let hash insertion detect
-	 * when it needs to re-lookup the hash chain to use.
-	 */
-	u32			rnd;
-	seqlock_t		rnd_seqlock;
 	unsigned int		qsize;
 
-	unsigned int		(*hashfn)(const struct inet_frag_queue *);
-	bool			(*match)(const struct inet_frag_queue *q,
-					 const void *arg);
 	void			(*constructor)(struct inet_frag_queue *q,
 					       const void *arg);
 	void			(*destructor)(struct inet_frag_queue *);
 	void			(*frag_expire)(struct timer_list *t);
 	struct kmem_cache	*frags_cachep;
 	const char		*frags_cache_name;
+	struct rhashtable_params rhash_params;
 };
 
 int inet_frags_init(struct inet_frags *);
@@ -108,15 +103,13 @@ void inet_frags_fini(struct inet_frags *);
 static inline int inet_frags_init_net(struct netns_frags *nf)
 {
 	atomic_set(&nf->mem, 0);
-	return 0;
+	return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
 }
 void inet_frags_exit_net(struct netns_frags *nf);
 
 void inet_frag_kill(struct inet_frag_queue *q);
 void inet_frag_destroy(struct inet_frag_queue *q);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
-		struct inet_frags *f, void *key, unsigned int hash);
-
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
 void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
 				   const char *prefix);
 
@@ -128,7 +121,7 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
 
 static inline bool inet_frag_evicting(struct inet_frag_queue *q)
 {
-	return !hlist_unhashed(&q->list_evictor);
+	return false;
 }
 
 /* Memory Tracking Functions. */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 57b7fe43d2ab..6fa9a2bc5896 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -579,17 +579,8 @@ enum ip6_defrag_users {
 	__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
 };
 
-struct ip6_create_arg {
-	__be32 id;
-	u32 user;
-	const struct in6_addr *src;
-	const struct in6_addr *dst;
-	int iif;
-	u8 ecn;
-};
-
 void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
+extern const struct rhashtable_params ip6_rhash_params;
 
 /*
  *	Equivalent of ipv4 struct ip
@@ -597,11 +588,6 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
 struct frag_queue {
 	struct inet_frag_queue	q;
 
-	__be32			id;		/* fragment id		*/
-	u32			user;
-	struct in6_addr		saddr;
-	struct in6_addr		daddr;
-
 	int			iif;
 	__u16			nhoffset;
 	u8			ecn;
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index d8de3bcfb103..b8d95cb71c25 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -17,37 +17,19 @@ typedef unsigned __bitwise lowpan_rx_result;
 #define LOWPAN_DISPATCH_FRAG1           0xc0
 #define LOWPAN_DISPATCH_FRAGN           0xe0
 
-struct lowpan_create_arg {
+struct frag_lowpan_compare_key {
 	u16 tag;
 	u16 d_size;
-	const struct ieee802154_addr *src;
-	const struct ieee802154_addr *dst;
+	const struct ieee802154_addr src;
+	const struct ieee802154_addr dst;
 };
 
-/* Equivalent of ipv4 struct ip
+/* Equivalent of ipv4 struct ipq
  */
 struct lowpan_frag_queue {
 	struct inet_frag_queue	q;
-
-	u16			tag;
-	u16			d_size;
-	struct ieee802154_addr	saddr;
-	struct ieee802154_addr	daddr;
 };
 
-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
-{
-	switch (a->mode) {
-	case IEEE802154_ADDR_LONG:
-		return (((__force u64)a->extended_addr) >> 32) ^
-			(((__force u64)a->extended_addr) & 0xffffffff);
-	case IEEE802154_ADDR_SHORT:
-		return (__force u32)(a->short_addr + (a->pan_id << 16));
-	default:
-		return 0;
-	}
-}
-
 int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
 void lowpan_net_frag_exit(void);
 int lowpan_net_frag_init(void);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index ddada12a044d..0fa0121f85d4 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
 static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
 			     struct sk_buff *prev, struct net_device *ldev);
 
-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
-				     const struct ieee802154_addr *saddr,
-				     const struct ieee802154_addr *daddr)
-{
-	net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
-	return jhash_3words(ieee802154_addr_hash(saddr),
-			    ieee802154_addr_hash(daddr),
-			    (__force u32)(tag + (d_size << 16)),
-			    lowpan_frags.rnd);
-}
-
-static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
-{
-	const struct lowpan_frag_queue *fq;
-
-	fq = container_of(q, struct lowpan_frag_queue, q);
-	return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
-}
-
-static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct lowpan_frag_queue *fq;
-	const struct lowpan_create_arg *arg = a;
-
-	fq = container_of(q, struct lowpan_frag_queue, q);
-	return	fq->tag == arg->tag && fq->d_size == arg->d_size &&
-		ieee802154_addr_equal(&fq->saddr, arg->src) &&
-		ieee802154_addr_equal(&fq->daddr, arg->dst);
-}
-
 static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
 {
-	const struct lowpan_create_arg *arg = a;
+	const struct frag_lowpan_compare_key *key = a;
 	struct lowpan_frag_queue *fq;
 
 	fq = container_of(q, struct lowpan_frag_queue, q);
 
-	fq->tag = arg->tag;
-	fq->d_size = arg->d_size;
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
+	BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
+	memcpy(&q->key, key, sizeof(*key));
 }
 
 static void lowpan_frag_expire(struct timer_list *t)
@@ -105,21 +73,17 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
 	const struct ieee802154_addr *src,
 	const struct ieee802154_addr *dst)
 {
-	struct inet_frag_queue *q;
-	struct lowpan_create_arg arg;
-	unsigned int hash;
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
+	struct frag_lowpan_compare_key key = {
+		.tag = cb->d_tag,
+		.d_size = cb->d_size,
+		.src = *src,
+		.dst = *dst,
+	};
+	struct inet_frag_queue *q;
 
-	arg.tag = cb->d_tag;
-	arg.d_size = cb->d_size;
-	arg.src = src;
-	arg.dst = dst;
-
-	hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
-
-	q = inet_frag_find(&ieee802154_lowpan->frags,
-			   &lowpan_frags, &arg, hash);
+	q = inet_frag_find(&ieee802154_lowpan->frags, &key);
 	if (IS_ERR_OR_NULL(q)) {
 		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
@@ -611,17 +575,46 @@ static struct pernet_operations lowpan_frags_ops = {
 	.exit = lowpan_frags_exit_net,
 };
 
+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key,
+		      sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_lowpan_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params lowpan_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= lowpan_key_hashfn,
+	.obj_hashfn		= lowpan_obj_hashfn,
+	.obj_cmpfn		= lowpan_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+
 int __init lowpan_net_frag_init(void)
 {
 	int ret;
 
-	lowpan_frags.hashfn = lowpan_hashfn;
 	lowpan_frags.constructor = lowpan_frag_init;
 	lowpan_frags.destructor = NULL;
 	lowpan_frags.qsize = sizeof(struct frag_queue);
-	lowpan_frags.match = lowpan_frag_match;
 	lowpan_frags.frag_expire = lowpan_frag_expire;
 	lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
+	lowpan_frags.rhash_params = lowpan_rhash_params;
 	ret = inet_frags_init(&lowpan_frags);
 	if (ret)
 		goto out;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 1ac69f65d0de..ebb8f411e0db 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -25,12 +25,6 @@
 #include <net/inet_frag.h>
 #include <net/inet_ecn.h>
 
-#define INETFRAGS_EVICT_BUCKETS   128
-#define INETFRAGS_EVICT_MAX	  512
-
-/* don't rebuild inetfrag table with new secret more often than this */
-#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
-
 /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
  * Value : 0xff if frame should be dropped.
  *         0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = {
 };
 EXPORT_SYMBOL(ip_frag_ecn_table);
 
-static unsigned int
-inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
-{
-	return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
-}
-
-static bool inet_frag_may_rebuild(struct inet_frags *f)
-{
-	return time_after(jiffies,
-	       f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
-}
-
-static void inet_frag_secret_rebuild(struct inet_frags *f)
-{
-	int i;
-
-	write_seqlock_bh(&f->rnd_seqlock);
-
-	if (!inet_frag_may_rebuild(f))
-		goto out;
-
-	get_random_bytes(&f->rnd, sizeof(u32));
-
-	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
-		struct inet_frag_bucket *hb;
-		struct inet_frag_queue *q;
-		struct hlist_node *n;
-
-		hb = &f->hash[i];
-		spin_lock(&hb->chain_lock);
-
-		hlist_for_each_entry_safe(q, n, &hb->chain, list) {
-			unsigned int hval = inet_frag_hashfn(f, q);
-
-			if (hval != i) {
-				struct inet_frag_bucket *hb_dest;
-
-				hlist_del(&q->list);
-
-				/* Relink to new hash chain. */
-				hb_dest = &f->hash[hval];
-
-				/* This is the only place where we take
-				 * another chain_lock while already holding
-				 * one.  As this will not run concurrently,
-				 * we cannot deadlock on hb_dest lock below, if its
-				 * already locked it will be released soon since
-				 * other caller cannot be waiting for hb lock
-				 * that we've taken above.
-				 */
-				spin_lock_nested(&hb_dest->chain_lock,
-						 SINGLE_DEPTH_NESTING);
-				hlist_add_head(&q->list, &hb_dest->chain);
-				spin_unlock(&hb_dest->chain_lock);
-			}
-		}
-		spin_unlock(&hb->chain_lock);
-	}
-
-	f->rebuild = false;
-	f->last_rebuild_jiffies = jiffies;
-out:
-	write_sequnlock_bh(&f->rnd_seqlock);
-}
-
-static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
-{
-	if (!hlist_unhashed(&q->list_evictor))
-		return false;
-
-	return q->net->low_thresh == 0 ||
-	       frag_mem_limit(q->net) >= q->net->low_thresh;
-}
-
-static unsigned int
-inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
-{
-	struct inet_frag_queue *fq;
-	struct hlist_node *n;
-	unsigned int evicted = 0;
-	HLIST_HEAD(expired);
-
-	spin_lock(&hb->chain_lock);
-
-	hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
-		if (!inet_fragq_should_evict(fq))
-			continue;
-
-		if (!del_timer(&fq->timer))
-			continue;
-
-		hlist_add_head(&fq->list_evictor, &expired);
-		++evicted;
-	}
-
-	spin_unlock(&hb->chain_lock);
-
-	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
-		f->frag_expire(&fq->timer);
-
-	return evicted;
-}
-
-static void inet_frag_worker(struct work_struct *work)
-{
-	unsigned int budget = INETFRAGS_EVICT_BUCKETS;
-	unsigned int i, evicted = 0;
-	struct inet_frags *f;
-
-	f = container_of(work, struct inet_frags, frags_work);
-
-	BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
-
-	local_bh_disable();
-
-	for (i = READ_ONCE(f->next_bucket); budget; --budget) {
-		evicted += inet_evict_bucket(f, &f->hash[i]);
-		i = (i + 1) & (INETFRAGS_HASHSZ - 1);
-		if (evicted > INETFRAGS_EVICT_MAX)
-			break;
-	}
-
-	f->next_bucket = i;
-
-	local_bh_enable();
-
-	if (f->rebuild && inet_frag_may_rebuild(f))
-		inet_frag_secret_rebuild(f);
-}
-
-static void inet_frag_schedule_worker(struct inet_frags *f)
-{
-	if (unlikely(!work_pending(&f->frags_work)))
-		schedule_work(&f->frags_work);
-}
-
 int inet_frags_init(struct inet_frags *f)
 {
-	int i;
-
-	INIT_WORK(&f->frags_work, inet_frag_worker);
-
-	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
-		struct inet_frag_bucket *hb = &f->hash[i];
-
-		spin_lock_init(&hb->chain_lock);
-		INIT_HLIST_HEAD(&hb->chain);
-	}
-
-	seqlock_init(&f->rnd_seqlock);
-	f->last_rebuild_jiffies = 0;
 	f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
 					    NULL);
 	if (!f->frags_cachep)
@@ -214,66 +59,42 @@ EXPORT_SYMBOL(inet_frags_init);
 
 void inet_frags_fini(struct inet_frags *f)
 {
-	cancel_work_sync(&f->frags_work);
+	/* We must wait that all inet_frag_destroy_rcu() have completed. */
+	rcu_barrier();
+
 	kmem_cache_destroy(f->frags_cachep);
+	f->frags_cachep = NULL;
 }
 EXPORT_SYMBOL(inet_frags_fini);
 
-void inet_frags_exit_net(struct netns_frags *nf)
-{
-	struct inet_frags *f =nf->f;
-	unsigned int seq;
-	int i;
-
-	nf->low_thresh = 0;
-
-evict_again:
-	local_bh_disable();
-	seq = read_seqbegin(&f->rnd_seqlock);
-
-	for (i = 0; i < INETFRAGS_HASHSZ ; i++)
-		inet_evict_bucket(f, &f->hash[i]);
-
-	local_bh_enable();
-	cond_resched();
-
-	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    sum_frag_mem_limit(nf))
-		goto evict_again;
-}
-EXPORT_SYMBOL(inet_frags_exit_net);
-
-static struct inet_frag_bucket *
-get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
-__acquires(hb->chain_lock)
+static void inet_frags_free_cb(void *ptr, void *arg)
 {
-	struct inet_frag_bucket *hb;
-	unsigned int seq, hash;
+	struct inet_frag_queue *fq = ptr;
 
- restart:
-	seq = read_seqbegin(&f->rnd_seqlock);
-
-	hash = inet_frag_hashfn(f, fq);
-	hb = &f->hash[hash];
+	/* If we can not cancel the timer, it means this frag_queue
+	 * is already disappearing, we have nothing to do.
+	 * Otherwise, we own a refcount until the end of this function.
+	 */
+	if (!del_timer(&fq->timer))
+		return;
 
-	spin_lock(&hb->chain_lock);
-	if (read_seqretry(&f->rnd_seqlock, seq)) {
-		spin_unlock(&hb->chain_lock);
-		goto restart;
+	spin_lock_bh(&fq->lock);
+	if (!(fq->flags & INET_FRAG_COMPLETE)) {
+		fq->flags |= INET_FRAG_COMPLETE;
+		refcount_dec(&fq->refcnt);
 	}
+	spin_unlock_bh(&fq->lock);
 
-	return hb;
+	inet_frag_put(fq);
 }
 
-static inline void fq_unlink(struct inet_frag_queue *fq)
+void inet_frags_exit_net(struct netns_frags *nf)
 {
-	struct inet_frag_bucket *hb;
+	nf->low_thresh = 0; /* prevent creation of new frags */
 
-	hb = get_frag_bucket_locked(fq, fq->net->f);
-	hlist_del(&fq->list);
-	fq->flags |= INET_FRAG_COMPLETE;
-	spin_unlock(&hb->chain_lock);
+	rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
 }
+EXPORT_SYMBOL(inet_frags_exit_net);
 
 void inet_frag_kill(struct inet_frag_queue *fq)
 {
@@ -281,12 +102,26 @@ void inet_frag_kill(struct inet_frag_queue *fq)
 		refcount_dec(&fq->refcnt);
 
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
-		fq_unlink(fq);
+		struct netns_frags *nf = fq->net;
+
+		fq->flags |= INET_FRAG_COMPLETE;
+		rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
 		refcount_dec(&fq->refcnt);
 	}
 }
 EXPORT_SYMBOL(inet_frag_kill);
 
+static void inet_frag_destroy_rcu(struct rcu_head *head)
+{
+	struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
+						 rcu);
+	struct inet_frags *f = q->net->f;
+
+	if (f->destructor)
+		f->destructor(q);
+	kmem_cache_free(f->frags_cachep, q);
+}
+
 void inet_frag_destroy(struct inet_frag_queue *q)
 {
 	struct sk_buff *fp;
@@ -310,59 +145,20 @@ void inet_frag_destroy(struct inet_frag_queue *q)
 	}
 	sum = sum_truesize + f->qsize;
 
-	if (f->destructor)
-		f->destructor(q);
-	kmem_cache_free(f->frags_cachep, q);
+	call_rcu(&q->rcu, inet_frag_destroy_rcu);
 
 	sub_frag_mem_limit(nf, sum);
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
-static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
-						struct inet_frag_queue *qp_in,
-						struct inet_frags *f,
-						void *arg)
-{
-	struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
-	struct inet_frag_queue *qp;
-
-#ifdef CONFIG_SMP
-	/* With SMP race we have to recheck hash table, because
-	 * such entry could have been created on other cpu before
-	 * we acquired hash bucket lock.
-	 */
-	hlist_for_each_entry(qp, &hb->chain, list) {
-		if (qp->net == nf && f->match(qp, arg)) {
-			refcount_inc(&qp->refcnt);
-			spin_unlock(&hb->chain_lock);
-			qp_in->flags |= INET_FRAG_COMPLETE;
-			inet_frag_put(qp_in);
-			return qp;
-		}
-	}
-#endif
-	qp = qp_in;
-	if (!mod_timer(&qp->timer, jiffies + nf->timeout))
-		refcount_inc(&qp->refcnt);
-
-	refcount_inc(&qp->refcnt);
-	hlist_add_head(&qp->list, &hb->chain);
-
-	spin_unlock(&hb->chain_lock);
-
-	return qp;
-}
-
 static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 					       struct inet_frags *f,
 					       void *arg)
 {
 	struct inet_frag_queue *q;
 
-	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
-		inet_frag_schedule_worker(f);
+	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
 		return NULL;
-	}
 
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
 	if (!q)
@@ -374,59 +170,52 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 
 	timer_setup(&q->timer, f->frag_expire, 0);
 	spin_lock_init(&q->lock);
-	refcount_set(&q->refcnt, 1);
+	refcount_set(&q->refcnt, 3);
 
 	return q;
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						struct inet_frags *f,
 						void *arg)
 {
+	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
+	int err;
 
 	q = inet_frag_alloc(nf, f, arg);
 	if (!q)
 		return NULL;
 
-	return inet_frag_intern(nf, q, f, arg);
+	mod_timer(&q->timer, jiffies + nf->timeout);
+
+	err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
+				     f->rhash_params);
+	if (err < 0) {
+		q->flags |= INET_FRAG_COMPLETE;
+		inet_frag_kill(q);
+		inet_frag_destroy(q);
+		return NULL;
+	}
+	return q;
 }
 
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
-				       struct inet_frags *f, void *key,
-				       unsigned int hash)
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
-	struct inet_frag_bucket *hb;
-	struct inet_frag_queue *q;
-	int depth = 0;
-
-	if (frag_mem_limit(nf) > nf->low_thresh)
-		inet_frag_schedule_worker(f);
-
-	hash &= (INETFRAGS_HASHSZ - 1);
-	hb = &f->hash[hash];
-
-	spin_lock(&hb->chain_lock);
-	hlist_for_each_entry(q, &hb->chain, list) {
-		if (q->net == nf && f->match(q, key)) {
-			refcount_inc(&q->refcnt);
-			spin_unlock(&hb->chain_lock);
-			return q;
-		}
-		depth++;
-	}
-	spin_unlock(&hb->chain_lock);
+	struct inet_frag_queue *fq;
 
-	if (depth <= INETFRAGS_MAXDEPTH)
-		return inet_frag_create(nf, f, key);
+	rcu_read_lock();
 
-	if (inet_frag_may_rebuild(f)) {
-		if (!f->rebuild)
-			f->rebuild = true;
-		inet_frag_schedule_worker(f);
+	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+	if (fq) {
+		if (!refcount_inc_not_zero(&fq->refcnt))
+			fq = NULL;
+		rcu_read_unlock();
+		return fq;
 	}
+	rcu_read_unlock();
 
-	return ERR_PTR(-ENOBUFS);
+	return inet_frag_create(nf, key);
 }
 EXPORT_SYMBOL(inet_frag_find);
 
@@ -434,8 +223,7 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
 				   const char *prefix)
 {
 	static const char msg[] = "inet_frag_find: Fragment hash bucket"
-		" list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
-		". Dropping fragment.\n";
+		" list length grew over limit. Dropping fragment.\n";
 
 	if (PTR_ERR(q) == -ENOBUFS)
 		net_dbg_ratelimited("%s%s", prefix, msg);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1a3bc85d6f5e..4021820db6f2 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -69,15 +69,9 @@ struct ipfrag_skb_cb
 struct ipq {
 	struct inet_frag_queue q;
 
-	u32		user;
-	__be32		saddr;
-	__be32		daddr;
-	__be16		id;
-	u8		protocol;
 	u8		ecn; /* RFC3168 support */
 	u16		max_df_size; /* largest frag with DF set seen */
 	int             iif;
-	int             vif;   /* L3 master device index */
 	unsigned int    rid;
 	struct inet_peer *peer;
 };
@@ -97,41 +91,6 @@ int ip_frag_mem(struct net *net)
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 			 struct net_device *dev);
 
-struct ip4_create_arg {
-	struct iphdr *iph;
-	u32 user;
-	int vif;
-};
-
-static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
-{
-	net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
-	return jhash_3words((__force u32)id << 16 | prot,
-			    (__force u32)saddr, (__force u32)daddr,
-			    ip4_frags.rnd);
-}
-
-static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
-{
-	const struct ipq *ipq;
-
-	ipq = container_of(q, struct ipq, q);
-	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
-}
-
-static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct ipq *qp;
-	const struct ip4_create_arg *arg = a;
-
-	qp = container_of(q, struct ipq, q);
-	return	qp->id == arg->iph->id &&
-		qp->saddr == arg->iph->saddr &&
-		qp->daddr == arg->iph->daddr &&
-		qp->protocol == arg->iph->protocol &&
-		qp->user == arg->user &&
-		qp->vif == arg->vif;
-}
 
 static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 {
@@ -140,17 +99,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 					       frags);
 	struct net *net = container_of(ipv4, struct net, ipv4);
 
-	const struct ip4_create_arg *arg = a;
+	const struct frag_v4_compare_key *key = a;
 
-	qp->protocol = arg->iph->protocol;
-	qp->id = arg->iph->id;
-	qp->ecn = ip4_frag_ecn(arg->iph->tos);
-	qp->saddr = arg->iph->saddr;
-	qp->daddr = arg->iph->daddr;
-	qp->vif = arg->vif;
-	qp->user = arg->user;
+	q->key.v4 = *key;
+	qp->ecn = 0;
 	qp->peer = q->net->max_dist ?
-		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+		inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
 		NULL;
 }
 
@@ -234,7 +188,7 @@ static void ip_expire(struct timer_list *t)
 		/* Only an end host needs to send an ICMP
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
-		if (frag_expire_skip_icmp(qp->user) &&
+		if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
 		    (skb_rtable(head)->rt_type != RTN_LOCAL))
 			goto out;
 
@@ -262,17 +216,17 @@ out_rcu_unlock:
 static struct ipq *ip_find(struct net *net, struct iphdr *iph,
 			   u32 user, int vif)
 {
+	struct frag_v4_compare_key key = {
+		.saddr = iph->saddr,
+		.daddr = iph->daddr,
+		.user = user,
+		.vif = vif,
+		.id = iph->id,
+		.protocol = iph->protocol,
+	};
 	struct inet_frag_queue *q;
-	struct ip4_create_arg arg;
-	unsigned int hash;
-
-	arg.iph = iph;
-	arg.user = user;
-	arg.vif = vif;
 
-	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
-
-	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
+	q = inet_frag_find(&net->ipv4.frags, &key);
 	if (IS_ERR_OR_NULL(q)) {
 		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
@@ -656,7 +610,7 @@ out_nomem:
 	err = -ENOMEM;
 	goto out_fail;
 out_oversize:
-	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
+	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
 out_fail:
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	return err;
@@ -894,15 +848,47 @@ static struct pernet_operations ip4_frags_ops = {
 	.exit = ipv4_frags_exit_net,
 };
 
+
+static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v4,
+		      sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v4_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params ip4_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.key_offset		= offsetof(struct inet_frag_queue, key),
+	.key_len		= sizeof(struct frag_v4_compare_key),
+	.hashfn			= ip4_key_hashfn,
+	.obj_hashfn		= ip4_obj_hashfn,
+	.obj_cmpfn		= ip4_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+
 void __init ipfrag_init(void)
 {
-	ip4_frags.hashfn = ip4_hashfn;
 	ip4_frags.constructor = ip4_frag_init;
 	ip4_frags.destructor = ip4_frag_free;
 	ip4_frags.qsize = sizeof(struct ipq);
-	ip4_frags.match = ip4_frag_match;
 	ip4_frags.frag_expire = ip_expire;
 	ip4_frags.frags_cache_name = ip_frag_cache_name;
+	ip4_frags.rhash_params = ip4_rhash_params;
 	if (inet_frags_init(&ip4_frags))
 		panic("IP: failed to allocate ip4_frags cache\n");
 	ip4_frags_ctl_register();
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c4b40fdee838..0ad3df551d98 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -152,23 +152,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
 }
 
-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
-				 const struct in6_addr *daddr)
-{
-	net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
-	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			    (__force u32)id, nf_frags.rnd);
-}
-
-
-static unsigned int nf_hashfn(const struct inet_frag_queue *q)
-{
-	const struct frag_queue *nq;
-
-	nq = container_of(q, struct frag_queue, q);
-	return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
-}
-
 static void nf_ct_frag6_expire(struct timer_list *t)
 {
 	struct inet_frag_queue *frag = from_timer(frag, t, timer);
@@ -182,26 +165,19 @@ static void nf_ct_frag6_expire(struct timer_list *t)
 }
 
 /* Creation primitives. */
-static inline struct frag_queue *fq_find(struct net *net, __be32 id,
-					 u32 user, struct in6_addr *src,
-					 struct in6_addr *dst, int iif, u8 ecn)
+static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
+				  const struct ipv6hdr *hdr, int iif)
 {
+	struct frag_v6_compare_key key = {
+		.id = id,
+		.saddr = hdr->saddr,
+		.daddr = hdr->daddr,
+		.user = user,
+		.iif = iif,
+	};
 	struct inet_frag_queue *q;
-	struct ip6_create_arg arg;
-	unsigned int hash;
-
-	arg.id = id;
-	arg.user = user;
-	arg.src = src;
-	arg.dst = dst;
-	arg.iif = iif;
-	arg.ecn = ecn;
-
-	local_bh_disable();
-	hash = nf_hash_frag(id, src, dst);
 
-	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
-	local_bh_enable();
+	q = inet_frag_find(&net->nf_frag.frags, &key);
 	if (IS_ERR_OR_NULL(q)) {
 		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
@@ -593,8 +569,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
 	skb_orphan(skb);
-	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
-		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+	fq = fq_find(net, fhdr->identification, user, hdr,
+		     skb->dev ? skb->dev->ifindex : 0);
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		return -ENOMEM;
@@ -660,13 +636,12 @@ int nf_ct_frag6_init(void)
 {
 	int ret = 0;
 
-	nf_frags.hashfn = nf_hashfn;
 	nf_frags.constructor = ip6_frag_init;
 	nf_frags.destructor = NULL;
 	nf_frags.qsize = sizeof(struct frag_queue);
-	nf_frags.match = ip6_frag_match;
 	nf_frags.frag_expire = nf_ct_frag6_expire;
 	nf_frags.frags_cache_name = nf_frags_cache_name;
+	nf_frags.rhash_params = ip6_rhash_params;
 	ret = inet_frags_init(&nf_frags);
 	if (ret)
 		goto out;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index f0071b113a92..3fc853e4492a 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -79,52 +79,13 @@ static struct inet_frags ip6_frags;
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 			  struct net_device *dev);
 
-/*
- * callers should be careful not to use the hash value outside the ipfrag_lock
- * as doing so could race with ipfrag_hash_rnd being recalculated.
- */
-static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
-				    const struct in6_addr *daddr)
-{
-	net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
-	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			    (__force u32)id, ip6_frags.rnd);
-}
-
-static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
-{
-	const struct frag_queue *fq;
-
-	fq = container_of(q, struct frag_queue, q);
-	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
-}
-
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct frag_queue *fq;
-	const struct ip6_create_arg *arg = a;
-
-	fq = container_of(q, struct frag_queue, q);
-	return	fq->id == arg->id &&
-		fq->user == arg->user &&
-		ipv6_addr_equal(&fq->saddr, arg->src) &&
-		ipv6_addr_equal(&fq->daddr, arg->dst) &&
-		(arg->iif == fq->iif ||
-		 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
-					       IPV6_ADDR_LINKLOCAL)));
-}
-EXPORT_SYMBOL(ip6_frag_match);
-
 void ip6_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	struct frag_queue *fq = container_of(q, struct frag_queue, q);
-	const struct ip6_create_arg *arg = a;
+	const struct frag_v6_compare_key *key = a;
 
-	fq->id = arg->id;
-	fq->user = arg->user;
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
-	fq->ecn = arg->ecn;
+	q->key.v6 = *key;
+	fq->ecn = 0;
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
@@ -182,23 +143,22 @@ static void ip6_frag_expire(struct timer_list *t)
 }
 
 static struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-	const struct in6_addr *dst, int iif, u8 ecn)
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
 {
+	struct frag_v6_compare_key key = {
+		.id = id,
+		.saddr = hdr->saddr,
+		.daddr = hdr->daddr,
+		.user = IP6_DEFRAG_LOCAL_DELIVER,
+		.iif = iif,
+	};
 	struct inet_frag_queue *q;
-	struct ip6_create_arg arg;
-	unsigned int hash;
-
-	arg.id = id;
-	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
-	arg.src = src;
-	arg.dst = dst;
-	arg.iif = iif;
-	arg.ecn = ecn;
 
-	hash = inet6_hash_frag(id, src, dst);
+	if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+					    IPV6_ADDR_LINKLOCAL)))
+		key.iif = 0;
 
-	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+	q = inet_frag_find(&net->ipv6.frags, &key);
 	if (IS_ERR_OR_NULL(q)) {
 		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
@@ -530,6 +490,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
+	int iif;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
 		goto fail_hdr;
@@ -558,13 +519,14 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
-	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+	iif = skb->dev ? skb->dev->ifindex : 0;
+	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
 		int ret;
 
 		spin_lock(&fq->q.lock);
 
+		fq->iif = iif;
 		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
 
 		spin_unlock(&fq->q.lock);
@@ -738,17 +700,47 @@ static struct pernet_operations ip6_frags_ops = {
 	.exit = ipv6_frags_exit_net,
 };
 
+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v6,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v6_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params ip6_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= ip6_key_hashfn,
+	.obj_hashfn		= ip6_obj_hashfn,
+	.obj_cmpfn		= ip6_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+EXPORT_SYMBOL(ip6_rhash_params);
+
 int __init ipv6_frag_init(void)
 {
 	int ret;
 
-	ip6_frags.hashfn = ip6_hashfn;
 	ip6_frags.constructor = ip6_frag_init;
 	ip6_frags.destructor = NULL;
 	ip6_frags.qsize = sizeof(struct frag_queue);
-	ip6_frags.match = ip6_frag_match;
 	ip6_frags.frag_expire = ip6_frag_expire;
 	ip6_frags.frags_cache_name = ip6_frag_cache_name;
+	ip6_frags.rhash_params = ip6_rhash_params;
 	ret = inet_frags_init(&ip6_frags);
 	if (ret)
 		goto out;
-- 
cgit v1.2.3


From 6befe4a78b1553edb6eed3a78b4bcd9748526672 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:50 -0700
Subject: inet: frags: remove some helpers

Remove sum_frag_mem_limit(), ip_frag_mem() & ip6_frag_mem()

Also since we use rhashtable we can bring back the number of fragments
in "grep FRAG /proc/net/sockstat /proc/net/sockstat6" that was
removed in commit 434d305405ab ("inet: frag: don't account number
of fragment queues")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h | 5 -----
 include/net/ip.h        | 1 -
 include/net/ipv6.h      | 7 -------
 net/ipv4/ip_fragment.c  | 5 -----
 net/ipv4/proc.c         | 6 +++---
 net/ipv6/proc.c         | 5 +++--
 6 files changed, 6 insertions(+), 23 deletions(-)

(limited to 'include/net')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 3fec0d3a0d01..4b5449df0aad 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -141,11 +141,6 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 	atomic_add(i, &nf->mem);
 }
 
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
-{
-	return atomic_read(&nf->mem);
-}
-
 /* RFC 3168 support :
  * We want to check ECN values of all fragments, do detect invalid combinations.
  * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
diff --git a/include/net/ip.h b/include/net/ip.h
index 36f8f7811093..ecffd843e7b8 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -588,7 +588,6 @@ static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *s
 	return skb;
 }
 #endif
-int ip_frag_mem(struct net *net);
 
 /*
  *	Functions provided by ip_forward.c
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6fa9a2bc5896..37455e840347 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -379,13 +379,6 @@ static inline bool ipv6_accept_ra(struct inet6_dev *idev)
 	    idev->cnf.accept_ra;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int ip6_frag_mem(struct net *net)
-{
-	return sum_frag_mem_limit(&net->ipv6.frags);
-}
-#endif
-
 #define IPV6_FRAG_HIGH_THRESH	(4 * 1024*1024)	/* 4194304 */
 #define IPV6_FRAG_LOW_THRESH	(3 * 1024*1024)	/* 3145728 */
 #define IPV6_FRAG_TIMEOUT	(60 * HZ)	/* 60 seconds */
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 4021820db6f2..44f4fa306e22 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -83,11 +83,6 @@ static u8 ip4_frag_ecn(u8 tos)
 
 static struct inet_frags ip4_frags;
 
-int ip_frag_mem(struct net *net)
-{
-	return sum_frag_mem_limit(&net->ipv4.frags);
-}
-
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 			 struct net_device *dev);
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index adfb75340275..aacfce0d7d82 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,6 @@
 static int sockstat_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
-	unsigned int frag_mem;
 	int orphans, sockets;
 
 	orphans = percpu_counter_sum_positive(&tcp_orphan_count);
@@ -72,8 +71,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
 		   sock_prot_inuse_get(net, &raw_prot));
-	frag_mem = ip_frag_mem(net);
-	seq_printf(seq,  "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
+	seq_printf(seq,  "FRAG: inuse %u memory %u\n",
+		   atomic_read(&net->ipv4.frags.rhashtable.nelems),
+		   frag_mem_limit(&net->ipv4.frags));
 	return 0;
 }
 
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 6e57028d2e91..8befeb91e071 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -38,7 +38,6 @@
 static int sockstat6_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
-	unsigned int frag_mem = ip6_frag_mem(net);
 
 	seq_printf(seq, "TCP6: inuse %d\n",
 		       sock_prot_inuse_get(net, &tcpv6_prot));
@@ -48,7 +47,9 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
 			sock_prot_inuse_get(net, &udplitev6_prot));
 	seq_printf(seq, "RAW6: inuse %d\n",
 		       sock_prot_inuse_get(net, &rawv6_prot));
-	seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem);
+	seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+		   atomic_read(&net->ipv6.frags.rhashtable.nelems),
+		   frag_mem_limit(&net->ipv6.frags));
 	return 0;
 }
 
-- 
cgit v1.2.3


From 399d1404be660d355192ff4df5ccc3f4159ec1e4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:51 -0700
Subject: inet: frags: get rif of inet_frag_evicting()

This refactors ip_expire() since one indentation level is removed.

Note: in the future, we should try hard to avoid the skb_clone()
since this is a serious performance cost.
Under DDOS, the ICMP message wont be sent because of rate limits.

Fact that ip6_expire_frag_queue() does not use skb_clone() is
disturbing too. Presumably IPv6 should have the same
issue than the one we fixed in commit ec4fbd64751d
("inet: frag: release spinlock before calling icmp_send()")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h |  5 ----
 net/ipv4/ip_fragment.c  | 65 ++++++++++++++++++++++++-------------------------
 net/ipv6/reassembly.c   |  4 ---
 3 files changed, 32 insertions(+), 42 deletions(-)

(limited to 'include/net')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 4b5449df0aad..0e8e159d88f7 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -119,11 +119,6 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
 		inet_frag_destroy(q);
 }
 
-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
-	return false;
-}
-
 /* Memory Tracking Functions. */
 
 static inline int frag_mem_limit(struct netns_frags *nf)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 44f4fa306e22..b844f517b75b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -143,8 +143,11 @@ static bool frag_expire_skip_icmp(u32 user)
 static void ip_expire(struct timer_list *t)
 {
 	struct inet_frag_queue *frag = from_timer(frag, t, timer);
-	struct ipq *qp;
+	struct sk_buff *clone, *head;
+	const struct iphdr *iph;
 	struct net *net;
+	struct ipq *qp;
+	int err;
 
 	qp = container_of(frag, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -158,45 +161,41 @@ static void ip_expire(struct timer_list *t)
 	ipq_kill(qp);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 
-	if (!inet_frag_evicting(&qp->q)) {
-		struct sk_buff *clone, *head = qp->q.fragments;
-		const struct iphdr *iph;
-		int err;
+	head = qp->q.fragments;
 
-		__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
+	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
-		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
-			goto out;
+	if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
+		goto out;
 
-		head->dev = dev_get_by_index_rcu(net, qp->iif);
-		if (!head->dev)
-			goto out;
+	head->dev = dev_get_by_index_rcu(net, qp->iif);
+	if (!head->dev)
+		goto out;
 
 
-		/* skb has no dst, perform route lookup again */
-		iph = ip_hdr(head);
-		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+	/* skb has no dst, perform route lookup again */
+	iph = ip_hdr(head);
+	err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
-		if (err)
-			goto out;
+	if (err)
+		goto out;
 
-		/* Only an end host needs to send an ICMP
-		 * "Fragment Reassembly Timeout" message, per RFC792.
-		 */
-		if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
-		    (skb_rtable(head)->rt_type != RTN_LOCAL))
-			goto out;
-
-		clone = skb_clone(head, GFP_ATOMIC);
-
-		/* Send an ICMP "Fragment Reassembly Timeout" message. */
-		if (clone) {
-			spin_unlock(&qp->q.lock);
-			icmp_send(clone, ICMP_TIME_EXCEEDED,
-				  ICMP_EXC_FRAGTIME, 0);
-			consume_skb(clone);
-			goto out_rcu_unlock;
-		}
+	/* Only an end host needs to send an ICMP
+	 * "Fragment Reassembly Timeout" message, per RFC792.
+	 */
+	if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
+	    (skb_rtable(head)->rt_type != RTN_LOCAL))
+		goto out;
+
+	clone = skb_clone(head, GFP_ATOMIC);
+
+	/* Send an ICMP "Fragment Reassembly Timeout" message. */
+	if (clone) {
+		spin_unlock(&qp->q.lock);
+		icmp_send(clone, ICMP_TIME_EXCEEDED,
+			  ICMP_EXC_FRAGTIME, 0);
+		consume_skb(clone);
+		goto out_rcu_unlock;
 	}
 out:
 	spin_unlock(&qp->q.lock);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3fc853e4492a..70acad126d04 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -106,10 +106,6 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
 		goto out_rcu_unlock;
 
 	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
-	if (inet_frag_evicting(&fq->q))
-		goto out_rcu_unlock;
-
 	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
 
 	/* Don't send error if the first segment did not arrive. */
-- 
cgit v1.2.3


From 2d44ed22e607f9a285b049de2263e3840673a260 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:52 -0700
Subject: inet: frags: remove inet_frag_maybe_warn_overflow()

This function is obsolete, after rhashtable addition to inet defrag.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 |  2 --
 net/ieee802154/6lowpan/reassembly.c     |  5 ++---
 net/ipv4/inet_fragment.c                | 11 -----------
 net/ipv4/ip_fragment.c                  |  5 ++---
 net/ipv6/netfilter/nf_conntrack_reasm.c |  5 ++---
 net/ipv6/reassembly.c                   |  5 ++---
 6 files changed, 8 insertions(+), 25 deletions(-)

(limited to 'include/net')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 0e8e159d88f7..95e353e3305b 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -110,8 +110,6 @@ void inet_frags_exit_net(struct netns_frags *nf);
 void inet_frag_kill(struct inet_frag_queue *q);
 void inet_frag_destroy(struct inet_frag_queue *q);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
-				   const char *prefix);
 
 static inline void inet_frag_put(struct inet_frag_queue *q)
 {
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 0fa0121f85d4..1aec71a3f904 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -84,10 +84,9 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
 	struct inet_frag_queue *q;
 
 	q = inet_frag_find(&ieee802154_lowpan->frags, &key);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct lowpan_frag_queue, q);
 }
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index ebb8f411e0db..c9e35b81d093 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -218,14 +218,3 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 	return inet_frag_create(nf, key);
 }
 EXPORT_SYMBOL(inet_frag_find);
-
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
-				   const char *prefix)
-{
-	static const char msg[] = "inet_frag_find: Fragment hash bucket"
-		" list length grew over limit. Dropping fragment.\n";
-
-	if (PTR_ERR(q) == -ENOBUFS)
-		net_dbg_ratelimited("%s%s", prefix, msg);
-}
-EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b844f517b75b..b0366224f314 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -221,10 +221,9 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph,
 	struct inet_frag_queue *q;
 
 	q = inet_frag_find(&net->ipv4.frags, &key);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct ipq, q);
 }
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 0ad3df551d98..d866412b8f6c 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -178,10 +178,9 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
 	struct inet_frag_queue *q;
 
 	q = inet_frag_find(&net->nf_frag.frags, &key);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct frag_queue, q);
 }
 
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 70acad126d04..2a77fda5e3bc 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -155,10 +155,9 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
 		key.iif = 0;
 
 	q = inet_frag_find(&net->ipv6.frags, &key);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct frag_queue, q);
 }
 
-- 
cgit v1.2.3


From 3e67f106f619dcfaf6f4e2039599bdb69848c714 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:53 -0700
Subject: inet: frags: break the 2GB limit for frags storage

Some users are willing to provision huge amounts of memory to be able
to perform reassembly reasonnably well under pressure.

Current memory tracking is using one atomic_t and integers.

Switch to atomic_long_t so that 64bit arches can use more than 2GB,
without any cost for 32bit arches.

Note that this patch avoids an overflow error, if high_thresh was set
to ~2GB, since this test in inet_frag_alloc() was never true :

if (... || frag_mem_limit(nf) > nf->high_thresh)

Tested:

$ echo 16000000000 >/proc/sys/net/ipv4/ipfrag_high_thresh

<frag DDOS>

$ grep FRAG /proc/net/sockstat
FRAG: inuse 14705885 memory 16000002880

$ nstat -n ; sleep 1 ; nstat | grep Reas
IpReasmReqds                    3317150            0.0
IpReasmFails                    3317112            0.0

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt  |  4 ++--
 include/net/inet_frag.h                 | 20 ++++++++++----------
 net/ieee802154/6lowpan/reassembly.c     | 10 +++++-----
 net/ipv4/ip_fragment.c                  | 10 +++++-----
 net/ipv4/proc.c                         |  2 +-
 net/ipv6/netfilter/nf_conntrack_reasm.c | 10 +++++-----
 net/ipv6/proc.c                         |  2 +-
 net/ipv6/reassembly.c                   |  6 +++---
 8 files changed, 32 insertions(+), 32 deletions(-)

(limited to 'include/net')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6f2a3670e44b..5dc1a040a2f1 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -133,10 +133,10 @@ min_adv_mss - INTEGER
 
 IP Fragmentation:
 
-ipfrag_high_thresh - INTEGER
+ipfrag_high_thresh - LONG INTEGER
 	Maximum memory used to reassemble IP fragments.
 
-ipfrag_low_thresh - INTEGER
+ipfrag_low_thresh - LONG INTEGER
 	(Obsolete since linux-4.17)
 	Maximum memory used to reassemble IP fragments before the kernel
 	begins to remove incomplete fragment queues to free up resources.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 95e353e3305b..a52e7273e7a5 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -8,11 +8,11 @@ struct netns_frags {
 	struct rhashtable       rhashtable ____cacheline_aligned_in_smp;
 
 	/* Keep atomic mem on separate cachelines in structs that include it */
-	atomic_t		mem ____cacheline_aligned_in_smp;
+	atomic_long_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
+	long			high_thresh;
+	long			low_thresh;
 	int			timeout;
-	int			high_thresh;
-	int			low_thresh;
 	int			max_dist;
 	struct inet_frags	*f;
 };
@@ -102,7 +102,7 @@ void inet_frags_fini(struct inet_frags *);
 
 static inline int inet_frags_init_net(struct netns_frags *nf)
 {
-	atomic_set(&nf->mem, 0);
+	atomic_long_set(&nf->mem, 0);
 	return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
 }
 void inet_frags_exit_net(struct netns_frags *nf);
@@ -119,19 +119,19 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
 
 /* Memory Tracking Functions. */
 
-static inline int frag_mem_limit(struct netns_frags *nf)
+static inline long frag_mem_limit(const struct netns_frags *nf)
 {
-	return atomic_read(&nf->mem);
+	return atomic_long_read(&nf->mem);
 }
 
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	atomic_sub(i, &nf->mem);
+	atomic_long_sub(val, &nf->mem);
 }
 
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	atomic_add(i, &nf->mem);
+	atomic_long_add(val, &nf->mem);
 }
 
 /* RFC 3168 support :
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 1aec71a3f904..44f148a6bb57 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -411,23 +411,23 @@ err:
 }
 
 #ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
 
 static struct ctl_table lowpan_frags_ns_ctl_table[] = {
 	{
 		.procname	= "6lowpanfrag_high_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ieee802154_lowpan.frags.low_thresh
 	},
 	{
 		.procname	= "6lowpanfrag_low_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &init_net.ieee802154_lowpan.frags.high_thresh
 	},
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b0366224f314..053869f2c49b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -678,23 +678,23 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 EXPORT_SYMBOL(ip_check_defrag);
 
 #ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
 
 static struct ctl_table ip4_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ipfrag_high_thresh",
 		.data		= &init_net.ipv4.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ipv4.frags.low_thresh
 	},
 	{
 		.procname	= "ipfrag_low_thresh",
 		.data		= &init_net.ipv4.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &init_net.ipv4.frags.high_thresh
 	},
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index aacfce0d7d82..a058de677e94 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -71,7 +71,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
 		   sock_prot_inuse_get(net, &raw_prot));
-	seq_printf(seq,  "FRAG: inuse %u memory %u\n",
+	seq_printf(seq,  "FRAG: inuse %u memory %lu\n",
 		   atomic_read(&net->ipv4.frags.rhashtable.nelems),
 		   frag_mem_limit(&net->ipv4.frags));
 	return 0;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index d866412b8f6c..603a39592859 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -63,7 +63,7 @@ struct nf_ct_frag6_skb_cb
 static struct inet_frags nf_frags;
 
 #ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
 
 static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
@@ -76,18 +76,18 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_frag6_low_thresh",
 		.data		= &init_net.nf_frag.frags.low_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &init_net.nf_frag.frags.high_thresh
 	},
 	{
 		.procname	= "nf_conntrack_frag6_high_thresh",
 		.data		= &init_net.nf_frag.frags.high_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.nf_frag.frags.low_thresh
 	},
 	{ }
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 8befeb91e071..a85f7e0b14b1 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -47,7 +47,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
 			sock_prot_inuse_get(net, &udplitev6_prot));
 	seq_printf(seq, "RAW6: inuse %d\n",
 		       sock_prot_inuse_get(net, &rawv6_prot));
-	seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+	seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
 		   atomic_read(&net->ipv6.frags.rhashtable.nelems),
 		   frag_mem_limit(&net->ipv6.frags));
 	return 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2a77fda5e3bc..905a8aee2671 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -552,15 +552,15 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ip6frag_high_thresh",
 		.data		= &init_net.ipv6.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ipv6.frags.low_thresh
 	},
 	{
 		.procname	= "ip6frag_low_thresh",
 		.data		= &init_net.ipv6.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
-- 
cgit v1.2.3


From c2615cf5a761b32bf74e85bddc223dfff3d9b9f0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:57 -0700
Subject: inet: frags: reorganize struct netns_frags

Put the read-mostly fields in a separate cache line
at the beginning of struct netns_frags, to reduce
false sharing noticed in inet_frag_kill()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/net')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index a52e7273e7a5..ed07e3786d98 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -5,16 +5,17 @@
 #include <linux/rhashtable.h>
 
 struct netns_frags {
-	struct rhashtable       rhashtable ____cacheline_aligned_in_smp;
-
-	/* Keep atomic mem on separate cachelines in structs that include it */
-	atomic_long_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
 	long			high_thresh;
 	long			low_thresh;
 	int			timeout;
 	int			max_dist;
 	struct inet_frags	*f;
+
+	struct rhashtable       rhashtable ____cacheline_aligned_in_smp;
+
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_long_t		mem ____cacheline_aligned_in_smp;
 };
 
 /**
-- 
cgit v1.2.3


From dd0bed1665d6ca17efd747a90a0bb804b4bf2005 Mon Sep 17 00:00:00 2001
From: Atul Gupta <atul.gupta@chelsio.com>
Date: Sat, 31 Mar 2018 21:41:52 +0530
Subject: tls: support for Inline tls record

Facility to register Inline TLS drivers to net/tls. Setup
TLS_HW_RECORD prot to listen on offload device.

Cases handled
- Inline TLS device exists, setup prot for TLS_HW_RECORD
- Atleast one Inline TLS exists, sets TLS_HW_RECORD.
- If non-inline device establish connection, move to TLS_SW_TX

Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  |  32 ++++++++++++++-
 net/tls/tls_main.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 142 insertions(+), 4 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tls.h b/include/net/tls.h
index 437a746300bf..3da8e13a6d96 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -56,6 +56,32 @@
 #define TLS_RECORD_TYPE_DATA		0x17
 
 #define TLS_AAD_SPACE_SIZE		13
+#define TLS_DEVICE_NAME_MAX		32
+
+/*
+ * This structure defines the routines for Inline TLS driver.
+ * The following routines are optional and filled with a
+ * null pointer if not defined.
+ *
+ * @name: Its the name of registered Inline tls device
+ * @dev_list: Inline tls device list
+ * int (*feature)(struct tls_device *device);
+ *     Called to return Inline TLS driver capability
+ *
+ * int (*hash)(struct tls_device *device, struct sock *sk);
+ *     This function sets Inline driver for listen and program
+ *     device specific functioanlity as required
+ *
+ * void (*unhash)(struct tls_device *device, struct sock *sk);
+ *     This function cleans listen state set by Inline TLS driver
+ */
+struct tls_device {
+	char name[TLS_DEVICE_NAME_MAX];
+	struct list_head dev_list;
+	int  (*feature)(struct tls_device *device);
+	int  (*hash)(struct tls_device *device, struct sock *sk);
+	void (*unhash)(struct tls_device *device, struct sock *sk);
+};
 
 struct tls_sw_context {
 	struct crypto_aead *aead_send;
@@ -114,7 +140,7 @@ struct tls_context {
 
 	void *priv_ctx;
 
-	u8 conf:2;
+	u8 conf:3;
 
 	struct cipher_context tx;
 	struct cipher_context rx;
@@ -135,6 +161,8 @@ struct tls_context {
 	int  (*getsockopt)(struct sock *sk, int level,
 			   int optname, char __user *optval,
 			   int __user *optlen);
+	int  (*hash)(struct sock *sk);
+	void (*unhash)(struct sock *sk);
 };
 
 int wait_on_pending_writer(struct sock *sk, long *timeo);
@@ -283,5 +311,7 @@ static inline struct tls_offload_context *tls_offload_ctx(
 
 int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
 		      unsigned char *record_type);
+void tls_register_device(struct tls_device *device);
+void tls_unregister_device(struct tls_device *device);
 
 #endif /* _TLS_OFFLOAD_H */
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 6f5c1146da4a..0d379970960e 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -38,6 +38,7 @@
 #include <linux/highmem.h>
 #include <linux/netdevice.h>
 #include <linux/sched/signal.h>
+#include <linux/inetdevice.h>
 
 #include <net/tls.h>
 
@@ -56,11 +57,14 @@ enum {
 	TLS_SW_TX,
 	TLS_SW_RX,
 	TLS_SW_RXTX,
+	TLS_HW_RECORD,
 	TLS_NUM_CONFIG,
 };
 
 static struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
+static LIST_HEAD(device_list);
+static DEFINE_MUTEX(device_mutex);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG];
 static struct proto_ops tls_sw_proto_ops;
 
@@ -241,8 +245,12 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	lock_sock(sk);
 	sk_proto_close = ctx->sk_proto_close;
 
+	if (ctx->conf == TLS_HW_RECORD)
+		goto skip_tx_cleanup;
+
 	if (ctx->conf == TLS_BASE) {
 		kfree(ctx);
+		ctx = NULL;
 		goto skip_tx_cleanup;
 	}
 
@@ -276,6 +284,11 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 skip_tx_cleanup:
 	release_sock(sk);
 	sk_proto_close(sk, timeout);
+	/* free ctx for TLS_HW_RECORD, used by tcp_set_state
+	 * for sk->sk_prot->unhash [tls_hw_unhash]
+	 */
+	if (ctx && ctx->conf == TLS_HW_RECORD)
+		kfree(ctx);
 }
 
 static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
@@ -493,6 +506,79 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
 	return do_tls_setsockopt(sk, optname, optval, optlen);
 }
 
+static struct tls_context *create_ctx(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tls_context *ctx;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return NULL;
+
+	icsk->icsk_ulp_data = ctx;
+	return ctx;
+}
+
+static int tls_hw_prot(struct sock *sk)
+{
+	struct tls_context *ctx;
+	struct tls_device *dev;
+	int rc = 0;
+
+	mutex_lock(&device_mutex);
+	list_for_each_entry(dev, &device_list, dev_list) {
+		if (dev->feature && dev->feature(dev)) {
+			ctx = create_ctx(sk);
+			if (!ctx)
+				goto out;
+
+			ctx->hash = sk->sk_prot->hash;
+			ctx->unhash = sk->sk_prot->unhash;
+			ctx->sk_proto_close = sk->sk_prot->close;
+			ctx->conf = TLS_HW_RECORD;
+			update_sk_prot(sk, ctx);
+			rc = 1;
+			break;
+		}
+	}
+out:
+	mutex_unlock(&device_mutex);
+	return rc;
+}
+
+static void tls_hw_unhash(struct sock *sk)
+{
+	struct tls_context *ctx = tls_get_ctx(sk);
+	struct tls_device *dev;
+
+	mutex_lock(&device_mutex);
+	list_for_each_entry(dev, &device_list, dev_list) {
+		if (dev->unhash)
+			dev->unhash(dev, sk);
+	}
+	mutex_unlock(&device_mutex);
+	ctx->unhash(sk);
+}
+
+static int tls_hw_hash(struct sock *sk)
+{
+	struct tls_context *ctx = tls_get_ctx(sk);
+	struct tls_device *dev;
+	int err;
+
+	err = ctx->hash(sk);
+	mutex_lock(&device_mutex);
+	list_for_each_entry(dev, &device_list, dev_list) {
+		if (dev->hash)
+			err |= dev->hash(dev, sk);
+	}
+	mutex_unlock(&device_mutex);
+
+	if (err)
+		tls_hw_unhash(sk);
+	return err;
+}
+
 static void build_protos(struct proto *prot, struct proto *base)
 {
 	prot[TLS_BASE] = *base;
@@ -511,15 +597,22 @@ static void build_protos(struct proto *prot, struct proto *base)
 	prot[TLS_SW_RXTX] = prot[TLS_SW_TX];
 	prot[TLS_SW_RXTX].recvmsg	= tls_sw_recvmsg;
 	prot[TLS_SW_RXTX].close		= tls_sk_proto_close;
+
+	prot[TLS_HW_RECORD] = *base;
+	prot[TLS_HW_RECORD].hash	= tls_hw_hash;
+	prot[TLS_HW_RECORD].unhash	= tls_hw_unhash;
+	prot[TLS_HW_RECORD].close	= tls_sk_proto_close;
 }
 
 static int tls_init(struct sock *sk)
 {
 	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
-	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tls_context *ctx;
 	int rc = 0;
 
+	if (tls_hw_prot(sk))
+		goto out;
+
 	/* The TLS ulp is currently supported only for TCP sockets
 	 * in ESTABLISHED state.
 	 * Supporting sockets in LISTEN state will require us
@@ -530,12 +623,11 @@ static int tls_init(struct sock *sk)
 		return -ENOTSUPP;
 
 	/* allocate tls context */
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = create_ctx(sk);
 	if (!ctx) {
 		rc = -ENOMEM;
 		goto out;
 	}
-	icsk->icsk_ulp_data = ctx;
 	ctx->setsockopt = sk->sk_prot->setsockopt;
 	ctx->getsockopt = sk->sk_prot->getsockopt;
 	ctx->sk_proto_close = sk->sk_prot->close;
@@ -557,6 +649,22 @@ out:
 	return rc;
 }
 
+void tls_register_device(struct tls_device *device)
+{
+	mutex_lock(&device_mutex);
+	list_add_tail(&device->dev_list, &device_list);
+	mutex_unlock(&device_mutex);
+}
+EXPORT_SYMBOL(tls_register_device);
+
+void tls_unregister_device(struct tls_device *device)
+{
+	mutex_lock(&device_mutex);
+	list_del(&device->dev_list);
+	mutex_unlock(&device_mutex);
+}
+EXPORT_SYMBOL(tls_unregister_device);
+
 static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 	.name			= "tls",
 	.uid			= TCP_ULP_TLS,
-- 
cgit v1.2.3


From 8c59c264e5e17670c0ad2063fa40e3091b549151 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Mon, 26 Feb 2018 12:11:07 +0530
Subject: Bluetooth: Fix data type of appearence

It should be __le16 instead of __u16 since its part of
mgmt API.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/net')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 72a456bbbcd5..e7303eee65cd 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -600,7 +600,7 @@ struct mgmt_rp_read_ext_info {
 
 #define MGMT_OP_SET_APPEARANCE		0x0043
 struct mgmt_cp_set_appearance {
-	__u16	appearance;
+	__le16	appearance;
 } __packed;
 #define MGMT_SET_APPEARANCE_SIZE	2
 
-- 
cgit v1.2.3