From e1bd1dc207dae92cdb5b424226f89d1b4e4bb182 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Thu, 14 Nov 2013 01:05:58 +0000
Subject: net_tstamp: Improve kernel-doc for struct hwtstamp_config

Fix the name of the rx_filter field.

Remove text about 32/64-bit compatibility; this works just the same as
for most socket ioctls and as the structure is not allowed to grow
there is no need to remind anyone how to maintain it.

Add explanation about drivers changing the filter mode.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 include/uapi/linux/net_tstamp.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index ae5df122e42f..c9a7de2a6276 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -30,13 +30,13 @@ enum {
  *
  * @flags:	no flags defined right now, must be zero
  * @tx_type:	one of HWTSTAMP_TX_*
- * @rx_type:	one of one of HWTSTAMP_FILTER_*
+ * @rx_filter:	one of HWTSTAMP_FILTER_*
  *
  * %SIOCSHWTSTAMP expects a &struct ifreq with a ifr_data pointer to
- * this structure. dev_ifsioc() in the kernel takes care of the
- * translation between 32 bit userspace and 64 bit kernel. The
- * structure is intentionally chosen so that it has the same layout on
- * 32 and 64 bit systems, don't break this!
+ * this structure.  If the driver or hardware does not support the
+ * requested @rx_filter value, the driver may use a more general
+ * filter mode.  In this case @rx_filter will indicate the actual mode
+ * on return.
  */
 struct hwtstamp_config {
 	int flags;
-- 
cgit v1.2.3


From fd468c74bd4d6949736810a80d6ca05eb20fba84 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Thu, 14 Nov 2013 01:19:29 +0000
Subject: net_tstamp: Add SIOCGHWTSTAMP ioctl to match SIOCSHWTSTAMP

SIOCSHWTSTAMP returns the real configuration to the application
using it, but there is currently no way for any other
application to find out the configuration non-destructively.
Add a new ioctl for this, making it unprivileged.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 Documentation/networking/timestamping.txt |  9 +++++++--
 include/uapi/linux/net_tstamp.h           | 14 +++++++-------
 include/uapi/linux/sockios.h              |  3 ++-
 net/core/dev_ioctl.c                      |  2 ++
 net/socket.c                              |  1 +
 5 files changed, 19 insertions(+), 10 deletions(-)

(limited to 'include/uapi')

diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 98097d8cb910..661d3c316a17 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -85,7 +85,7 @@ Filled in if SOF_TIMESTAMPING_SYS_HARDWARE is set. Requires support
 by the network device and will be empty without that support.
 
 
-SIOCSHWTSTAMP:
+SIOCSHWTSTAMP, SIOCGHWTSTAMP:
 
 Hardware time stamping must also be initialized for each device driver
 that is expected to do hardware time stamping. The parameter is defined in
@@ -115,6 +115,10 @@ Only a processes with admin rights may change the configuration. User
 space is responsible to ensure that multiple processes don't interfere
 with each other and that the settings are reset.
 
+Any process can read the actual configuration by passing this
+structure to ioctl(SIOCGHWTSTAMP) in the same way.  However, this has
+not been implemented in all drivers.
+
 /* possible values for hwtstamp_config->tx_type */
 enum {
 	/*
@@ -157,7 +161,8 @@ DEVICE IMPLEMENTATION
 
 A driver which supports hardware time stamping must support the
 SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with
-the actual values as described in the section on SIOCSHWTSTAMP.
+the actual values as described in the section on SIOCSHWTSTAMP.  It
+should also support SIOCGHWTSTAMP.
 
 Time stamps for received packets must be stored in the skb. To get a pointer
 to the shared time stamp structure of the skb call skb_hwtstamps(). Then
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index c9a7de2a6276..f53879c0f590 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -26,17 +26,17 @@ enum {
 };
 
 /**
- * struct hwtstamp_config - %SIOCSHWTSTAMP parameter
+ * struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter
  *
- * @flags:	no flags defined right now, must be zero
+ * @flags:	no flags defined right now, must be zero for %SIOCSHWTSTAMP
  * @tx_type:	one of HWTSTAMP_TX_*
  * @rx_filter:	one of HWTSTAMP_FILTER_*
  *
- * %SIOCSHWTSTAMP expects a &struct ifreq with a ifr_data pointer to
- * this structure.  If the driver or hardware does not support the
- * requested @rx_filter value, the driver may use a more general
- * filter mode.  In this case @rx_filter will indicate the actual mode
- * on return.
+ * %SIOCGHWTSTAMP and %SIOCSHWTSTAMP expect a &struct ifreq with a
+ * ifr_data pointer to this structure.  For %SIOCSHWTSTAMP, if the
+ * driver or hardware does not support the requested @rx_filter value,
+ * the driver may use a more general filter mode.  In this case
+ * @rx_filter will indicate the actual mode on return.
  */
 struct hwtstamp_config {
 	int flags;
diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h
index 7997a506ad41..e888b1aed69f 100644
--- a/include/uapi/linux/sockios.h
+++ b/include/uapi/linux/sockios.h
@@ -125,7 +125,8 @@
 #define SIOCBRDELIF	0x89a3		/* remove interface from bridge */
 
 /* hardware time stamping: parameters in linux/net_tstamp.h */
-#define SIOCSHWTSTAMP   0x89b0
+#define SIOCSHWTSTAMP	0x89b0		/* set and get config		*/
+#define SIOCGHWTSTAMP	0x89b1		/* get config			*/
 
 /* Device private ioctl calls */
 
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 5b7d0e1d0664..cf999e09bcd2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -327,6 +327,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		    cmd == SIOCBRADDIF ||
 		    cmd == SIOCBRDELIF ||
 		    cmd == SIOCSHWTSTAMP ||
+		    cmd == SIOCGHWTSTAMP ||
 		    cmd == SIOCWANDEV) {
 			err = -EOPNOTSUPP;
 			if (ops->ndo_do_ioctl) {
@@ -546,6 +547,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	 */
 	default:
 		if (cmd == SIOCWANDEV ||
+		    cmd == SIOCGHWTSTAMP ||
 		    (cmd >= SIOCDEVPRIVATE &&
 		     cmd <= SIOCDEVPRIVATE + 15)) {
 			dev_load(net, ifr.ifr_name);
diff --git a/net/socket.c b/net/socket.c
index 7a766ab83ca5..1a548b70ef3a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3231,6 +3231,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBONDSLAVEINFOQUERY:
 	case SIOCBONDINFOQUERY:
 	case SIOCSHWTSTAMP:
+	case SIOCGHWTSTAMP:
 		return compat_ifr_data_ioctl(net, cmd, argp);
 
 	case FIOSETOWN:
-- 
cgit v1.2.3


From c17bff87bed4bda1835ee41dc908e926414d8d85 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Thu, 31 Oct 2013 14:54:35 +0200
Subject: nl80211: better document NL80211_CMD_TDLS_MGMT

This command has different semantics depending on the action code sent.
Document this fact and detail the supported action codes.

Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f752e9821e71..3d8325bb50cd 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -581,7 +581,14 @@
  *	operation, %NL80211_ATTR_MAC contains the peer MAC address, and
  *	%NL80211_ATTR_REASON_CODE the reason code to be used (only with
  *	%NL80211_TDLS_TEARDOWN).
- * @NL80211_CMD_TDLS_MGMT: Send a TDLS management frame.
+ * @NL80211_CMD_TDLS_MGMT: Send a TDLS management frame. The
+ *	%NL80211_ATTR_TDLS_ACTION attribute determines the type of frame to be
+ *	sent. Public Action codes (802.11-2012 8.1.5.1) will be sent as
+ *	802.11 management frames, while TDLS action codes (802.11-2012
+ *	8.5.13.1) will be encapsulated and sent as data frames. The currently
+ *	supported Public Action code is %WLAN_PUB_ACTION_TDLS_DISCOVER_RES
+ *	and the currently supported TDLS actions codes are given in
+ *	&enum ieee80211_tdls_actioncode.
  *
  * @NL80211_CMD_UNEXPECTED_FRAME: Used by an application controlling an AP
  *	(or GO) interface (i.e. hostapd) to ask for unexpected frames to
-- 
cgit v1.2.3


From 8fe02e167efa8ed4a4503a5eedc0f49fcb7e3eb9 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
Date: Mon, 21 Oct 2013 19:22:25 +0200
Subject: cfg80211: consolidate passive-scan and no-ibss flags

These two flags are used for the same purpose, just
combine them into a no-ir flag to annotate no initiating
radiation is allowed.

Old userspace sending either flag will have it treated as
the no-ir flag. To be considerate to older userspace we
also send both the no-ir flag and the old no-ibss flags.
Newer userspace will have to be aware of older kernels.

Update all places in the tree using these flags with the
following semantic patch:

@@
@@
-NL80211_RRF_PASSIVE_SCAN
+NL80211_RRF_NO_IR
@@
@@
-NL80211_RRF_NO_IBSS
+NL80211_RRF_NO_IR
@@
@@
-IEEE80211_CHAN_PASSIVE_SCAN
+IEEE80211_CHAN_NO_IR
@@
@@
-IEEE80211_CHAN_NO_IBSS
+IEEE80211_CHAN_NO_IR
@@
@@
-NL80211_RRF_NO_IR | NL80211_RRF_NO_IR
+NL80211_RRF_NO_IR
@@
@@
-IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_IR
+IEEE80211_CHAN_NO_IR
@@
@@
-(NL80211_RRF_NO_IR)
+NL80211_RRF_NO_IR
@@
@@
-(IEEE80211_CHAN_NO_IR)
+IEEE80211_CHAN_NO_IR

Along with some hand-optimisations in documentation, to
remove duplicates and to fix some indentation.

Signed-off-by: Luis R. Rodriguez <mcgrof@do-not-panic.com>
[do all the driver updates in one go]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 Documentation/networking/regulatory.txt            |  4 +-
 drivers/net/wireless/ath/ath10k/mac.c              |  4 +-
 drivers/net/wireless/ath/regd.c                    | 47 +++++++--------
 drivers/net/wireless/brcm80211/brcmfmac/p2p.c      |  2 +-
 .../net/wireless/brcm80211/brcmfmac/wl_cfg80211.c  | 10 ++--
 drivers/net/wireless/brcm80211/brcmsmac/channel.c  | 31 ++++------
 .../net/wireless/brcm80211/brcmsmac/mac80211_if.c  | 66 +++++++++++-----------
 drivers/net/wireless/cw1200/scan.c                 | 10 ++--
 drivers/net/wireless/ipw2x00/ipw2100.c             |  4 +-
 drivers/net/wireless/ipw2x00/ipw2200.c             |  8 +--
 drivers/net/wireless/iwlegacy/3945-mac.c           |  2 +-
 drivers/net/wireless/iwlegacy/4965-mac.c           |  2 +-
 drivers/net/wireless/iwlegacy/common.c             |  4 +-
 drivers/net/wireless/iwlegacy/debug.c              |  8 +--
 drivers/net/wireless/iwlwifi/dvm/debugfs.c         |  8 +--
 drivers/net/wireless/iwlwifi/dvm/scan.c            |  2 +-
 drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c    |  4 +-
 drivers/net/wireless/iwlwifi/iwl-nvm-parse.c       |  4 +-
 drivers/net/wireless/iwlwifi/mvm/scan.c            |  4 +-
 drivers/net/wireless/mac80211_hwsim.c              |  4 +-
 drivers/net/wireless/mwifiex/cfg80211.c            | 14 ++---
 drivers/net/wireless/mwifiex/scan.c                |  4 +-
 drivers/net/wireless/rtlwifi/regd.c                | 48 +++++++---------
 drivers/net/wireless/ti/wl12xx/scan.c              |  2 +-
 drivers/net/wireless/ti/wlcore/cmd.c               |  2 +-
 drivers/net/wireless/ti/wlcore/main.c              |  3 +-
 drivers/net/wireless/ti/wlcore/scan.c              | 12 ++--
 include/net/cfg80211.h                             |  9 ++-
 include/uapi/linux/nl80211.h                       | 30 ++++++----
 net/mac80211/scan.c                                | 10 ++--
 net/mac80211/tx.c                                  |  3 +-
 net/wireless/chan.c                                |  3 +-
 net/wireless/genregdb.awk                          |  7 ++-
 net/wireless/ibss.c                                |  4 +-
 net/wireless/mesh.c                                |  3 +-
 net/wireless/nl80211.c                             | 12 ++--
 net/wireless/reg.c                                 | 33 ++++-------
 37 files changed, 197 insertions(+), 230 deletions(-)

(limited to 'include/uapi')

diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
index 9551622d0a7b..356f791af574 100644
--- a/Documentation/networking/regulatory.txt
+++ b/Documentation/networking/regulatory.txt
@@ -159,10 +159,10 @@ struct ieee80211_regdomain mydriver_jp_regdom = {
 		REG_RULE(2412-20, 2484+20, 40, 6, 20, 0),
 		/* IEEE 802.11a, channels 34..48 */
 		REG_RULE(5170-20, 5240+20, 40, 6, 20,
-			NL80211_RRF_PASSIVE_SCAN),
+			NL80211_RRF_NO_IR),
 		/* IEEE 802.11a, channels 52..64 */
 		REG_RULE(5260-20, 5320+20, 40, 6, 20,
-			NL80211_RRF_NO_IBSS |
+			NL80211_RRF_NO_IR|
 			NL80211_RRF_DFS),
 	}
 };
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 0b1cc516e778..f23d61fda243 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -1351,12 +1351,12 @@ static int ath10k_update_channel_list(struct ath10k *ar)
 			ch->allow_vht = true;
 
 			ch->allow_ibss =
-				!(channel->flags & IEEE80211_CHAN_NO_IBSS);
+				!(channel->flags & IEEE80211_CHAN_NO_IR);
 
 			ch->ht40plus =
 				!(channel->flags & IEEE80211_CHAN_NO_HT40PLUS);
 
-			passive = channel->flags & IEEE80211_CHAN_PASSIVE_SCAN;
+			passive = channel->flags & IEEE80211_CHAN_NO_IR;
 			ch->passive = passive;
 
 			ch->freq = channel->center_freq;
diff --git a/drivers/net/wireless/ath/regd.c b/drivers/net/wireless/ath/regd.c
index c00687e05688..e93e517a699f 100644
--- a/drivers/net/wireless/ath/regd.c
+++ b/drivers/net/wireless/ath/regd.c
@@ -37,17 +37,18 @@ static int __ath_regd_init(struct ath_regulatory *reg);
 
 /* We enable active scan on these a case by case basis by regulatory domain */
 #define ATH9K_2GHZ_CH12_13	REG_RULE(2467-10, 2472+10, 40, 0, 20,\
-					NL80211_RRF_PASSIVE_SCAN)
+					 NL80211_RRF_NO_IR)
 #define ATH9K_2GHZ_CH14		REG_RULE(2484-10, 2484+10, 40, 0, 20,\
-				NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_OFDM)
+					 NL80211_RRF_NO_IR | \
+					 NL80211_RRF_NO_OFDM)
 
 /* We allow IBSS on these on a case by case basis by regulatory domain */
 #define ATH9K_5GHZ_5150_5350	REG_RULE(5150-10, 5350+10, 80, 0, 30,\
-				NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 #define ATH9K_5GHZ_5470_5850	REG_RULE(5470-10, 5850+10, 80, 0, 30,\
-				NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 #define ATH9K_5GHZ_5725_5850	REG_RULE(5725-10, 5850+10, 80, 0, 30,\
-				NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 
 #define ATH9K_2GHZ_ALL		ATH9K_2GHZ_CH01_11, \
 				ATH9K_2GHZ_CH12_13, \
@@ -223,18 +224,11 @@ ath_reg_apply_beaconing_flags(struct wiphy *wiphy,
 				 * default during init, prior to calling our
 				 * regulatory_hint().
 				 */
-				if (!(reg_rule->flags &
-				    NL80211_RRF_NO_IBSS))
-					ch->flags &=
-					  ~IEEE80211_CHAN_NO_IBSS;
-				if (!(reg_rule->flags &
-				    NL80211_RRF_PASSIVE_SCAN))
-					ch->flags &=
-					  ~IEEE80211_CHAN_PASSIVE_SCAN;
+				if (!(reg_rule->flags & NL80211_RRF_NO_IR))
+					ch->flags &= ~IEEE80211_CHAN_NO_IR;
 			} else {
 				if (ch->beacon_found)
-					ch->flags &= ~(IEEE80211_CHAN_NO_IBSS |
-					  IEEE80211_CHAN_PASSIVE_SCAN);
+					ch->flags &= ~IEEE80211_CHAN_NO_IR;
 			}
 		}
 	}
@@ -260,11 +254,11 @@ ath_reg_apply_active_scan_flags(struct wiphy *wiphy,
 	 */
 	if (initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) {
 		ch = &sband->channels[11]; /* CH 12 */
-		if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-			ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (ch->flags & IEEE80211_CHAN_NO_IR)
+			ch->flags &= ~IEEE80211_CHAN_NO_IR;
 		ch = &sband->channels[12]; /* CH 13 */
-		if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-			ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (ch->flags & IEEE80211_CHAN_NO_IR)
+			ch->flags &= ~IEEE80211_CHAN_NO_IR;
 		return;
 	}
 
@@ -278,17 +272,17 @@ ath_reg_apply_active_scan_flags(struct wiphy *wiphy,
 	ch = &sband->channels[11]; /* CH 12 */
 	reg_rule = freq_reg_info(wiphy, ch->center_freq);
 	if (!IS_ERR(reg_rule)) {
-		if (!(reg_rule->flags & NL80211_RRF_PASSIVE_SCAN))
-			if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-				ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (!(reg_rule->flags & NL80211_RRF_NO_IR))
+			if (ch->flags & IEEE80211_CHAN_NO_IR)
+				ch->flags &= ~IEEE80211_CHAN_NO_IR;
 	}
 
 	ch = &sband->channels[12]; /* CH 13 */
 	reg_rule = freq_reg_info(wiphy, ch->center_freq);
 	if (!IS_ERR(reg_rule)) {
-		if (!(reg_rule->flags & NL80211_RRF_PASSIVE_SCAN))
-			if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-				ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (!(reg_rule->flags & NL80211_RRF_NO_IR))
+			if (ch->flags & IEEE80211_CHAN_NO_IR)
+				ch->flags &= ~IEEE80211_CHAN_NO_IR;
 	}
 }
 
@@ -320,8 +314,7 @@ static void ath_reg_apply_radar_flags(struct wiphy *wiphy)
 		 */
 		if (!(ch->flags & IEEE80211_CHAN_DISABLED))
 			ch->flags |= IEEE80211_CHAN_RADAR |
-				     IEEE80211_CHAN_NO_IBSS |
-				     IEEE80211_CHAN_PASSIVE_SCAN;
+				     IEEE80211_CHAN_NO_IR;
 	}
 }
 
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
index d7a974532909..fd0a4971244a 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
@@ -812,7 +812,7 @@ static s32 brcmf_p2p_run_escan(struct brcmf_cfg80211_info *cfg,
 			struct ieee80211_channel *chan = request->channels[i];
 
 			if (chan->flags & (IEEE80211_CHAN_RADAR |
-					   IEEE80211_CHAN_PASSIVE_SCAN))
+					   IEEE80211_CHAN_NO_IR))
 				continue;
 
 			chanspecs[i] = channel_to_chanspec(&p2p->cfg->d11inf,
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index 571f013cebbb..b6a09f97f9a3 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -202,9 +202,9 @@ static struct ieee80211_supported_band __wl_band_5ghz_a = {
 
 /* This is to override regulatory domains defined in cfg80211 module (reg.c)
  * By default world regulatory domain defined in reg.c puts the flags
- * NL80211_RRF_PASSIVE_SCAN and NL80211_RRF_NO_IBSS for 5GHz channels (for
- * 36..48 and 149..165). With respect to these flags, wpa_supplicant doesn't
- * start p2p operations on 5GHz channels. All the changes in world regulatory
+ * NL80211_RRF_NO_IR for 5GHz channels (for * 36..48 and 149..165).
+ * With respect to these flags, wpa_supplicant doesn't * start p2p
+ * operations on 5GHz channels. All the changes in world regulatory
  * domain are to be done here.
  */
 static const struct ieee80211_regdomain brcmf_regdom = {
@@ -5197,10 +5197,10 @@ static s32 brcmf_construct_reginfo(struct brcmf_cfg80211_info *cfg, u32 bw_cap)
 					if (channel & WL_CHAN_RADAR)
 						band_chan_arr[index].flags |=
 							(IEEE80211_CHAN_RADAR |
-							IEEE80211_CHAN_NO_IBSS);
+							IEEE80211_CHAN_NO_IR);
 					if (channel & WL_CHAN_PASSIVE)
 						band_chan_arr[index].flags |=
-						    IEEE80211_CHAN_PASSIVE_SCAN;
+						    IEEE80211_CHAN_NO_IR;
 				}
 			}
 			if (!update)
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/channel.c b/drivers/net/wireless/brcm80211/brcmsmac/channel.c
index cc87926f5055..7d8f3fd69a87 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/channel.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/channel.c
@@ -59,23 +59,18 @@
 
 #define BRCM_2GHZ_2412_2462	REG_RULE(2412-10, 2462+10, 40, 0, 19, 0)
 #define BRCM_2GHZ_2467_2472	REG_RULE(2467-10, 2472+10, 20, 0, 19, \
-					 NL80211_RRF_PASSIVE_SCAN | \
-					 NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 
 #define BRCM_5GHZ_5180_5240	REG_RULE(5180-10, 5240+10, 40, 0, 21, \
-					 NL80211_RRF_PASSIVE_SCAN | \
-					 NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 #define BRCM_5GHZ_5260_5320	REG_RULE(5260-10, 5320+10, 40, 0, 21, \
-					 NL80211_RRF_PASSIVE_SCAN | \
 					 NL80211_RRF_DFS | \
-					 NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 #define BRCM_5GHZ_5500_5700	REG_RULE(5500-10, 5700+10, 40, 0, 21, \
-					 NL80211_RRF_PASSIVE_SCAN | \
 					 NL80211_RRF_DFS | \
-					 NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 #define BRCM_5GHZ_5745_5825	REG_RULE(5745-10, 5825+10, 40, 0, 21, \
-					 NL80211_RRF_PASSIVE_SCAN | \
-					 NL80211_RRF_NO_IBSS)
+					 NL80211_RRF_NO_IR)
 
 static const struct ieee80211_regdomain brcms_regdom_x2 = {
 	.n_reg_rules = 6,
@@ -395,7 +390,7 @@ brcms_c_channel_set_chanspec(struct brcms_cm_info *wlc_cm, u16 chanspec,
 		brcms_c_set_gmode(wlc, wlc->protection->gmode_user, false);
 
 	brcms_b_set_chanspec(wlc->hw, chanspec,
-			      !!(ch->flags & IEEE80211_CHAN_PASSIVE_SCAN),
+			      !!(ch->flags & IEEE80211_CHAN_NO_IR),
 			      &txpwr);
 }
 
@@ -657,8 +652,8 @@ static void brcms_reg_apply_radar_flags(struct wiphy *wiphy)
 		 */
 		if (!(ch->flags & IEEE80211_CHAN_DISABLED))
 			ch->flags |= IEEE80211_CHAN_RADAR |
-				     IEEE80211_CHAN_NO_IBSS |
-				     IEEE80211_CHAN_PASSIVE_SCAN;
+				     IEEE80211_CHAN_NO_IR |
+				     IEEE80211_CHAN_NO_IR;
 	}
 }
 
@@ -688,14 +683,10 @@ brcms_reg_apply_beaconing_flags(struct wiphy *wiphy,
 				if (IS_ERR(rule))
 					continue;
 
-				if (!(rule->flags & NL80211_RRF_NO_IBSS))
-					ch->flags &= ~IEEE80211_CHAN_NO_IBSS;
-				if (!(rule->flags & NL80211_RRF_PASSIVE_SCAN))
-					ch->flags &=
-						~IEEE80211_CHAN_PASSIVE_SCAN;
+				if (!(rule->flags & NL80211_RRF_NO_IR))
+					ch->flags &= ~IEEE80211_CHAN_NO_IR;
 			} else if (ch->beacon_found) {
-				ch->flags &= ~(IEEE80211_CHAN_NO_IBSS |
-					       IEEE80211_CHAN_PASSIVE_SCAN);
+				ch->flags &= ~IEEE80211_CHAN_NO_IR;
 			}
 		}
 	}
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index edc5d105ff98..e71ce8c842a2 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -125,13 +125,13 @@ static struct ieee80211_channel brcms_2ghz_chantable[] = {
 	CHAN2GHZ(10, 2457, IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN2GHZ(11, 2462, IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN2GHZ(12, 2467,
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_IBSS |
+		 IEEE80211_CHAN_NO_IR |
 		 IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN2GHZ(13, 2472,
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_IBSS |
+		 IEEE80211_CHAN_NO_IR |
 		 IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN2GHZ(14, 2484,
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_IBSS |
+		 IEEE80211_CHAN_NO_IR |
 		 IEEE80211_CHAN_NO_HT40PLUS | IEEE80211_CHAN_NO_HT40MINUS |
 		 IEEE80211_CHAN_NO_OFDM)
 };
@@ -144,51 +144,51 @@ static struct ieee80211_channel brcms_5ghz_nphy_chantable[] = {
 	CHAN5GHZ(48, IEEE80211_CHAN_NO_HT40PLUS),
 	/* UNII-2 */
 	CHAN5GHZ(52,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40MINUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40MINUS),
 	CHAN5GHZ(56,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN5GHZ(60,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40MINUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40MINUS),
 	CHAN5GHZ(64,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS),
 	/* MID */
 	CHAN5GHZ(100,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40MINUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40MINUS),
 	CHAN5GHZ(104,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN5GHZ(108,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40MINUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40MINUS),
 	CHAN5GHZ(112,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN5GHZ(116,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40MINUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40MINUS),
 	CHAN5GHZ(120,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN5GHZ(124,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40MINUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40MINUS),
 	CHAN5GHZ(128,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN5GHZ(132,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40MINUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40MINUS),
 	CHAN5GHZ(136,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS),
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS),
 	CHAN5GHZ(140,
-		 IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IBSS |
-		 IEEE80211_CHAN_PASSIVE_SCAN | IEEE80211_CHAN_NO_HT40PLUS |
+		 IEEE80211_CHAN_RADAR |
+		 IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_NO_HT40PLUS |
 		 IEEE80211_CHAN_NO_HT40MINUS),
 	/* UNII-3 */
 	CHAN5GHZ(149, IEEE80211_CHAN_NO_HT40MINUS),
diff --git a/drivers/net/wireless/cw1200/scan.c b/drivers/net/wireless/cw1200/scan.c
index ee3c19037aac..8c017bfd2ffc 100644
--- a/drivers/net/wireless/cw1200/scan.c
+++ b/drivers/net/wireless/cw1200/scan.c
@@ -197,9 +197,9 @@ void cw1200_scan_work(struct work_struct *work)
 			if ((*it)->band != first->band)
 				break;
 			if (((*it)->flags ^ first->flags) &
-					IEEE80211_CHAN_PASSIVE_SCAN)
+					IEEE80211_CHAN_NO_IR)
 				break;
-			if (!(first->flags & IEEE80211_CHAN_PASSIVE_SCAN) &&
+			if (!(first->flags & IEEE80211_CHAN_NO_IR) &&
 			    (*it)->max_power != first->max_power)
 				break;
 		}
@@ -210,7 +210,7 @@ void cw1200_scan_work(struct work_struct *work)
 		else
 			scan.max_tx_rate = WSM_TRANSMIT_RATE_1;
 		scan.num_probes =
-			(first->flags & IEEE80211_CHAN_PASSIVE_SCAN) ? 0 : 2;
+			(first->flags & IEEE80211_CHAN_NO_IR) ? 0 : 2;
 		scan.num_ssids = priv->scan.n_ssids;
 		scan.ssids = &priv->scan.ssids[0];
 		scan.num_channels = it - priv->scan.curr;
@@ -233,7 +233,7 @@ void cw1200_scan_work(struct work_struct *work)
 		}
 		for (i = 0; i < scan.num_channels; ++i) {
 			scan.ch[i].number = priv->scan.curr[i]->hw_value;
-			if (priv->scan.curr[i]->flags & IEEE80211_CHAN_PASSIVE_SCAN) {
+			if (priv->scan.curr[i]->flags & IEEE80211_CHAN_NO_IR) {
 				scan.ch[i].min_chan_time = 50;
 				scan.ch[i].max_chan_time = 100;
 			} else {
@@ -241,7 +241,7 @@ void cw1200_scan_work(struct work_struct *work)
 				scan.ch[i].max_chan_time = 25;
 			}
 		}
-		if (!(first->flags & IEEE80211_CHAN_PASSIVE_SCAN) &&
+		if (!(first->flags & IEEE80211_CHAN_NO_IR) &&
 		    priv->scan.output_power != first->max_power) {
 			priv->scan.output_power = first->max_power;
 			wsm_set_output_power(priv,
diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c
index f8ab193009cd..813c9af0ebd6 100644
--- a/drivers/net/wireless/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/ipw2x00/ipw2100.c
@@ -1930,10 +1930,10 @@ static int ipw2100_wdev_init(struct net_device *dev)
 			bg_band->channels[i].max_power = geo->bg[i].max_power;
 			if (geo->bg[i].flags & LIBIPW_CH_PASSIVE_ONLY)
 				bg_band->channels[i].flags |=
-					IEEE80211_CHAN_PASSIVE_SCAN;
+					IEEE80211_CHAN_NO_IR;
 			if (geo->bg[i].flags & LIBIPW_CH_NO_IBSS)
 				bg_band->channels[i].flags |=
-					IEEE80211_CHAN_NO_IBSS;
+					IEEE80211_CHAN_NO_IR;
 			if (geo->bg[i].flags & LIBIPW_CH_RADAR_DETECT)
 				bg_band->channels[i].flags |=
 					IEEE80211_CHAN_RADAR;
diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c
index f394af777cf5..4eca9e20adea 100644
--- a/drivers/net/wireless/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/ipw2x00/ipw2200.c
@@ -11472,10 +11472,10 @@ static int ipw_wdev_init(struct net_device *dev)
 			bg_band->channels[i].max_power = geo->bg[i].max_power;
 			if (geo->bg[i].flags & LIBIPW_CH_PASSIVE_ONLY)
 				bg_band->channels[i].flags |=
-					IEEE80211_CHAN_PASSIVE_SCAN;
+					IEEE80211_CHAN_NO_IR;
 			if (geo->bg[i].flags & LIBIPW_CH_NO_IBSS)
 				bg_band->channels[i].flags |=
-					IEEE80211_CHAN_NO_IBSS;
+					IEEE80211_CHAN_NO_IR;
 			if (geo->bg[i].flags & LIBIPW_CH_RADAR_DETECT)
 				bg_band->channels[i].flags |=
 					IEEE80211_CHAN_RADAR;
@@ -11511,10 +11511,10 @@ static int ipw_wdev_init(struct net_device *dev)
 			a_band->channels[i].max_power = geo->a[i].max_power;
 			if (geo->a[i].flags & LIBIPW_CH_PASSIVE_ONLY)
 				a_band->channels[i].flags |=
-					IEEE80211_CHAN_PASSIVE_SCAN;
+					IEEE80211_CHAN_NO_IR;
 			if (geo->a[i].flags & LIBIPW_CH_NO_IBSS)
 				a_band->channels[i].flags |=
-					IEEE80211_CHAN_NO_IBSS;
+					IEEE80211_CHAN_NO_IR;
 			if (geo->a[i].flags & LIBIPW_CH_RADAR_DETECT)
 				a_band->channels[i].flags |=
 					IEEE80211_CHAN_RADAR;
diff --git a/drivers/net/wireless/iwlegacy/3945-mac.c b/drivers/net/wireless/iwlegacy/3945-mac.c
index dea3b50d68b9..5a66595b0faf 100644
--- a/drivers/net/wireless/iwlegacy/3945-mac.c
+++ b/drivers/net/wireless/iwlegacy/3945-mac.c
@@ -1595,7 +1595,7 @@ il3945_get_channels_for_scan(struct il_priv *il, enum ieee80211_band band,
 		 *  and use long active_dwell time.
 		 */
 		if (!is_active || il_is_channel_passive(ch_info) ||
-		    (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN)) {
+		    (chan->flags & IEEE80211_CHAN_NO_IR)) {
 			scan_ch->type = 0;	/* passive */
 			if (IL_UCODE_API(il->ucode_ver) == 1)
 				scan_ch->active_dwell =
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index 3982ab76f375..1c5f8cdbd3a5 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -805,7 +805,7 @@ il4965_get_channels_for_scan(struct il_priv *il, struct ieee80211_vif *vif,
 		}
 
 		if (!is_active || il_is_channel_passive(ch_info) ||
-		    (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN))
+		    (chan->flags & IEEE80211_CHAN_NO_IR))
 			scan_ch->type = SCAN_CHANNEL_TYPE_PASSIVE;
 		else
 			scan_ch->type = SCAN_CHANNEL_TYPE_ACTIVE;
diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c
index b03e22ef5462..a27b14cfeaec 100644
--- a/drivers/net/wireless/iwlegacy/common.c
+++ b/drivers/net/wireless/iwlegacy/common.c
@@ -3445,10 +3445,10 @@ il_init_geos(struct il_priv *il)
 
 		if (il_is_channel_valid(ch)) {
 			if (!(ch->flags & EEPROM_CHANNEL_IBSS))
-				geo_ch->flags |= IEEE80211_CHAN_NO_IBSS;
+				geo_ch->flags |= IEEE80211_CHAN_NO_IR;
 
 			if (!(ch->flags & EEPROM_CHANNEL_ACTIVE))
-				geo_ch->flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+				geo_ch->flags |= IEEE80211_CHAN_NO_IR;
 
 			if (ch->flags & EEPROM_CHANNEL_RADAR)
 				geo_ch->flags |= IEEE80211_CHAN_RADAR;
diff --git a/drivers/net/wireless/iwlegacy/debug.c b/drivers/net/wireless/iwlegacy/debug.c
index eff26501d60a..3a487a3bb5de 100644
--- a/drivers/net/wireless/iwlegacy/debug.c
+++ b/drivers/net/wireless/iwlegacy/debug.c
@@ -567,12 +567,12 @@ il_dbgfs_channels_read(struct file *file, char __user *user_buf, size_t count,
 				      flags & IEEE80211_CHAN_RADAR ?
 				      " (IEEE 802.11h required)" : "",
 				      ((channels[i].
-					flags & IEEE80211_CHAN_NO_IBSS) ||
+					flags & IEEE80211_CHAN_NO_IR) ||
 				       (channels[i].
 					flags & IEEE80211_CHAN_RADAR)) ? "" :
 				      ", IBSS",
 				      channels[i].
-				      flags & IEEE80211_CHAN_PASSIVE_SCAN ?
+				      flags & IEEE80211_CHAN_NO_IR ?
 				      "passive only" : "active/passive");
 	}
 	supp_band = il_get_hw_mode(il, IEEE80211_BAND_5GHZ);
@@ -594,12 +594,12 @@ il_dbgfs_channels_read(struct file *file, char __user *user_buf, size_t count,
 				      flags & IEEE80211_CHAN_RADAR ?
 				      " (IEEE 802.11h required)" : "",
 				      ((channels[i].
-					flags & IEEE80211_CHAN_NO_IBSS) ||
+					flags & IEEE80211_CHAN_NO_IR) ||
 				       (channels[i].
 					flags & IEEE80211_CHAN_RADAR)) ? "" :
 				      ", IBSS",
 				      channels[i].
-				      flags & IEEE80211_CHAN_PASSIVE_SCAN ?
+				      flags & IEEE80211_CHAN_NO_IR ?
 				      "passive only" : "active/passive");
 	}
 	ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos);
diff --git a/drivers/net/wireless/iwlwifi/dvm/debugfs.c b/drivers/net/wireless/iwlwifi/dvm/debugfs.c
index d94f8ab15004..f69301e505ee 100644
--- a/drivers/net/wireless/iwlwifi/dvm/debugfs.c
+++ b/drivers/net/wireless/iwlwifi/dvm/debugfs.c
@@ -352,12 +352,12 @@ static ssize_t iwl_dbgfs_channels_read(struct file *file, char __user *user_buf,
 					channels[i].max_power,
 					channels[i].flags & IEEE80211_CHAN_RADAR ?
 					" (IEEE 802.11h required)" : "",
-					((channels[i].flags & IEEE80211_CHAN_NO_IBSS)
+					((channels[i].flags & IEEE80211_CHAN_NO_IR)
 					|| (channels[i].flags &
 					IEEE80211_CHAN_RADAR)) ? "" :
 					", IBSS",
 					channels[i].flags &
-					IEEE80211_CHAN_PASSIVE_SCAN ?
+					IEEE80211_CHAN_NO_IR ?
 					"passive only" : "active/passive");
 	}
 	supp_band = iwl_get_hw_mode(priv, IEEE80211_BAND_5GHZ);
@@ -375,12 +375,12 @@ static ssize_t iwl_dbgfs_channels_read(struct file *file, char __user *user_buf,
 					channels[i].max_power,
 					channels[i].flags & IEEE80211_CHAN_RADAR ?
 					" (IEEE 802.11h required)" : "",
-					((channels[i].flags & IEEE80211_CHAN_NO_IBSS)
+					((channels[i].flags & IEEE80211_CHAN_NO_IR)
 					|| (channels[i].flags &
 					IEEE80211_CHAN_RADAR)) ? "" :
 					", IBSS",
 					channels[i].flags &
-					IEEE80211_CHAN_PASSIVE_SCAN ?
+					IEEE80211_CHAN_NO_IR ?
 					"passive only" : "active/passive");
 	}
 	ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos);
diff --git a/drivers/net/wireless/iwlwifi/dvm/scan.c b/drivers/net/wireless/iwlwifi/dvm/scan.c
index 35e0ee8b4e5b..928f8640a0a7 100644
--- a/drivers/net/wireless/iwlwifi/dvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/dvm/scan.c
@@ -544,7 +544,7 @@ static int iwl_get_channels_for_scan(struct iwl_priv *priv,
 		channel = chan->hw_value;
 		scan_ch->channel = cpu_to_le16(channel);
 
-		if (!is_active || (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN))
+		if (!is_active || (chan->flags & IEEE80211_CHAN_NO_IR))
 			scan_ch->type = SCAN_CHANNEL_TYPE_PASSIVE;
 		else
 			scan_ch->type = SCAN_CHANNEL_TYPE_ACTIVE;
diff --git a/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c b/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c
index 4c887f365908..f4a6d317a023 100644
--- a/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-eeprom-parse.c
@@ -614,10 +614,10 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 			channel->flags = IEEE80211_CHAN_NO_HT40;
 
 			if (!(eeprom_ch->flags & EEPROM_CHANNEL_IBSS))
-				channel->flags |= IEEE80211_CHAN_NO_IBSS;
+				channel->flags |= IEEE80211_CHAN_NO_IR;
 
 			if (!(eeprom_ch->flags & EEPROM_CHANNEL_ACTIVE))
-				channel->flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+				channel->flags |= IEEE80211_CHAN_NO_IR;
 
 			if (eeprom_ch->flags & EEPROM_CHANNEL_RADAR)
 				channel->flags |= IEEE80211_CHAN_RADAR;
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index b76a9a8fc0b3..2fab203d3027 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -223,10 +223,10 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 			channel->flags |= IEEE80211_CHAN_NO_160MHZ;
 
 		if (!(ch_flags & NVM_CHANNEL_IBSS))
-			channel->flags |= IEEE80211_CHAN_NO_IBSS;
+			channel->flags |= IEEE80211_CHAN_NO_IR;
 
 		if (!(ch_flags & NVM_CHANNEL_ACTIVE))
-			channel->flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+			channel->flags |= IEEE80211_CHAN_NO_IR;
 
 		if (ch_flags & NVM_CHANNEL_RADAR)
 			channel->flags |= IEEE80211_CHAN_RADAR;
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index dff7592e1ff8..e0cd100b40cd 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -192,7 +192,7 @@ static void iwl_mvm_scan_fill_channels(struct iwl_scan_cmd *cmd,
 	for (i = 0; i < cmd->channel_count; i++) {
 		chan->channel = cpu_to_le16(req->channels[i]->hw_value);
 		chan->type = cpu_to_le32(type);
-		if (req->channels[i]->flags & IEEE80211_CHAN_PASSIVE_SCAN)
+		if (req->channels[i]->flags & IEEE80211_CHAN_NO_IR)
 			chan->type &= cpu_to_le32(~SCAN_CHANNEL_TYPE_ACTIVE);
 		chan->active_dwell = cpu_to_le16(active_dwell);
 		chan->passive_dwell = cpu_to_le16(passive_dwell);
@@ -642,7 +642,7 @@ static void iwl_build_channel_cfg(struct iwl_mvm *mvm,
 		channels->iter_count[index] = cpu_to_le16(1);
 		channels->iter_interval[index] = 0;
 
-		if (!(s_band->channels[i].flags & IEEE80211_CHAN_PASSIVE_SCAN))
+		if (!(s_band->channels[i].flags & IEEE80211_CHAN_NO_IR))
 			channels->type[index] |=
 				cpu_to_le32(IWL_SCAN_OFFLOAD_CHANNEL_ACTIVE);
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index de0df86704e7..33d4b31995da 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -159,7 +159,7 @@ static const struct ieee80211_regdomain hwsim_world_regdom_custom_02 = {
 	.reg_rules = {
 		REG_RULE(2412-10, 2462+10, 40, 0, 20, 0),
 		REG_RULE(5725-10, 5850+10, 40, 0, 30,
-			NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS),
+			 NL80211_RRF_NO_IR),
 	}
 };
 
@@ -1485,7 +1485,7 @@ static void hw_scan_work(struct work_struct *work)
 		    req->channels[hwsim->scan_chan_idx]->center_freq);
 
 	hwsim->tmp_chan = req->channels[hwsim->scan_chan_idx];
-	if (hwsim->tmp_chan->flags & IEEE80211_CHAN_PASSIVE_SCAN ||
+	if (hwsim->tmp_chan->flags & IEEE80211_CHAN_NO_IR ||
 	    !req->n_ssids) {
 		dwell = 120;
 	} else {
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index fbad00a5abc8..7f68943f02c2 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -50,24 +50,24 @@ static const struct ieee80211_regdomain mwifiex_world_regdom_custom = {
 		REG_RULE(2412-10, 2462+10, 40, 3, 20, 0),
 		/* Channel 12 - 13 */
 		REG_RULE(2467-10, 2472+10, 20, 3, 20,
-			 NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS),
+			 NL80211_RRF_NO_IR),
 		/* Channel 14 */
 		REG_RULE(2484-10, 2484+10, 20, 3, 20,
-			 NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS |
+			 NL80211_RRF_NO_IR |
 			 NL80211_RRF_NO_OFDM),
 		/* Channel 36 - 48 */
 		REG_RULE(5180-10, 5240+10, 40, 3, 20,
-			 NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS),
+			 NL80211_RRF_NO_IR),
 		/* Channel 149 - 165 */
 		REG_RULE(5745-10, 5825+10, 40, 3, 20,
-			 NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS),
+			 NL80211_RRF_NO_IR),
 		/* Channel 52 - 64 */
 		REG_RULE(5260-10, 5320+10, 40, 3, 30,
-			 NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS |
+			 NL80211_RRF_NO_IR |
 			 NL80211_RRF_DFS),
 		/* Channel 100 - 140 */
 		REG_RULE(5500-10, 5700+10, 40, 3, 30,
-			 NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS |
+			 NL80211_RRF_NO_IR |
 			 NL80211_RRF_DFS),
 	}
 };
@@ -1968,7 +1968,7 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy,
 		user_scan_cfg->chan_list[i].chan_number = chan->hw_value;
 		user_scan_cfg->chan_list[i].radio_type = chan->band;
 
-		if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN)
+		if (chan->flags & IEEE80211_CHAN_NO_IR)
 			user_scan_cfg->chan_list[i].scan_type =
 						MWIFIEX_SCAN_TYPE_PASSIVE;
 		else
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index 8cf7d50a7603..0ed06646f19a 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -515,14 +515,14 @@ mwifiex_scan_create_channel_list(struct mwifiex_private *priv,
 				scan_chan_list[chan_idx].max_scan_time =
 					cpu_to_le16((u16) user_scan_in->
 					chan_list[0].scan_time);
-			else if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
+			else if (ch->flags & IEEE80211_CHAN_NO_IR)
 				scan_chan_list[chan_idx].max_scan_time =
 					cpu_to_le16(adapter->passive_scan_time);
 			else
 				scan_chan_list[chan_idx].max_scan_time =
 					cpu_to_le16(adapter->active_scan_time);
 
-			if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
+			if (ch->flags & IEEE80211_CHAN_NO_IR)
 				scan_chan_list[chan_idx].chan_scan_mode_bitmap
 					|= MWIFIEX_PASSIVE_SCAN;
 			else
diff --git a/drivers/net/wireless/rtlwifi/regd.c b/drivers/net/wireless/rtlwifi/regd.c
index d7d0d4948b01..8453c53143f5 100644
--- a/drivers/net/wireless/rtlwifi/regd.c
+++ b/drivers/net/wireless/rtlwifi/regd.c
@@ -59,30 +59,26 @@ static struct country_code_to_enum_rd allCountries[] = {
  */
 #define RTL819x_2GHZ_CH12_13	\
 	REG_RULE(2467-10, 2472+10, 40, 0, 20,\
-	NL80211_RRF_PASSIVE_SCAN)
+		 NL80211_RRF_NO_IR)
 
 #define RTL819x_2GHZ_CH14	\
 	REG_RULE(2484-10, 2484+10, 40, 0, 20, \
-	NL80211_RRF_PASSIVE_SCAN | \
-	NL80211_RRF_NO_OFDM)
+		 NL80211_RRF_NO_IR | NL80211_RRF_NO_OFDM)
 
 /* 5G chan 36 - chan 64*/
 #define RTL819x_5GHZ_5150_5350	\
 	REG_RULE(5150-10, 5350+10, 40, 0, 30, \
-	NL80211_RRF_PASSIVE_SCAN | \
-	NL80211_RRF_NO_IBSS)
+		 NL80211_RRF_NO_IR)
 
 /* 5G chan 100 - chan 165*/
 #define RTL819x_5GHZ_5470_5850	\
 	REG_RULE(5470-10, 5850+10, 40, 0, 30, \
-	NL80211_RRF_PASSIVE_SCAN | \
-	NL80211_RRF_NO_IBSS)
+		 NL80211_RRF_NO_IR)
 
 /* 5G chan 149 - chan 165*/
 #define RTL819x_5GHZ_5725_5850	\
 	REG_RULE(5725-10, 5850+10, 40, 0, 30, \
-	NL80211_RRF_PASSIVE_SCAN | \
-	NL80211_RRF_NO_IBSS)
+		 NL80211_RRF_NO_IR)
 
 #define RTL819x_5GHZ_ALL	\
 	(RTL819x_5GHZ_5150_5350, RTL819x_5GHZ_5470_5850)
@@ -185,16 +181,11 @@ static void _rtl_reg_apply_beaconing_flags(struct wiphy *wiphy,
 				 *regulatory_hint().
 				 */
 
-				if (!(reg_rule->flags & NL80211_RRF_NO_IBSS))
-					ch->flags &= ~IEEE80211_CHAN_NO_IBSS;
-				if (!(reg_rule->
-				     flags & NL80211_RRF_PASSIVE_SCAN))
-					ch->flags &=
-					    ~IEEE80211_CHAN_PASSIVE_SCAN;
+				if (!(reg_rule->flags & NL80211_RRF_NO_IR))
+					ch->flags &= ~IEEE80211_CHAN_NO_IR;
 			} else {
 				if (ch->beacon_found)
-					ch->flags &= ~(IEEE80211_CHAN_NO_IBSS |
-						  IEEE80211_CHAN_PASSIVE_SCAN);
+					ch->flags &= ~IEEE80211_CHAN_NO_IR;
 			}
 		}
 	}
@@ -219,11 +210,11 @@ static void _rtl_reg_apply_active_scan_flags(struct wiphy *wiphy,
 	 */
 	if (initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) {
 		ch = &sband->channels[11];	/* CH 12 */
-		if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-			ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (ch->flags & IEEE80211_CHAN_NO_IR)
+			ch->flags &= ~IEEE80211_CHAN_NO_IR;
 		ch = &sband->channels[12];	/* CH 13 */
-		if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-			ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (ch->flags & IEEE80211_CHAN_NO_IR)
+			ch->flags &= ~IEEE80211_CHAN_NO_IR;
 		return;
 	}
 
@@ -237,17 +228,17 @@ static void _rtl_reg_apply_active_scan_flags(struct wiphy *wiphy,
 	ch = &sband->channels[11];	/* CH 12 */
 	reg_rule = freq_reg_info(wiphy, ch->center_freq);
 	if (!IS_ERR(reg_rule)) {
-		if (!(reg_rule->flags & NL80211_RRF_PASSIVE_SCAN))
-			if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-				ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (!(reg_rule->flags & NL80211_RRF_NO_IR))
+			if (ch->flags & IEEE80211_CHAN_NO_IR)
+				ch->flags &= ~IEEE80211_CHAN_NO_IR;
 	}
 
 	ch = &sband->channels[12];	/* CH 13 */
 	reg_rule = freq_reg_info(wiphy, ch->center_freq);
 	if (!IS_ERR(reg_rule)) {
-		if (!(reg_rule->flags & NL80211_RRF_PASSIVE_SCAN))
-			if (ch->flags & IEEE80211_CHAN_PASSIVE_SCAN)
-				ch->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
+		if (!(reg_rule->flags & NL80211_RRF_NO_IR))
+			if (ch->flags & IEEE80211_CHAN_NO_IR)
+				ch->flags &= ~IEEE80211_CHAN_NO_IR;
 	}
 }
 
@@ -284,8 +275,7 @@ static void _rtl_reg_apply_radar_flags(struct wiphy *wiphy)
 		 */
 		if (!(ch->flags & IEEE80211_CHAN_DISABLED))
 			ch->flags |= IEEE80211_CHAN_RADAR |
-			    IEEE80211_CHAN_NO_IBSS |
-			    IEEE80211_CHAN_PASSIVE_SCAN;
+				     IEEE80211_CHAN_NO_IR;
 	}
 }
 
diff --git a/drivers/net/wireless/ti/wl12xx/scan.c b/drivers/net/wireless/ti/wl12xx/scan.c
index 4a0bbb13806b..7541bd1a4a4b 100644
--- a/drivers/net/wireless/ti/wl12xx/scan.c
+++ b/drivers/net/wireless/ti/wl12xx/scan.c
@@ -47,7 +47,7 @@ static int wl1271_get_scan_channels(struct wl1271 *wl,
 		     * In active scans, we only scan channels not
 		     * marked as passive.
 		     */
-		    (passive || !(flags & IEEE80211_CHAN_PASSIVE_SCAN))) {
+		    (passive || !(flags & IEEE80211_CHAN_NO_IR))) {
 			wl1271_debug(DEBUG_SCAN, "band %d, center_freq %d ",
 				     req->channels[i]->band,
 				     req->channels[i]->center_freq);
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 34d9dfff2ad3..9b2ecf52449f 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -1688,7 +1688,7 @@ int wlcore_cmd_regdomain_config_locked(struct wl1271 *wl)
 
 			if (channel->flags & (IEEE80211_CHAN_DISABLED |
 					      IEEE80211_CHAN_RADAR |
-					      IEEE80211_CHAN_PASSIVE_SCAN))
+					      IEEE80211_CHAN_NO_IR))
 				continue;
 
 			ch_bit_idx = wlcore_get_reg_conf_ch_idx(b, ch);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 0368b9cbfb89..e9da47cead58 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -91,8 +91,7 @@ static void wl1271_reg_notify(struct wiphy *wiphy,
 			continue;
 
 		if (ch->flags & IEEE80211_CHAN_RADAR)
-			ch->flags |= IEEE80211_CHAN_NO_IBSS |
-				     IEEE80211_CHAN_PASSIVE_SCAN;
+			ch->flags |= IEEE80211_CHAN_NO_IR;
 
 	}
 
diff --git a/drivers/net/wireless/ti/wlcore/scan.c b/drivers/net/wireless/ti/wlcore/scan.c
index 7ed86203304b..1e3d51cd673a 100644
--- a/drivers/net/wireless/ti/wlcore/scan.c
+++ b/drivers/net/wireless/ti/wlcore/scan.c
@@ -188,16 +188,14 @@ wlcore_scan_get_channels(struct wl1271 *wl,
 		flags = req_channels[i]->flags;
 
 		if (force_passive)
-			flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+			flags |= IEEE80211_CHAN_NO_IR;
 
 		if ((req_channels[i]->band == band) &&
 		    !(flags & IEEE80211_CHAN_DISABLED) &&
 		    (!!(flags & IEEE80211_CHAN_RADAR) == radar) &&
 		    /* if radar is set, we ignore the passive flag */
 		    (radar ||
-		     !!(flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive)) {
-
-
+		     !!(flags & IEEE80211_CHAN_NO_IR) == passive)) {
 			if (flags & IEEE80211_CHAN_RADAR) {
 				channels[j].flags |= SCAN_CHANNEL_FLAGS_DFS;
 
@@ -220,7 +218,7 @@ wlcore_scan_get_channels(struct wl1271 *wl,
 			    (band == IEEE80211_BAND_2GHZ) &&
 			    (channels[j].channel >= 12) &&
 			    (channels[j].channel <= 14) &&
-			    (flags & IEEE80211_CHAN_PASSIVE_SCAN) &&
+			    (flags & IEEE80211_CHAN_NO_IR) &&
 			    !force_passive) {
 				/* pactive channels treated as DFS */
 				channels[j].flags = SCAN_CHANNEL_FLAGS_DFS;
@@ -243,8 +241,8 @@ wlcore_scan_get_channels(struct wl1271 *wl,
 				     max_dwell_time_active,
 				     flags & IEEE80211_CHAN_RADAR ?
 					", DFS" : "",
-				     flags & IEEE80211_CHAN_PASSIVE_SCAN ?
-					", PASSIVE" : "");
+				     flags & IEEE80211_CHAN_NO_IR ?
+					", NO-IR" : "");
 			j++;
 		}
 	}
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 3eae46cb1acf..c1b887413234 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -91,9 +91,8 @@ enum ieee80211_band {
  * Channel flags set by the regulatory control code.
  *
  * @IEEE80211_CHAN_DISABLED: This channel is disabled.
- * @IEEE80211_CHAN_PASSIVE_SCAN: Only passive scanning is permitted
- *	on this channel.
- * @IEEE80211_CHAN_NO_IBSS: IBSS is not allowed on this channel.
+ * @IEEE80211_CHAN_NO_IR: do not initiate radiation, this includes
+ * 	sending probe requests or beaconing.
  * @IEEE80211_CHAN_RADAR: Radar detection is required on this channel.
  * @IEEE80211_CHAN_NO_HT40PLUS: extension channel above this channel
  * 	is not permitted.
@@ -113,8 +112,8 @@ enum ieee80211_band {
  */
 enum ieee80211_channel_flags {
 	IEEE80211_CHAN_DISABLED		= 1<<0,
-	IEEE80211_CHAN_PASSIVE_SCAN	= 1<<1,
-	IEEE80211_CHAN_NO_IBSS		= 1<<2,
+	IEEE80211_CHAN_NO_IR		= 1<<1,
+	/* hole at 1<<2 */
 	IEEE80211_CHAN_RADAR		= 1<<3,
 	IEEE80211_CHAN_NO_HT40PLUS	= 1<<4,
 	IEEE80211_CHAN_NO_HT40MINUS	= 1<<5,
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 3d8325bb50cd..7e25164adfe9 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2231,10 +2231,9 @@ enum nl80211_band_attr {
  * @NL80211_FREQUENCY_ATTR_FREQ: Frequency in MHz
  * @NL80211_FREQUENCY_ATTR_DISABLED: Channel is disabled in current
  *	regulatory domain.
- * @NL80211_FREQUENCY_ATTR_PASSIVE_SCAN: Only passive scanning is
- *	permitted on this channel in current regulatory domain.
- * @NL80211_FREQUENCY_ATTR_NO_IBSS: IBSS networks are not permitted
- *	on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_NO_IR: no mechanisms that initiate radiation
+ * 	are permitted on this channel, this includes sending probe
+ * 	requests, or modes of operation that require beaconing.
  * @NL80211_FREQUENCY_ATTR_RADAR: Radar detection is mandatory
  *	on this channel in current regulatory domain.
  * @NL80211_FREQUENCY_ATTR_MAX_TX_POWER: Maximum transmission power in mBm
@@ -2261,8 +2260,8 @@ enum nl80211_frequency_attr {
 	__NL80211_FREQUENCY_ATTR_INVALID,
 	NL80211_FREQUENCY_ATTR_FREQ,
 	NL80211_FREQUENCY_ATTR_DISABLED,
-	NL80211_FREQUENCY_ATTR_PASSIVE_SCAN,
-	NL80211_FREQUENCY_ATTR_NO_IBSS,
+	NL80211_FREQUENCY_ATTR_NO_IR,
+	__NL80211_FREQUENCY_ATTR_NO_IBSS,
 	NL80211_FREQUENCY_ATTR_RADAR,
 	NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
 	NL80211_FREQUENCY_ATTR_DFS_STATE,
@@ -2278,6 +2277,9 @@ enum nl80211_frequency_attr {
 };
 
 #define NL80211_FREQUENCY_ATTR_MAX_TX_POWER NL80211_FREQUENCY_ATTR_MAX_TX_POWER
+#define NL80211_FREQUENCY_ATTR_PASSIVE_SCAN	NL80211_FREQUENCY_ATTR_NO_IR
+#define NL80211_FREQUENCY_ATTR_NO_IBSS		NL80211_FREQUENCY_ATTR_NO_IR
+#define NL80211_FREQUENCY_ATTR_NO_IR		NL80211_FREQUENCY_ATTR_NO_IR
 
 /**
  * enum nl80211_bitrate_attr - bitrate attributes
@@ -2420,8 +2422,9 @@ enum nl80211_sched_scan_match_attr {
  * @NL80211_RRF_DFS: DFS support is required to be used
  * @NL80211_RRF_PTP_ONLY: this is only for Point To Point links
  * @NL80211_RRF_PTMP_ONLY: this is only for Point To Multi Point links
- * @NL80211_RRF_PASSIVE_SCAN: passive scan is required
- * @NL80211_RRF_NO_IBSS: no IBSS is allowed
+ * @NL80211_RRF_NO_IR: no mechanisms that initiate radiation are allowed,
+ * 	this includes probe requests or modes of operation that require
+ * 	beaconing.
  */
 enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_OFDM		= 1<<0,
@@ -2431,10 +2434,17 @@ enum nl80211_reg_rule_flags {
 	NL80211_RRF_DFS			= 1<<4,
 	NL80211_RRF_PTP_ONLY		= 1<<5,
 	NL80211_RRF_PTMP_ONLY		= 1<<6,
-	NL80211_RRF_PASSIVE_SCAN	= 1<<7,
-	NL80211_RRF_NO_IBSS		= 1<<8,
+	NL80211_RRF_NO_IR		= 1<<7,
+	__NL80211_RRF_NO_IBSS		= 1<<8,
 };
 
+#define NL80211_RRF_PASSIVE_SCAN	NL80211_RRF_NO_IR
+#define NL80211_RRF_NO_IBSS		NL80211_RRF_NO_IR
+#define NL80211_RRF_NO_IR		NL80211_RRF_NO_IR
+
+/* For backport compatibility with older userspace */
+#define NL80211_RRF_NO_IR_ALL		(NL80211_RRF_NO_IR | __NL80211_RRF_NO_IBSS)
+
 /**
  * enum nl80211_dfs_regions - regulatory DFS regions
  *
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 5ad66a83ef7f..c22cbb57b49d 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -526,7 +526,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		ieee80211_hw_config(local, 0);
 
 		if ((req->channels[0]->flags &
-		     IEEE80211_CHAN_PASSIVE_SCAN) ||
+		     IEEE80211_CHAN_NO_IR) ||
 		    !local->scan_req->n_ssids) {
 			next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
 		} else {
@@ -572,7 +572,7 @@ ieee80211_scan_get_channel_time(struct ieee80211_channel *chan)
 	 * TODO: channel switching also consumes quite some time,
 	 * add that delay as well to get a better estimation
 	 */
-	if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN)
+	if (chan->flags & IEEE80211_CHAN_NO_IR)
 		return IEEE80211_PASSIVE_CHANNEL_TIME;
 	return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME;
 }
@@ -696,7 +696,7 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 	 *
 	 * In any case, it is not necessary for a passive scan.
 	 */
-	if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN ||
+	if (chan->flags & IEEE80211_CHAN_NO_IR ||
 	    !local->scan_req->n_ssids) {
 		*next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
 		local->next_scan_state = SCAN_DECISION;
@@ -881,7 +881,7 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 				struct ieee80211_channel *tmp_ch =
 				    &local->hw.wiphy->bands[band]->channels[i];
 
-				if (tmp_ch->flags & (IEEE80211_CHAN_NO_IBSS |
+				if (tmp_ch->flags & (IEEE80211_CHAN_NO_IR |
 						     IEEE80211_CHAN_DISABLED))
 					continue;
 
@@ -895,7 +895,7 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 
 		local->int_scan_req->n_channels = n_ch;
 	} else {
-		if (WARN_ON_ONCE(chan->flags & (IEEE80211_CHAN_NO_IBSS |
+		if (WARN_ON_ONCE(chan->flags & (IEEE80211_CHAN_NO_IR |
 						IEEE80211_CHAN_DISABLED)))
 			goto unlock;
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index c558b246ef00..5ad2e8b1f92c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1724,8 +1724,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 	 * radar detection by itself. We can do that later by adding a
 	 * monitor flag interfaces used for AP support.
 	 */
-	if ((chan->flags & (IEEE80211_CHAN_NO_IBSS | IEEE80211_CHAN_RADAR |
-			    IEEE80211_CHAN_PASSIVE_SCAN)))
+	if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)))
 		goto fail_rcu;
 
 	ieee80211_xmit(sdata, skb, chan->band);
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 9b8cc877eb19..344966496b70 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -467,8 +467,7 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
 
 	res = cfg80211_chandef_usable(wiphy, chandef,
 				      IEEE80211_CHAN_DISABLED |
-				      IEEE80211_CHAN_PASSIVE_SCAN |
-				      IEEE80211_CHAN_NO_IBSS |
+				      IEEE80211_CHAN_NO_IR |
 				      IEEE80211_CHAN_RADAR);
 
 	trace_cfg80211_return_bool(res);
diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk
index 42ed274e81f4..c808619ac9c6 100644
--- a/net/wireless/genregdb.awk
+++ b/net/wireless/genregdb.awk
@@ -107,10 +107,13 @@ active && /^[ \t]*\(/ {
 		} else if (flagarray[arg] == "PTMP-ONLY") {
 			flags = flags "\n\t\t\tNL80211_RRF_PTMP_ONLY | "
 		} else if (flagarray[arg] == "PASSIVE-SCAN") {
-			flags = flags "\n\t\t\tNL80211_RRF_PASSIVE_SCAN | "
+			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
 		} else if (flagarray[arg] == "NO-IBSS") {
-			flags = flags "\n\t\t\tNL80211_RRF_NO_IBSS | "
+			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
+		} else if (flagarray[arg] == "NO-IR") {
+			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
 		}
+
 	}
 	flags = flags "0"
 	printf "\t\tREG_RULE(%d, %d, %d, %d, %d, %s),\n", start, end, bw, gain, power, flags
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 9d797df56649..f79105712949 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -274,7 +274,7 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev,
 
 			for (i = 0; i < sband->n_channels; i++) {
 				chan = &sband->channels[i];
-				if (chan->flags & IEEE80211_CHAN_NO_IBSS)
+				if (chan->flags & IEEE80211_CHAN_NO_IR)
 					continue;
 				if (chan->flags & IEEE80211_CHAN_DISABLED)
 					continue;
@@ -345,7 +345,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 		chan = ieee80211_get_channel(wdev->wiphy, freq);
 		if (!chan)
 			return -EINVAL;
-		if (chan->flags & IEEE80211_CHAN_NO_IBSS ||
+		if (chan->flags & IEEE80211_CHAN_NO_IR ||
 		    chan->flags & IEEE80211_CHAN_DISABLED)
 			return -EINVAL;
 	}
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index 0553fd4d85ae..b0e1869de7de 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -141,8 +141,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 
 			for (i = 0; i < sband->n_channels; i++) {
 				chan = &sband->channels[i];
-				if (chan->flags & (IEEE80211_CHAN_NO_IBSS |
-						   IEEE80211_CHAN_PASSIVE_SCAN |
+				if (chan->flags & (IEEE80211_CHAN_NO_IR |
 						   IEEE80211_CHAN_DISABLED |
 						   IEEE80211_CHAN_RADAR))
 					continue;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index a7f4e7902104..41af3a0e9961 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -545,12 +545,12 @@ static int nl80211_msg_put_channel(struct sk_buff *msg,
 	if ((chan->flags & IEEE80211_CHAN_DISABLED) &&
 	    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DISABLED))
 		goto nla_put_failure;
-	if ((chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) &&
-	    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_PASSIVE_SCAN))
-		goto nla_put_failure;
-	if ((chan->flags & IEEE80211_CHAN_NO_IBSS) &&
-	    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_IBSS))
-		goto nla_put_failure;
+	if (chan->flags & IEEE80211_CHAN_NO_IR) {
+		if (nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_IR))
+			goto nla_put_failure;
+		if (nla_put_flag(msg, __NL80211_FREQUENCY_ATTR_NO_IBSS))
+			goto nla_put_failure;
+	}
 	if (chan->flags & IEEE80211_CHAN_RADAR) {
 		if (nla_put_flag(msg, NL80211_FREQUENCY_ATTR_RADAR))
 			goto nla_put_failure;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 7da67fd0b418..e4e3337ba296 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -163,35 +163,29 @@ static const struct ieee80211_regdomain world_regdom = {
 		REG_RULE(2412-10, 2462+10, 40, 6, 20, 0),
 		/* IEEE 802.11b/g, channels 12..13. */
 		REG_RULE(2467-10, 2472+10, 40, 6, 20,
-			NL80211_RRF_PASSIVE_SCAN |
-			NL80211_RRF_NO_IBSS),
+			NL80211_RRF_NO_IR),
 		/* IEEE 802.11 channel 14 - Only JP enables
 		 * this and for 802.11b only */
 		REG_RULE(2484-10, 2484+10, 20, 6, 20,
-			NL80211_RRF_PASSIVE_SCAN |
-			NL80211_RRF_NO_IBSS |
+			NL80211_RRF_NO_IR |
 			NL80211_RRF_NO_OFDM),
 		/* IEEE 802.11a, channel 36..48 */
 		REG_RULE(5180-10, 5240+10, 160, 6, 20,
-                        NL80211_RRF_PASSIVE_SCAN |
-                        NL80211_RRF_NO_IBSS),
+                        NL80211_RRF_NO_IR),
 
 		/* IEEE 802.11a, channel 52..64 - DFS required */
 		REG_RULE(5260-10, 5320+10, 160, 6, 20,
-			NL80211_RRF_PASSIVE_SCAN |
-			NL80211_RRF_NO_IBSS |
+			NL80211_RRF_NO_IR |
 			NL80211_RRF_DFS),
 
 		/* IEEE 802.11a, channel 100..144 - DFS required */
 		REG_RULE(5500-10, 5720+10, 160, 6, 20,
-			NL80211_RRF_PASSIVE_SCAN |
-			NL80211_RRF_NO_IBSS |
+			NL80211_RRF_NO_IR |
 			NL80211_RRF_DFS),
 
 		/* IEEE 802.11a, channel 149..165 */
 		REG_RULE(5745-10, 5825+10, 80, 6, 20,
-			NL80211_RRF_PASSIVE_SCAN |
-			NL80211_RRF_NO_IBSS),
+			NL80211_RRF_NO_IR),
 
 		/* IEEE 802.11ad (60gHz), channels 1..3 */
 		REG_RULE(56160+2160*1-1080, 56160+2160*3+1080, 2160, 0, 0, 0),
@@ -698,10 +692,8 @@ regdom_intersect(const struct ieee80211_regdomain *rd1,
 static u32 map_regdom_flags(u32 rd_flags)
 {
 	u32 channel_flags = 0;
-	if (rd_flags & NL80211_RRF_PASSIVE_SCAN)
-		channel_flags |= IEEE80211_CHAN_PASSIVE_SCAN;
-	if (rd_flags & NL80211_RRF_NO_IBSS)
-		channel_flags |= IEEE80211_CHAN_NO_IBSS;
+	if (rd_flags & NL80211_RRF_NO_IR_ALL)
+		channel_flags |= IEEE80211_CHAN_NO_IR;
 	if (rd_flags & NL80211_RRF_DFS)
 		channel_flags |= IEEE80211_CHAN_RADAR;
 	if (rd_flags & NL80211_RRF_NO_OFDM)
@@ -1066,13 +1058,8 @@ static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx,
 	chan_before.center_freq = chan->center_freq;
 	chan_before.flags = chan->flags;
 
-	if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) {
-		chan->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN;
-		channel_changed = true;
-	}
-
-	if (chan->flags & IEEE80211_CHAN_NO_IBSS) {
-		chan->flags &= ~IEEE80211_CHAN_NO_IBSS;
+	if (chan->flags & IEEE80211_CHAN_NO_IR) {
+		chan->flags &= ~IEEE80211_CHAN_NO_IR;
 		channel_changed = true;
 	}
 
-- 
cgit v1.2.3


From 01e0daa43f129fc1a6bc6f1197343c0293af866d Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Sat, 9 Nov 2013 14:57:54 +0100
Subject: cfg80211: fix reporting 5/10 MHz support to user space

nla_put_flag needs a real nl80211 attribute id, not a wiphy flag bit.
While at it, split 5 and 10 MHz capability flags in case we ever need
to support hardware that can only do one of the two.

Also move the flag settings to the split-only information so we don't
increase the space needed for old userspace.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
[change location of flag setting]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 8 ++++++++
 net/wireless/nl80211.c       | 9 +++++----
 2 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 7e25164adfe9..129b7b087148 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1515,6 +1515,11 @@ enum nl80211_commands {
  *	to react to radar events, e.g. initiate a channel switch or leave the
  *	IBSS network.
  *
+ * @NL80211_ATTR_SUPPORT_5_MHZ: A flag indicating that the device supports
+ *	5 MHz channel bandwidth.
+ * @NL80211_ATTR_SUPPORT_10_MHZ: A flag indicating that the device supports
+ *	10 MHz channel bandwidth.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1831,6 +1836,9 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_HANDLE_DFS,
 
+	NL80211_ATTR_SUPPORT_5_MHZ,
+	NL80211_ATTR_SUPPORT_10_MHZ,
+
 	/* 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 79632edebb6c..8c83fbb3824f 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1228,10 +1228,6 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if ((dev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) &&
 		    nla_put_flag(msg, NL80211_ATTR_TDLS_EXTERNAL_SETUP))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) &&
-		    nla_put_flag(msg, WIPHY_FLAG_SUPPORTS_5_10_MHZ))
-			goto nla_put_failure;
-
 		state->split_start++;
 		if (state->split)
 			break;
@@ -1560,6 +1556,11 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if (nl80211_send_coalesce(msg, dev))
 			goto nla_put_failure;
 
+		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) &&
+		    (nla_put_flag(msg, NL80211_ATTR_SUPPORT_5_MHZ) ||
+		     nla_put_flag(msg, NL80211_ATTR_SUPPORT_10_MHZ)))
+			goto nla_put_failure;
+
 		/* done */
 		state->split_start = 0;
 		break;
-- 
cgit v1.2.3


From 60f4a7b1676c9028edb90e22f6994ebb698c9088 Mon Sep 17 00:00:00 2001
From: Marek Kwaczynski <marek.kwaczynski@tieto.com>
Date: Tue, 3 Dec 2013 10:04:59 +0100
Subject: nl80211/cfg80211: Set Operating Mode Notification

This attribute is needed for setting Operating Mode Notification
in AP mode from User Space. This functionality is required when
User Space received Assoc Request contains Operation Mode
Notification element.

Signed-off-by: Marek Kwaczynski <marek.kwaczynski@tieto.com>
[fix typos, nl80211 documentation]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 4 ++++
 include/uapi/linux/nl80211.h | 6 ++++++
 net/wireless/nl80211.c       | 7 +++++++
 3 files changed, 17 insertions(+)

(limited to 'include/uapi')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index e9abc7b536cd..47290a4059ae 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -747,6 +747,8 @@ enum station_parameters_apply_mask {
  * @supported_channels_len: number of supported channels
  * @supported_oper_classes: supported oper classes in IEEE 802.11 format
  * @supported_oper_classes_len: number of supported operating classes
+ * @opmode_notif: operating mode field from Operating Mode Notification
+ * @opmode_notif_used: information if operating mode field is used
  */
 struct station_parameters {
 	const u8 *supported_rates;
@@ -770,6 +772,8 @@ struct station_parameters {
 	u8 supported_channels_len;
 	const u8 *supported_oper_classes;
 	u8 supported_oper_classes_len;
+	u8 opmode_notif;
+	bool opmode_notif_used;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 129b7b087148..9a4d0e18251c 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1520,6 +1520,10 @@ enum nl80211_commands {
  * @NL80211_ATTR_SUPPORT_10_MHZ: A flag indicating that the device supports
  *	10 MHz channel bandwidth.
  *
+ * @NL80211_ATTR_OPMODE_NOTIF: Operating mode field from Operating Mode
+ *	Notification Element based on association request when used with
+ *	%NL80211_CMD_NEW_STATION; u8 attribute.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1839,6 +1843,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_SUPPORT_5_MHZ,
 	NL80211_ATTR_SUPPORT_10_MHZ,
 
+	NL80211_ATTR_OPMODE_NOTIF,
+
 	/* 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 95882a788b5b..93e3356091ff 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -357,6 +357,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY },
 	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
 	[NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG },
+	[NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 },
 };
 
 /* policy for the key attributes */
@@ -4132,6 +4133,12 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 		params.vht_capa =
 			nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
 
+	if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) {
+		params.opmode_notif_used = true;
+		params.opmode_notif =
+			nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]);
+	}
+
 	if (info->attrs[NL80211_ATTR_STA_PLINK_ACTION]) {
 		params.plink_action =
 			nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]);
-- 
cgit v1.2.3


From ad7e718c9b4f717823fd920a0103f7b0fb06183f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 13 Nov 2013 13:37:47 +0100
Subject: nl80211: vendor command support

Add support for vendor-specific commands to nl80211. This is
intended to be used for really vendor-specific functionality
that can't be implemented in a generic fashion for any reason.
It's *NOT* intended to be used for any normal/generic feature
or any optimisations that could be implemented across drivers.

Currently, only vendor commands (with replies) are supported,
no dump operations or vendor-specific notifications.

Also add a function wdev_to_ieee80211_vif() to mac80211 which
is needed for mac80211-based drivers wanting to implement any
vendor commands.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 116 ++++++++++++++++++++-
 include/net/mac80211.h       |  13 +++
 include/uapi/linux/nl80211.h |  41 ++++++++
 net/mac80211/util.c          |  11 ++
 net/wireless/core.h          |   4 +-
 net/wireless/nl80211.c       | 237 ++++++++++++++++++++++++++++++-------------
 6 files changed, 348 insertions(+), 74 deletions(-)

(limited to 'include/uapi')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 47290a4059ae..884ac69b5e55 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2679,6 +2679,34 @@ struct wiphy_coalesce_support {
 	int max_pkt_offset;
 };
 
+/**
+ * enum wiphy_vendor_command_flags - validation flags for vendor commands
+ * @WIPHY_VENDOR_CMD_NEED_WDEV: vendor command requires wdev
+ * @WIPHY_VENDOR_CMD_NEED_NETDEV: vendor command requires netdev
+ * @WIPHY_VENDOR_CMD_NEED_RUNNING: interface/wdev must be up & running
+ *	(must be combined with %_WDEV or %_NETDEV)
+ */
+enum wiphy_vendor_command_flags {
+	WIPHY_VENDOR_CMD_NEED_WDEV = BIT(0),
+	WIPHY_VENDOR_CMD_NEED_NETDEV = BIT(1),
+	WIPHY_VENDOR_CMD_NEED_RUNNING = BIT(2),
+};
+
+/**
+ * struct wiphy_vendor_command - vendor command definition
+ * @info: vendor command identifying information, as used in nl80211
+ * @flags: flags, see &enum wiphy_vendor_command_flags
+ * @doit: callback for the operation, note that wdev is %NULL if the
+ *	flags didn't ask for a wdev and non-%NULL otherwise; the data
+ *	pointer may be %NULL if userspace provided no data at all
+ */
+struct wiphy_vendor_command {
+	struct nl80211_vendor_cmd_info info;
+	u32 flags;
+	int (*doit)(struct wiphy *wiphy, struct wireless_dev *wdev,
+		    const void *data, int data_len);
+};
+
 /**
  * struct wiphy - wireless hardware description
  * @reg_notifier: the driver's regulatory notification callback,
@@ -2792,6 +2820,9 @@ struct wiphy_coalesce_support {
  * @extended_capabilities_mask: mask of the valid values
  * @extended_capabilities_len: length of the extended capabilities
  * @coalesce: packet coalescing support information
+ *
+ * @vendor_commands: array of vendor commands supported by the hardware
+ * @n_vendor_commands: number of vendor commands
  */
 struct wiphy {
 	/* assign these fields before you register the wiphy */
@@ -2903,6 +2934,9 @@ struct wiphy {
 
 	const struct wiphy_coalesce_support *coalesce;
 
+	const struct wiphy_vendor_command *vendor_commands;
+	int n_vendor_commands;
+
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
@@ -3847,6 +3881,75 @@ void wiphy_rfkill_start_polling(struct wiphy *wiphy);
  */
 void wiphy_rfkill_stop_polling(struct wiphy *wiphy);
 
+/**
+ * DOC: Vendor commands
+ *
+ * Occasionally, there are special protocol or firmware features that
+ * can't be implemented very openly. For this and similar cases, the
+ * vendor command functionality allows implementing the features with
+ * (typically closed-source) userspace and firmware, using nl80211 as
+ * the configuration mechanism.
+ *
+ * A driver supporting vendor commands must register them as an array
+ * in struct wiphy, with handlers for each one, each command has an
+ * OUI and sub command ID to identify it.
+ *
+ * Note that this feature should not be (ab)used to implement protocol
+ * features that could openly be shared across drivers. In particular,
+ * it must never be required to use vendor commands to implement any
+ * "normal" functionality that higher-level userspace like connection
+ * managers etc. need.
+ */
+
+struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
+					   enum nl80211_commands cmd,
+					   enum nl80211_attrs attr,
+					   int approxlen);
+
+/**
+ * cfg80211_vendor_cmd_alloc_reply_skb - allocate vendor command reply
+ * @wiphy: the wiphy
+ * @approxlen: an upper bound of the length of the data that will
+ *	be put into the skb
+ *
+ * This function allocates and pre-fills an skb for a reply to
+ * a vendor command. Since it is intended for a reply, calling
+ * it outside of a vendor command's doit() operation is invalid.
+ *
+ * The returned skb is pre-filled with some identifying data in
+ * a way that any data that is put into the skb (with skb_put(),
+ * nla_put() or similar) will end up being within the
+ * %NL80211_ATTR_VENDOR_DATA attribute, so all that needs to be done
+ * with the skb is adding data for the corresponding userspace tool
+ * which can then read that data out of the vendor data attribute.
+ * You must not modify the skb in any other way.
+ *
+ * When done, call cfg80211_vendor_cmd_reply() with the skb and return
+ * its error code as the result of the doit() operation.
+ *
+ * Return: An allocated and pre-filled skb. %NULL if any errors happen.
+ */
+static inline struct sk_buff *
+cfg80211_vendor_cmd_alloc_reply_skb(struct wiphy *wiphy, int approxlen)
+{
+	return __cfg80211_alloc_reply_skb(wiphy, NL80211_CMD_VENDOR,
+					  NL80211_ATTR_VENDOR_DATA, approxlen);
+}
+
+/**
+ * cfg80211_vendor_cmd_reply - send the reply skb
+ * @skb: The skb, must have been allocated with
+ *	cfg80211_vendor_cmd_alloc_reply_skb()
+ *
+ * Since calling this function will usually be the last thing
+ * before returning from the vendor command doit() you should
+ * return the error code.  Note that this function consumes the
+ * skb regardless of the return value.
+ *
+ * Return: An error code or 0 on success.
+ */
+int cfg80211_vendor_cmd_reply(struct sk_buff *skb);
+
 #ifdef CONFIG_NL80211_TESTMODE
 /**
  * DOC: Test mode
@@ -3882,8 +3985,12 @@ void wiphy_rfkill_stop_polling(struct wiphy *wiphy);
  *
  * Return: An allocated and pre-filled skb. %NULL if any errors happen.
  */
-struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy,
-						  int approxlen);
+static inline struct sk_buff *
+cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy, int approxlen)
+{
+	return __cfg80211_alloc_reply_skb(wiphy, NL80211_CMD_TESTMODE,
+					  NL80211_ATTR_TESTDATA, approxlen);
+}
 
 /**
  * cfg80211_testmode_reply - send the reply skb
@@ -3897,7 +4004,10 @@ struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy,
  *
  * Return: An error code or 0 on success.
  */
-int cfg80211_testmode_reply(struct sk_buff *skb);
+static inline int cfg80211_testmode_reply(struct sk_buff *skb)
+{
+	return cfg80211_vendor_cmd_reply(skb);
+}
 
 /**
  * cfg80211_testmode_alloc_event_skb - allocate testmode event
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 73d99bc3e636..c014acc09ebc 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1162,6 +1162,19 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif)
 	return false;
 }
 
+/**
+ * wdev_to_ieee80211_vif - return a vif struct from a wdev
+ * @wdev: the wdev to get the vif for
+ *
+ * This can be used by mac80211 drivers with direct cfg80211 APIs
+ * (like the vendor commands) that get a wdev.
+ *
+ * Note that this function may return %NULL if the given wdev isn't
+ * associated with a vif that the driver knows about (e.g. monitor
+ * or AP_VLAN interfaces.)
+ */
+struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
+
 /**
  * enum ieee80211_key_flags - key flags
  *
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 9a4d0e18251c..72ba3584c90d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -693,6 +693,15 @@
  *	other station that transmission must be blocked until the channel
  *	switch is complete.
  *
+ * @NL80211_CMD_VENDOR: Vendor-specified command/event. The command is specified
+ *	by the %NL80211_ATTR_VENDOR_ID attribute and a sub-command in
+ *	%NL80211_ATTR_VENDOR_SUBCMD. Parameter(s) can be transported in
+ *	%NL80211_ATTR_VENDOR_DATA.
+ *	For feature advertisement, the %NL80211_ATTR_VENDOR_DATA attribute is
+ *	used in the wiphy data as a nested attribute containing descriptions
+ *	(&struct nl80211_vendor_cmd_info) of the supported vendor commands.
+ *	This may also be sent as an event with the same attributes.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -860,6 +869,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_CHANNEL_SWITCH,
 
+	NL80211_CMD_VENDOR,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -1524,6 +1535,12 @@ enum nl80211_commands {
  *	Notification Element based on association request when used with
  *	%NL80211_CMD_NEW_STATION; u8 attribute.
  *
+ * @NL80211_ATTR_VENDOR_ID: The vendor ID, either a 24-bit OUI or, if
+ *	%NL80211_VENDOR_ID_IS_LINUX is set, a special Linux ID (not used yet)
+ * @NL80211_ATTR_VENDOR_SUBCMD: vendor sub-command
+ * @NL80211_ATTR_VENDOR_DATA: data for the vendor command, if any; this
+ *	attribute is also used for vendor command feature advertisement
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1845,6 +1862,10 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_OPMODE_NOTIF,
 
+	NL80211_ATTR_VENDOR_ID,
+	NL80211_ATTR_VENDOR_SUBCMD,
+	NL80211_ATTR_VENDOR_DATA,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -3965,4 +3986,24 @@ enum nl80211_rxmgmt_flags {
 	NL80211_RXMGMT_FLAG_ANSWERED = 1 << 0,
 };
 
+/*
+ * If this flag is unset, the lower 24 bits are an OUI, if set
+ * a Linux nl80211 vendor ID is used (no such IDs are allocated
+ * yet, so that's not valid so far)
+ */
+#define NL80211_VENDOR_ID_IS_LINUX	0x80000000
+
+/**
+ * struct nl80211_vendor_cmd_info - vendor command data
+ * @vendor_id: If the %NL80211_VENDOR_ID_IS_LINUX flag is clear, then the
+ *	value is a 24-bit OUI; if it is set then a separately allocated ID
+ *	may be used, but no such IDs are allocated yet. New IDs should be
+ *	added to this file when needed.
+ * @subcmd: sub-command ID for the command
+ */
+struct nl80211_vendor_cmd_info {
+	__u32 vendor_id;
+	__u32 subcmd;
+};
+
 #endif /* __LINUX_NL80211_H */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 06265d7f8cc3..4a376a724153 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -642,6 +642,17 @@ void ieee80211_iterate_active_interfaces_rtnl(
 }
 EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl);
 
+struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+
+	if (!ieee80211_sdata_running(sdata) ||
+	    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+		return NULL;
+	return &sdata->vif;
+}
+EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif);
+
 /*
  * Nothing should have been stuffed into the workqueue during
  * the suspend->resume cycle. If this WARN is seen then there
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 6716c5c3f748..ac77644cf894 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -67,9 +67,7 @@ struct cfg80211_registered_device {
 	struct work_struct scan_done_wk;
 	struct work_struct sched_scan_results_wk;
 
-#ifdef CONFIG_NL80211_TESTMODE
-	struct genl_info *testmode_info;
-#endif
+	struct genl_info *cur_cmd_info;
 
 	struct work_struct conn_work;
 	struct work_struct event_work;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index bdcf256e3628..6989989de092 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -358,6 +358,9 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
 	[NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG },
 	[NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 },
+	[NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 },
+	[NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
+	[NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
 };
 
 /* policy for the key attributes */
@@ -1166,6 +1169,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 	struct nlattr *nl_bands, *nl_band;
 	struct nlattr *nl_freqs, *nl_freq;
 	struct nlattr *nl_cmds;
+	struct nlattr *nl_vendor_cmds;
 	enum ieee80211_band band;
 	struct ieee80211_channel *chan;
 	int i;
@@ -1561,6 +1565,19 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		    (nla_put_flag(msg, NL80211_ATTR_SUPPORT_5_MHZ) ||
 		     nla_put_flag(msg, NL80211_ATTR_SUPPORT_10_MHZ)))
 			goto nla_put_failure;
+		state->split_start++;
+		break;
+	case 11:
+		nl_vendor_cmds = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA);
+		if (!nl_vendor_cmds)
+			goto nla_put_failure;
+
+		for (i = 0; i < dev->wiphy.n_vendor_commands; i++)
+			if (nla_put(msg, i + 1,
+				    sizeof(struct nl80211_vendor_cmd_info),
+				    &dev->wiphy.vendor_commands[i].info))
+				goto nla_put_failure;
+		nla_nest_end(msg, nl_vendor_cmds);
 
 		/* done */
 		state->split_start = 0;
@@ -6682,6 +6699,40 @@ static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+static struct sk_buff *
+__cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
+			    int approxlen, u32 portid, u32 seq,
+			    enum nl80211_commands cmd,
+			    enum nl80211_attrs attr, gfp_t gfp)
+{
+	struct sk_buff *skb;
+	void *hdr;
+	struct nlattr *data;
+
+	skb = nlmsg_new(approxlen + 100, gfp);
+	if (!skb)
+		return NULL;
+
+	hdr = nl80211hdr_put(skb, portid, seq, 0, cmd);
+	if (!hdr) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
+		goto nla_put_failure;
+	data = nla_nest_start(skb, attr);
+
+	((void **)skb->cb)[0] = rdev;
+	((void **)skb->cb)[1] = hdr;
+	((void **)skb->cb)[2] = data;
+
+	return skb;
+
+ nla_put_failure:
+	kfree_skb(skb);
+	return NULL;
+}
 
 #ifdef CONFIG_NL80211_TESTMODE
 static struct genl_multicast_group nl80211_testmode_mcgrp = {
@@ -6710,11 +6761,11 @@ static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NL80211_ATTR_TESTDATA])
 		return -EINVAL;
 
-	rdev->testmode_info = info;
+	rdev->cur_cmd_info = info;
 	err = rdev_testmode_cmd(rdev, wdev,
 				nla_data(info->attrs[NL80211_ATTR_TESTDATA]),
 				nla_len(info->attrs[NL80211_ATTR_TESTDATA]));
-	rdev->testmode_info = NULL;
+	rdev->cur_cmd_info = NULL;
 
 	return err;
 }
@@ -6814,77 +6865,14 @@ static int nl80211_testmode_dump(struct sk_buff *skb,
 	return err;
 }
 
-static struct sk_buff *
-__cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev,
-			      int approxlen, u32 portid, u32 seq, gfp_t gfp)
-{
-	struct sk_buff *skb;
-	void *hdr;
-	struct nlattr *data;
-
-	skb = nlmsg_new(approxlen + 100, gfp);
-	if (!skb)
-		return NULL;
-
-	hdr = nl80211hdr_put(skb, portid, seq, 0, NL80211_CMD_TESTMODE);
-	if (!hdr) {
-		kfree_skb(skb);
-		return NULL;
-	}
-
-	if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
-		goto nla_put_failure;
-	data = nla_nest_start(skb, NL80211_ATTR_TESTDATA);
-
-	((void **)skb->cb)[0] = rdev;
-	((void **)skb->cb)[1] = hdr;
-	((void **)skb->cb)[2] = data;
-
-	return skb;
-
- nla_put_failure:
-	kfree_skb(skb);
-	return NULL;
-}
-
-struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy,
-						  int approxlen)
-{
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
-
-	if (WARN_ON(!rdev->testmode_info))
-		return NULL;
-
-	return __cfg80211_testmode_alloc_skb(rdev, approxlen,
-				rdev->testmode_info->snd_portid,
-				rdev->testmode_info->snd_seq,
-				GFP_KERNEL);
-}
-EXPORT_SYMBOL(cfg80211_testmode_alloc_reply_skb);
-
-int cfg80211_testmode_reply(struct sk_buff *skb)
-{
-	struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
-	void *hdr = ((void **)skb->cb)[1];
-	struct nlattr *data = ((void **)skb->cb)[2];
-
-	if (WARN_ON(!rdev->testmode_info)) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
-	nla_nest_end(skb, data);
-	genlmsg_end(skb, hdr);
-	return genlmsg_reply(skb, rdev->testmode_info);
-}
-EXPORT_SYMBOL(cfg80211_testmode_reply);
-
 struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy,
 						  int approxlen, gfp_t gfp)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
 
-	return __cfg80211_testmode_alloc_skb(rdev, approxlen, 0, 0, gfp);
+	return __cfg80211_alloc_vendor_skb(rdev, approxlen, 0, 0,
+					   NL80211_CMD_TESTMODE,
+					   NL80211_ATTR_TESTDATA, gfp);
 }
 EXPORT_SYMBOL(cfg80211_testmode_alloc_event_skb);
 
@@ -8867,6 +8855,111 @@ static int nl80211_crit_protocol_stop(struct sk_buff *skb,
 	return 0;
 }
 
+static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct wireless_dev *wdev =
+		__cfg80211_wdev_from_attrs(genl_info_net(info), info->attrs);
+	int i, err;
+	u32 vid, subcmd;
+
+	if (!rdev->wiphy.vendor_commands)
+		return -EOPNOTSUPP;
+
+	if (IS_ERR(wdev)) {
+		err = PTR_ERR(wdev);
+		if (err != -EINVAL)
+			return err;
+		wdev = NULL;
+	} else if (wdev->wiphy != &rdev->wiphy) {
+		return -EINVAL;
+	}
+
+	if (!info->attrs[NL80211_ATTR_VENDOR_ID] ||
+	    !info->attrs[NL80211_ATTR_VENDOR_SUBCMD])
+		return -EINVAL;
+
+	vid = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_ID]);
+	subcmd = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_SUBCMD]);
+	for (i = 0; i < rdev->wiphy.n_vendor_commands; i++) {
+		const struct wiphy_vendor_command *vcmd;
+		void *data = NULL;
+		int len = 0;
+
+		vcmd = &rdev->wiphy.vendor_commands[i];
+
+		if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
+			continue;
+
+		if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
+				   WIPHY_VENDOR_CMD_NEED_NETDEV)) {
+			if (!wdev)
+				return -EINVAL;
+			if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
+			    !wdev->netdev)
+				return -EINVAL;
+
+			if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
+				if (wdev->netdev &&
+				    !netif_running(wdev->netdev))
+					return -ENETDOWN;
+				if (!wdev->netdev && !wdev->p2p_started)
+					return -ENETDOWN;
+			}
+		} else {
+			wdev = NULL;
+		}
+
+		if (info->attrs[NL80211_ATTR_VENDOR_DATA]) {
+			data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]);
+			len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]);
+		}
+
+		rdev->cur_cmd_info = info;
+		err = rdev->wiphy.vendor_commands[i].doit(&rdev->wiphy, wdev,
+							  data, len);
+		rdev->cur_cmd_info = NULL;
+		return err;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
+					   enum nl80211_commands cmd,
+					   enum nl80211_attrs attr,
+					   int approxlen)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+
+	if (WARN_ON(!rdev->cur_cmd_info))
+		return NULL;
+
+	return __cfg80211_alloc_vendor_skb(rdev, approxlen,
+					   rdev->cur_cmd_info->snd_portid,
+					   rdev->cur_cmd_info->snd_seq,
+					   cmd, attr, GFP_KERNEL);
+}
+EXPORT_SYMBOL(__cfg80211_alloc_reply_skb);
+
+int cfg80211_vendor_cmd_reply(struct sk_buff *skb)
+{
+	struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
+	void *hdr = ((void **)skb->cb)[1];
+	struct nlattr *data = ((void **)skb->cb)[2];
+
+	if (WARN_ON(!rdev->cur_cmd_info)) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	nla_nest_end(skb, data);
+	genlmsg_end(skb, hdr);
+	return genlmsg_reply(skb, rdev->cur_cmd_info);
+}
+EXPORT_SYMBOL_GPL(cfg80211_vendor_cmd_reply);
+
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -9591,6 +9684,14 @@ static struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_VENDOR,
+		.doit = nl80211_vendor_cmd,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_WIPHY |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_multicast_group nl80211_mlme_mcgrp = {
-- 
cgit v1.2.3


From d1e33e654ef6bb3dee766353ed9dd31e7dcb8a94 Mon Sep 17 00:00:00 2001
From: Janusz Dziedzic <janusz.dziedzic@tieto.com>
Date: Thu, 5 Dec 2013 10:02:15 +0100
Subject: cfg80211: in bitrate_mask, rename mcs to ht_mcs

Rename NL80211_TXRATE_MCS to NL80211_TXRATE_HT and also
rename mcs to ht_mcs in struct cfg80211_bitrate_mask.

Signed-off-by: Janusz Dziedzic <janusz.dziedzic@tieto.com>
[reword commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/wmi.c   |  6 +++---
 drivers/net/wireless/mwifiex/cfg80211.c |  6 +++---
 include/net/cfg80211.h                  |  2 +-
 include/uapi/linux/nl80211.h            |  6 ++++--
 net/mac80211/cfg.c                      |  4 ++--
 net/wireless/nl80211.c                  | 18 +++++++++---------
 6 files changed, 22 insertions(+), 20 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index 546d5da0b894..4f16d79c9eb1 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -2754,9 +2754,9 @@ static int ath6kl_set_bitrate_mask64(struct wmi *wmi, u8 if_idx,
 				mask->control[band].legacy << 4;
 
 		/* copy mcs rate mask */
-		mcsrate = mask->control[band].mcs[1];
+		mcsrate = mask->control[band].ht_mcs[1];
 		mcsrate <<= 8;
-		mcsrate |= mask->control[band].mcs[0];
+		mcsrate |= mask->control[band].ht_mcs[0];
 		ratemask[band] |= mcsrate << 12;
 		ratemask[band] |= mcsrate << 28;
 	}
@@ -2806,7 +2806,7 @@ static int ath6kl_set_bitrate_mask32(struct wmi *wmi, u8 if_idx,
 				mask->control[band].legacy << 4;
 
 		/* copy mcs rate mask */
-		mcsrate = mask->control[band].mcs[0];
+		mcsrate = mask->control[band].ht_mcs[0];
 		ratemask[band] |= mcsrate << 12;
 		ratemask[band] |= mcsrate << 20;
 	}
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 1c8116d46845..6f5e49b32e79 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1170,10 +1170,10 @@ static int mwifiex_cfg80211_set_bitrate_mask(struct wiphy *wiphy,
 	else
 		bitmap_rates[1] = mask->control[band].legacy;
 
-	/* Fill MCS rates */
-	bitmap_rates[2] = mask->control[band].mcs[0];
+	/* Fill HT MCS rates */
+	bitmap_rates[2] = mask->control[band].ht_mcs[0];
 	if (priv->adapter->hw_dev_mcs_support == HT_STREAM_2X2)
-		bitmap_rates[2] |= mask->control[band].mcs[1] << 8;
+		bitmap_rates[2] |= mask->control[band].ht_mcs[1] << 8;
 
 	return mwifiex_send_cmd_sync(priv, HostCmd_CMD_TX_RATE_CFG,
 				     HostCmd_ACT_GEN_SET, 0, bitmap_rates);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 884ac69b5e55..6c3a650f3a8f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1766,7 +1766,7 @@ enum wiphy_params_flags {
 struct cfg80211_bitrate_mask {
 	struct {
 		u32 legacy;
-		u8 mcs[IEEE80211_HT_MCS_MASK_LEN];
+		u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN];
 	} control[IEEE80211_NUM_BANDS];
 };
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 72ba3584c90d..6e700645cd27 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3110,7 +3110,7 @@ enum nl80211_key_attributes {
  *	in an array of rates as defined in IEEE 802.11 7.3.2.2 (u8 values with
  *	1 = 500 kbps) but without the IE length restriction (at most
  *	%NL80211_MAX_SUPP_RATES in a single array).
- * @NL80211_TXRATE_MCS: HT (MCS) rates allowed for TX rate selection
+ * @NL80211_TXRATE_HT: HT (MCS) rates allowed for TX rate selection
  *	in an array of MCS numbers.
  * @__NL80211_TXRATE_AFTER_LAST: internal
  * @NL80211_TXRATE_MAX: highest TX rate attribute
@@ -3118,13 +3118,15 @@ enum nl80211_key_attributes {
 enum nl80211_tx_rate_attributes {
 	__NL80211_TXRATE_INVALID,
 	NL80211_TXRATE_LEGACY,
-	NL80211_TXRATE_MCS,
+	NL80211_TXRATE_HT,
 
 	/* keep last */
 	__NL80211_TXRATE_AFTER_LAST,
 	NL80211_TXRATE_MAX = __NL80211_TXRATE_AFTER_LAST - 1
 };
 
+#define NL80211_TXRATE_MCS NL80211_TXRATE_HT
+
 /**
  * enum nl80211_band - Frequency band
  * @NL80211_BAND_2GHZ: 2.4 GHz ISM band
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 754069cbb756..a74d61d520b0 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2588,8 +2588,8 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 		int j;
 
 		sdata->rc_rateidx_mask[i] = mask->control[i].legacy;
-		memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].mcs,
-		       sizeof(mask->control[i].mcs));
+		memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].ht_mcs,
+		       sizeof(mask->control[i].ht_mcs));
 
 		sdata->rc_has_mcs_mask[i] = false;
 		if (!sband)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f61b74c40d28..801e57da88b4 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7312,8 +7312,8 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband,
 static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = {
 	[NL80211_TXRATE_LEGACY] = { .type = NLA_BINARY,
 				    .len = NL80211_MAX_SUPP_RATES },
-	[NL80211_TXRATE_MCS] = { .type = NLA_BINARY,
-				 .len = NL80211_MAX_SUPP_HT_RATES },
+	[NL80211_TXRATE_HT] = { .type = NLA_BINARY,
+				.len = NL80211_MAX_SUPP_HT_RATES },
 };
 
 static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
@@ -7339,9 +7339,9 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 			continue;
 
 		mask.control[i].legacy = (1 << sband->n_bitrates) - 1;
-		memcpy(mask.control[i].mcs,
+		memcpy(mask.control[i].ht_mcs,
 		       sband->ht_cap.mcs.rx_mask,
-		       sizeof(mask.control[i].mcs));
+		       sizeof(mask.control[i].ht_mcs));
 	}
 
 	/* if no rates are given set it back to the defaults */
@@ -7372,12 +7372,12 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 			    nla_len(tb[NL80211_TXRATE_LEGACY]))
 				return -EINVAL;
 		}
-		if (tb[NL80211_TXRATE_MCS]) {
+		if (tb[NL80211_TXRATE_HT]) {
 			if (!ht_rateset_to_mask(
 					sband,
-					nla_data(tb[NL80211_TXRATE_MCS]),
-					nla_len(tb[NL80211_TXRATE_MCS]),
-					mask.control[band].mcs))
+					nla_data(tb[NL80211_TXRATE_HT]),
+					nla_len(tb[NL80211_TXRATE_HT]),
+					mask.control[band].ht_mcs))
 				return -EINVAL;
 		}
 
@@ -7388,7 +7388,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 				return -EINVAL;
 
 			for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++)
-				if (mask.control[band].mcs[i])
+				if (mask.control[band].ht_mcs[i])
 					break;
 
 			/* legacy and mcs rates may not be both empty */
-- 
cgit v1.2.3


From 4b2f13a25133b115eb56771bd4a8e71a82aea968 Mon Sep 17 00:00:00 2001
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Fri, 6 Dec 2013 06:28:48 -0800
Subject: sctp: Fix FSF address in file headers

Several files refer to an old address for the Free Software Foundation
in the file header comment.  Resolve by replacing the address with
the URL <http://www.gnu.org/licenses/> so that we do not have to keep
updating the header comments anytime the address changes.

CC: Vlad Yasevich <vyasevich@gmail.com>
CC: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sctp.h        | 5 ++---
 include/net/sctp/sctp.h     | 5 ++---
 include/net/sctp/sm.h       | 5 ++---
 include/net/sctp/structs.h  | 5 ++---
 include/net/sctp/tsnmap.h   | 5 ++---
 include/net/sctp/ulpevent.h | 5 ++---
 include/net/sctp/ulpqueue.h | 5 ++---
 include/uapi/linux/sctp.h   | 5 ++---
 net/sctp/associola.c        | 5 ++---
 net/sctp/auth.c             | 5 ++---
 net/sctp/bind_addr.c        | 5 ++---
 net/sctp/chunk.c            | 5 ++---
 net/sctp/command.c          | 5 ++---
 net/sctp/debug.c            | 5 ++---
 net/sctp/endpointola.c      | 5 ++---
 net/sctp/input.c            | 5 ++---
 net/sctp/inqueue.c          | 5 ++---
 net/sctp/ipv6.c             | 5 ++---
 net/sctp/objcnt.c           | 5 ++---
 net/sctp/output.c           | 5 ++---
 net/sctp/outqueue.c         | 5 ++---
 net/sctp/primitive.c        | 5 ++---
 net/sctp/proc.c             | 5 ++---
 net/sctp/protocol.c         | 5 ++---
 net/sctp/sm_make_chunk.c    | 5 ++---
 net/sctp/sm_sideeffect.c    | 5 ++---
 net/sctp/sm_statefuns.c     | 5 ++---
 net/sctp/sm_statetable.c    | 5 ++---
 net/sctp/socket.c           | 5 ++---
 net/sctp/ssnmap.c           | 5 ++---
 net/sctp/sysctl.c           | 5 ++---
 net/sctp/transport.c        | 5 ++---
 net/sctp/tsnmap.c           | 5 ++---
 net/sctp/ulpevent.c         | 5 ++---
 net/sctp/ulpqueue.c         | 5 ++---
 35 files changed, 70 insertions(+), 105 deletions(-)

(limited to 'include/uapi')

diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index 3bfe8d6ee248..c4c5eba26d9f 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -23,9 +23,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index c5fe80697f8d..610a8c8738fa 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -21,9 +21,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 4ef75af340b6..7f4eeb340a54 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -21,9 +21,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email addresses:
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ea0ca5f6e629..e416d6ac9c70 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -19,9 +19,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email addresses:
diff --git a/include/net/sctp/tsnmap.h b/include/net/sctp/tsnmap.h
index 54bbbe547303..31b8dbaad45a 100644
--- a/include/net/sctp/tsnmap.h
+++ b/include/net/sctp/tsnmap.h
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index 27b9f5c90153..daacb32b55b5 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -25,9 +25,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h
index b0cf5d54d717..e0dce07b8794 100644
--- a/include/net/sctp/ulpqueue.h
+++ b/include/net/sctp/ulpqueue.h
@@ -24,9 +24,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email addresses:
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index ca451e99b28b..266022a2be4a 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 68a27f9796d2..66882a26713b 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 46b5977978a1..5c9f64c1c906 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -16,9 +16,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 077bb070052b..871cdf9567e6 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -21,9 +21,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index f2044fcb9dd1..5573e425b0c0 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -18,9 +18,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/command.c b/net/sctp/command.c
index 3d9a9ff69c03..dd7375851618 100644
--- a/net/sctp/command.c
+++ b/net/sctp/command.c
@@ -19,9 +19,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/debug.c b/net/sctp/debug.c
index e89015d8935a..95d7b15dad21 100644
--- a/net/sctp/debug.c
+++ b/net/sctp/debug.c
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 09b8daac87c8..6ffb6c1b13b7 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -23,9 +23,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 98b69bbecdd9..66038533ca5c 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -23,9 +23,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 5856932fdc38..4de12afa13d4 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -24,9 +24,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 7567e6f1a920..32db816ffbaa 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -21,9 +21,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c
index 647396baa56f..0c28e8a55324 100644
--- a/net/sctp/objcnt.c
+++ b/net/sctp/objcnt.c
@@ -20,9 +20,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 0e2644d0a773..6371337e1fe7 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -20,9 +20,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index f51ba985a36e..b6b09f3f1a81 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c
index ce1ffd811775..ab8d9f96a177 100644
--- a/net/sctp/primitive.c
+++ b/net/sctp/primitive.c
@@ -23,9 +23,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 0c0642156842..de32e14f7398 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -16,9 +16,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 5e17092f4ada..19bd4c5bdae9 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -23,9 +23,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index fe690320b1e4..d9aaf9641aaa 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -23,9 +23,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 1a6eef39ab2f..02b7ad1ff467 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index dfe3f36ff2aa..dd0eba919a8b 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index c5999b2dde7d..a4f17437fb22 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 72046b9729a8..191cd9257806 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -28,9 +28,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/ssnmap.c b/net/sctp/ssnmap.c
index 6007124aefa0..b9c8521c1a98 100644
--- a/net/sctp/ssnmap.c
+++ b/net/sctp/ssnmap.c
@@ -18,9 +18,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 6b36561a1b3b..80b17b5df6bb 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -19,9 +19,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index e332efb124cc..1d4f3ac29baf 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -24,9 +24,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c
index fbda20028285..7635f9f2311d 100644
--- a/net/sctp/tsnmap.c
+++ b/net/sctp/tsnmap.c
@@ -21,9 +21,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 81089ed65456..85c64658bd0b 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -22,9 +22,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 1c1484ed605d..a67470083be8 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -21,9 +21,8 @@
  * See the GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING.  If not, write to
- * the Free Software Foundation, 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * along with GNU CC; see the file COPYING.  If not, see
+ * <http://www.gnu.org/licenses/>.
  *
  * Please send any bug reports or fixes you make to the
  * email address(es):
-- 
cgit v1.2.3


From e664eabd18c4581b21ea6f62e2e599df5a719a5b Mon Sep 17 00:00:00 2001
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Fri, 6 Dec 2013 09:13:42 -0800
Subject: netfilter: Fix FSF address in file headers

Several files refer to an old address for the Free Software Foundation
in the file header comment.  Resolve by replacing the address with
the URL <http://www.gnu.org/licenses/> so that we do not have to keep
updating the header comments anytime the address changes.

CC: netfilter@vger.kernel.org
CC: Pablo Neira Ayuso <pablo@netfilter.org>
CC: Patrick McHardy <kaber@trash.net>
CC: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/netfilter/xt_osf.h | 3 +--
 net/bridge/netfilter/ebt_vlan.c       | 3 +--
 net/netfilter/ipvs/ip_vs_nfct.c       | 3 +--
 net/netfilter/xt_connmark.c           | 3 +--
 net/netfilter/xt_osf.c                | 3 +--
 5 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h
index 18afa495f973..5d66caeba3ee 100644
--- a/include/uapi/linux/netfilter/xt_osf.h
+++ b/include/uapi/linux/netfilter/xt_osf.h
@@ -13,8 +13,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _XT_OSF_H
diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c
index eae67bf0446c..8d3f8c7651f0 100644
--- a/net/bridge/netfilter/ebt_vlan.c
+++ b/net/bridge/netfilter/ebt_vlan.c
@@ -14,8 +14,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/if_ether.h>
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index c8beafd401aa..d5f41514f577 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -19,8 +19,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  *
  * Authors:
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 7278145e6a68..69f78e96fdb4 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -17,8 +17,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/module.h>
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 647d989a01e6..7174611bd672 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -13,8 +13,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/module.h>
-- 
cgit v1.2.3


From f54b311142a92ea2e42598e347b84e1655caf8e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Dec 2013 22:36:05 -0800
Subject: tcp: auto corking

With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.

Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)

If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.

This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.

The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.

Using FQ/pacing is a way to increase the probability of
autocorking being triggered.

Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)

Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.

Tested:

Interesting effects when using line buffered commands under ssh.

Excellent performance results in term of cpu usage and total throughput.

lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39

 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':

      35209.439626 task-clock                #    2.901 CPUs utilized
             2,294 context-switches          #    0.065 K/sec
               101 CPU-migrations            #    0.003 K/sec
             4,079 page-faults               #    0.116 K/sec
    97,923,241,298 cycles                    #    2.781 GHz                     [83.31%]
    51,832,908,236 stalled-cycles-frontend   #   52.93% frontend cycles idle    [83.30%]
    25,697,986,603 stalled-cycles-backend    #   26.24% backend  cycles idle    [66.70%]
   102,225,978,536 instructions              #    1.04  insns per cycle
                                             #    0.51  stalled cycles per insn [83.38%]
    18,657,696,819 branches                  #  529.906 M/sec                   [83.29%]
        91,679,646 branch-misses             #    0.49% of all branches         [83.40%]

      12.136204899 seconds time elapsed

lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89

 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
      40045.864494 task-clock                #    3.301 CPUs utilized
               171 context-switches          #    0.004 K/sec
                53 CPU-migrations            #    0.001 K/sec
             4,080 page-faults               #    0.102 K/sec
   111,340,458,645 cycles                    #    2.780 GHz                     [83.34%]
    61,778,039,277 stalled-cycles-frontend   #   55.49% frontend cycles idle    [83.31%]
    29,295,522,759 stalled-cycles-backend    #   26.31% backend  cycles idle    [66.67%]
   108,654,349,355 instructions              #    0.98  insns per cycle
                                             #    0.57  stalled cycles per insn [83.34%]
    19,552,170,748 branches                  #  488.244 M/sec                   [83.34%]
       157,875,417 branch-misses             #    0.81% of all branches         [83.34%]

      12.130267788 seconds time elapsed

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 10 ++++++
 include/net/tcp.h                      |  1 +
 include/uapi/linux/snmp.h              |  1 +
 net/ipv4/proc.c                        |  1 +
 net/ipv4/sysctl_net_ipv4.c             |  9 +++++
 net/ipv4/tcp.c                         | 63 +++++++++++++++++++++++++++-------
 6 files changed, 72 insertions(+), 13 deletions(-)

(limited to 'include/uapi')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3c12d9a7ed00..12ba2cd9f03d 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -156,6 +156,16 @@ tcp_app_win - INTEGER
 	buffer. Value 0 is special, it means that nothing is reserved.
 	Default: 31
 
+tcp_autocorking - BOOLEAN
+	Enable TCP auto corking :
+	When applications do consecutive small write()/sendmsg() system calls,
+	we try to coalesce these small writes as much as possible, to lower
+	total amount of sent packets. This is done if at least one prior
+	packet for the flow is waiting in Qdisc queues or device transmit
+	queue. Applications can still use TCP_CORK for optimal behavior
+	when they know how/when to uncork their sockets.
+	Default : 1
+
 tcp_available_congestion_control - STRING
 	Shows the available congestion control choices that are registered.
 	More congestion control algorithms may be available as modules,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 70e55d200610..f7e1ab2139ef 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -282,6 +282,7 @@ extern int sysctl_tcp_limit_output_bytes;
 extern int sysctl_tcp_challenge_ack_limit;
 extern unsigned int sysctl_tcp_notsent_lowat;
 extern int sysctl_tcp_min_tso_segs;
+extern int sysctl_tcp_autocorking;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 1bdb4a39d1e1..bbaba22f2d1b 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -258,6 +258,7 @@ enum
 	LINUX_MIB_TCPFASTOPENCOOKIEREQD,	/* TCPFastOpenCookieReqd */
 	LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
 	LINUX_MIB_BUSYPOLLRXPACKETS,		/* BusyPollRxPackets */
+	LINUX_MIB_TCPAUTOCORKING,		/* TCPAutoCorking */
 	__LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 4a0335854b89..8ecd7ad959b4 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -279,6 +279,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
 	SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
 	SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
+	SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3d69ec8dac57..38c8ec90ff68 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -732,6 +732,15 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &zero,
 		.extra2		= &gso_max_segs,
 	},
+	{
+		.procname	= "tcp_autocorking",
+		.data		= &sysctl_tcp_autocorking,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{
 		.procname	= "udp_mem",
 		.data		= &sysctl_udp_mem,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c4638e6f0238..0ca87547becb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -285,6 +285,8 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 
 int sysctl_tcp_min_tso_segs __read_mostly = 2;
 
+int sysctl_tcp_autocorking __read_mostly = 1;
+
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
@@ -619,19 +621,52 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
 		tp->snd_up = tp->write_seq;
 }
 
-static inline void tcp_push(struct sock *sk, int flags, int mss_now,
-			    int nonagle)
+/* If a not yet filled skb is pushed, do not send it if
+ * we have packets in Qdisc or NIC queues :
+ * Because TX completion will happen shortly, it gives a chance
+ * to coalesce future sendmsg() payload into this skb, without
+ * need for a timer, and with no latency trade off.
+ * As packets containing data payload have a bigger truesize
+ * than pure acks (dataless) packets, the last check prevents
+ * autocorking if we only have an ACK in Qdisc/NIC queues.
+ */
+static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
+				int size_goal)
 {
-	if (tcp_send_head(sk)) {
-		struct tcp_sock *tp = tcp_sk(sk);
+	return skb->len < size_goal &&
+	       sysctl_tcp_autocorking &&
+	       atomic_read(&sk->sk_wmem_alloc) > skb->truesize;
+}
+
+static void tcp_push(struct sock *sk, int flags, int mss_now,
+		     int nonagle, int size_goal)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *skb;
 
-		if (!(flags & MSG_MORE) || forced_push(tp))
-			tcp_mark_push(tp, tcp_write_queue_tail(sk));
+	if (!tcp_send_head(sk))
+		return;
+
+	skb = tcp_write_queue_tail(sk);
+	if (!(flags & MSG_MORE) || forced_push(tp))
+		tcp_mark_push(tp, skb);
+
+	tcp_mark_urg(tp, flags);
+
+	if (tcp_should_autocork(sk, skb, size_goal)) {
 
-		tcp_mark_urg(tp, flags);
-		__tcp_push_pending_frames(sk, mss_now,
-					  (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
+		/* avoid atomic op if TSQ_THROTTLED bit is already set */
+		if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
+			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
+		}
+		return;
 	}
+
+	if (flags & MSG_MORE)
+		nonagle = TCP_NAGLE_CORK;
+
+	__tcp_push_pending_frames(sk, mss_now, nonagle);
 }
 
 static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
@@ -934,7 +969,8 @@ new_segment:
 wait_for_sndbuf:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-		tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+		tcp_push(sk, flags & ~MSG_MORE, mss_now,
+			 TCP_NAGLE_PUSH, size_goal);
 
 		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 			goto do_error;
@@ -944,7 +980,7 @@ wait_for_memory:
 
 out:
 	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
-		tcp_push(sk, flags, mss_now, tp->nonagle);
+		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	return copied;
 
 do_error:
@@ -1225,7 +1261,8 @@ wait_for_sndbuf:
 			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
 			if (copied)
-				tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+				tcp_push(sk, flags & ~MSG_MORE, mss_now,
+					 TCP_NAGLE_PUSH, size_goal);
 
 			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
 				goto do_error;
@@ -1236,7 +1273,7 @@ wait_for_memory:
 
 out:
 	if (copied)
-		tcp_push(sk, flags, mss_now, tp->nonagle);
+		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	release_sock(sk);
 	return copied + copied_syn;
 
-- 
cgit v1.2.3


From 479840ffdbe4242e8a25349218c8e0859223aa35 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 6 Dec 2013 09:45:21 +0100
Subject: ipv6 addrconf: extend ifa_flags to u32

There is no more space in u8 ifa_flags. So do what davem suffested and
add another netlink attr called IFA_FLAGS for carry more flags.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Thomas Haller <thaller@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h       |  4 ++--
 include/net/if_inet6.h       |  2 +-
 include/uapi/linux/if_addr.h |  4 ++++
 net/ipv6/addrconf.c          | 32 ++++++++++++++++++++------------
 4 files changed, 27 insertions(+), 15 deletions(-)

(limited to 'include/uapi')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 86505bfa5d2c..e70278eef12a 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -81,9 +81,9 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev,
 		       const struct in6_addr *daddr, unsigned int srcprefs,
 		       struct in6_addr *saddr);
 int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
-		      unsigned char banned_flags);
+		      u32 banned_flags);
 int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
-		    unsigned char banned_flags);
+		    u32 banned_flags);
 int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2);
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 76d54270f2e2..b58c36c1c3f6 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -50,8 +50,8 @@ struct inet6_ifaddr {
 
 	int			state;
 
+	__u32			flags;
 	__u8			dad_probes;
-	__u8			flags;
 
 	__u16			scope;
 
diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index 23357ab81a77..8ab0c2cc9b73 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -18,6 +18,9 @@ struct ifaddrmsg {
  * It makes no difference for normally configured broadcast interfaces,
  * but for point-to-point IFA_ADDRESS is DESTINATION address,
  * local address is supplied in IFA_LOCAL attribute.
+ *
+ * IFA_FLAGS is a u32 attribute that extends the u8 field ifa_flags.
+ * If present, the value from struct ifaddrmsg will be ignored.
  */
 enum {
 	IFA_UNSPEC,
@@ -28,6 +31,7 @@ enum {
 	IFA_ANYCAST,
 	IFA_CACHEINFO,
 	IFA_MULTICAST,
+	IFA_FLAGS,
 	__IFA_MAX,
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d5fa5b8c443e..334a7e114e1d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1407,7 +1407,7 @@ try_nextdev:
 EXPORT_SYMBOL(ipv6_dev_get_saddr);
 
 int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
-		      unsigned char banned_flags)
+		      u32 banned_flags)
 {
 	struct inet6_ifaddr *ifp;
 	int err = -EADDRNOTAVAIL;
@@ -1424,7 +1424,7 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
 }
 
 int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
-		    unsigned char banned_flags)
+		    u32 banned_flags)
 {
 	struct inet6_dev *idev;
 	int err = -EADDRNOTAVAIL;
@@ -2178,7 +2178,7 @@ ok:
 		}
 
 		if (ifp) {
-			int flags;
+			u32 flags;
 			unsigned long now;
 			struct inet6_ifaddr *ift;
 			u32 stored_lft;
@@ -2363,10 +2363,11 @@ err_exit:
 /*
  *	Manual configuration of address on an interface
  */
-static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx,
+static int inet6_addr_add(struct net *net, int ifindex,
+			  const struct in6_addr *pfx,
 			  const struct in6_addr *peer_pfx,
-			  unsigned int plen, __u8 ifa_flags, __u32 prefered_lft,
-			  __u32 valid_lft)
+			  unsigned int plen, __u32 ifa_flags,
+			  __u32 prefered_lft, __u32 valid_lft)
 {
 	struct inet6_ifaddr *ifp;
 	struct inet6_dev *idev;
@@ -3351,7 +3352,7 @@ static void if6_seq_stop(struct seq_file *seq, void *v)
 static int if6_seq_show(struct seq_file *seq, void *v)
 {
 	struct inet6_ifaddr *ifp = (struct inet6_ifaddr *)v;
-	seq_printf(seq, "%pi6 %02x %02x %02x %02x %8s\n",
+	seq_printf(seq, "%pi6 %02x %02x %02x %03x %8s\n",
 		   &ifp->addr,
 		   ifp->idev->dev->ifindex,
 		   ifp->prefix_len,
@@ -3572,6 +3573,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = {
 	[IFA_ADDRESS]		= { .len = sizeof(struct in6_addr) },
 	[IFA_LOCAL]		= { .len = sizeof(struct in6_addr) },
 	[IFA_CACHEINFO]		= { .len = sizeof(struct ifa_cacheinfo) },
+	[IFA_FLAGS]		= { .len = sizeof(u32) },
 };
 
 static int
@@ -3595,7 +3597,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	return inet6_addr_del(net, ifm->ifa_index, pfx, ifm->ifa_prefixlen);
 }
 
-static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags,
+static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 			     u32 prefered_lft, u32 valid_lft)
 {
 	u32 flags;
@@ -3650,7 +3652,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct inet6_ifaddr *ifa;
 	struct net_device *dev;
 	u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME;
-	u8 ifa_flags;
+	u32 ifa_flags;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
@@ -3677,8 +3679,10 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (dev == NULL)
 		return -ENODEV;
 
+	ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
+
 	/* We ignore other flags so far. */
-	ifa_flags = ifm->ifa_flags & (IFA_F_NODAD | IFA_F_HOMEADDRESS);
+	ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS;
 
 	ifa = ipv6_get_ifaddr(net, pfx, dev, 1);
 	if (ifa == NULL) {
@@ -3702,7 +3706,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	return err;
 }
 
-static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u8 flags,
+static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u32 flags,
 			  u8 scope, int ifindex)
 {
 	struct ifaddrmsg *ifm;
@@ -3745,7 +3749,8 @@ static inline int inet6_ifaddr_msgsize(void)
 	return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
 	       + nla_total_size(16) /* IFA_LOCAL */
 	       + nla_total_size(16) /* IFA_ADDRESS */
-	       + nla_total_size(sizeof(struct ifa_cacheinfo));
+	       + nla_total_size(sizeof(struct ifa_cacheinfo))
+	       + nla_total_size(4)  /* IFA_FLAGS */;
 }
 
 static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
@@ -3793,6 +3798,9 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0)
 		goto error;
 
+	if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0)
+		goto error;
+
 	return nlmsg_end(skb, nlh);
 
 error:
-- 
cgit v1.2.3


From 53bd674915379d91e0e505332c89741b34eab05c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 6 Dec 2013 09:45:22 +0100
Subject: ipv6 addrconf: introduce IFA_F_MANAGETEMPADDR to tell kernel to
 manage temporary addresses

Creating an address with this flag set will result in kernel taking care
of temporary addresses in the same way as if the address was created by
kernel itself (after RA receive). This allows userspace applications
implementing the autoconfiguration (NetworkManager for example) to
implement ipv6 addresses privacy.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Thomas Haller <thaller@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_addr.h |   1 +
 net/ipv6/addrconf.c          | 171 +++++++++++++++++++++++++------------------
 2 files changed, 100 insertions(+), 72 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index 8ab0c2cc9b73..cfed10be7529 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -48,6 +48,7 @@ enum {
 #define IFA_F_DEPRECATED	0x20
 #define IFA_F_TENTATIVE		0x40
 #define IFA_F_PERMANENT		0x80
+#define IFA_F_MANAGETEMPADDR	0x100
 
 struct ifa_cacheinfo {
 	__u32	ifa_prefered;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 334a7e114e1d..5087cc5cb810 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1024,7 +1024,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i
 	u32 addr_flags;
 	unsigned long now = jiffies;
 
-	write_lock(&idev->lock);
+	write_lock_bh(&idev->lock);
 	if (ift) {
 		spin_lock_bh(&ift->lock);
 		memcpy(&addr.s6_addr[8], &ift->addr.s6_addr[8], 8);
@@ -1036,7 +1036,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i
 retry:
 	in6_dev_hold(idev);
 	if (idev->cnf.use_tempaddr <= 0) {
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		pr_info("%s: use_tempaddr is disabled\n", __func__);
 		in6_dev_put(idev);
 		ret = -1;
@@ -1046,7 +1046,7 @@ retry:
 	if (ifp->regen_count++ >= idev->cnf.regen_max_retry) {
 		idev->cnf.use_tempaddr = -1;	/*XXX*/
 		spin_unlock_bh(&ifp->lock);
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		pr_warn("%s: regeneration time exceeded - disabled temporary address support\n",
 			__func__);
 		in6_dev_put(idev);
@@ -1072,7 +1072,7 @@ retry:
 	regen_advance = idev->cnf.regen_max_retry *
 	                idev->cnf.dad_transmits *
 	                idev->nd_parms->retrans_time / HZ;
-	write_unlock(&idev->lock);
+	write_unlock_bh(&idev->lock);
 
 	/* A temporary address is created only if this calculated Preferred
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
@@ -1099,7 +1099,7 @@ retry:
 		in6_dev_put(idev);
 		pr_info("%s: retry temporary address regeneration\n", __func__);
 		tmpaddr = &addr;
-		write_lock(&idev->lock);
+		write_lock_bh(&idev->lock);
 		goto retry;
 	}
 
@@ -2016,6 +2016,73 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
 	return idev;
 }
 
+static void manage_tempaddrs(struct inet6_dev *idev,
+			     struct inet6_ifaddr *ifp,
+			     __u32 valid_lft, __u32 prefered_lft,
+			     bool create, unsigned long now)
+{
+	u32 flags;
+	struct inet6_ifaddr *ift;
+
+	read_lock_bh(&idev->lock);
+	/* update all temporary addresses in the list */
+	list_for_each_entry(ift, &idev->tempaddr_list, tmp_list) {
+		int age, max_valid, max_prefered;
+
+		if (ifp != ift->ifpub)
+			continue;
+
+		/* RFC 4941 section 3.3:
+		 * If a received option will extend the lifetime of a public
+		 * address, the lifetimes of temporary addresses should
+		 * be extended, subject to the overall constraint that no
+		 * temporary addresses should ever remain "valid" or "preferred"
+		 * for a time longer than (TEMP_VALID_LIFETIME) or
+		 * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), respectively.
+		 */
+		age = (now - ift->cstamp) / HZ;
+		max_valid = idev->cnf.temp_valid_lft - age;
+		if (max_valid < 0)
+			max_valid = 0;
+
+		max_prefered = idev->cnf.temp_prefered_lft -
+			       idev->cnf.max_desync_factor - age;
+		if (max_prefered < 0)
+			max_prefered = 0;
+
+		if (valid_lft > max_valid)
+			valid_lft = max_valid;
+
+		if (prefered_lft > max_prefered)
+			prefered_lft = max_prefered;
+
+		spin_lock(&ift->lock);
+		flags = ift->flags;
+		ift->valid_lft = valid_lft;
+		ift->prefered_lft = prefered_lft;
+		ift->tstamp = now;
+		if (prefered_lft > 0)
+			ift->flags &= ~IFA_F_DEPRECATED;
+
+		spin_unlock(&ift->lock);
+		if (!(flags&IFA_F_TENTATIVE))
+			ipv6_ifa_notify(0, ift);
+	}
+
+	if ((create || list_empty(&idev->tempaddr_list)) &&
+	    idev->cnf.use_tempaddr > 0) {
+		/* When a new public address is created as described
+		 * in [ADDRCONF], also create a new temporary address.
+		 * Also create a temporary address if it's enabled but
+		 * no temporary address currently exists.
+		 */
+		read_unlock_bh(&idev->lock);
+		ipv6_create_tempaddr(ifp, NULL);
+	} else {
+		read_unlock_bh(&idev->lock);
+	}
+}
+
 void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 {
 	struct prefix_info *pinfo;
@@ -2170,6 +2237,7 @@ ok:
 				return;
 			}
 
+			ifp->flags |= IFA_F_MANAGETEMPADDR;
 			update_lft = 0;
 			create = 1;
 			ifp->cstamp = jiffies;
@@ -2180,7 +2248,6 @@ ok:
 		if (ifp) {
 			u32 flags;
 			unsigned long now;
-			struct inet6_ifaddr *ift;
 			u32 stored_lft;
 
 			/* update lifetime (RFC2462 5.5.3 e) */
@@ -2221,70 +2288,8 @@ ok:
 			} else
 				spin_unlock(&ifp->lock);
 
-			read_lock_bh(&in6_dev->lock);
-			/* update all temporary addresses in the list */
-			list_for_each_entry(ift, &in6_dev->tempaddr_list,
-					    tmp_list) {
-				int age, max_valid, max_prefered;
-
-				if (ifp != ift->ifpub)
-					continue;
-
-				/*
-				 * RFC 4941 section 3.3:
-				 * If a received option will extend the lifetime
-				 * of a public address, the lifetimes of
-				 * temporary addresses should be extended,
-				 * subject to the overall constraint that no
-				 * temporary addresses should ever remain
-				 * "valid" or "preferred" for a time longer than
-				 * (TEMP_VALID_LIFETIME) or
-				 * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR),
-				 * respectively.
-				 */
-				age = (now - ift->cstamp) / HZ;
-				max_valid = in6_dev->cnf.temp_valid_lft - age;
-				if (max_valid < 0)
-					max_valid = 0;
-
-				max_prefered = in6_dev->cnf.temp_prefered_lft -
-					       in6_dev->cnf.max_desync_factor -
-					       age;
-				if (max_prefered < 0)
-					max_prefered = 0;
-
-				if (valid_lft > max_valid)
-					valid_lft = max_valid;
-
-				if (prefered_lft > max_prefered)
-					prefered_lft = max_prefered;
-
-				spin_lock(&ift->lock);
-				flags = ift->flags;
-				ift->valid_lft = valid_lft;
-				ift->prefered_lft = prefered_lft;
-				ift->tstamp = now;
-				if (prefered_lft > 0)
-					ift->flags &= ~IFA_F_DEPRECATED;
-
-				spin_unlock(&ift->lock);
-				if (!(flags&IFA_F_TENTATIVE))
-					ipv6_ifa_notify(0, ift);
-			}
-
-			if ((create || list_empty(&in6_dev->tempaddr_list)) && in6_dev->cnf.use_tempaddr > 0) {
-				/*
-				 * When a new public address is created as
-				 * described in [ADDRCONF], also create a new
-				 * temporary address. Also create a temporary
-				 * address if it's enabled but no temporary
-				 * address currently exists.
-				 */
-				read_unlock_bh(&in6_dev->lock);
-				ipv6_create_tempaddr(ifp, NULL);
-			} else {
-				read_unlock_bh(&in6_dev->lock);
-			}
+			manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
+					 create, now);
 
 			in6_ifa_put(ifp);
 			addrconf_verify(0);
@@ -2386,6 +2391,9 @@ static int inet6_addr_add(struct net *net, int ifindex,
 	if (!valid_lft || prefered_lft > valid_lft)
 		return -EINVAL;
 
+	if (ifa_flags & IFA_F_MANAGETEMPADDR && plen != 64)
+		return -EINVAL;
+
 	dev = __dev_get_by_index(net, ifindex);
 	if (!dev)
 		return -ENODEV;
@@ -2426,6 +2434,9 @@ static int inet6_addr_add(struct net *net, int ifindex,
 		 * manually configured addresses
 		 */
 		addrconf_dad_start(ifp);
+		if (ifa_flags & IFA_F_MANAGETEMPADDR)
+			manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
+					 true, jiffies);
 		in6_ifa_put(ifp);
 		addrconf_verify(0);
 		return 0;
@@ -3603,10 +3614,15 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 	u32 flags;
 	clock_t expires;
 	unsigned long timeout;
+	bool was_managetempaddr;
 
 	if (!valid_lft || (prefered_lft > valid_lft))
 		return -EINVAL;
 
+	if (ifa_flags & IFA_F_MANAGETEMPADDR &&
+	    (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64))
+		return -EINVAL;
+
 	timeout = addrconf_timeout_fixup(valid_lft, HZ);
 	if (addrconf_finite_timeout(timeout)) {
 		expires = jiffies_to_clock_t(timeout * HZ);
@@ -3626,7 +3642,10 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 	}
 
 	spin_lock_bh(&ifp->lock);
-	ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags;
+	was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR;
+	ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD |
+			IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR);
+	ifp->flags |= ifa_flags;
 	ifp->tstamp = jiffies;
 	ifp->valid_lft = valid_lft;
 	ifp->prefered_lft = prefered_lft;
@@ -3637,6 +3656,14 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 
 	addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev,
 			      expires, flags);
+
+	if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) {
+		if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR))
+			valid_lft = prefered_lft = 0;
+		manage_tempaddrs(ifp->idev, ifp, valid_lft, prefered_lft,
+				 !was_managetempaddr, jiffies);
+	}
+
 	addrconf_verify(0);
 
 	return 0;
@@ -3682,7 +3709,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
 
 	/* We ignore other flags so far. */
-	ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS;
+	ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR;
 
 	ifa = ipv6_get_ifaddr(net, pfx, dev, 1);
 	if (ifa == NULL) {
-- 
cgit v1.2.3


From 0aff078d58e1c69139189e45ba5e929c030e8056 Mon Sep 17 00:00:00 2001
From: Eric Leblond <eric@regit.org>
Date: Fri, 6 Dec 2013 00:24:13 +0100
Subject: netfilter: nft: add queue module

This patch adds a new nft module named "nft_queue" which provides
a new nftables expression that allows you to enqueue packets to
userspace via the nfnetlink_queue subsystem. It provides the same
level of functionality as NFQUEUE and it shares some code with it.

Signed-off-by: Eric Leblond <eric@regit.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  20 +++++
 net/netfilter/Kconfig                    |   9 +++
 net/netfilter/Makefile                   |   1 +
 net/netfilter/nft_queue.c                | 134 +++++++++++++++++++++++++++++++
 4 files changed, 164 insertions(+)
 create mode 100644 net/netfilter/nft_queue.c

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index fbfd229a8e99..256d36b1b94a 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -657,6 +657,26 @@ enum nft_log_attributes {
 };
 #define NFTA_LOG_MAX		(__NFTA_LOG_MAX - 1)
 
+/**
+ * enum nft_queue_attributes - nf_tables queue expression netlink attributes
+ *
+ * @NFTA_QUEUE_NUM: netlink queue to send messages to (NLA_U16)
+ * @NFTA_QUEUE_TOTAL: number of queues to load balance packets on (NLA_U16)
+ * @NFTA_QUEUE_FLAGS: various flags (NLA_U16)
+ */
+enum nft_queue_attributes {
+	NFTA_QUEUE_UNSPEC,
+	NFTA_QUEUE_NUM,
+	NFTA_QUEUE_TOTAL,
+	NFTA_QUEUE_FLAGS,
+	__NFTA_QUEUE_MAX
+};
+#define NFTA_QUEUE_MAX		(__NFTA_QUEUE_MAX - 1)
+
+#define NFT_QUEUE_FLAG_BYPASS		0x01 /* for compatibility with v2 */
+#define NFT_QUEUE_FLAG_CPU_FANOUT	0x02 /* use current CPU (no hashing) */
+#define NFT_QUEUE_FLAG_MASK		0x03
+
 /**
  * enum nft_reject_types - nf_tables reject expression reject types
  *
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 48acec17e27a..4371c9819d97 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -456,6 +456,15 @@ config NFT_NAT
 	depends on NF_NAT
 	tristate "Netfilter nf_tables nat module"
 
+config NFT_QUEUE
+	depends on NF_TABLES
+	depends on NETFILTER_XTABLES
+	depends on NETFILTER_NETLINK_QUEUE
+	tristate "Netfilter nf_tables queue module"
+	help
+	  This is required if you intend to use the userspace queueing
+	  infrastructure (also known as NFQUEUE) from nftables.
+
 config NFT_COMPAT
 	depends on NF_TABLES
 	depends on NETFILTER_XTABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 394483b2c193..e7637463226e 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -76,6 +76,7 @@ obj-$(CONFIG_NFT_META)		+= nft_meta.o
 obj-$(CONFIG_NFT_CT)		+= nft_ct.o
 obj-$(CONFIG_NFT_LIMIT)		+= nft_limit.o
 obj-$(CONFIG_NFT_NAT)		+= nft_nat.o
+obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
 #nf_tables-objs			+= nft_meta_target.o
 obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
new file mode 100644
index 000000000000..cbea473d69e9
--- /dev/null
+++ b/net/netfilter/nft_queue.c
@@ -0,0 +1,134 @@
+/*
+ * Copyright (c) 2013 Eric Leblond <eric@regit.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 partly funded by OISF
+ * (http://www.openinfosecfoundation.org/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/jhash.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_queue.h>
+
+static u32 jhash_initval __read_mostly;
+
+struct nft_queue {
+	u16	queuenum;
+	u16	queues_total;
+	u16	flags;
+	u8	family;
+};
+
+static void nft_queue_eval(const struct nft_expr *expr,
+			   struct nft_data data[NFT_REG_MAX + 1],
+			   const struct nft_pktinfo *pkt)
+{
+	struct nft_queue *priv = nft_expr_priv(expr);
+	u32 queue = priv->queuenum;
+	u32 ret;
+
+	if (priv->queues_total > 1) {
+		if (priv->flags & NFT_QUEUE_FLAG_CPU_FANOUT) {
+			int cpu = smp_processor_id();
+
+			queue = priv->queuenum + cpu % priv->queues_total;
+		} else {
+			queue = nfqueue_hash(pkt->skb, queue,
+					     priv->queues_total, priv->family,
+					     jhash_initval);
+		}
+	}
+
+	ret = NF_QUEUE_NR(queue);
+	if (priv->flags & NFT_QUEUE_FLAG_BYPASS)
+		ret |= NF_VERDICT_FLAG_QUEUE_BYPASS;
+
+	data[NFT_REG_VERDICT].verdict = ret;
+}
+
+static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = {
+	[NFTA_QUEUE_NUM]	= { .type = NLA_U16 },
+	[NFTA_QUEUE_TOTAL]	= { .type = NLA_U16 },
+	[NFTA_QUEUE_FLAGS]	= { .type = NLA_U16 },
+};
+
+static int nft_queue_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_queue *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_QUEUE_NUM] == NULL)
+		return -EINVAL;
+
+	init_hashrandom(&jhash_initval);
+	priv->family = ctx->afi->family;
+	priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM]));
+
+	if (tb[NFTA_QUEUE_TOTAL] != NULL)
+		priv->queues_total = ntohs(nla_get_be16(tb[NFTA_QUEUE_TOTAL]));
+	if (tb[NFTA_QUEUE_FLAGS] != NULL) {
+		priv->flags = ntohs(nla_get_be16(tb[NFTA_QUEUE_FLAGS]));
+		if (priv->flags & ~NFT_QUEUE_FLAG_MASK)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int nft_queue_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_queue *priv = nft_expr_priv(expr);
+
+	if (nla_put_be16(skb, NFTA_QUEUE_NUM, htons(priv->queuenum)) ||
+	    nla_put_be16(skb, NFTA_QUEUE_TOTAL, htons(priv->queues_total)) ||
+	    nla_put_be16(skb, NFTA_QUEUE_FLAGS, htons(priv->flags)))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_queue_type;
+static const struct nft_expr_ops nft_queue_ops = {
+	.type		= &nft_queue_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_queue)),
+	.eval		= nft_queue_eval,
+	.init		= nft_queue_init,
+	.dump		= nft_queue_dump,
+};
+
+static struct nft_expr_type nft_queue_type __read_mostly = {
+	.name		= "queue",
+	.ops		= &nft_queue_ops,
+	.policy		= nft_queue_policy,
+	.maxattr	= NFTA_QUEUE_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_queue_module_init(void)
+{
+	return nft_register_expr(&nft_queue_type);
+}
+
+static void __exit nft_queue_module_exit(void)
+{
+	nft_unregister_expr(&nft_queue_type);
+}
+
+module_init(nft_queue_module_init);
+module_exit(nft_queue_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Leblond <eric@regit.org>");
+MODULE_ALIAS_NFT_EXPR("queue");
-- 
cgit v1.2.3


From d346a3fae3ff1d99f5d0c819bf86edf9094a26a1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 6 Dec 2013 11:36:17 +0100
Subject: packet: introduce PACKET_QDISC_BYPASS socket option

This patch introduces a PACKET_QDISC_BYPASS socket option, that
allows for using a similar xmit() function as in pktgen instead
of taking the dev_queue_xmit() path. This can be very useful when
PF_PACKET applications are required to be used in a similar
scenario as pktgen, but with full, flexible packet payload that
needs to be provided, for example.

On default, nothing changes in behaviour for normal PF_PACKET
TX users, so everything stays as is for applications. New users,
however, can now set PACKET_QDISC_BYPASS if needed to prevent
own packets from i) reentering packet_rcv() and ii) to directly
push the frame to the driver.

In doing so we can increase pps (here 64 byte packets) for
PF_PACKET a bit:

  # CPUs -- QDISC_BYPASS   -- qdisc path -- qdisc path[**]
  1 CPU  ==  1,509,628 pps --  1,208,708 --  1,247,436
  2 CPUs ==  3,198,659 pps --  2,536,012 --  1,605,779
  3 CPUs ==  4,787,992 pps --  3,788,740 --  1,735,610
  4 CPUs ==  6,173,956 pps --  4,907,799 --  1,909,114
  5 CPUs ==  7,495,676 pps --  5,956,499 --  2,014,422
  6 CPUs ==  9,001,496 pps --  7,145,064 --  2,155,261
  7 CPUs == 10,229,776 pps --  8,190,596 --  2,220,619
  8 CPUs == 11,040,732 pps --  9,188,544 --  2,241,879
  9 CPUs == 12,009,076 pps -- 10,275,936 --  2,068,447
 10 CPUs == 11,380,052 pps -- 11,265,337 --  1,578,689
 11 CPUs == 11,672,676 pps -- 11,845,344 --  1,297,412
 [...]
 20 CPUs == 11,363,192 pps -- 11,014,933 --  1,245,081

 [**]: qdisc path with packet_rcv(), how probably most people
       seem to use it (hopefully not anymore if not needed)

The test was done using a modified trafgen, sending a simple
static 64 bytes packet, on all CPUs.  The trick in the fast
"qdisc path" case, is to avoid reentering packet_rcv() by
setting the RAW socket protocol to zero, like:
socket(PF_PACKET, SOCK_RAW, 0);

Tradeoffs are documented as well in this patch, clearly, if
queues are busy, we will drop more packets, tc disciplines are
ignored, and these packets are not visible to taps anymore. For
a pktgen like scenario, we argue that this is acceptable.

The pointer to the xmit function has been placed in packet
socket structure hole between cached_dev and prot_hook that
is hot anyway as we're working on cached_dev in each send path.

Done in joint work together with Jesper Dangaard Brouer.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/packet_mmap.txt | 21 ++++++++
 include/uapi/linux/if_packet.h           |  1 +
 net/packet/af_packet.c                   | 91 +++++++++++++++++++++++++++-----
 net/packet/internal.h                    |  1 +
 4 files changed, 102 insertions(+), 12 deletions(-)

(limited to 'include/uapi')

diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 8e48e3b14227..4288ffafba9f 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -952,6 +952,27 @@ int main(int argc, char **argp)
 	return 0;
 }
 
+-------------------------------------------------------------------------------
++ PACKET_QDISC_BYPASS
+-------------------------------------------------------------------------------
+
+If there is a requirement to load the network with many packets in a similar
+fashion as pktgen does, you might set the following option after socket
+creation:
+
+    int one = 1;
+    setsockopt(fd, SOL_PACKET, PACKET_QDISC_BYPASS, &one, sizeof(one));
+
+This has the side-effect, that packets sent through PF_PACKET will bypass the
+kernel's qdisc layer and are forcedly pushed to the driver directly. Meaning,
+packet are not buffered, tc disciplines are ignored, increased loss can occur
+and such packets are also not visible to other PF_PACKET sockets anymore. So,
+you have been warned; generally, this can be useful for stress testing various
+components of a system.
+
+On default, PACKET_QDISC_BYPASS is disabled and needs to be explicitly enabled
+on PF_PACKET sockets.
+
 -------------------------------------------------------------------------------
 + PACKET_TIMESTAMP
 -------------------------------------------------------------------------------
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index dbf06667394b..1e24aa701cbd 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -51,6 +51,7 @@ struct sockaddr_ll {
 #define PACKET_TIMESTAMP		17
 #define PACKET_FANOUT			18
 #define PACKET_TX_HAS_OFF		19
+#define PACKET_QDISC_BYPASS		20
 
 #define PACKET_FANOUT_HASH		0
 #define PACKET_FANOUT_LB		1
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e4171dd98590..9d70f1349926 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -237,6 +237,48 @@ struct packet_skb_cb {
 static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
 static void __fanout_link(struct sock *sk, struct packet_sock *po);
 
+static int packet_direct_xmit(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	const struct net_device_ops *ops = dev->netdev_ops;
+	netdev_features_t features;
+	struct netdev_queue *txq;
+	u16 queue_map;
+	int ret;
+
+	if (unlikely(!netif_running(dev) ||
+		     !netif_carrier_ok(dev))) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	features = netif_skb_features(skb);
+	if (skb_needs_linearize(skb, features) &&
+	    __skb_linearize(skb)) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	queue_map = skb_get_queue_mapping(skb);
+	txq = netdev_get_tx_queue(dev, queue_map);
+
+	__netif_tx_lock_bh(txq);
+	if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
+		ret = NETDEV_TX_BUSY;
+		kfree_skb(skb);
+		goto out;
+	}
+
+	ret = ops->ndo_start_xmit(skb, dev);
+	if (likely(dev_xmit_complete(ret)))
+		txq_trans_update(txq);
+	else
+		kfree_skb(skb);
+out:
+	__netif_tx_unlock_bh(txq);
+	return ret;
+}
+
 static struct net_device *packet_cached_dev_get(struct packet_sock *po)
 {
 	struct net_device *dev;
@@ -261,6 +303,16 @@ static void packet_cached_dev_reset(struct packet_sock *po)
 	RCU_INIT_POINTER(po->cached_dev, NULL);
 }
 
+static bool packet_use_direct_xmit(const struct packet_sock *po)
+{
+	return po->xmit == packet_direct_xmit;
+}
+
+static u16 packet_pick_tx_queue(struct net_device *dev)
+{
+	return (u16) smp_processor_id() % dev->real_num_tx_queues;
+}
+
 /* register_prot_hook must be invoked with the po->bind_lock held,
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
@@ -1994,9 +2046,10 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
-	skb_probe_transport_header(skb, 0);
 
-	if (po->tp_tx_has_off) {
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, 0);
+	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
 		off_max = po->tx_ring.frame_size - tp_len;
@@ -2166,12 +2219,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 			}
 		}
 
+		skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
 		skb->destructor = tpacket_destruct_skb;
 		__packet_set_status(po, ph, TP_STATUS_SENDING);
 		atomic_inc(&po->tx_ring.pending);
 
 		status = TP_STATUS_SEND_REQUEST;
-		err = dev_queue_xmit(skb);
+		err = po->xmit(skb);
 		if (unlikely(err > 0)) {
 			err = net_xmit_errno(err);
 			if (err && __packet_get_status(po, ph) ==
@@ -2230,8 +2284,7 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
 	return skb;
 }
 
-static int packet_snd(struct socket *sock,
-			  struct msghdr *msg, size_t len)
+static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
@@ -2376,6 +2429,7 @@ static int packet_snd(struct socket *sock,
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
@@ -2396,16 +2450,12 @@ static int packet_snd(struct socket *sock,
 		len += vnet_hdr_len;
 	}
 
-	skb_probe_transport_header(skb, reserve);
-
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, reserve);
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
-	/*
-	 *	Now send it
-	 */
-
-	err = dev_queue_xmit(skb);
+	err = po->xmit(skb);
 	if (err > 0 && (err = net_xmit_errno(err)) != 0)
 		goto out_unlock;
 
@@ -2427,6 +2477,7 @@ static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
+
 	if (po->tx_ring.pg_vec)
 		return tpacket_snd(po, msg);
 	else
@@ -2641,6 +2692,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	po = pkt_sk(sk);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
+	po->xmit = dev_queue_xmit;
 
 	packet_cached_dev_reset(po);
 
@@ -3220,6 +3272,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		po->tp_tx_has_off = !!val;
 		return 0;
 	}
+	case PACKET_QDISC_BYPASS:
+	{
+		int val;
+
+		if (optlen != sizeof(val))
+			return -EINVAL;
+		if (copy_from_user(&val, optval, sizeof(val)))
+			return -EFAULT;
+
+		po->xmit = val ? packet_direct_xmit : dev_queue_xmit;
+		return 0;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -3312,6 +3376,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
 		break;
+	case PACKET_QDISC_BYPASS:
+		val = packet_use_direct_xmit(po);
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 1035fa2d909c..0a87d7b36c9e 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -114,6 +114,7 @@ struct packet_sock {
 	unsigned int		tp_tx_has_off:1;
 	unsigned int		tp_tstamp;
 	struct net_device __rcu	*cached_dev;
+	int			(*xmit)(struct sk_buff *skb);
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
 };
 
-- 
cgit v1.2.3


From 0abc652c796dab74d34d60473ec5594cd21620be Mon Sep 17 00:00:00 2001
From: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Date: Wed, 11 Dec 2013 17:05:35 +0200
Subject: net: if_arp: add ARPHRD_6LOWPAN type

Used for IPv6 over LoWPAN networks. Example of this is
Bluetooth 6LoWPAN network.

Signed-off-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/uapi/linux/if_arp.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h
index d7fea3496f32..4d024d75d64b 100644
--- a/include/uapi/linux/if_arp.h
+++ b/include/uapi/linux/if_arp.h
@@ -94,6 +94,7 @@
 #define ARPHRD_CAIF	822		/* CAIF media type		*/
 #define ARPHRD_IP6GRE	823		/* GRE over IPv6		*/
 #define ARPHRD_NETLINK	824		/* Netlink header		*/
+#define ARPHRD_6LOWPAN	825		/* IPv6 over LoWPAN             */
 
 #define ARPHRD_VOID	  0xFFFF	/* Void type, nothing is known */
 #define ARPHRD_NONE	  0xFFFE	/* zero header length */
-- 
cgit v1.2.3


From f085ff1c131c08fb6b34802f63c22921c4d8c506 Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Thu, 12 Dec 2013 13:06:50 -0800
Subject: netconf: add proxy-arp support

Add support to netconf to show changes to proxy-arp status on a per
interface basis via netlink in a manner similar to forwarding
and reverse path state.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/netconf.h |  1 +
 net/ipv4/devinet.c           | 41 +++++++++++++++++++++++++++++------------
 2 files changed, 30 insertions(+), 12 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index 64804a798b0c..bd969d77ce52 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -14,6 +14,7 @@ enum {
 	NETCONFA_FORWARDING,
 	NETCONFA_RP_FILTER,
 	NETCONFA_MC_FORWARDING,
+	NETCONFA_PROXY_ARP,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 84956f5f0135..de03fe7002d0 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1696,6 +1696,8 @@ static int inet_netconf_msgsize_devconf(int type)
 		size += nla_total_size(4);
 	if (type == -1 || type == NETCONFA_MC_FORWARDING)
 		size += nla_total_size(4);
+	if (type == -1 || type == NETCONFA_PROXY_ARP)
+		size += nla_total_size(4);
 
 	return size;
 }
@@ -1732,6 +1734,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
 			IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
 		goto nla_put_failure;
+	if ((type == -1 || type == NETCONFA_PROXY_ARP) &&
+	    nla_put_s32(skb, NETCONFA_PROXY_ARP,
+			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
+		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
 
@@ -1769,6 +1775,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
 	[NETCONFA_IFINDEX]	= { .len = sizeof(int) },
 	[NETCONFA_FORWARDING]	= { .len = sizeof(int) },
 	[NETCONFA_RP_FILTER]	= { .len = sizeof(int) },
+	[NETCONFA_PROXY_ARP]	= { .len = sizeof(int) },
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
@@ -1950,6 +1957,19 @@ static void inet_forward_change(struct net *net)
 	}
 }
 
+static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf)
+{
+	if (cnf == net->ipv4.devconf_dflt)
+		return NETCONFA_IFINDEX_DEFAULT;
+	else if (cnf == net->ipv4.devconf_all)
+		return NETCONFA_IFINDEX_ALL;
+	else {
+		struct in_device *idev
+			= container_of(cnf, struct in_device, cnf);
+		return idev->dev->ifindex;
+	}
+}
+
 static int devinet_conf_proc(struct ctl_table *ctl, int write,
 			     void __user *buffer,
 			     size_t *lenp, loff_t *ppos)
@@ -1962,6 +1982,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		struct ipv4_devconf *cnf = ctl->extra1;
 		struct net *net = ctl->extra2;
 		int i = (int *)ctl->data - cnf->data;
+		int ifindex;
 
 		set_bit(i, cnf->state);
 
@@ -1971,23 +1992,19 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		    i == IPV4_DEVCONF_ROUTE_LOCALNET - 1)
 			if ((new_value == 0) && (old_value != 0))
 				rt_cache_flush(net);
+
 		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
 		    new_value != old_value) {
-			int ifindex;
-
-			if (cnf == net->ipv4.devconf_dflt)
-				ifindex = NETCONFA_IFINDEX_DEFAULT;
-			else if (cnf == net->ipv4.devconf_all)
-				ifindex = NETCONFA_IFINDEX_ALL;
-			else {
-				struct in_device *idev =
-					container_of(cnf, struct in_device,
-						     cnf);
-				ifindex = idev->dev->ifindex;
-			}
+			ifindex = devinet_conf_ifindex(net, cnf);
 			inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
 						    ifindex, cnf);
 		}
+		if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
+		    new_value != old_value) {
+			ifindex = devinet_conf_ifindex(net, cnf);
+			inet_netconf_notify_devconf(net, NETCONFA_PROXY_ARP,
+						    ifindex, cnf);
+		}
 	}
 
 	return ret;
-- 
cgit v1.2.3


From eecdaa6e20284efbe9e76eebd44eac2b22f7b5d7 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:09:55 -0800
Subject: bonding: add miimon netlink support

Add IFLA_BOND_MIIMON to allow get/set of bonding parameter
miimon via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 32 ++++++++++++++++++-----
 drivers/net/bonding/bond_options.c | 42 ++++++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 53 +++++++-------------------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 80 insertions(+), 49 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 40e7b1cb4aea..28a88beb749b 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -1,6 +1,7 @@
 /*
  * drivers/net/bond/bond_netlink.c - Netlink interface for bonding
  * Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -23,6 +24,7 @@
 static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MODE]		= { .type = NLA_U8 },
 	[IFLA_BOND_ACTIVE_SLAVE]	= { .type = NLA_U32 },
+	[IFLA_BOND_MIIMON]		= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -42,14 +44,17 @@ static int bond_changelink(struct net_device *bond_dev,
 	struct bonding *bond = netdev_priv(bond_dev);
 	int err;
 
-	if (data && data[IFLA_BOND_MODE]) {
+	if (!data)
+		return 0;
+
+	if (data[IFLA_BOND_MODE]) {
 		int mode = nla_get_u8(data[IFLA_BOND_MODE]);
 
 		err = bond_option_mode_set(bond, mode);
 		if (err)
 			return err;
 	}
-	if (data && data[IFLA_BOND_ACTIVE_SLAVE]) {
+	if (data[IFLA_BOND_ACTIVE_SLAVE]) {
 		int ifindex = nla_get_u32(data[IFLA_BOND_ACTIVE_SLAVE]);
 		struct net_device *slave_dev;
 
@@ -65,6 +70,13 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_MIIMON]) {
+		int miimon = nla_get_u32(data[IFLA_BOND_MIIMON]);
+
+		err = bond_option_miimon_set(bond, miimon);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -83,7 +95,9 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 static size_t bond_get_size(const struct net_device *bond_dev)
 {
 	return nla_total_size(sizeof(u8)) +	/* IFLA_BOND_MODE */
-		nla_total_size(sizeof(u32));	/* IFLA_BOND_ACTIVE_SLAVE */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ACTIVE_SLAVE */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIIMON */
+		0;
 }
 
 static int bond_fill_info(struct sk_buff *skb,
@@ -92,10 +106,16 @@ static int bond_fill_info(struct sk_buff *skb,
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct net_device *slave_dev = bond_option_active_slave_get(bond);
 
-	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode) ||
-	    (slave_dev &&
-	     nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, slave_dev->ifindex)))
+	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
 		goto nla_put_failure;
+
+	if (slave_dev &&
+	    nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, slave_dev->ifindex))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index ea6f640782b7..8ae42d36f11f 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1,6 +1,7 @@
 /*
  * drivers/net/bond/bond_options.c - bonding options
  * Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -145,3 +146,44 @@ int bond_option_active_slave_set(struct bonding *bond,
 	unblock_netpoll_tx();
 	return ret;
 }
+
+int bond_option_miimon_set(struct bonding *bond, int miimon)
+{
+	if (miimon < 0) {
+		pr_err("%s: Invalid miimon value %d not in range %d-%d; rejected.\n",
+		       bond->dev->name, miimon, 0, INT_MAX);
+		return -EINVAL;
+	}
+	pr_info("%s: Setting MII monitoring interval to %d.\n",
+		bond->dev->name, miimon);
+	bond->params.miimon = miimon;
+	if (bond->params.updelay)
+		pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n",
+			bond->dev->name,
+			bond->params.updelay * bond->params.miimon);
+	if (bond->params.downdelay)
+		pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n",
+			bond->dev->name,
+			bond->params.downdelay * bond->params.miimon);
+	if (miimon && bond->params.arp_interval) {
+		pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n",
+			bond->dev->name);
+		bond->params.arp_interval = 0;
+		if (bond->params.arp_validate)
+			bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
+	}
+	if (bond->dev->flags & IFF_UP) {
+		/* If the interface is up, we may need to fire off
+		 * the MII timer. If the interface is down, the
+		 * timer will get fired off when the open function
+		 * is called.
+		 */
+		if (!miimon) {
+			cancel_delayed_work_sync(&bond->mii_work);
+		} else {
+			cancel_delayed_work_sync(&bond->arp_work);
+			queue_delayed_work(bond->wq, &bond->mii_work, 0);
+		}
+	}
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index e46467683e82..d6d6fc7812d5 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -970,55 +970,22 @@ static ssize_t bonding_store_miimon(struct device *d,
 				    struct device_attribute *attr,
 				    const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no miimon value specified.\n",
 		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-	if (new_value < 0) {
-		pr_err("%s: Invalid miimon value %d not in range %d-%d; rejected.\n",
-		       bond->dev->name, new_value, 0, INT_MAX);
-		ret = -EINVAL;
-		goto out;
-	}
-	pr_info("%s: Setting MII monitoring interval to %d.\n",
-		bond->dev->name, new_value);
-	bond->params.miimon = new_value;
-	if (bond->params.updelay)
-		pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n",
-			bond->dev->name,
-			bond->params.updelay * bond->params.miimon);
-	if (bond->params.downdelay)
-		pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n",
-			bond->dev->name,
-			bond->params.downdelay * bond->params.miimon);
-	if (new_value && bond->params.arp_interval) {
-		pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n",
-			bond->dev->name);
-		bond->params.arp_interval = 0;
-		if (bond->params.arp_validate)
-			bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
-	}
-	if (bond->dev->flags & IFF_UP) {
-		/* If the interface is up, we may need to fire off
-		 * the MII timer. If the interface is down, the
-		 * timer will get fired off when the open function
-		 * is called.
-		 */
-		if (!new_value) {
-			cancel_delayed_work_sync(&bond->mii_work);
-		} else {
-			cancel_delayed_work_sync(&bond->arp_work);
-			queue_delayed_work(bond->wq, &bond->mii_work, 0);
-		}
+		return -EINVAL;
 	}
-out:
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_miimon_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index a74c92c83ead..b146479d5859 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -439,6 +439,7 @@ int bond_netlink_init(void);
 void bond_netlink_fini(void);
 int bond_option_mode_set(struct bonding *bond, int mode);
 int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_dev);
+int bond_option_miimon_set(struct bonding *bond, int miimon);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6db460121f84..739b2db3f035 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -331,6 +331,7 @@ enum {
 	IFLA_BOND_UNSPEC,
 	IFLA_BOND_MODE,
 	IFLA_BOND_ACTIVE_SLAVE,
+	IFLA_BOND_MIIMON,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 25852e29dfc58d249ad0db235996b36c33db6d61 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:10:02 -0800
Subject: bonding: add updelay netlink support

Add IFLA_BOND_UPDELAY to allow get/set of bonding parameter
updelay via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 13 ++++++++++++
 drivers/net/bonding/bond_options.c | 29 ++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 42 +++++++++-----------------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 54 insertions(+), 32 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 28a88beb749b..086cf4f5f0a6 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -25,6 +25,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MODE]		= { .type = NLA_U8 },
 	[IFLA_BOND_ACTIVE_SLAVE]	= { .type = NLA_U32 },
 	[IFLA_BOND_MIIMON]		= { .type = NLA_U32 },
+	[IFLA_BOND_UPDELAY]		= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -77,6 +78,13 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_UPDELAY]) {
+		int updelay = nla_get_u32(data[IFLA_BOND_UPDELAY]);
+
+		err = bond_option_updelay_set(bond, updelay);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -97,6 +105,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 	return nla_total_size(sizeof(u8)) +	/* IFLA_BOND_MODE */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ACTIVE_SLAVE */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIIMON */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_UPDELAY */
 		0;
 }
 
@@ -116,6 +125,10 @@ static int bond_fill_info(struct sk_buff *skb,
 	if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, IFLA_BOND_UPDELAY,
+			bond->params.updelay * bond->params.miimon))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 8ae42d36f11f..ae94b847ffcc 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -187,3 +187,32 @@ int bond_option_miimon_set(struct bonding *bond, int miimon)
 	}
 	return 0;
 }
+
+int bond_option_updelay_set(struct bonding *bond, int updelay)
+{
+	if (!(bond->params.miimon)) {
+		pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
+		       bond->dev->name);
+		return -EPERM;
+	}
+
+	if (updelay < 0) {
+		pr_err("%s: Invalid up delay value %d not in range %d-%d; rejected.\n",
+		       bond->dev->name, updelay, 0, INT_MAX);
+		return -EINVAL;
+	} else {
+		if ((updelay % bond->params.miimon) != 0) {
+			pr_warn("%s: Warning: up delay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
+				bond->dev->name, updelay,
+				bond->params.miimon,
+				(updelay / bond->params.miimon) *
+				bond->params.miimon);
+		}
+		bond->params.updelay = updelay / bond->params.miimon;
+		pr_info("%s: Setting up delay to %d.\n",
+			bond->dev->name,
+			bond->params.updelay * bond->params.miimon);
+	}
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index d6d6fc7812d5..4dcbec4e07c0 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -747,44 +747,22 @@ static ssize_t bonding_store_updelay(struct device *d,
 				     struct device_attribute *attr,
 				     const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-	if (!(bond->params.miimon)) {
-		pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
-		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
-	}
-
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no up delay value specified.\n",
-		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-	if (new_value < 0) {
-		pr_err("%s: Invalid up delay value %d not in range %d-%d; rejected.\n",
-		       bond->dev->name, new_value, 0, INT_MAX);
-		ret = -EINVAL;
-		goto out;
-	} else {
-		if ((new_value % bond->params.miimon) != 0) {
-			pr_warning("%s: Warning: up delay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
-				   bond->dev->name, new_value,
-				   bond->params.miimon,
-				   (new_value / bond->params.miimon) *
-				   bond->params.miimon);
-		}
-		bond->params.updelay = new_value / bond->params.miimon;
-		pr_info("%s: Setting up delay to %d.\n",
-			bond->dev->name,
-			bond->params.updelay * bond->params.miimon);
+		bond->dev->name);
+		return -EINVAL;
 	}
 
-out:
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_updelay_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index b146479d5859..8a91f7187e51 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -440,6 +440,7 @@ void bond_netlink_fini(void);
 int bond_option_mode_set(struct bonding *bond, int mode);
 int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_dev);
 int bond_option_miimon_set(struct bonding *bond, int miimon);
+int bond_option_updelay_set(struct bonding *bond, int updelay);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 739b2db3f035..7588c8120e7f 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -332,6 +332,7 @@ enum {
 	IFLA_BOND_MODE,
 	IFLA_BOND_ACTIVE_SLAVE,
 	IFLA_BOND_MIIMON,
+	IFLA_BOND_UPDELAY,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From c7461f9bf5a11bf88fdbd05b26c6d55b77dcd46d Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:10:09 -0800
Subject: bonding: add downdelay netlink support

Add IFLA_BOND_DOWNDELAY to allow get/set of bonding parameter
downdelay via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 13 +++++++++++++
 drivers/net/bonding/bond_options.c | 29 ++++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 39 ++++++++------------------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 52 insertions(+), 31 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 086cf4f5f0a6..a0a2e8c32fe5 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -26,6 +26,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_ACTIVE_SLAVE]	= { .type = NLA_U32 },
 	[IFLA_BOND_MIIMON]		= { .type = NLA_U32 },
 	[IFLA_BOND_UPDELAY]		= { .type = NLA_U32 },
+	[IFLA_BOND_DOWNDELAY]		= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -85,6 +86,13 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_DOWNDELAY]) {
+		int downdelay = nla_get_u32(data[IFLA_BOND_DOWNDELAY]);
+
+		err = bond_option_downdelay_set(bond, downdelay);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -106,6 +114,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ACTIVE_SLAVE */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIIMON */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_UPDELAY */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_DOWNDELAY */
 		0;
 }
 
@@ -129,6 +138,10 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->params.updelay * bond->params.miimon))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY,
+			bond->params.downdelay * bond->params.miimon))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index ae94b847ffcc..2914d649ee34 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -216,3 +216,32 @@ int bond_option_updelay_set(struct bonding *bond, int updelay)
 
 	return 0;
 }
+
+int bond_option_downdelay_set(struct bonding *bond, int downdelay)
+{
+	if (!(bond->params.miimon)) {
+		pr_err("%s: Unable to set down delay as MII monitoring is disabled\n",
+		       bond->dev->name);
+		return -EPERM;
+	}
+
+	if (downdelay < 0) {
+		pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n",
+		       bond->dev->name, downdelay, 0, INT_MAX);
+		return -EINVAL;
+	} else {
+		if ((downdelay % bond->params.miimon) != 0) {
+			pr_warn("%s: Warning: down delay (%d) is not a multiple of miimon (%d), delay rounded to %d ms\n",
+				bond->dev->name, downdelay,
+				bond->params.miimon,
+				(downdelay / bond->params.miimon) *
+				bond->params.miimon);
+		}
+		bond->params.downdelay = downdelay / bond->params.miimon;
+		pr_info("%s: Setting down delay to %d.\n",
+			bond->dev->name,
+			bond->params.downdelay * bond->params.miimon);
+	}
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 4dcbec4e07c0..bec20bc08d31 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -689,44 +689,21 @@ static ssize_t bonding_store_downdelay(struct device *d,
 				       struct device_attribute *attr,
 				       const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-	if (!(bond->params.miimon)) {
-		pr_err("%s: Unable to set down delay as MII monitoring is disabled\n",
-		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
-	}
-
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no down delay value specified.\n", bond->dev->name);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
-	if (new_value < 0) {
-		pr_err("%s: Invalid down delay value %d not in range %d-%d; rejected.\n",
-		       bond->dev->name, new_value, 0, INT_MAX);
-		ret = -EINVAL;
-		goto out;
-	} else {
-		if ((new_value % bond->params.miimon) != 0) {
-			pr_warning("%s: Warning: down delay (%d) is not a multiple of miimon (%d), delay rounded to %d ms\n",
-				   bond->dev->name, new_value,
-				   bond->params.miimon,
-				   (new_value / bond->params.miimon) *
-				   bond->params.miimon);
-		}
-		bond->params.downdelay = new_value / bond->params.miimon;
-		pr_info("%s: Setting down delay to %d.\n",
-			bond->dev->name,
-			bond->params.downdelay * bond->params.miimon);
 
-	}
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_downdelay_set(bond, new_value);
+	if (!ret)
+		ret = count;
 
-out:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 8a91f7187e51..f5749b18d168 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -441,6 +441,7 @@ int bond_option_mode_set(struct bonding *bond, int mode);
 int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_dev);
 int bond_option_miimon_set(struct bonding *bond, int miimon);
 int bond_option_updelay_set(struct bonding *bond, int updelay);
+int bond_option_downdelay_set(struct bonding *bond, int downdelay);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 7588c8120e7f..f95506777710 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
 	IFLA_BOND_ACTIVE_SLAVE,
 	IFLA_BOND_MIIMON,
 	IFLA_BOND_UPDELAY,
+	IFLA_BOND_DOWNDELAY,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 9f53e14e86c46a2300f17309f6308ad0dfbb53ff Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:10:16 -0800
Subject: bonding: add use_carrier netlink support

Add IFLA_BOND_USE_CARRIER to allow get/set of bonding parameter
use_carrier via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 12 ++++++++++++
 drivers/net/bonding/bond_options.c | 14 ++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 24 +++++++++++-------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 39 insertions(+), 13 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index a0a2e8c32fe5..7edf6399cea2 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -27,6 +27,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MIIMON]		= { .type = NLA_U32 },
 	[IFLA_BOND_UPDELAY]		= { .type = NLA_U32 },
 	[IFLA_BOND_DOWNDELAY]		= { .type = NLA_U32 },
+	[IFLA_BOND_USE_CARRIER]		= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -93,6 +94,13 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_USE_CARRIER]) {
+		int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]);
+
+		err = bond_option_use_carrier_set(bond, use_carrier);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -115,6 +123,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIIMON */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_UPDELAY */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_DOWNDELAY */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_USE_CARRIER */
 		0;
 }
 
@@ -142,6 +151,9 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->params.downdelay * bond->params.miimon))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 2914d649ee34..6fc7bbf0b85f 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -245,3 +245,17 @@ int bond_option_downdelay_set(struct bonding *bond, int downdelay)
 
 	return 0;
 }
+
+int bond_option_use_carrier_set(struct bonding *bond, int use_carrier)
+{
+	if ((use_carrier == 0) || (use_carrier == 1)) {
+		bond->params.use_carrier = use_carrier;
+		pr_info("%s: Setting use_carrier to %d.\n",
+			bond->dev->name, use_carrier);
+	} else {
+		pr_info("%s: Ignoring invalid use_carrier value %d.\n",
+			bond->dev->name, use_carrier);
+	}
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index bec20bc08d31..114760af9a6d 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1097,25 +1097,23 @@ static ssize_t bonding_store_carrier(struct device *d,
 				     struct device_attribute *attr,
 				     const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
-
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no use_carrier value specified.\n",
 		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-	if ((new_value == 0) || (new_value == 1)) {
-		bond->params.use_carrier = new_value;
-		pr_info("%s: Setting use_carrier to %d.\n",
-			bond->dev->name, new_value);
-	} else {
-		pr_info("%s: Ignoring invalid use_carrier value %d.\n",
-			bond->dev->name, new_value);
+		return -EINVAL;
 	}
-out:
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_use_carrier_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index f5749b18d168..df159da8db30 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -442,6 +442,7 @@ int bond_option_active_slave_set(struct bonding *bond, struct net_device *slave_
 int bond_option_miimon_set(struct bonding *bond, int miimon);
 int bond_option_updelay_set(struct bonding *bond, int updelay);
 int bond_option_downdelay_set(struct bonding *bond, int downdelay);
+int bond_option_use_carrier_set(struct bonding *bond, int use_carrier);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index f95506777710..77c41bda36a4 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -334,6 +334,7 @@ enum {
 	IFLA_BOND_MIIMON,
 	IFLA_BOND_UPDELAY,
 	IFLA_BOND_DOWNDELAY,
+	IFLA_BOND_USE_CARRIER,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 06151dbcf3f76edbe900138cde9e862f429918c9 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:10:24 -0800
Subject: bonding: add arp_interval netlink support

Add IFLA_BOND_ARP_INTERVAL to allow get/set of bonding parameter
arp_interval via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 21 ++++++++++++-
 drivers/net/bonding/bond_options.c | 47 +++++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 61 +++++++-------------------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 80 insertions(+), 51 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 7edf6399cea2..58e71235b75f 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -28,6 +28,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_UPDELAY]		= { .type = NLA_U32 },
 	[IFLA_BOND_DOWNDELAY]		= { .type = NLA_U32 },
 	[IFLA_BOND_USE_CARRIER]		= { .type = NLA_U8 },
+	[IFLA_BOND_ARP_INTERVAL]	= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -45,6 +46,7 @@ static int bond_changelink(struct net_device *bond_dev,
 			   struct nlattr *tb[], struct nlattr *data[])
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	int miimon = 0;
 	int err;
 
 	if (!data)
@@ -74,7 +76,7 @@ static int bond_changelink(struct net_device *bond_dev,
 			return err;
 	}
 	if (data[IFLA_BOND_MIIMON]) {
-		int miimon = nla_get_u32(data[IFLA_BOND_MIIMON]);
+		miimon = nla_get_u32(data[IFLA_BOND_MIIMON]);
 
 		err = bond_option_miimon_set(bond, miimon);
 		if (err)
@@ -101,6 +103,19 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_ARP_INTERVAL]) {
+		int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]);
+
+		if (arp_interval && miimon) {
+			pr_err("%s: ARP monitoring cannot be used with MII monitoring.\n",
+			       bond->dev->name);
+			return -EINVAL;
+		}
+
+		err = bond_option_arp_interval_set(bond, arp_interval);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -124,6 +139,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_UPDELAY */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_DOWNDELAY */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_USE_CARRIER */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_INTERVAL */
 		0;
 }
 
@@ -154,6 +170,9 @@ static int bond_fill_info(struct sk_buff *skb,
 	if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 6fc7bbf0b85f..a84e729d02ef 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -259,3 +259,50 @@ int bond_option_use_carrier_set(struct bonding *bond, int use_carrier)
 
 	return 0;
 }
+
+int bond_option_arp_interval_set(struct bonding *bond, int arp_interval)
+{
+	if (arp_interval < 0) {
+		pr_err("%s: Invalid arp_interval value %d not in range 0-%d; rejected.\n",
+		       bond->dev->name, arp_interval, INT_MAX);
+		return -EINVAL;
+	}
+	if (BOND_NO_USES_ARP(bond->params.mode)) {
+		pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n",
+			bond->dev->name, bond->dev->name);
+		return -EINVAL;
+	}
+	pr_info("%s: Setting ARP monitoring interval to %d.\n",
+		bond->dev->name, arp_interval);
+	bond->params.arp_interval = arp_interval;
+	if (arp_interval) {
+		if (bond->params.miimon) {
+			pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n",
+				bond->dev->name, bond->dev->name);
+			bond->params.miimon = 0;
+		}
+		if (!bond->params.arp_targets[0])
+			pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n",
+				bond->dev->name);
+	}
+	if (bond->dev->flags & IFF_UP) {
+		/* If the interface is up, we may need to fire off
+		 * the ARP timer.  If the interface is down, the
+		 * timer will get fired off when the open function
+		 * is called.
+		 */
+		if (!arp_interval) {
+			if (bond->params.arp_validate)
+				bond->recv_probe = NULL;
+			cancel_delayed_work_sync(&bond->arp_work);
+		} else {
+			/* arp_validate can be set only in active-backup mode */
+			if (bond->params.arp_validate)
+				bond->recv_probe = bond_arp_rcv;
+			cancel_delayed_work_sync(&bond->mii_work);
+			queue_delayed_work(bond->wq, &bond->arp_work, 0);
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 114760af9a6d..12128bfa88ce 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -506,60 +506,21 @@ static ssize_t bonding_store_arp_interval(struct device *d,
 					  const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int new_value, ret = count;
+	int new_value, ret;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no arp_interval value specified.\n",
-		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-	if (new_value < 0) {
-		pr_err("%s: Invalid arp_interval value %d not in range 0-%d; rejected.\n",
-		       bond->dev->name, new_value, INT_MAX);
-		ret = -EINVAL;
-		goto out;
-	}
-	if (BOND_NO_USES_ARP(bond->params.mode)) {
-		pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n",
-			bond->dev->name, bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-	pr_info("%s: Setting ARP monitoring interval to %d.\n",
-		bond->dev->name, new_value);
-	bond->params.arp_interval = new_value;
-	if (new_value) {
-		if (bond->params.miimon) {
-			pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n",
-				bond->dev->name, bond->dev->name);
-			bond->params.miimon = 0;
-		}
-		if (!bond->params.arp_targets[0])
-			pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n",
-				bond->dev->name);
-	}
-	if (bond->dev->flags & IFF_UP) {
-		/* If the interface is up, we may need to fire off
-		 * the ARP timer.  If the interface is down, the
-		 * timer will get fired off when the open function
-		 * is called.
-		 */
-		if (!new_value) {
-			if (bond->params.arp_validate)
-				bond->recv_probe = NULL;
-			cancel_delayed_work_sync(&bond->arp_work);
-		} else {
-			/* arp_validate can be set only in active-backup mode */
-			if (bond->params.arp_validate)
-				bond->recv_probe = bond_arp_rcv;
-			cancel_delayed_work_sync(&bond->mii_work);
-			queue_delayed_work(bond->wq, &bond->arp_work, 0);
-		}
+		bond->dev->name);
+		return -EINVAL;
 	}
-out:
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_arp_interval_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index df159da8db30..44df2738577d 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -443,6 +443,7 @@ int bond_option_miimon_set(struct bonding *bond, int miimon);
 int bond_option_updelay_set(struct bonding *bond, int updelay);
 int bond_option_downdelay_set(struct bonding *bond, int downdelay);
 int bond_option_use_carrier_set(struct bonding *bond, int use_carrier);
+int bond_option_arp_interval_set(struct bonding *bond, int arp_interval);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 77c41bda36a4..c73d878afd58 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -335,6 +335,7 @@ enum {
 	IFLA_BOND_UPDELAY,
 	IFLA_BOND_DOWNDELAY,
 	IFLA_BOND_USE_CARRIER,
+	IFLA_BOND_ARP_INTERVAL,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 7f28fa10e21376a10d3b9faad5836869465cc376 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:10:31 -0800
Subject: bonding: add arp_ip_target netlink support

Add IFLA_BOND_ARP_IP_TARGET to allow get/set of bonding parameter
arp_ip_target via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c |  36 ++++++++++
 drivers/net/bonding/bond_options.c | 130 +++++++++++++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   |  84 +++++-------------------
 drivers/net/bonding/bonding.h      |   4 ++
 include/uapi/linux/if_link.h       |   1 +
 5 files changed, 187 insertions(+), 68 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 58e71235b75f..6d30e5db9e3c 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -29,6 +29,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_DOWNDELAY]		= { .type = NLA_U32 },
 	[IFLA_BOND_USE_CARRIER]		= { .type = NLA_U8 },
 	[IFLA_BOND_ARP_INTERVAL]	= { .type = NLA_U32 },
+	[IFLA_BOND_ARP_IP_TARGET]	= { .type = NLA_NESTED },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -116,6 +117,20 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_ARP_IP_TARGET]) {
+		__be32 targets[BOND_MAX_ARP_TARGETS] = { 0, };
+		struct nlattr *attr;
+		int i = 0, rem;
+
+		nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) {
+			__be32 target = nla_get_u32(attr);
+			targets[i++] = target;
+		}
+
+		err = bond_option_arp_ip_targets_set(bond, targets, i);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -140,6 +155,8 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_DOWNDELAY */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_USE_CARRIER */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_INTERVAL */
+						/* IFLA_BOND_ARP_IP_TARGET */
+		nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
 		0;
 }
 
@@ -148,6 +165,8 @@ static int bond_fill_info(struct sk_buff *skb,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct net_device *slave_dev = bond_option_active_slave_get(bond);
+	struct nlattr *targets;
+	int i, targets_added;
 
 	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
 		goto nla_put_failure;
@@ -173,6 +192,23 @@ static int bond_fill_info(struct sk_buff *skb,
 	if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
 		goto nla_put_failure;
 
+	targets = nla_nest_start(skb, IFLA_BOND_ARP_IP_TARGET);
+	if (!targets)
+		goto nla_put_failure;
+
+	targets_added = 0;
+	for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) {
+		if (bond->params.arp_targets[i]) {
+			nla_put_u32(skb, i, bond->params.arp_targets[i]);
+			targets_added = 1;
+		}
+	}
+
+	if (targets_added)
+		nla_nest_end(skb, targets);
+	else
+		nla_nest_cancel(skb, targets);
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index a84e729d02ef..f8c2e4f17066 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -306,3 +306,133 @@ int bond_option_arp_interval_set(struct bonding *bond, int arp_interval)
 
 	return 0;
 }
+
+static void _bond_options_arp_ip_target_set(struct bonding *bond, int slot,
+					    __be32 target,
+					    unsigned long last_rx)
+{
+	__be32 *targets = bond->params.arp_targets;
+	struct list_head *iter;
+	struct slave *slave;
+
+	if (slot >= 0 && slot < BOND_MAX_ARP_TARGETS) {
+		bond_for_each_slave(bond, slave, iter)
+			slave->target_last_arp_rx[slot] = last_rx;
+		targets[slot] = target;
+	}
+}
+
+static int _bond_option_arp_ip_target_add(struct bonding *bond, __be32 target)
+{
+	__be32 *targets = bond->params.arp_targets;
+	int ind;
+
+	if (IS_IP_TARGET_UNUSABLE_ADDRESS(target)) {
+		pr_err("%s: invalid ARP target %pI4 specified for addition\n",
+		       bond->dev->name, &target);
+		return -EINVAL;
+	}
+
+	if (bond_get_targets_ip(targets, target) != -1) { /* dup */
+		pr_err("%s: ARP target %pI4 is already present\n",
+		       bond->dev->name, &target);
+		return -EINVAL;
+	}
+
+	ind = bond_get_targets_ip(targets, 0); /* first free slot */
+	if (ind == -1) {
+		pr_err("%s: ARP target table is full!\n",
+		       bond->dev->name);
+		return -EINVAL;
+	}
+
+	pr_info("%s: adding ARP target %pI4.\n", bond->dev->name, &target);
+
+	_bond_options_arp_ip_target_set(bond, ind, target, jiffies);
+
+	return 0;
+}
+
+int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target)
+{
+	int ret;
+
+	/* not to race with bond_arp_rcv */
+	write_lock_bh(&bond->lock);
+	ret = _bond_option_arp_ip_target_add(bond, target);
+	write_unlock_bh(&bond->lock);
+
+	return ret;
+}
+
+int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target)
+{
+	__be32 *targets = bond->params.arp_targets;
+	struct list_head *iter;
+	struct slave *slave;
+	unsigned long *targets_rx;
+	int ind, i;
+
+	if (IS_IP_TARGET_UNUSABLE_ADDRESS(target)) {
+		pr_err("%s: invalid ARP target %pI4 specified for removal\n",
+		       bond->dev->name, &target);
+		return -EINVAL;
+	}
+
+	ind = bond_get_targets_ip(targets, target);
+	if (ind == -1) {
+		pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
+		       bond->dev->name, &target);
+		return -EINVAL;
+	}
+
+	if (ind == 0 && !targets[1] && bond->params.arp_interval)
+		pr_warn("%s: removing last arp target with arp_interval on\n",
+			bond->dev->name);
+
+	pr_info("%s: removing ARP target %pI4.\n", bond->dev->name,
+		&target);
+
+	/* not to race with bond_arp_rcv */
+	write_lock_bh(&bond->lock);
+
+	bond_for_each_slave(bond, slave, iter) {
+		targets_rx = slave->target_last_arp_rx;
+		for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
+			targets_rx[i] = targets_rx[i+1];
+		targets_rx[i] = 0;
+	}
+	for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
+		targets[i] = targets[i+1];
+	targets[i] = 0;
+
+	write_unlock_bh(&bond->lock);
+
+	return 0;
+}
+
+int bond_option_arp_ip_targets_set(struct bonding *bond, __be32 *targets,
+				   int count)
+{
+	int i, ret = 0;
+
+	/* not to race with bond_arp_rcv */
+	write_lock_bh(&bond->lock);
+
+	/* clear table */
+	for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
+		_bond_options_arp_ip_target_set(bond, i, 0, 0);
+
+	if (count == 0 && bond->params.arp_interval)
+		pr_warn("%s: removing last arp target with arp_interval on\n",
+			bond->dev->name);
+
+	for (i = 0; i < count; i++) {
+		ret = _bond_option_arp_ip_target_add(bond, targets[i]);
+		if (ret)
+			break;
+	}
+
+	write_unlock_bh(&bond->lock);
+	return ret;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 12128bfa88ce..a443bbd0fe86 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -552,81 +552,29 @@ static ssize_t bonding_store_arp_targets(struct device *d,
 					 const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	struct list_head *iter;
-	struct slave *slave;
-	__be32 newtarget, *targets;
-	unsigned long *targets_rx;
-	int ind, i, j, ret = -EINVAL;
+	__be32 target;
+	int ret = -EPERM;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-
-	targets = bond->params.arp_targets;
-	if (!in4_pton(buf + 1, -1, (u8 *)&newtarget, -1, NULL) ||
-	    IS_IP_TARGET_UNUSABLE_ADDRESS(newtarget)) {
-		pr_err("%s: invalid ARP target %pI4 specified for addition\n",
-		       bond->dev->name, &newtarget);
-		goto out;
+	if (!in4_pton(buf + 1, -1, (u8 *)&target, -1, NULL)) {
+		pr_err("%s: invalid ARP target %pI4 specified\n",
+		       bond->dev->name, &target);
+		return -EPERM;
 	}
-	/* look for adds */
-	if (buf[0] == '+') {
-		if (bond_get_targets_ip(targets, newtarget) != -1) { /* dup */
-			pr_err("%s: ARP target %pI4 is already present\n",
-			       bond->dev->name, &newtarget);
-			goto out;
-		}
-
-		ind = bond_get_targets_ip(targets, 0); /* first free slot */
-		if (ind == -1) {
-			pr_err("%s: ARP target table is full!\n",
-			       bond->dev->name);
-			goto out;
-		}
-
-		pr_info("%s: adding ARP target %pI4.\n", bond->dev->name,
-			 &newtarget);
-		/* not to race with bond_arp_rcv */
-		write_lock_bh(&bond->lock);
-		bond_for_each_slave(bond, slave, iter)
-			slave->target_last_arp_rx[ind] = jiffies;
-		targets[ind] = newtarget;
-		write_unlock_bh(&bond->lock);
-	} else if (buf[0] == '-')	{
-		ind = bond_get_targets_ip(targets, newtarget);
-		if (ind == -1) {
-			pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
-				bond->dev->name, &newtarget);
-			goto out;
-		}
 
-		if (ind == 0 && !targets[1] && bond->params.arp_interval)
-			pr_warn("%s: removing last arp target with arp_interval on\n",
-				bond->dev->name);
-
-		pr_info("%s: removing ARP target %pI4.\n", bond->dev->name,
-			&newtarget);
+	if (!rtnl_trylock())
+		return restart_syscall();
 
-		write_lock_bh(&bond->lock);
-		bond_for_each_slave(bond, slave, iter) {
-			targets_rx = slave->target_last_arp_rx;
-			j = ind;
-			for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++)
-				targets_rx[j] = targets_rx[j+1];
-			targets_rx[j] = 0;
-		}
-		for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++)
-			targets[i] = targets[i+1];
-		targets[i] = 0;
-		write_unlock_bh(&bond->lock);
-	} else {
+	if (buf[0] == '+')
+		ret = bond_option_arp_ip_target_add(bond, target);
+	else if (buf[0] == '-')
+		ret = bond_option_arp_ip_target_rem(bond, target);
+	else
 		pr_err("no command found in arp_ip_targets file for bond %s. Use +<addr> or -<addr>.\n",
 		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
-	}
 
-	ret = count;
-out:
+	if (!ret)
+		ret = count;
+
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 44df2738577d..dcdc8095c169 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -444,6 +444,10 @@ int bond_option_updelay_set(struct bonding *bond, int updelay);
 int bond_option_downdelay_set(struct bonding *bond, int downdelay);
 int bond_option_use_carrier_set(struct bonding *bond, int use_carrier);
 int bond_option_arp_interval_set(struct bonding *bond, int arp_interval);
+int bond_option_arp_ip_targets_set(struct bonding *bond, __be32 *targets,
+				   int count);
+int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
+int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index c73d878afd58..5b0c44469279 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -336,6 +336,7 @@ enum {
 	IFLA_BOND_DOWNDELAY,
 	IFLA_BOND_USE_CARRIER,
 	IFLA_BOND_ARP_INTERVAL,
+	IFLA_BOND_ARP_IP_TARGET,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 29c4948293bfc426e52a921f4259eb3676961e81 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:10:38 -0800
Subject: bonding: add arp_validate netlink support

Add IFLA_BOND_ARP_VALIDATE to allow get/set of bonding parameter
arp_validate via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 18 ++++++++++++++++++
 drivers/net/bonding/bond_options.c | 22 ++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 30 ++++++++----------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 50 insertions(+), 22 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 6d30e5db9e3c..8588cb91caa9 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -30,6 +30,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_USE_CARRIER]		= { .type = NLA_U8 },
 	[IFLA_BOND_ARP_INTERVAL]	= { .type = NLA_U32 },
 	[IFLA_BOND_ARP_IP_TARGET]	= { .type = NLA_NESTED },
+	[IFLA_BOND_ARP_VALIDATE]	= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -131,6 +132,19 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_ARP_VALIDATE]) {
+		int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]);
+
+		if (arp_validate && miimon) {
+			pr_err("%s: ARP validating cannot be used with MII monitoring.\n",
+			       bond->dev->name);
+			return -EINVAL;
+		}
+
+		err = bond_option_arp_validate_set(bond, arp_validate);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -157,6 +171,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_INTERVAL */
 						/* IFLA_BOND_ARP_IP_TARGET */
 		nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_VALIDATE */
 		0;
 }
 
@@ -209,6 +224,9 @@ static int bond_fill_info(struct sk_buff *skb,
 	else
 		nla_nest_cancel(skb, targets);
 
+	if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index f8c2e4f17066..698079e94e74 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -436,3 +436,25 @@ int bond_option_arp_ip_targets_set(struct bonding *bond, __be32 *targets,
 	write_unlock_bh(&bond->lock);
 	return ret;
 }
+
+int bond_option_arp_validate_set(struct bonding *bond, int arp_validate)
+{
+	if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
+		pr_err("%s: arp_validate only supported in active-backup mode.\n",
+		       bond->dev->name);
+		return -EINVAL;
+	}
+	pr_info("%s: setting arp_validate to %s (%d).\n",
+		bond->dev->name, arp_validate_tbl[arp_validate].modename,
+		arp_validate);
+
+	if (bond->dev->flags & IFF_UP) {
+		if (!arp_validate)
+			bond->recv_probe = NULL;
+		else if (bond->params.arp_interval)
+			bond->recv_probe = bond_arp_rcv;
+	}
+	bond->params.arp_validate = arp_validate;
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index a443bbd0fe86..bda00a01393a 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -358,35 +358,21 @@ static ssize_t bonding_store_arp_validate(struct device *d,
 					  const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int new_value, ret = count;
+	int new_value, ret;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
 	new_value = bond_parse_parm(buf, arp_validate_tbl);
 	if (new_value < 0) {
 		pr_err("%s: Ignoring invalid arp_validate value %s\n",
 		       bond->dev->name, buf);
-		ret = -EINVAL;
-		goto out;
-	}
-	if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
-		pr_err("%s: arp_validate only supported in active-backup mode.\n",
-		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
-	pr_info("%s: setting arp_validate to %s (%d).\n",
-		bond->dev->name, arp_validate_tbl[new_value].modename,
-		new_value);
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_arp_validate_set(bond, new_value);
+	if (!ret)
+		ret = count;
 
-	if (bond->dev->flags & IFF_UP) {
-		if (!new_value)
-			bond->recv_probe = NULL;
-		else if (bond->params.arp_interval)
-			bond->recv_probe = bond_arp_rcv;
-	}
-	bond->params.arp_validate = new_value;
-out:
 	rtnl_unlock();
 
 	return ret;
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index dcdc8095c169..cef10adac6e6 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -448,6 +448,7 @@ int bond_option_arp_ip_targets_set(struct bonding *bond, __be32 *targets,
 				   int count);
 int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
 int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
+int bond_option_arp_validate_set(struct bonding *bond, int arp_validate);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 5b0c44469279..3ba16fa9ad6c 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -337,6 +337,7 @@ enum {
 	IFLA_BOND_USE_CARRIER,
 	IFLA_BOND_ARP_INTERVAL,
 	IFLA_BOND_ARP_IP_TARGET,
+	IFLA_BOND_ARP_VALIDATE,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From d5c842544342fc3f13774ffc5581d4dd3975059b Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 12 Dec 2013 14:10:45 -0800
Subject: bonding: add arp_all_targets netlink support

Add IFLA_BOND_ARP_ALL_TARGETS to allow get/set of bonding parameter
arp_all_targets via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c | 11 +++++++++++
 drivers/net/bonding/bond_sysfs.c   | 16 ++++++++++------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 37 insertions(+), 6 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 8588cb91caa9..d7d84db9eed7 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -31,6 +31,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_ARP_INTERVAL]	= { .type = NLA_U32 },
 	[IFLA_BOND_ARP_IP_TARGET]	= { .type = NLA_NESTED },
 	[IFLA_BOND_ARP_VALIDATE]	= { .type = NLA_U32 },
+	[IFLA_BOND_ARP_ALL_TARGETS]	= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -145,6 +146,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_ARP_ALL_TARGETS]) {
+		int arp_all_targets =
+			nla_get_u32(data[IFLA_BOND_ARP_ALL_TARGETS]);
+
+		err = bond_option_arp_all_targets_set(bond, arp_all_targets);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -172,6 +181,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 						/* IFLA_BOND_ARP_IP_TARGET */
 		nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_VALIDATE */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_ALL_TARGETS */
 		0;
 }
 
@@ -227,6 +237,10 @@ static int bond_fill_info(struct sk_buff *skb,
 	if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, IFLA_BOND_ARP_ALL_TARGETS,
+			bond->params.arp_all_targets))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 698079e94e74..dfef673d53d1 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -458,3 +458,14 @@ int bond_option_arp_validate_set(struct bonding *bond, int arp_validate)
 
 	return 0;
 }
+
+int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets)
+{
+	pr_info("%s: setting arp_all_targets to %s (%d).\n",
+		bond->dev->name, arp_all_targets_tbl[arp_all_targets].modename,
+		arp_all_targets);
+
+	bond->params.arp_all_targets = arp_all_targets;
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index bda00a01393a..dad9bea95122 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -399,7 +399,7 @@ static ssize_t bonding_store_arp_all_targets(struct device *d,
 					  const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int new_value;
+	int new_value, ret;
 
 	new_value = bond_parse_parm(buf, arp_all_targets_tbl);
 	if (new_value < 0) {
@@ -407,13 +407,17 @@ static ssize_t bonding_store_arp_all_targets(struct device *d,
 		       bond->dev->name, buf);
 		return -EINVAL;
 	}
-	pr_info("%s: setting arp_all_targets to %s (%d).\n",
-		bond->dev->name, arp_all_targets_tbl[new_value].modename,
-		new_value);
 
-	bond->params.arp_all_targets = new_value;
+	if (!rtnl_trylock())
+		return restart_syscall();
 
-	return count;
+	ret = bond_option_arp_all_targets_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
+
+	return ret;
 }
 
 static DEVICE_ATTR(arp_all_targets, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index cef10adac6e6..8283cbdec50a 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -449,6 +449,7 @@ int bond_option_arp_ip_targets_set(struct bonding *bond, __be32 *targets,
 int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
 int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
 int bond_option_arp_validate_set(struct bonding *bond, int arp_validate);
+int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 3ba16fa9ad6c..a897b7e22541 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -338,6 +338,7 @@ enum {
 	IFLA_BOND_ARP_INTERVAL,
 	IFLA_BOND_ARP_IP_TARGET,
 	IFLA_BOND_ARP_VALIDATE,
+	IFLA_BOND_ARP_ALL_TARGETS,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 204e35a91c4b3327b7239d7687fbd4923edbbf08 Mon Sep 17 00:00:00 2001
From: Janusz Dziedzic <janusz.dziedzic@tieto.com>
Date: Thu, 5 Dec 2013 20:42:58 +0100
Subject: nl80211: add VHT support for set_bitrate_mask

Add VHT MCS/NSS set support for nl80211_set_tx_bitrate_mask().
This should be used mainly for test purpose, to check
different MCS/NSS VHT combinations.

Signed-off-by: Janusz Dziedzic <janusz.dziedzic@tieto.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  1 +
 include/uapi/linux/nl80211.h | 12 ++++++
 net/wireless/nl80211.c       | 92 +++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 99 insertions(+), 6 deletions(-)

(limited to 'include/uapi')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 6c3a650f3a8f..80a10212b1b9 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1767,6 +1767,7 @@ struct cfg80211_bitrate_mask {
 	struct {
 		u32 legacy;
 		u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN];
+		u16 vht_mcs[NL80211_VHT_NSS_MAX];
 	} control[IEEE80211_NUM_BANDS];
 };
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 6e700645cd27..e1307909ecf1 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3112,6 +3112,8 @@ enum nl80211_key_attributes {
  *	%NL80211_MAX_SUPP_RATES in a single array).
  * @NL80211_TXRATE_HT: HT (MCS) rates allowed for TX rate selection
  *	in an array of MCS numbers.
+ * @NL80211_TXRATE_VHT: VHT rates allowed for TX rate selection,
+ *	see &struct nl80211_txrate_vht
  * @__NL80211_TXRATE_AFTER_LAST: internal
  * @NL80211_TXRATE_MAX: highest TX rate attribute
  */
@@ -3119,6 +3121,7 @@ enum nl80211_tx_rate_attributes {
 	__NL80211_TXRATE_INVALID,
 	NL80211_TXRATE_LEGACY,
 	NL80211_TXRATE_HT,
+	NL80211_TXRATE_VHT,
 
 	/* keep last */
 	__NL80211_TXRATE_AFTER_LAST,
@@ -3126,6 +3129,15 @@ enum nl80211_tx_rate_attributes {
 };
 
 #define NL80211_TXRATE_MCS NL80211_TXRATE_HT
+#define NL80211_VHT_NSS_MAX		8
+
+/**
+ * struct nl80211_txrate_vht - VHT MCS/NSS txrate bitmap
+ * @mcs: MCS bitmap table for each NSS (array index 0 for 1 stream, etc.)
+ */
+struct nl80211_txrate_vht {
+	__u16 mcs[NL80211_VHT_NSS_MAX];
+};
 
 /**
  * enum nl80211_band - Frequency band
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 2d0c19c6133b..04681a46eda8 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7328,11 +7328,72 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband,
 	return true;
 }
 
+static u16 vht_mcs_map_to_mcs_mask(u8 vht_mcs_map)
+{
+	u16 mcs_mask = 0;
+
+	switch (vht_mcs_map) {
+	case IEEE80211_VHT_MCS_NOT_SUPPORTED:
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_7:
+		mcs_mask = 0x00FF;
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_8:
+		mcs_mask = 0x01FF;
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_9:
+		mcs_mask = 0x03FF;
+		break;
+	default:
+		break;
+	}
+
+	return mcs_mask;
+}
+
+static void vht_build_mcs_mask(u16 vht_mcs_map,
+			       u16 vht_mcs_mask[NL80211_VHT_NSS_MAX])
+{
+	u8 nss;
+
+	for (nss = 0; nss < NL80211_VHT_NSS_MAX; nss++) {
+		vht_mcs_mask[nss] = vht_mcs_map_to_mcs_mask(vht_mcs_map & 0x03);
+		vht_mcs_map >>= 2;
+	}
+}
+
+static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband,
+			     struct nl80211_txrate_vht *txrate,
+			     u16 mcs[NL80211_VHT_NSS_MAX])
+{
+	u16 tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map);
+	u16 tx_mcs_mask[NL80211_VHT_NSS_MAX] = {};
+	u8 i;
+
+	if (!sband->vht_cap.vht_supported)
+		return false;
+
+	memset(mcs, 0, sizeof(u16) * NL80211_VHT_NSS_MAX);
+
+	/* Build vht_mcs_mask from VHT capabilities */
+	vht_build_mcs_mask(tx_mcs_map, tx_mcs_mask);
+
+	for (i = 0; i < NL80211_VHT_NSS_MAX; i++) {
+		if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i])
+			mcs[i] = txrate->mcs[i];
+		else
+			return false;
+	}
+
+	return true;
+}
+
 static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = {
 	[NL80211_TXRATE_LEGACY] = { .type = NLA_BINARY,
 				    .len = NL80211_MAX_SUPP_RATES },
 	[NL80211_TXRATE_HT] = { .type = NLA_BINARY,
 				.len = NL80211_MAX_SUPP_HT_RATES },
+	[NL80211_TXRATE_VHT] = { .len = sizeof(struct nl80211_txrate_vht)},
 };
 
 static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
@@ -7345,6 +7406,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 	struct net_device *dev = info->user_ptr[1];
 	struct nlattr *tx_rates;
 	struct ieee80211_supported_band *sband;
+	u16 vht_tx_mcs_map;
 
 	if (!rdev->ops->set_bitrate_mask)
 		return -EOPNOTSUPP;
@@ -7361,6 +7423,12 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 		memcpy(mask.control[i].ht_mcs,
 		       sband->ht_cap.mcs.rx_mask,
 		       sizeof(mask.control[i].ht_mcs));
+
+		if (!sband->vht_cap.vht_supported)
+			continue;
+
+		vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map);
+		vht_build_mcs_mask(vht_tx_mcs_map, mask.control[i].vht_mcs);
 	}
 
 	/* if no rates are given set it back to the defaults */
@@ -7399,20 +7467,32 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 					mask.control[band].ht_mcs))
 				return -EINVAL;
 		}
+		if (tb[NL80211_TXRATE_VHT]) {
+			if (!vht_set_mcs_mask(
+					sband,
+					nla_data(tb[NL80211_TXRATE_VHT]),
+					mask.control[band].vht_mcs))
+				return -EINVAL;
+		}
 
 		if (mask.control[band].legacy == 0) {
-			/* don't allow empty legacy rates if HT
-			 * is not even supported. */
-			if (!rdev->wiphy.bands[band]->ht_cap.ht_supported)
+			/* don't allow empty legacy rates if HT or VHT
+			 * are not even supported.
+			 */
+			if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported ||
+			      rdev->wiphy.bands[band]->vht_cap.vht_supported))
 				return -EINVAL;
 
 			for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++)
 				if (mask.control[band].ht_mcs[i])
-					break;
+					goto out;
+
+			for (i = 0; i < NL80211_VHT_NSS_MAX; i++)
+				if (mask.control[band].vht_mcs[i])
+					goto out;
 
 			/* legacy and mcs rates may not be both empty */
-			if (i == IEEE80211_HT_MCS_MASK_LEN)
-				return -EINVAL;
+			return -EINVAL;
 		}
 	}
 
-- 
cgit v1.2.3


From d8bcc768c80e73cf4e948cb327949174b4b5b9e7 Mon Sep 17 00:00:00 2001
From: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>
Date: Thu, 12 Dec 2013 15:00:42 +0200
Subject: netfilter: nf_tables: Expose the table usage counter via netlink

Userspace can therefore know whether a table is in use or not, and
by how many chains. Suggested by Pablo Neira Ayuso.

Signed-off-by: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nf_tables_api.c            | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 256d36b1b94a..b25481e16f0a 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -110,11 +110,13 @@ enum nft_table_flags {
  *
  * @NFTA_TABLE_NAME: name of the table (NLA_STRING)
  * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32)
+ * @NFTA_TABLE_USE: number of chains in this table (NLA_U32)
  */
 enum nft_table_attributes {
 	NFTA_TABLE_UNSPEC,
 	NFTA_TABLE_NAME,
 	NFTA_TABLE_FLAGS,
+	NFTA_TABLE_USE,
 	__NFTA_TABLE_MAX
 };
 #define NFTA_TABLE_MAX		(__NFTA_TABLE_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index dcddc49c0e08..604512d523f7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -180,7 +180,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
 	nfmsg->res_id		= 0;
 
 	if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
-	    nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)))
+	    nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
+	    nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)))
 		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
-- 
cgit v1.2.3


From 0a98a0d12c40f9354b942325045cae123d594341 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Sun, 15 Dec 2013 16:41:51 -0800
Subject: bonding: add primary attribute netlink support

Add IFLA_BOND_PRIMARY to allow get/set of bonding parameter
primary via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 20 +++++++++++++++
 drivers/net/bonding/bond_options.c | 52 ++++++++++++++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 52 +++++++-------------------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 83 insertions(+), 43 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 990793dcccde..9445243593fc 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -32,6 +32,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_ARP_IP_TARGET]	= { .type = NLA_NESTED },
 	[IFLA_BOND_ARP_VALIDATE]	= { .type = NLA_U32 },
 	[IFLA_BOND_ARP_ALL_TARGETS]	= { .type = NLA_U32 },
+	[IFLA_BOND_PRIMARY]		= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -154,6 +155,19 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_PRIMARY]) {
+		int ifindex = nla_get_u32(data[IFLA_BOND_PRIMARY]);
+		struct net_device *dev;
+		char *primary = "";
+
+		dev = __dev_get_by_index(dev_net(bond_dev), ifindex);
+		if (dev)
+			primary = dev->name;
+
+		err = bond_option_primary_set(bond, primary);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -182,6 +196,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS +
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_VALIDATE */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_ALL_TARGETS */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_PRIMARY */
 		0;
 }
 
@@ -241,6 +256,11 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->params.arp_all_targets))
 		goto nla_put_failure;
 
+	if (bond->primary_slave &&
+	    nla_put_u32(skb, IFLA_BOND_PRIMARY,
+			bond->primary_slave->dev->ifindex))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 600779e5904f..c410d2d0dc33 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -467,3 +467,55 @@ int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets)
 
 	return 0;
 }
+
+int bond_option_primary_set(struct bonding *bond, const char *primary)
+{
+	struct list_head *iter;
+	struct slave *slave;
+	int err = 0;
+
+	block_netpoll_tx();
+	read_lock(&bond->lock);
+	write_lock_bh(&bond->curr_slave_lock);
+
+	if (!USES_PRIMARY(bond->params.mode)) {
+		pr_err("%s: Unable to set primary slave; %s is in mode %d\n",
+		       bond->dev->name, bond->dev->name, bond->params.mode);
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* check to see if we are clearing primary */
+	if (!strlen(primary)) {
+		pr_info("%s: Setting primary slave to None.\n",
+			bond->dev->name);
+		bond->primary_slave = NULL;
+		memset(bond->params.primary, 0, sizeof(bond->params.primary));
+		bond_select_active_slave(bond);
+		goto out;
+	}
+
+	bond_for_each_slave(bond, slave, iter) {
+		if (strncmp(slave->dev->name, primary, IFNAMSIZ) == 0) {
+			pr_info("%s: Setting %s as primary slave.\n",
+				bond->dev->name, slave->dev->name);
+			bond->primary_slave = slave;
+			strcpy(bond->params.primary, slave->dev->name);
+			bond_select_active_slave(bond);
+			goto out;
+		}
+	}
+
+	strncpy(bond->params.primary, primary, IFNAMSIZ);
+	bond->params.primary[IFNAMSIZ - 1] = 0;
+
+	pr_info("%s: Recording %s as primary, but it has not been enslaved to %s yet.\n",
+		bond->dev->name, primary, bond->dev->name);
+
+out:
+	write_unlock_bh(&bond->curr_slave_lock);
+	read_unlock(&bond->lock);
+	unblock_netpoll_tx();
+
+	return err;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 6368d299d5a6..7304c2bd2285 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -871,56 +871,22 @@ static ssize_t bonding_store_primary(struct device *d,
 				     const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	struct list_head *iter;
 	char ifname[IFNAMSIZ];
-	struct slave *slave;
-
-	if (!rtnl_trylock())
-		return restart_syscall();
-	block_netpoll_tx();
-	write_lock_bh(&bond->curr_slave_lock);
-
-	if (!USES_PRIMARY(bond->params.mode)) {
-		pr_info("%s: Unable to set primary slave; %s is in mode %d\n",
-			bond->dev->name, bond->dev->name, bond->params.mode);
-		goto out;
-	}
+	int ret;
 
 	sscanf(buf, "%15s", ifname); /* IFNAMSIZ */
+	if (ifname[0] == '\n')
+		ifname[0] = '\0';
 
-	/* check to see if we are clearing primary */
-	if (!strlen(ifname) || buf[0] == '\n') {
-		pr_info("%s: Setting primary slave to None.\n",
-			bond->dev->name);
-		bond->primary_slave = NULL;
-		memset(bond->params.primary, 0, sizeof(bond->params.primary));
-		bond_select_active_slave(bond);
-		goto out;
-	}
-
-	bond_for_each_slave(bond, slave, iter) {
-		if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) {
-			pr_info("%s: Setting %s as primary slave.\n",
-				bond->dev->name, slave->dev->name);
-			bond->primary_slave = slave;
-			strcpy(bond->params.primary, slave->dev->name);
-			bond_select_active_slave(bond);
-			goto out;
-		}
-	}
+	if (!rtnl_trylock())
+		return restart_syscall();
 
-	strncpy(bond->params.primary, ifname, IFNAMSIZ);
-	bond->params.primary[IFNAMSIZ - 1] = 0;
+	ret = bond_option_primary_set(bond, ifname);
+	if (!ret)
+		ret = count;
 
-	pr_info("%s: Recording %s as primary, "
-		"but it has not been enslaved to %s yet.\n",
-		bond->dev->name, ifname, bond->dev->name);
-out:
-	write_unlock_bh(&bond->curr_slave_lock);
-	unblock_netpoll_tx();
 	rtnl_unlock();
-
-	return count;
+	return ret;
 }
 static DEVICE_ATTR(primary, S_IRUGO | S_IWUSR,
 		   bonding_show_primary, bonding_store_primary);
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 8f0d6d0c383b..ec35802cd265 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -454,6 +454,7 @@ int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
 int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
 int bond_option_arp_validate_set(struct bonding *bond, int arp_validate);
 int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets);
+int bond_option_primary_set(struct bonding *bond, const char *primary);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index a897b7e22541..fb3cfe2b176a 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -339,6 +339,7 @@ enum {
 	IFLA_BOND_ARP_IP_TARGET,
 	IFLA_BOND_ARP_VALIDATE,
 	IFLA_BOND_ARP_ALL_TARGETS,
+	IFLA_BOND_PRIMARY,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 8a41ae4496e534a8b68d9bc3c79113e16d1fcd4c Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Sun, 15 Dec 2013 16:41:58 -0800
Subject: bonding: add primary_select attribute netlink support

Add IFLA_BOND_PRIMARY_SELECT to allow get/set of bonding parameter
primary_select via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c | 16 ++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 24 ++++++++----------------
 drivers/net/bonding/bonding.h      |  2 ++
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 41 insertions(+), 16 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 9445243593fc..b361c674dc00 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -33,6 +33,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_ARP_VALIDATE]	= { .type = NLA_U32 },
 	[IFLA_BOND_ARP_ALL_TARGETS]	= { .type = NLA_U32 },
 	[IFLA_BOND_PRIMARY]		= { .type = NLA_U32 },
+	[IFLA_BOND_PRIMARY_RESELECT]	= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -168,6 +169,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_PRIMARY_RESELECT]) {
+		int primary_reselect =
+			nla_get_u8(data[IFLA_BOND_PRIMARY_RESELECT]);
+
+		err = bond_option_primary_reselect_set(bond, primary_reselect);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -197,6 +206,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_VALIDATE */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_ALL_TARGETS */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_PRIMARY */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_PRIMARY_RESELECT */
 		0;
 }
 
@@ -261,6 +271,10 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->primary_slave->dev->ifindex))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_PRIMARY_RESELECT,
+		       bond->params.primary_reselect))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index c410d2d0dc33..80a9df4e4bf7 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -519,3 +519,19 @@ out:
 
 	return err;
 }
+
+int bond_option_primary_reselect_set(struct bonding *bond, int primary_reselect)
+{
+	bond->params.primary_reselect = primary_reselect;
+	pr_info("%s: setting primary_reselect to %s (%d).\n",
+		bond->dev->name, pri_reselect_tbl[primary_reselect].modename,
+		primary_reselect);
+
+	block_netpoll_tx();
+	write_lock_bh(&bond->curr_slave_lock);
+	bond_select_active_slave(bond);
+	write_unlock_bh(&bond->curr_slave_lock);
+	unblock_netpoll_tx();
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 7304c2bd2285..324afa5fda93 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -909,32 +909,24 @@ static ssize_t bonding_store_primary_reselect(struct device *d,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-
 	new_value = bond_parse_parm(buf, pri_reselect_tbl);
 	if (new_value < 0)  {
 		pr_err("%s: Ignoring invalid primary_reselect value %.*s.\n",
 		       bond->dev->name,
 		       (int) strlen(buf) - 1, buf);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	bond->params.primary_reselect = new_value;
-	pr_info("%s: setting primary_reselect to %s (%d).\n",
-		bond->dev->name, pri_reselect_tbl[new_value].modename,
-		new_value);
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_primary_reselect_set(bond, new_value);
+	if (!ret)
+		ret = count;
 
-	block_netpoll_tx();
-	write_lock_bh(&bond->curr_slave_lock);
-	bond_select_active_slave(bond);
-	write_unlock_bh(&bond->curr_slave_lock);
-	unblock_netpoll_tx();
-out:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index ec35802cd265..4e89d0480a5e 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -455,6 +455,8 @@ int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
 int bond_option_arp_validate_set(struct bonding *bond, int arp_validate);
 int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets);
 int bond_option_primary_set(struct bonding *bond, const char *primary);
+int bond_option_primary_reselect_set(struct bonding *bond,
+				     int primary_reselect);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index fb3cfe2b176a..cf59d54a199d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -340,6 +340,7 @@ enum {
 	IFLA_BOND_ARP_VALIDATE,
 	IFLA_BOND_ARP_ALL_TARGETS,
 	IFLA_BOND_PRIMARY,
+	IFLA_BOND_PRIMARY_RESELECT,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 89901972de4c00e74e56529804493734d77ee3d3 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Sun, 15 Dec 2013 16:42:05 -0800
Subject: bonding: add fail_over_mac attribute netlink support

Add IFLA_BOND_FAIL_OVER_MAC to allow get/set of bonding parameter
fail_over_mac via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c | 16 ++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 26 ++++++++------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 40 insertions(+), 18 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index b361c674dc00..dc465ad3fb7c 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -34,6 +34,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_ARP_ALL_TARGETS]	= { .type = NLA_U32 },
 	[IFLA_BOND_PRIMARY]		= { .type = NLA_U32 },
 	[IFLA_BOND_PRIMARY_RESELECT]	= { .type = NLA_U8 },
+	[IFLA_BOND_FAIL_OVER_MAC]	= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -177,6 +178,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_FAIL_OVER_MAC]) {
+		int fail_over_mac =
+			nla_get_u8(data[IFLA_BOND_FAIL_OVER_MAC]);
+
+		err = bond_option_fail_over_mac_set(bond, fail_over_mac);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -207,6 +216,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_ARP_ALL_TARGETS */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_PRIMARY */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_PRIMARY_RESELECT */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_FAIL_OVER_MAC */
 		0;
 }
 
@@ -275,6 +285,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.primary_reselect))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_FAIL_OVER_MAC,
+		       bond->params.fail_over_mac))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 80a9df4e4bf7..86f462008932 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -535,3 +535,19 @@ int bond_option_primary_reselect_set(struct bonding *bond, int primary_reselect)
 
 	return 0;
 }
+
+int bond_option_fail_over_mac_set(struct bonding *bond, int fail_over_mac)
+{
+	if (bond_has_slaves(bond)) {
+		pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n",
+		       bond->dev->name);
+		return -EPERM;
+	}
+
+	bond->params.fail_over_mac = fail_over_mac;
+	pr_info("%s: Setting fail_over_mac to %s (%d).\n",
+		bond->dev->name, fail_over_mac_tbl[fail_over_mac].modename,
+		fail_over_mac);
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 324afa5fda93..c84a90f9a0ac 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -442,33 +442,23 @@ static ssize_t bonding_store_fail_over_mac(struct device *d,
 					   struct device_attribute *attr,
 					   const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
-
-	if (bond_has_slaves(bond)) {
-		pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n",
-		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
-	}
-
 	new_value = bond_parse_parm(buf, fail_over_mac_tbl);
 	if (new_value < 0) {
 		pr_err("%s: Ignoring invalid fail_over_mac value %s.\n",
 		       bond->dev->name, buf);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	bond->params.fail_over_mac = new_value;
-	pr_info("%s: Setting fail_over_mac to %s (%d).\n",
-		bond->dev->name, fail_over_mac_tbl[new_value].modename,
-		new_value);
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_fail_over_mac_set(bond, new_value);
+	if (!ret)
+		ret = count;
 
-out:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 4e89d0480a5e..b69059b361a0 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -457,6 +457,7 @@ int bond_option_arp_all_targets_set(struct bonding *bond, int arp_all_targets);
 int bond_option_primary_set(struct bonding *bond, const char *primary);
 int bond_option_primary_reselect_set(struct bonding *bond,
 				     int primary_reselect);
+int bond_option_fail_over_mac_set(struct bonding *bond, int fail_over_mac);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cf59d54a199d..fd181abd19b9 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -341,6 +341,7 @@ enum {
 	IFLA_BOND_ARP_ALL_TARGETS,
 	IFLA_BOND_PRIMARY,
 	IFLA_BOND_PRIMARY_RESELECT,
+	IFLA_BOND_FAIL_OVER_MAC,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From f70161c67231f54f784529d7447ce4386d258b7a Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Sun, 15 Dec 2013 16:42:12 -0800
Subject: bonding: add xmit_hash_policy attribute netlink support

Add IFLA_BOND_XMIT_HASH_POLICY to allow get/set of bonding parameter
xmit_hash_policy via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c | 10 ++++++++++
 drivers/net/bonding/bond_sysfs.c   | 17 ++++++++++-------
 drivers/net/bonding/bonding.h      |  2 ++
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 37 insertions(+), 7 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index dc465ad3fb7c..67acd21a2170 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -35,6 +35,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_PRIMARY]		= { .type = NLA_U32 },
 	[IFLA_BOND_PRIMARY_RESELECT]	= { .type = NLA_U8 },
 	[IFLA_BOND_FAIL_OVER_MAC]	= { .type = NLA_U8 },
+	[IFLA_BOND_XMIT_HASH_POLICY]	= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -186,6 +187,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_XMIT_HASH_POLICY]) {
+		int xmit_hash_policy =
+			nla_get_u8(data[IFLA_BOND_XMIT_HASH_POLICY]);
+
+		err = bond_option_xmit_hash_policy_set(bond, xmit_hash_policy);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -217,6 +226,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_PRIMARY */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_PRIMARY_RESELECT */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_FAIL_OVER_MAC */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_XMIT_HASH_POLICY */
 		0;
 }
 
@@ -289,6 +299,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.fail_over_mac))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_XMIT_HASH_POLICY,
+		       bond->params.xmit_policy))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 86f462008932..8510c6df115b 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -551,3 +551,13 @@ int bond_option_fail_over_mac_set(struct bonding *bond, int fail_over_mac)
 
 	return 0;
 }
+
+int bond_option_xmit_hash_policy_set(struct bonding *bond, int xmit_hash_policy)
+{
+	bond->params.xmit_policy = xmit_hash_policy;
+	pr_info("%s: setting xmit hash policy to %s (%d).\n",
+		bond->dev->name,
+		xmit_hashtype_tbl[xmit_hash_policy].modename, xmit_hash_policy);
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index c84a90f9a0ac..4c7532289d87 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -318,7 +318,7 @@ static ssize_t bonding_store_xmit_hash(struct device *d,
 				       struct device_attribute *attr,
 				       const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
 	new_value = bond_parse_parm(buf, xmit_hashtype_tbl);
@@ -326,14 +326,17 @@ static ssize_t bonding_store_xmit_hash(struct device *d,
 		pr_err("%s: Ignoring invalid xmit hash policy value %.*s.\n",
 		       bond->dev->name,
 		       (int)strlen(buf) - 1, buf);
-		ret = -EINVAL;
-	} else {
-		bond->params.xmit_policy = new_value;
-		pr_info("%s: setting xmit hash policy to %s (%d).\n",
-			bond->dev->name,
-			xmit_hashtype_tbl[new_value].modename, new_value);
+		return -EINVAL;
 	}
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_xmit_hash_policy_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(xmit_hash_policy, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index b69059b361a0..4cb603e9c591 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -458,6 +458,8 @@ int bond_option_primary_set(struct bonding *bond, const char *primary);
 int bond_option_primary_reselect_set(struct bonding *bond,
 				     int primary_reselect);
 int bond_option_fail_over_mac_set(struct bonding *bond, int fail_over_mac);
+int bond_option_xmit_hash_policy_set(struct bonding *bond,
+				     int xmit_hash_policy);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index fd181abd19b9..1a5d394894ea 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -342,6 +342,7 @@ enum {
 	IFLA_BOND_PRIMARY,
 	IFLA_BOND_PRIMARY_RESELECT,
 	IFLA_BOND_FAIL_OVER_MAC,
+	IFLA_BOND_XMIT_HASH_POLICY,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From d8838de70adc64e20db531333e035aacd5910fca Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Sun, 15 Dec 2013 16:42:19 -0800
Subject: bonding: add resend_igmp attribute netlink support

Add IFLA_BOND_RESEND_IGMP to allow get/set of bonding parameter
resend_igmp via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c | 15 +++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 20 ++++++++------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 39 insertions(+), 12 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 67acd21a2170..e161c9cbd91e 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -36,6 +36,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_PRIMARY_RESELECT]	= { .type = NLA_U8 },
 	[IFLA_BOND_FAIL_OVER_MAC]	= { .type = NLA_U8 },
 	[IFLA_BOND_XMIT_HASH_POLICY]	= { .type = NLA_U8 },
+	[IFLA_BOND_RESEND_IGMP]		= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -195,6 +196,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_RESEND_IGMP]) {
+		int resend_igmp =
+			nla_get_u32(data[IFLA_BOND_RESEND_IGMP]);
+
+		err = bond_option_resend_igmp_set(bond, resend_igmp);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -227,6 +236,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_PRIMARY_RESELECT */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_FAIL_OVER_MAC */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_XMIT_HASH_POLICY */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_RESEND_IGMP */
 		0;
 }
 
@@ -303,6 +313,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.xmit_policy))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP,
+		        bond->params.resend_igmp))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 8510c6df115b..1ed7dff9a679 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -561,3 +561,18 @@ int bond_option_xmit_hash_policy_set(struct bonding *bond, int xmit_hash_policy)
 
 	return 0;
 }
+
+int bond_option_resend_igmp_set(struct bonding *bond, int resend_igmp)
+{
+	if (resend_igmp < 0 || resend_igmp > 255) {
+		pr_err("%s: Invalid resend_igmp value %d not in range 0-255; rejected.\n",
+		       bond->dev->name, resend_igmp);
+		return -EINVAL;
+	}
+
+	bond->params.resend_igmp = resend_igmp;
+	pr_info("%s: Setting resend_igmp to %d.\n",
+		bond->dev->name, resend_igmp);
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 4c7532289d87..f5c1a54095b9 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1336,21 +1336,17 @@ static ssize_t bonding_store_resend_igmp(struct device *d,
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no resend_igmp value specified.\n",
 		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	if (new_value < 0 || new_value > 255) {
-		pr_err("%s: Invalid resend_igmp value %d not in range 0-255; rejected.\n",
-		       bond->dev->name, new_value);
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!rtnl_trylock())
+		return restart_syscall();
 
-	pr_info("%s: Setting resend_igmp to %d.\n",
-		bond->dev->name, new_value);
-	bond->params.resend_igmp = new_value;
-out:
+	ret = bond_option_resend_igmp_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
 	return ret;
 }
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 4cb603e9c591..c70ad9f02b1e 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -460,6 +460,7 @@ int bond_option_primary_reselect_set(struct bonding *bond,
 int bond_option_fail_over_mac_set(struct bonding *bond, int fail_over_mac);
 int bond_option_xmit_hash_policy_set(struct bonding *bond,
 				     int xmit_hash_policy);
+int bond_option_resend_igmp_set(struct bonding *bond, int resend_igmp);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1a5d394894ea..6e275d5214f3 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -343,6 +343,7 @@ enum {
 	IFLA_BOND_PRIMARY_RESELECT,
 	IFLA_BOND_FAIL_OVER_MAC,
 	IFLA_BOND_XMIT_HASH_POLICY,
+	IFLA_BOND_RESEND_IGMP,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From e4d26f4b080f55e9577b45e6b51a04971eb459e9 Mon Sep 17 00:00:00 2001
From: Atzm Watanabe <atzm@stratosphere.co.jp>
Date: Tue, 17 Dec 2013 22:53:36 +0900
Subject: packet: fill the gap of TPACKET_ALIGNMENT with zeros

struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
Explicitly defining and zeroing the gap of this makes additional changes
easier.

Signed-off-by: Atzm Watanabe <atzm@stratosphere.co.jp>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_packet.h | 3 ++-
 net/packet/af_packet.c         | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index 1e24aa701cbd..9185dc9a4485 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -133,7 +133,7 @@ struct tpacket2_hdr {
 	__u32		tp_sec;
 	__u32		tp_nsec;
 	__u16		tp_vlan_tci;
-	__u16		tp_padding;
+	__u8		tp_padding[6];
 };
 
 struct tpacket_hdr_variant1 {
@@ -154,6 +154,7 @@ struct tpacket3_hdr {
 	union {
 		struct tpacket_hdr_variant1 hv1;
 	};
+	__u8		tp_padding[12];
 };
 
 struct tpacket_bd_ts {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 4fd52181b6ce..f281999ba92e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1929,7 +1929,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		} else {
 			h.h2->tp_vlan_tci = 0;
 		}
-		h.h2->tp_padding = 0;
+		memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding));
 		hdrlen = sizeof(*h.h2);
 		break;
 	case TPACKET_V3:
@@ -1943,6 +1943,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h3->tp_net = netoff;
 		h.h3->tp_sec  = ts.tv_sec;
 		h.h3->tp_nsec = ts.tv_nsec;
+		memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding));
 		hdrlen = sizeof(*h.h3);
 		break;
 	default:
-- 
cgit v1.2.3


From a0cdfcf39362410d5ea983f4daf67b38de129408 Mon Sep 17 00:00:00 2001
From: Atzm Watanabe <atzm@stratosphere.co.jp>
Date: Tue, 17 Dec 2013 22:53:40 +0900
Subject: packet: deliver VLAN TPID to userspace

This enables userspace to get VLAN TPID as well as the VLAN TCI.

Signed-off-by: Atzm Watanabe <atzm@stratosphere.co.jp>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_packet.h | 24 ++++++++++++++----------
 net/packet/af_packet.c         | 14 ++++++++++----
 2 files changed, 24 insertions(+), 14 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index 9185dc9a4485..e9d844c80c11 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -84,17 +84,18 @@ struct tpacket_auxdata {
 	__u16		tp_mac;
 	__u16		tp_net;
 	__u16		tp_vlan_tci;
-	__u16		tp_padding;
+	__u16		tp_vlan_tpid;
 };
 
 /* Rx ring - header status */
-#define TP_STATUS_KERNEL	      0
-#define TP_STATUS_USER		(1 << 0)
-#define TP_STATUS_COPY		(1 << 1)
-#define TP_STATUS_LOSING	(1 << 2)
-#define TP_STATUS_CSUMNOTREADY	(1 << 3)
-#define TP_STATUS_VLAN_VALID	(1 << 4) /* auxdata has valid tp_vlan_tci */
-#define TP_STATUS_BLK_TMO	(1 << 5)
+#define TP_STATUS_KERNEL		      0
+#define TP_STATUS_USER			(1 << 0)
+#define TP_STATUS_COPY			(1 << 1)
+#define TP_STATUS_LOSING		(1 << 2)
+#define TP_STATUS_CSUMNOTREADY		(1 << 3)
+#define TP_STATUS_VLAN_VALID		(1 << 4) /* auxdata has valid tp_vlan_tci */
+#define TP_STATUS_BLK_TMO		(1 << 5)
+#define TP_STATUS_VLAN_TPID_VALID	(1 << 6) /* auxdata has valid tp_vlan_tpid */
 
 /* Tx ring - header status */
 #define TP_STATUS_AVAILABLE	      0
@@ -133,12 +134,15 @@ struct tpacket2_hdr {
 	__u32		tp_sec;
 	__u32		tp_nsec;
 	__u16		tp_vlan_tci;
-	__u8		tp_padding[6];
+	__u16		tp_vlan_tpid;
+	__u8		tp_padding[4];
 };
 
 struct tpacket_hdr_variant1 {
 	__u32	tp_rxhash;
 	__u32	tp_vlan_tci;
+	__u16	tp_vlan_tpid;
+	__u16	tp_padding;
 };
 
 struct tpacket3_hdr {
@@ -154,7 +158,7 @@ struct tpacket3_hdr {
 	union {
 		struct tpacket_hdr_variant1 hv1;
 	};
-	__u8		tp_padding[12];
+	__u8		tp_padding[8];
 };
 
 struct tpacket_bd_ts {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f281999ba92e..dd3840846ce2 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -977,9 +977,11 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 {
 	if (vlan_tx_tag_present(pkc->skb)) {
 		ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb);
-		ppd->tp_status = TP_STATUS_VLAN_VALID;
+		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
+		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 	} else {
 		ppd->hv1.tp_vlan_tci = 0;
+		ppd->hv1.tp_vlan_tpid = 0;
 		ppd->tp_status = TP_STATUS_AVAILABLE;
 	}
 }
@@ -987,6 +989,7 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
+	ppd->hv1.tp_padding = 0;
 	prb_fill_vlan_info(pkc, ppd);
 
 	if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH)
@@ -1925,9 +1928,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h2->tp_nsec = ts.tv_nsec;
 		if (vlan_tx_tag_present(skb)) {
 			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
-			status |= TP_STATUS_VLAN_VALID;
+			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
+			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			h.h2->tp_vlan_tci = 0;
+			h.h2->tp_vlan_tpid = 0;
 		}
 		memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding));
 		hdrlen = sizeof(*h.h2);
@@ -2875,11 +2880,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		aux.tp_net = skb_network_offset(skb);
 		if (vlan_tx_tag_present(skb)) {
 			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-			aux.tp_status |= TP_STATUS_VLAN_VALID;
+			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
+			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			aux.tp_vlan_tci = 0;
+			aux.tp_vlan_tpid = 0;
 		}
-		aux.tp_padding = 0;
 		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
 	}
 
-- 
cgit v1.2.3


From 93b36cf3425b9bd9c56df7680fb237686b9c82ae Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sun, 15 Dec 2013 03:41:14 +0100
Subject: ipv6: support IPV6_PMTU_INTERFACE on sockets

IPV6_PMTU_INTERFACE is the same as IPV6_PMTU_PROBE for ipv6. Add it
nontheless for symmetry with IPv4 sockets. Also drop incoming MTU
information if this mode is enabled.

The additional bit in ipv6_pinfo just eats in the padding behind the
bitfield. There are no changes to the layout of the struct at all.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h     | 2 +-
 include/net/ip6_route.h  | 7 ++++++-
 include/uapi/linux/in6.h | 4 ++++
 net/dccp/ipv6.c          | 3 +++
 net/ipv6/ip6_output.c    | 6 +++---
 net/ipv6/ipv6_sockglue.c | 2 +-
 net/ipv6/tcp_ipv6.c      | 3 +++
 net/ipv6/udp.c           | 5 ++++-
 net/sctp/input.c         | 3 +++
 9 files changed, 28 insertions(+), 7 deletions(-)

(limited to 'include/uapi')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 3fde06645553..7e1ded0d8e45 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -191,7 +191,7 @@ struct ipv6_pinfo {
 	/* sockopt flags */
 	__u16			recverr:1,
 	                        sndflow:1,
-				pmtudisc:2,
+				pmtudisc:3,
 				ipv6only:1,
 				srcprefs:3,	/* 001: prefer temporary address
 						 * 010: prefer public address
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 733747ce163c..c2626ce1f2ad 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -178,10 +178,15 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
 
-	return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ?
+	return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ?
 	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
 }
 
+static inline bool ip6_sk_accept_pmtu(const struct sock *sk)
+{
+	return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE;
+}
+
 static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt)
 {
 	return &rt->rt6i_gateway;
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 440d5c479145..f94f1d013bf2 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -188,6 +188,10 @@ enum {
 #define IPV6_PMTUDISC_WANT		1
 #define IPV6_PMTUDISC_DO		2
 #define IPV6_PMTUDISC_PROBE		3
+/* same as IPV6_PMTUDISC_PROBE, provided for symetry with IPv4
+ * also see comments on IP_PMTUDISC_INTERFACE
+ */
+#define IPV6_PMTUDISC_INTERFACE		4
 
 /* Flowlabel */
 #define IPV6_FLOWLABEL_MGR	32
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 2b90a786e475..629019e6f8e9 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -141,6 +141,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == ICMPV6_PKT_TOOBIG) {
 		struct dst_entry *dst = NULL;
 
+		if (!ip6_sk_accept_pmtu(sk))
+			goto out;
+
 		if (sock_owned_by_user(sk))
 			goto out;
 		if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9a311cc79672..bc4e1bcdf4c0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1165,10 +1165,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
 		if (rt->dst.flags & DST_XFRM_TUNNEL)
-			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
 			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
 		else
-			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
 			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
 		if (np->frag_size < mtu) {
 			if (np->frag_size)
@@ -1270,7 +1270,7 @@ alloc_new_skb:
 			if (skb == NULL || skb_prev == NULL)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
-						    np->pmtudisc ==
+						    np->pmtudisc >=
 						    IPV6_PMTUDISC_PROBE);
 
 			skb_prev = skb;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 759fbf96515b..af0ecb94b3b4 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -722,7 +722,7 @@ done:
 	case IPV6_MTU_DISCOVER:
 		if (optlen < sizeof(int))
 			goto e_inval;
-		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
+		if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE)
 			goto e_inval;
 		np->pmtudisc = val;
 		retv = 0;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index da046a5d7ffb..d955487f2c54 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -397,6 +397,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (sk->sk_state == TCP_LISTEN)
 			goto out;
 
+		if (!ip6_sk_accept_pmtu(sk))
+			goto out;
+
 		tp->mtu_info = ntohl(info);
 		if (!sock_owned_by_user(sk))
 			tcp_v6_mtu_reduced(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 089c741a3992..65ed5cd79264 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -538,8 +538,11 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (sk == NULL)
 		return;
 
-	if (type == ICMPV6_PKT_TOOBIG)
+	if (type == ICMPV6_PKT_TOOBIG) {
+		if (!ip6_sk_accept_pmtu(sk))
+			goto out;
 		ip6_sk_update_pmtu(skb, sk, info);
+	}
 	if (type == NDISC_REDIRECT) {
 		ip6_sk_redirect(skb, sk);
 		goto out;
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 2a192a7c5d81..042ec6c9ae24 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -389,6 +389,9 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 	if (!t || (t->pathmtu <= pmtu))
 		return;
 
+	if (!ip6_sk_accept_pmtu(sk))
+		return;
+
 	if (sock_owned_by_user(sk)) {
 		asoc->pmtu_pending = 1;
 		t->pmtu_pending = 1;
-- 
cgit v1.2.3


From 567ffc3509b2d3f965a49a18631d3da7f9a96d4f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 18 Dec 2013 14:43:31 +0100
Subject: nl80211: support vendor-specific events

In addition to vendor-specific commands, also support vendor-specific
events. These must be registered with cfg80211 before they can be used.
They're also advertised in nl80211 in the wiphy information so that
userspace knows can be expected. The events themselves are sent on a
new multicast group called "vendor".

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 65 +++++++++++++++++++++++++++--
 include/uapi/linux/nl80211.h |  3 ++
 net/wireless/nl80211.c       | 98 +++++++++++++++++++++++++++++++++++---------
 3 files changed, 143 insertions(+), 23 deletions(-)

(limited to 'include/uapi')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 80a10212b1b9..6d238a4331bd 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2824,6 +2824,8 @@ struct wiphy_vendor_command {
  *
  * @vendor_commands: array of vendor commands supported by the hardware
  * @n_vendor_commands: number of vendor commands
+ * @vendor_events: array of vendor events supported by the hardware
+ * @n_vendor_events: number of vendor events
  */
 struct wiphy {
 	/* assign these fields before you register the wiphy */
@@ -2936,7 +2938,8 @@ struct wiphy {
 	const struct wiphy_coalesce_support *coalesce;
 
 	const struct wiphy_vendor_command *vendor_commands;
-	int n_vendor_commands;
+	const struct nl80211_vendor_cmd_info *vendor_events;
+	int n_vendor_commands, n_vendor_events;
 
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
@@ -3907,6 +3910,14 @@ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
 					   enum nl80211_attrs attr,
 					   int approxlen);
 
+struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
+					   enum nl80211_commands cmd,
+					   enum nl80211_attrs attr,
+					   int vendor_event_idx,
+					   int approxlen, gfp_t gfp);
+
+void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp);
+
 /**
  * cfg80211_vendor_cmd_alloc_reply_skb - allocate vendor command reply
  * @wiphy: the wiphy
@@ -3951,6 +3962,44 @@ cfg80211_vendor_cmd_alloc_reply_skb(struct wiphy *wiphy, int approxlen)
  */
 int cfg80211_vendor_cmd_reply(struct sk_buff *skb);
 
+/**
+ * cfg80211_vendor_event_alloc - allocate vendor-specific event skb
+ * @wiphy: the wiphy
+ * @event_idx: index of the vendor event in the wiphy's vendor_events
+ * @approxlen: an upper bound of the length of the data that will
+ *	be put into the skb
+ * @gfp: allocation flags
+ *
+ * This function allocates and pre-fills an skb for an event on the
+ * vendor-specific multicast group.
+ *
+ * When done filling the skb, call cfg80211_vendor_event() with the
+ * skb to send the event.
+ *
+ * Return: An allocated and pre-filled skb. %NULL if any errors happen.
+ */
+static inline struct sk_buff *
+cfg80211_vendor_event_alloc(struct wiphy *wiphy, int approxlen,
+			    int event_idx, gfp_t gfp)
+{
+	return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_VENDOR,
+					  NL80211_ATTR_VENDOR_DATA,
+					  event_idx, approxlen, gfp);
+}
+
+/**
+ * cfg80211_vendor_event - send the event
+ * @skb: The skb, must have been allocated with cfg80211_vendor_event_alloc()
+ * @gfp: allocation flags
+ *
+ * This function sends the given @skb, which must have been allocated
+ * by cfg80211_vendor_event_alloc(), as an event. It always consumes it.
+ */
+static inline void cfg80211_vendor_event(struct sk_buff *skb, gfp_t gfp)
+{
+	__cfg80211_send_event_skb(skb, gfp);
+}
+
 #ifdef CONFIG_NL80211_TESTMODE
 /**
  * DOC: Test mode
@@ -4031,8 +4080,13 @@ static inline int cfg80211_testmode_reply(struct sk_buff *skb)
  *
  * Return: An allocated and pre-filled skb. %NULL if any errors happen.
  */
-struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy,
-						  int approxlen, gfp_t gfp);
+static inline struct sk_buff *
+cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy, int approxlen, gfp_t gfp)
+{
+	return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_TESTMODE,
+					  NL80211_ATTR_TESTDATA, -1,
+					  approxlen, gfp);
+}
 
 /**
  * cfg80211_testmode_event - send the event
@@ -4044,7 +4098,10 @@ struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy,
  * by cfg80211_testmode_alloc_event_skb(), as an event. It always
  * consumes it.
  */
-void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp);
+static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
+{
+	__cfg80211_send_event_skb(skb, gfp);
+}
 
 #define CFG80211_TESTMODE_CMD(cmd)	.testmode_cmd = (cmd),
 #define CFG80211_TESTMODE_DUMP(cmd)	.testmode_dump = (cmd),
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index e1307909ecf1..381184eb6c96 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1540,6 +1540,8 @@ enum nl80211_commands {
  * @NL80211_ATTR_VENDOR_SUBCMD: vendor sub-command
  * @NL80211_ATTR_VENDOR_DATA: data for the vendor command, if any; this
  *	attribute is also used for vendor command feature advertisement
+ * @NL80211_ATTR_VENDOR_EVENTS: used for event list advertising in the wiphy
+ *	info, containing a nested array of possible events
  *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -1865,6 +1867,7 @@ enum nl80211_attrs {
 	NL80211_ATTR_VENDOR_ID,
 	NL80211_ATTR_VENDOR_SUBCMD,
 	NL80211_ATTR_VENDOR_DATA,
+	NL80211_ATTR_VENDOR_EVENTS,
 
 	/* add attributes here, update the policy in nl80211.c */
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 04681a46eda8..8a7ff041349b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -53,6 +53,7 @@ enum nl80211_multicast_groups {
 	NL80211_MCGRP_SCAN,
 	NL80211_MCGRP_REGULATORY,
 	NL80211_MCGRP_MLME,
+	NL80211_MCGRP_VENDOR,
 	NL80211_MCGRP_TESTMODE /* keep last - ifdef! */
 };
 
@@ -61,6 +62,7 @@ static const struct genl_multicast_group nl80211_mcgrps[] = {
 	[NL80211_MCGRP_SCAN] = { .name = "scan", },
 	[NL80211_MCGRP_REGULATORY] = { .name = "regulatory", },
 	[NL80211_MCGRP_MLME] = { .name = "mlme", },
+	[NL80211_MCGRP_VENDOR] = { .name = "vendor", },
 #ifdef CONFIG_NL80211_TESTMODE
 	[NL80211_MCGRP_TESTMODE] = { .name = "testmode", }
 #endif
@@ -1188,7 +1190,6 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 	struct nlattr *nl_bands, *nl_band;
 	struct nlattr *nl_freqs, *nl_freq;
 	struct nlattr *nl_cmds;
-	struct nlattr *nl_vendor_cmds;
 	enum ieee80211_band band;
 	struct ieee80211_channel *chan;
 	int i;
@@ -1587,16 +1588,38 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		state->split_start++;
 		break;
 	case 11:
-		nl_vendor_cmds = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA);
-		if (!nl_vendor_cmds)
-			goto nla_put_failure;
+		if (dev->wiphy.n_vendor_commands) {
+			const struct nl80211_vendor_cmd_info *info;
+			struct nlattr *nested;
+
+			nested = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA);
+			if (!nested)
+				goto nla_put_failure;
+
+			for (i = 0; i < dev->wiphy.n_vendor_commands; i++) {
+				info = &dev->wiphy.vendor_commands[i].info;
+				if (nla_put(msg, i + 1, sizeof(*info), info))
+					goto nla_put_failure;
+			}
+			nla_nest_end(msg, nested);
+		}
+
+		if (dev->wiphy.n_vendor_events) {
+			const struct nl80211_vendor_cmd_info *info;
+			struct nlattr *nested;
 
-		for (i = 0; i < dev->wiphy.n_vendor_commands; i++)
-			if (nla_put(msg, i + 1,
-				    sizeof(struct nl80211_vendor_cmd_info),
-				    &dev->wiphy.vendor_commands[i].info))
+			nested = nla_nest_start(msg,
+						NL80211_ATTR_VENDOR_EVENTS);
+			if (!nested)
 				goto nla_put_failure;
-		nla_nest_end(msg, nl_vendor_cmds);
+
+			for (i = 0; i < dev->wiphy.n_vendor_events; i++) {
+				info = &dev->wiphy.vendor_events[i];
+				if (nla_put(msg, i + 1, sizeof(*info), info))
+					goto nla_put_failure;
+			}
+			nla_nest_end(msg, nested);
+		}
 
 		/* done */
 		state->split_start = 0;
@@ -6726,7 +6749,9 @@ static struct sk_buff *
 __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
 			    int approxlen, u32 portid, u32 seq,
 			    enum nl80211_commands cmd,
-			    enum nl80211_attrs attr, gfp_t gfp)
+			    enum nl80211_attrs attr,
+			    const struct nl80211_vendor_cmd_info *info,
+			    gfp_t gfp)
 {
 	struct sk_buff *skb;
 	void *hdr;
@@ -6744,6 +6769,16 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
 
 	if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
 		goto nla_put_failure;
+
+	if (info) {
+		if (nla_put_u32(skb, NL80211_ATTR_VENDOR_ID,
+				info->vendor_id))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, NL80211_ATTR_VENDOR_SUBCMD,
+				info->subcmd))
+			goto nla_put_failure;
+	}
+
 	data = nla_nest_start(skb, attr);
 
 	((void **)skb->cb)[0] = rdev;
@@ -6884,29 +6919,54 @@ static int nl80211_testmode_dump(struct sk_buff *skb,
 	return err;
 }
 
-struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy,
-						  int approxlen, gfp_t gfp)
+struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
+					   enum nl80211_commands cmd,
+					   enum nl80211_attrs attr,
+					   int vendor_event_idx,
+					   int approxlen, gfp_t gfp)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	const struct nl80211_vendor_cmd_info *info;
+
+	switch (cmd) {
+	case NL80211_CMD_TESTMODE:
+		if (WARN_ON(vendor_event_idx != -1))
+			return NULL;
+		info = NULL;
+		break;
+	case NL80211_CMD_VENDOR:
+		if (WARN_ON(vendor_event_idx < 0 ||
+			    vendor_event_idx >= wiphy->n_vendor_events))
+			return NULL;
+		info = &wiphy->vendor_events[vendor_event_idx];
+		break;
+	default:
+		WARN_ON(1);
+		return NULL;
+	}
 
 	return __cfg80211_alloc_vendor_skb(rdev, approxlen, 0, 0,
-					   NL80211_CMD_TESTMODE,
-					   NL80211_ATTR_TESTDATA, gfp);
+					   cmd, attr, info, gfp);
 }
-EXPORT_SYMBOL(cfg80211_testmode_alloc_event_skb);
+EXPORT_SYMBOL(__cfg80211_alloc_event_skb);
 
-void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
+void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp)
 {
 	struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
 	void *hdr = ((void **)skb->cb)[1];
 	struct nlattr *data = ((void **)skb->cb)[2];
+	enum nl80211_multicast_groups mcgrp = NL80211_MCGRP_TESTMODE;
 
 	nla_nest_end(skb, data);
 	genlmsg_end(skb, hdr);
+
+	if (data->nla_type == NL80211_ATTR_VENDOR_DATA)
+		mcgrp = NL80211_MCGRP_VENDOR;
+
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), skb, 0,
-				NL80211_MCGRP_TESTMODE, gfp);
+				mcgrp, gfp);
 }
-EXPORT_SYMBOL(cfg80211_testmode_event);
+EXPORT_SYMBOL(__cfg80211_send_event_skb);
 #endif
 
 static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
@@ -9039,7 +9099,7 @@ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
 	return __cfg80211_alloc_vendor_skb(rdev, approxlen,
 					   rdev->cur_cmd_info->snd_portid,
 					   rdev->cur_cmd_info->snd_seq,
-					   cmd, attr, GFP_KERNEL);
+					   cmd, attr, NULL, GFP_KERNEL);
 }
 EXPORT_SYMBOL(__cfg80211_alloc_reply_skb);
 
-- 
cgit v1.2.3


From fa9ffc745610f31c6bc136d5a6a1782e00870e72 Mon Sep 17 00:00:00 2001
From: Kyeyoon Park <kyeyoonp@qca.qualcomm.com>
Date: Mon, 16 Dec 2013 23:01:30 -0800
Subject: cfg80211: Add support for QoS mapping

This allows QoS mapping from external networks to be implemented as
defined in IEEE Std 802.11-2012, 10.24.9. APs can use this to advertise
DSCP ranges and exceptions for mapping frames to a specific UP over
Wi-Fi.

The payload of the QoS Map Set element (IEEE Std 802.11-2012, 8.4.2.97)
is sent to the driver through the new NL80211_ATTR_QOS_MAP attribute to
configure the local behavior either on the AP (based on local
configuration) or on a station (based on information received from the
AP).

Signed-off-by: Kyeyoon Park <kyeyoonp@qca.qualcomm.com>
Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c |  2 +-
 drivers/net/wireless/mwifiex/main.c                |  2 +-
 include/net/cfg80211.h                             | 53 +++++++++++++++++-
 include/uapi/linux/nl80211.h                       | 14 +++++
 net/mac80211/wme.c                                 |  2 +-
 net/wireless/ap.c                                  |  1 +
 net/wireless/ibss.c                                |  2 +
 net/wireless/mesh.c                                |  1 +
 net/wireless/nl80211.c                             | 62 ++++++++++++++++++++++
 net/wireless/rdev-ops.h                            | 15 ++++++
 net/wireless/sme.c                                 |  2 +
 net/wireless/trace.h                               | 40 ++++++++++++++
 net/wireless/util.c                                | 19 ++++++-
 13 files changed, 210 insertions(+), 5 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
index e9bdfdb95d8f..4f80e12a1d4a 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
@@ -1873,7 +1873,7 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 	brcmf_dbg(DATA, "tx proto=0x%X\n", ntohs(eh->h_proto));
 	/* determine the priority */
 	if (!skb->priority)
-		skb->priority = cfg80211_classify8021d(skb);
+		skb->priority = cfg80211_classify8021d(skb, NULL);
 
 	drvr->tx_multicast += !!multicast;
 	if (pae)
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 6bf58aba51d2..2d6f5e1721cf 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -749,7 +749,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
 static u16
 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb)
 {
-	skb->priority = cfg80211_classify8021d(skb);
+	skb->priority = cfg80211_classify8021d(skb, NULL);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
 }
 
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 6d238a4331bd..56c597793d6d 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1971,6 +1971,50 @@ struct cfg80211_mgmt_tx_params {
 	bool dont_wait_for_ack;
 };
 
+/**
+ * struct cfg80211_dscp_exception - DSCP exception
+ *
+ * @dscp: DSCP value that does not adhere to the user priority range definition
+ * @up: user priority value to which the corresponding DSCP value belongs
+ */
+struct cfg80211_dscp_exception {
+	u8 dscp;
+	u8 up;
+};
+
+/**
+ * struct cfg80211_dscp_range - DSCP range definition for user priority
+ *
+ * @low: lowest DSCP value of this user priority range, inclusive
+ * @high: highest DSCP value of this user priority range, inclusive
+ */
+struct cfg80211_dscp_range {
+	u8 low;
+	u8 high;
+};
+
+/* QoS Map Set element length defined in IEEE Std 802.11-2012, 8.4.2.97 */
+#define IEEE80211_QOS_MAP_MAX_EX	21
+#define IEEE80211_QOS_MAP_LEN_MIN	16
+#define IEEE80211_QOS_MAP_LEN_MAX \
+	(IEEE80211_QOS_MAP_LEN_MIN + 2 * IEEE80211_QOS_MAP_MAX_EX)
+
+/**
+ * struct cfg80211_qos_map - QoS Map Information
+ *
+ * This struct defines the Interworking QoS map setting for DSCP values
+ *
+ * @num_des: number of DSCP exceptions (0..21)
+ * @dscp_exception: optionally up to maximum of 21 DSCP exceptions from
+ *	the user priority DSCP range definition
+ * @up: DSCP range definition for a particular user priority
+ */
+struct cfg80211_qos_map {
+	u8 num_des;
+	struct cfg80211_dscp_exception dscp_exception[IEEE80211_QOS_MAP_MAX_EX];
+	struct cfg80211_dscp_range up[8];
+};
+
 /**
  * struct cfg80211_ops - backend description for wireless configuration
  *
@@ -2213,6 +2257,8 @@ struct cfg80211_mgmt_tx_params {
  * @set_coalesce: Set coalesce parameters.
  *
  * @channel_switch: initiate channel-switch procedure (with CSA)
+ *
+ * @set_qos_map: Set QoS mapping information to the driver
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -2454,6 +2500,9 @@ struct cfg80211_ops {
 	int	(*channel_switch)(struct wiphy *wiphy,
 				  struct net_device *dev,
 				  struct cfg80211_csa_settings *params);
+	int     (*set_qos_map)(struct wiphy *wiphy,
+			       struct net_device *dev,
+			       struct cfg80211_qos_map *qos_map);
 };
 
 /*
@@ -3432,9 +3481,11 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 /**
  * cfg80211_classify8021d - determine the 802.1p/1d tag for a data frame
  * @skb: the data frame
+ * @qos_map: Interworking QoS mapping or %NULL if not in use
  * Return: The 802.1p/1d tag.
  */
-unsigned int cfg80211_classify8021d(struct sk_buff *skb);
+unsigned int cfg80211_classify8021d(struct sk_buff *skb,
+				    struct cfg80211_qos_map *qos_map);
 
 /**
  * cfg80211_find_ie - find information element in data
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 381184eb6c96..91054fd660e0 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -702,6 +702,12 @@
  *	(&struct nl80211_vendor_cmd_info) of the supported vendor commands.
  *	This may also be sent as an event with the same attributes.
  *
+ * @NL80211_CMD_SET_QOS_MAP: Set Interworking QoS mapping for IP DSCP values.
+ *	The QoS mapping information is included in %NL80211_ATTR_QOS_MAP. If
+ *	that attribute is not included, QoS mapping is disabled. Since this
+ *	QoS mapping is relevant for IP packets, it is only valid during an
+ *	association. This is cleared on disassociation and AP restart.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -871,6 +877,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_VENDOR,
 
+	NL80211_CMD_SET_QOS_MAP,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -1543,6 +1551,10 @@ enum nl80211_commands {
  * @NL80211_ATTR_VENDOR_EVENTS: used for event list advertising in the wiphy
  *	info, containing a nested array of possible events
  *
+ * @NL80211_ATTR_QOS_MAP: IP DSCP mapping for Interworking QoS mapping. This
+ *	data is in the format defined for the payload of the QoS Map Set element
+ *	in IEEE Std 802.11-2012, 8.4.2.97.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1869,6 +1881,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_VENDOR_DATA,
 	NL80211_ATTR_VENDOR_EVENTS,
 
+	NL80211_ATTR_QOS_MAP,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index afba19cb6f87..faa9d8e451f0 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -155,7 +155,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 
 	/* use the data classifier to determine what 802.1d tag the
 	 * data frame has */
-	skb->priority = cfg80211_classify8021d(skb);
+	skb->priority = cfg80211_classify8021d(skb, NULL);
 
 	return ieee80211_downgrade_queue(sdata, skb);
 }
diff --git a/net/wireless/ap.c b/net/wireless/ap.c
index 324e8d851dc4..11ee4ed04f73 100644
--- a/net/wireless/ap.c
+++ b/net/wireless/ap.c
@@ -29,6 +29,7 @@ static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
 		wdev->beacon_interval = 0;
 		wdev->channel = NULL;
 		wdev->ssid_len = 0;
+		rdev_set_qos_map(rdev, dev, NULL);
 	}
 
 	return err;
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 730147ed8e65..f911c5f9f903 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -183,6 +183,8 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext)
 	kfree(wdev->connect_keys);
 	wdev->connect_keys = NULL;
 
+	rdev_set_qos_map(rdev, dev, NULL);
+
 	/*
 	 * Delete all the keys ... pairwise keys can't really
 	 * exist any more anyway, but default keys might.
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index 9c7a11ae7936..885862447b63 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -277,6 +277,7 @@ static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
 	if (!err) {
 		wdev->mesh_id_len = 0;
 		wdev->channel = NULL;
+		rdev_set_qos_map(rdev, dev, NULL);
 	}
 
 	return err;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 8a7ff041349b..b4f40fe84a01 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -382,6 +382,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 },
 	[NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
 	[NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
+	[NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY,
+				   .len = IEEE80211_QOS_MAP_LEN_MAX },
 };
 
 /* policy for the key attributes */
@@ -1456,6 +1458,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			if (dev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
 				CMD(channel_switch, CHANNEL_SWITCH);
 		}
+		CMD(set_qos_map, SET_QOS_MAP);
 
 #ifdef CONFIG_NL80211_TESTMODE
 		CMD(testmode_cmd, TESTMODE);
@@ -9121,6 +9124,57 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb)
 EXPORT_SYMBOL_GPL(cfg80211_vendor_cmd_reply);
 
 
+static int nl80211_set_qos_map(struct sk_buff *skb,
+			       struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct cfg80211_qos_map *qos_map = NULL;
+	struct net_device *dev = info->user_ptr[1];
+	u8 *pos, len, num_des, des_len, des;
+	int ret;
+
+	if (!rdev->ops->set_qos_map)
+		return -EOPNOTSUPP;
+
+	if (info->attrs[NL80211_ATTR_QOS_MAP]) {
+		pos = nla_data(info->attrs[NL80211_ATTR_QOS_MAP]);
+		len = nla_len(info->attrs[NL80211_ATTR_QOS_MAP]);
+
+		if (len % 2 || len < IEEE80211_QOS_MAP_LEN_MIN ||
+		    len > IEEE80211_QOS_MAP_LEN_MAX)
+			return -EINVAL;
+
+		qos_map = kzalloc(sizeof(struct cfg80211_qos_map), GFP_KERNEL);
+		if (!qos_map)
+			return -ENOMEM;
+
+		num_des = (len - IEEE80211_QOS_MAP_LEN_MIN) >> 1;
+		if (num_des) {
+			des_len = num_des *
+				sizeof(struct cfg80211_dscp_exception);
+			memcpy(qos_map->dscp_exception, pos, des_len);
+			qos_map->num_des = num_des;
+			for (des = 0; des < num_des; des++) {
+				if (qos_map->dscp_exception[des].up > 7) {
+					kfree(qos_map);
+					return -EINVAL;
+				}
+			}
+			pos += des_len;
+		}
+		memcpy(qos_map->up, pos, IEEE80211_QOS_MAP_LEN_MIN);
+	}
+
+	wdev_lock(dev->ieee80211_ptr);
+	ret = nl80211_key_allowed(dev->ieee80211_ptr);
+	if (!ret)
+		ret = rdev_set_qos_map(rdev, dev, qos_map);
+	wdev_unlock(dev->ieee80211_ptr);
+
+	kfree(qos_map);
+	return ret;
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -9853,6 +9907,14 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_SET_QOS_MAP,
+		.doit = nl80211_set_qos_map,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 /* notification functions */
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index a6c03ab14a0d..c8e225947adb 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -932,4 +932,19 @@ static inline int rdev_channel_switch(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev,
+				   struct net_device *dev,
+				   struct cfg80211_qos_map *qos_map)
+{
+	int ret = -EOPNOTSUPP;
+
+	if (rdev->ops->set_qos_map) {
+		trace_rdev_set_qos_map(&rdev->wiphy, dev, qos_map);
+		ret = rdev->ops->set_qos_map(&rdev->wiphy, dev, qos_map);
+		trace_rdev_return_int(&rdev->wiphy, ret);
+	}
+
+	return ret;
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 65f800890d70..3f64202358f4 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -870,6 +870,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 		for (i = 0; i < 6; i++)
 			rdev_del_key(rdev, dev, i, false, NULL);
 
+	rdev_set_qos_map(rdev, dev, NULL);
+
 #ifdef CONFIG_CFG80211_WEXT
 	memset(&wrqu, 0, sizeof(wrqu));
 	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index f7aa7a72d9bc..fbcc23edee54 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -186,6 +186,28 @@
 
 #define BOOL_TO_STR(bo) (bo) ? "true" : "false"
 
+#define QOS_MAP_ENTRY __field(u8, num_des)			\
+		      __array(u8, dscp_exception,		\
+			      2 * IEEE80211_QOS_MAP_MAX_EX)	\
+		      __array(u8, up, IEEE80211_QOS_MAP_LEN_MIN)
+#define QOS_MAP_ASSIGN(qos_map)					\
+	do {							\
+		if ((qos_map)) {				\
+			__entry->num_des = (qos_map)->num_des;	\
+			memcpy(__entry->dscp_exception,		\
+			       &(qos_map)->dscp_exception,	\
+			       2 * IEEE80211_QOS_MAP_MAX_EX);	\
+			memcpy(__entry->up, &(qos_map)->up,	\
+			       IEEE80211_QOS_MAP_LEN_MIN);	\
+		} else {					\
+			__entry->num_des = 0;			\
+			memset(__entry->dscp_exception, 0,	\
+			       2 * IEEE80211_QOS_MAP_MAX_EX);	\
+			memset(__entry->up, 0,			\
+			       IEEE80211_QOS_MAP_LEN_MIN);	\
+		}						\
+	} while (0)
+
 /*************************************************************
  *			rdev->ops traces		     *
  *************************************************************/
@@ -1875,6 +1897,24 @@ TRACE_EVENT(rdev_channel_switch,
 		  __entry->counter_offset_presp)
 );
 
+TRACE_EVENT(rdev_set_qos_map,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_qos_map *qos_map),
+	TP_ARGS(wiphy, netdev, qos_map),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		QOS_MAP_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		QOS_MAP_ASSIGN(qos_map);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", num_des: %u",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->num_des)
+);
+
 /*************************************************************
  *	     cfg80211 exported functions traces		     *
  *************************************************************/
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 935dea9485da..5618888853b2 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -689,7 +689,8 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 EXPORT_SYMBOL(ieee80211_amsdu_to_8023s);
 
 /* Given a data frame determine the 802.1p/1d tag to use. */
-unsigned int cfg80211_classify8021d(struct sk_buff *skb)
+unsigned int cfg80211_classify8021d(struct sk_buff *skb,
+				    struct cfg80211_qos_map *qos_map)
 {
 	unsigned int dscp;
 	unsigned char vlan_priority;
@@ -720,6 +721,21 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb)
 		return 0;
 	}
 
+	if (qos_map) {
+		unsigned int i, tmp_dscp = dscp >> 2;
+
+		for (i = 0; i < qos_map->num_des; i++) {
+			if (tmp_dscp == qos_map->dscp_exception[i].dscp)
+				return qos_map->dscp_exception[i].up;
+		}
+
+		for (i = 0; i < 8; i++) {
+			if (tmp_dscp >= qos_map->up[i].low &&
+			    tmp_dscp <= qos_map->up[i].high)
+				return i;
+		}
+	}
+
 	return dscp >> 5;
 }
 EXPORT_SYMBOL(cfg80211_classify8021d);
@@ -863,6 +879,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 
 		dev->ieee80211_ptr->use_4addr = false;
 		dev->ieee80211_ptr->mesh_id_up_len = 0;
+		rdev_set_qos_map(rdev, dev, NULL);
 
 		switch (otype) {
 		case NL80211_IFTYPE_AP:
-- 
cgit v1.2.3


From 10239edf86f137ce4c39b62ea9575e8053c549a0 Mon Sep 17 00:00:00 2001
From: Terry Lam <vtlam@google.com>
Date: Sun, 15 Dec 2013 00:30:21 -0800
Subject: net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc

This patch implements the first size-based qdisc that attempts to
differentiate between small flows and heavy-hitters.  The goal is to
catch the heavy-hitters and move them to a separate queue with less
priority so that bulk traffic does not affect the latency of critical
traffic.  Currently "less priority" means less weight (2:1 in
particular) in a Weighted Deficit Round Robin (WDRR) scheduler.

In essence, this patch addresses the "delay-bloat" problem due to
bloated buffers. In some systems, large queues may be necessary for
obtaining CPU efficiency, or due to the presence of unresponsive
traffic like UDP, or just a large number of connections with each
having a small amount of outstanding traffic. In these circumstances,
HHF aims to reduce the HoL blocking for latency sensitive traffic,
while not impacting the queues built up by bulk traffic.  HHF can also
be used in conjunction with other AQM mechanisms such as CoDel.

To capture heavy-hitters, we implement the "multi-stage filter" design
in the following paper:
C. Estan and G. Varghese, "New Directions in Traffic Measurement and
Accounting", in ACM SIGCOMM, 2002.

Some configurable qdisc settings through 'tc':
- hhf_reset_timeout: period to reset counter values in the multi-stage
                     filter (default 40ms)
- hhf_admit_bytes:   threshold to classify heavy-hitters
                     (default 128KB)
- hhf_evict_timeout: threshold to evict idle heavy-hitters
                     (default 1s)
- hhf_non_hh_weight: Weighted Deficit Round Robin (WDRR) weight for
                     non-heavy-hitters (default 2)
- hh_flows_limit:    max number of heavy-hitter flow entries
                     (default 2048)

Note that the ratio between hhf_admit_bytes and hhf_reset_timeout
reflects the bandwidth of heavy-hitters that we attempt to capture
(25Mbps with the above default settings).

The false negative rate (heavy-hitter flows getting away unclassified)
is zero by the design of the multi-stage filter algorithm.
With 100 heavy-hitter flows, using four hashes and 4000 counters yields
a false positive rate (non-heavy-hitters mistakenly classified as
heavy-hitters) of less than 1e-4.

Signed-off-by: Terry Lam <vtlam@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  25 ++
 net/sched/Kconfig              |   9 +
 net/sched/Makefile             |   1 +
 net/sched/sch_hhf.c            | 746 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 781 insertions(+)
 create mode 100644 net/sched/sch_hhf.c

(limited to 'include/uapi')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index a806687ad98f..4566993b8385 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -790,4 +790,29 @@ struct tc_fq_qd_stats {
 	__u32	throttled_flows;
 	__u32	pad;
 };
+
+/* Heavy-Hitter Filter */
+
+enum {
+	TCA_HHF_UNSPEC,
+	TCA_HHF_BACKLOG_LIMIT,
+	TCA_HHF_QUANTUM,
+	TCA_HHF_HH_FLOWS_LIMIT,
+	TCA_HHF_RESET_TIMEOUT,
+	TCA_HHF_ADMIT_BYTES,
+	TCA_HHF_EVICT_TIMEOUT,
+	TCA_HHF_NON_HH_WEIGHT,
+	__TCA_HHF_MAX
+};
+
+#define TCA_HHF_MAX	(__TCA_HHF_MAX - 1)
+
+struct tc_hhf_xstats {
+	__u32	drop_overlimit; /* number of times max qdisc packet limit
+				 * was hit
+				 */
+	__u32	hh_overlimit;   /* number of times max heavy-hitters was hit */
+	__u32	hh_tot_count;   /* number of captured heavy-hitters so far */
+	__u32	hh_cur_count;   /* number of current heavy-hitters */
+};
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index ad1f1d819203..919847beec39 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -286,6 +286,15 @@ config NET_SCH_FQ
 
 	  If unsure, say N.
 
+config NET_SCH_HHF
+	tristate "Heavy-Hitter Filter (HHF)"
+	help
+	  Say Y here if you want to use the Heavy-Hitter Filter (HHF)
+	  packet scheduling algorithm.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_hhf.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 35fa47a494ab..3442e5fbc4d7 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_NET_SCH_QFQ)	+= sch_qfq.o
 obj-$(CONFIG_NET_SCH_CODEL)	+= sch_codel.o
 obj-$(CONFIG_NET_SCH_FQ_CODEL)	+= sch_fq_codel.o
 obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
+obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
new file mode 100644
index 000000000000..97aa33dbb90f
--- /dev/null
+++ b/net/sched/sch_hhf.c
@@ -0,0 +1,746 @@
+/* net/sched/sch_hhf.c		Heavy-Hitter Filter (HHF)
+ *
+ * Copyright (C) 2013 Terry Lam <vtlam@google.com>
+ * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com>
+ */
+
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/vmalloc.h>
+#include <net/flow_keys.h>
+#include <net/pkt_sched.h>
+#include <net/sock.h>
+
+/*	Heavy-Hitter Filter (HHF)
+ *
+ * Principles :
+ * Flows are classified into two buckets: non-heavy-hitter and heavy-hitter
+ * buckets. Initially, a new flow starts as non-heavy-hitter. Once classified
+ * as heavy-hitter, it is immediately switched to the heavy-hitter bucket.
+ * The buckets are dequeued by a Weighted Deficit Round Robin (WDRR) scheduler,
+ * in which the heavy-hitter bucket is served with less weight.
+ * In other words, non-heavy-hitters (e.g., short bursts of critical traffic)
+ * are isolated from heavy-hitters (e.g., persistent bulk traffic) and also have
+ * higher share of bandwidth.
+ *
+ * To capture heavy-hitters, we use the "multi-stage filter" algorithm in the
+ * following paper:
+ * [EV02] C. Estan and G. Varghese, "New Directions in Traffic Measurement and
+ * Accounting", in ACM SIGCOMM, 2002.
+ *
+ * Conceptually, a multi-stage filter comprises k independent hash functions
+ * and k counter arrays. Packets are indexed into k counter arrays by k hash
+ * functions, respectively. The counters are then increased by the packet sizes.
+ * Therefore,
+ *    - For a heavy-hitter flow: *all* of its k array counters must be large.
+ *    - For a non-heavy-hitter flow: some of its k array counters can be large
+ *      due to hash collision with other small flows; however, with high
+ *      probability, not *all* k counters are large.
+ *
+ * By the design of the multi-stage filter algorithm, the false negative rate
+ * (heavy-hitters getting away uncaptured) is zero. However, the algorithm is
+ * susceptible to false positives (non-heavy-hitters mistakenly classified as
+ * heavy-hitters).
+ * Therefore, we also implement the following optimizations to reduce false
+ * positives by avoiding unnecessary increment of the counter values:
+ *    - Optimization O1: once a heavy-hitter is identified, its bytes are not
+ *        accounted in the array counters. This technique is called "shielding"
+ *        in Section 3.3.1 of [EV02].
+ *    - Optimization O2: conservative update of counters
+ *                       (Section 3.3.2 of [EV02]),
+ *        New counter value = max {old counter value,
+ *                                 smallest counter value + packet bytes}
+ *
+ * Finally, we refresh the counters periodically since otherwise the counter
+ * values will keep accumulating.
+ *
+ * Once a flow is classified as heavy-hitter, we also save its per-flow state
+ * in an exact-matching flow table so that its subsequent packets can be
+ * dispatched to the heavy-hitter bucket accordingly.
+ *
+ *
+ * At a high level, this qdisc works as follows:
+ * Given a packet p:
+ *   - If the flow-id of p (e.g., TCP 5-tuple) is already in the exact-matching
+ *     heavy-hitter flow table, denoted table T, then send p to the heavy-hitter
+ *     bucket.
+ *   - Otherwise, forward p to the multi-stage filter, denoted filter F
+ *        + If F decides that p belongs to a non-heavy-hitter flow, then send p
+ *          to the non-heavy-hitter bucket.
+ *        + Otherwise, if F decides that p belongs to a new heavy-hitter flow,
+ *          then set up a new flow entry for the flow-id of p in the table T and
+ *          send p to the heavy-hitter bucket.
+ *
+ * In this implementation:
+ *   - T is a fixed-size hash-table with 1024 entries. Hash collision is
+ *     resolved by linked-list chaining.
+ *   - F has four counter arrays, each array containing 1024 32-bit counters.
+ *     That means 4 * 1024 * 32 bits = 16KB of memory.
+ *   - Since each array in F contains 1024 counters, 10 bits are sufficient to
+ *     index into each array.
+ *     Hence, instead of having four hash functions, we chop the 32-bit
+ *     skb-hash into three 10-bit chunks, and the remaining 10-bit chunk is
+ *     computed as XOR sum of those three chunks.
+ *   - We need to clear the counter arrays periodically; however, directly
+ *     memsetting 16KB of memory can lead to cache eviction and unwanted delay.
+ *     So by representing each counter by a valid bit, we only need to reset
+ *     4K of 1 bit (i.e. 512 bytes) instead of 16KB of memory.
+ *   - The Deficit Round Robin engine is taken from fq_codel implementation
+ *     (net/sched/sch_fq_codel.c). Note that wdrr_bucket corresponds to
+ *     fq_codel_flow in fq_codel implementation.
+ *
+ */
+
+/* Non-configurable parameters */
+#define HH_FLOWS_CNT	 1024  /* number of entries in exact-matching table T */
+#define HHF_ARRAYS_CNT	 4     /* number of arrays in multi-stage filter F */
+#define HHF_ARRAYS_LEN	 1024  /* number of counters in each array of F */
+#define HHF_BIT_MASK_LEN 10    /* masking 10 bits */
+#define HHF_BIT_MASK	 0x3FF /* bitmask of 10 bits */
+
+#define WDRR_BUCKET_CNT  2     /* two buckets for Weighted DRR */
+enum wdrr_bucket_idx {
+	WDRR_BUCKET_FOR_HH	= 0, /* bucket id for heavy-hitters */
+	WDRR_BUCKET_FOR_NON_HH	= 1  /* bucket id for non-heavy-hitters */
+};
+
+#define hhf_time_before(a, b)	\
+	(typecheck(u32, a) && typecheck(u32, b) && ((s32)((a) - (b)) < 0))
+
+/* Heavy-hitter per-flow state */
+struct hh_flow_state {
+	u32		 hash_id;	/* hash of flow-id (e.g. TCP 5-tuple) */
+	u32		 hit_timestamp;	/* last time heavy-hitter was seen */
+	struct list_head flowchain;	/* chaining under hash collision */
+};
+
+/* Weighted Deficit Round Robin (WDRR) scheduler */
+struct wdrr_bucket {
+	struct sk_buff	  *head;
+	struct sk_buff	  *tail;
+	struct list_head  bucketchain;
+	int		  deficit;
+};
+
+struct hhf_sched_data {
+	struct wdrr_bucket buckets[WDRR_BUCKET_CNT];
+	u32		   perturbation;   /* hash perturbation */
+	u32		   quantum;        /* psched_mtu(qdisc_dev(sch)); */
+	u32		   drop_overlimit; /* number of times max qdisc packet
+					    * limit was hit
+					    */
+	struct list_head   *hh_flows;       /* table T (currently active HHs) */
+	u32		   hh_flows_limit;            /* max active HH allocs */
+	u32		   hh_flows_overlimit; /* num of disallowed HH allocs */
+	u32		   hh_flows_total_cnt;          /* total admitted HHs */
+	u32		   hh_flows_current_cnt;        /* total current HHs  */
+	u32		   *hhf_arrays[HHF_ARRAYS_CNT]; /* HH filter F */
+	u32		   hhf_arrays_reset_timestamp;  /* last time hhf_arrays
+							 * was reset
+							 */
+	unsigned long	   *hhf_valid_bits[HHF_ARRAYS_CNT]; /* shadow valid bits
+							     * of hhf_arrays
+							     */
+	/* Similar to the "new_flows" vs. "old_flows" concept in fq_codel DRR */
+	struct list_head   new_buckets; /* list of new buckets */
+	struct list_head   old_buckets; /* list of old buckets */
+
+	/* Configurable HHF parameters */
+	u32		   hhf_reset_timeout; /* interval to reset counter
+					       * arrays in filter F
+					       * (default 40ms)
+					       */
+	u32		   hhf_admit_bytes;   /* counter thresh to classify as
+					       * HH (default 128KB).
+					       * With these default values,
+					       * 128KB / 40ms = 25 Mbps
+					       * i.e., we expect to capture HHs
+					       * sending > 25 Mbps.
+					       */
+	u32		   hhf_evict_timeout; /* aging threshold to evict idle
+					       * HHs out of table T. This should
+					       * be large enough to avoid
+					       * reordering during HH eviction.
+					       * (default 1s)
+					       */
+	u32		   hhf_non_hh_weight; /* WDRR weight for non-HHs
+					       * (default 2,
+					       *  i.e., non-HH : HH = 2 : 1)
+					       */
+};
+
+static u32 hhf_time_stamp(void)
+{
+	return jiffies;
+}
+
+static unsigned int skb_hash(const struct hhf_sched_data *q,
+			     const struct sk_buff *skb)
+{
+	struct flow_keys keys;
+	unsigned int hash;
+
+	if (skb->sk && skb->sk->sk_hash)
+		return skb->sk->sk_hash;
+
+	skb_flow_dissect(skb, &keys);
+	hash = jhash_3words((__force u32)keys.dst,
+			    (__force u32)keys.src ^ keys.ip_proto,
+			    (__force u32)keys.ports, q->perturbation);
+	return hash;
+}
+
+/* Looks up a heavy-hitter flow in a chaining list of table T. */
+static struct hh_flow_state *seek_list(const u32 hash,
+				       struct list_head *head,
+				       struct hhf_sched_data *q)
+{
+	struct hh_flow_state *flow, *next;
+	u32 now = hhf_time_stamp();
+
+	if (list_empty(head))
+		return NULL;
+
+	list_for_each_entry_safe(flow, next, head, flowchain) {
+		u32 prev = flow->hit_timestamp + q->hhf_evict_timeout;
+
+		if (hhf_time_before(prev, now)) {
+			/* Delete expired heavy-hitters, but preserve one entry
+			 * to avoid kzalloc() when next time this slot is hit.
+			 */
+			if (list_is_last(&flow->flowchain, head))
+				return NULL;
+			list_del(&flow->flowchain);
+			kfree(flow);
+			q->hh_flows_current_cnt--;
+		} else if (flow->hash_id == hash) {
+			return flow;
+		}
+	}
+	return NULL;
+}
+
+/* Returns a flow state entry for a new heavy-hitter.  Either reuses an expired
+ * entry or dynamically alloc a new entry.
+ */
+static struct hh_flow_state *alloc_new_hh(struct list_head *head,
+					  struct hhf_sched_data *q)
+{
+	struct hh_flow_state *flow;
+	u32 now = hhf_time_stamp();
+
+	if (!list_empty(head)) {
+		/* Find an expired heavy-hitter flow entry. */
+		list_for_each_entry(flow, head, flowchain) {
+			u32 prev = flow->hit_timestamp + q->hhf_evict_timeout;
+
+			if (hhf_time_before(prev, now))
+				return flow;
+		}
+	}
+
+	if (q->hh_flows_current_cnt >= q->hh_flows_limit) {
+		q->hh_flows_overlimit++;
+		return NULL;
+	}
+	/* Create new entry. */
+	flow = kzalloc(sizeof(struct hh_flow_state), GFP_ATOMIC);
+	if (!flow)
+		return NULL;
+
+	q->hh_flows_current_cnt++;
+	INIT_LIST_HEAD(&flow->flowchain);
+	list_add_tail(&flow->flowchain, head);
+
+	return flow;
+}
+
+/* Assigns packets to WDRR buckets.  Implements a multi-stage filter to
+ * classify heavy-hitters.
+ */
+static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	u32 tmp_hash, hash;
+	u32 xorsum, filter_pos[HHF_ARRAYS_CNT], flow_pos;
+	struct hh_flow_state *flow;
+	u32 pkt_len, min_hhf_val;
+	int i;
+	u32 prev;
+	u32 now = hhf_time_stamp();
+
+	/* Reset the HHF counter arrays if this is the right time. */
+	prev = q->hhf_arrays_reset_timestamp + q->hhf_reset_timeout;
+	if (hhf_time_before(prev, now)) {
+		for (i = 0; i < HHF_ARRAYS_CNT; i++)
+			bitmap_zero(q->hhf_valid_bits[i], HHF_ARRAYS_LEN);
+		q->hhf_arrays_reset_timestamp = now;
+	}
+
+	/* Get hashed flow-id of the skb. */
+	hash = skb_hash(q, skb);
+
+	/* Check if this packet belongs to an already established HH flow. */
+	flow_pos = hash & HHF_BIT_MASK;
+	flow = seek_list(hash, &q->hh_flows[flow_pos], q);
+	if (flow) { /* found its HH flow */
+		flow->hit_timestamp = now;
+		return WDRR_BUCKET_FOR_HH;
+	}
+
+	/* Now pass the packet through the multi-stage filter. */
+	tmp_hash = hash;
+	xorsum = 0;
+	for (i = 0; i < HHF_ARRAYS_CNT - 1; i++) {
+		/* Split the skb_hash into three 10-bit chunks. */
+		filter_pos[i] = tmp_hash & HHF_BIT_MASK;
+		xorsum ^= filter_pos[i];
+		tmp_hash >>= HHF_BIT_MASK_LEN;
+	}
+	/* The last chunk is computed as XOR sum of other chunks. */
+	filter_pos[HHF_ARRAYS_CNT - 1] = xorsum ^ tmp_hash;
+
+	pkt_len = qdisc_pkt_len(skb);
+	min_hhf_val = ~0U;
+	for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+		u32 val;
+
+		if (!test_bit(filter_pos[i], q->hhf_valid_bits[i])) {
+			q->hhf_arrays[i][filter_pos[i]] = 0;
+			__set_bit(filter_pos[i], q->hhf_valid_bits[i]);
+		}
+
+		val = q->hhf_arrays[i][filter_pos[i]] + pkt_len;
+		if (min_hhf_val > val)
+			min_hhf_val = val;
+	}
+
+	/* Found a new HH iff all counter values > HH admit threshold. */
+	if (min_hhf_val > q->hhf_admit_bytes) {
+		/* Just captured a new heavy-hitter. */
+		flow = alloc_new_hh(&q->hh_flows[flow_pos], q);
+		if (!flow) /* memory alloc problem */
+			return WDRR_BUCKET_FOR_NON_HH;
+		flow->hash_id = hash;
+		flow->hit_timestamp = now;
+		q->hh_flows_total_cnt++;
+
+		/* By returning without updating counters in q->hhf_arrays,
+		 * we implicitly implement "shielding" (see Optimization O1).
+		 */
+		return WDRR_BUCKET_FOR_HH;
+	}
+
+	/* Conservative update of HHF arrays (see Optimization O2). */
+	for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+		if (q->hhf_arrays[i][filter_pos[i]] < min_hhf_val)
+			q->hhf_arrays[i][filter_pos[i]] = min_hhf_val;
+	}
+	return WDRR_BUCKET_FOR_NON_HH;
+}
+
+/* Removes one skb from head of bucket. */
+static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket)
+{
+	struct sk_buff *skb = bucket->head;
+
+	bucket->head = skb->next;
+	skb->next = NULL;
+	return skb;
+}
+
+/* Tail-adds skb to bucket. */
+static void bucket_add(struct wdrr_bucket *bucket, struct sk_buff *skb)
+{
+	if (bucket->head == NULL)
+		bucket->head = skb;
+	else
+		bucket->tail->next = skb;
+	bucket->tail = skb;
+	skb->next = NULL;
+}
+
+static unsigned int hhf_drop(struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct wdrr_bucket *bucket;
+
+	/* Always try to drop from heavy-hitters first. */
+	bucket = &q->buckets[WDRR_BUCKET_FOR_HH];
+	if (!bucket->head)
+		bucket = &q->buckets[WDRR_BUCKET_FOR_NON_HH];
+
+	if (bucket->head) {
+		struct sk_buff *skb = dequeue_head(bucket);
+
+		sch->q.qlen--;
+		sch->qstats.drops++;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		kfree_skb(skb);
+	}
+
+	/* Return id of the bucket from which the packet was dropped. */
+	return bucket - q->buckets;
+}
+
+static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	enum wdrr_bucket_idx idx;
+	struct wdrr_bucket *bucket;
+
+	idx = hhf_classify(skb, sch);
+
+	bucket = &q->buckets[idx];
+	bucket_add(bucket, skb);
+	sch->qstats.backlog += qdisc_pkt_len(skb);
+
+	if (list_empty(&bucket->bucketchain)) {
+		unsigned int weight;
+
+		/* The logic of new_buckets vs. old_buckets is the same as
+		 * new_flows vs. old_flows in the implementation of fq_codel,
+		 * i.e., short bursts of non-HHs should have strict priority.
+		 */
+		if (idx == WDRR_BUCKET_FOR_HH) {
+			/* Always move heavy-hitters to old bucket. */
+			weight = 1;
+			list_add_tail(&bucket->bucketchain, &q->old_buckets);
+		} else {
+			weight = q->hhf_non_hh_weight;
+			list_add_tail(&bucket->bucketchain, &q->new_buckets);
+		}
+		bucket->deficit = weight * q->quantum;
+	}
+	if (++sch->q.qlen < sch->limit)
+		return NET_XMIT_SUCCESS;
+
+	q->drop_overlimit++;
+	/* Return Congestion Notification only if we dropped a packet from this
+	 * bucket.
+	 */
+	if (hhf_drop(sch) == idx)
+		return NET_XMIT_CN;
+
+	/* As we dropped a packet, better let upper stack know this. */
+	qdisc_tree_decrease_qlen(sch, 1);
+	return NET_XMIT_SUCCESS;
+}
+
+static struct sk_buff *hhf_dequeue(struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb = NULL;
+	struct wdrr_bucket *bucket;
+	struct list_head *head;
+
+begin:
+	head = &q->new_buckets;
+	if (list_empty(head)) {
+		head = &q->old_buckets;
+		if (list_empty(head))
+			return NULL;
+	}
+	bucket = list_first_entry(head, struct wdrr_bucket, bucketchain);
+
+	if (bucket->deficit <= 0) {
+		int weight = (bucket - q->buckets == WDRR_BUCKET_FOR_HH) ?
+			      1 : q->hhf_non_hh_weight;
+
+		bucket->deficit += weight * q->quantum;
+		list_move_tail(&bucket->bucketchain, &q->old_buckets);
+		goto begin;
+	}
+
+	if (bucket->head) {
+		skb = dequeue_head(bucket);
+		sch->q.qlen--;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+	}
+
+	if (!skb) {
+		/* Force a pass through old_buckets to prevent starvation. */
+		if ((head == &q->new_buckets) && !list_empty(&q->old_buckets))
+			list_move_tail(&bucket->bucketchain, &q->old_buckets);
+		else
+			list_del_init(&bucket->bucketchain);
+		goto begin;
+	}
+	qdisc_bstats_update(sch, skb);
+	bucket->deficit -= qdisc_pkt_len(skb);
+
+	return skb;
+}
+
+static void hhf_reset(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+
+	while ((skb = hhf_dequeue(sch)) != NULL)
+		kfree_skb(skb);
+}
+
+static void *hhf_zalloc(size_t sz)
+{
+	void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN);
+
+	if (!ptr)
+		ptr = vzalloc(sz);
+
+	return ptr;
+}
+
+static void hhf_free(void *addr)
+{
+	if (addr) {
+		if (is_vmalloc_addr(addr))
+			vfree(addr);
+		else
+			kfree(addr);
+	}
+}
+
+static void hhf_destroy(struct Qdisc *sch)
+{
+	int i;
+	struct hhf_sched_data *q = qdisc_priv(sch);
+
+	for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+		hhf_free(q->hhf_arrays[i]);
+		hhf_free(q->hhf_valid_bits[i]);
+	}
+
+	for (i = 0; i < HH_FLOWS_CNT; i++) {
+		struct hh_flow_state *flow, *next;
+		struct list_head *head = &q->hh_flows[i];
+
+		if (list_empty(head))
+			continue;
+		list_for_each_entry_safe(flow, next, head, flowchain) {
+			list_del(&flow->flowchain);
+			kfree(flow);
+		}
+	}
+	hhf_free(q->hh_flows);
+}
+
+static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = {
+	[TCA_HHF_BACKLOG_LIMIT]	 = { .type = NLA_U32 },
+	[TCA_HHF_QUANTUM]	 = { .type = NLA_U32 },
+	[TCA_HHF_HH_FLOWS_LIMIT] = { .type = NLA_U32 },
+	[TCA_HHF_RESET_TIMEOUT]	 = { .type = NLA_U32 },
+	[TCA_HHF_ADMIT_BYTES]	 = { .type = NLA_U32 },
+	[TCA_HHF_EVICT_TIMEOUT]	 = { .type = NLA_U32 },
+	[TCA_HHF_NON_HH_WEIGHT]	 = { .type = NLA_U32 },
+};
+
+static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_HHF_MAX + 1];
+	unsigned int qlen;
+	int err;
+	u64 non_hh_quantum;
+	u32 new_quantum = q->quantum;
+	u32 new_hhf_non_hh_weight = q->hhf_non_hh_weight;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_HHF_MAX, opt, hhf_policy);
+	if (err < 0)
+		return err;
+
+	sch_tree_lock(sch);
+
+	if (tb[TCA_HHF_BACKLOG_LIMIT])
+		sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]);
+
+	if (tb[TCA_HHF_QUANTUM])
+		new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]);
+
+	if (tb[TCA_HHF_NON_HH_WEIGHT])
+		new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]);
+
+	non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight;
+	if (non_hh_quantum > INT_MAX)
+		return -EINVAL;
+	q->quantum = new_quantum;
+	q->hhf_non_hh_weight = new_hhf_non_hh_weight;
+
+	if (tb[TCA_HHF_HH_FLOWS_LIMIT])
+		q->hh_flows_limit = nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]);
+
+	if (tb[TCA_HHF_RESET_TIMEOUT]) {
+		u32 ms = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]);
+
+		q->hhf_reset_timeout = msecs_to_jiffies(ms);
+	}
+
+	if (tb[TCA_HHF_ADMIT_BYTES])
+		q->hhf_admit_bytes = nla_get_u32(tb[TCA_HHF_ADMIT_BYTES]);
+
+	if (tb[TCA_HHF_EVICT_TIMEOUT]) {
+		u32 ms = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]);
+
+		q->hhf_evict_timeout = msecs_to_jiffies(ms);
+	}
+
+	qlen = sch->q.qlen;
+	while (sch->q.qlen > sch->limit) {
+		struct sk_buff *skb = hhf_dequeue(sch);
+
+		kfree_skb(skb);
+	}
+	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+static int hhf_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	int i;
+
+	sch->limit = 1000;
+	q->quantum = psched_mtu(qdisc_dev(sch));
+	q->perturbation = net_random();
+	INIT_LIST_HEAD(&q->new_buckets);
+	INIT_LIST_HEAD(&q->old_buckets);
+
+	/* Configurable HHF parameters */
+	q->hhf_reset_timeout = HZ / 25; /* 40  ms */
+	q->hhf_admit_bytes = 131072;    /* 128 KB */
+	q->hhf_evict_timeout = HZ;      /* 1  sec */
+	q->hhf_non_hh_weight = 2;
+
+	if (opt) {
+		int err = hhf_change(sch, opt);
+
+		if (err)
+			return err;
+	}
+
+	if (!q->hh_flows) {
+		/* Initialize heavy-hitter flow table. */
+		q->hh_flows = hhf_zalloc(HH_FLOWS_CNT *
+					 sizeof(struct list_head));
+		if (!q->hh_flows)
+			return -ENOMEM;
+		for (i = 0; i < HH_FLOWS_CNT; i++)
+			INIT_LIST_HEAD(&q->hh_flows[i]);
+
+		/* Cap max active HHs at twice len of hh_flows table. */
+		q->hh_flows_limit = 2 * HH_FLOWS_CNT;
+		q->hh_flows_overlimit = 0;
+		q->hh_flows_total_cnt = 0;
+		q->hh_flows_current_cnt = 0;
+
+		/* Initialize heavy-hitter filter arrays. */
+		for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+			q->hhf_arrays[i] = hhf_zalloc(HHF_ARRAYS_LEN *
+						      sizeof(u32));
+			if (!q->hhf_arrays[i]) {
+				hhf_destroy(sch);
+				return -ENOMEM;
+			}
+		}
+		q->hhf_arrays_reset_timestamp = hhf_time_stamp();
+
+		/* Initialize valid bits of heavy-hitter filter arrays. */
+		for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+			q->hhf_valid_bits[i] = hhf_zalloc(HHF_ARRAYS_LEN /
+							  BITS_PER_BYTE);
+			if (!q->hhf_valid_bits[i]) {
+				hhf_destroy(sch);
+				return -ENOMEM;
+			}
+		}
+
+		/* Initialize Weighted DRR buckets. */
+		for (i = 0; i < WDRR_BUCKET_CNT; i++) {
+			struct wdrr_bucket *bucket = q->buckets + i;
+
+			INIT_LIST_HEAD(&bucket->bucketchain);
+		}
+	}
+
+	return 0;
+}
+
+static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_HHF_BACKLOG_LIMIT, sch->limit) ||
+	    nla_put_u32(skb, TCA_HHF_QUANTUM, q->quantum) ||
+	    nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, q->hh_flows_limit) ||
+	    nla_put_u32(skb, TCA_HHF_RESET_TIMEOUT,
+			jiffies_to_msecs(q->hhf_reset_timeout)) ||
+	    nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, q->hhf_admit_bytes) ||
+	    nla_put_u32(skb, TCA_HHF_EVICT_TIMEOUT,
+			jiffies_to_msecs(q->hhf_evict_timeout)) ||
+	    nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, opts);
+	return skb->len;
+
+nla_put_failure:
+	return -1;
+}
+
+static int hhf_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct tc_hhf_xstats st = {
+		.drop_overlimit = q->drop_overlimit,
+		.hh_overlimit	= q->hh_flows_overlimit,
+		.hh_tot_count	= q->hh_flows_total_cnt,
+		.hh_cur_count	= q->hh_flows_current_cnt,
+	};
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+struct Qdisc_ops hhf_qdisc_ops __read_mostly = {
+	.id		=	"hhf",
+	.priv_size	=	sizeof(struct hhf_sched_data),
+
+	.enqueue	=	hhf_enqueue,
+	.dequeue	=	hhf_dequeue,
+	.peek		=	qdisc_peek_dequeued,
+	.drop		=	hhf_drop,
+	.init		=	hhf_init,
+	.reset		=	hhf_reset,
+	.destroy	=	hhf_destroy,
+	.change		=	hhf_change,
+	.dump		=	hhf_dump,
+	.dump_stats	=	hhf_dump_stats,
+	.owner		=	THIS_MODULE,
+};
+EXPORT_SYMBOL(hhf_qdisc_ops);
+
+static int __init hhf_module_init(void)
+{
+	return register_qdisc(&hhf_qdisc_ops);
+}
+
+static void __exit hhf_module_exit(void)
+{
+	unregister_qdisc(&hhf_qdisc_ops);
+}
+
+module_init(hhf_module_init)
+module_exit(hhf_module_exit)
+MODULE_AUTHOR("Terry Lam");
+MODULE_AUTHOR("Nandita Dukkipati");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 2c9839c143bbc8c6612f56351dae8d57111aee37 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Tue, 17 Dec 2013 21:30:09 -0800
Subject: bonding: add num_grat_arp attribute netlink support

Add IFLA_BOND_NUM_PEER_NOTIF to allow get/set of bonding parameter
num_grat_arp via netlink.  Bonding parameter num_unsol_na is
synonymous with num_grat_arp, so add only one netlink attribute
to represent both bonding parameters.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c |  6 ++++++
 drivers/net/bonding/bond_sysfs.c   | 21 +++++++++++++++++++--
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 41 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index e161c9cbd91e..07123a0fcf5d 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -37,6 +37,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_FAIL_OVER_MAC]	= { .type = NLA_U8 },
 	[IFLA_BOND_XMIT_HASH_POLICY]	= { .type = NLA_U8 },
 	[IFLA_BOND_RESEND_IGMP]		= { .type = NLA_U32 },
+	[IFLA_BOND_NUM_PEER_NOTIF]	= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -204,6 +205,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_NUM_PEER_NOTIF]) {
+		int num_peer_notif =
+			nla_get_u8(data[IFLA_BOND_NUM_PEER_NOTIF]);
+
+		err = bond_option_num_peer_notif_set(bond, num_peer_notif);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -237,6 +246,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_FAIL_OVER_MAC */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_XMIT_HASH_POLICY */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_RESEND_IGMP */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_NUM_PEER_NOTIF */
 		0;
 }
 
@@ -317,6 +327,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		        bond->params.resend_igmp))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF,
+		       bond->params.num_peer_notif))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 1ed7dff9a679..01a966916dcb 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -576,3 +576,9 @@ int bond_option_resend_igmp_set(struct bonding *bond, int resend_igmp)
 
 	return 0;
 }
+
+int bond_option_num_peer_notif_set(struct bonding *bond, int num_peer_notif)
+{
+	bond->params.num_peer_notif = num_peer_notif;
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index f5c1a54095b9..7efa33a8553f 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -790,8 +790,25 @@ static ssize_t bonding_store_num_peer_notif(struct device *d,
 					    const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int err = kstrtou8(buf, 10, &bond->params.num_peer_notif);
-	return err ? err : count;
+	u8 new_value;
+	int ret;
+
+	ret = kstrtou8(buf, 10, &new_value);
+	if (!ret) {
+		pr_err("%s: invalid value %s specified.\n",
+		       bond->dev->name, buf);
+		return ret;
+	}
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_num_peer_notif_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
+	return ret;
 }
 static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR,
 		   bonding_show_num_peer_notif, bonding_store_num_peer_notif);
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index c70ad9f02b1e..73538b7a45e1 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -461,6 +461,7 @@ int bond_option_fail_over_mac_set(struct bonding *bond, int fail_over_mac);
 int bond_option_xmit_hash_policy_set(struct bonding *bond,
 				     int xmit_hash_policy);
 int bond_option_resend_igmp_set(struct bonding *bond, int resend_igmp);
+int bond_option_num_peer_notif_set(struct bonding *bond, int num_peer_notif);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6e275d5214f3..bfe3d3b561ee 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -344,6 +344,7 @@ enum {
 	IFLA_BOND_FAIL_OVER_MAC,
 	IFLA_BOND_XMIT_HASH_POLICY,
 	IFLA_BOND_RESEND_IGMP,
+	IFLA_BOND_NUM_PEER_NOTIF,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 1cc0b1e30c662d84a89690f42826cf49e2278b97 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Tue, 17 Dec 2013 21:30:16 -0800
Subject: bonding: add all_slaves_active attribute netlink support

Add IFLA_BOND_ALL_SLAVES_ACTIVE to allow get/set of bonding parameter
all_slaves_active via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 15 +++++++++++++++
 drivers/net/bonding/bond_options.c | 29 +++++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 34 +++++++---------------------------
 drivers/net/bonding/bonding.h      |  2 ++
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 54 insertions(+), 27 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 07123a0fcf5d..517521569adf 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -38,6 +38,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_XMIT_HASH_POLICY]	= { .type = NLA_U8 },
 	[IFLA_BOND_RESEND_IGMP]		= { .type = NLA_U32 },
 	[IFLA_BOND_NUM_PEER_NOTIF]	= { .type = NLA_U8 },
+	[IFLA_BOND_ALL_SLAVES_ACTIVE]	= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -213,6 +214,15 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_ALL_SLAVES_ACTIVE]) {
+		int all_slaves_active =
+			nla_get_u8(data[IFLA_BOND_ALL_SLAVES_ACTIVE]);
+
+		err = bond_option_all_slaves_active_set(bond,
+							all_slaves_active);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -247,6 +257,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_XMIT_HASH_POLICY */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_RESEND_IGMP */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_NUM_PEER_NOTIF */
+		nla_total_size(sizeof(u8)) +   /* IFLA_BOND_ALL_SLAVES_ACTIVE */
 		0;
 }
 
@@ -331,6 +342,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.num_peer_notif))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_ALL_SLAVES_ACTIVE,
+		       bond->params.all_slaves_active))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 01a966916dcb..cbd832293da4 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -582,3 +582,32 @@ int bond_option_num_peer_notif_set(struct bonding *bond, int num_peer_notif)
 	bond->params.num_peer_notif = num_peer_notif;
 	return 0;
 }
+
+int bond_option_all_slaves_active_set(struct bonding *bond,
+				      int all_slaves_active)
+{
+	struct list_head *iter;
+	struct slave *slave;
+
+	if (all_slaves_active == bond->params.all_slaves_active)
+		return 0;
+
+	if ((all_slaves_active == 0) || (all_slaves_active == 1)) {
+		bond->params.all_slaves_active = all_slaves_active;
+	} else {
+		pr_info("%s: Ignoring invalid all_slaves_active value %d.\n",
+			bond->dev->name, all_slaves_active);
+		return -EINVAL;
+	}
+
+	bond_for_each_slave(bond, slave, iter) {
+		if (!bond_is_active_slave(slave)) {
+			if (all_slaves_active)
+				slave->inactive = 0;
+			else
+				slave->inactive = 1;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 7efa33a8553f..9a3712513932 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1290,41 +1290,21 @@ static ssize_t bonding_store_slaves_active(struct device *d,
 					   const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int new_value, ret = count;
-	struct list_head *iter;
-	struct slave *slave;
-
-	if (!rtnl_trylock())
-		return restart_syscall();
+	int new_value, ret;
 
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no all_slaves_active value specified.\n",
 		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	if (new_value == bond->params.all_slaves_active)
-		goto out;
+	if (!rtnl_trylock())
+		return restart_syscall();
 
-	if ((new_value == 0) || (new_value == 1)) {
-		bond->params.all_slaves_active = new_value;
-	} else {
-		pr_info("%s: Ignoring invalid all_slaves_active value %d.\n",
-			bond->dev->name, new_value);
-		ret = -EINVAL;
-		goto out;
-	}
+	ret = bond_option_all_slaves_active_set(bond, new_value);
+	if (!ret)
+		ret = count;
 
-	bond_for_each_slave(bond, slave, iter) {
-		if (!bond_is_active_slave(slave)) {
-			if (new_value)
-				slave->inactive = 0;
-			else
-				slave->inactive = 1;
-		}
-	}
-out:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 73538b7a45e1..3701e7d1fb16 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -462,6 +462,8 @@ int bond_option_xmit_hash_policy_set(struct bonding *bond,
 				     int xmit_hash_policy);
 int bond_option_resend_igmp_set(struct bonding *bond, int resend_igmp);
 int bond_option_num_peer_notif_set(struct bonding *bond, int num_peer_notif);
+int bond_option_all_slaves_active_set(struct bonding *bond,
+				      int all_slaves_active);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index bfe3d3b561ee..93e9c1b99f7a 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -345,6 +345,7 @@ enum {
 	IFLA_BOND_XMIT_HASH_POLICY,
 	IFLA_BOND_RESEND_IGMP,
 	IFLA_BOND_NUM_PEER_NOTIF,
+	IFLA_BOND_ALL_SLAVES_ACTIVE,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 7d1010082785b2020b1e2e1211b76209976a33df Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Tue, 17 Dec 2013 21:30:23 -0800
Subject: bonding: add min_links attribute netlink support

Add IFLA_BOND_MIN_LINKS to allow get/set of bonding parameter
min_links via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c |  9 +++++++++
 drivers/net/bonding/bond_sysfs.c   | 13 +++++++++----
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 34 insertions(+), 4 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 517521569adf..ac9a10c90a50 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -39,6 +39,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_RESEND_IGMP]		= { .type = NLA_U32 },
 	[IFLA_BOND_NUM_PEER_NOTIF]	= { .type = NLA_U8 },
 	[IFLA_BOND_ALL_SLAVES_ACTIVE]	= { .type = NLA_U8 },
+	[IFLA_BOND_MIN_LINKS]		= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -223,6 +224,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_MIN_LINKS]) {
+		int min_links =
+			nla_get_u32(data[IFLA_BOND_MIN_LINKS]);
+
+		err = bond_option_min_links_set(bond, min_links);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -258,6 +267,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_RESEND_IGMP */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_NUM_PEER_NOTIF */
 		nla_total_size(sizeof(u8)) +   /* IFLA_BOND_ALL_SLAVES_ACTIVE */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIN_LINKS */
 		0;
 }
 
@@ -346,6 +356,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.all_slaves_active))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, IFLA_BOND_MIN_LINKS,
+			bond->params.min_links))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index cbd832293da4..da49ac4a8d8e 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -611,3 +611,12 @@ int bond_option_all_slaves_active_set(struct bonding *bond,
 
 	return 0;
 }
+
+int bond_option_min_links_set(struct bonding *bond, int min_links)
+{
+	pr_info("%s: Setting min links value to %u\n",
+		bond->dev->name, min_links);
+	bond->params.min_links = min_links;
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 9a3712513932..359adda17dba 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -722,10 +722,15 @@ static ssize_t bonding_store_min_links(struct device *d,
 		return ret;
 	}
 
-	pr_info("%s: Setting min links value to %u\n",
-		bond->dev->name, new_value);
-	bond->params.min_links = new_value;
-	return count;
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_min_links_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
+	return ret;
 }
 static DEVICE_ATTR(min_links, S_IRUGO | S_IWUSR,
 		   bonding_show_min_links, bonding_store_min_links);
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 3701e7d1fb16..7d7ad1ccbd99 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -464,6 +464,7 @@ int bond_option_resend_igmp_set(struct bonding *bond, int resend_igmp);
 int bond_option_num_peer_notif_set(struct bonding *bond, int num_peer_notif);
 int bond_option_all_slaves_active_set(struct bonding *bond,
 				      int all_slaves_active);
+int bond_option_min_links_set(struct bonding *bond, int min_links);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 93e9c1b99f7a..c7a0f89d59b2 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -346,6 +346,7 @@ enum {
 	IFLA_BOND_RESEND_IGMP,
 	IFLA_BOND_NUM_PEER_NOTIF,
 	IFLA_BOND_ALL_SLAVES_ACTIVE,
+	IFLA_BOND_MIN_LINKS,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 8d836d092ed7b77d13ac1108399165ee7de7463f Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Tue, 17 Dec 2013 21:30:30 -0800
Subject: bonding: add lp_interval attribute netlink support

Add IFLA_BOND_LP_INTERVAL to allow get/set of bonding parameter
lp_interval via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++++
 drivers/net/bonding/bond_options.c | 13 +++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 20 +++++++++-----------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 38 insertions(+), 11 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index ac9a10c90a50..6c8339bec1bf 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -40,6 +40,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_NUM_PEER_NOTIF]	= { .type = NLA_U8 },
 	[IFLA_BOND_ALL_SLAVES_ACTIVE]	= { .type = NLA_U8 },
 	[IFLA_BOND_MIN_LINKS]		= { .type = NLA_U32 },
+	[IFLA_BOND_LP_INTERVAL]		= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -232,6 +233,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_LP_INTERVAL]) {
+		int lp_interval =
+			nla_get_u32(data[IFLA_BOND_LP_INTERVAL]);
+
+		err = bond_option_lp_interval_set(bond, lp_interval);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -268,6 +277,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_NUM_PEER_NOTIF */
 		nla_total_size(sizeof(u8)) +   /* IFLA_BOND_ALL_SLAVES_ACTIVE */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIN_LINKS */
+		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_LP_INTERVAL */
 		0;
 }
 
@@ -360,6 +370,10 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->params.min_links))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, IFLA_BOND_LP_INTERVAL,
+			bond->params.lp_interval))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index da49ac4a8d8e..e313a8f8fae0 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -620,3 +620,16 @@ int bond_option_min_links_set(struct bonding *bond, int min_links)
 
 	return 0;
 }
+
+int bond_option_lp_interval_set(struct bonding *bond, int lp_interval)
+{
+	if (lp_interval <= 0) {
+		pr_err("%s: lp_interval must be between 1 and %d\n",
+		       bond->dev->name, INT_MAX);
+		return -EINVAL;
+	}
+
+	bond->params.lp_interval = lp_interval;
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 359adda17dba..c4cdbf6469ae 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1369,24 +1369,22 @@ static ssize_t bonding_store_lp_interval(struct device *d,
 					 const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int new_value, ret = count;
+	int new_value, ret;
 
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no lp interval value specified.\n",
 			bond->dev->name);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	if (new_value <= 0) {
-		pr_err ("%s: lp_interval must be between 1 and %d\n",
-			bond->dev->name, INT_MAX);
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!rtnl_trylock())
+		return restart_syscall();
 
-	bond->params.lp_interval = new_value;
-out:
+	ret = bond_option_lp_interval_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
 	return ret;
 }
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 7d7ad1ccbd99..0a1a69e001a4 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -465,6 +465,7 @@ int bond_option_num_peer_notif_set(struct bonding *bond, int num_peer_notif);
 int bond_option_all_slaves_active_set(struct bonding *bond,
 				      int all_slaves_active);
 int bond_option_min_links_set(struct bonding *bond, int min_links);
+int bond_option_lp_interval_set(struct bonding *bond, int min_links);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index c7a0f89d59b2..4825ae74f1aa 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -347,6 +347,7 @@ enum {
 	IFLA_BOND_NUM_PEER_NOTIF,
 	IFLA_BOND_ALL_SLAVES_ACTIVE,
 	IFLA_BOND_MIN_LINKS,
+	IFLA_BOND_LP_INTERVAL,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From c13ab3ff176eab78b6ee93817484584af5807cf2 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Tue, 17 Dec 2013 21:30:37 -0800
Subject: bonding: add packets_per_slave attribute netlink support

Add IFLA_BOND_PACKETS_PER_SLAVE to allow get/set of bonding parameter
packets_per_slave via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 21 +++++++++++++++++++++
 drivers/net/bonding/bond_options.c | 23 +++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 28 +++++++++++-----------------
 drivers/net/bonding/bonding.h      |  2 ++
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 58 insertions(+), 17 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 6c8339bec1bf..84acd144d075 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -19,6 +19,7 @@
 #include <linux/if_ether.h>
 #include <net/netlink.h>
 #include <net/rtnetlink.h>
+#include <linux/reciprocal_div.h>
 #include "bonding.h"
 
 static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
@@ -41,6 +42,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_ALL_SLAVES_ACTIVE]	= { .type = NLA_U8 },
 	[IFLA_BOND_MIN_LINKS]		= { .type = NLA_U32 },
 	[IFLA_BOND_LP_INTERVAL]		= { .type = NLA_U32 },
+	[IFLA_BOND_PACKETS_PER_SLAVE]	= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -241,6 +243,15 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_PACKETS_PER_SLAVE]) {
+		int packets_per_slave =
+			nla_get_u32(data[IFLA_BOND_PACKETS_PER_SLAVE]);
+
+		err = bond_option_packets_per_slave_set(bond,
+							packets_per_slave);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -278,6 +289,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u8)) +   /* IFLA_BOND_ALL_SLAVES_ACTIVE */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIN_LINKS */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_LP_INTERVAL */
+		nla_total_size(sizeof(u32)) +  /* IFLA_BOND_PACKETS_PER_SLAVE */
 		0;
 }
 
@@ -287,6 +299,7 @@ static int bond_fill_info(struct sk_buff *skb,
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct net_device *slave_dev = bond_option_active_slave_get(bond);
 	struct nlattr *targets;
+	unsigned int packets_per_slave;
 	int i, targets_added;
 
 	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
@@ -374,6 +387,14 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->params.lp_interval))
 		goto nla_put_failure;
 
+	packets_per_slave = bond->params.packets_per_slave;
+	if (packets_per_slave > 1)
+		packets_per_slave = reciprocal_value(packets_per_slave);
+
+	if (nla_put_u32(skb, IFLA_BOND_PACKETS_PER_SLAVE,
+			packets_per_slave))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index e313a8f8fae0..f8a2cd8c7b57 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -16,6 +16,7 @@
 #include <linux/netdevice.h>
 #include <linux/rwlock.h>
 #include <linux/rcupdate.h>
+#include <linux/reciprocal_div.h>
 #include "bonding.h"
 
 static bool bond_mode_is_valid(int mode)
@@ -633,3 +634,25 @@ int bond_option_lp_interval_set(struct bonding *bond, int lp_interval)
 
 	return 0;
 }
+
+int bond_option_packets_per_slave_set(struct bonding *bond,
+				      int packets_per_slave)
+{
+	if (packets_per_slave < 0 || packets_per_slave > USHRT_MAX) {
+		pr_err("%s: packets_per_slave must be between 0 and %u\n",
+		       bond->dev->name, USHRT_MAX);
+		return -EINVAL;
+	}
+
+	if (bond->params.mode != BOND_MODE_ROUNDROBIN)
+		pr_warn("%s: Warning: packets_per_slave has effect only in balance-rr mode\n",
+			bond->dev->name);
+
+	if (packets_per_slave > 1)
+		bond->params.packets_per_slave =
+			reciprocal_value(packets_per_slave);
+	else
+		bond->params.packets_per_slave = packets_per_slave;
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index c4cdbf6469ae..a0a3476fadba 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1409,28 +1409,22 @@ static ssize_t bonding_store_packets_per_slave(struct device *d,
 					       const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int new_value, ret = count;
+	int new_value, ret;
 
 	if (sscanf(buf, "%d", &new_value) != 1) {
 		pr_err("%s: no packets_per_slave value specified.\n",
 		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-	if (new_value < 0 || new_value > USHRT_MAX) {
-		pr_err("%s: packets_per_slave must be between 0 and %u\n",
-		       bond->dev->name, USHRT_MAX);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
-	if (bond->params.mode != BOND_MODE_ROUNDROBIN)
-		pr_warn("%s: Warning: packets_per_slave has effect only in balance-rr mode\n",
-			bond->dev->name);
-	if (new_value > 1)
-		bond->params.packets_per_slave = reciprocal_value(new_value);
-	else
-		bond->params.packets_per_slave = new_value;
-out:
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_packets_per_slave_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
 	return ret;
 }
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 0a1a69e001a4..5886f07dc1f3 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -466,6 +466,8 @@ int bond_option_all_slaves_active_set(struct bonding *bond,
 				      int all_slaves_active);
 int bond_option_min_links_set(struct bonding *bond, int min_links);
 int bond_option_lp_interval_set(struct bonding *bond, int min_links);
+int bond_option_packets_per_slave_set(struct bonding *bond,
+				      int packets_per_slave);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 4825ae74f1aa..8fbc7ca878b4 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -348,6 +348,7 @@ enum {
 	IFLA_BOND_ALL_SLAVES_ACTIVE,
 	IFLA_BOND_MIN_LINKS,
 	IFLA_BOND_LP_INTERVAL,
+	IFLA_BOND_PACKETS_PER_SLAVE,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 08c0cad69f32ad1e881fa3fb7f5e0a25db5b07ce Mon Sep 17 00:00:00 2001
From: Valentina Giusti <valentina.giusti@bmw-carit.de>
Date: Fri, 20 Dec 2013 17:28:53 +0100
Subject: netfilter: nfnetlink_queue: enable UID/GID socket info retrieval

Thanks to commits 41063e9 (ipv4: Early TCP socket demux) and 421b388
(udp: ipv4: Add udp early demux) it is now possible to parse UID and
GID socket info also for incoming TCP and UDP connections. Having
this info available, it is convenient to let NFQUEUE parse it in
order to improve and refine the traffic analysis in userspace.

Signed-off-by: Valentina Giusti <valentina.giusti@bmw-carit.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nfnetlink_queue.h |  5 +++-
 net/netfilter/nfnetlink_queue_core.c           | 34 ++++++++++++++++++++++++++
 2 files changed, 38 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h
index 0132bad79de7..8dd819e2b5fe 100644
--- a/include/uapi/linux/netfilter/nfnetlink_queue.h
+++ b/include/uapi/linux/netfilter/nfnetlink_queue.h
@@ -47,6 +47,8 @@ enum nfqnl_attr_type {
 	NFQA_CAP_LEN,			/* __u32 length of captured packet */
 	NFQA_SKB_INFO,			/* __u32 skb meta information */
 	NFQA_EXP,			/* nf_conntrack_netlink.h */
+	NFQA_UID,			/* __u32 sk uid */
+	NFQA_GID,			/* __u32 sk gid */
 
 	__NFQA_MAX
 };
@@ -99,7 +101,8 @@ enum nfqnl_attr_config {
 #define NFQA_CFG_F_FAIL_OPEN			(1 << 0)
 #define NFQA_CFG_F_CONNTRACK			(1 << 1)
 #define NFQA_CFG_F_GSO				(1 << 2)
-#define NFQA_CFG_F_MAX				(1 << 3)
+#define NFQA_CFG_F_UID_GID			(1 << 3)
+#define NFQA_CFG_F_MAX				(1 << 4)
 
 /* flags for NFQA_SKB_INFO */
 /* packet appears to have wrong checksums, but they are ok */
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 21258cf70091..d3cf12b83174 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -297,6 +297,31 @@ nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet,
 	return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0;
 }
 
+static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk)
+{
+	const struct cred *cred;
+
+	if (sk->sk_state == TCP_TIME_WAIT)
+		return 0;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	if (sk->sk_socket && sk->sk_socket->file) {
+		cred = sk->sk_socket->file->f_cred;
+		if (nla_put_be32(skb, NFQA_UID,
+		    htonl(from_kuid_munged(&init_user_ns, cred->fsuid))))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFQA_GID,
+		    htonl(from_kgid_munged(&init_user_ns, cred->fsgid))))
+			goto nla_put_failure;
+	}
+	read_unlock_bh(&sk->sk_callback_lock);
+	return 0;
+
+nla_put_failure:
+	read_unlock_bh(&sk->sk_callback_lock);
+	return -1;
+}
+
 static struct sk_buff *
 nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			   struct nf_queue_entry *entry,
@@ -372,6 +397,11 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	if (queue->flags & NFQA_CFG_F_CONNTRACK)
 		ct = nfqnl_ct_get(entskb, &size, &ctinfo);
 
+	if (queue->flags & NFQA_CFG_F_UID_GID) {
+		size +=  (nla_total_size(sizeof(u_int32_t))	/* uid */
+			+ nla_total_size(sizeof(u_int32_t)));	/* gid */
+	}
+
 	skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
 				  GFP_ATOMIC);
 	if (!skb)
@@ -484,6 +514,10 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			goto nla_put_failure;
 	}
 
+	if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk &&
+	    nfqnl_put_sk_uidgid(skb, entskb->sk) < 0)
+		goto nla_put_failure;
+
 	if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
 		goto nla_put_failure;
 
-- 
cgit v1.2.3


From 09aea5df7fbf0b987623f7007a11e64008284a0e Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Tue, 17 Dec 2013 22:35:52 -0800
Subject: netconf: rename PROXY_ARP to NEIGH_PROXY

Use same field for both IPv4 (proxy_arp) and IPv6 (proxy_ndp)
so fix it before API is set to be a common name

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/netconf.h |  2 +-
 net/ipv4/devinet.c           | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index bd969d77ce52..669a1f0b1d97 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -14,7 +14,7 @@ enum {
 	NETCONFA_FORWARDING,
 	NETCONFA_RP_FILTER,
 	NETCONFA_MC_FORWARDING,
-	NETCONFA_PROXY_ARP,
+	NETCONFA_PROXY_NEIGH,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index de03fe7002d0..0feebd5de295 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1696,7 +1696,7 @@ static int inet_netconf_msgsize_devconf(int type)
 		size += nla_total_size(4);
 	if (type == -1 || type == NETCONFA_MC_FORWARDING)
 		size += nla_total_size(4);
-	if (type == -1 || type == NETCONFA_PROXY_ARP)
+	if (type == -1 || type == NETCONFA_PROXY_NEIGH)
 		size += nla_total_size(4);
 
 	return size;
@@ -1734,8 +1734,8 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
 			IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
 		goto nla_put_failure;
-	if ((type == -1 || type == NETCONFA_PROXY_ARP) &&
-	    nla_put_s32(skb, NETCONFA_PROXY_ARP,
+	if ((type == -1 || type == NETCONFA_PROXY_NEIGH) &&
+	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
 			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
 		goto nla_put_failure;
 
@@ -1775,7 +1775,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
 	[NETCONFA_IFINDEX]	= { .len = sizeof(int) },
 	[NETCONFA_FORWARDING]	= { .len = sizeof(int) },
 	[NETCONFA_RP_FILTER]	= { .len = sizeof(int) },
-	[NETCONFA_PROXY_ARP]	= { .len = sizeof(int) },
+	[NETCONFA_PROXY_NEIGH]	= { .len = sizeof(int) },
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
@@ -2002,7 +2002,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_PROXY_ARP,
+			inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
 						    ifindex, cnf);
 		}
 	}
-- 
cgit v1.2.3


From 6a649f339802f104549e1fb211e381036661e244 Mon Sep 17 00:00:00 2001
From: "fan.du" <fan.du@windriver.com>
Date: Wed, 18 Dec 2013 11:27:02 +0800
Subject: netfilter: add IPv4/6 IPComp extension match support

With this plugin, user could specify IPComp tagged with certain
CPI that host not interested will be DROPped or any other action.

For example:
iptables  -A INPUT -p 108 -m ipcomp --ipcompspi 0x87 -j DROP
ip6tables -A INPUT -p 108 -m ipcomp --ipcompspi 0x87 -j DROP

Then input IPComp packet with CPI equates 0x87 will not reach
upper layer anymore.

Signed-off-by: Fan Du <fan.du@windriver.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/Kbuild      |   1 +
 include/uapi/linux/netfilter/xt_ipcomp.h |  16 +++++
 net/netfilter/Kconfig                    |   9 +++
 net/netfilter/Makefile                   |   1 +
 net/netfilter/xt_ipcomp.c                | 111 +++++++++++++++++++++++++++++++
 5 files changed, 138 insertions(+)
 create mode 100644 include/uapi/linux/netfilter/xt_ipcomp.h
 create mode 100644 net/netfilter/xt_ipcomp.c

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 17c3af2c4bb9..91be8ce623f0 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -54,6 +54,7 @@ header-y += xt_ecn.h
 header-y += xt_esp.h
 header-y += xt_hashlimit.h
 header-y += xt_helper.h
+header-y += xt_ipcomp.h
 header-y += xt_iprange.h
 header-y += xt_ipvs.h
 header-y += xt_length.h
diff --git a/include/uapi/linux/netfilter/xt_ipcomp.h b/include/uapi/linux/netfilter/xt_ipcomp.h
new file mode 100644
index 000000000000..45c7e40eb8e1
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_ipcomp.h
@@ -0,0 +1,16 @@
+#ifndef _XT_IPCOMP_H
+#define _XT_IPCOMP_H
+
+#include <linux/types.h>
+
+struct xt_ipcomp {
+	__u32 spis[2];	/* Security Parameter Index */
+	__u8 invflags;	/* Inverse flags */
+	__u8 hdrres;	/* Test of the Reserved Filed */
+};
+
+/* Values for "invflags" field in struct xt_ipcomp. */
+#define XT_IPCOMP_INV_SPI	0x01	/* Invert the sense of spi. */
+#define XT_IPCOMP_INV_MASK	0x01	/* All possible flags. */
+
+#endif /*_XT_IPCOMP_H*/
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c3398cd99b94..6d8e48b376fc 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -1035,6 +1035,15 @@ config NETFILTER_XT_MATCH_HL
 	in the IPv6 header, or the time-to-live field in the IPv4
 	header of the packet.
 
+config NETFILTER_XT_MATCH_IPCOMP
+	tristate '"ipcomp" match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  This match extension allows you to match a range of CPIs(16 bits)
+	  inside IPComp header of IPSec packets.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config NETFILTER_XT_MATCH_IPRANGE
 	tristate '"iprange" address range match support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 394483b2c193..398cd709aa09 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -133,6 +133,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_IPCOMP) += xt_ipcomp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c
new file mode 100644
index 000000000000..a4c7561698c5
--- /dev/null
+++ b/net/netfilter/xt_ipcomp.c
@@ -0,0 +1,111 @@
+/*  Kernel module to match IPComp parameters for IPv4 and IPv6
+ *
+ *  Copyright (C) 2013 WindRiver
+ *
+ *  Author:
+ *  Fan Du <fan.du@windriver.com>
+ *
+ *  Based on:
+ *  net/netfilter/xt_esp.c
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+
+#include <linux/netfilter/xt_ipcomp.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Fan Du <fan.du@windriver.com>");
+MODULE_DESCRIPTION("Xtables: IPv4/6 IPsec-IPComp SPI match");
+
+/* Returns 1 if the spi is matched by the range, 0 otherwise */
+static inline bool
+spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert)
+{
+	bool r;
+	pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n",
+		 invert ? '!' : ' ', min, spi, max);
+	r = (spi >= min && spi <= max) ^ invert;
+	pr_debug(" result %s\n", r ? "PASS" : "FAILED");
+	return r;
+}
+
+static bool comp_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct ip_comp_hdr _comphdr;
+	const struct ip_comp_hdr *chdr;
+	const struct xt_ipcomp *compinfo = par->matchinfo;
+
+	/* Must not be a fragment. */
+	if (par->fragoff != 0)
+		return false;
+
+	chdr = skb_header_pointer(skb, par->thoff, sizeof(_comphdr), &_comphdr);
+	if (chdr == NULL) {
+		/* We've been asked to examine this packet, and we
+		 * can't.  Hence, no choice but to drop.
+		 */
+		pr_debug("Dropping evil IPComp tinygram.\n");
+		par->hotdrop = true;
+		return 0;
+	}
+
+	return spi_match(compinfo->spis[0], compinfo->spis[1],
+			 ntohl(chdr->cpi << 16),
+			 !!(compinfo->invflags & XT_IPCOMP_INV_SPI));
+}
+
+static int comp_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct xt_ipcomp *compinfo = par->matchinfo;
+
+	/* Must specify no unknown invflags */
+	if (compinfo->invflags & ~XT_IPCOMP_INV_MASK) {
+		pr_err("unknown flags %X\n", compinfo->invflags);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct xt_match comp_mt_reg[] __read_mostly = {
+	{
+		.name		= "ipcomp",
+		.family		= NFPROTO_IPV4,
+		.match		= comp_mt,
+		.matchsize	= sizeof(struct xt_ipcomp),
+		.proto		= IPPROTO_COMP,
+		.checkentry	= comp_mt_check,
+		.me		= THIS_MODULE,
+	},
+	{
+		.name		= "ipcomp",
+		.family		= NFPROTO_IPV6,
+		.match		= comp_mt,
+		.matchsize	= sizeof(struct xt_ipcomp),
+		.proto		= IPPROTO_COMP,
+		.checkentry	= comp_mt_check,
+		.me		= THIS_MODULE,
+	},
+};
+
+static int __init comp_mt_init(void)
+{
+	return xt_register_matches(comp_mt_reg, ARRAY_SIZE(comp_mt_reg));
+}
+
+static void __exit comp_mt_exit(void)
+{
+	xt_unregister_matches(comp_mt_reg, ARRAY_SIZE(comp_mt_reg));
+}
+
+module_init(comp_mt_init);
+module_exit(comp_mt_exit);
-- 
cgit v1.2.3


From 2e04ad424b03661ec8239acd52146497eb33be1c Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Fri, 20 Dec 2013 09:24:47 +0800
Subject: sch_tbf: add TBF_BURST/TBF_PBURST attribute

When we set burst to 1514 with low rate in userspace,
the kernel get a value of burst that less than 1514,
which doesn't work.

Because it may make some loss when transform burst
to buffer in userspace. This makes burst lose some
bytes, when the kernel transform the buffer back to
burst.

This patch adds two new attributes to support sending
burst/mtu to kernel directly to avoid the loss.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  2 ++
 net/sched/sch_tbf.c            | 29 ++++++++++++++++++++++++-----
 2 files changed, 26 insertions(+), 5 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 4566993b8385..fe1192056fd1 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -173,6 +173,8 @@ enum {
 	TCA_TBF_PTAB,
 	TCA_TBF_RATE64,
 	TCA_TBF_PRATE64,
+	TCA_TBF_BURST,
+	TCA_TBF_PBURST,
 	__TCA_TBF_MAX,
 };
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 887e672f9d7d..fbba5b0ec121 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -307,6 +307,8 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
 	[TCA_TBF_PTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_TBF_RATE64]	= { .type = NLA_U64 },
 	[TCA_TBF_PRATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_BURST] = { .type = NLA_U32 },
+	[TCA_TBF_PBURST] = { .type = NLA_U32 },
 };
 
 static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
@@ -358,7 +360,12 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
 	psched_ratecfg_precompute(&rate, &qopt->rate, rate64);
 
-	max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
+	if (tb[TCA_TBF_BURST]) {
+		max_size = nla_get_u32(tb[TCA_TBF_BURST]);
+		buffer = psched_l2t_ns(&rate, max_size);
+	} else {
+		max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
+	}
 
 	if (qopt->peakrate.rate) {
 		if (tb[TCA_TBF_PRATE64])
@@ -366,12 +373,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64);
 		if (peak.rate_bytes_ps <= rate.rate_bytes_ps) {
 			pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
-					    peak.rate_bytes_ps, rate.rate_bytes_ps);
+					peak.rate_bytes_ps, rate.rate_bytes_ps);
 			err = -EINVAL;
 			goto done;
 		}
 
-		max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
+		if (tb[TCA_TBF_PBURST]) {
+			u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]);
+			max_size = min_t(u32, max_size, pburst);
+			mtu = psched_l2t_ns(&peak, pburst);
+		} else {
+			max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
+		}
 	}
 
 	if (max_size < psched_mtu(qdisc_dev(sch)))
@@ -391,9 +404,15 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
-	q->mtu = PSCHED_TICKS2NS(qopt->mtu);
+	if (tb[TCA_TBF_PBURST])
+		q->mtu = mtu;
+	else
+		q->mtu = PSCHED_TICKS2NS(qopt->mtu);
 	q->max_size = max_size;
-	q->buffer = PSCHED_TICKS2NS(qopt->buffer);
+	if (tb[TCA_TBF_BURST])
+		q->buffer = buffer;
+	else
+		q->buffer = PSCHED_TICKS2NS(qopt->buffer);
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 
-- 
cgit v1.2.3


From e035b77ac7be430a5fef8c9c23f60b6b50ec81c5 Mon Sep 17 00:00:00 2001
From: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Date: Thu, 26 Dec 2013 16:38:01 +0100
Subject: netfilter: nf_tables: nft_meta module get/set ops

This patch adds kernel support for the meta expression in get/set
flavour. The set operation indicates that a given packet has to be
set with a property, currently one of mark, priority, nftrace.
The get op is what was currently working: evaluate the given
packet property.

In the nftrace case, the value is always 1. Such behaviour is copied
from net/netfilter/xt_TRACE.c

The NFTA_META_DREG and NFTA_META_SREG attributes are mutually
exclusives.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |   2 +
 net/netfilter/nft_meta.c                 | 146 ++++++++++++++++++++++++++-----
 2 files changed, 125 insertions(+), 23 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index b25481e16f0a..aa86a15293e1 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -555,11 +555,13 @@ enum nft_meta_keys {
  *
  * @NFTA_META_DREG: destination register (NLA_U32)
  * @NFTA_META_KEY: meta data item to load (NLA_U32: nft_meta_keys)
+ * @NFTA_META_SREG: source register (NLA_U32)
  */
 enum nft_meta_attributes {
 	NFTA_META_UNSPEC,
 	NFTA_META_DREG,
 	NFTA_META_KEY,
+	NFTA_META_SREG,
 	__NFTA_META_MAX
 };
 #define NFTA_META_MAX		(__NFTA_META_MAX - 1)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 8c28220a90b3..1ceaaa6dfe72 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -21,12 +21,15 @@
 
 struct nft_meta {
 	enum nft_meta_keys	key:8;
-	enum nft_registers	dreg:8;
+	union {
+		enum nft_registers	dreg:8;
+		enum nft_registers	sreg:8;
+	};
 };
 
-static void nft_meta_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt)
+static void nft_meta_get_eval(const struct nft_expr *expr,
+			      struct nft_data data[NFT_REG_MAX + 1],
+			      const struct nft_pktinfo *pkt)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 	const struct sk_buff *skb = pkt->skb;
@@ -132,23 +135,50 @@ err:
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
 }
 
+static void nft_meta_set_eval(const struct nft_expr *expr,
+			      struct nft_data data[NFT_REG_MAX + 1],
+			      const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *meta = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	u32 value = data[meta->sreg].data[0];
+
+	switch (meta->key) {
+	case NFT_META_MARK:
+		skb->mark = value;
+		break;
+	case NFT_META_PRIORITY:
+		skb->priority = value;
+		break;
+	case NFT_META_NFTRACE:
+		skb->nf_trace = 1;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
 static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
 	[NFTA_META_DREG]	= { .type = NLA_U32 },
 	[NFTA_META_KEY]		= { .type = NLA_U32 },
+	[NFTA_META_SREG]	= { .type = NLA_U32 },
 };
 
-static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			 const struct nlattr * const tb[])
+static int nft_meta_init_validate_set(uint32_t key)
 {
-	struct nft_meta *priv = nft_expr_priv(expr);
-	int err;
-
-	if (tb[NFTA_META_DREG] == NULL ||
-	    tb[NFTA_META_KEY] == NULL)
-		return -EINVAL;
+	switch (key) {
+	case NFT_META_MARK:
+	case NFT_META_PRIORITY:
+	case NFT_META_NFTRACE:
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
 
-	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
-	switch (priv->key) {
+static int nft_meta_init_validate_get(uint32_t key)
+{
+	switch (key) {
 	case NFT_META_LEN:
 	case NFT_META_PROTOCOL:
 	case NFT_META_PRIORITY:
@@ -167,26 +197,69 @@ static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 #ifdef CONFIG_NETWORK_SECMARK
 	case NFT_META_SECMARK:
 #endif
-		break;
+		return 0;
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
-	err = nft_validate_output_register(priv->dreg);
+}
+
+static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			 const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+
+	if (tb[NFTA_META_DREG]) {
+		err = nft_meta_init_validate_get(priv->key);
+		if (err < 0)
+			return err;
+
+		priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
+		err = nft_validate_output_register(priv->dreg);
+		if (err < 0)
+			return err;
+
+		return nft_validate_data_load(ctx, priv->dreg, NULL,
+					      NFT_DATA_VALUE);
+	}
+
+	err = nft_meta_init_validate_set(priv->key);
 	if (err < 0)
 		return err;
-	return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_META_SREG]));
+
+	return 0;
 }
 
-static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_meta_get_dump(struct sk_buff *skb,
+			     const struct nft_expr *expr)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 
+	if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
+		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_META_DREG, htonl(priv->dreg)))
 		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static int nft_meta_set_dump(struct sk_buff *skb,
+			     const struct nft_expr *expr)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+
 	if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
 		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_META_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -194,17 +267,44 @@ nla_put_failure:
 }
 
 static struct nft_expr_type nft_meta_type;
-static const struct nft_expr_ops nft_meta_ops = {
+static const struct nft_expr_ops nft_meta_get_ops = {
 	.type		= &nft_meta_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
-	.eval		= nft_meta_eval,
+	.eval		= nft_meta_get_eval,
 	.init		= nft_meta_init,
-	.dump		= nft_meta_dump,
+	.dump		= nft_meta_get_dump,
 };
 
+static const struct nft_expr_ops nft_meta_set_ops = {
+	.type		= &nft_meta_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_set_eval,
+	.init		= nft_meta_init,
+	.dump		= nft_meta_set_dump,
+};
+
+static const struct nft_expr_ops *
+nft_meta_select_ops(const struct nft_ctx *ctx,
+		    const struct nlattr * const tb[])
+{
+	if (tb[NFTA_META_KEY] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG])
+		return &nft_meta_get_ops;
+
+	if (tb[NFTA_META_SREG])
+		return &nft_meta_set_ops;
+
+	return ERR_PTR(-EINVAL);
+}
+
 static struct nft_expr_type nft_meta_type __read_mostly = {
 	.name		= "meta",
-	.ops		= &nft_meta_ops,
+	.select_ops	= &nft_meta_select_ops,
 	.policy		= nft_meta_policy,
 	.maxattr	= NFTA_META_MAX,
 	.owner		= THIS_MODULE,
-- 
cgit v1.2.3


From 604d13c97f0d863e41da3f5835c62e3cf899962b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 23 Dec 2013 14:35:56 +0100
Subject: netlink: specify netlink packet direction for nlmon

In order to facilitate development for netlink protocol dissector,
fill the unused field skb->pkt_type of the cloned skb with a hint
of the address space of the new owner (receiver) socket in the
notion of "to kernel" resp. "to user".

At the time we invoke __netlink_deliver_tap_skb(), we already have
set the new skb owner via netlink_skb_set_owner_r(), so we can use
that for netlink_is_kernel() probing.

In normal PF_PACKET network traffic, this field denotes if the
packet is destined for us (PACKET_HOST), if it's broadcast
(PACKET_BROADCAST), etc.

As we only have 3 bit reserved, we can use the value (= 6) of
PACKET_FASTROUTE as it's _not used_ anywhere in the whole kernel
and not supported anywhere, and packets of such type were never
exposed to user space, so there are no overlapping users of such
kind. Thus, as wished, that seems the only way to make both
PACKET_* values non-overlapping and therefore device agnostic.

By using those two flags for netlink skbs on nlmon devices, they
can be made available and picked up via sll_pkttype (previously
unused in netlink context) in struct sockaddr_ll. We now have
these two directions:

 - PACKET_USER (= 6)    ->  to user space
 - PACKET_KERNEL (= 7)  ->  to kernel space

Partial `ip a` example strace for sa_family=AF_NETLINK with
detected nl msg direction:

syscall:                     direction:
sendto(3,  ...) = 40         /* to kernel */
recvmsg(3, ...) = 3404       /* to user */
recvmsg(3, ...) = 1120       /* to user */
recvmsg(3, ...) = 20         /* to user */
sendto(3,  ...) = 40         /* to kernel */
recvmsg(3, ...) = 168        /* to user */
recvmsg(3, ...) = 144        /* to user */
recvmsg(3, ...) = 20         /* to user */

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_packet.h | 4 +++-
 net/netlink/af_netlink.c       | 2 ++
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index e9d844c80c11..1988a02842cc 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -26,8 +26,10 @@ struct sockaddr_ll {
 #define PACKET_MULTICAST	2		/* To group		*/
 #define PACKET_OTHERHOST	3		/* To someone else 	*/
 #define PACKET_OUTGOING		4		/* Outgoing of any type */
-/* These ones are invisible by user level */
 #define PACKET_LOOPBACK		5		/* MC/BRD frame looped back */
+#define PACKET_USER		6		/* To user space	*/
+#define PACKET_KERNEL		7		/* To kernel space	*/
+/* Unused, PACKET_FASTROUTE and PACKET_LOOPBACK are invisible to user space */
 #define PACKET_FASTROUTE	6		/* Fastrouted frame	*/
 
 /* Packet socket options */
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 56e09d8a55fd..3f75f1cd9eb3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -204,6 +204,8 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
+		nskb->pkt_type = netlink_is_kernel(sk) ?
+				 PACKET_KERNEL : PACKET_USER;
 
 		ret = dev_queue_xmit(nskb);
 		if (unlikely(ret > 0))
-- 
cgit v1.2.3


From 6a031f67c83aa175aedd10d4ae64750415ab57b0 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Wed, 25 Dec 2013 17:35:15 +0800
Subject: sch_netem: support of 64bit rates

Add a new attribute to support 64bit rates so that
tc can use them to break the 32bit limit.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  1 +
 net/sched/sch_netem.c          | 15 +++++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index fe1192056fd1..77eb331810b8 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -525,6 +525,7 @@ enum {
 	TCA_NETEM_LOSS,
 	TCA_NETEM_RATE,
 	TCA_NETEM_ECN,
+	TCA_NETEM_RATE64,
 	__TCA_NETEM_MAX,
 };
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 9632a4e753b7..090a4e3ecd0d 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -88,7 +88,7 @@ struct netem_sched_data {
 	u32 duplicate;
 	u32 reorder;
 	u32 corrupt;
-	u32 rate;
+	u64 rate;
 	s32 packet_overhead;
 	u32 cell_size;
 	u32 cell_size_reciprocal;
@@ -782,6 +782,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_RATE]	= { .len = sizeof(struct tc_netem_rate) },
 	[TCA_NETEM_LOSS]	= { .type = NLA_NESTED },
 	[TCA_NETEM_ECN]		= { .type = NLA_U32 },
+	[TCA_NETEM_RATE64]	= { .type = NLA_U64 },
 };
 
 static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -852,6 +853,10 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 	if (tb[TCA_NETEM_RATE])
 		get_rate(sch, tb[TCA_NETEM_RATE]);
 
+	if (tb[TCA_NETEM_RATE64])
+		q->rate = max_t(u64, q->rate,
+				nla_get_u64(tb[TCA_NETEM_RATE64]));
+
 	if (tb[TCA_NETEM_ECN])
 		q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]);
 
@@ -974,7 +979,13 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt))
 		goto nla_put_failure;
 
-	rate.rate = q->rate;
+	if (q->rate >= (1ULL << 32)) {
+		if (nla_put_u64(skb, TCA_NETEM_RATE64, q->rate))
+			goto nla_put_failure;
+		rate.rate = ~0U;
+	} else {
+		rate.rate = q->rate;
+	}
 	rate.packet_overhead = q->packet_overhead;
 	rate.cell_size = q->cell_size;
 	rate.cell_overhead = q->cell_overhead;
-- 
cgit v1.2.3


From 34ce324019e76f6d93768d68343a0e78f464d754 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 20 Dec 2013 22:40:29 +0100
Subject: netfilter: nf_nat: add full port randomization support

We currently use prandom_u32() for allocation of ports in tcp bind(0)
and udp code. In case of plain SNAT we try to keep the ports as is
or increment on collision.

SNAT --random mode does use per-destination incrementing port
allocation. As a recent paper pointed out in [1] that this mode of
port allocation makes it possible to an attacker to find the randomly
allocated ports through a timing side-channel in a socket overloading
attack conducted through an off-path attacker.

So, NF_NAT_RANGE_PROTO_RANDOM actually weakens the port randomization
in regard to the attack described in this paper. As we need to keep
compatibility, add another flag called NF_NAT_RANGE_PROTO_RANDOM_FULLY
that would replace the NF_NAT_RANGE_PROTO_RANDOM hash-based port
selection algorithm with a simple prandom_u32() in order to mitigate
this attack vector. Note that the lfsr113's internal state is
periodically reseeded by the kernel through a local secure entropy
source.

More details can be found in [1], the basic idea is to send bursts
of packets to a socket to overflow its receive queue and measure
the latency to detect a possible retransmit when the port is found.
Because of increasing ports to given destination and port, further
allocations can be predicted. This information could then be used by
an attacker for e.g. for cache-poisoning, NS pinning, and degradation
of service attacks against DNS servers [1]:

  The best defense against the poisoning attacks is to properly
  deploy and validate DNSSEC; DNSSEC provides security not only
  against off-path attacker but even against MitM attacker. We hope
  that our results will help motivate administrators to adopt DNSSEC.
  However, full DNSSEC deployment make take significant time, and
  until that happens, we recommend short-term, non-cryptographic
  defenses. We recommend to support full port randomisation,
  according to practices recommended in [2], and to avoid
  per-destination sequential port allocation, which we show may be
  vulnerable to derandomisation attacks.

Joint work between Hannes Frederic Sowa and Daniel Borkmann.

 [1] https://sites.google.com/site/hayashulman/files/NIC-derandomisation.pdf
 [2] http://arxiv.org/pdf/1205.5190v1.pdf

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_nat.h | 12 ++++++++----
 net/netfilter/nf_nat_core.c           |  4 ++--
 net/netfilter/nf_nat_proto_common.c   | 10 ++++++----
 3 files changed, 16 insertions(+), 10 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nf_nat.h b/include/uapi/linux/netfilter/nf_nat.h
index bf0cc373ffb6..1ad3659102b6 100644
--- a/include/uapi/linux/netfilter/nf_nat.h
+++ b/include/uapi/linux/netfilter/nf_nat.h
@@ -4,10 +4,14 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_conntrack_tuple_common.h>
 
-#define NF_NAT_RANGE_MAP_IPS		1
-#define NF_NAT_RANGE_PROTO_SPECIFIED	2
-#define NF_NAT_RANGE_PROTO_RANDOM	4
-#define NF_NAT_RANGE_PERSISTENT		8
+#define NF_NAT_RANGE_MAP_IPS			(1 << 0)
+#define NF_NAT_RANGE_PROTO_SPECIFIED		(1 << 1)
+#define NF_NAT_RANGE_PROTO_RANDOM		(1 << 2)
+#define NF_NAT_RANGE_PERSISTENT			(1 << 3)
+#define NF_NAT_RANGE_PROTO_RANDOM_FULLY		(1 << 4)
+
+#define NF_NAT_RANGE_PROTO_RANDOM_ALL		\
+	(NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY)
 
 struct nf_nat_ipv4_range {
 	unsigned int			flags;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 63a815402211..d3f5cd6dd962 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -315,7 +315,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	 * manips not an issue.
 	 */
 	if (maniptype == NF_NAT_MANIP_SRC &&
-	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
+	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		/* try the original tuple first */
 		if (in_range(l3proto, l4proto, orig_tuple, range)) {
 			if (!nf_nat_used_tuple(orig_tuple, ct)) {
@@ -339,7 +339,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	 */
 
 	/* Only bother mapping if it's not already in range and unique */
-	if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
+	if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
 			if (l4proto->in_range(tuple, maniptype,
 					      &range->min_proto,
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index 9baaf734c142..83a72a235cae 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -74,22 +74,24 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		range_size = ntohs(range->max_proto.all) - min + 1;
 	}
 
-	if (range->flags & NF_NAT_RANGE_PROTO_RANDOM)
+	if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) {
 		off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC
 						  ? tuple->dst.u.all
 						  : tuple->src.u.all);
-	else
+	} else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) {
+		off = prandom_u32();
+	} else {
 		off = *rover;
+	}
 
 	for (i = 0; ; ++off) {
 		*portptr = htons(min + off % range_size);
 		if (++i != range_size && nf_nat_used_tuple(tuple, ct))
 			continue;
-		if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM))
+		if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL))
 			*rover = off;
 		return;
 	}
-	return;
 }
 EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple);
 
-- 
cgit v1.2.3


From 82a37132f300ea53bdcd812917af5a6329ec80c3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Sun, 29 Dec 2013 18:27:12 +0100
Subject: netfilter: x_tables: lightweight process control group matching

It would be useful e.g. in a server or desktop environment to have
a facility in the notion of fine-grained "per application" or "per
application group" firewall policies. Probably, users in the mobile,
embedded area (e.g. Android based) with different security policy
requirements for application groups could have great benefit from
that as well. For example, with a little bit of configuration effort,
an admin could whitelist well-known applications, and thus block
otherwise unwanted "hard-to-track" applications like [1] from a
user's machine. Blocking is just one example, but it is not limited
to that, meaning we can have much different scenarios/policies that
netfilter allows us than just blocking, e.g. fine grained settings
where applications are allowed to connect/send traffic to, application
traffic marking/conntracking, application-specific packet mangling,
and so on.

Implementation of PID-based matching would not be appropriate
as they frequently change, and child tracking would make that
even more complex and ugly. Cgroups would be a perfect candidate
for accomplishing that as they associate a set of tasks with a
set of parameters for one or more subsystems, in our case the
netfilter subsystem, which, of course, can be combined with other
cgroup subsystems into something more complex if needed.

As mentioned, to overcome this constraint, such processes could
be placed into one or multiple cgroups where different fine-grained
rules can be defined depending on the application scenario, while
e.g. everything else that is not part of that could be dropped (or
vice versa), thus making life harder for unwanted processes to
communicate to the outside world. So, we make use of cgroups here
to track jobs and limit their resources in terms of iptables
policies; in other words, limiting, tracking, etc what they are
allowed to communicate.

In our case we're working on outgoing traffic based on which local
socket that originated from. Also, one doesn't even need to have
an a-prio knowledge of the application internals regarding their
particular use of ports or protocols. Matching is *extremly*
lightweight as we just test for the sk_classid marker of sockets,
originating from net_cls. net_cls and netfilter do not contradict
each other; in fact, each construct can live as standalone or they
can be used in combination with each other, which is perfectly fine,
plus it serves Tejun's requirement to not introduce a new cgroups
subsystem. Through this, we result in a very minimal and efficient
module, and don't add anything except netfilter code.

One possible, minimal usage example (many other iptables options
can be applied obviously):

 1) Configuring cgroups if not already done, e.g.:

  mkdir /sys/fs/cgroup/net_cls
  mount -t cgroup -o net_cls net_cls /sys/fs/cgroup/net_cls
  mkdir /sys/fs/cgroup/net_cls/0
  echo 1 > /sys/fs/cgroup/net_cls/0/net_cls.classid
  (resp. a real flow handle id for tc)

 2) Configuring netfilter (iptables-nftables), e.g.:

  iptables -A OUTPUT -m cgroup ! --cgroup 1 -j DROP

 3) Running applications, e.g.:

  ping 208.67.222.222  <pid:1799>
  echo 1799 > /sys/fs/cgroup/net_cls/0/tasks
  64 bytes from 208.67.222.222: icmp_seq=44 ttl=49 time=11.9 ms
  [...]
  ping 208.67.220.220  <pid:1804>
  ping: sendmsg: Operation not permitted
  [...]
  echo 1804 > /sys/fs/cgroup/net_cls/0/tasks
  64 bytes from 208.67.220.220: icmp_seq=89 ttl=56 time=19.0 ms
  [...]

Of course, real-world deployments would make use of cgroups user
space toolsuite, or own custom policy daemons dynamically moving
applications from/to various cgroups.

  [1] http://www.blackhat.com/presentations/bh-europe-06/bh-eu-06-biondi/bh-eu-06-biondi-up.pdf

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: cgroups@vger.kernel.org
Acked-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 Documentation/cgroups/net_cls.txt        |  5 +++
 include/uapi/linux/netfilter/Kbuild      |  1 +
 include/uapi/linux/netfilter/xt_cgroup.h | 11 +++++
 net/netfilter/Kconfig                    | 10 +++++
 net/netfilter/Makefile                   |  1 +
 net/netfilter/xt_cgroup.c                | 71 ++++++++++++++++++++++++++++++++
 6 files changed, 99 insertions(+)
 create mode 100644 include/uapi/linux/netfilter/xt_cgroup.h
 create mode 100644 net/netfilter/xt_cgroup.c

(limited to 'include/uapi')

diff --git a/Documentation/cgroups/net_cls.txt b/Documentation/cgroups/net_cls.txt
index 9face6bb578a..ec182346dea2 100644
--- a/Documentation/cgroups/net_cls.txt
+++ b/Documentation/cgroups/net_cls.txt
@@ -6,6 +6,8 @@ tag network packets with a class identifier (classid).
 
 The Traffic Controller (tc) can be used to assign
 different priorities to packets from different cgroups.
+Also, Netfilter (iptables) can use this tag to perform
+actions on such packets.
 
 Creating a net_cls cgroups instance creates a net_cls.classid file.
 This net_cls.classid value is initialized to 0.
@@ -32,3 +34,6 @@ tc class add dev eth0 parent 10: classid 10:1 htb rate 40mbit
  - creating traffic class 10:1
 
 tc filter add dev eth0 parent 10: protocol ip prio 10 handle 1: cgroup
+
+configuring iptables, basic example:
+iptables -A OUTPUT -m cgroup ! --cgroup 0x100001 -j DROP
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 91be8ce623f0..2344f5a319fc 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -39,6 +39,7 @@ header-y += xt_TEE.h
 header-y += xt_TPROXY.h
 header-y += xt_addrtype.h
 header-y += xt_bpf.h
+header-y += xt_cgroup.h
 header-y += xt_cluster.h
 header-y += xt_comment.h
 header-y += xt_connbytes.h
diff --git a/include/uapi/linux/netfilter/xt_cgroup.h b/include/uapi/linux/netfilter/xt_cgroup.h
new file mode 100644
index 000000000000..43acb7e175f6
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_cgroup.h
@@ -0,0 +1,11 @@
+#ifndef _UAPI_XT_CGROUP_H
+#define _UAPI_XT_CGROUP_H
+
+#include <linux/types.h>
+
+struct xt_cgroup_info {
+	__u32 id;
+	__u32 invert;
+};
+
+#endif /* _UAPI_XT_CGROUP_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 6d8e48b376fc..c17902cb5df9 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -858,6 +858,16 @@ config NETFILTER_XT_MATCH_BPF
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NETFILTER_XT_MATCH_CGROUP
+	tristate '"control group" match support'
+	depends on NETFILTER_ADVANCED
+	depends on CGROUPS
+	select CGROUP_NET_CLASSID
+	---help---
+	Socket/process control group matching allows you to match locally
+	generated packets based on which net_cls control group processes
+	belong to.
+
 config NETFILTER_XT_MATCH_CLUSTER
 	tristate '"cluster" match support'
 	depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 398cd709aa09..407fc232f625 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -143,6 +143,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_NFACCT) += xt_nfacct.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_CGROUP) += xt_cgroup.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
new file mode 100644
index 000000000000..9a8e77e7f8d4
--- /dev/null
+++ b/net/netfilter/xt_cgroup.c
@@ -0,0 +1,71 @@
+/*
+ * Xtables module to match the process control group.
+ *
+ * Might be used to implement individual "per-application" firewall
+ * policies in contrast to global policies based on control groups.
+ * Matching is based upon processes tagged to net_cls' classid marker.
+ *
+ * (C) 2013 Daniel Borkmann <dborkman@redhat.com>
+ *
+ * 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/skbuff.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_cgroup.h>
+#include <net/sock.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
+MODULE_DESCRIPTION("Xtables: process control group matching");
+MODULE_ALIAS("ipt_cgroup");
+MODULE_ALIAS("ip6t_cgroup");
+
+static int cgroup_mt_check(const struct xt_mtchk_param *par)
+{
+	struct xt_cgroup_info *info = par->matchinfo;
+
+	if (info->invert & ~1)
+		return -EINVAL;
+
+	return info->id ? 0 : -EINVAL;
+}
+
+static bool
+cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_cgroup_info *info = par->matchinfo;
+
+	if (skb->sk == NULL)
+		return false;
+
+	return (info->id == skb->sk->sk_classid) ^ info->invert;
+}
+
+static struct xt_match cgroup_mt_reg __read_mostly = {
+	.name       = "cgroup",
+	.revision   = 0,
+	.family     = NFPROTO_UNSPEC,
+	.checkentry = cgroup_mt_check,
+	.match      = cgroup_mt,
+	.matchsize  = sizeof(struct xt_cgroup_info),
+	.me         = THIS_MODULE,
+	.hooks      = (1 << NF_INET_LOCAL_OUT) |
+		      (1 << NF_INET_POST_ROUTING),
+};
+
+static int __init cgroup_mt_init(void)
+{
+	return xt_register_match(&cgroup_mt_reg);
+}
+
+static void __exit cgroup_mt_exit(void)
+{
+	xt_unregister_match(&cgroup_mt_reg);
+}
+
+module_init(cgroup_mt_init);
+module_exit(cgroup_mt_exit);
-- 
cgit v1.2.3


From 998e40bbf8f0e10b5d84107afc61e29dbc8d2de4 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Fri, 3 Jan 2014 14:18:41 -0800
Subject: bonding: add lacp_rate attribute netlink support

Add IFLA_BOND_AD_LACP_RATE to allow get/set of bonding parameter
lacp_rate via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 14 +++++++++++++
 drivers/net/bonding/bond_options.c | 29 +++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 40 +++++++++++---------------------------
 drivers/net/bonding/bonding.h      |  1 +
 include/uapi/linux/if_link.h       |  1 +
 5 files changed, 56 insertions(+), 29 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 84acd144d075..45de8734514d 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -43,6 +43,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MIN_LINKS]		= { .type = NLA_U32 },
 	[IFLA_BOND_LP_INTERVAL]		= { .type = NLA_U32 },
 	[IFLA_BOND_PACKETS_PER_SLAVE]	= { .type = NLA_U32 },
+	[IFLA_BOND_AD_LACP_RATE]	= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -252,6 +253,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_AD_LACP_RATE]) {
+		int lacp_rate =
+			nla_get_u8(data[IFLA_BOND_AD_LACP_RATE]);
+
+		err = bond_option_lacp_rate_set(bond, lacp_rate);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -290,6 +299,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_MIN_LINKS */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_LP_INTERVAL */
 		nla_total_size(sizeof(u32)) +  /* IFLA_BOND_PACKETS_PER_SLAVE */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_LACP_RATE */
 		0;
 }
 
@@ -395,6 +405,10 @@ static int bond_fill_info(struct sk_buff *skb,
 			packets_per_slave))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE,
+		       bond->params.lacp_fast))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index f8a2cd8c7b57..ad67fbf1ba61 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -656,3 +656,32 @@ int bond_option_packets_per_slave_set(struct bonding *bond,
 
 	return 0;
 }
+
+int bond_option_lacp_rate_set(struct bonding *bond, int lacp_rate)
+{
+	if (bond->dev->flags & IFF_UP) {
+		pr_err("%s: Unable to update LACP rate because interface is up.\n",
+		       bond->dev->name);
+		return -EPERM;
+	}
+
+	if (bond->params.mode != BOND_MODE_8023AD) {
+		pr_err("%s: Unable to update LACP rate because bond is not in 802.3ad mode.\n",
+		       bond->dev->name);
+		return -EPERM;
+	}
+
+	if ((lacp_rate == 1) || (lacp_rate == 0)) {
+		bond->params.lacp_fast = lacp_rate;
+		bond_3ad_update_lacp_rate(bond);
+		pr_info("%s: Setting LACP rate to %s (%d).\n",
+			bond->dev->name, bond_lacp_tbl[lacp_rate].modename,
+			lacp_rate);
+	} else {
+		pr_err("%s: Ignoring invalid LACP rate value %d.\n",
+		       bond->dev->name, lacp_rate);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index a0a3476fadba..62d33dcc9243 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -658,41 +658,23 @@ static ssize_t bonding_store_lacp(struct device *d,
 				  const char *buf, size_t count)
 {
 	struct bonding *bond = to_bond(d);
-	int new_value, ret = count;
-
-	if (!rtnl_trylock())
-		return restart_syscall();
-
-	if (bond->dev->flags & IFF_UP) {
-		pr_err("%s: Unable to update LACP rate because interface is up.\n",
-		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
-	}
-
-	if (bond->params.mode != BOND_MODE_8023AD) {
-		pr_err("%s: Unable to update LACP rate because bond is not in 802.3ad mode.\n",
-		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
-	}
+	int new_value, ret;
 
 	new_value = bond_parse_parm(buf, bond_lacp_tbl);
-
-	if ((new_value == 1) || (new_value == 0)) {
-		bond->params.lacp_fast = new_value;
-		bond_3ad_update_lacp_rate(bond);
-		pr_info("%s: Setting LACP rate to %s (%d).\n",
-			bond->dev->name, bond_lacp_tbl[new_value].modename,
-			new_value);
-	} else {
+	if (new_value < 0) {
 		pr_err("%s: Ignoring invalid LACP rate value %.*s.\n",
 		       bond->dev->name, (int)strlen(buf) - 1, buf);
-		ret = -EINVAL;
+		return -EINVAL;
 	}
-out:
-	rtnl_unlock();
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_lacp_rate_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 8e8817f3ef31..585bfefe3b47 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -464,6 +464,7 @@ int bond_option_min_links_set(struct bonding *bond, int min_links);
 int bond_option_lp_interval_set(struct bonding *bond, int min_links);
 int bond_option_packets_per_slave_set(struct bonding *bond,
 				      int packets_per_slave);
+int bond_option_lacp_rate_set(struct bonding *bond, int lacp_rate);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 8fbc7ca878b4..0f8f38f965cb 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -349,6 +349,7 @@ enum {
 	IFLA_BOND_MIN_LINKS,
 	IFLA_BOND_LP_INTERVAL,
 	IFLA_BOND_PACKETS_PER_SLAVE,
+	IFLA_BOND_AD_LACP_RATE,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From ec029fac3e96980fa8f6f81b8327787a9600dfaa Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Fri, 3 Jan 2014 14:18:49 -0800
Subject: bonding: add ad_select attribute netlink support

Add IFLA_BOND_AD_SELECT to allow get/set of bonding parameter
ad_select via netlink.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c    | 45 ++++++++++++++++++++++++--------------
 drivers/net/bonding/bond_netlink.c | 14 ++++++++++++
 drivers/net/bonding/bond_options.c | 22 +++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c   | 29 ++++++++++--------------
 drivers/net/bonding/bonding.h      |  2 ++
 include/uapi/linux/if_link.h       |  1 +
 6 files changed, 80 insertions(+), 33 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 11bedbaf37db..e06c4453eabb 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3933,6 +3933,29 @@ static void bond_uninit(struct net_device *bond_dev)
 
 /*------------------------- Module initialization ---------------------------*/
 
+int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl)
+{
+	int i;
+
+	for (i = 0; tbl[i].modename; i++)
+		if (mode == tbl[i].mode)
+			return tbl[i].mode;
+
+	return -1;
+}
+
+static int bond_parm_tbl_lookup_name(const char *modename,
+				     const struct bond_parm_tbl *tbl)
+{
+	int i;
+
+	for (i = 0; tbl[i].modename; i++)
+		if (strcmp(modename, tbl[i].modename) == 0)
+			return tbl[i].mode;
+
+	return -1;
+}
+
 /*
  * Convert string input module parms.  Accept either the
  * number of the mode or its string name.  A bit complicated because
@@ -3941,27 +3964,17 @@ static void bond_uninit(struct net_device *bond_dev)
  */
 int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl)
 {
-	int modeint = -1, i, rv;
-	char *p, modestr[BOND_MAX_MODENAME_LEN + 1] = { 0, };
+	int modeint;
+	char *p, modestr[BOND_MAX_MODENAME_LEN + 1];
 
 	for (p = (char *)buf; *p; p++)
 		if (!(isdigit(*p) || isspace(*p)))
 			break;
 
-	if (*p)
-		rv = sscanf(buf, "%20s", modestr);
-	else
-		rv = sscanf(buf, "%d", &modeint);
-
-	if (!rv)
-		return -1;
-
-	for (i = 0; tbl[i].modename; i++) {
-		if (modeint == tbl[i].mode)
-			return tbl[i].mode;
-		if (strcmp(modestr, tbl[i].modename) == 0)
-			return tbl[i].mode;
-	}
+	if (*p && sscanf(buf, "%20s", modestr) != 0)
+		return bond_parm_tbl_lookup_name(modestr, tbl);
+	else if (sscanf(buf, "%d", &modeint) != 0)
+		return bond_parm_tbl_lookup(modeint, tbl);
 
 	return -1;
 }
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 45de8734514d..df66dd8c08b5 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -44,6 +44,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_LP_INTERVAL]		= { .type = NLA_U32 },
 	[IFLA_BOND_PACKETS_PER_SLAVE]	= { .type = NLA_U32 },
 	[IFLA_BOND_AD_LACP_RATE]	= { .type = NLA_U8 },
+	[IFLA_BOND_AD_SELECT]		= { .type = NLA_U8 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -261,6 +262,14 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_AD_SELECT]) {
+		int ad_select =
+			nla_get_u8(data[IFLA_BOND_AD_SELECT]);
+
+		err = bond_option_ad_select_set(bond, ad_select);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -300,6 +309,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_LP_INTERVAL */
 		nla_total_size(sizeof(u32)) +  /* IFLA_BOND_PACKETS_PER_SLAVE */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_LACP_RATE */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_SELECT */
 		0;
 }
 
@@ -409,6 +419,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.lacp_fast))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_AD_SELECT,
+		       bond->params.ad_select))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index ad67fbf1ba61..c9691bf0586c 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -685,3 +685,25 @@ int bond_option_lacp_rate_set(struct bonding *bond, int lacp_rate)
 
 	return 0;
 }
+
+int bond_option_ad_select_set(struct bonding *bond, int ad_select)
+{
+	if (bond->dev->flags & IFF_UP) {
+		pr_err("%s: Unable to update ad_select because interface is up.\n",
+		       bond->dev->name);
+		return -EPERM;
+	}
+
+	if (bond_parm_tbl_lookup(ad_select, ad_select_tbl) < 0) {
+		pr_err("%s: Ignoring invalid ad_select value %d.\n",
+		       bond->dev->name, ad_select);
+		return -EINVAL;
+	}
+
+	bond->params.ad_select = ad_select;
+	pr_info("%s: Setting ad_select to %s (%d).\n",
+		bond->dev->name, ad_select_tbl[ad_select].modename,
+		ad_select);
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 62d33dcc9243..9a1ea4a171c7 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -733,29 +733,24 @@ static ssize_t bonding_store_ad_select(struct device *d,
 				       struct device_attribute *attr,
 				       const char *buf, size_t count)
 {
-	int new_value, ret = count;
+	int new_value, ret;
 	struct bonding *bond = to_bond(d);
 
-	if (bond->dev->flags & IFF_UP) {
-		pr_err("%s: Unable to update ad_select because interface is up.\n",
-		       bond->dev->name);
-		ret = -EPERM;
-		goto out;
-	}
-
 	new_value = bond_parse_parm(buf, ad_select_tbl);
-
-	if (new_value != -1) {
-		bond->params.ad_select = new_value;
-		pr_info("%s: Setting ad_select to %s (%d).\n",
-			bond->dev->name, ad_select_tbl[new_value].modename,
-			new_value);
-	} else {
+	if (new_value < 0) {
 		pr_err("%s: Ignoring invalid ad_select value %.*s.\n",
 		       bond->dev->name, (int)strlen(buf) - 1, buf);
-		ret = -EINVAL;
+		return -EINVAL;
 	}
-out:
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	ret = bond_option_ad_select_set(bond, new_value);
+	if (!ret)
+		ret = count;
+
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 585bfefe3b47..955dc4839f1d 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -425,6 +425,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
 int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
 int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count);
 int bond_parse_parm(const char *mode_arg, const struct bond_parm_tbl *tbl);
+int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl);
 void bond_select_active_slave(struct bonding *bond);
 void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
 void bond_create_debugfs(void);
@@ -465,6 +466,7 @@ int bond_option_lp_interval_set(struct bonding *bond, int min_links);
 int bond_option_packets_per_slave_set(struct bonding *bond,
 				      int packets_per_slave);
 int bond_option_lacp_rate_set(struct bonding *bond, int lacp_rate);
+int bond_option_ad_select_set(struct bonding *bond, int ad_select);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 0f8f38f965cb..0fbb01824dd3 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -350,6 +350,7 @@ enum {
 	IFLA_BOND_LP_INTERVAL,
 	IFLA_BOND_PACKETS_PER_SLAVE,
 	IFLA_BOND_AD_LACP_RATE,
+	IFLA_BOND_AD_SELECT,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit v1.2.3


From 4ee7ac7526d4a9413cafa733d824edfe49fdcc46 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Fri, 3 Jan 2014 14:18:56 -0800
Subject: bonding: add ad_info attribute netlink support

Add nested IFLA_BOND_AD_INFO for bonding 802.3ad info.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 38 ++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/if_link.h       | 12 ++++++++++++
 2 files changed, 50 insertions(+)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index df66dd8c08b5..1b4013b5f230 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -45,6 +45,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_PACKETS_PER_SLAVE]	= { .type = NLA_U32 },
 	[IFLA_BOND_AD_LACP_RATE]	= { .type = NLA_U8 },
 	[IFLA_BOND_AD_SELECT]		= { .type = NLA_U8 },
+	[IFLA_BOND_AD_INFO]		= { .type = NLA_NESTED },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -310,6 +311,12 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u32)) +  /* IFLA_BOND_PACKETS_PER_SLAVE */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_LACP_RATE */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_AD_SELECT */
+		nla_total_size(sizeof(struct nlattr)) + /* IFLA_BOND_AD_INFO */
+		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_AGGREGATOR */
+		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_NUM_PORTS */
+		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_ACTOR_KEY */
+		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_PARTNER_KEY*/
+		nla_total_size(ETH_ALEN) +    /* IFLA_BOND_AD_INFO_PARTNER_MAC*/
 		0;
 }
 
@@ -423,6 +430,37 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.ad_select))
 		goto nla_put_failure;
 
+	if (bond->params.mode == BOND_MODE_8023AD) {
+		struct ad_info info;
+
+		if (!bond_3ad_get_active_agg_info(bond, &info)) {
+			struct nlattr *nest;
+
+			nest = nla_nest_start(skb, IFLA_BOND_AD_INFO);
+			if (!nest)
+				goto nla_put_failure;
+
+			if (nla_put_u16(skb, IFLA_BOND_AD_INFO_AGGREGATOR,
+					info.aggregator_id))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_BOND_AD_INFO_NUM_PORTS,
+					info.ports))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_BOND_AD_INFO_ACTOR_KEY,
+					info.actor_key))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_BOND_AD_INFO_PARTNER_KEY,
+					info.partner_key))
+				goto nla_put_failure;
+			if (nla_put(skb, IFLA_BOND_AD_INFO_PARTNER_MAC,
+				    sizeof(info.partner_system),
+				    &info.partner_system))
+				goto nla_put_failure;
+
+			nla_nest_end(skb, nest);
+		}
+	}
+
 	return 0;
 
 nla_put_failure:
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 0fbb01824dd3..3e6bd3c7445d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -351,11 +351,23 @@ enum {
 	IFLA_BOND_PACKETS_PER_SLAVE,
 	IFLA_BOND_AD_LACP_RATE,
 	IFLA_BOND_AD_SELECT,
+	IFLA_BOND_AD_INFO,
 	__IFLA_BOND_MAX,
 };
 
 #define IFLA_BOND_MAX	(__IFLA_BOND_MAX - 1)
 
+enum {
+	IFLA_BOND_AD_INFO_AGGREGATOR,
+	IFLA_BOND_AD_INFO_NUM_PORTS,
+	IFLA_BOND_AD_INFO_ACTOR_KEY,
+	IFLA_BOND_AD_INFO_PARTNER_KEY,
+	IFLA_BOND_AD_INFO_PARTNER_MAC,
+	__IFLA_BOND_AD_INFO_MAX,
+};
+
+#define IFLA_BOND_AD_INFO_MAX	(__IFLA_BOND_AD_INFO_MAX - 1)
+
 /* SR-IOV virtual function management section */
 
 enum {
-- 
cgit v1.2.3


From 55fdbfe7beb68c71060a27965a72f7eed09fa81d Mon Sep 17 00:00:00 2001
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Sat, 28 Dec 2013 04:28:18 -0800
Subject: pci_regs.h: Add PCI bus link speed and width defines

Add missing PCI bus link speed 8.0 GT/s and bus link widths of
x1, x2, x4 and x8.

CC: <linux-kernel@vger.kernel.org>
CC: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/uapi/linux/pci_regs.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 4a98e85438a7..c870c2a71d65 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -489,7 +489,12 @@
 #define  PCI_EXP_LNKSTA_CLS	0x000f	/* Current Link Speed */
 #define  PCI_EXP_LNKSTA_CLS_2_5GB 0x0001 /* Current Link Speed 2.5GT/s */
 #define  PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */
+#define  PCI_EXP_LNKSTA_CLS_8_0GB 0x0003 /* Current Link Speed 8.0GT/s */
 #define  PCI_EXP_LNKSTA_NLW	0x03f0	/* Negotiated Link Width */
+#define  PCI_EXP_LNKSTA_NLW_X1	0x0010	/* Current Link Width x1 */
+#define  PCI_EXP_LNKSTA_NLW_X2	0x0020	/* Current Link Width x2 */
+#define  PCI_EXP_LNKSTA_NLW_X4	0x0040	/* Current Link Width x4 */
+#define  PCI_EXP_LNKSTA_NLW_X8	0x0080	/* Current Link Width x8 */
 #define  PCI_EXP_LNKSTA_NLW_SHIFT 4	/* start of NLW mask in link status */
 #define  PCI_EXP_LNKSTA_LT	0x0800	/* Link Training */
 #define  PCI_EXP_LNKSTA_SLC	0x1000	/* Slot Clock Configuration */
-- 
cgit v1.2.3


From d4b36210c2e6ecef0ce52fb6c18c51144f5c2d88 Mon Sep 17 00:00:00 2001
From: Vijay Subramanian <vijaynsu@cisco.com>
Date: Sat, 4 Jan 2014 17:33:55 -0800
Subject: net: pkt_sched: PIE AQM scheme

Proportional Integral controller Enhanced (PIE) is a scheduler to address the
bufferbloat problem.

>From the IETF draft below:
" Bufferbloat is a phenomenon where excess buffers in the network cause high
latency and jitter. As more and more interactive applications (e.g. voice over
IP, real time video streaming and financial transactions) run in the Internet,
high latency and jitter degrade application performance. There is a pressing
need to design intelligent queue management schemes that can control latency and
jitter; and hence provide desirable quality of service to users.

We present here a lightweight design, PIE(Proportional Integral controller
Enhanced) that can effectively control the average queueing latency to a target
value. Simulation results, theoretical analysis and Linux testbed results have
shown that PIE can ensure low latency and achieve high link utilization under
various congestion situations. The design does not require per-packet
timestamp, so it incurs very small overhead and is simple enough to implement
in both hardware and software.  "

Many thanks to Dave Taht for extensive feedback, reviews, testing and
suggestions. Thanks also to Stephen Hemminger and Eric Dumazet for reviews and
suggestions.  Naeem Khademi and Dave Taht independently contributed to ECN
support.

For more information, please see technical paper about PIE in the IEEE
Conference on High Performance Switching and Routing 2013. A copy of the paper
can be found at ftp://ftpeng.cisco.com/pie/.

Please also refer to the IETF draft submission at
http://tools.ietf.org/html/draft-pan-tsvwg-pie-00

All relevant code, documents and test scripts and results can be found at
ftp://ftpeng.cisco.com/pie/.

For problems with the iproute2/tc or Linux kernel code, please contact Vijay
Subramanian (vijaynsu@cisco.com or subramanian.vijay@gmail.com) Mythili Prabhu
(mysuryan@cisco.com)

Signed-off-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: Mythili Prabhu <mysuryan@cisco.com>
CC: Dave Taht <dave.taht@bufferbloat.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  25 ++
 net/sched/Kconfig              |  13 +
 net/sched/Makefile             |   1 +
 net/sched/sch_pie.c            | 555 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 594 insertions(+)
 create mode 100644 net/sched/sch_pie.c

(limited to 'include/uapi')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 77eb331810b8..d62316baae94 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -818,4 +818,29 @@ struct tc_hhf_xstats {
 	__u32	hh_tot_count;   /* number of captured heavy-hitters so far */
 	__u32	hh_cur_count;   /* number of current heavy-hitters */
 };
+
+/* PIE */
+enum {
+	TCA_PIE_UNSPEC,
+	TCA_PIE_TARGET,
+	TCA_PIE_LIMIT,
+	TCA_PIE_TUPDATE,
+	TCA_PIE_ALPHA,
+	TCA_PIE_BETA,
+	TCA_PIE_ECN,
+	TCA_PIE_BYTEMODE,
+	__TCA_PIE_MAX
+};
+#define TCA_PIE_MAX   (__TCA_PIE_MAX - 1)
+
+struct tc_pie_xstats {
+	__u32 prob;             /* current probability */
+	__u32 delay;            /* current delay in ms */
+	__u32 avg_dq_rate;      /* current average dq_rate in bits/pie_time */
+	__u32 packets_in;       /* total number of packets enqueued */
+	__u32 dropped;          /* packets dropped due to pie_action */
+	__u32 overlimit;        /* dropped due to lack of space in queue */
+	__u32 maxq;             /* maximum queue size */
+	__u32 ecn_mark;         /* packets marked with ecn*/
+};
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index d3d7a0a66e28..a1a8e29e5fc9 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -295,6 +295,19 @@ config NET_SCH_HHF
 	  To compile this driver as a module, choose M here: the module
 	  will be called sch_hhf.
 
+config NET_SCH_PIE
+	tristate "Proportional Integral controller Enhanced (PIE) scheduler"
+	help
+	  Say Y here if you want to use the Proportional Integral controller
+	  Enhanced scheduler packet scheduling algorithm.
+	  For more information, please see
+	  http://tools.ietf.org/html/draft-pan-tsvwg-pie-00
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_pie.
+
+	  If unsure, say N.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 3442e5fbc4d7..0a869a11f3e6 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_NET_SCH_CODEL)	+= sch_codel.o
 obj-$(CONFIG_NET_SCH_FQ_CODEL)	+= sch_fq_codel.o
 obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
 obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
+obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
new file mode 100644
index 000000000000..fe65340c8eb4
--- /dev/null
+++ b/net/sched/sch_pie.c
@@ -0,0 +1,555 @@
+/* Copyright (C) 2013 Cisco Systems, Inc, 2013.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Author: Vijay Subramanian <vijaynsu@cisco.com>
+ * Author: Mythili Prabhu <mysuryan@cisco.com>
+ *
+ * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no>
+ * University of Oslo, Norway.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/pkt_sched.h>
+#include <net/inet_ecn.h>
+
+#define QUEUE_THRESHOLD 10000
+#define DQCOUNT_INVALID -1
+#define MAX_PROB  0xffffffff
+#define PIE_SCALE 8
+
+/* parameters used */
+struct pie_params {
+	psched_time_t target;	/* user specified target delay in pschedtime */
+	u32 tupdate;		/* timer frequency (in jiffies) */
+	u32 limit;		/* number of packets that can be enqueued */
+	u32 alpha;		/* alpha and beta are between -4 and 4 */
+	u32 beta;		/* and are used for shift relative to 1 */
+	bool ecn;		/* true if ecn is enabled */
+	bool bytemode;		/* to scale drop early prob based on pkt size */
+};
+
+/* variables used */
+struct pie_vars {
+	u32 prob;		/* probability but scaled by u32 limit. */
+	psched_time_t burst_time;
+	psched_time_t qdelay;
+	psched_time_t qdelay_old;
+	u64 dq_count;		/* measured in bytes */
+	psched_time_t dq_tstamp;	/* drain rate */
+	u32 avg_dq_rate;	/* bytes per pschedtime tick,scaled */
+	u32 qlen_old;		/* in bytes */
+};
+
+/* statistics gathering */
+struct pie_stats {
+	u32 packets_in;		/* total number of packets enqueued */
+	u32 dropped;		/* packets dropped due to pie_action */
+	u32 overlimit;		/* dropped due to lack of space in queue */
+	u32 maxq;		/* maximum queue size */
+	u32 ecn_mark;		/* packets marked with ECN */
+};
+
+/* private data for the Qdisc */
+struct pie_sched_data {
+	struct pie_params params;
+	struct pie_vars vars;
+	struct pie_stats stats;
+	struct timer_list adapt_timer;
+};
+
+static void pie_params_init(struct pie_params *params)
+{
+	params->alpha = 2;
+	params->beta = 20;
+	params->tupdate = usecs_to_jiffies(30 * USEC_PER_MSEC);	/* 30 ms */
+	params->limit = 1000;	/* default of 1000 packets */
+	params->target = PSCHED_NS2TICKS(20 * NSEC_PER_MSEC);	/* 20 ms */
+	params->ecn = false;
+	params->bytemode = false;
+}
+
+static void pie_vars_init(struct pie_vars *vars)
+{
+	vars->dq_count = DQCOUNT_INVALID;
+	vars->avg_dq_rate = 0;
+	/* default of 100 ms in pschedtime */
+	vars->burst_time = PSCHED_NS2TICKS(100 * NSEC_PER_MSEC);
+}
+
+static bool drop_early(struct Qdisc *sch, u32 packet_size)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	u32 rnd;
+	u32 local_prob = q->vars.prob;
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+
+	/* If there is still burst allowance left skip random early drop */
+	if (q->vars.burst_time > 0)
+		return false;
+
+	/* If current delay is less than half of target, and
+	 * if drop prob is low already, disable early_drop
+	 */
+	if ((q->vars.qdelay < q->params.target / 2)
+	    && (q->vars.prob < MAX_PROB / 5))
+		return false;
+
+	/* If we have fewer than 2 mtu-sized packets, disable drop_early,
+	 * similar to min_th in RED
+	 */
+	if (sch->qstats.backlog < 2 * mtu)
+		return false;
+
+	/* If bytemode is turned on, use packet size to compute new
+	 * probablity. Smaller packets will have lower drop prob in this case
+	 */
+	if (q->params.bytemode && packet_size <= mtu)
+		local_prob = (local_prob / mtu) * packet_size;
+	else
+		local_prob = q->vars.prob;
+
+	rnd = net_random();
+	if (rnd < local_prob)
+		return true;
+
+	return false;
+}
+
+static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	bool enqueue = false;
+
+	if (unlikely(qdisc_qlen(sch) >= sch->limit)) {
+		q->stats.overlimit++;
+		goto out;
+	}
+
+	if (!drop_early(sch, skb->len)) {
+		enqueue = true;
+	} else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) &&
+		   INET_ECN_set_ce(skb)) {
+		/* If packet is ecn capable, mark it if drop probability
+		 * is lower than 10%, else drop it.
+		 */
+		q->stats.ecn_mark++;
+		enqueue = true;
+	}
+
+	/* we can enqueue the packet */
+	if (enqueue) {
+		q->stats.packets_in++;
+		if (qdisc_qlen(sch) > q->stats.maxq)
+			q->stats.maxq = qdisc_qlen(sch);
+
+		return qdisc_enqueue_tail(skb, sch);
+	}
+
+out:
+	q->stats.dropped++;
+	return qdisc_drop(skb, sch);
+}
+
+static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = {
+	[TCA_PIE_TARGET] = {.type = NLA_U32},
+	[TCA_PIE_LIMIT] = {.type = NLA_U32},
+	[TCA_PIE_TUPDATE] = {.type = NLA_U32},
+	[TCA_PIE_ALPHA] = {.type = NLA_U32},
+	[TCA_PIE_BETA] = {.type = NLA_U32},
+	[TCA_PIE_ECN] = {.type = NLA_U32},
+	[TCA_PIE_BYTEMODE] = {.type = NLA_U32},
+};
+
+static int pie_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_PIE_MAX + 1];
+	unsigned int qlen;
+	int err;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy);
+	if (err < 0)
+		return err;
+
+	sch_tree_lock(sch);
+
+	/* convert from microseconds to pschedtime */
+	if (tb[TCA_PIE_TARGET]) {
+		/* target is in us */
+		u32 target = nla_get_u32(tb[TCA_PIE_TARGET]);
+
+		/* convert to pschedtime */
+		q->params.target = PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC);
+	}
+
+	/* tupdate is in jiffies */
+	if (tb[TCA_PIE_TUPDATE])
+		q->params.tupdate = usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE]));
+
+	if (tb[TCA_PIE_LIMIT]) {
+		u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]);
+
+		q->params.limit = limit;
+		sch->limit = limit;
+	}
+
+	if (tb[TCA_PIE_ALPHA])
+		q->params.alpha = nla_get_u32(tb[TCA_PIE_ALPHA]);
+
+	if (tb[TCA_PIE_BETA])
+		q->params.beta = nla_get_u32(tb[TCA_PIE_BETA]);
+
+	if (tb[TCA_PIE_ECN])
+		q->params.ecn = nla_get_u32(tb[TCA_PIE_ECN]);
+
+	if (tb[TCA_PIE_BYTEMODE])
+		q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]);
+
+	/* Drop excess packets if new limit is lower */
+	qlen = sch->q.qlen;
+	while (sch->q.qlen > sch->limit) {
+		struct sk_buff *skb = __skb_dequeue(&sch->q);
+
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_drop(skb, sch);
+	}
+	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
+{
+
+	struct pie_sched_data *q = qdisc_priv(sch);
+	int qlen = sch->qstats.backlog;	/* current queue size in bytes */
+
+	/* If current queue is about 10 packets or more and dq_count is unset
+	 * we have enough packets to calculate the drain rate. Save
+	 * current time as dq_tstamp and start measurement cycle.
+	 */
+	if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) {
+		q->vars.dq_tstamp = psched_get_time();
+		q->vars.dq_count = 0;
+	}
+
+	/* Calculate the average drain rate from this value.  If queue length
+	 * has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset
+	 * the dq_count to -1 as we don't have enough packets to calculate the
+	 * drain rate anymore The following if block is entered only when we
+	 * have a substantial queue built up (QUEUE_THRESHOLD bytes or more)
+	 * and we calculate the drain rate for the threshold here.  dq_count is
+	 * in bytes, time difference in psched_time, hence rate is in
+	 * bytes/psched_time.
+	 */
+	if (q->vars.dq_count != DQCOUNT_INVALID) {
+		q->vars.dq_count += skb->len;
+
+		if (q->vars.dq_count >= QUEUE_THRESHOLD) {
+			psched_time_t now = psched_get_time();
+			u32 dtime = now - q->vars.dq_tstamp;
+			u32 count = q->vars.dq_count << PIE_SCALE;
+
+			if (dtime == 0)
+				return;
+
+			count = count / dtime;
+
+			if (q->vars.avg_dq_rate == 0)
+				q->vars.avg_dq_rate = count;
+			else
+				q->vars.avg_dq_rate =
+				    (q->vars.avg_dq_rate -
+				     (q->vars.avg_dq_rate >> 3)) + (count >> 3);
+
+			/* If the queue has receded below the threshold, we hold
+			 * on to the last drain rate calculated, else we reset
+			 * dq_count to 0 to re-enter the if block when the next
+			 * packet is dequeued
+			 */
+			if (qlen < QUEUE_THRESHOLD)
+				q->vars.dq_count = DQCOUNT_INVALID;
+			else {
+				q->vars.dq_count = 0;
+				q->vars.dq_tstamp = psched_get_time();
+			}
+
+			if (q->vars.burst_time > 0) {
+				if (q->vars.burst_time > dtime)
+					q->vars.burst_time -= dtime;
+				else
+					q->vars.burst_time = 0;
+			}
+		}
+	}
+}
+
+static void calculate_probability(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	u32 qlen = sch->qstats.backlog;	/* queue size in bytes */
+	psched_time_t qdelay = 0;	/* in pschedtime */
+	psched_time_t qdelay_old = q->vars.qdelay;	/* in pschedtime */
+	s32 delta = 0;		/* determines the change in probability */
+	u32 oldprob;
+	u32 alpha, beta;
+	bool update_prob = true;
+
+	q->vars.qdelay_old = q->vars.qdelay;
+
+	if (q->vars.avg_dq_rate > 0)
+		qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate;
+	else
+		qdelay = 0;
+
+	/* If qdelay is zero and qlen is not, it means qlen is very small, less
+	 * than dequeue_rate, so we do not update probabilty in this round
+	 */
+	if (qdelay == 0 && qlen != 0)
+		update_prob = false;
+
+	/* Add ranges for alpha and beta, more aggressive for high dropping
+	 * mode and gentle steps for light dropping mode
+	 * In light dropping mode, take gentle steps; in medium dropping mode,
+	 * take medium steps; in high dropping mode, take big steps.
+	 */
+	if (q->vars.prob < MAX_PROB / 100) {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7;
+	} else if (q->vars.prob < MAX_PROB / 10) {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5;
+	} else {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+	}
+
+	/* alpha and beta should be between 0 and 32, in multiples of 1/16 */
+	delta += alpha * ((qdelay - q->params.target));
+	delta += beta * ((qdelay - qdelay_old));
+
+	oldprob = q->vars.prob;
+
+	/* to ensure we increase probability in steps of no more than 2% */
+	if (delta > (s32) (MAX_PROB / (100 / 2)) &&
+	    q->vars.prob >= MAX_PROB / 10)
+		delta = (MAX_PROB / 100) * 2;
+
+	/* Non-linear drop:
+	 * Tune drop probability to increase quickly for high delays(>= 250ms)
+	 * 250ms is derived through experiments and provides error protection
+	 */
+
+	if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC)))
+		delta += MAX_PROB / (100 / 2);
+
+	q->vars.prob += delta;
+
+	if (delta > 0) {
+		/* prevent overflow */
+		if (q->vars.prob < oldprob) {
+			q->vars.prob = MAX_PROB;
+			/* Prevent normalization error. If probability is at
+			 * maximum value already, we normalize it here, and
+			 * skip the check to do a non-linear drop in the next
+			 * section.
+			 */
+			update_prob = false;
+		}
+	} else {
+		/* prevent underflow */
+		if (q->vars.prob > oldprob)
+			q->vars.prob = 0;
+	}
+
+	/* Non-linear drop in probability: Reduce drop probability quickly if
+	 * delay is 0 for 2 consecutive Tupdate periods.
+	 */
+
+	if ((qdelay == 0) && (qdelay_old == 0) && update_prob)
+		q->vars.prob = (q->vars.prob * 98) / 100;
+
+	q->vars.qdelay = qdelay;
+	q->vars.qlen_old = qlen;
+
+	/* We restart the measurement cycle if the following conditions are met
+	 * 1. If the delay has been low for 2 consecutive Tupdate periods
+	 * 2. Calculated drop probability is zero
+	 * 3. We have atleast one estimate for the avg_dq_rate ie.,
+	 *    is a non-zero value
+	 */
+	if ((q->vars.qdelay < q->params.target / 2) &&
+	    (q->vars.qdelay_old < q->params.target / 2) &&
+	    (q->vars.prob == 0) &&
+	    (q->vars.avg_dq_rate > 0))
+		pie_vars_init(&q->vars);
+}
+
+static void pie_timer(unsigned long arg)
+{
+	struct Qdisc *sch = (struct Qdisc *)arg;
+	struct pie_sched_data *q = qdisc_priv(sch);
+	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+
+	spin_lock(root_lock);
+	calculate_probability(sch);
+
+	/* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */
+	if (q->params.tupdate)
+		mod_timer(&q->adapt_timer, jiffies + q->params.tupdate);
+	spin_unlock(root_lock);
+
+}
+
+static int pie_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+
+	pie_params_init(&q->params);
+	pie_vars_init(&q->vars);
+	sch->limit = q->params.limit;
+
+	setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch);
+	mod_timer(&q->adapt_timer, jiffies + HZ / 2);
+
+	if (opt) {
+		int err = pie_change(sch, opt);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int pie_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+
+	/* convert target from pschedtime to us */
+	if (nla_put_u32(skb, TCA_PIE_TARGET,
+			((u32) PSCHED_TICKS2NS(q->params.target)) /
+			NSEC_PER_USEC) ||
+	    nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) ||
+	    nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(q->params.tupdate)) ||
+	    nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) ||
+	    nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) ||
+	    nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) ||
+	    nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -1;
+
+}
+
+static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct tc_pie_xstats st = {
+		.prob		= q->vars.prob,
+		.delay		= ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) /
+				   NSEC_PER_USEC,
+		/* unscale and return dq_rate in bytes per sec */
+		.avg_dq_rate	= q->vars.avg_dq_rate *
+				  (PSCHED_TICKS_PER_SEC) >> PIE_SCALE,
+		.packets_in	= q->stats.packets_in,
+		.overlimit	= q->stats.overlimit,
+		.maxq		= q->stats.maxq,
+		.dropped	= q->stats.dropped,
+		.ecn_mark	= q->stats.ecn_mark,
+	};
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+	skb = __qdisc_dequeue_head(sch, &sch->q);
+
+	if (!skb)
+		return NULL;
+
+	pie_process_dequeue(sch, skb);
+	return skb;
+}
+
+static void pie_reset(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	qdisc_reset_queue(sch);
+	pie_vars_init(&q->vars);
+}
+
+static void pie_destroy(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	q->params.tupdate = 0;
+	del_timer_sync(&q->adapt_timer);
+}
+
+static struct Qdisc_ops pie_qdisc_ops __read_mostly = {
+	.id = "pie",
+	.priv_size	= sizeof(struct pie_sched_data),
+	.enqueue	= pie_qdisc_enqueue,
+	.dequeue	= pie_qdisc_dequeue,
+	.peek		= qdisc_peek_dequeued,
+	.init		= pie_init,
+	.destroy	= pie_destroy,
+	.reset		= pie_reset,
+	.change		= pie_change,
+	.dump		= pie_dump,
+	.dump_stats	= pie_dump_stats,
+	.owner		= THIS_MODULE,
+};
+
+static int __init pie_module_init(void)
+{
+	return register_qdisc(&pie_qdisc_ops);
+}
+
+static void __exit pie_module_exit(void)
+{
+	unregister_qdisc(&pie_qdisc_ops);
+}
+
+module_init(pie_module_init);
+module_exit(pie_module_exit);
+
+MODULE_DESCRIPTION("Proportional Integral controller Enhanced (PIE) scheduler");
+MODULE_AUTHOR("Vijay Subramanian");
+MODULE_AUTHOR("Mythili Prabhu");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 43d4be9cb55f3bac5253e9289996fd9d735531db Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 13 Dec 2013 15:22:18 +0100
Subject: openvswitch: Allow user space to announce ability to accept unaligned
 Netlink messages

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Reviewed-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/uapi/linux/openvswitch.h |  4 ++++
 net/openvswitch/datapath.c       | 14 ++++++++++++++
 net/openvswitch/datapath.h       |  2 ++
 3 files changed, 20 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index d120f9fe0017..07ef2c3e21fa 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -75,6 +75,7 @@ enum ovs_datapath_attr {
 	OVS_DP_ATTR_UPCALL_PID,		/* Netlink PID to receive upcalls */
 	OVS_DP_ATTR_STATS,		/* struct ovs_dp_stats */
 	OVS_DP_ATTR_MEGAFLOW_STATS,	/* struct ovs_dp_megaflow_stats */
+	OVS_DP_ATTR_USER_FEATURES,	/* OVS_DP_F_*  */
 	__OVS_DP_ATTR_MAX
 };
 
@@ -106,6 +107,9 @@ struct ovs_vport_stats {
 	__u64   tx_dropped;		/* no space available in linux  */
 };
 
+/* Allow last Netlink attribute to be unaligned */
+#define OVS_DP_F_UNALIGNED	(1 << 0)
+
 /* Fixed logical ports. */
 #define OVSP_LOCAL      ((__u32)0)
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 50d7782d8d7c..6a9b0cb8a1db 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1040,6 +1040,7 @@ static const struct genl_ops dp_flow_genl_ops[] = {
 static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
 	[OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
 	[OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
 };
 
 static struct genl_family dp_datapath_genl_family = {
@@ -1098,6 +1099,9 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 			&dp_megaflow_stats))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features))
+		goto nla_put_failure;
+
 	return genlmsg_end(skb, ovs_header);
 
 nla_put_failure:
@@ -1144,6 +1148,12 @@ static struct datapath *lookup_datapath(struct net *net,
 	return dp ? dp : ERR_PTR(-ENODEV);
 }
 
+static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
+{
+	if (a[OVS_DP_ATTR_USER_FEATURES])
+		dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
+}
+
 static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
@@ -1202,6 +1212,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	parms.port_no = OVSP_LOCAL;
 	parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]);
 
+	ovs_dp_change(dp, a);
+
 	vport = new_vport(&parms);
 	if (IS_ERR(vport)) {
 		err = PTR_ERR(vport);
@@ -1305,6 +1317,8 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	if (IS_ERR(dp))
 		goto unlock;
 
+	ovs_dp_change(dp, info->attrs);
+
 	reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index ba13be4a680f..62619a4ee649 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -88,6 +88,8 @@ struct datapath {
 	/* Network namespace ref. */
 	struct net *net;
 #endif
+
+	u32 user_features;
 };
 
 /**
-- 
cgit v1.2.3


From 44da5ae5fbea4686f667dc854e5ea16814e44c59 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 13 Dec 2013 15:22:19 +0100
Subject: openvswitch: Drop user features if old user space attempted to create
 datapath

Drop user features if an outdated user space instance that does not
understand the concept of user_features attempted to create a new
datapath.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/uapi/linux/openvswitch.h | 10 +++++++++-
 net/openvswitch/datapath.c       | 21 +++++++++++++++++++++
 2 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 07ef2c3e21fa..970553cbbc8e 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -40,7 +40,15 @@ struct ovs_header {
 
 #define OVS_DATAPATH_FAMILY  "ovs_datapath"
 #define OVS_DATAPATH_MCGROUP "ovs_datapath"
-#define OVS_DATAPATH_VERSION 0x1
+
+/* V2:
+ *   - API users are expected to provide OVS_DP_ATTR_USER_FEATURES
+ *     when creating the datapath.
+ */
+#define OVS_DATAPATH_VERSION 2
+
+/* First OVS datapath version to support features */
+#define OVS_DP_VER_FEATURES 2
 
 enum ovs_datapath_cmd {
 	OVS_DP_CMD_UNSPEC,
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6a9b0cb8a1db..497b2fd36df4 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1148,6 +1148,18 @@ static struct datapath *lookup_datapath(struct net *net,
 	return dp ? dp : ERR_PTR(-ENODEV);
 }
 
+static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info)
+{
+	struct datapath *dp;
+
+	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+	if (!dp)
+		return;
+
+	WARN(dp->user_features, "Dropping previously announced user features\n");
+	dp->user_features = 0;
+}
+
 static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
 {
 	if (a[OVS_DP_ATTR_USER_FEATURES])
@@ -1220,6 +1232,15 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		if (err == -EBUSY)
 			err = -EEXIST;
 
+		if (err == -EEXIST) {
+			/* An outdated user space instance that does not understand
+			 * the concept of user_features has attempted to create a new
+			 * datapath and is likely to reuse it. Drop all user features.
+			 */
+			if (info->genlhdr->version < OVS_DP_VER_FEATURES)
+				ovs_dp_reset_user_features(skb, info);
+		}
+
 		goto err_destroy_ports_array;
 	}
 
-- 
cgit v1.2.3


From 1d49144c0aaa61be4e3ccbef9cc5c40b0ec5f2fe Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Fri, 3 Jan 2014 12:16:16 +0000
Subject: netfilter: nf_tables: add "inet" table for IPv4/IPv6

This patch adds a new table family and a new filter chain that you can
use to attach IPv4 and IPv6 rules. This should help to simplify
rule-set maintainance in dual-stack setups.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_ipv4.h |  2 +
 include/net/netfilter/nf_tables_ipv6.h |  2 +
 include/net/netns/nftables.h           |  1 +
 include/uapi/linux/netfilter.h         |  1 +
 net/ipv4/netfilter/nf_tables_ipv4.c    |  3 +-
 net/ipv6/netfilter/nf_tables_ipv6.c    |  3 +-
 net/netfilter/Kconfig                  |  8 +++
 net/netfilter/Makefile                 |  1 +
 net/netfilter/nf_tables_inet.c         | 97 ++++++++++++++++++++++++++++++++++
 9 files changed, 116 insertions(+), 2 deletions(-)
 create mode 100644 net/netfilter/nf_tables_inet.c

(limited to 'include/uapi')

diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index 1be1c2c197ee..f7b3a669aad3 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -20,4 +20,6 @@ nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
 	pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
 }
 
+extern struct nft_af_info nft_af_ipv4;
+
 #endif
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index 4a9b88a65963..3d8ae489be0d 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -27,4 +27,6 @@ nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
 	return 0;
 }
 
+extern struct nft_af_info nft_af_ipv6;
+
 #endif
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 15d056d534e3..26a394cb91a8 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -10,6 +10,7 @@ struct netns_nftables {
 	struct list_head	commit_list;
 	struct nft_af_info	*ipv4;
 	struct nft_af_info	*ipv6;
+	struct nft_af_info	*inet;
 	struct nft_af_info	*arp;
 	struct nft_af_info	*bridge;
 	u8			gencursor;
diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h
index f7dc0ebeeba5..ef1b1f88ca18 100644
--- a/include/uapi/linux/netfilter.h
+++ b/include/uapi/linux/netfilter.h
@@ -53,6 +53,7 @@ enum nf_inet_hooks {
 
 enum {
 	NFPROTO_UNSPEC =  0,
+	NFPROTO_INET   =  1,
 	NFPROTO_IPV4   =  2,
 	NFPROTO_ARP    =  3,
 	NFPROTO_BRIDGE =  7,
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index 177c3bceb7ca..da927dc9f636 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -48,7 +48,7 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
 	return nft_do_chain_ipv4(ops, skb, in, out, okfn);
 }
 
-static struct nft_af_info nft_af_ipv4 __read_mostly = {
+struct nft_af_info nft_af_ipv4 __read_mostly = {
 	.family		= NFPROTO_IPV4,
 	.nhooks		= NF_INET_NUMHOOKS,
 	.owner		= THIS_MODULE,
@@ -61,6 +61,7 @@ static struct nft_af_info nft_af_ipv4 __read_mostly = {
 		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv4,
 	},
 };
+EXPORT_SYMBOL_GPL(nft_af_ipv4);
 
 static int nf_tables_ipv4_init_net(struct net *net)
 {
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index 642280e44b65..025e7f4e8ac5 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -47,7 +47,7 @@ static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
 	return nft_do_chain_ipv6(ops, skb, in, out, okfn);
 }
 
-static struct nft_af_info nft_af_ipv6 __read_mostly = {
+struct nft_af_info nft_af_ipv6 __read_mostly = {
 	.family		= NFPROTO_IPV6,
 	.nhooks		= NF_INET_NUMHOOKS,
 	.owner		= THIS_MODULE,
@@ -60,6 +60,7 @@ static struct nft_af_info nft_af_ipv6 __read_mostly = {
 		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv6,
 	},
 };
+EXPORT_SYMBOL_GPL(nft_af_ipv6);
 
 static int nf_tables_ipv6_init_net(struct net *net)
 {
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c3b3b26c4c4e..37d2092705a7 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -428,6 +428,14 @@ config NF_TABLES
 
 	  To compile it as a module, choose M here.
 
+config NF_TABLES_INET
+	depends on NF_TABLES
+	select NF_TABLES_IPV4
+	select NF_TABLES_IPV6
+	tristate "Netfilter nf_tables mixed IPv4/IPv6 tables support"
+	help
+	  This option enables support for a mixed IPv4/IPv6 "inet" table.
+
 config NFT_EXTHDR
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables IPv6 exthdr module"
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 78b4e1c9c595..74c066109334 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -70,6 +70,7 @@ nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
 nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
 
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
+obj-$(CONFIG_NF_TABLES_INET)	+= nf_tables_inet.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_inet.c b/net/netfilter/nf_tables_inet.c
new file mode 100644
index 000000000000..ac0edcb549de
--- /dev/null
+++ b/net/netfilter/nf_tables_inet.c
@@ -0,0 +1,97 @@
+/*
+ * 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/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 void nft_inet_hook_ops_init(struct nf_hook_ops *ops, unsigned int n)
+{
+	struct nft_af_info *afi;
+
+	if (n == 1)
+		afi = &nft_af_ipv4;
+	else
+		afi = &nft_af_ipv6;
+
+	ops->pf = afi->family;
+	if (afi->hooks[ops->hooknum])
+		ops->hook = afi->hooks[ops->hooknum];
+}
+
+static struct nft_af_info nft_af_inet __read_mostly = {
+	.family		= NFPROTO_INET,
+	.nhooks		= NF_INET_NUMHOOKS,
+	.owner		= THIS_MODULE,
+	.nops		= 2,
+	.hook_ops_init	= nft_inet_hook_ops_init,
+};
+
+static int __net_init nf_tables_inet_init_net(struct net *net)
+{
+	net->nft.inet = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
+	if (net->nft.inet == NULL)
+		return -ENOMEM;
+	memcpy(net->nft.inet, &nft_af_inet, sizeof(nft_af_inet));
+
+	if (nft_register_afinfo(net, net->nft.inet) < 0)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(net->nft.inet);
+	return -ENOMEM;
+}
+
+static void __net_exit nf_tables_inet_exit_net(struct net *net)
+{
+	nft_unregister_afinfo(net->nft.inet);
+	kfree(net->nft.inet);
+}
+
+static struct pernet_operations nf_tables_inet_net_ops = {
+	.init	= nf_tables_inet_init_net,
+	.exit	= nf_tables_inet_exit_net,
+};
+
+static struct nf_chain_type filter_inet = {
+	.family		= NFPROTO_INET,
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.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),
+};
+
+static int __init nf_tables_inet_init(void)
+{
+	nft_register_chain_type(&filter_inet);
+	return register_pernet_subsys(&nf_tables_inet_net_ops);
+}
+
+static void __exit nf_tables_inet_exit(void)
+{
+	unregister_pernet_subsys(&nf_tables_inet_net_ops);
+	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_FAMILY(1);
-- 
cgit v1.2.3


From 124edfa9e0451e97d621cd2796a44ff499e21036 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Fri, 3 Jan 2014 12:16:17 +0000
Subject: netfilter: nf_tables: add nfproto support to meta expression

Needed by multi-family tables to distinguish IPv4 and IPv6 packets.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nft_meta.c                 | 4 ++++
 2 files changed, 6 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index aa86a15293e1..10afbfc0e66a 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -531,6 +531,7 @@ enum nft_exthdr_attributes {
  * @NFT_META_NFTRACE: packet nftrace bit
  * @NFT_META_RTCLASSID: realm value of packet's route (skb->dst->tclassid)
  * @NFT_META_SECMARK: packet secmark (skb->secmark)
+ * @NFT_META_NFPROTO: netfilter protocol
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -548,6 +549,7 @@ enum nft_meta_keys {
 	NFT_META_NFTRACE,
 	NFT_META_RTCLASSID,
 	NFT_META_SECMARK,
+	NFT_META_NFPROTO,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 1ceaaa6dfe72..999d04688433 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -43,6 +43,9 @@ static void nft_meta_get_eval(const struct nft_expr *expr,
 	case NFT_META_PROTOCOL:
 		*(__be16 *)dest->data = skb->protocol;
 		break;
+	case NFT_META_NFPROTO:
+		dest->data[0] = pkt->ops->pf;
+		break;
 	case NFT_META_PRIORITY:
 		dest->data[0] = skb->priority;
 		break;
@@ -181,6 +184,7 @@ static int nft_meta_init_validate_get(uint32_t key)
 	switch (key) {
 	case NFT_META_LEN:
 	case NFT_META_PROTOCOL:
+	case NFT_META_NFPROTO:
 	case NFT_META_PRIORITY:
 	case NFT_META_MARK:
 	case NFT_META_IIF:
-- 
cgit v1.2.3


From 4566bf27069b7780e453cffb24ea5f5323059885 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Fri, 3 Jan 2014 12:16:18 +0000
Subject: netfilter: nft_meta: add l4proto support

For L3-proto independant rules we need to get at the L4 protocol value
directly. Add it to the nft_pktinfo struct and use the meta expression
to retrieve it.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        | 1 +
 include/net/netfilter/nf_tables_ipv4.h   | 3 ++-
 include/net/netfilter/nf_tables_ipv6.h   | 1 +
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nft_meta.c                 | 4 ++++
 5 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index f066f252e5e5..5d2b703efe1c 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -16,6 +16,7 @@ struct nft_pktinfo {
 	const struct nf_hook_ops	*ops;
 	u8				nhoff;
 	u8				thoff;
+	u8				tprot;
 	/* for x_tables compatibility */
 	struct xt_action_param		xt;
 };
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index f7b3a669aad3..cba143fbd2e4 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -15,8 +15,9 @@ nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
 
 	nft_set_pktinfo(pkt, ops, skb, in, out);
 
-	pkt->xt.thoff = ip_hdrlen(pkt->skb);
 	ip = ip_hdr(pkt->skb);
+	pkt->tprot = ip->protocol;
+	pkt->xt.thoff = ip_hdrlen(pkt->skb);
 	pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
 }
 
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index 3d8ae489be0d..74d976137658 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -21,6 +21,7 @@ nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
 	if (protohdr < 0)
 		return -1;
 
+	pkt->tprot = protohdr;
 	pkt->xt.thoff = thoff;
 	pkt->xt.fragoff = frag_off;
 
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 10afbfc0e66a..448593c07120 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -532,6 +532,7 @@ enum nft_exthdr_attributes {
  * @NFT_META_RTCLASSID: realm value of packet's route (skb->dst->tclassid)
  * @NFT_META_SECMARK: packet secmark (skb->secmark)
  * @NFT_META_NFPROTO: netfilter protocol
+ * @NFT_META_L4PROTO: layer 4 protocol number
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -550,6 +551,7 @@ enum nft_meta_keys {
 	NFT_META_RTCLASSID,
 	NFT_META_SECMARK,
 	NFT_META_NFPROTO,
+	NFT_META_L4PROTO,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 999d04688433..b43975a43309 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -46,6 +46,9 @@ static void nft_meta_get_eval(const struct nft_expr *expr,
 	case NFT_META_NFPROTO:
 		dest->data[0] = pkt->ops->pf;
 		break;
+	case NFT_META_L4PROTO:
+		dest->data[0] = pkt->tprot;
+		break;
 	case NFT_META_PRIORITY:
 		dest->data[0] = skb->priority;
 		break;
@@ -185,6 +188,7 @@ static int nft_meta_init_validate_get(uint32_t key)
 	case NFT_META_LEN:
 	case NFT_META_PROTOCOL:
 	case NFT_META_NFPROTO:
+	case NFT_META_L4PROTO:
 	case NFT_META_PRIORITY:
 	case NFT_META_MARK:
 	case NFT_META_IIF:
-- 
cgit v1.2.3


From c4ede3d3821a732120fd671846c2606a1eb4e8b3 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Tue, 7 Jan 2014 16:43:54 +0100
Subject: netfilter: nft_ct: Add support to set the connmark

This patch adds kernel support for setting properties of tracked
connections. Currently, only connmark is supported. One use-case
for this feature is to provide the same functionality as
-j CONNMARK --save-mark in iptables.

Some restructuring was needed to implement the set op. The new
structure follows that of nft_meta.

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |   2 +
 net/netfilter/nft_ct.c                   | 164 +++++++++++++++++++++++++------
 2 files changed, 136 insertions(+), 30 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 448593c07120..83c985a6170b 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -609,12 +609,14 @@ enum nft_ct_keys {
  * @NFTA_CT_DREG: destination register (NLA_U32)
  * @NFTA_CT_KEY: conntrack data item to load (NLA_U32: nft_ct_keys)
  * @NFTA_CT_DIRECTION: direction in case of directional keys (NLA_U8)
+ * @NFTA_CT_SREG: source register (NLA_U32)
  */
 enum nft_ct_attributes {
 	NFTA_CT_UNSPEC,
 	NFTA_CT_DREG,
 	NFTA_CT_KEY,
 	NFTA_CT_DIRECTION,
+	NFTA_CT_SREG,
 	__NFTA_CT_MAX
 };
 #define NFTA_CT_MAX		(__NFTA_CT_MAX - 1)
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 3727a321c9a7..c7c12858e113 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -18,17 +18,21 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_ecache.h>
 
 struct nft_ct {
 	enum nft_ct_keys	key:8;
 	enum ip_conntrack_dir	dir:8;
-	enum nft_registers	dreg:8;
+	union{
+		enum nft_registers	dreg:8;
+		enum nft_registers	sreg:8;
+	};
 	uint8_t			family;
 };
 
-static void nft_ct_eval(const struct nft_expr *expr,
-			struct nft_data data[NFT_REG_MAX + 1],
-			const struct nft_pktinfo *pkt)
+static void nft_ct_get_eval(const struct nft_expr *expr,
+			    struct nft_data data[NFT_REG_MAX + 1],
+			    const struct nft_pktinfo *pkt)
 {
 	const struct nft_ct *priv = nft_expr_priv(expr);
 	struct nft_data *dest = &data[priv->dreg];
@@ -123,10 +127,37 @@ err:
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
 }
 
+static void nft_ct_set_eval(const struct nft_expr *expr,
+			    struct nft_data data[NFT_REG_MAX + 1],
+			    const struct nft_pktinfo *pkt)
+{
+	const struct nft_ct *priv = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	u32 value = data[priv->sreg].data[0];
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct == NULL)
+		return;
+
+	switch (priv->key) {
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	case NFT_CT_MARK:
+		if (ct->mark != value) {
+			ct->mark = value;
+			nf_conntrack_event_cache(IPCT_MARK, ct);
+		}
+		break;
+#endif
+	}
+}
+
 static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = {
 	[NFTA_CT_DREG]		= { .type = NLA_U32 },
 	[NFTA_CT_KEY]		= { .type = NLA_U32 },
 	[NFTA_CT_DIRECTION]	= { .type = NLA_U8 },
+	[NFTA_CT_SREG]		= { .type = NLA_U32 },
 };
 
 static int nft_ct_l3proto_try_module_get(uint8_t family)
@@ -162,18 +193,11 @@ static void nft_ct_l3proto_module_put(uint8_t family)
 		nf_ct_l3proto_module_put(family);
 }
 
-static int nft_ct_init(const struct nft_ctx *ctx,
-		       const struct nft_expr *expr,
-		       const struct nlattr * const tb[])
+static int nft_ct_init_validate_get(const struct nft_expr *expr,
+				    const struct nlattr * const tb[])
 {
 	struct nft_ct *priv = nft_expr_priv(expr);
-	int err;
 
-	if (tb[NFTA_CT_DREG] == NULL ||
-	    tb[NFTA_CT_KEY] == NULL)
-		return -EINVAL;
-
-	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
 	if (tb[NFTA_CT_DIRECTION] != NULL) {
 		priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]);
 		switch (priv->dir) {
@@ -212,24 +236,62 @@ static int nft_ct_init(const struct nft_ctx *ctx,
 		return -EOPNOTSUPP;
 	}
 
+	return 0;
+}
+
+static int nft_ct_init_validate_set(uint32_t key)
+{
+	switch (key) {
+	case NFT_CT_MARK:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int nft_ct_init(const struct nft_ctx *ctx,
+		       const struct nft_expr *expr,
+		       const struct nlattr * const tb[])
+{
+	struct nft_ct *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
+
+	if (tb[NFTA_CT_DREG]) {
+		err = nft_ct_init_validate_get(expr, tb);
+		if (err < 0)
+			return err;
+
+		priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG]));
+		err = nft_validate_output_register(priv->dreg);
+		if (err < 0)
+			return err;
+
+		err = nft_validate_data_load(ctx, priv->dreg, NULL,
+					     NFT_DATA_VALUE);
+		if (err < 0)
+			return err;
+	} else {
+		err = nft_ct_init_validate_set(priv->key);
+		if (err < 0)
+			return err;
+
+		priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG]));
+		err = nft_validate_input_register(priv->sreg);
+		if (err < 0)
+			return err;
+	}
+
 	err = nft_ct_l3proto_try_module_get(ctx->afi->family);
 	if (err < 0)
 		return err;
-	priv->family = ctx->afi->family;
 
-	priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG]));
-	err = nft_validate_output_register(priv->dreg);
-	if (err < 0)
-		goto err1;
+	priv->family = ctx->afi->family;
 
-	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
-	if (err < 0)
-		goto err1;
 	return 0;
-
-err1:
-	nft_ct_l3proto_module_put(ctx->afi->family);
-	return err;
 }
 
 static void nft_ct_destroy(const struct nft_expr *expr)
@@ -239,7 +301,7 @@ static void nft_ct_destroy(const struct nft_expr *expr)
 	nft_ct_l3proto_module_put(priv->family);
 }
 
-static int nft_ct_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_ct *priv = nft_expr_priv(expr);
 
@@ -255,19 +317,61 @@ nla_put_failure:
 	return -1;
 }
 
+static int nft_ct_set_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_ct *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_CT_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
 static struct nft_expr_type nft_ct_type;
-static const struct nft_expr_ops nft_ct_ops = {
+static const struct nft_expr_ops nft_ct_get_ops = {
 	.type		= &nft_ct_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
-	.eval		= nft_ct_eval,
+	.eval		= nft_ct_get_eval,
 	.init		= nft_ct_init,
 	.destroy	= nft_ct_destroy,
-	.dump		= nft_ct_dump,
+	.dump		= nft_ct_get_dump,
 };
 
+static const struct nft_expr_ops nft_ct_set_ops = {
+	.type		= &nft_ct_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
+	.eval		= nft_ct_set_eval,
+	.init		= nft_ct_init,
+	.destroy	= nft_ct_destroy,
+	.dump		= nft_ct_set_dump,
+};
+
+static const struct nft_expr_ops *
+nft_ct_select_ops(const struct nft_ctx *ctx,
+		    const struct nlattr * const tb[])
+{
+	if (tb[NFTA_CT_KEY] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_CT_DREG] && tb[NFTA_CT_SREG])
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_CT_DREG])
+		return &nft_ct_get_ops;
+
+	if (tb[NFTA_CT_SREG])
+		return &nft_ct_set_ops;
+
+	return ERR_PTR(-EINVAL);
+}
+
 static struct nft_expr_type nft_ct_type __read_mostly = {
 	.name		= "ct",
-	.ops		= &nft_ct_ops,
+	.select_ops	= &nft_ct_select_ops,
 	.policy		= nft_ct_policy,
 	.maxattr	= NFTA_CT_MAX,
 	.owner		= THIS_MODULE,
-- 
cgit v1.2.3


From 74f77a6b2b1c98d3f14364dccdd2353b99ecfeda Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 6 Jan 2014 10:17:08 +0000
Subject: netfilter: introduce l2tp match extension

Introduce an xtables add-on for matching L2TP packets. Supports L2TPv2
and L2TPv3 over IPv4 and IPv6. As well as filtering on L2TP tunnel-id
and session-id, the filtering decision can also include the L2TP
packet type (control or data), protocol version (2 or 3) and
encapsulation type (UDP or IP).

The most common use for this will likely be to filter L2TP data
packets of individual L2TP tunnels or sessions. While a u32 match can
be used, the L2TP protocol headers are such that field offsets differ
depending on bits set in the header, making rules for matching generic
L2TP connections cumbersome. This match extension takes care of all
that.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/Kbuild    |   1 +
 include/uapi/linux/netfilter/xt_l2tp.h |  27 +++
 net/netfilter/Kconfig                  |  10 +
 net/netfilter/Makefile                 |   1 +
 net/netfilter/xt_l2tp.c                | 354 +++++++++++++++++++++++++++++++++
 5 files changed, 393 insertions(+)
 create mode 100644 include/uapi/linux/netfilter/xt_l2tp.h
 create mode 100644 net/netfilter/xt_l2tp.c

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 2344f5a319fc..1d973d2ba417 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -58,6 +58,7 @@ header-y += xt_helper.h
 header-y += xt_ipcomp.h
 header-y += xt_iprange.h
 header-y += xt_ipvs.h
+header-y += xt_l2tp.h
 header-y += xt_length.h
 header-y += xt_limit.h
 header-y += xt_mac.h
diff --git a/include/uapi/linux/netfilter/xt_l2tp.h b/include/uapi/linux/netfilter/xt_l2tp.h
new file mode 100644
index 000000000000..7dccfa0acbfa
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_l2tp.h
@@ -0,0 +1,27 @@
+#ifndef _LINUX_NETFILTER_XT_L2TP_H
+#define _LINUX_NETFILTER_XT_L2TP_H
+
+#include <linux/types.h>
+
+enum xt_l2tp_type {
+	XT_L2TP_TYPE_CONTROL,
+	XT_L2TP_TYPE_DATA,
+};
+
+/* L2TP matching stuff */
+struct xt_l2tp_info {
+	__u32 tid;			/* tunnel id */
+	__u32 sid;			/* session id */
+	__u8 version;			/* L2TP protocol version */
+	__u8 type;			/* L2TP packet type */
+	__u8 flags;			/* which fields to match */
+};
+
+enum {
+	XT_L2TP_TID	= (1 << 0),	/* match L2TP tunnel id */
+	XT_L2TP_SID	= (1 << 1),	/* match L2TP session id */
+	XT_L2TP_VERSION	= (1 << 2),	/* match L2TP protocol version */
+	XT_L2TP_TYPE	= (1 << 3),	/* match L2TP packet type */
+};
+
+#endif /* _LINUX_NETFILTER_XT_L2TP_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c3b3b26c4c4e..a1be47be0ad7 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -1131,6 +1131,16 @@ config NETFILTER_XT_MATCH_IPVS
 
 	  If unsure, say N.
 
+config NETFILTER_XT_MATCH_L2TP
+	tristate '"l2tp" match support'
+	depends on NETFILTER_ADVANCED
+	default L2TP
+	---help---
+	This option adds an "L2TP" match, which allows you to match against
+	L2TP protocol header fields.
+
+	To compile it as a module, choose M here. If unsure, say N.
+
 config NETFILTER_XT_MATCH_LENGTH
 	tristate '"length" match support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 78b4e1c9c595..b8bc5b85c728 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -137,6 +137,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPCOMP) += xt_ipcomp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_L2TP) += xt_l2tp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
diff --git a/net/netfilter/xt_l2tp.c b/net/netfilter/xt_l2tp.c
new file mode 100644
index 000000000000..8aee572771f2
--- /dev/null
+++ b/net/netfilter/xt_l2tp.c
@@ -0,0 +1,354 @@
+/* Kernel module to match L2TP header parameters. */
+
+/* (C) 2013      James Chapman <jchapman@katalix.com>
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/if_ether.h>
+#include <net/ip.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+#include <linux/l2tp.h>
+
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_tcpudp.h>
+#include <linux/netfilter/xt_l2tp.h>
+
+/* L2TP header masks */
+#define L2TP_HDR_T_BIT	0x8000
+#define L2TP_HDR_L_BIT	0x4000
+#define L2TP_HDR_VER	0x000f
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("Xtables: L2TP header match");
+MODULE_ALIAS("ipt_l2tp");
+MODULE_ALIAS("ip6t_l2tp");
+
+/* The L2TP fields that can be matched */
+struct l2tp_data {
+	u32 tid;
+	u32 sid;
+	u8 type;
+	u8 version;
+};
+
+union l2tp_val {
+	__be16 val16[2];
+	__be32 val32;
+};
+
+static bool l2tp_match(const struct xt_l2tp_info *info, struct l2tp_data *data)
+{
+	if ((info->flags & XT_L2TP_TYPE) && (info->type != data->type))
+		return false;
+
+	if ((info->flags & XT_L2TP_VERSION) && (info->version != data->version))
+		return false;
+
+	/* Check tid only for L2TPv3 control or any L2TPv2 packets */
+	if ((info->flags & XT_L2TP_TID) &&
+	    ((data->type == XT_L2TP_TYPE_CONTROL) || (data->version == 2)) &&
+	    (info->tid != data->tid))
+		return false;
+
+	/* Check sid only for L2TP data packets */
+	if ((info->flags & XT_L2TP_SID) && (data->type == XT_L2TP_TYPE_DATA) &&
+	    (info->sid != data->sid))
+		return false;
+
+	return true;
+}
+
+/* Parse L2TP header fields when UDP encapsulation is used. Handles
+ * L2TPv2 and L2TPv3. Note the L2TPv3 control and data packets have a
+ * different format. See
+ * RFC2661, Section 3.1, L2TPv2 Header Format
+ * RFC3931, Section 3.2.1, L2TPv3 Control Message Header
+ * RFC3931, Section 3.2.2, L2TPv3 Data Message Header
+ * RFC3931, Section 4.1.2.1, L2TPv3 Session Header over UDP
+ */
+static bool l2tp_udp_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	int uhlen = sizeof(struct udphdr);
+	int offs = thoff + uhlen;
+	union l2tp_val *lh;
+	union l2tp_val lhbuf;
+	u16 flags;
+	struct l2tp_data data = { 0, };
+
+	if (par->fragoff != 0)
+		return false;
+
+	/* Extract L2TP header fields. The flags in the first 16 bits
+	 * tell us where the other fields are.
+	 */
+	lh = skb_header_pointer(skb, offs, 2, &lhbuf);
+	if (lh == NULL)
+		return false;
+
+	flags = ntohs(lh->val16[0]);
+	if (flags & L2TP_HDR_T_BIT)
+		data.type = XT_L2TP_TYPE_CONTROL;
+	else
+		data.type = XT_L2TP_TYPE_DATA;
+	data.version = (u8) flags & L2TP_HDR_VER;
+
+	/* Now extract the L2TP tid/sid. These are in different places
+	 * for L2TPv2 (rfc2661) and L2TPv3 (rfc3931). For L2TPv2, we
+	 * must also check to see if the length field is present,
+	 * since this affects the offsets into the packet of the
+	 * tid/sid fields.
+	 */
+	if (data.version == 3) {
+		lh = skb_header_pointer(skb, offs + 4, 4, &lhbuf);
+		if (lh == NULL)
+			return false;
+		if (data.type == XT_L2TP_TYPE_CONTROL)
+			data.tid = ntohl(lh->val32);
+		else
+			data.sid = ntohl(lh->val32);
+	} else if (data.version == 2) {
+		if (flags & L2TP_HDR_L_BIT)
+			offs += 2;
+		lh = skb_header_pointer(skb, offs + 2, 4, &lhbuf);
+		if (lh == NULL)
+			return false;
+		data.tid = (u32) ntohs(lh->val16[0]);
+		data.sid = (u32) ntohs(lh->val16[1]);
+	} else
+		return false;
+
+	return l2tp_match(info, &data);
+}
+
+/* Parse L2TP header fields for IP encapsulation (no UDP header).
+ * L2TPv3 data packets have a different form with IP encap. See
+ * RC3931, Section 4.1.1.1, L2TPv3 Session Header over IP.
+ * RC3931, Section 4.1.1.2, L2TPv3 Control and Data Traffic over IP.
+ */
+static bool l2tp_ip_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	union l2tp_val *lh;
+	union l2tp_val lhbuf;
+	struct l2tp_data data = { 0, };
+
+	/* For IP encap, the L2TP sid is the first 32-bits. */
+	lh = skb_header_pointer(skb, thoff, sizeof(lhbuf), &lhbuf);
+	if (lh == NULL)
+		return false;
+	if (lh->val32 == 0) {
+		/* Must be a control packet. The L2TP tid is further
+		 * into the packet.
+		 */
+		data.type = XT_L2TP_TYPE_CONTROL;
+		lh = skb_header_pointer(skb, thoff + 8, sizeof(lhbuf),
+					&lhbuf);
+		if (lh == NULL)
+			return false;
+		data.tid = ntohl(lh->val32);
+	} else {
+		data.sid = ntohl(lh->val32);
+		data.type = XT_L2TP_TYPE_DATA;
+	}
+
+	data.version = 3;
+
+	return l2tp_match(info, &data);
+}
+
+static bool l2tp_mt4(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	u8 ipproto = iph->protocol;
+
+	/* l2tp_mt_check4 already restricts the transport protocol */
+	switch (ipproto) {
+	case IPPROTO_UDP:
+		return l2tp_udp_mt(skb, par, par->thoff);
+	case IPPROTO_L2TP:
+		return l2tp_ip_mt(skb, par, par->thoff);
+	}
+
+	return false;
+}
+
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
+static bool l2tp_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	unsigned int thoff = 0;
+	unsigned short fragoff = 0;
+	int ipproto;
+
+	ipproto = ipv6_find_hdr(skb, &thoff, -1, &fragoff, NULL);
+	if (fragoff != 0)
+		return false;
+
+	/* l2tp_mt_check6 already restricts the transport protocol */
+	switch (ipproto) {
+	case IPPROTO_UDP:
+		return l2tp_udp_mt(skb, par, thoff);
+	case IPPROTO_L2TP:
+		return l2tp_ip_mt(skb, par, thoff);
+	}
+
+	return false;
+}
+#endif
+
+static int l2tp_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+
+	/* Check for invalid flags */
+	if (info->flags & ~(XT_L2TP_TID | XT_L2TP_SID | XT_L2TP_VERSION |
+			    XT_L2TP_TYPE)) {
+		pr_info("unknown flags: %x\n", info->flags);
+		return -EINVAL;
+	}
+
+	/* At least one of tid, sid or type=control must be specified */
+	if ((!(info->flags & XT_L2TP_TID)) &&
+	    (!(info->flags & XT_L2TP_SID)) &&
+	    ((!(info->flags & XT_L2TP_TYPE)) ||
+	     (info->type != XT_L2TP_TYPE_CONTROL))) {
+		pr_info("invalid flags combination: %x\n", info->flags);
+		return -EINVAL;
+	}
+
+	/* If version 2 is specified, check that incompatible params
+	 * are not supplied
+	 */
+	if (info->flags & XT_L2TP_VERSION) {
+		if ((info->version < 2) || (info->version > 3)) {
+			pr_info("wrong L2TP version: %u\n", info->version);
+			return -EINVAL;
+		}
+
+		if (info->version == 2) {
+			if ((info->flags & XT_L2TP_TID) &&
+			    (info->tid > 0xffff)) {
+				pr_info("v2 tid > 0xffff: %u\n", info->tid);
+				return -EINVAL;
+			}
+			if ((info->flags & XT_L2TP_SID) &&
+			    (info->sid > 0xffff)) {
+				pr_info("v2 sid > 0xffff: %u\n", info->sid);
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int l2tp_mt_check4(const struct xt_mtchk_param *par)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	const struct ipt_entry *e = par->entryinfo;
+	const struct ipt_ip *ip = &e->ip;
+	int ret;
+
+	ret = l2tp_mt_check(par);
+	if (ret != 0)
+		return ret;
+
+	if ((ip->proto != IPPROTO_UDP) &&
+	    (ip->proto != IPPROTO_L2TP)) {
+		pr_info("missing protocol rule (udp|l2tpip)\n");
+		return -EINVAL;
+	}
+
+	if ((ip->proto == IPPROTO_L2TP) &&
+	    (info->version == 2)) {
+		pr_info("v2 doesn't support IP mode\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
+static int l2tp_mt_check6(const struct xt_mtchk_param *par)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	const struct ip6t_entry *e = par->entryinfo;
+	const struct ip6t_ip6 *ip = &e->ipv6;
+	int ret;
+
+	ret = l2tp_mt_check(par);
+	if (ret != 0)
+		return ret;
+
+	if ((ip->proto != IPPROTO_UDP) &&
+	    (ip->proto != IPPROTO_L2TP)) {
+		pr_info("missing protocol rule (udp|l2tpip)\n");
+		return -EINVAL;
+	}
+
+	if ((ip->proto == IPPROTO_L2TP) &&
+	    (info->version == 2)) {
+		pr_info("v2 doesn't support IP mode\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#endif
+
+static struct xt_match l2tp_mt_reg[] __read_mostly = {
+	{
+		.name      = "l2tp",
+		.revision  = 0,
+		.family    = NFPROTO_IPV4,
+		.match     = l2tp_mt4,
+		.matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)),
+		.checkentry = l2tp_mt_check4,
+		.hooks     = ((1 << NF_INET_PRE_ROUTING) |
+			      (1 << NF_INET_LOCAL_IN) |
+			      (1 << NF_INET_LOCAL_OUT) |
+			      (1 << NF_INET_FORWARD)),
+		.me        = THIS_MODULE,
+	},
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
+	{
+		.name      = "l2tp",
+		.revision  = 0,
+		.family    = NFPROTO_IPV6,
+		.match     = l2tp_mt6,
+		.matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)),
+		.checkentry = l2tp_mt_check6,
+		.hooks     = ((1 << NF_INET_PRE_ROUTING) |
+			      (1 << NF_INET_LOCAL_IN) |
+			      (1 << NF_INET_LOCAL_OUT) |
+			      (1 << NF_INET_FORWARD)),
+		.me        = THIS_MODULE,
+	},
+#endif
+};
+
+static int __init l2tp_mt_init(void)
+{
+	return xt_register_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg));
+}
+
+static void __exit l2tp_mt_exit(void)
+{
+	xt_unregister_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg));
+}
+
+module_init(l2tp_mt_init);
+module_exit(l2tp_mt_exit);
-- 
cgit v1.2.3


From 8a59359cb80f448923a7bc9f555d477e74547d7a Mon Sep 17 00:00:00 2001
From: Christoph Paasch <christoph.paasch@uclouvain.be>
Date: Wed, 8 Jan 2014 16:05:57 +0100
Subject: tcp: metrics: New netlink attribute for src IP and dumped in netlink
 reply

This patch adds a new netlink attribute for the source-IP and appends it
to the netlink reply. Now, iproute2 can have access to the source-IP.

Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tcp_metrics.h | 2 ++
 net/ipv4/tcp_metrics.c           | 6 ++++++
 2 files changed, 8 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h
index cb5157b55f32..54a37b13f2c4 100644
--- a/include/uapi/linux/tcp_metrics.h
+++ b/include/uapi/linux/tcp_metrics.h
@@ -35,6 +35,8 @@ enum {
 	TCP_METRICS_ATTR_FOPEN_SYN_DROPS,	/* u16, count of drops */
 	TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS,	/* msecs age */
 	TCP_METRICS_ATTR_FOPEN_COOKIE,		/* binary */
+	TCP_METRICS_ATTR_SADDR_IPV4,		/* u32 */
+	TCP_METRICS_ATTR_SADDR_IPV6,		/* binary */
 
 	__TCP_METRICS_ATTR_MAX,
 };
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index de32aa41a846..199659f7a871 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -745,11 +745,17 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 		if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4,
 				tm->tcpm_daddr.addr.a4) < 0)
 			goto nla_put_failure;
+		if (nla_put_be32(msg, TCP_METRICS_ATTR_SADDR_IPV4,
+				tm->tcpm_saddr.addr.a4) < 0)
+			goto nla_put_failure;
 		break;
 	case AF_INET6:
 		if (nla_put(msg, TCP_METRICS_ATTR_ADDR_IPV6, 16,
 			    tm->tcpm_daddr.addr.a6) < 0)
 			goto nla_put_failure;
+		if (nla_put(msg, TCP_METRICS_ATTR_SADDR_IPV6, 16,
+			    tm->tcpm_saddr.addr.a6) < 0)
+			goto nla_put_failure;
 		break;
 	default:
 		return -EAFNOSUPPORT;
-- 
cgit v1.2.3


From 761aac737eb11901c382a3f021dead59a26983fc Mon Sep 17 00:00:00 2001
From: Thomas Haller <thaller@redhat.com>
Date: Wed, 15 Jan 2014 15:36:58 +0100
Subject: ipv6 addrconf: add IFA_F_NOPREFIXROUTE flag to suppress creation of
 IP6 routes

When adding/modifying an IPv6 address, the userspace application needs
a way to suppress adding a prefix route. This is for example relevant
together with IFA_F_MANAGERTEMPADDR, where userspace creates autoconf
generated addresses, but depending on on-link, no route for the
prefix should be added.

Signed-off-by: Thomas Haller <thaller@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_addr.h |  1 +
 net/ipv6/addrconf.c          | 19 +++++++++++++------
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index cfed10be7529..dea10a87dfd1 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -49,6 +49,7 @@ enum {
 #define IFA_F_TENTATIVE		0x40
 #define IFA_F_PERMANENT		0x80
 #define IFA_F_MANAGETEMPADDR	0x100
+#define IFA_F_NOPREFIXROUTE	0x200
 
 struct ifa_cacheinfo {
 	__u32	ifa_prefered;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1b2e4ee3ce5e..85100c1ac761 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2434,8 +2434,11 @@ static int inet6_addr_add(struct net *net, int ifindex,
 			    valid_lft, prefered_lft);
 
 	if (!IS_ERR(ifp)) {
-		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
-				      expires, flags);
+		if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
+			addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
+					      expires, flags);
+		}
+
 		/*
 		 * Note that section 3.1 of RFC 4429 indicates
 		 * that the Optimistic flag should not be set for
@@ -3662,7 +3665,8 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 	spin_lock_bh(&ifp->lock);
 	was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR;
 	ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD |
-			IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR);
+			IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR |
+			IFA_F_NOPREFIXROUTE);
 	ifp->flags |= ifa_flags;
 	ifp->tstamp = jiffies;
 	ifp->valid_lft = valid_lft;
@@ -3672,8 +3676,10 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 	if (!(ifp->flags&IFA_F_TENTATIVE))
 		ipv6_ifa_notify(0, ifp);
 
-	addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev,
-			      expires, flags);
+	if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
+		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev,
+				      expires, flags);
+	}
 
 	if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) {
 		if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR))
@@ -3727,7 +3733,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
 
 	/* We ignore other flags so far. */
-	ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR;
+	ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR |
+		     IFA_F_NOPREFIXROUTE;
 
 	ifa = ipv6_get_ifaddr(net, pfx, dev, 1);
 	if (ifa == NULL) {
-- 
cgit v1.2.3


From 6c80563c2fdd9b32e37e2570e5b1ba9befd591c0 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 15 Jan 2014 15:38:43 -0800
Subject: net_sched: act: pick a different type for act_xt

In tcf_register_action() we check either ->type or ->kind to see if
there is an existing action registered, but ipt action registers two
actions with same type but different kinds. They should have different
types too.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tc_act/tc_ipt.h | 1 +
 net/sched/act_ipt.c                | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h
index a2335563d21f..130aaadf6fac 100644
--- a/include/uapi/linux/tc_act/tc_ipt.h
+++ b/include/uapi/linux/tc_act/tc_ipt.h
@@ -4,6 +4,7 @@
 #include <linux/pkt_cls.h>
 
 #define TCA_ACT_IPT 6
+#define TCA_ACT_XT 10
 
 enum {
 	TCA_IPT_UNSPEC,
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 484bd19601e3..bc9f498f6fef 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -298,7 +298,7 @@ static struct tc_action_ops act_ipt_ops = {
 static struct tc_action_ops act_xt_ops = {
 	.kind		=	"xt",
 	.hinfo		=	&ipt_hash_info,
-	.type		=	TCA_ACT_IPT,
+	.type		=	TCA_ACT_XT,
 	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_ipt,
-- 
cgit v1.2.3


From 1d3ee88ae0d605629bf369ab0b868dae8ca62a48 Mon Sep 17 00:00:00 2001
From: "sfeldma@cumulusnetworks.com" <sfeldma@cumulusnetworks.com>
Date: Thu, 16 Jan 2014 22:57:56 -0800
Subject: bonding: add netlink attributes to slave link dev

If link is IFF_SLAVE, extend link dev netlink attributes to include
slave attributes with new IFLA_SLAVE nest.  Add netlink notification
(RTM_NEWLINK) when slave status changes from backup to active, or
visa-versa.

Adds new ndo_get_slave op to net_device_ops to fill skb with IFLA_SLAVE
attributes.  Currently only used by bonding driver, but could be
used by other aggregating devices with slaves.

Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c    |  1 +
 drivers/net/bonding/bond_netlink.c | 36 +++++++++++++++++++++++++
 drivers/net/bonding/bonding.h      | 11 ++++++--
 include/linux/netdevice.h          |  5 ++++
 include/uapi/linux/if_link.h       | 13 +++++++++
 net/core/rtnetlink.c               | 54 ++++++++++++++++++++++++++++++++++++++
 6 files changed, 118 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index df85cec3e5d9..3220b488dd1e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3883,6 +3883,7 @@ static const struct net_device_ops bond_netdev_ops = {
 #endif
 	.ndo_add_slave		= bond_enslave,
 	.ndo_del_slave		= bond_release,
+	.ndo_get_slave		= bond_get_slave,
 	.ndo_fix_features	= bond_fix_features,
 };
 
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 555c7837d8e6..21c648854a8c 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -22,6 +22,42 @@
 #include <linux/reciprocal_div.h>
 #include "bonding.h"
 
+int bond_get_slave(struct net_device *slave_dev, struct sk_buff *skb)
+{
+	struct slave *slave = bond_slave_get_rtnl(slave_dev);
+	const struct aggregator *agg;
+
+	if (nla_put_u8(skb, IFLA_SLAVE_STATE, bond_slave_state(slave)))
+		goto nla_put_failure;
+
+	if (nla_put_u8(skb, IFLA_SLAVE_MII_STATUS, slave->link))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, IFLA_SLAVE_LINK_FAILURE_COUNT,
+			slave->link_failure_count))
+		goto nla_put_failure;
+
+	if (nla_put(skb, IFLA_SLAVE_PERM_HWADDR,
+		    slave_dev->addr_len, slave->perm_hwaddr))
+		goto nla_put_failure;
+
+	if (nla_put_u16(skb, IFLA_SLAVE_QUEUE_ID, slave->queue_id))
+		goto nla_put_failure;
+
+	if (slave->bond->params.mode == BOND_MODE_8023AD) {
+		agg = SLAVE_AD_INFO(slave).port.aggregator;
+		if (agg)
+			if (nla_put_u16(skb, IFLA_SLAVE_AD_AGGREGATOR_ID,
+					agg->aggregator_identifier))
+				goto nla_put_failure;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MODE]		= { .type = NLA_U8 },
 	[IFLA_BOND_ACTIVE_SLAVE]	= { .type = NLA_U32 },
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 309757d8482b..8a935f8f2b3c 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -285,12 +285,18 @@ static inline bool bond_is_lb(const struct bonding *bond)
 
 static inline void bond_set_active_slave(struct slave *slave)
 {
-	slave->backup = 0;
+	if (slave->backup) {
+		slave->backup = 0;
+		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL);
+	}
 }
 
 static inline void bond_set_backup_slave(struct slave *slave)
 {
-	slave->backup = 1;
+	if (!slave->backup) {
+		slave->backup = 1;
+		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL);
+	}
 }
 
 static inline int bond_slave_state(struct slave *slave)
@@ -426,6 +432,7 @@ int bond_sysfs_slave_add(struct slave *slave);
 void bond_sysfs_slave_del(struct slave *slave);
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
 int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
+int bond_get_slave(struct net_device *slave_dev, struct sk_buff *skb);
 int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count);
 int bond_parse_parm(const char *mode_arg, const struct bond_parm_tbl *tbl);
 int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e985231fe04b..83ce2aee65e6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -921,6 +921,9 @@ struct netdev_phys_port_id {
  * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
  *	Called to release previously enslaved netdev.
  *
+ * int (*ndo_get_slave)(struct net_device *slave_dev, struct sk_buff *skb);
+ *	Called to fill netlink skb with slave info.
+ *
  *      Feature/offload setting functions.
  * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
  *		netdev_features_t features);
@@ -1093,6 +1096,8 @@ struct net_device_ops {
 						 struct net_device *slave_dev);
 	int			(*ndo_del_slave)(struct net_device *dev,
 						 struct net_device *slave_dev);
+	int			(*ndo_get_slave)(struct net_device *slave_dev,
+						 struct sk_buff *skb);
 	netdev_features_t	(*ndo_fix_features)(struct net_device *dev,
 						    netdev_features_t features);
 	int			(*ndo_set_features)(struct net_device *dev,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 3e6bd3c7445d..ba2f3bf5fdf5 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -144,6 +144,7 @@ enum {
 	IFLA_NUM_RX_QUEUES,
 	IFLA_CARRIER,
 	IFLA_PHYS_PORT_ID,
+	IFLA_SLAVE,
 	__IFLA_MAX
 };
 
@@ -368,6 +369,18 @@ enum {
 
 #define IFLA_BOND_AD_INFO_MAX	(__IFLA_BOND_AD_INFO_MAX - 1)
 
+enum {
+	IFLA_SLAVE_STATE,
+	IFLA_SLAVE_MII_STATUS,
+	IFLA_SLAVE_LINK_FAILURE_COUNT,
+	IFLA_SLAVE_PERM_HWADDR,
+	IFLA_SLAVE_QUEUE_ID,
+	IFLA_SLAVE_AD_AGGREGATOR_ID,
+	__IFLA_SLAVE_MAX,
+};
+
+#define IFLA_SLAVE_MAX	(__IFLA_SLAVE_MAX - 1)
+
 /* SR-IOV virtual function management section */
 
 enum {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e6e7d582f901..4f85de7aca33 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -721,6 +721,28 @@ static size_t rtnl_port_size(const struct net_device *dev)
 		return port_self_size;
 }
 
+static size_t rtnl_bond_slave_size(const struct net_device *dev)
+{
+	struct net_device *bond;
+	size_t slave_size =
+		nla_total_size(sizeof(struct nlattr)) +	/* IFLA_SLAVE */
+		nla_total_size(1) +	/* IFLA_SLAVE_STATE */
+		nla_total_size(1) +	/* IFLA_SLAVE_MII_STATUS */
+		nla_total_size(4) +	/* IFLA_SLAVE_LINK_FAILURE_COUNT */
+		nla_total_size(MAX_ADDR_LEN) +	/* IFLA_SLAVE_PERM_HWADDR */
+		nla_total_size(2) +	/* IFLA_SLAVE_QUEUE_ID */
+		nla_total_size(2) +	/* IFLA_SLAVE_AD_AGGREGATOR_ID */
+		0;
+
+	if (netif_is_bond_slave((struct net_device *)dev)) {
+		bond = netdev_master_upper_dev_get((struct net_device *)dev);
+		if (bond && bond->netdev_ops->ndo_get_slave)
+			return slave_size;
+	}
+
+	return 0;
+}
+
 static noinline size_t if_nlmsg_size(const struct net_device *dev,
 				     u32 ext_filter_mask)
 {
@@ -750,6 +772,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
+	       + rtnl_bond_slave_size(dev) /* IFLA_SLAVE */
 	       + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
 }
 
@@ -847,6 +870,34 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
+static size_t rtnl_bond_slave_fill(struct sk_buff *skb, struct net_device *dev)
+{
+	struct net_device *bond;
+	struct nlattr *nest;
+	int err;
+
+	if (!netif_is_bond_slave(dev))
+		return 0;
+
+	bond = netdev_master_upper_dev_get(dev);
+	if (!bond || !bond->netdev_ops->ndo_get_slave)
+		return 0;
+
+	nest = nla_nest_start(skb, IFLA_SLAVE);
+	if (!nest)
+		return -EMSGSIZE;
+
+	err = bond->netdev_ops->ndo_get_slave(dev, skb);
+	if (err) {
+		nla_nest_cancel(skb, nest);
+		return (err == -EMSGSIZE) ? err : 0;
+	}
+
+	nla_nest_end(skb, nest);
+
+	return 0;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
 			    unsigned int flags, u32 ext_filter_mask)
@@ -1001,6 +1052,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	if (rtnl_port_fill(skb, dev))
 		goto nla_put_failure;
 
+	if (rtnl_bond_slave_fill(skb, dev))
+		goto nla_put_failure;
+
 	if (dev->rtnl_link_ops) {
 		if (rtnl_link_fill(skb, dev) < 0)
 			goto nla_put_failure;
-- 
cgit v1.2.3


From ea02f9411d9faa3553ed09ce0ec9f00ceae9885e Mon Sep 17 00:00:00 2001
From: Michal Sekletar <msekleta@redhat.com>
Date: Fri, 17 Jan 2014 17:09:45 +0100
Subject: net: introduce SO_BPF_EXTENSIONS

For user space packet capturing libraries such as libpcap, there's
currently only one way to check which BPF extensions are supported
by the kernel, that is, commit aa1113d9f85d ("net: filter: return
-EINVAL if BPF_S_ANC* operation is not supported"). For querying all
extensions at once this might be rather inconvenient.

Therefore, this patch introduces a new option which can be used as
an argument for getsockopt(), and allows one to obtain information
about which BPF extensions are supported by the current kernel.

As David Miller suggests, we do not need to define any bits right
now and status quo can just return 0 in order to state that this
versions supports SKF_AD_PROTOCOL up to SKF_AD_PAY_OFFSET. Later
additions to BPF extensions need to add their bits to the
bpf_tell_extensions() function, as documented in the comment.

Signed-off-by: Michal Sekletar <msekleta@redhat.com>
Cc: David Miller <davem@davemloft.net>
Reviewed-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/uapi/asm/socket.h   |  2 ++
 arch/avr32/include/uapi/asm/socket.h   |  2 ++
 arch/cris/include/uapi/asm/socket.h    |  2 ++
 arch/frv/include/uapi/asm/socket.h     |  2 ++
 arch/ia64/include/uapi/asm/socket.h    |  2 ++
 arch/m32r/include/uapi/asm/socket.h    |  2 ++
 arch/mips/include/uapi/asm/socket.h    |  2 ++
 arch/mn10300/include/uapi/asm/socket.h |  2 ++
 arch/parisc/include/uapi/asm/socket.h  |  2 ++
 arch/powerpc/include/uapi/asm/socket.h |  2 ++
 arch/s390/include/uapi/asm/socket.h    |  2 ++
 arch/sparc/include/uapi/asm/socket.h   |  2 ++
 arch/xtensa/include/uapi/asm/socket.h  |  2 ++
 include/linux/filter.h                 | 11 +++++++++++
 include/uapi/asm-generic/socket.h      |  2 ++
 net/core/sock.c                        |  4 ++++
 16 files changed, 43 insertions(+)

(limited to 'include/uapi')

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index e3a1491d5073..3de1394bcab8 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -85,4 +85,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index cbf902e4cd9e..6e6cd159924b 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -78,4 +78,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index 13829aaaeec5..ed94e5ed0a23 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -80,6 +80,8 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index 5d4299762426..ca2c6e6f31c6 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -78,5 +78,7 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index c25302fb48d9..a1b49bac7951 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 52966650114f..6c9a24b3aefa 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -78,4 +78,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 0df9787cd84d..a14baa218c76 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -96,4 +96,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 71dedcae55a6..6aa3ce1854aa 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -78,4 +78,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 70b3674dac4e..fe35ceacf0e7 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -77,4 +77,6 @@
 
 #define SO_MAX_PACING_RATE	0x4028
 
+#define SO_BPF_EXTENSIONS	0x4029
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index fa698324a1fd..a9c3e2e18c05 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -85,4 +85,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index c286c2e868f0..e031332096d7 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -84,4 +84,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 0f21e9a5ca18..54d9608681b6 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -74,6 +74,8 @@
 
 #define SO_MAX_PACING_RATE	0x0031
 
+#define SO_BPF_EXTENSIONS	0x0032
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 7db5c22faa68..39acec0cf0b1 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -89,4 +89,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index ff4e40cd45b1..1a95a2dcf113 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -83,6 +83,17 @@ static inline void bpf_jit_free(struct sk_filter *fp)
 #define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
 #endif
 
+static inline int bpf_tell_extensions(void)
+{
+	/* When adding new BPF extension it is necessary to enumerate
+	 * it here, so userspace software which wants to know what is
+	 * supported can do so by inspecting return value of this
+	 * function
+	 */
+
+	return 0;
+}
+
 enum {
 	BPF_S_RET_K = 1,
 	BPF_S_RET_A,
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 38f14d0264c3..ea0796bdcf88 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -80,4 +80,6 @@
 
 #define SO_MAX_PACING_RATE	47
 
+#define SO_BPF_EXTENSIONS	48
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index b3f7ee3008a0..0c127dcdf6a8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1167,6 +1167,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
 		break;
 
+	case SO_BPF_EXTENSIONS:
+		v.val = bpf_tell_extensions();
+		break;
+
 	case SO_SELECT_ERR_QUEUE:
 		v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
 		break;
-- 
cgit v1.2.3


From df3687ffc6653e4d32168338b4dee20c164ed7c9 Mon Sep 17 00:00:00 2001
From: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Date: Fri, 17 Jan 2014 17:15:03 +0100
Subject: ipv6: add the IPV6_FL_F_REFLECT flag to IPV6_FL_A_GET

With this option, the socket will reply with the flow label value read
on received packets.

The goal is to have a connection with the same flow label in both
direction of the communication.

Changelog of V4:
 * Do not erase the flow label on the listening socket. Use pktopts to
 store the received value

Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h     |  1 +
 include/uapi/linux/in6.h |  1 +
 net/ipv6/ip6_flowlabel.c | 21 +++++++++++++++++++++
 net/ipv6/tcp_ipv6.c      | 12 +++++++++++-
 4 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7e1ded0d8e45..1084304fd75a 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -191,6 +191,7 @@ struct ipv6_pinfo {
 	/* sockopt flags */
 	__u16			recverr:1,
 	                        sndflow:1,
+				repflow:1,
 				pmtudisc:3,
 				ipv6only:1,
 				srcprefs:3,	/* 001: prefer temporary address
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index f94f1d013bf2..02c0cd685a27 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -85,6 +85,7 @@ struct in6_flowlabel_req {
 
 #define IPV6_FL_F_CREATE	1
 #define IPV6_FL_F_EXCL		2
+#define IPV6_FL_F_REFLECT	4
 
 #define IPV6_FL_S_NONE		0
 #define IPV6_FL_S_EXCL		1
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cbc93517b455..55823f187446 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -486,6 +486,11 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq)
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct ipv6_fl_socklist *sfl;
 
+	if (np->repflow) {
+		freq->flr_label = np->flow_label;
+		return 0;
+	}
+
 	rcu_read_lock_bh();
 
 	for_each_sk_fl_rcu(np, sfl) {
@@ -527,6 +532,15 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 
 	switch (freq.flr_action) {
 	case IPV6_FL_A_PUT:
+		if (freq.flr_flags & IPV6_FL_F_REFLECT) {
+			if (sk->sk_protocol != IPPROTO_TCP)
+				return -ENOPROTOOPT;
+			if (!np->repflow)
+				return -ESRCH;
+			np->flow_label = 0;
+			np->repflow = 0;
+			return 0;
+		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
 		     (sfl = rcu_dereference(*sflp))!=NULL;
@@ -567,6 +581,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		return -ESRCH;
 
 	case IPV6_FL_A_GET:
+		if (freq.flr_flags & IPV6_FL_F_REFLECT) {
+			if (sk->sk_protocol != IPPROTO_TCP)
+				return -ENOPROTOOPT;
+			np->repflow = 1;
+			return 0;
+		}
+
 		if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
 			return -EINVAL;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b5512696e9ed..b61fa8bac3bd 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -483,6 +483,9 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 				    &ireq->ir_v6_rmt_addr);
 
 		fl6->daddr = ireq->ir_v6_rmt_addr;
+		if (np->repflow && (ireq->pktopts != NULL))
+			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
+
 		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
 		err = net_xmit_eval(err);
@@ -1018,7 +1021,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (!isn) {
 		if (ipv6_opt_accepted(sk, skb) ||
 		    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
-		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
+		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim ||
+		    np->repflow) {
 			atomic_inc(&skb->users);
 			ireq->pktopts = skb;
 		}
@@ -1143,6 +1147,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newnp->mcast_oif   = inet6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
 		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+		if (np->repflow)
+			newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
@@ -1223,6 +1229,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newnp->mcast_oif  = inet6_iif(skb);
 	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
 	newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+	if (np->repflow)
+		newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
 	/* Clone native IPv6 options from listening socket (if any)
 
@@ -1434,6 +1442,8 @@ ipv6_pktoptions:
 			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
 		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
 			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
+		if (np->repflow)
+			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
 		if (ipv6_opt_accepted(sk, opt_skb)) {
 			skb_set_owner_r(opt_skb, sk);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
-- 
cgit v1.2.3


From 46e5f401762c639e38eea350d335c0f54ec2442f Mon Sep 17 00:00:00 2001
From: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Date: Fri, 17 Jan 2014 17:15:04 +0100
Subject: ipv6: add a flag to get the flow label used remotly

This information is already available via IPV6_FLOWINFO
of IPV6_2292PKTOPTIONS, and them a filtering to get the flow label
information. But it is probably logical and easier for users to add this
here, and to control both sent/received flow label values with the
IPV6_FLOWLABEL_MGR option.

Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h       | 3 ++-
 include/uapi/linux/in6.h | 1 +
 net/ipv6/ip6_flowlabel.c | 8 +++++++-
 net/ipv6/ipv6_sockglue.c | 5 ++++-
 4 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include/uapi')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6d80f51897a5..78d3d5124918 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -253,7 +253,8 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ipv6_txoptions *fopt);
 void fl6_free_socklist(struct sock *sk);
 int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen);
-int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq);
+int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
+			   int flags);
 int ip6_flowlabel_init(void);
 void ip6_flowlabel_cleanup(void);
 
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 02c0cd685a27..633b93cac1ed 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -86,6 +86,7 @@ struct in6_flowlabel_req {
 #define IPV6_FL_F_CREATE	1
 #define IPV6_FL_F_EXCL		2
 #define IPV6_FL_F_REFLECT	4
+#define IPV6_FL_F_REMOTE	8
 
 #define IPV6_FL_S_NONE		0
 #define IPV6_FL_S_EXCL		1
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 55823f187446..01bf2524c72a 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -481,11 +481,17 @@ static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl,
 	spin_unlock_bh(&ip6_sk_fl_lock);
 }
 
-int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq)
+int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
+			   int flags)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct ipv6_fl_socklist *sfl;
 
+	if (flags & IPV6_FL_F_REMOTE) {
+		freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK;
+		return 0;
+	}
+
 	if (np->repflow) {
 		freq->flr_label = np->flow_label;
 		return 0;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 2855b00ed49d..7024a874e901 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1221,6 +1221,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	case IPV6_FLOWLABEL_MGR:
 	{
 		struct in6_flowlabel_req freq;
+		int flags;
 
 		if (len < sizeof(freq))
 			return -EINVAL;
@@ -1232,9 +1233,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 
 		len = sizeof(freq);
+		flags = freq.flr_flags;
+
 		memset(&freq, 0, sizeof(freq));
 
-		val = ipv6_flowlabel_opt_get(sk, &freq);
+		val = ipv6_flowlabel_opt_get(sk, &freq, flags);
 		if (val < 0)
 			return val;
 
-- 
cgit v1.2.3


From 2d36097d26b5991d71a2cf4a20c1a158f0f1bfcd Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Wed, 22 Jan 2014 16:01:44 -0500
Subject: af_packet: Add Queue mapping mode to af_packet fanout operation

This patch adds a queue mapping mode to the fanout operation of af_packet
sockets.  This allows user space af_packet users to better filter on flows
ingressing and egressing via a specific hardware queue, and avoids the potential
packet reordering that can occur when FANOUT_CPU is being used and irq affinity
varies.

Tested successfully by myself.  applies to net-next

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_packet.h |  1 +
 net/packet/af_packet.c         | 11 +++++++++++
 2 files changed, 12 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index 1988a02842cc..bac27fa05f5b 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -60,6 +60,7 @@ struct sockaddr_ll {
 #define PACKET_FANOUT_CPU		2
 #define PACKET_FANOUT_ROLLOVER		3
 #define PACKET_FANOUT_RND		4
+#define PACKET_FANOUT_QM		5
 #define PACKET_FANOUT_FLAG_ROLLOVER	0x1000
 #define PACKET_FANOUT_FLAG_DEFRAG	0x8000
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 97346162803d..6a2bb37506c5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1312,6 +1312,13 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f,
 	return idx;
 }
 
+static unsigned int fanout_demux_qm(struct packet_fanout *f,
+				    struct sk_buff *skb,
+				    unsigned int num)
+{
+	return skb_get_queue_mapping(skb) % num;
+}
+
 static bool fanout_has_flag(struct packet_fanout *f, u16 flag)
 {
 	return f->flags & (flag >> 8);
@@ -1351,6 +1358,9 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	case PACKET_FANOUT_RND:
 		idx = fanout_demux_rnd(f, skb, num);
 		break;
+	case PACKET_FANOUT_QM:
+		idx = fanout_demux_qm(f, skb, num);
+		break;
 	case PACKET_FANOUT_ROLLOVER:
 		idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num);
 		break;
@@ -1421,6 +1431,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	case PACKET_FANOUT_LB:
 	case PACKET_FANOUT_CPU:
 	case PACKET_FANOUT_RND:
+	case PACKET_FANOUT_QM:
 		break;
 	default:
 		return -EINVAL;
-- 
cgit v1.2.3


From df7dbcbbafc0b8f3fb31a40c6f3c4a7e15cb0b40 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 22 Jan 2014 09:05:54 +0100
Subject: rtnetlink: put "BOND" into nl attribute names which are related to
 bonding

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 12 ++++++------
 include/uapi/linux/if_link.h       | 19 ++++++++++---------
 net/core/rtnetlink.c               | 16 ++++++++--------
 3 files changed, 24 insertions(+), 23 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index a8fa7256b7b1..549eb8702ebb 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -26,27 +26,27 @@ int bond_get_slave(struct net_device *slave_dev, struct sk_buff *skb)
 	struct slave *slave = bond_slave_get_rtnl(slave_dev);
 	const struct aggregator *agg;
 
-	if (nla_put_u8(skb, IFLA_SLAVE_STATE, bond_slave_state(slave)))
+	if (nla_put_u8(skb, IFLA_BOND_SLAVE_STATE, bond_slave_state(slave)))
 		goto nla_put_failure;
 
-	if (nla_put_u8(skb, IFLA_SLAVE_MII_STATUS, slave->link))
+	if (nla_put_u8(skb, IFLA_BOND_SLAVE_MII_STATUS, slave->link))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, IFLA_SLAVE_LINK_FAILURE_COUNT,
+	if (nla_put_u32(skb, IFLA_BOND_SLAVE_LINK_FAILURE_COUNT,
 			slave->link_failure_count))
 		goto nla_put_failure;
 
-	if (nla_put(skb, IFLA_SLAVE_PERM_HWADDR,
+	if (nla_put(skb, IFLA_BOND_SLAVE_PERM_HWADDR,
 		    slave_dev->addr_len, slave->perm_hwaddr))
 		goto nla_put_failure;
 
-	if (nla_put_u16(skb, IFLA_SLAVE_QUEUE_ID, slave->queue_id))
+	if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, slave->queue_id))
 		goto nla_put_failure;
 
 	if (slave->bond->params.mode == BOND_MODE_8023AD) {
 		agg = SLAVE_AD_INFO(slave).port.aggregator;
 		if (agg)
-			if (nla_put_u16(skb, IFLA_SLAVE_AD_AGGREGATOR_ID,
+			if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 					agg->aggregator_identifier))
 				goto nla_put_failure;
 	}
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index ba2f3bf5fdf5..1f30b85ebf9d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -144,7 +144,7 @@ enum {
 	IFLA_NUM_RX_QUEUES,
 	IFLA_CARRIER,
 	IFLA_PHYS_PORT_ID,
-	IFLA_SLAVE,
+	IFLA_BOND_SLAVE,
 	__IFLA_MAX
 };
 
@@ -370,16 +370,17 @@ enum {
 #define IFLA_BOND_AD_INFO_MAX	(__IFLA_BOND_AD_INFO_MAX - 1)
 
 enum {
-	IFLA_SLAVE_STATE,
-	IFLA_SLAVE_MII_STATUS,
-	IFLA_SLAVE_LINK_FAILURE_COUNT,
-	IFLA_SLAVE_PERM_HWADDR,
-	IFLA_SLAVE_QUEUE_ID,
-	IFLA_SLAVE_AD_AGGREGATOR_ID,
-	__IFLA_SLAVE_MAX,
+	IFLA_BOND_SLAVE_UNSPEC,
+	IFLA_BOND_SLAVE_STATE,
+	IFLA_BOND_SLAVE_MII_STATUS,
+	IFLA_BOND_SLAVE_LINK_FAILURE_COUNT,
+	IFLA_BOND_SLAVE_PERM_HWADDR,
+	IFLA_BOND_SLAVE_QUEUE_ID,
+	IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
+	__IFLA_BOND_SLAVE_MAX,
 };
 
-#define IFLA_SLAVE_MAX	(__IFLA_SLAVE_MAX - 1)
+#define IFLA_BOND_SLAVE_MAX	(__IFLA_BOND_SLAVE_MAX - 1)
 
 /* SR-IOV virtual function management section */
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4f85de7aca33..cace14962234 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -725,13 +725,13 @@ static size_t rtnl_bond_slave_size(const struct net_device *dev)
 {
 	struct net_device *bond;
 	size_t slave_size =
-		nla_total_size(sizeof(struct nlattr)) +	/* IFLA_SLAVE */
-		nla_total_size(1) +	/* IFLA_SLAVE_STATE */
-		nla_total_size(1) +	/* IFLA_SLAVE_MII_STATUS */
-		nla_total_size(4) +	/* IFLA_SLAVE_LINK_FAILURE_COUNT */
-		nla_total_size(MAX_ADDR_LEN) +	/* IFLA_SLAVE_PERM_HWADDR */
-		nla_total_size(2) +	/* IFLA_SLAVE_QUEUE_ID */
-		nla_total_size(2) +	/* IFLA_SLAVE_AD_AGGREGATOR_ID */
+		nla_total_size(sizeof(struct nlattr)) +	/* IFLA_BOND_SLAVE */
+		nla_total_size(1) +	/* IFLA_BOND_SLAVE_STATE */
+		nla_total_size(1) +	/* IFLA_BOND_SLAVE_MII_STATUS */
+		nla_total_size(4) +	/* IFLA_BOND_SLAVE_LINK_FAILURE_COUNT */
+		nla_total_size(MAX_ADDR_LEN) +	/* IFLA_BOND_SLAVE_PERM_HWADDR */
+		nla_total_size(2) +	/* IFLA_BOND_SLAVE_QUEUE_ID */
+		nla_total_size(2) +	/* IFLA_BOND_SLAVE_AD_AGGREGATOR_ID */
 		0;
 
 	if (netif_is_bond_slave((struct net_device *)dev)) {
@@ -883,7 +883,7 @@ static size_t rtnl_bond_slave_fill(struct sk_buff *skb, struct net_device *dev)
 	if (!bond || !bond->netdev_ops->ndo_get_slave)
 		return 0;
 
-	nest = nla_nest_start(skb, IFLA_SLAVE);
+	nest = nla_nest_start(skb, IFLA_BOND_SLAVE);
 	if (!nest)
 		return -EMSGSIZE;
 
-- 
cgit v1.2.3


From ba7d49b1f0f8e5f24294a880ed576964059af5ef Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 22 Jan 2014 09:05:55 +0100
Subject: rtnetlink: provide api for getting and setting slave info

Recent patch
bonding: add netlink attributes to slave link dev (1d3ee88ae0d6)

Introduced yet another device specific way to access slave information
over rtnetlink. There is one already there for bridge.

This patch introduces generic way to do this, for getting and setting
info as well by extending link_ops. Later on, this new interface will
be used for bridge ports as well.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rtnetlink.h      |  14 ++++
 include/uapi/linux/if_link.h |   2 +
 net/core/rtnetlink.c         | 158 +++++++++++++++++++++++++++++++++++++------
 3 files changed, 154 insertions(+), 20 deletions(-)

(limited to 'include/uapi')

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 8fb42070a2c1..661e45d38051 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -79,6 +79,20 @@ struct rtnl_link_ops {
 					       const struct net_device *dev);
 	unsigned int		(*get_num_tx_queues)(void);
 	unsigned int		(*get_num_rx_queues)(void);
+
+	int			slave_maxtype;
+	const struct nla_policy	*slave_policy;
+	int			(*slave_validate)(struct nlattr *tb[],
+						  struct nlattr *data[]);
+	int			(*slave_changelink)(struct net_device *dev,
+						    struct net_device *slave_dev,
+						    struct nlattr *tb[],
+						    struct nlattr *data[]);
+	size_t			(*get_slave_size)(const struct net_device *dev,
+						  const struct net_device *slave_dev);
+	int			(*fill_slave_info)(struct sk_buff *skb,
+						   const struct net_device *dev,
+						   const struct net_device *slave_dev);
 };
 
 int __rtnl_link_register(struct rtnl_link_ops *ops);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1f30b85ebf9d..b8fb352b58f6 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -241,6 +241,8 @@ enum {
 	IFLA_INFO_KIND,
 	IFLA_INFO_DATA,
 	IFLA_INFO_XSTATS,
+	IFLA_INFO_SLAVE_KIND,
+	IFLA_INFO_SLAVE_DATA,
 	__IFLA_INFO_MAX,
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cace14962234..a56bccf6629e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -365,6 +365,22 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops)
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 
+static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev)
+{
+	struct net_device *master_dev;
+	const struct rtnl_link_ops *ops;
+
+	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	if (!master_dev)
+		return 0;
+	ops = master_dev->rtnl_link_ops;
+	if (!ops->get_slave_size)
+		return 0;
+	/* IFLA_INFO_SLAVE_DATA + nested data */
+	return nla_total_size(sizeof(struct nlattr)) +
+	       ops->get_slave_size(master_dev, dev);
+}
+
 static size_t rtnl_link_get_size(const struct net_device *dev)
 {
 	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
@@ -385,6 +401,8 @@ static size_t rtnl_link_get_size(const struct net_device *dev)
 		/* IFLA_INFO_XSTATS */
 		size += nla_total_size(ops->get_xstats_size(dev));
 
+	size += rtnl_link_get_slave_info_data_size(dev);
+
 	return size;
 }
 
@@ -459,40 +477,101 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev)
 	return size;
 }
 
-static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
+static bool rtnl_have_link_slave_info(const struct net_device *dev)
 {
-	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
-	struct nlattr *linkinfo, *data;
-	int err = -EMSGSIZE;
+	struct net_device *master_dev;
 
-	linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
-	if (linkinfo == NULL)
-		goto out;
+	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	if (master_dev && master_dev->rtnl_link_ops &&
+	    master_dev->rtnl_link_ops->fill_slave_info)
+		return true;
+	return false;
+}
+
+static int rtnl_link_slave_info_fill(struct sk_buff *skb,
+				     const struct net_device *dev)
+{
+	struct net_device *master_dev;
+	const struct rtnl_link_ops *ops;
+	struct nlattr *slave_data;
+	int err;
 
+	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	if (!master_dev)
+		return 0;
+	ops = master_dev->rtnl_link_ops;
+	if (!ops)
+		return 0;
+	if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0)
+		return -EMSGSIZE;
+	if (ops->fill_slave_info) {
+		slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA);
+		if (!slave_data)
+			return -EMSGSIZE;
+		err = ops->fill_slave_info(skb, master_dev, dev);
+		if (err < 0)
+			goto err_cancel_slave_data;
+		nla_nest_end(skb, slave_data);
+	}
+	return 0;
+
+err_cancel_slave_data:
+	nla_nest_cancel(skb, slave_data);
+	return err;
+}
+
+static int rtnl_link_info_fill(struct sk_buff *skb,
+			       const struct net_device *dev)
+{
+	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
+	struct nlattr *data;
+	int err;
+
+	if (!ops)
+		return 0;
 	if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0)
-		goto err_cancel_link;
+		return -EMSGSIZE;
 	if (ops->fill_xstats) {
 		err = ops->fill_xstats(skb, dev);
 		if (err < 0)
-			goto err_cancel_link;
+			return err;
 	}
 	if (ops->fill_info) {
 		data = nla_nest_start(skb, IFLA_INFO_DATA);
-		if (data == NULL) {
-			err = -EMSGSIZE;
-			goto err_cancel_link;
-		}
+		if (data == NULL)
+			return -EMSGSIZE;
 		err = ops->fill_info(skb, dev);
 		if (err < 0)
 			goto err_cancel_data;
 		nla_nest_end(skb, data);
 	}
-
-	nla_nest_end(skb, linkinfo);
 	return 0;
 
 err_cancel_data:
 	nla_nest_cancel(skb, data);
+	return err;
+}
+
+static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct nlattr *linkinfo;
+	int err = -EMSGSIZE;
+
+	linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
+	if (linkinfo == NULL)
+		goto out;
+
+	err = rtnl_link_info_fill(skb, dev);
+	if (err < 0)
+		goto err_cancel_link;
+
+	err = rtnl_link_slave_info_fill(skb, dev);
+	if (err < 0)
+		goto err_cancel_link;
+
+	nla_nest_end(skb, linkinfo);
+	return 0;
+
 err_cancel_link:
 	nla_nest_cancel(skb, linkinfo);
 out:
@@ -1052,10 +1131,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	if (rtnl_port_fill(skb, dev))
 		goto nla_put_failure;
 
-	if (rtnl_bond_slave_fill(skb, dev))
-		goto nla_put_failure;
-
-	if (dev->rtnl_link_ops) {
+	if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) {
 		if (rtnl_link_fill(skb, dev) < 0)
 			goto nla_put_failure;
 	}
@@ -1178,6 +1254,8 @@ EXPORT_SYMBOL(ifla_policy);
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
 	[IFLA_INFO_KIND]	= { .type = NLA_STRING },
 	[IFLA_INFO_DATA]	= { .type = NLA_NESTED },
+	[IFLA_INFO_SLAVE_KIND]	= { .type = NLA_STRING },
+	[IFLA_INFO_SLAVE_DATA]	= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
@@ -1765,7 +1843,9 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
+	const struct rtnl_link_ops *m_ops = NULL;
 	struct net_device *dev;
+	struct net_device *master_dev = NULL;
 	struct ifinfomsg *ifm;
 	char kind[MODULE_NAME_LEN];
 	char ifname[IFNAMSIZ];
@@ -1795,6 +1875,12 @@ replay:
 			dev = NULL;
 	}
 
+	if (dev) {
+		master_dev = netdev_master_upper_dev_get(dev);
+		if (master_dev)
+			m_ops = master_dev->rtnl_link_ops;
+	}
+
 	err = validate_linkmsg(dev, tb);
 	if (err < 0)
 		return err;
@@ -1816,7 +1902,10 @@ replay:
 	}
 
 	if (1) {
-		struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL;
+		struct nlattr *attr[ops ? ops->maxtype + 1 : 0];
+		struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0];
+		struct nlattr **data = NULL;
+		struct nlattr **slave_data = NULL;
 		struct net *dest_net;
 
 		if (ops) {
@@ -1835,6 +1924,24 @@ replay:
 			}
 		}
 
+		if (m_ops) {
+			if (m_ops->slave_maxtype &&
+			    linkinfo[IFLA_INFO_SLAVE_DATA]) {
+				err = nla_parse_nested(slave_attr,
+						       m_ops->slave_maxtype,
+						       linkinfo[IFLA_INFO_SLAVE_DATA],
+						       m_ops->slave_policy);
+				if (err < 0)
+					return err;
+				slave_data = slave_attr;
+			}
+			if (m_ops->slave_validate) {
+				err = m_ops->slave_validate(tb, slave_data);
+				if (err < 0)
+					return err;
+			}
+		}
+
 		if (dev) {
 			int modified = 0;
 
@@ -1854,6 +1961,17 @@ replay:
 				modified = 1;
 			}
 
+			if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
+				if (!m_ops || !m_ops->slave_changelink)
+					return -EOPNOTSUPP;
+
+				err = m_ops->slave_changelink(master_dev, dev,
+							      tb, slave_data);
+				if (err < 0)
+					return err;
+				modified = 1;
+			}
+
 			return do_setlink(dev, ifm, tb, ifname, modified);
 		}
 
-- 
cgit v1.2.3


From 237266f76d417b5fb1984ac3774e3a4fe070fe5d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Thu, 23 Jan 2014 16:51:27 +0100
Subject: rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index b8fb352b58f6..206f6511449d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -361,6 +361,7 @@ enum {
 #define IFLA_BOND_MAX	(__IFLA_BOND_MAX - 1)
 
 enum {
+	IFLA_BOND_AD_INFO_UNSPEC,
 	IFLA_BOND_AD_INFO_AGGREGATOR,
 	IFLA_BOND_AD_INFO_NUM_PORTS,
 	IFLA_BOND_AD_INFO_ACTOR_KEY,
-- 
cgit v1.2.3


From f55aa836fb7a90b62cb2c533b899e331cdffcf0c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 24 Jan 2014 08:39:16 +0100
Subject: rtnetlink: remove IFLA_BOND_SLAVE definition

This is in net-next only, for couple of days. Not used anymore, and never
should have been. So just remove it and pretend it was never there.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 206f6511449d..16410b6e7819 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -144,7 +144,6 @@ enum {
 	IFLA_NUM_RX_QUEUES,
 	IFLA_CARRIER,
 	IFLA_PHYS_PORT_ID,
-	IFLA_BOND_SLAVE,
 	__IFLA_MAX
 };
 
-- 
cgit v1.2.3