From 47846c9b0c10808d9337d2e7d09361f3e0a0a71a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 25 Nov 2009 17:46:19 +0100 Subject: mac80211: reduce reliance on netdev For bluetooth 3, we will most likely not have a netdev for a virtual interface (sdata), so prepare for that by reducing the reliance on having a netdev. This patch moves the name and address fields into the sdata struct and uses them from there all over. Some work is needed to keep them sync'ed, but that's not a lot of work and in slow paths anyway. In doing so, this also reduces the number of pointer dereferences in many places, because of things like sdata->dev->dev_addr becoming sdata->vif.addr. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2aff490..e94cc52 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -659,12 +659,14 @@ struct ieee80211_conf { * @type: type of this virtual interface * @bss_conf: BSS configuration for this interface, either our own * or the BSS we're associated to + * @addr: address of this interface * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *). */ struct ieee80211_vif { enum nl80211_iftype type; struct ieee80211_bss_conf bss_conf; + u8 addr[ETH_ALEN]; /* must be last */ u8 drv_priv[0] __attribute__((__aligned__(sizeof(void *)))); }; -- cgit v1.1 From eaf85ca7fecb218fc41ff57c1642ca73b097aabb Mon Sep 17 00:00:00 2001 From: Zhu Yi Date: Tue, 1 Dec 2009 10:18:37 +0800 Subject: wireless: add ieee80211_amsdu_to_8023s Move the A-MSDU handling code from mac80211 to cfg80211 so that more drivers can use it. The new created function ieee80211_amsdu_to_8023s converts an A-MSDU frame to a list of 802.3 frames. Cc: Johannes Berg Signed-off-by: Zhu Yi Signed-off-by: John W. Linville --- include/net/cfg80211.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0884b9a..542a477 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1578,7 +1578,7 @@ unsigned int ieee80211_hdrlen(__le16 fc); * @addr: the device MAC address * @iftype: the virtual interface type */ -int ieee80211_data_to_8023(struct sk_buff *skb, u8 *addr, +int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype); /** @@ -1589,10 +1589,28 @@ int ieee80211_data_to_8023(struct sk_buff *skb, u8 *addr, * @bssid: the network bssid (used only for iftype STATION and ADHOC) * @qos: build 802.11 QoS data frame */ -int ieee80211_data_from_8023(struct sk_buff *skb, u8 *addr, +int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype, u8 *bssid, bool qos); /** + * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame + * + * Decode an IEEE 802.11n A-MSDU frame and convert it to a list of + * 802.3 frames. The @list will be empty if the decode fails. The + * @skb is consumed after the function returns. + * + * @skb: The input IEEE 802.11n A-MSDU frame. + * @list: The output list of 802.3 frames. It must be allocated and + * initialized by by the caller. + * @addr: The device MAC address. + * @iftype: The device interface type. + * @extra_headroom: The hardware extra headroom for SKBs in the @list. + */ +void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, + const u8 *addr, enum nl80211_iftype iftype, + const unsigned int extra_headroom); + +/** * cfg80211_classify8021d - determine the 802.1p/1d tag for a data frame * @skb: the data frame */ -- cgit v1.1 From 0f78231bffb868a30e8533aace142213266bb811 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 1 Dec 2009 13:37:02 +0100 Subject: mac80211: enable spatial multiplexing powersave Enable spatial multiplexing in mac80211 by telling the driver what to do and, where necessary, sending action frames to the AP to update the requested SMPS mode. Also includes a trivial implementation for hwsim that just logs the requested mode. For now, the userspace interface is in debugfs only, and let you toggle the requested mode at any time. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 25 +++++++++++++++++++- include/net/mac80211.h | 59 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9724a2..e8d43d0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -707,6 +707,10 @@ struct ieee80211_mgmt { u8 action; u8 trans_id[WLAN_SA_QUERY_TR_ID_LEN]; } __attribute__ ((packed)) sa_query; + struct { + u8 action; + u8 smps_control; + } __attribute__ ((packed)) ht_smps; } u; } __attribute__ ((packed)) action; } u; @@ -824,6 +828,7 @@ struct ieee80211_ht_cap { #define IEEE80211_HT_CAP_LDPC_CODING 0x0001 #define IEEE80211_HT_CAP_SUP_WIDTH_20_40 0x0002 #define IEEE80211_HT_CAP_SM_PS 0x000C +#define IEEE80211_HT_CAP_SM_PS_SHIFT 2 #define IEEE80211_HT_CAP_GRN_FLD 0x0010 #define IEEE80211_HT_CAP_SGI_20 0x0020 #define IEEE80211_HT_CAP_SGI_40 0x0040 @@ -839,6 +844,7 @@ struct ieee80211_ht_cap { /* 802.11n HT capability AMPDU settings (for ampdu_params_info) */ #define IEEE80211_HT_AMPDU_PARM_FACTOR 0x03 #define IEEE80211_HT_AMPDU_PARM_DENSITY 0x1C +#define IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT 2 /* * Maximum length of AMPDU that the STA can receive. @@ -922,12 +928,17 @@ struct ieee80211_ht_info { #define IEEE80211_MAX_AMPDU_BUF 0x40 -/* Spatial Multiplexing Power Save Modes */ +/* Spatial Multiplexing Power Save Modes (for capability) */ #define WLAN_HT_CAP_SM_PS_STATIC 0 #define WLAN_HT_CAP_SM_PS_DYNAMIC 1 #define WLAN_HT_CAP_SM_PS_INVALID 2 #define WLAN_HT_CAP_SM_PS_DISABLED 3 +/* for SM power control field lower two bits */ +#define WLAN_HT_SMPS_CONTROL_DISABLED 0 +#define WLAN_HT_SMPS_CONTROL_STATIC 1 +#define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -1150,6 +1161,18 @@ enum ieee80211_spectrum_mgmt_actioncode { WLAN_ACTION_SPCT_CHL_SWITCH = 4, }; +/* HT action codes */ +enum ieee80211_ht_actioncode { + WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0, + WLAN_HT_ACTION_SMPS = 1, + WLAN_HT_ACTION_PSMP = 2, + WLAN_HT_ACTION_PCO_PHASE = 3, + WLAN_HT_ACTION_CSI = 4, + WLAN_HT_ACTION_NONCOMPRESSED_BF = 5, + WLAN_HT_ACTION_COMPRESSED_BF = 6, + WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7, +}; + /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e94cc52..e6b6bf8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -597,8 +597,10 @@ enum ieee80211_conf_flags { * @IEEE80211_CONF_CHANGE_CHANNEL: the channel/channel_type changed * @IEEE80211_CONF_CHANGE_RETRY_LIMITS: retry limits changed * @IEEE80211_CONF_CHANGE_IDLE: Idle flag changed + * @IEEE80211_CONF_CHANGE_SMPS: Spatial multiplexing powersave mode changed */ enum ieee80211_conf_changed { + IEEE80211_CONF_CHANGE_SMPS = BIT(1), IEEE80211_CONF_CHANGE_LISTEN_INTERVAL = BIT(2), IEEE80211_CONF_CHANGE_MONITOR = BIT(3), IEEE80211_CONF_CHANGE_PS = BIT(4), @@ -609,6 +611,21 @@ enum ieee80211_conf_changed { }; /** + * enum ieee80211_smps_mode - spatial multiplexing power save mode + * + * @ + */ +enum ieee80211_smps_mode { + IEEE80211_SMPS_AUTOMATIC, + IEEE80211_SMPS_OFF, + IEEE80211_SMPS_STATIC, + IEEE80211_SMPS_DYNAMIC, + + /* keep last */ + IEEE80211_SMPS_NUM_MODES, +}; + +/** * struct ieee80211_conf - configuration of the device * * This struct indicates how the driver shall configure the hardware. @@ -636,6 +653,10 @@ enum ieee80211_conf_changed { * @short_frame_max_tx_count: Maximum number of transmissions for a "short" * frame, called "dot11ShortRetryLimit" in 802.11, but actually means the * number of transmissions not the number of retries + * + * @smps_mode: spatial multiplexing powersave mode; note that + * %IEEE80211_SMPS_STATIC is used when the device is not + * configured for an HT channel */ struct ieee80211_conf { u32 flags; @@ -648,6 +669,7 @@ struct ieee80211_conf { struct ieee80211_channel *channel; enum nl80211_channel_type channel_type; + enum ieee80211_smps_mode smps_mode; }; /** @@ -930,6 +952,16 @@ enum ieee80211_tkip_key_type { * @IEEE80211_HW_BEACON_FILTER: * Hardware supports dropping of irrelevant beacon frames to * avoid waking up cpu. + * + * @IEEE80211_HW_SUPPORTS_STATIC_SMPS: + * Hardware supports static spatial multiplexing powersave, + * ie. can turn off all but one chain even on HT connections + * that should be using more chains. + * + * @IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS: + * Hardware supports dynamic spatial multiplexing powersave, + * ie. can turn off all but one chain and then wake the rest + * up as required after, for example, rts/cts handshake. */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -947,6 +979,8 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_DYNAMIC_PS = 1<<12, IEEE80211_HW_MFP_CAPABLE = 1<<13, IEEE80211_HW_BEACON_FILTER = 1<<14, + IEEE80211_HW_SUPPORTS_STATIC_SMPS = 1<<15, + IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS = 1<<16, }; /** @@ -1215,6 +1249,31 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, */ /** + * DOC: Spatial multiplexing power save + * + * SMPS (Spatial multiplexing power save) is a mechanism to conserve + * power in an 802.11n implementation. For details on the mechanism + * and rationale, please refer to 802.11 (as amended by 802.11n-2009) + * "11.2.3 SM power save". + * + * The mac80211 implementation is capable of sending action frames + * to update the AP about the station's SMPS mode, and will instruct + * the driver to enter the specific mode. It will also announce the + * requested SMPS mode during the association handshake. Hardware + * support for this feature is required, and can be indicated by + * hardware flags. + * + * The default mode will be "automatic", which nl80211/cfg80211 + * defines to be dynamic SMPS in (regular) powersave, and SMPS + * turned off otherwise. + * + * To support this feature, the driver must set the appropriate + * hardware support flags, and handle the SMPS flag to the config() + * operation. It will then with this mechanism be instructed to + * enter the requested SMPS mode while associated to an HT AP. + */ + +/** * DOC: Frame filtering * * mac80211 requires to see many management frames for proper -- cgit v1.1 From 9da3e068142ec7856b2f13261dcf0660fad32b61 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Mon, 7 Dec 2009 15:57:50 -0500 Subject: mac80211: only bother printing highest data rate on debugfs if its set IEEE-802.11n spec says the RX highest data rate field does not specify the highest supported RX data rate if its not set. Ignore it if not set then. Refer to section 7.3.56.4 Cc: johannes@sipsolutions.net Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e8d43d0..098bedc 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -775,7 +775,10 @@ struct ieee80211_bar { /** * struct ieee80211_mcs_info - MCS information * @rx_mask: RX mask - * @rx_highest: highest supported RX rate + * @rx_highest: highest supported RX rate. If set represents + * the highest supported RX data rate in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest RX data rate supported. * @tx_params: TX parameters */ struct ieee80211_mcs_info { -- cgit v1.1 From 12d50c46dc0f7fd2e625c4befaa5fa5740a7a594 Mon Sep 17 00:00:00 2001 From: Krishna Kumar Date: Tue, 8 Dec 2009 22:26:13 +0000 Subject: tcp: Remove check in __tcp_push_pending_frames MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit tcp_push checks tcp_send_head and calls __tcp_push_pending_frames, which again checks tcp_send_head, and this unnecessary check is done for every other caller of __tcp_push_pending_frames. Remove tcp_send_head check in __tcp_push_pending_frames and add the check to tcp_push_pending_frames. Other functions call __tcp_push_pending_frames only when tcp_send_head would evaluate to true. Signed-off-by: Krishna Kumar Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 34f5cc2..185e22b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -856,13 +856,6 @@ static inline void tcp_check_probe_timer(struct sock *sk) icsk->icsk_rto, TCP_RTO_MAX); } -static inline void tcp_push_pending_frames(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); -} - static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; @@ -1342,6 +1335,15 @@ static inline int tcp_write_queue_empty(struct sock *sk) return skb_queue_empty(&sk->sk_write_queue); } +static inline void tcp_push_pending_frames(struct sock *sk) +{ + if (tcp_send_head(sk)) { + struct tcp_sock *tp = tcp_sk(sk); + + __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); + } +} + /* Start sequence of the highest skb with SACKed bit, valid only if * sacked > 0 or when the caller has ensured validity by itself. */ -- cgit v1.1 From 31d12926e37291970dd4f6e9940df3897766a81d Mon Sep 17 00:00:00 2001 From: laurent chavey Date: Tue, 15 Dec 2009 11:15:28 +0000 Subject: net: Add rtnetlink init_rcvwnd to set the TCP initial receive window Add rtnetlink init_rcvwnd to set the TCP initial receive window size advertised by passive and active TCP connections. The current Linux TCP implementation limits the advertised TCP initial receive window to the one prescribed by slow start. For short lived TCP connections used for transaction type of traffic (i.e. http requests), bounding the advertised TCP initial receive window results in increased latency to complete the transaction. Support for setting initial congestion window is already supported using rtnetlink init_cwnd, but the feature is useless without the ability to set a larger TCP initial receive window. The rtnetlink init_rcvwnd allows increasing the TCP initial receive window, allowing TCP connection to advertise larger TCP receive window than the ones bounded by slow start. Signed-off-by: Laurent Chavey Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ include/net/dst.h | 2 -- include/net/tcp.h | 3 ++- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 05330fc..9590364 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -362,6 +362,8 @@ enum { #define RTAX_FEATURES RTAX_FEATURES RTAX_RTO_MIN, #define RTAX_RTO_MIN RTAX_RTO_MIN + RTAX_INITRWND, +#define RTAX_INITRWND RTAX_INITRWND __RTAX_MAX }; diff --git a/include/net/dst.h b/include/net/dst.h index 39c4a59..ce078cda 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -83,8 +83,6 @@ struct dst_entry { * (L1_CACHE_SIZE would be too much) */ #ifdef CONFIG_64BIT - long __pad_to_align_refcnt[2]; -#else long __pad_to_align_refcnt[1]; #endif /* diff --git a/include/net/tcp.h b/include/net/tcp.h index 185e22b..788c99f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -965,7 +965,8 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) /* Determine a window scaling and initial window to offer. */ extern void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, - int wscale_ok, __u8 *rcv_wscale); + int wscale_ok, __u8 *rcv_wscale, + __u32 init_rcv_wnd); static inline int tcp_win_from_space(int space) { -- cgit v1.1 From e5cd6fe391aa8c93560bb7ffdfe334cf4d0a02e4 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sat, 26 Dec 2009 11:51:00 +0000 Subject: llc: add support for LLC_OPT_PKTINFO Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/linux/llc.h | 7 +++++++ include/net/llc_conn.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/llc.h b/include/linux/llc.h index 77335856..ad7074b 100644 --- a/include/linux/llc.h +++ b/include/linux/llc.h @@ -36,6 +36,7 @@ enum llc_sockopts { LLC_OPT_BUSY_TMR_EXP, /* busy state expire time (secs). */ LLC_OPT_TX_WIN, /* tx window size. */ LLC_OPT_RX_WIN, /* rx window size. */ + LLC_OPT_PKTINFO, /* ancillary packet information. */ LLC_OPT_MAX }; @@ -70,6 +71,12 @@ enum llc_sockopts { #define LLC_SAP_RM 0xD4 /* Resource Management */ #define LLC_SAP_GLOBAL 0xFF /* Global SAP. */ +struct llc_pktinfo { + int lpi_ifindex; + unsigned char lpi_sap; + unsigned char lpi_mac[IFHWADDRLEN]; +}; + #ifdef __KERNEL__ #define LLC_SAP_DYN_START 0xC0 #define LLC_SAP_DYN_STOP 0xDE diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index e2374e3..fe982fd 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -76,6 +76,7 @@ struct llc_sock { u32 rx_pdu_hdr; /* used for saving header of last pdu received and caused sending FRMR. Used for resending FRMR */ + u32 cmsg_flags; }; static inline struct llc_sock *llc_sk(const struct sock *sk) -- cgit v1.1 From b76f5a8427ac2928c07fa4ff2144bb8db072c240 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sat, 26 Dec 2009 11:51:02 +0000 Subject: llc: convert the socket list to RCU locking For the reclamation phase we use the SLAB_DESTROY_BY_RCU mechanism, which require some extra checks in the lookup code: a) If the current socket was released, reallocated & inserted in another list it will short circuit the iteration for the current list, thus we need to restart the lookup. b) If the current socket was released, reallocated & inserted in the same list we just need to recheck it matches the look-up criteria and if not we can skip to the next element. In this case there is no need to restart the lookup, since sockets are inserted at the start of the list and the worst that will happen is that we will iterate throught some of the list elements more then once. Note that the /proc and multicast delivery was not yet converted to RCU, it still uses spinlocks for protection. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/llc.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/llc.h b/include/net/llc.h index 7940da1..1559cf1 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -16,6 +16,7 @@ #include #include #include +#include #include @@ -53,10 +54,8 @@ struct llc_sap { struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; - struct { - rwlock_t lock; - struct hlist_head list; - } sk_list; + spinlock_t sk_lock; + struct hlist_nulls_head sk_list; }; #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ -- cgit v1.1 From 6d2e3ea284463d5ab34e9cf2a41d0b8627b95d02 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sat, 26 Dec 2009 11:51:04 +0000 Subject: llc: use a device based hash table to speed up multicast delivery This patch adds a per SAP device based hash table to solve the multicast delivery scalability issue when we have large number of interfaces and a large number of sockets bound to the same SAP. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/llc.h | 11 +++++++++++ include/net/llc_conn.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/llc.h b/include/net/llc.h index 1559cf1..dbef591 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -32,6 +32,9 @@ struct llc_addr { #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 +#define LLC_SK_DEV_HASH_BITS 6 +#define LLC_SK_DEV_HASH_ENTRIES (1<sk_dev_hash[ifindex % LLC_SK_DEV_HASH_ENTRIES]; +} + + #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index fe982fd..2f97d8d 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -77,6 +77,7 @@ struct llc_sock { received and caused sending FRMR. Used for resending FRMR */ u32 cmsg_flags; + struct hlist_node dev_hash_node; }; static inline struct llc_sock *llc_sk(const struct sock *sk) -- cgit v1.1 From 52d58aef5ee460fedd7f250f05e79081019f2c79 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sat, 26 Dec 2009 11:51:05 +0000 Subject: llc: replace the socket list with a local address based hash For the cases where a lot of interfaces are used in conjunction with a lot of LLC sockets bound to the same SAP, the iteration of the socket list becomes prohibitively expensive. Replacing the list with a a local address based hash significantly improves the bind and listener lookup operations as well as the datagram delivery. Connected sockets delivery is also improved, but this patch does not address the case where we have lots of sockets with the same local address connected to different remote addresses. In order to keep the socket sanity checks alive and fast a socket counter was added to the SAP structure. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/llc.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/llc.h b/include/net/llc.h index dbef591..709a9b3 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -17,6 +17,8 @@ #include #include #include +#include +#include #include @@ -35,6 +37,9 @@ struct llc_addr { #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<sk_dev_hash[ifindex % LLC_SK_DEV_HASH_ENTRIES]; } +static inline +u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) +{ + return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), + LLC_SK_LADDR_HASH_BITS); +} + +static inline +struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, + const struct llc_addr *laddr) +{ + return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; +} #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ -- cgit v1.1 From 8beb9ab6c2df203e8d68cb1f48cf42604a6bed86 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sat, 26 Dec 2009 11:51:06 +0000 Subject: llc: convert llc_sap_list to RCU Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/llc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/llc.h b/include/net/llc.h index 709a9b3..5503b74 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -93,7 +93,7 @@ struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; -extern rwlock_t llc_sap_list_lock; +extern spinlock_t llc_sap_list_lock; extern int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); -- cgit v1.1 From a80f7c0b088187c8471b441d461e937991870661 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 23 Dec 2009 13:15:32 +0100 Subject: mac80211: introduce flush operation We've long lacked a good confirmation that frames have really gone out, e.g. before going off-channel for a scan. Add a flush() operation that drivers can implement to provide that confirmation, and use it in a few places: * before scanning sends the nullfunc frames * after scanning sends the nullfunc frames, if any * when going idle, to send any pending frames Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 494ac69..77ea34b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1545,6 +1545,10 @@ enum ieee80211_ampdu_mlme_action { * and need to call wiphy_rfkill_set_hw_state() in the callback. * * @testmode_cmd: Implement a cfg80211 test mode command. + * + * @flush: Flush all pending frames from the hardware queue, making sure + * that the hardware queues are empty. If the parameter @drop is set + * to %true, pending frames may be dropped. */ struct ieee80211_ops { int (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb); @@ -1601,6 +1605,7 @@ struct ieee80211_ops { #ifdef CONFIG_NL80211_TESTMODE int (*testmode_cmd)(struct ieee80211_hw *hw, void *data, int len); #endif + void (*flush)(struct ieee80211_hw *hw, bool drop); }; /** -- cgit v1.1 From 8e664fb3fd2b04e3ac5fad7f046000ba54e0e275 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 23 Dec 2009 13:15:38 +0100 Subject: mac80211: split up and insert custom IEs correctly Currently, we insert all user-specified IEs before the HT IE for association, and after the HT IE for probe requests. For association, that's correct only if the user-specified IEs are RSN only, incorrect in all other cases including WPA. Change this to split apart the user-specified IEs in two places for association: before the HT IE (e.g. RSN), after the HT IE (generally empty right now I think?) and after WMM (all other vendor-specific IEs). For probes, split the IEs in different places to be correct according to the spec. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 39 ++++++++++++++++++++++++++++++--------- 1 file changed, 30 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d62edc7..aeea282 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1085,12 +1085,12 @@ enum ieee80211_eid { WLAN_EID_TIM = 5, WLAN_EID_IBSS_PARAMS = 6, WLAN_EID_CHALLENGE = 16, - /* 802.11d */ + WLAN_EID_COUNTRY = 7, WLAN_EID_HP_PARAMS = 8, WLAN_EID_HP_TABLE = 9, WLAN_EID_REQUEST = 10, - /* 802.11e */ + WLAN_EID_QBSS_LOAD = 11, WLAN_EID_EDCA_PARAM_SET = 12, WLAN_EID_TSPEC = 13, @@ -1113,7 +1113,7 @@ enum ieee80211_eid { WLAN_EID_PREP = 69, WLAN_EID_PERR = 70, WLAN_EID_RANN = 49, /* compatible with FreeBSD */ - /* 802.11h */ + WLAN_EID_PWR_CONSTRAINT = 32, WLAN_EID_PWR_CAPABILITY = 33, WLAN_EID_TPC_REQUEST = 34, @@ -1124,20 +1124,41 @@ enum ieee80211_eid { WLAN_EID_MEASURE_REPORT = 39, WLAN_EID_QUIET = 40, WLAN_EID_IBSS_DFS = 41, - /* 802.11g */ + WLAN_EID_ERP_INFO = 42, WLAN_EID_EXT_SUPP_RATES = 50, - /* 802.11n */ + WLAN_EID_HT_CAPABILITY = 45, WLAN_EID_HT_INFORMATION = 61, - /* 802.11i */ + WLAN_EID_RSN = 48, - WLAN_EID_TIMEOUT_INTERVAL = 56, - WLAN_EID_MMIE = 76 /* 802.11w */, + WLAN_EID_MMIE = 76, WLAN_EID_WPA = 221, WLAN_EID_GENERIC = 221, WLAN_EID_VENDOR_SPECIFIC = 221, - WLAN_EID_QOS_PARAMETER = 222 + WLAN_EID_QOS_PARAMETER = 222, + + WLAN_EID_AP_CHAN_REPORT = 51, + WLAN_EID_NEIGHBOR_REPORT = 52, + WLAN_EID_RCPI = 53, + WLAN_EID_BSS_AVG_ACCESS_DELAY = 63, + WLAN_EID_ANTENNA_INFO = 64, + WLAN_EID_RSNI = 65, + WLAN_EID_MEASUREMENT_PILOT_TX_INFO = 66, + WLAN_EID_BSS_AVAILABLE_CAPACITY = 67, + WLAN_EID_BSS_AC_ACCESS_DELAY = 68, + WLAN_EID_RRM_ENABLED_CAPABILITIES = 70, + WLAN_EID_MULTIPLE_BSSID = 71, + + WLAN_EID_MOBILITY_DOMAIN = 54, + WLAN_EID_FAST_BSS_TRANSITION = 55, + WLAN_EID_TIMEOUT_INTERVAL = 56, + WLAN_EID_RIC_DATA = 57, + WLAN_EID_RIC_DESCRIPTOR = 75, + + WLAN_EID_DSE_REGISTERED_LOCATION = 58, + WLAN_EID_SUPPORTED_REGULATORY_CLASSES = 59, + WLAN_EID_EXT_CHANSWITCH_ANN = 60, }; /* Action category code */ -- cgit v1.1 From 9588bbd5529461a3dacd435bf239c84c3508f569 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Wed, 23 Dec 2009 13:15:41 +0100 Subject: cfg80211: add remain-on-channel command Add new commands for requesting the driver to remain awake on a specified channel for the specified amount of time (and another command to cancel such an operation). This can be used to implement userspace-controlled off-channel operations, like Public Action frame exchange on another channel than the operation channel. The off-channel operation should behave similarly to scan, i.e. the local station (if associated) moves into power save mode to request the AP to buffer frames for it and then moves to the other channel to allow the off-channel operation to be completed. The duration parameter can be used to request enough time to receive a response from the target station. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 36 ++++++++++++++++++++++++++++++++++++ include/net/cfg80211.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index da8ea2e..2bfbe88 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -270,6 +270,31 @@ * @NL80211_CMD_SET_WIPHY_NETNS: Set a wiphy's netns. Note that all devices * associated with this wiphy must be down and will follow. * + * @NL80211_CMD_REMAIN_ON_CHANNEL: Request to remain awake on the specified + * channel for the specified amount of time. This can be used to do + * off-channel operations like transmit a Public Action frame and wait for + * a response while being associated to an AP on another channel. + * %NL80211_ATTR_WIPHY or %NL80211_ATTR_IFINDEX is used to specify which + * radio is used. %NL80211_ATTR_WIPHY_FREQ is used to specify the + * frequency for the operation and %NL80211_ATTR_WIPHY_CHANNEL_TYPE may be + * optionally used to specify additional channel parameters. + * %NL80211_ATTR_DURATION is used to specify the duration in milliseconds + * to remain on the channel. This command is also used as an event to + * notify when the requested duration starts (it may take a while for the + * driver to schedule this time due to other concurrent needs for the + * radio). + * When called, this operation returns a cookie (%NL80211_ATTR_COOKIE) + * that will be included with any events pertaining to this request; + * the cookie is also used to cancel the request. + * @NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL: This command can be used to cancel a + * pending remain-on-channel duration if the desired operation has been + * completed prior to expiration of the originally requested duration. + * %NL80211_ATTR_WIPHY or %NL80211_ATTR_IFINDEX is used to specify the + * radio. The %NL80211_ATTR_COOKIE attribute must be given as well to + * uniquely identify the request. + * This command is also used as an event to notify when a requested + * remain-on-channel duration has expired. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -353,6 +378,9 @@ enum nl80211_commands { NL80211_CMD_DEL_PMKSA, NL80211_CMD_FLUSH_PMKSA, + NL80211_CMD_REMAIN_ON_CHANNEL, + NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -606,6 +634,10 @@ enum nl80211_commands { * @NL80211_ATTR_MAX_NUM_PMKIDS: maximum number of PMKIDs a firmware can * cache, a wiphy attribute. * + * @NL80211_ATTR_DURATION: Duration of an operation in milliseconds, u32. + * + * @NL80211_ATTR_COOKIE: Generic 64-bit cookie to identify objects. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -743,6 +775,10 @@ enum nl80211_attrs { NL80211_ATTR_PMKID, NL80211_ATTR_MAX_NUM_PMKIDS, + NL80211_ATTR_DURATION, + + NL80211_ATTR_COOKIE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 542a477..b66beb0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -988,6 +988,15 @@ struct cfg80211_pmksa { * * @dump_survey: get site survey information. * + * @remain_on_channel: Request the driver to remain awake on the specified + * channel for the specified duration to complete an off-channel + * operation (e.g., public action frame exchange). When the driver is + * ready on the requested channel, it must indicate this with an event + * notification by calling cfg80211_ready_on_channel(). + * @cancel_remain_on_channel: Cancel an on-going remain-on-channel operation. + * This allows the operation to be terminated prior to timeout based on + * the duration value. + * * @testmode_cmd: run a test mode command * * @set_pmksa: Cache a PMKID for a BSSID. This is mostly useful for fullmac @@ -1123,6 +1132,16 @@ struct cfg80211_ops { struct cfg80211_pmksa *pmksa); int (*flush_pmksa)(struct wiphy *wiphy, struct net_device *netdev); + int (*remain_on_channel)(struct wiphy *wiphy, + struct net_device *dev, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type, + unsigned int duration, + u64 *cookie); + int (*cancel_remain_on_channel)(struct wiphy *wiphy, + struct net_device *dev, + u64 cookie); + /* some temporary stuff to finish wext */ int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); @@ -2147,5 +2166,33 @@ void cfg80211_roamed(struct net_device *dev, const u8 *bssid, void cfg80211_disconnected(struct net_device *dev, u16 reason, u8 *ie, size_t ie_len, gfp_t gfp); +/** + * cfg80211_ready_on_channel - notification of remain_on_channel start + * @dev: network device + * @cookie: the request cookie + * @chan: The current channel (from remain_on_channel request) + * @channel_type: Channel type + * @duration: Duration in milliseconds that the driver intents to remain on the + * channel + * @gfp: allocation flags + */ +void cfg80211_ready_on_channel(struct net_device *dev, u64 cookie, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type, + unsigned int duration, gfp_t gfp); + +/** + * cfg80211_remain_on_channel_expired - remain_on_channel duration expired + * @dev: network device + * @cookie: the request cookie + * @chan: The current channel (from remain_on_channel request) + * @channel_type: Channel type + * @gfp: allocation flags + */ +void cfg80211_remain_on_channel_expired(struct net_device *dev, + u64 cookie, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type, + gfp_t gfp); #endif /* __NET_CFG80211_H */ -- cgit v1.1 From 98b6218388e345064c3f2d3c161383a18274c638 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 23 Dec 2009 13:15:44 +0100 Subject: mac80211/cfg80211: add station events When, for instance, a new IBSS peer is found, userspace wants to be notified. Add events for all new stations that mac80211 learns about. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b66beb0..add7993 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2195,4 +2195,16 @@ void cfg80211_remain_on_channel_expired(struct net_device *dev, enum nl80211_channel_type channel_type, gfp_t gfp); + +/** + * cfg80211_new_sta - notify userspace about station + * + * @dev: the netdev + * @mac_addr: the station's address + * @sinfo: the station information + * @gfp: allocation flags + */ +void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, + struct station_info *sinfo, gfp_t gfp); + #endif /* __NET_CFG80211_H */ -- cgit v1.1 From 1ed32e4fc8cfc9656cc1101e7f9617d485fcbe7b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 23 Dec 2009 13:15:45 +0100 Subject: mac80211: remove struct ieee80211_if_init_conf All its members (vif, mac_addr, type) are now available in the vif struct directly, so we can pass that instead of the conf struct. I generated this patch (except the mac80211 and header file changes) with this semantic patch: @@ identifier conf, fn, hw; type tp; @@ tp fn(struct ieee80211_hw *hw, -struct ieee80211_if_init_conf *conf) +struct ieee80211_vif *vif) { <... ( -conf->type +vif->type | -conf->mac_addr +vif->addr | -conf->vif +vif ) ...> } Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 57 +++++++++++++------------------------------------- 1 file changed, 15 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 77ea34b..08d4135 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -702,33 +702,6 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) } /** - * struct ieee80211_if_init_conf - initial configuration of an interface - * - * @vif: pointer to a driver-use per-interface structure. The pointer - * itself is also used for various functions including - * ieee80211_beacon_get() and ieee80211_get_buffered_bc(). - * @type: one of &enum nl80211_iftype constants. Determines the type of - * added/removed interface. - * @mac_addr: pointer to MAC address of the interface. This pointer is valid - * until the interface is removed (i.e. it cannot be used after - * remove_interface() callback was called for this interface). - * - * This structure is used in add_interface() and remove_interface() - * callbacks of &struct ieee80211_hw. - * - * When you allow multiple interfaces to be added to your PHY, take care - * that the hardware can actually handle multiple MAC addresses. However, - * also take care that when there's no interface left with mac_addr != %NULL - * you remove the MAC address from the device to avoid acknowledging packets - * in pure monitor mode. - */ -struct ieee80211_if_init_conf { - enum nl80211_iftype type; - struct ieee80211_vif *vif; - void *mac_addr; -}; - -/** * enum ieee80211_key_alg - key algorithm * @ALG_WEP: WEP40 or WEP104 * @ALG_TKIP: TKIP @@ -1555,9 +1528,9 @@ struct ieee80211_ops { int (*start)(struct ieee80211_hw *hw); void (*stop)(struct ieee80211_hw *hw); int (*add_interface)(struct ieee80211_hw *hw, - struct ieee80211_if_init_conf *conf); + struct ieee80211_vif *vif); void (*remove_interface)(struct ieee80211_hw *hw, - struct ieee80211_if_init_conf *conf); + struct ieee80211_vif *vif); int (*config)(struct ieee80211_hw *hw, u32 changed); void (*bss_info_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -1845,7 +1818,7 @@ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, /** * ieee80211_beacon_get_tim - beacon generation function * @hw: pointer obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @tim_offset: pointer to variable that will receive the TIM IE offset. * Set to 0 if invalid (in non-AP modes). * @tim_length: pointer to variable that will receive the TIM IE length, @@ -1873,7 +1846,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, /** * ieee80211_beacon_get - beacon generation function * @hw: pointer obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * See ieee80211_beacon_get_tim(). */ @@ -1886,7 +1859,7 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, /** * ieee80211_rts_get - RTS frame generation function * @hw: pointer obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame: pointer to the frame that is going to be protected by the RTS. * @frame_len: the frame length (in octets). * @frame_txctl: &struct ieee80211_tx_info of the frame. @@ -1905,7 +1878,7 @@ void ieee80211_rts_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, /** * ieee80211_rts_duration - Get the duration field for an RTS frame * @hw: pointer obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame_len: the length of the frame that is going to be protected by the RTS. * @frame_txctl: &struct ieee80211_tx_info of the frame. * @@ -1920,7 +1893,7 @@ __le16 ieee80211_rts_duration(struct ieee80211_hw *hw, /** * ieee80211_ctstoself_get - CTS-to-self frame generation function * @hw: pointer obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame: pointer to the frame that is going to be protected by the CTS-to-self. * @frame_len: the frame length (in octets). * @frame_txctl: &struct ieee80211_tx_info of the frame. @@ -1940,7 +1913,7 @@ void ieee80211_ctstoself_get(struct ieee80211_hw *hw, /** * ieee80211_ctstoself_duration - Get the duration field for a CTS-to-self frame * @hw: pointer obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame_len: the length of the frame that is going to be protected by the CTS-to-self. * @frame_txctl: &struct ieee80211_tx_info of the frame. * @@ -1956,7 +1929,7 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, /** * ieee80211_generic_frame_duration - Calculate the duration field for a frame * @hw: pointer obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame_len: the length of the frame. * @rate: the rate at which the frame is going to be transmitted. * @@ -1971,7 +1944,7 @@ __le16 ieee80211_generic_frame_duration(struct ieee80211_hw *hw, /** * ieee80211_get_buffered_bc - accessing buffered broadcast and multicast frames * @hw: pointer as obtained from ieee80211_alloc_hw(). - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * Function for accessing buffered broadcast and multicast frames. If * hardware/firmware does not implement buffering of broadcast/multicast @@ -2139,7 +2112,7 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *sta, u16 tid); /** * ieee80211_start_tx_ba_cb - low level driver ready to aggregate. - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf + * @vif: &struct ieee80211_vif pointer from the add_interface callback * @ra: receiver address of the BA session recipient. * @tid: the TID to BA on. * @@ -2150,7 +2123,7 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid); /** * ieee80211_start_tx_ba_cb_irqsafe - low level driver ready to aggregate. - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf + * @vif: &struct ieee80211_vif pointer from the add_interface callback * @ra: receiver address of the BA session recipient. * @tid: the TID to BA on. * @@ -2178,7 +2151,7 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *sta, u16 tid, /** * ieee80211_stop_tx_ba_cb - low level driver ready to stop aggregate. - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf + * @vif: &struct ieee80211_vif pointer from the add_interface callback * @ra: receiver address of the BA session recipient. * @tid: the desired TID to BA on. * @@ -2189,7 +2162,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid); /** * ieee80211_stop_tx_ba_cb_irqsafe - low level driver ready to stop aggregate. - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf + * @vif: &struct ieee80211_vif pointer from the add_interface callback * @ra: receiver address of the BA session recipient. * @tid: the desired TID to BA on. * @@ -2268,7 +2241,7 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, /** * ieee80211_beacon_loss - inform hardware does not receive beacons * - * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * When beacon filtering is enabled with IEEE80211_HW_BEACON_FILTERING and * IEEE80211_CONF_PS is set, the driver needs to inform whenever the -- cgit v1.1 From e1781ed33a8809c58ad6c3b6d432d656446efa43 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Wed, 23 Dec 2009 13:15:47 +0100 Subject: mac80211: annotate sleeping driver ops To make it easier to notice cases of calling sleeping ops in atomic context, annotate driver-ops.h with appropiate might_sleep() calls. At the same time, also document in mac80211.h the op functions with missing contexts. mac80211 doesn't seem to use get_tx_stats anywhere currently. Just to be on the safe side, I documented it to be atomic, but hopefully the op can be removed in the future. Compile-tested only. Signed-off-by: Kalle Valo Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 43 +++++++++++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 08d4135..5ee666a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1383,7 +1383,7 @@ enum ieee80211_ampdu_mlme_action { * When the device is started it should not have a MAC address * to avoid acknowledging frames before a non-monitor device * is added. - * Must be implemented. + * Must be implemented and can sleep. * * @stop: Called after last netdevice attached to the hardware * is disabled. This should turn off the hardware (at least @@ -1391,7 +1391,7 @@ enum ieee80211_ampdu_mlme_action { * May be called right after add_interface if that rejects * an interface. If you added any work onto the mac80211 workqueue * you should ensure to cancel it on this callback. - * Must be implemented. + * Must be implemented and can sleep. * * @add_interface: Called when a netdevice attached to the hardware is * enabled. Because it is not called for monitor mode devices, @start @@ -1401,7 +1401,7 @@ enum ieee80211_ampdu_mlme_action { * interface is given in the conf parameter. * The callback may refuse to add an interface by returning a * negative error code (which will be seen in userspace.) - * Must be implemented. + * Must be implemented and can sleep. * * @remove_interface: Notifies a driver that an interface is going down. * The @stop callback is called after this if it is the last interface @@ -1410,19 +1410,20 @@ enum ieee80211_ampdu_mlme_action { * must be cleared so the device no longer acknowledges packets, * the mac_addr member of the conf structure is, however, set to the * MAC address of the device going away. - * Hence, this callback must be implemented. + * Hence, this callback must be implemented. It can sleep. * * @config: Handler for configuration requests. IEEE 802.11 code calls this * function to change hardware configuration, e.g., channel. * This function should never fail but returns a negative error code - * if it does. + * if it does. The callback can sleep. * * @bss_info_changed: Handler for configuration requests related to BSS * parameters that may vary during BSS's lifespan, and may affect low * level driver (e.g. assoc/disassoc status, erp parameters). * This function should not be used if no BSS has been set, unless * for association indication. The @changed parameter indicates which - * of the bss parameters has changed when a call is made. + * of the bss parameters has changed when a call is made. The callback + * can sleep. * * @prepare_multicast: Prepare for multicast filter configuration. * This callback is optional, and its return value is passed @@ -1430,20 +1431,22 @@ enum ieee80211_ampdu_mlme_action { * * @configure_filter: Configure the device's RX filter. * See the section "Frame filtering" for more information. - * This callback must be implemented. + * This callback must be implemented and can sleep. * * @set_tim: Set TIM bit. mac80211 calls this function when a TIM bit * must be set or cleared for a given STA. Must be atomic. * * @set_key: See the section "Hardware crypto acceleration" - * This callback can sleep, and is only called between add_interface - * and remove_interface calls, i.e. while the given virtual interface + * This callback is only called between add_interface and + * remove_interface calls, i.e. while the given virtual interface * is enabled. * Returns a negative error code if the key can't be added. + * The callback can sleep. * * @update_tkip_key: See the section "Hardware crypto acceleration" * This callback will be called in the context of Rx. Called for drivers * which set IEEE80211_KEY_FLAG_TKIP_REQ_RX_P1_KEY. + * The callback can sleep. * * @hw_scan: Ask the hardware to service the scan request, no need to start * the scan state machine in stack. The scan must honour the channel @@ -1457,21 +1460,28 @@ enum ieee80211_ampdu_mlme_action { * When the scan finishes, ieee80211_scan_completed() must be called; * note that it also must be called when the scan cannot finish due to * any error unless this callback returned a negative error code. + * The callback can sleep. * * @sw_scan_start: Notifier function that is called just before a software scan * is started. Can be NULL, if the driver doesn't need this notification. + * The callback can sleep. * - * @sw_scan_complete: Notifier function that is called just after a software scan - * finished. Can be NULL, if the driver doesn't need this notification. + * @sw_scan_complete: Notifier function that is called just after a + * software scan finished. Can be NULL, if the driver doesn't need + * this notification. + * The callback can sleep. * * @get_stats: Return low-level statistics. * Returns zero if statistics are available. + * The callback can sleep. * * @get_tkip_seq: If your device implements TKIP encryption in hardware this * callback should be provided to read the TKIP transmit IVs (both IV32 * and IV16) for the given key from hardware. + * The callback must be atomic. * * @set_rts_threshold: Configuration of RTS threshold (if device needs it) + * The callback can sleep. * * @sta_notify: Notifies low level driver about addition, removal or power * state transition of an associated station, AP, IBSS/WDS/mesh peer etc. @@ -1480,30 +1490,36 @@ enum ieee80211_ampdu_mlme_action { * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max), * bursting) for a hardware TX queue. * Returns a negative error code on failure. + * The callback can sleep. * * @get_tx_stats: Get statistics of the current TX queue status. This is used * to get number of currently queued packets (queue length), maximum queue * size (limit), and total number of packets sent using each TX queue * (count). The 'stats' pointer points to an array that has hw->queues * items. + * The callback must be atomic. * * @get_tsf: Get the current TSF timer value from firmware/hardware. Currently, * this is only used for IBSS mode BSSID merging and debugging. Is not a * required function. + * The callback can sleep. * * @set_tsf: Set the TSF timer to the specified value in the firmware/hardware. * Currently, this is only used for IBSS mode debugging. Is not a * required function. + * The callback can sleep. * * @reset_tsf: Reset the TSF timer and allow firmware/hardware to synchronize * with other STAs in the IBSS. This is only used in IBSS mode. This * function is optional if the firmware/hardware takes full care of * TSF synchronization. + * The callback can sleep. * * @tx_last_beacon: Determine whether the last IBSS beacon was sent by us. * This is needed only for IBSS mode and the result of this function is * used to determine whether to reply to Probe Requests. * Returns non-zero if this device sent the last beacon. + * The callback can sleep. * * @ampdu_action: Perform a certain A-MPDU action * The RA/TID combination determines the destination and TID we want @@ -1512,16 +1528,19 @@ enum ieee80211_ampdu_mlme_action { * is the first frame we expect to perform the action on. Notice * that TX/RX_STOP can pass NULL for this parameter. * Returns a negative error code on failure. + * The callback must be atomic. * * @rfkill_poll: Poll rfkill hardware state. If you need this, you also * need to set wiphy->rfkill_poll to %true before registration, * and need to call wiphy_rfkill_set_hw_state() in the callback. + * The callback can sleep. * * @testmode_cmd: Implement a cfg80211 test mode command. + * The callback can sleep. * * @flush: Flush all pending frames from the hardware queue, making sure * that the hardware queues are empty. If the parameter @drop is set - * to %true, pending frames may be dropped. + * to %true, pending frames may be dropped. The callback can sleep. */ struct ieee80211_ops { int (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb); -- cgit v1.1 From c1c5523dd1517250cac8b15a4acbc237c24a67d4 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 23 Dec 2009 01:27:48 +0000 Subject: can/netlink: add CAN_CTRLMODE_ONE_SHOT This patch adds the flag CAN_CTRLMODE_ONE_SHOT. It is used as mask or flag in the "struct can_ctrlmode". It allows userspace via netlink to set a CAN controller into the special "one-shot" mode. In this mode, if supported by the CAN controller, it tries only once to deliver a CAN frame and aborts it if an error (e.g.: arbitration lost) happens. Signed-off-by: Marc Kleine-Budde Acked-by: Wolfgang Grandegger Signed-off-by: David S. Miller --- include/linux/can/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/can/netlink.h b/include/linux/can/netlink.h index 9ecbb78..c818335 100644 --- a/include/linux/can/netlink.h +++ b/include/linux/can/netlink.h @@ -80,6 +80,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_LOOPBACK 0x1 /* Loopback mode */ #define CAN_CTRLMODE_LISTENONLY 0x2 /* Listen-only mode */ #define CAN_CTRLMODE_3_SAMPLES 0x4 /* Triple sampling mode */ +#define CAN_CTRLMODE_ONE_SHOT 0x8 /* One-Shot mode */ /* * CAN device statistics -- cgit v1.1 From 6f7edb4881bf51300060e89915926e070ace8c4d Mon Sep 17 00:00:00 2001 From: "Catalin(ux) M. BOIE" Date: Tue, 5 Jan 2010 05:50:24 +0100 Subject: IPVS: Allow boot time change of hash size I was very frustrated about the fact that I have to recompile the kernel to change the hash size. So, I created this patch. If IPVS is built-in you can append ip_vs.conn_tab_bits=?? to kernel command line, or, if you built IPVS as modules, you can add options ip_vs conn_tab_bits=??. To keep everything backward compatible, you still can select the size at compile time, and that will be used as default. It has been about a year since this patch was originally posted and subsequently dropped on the basis of insufficient test data. Mark Bergsma has provided the following test results which seem to strongly support the need for larger hash table sizes: We do however run into the same problem with the default setting (212 = 4096 entries), as most of our LVS balancers handle around a million connections/SLAB entries at any point in time (around 100-150 kpps load). With only 4096 hash table entries this implies that each entry consists of a linked list of 256 connections *on average*. To provide some statistics, I did an oprofile run on an 2.6.31 kernel, with both the default 4096 table size, and the same kernel recompiled with IP_VS_CONN_TAB_BITS set to 18 (218 = 262144 entries). I built a quick test setup with a part of Wikimedia/Wikipedia's live traffic mirrored by the switch to the test host. With the default setting, at ~ 120 kpps packet load we saw a typical %si CPU usage of around 30-35%, and oprofile reported a hot spot in ip_vs_conn_in_get: samples % image name app name symbol name 1719761 42.3741 ip_vs.ko ip_vs.ko ip_vs_conn_in_get 302577 7.4554 bnx2 bnx2 /bnx2 181984 4.4840 vmlinux vmlinux __ticket_spin_lock 128636 3.1695 vmlinux vmlinux ip_route_input 74345 1.8318 ip_vs.ko ip_vs.ko ip_vs_conn_out_get 68482 1.6874 vmlinux vmlinux mwait_idle After loading the recompiled kernel with 218 entries, %si CPU usage dropped in half to around 12-18%, and oprofile looks much healthier, with only 7% spent in ip_vs_conn_in_get: samples % image name app name symbol name 265641 14.4616 bnx2 bnx2 /bnx2 143251 7.7986 vmlinux vmlinux __ticket_spin_lock 140661 7.6576 ip_vs.ko ip_vs.ko ip_vs_conn_in_get 94364 5.1372 vmlinux vmlinux mwait_idle 86267 4.6964 vmlinux vmlinux ip_route_input [ horms@verge.net.au: trivial up-port and minor style fixes ] Signed-off-by: Catalin(ux) M. BOIE Cc: Mark Bergsma Signed-off-by: Simon Horman Signed-off-by: Patrick McHardy --- include/net/ip_vs.h | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 8dc3296..a816c37 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -26,6 +26,11 @@ #include /* for struct ipv6hdr */ #include /* for ipv6_addr_copy */ + +/* Connections' size value needed by ip_vs_ctl.c */ +extern int ip_vs_conn_tab_size; + + struct ip_vs_iphdr { int len; __u8 protocol; @@ -592,17 +597,6 @@ extern void ip_vs_init_hash_table(struct list_head *table, int rows); * (from ip_vs_conn.c) */ -/* - * IPVS connection entry hash table - */ -#ifndef CONFIG_IP_VS_TAB_BITS -#define CONFIG_IP_VS_TAB_BITS 12 -#endif - -#define IP_VS_CONN_TAB_BITS CONFIG_IP_VS_TAB_BITS -#define IP_VS_CONN_TAB_SIZE (1 << IP_VS_CONN_TAB_BITS) -#define IP_VS_CONN_TAB_MASK (IP_VS_CONN_TAB_SIZE - 1) - enum { IP_VS_DIR_INPUT = 0, IP_VS_DIR_OUTPUT, -- cgit v1.1 From fc6a110754476362f9f4fa3199a637f2331c5993 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Mon, 4 Jan 2010 02:02:47 +0000 Subject: Phonet: zero-copy aligned GPRS RX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Newer Nokia cellular modems can use aligned payload for their GPRS pipe. Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/pep.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h index 4c61cdc..c371625 100644 --- a/include/net/phonet/pep.h +++ b/include/net/phonet/pep.h @@ -77,6 +77,7 @@ static inline struct pnpipehdr *pnp_hdr(struct sk_buff *skb) enum { PNS_PIPE_DATA = 0x20, + PNS_PIPE_ALIGNED_DATA, PNS_PEP_CONNECT_REQ = 0x40, PNS_PEP_CONNECT_RESP, -- cgit v1.1 From fea93ecef619b5779ca6984568517b1685079b05 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Mon, 4 Jan 2010 02:02:48 +0000 Subject: Phonet: zero-copy GPRS TX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Send aligned pipe payload if requested to do so. Then, the socket buffer needs not be fragmented anymore. Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/pep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h index c371625..35672b1 100644 --- a/include/net/phonet/pep.h +++ b/include/net/phonet/pep.h @@ -44,6 +44,7 @@ struct pep_sock { u8 rx_fc; /* RX flow control */ u8 tx_fc; /* TX flow control */ u8 init_enable; /* auto-enable at creation */ + u8 aligned; }; static inline struct pep_sock *pep_sk(struct sock *sk) @@ -139,6 +140,7 @@ enum { PN_PIPE_SB_NEGOTIATED_FC, PN_PIPE_SB_REQUIRED_FC_TX, PN_PIPE_SB_PREFERRED_FC_RX, + PN_PIPE_SB_ALIGNED_DATA, }; /* Phonet pipe flow control models */ -- cgit v1.1 From 65324144b50bc7022cc9b6ca8f4a536a957019e3 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 5 Jan 2010 05:50:47 +0000 Subject: net: RFC3069, private VLAN proxy arp support This is to be used together with switch technologies, like RFC3069, that where the individual ports are not allowed to communicate with each other, but they are allowed to talk to the upstream router. As described in RFC 3069, it is possible to allow these hosts to communicate through the upstream router by proxy_arp'ing. This patch basically allow proxy arp replies back to the same interface (from which the ARP request/solicitation was received). Tunable per device via proc "proxy_arp_pvlan": /proc/sys/net/ipv4/conf/*/proxy_arp_pvlan This switch technology is known by different vendor names: - In RFC 3069 it is called VLAN Aggregation. - Cisco and Allied Telesyn call it Private VLAN. - Hewlett-Packard call it Source-Port filtering or port-isolation. - Ericsson call it MAC-Forced Forwarding (RFC Draft). Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 + include/linux/sysctl.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 699e85c..9a8c574 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -88,6 +88,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) +#define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_CONF_GET(in_dev, PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 877ba03..24ff7e3 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -482,6 +482,7 @@ enum NET_IPV4_CONF_ARP_ACCEPT=21, NET_IPV4_CONF_ARP_NOTIFY=22, NET_IPV4_CONF_ACCEPT_LOCAL=23, + NET_IPV4_CONF_PROXY_ARP_PVLAN=24, __NET_IPV4_CONF_MAX }; -- cgit v1.1 From 3c9732c06879d85f2fdf7ec69198c1d78da42a98 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 6 Jan 2010 23:07:13 +0000 Subject: stmmac: add the new Header file for stmmac platform data Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/stmmac.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 include/linux/stmmac.h (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h new file mode 100644 index 0000000..32bfd1a --- /dev/null +++ b/include/linux/stmmac.h @@ -0,0 +1,53 @@ +/******************************************************************************* + + Header file for stmmac platform data + + Copyright (C) 2009 STMicroelectronics Ltd + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope 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. + + 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., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Author: Giuseppe Cavallaro +*******************************************************************************/ + +#ifndef __STMMAC_PLATFORM_DATA +#define __STMMAC_PLATFORM_DATA + +/* platfrom data for platfrom device structure's platfrom_data field */ + +/* Private data for the STM on-board ethernet driver */ +struct plat_stmmacenet_data { + int bus_id; + int pbl; + int has_gmac; + void (*fix_mac_speed)(void *priv, unsigned int speed); + void (*bus_setup)(unsigned long ioaddr); +#ifdef CONFIG_STM_DRIVERS + struct stm_pad_config *pad_config; +#endif + void *bsp_priv; +}; + +struct plat_stmmacphy_data { + int bus_id; + int phy_addr; + unsigned int phy_mask; + int interface; + int (*phy_reset)(void *priv); + void *priv; +}; +#endif + -- cgit v1.1 From d218d11133d888f9745802146a50255a4781d37a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 11 Jan 2010 16:28:01 -0800 Subject: tcp: Generalized TTL Security Mechanism This patch adds the kernel portions needed to implement RFC 5082 Generalized TTL Security Mechanism (GTSM). It is a lightweight security measure against forged packets causing DoS attacks (for BGP). This is already implemented the same way in BSD kernels. For the necessary Quagga patch http://www.gossamer-threads.com/lists/quagga/dev/17389 Description from Cisco http://www.cisco.com/en/US/docs/ios/12_3t/12_3t7/feature/guide/gt_btsh.html It does add one byte to each socket structure, but I did a little rearrangement to reuse a hole (on 64 bit), but it does grow the structure on 32 bit This should be documented on ip(4) man page and the Glibc in.h file also needs update. IPV6_MINHOPLIMIT should also be added (although BSD doesn't support that). Only TCP is supported, but could also be added to UDP, DCCP, SCTP if desired. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/in.h | 2 ++ include/net/inet_sock.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/in.h b/include/linux/in.h index b615649..583c76f 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -84,6 +84,8 @@ struct in_addr { #define IP_ORIGDSTADDR 20 #define IP_RECVORIGDSTADDR IP_ORIGDSTADDR +#define IP_MINTTL 21 + /* IP_MTU_DISCOVER values */ #define IP_PMTUDISC_DONT 0 /* Never send DF frames */ #define IP_PMTUDISC_WANT 1 /* Use per route hints */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index bd4c53f..83fd344 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -122,10 +122,12 @@ struct inet_sock { __be32 inet_saddr; __s16 uc_ttl; __u16 cmsg_flags; - struct ip_options *opt; __be16 inet_sport; __u16 inet_id; + + struct ip_options *opt; __u8 tos; + __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; __u8 recverr:1, -- cgit v1.1 From 3ccd4c6167d3b39d52631767ebbf8b5677c5855d Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 12 Jan 2010 02:00:46 -0800 Subject: can: Unify droping of invalid tx skbs and netdev stats To prevent the CAN drivers to operate on invalid socketbuffers the skbs are now checked and silently dropped at the xmit-function consistently. Also the netdev stats are consistently using the CAN data length code (dlc) for [rx|tx]_bytes now. Signed-off-by: Oliver Hartkopp Acked-by: Wolfgang Grandegger Signed-off-by: David S. Miller --- include/linux/can/dev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 3db7767..7e7c98a 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -60,6 +60,21 @@ struct can_priv { */ #define get_can_dlc(i) (min_t(__u8, (i), 8)) +/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ +static inline int can_dropped_invalid_skb(struct net_device *dev, + struct sk_buff *skb) +{ + const struct can_frame *cf = (struct can_frame *)skb->data; + + if (unlikely(skb->len != sizeof(*cf) || cf->can_dlc > 8)) { + kfree_skb(skb); + dev->stats.tx_dropped++; + return 1; + } + + return 0; +} + struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max); void free_candev(struct net_device *dev); -- cgit v1.1 From 81077e82c3f591578625805dd6464a27a9ff56ec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Luk=C3=A1=C5=A1=20Turek?= <8an@praha12.net> Date: Mon, 21 Dec 2009 22:50:47 +0100 Subject: nl80211: Add new WIPHY attribute COVERAGE_CLASS The new attribute NL80211_ATTR_WIPHY_COVERAGE_CLASS sets IEEE 802.11 Coverage Class, which depends on maximum distance of nodes in a wireless network. It's required for long distance links (more than a few hundred meters). The attribute is now ignored by two non-mac80211 drivers, rndis and iwmc3200wifi, together with WIPHY_PARAM_RETRY_SHORT and WIPHY_PARAM_RETRY_LONG. If it turns out to be a problem, we could split set_wiphy_params callback or add new capability bits. Signed-off-by: Lukas Turek <8an@praha12.net> Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ include/net/cfg80211.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 2bfbe88..d4c556d 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -430,6 +430,8 @@ enum nl80211_commands { * @NL80211_ATTR_WIPHY_RTS_THRESHOLD: RTS threshold (TX frames with length * larger than or equal to this use RTS/CTS handshake); allowed range: * 0..65536, disable with (u32)-1; dot11RTSThreshold; u32 + * @NL80211_ATTR_WIPHY_COVERAGE_CLASS: Coverage Class as defined by IEEE 802.11 + * section 7.3.2.9; dot11CoverageClass; u8 * * @NL80211_ATTR_IFINDEX: network interface index of the device to operate on * @NL80211_ATTR_IFNAME: network interface name @@ -779,6 +781,8 @@ enum nl80211_attrs { NL80211_ATTR_COOKIE, + NL80211_ATTR_WIPHY_COVERAGE_CLASS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index add7993..a8d5d04 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -837,6 +837,7 @@ enum wiphy_params_flags { WIPHY_PARAM_RETRY_LONG = 1 << 1, WIPHY_PARAM_FRAG_THRESHOLD = 1 << 2, WIPHY_PARAM_RTS_THRESHOLD = 1 << 3, + WIPHY_PARAM_COVERAGE_CLASS = 1 << 4, }; /** @@ -1236,6 +1237,7 @@ struct wiphy { u8 retry_long; u32 frag_threshold; u32 rts_threshold; + u8 coverage_class; char fw_version[ETHTOOL_BUSINFO_LEN]; u32 hw_version; -- cgit v1.1 From 310bc676e314e92c18257bfc916951879451ee32 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Luk=C3=A1=C5=A1=20Turek?= <8an@praha12.net> Date: Mon, 21 Dec 2009 22:50:48 +0100 Subject: mac80211: Add new callback set_coverage_class Mac80211 callback to driver set_coverage_class() sets slot time and ACK timeout for given IEEE 802.11 coverage class. The callback is optional, but it's essential for long distance links. Signed-off-by: Lukas Turek <8an@praha12.net> Signed-off-by: John W. Linville --- include/net/mac80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f073a2a..ad4b700 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1533,6 +1533,10 @@ enum ieee80211_ampdu_mlme_action { * and need to call wiphy_rfkill_set_hw_state() in the callback. * The callback can sleep. * + * @set_coverage_class: Set slot time for given coverage class as specified + * in IEEE 802.11-2007 section 17.3.8.6 and modify ACK timeout + * accordingly. This callback is not required and may sleep. + * * @testmode_cmd: Implement a cfg80211 test mode command. * The callback can sleep. * @@ -1592,6 +1596,7 @@ struct ieee80211_ops { struct ieee80211_sta *sta, u16 tid, u16 *ssn); void (*rfkill_poll)(struct ieee80211_hw *hw); + void (*set_coverage_class)(struct ieee80211_hw *hw, u8 coverage_class); #ifdef CONFIG_NL80211_TESTMODE int (*testmode_cmd)(struct ieee80211_hw *hw, void *data, int len); #endif -- cgit v1.1 From e00cfce0cb2a397859607bf515c6de9ce064b64a Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Tue, 29 Dec 2009 12:59:19 +0200 Subject: mac80211: Select lowest rate based on basic rate set in AP mode If the basic rate set is configured to not include the lowest rate (e.g., basic rate set = 6, 12, 24 Mbps in IEEE 802.11g mode), the AP should not send out broadcast frames at 1 Mbps. This type of configuration can be used to optimize channel usage in cases where there is no need for backwards compatibility with IEEE 802.11b-only devices. In AP mode, mac80211 was unconditionally using the lowest rate for Beacon frames and similarly, with all rate control algorithms that use rate_control_send_low(), the lowest rate ended up being used for all broadcast frames (and all unicast frames that are sent before association). Change this to take into account the basic rate configuration in AP mode, i.e., use the lowest rate in the basic rate set instead of the lowest supported rate when selecting the rate. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ad4b700..39c516c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2299,6 +2299,7 @@ enum rate_control_changed { * @max_rate_idx: user-requested maximum rate (not MCS for now) * @skb: the skb that will be transmitted, the control information in it needs * to be filled in + * @ap: whether this frame is sent out in AP mode */ struct ieee80211_tx_rate_control { struct ieee80211_hw *hw; @@ -2308,6 +2309,7 @@ struct ieee80211_tx_rate_control { struct ieee80211_tx_rate reported_rate; bool rts, short_preamble; u8 max_rate_idx; + bool ap; }; struct rate_control_ops { -- cgit v1.1 From 37eb0b164cf9fa9f70c8500926f5cde7c652f48e Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Wed, 6 Jan 2010 13:09:08 +0200 Subject: cfg80211/mac80211: Use more generic bitrate mask for rate control Extend struct cfg80211_bitrate_mask to actually use a bitfield mask instead of just a single fixed or maximum rate index. This change itself does not modify the behavior (except for debugfs files), but it prepares cfg80211 and mac80211 for a new nl80211 command for setting which rates can be used in TX rate control. Since frames are now going through the rate control algorithm unconditionally, the internal IEEE80211_TX_INTFL_RCALGO flag can now be removed. The RC implementations can use the rate_idx_mask value to optimize their behavior if only a single rate is enabled. The old max_rate_idx in struct ieee80211_tx_rate_control is maintained (but commented as deprecated) for backwards compatibility with existing RC implementations. Once these implementations have been updated to use the more generic rate_idx_mask, the max_rate_idx value can be removed. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/net/cfg80211.h | 13 ++----------- include/net/mac80211.h | 8 ++++---- 2 files changed, 6 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a8d5d04..22e062a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -857,20 +857,11 @@ enum tx_power_setting { * cfg80211_bitrate_mask - masks for bitrate control */ struct cfg80211_bitrate_mask { -/* - * As discussed in Berlin, this struct really - * should look like this: - struct { u32 legacy; - u8 mcs[IEEE80211_HT_MCS_MASK_LEN]; + /* TODO: add support for masking MCS rates; e.g.: */ + /* u8 mcs[IEEE80211_HT_MCS_MASK_LEN]; */ } control[IEEE80211_NUM_BANDS]; - - * Since we can always fix in-kernel users, let's keep - * it simpler for now: - */ - u32 fixed; /* fixed bitrate, 0 == not fixed */ - u32 maxrate; /* in kbps, 0 == no limit */ }; /** * struct cfg80211_pmksa - PMK Security Association diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 39c516c..7e5af6d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -255,9 +255,6 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_CTL_RATE_CTRL_PROBE: internal to mac80211, can be * set by rate control algorithms to indicate probe rate, will * be cleared for fragmented frames (except on the last fragment) - * @IEEE80211_TX_INTFL_RCALGO: mac80211 internal flag, do not test or - * set this flag in the driver; indicates that the rate control - * algorithm was used and should be notified of TX status * @IEEE80211_TX_INTFL_NEED_TXPROCESSING: completely internal to mac80211, * used to indicate that a pending frame requires TX processing before * it can be sent out. @@ -287,7 +284,6 @@ enum mac80211_tx_control_flags { IEEE80211_TX_STAT_AMPDU = BIT(10), IEEE80211_TX_STAT_AMPDU_NO_BACK = BIT(11), IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12), - IEEE80211_TX_INTFL_RCALGO = BIT(13), IEEE80211_TX_INTFL_NEED_TXPROCESSING = BIT(14), IEEE80211_TX_INTFL_RETRIED = BIT(15), IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16), @@ -2297,6 +2293,9 @@ enum rate_control_changed { * @short_preamble: whether mac80211 will request short-preamble transmission * if the selected rate supports it * @max_rate_idx: user-requested maximum rate (not MCS for now) + * (deprecated; this will be removed once drivers get updated to use + * rate_idx_mask) + * @rate_idx_mask: user-requested rate mask (not MCS for now) * @skb: the skb that will be transmitted, the control information in it needs * to be filled in * @ap: whether this frame is sent out in AP mode @@ -2309,6 +2308,7 @@ struct ieee80211_tx_rate_control { struct ieee80211_tx_rate reported_rate; bool rts, short_preamble; u8 max_rate_idx; + u32 rate_idx_mask; bool ap; }; -- cgit v1.1 From 13ae75b103e07304a34ab40c9136e9f53e06475c Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Tue, 29 Dec 2009 12:59:45 +0200 Subject: nl80211: New command for setting TX rate mask for rate control Add a new NL80211_CMD_SET_TX_BITRATE_MASK command and related attributes to provide support for setting TX rate mask for rate control. This uses the existing cfg80211 set_bitrate_mask operation that was previously used only with WEXT compat code (SIOCSIWRATE). The nl80211 command allows more generic configuration of allowed rates as a mask instead of fixed/max rate. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/net/cfg80211.h | 4 ++-- 2 files changed, 46 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index d4c556d..7a1c8c1 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -295,6 +295,10 @@ * This command is also used as an event to notify when a requested * remain-on-channel duration has expired. * + * @NL80211_CMD_SET_TX_BITRATE_MASK: Set the mask of rates to be used in TX + * rate selection. %NL80211_ATTR_IFINDEX is used to specify the interface + * and @NL80211_ATTR_TX_RATES the set of allowed rates. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -381,6 +385,8 @@ enum nl80211_commands { NL80211_CMD_REMAIN_ON_CHANNEL, NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, + NL80211_CMD_SET_TX_BITRATE_MASK, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -640,6 +646,13 @@ enum nl80211_commands { * * @NL80211_ATTR_COOKIE: Generic 64-bit cookie to identify objects. * + * @NL80211_ATTR_TX_RATES: Nested set of attributes + * (enum nl80211_tx_rate_attributes) describing TX rates per band. The + * enum nl80211_band value is used as the index (nla_type() of the nested + * data. If a band is not included, it will be configured to allow all + * rates based on negotiated supported rates information. This attribute + * is used with %NL80211_CMD_SET_TX_BITRATE_MASK. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -783,6 +796,8 @@ enum nl80211_attrs { NL80211_ATTR_WIPHY_COVERAGE_CLASS, + NL80211_ATTR_TX_RATES, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1482,4 +1497,33 @@ enum nl80211_key_attributes { NL80211_KEY_MAX = __NL80211_KEY_AFTER_LAST - 1 }; +/** + * enum nl80211_tx_rate_attributes - TX rate set attributes + * @__NL80211_TXRATE_INVALID: invalid + * @NL80211_TXRATE_LEGACY: Legacy (non-MCS) rates allowed for TX rate selection + * 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_AFTER_LAST: internal + * @NL80211_TXRATE_MAX: highest TX rate attribute + */ +enum nl80211_tx_rate_attributes { + __NL80211_TXRATE_INVALID, + NL80211_TXRATE_LEGACY, + + /* keep last */ + __NL80211_TXRATE_AFTER_LAST, + NL80211_TXRATE_MAX = __NL80211_TXRATE_AFTER_LAST - 1 +}; + +/** + * enum nl80211_band - Frequency band + * @NL80211_BAND_2GHZ - 2.4 GHz ISM band + * @NL80211_BAND_5GHZ - around 5 GHz band (4.9 - 5.7 GHz) + */ +enum nl80211_band { + NL80211_BAND_2GHZ, + NL80211_BAND_5GHZ, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 22e062a..0d73441 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -39,8 +39,8 @@ * @IEEE80211_BAND_5GHZ: around 5GHz band (4.9-5.7) */ enum ieee80211_band { - IEEE80211_BAND_2GHZ, - IEEE80211_BAND_5GHZ, + IEEE80211_BAND_2GHZ = NL80211_BAND_2GHZ, + IEEE80211_BAND_5GHZ = NL80211_BAND_5GHZ, /* keep last */ IEEE80211_NUM_BANDS -- cgit v1.1 From 7044cc565b45a898c140fb185174a66f2d68a163 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Tue, 5 Jan 2010 20:16:19 +0200 Subject: mac80211: add functions to create PS Poll and Nullfunc templates Some hardware, for example wl1251 and wl1271, handle the transmission of power save related frames in hardware, but the driver is responsible for creating the templates. It's better to create the templates in mac80211, that way all drivers can benefit from this. Add two new functions, ieee80211_pspoll_get() and ieee80211_nullfunc_get() which drivers need to call to get the frame. Drivers are also responsible for updating the templates after each association. Also new struct ieee80211_hdr_3addr is added to ieee80211.h to make it easy to calculate length of the Nullfunc frame. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 9 +++++++++ include/net/mac80211.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index aeea282..602c069 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -130,6 +130,15 @@ struct ieee80211_hdr { u8 addr4[6]; } __attribute__ ((packed)); +struct ieee80211_hdr_3addr { + __le16 frame_control; + __le16 duration_id; + u8 addr1[6]; + u8 addr2[6]; + u8 addr3[6]; + __le16 seq_ctrl; +} __attribute__ ((packed)); + /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7e5af6d..75f46e2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1875,6 +1875,36 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, } /** + * ieee80211_pspoll_get - retrieve a PS Poll template + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * Creates a PS Poll a template which can, for example, uploaded to + * hardware. The template must be updated after association so that correct + * AID, BSSID and MAC address is used. + * + * Note: Caller (or hardware) is responsible for setting the + * &IEEE80211_FCTL_PM bit. + */ +struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + +/** + * ieee80211_nullfunc_get - retrieve a nullfunc template + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * Creates a Nullfunc template which can, for example, uploaded to + * hardware. The template must be updated after association so that correct + * BSSID and address is used. + * + * Note: Caller (or hardware) is responsible for setting the + * &IEEE80211_FCTL_PM bit as well as Duration and Sequence Control fields. + */ +struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + +/** * ieee80211_rts_get - RTS frame generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. -- cgit v1.1 From 05e54ea6cce400ac34528d705179b45244f61074 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Tue, 5 Jan 2010 20:16:38 +0200 Subject: mac80211: create Probe Request template Certain type of hardware, for example wl1251 and wl1271, need a template for the Probe Request. Create a function ieee80211_probereq_get() which creates the template and drivers send it to hardware. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/net/mac80211.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 75f46e2..e1e73c6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1905,6 +1905,23 @@ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif); /** + * ieee80211_probereq_get - retrieve a Probe Request template + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @ssid: SSID buffer + * @ssid_len: length of SSID + * @ie: buffer containing all IEs except SSID for the template + * @ie_len: length of the IE buffer + * + * Creates a Probe Request template which can, for example, be uploaded to + * hardware. + */ +struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + const u8 *ssid, size_t ssid_len, + const u8 *ie, size_t ie_len); + +/** * ieee80211_rts_get - RTS frame generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. -- cgit v1.1 From 34a6eddbabd704b3c7dae9362234552267573be2 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Wed, 6 Jan 2010 16:19:24 +0200 Subject: cfg80211: Store IEs from both Beacon and Probe Response frames Store information elements from Beacon and Probe Response frames in separate buffers to allow both sets to be made available through nl80211. This allows user space applications to get access to IEs from Beacon frames even if we have received Probe Response frames from the BSS. Previously, the IEs from Probe Response frames would have overridden the IEs from Beacon frames. This feature is of somewhat limited use since most protocols include the same (or extended) information in Probe Response frames. However, there are couple of exceptions where the IEs from Beacon frames could be of some use: TIM IE is only included in Beacon frames (and it would be needed to figure out the DTIM period used in the BSS) and at least some implementations of Wireless Provisioning Services seem to include the full IE only in Beacon frames). The new BSS attribute for scan results is added to allow both the IE sets to be delivered. This is done in a way that maintains the previously used behavior for applications that are not aware of the new NL80211_BSS_BEACON_IES attribute. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 10 +++++++++- include/net/cfg80211.h | 12 +++++++++++- 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 7a1c8c1..127a730 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1378,13 +1378,20 @@ enum nl80211_channel_type { * @NL80211_BSS_BEACON_INTERVAL: beacon interval of the (I)BSS (u16) * @NL80211_BSS_CAPABILITY: capability field (CPU order, u16) * @NL80211_BSS_INFORMATION_ELEMENTS: binary attribute containing the - * raw information elements from the probe response/beacon (bin) + * raw information elements from the probe response/beacon (bin); + * if the %NL80211_BSS_BEACON_IES attribute is present, the IEs here are + * from a Probe Response frame; otherwise they are from a Beacon frame. + * However, if the driver does not indicate the source of the IEs, these + * IEs may be from either frame subtype. * @NL80211_BSS_SIGNAL_MBM: signal strength of probe response/beacon * in mBm (100 * dBm) (s32) * @NL80211_BSS_SIGNAL_UNSPEC: signal strength of the probe response/beacon * in unspecified units, scaled to 0..100 (u8) * @NL80211_BSS_STATUS: status, if this BSS is "used" * @NL80211_BSS_SEEN_MS_AGO: age of this BSS entry in ms + * @NL80211_BSS_BEACON_IES: binary attribute containing the raw information + * elements from a Beacon frame (bin); not present if no Beacon frame has + * yet been received * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -1400,6 +1407,7 @@ enum nl80211_bss { NL80211_BSS_SIGNAL_UNSPEC, NL80211_BSS_STATUS, NL80211_BSS_SEEN_MS_AGO, + NL80211_BSS_BEACON_IES, /* keep last */ __NL80211_BSS_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0d73441..2af5270 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -626,8 +626,14 @@ enum cfg80211_signal_type { * @beacon_interval: the beacon interval as from the frame * @capability: the capability field in host byte order * @information_elements: the information elements (Note that there - * is no guarantee that these are well-formed!) + * is no guarantee that these are well-formed!); this is a pointer to + * either the beacon_ies or proberesp_ies depending on whether Probe + * Response frame has been received * @len_information_elements: total length of the information elements + * @beacon_ies: the information elements from the last Beacon frame + * @len_beacon_ies: total length of the beacon_ies + * @proberesp_ies: the information elements from the last Probe Response frame + * @len_proberesp_ies: total length of the proberesp_ies * @signal: signal strength value (type depends on the wiphy's signal_type) * @free_priv: function pointer to free private data * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes @@ -641,6 +647,10 @@ struct cfg80211_bss { u16 capability; u8 *information_elements; size_t len_information_elements; + u8 *beacon_ies; + size_t len_beacon_ies; + u8 *proberesp_ies; + size_t len_proberesp_ies; s32 signal; -- cgit v1.1 From ab13315af97919fae0e014748105fdc2e30afb2d Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Tue, 12 Jan 2010 10:42:31 +0200 Subject: mac80211: add U-APSD client support Add Unscheduled Automatic Power-Save Delivery (U-APSD) client support. The idea is that the data frames from the client trigger AP to send the buffered frames with ACs which have U-APSD enabled. This decreases latency and makes it possible to save even more power. Driver needs to use IEEE80211_HW_UAPSD to enable the feature. The current implementation assumes that firmware takes care of the wakeup and hardware needing IEEE80211_HW_PS_NULLFUNC_STACK is not yet supported. Tested with wl1251 on a Nokia N900 and Cisco Aironet 1231G AP and running various test traffic with ping. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 18 ++++++++++++++++++ include/net/mac80211.h | 7 +++++++ 2 files changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 602c069..a8c6069 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -120,6 +120,24 @@ #define IEEE80211_QOS_CTL_TID_MASK 0x000F #define IEEE80211_QOS_CTL_TAG1D_MASK 0x0007 +/* U-APSD queue for WMM IEs sent by AP */ +#define IEEE80211_WMM_IE_AP_QOSINFO_UAPSD (1<<7) + +/* U-APSD queues for WMM IEs sent by STA */ +#define IEEE80211_WMM_IE_STA_QOSINFO_AC_VO (1<<0) +#define IEEE80211_WMM_IE_STA_QOSINFO_AC_VI (1<<1) +#define IEEE80211_WMM_IE_STA_QOSINFO_AC_BK (1<<2) +#define IEEE80211_WMM_IE_STA_QOSINFO_AC_BE (1<<3) +#define IEEE80211_WMM_IE_STA_QOSINFO_AC_MASK 0x0f + +/* U-APSD max SP length for WMM IEs sent by STA */ +#define IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL 0x00 +#define IEEE80211_WMM_IE_STA_QOSINFO_SP_2 0x01 +#define IEEE80211_WMM_IE_STA_QOSINFO_SP_4 0x02 +#define IEEE80211_WMM_IE_STA_QOSINFO_SP_6 0x03 +#define IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK 0x03 +#define IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT 5 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e1e73c6..f313a3c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -113,6 +113,7 @@ struct ieee80211_tx_queue_params { u16 cw_min; u16 cw_max; u8 aifs; + bool uapsd; }; /** @@ -929,6 +930,11 @@ enum ieee80211_tkip_key_type { * Hardware supports dynamic spatial multiplexing powersave, * ie. can turn off all but one chain and then wake the rest * up as required after, for example, rts/cts handshake. + * + * @IEEE80211_HW_SUPPORTS_UAPSD: + * Hardware supports Unscheduled Automatic Power Save Delivery + * (U-APSD) in managed mode. The mode is configured with + * conf_tx() operation. */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -948,6 +954,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_BEACON_FILTER = 1<<14, IEEE80211_HW_SUPPORTS_STATIC_SMPS = 1<<15, IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS = 1<<16, + IEEE80211_HW_SUPPORTS_UAPSD = 1<<17, }; /** -- cgit v1.1 From 558a6669d7cb407fbb0b5aec184b5c3b9a893d30 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Tue, 12 Jan 2010 10:43:00 +0200 Subject: ieee80211: add struct ieee80211_hdr_qos The header can be used to create qos nullfunc frames, for example. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a8c6069..8427019 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -157,6 +157,16 @@ struct ieee80211_hdr_3addr { __le16 seq_ctrl; } __attribute__ ((packed)); +struct ieee80211_qos_hdr { + __le16 frame_control; + __le16 duration_id; + u8 addr1[6]; + u8 addr2[6]; + u8 addr3[6]; + __le16 seq_ctrl; + __le16 qos_ctrl; +} __attribute__ ((packed)); + /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder -- cgit v1.1 From cd8c20b650f49354722b8cc1f03320b004815a0a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 13 Jan 2010 16:02:14 +0100 Subject: netfilter: nfnetlink: netns support Make nfnl socket per-petns. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink.h | 8 ++++---- include/net/net_namespace.h | 2 ++ 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 49d321f..5392386 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -73,11 +73,11 @@ struct nfnetlink_subsystem { extern int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); -extern int nfnetlink_has_listeners(unsigned int group); -extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, +extern int nfnetlink_has_listeners(struct net *net, unsigned int group); +extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo, gfp_t flags); -extern void nfnetlink_set_err(u32 pid, u32 group, int error); -extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags); +extern void nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error); +extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags); extern void nfnl_lock(void); extern void nfnl_unlock(void); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index f307e13..82b7be4 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -81,6 +81,8 @@ struct net { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif + struct sock *nfnl; + struct sock *nfnl_stash; #endif #ifdef CONFIG_XFRM struct netns_xfrm xfrm; -- cgit v1.1 From 508e14b4a4fb1a824a14f2c5b8d7df67b313f8e4 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 12 Jan 2010 14:27:30 +0000 Subject: netpoll: allow execution of multiple rx_hooks per interface Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netpoll.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 2524267..a765ea8 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -21,15 +21,20 @@ struct netpoll { __be32 local_ip, remote_ip; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; + + struct list_head rx; /* rx_np list element */ }; struct netpoll_info { atomic_t refcnt; + int rx_flags; spinlock_t rx_lock; - struct netpoll *rx_np; /* netpoll that registered an rx_hook */ + struct list_head rx_np; /* netpolls that registered an rx_hook */ + struct sk_buff_head arp_tx; /* list of arp requests to reply to */ struct sk_buff_head txq; + struct delayed_work tx_work; }; @@ -51,7 +56,7 @@ static inline int netpoll_rx(struct sk_buff *skb) unsigned long flags; int ret = 0; - if (!npinfo || (!npinfo->rx_np && !npinfo->rx_flags)) + if (!npinfo || (list_empty(&npinfo->rx_np) && !npinfo->rx_flags)) return 0; spin_lock_irqsave(&npinfo->rx_lock, flags); @@ -67,7 +72,7 @@ static inline int netpoll_rx_on(struct sk_buff *skb) { struct netpoll_info *npinfo = skb->dev->npinfo; - return npinfo && (npinfo->rx_np || npinfo->rx_flags); + return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags); } static inline int netpoll_receive_skb(struct sk_buff *skb) -- cgit v1.1 From 9a58a80a701bdb2d220cdab4914218df5b48d781 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 14 Jan 2010 03:10:54 -0800 Subject: proc_fops: convert drivers/isdn/ to seq_file Convert code away from ->read_proc/->write_proc interfaces. Switch to proc_create()/proc_create_data() which make addition of proc entries reliable wrt NULL ->proc_fops, NULL ->data and so on. Problem with ->read_proc et al is described here commit 786d7e1612f0b0adb6046f19b906609e4fe8b1ba "Fix rmmod/read/write races in /proc entries" [akpm@linux-foundation.org: CONFIG_PROC_FS=n build fix] Signed-off-by: Alexey Dobriyan Signed-off-by: Tilman Schmidt Signed-off-by: Karsten Keil Signed-off-by: David S. Miller --- include/linux/isdn/capilli.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/isdn/capilli.h b/include/linux/isdn/capilli.h index 7acb87a..d3e5e9d 100644 --- a/include/linux/isdn/capilli.h +++ b/include/linux/isdn/capilli.h @@ -50,8 +50,7 @@ struct capi_ctr { u16 (*send_message)(struct capi_ctr *, struct sk_buff *skb); char *(*procinfo)(struct capi_ctr *); - int (*ctr_read_proc)(char *page, char **start, off_t off, - int count, int *eof, struct capi_ctr *card); + const struct file_operations *proc_fops; /* filled in before calling ready callback */ u8 manu[CAPI_MANUFACTURER_LEN]; /* CAPI_GET_MANUFACTURER */ -- cgit v1.1 From 9d173fc5dfa8c1b4578b331ac7ff3ce8af27006e Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Thu, 14 Jan 2010 13:09:14 +0200 Subject: mac80211: fix mac80211.h documentation warnings There were some warnings about missing documentation and a missing reference. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/net/mac80211.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f313a3c..bbfa475 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -107,6 +107,7 @@ enum ieee80211_max_queues { * 2^n-1 in the range 1..32767] * @cw_max: maximum contention window [like @cw_min] * @txop: maximum burst time in units of 32 usecs, 0 meaning disabled + * @uapsd: is U-APSD mode enabled for the queue */ struct ieee80211_tx_queue_params { u16 txop; @@ -608,7 +609,11 @@ enum ieee80211_conf_changed { /** * enum ieee80211_smps_mode - spatial multiplexing power save mode * - * @ + * @IEEE80211_SMPS_AUTOMATIC: automatic + * @IEEE80211_SMPS_OFF: off + * @IEEE80211_SMPS_STATIC: static + * @IEEE80211_SMPS_DYNAMIC: dynamic + * @IEEE80211_SMPS_NUM_MODES: internal, don't use */ enum ieee80211_smps_mode { IEEE80211_SMPS_AUTOMATIC, -- cgit v1.1 From c99445b14054e0c4ed4715df1dad1fc608cbab46 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Thu, 14 Jan 2010 13:09:21 +0200 Subject: mac80211: improve powersave documentation There has been some confusion how drivers should implement powersave support. Improve the documentation a bit to make it more clear what drivers need to do. Also mention about U-APSD. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/net/mac80211.h | 75 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 54 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index bbfa475..c90047d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -569,7 +569,13 @@ struct ieee80211_rx_status { * @IEEE80211_CONF_MONITOR: there's a monitor interface present -- use this * to determine for example whether to calculate timestamps for packets * or not, do not use instead of filter flags! - * @IEEE80211_CONF_PS: Enable 802.11 power save mode (managed mode only) + * @IEEE80211_CONF_PS: Enable 802.11 power save mode (managed mode only). + * This is the power save mode defined by IEEE 802.11-2007 section 11.2, + * meaning that the hardware still wakes up for beacons, is able to + * transmit frames and receive the possible acknowledgment frames. + * Not to be confused with hardware specific wakeup/sleep states, + * driver is responsible for that. See the section "Powersave support" + * for more. * @IEEE80211_CONF_IDLE: The device is running, but idle; if the flag is set * the driver should be prepared to handle configuration requests but * may turn the device off as much as possible. Typically, this flag will @@ -1138,18 +1144,24 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, * * mac80211 has support for various powersave implementations. * - * First, it can support hardware that handles all powersaving by - * itself, such hardware should simply set the %IEEE80211_HW_SUPPORTS_PS - * hardware flag. In that case, it will be told about the desired - * powersave mode depending on the association status, and the driver - * must take care of sending nullfunc frames when necessary, i.e. when - * entering and leaving powersave mode. The driver is required to look at - * the AID in beacons and signal to the AP that it woke up when it finds - * traffic directed to it. This mode supports dynamic PS by simply - * enabling/disabling PS. - * - * Additionally, such hardware may set the %IEEE80211_HW_SUPPORTS_DYNAMIC_PS - * flag to indicate that it can support dynamic PS mode itself (see below). + * First, it can support hardware that handles all powersaving by itself, + * such hardware should simply set the %IEEE80211_HW_SUPPORTS_PS hardware + * flag. In that case, it will be told about the desired powersave mode + * with the %IEEE80211_CONF_PS flag depending on the association status. + * The hardware must take care of sending nullfunc frames when necessary, + * i.e. when entering and leaving powersave mode. The hardware is required + * to look at the AID in beacons and signal to the AP that it woke up when + * it finds traffic directed to it. + * + * %IEEE80211_CONF_PS flag enabled means that the powersave mode defined in + * IEEE 802.11-2007 section 11.2 is enabled. This is not to be confused + * with hardware wakeup and sleep states. Driver is responsible for waking + * up the hardware before issueing commands to the hardware and putting it + * back to sleep at approriate times. + * + * When PS is enabled, hardware needs to wakeup for beacons and receive the + * buffered multicast/broadcast frames after the beacon. Also it must be + * possible to send frames and receive the acknowledment frame. * * Other hardware designs cannot send nullfunc frames by themselves and also * need software support for parsing the TIM bitmap. This is also supported @@ -1157,14 +1169,35 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, * %IEEE80211_HW_PS_NULLFUNC_STACK flags. The hardware is of course still * required to pass up beacons. The hardware is still required to handle * waking up for multicast traffic; if it cannot the driver must handle that - * as best as it can, mac80211 is too slow. - * - * Dynamic powersave mode is an extension to normal powersave mode in which - * the hardware stays awake for a user-specified period of time after sending - * a frame so that reply frames need not be buffered and therefore delayed - * to the next wakeup. This can either be supported by hardware, in which case - * the driver needs to look at the @dynamic_ps_timeout hardware configuration - * value, or by the stack if all nullfunc handling is in the stack. + * as best as it can, mac80211 is too slow to do that. + * + * Dynamic powersave is an extension to normal powersave in which the + * hardware stays awake for a user-specified period of time after sending a + * frame so that reply frames need not be buffered and therefore delayed to + * the next wakeup. It's compromise of getting good enough latency when + * there's data traffic and still saving significantly power in idle + * periods. + * + * Dynamic powersave is supported by simply mac80211 enabling and disabling + * PS based on traffic. Driver needs to only set %IEEE80211_HW_SUPPORTS_PS + * flag and mac80211 will handle everything automatically. Additionally, + * hardware having support for the dynamic PS feature may set the + * %IEEE80211_HW_SUPPORTS_DYNAMIC_PS flag to indicate that it can support + * dynamic PS mode itself. The driver needs to look at the + * @dynamic_ps_timeout hardware configuration value and use it that value + * whenever %IEEE80211_CONF_PS is set. In this case mac80211 will disable + * dynamic PS feature in stack and will just keep %IEEE80211_CONF_PS + * enabled whenever user has enabled powersave. + * + * Driver informs U-APSD client support by enabling + * %IEEE80211_HW_SUPPORTS_UAPSD flag. The mode is configured through the + * uapsd paramater in conf_tx() operation. Hardware needs to send the QoS + * Nullfunc frames and stay awake until the service period has ended. To + * utilize U-APSD, dynamic powersave is disabled for voip AC and all frames + * from that AC are transmitted with powersave enabled. + * + * Note: U-APSD client mode is not yet supported with + * %IEEE80211_HW_PS_NULLFUNC_STACK. */ /** -- cgit v1.1 From ad72c347e56bf3a0231b9d686e17764157d2961c Mon Sep 17 00:00:00 2001 From: Christian Pellegrin Date: Thu, 14 Jan 2010 07:08:34 +0000 Subject: can: Proper ctrlmode handling for CAN devices This patch adds error checking of ctrlmode values for CAN devices. As an example all availabe bits are implemented in the mcp251x driver. Signed-off-by: Christian Pellegrin Acked-by: Wolfgang Grandegger Signed-off-by: David S. Miller --- include/linux/can/dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 7e7c98a..c8c660a 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -38,6 +38,7 @@ struct can_priv { enum can_state state; u32 ctrlmode; + u32 ctrlmode_supported; int restart_ms; struct timer_list restart_timer; -- cgit v1.1 From 05c2828c72c4eabf62376adfe27bd24797621f62 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 14 Jan 2010 06:17:09 +0000 Subject: tun: export underlying socket Tun device looks similar to a packet socket in that both pass complete frames from/to userspace. This patch fills in enough fields in the socket underlying tun driver to support sendmsg/recvmsg operations, and message flags MSG_TRUNC and MSG_DONTWAIT, and exports access to this socket to modules. Regular read/write behaviour is unchanged. This way, code using raw sockets to inject packets into a physical device, can support injecting packets into host network stack almost without modification. First user of this interface will be vhost virtualization accelerator. Signed-off-by: Michael S. Tsirkin Acked-by: Herbert Xu Acked-by: David S. Miller Signed-off-by: David S. Miller --- include/linux/if_tun.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 3f5fd52..404abe0 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -86,4 +86,18 @@ struct tun_filter { __u8 addr[0][ETH_ALEN]; }; +#ifdef __KERNEL__ +#if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) +struct socket *tun_get_socket(struct file *); +#else +#include +#include +struct file; +struct socket; +static inline struct socket *tun_get_socket(struct file *f) +{ + return ERR_PTR(-EINVAL); +} +#endif /* CONFIG_TUN */ +#endif /* __KERNEL__ */ #endif /* __IF_TUN_H */ -- cgit v1.1 From 3a4d5c94e959359ece6d6b55045c3f046677f55c Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 14 Jan 2010 06:17:27 +0000 Subject: vhost_net: a kernel-level virtio server What it is: vhost net is a character device that can be used to reduce the number of system calls involved in virtio networking. Existing virtio net code is used in the guest without modification. There's similarity with vringfd, with some differences and reduced scope - uses eventfd for signalling - structures can be moved around in memory at any time (good for migration, bug work-arounds in userspace) - write logging is supported (good for migration) - support memory table and not just an offset (needed for kvm) common virtio related code has been put in a separate file vhost.c and can be made into a separate module if/when more backends appear. I used Rusty's lguest.c as the source for developing this part : this supplied me with witty comments I wouldn't be able to write myself. What it is not: vhost net is not a bus, and not a generic new system call. No assumptions are made on how guest performs hypercalls. Userspace hypervisors are supported as well as kvm. How it works: Basically, we connect virtio frontend (configured by userspace) to a backend. The backend could be a network device, or a tap device. Backend is also configured by userspace, including vlan/mac etc. Status: This works for me, and I haven't see any crashes. Compared to userspace, people reported improved latency (as I save up to 4 system calls per packet), as well as better bandwidth and CPU utilization. Features that I plan to look at in the future: - mergeable buffers - zero copy - scalability tuning: figure out the best threading model to use Note on RCU usage (this is also documented in vhost.h, near private_pointer which is the value protected by this variant of RCU): what is happening is that the rcu_dereference() is being used in a workqueue item. The role of rcu_read_lock() is taken on by the start of execution of the workqueue item, of rcu_read_unlock() by the end of execution of the workqueue item, and of synchronize_rcu() by flush_workqueue()/flush_work(). In the future we might need to apply some gcc attribute or sparse annotation to the function passed to INIT_WORK(). Paul's ack below is for this RCU usage. (Includes fixes by Alan Cox , David L Stevens , Chris Wright ) Acked-by: Rusty Russell Acked-by: Arnd Bergmann Acked-by: "Paul E. McKenney" Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + include/linux/miscdevice.h | 1 + include/linux/vhost.h | 130 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 132 insertions(+) create mode 100644 include/linux/vhost.h (limited to 'include') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 756f831..d930807 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -362,6 +362,7 @@ unifdef-y += uio.h unifdef-y += unistd.h unifdef-y += usbdevice_fs.h unifdef-y += utsname.h +unifdef-y += vhost.h unifdef-y += videodev2.h unifdef-y += videodev.h unifdef-y += virtio_config.h diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index adaf3c1..8b5f7cc 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -30,6 +30,7 @@ #define HPET_MINOR 228 #define FUSE_MINOR 229 #define KVM_MINOR 232 +#define VHOST_NET_MINOR 233 #define MISC_DYNAMIC_MINOR 255 struct device; diff --git a/include/linux/vhost.h b/include/linux/vhost.h new file mode 100644 index 0000000..e847f1e --- /dev/null +++ b/include/linux/vhost.h @@ -0,0 +1,130 @@ +#ifndef _LINUX_VHOST_H +#define _LINUX_VHOST_H +/* Userspace interface for in-kernel virtio accelerators. */ + +/* vhost is used to reduce the number of system calls involved in virtio. + * + * Existing virtio net code is used in the guest without modification. + * + * This header includes interface used by userspace hypervisor for + * device configuration. + */ + +#include +#include +#include +#include +#include + +struct vhost_vring_state { + unsigned int index; + unsigned int num; +}; + +struct vhost_vring_file { + unsigned int index; + int fd; /* Pass -1 to unbind from file. */ + +}; + +struct vhost_vring_addr { + unsigned int index; + /* Option flags. */ + unsigned int flags; + /* Flag values: */ + /* Whether log address is valid. If set enables logging. */ +#define VHOST_VRING_F_LOG 0 + + /* Start of array of descriptors (virtually contiguous) */ + __u64 desc_user_addr; + /* Used structure address. Must be 32 bit aligned */ + __u64 used_user_addr; + /* Available structure address. Must be 16 bit aligned */ + __u64 avail_user_addr; + /* Logging support. */ + /* Log writes to used structure, at offset calculated from specified + * address. Address must be 32 bit aligned. */ + __u64 log_guest_addr; +}; + +struct vhost_memory_region { + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; + __u64 flags_padding; /* No flags are currently specified. */ +}; + +/* All region addresses and sizes must be 4K aligned. */ +#define VHOST_PAGE_SIZE 0x1000 + +struct vhost_memory { + __u32 nregions; + __u32 padding; + struct vhost_memory_region regions[0]; +}; + +/* ioctls */ + +#define VHOST_VIRTIO 0xAF + +/* Features bitmask for forward compatibility. Transport bits are used for + * vhost specific features. */ +#define VHOST_GET_FEATURES _IOR(VHOST_VIRTIO, 0x00, __u64) +#define VHOST_SET_FEATURES _IOW(VHOST_VIRTIO, 0x00, __u64) + +/* Set current process as the (exclusive) owner of this file descriptor. This + * must be called before any other vhost command. Further calls to + * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */ +#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01) +/* Give up ownership, and reset the device to default values. + * Allows subsequent call to VHOST_OWNER_SET to succeed. */ +#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02) + +/* Set up/modify memory layout */ +#define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory) + +/* Write logging setup. */ +/* Memory writes can optionally be logged by setting bit at an offset + * (calculated from the physical address) from specified log base. + * The bit is set using an atomic 32 bit operation. */ +/* Set base address for logging. */ +#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64) +/* Specify an eventfd file descriptor to signal on log write. */ +#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int) + +/* Ring setup. */ +/* Set number of descriptors in ring. This parameter can not + * be modified while ring is running (bound to a device). */ +#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state) +/* Set addresses for the ring. */ +#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr) +/* Base value where queue looks for available descriptors */ +#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state) +/* Get accessor: reads index, writes value in num */ +#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state) + +/* The following ioctls use eventfd file descriptors to signal and poll + * for events. */ + +/* Set eventfd to poll for added buffers */ +#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file) +/* Set eventfd to signal when buffers have beed used */ +#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file) +/* Set eventfd to signal an error */ +#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file) + +/* VHOST_NET specific defines */ + +/* Attach virtio net ring to a raw socket, or tap device. + * The socket must be already bound to an ethernet device, this device will be + * used for transmit. Pass fd -1 to unbind from the socket and the transmit + * device. This can be used to stop the ring (e.g. for migration). */ +#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file) + +/* Feature bits */ +/* Log all write descriptors. Can be changed while device is active. */ +#define VHOST_F_LOG_ALL 26 +/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ +#define VHOST_NET_F_VIRTIO_NET_HDR 27 + +#endif -- cgit v1.1 From 72659ecce68588b74f6c46862c2b4cec137d7a5a Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sun, 17 Jan 2010 19:09:39 -0800 Subject: tcp: account SYN-ACK timeouts & retransmissions Currently we don't increment SYN-ACK timeouts & retransmissions although we do increment the same stats for SYN. We seem to have lost the SYN-ACK accounting with the introduction of tcp_syn_recv_timer (commit 2248761e in the netdev-vger-cvs tree). This patch fixes this issue. In the process we also rename the v4/v6 syn/ack retransmit functions for clarity. We also add a new request_socket operations (syn_ack_timeout) so we can keep code in inet_connection_sock.c protocol agnostic. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 ++ include/net/tcp.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index c9b50eb..99e6e19 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -45,6 +45,8 @@ struct request_sock_ops { void (*send_reset)(struct sock *sk, struct sk_buff *skb); void (*destructor)(struct request_sock *req); + void (*syn_ack_timeout)(struct sock *sk, + struct request_sock *req); }; /* struct request_sock - mini sock to represent a connection request diff --git a/include/net/tcp.h b/include/net/tcp.h index 788c99f..87d164b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -400,6 +400,8 @@ extern int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); extern void tcp_set_keepalive(struct sock *sk, int val); +extern void tcp_syn_ack_timeout(struct sock *sk, + struct request_sock *req); extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int nonblock, -- cgit v1.1 From e9d3897cc2205eec8b7afcc022e4730914b4f48c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:08:37 +0100 Subject: netfilter: netns: #ifdef ->iptable_security, ->ip6table_security 'security' tables depend on SECURITY, so ifdef them. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/net/netns/ipv4.h | 2 ++ include/net/netns/ipv6.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2eb3814..8098f6b 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -37,7 +37,9 @@ struct netns_ipv4 { struct xt_table *iptable_mangle; struct xt_table *iptable_raw; struct xt_table *arptable_filter; +#ifdef CONFIG_SECURITY struct xt_table *iptable_security; +#endif struct xt_table *nat_table; struct hlist_head *nat_bysource; int nat_vmalloced; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index dfeb2d7..1f11ebc 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -36,8 +36,10 @@ struct netns_ipv6 { struct xt_table *ip6table_filter; struct xt_table *ip6table_mangle; struct xt_table *ip6table_raw; +#ifdef CONFIG_SECURITY struct xt_table *ip6table_security; #endif +#endif struct rt6_info *ip6_null_entry; struct rt6_statistics *rt6_stats; struct timer_list ip6_fib_timer; -- cgit v1.1 From a83d8e8d099fc373a5ca7112ad08c553bb2c180f Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:21:13 +0100 Subject: netfilter: xtables: add struct xt_mtchk_param::net Some complex match modules (like xt_hashlimit/xt_recent) want netns information at constructor and destructor time. We propably can play games at match destruction time, because netns can be passed in object, but I think it's cleaner to explicitly pass netns. Add ->net, make sure it's set from ebtables/iptables/ip6tables code. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 378f27a..88261b9 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -205,6 +205,7 @@ struct xt_match_param { * @hook_mask: via which hooks the new rule is reachable */ struct xt_mtchk_param { + struct net *net; const char *table; const void *entryinfo; const struct xt_match *match; -- cgit v1.1 From f54e9367f8499a9bf6b2afbc0dce63e1d53c525a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:25:47 +0100 Subject: netfilter: xtables: add struct xt_mtdtor_param::net Add ->net to match destructor list like ->net in constructor list. Make sure it's set in ebtables/iptables/ip6tables, this requires to propagate netns up to *_unregister_table(). Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 1 + include/linux/netfilter_bridge/ebtables.h | 2 +- include/linux/netfilter_ipv4/ip_tables.h | 2 +- include/linux/netfilter_ipv6/ip6_tables.h | 2 +- 4 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 88261b9..3caf5e1 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -216,6 +216,7 @@ struct xt_mtchk_param { /* Match destructor parameters */ struct xt_mtdtor_param { + struct net *net; const struct xt_match *match; void *matchinfo; u_int8_t family; diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 3cc40c1..1c6f0c5 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -289,7 +289,7 @@ struct ebt_table { ~(__alignof__(struct ebt_replace)-1)) extern struct ebt_table *ebt_register_table(struct net *net, const struct ebt_table *table); -extern void ebt_unregister_table(struct ebt_table *table); +extern void ebt_unregister_table(struct net *net, struct ebt_table *table); extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, struct ebt_table *table); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 27b3f58..8d1f273 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -242,7 +242,7 @@ extern void ipt_init(void) __init; extern struct xt_table *ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl); -extern void ipt_unregister_table(struct xt_table *table); +extern void ipt_unregister_table(struct net *net, struct xt_table *table); /* Standard entry. */ struct ipt_standard { diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index b31050d..d2952d2 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -300,7 +300,7 @@ extern void ip6t_init(void) __init; extern struct xt_table *ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl); -extern void ip6t_unregister_table(struct xt_table *table); +extern void ip6t_unregister_table(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, unsigned int hook, const struct net_device *in, -- cgit v1.1 From c6fcf6bcfc3cfc1c00cc7fd9610cfa2b1a18041f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 17 Jan 2010 01:47:59 +0100 Subject: mac80211: re-enable re-transmission of filtered frames In an earlier commit, mac80211: disable software retry for now Pavel Roskin reported a problem that seems to be due to software retry of already transmitted frames. It turns out that we've never done that correctly, but due to some recent changes it now crashes in the TX code. I've added a comment in the patch that explains the problem better and also points to possible solutions -- which I can't implement right now. I disabled software retry of failed/filtered frames because it was broken. With the work of the previous patches, it now becomes fairly easy to re-enable it by adding a flag indicating that the frame shouldn't be modified, but still running it through the transmit handlers to populate the control information. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c90047d..f03f97b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -271,6 +271,9 @@ struct ieee80211_bss_conf { * transmit function after the current frame, this can be used * by drivers to kick the DMA queue only if unset or when the * queue gets full. + * @IEEE80211_TX_INTFL_RETRANSMISSION: This frame is being retransmitted + * after TX status because the destination was asleep, it must not + * be modified again (no seqno assignment, crypto, etc.) */ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), @@ -291,6 +294,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16), IEEE80211_TX_CTL_PSPOLL_RESPONSE = BIT(17), IEEE80211_TX_CTL_MORE_FRAMES = BIT(18), + IEEE80211_TX_INTFL_RETRANSMISSION = BIT(19), }; /** -- cgit v1.1 From 11380a4b2d86fae9a6bce75c9373668cc323fe57 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 19 Jan 2010 13:46:10 -0800 Subject: net: Unexport napi_gro_flush(). Nothing outside of net/core/dev.c uses it. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a3fccc8..468a11d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1527,7 +1527,6 @@ extern int netif_rx(struct sk_buff *skb); extern int netif_rx_ni(struct sk_buff *skb); #define HAVE_NETIF_RECEIVE_SKB 1 extern int netif_receive_skb(struct sk_buff *skb); -extern void napi_gro_flush(struct napi_struct *napi); extern gro_result_t dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb); extern gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb); -- cgit v1.1 From 7c070aa947d1a4105742378579c267f6e7fd08a1 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Wed, 20 Jan 2010 10:42:41 +0100 Subject: IPv6: reassembly: replace magic number with macro definitions Use macro to define high/low thresh value, refer to IPV6_FRAG_TIMEOUT. Signed-off-by: Shan Wei Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- include/net/ipv6.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index ccab594..299bbf5 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -246,6 +246,8 @@ extern int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb); int ip6_frag_nqueues(struct net *net); int ip6_frag_mem(struct net *net); +#define IPV6_FRAG_HIGH_THRESH 262144 /* == 256*1024 */ +#define IPV6_FRAG_LOW_THRESH 196608 /* == 192*1024 */ #define IPV6_FRAG_TIMEOUT (60*HZ) /* 60 seconds */ extern int __ipv6_addr_type(const struct in6_addr *addr); -- cgit v1.1 From b3fbdcf49f940d0703c356441e0daf045e64e076 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Jan 2010 11:40:47 +0100 Subject: mac80211: pass vif and station to update_tkip_key When a TKIP key is updated, we should pass the station pointer instead of just the address, since drivers can use that to store their own data. We also need to pass the virtual interface pointer. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f03f97b..f56d6f4 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1614,8 +1614,10 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key); void (*update_tkip_key)(struct ieee80211_hw *hw, - struct ieee80211_key_conf *conf, const u8 *address, - u32 iv32, u16 *phase1key); + struct ieee80211_vif *vif, + struct ieee80211_key_conf *conf, + struct ieee80211_sta *sta, + u32 iv32, u16 *phase1key); int (*hw_scan)(struct ieee80211_hw *hw, struct cfg80211_scan_request *req); void (*sw_scan_start)(struct ieee80211_hw *hw); -- cgit v1.1 From ef15aac6073b27fd4f70007784d2d52ed394bf43 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jan 2010 12:02:33 +0100 Subject: cfg80211: export multiple MAC addresses in sysfs If a device has multiple MAC addresses, userspace will need to know about that. Similarly, if it allows the MAC addresses to vary by a bitmask. If a driver exports multiple addresses, it is assumed that it will be able to deal with that many different addresses, which need not necessarily match the ones programmed into the device; if a mask is set then the device should deal addresses within that mask based on an arbitrary "base address". To test it all and show how it is used, add support to hwsim even though it can't actually deal with addresses different from the default. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2af5270..c5d16f2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1195,6 +1195,10 @@ enum wiphy_flags { WIPHY_FLAG_4ADDR_STATION = BIT(6), }; +struct mac_address { + u8 addr[ETH_ALEN]; +}; + /** * struct wiphy - wireless hardware description * @idx: the wiphy index assigned to this item @@ -1213,12 +1217,28 @@ enum wiphy_flags { * -1 = fragmentation disabled, only odd values >= 256 used * @rts_threshold: RTS threshold (dot11RTSThreshold); -1 = RTS/CTS disabled * @net: the network namespace this wiphy currently lives in + * @perm_addr: permanent MAC address of this device + * @addr_mask: If the device supports multiple MAC addresses by masking, + * set this to a mask with variable bits set to 1, e.g. if the last + * four bits are variable then set it to 00:...:00:0f. The actual + * variable bits shall be determined by the interfaces added, with + * interfaces not matching the mask being rejected to be brought up. + * @n_addresses: number of addresses in @addresses. + * @addresses: If the device has more than one address, set this pointer + * to a list of addresses (6 bytes each). The first one will be used + * by default for perm_addr. In this case, the mask should be set to + * all-zeroes. In this case it is assumed that the device can handle + * the same number of arbitrary MAC addresses. */ struct wiphy { /* assign these fields before you register the wiphy */ - /* permanent MAC address */ + /* permanent MAC address(es) */ u8 perm_addr[ETH_ALEN]; + u8 addr_mask[ETH_ALEN]; + + u16 n_addresses; + struct mac_address *addresses; /* Supported interface modes, OR together BIT(NL80211_IFTYPE_...) */ u16 interface_modes; -- cgit v1.1 From d0dd2de0d055f0ffb1e2ecdc21380de9d12a85e2 Mon Sep 17 00:00:00 2001 From: Andriy Tkachuk Date: Wed, 20 Jan 2010 13:55:06 +0200 Subject: mac80211: Account HT Control field in Data frame hdrlen according to 802.11n-2009 ieee80211_hdrlen() should account account new HT Control field in 802.11 data frame header introduced by IEEE 802.11n standard. According to 802.11n-2009 HT Control field is present in data frames when both of following are met: 1. It is QoS data frame. 2. Order bit is set in Frame Control field. The change might be totally compatible with legacy non-11n aware frames, because 802.11-2007 standard states that "all QoS STAs set this subfield to 0". Signed-off-by: Andriy V. Tkachuk Acked-by : Benoit Papillault Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8427019..1998495 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -138,6 +138,8 @@ #define IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK 0x03 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT 5 +#define IEEE80211_HT_CTL_LEN 4 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; -- cgit v1.1 From a271623f871dda970319ca15dfad3a8c8c36249f Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 22 Jan 2010 10:13:10 +0000 Subject: netdev: remove certain HAVE_ macros After netdev_ops compat code HAVE_* macros aren't needed, in fact they _will_ result in compile breakage for out of tree drivers. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 468a11d..b5fb51d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -621,30 +621,21 @@ struct net_device_ops { struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb); -#define HAVE_CHANGE_RX_FLAGS void (*ndo_change_rx_flags)(struct net_device *dev, int flags); -#define HAVE_SET_RX_MODE void (*ndo_set_rx_mode)(struct net_device *dev); -#define HAVE_MULTICAST void (*ndo_set_multicast_list)(struct net_device *dev); -#define HAVE_SET_MAC_ADDR int (*ndo_set_mac_address)(struct net_device *dev, void *addr); -#define HAVE_VALIDATE_ADDR int (*ndo_validate_addr)(struct net_device *dev); -#define HAVE_PRIVATE_IOCTL int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); -#define HAVE_SET_CONFIG int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); -#define HAVE_CHANGE_MTU int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); int (*ndo_neigh_setup)(struct net_device *dev, struct neigh_parms *); -#define HAVE_TX_TIMEOUT void (*ndo_tx_timeout) (struct net_device *dev); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); @@ -656,7 +647,6 @@ struct net_device_ops { void (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); #ifdef CONFIG_NET_POLL_CONTROLLER -#define HAVE_NETDEV_POLL void (*ndo_poll_controller)(struct net_device *dev); #endif #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) -- cgit v1.1 From 5833929cc2ad2b3064b4fac8c44e293972d240d8 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 22 Jan 2010 10:17:26 +0000 Subject: net: constify MIB name tables Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/snmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/snmp.h b/include/net/snmp.h index f0d756f..da02ee0 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -32,7 +32,7 @@ * - name of entries. */ struct snmp_mib { - char *name; + const char *name; int entry; }; -- cgit v1.1 From e754834e65220b2b674c55c3b6dfb2fb1a2804d0 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 22 Jan 2010 10:18:25 +0000 Subject: icmp: move icmp_err_convert[] to .rodata Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/icmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/icmp.h b/include/net/icmp.h index dfa72d4..15b3dfe 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -28,7 +28,7 @@ struct icmp_err { unsigned fatal:1; }; -extern struct icmp_err icmp_err_convert[]; +extern const struct icmp_err icmp_err_convert[]; #define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define ICMP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.icmp_statistics, field) #define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmpmsg_statistics, field+256) -- cgit v1.1 From 32e7bfc41110bc8f29ec0f293c3bcee6645fef34 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Jan 2010 13:36:10 -0800 Subject: net: use helpers to access uc list V2 This patch introduces three macros to work with uc list from net drivers. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b5fb51d..93a32a5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -263,6 +263,11 @@ struct netdev_hw_addr_list { int count; }; +#define netdev_uc_count(dev) ((dev)->uc.count) +#define netdev_uc_empty(dev) ((dev)->uc.count == 0) +#define netdev_for_each_uc_addr(ha, dev) \ + list_for_each_entry(ha, &dev->uc.list, list) + struct hh_cache { struct hh_cache *hh_next; /* Next entry */ atomic_t hh_refcnt; /* number of users */ -- cgit v1.1 From eb807fb23878bc319e029ed8ce3d835d239723a5 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Sun, 24 Jan 2010 14:55:12 +0200 Subject: mac80211: fix update_tkip_key() documentation about the context Johannes noticed that I had incorrectly documented the context of update_tkip_key() driver operation. It must be atomic because all RX code is run inside rcu critical section. Reported-by: Johannes Berg Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f56d6f4..f64402f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1489,7 +1489,7 @@ enum ieee80211_ampdu_mlme_action { * @update_tkip_key: See the section "Hardware crypto acceleration" * This callback will be called in the context of Rx. Called for drivers * which set IEEE80211_KEY_FLAG_TKIP_REQ_RX_P1_KEY. - * The callback can sleep. + * The callback must be atomic. * * @hw_scan: Ask the hardware to service the scan request, no need to start * the scan state machine in stack. The scan must honour the channel -- cgit v1.1 From c21dbf9214bce129f92e1af05552553ff0e318ed Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Jan 2010 14:15:46 +0100 Subject: cfg80211: export cfg80211_find_ie This new function (previously a static function called just "find_ie" can be used to find a specific IE in a buffer of IEs. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index c5d16f2..a3f0a7e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1658,6 +1658,22 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, */ unsigned int cfg80211_classify8021d(struct sk_buff *skb); +/** + * cfg80211_find_ie - find information element in data + * + * @eid: element ID + * @ies: data consisting of IEs + * @len: length of data + * + * This function will return %NULL if the element ID could + * not be found or if the element is invalid (claims to be + * longer than the given data), or a pointer to the first byte + * of the requested element, that is the byte containing the + * element ID. There are no checks on the element length + * other than having to fit into the given data. + */ +const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len); + /* * Regulatory helper functions for wiphys */ -- cgit v1.1 From 56007a028c51cbf800a6c969d6f6431d23443b99 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Jan 2010 14:19:52 +0100 Subject: mac80211: wait for beacon before enabling powersave Because DTIM information is required for powersave but is only conveyed in beacons, wait for a beacon before enabling powersave, and change the way the information is conveyed to the driver accordingly. mwl8k doesn't currently seem to implement PS but requires the DTIM period in a different way; after talking to Lennert we agreed to just have mwl8k do the parsing itself in the finalize_join work. Signed-off-by: Johannes Berg Acked-by: Lennert Buytenhek Signed-off-by: John W. Linville --- include/net/mac80211.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f64402f..1e9c930 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -186,7 +186,8 @@ enum ieee80211_bss_change { * @use_short_slot: use short slot time (only relevant for ERP); * if the hardware cannot handle this it must set the * IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE hardware flag - * @dtim_period: num of beacons before the next DTIM, for PSM + * @dtim_period: num of beacons before the next DTIM, for beaconing, + * not valid in station mode (cf. hw conf ps_dtim_period) * @timestamp: beacon timestamp * @beacon_int: beacon interval * @assoc_capability: capabilities taken from assoc resp @@ -648,6 +649,9 @@ enum ieee80211_smps_mode { * value will be only achievable between DTIM frames, the hardware * needs to check for the multicast traffic bit in DTIM beacons. * This variable is valid only when the CONF_PS flag is set. + * @ps_dtim_period: The DTIM period of the AP we're connected to, for use + * in power saving. Power saving will not be enabled until a beacon + * has been received and the DTIM period is known. * @dynamic_ps_timeout: The dynamic powersave timeout (in ms), see the * powersave documentation below. This variable is valid only when * the CONF_PS flag is set. @@ -674,6 +678,7 @@ struct ieee80211_conf { int max_sleep_period; u16 listen_interval; + u8 ps_dtim_period; u8 long_frame_max_tx_count, short_frame_max_tx_count; -- cgit v1.1 From a1664773907a2b69e2a3019598dcbeffa6bc724b Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 25 Jan 2010 10:37:54 +0000 Subject: netns xfrm: xfrm6_tunnel in netns I'm not sure about rcu stuff near kmem cache destruction: * checks for non-empty hashes look bogus, they're done _before_ rcu_berrier() * unregistering netns ops is done before kmem_cache destoy (as it should), and unregistering involves rcu barriers by itself So it looks nothing should be done. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/xfrm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 60c2770..fcee547 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1408,9 +1408,9 @@ extern int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto); extern int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family); extern int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family); -extern __be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr); -extern void xfrm6_tunnel_free_spi(xfrm_address_t *saddr); -extern __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr); +extern __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); +extern void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr); +extern __be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr); extern int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm6_output(struct sk_buff *skb); -- cgit v1.1 From 57dbb2d83d100ea601c54fe129bfde0678db5dee Mon Sep 17 00:00:00 2001 From: Hagen Paul Pfeifer Date: Sun, 24 Jan 2010 12:30:59 +0000 Subject: sched: add head drop fifo queue This adds an additional queuing strategy, called pfifo_head_drop, to remove the oldest skb in the case of an overflow within the queue - the head element - instead of the last skb (tail). To remove the oldest skb in congested situations is useful for sensor network environments where newer packets reflect the superior information. Reviewed-by: Florian Westphal Acked-by: Patrick McHardy Signed-off-by: Hagen Paul Pfeifer Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 1 + include/net/sch_generic.h | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 2d56726..b6cdc33 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -71,6 +71,7 @@ extern void qdisc_watchdog_cancel(struct qdisc_watchdog *wd); extern struct Qdisc_ops pfifo_qdisc_ops; extern struct Qdisc_ops bfifo_qdisc_ops; +extern struct Qdisc_ops pfifo_head_drop_qdisc_ops; extern int fifo_set_limit(struct Qdisc *q, unsigned int limit); extern struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index dad558b..67dc08e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -427,6 +427,25 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) return __qdisc_dequeue_head(sch, &sch->q); } +static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, + struct sk_buff_head *list) +{ + struct sk_buff *skb = __qdisc_dequeue_head(sch, list); + + if (likely(skb != NULL)) { + unsigned int len = qdisc_pkt_len(skb); + kfree_skb(skb); + return len; + } + + return 0; +} + +static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch) +{ + return __qdisc_queue_drop_head(sch, &sch->q); +} + static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch, struct sk_buff_head *list) { -- cgit v1.1 From 09d989d179d0c679043556dda77c51b41a2dae7e Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Fri, 29 Jan 2010 19:58:57 -0500 Subject: cfg80211: add regulatory hint disconnect support This adds a new regulatory hint to be used when we know all devices have been disconnected and idle. This can happen when we suspend, for instance. When we disconnect we can no longer assume the same regulatory rules learned from a country IE or beacon hints are applicable so restore regulatory settings to an initial state. Since driver hints are cached on the wiphy that called the hint, those hints are not reproduced onto cfg80211 as the wiphy will respect its own wiphy->regd regardless. Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/net/regulatory.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 47995b8..f873ee3 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -39,6 +39,7 @@ enum environment_cap { * 00 - World regulatory domain * 99 - built by driver but a specific alpha2 cannot be determined * 98 - result of an intersection between two regulatory domains + * 97 - regulatory domain has not yet been configured * @intersect: indicates whether the wireless core should intersect * the requested regulatory domain with the presently set regulatory * domain. -- cgit v1.1 From 17ad353b8d9843731258b5d23556667b764939e9 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sun, 31 Jan 2010 21:56:25 +0100 Subject: mac80211: fix monitor mode tx radiotap header handling When an injected frame gets buffered for a powersave STA or filtered and retransmitted, mac80211 attempts to parse the radiotap header again, which doesn't work because it's gone at that point. This patch adds a new flag for checking the availability of a radiotap header, so that it only attempts to parse it once, reusing the tx info on the next call to ieee80211_tx(). This fixes severe issues with rekeying in AP mode. Signed-off-by: Felix Fietkau Cc: stable@kernel.org Signed-off-by: John W. Linville --- include/net/mac80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1e9c930..74ccf30 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -275,6 +275,8 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_INTFL_RETRANSMISSION: This frame is being retransmitted * after TX status because the destination was asleep, it must not * be modified again (no seqno assignment, crypto, etc.) + * @IEEE80211_TX_INTFL_HAS_RADIOTAP: This frame was injected and still + * has a radiotap header at skb->data. */ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), @@ -296,6 +298,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_PSPOLL_RESPONSE = BIT(17), IEEE80211_TX_CTL_MORE_FRAMES = BIT(18), IEEE80211_TX_INTFL_RETRANSMISSION = BIT(19), + IEEE80211_TX_INTFL_HAS_RADIOTAP = BIT(20), }; /** -- cgit v1.1 From c30f540b63047437ffa894b5353216410c480d1a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 2 Feb 2010 15:03:24 +0100 Subject: netfilter: xtables: CONFIG_COMPAT redux Ifdef out struct nf_sockopt_ops::compat_set struct nf_sockopt_ops::compat_get struct xt_match::compat_from_user struct xt_match::compat_to_user struct xt_match::compatsize to make structures smaller on COMPAT=n kernels. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 9 ++++++--- include/linux/netfilter/x_tables.h | 12 ++++++++---- 2 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 48c5496..78f33d2 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -114,15 +114,17 @@ struct nf_sockopt_ops { int set_optmin; int set_optmax; int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len); +#ifdef CONFIG_COMPAT int (*compat_set)(struct sock *sk, int optval, void __user *user, unsigned int len); - +#endif int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); +#ifdef CONFIG_COMPAT int (*compat_get)(struct sock *sk, int optval, void __user *user, int *len); - +#endif /* Use the module struct to lock set/get code in place */ struct module *owner; }; @@ -222,11 +224,12 @@ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); - +#ifdef CONFIG_COMPAT int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, unsigned int len); int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); +#endif /* Call this before modifying an existing packet: ensures it is modifiable and linear to the point you care about (writable_len). diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 3caf5e1..026eb78 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -283,11 +283,11 @@ struct xt_match { /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); - +#ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, void *src); int (*compat_to_user)(void __user *dst, void *src); - +#endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -296,7 +296,9 @@ struct xt_match { const char *table; unsigned int matchsize; +#ifdef CONFIG_COMPAT unsigned int compatsize; +#endif unsigned int hooks; unsigned short proto; @@ -323,17 +325,19 @@ struct xt_target { /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); - +#ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, void *src); int (*compat_to_user)(void __user *dst, void *src); - +#endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int targetsize; +#ifdef CONFIG_COMPAT unsigned int compatsize; +#endif unsigned int hooks; unsigned short proto; -- cgit v1.1 From c85bb41e93184bf5494dde6d8fe5a81b564c84c8 Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Tue, 2 Feb 2010 07:32:29 -0800 Subject: igmp: fix ip_mc_sf_allow race [v5] Almost all igmp functions accessing inet->mc_list are protected by rtnl_lock(), but there is one exception which is ip_mc_sf_allow(), so there is a chance of either ip_mc_drop_socket or ip_mc_leave_group remove an entry while ip_mc_sf_allow is running causing a crash. Signed-off-by: Flavio Leitner Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 724c27e..93fc244 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -153,6 +153,7 @@ extern int sysctl_igmp_max_msf; struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; + struct rcu_head rcu; __be32 sl_addr[0]; }; @@ -170,6 +171,7 @@ struct ip_mc_socklist { struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip_sf_socklist *sflist; + struct rcu_head rcu; }; struct ip_sf_list { -- cgit v1.1 From f9bfbebf34eab707b065116cdc9699d25ba4252a Mon Sep 17 00:00:00 2001 From: Shirley Ma Date: Fri, 29 Jan 2010 03:19:05 +0000 Subject: virtio: Add ability to detach unused buffers from vrings There's currently no way for a virtio driver to ask for unused buffers, so it has to keep a list itself to reclaim them at shutdown. This is redundant, since virtio_ring stores that information. So add a new hook to do this. Signed-off-by: Shirley Ma Signed-off-by: Amit Shah Signed-off-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/virtio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 057a2e0..f508c65 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -51,6 +51,9 @@ struct virtqueue { * This re-enables callbacks; it returns "false" if there are pending * buffers in the queue, to detect a possible race between the driver * checking for more work, and enabling callbacks. + * @detach_unused_buf: detach first unused buffer + * vq: the struct virtqueue we're talking about. + * Returns NULL or the "data" token handed to add_buf * * Locking rules are straightforward: the driver is responsible for * locking. No two operations may be invoked simultaneously, with the exception @@ -71,6 +74,7 @@ struct virtqueue_ops { void (*disable_cb)(struct virtqueue *vq); bool (*enable_cb)(struct virtqueue *vq); + void *(*detach_unused_buf)(struct virtqueue *vq); }; /** -- cgit v1.1 From 794e68716bab578ae8f8912dc934496d7c7abc90 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:41:29 +0100 Subject: netfilter: ctnetlink: only assign helpers for matching protocols Make sure not to assign a helper for a different network or transport layer protocol to a connection. Additionally change expectation deletion by helper to compare the name directly - there might be multiple helper registrations using the same name, currently one of them is chosen in an unpredictable manner and only those expectations are removed. Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack_helper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index d015de9..86be7c4 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -40,7 +40,7 @@ struct nf_conntrack_helper { }; extern struct nf_conntrack_helper * -__nf_conntrack_helper_find_byname(const char *name); +__nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum); extern int nf_conntrack_helper_register(struct nf_conntrack_helper *); extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *); -- cgit v1.1 From add67461240c1dadc7c8d97e66f8f92b556ca523 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:45:12 +0100 Subject: netfilter: add struct net * to target parameters Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 026eb78..365fabe 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -249,6 +249,7 @@ struct xt_target_param { * Other fields see above. */ struct xt_tgchk_param { + struct net *net; const char *table; const void *entryinfo; const struct xt_target *target; @@ -259,6 +260,7 @@ struct xt_tgchk_param { /* Target destructor parameters */ struct xt_tgdtor_param { + struct net *net; const struct xt_target *target; void *targinfo; u_int8_t family; -- cgit v1.1 From 858b31330054a9ad259feceea0ad1ce5385c47f0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:48:53 +0100 Subject: netfilter: nf_conntrack: split up IPCT_STATUS event Split up the IPCT_STATUS event into an IPCT_REPLY event, which is generated when the IPS_SEEN_REPLY bit is set, and an IPCT_ASSURED event, which is generated when the IPS_ASSURED bit is set. In combination with a following patch to support selective event delivery, this can be used for "sparse" conntrack replication: start replicating the conntrack entry after it reached the ASSURED state and that way it's SYN-flood resistant. Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack_ecache.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 475facc..5e05fb8 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -14,19 +14,20 @@ /* Connection tracking event types */ enum ip_conntrack_events { - IPCT_NEW = 0, /* new conntrack */ - IPCT_RELATED = 1, /* related conntrack */ - IPCT_DESTROY = 2, /* destroyed conntrack */ - IPCT_STATUS = 3, /* status has changed */ - IPCT_PROTOINFO = 4, /* protocol information has changed */ - IPCT_HELPER = 5, /* new helper has been set */ - IPCT_MARK = 6, /* new mark has been set */ - IPCT_NATSEQADJ = 7, /* NAT is doing sequence adjustment */ - IPCT_SECMARK = 8, /* new security mark has been set */ + IPCT_NEW, /* new conntrack */ + IPCT_RELATED, /* related conntrack */ + IPCT_DESTROY, /* destroyed conntrack */ + IPCT_REPLY, /* connection has seen two-way traffic */ + IPCT_ASSURED, /* connection status has changed to assured */ + IPCT_PROTOINFO, /* protocol information has changed */ + IPCT_HELPER, /* new helper has been set */ + IPCT_MARK, /* new mark has been set */ + IPCT_NATSEQADJ, /* NAT is doing sequence adjustment */ + IPCT_SECMARK, /* new security mark has been set */ }; enum ip_conntrack_expect_events { - IPEXP_NEW = 0, /* new expectation */ + IPEXP_NEW, /* new expectation */ }; struct nf_conntrack_ecache { -- cgit v1.1 From 0cebe4b4163b6373c9d24c1a192939777bc27e55 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:51:51 +0100 Subject: netfilter: ctnetlink: support selective event delivery Add two masks for conntrack end expectation events to struct nf_conntrack_ecache and use them to filter events. Their default value is "all events" when the event sysctl is on and "no events" when it is off. A following patch will add specific initializations. Expectation events depend on the ecache struct of their master conntrack. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_common.h | 18 ++++++++ include/net/netfilter/nf_conntrack_ecache.h | 59 +++++++++++++-------------- 2 files changed, 46 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index a374787..ebfed90 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -74,6 +74,24 @@ enum ip_conntrack_status { IPS_FIXED_TIMEOUT = (1 << IPS_FIXED_TIMEOUT_BIT), }; +/* Connection tracking event types */ +enum ip_conntrack_events { + IPCT_NEW, /* new conntrack */ + IPCT_RELATED, /* related conntrack */ + IPCT_DESTROY, /* destroyed conntrack */ + IPCT_REPLY, /* connection has seen two-way traffic */ + IPCT_ASSURED, /* connection status has changed to assured */ + IPCT_PROTOINFO, /* protocol information has changed */ + IPCT_HELPER, /* new helper has been set */ + IPCT_MARK, /* new mark has been set */ + IPCT_NATSEQADJ, /* NAT is doing sequence adjustment */ + IPCT_SECMARK, /* new security mark has been set */ +}; + +enum ip_conntrack_expect_events { + IPEXP_NEW, /* new expectation */ +}; + #ifdef __KERNEL__ struct ip_conntrack_stat { unsigned int searched; diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 5e05fb8..96ba5f7 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -12,28 +12,12 @@ #include #include -/* Connection tracking event types */ -enum ip_conntrack_events { - IPCT_NEW, /* new conntrack */ - IPCT_RELATED, /* related conntrack */ - IPCT_DESTROY, /* destroyed conntrack */ - IPCT_REPLY, /* connection has seen two-way traffic */ - IPCT_ASSURED, /* connection status has changed to assured */ - IPCT_PROTOINFO, /* protocol information has changed */ - IPCT_HELPER, /* new helper has been set */ - IPCT_MARK, /* new mark has been set */ - IPCT_NATSEQADJ, /* NAT is doing sequence adjustment */ - IPCT_SECMARK, /* new security mark has been set */ -}; - -enum ip_conntrack_expect_events { - IPEXP_NEW, /* new expectation */ -}; - struct nf_conntrack_ecache { - unsigned long cache; /* bitops want long */ - unsigned long missed; /* missed events */ - u32 pid; /* netlink pid of destroyer */ + unsigned long cache; /* bitops want long */ + unsigned long missed; /* missed events */ + u16 ctmask; /* bitmask of ct events to be delivered */ + u16 expmask; /* bitmask of expect events to be delivered */ + u32 pid; /* netlink pid of destroyer */ }; static inline struct nf_conntrack_ecache * @@ -43,14 +27,24 @@ nf_ct_ecache_find(const struct nf_conn *ct) } static inline struct nf_conntrack_ecache * -nf_ct_ecache_ext_add(struct nf_conn *ct, gfp_t gfp) +nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { struct net *net = nf_ct_net(ct); + struct nf_conntrack_ecache *e; - if (!net->ct.sysctl_events) + if (!ctmask && !expmask && net->ct.sysctl_events) { + ctmask = ~0; + expmask = ~0; + } + if (!ctmask && !expmask) return NULL; - return nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); + e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); + if (e) { + e->ctmask = ctmask; + e->expmask = expmask; + } + return e; }; #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -83,6 +77,9 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) if (e == NULL) return; + if (!(e->ctmask & (1 << event))) + return; + set_bit(event, &e->cache); } @@ -93,7 +90,6 @@ nf_conntrack_eventmask_report(unsigned int eventmask, int report) { int ret = 0; - struct net *net = nf_ct_net(ct); struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; @@ -102,9 +98,6 @@ nf_conntrack_eventmask_report(unsigned int eventmask, if (notify == NULL) goto out_unlock; - if (!net->ct.sysctl_events) - goto out_unlock; - e = nf_ct_ecache_find(ct); if (e == NULL) goto out_unlock; @@ -118,6 +111,9 @@ nf_conntrack_eventmask_report(unsigned int eventmask, /* This is a resent of a destroy event? If so, skip missed */ unsigned long missed = e->pid ? 0 : e->missed; + if (!((eventmask | missed) & e->ctmask)) + goto out_unlock; + ret = notify->fcn(eventmask | missed, &item); if (unlikely(ret < 0 || missed)) { spin_lock_bh(&ct->lock); @@ -173,18 +169,19 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event, u32 pid, int report) { - struct net *net = nf_ct_exp_net(exp); struct nf_exp_event_notifier *notify; + struct nf_conntrack_ecache *e; rcu_read_lock(); notify = rcu_dereference(nf_expect_event_cb); if (notify == NULL) goto out_unlock; - if (!net->ct.sysctl_events) + e = nf_ct_ecache_find(exp->master); + if (e == NULL) goto out_unlock; - { + if (e->expmask & (1 << event)) { struct nf_exp_event item = { .exp = exp, .pid = pid, -- cgit v1.1 From b2a15a604d379af323645e330638e2cfcc696aff Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 14:13:03 +0100 Subject: netfilter: nf_conntrack: support conntrack templates Support initializing selected parameters of new conntrack entries from a "conntrack template", which is a specially marked conntrack entry attached to the skb. Currently the helper and the event delivery masks can be initialized this way. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_common.h | 4 ++++ include/net/netfilter/nf_conntrack.h | 5 +++++ include/net/netfilter/nf_conntrack_helper.h | 3 ++- 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index ebfed90..c608677 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -72,6 +72,10 @@ enum ip_conntrack_status { /* Connection has fixed timeout. */ IPS_FIXED_TIMEOUT_BIT = 10, IPS_FIXED_TIMEOUT = (1 << IPS_FIXED_TIMEOUT_BIT), + + /* Conntrack is a template */ + IPS_TEMPLATE_BIT = 11, + IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT), }; /* Connection tracking event types */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index a0904ad..5043d61 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -272,6 +272,11 @@ nf_conntrack_alloc(struct net *net, const struct nf_conntrack_tuple *repl, gfp_t gfp); +static inline int nf_ct_is_template(const struct nf_conn *ct) +{ + return test_bit(IPS_TEMPLATE_BIT, &ct->status); +} + /* It's confirmed if it is, or has been in the hash table. */ static inline int nf_ct_is_confirmed(struct nf_conn *ct) { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 86be7c4..e17aaa3 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -47,7 +47,8 @@ extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *); extern struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp); -extern int __nf_ct_try_assign_helper(struct nf_conn *ct, gfp_t flags); +extern int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, + gfp_t flags); extern void nf_ct_helper_destroy(struct nf_conn *ct); -- cgit v1.1 From 84f3bb9ae9db90f7fb15d98b55279a58ab1b2363 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 17:17:06 +0100 Subject: netfilter: xtables: add CT target Add a new target for the raw table, which can be used to specify conntrack parameters for specific connections, f.i. the conntrack helper. The target attaches a "template" connection tracking entry to the skb, which is used by the conntrack core when initializing a new conntrack. Signed-off-by: Patrick McHardy --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_CT.h | 17 +++++++++++++++++ include/net/netfilter/nf_conntrack_helper.h | 3 +++ 3 files changed, 21 insertions(+) create mode 100644 include/linux/netfilter/xt_CT.h (limited to 'include') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 2aea503..a5a63e4 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -6,6 +6,7 @@ header-y += nfnetlink_queue.h header-y += xt_CLASSIFY.h header-y += xt_CONNMARK.h header-y += xt_CONNSECMARK.h +header-y += xt_CT.h header-y += xt_DSCP.h header-y += xt_LED.h header-y += xt_MARK.h diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h new file mode 100644 index 0000000..7fd0eff --- /dev/null +++ b/include/linux/netfilter/xt_CT.h @@ -0,0 +1,17 @@ +#ifndef _XT_CT_H +#define _XT_CT_H + +#define XT_CT_NOTRACK 0x1 + +struct xt_ct_target_info { + u_int16_t flags; + u_int16_t __unused; + u_int32_t ct_events; + u_int32_t exp_events; + char helper[16]; + + /* Used internally by the kernel */ + struct nf_conn *ct __attribute__((aligned(8))); +}; + +#endif /* _XT_CT_H */ diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index e17aaa3..32c305d 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -42,6 +42,9 @@ struct nf_conntrack_helper { extern struct nf_conntrack_helper * __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum); +extern struct nf_conntrack_helper * +nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum); + extern int nf_conntrack_helper_register(struct nf_conntrack_helper *); extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *); -- cgit v1.1 From 8a83a00b0735190384a348156837918271034144 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:23:03 +0000 Subject: net: maintain namespace isolation between vlan and real device In the vlan and macvlan drivers, the start_xmit function forwards data to the dev_queue_xmit function for another device, which may potentially belong to a different namespace. To make sure that classification stays within a single namespace, this resets the potentially critical fields. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 93a32a5..622ba5a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1004,6 +1004,15 @@ static inline bool netdev_uses_dsa_tags(struct net_device *dev) return 0; } +#ifndef CONFIG_NET_NS +static inline void skb_set_dev(struct sk_buff *skb, struct net_device *dev) +{ + skb->dev = dev; +} +#else /* CONFIG_NET_NS */ +void skb_set_dev(struct sk_buff *skb, struct net_device *dev); +#endif + static inline bool netdev_uses_trailer_tags(struct net_device *dev) { #ifdef CONFIG_NET_DSA_TAG_TRAILER -- cgit v1.1 From fc0663d6b5e6d8e9b57f872a644c0aafd82361b7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:23:40 +0000 Subject: macvlan: allow multiple driver backends This makes it possible to hook into the macvlan driver from another kernel module. In particular, the goal is to extend it with the macvtap backend that provides a tun/tap compatible interface directly on the macvlan device. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 5f200ba..9a11544 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -1,6 +1,76 @@ #ifndef _LINUX_IF_MACVLAN_H #define _LINUX_IF_MACVLAN_H +#include +#include +#include +#include +#include + +struct macvlan_port; +struct macvtap_queue; + +/** + * struct macvlan_rx_stats - MACVLAN percpu rx stats + * @rx_packets: number of received packets + * @rx_bytes: number of received bytes + * @multicast: number of received multicast packets + * @rx_errors: number of errors + */ +struct macvlan_rx_stats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long multicast; + unsigned long rx_errors; +}; + +struct macvlan_dev { + struct net_device *dev; + struct list_head list; + struct hlist_node hlist; + struct macvlan_port *port; + struct net_device *lowerdev; + struct macvlan_rx_stats *rx_stats; + enum macvlan_mode mode; + int (*receive)(struct sk_buff *skb); + int (*forward)(struct net_device *dev, struct sk_buff *skb); +}; + +static inline void macvlan_count_rx(const struct macvlan_dev *vlan, + unsigned int len, bool success, + bool multicast) +{ + struct macvlan_rx_stats *rx_stats; + + rx_stats = per_cpu_ptr(vlan->rx_stats, smp_processor_id()); + if (likely(success)) { + rx_stats->rx_packets++;; + rx_stats->rx_bytes += len; + if (multicast) + rx_stats->multicast++; + } else { + rx_stats->rx_errors++; + } +} + +extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + int (*receive)(struct sk_buff *skb), + int (*forward)(struct net_device *dev, + struct sk_buff *skb)); + +extern void macvlan_count_rx(const struct macvlan_dev *vlan, + unsigned int len, bool success, + bool multicast); + +extern void macvlan_dellink(struct net_device *dev, struct list_head *head); + +extern int macvlan_link_register(struct rtnl_link_ops *ops); + +extern netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, + struct net_device *dev); + + extern struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *); #endif /* _LINUX_IF_MACVLAN_H */ -- cgit v1.1 From 20d29d7a916a47bf533b5709437fe735b6b5b79e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:24:26 +0000 Subject: net: macvtap driver In order to use macvlan with qemu and other tools that require a tap file descriptor, the macvtap driver adds a small backend with a character device with the same interface as the tun driver, with a minimum set of features. Macvtap interfaces are created in the same way as macvlan interfaces using ip link, but the netif is just used as a handle for configuration and accounting, while the data goes through the chardev. Each macvtap interface has its own character device, simplifying permission management significantly over the generic tun/tap driver. Cc: Patrick McHardy Cc: Stephen Hemminger Cc: David S. Miller" Cc: "Michael S. Tsirkin" Cc: Herbert Xu Cc: Or Gerlitz Cc: netdev@vger.kernel.org Cc: bridge@lists.linux-foundation.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 9a11544..51f1512 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -34,6 +34,7 @@ struct macvlan_dev { enum macvlan_mode mode; int (*receive)(struct sk_buff *skb); int (*forward)(struct net_device *dev, struct sk_buff *skb); + struct macvtap_queue *tap; }; static inline void macvlan_count_rx(const struct macvlan_dev *vlan, -- cgit v1.1 From 1621e0940294c20e302faf401f41204de7252e22 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 1 Feb 2010 09:44:19 +0000 Subject: net: CONFIG_COMPAT redux Ifdef out struct proto_ops::compat_ioctl struct proto_ops::compat_setsockopt struct proto_ops::compat_getsockopt to make structures smaller on COMPAT=n kernels. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/net.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 5e8083c..4157b5d 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -174,18 +174,22 @@ struct proto_ops { struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT int (*compat_ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); +#endif int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); +#ifdef CONFIG_COMPAT int (*compat_setsockopt)(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen); int (*compat_getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); +#endif int (*sendmsg) (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len); int (*recvmsg) (struct kiocb *iocb, struct socket *sock, -- cgit v1.1 From 6683ece36e3531fc8c75f69e7165c5f20930be88 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 4 Feb 2010 10:22:25 -0800 Subject: net: use helpers to access mc list V2 This patch introduces the similar helpers as those already done for uc list. However multicast lists are no list_head lists but "mademanually". The three macros added by this patch will make the transition of mc_list to list_head smooth in two steps: 1) convert all drivers to use these macros (with the original iterator of type "struct dev_mc_list") 2) once all drivers are converted, convert list type and iterators to "struct netdev_hw_addr" in one patch. >From now on, drivers can (and should) use "netdev_for_each_mc_addr" to iterate over the addresses with iterator of type "struct netdev_hw_addr". Also macros "netdev_mc_count" and "netdev_mc_empty" to read list's length. This is the state which should be reached in all drivers. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 622ba5a..e535700 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -268,6 +268,12 @@ struct netdev_hw_addr_list { #define netdev_for_each_uc_addr(ha, dev) \ list_for_each_entry(ha, &dev->uc.list, list) +#define netdev_mc_count(dev) ((dev)->mc_count) +#define netdev_mc_empty(dev) (netdev_mc_count(dev) == 0) + +#define netdev_for_each_mc_addr(mclist, dev) \ + for (mclist = dev->mc_list; mclist; mclist = mclist->next) + struct hh_cache { struct hh_cache *hh_next; /* Next entry */ atomic_t hh_refcnt; /* number of users */ -- cgit v1.1 From f8f76db1db369f3a130ac3fd33e2eee5f1610d9c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 4 Feb 2010 10:23:02 -0800 Subject: libphy: add phy_find_first function Many drivers do this in them manually. Now they can use this function. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 6a7eb40..14d7fdf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -452,6 +452,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface); struct phy_device * phy_attach(struct net_device *dev, const char *bus_id, u32 flags, phy_interface_t interface); +struct phy_device *phy_find_first(struct mii_bus *bus); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), u32 flags, phy_interface_t interface); -- cgit v1.1 From bfd5f4a3d605e0f6054df0b59fe0907ff7e696d3 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 4 Feb 2010 20:24:10 -0800 Subject: packet: Add GSO/csum offload support. This patch adds GSO/checksum offload to af_packet sockets using virtio_net_hdr. Based on Rusty's patch to add this support to tun. It allows GSO/checksum offload to be enabled when using raw socket backend with virtio_net. Adds PACKET_VNET_HDR socket option to prepend virtio_net_hdr in the receive path and process/skip virtio_net_hdr in the send path. This option is only allowed with SOCK_RAW sockets attached to ethernet type devices. v2 updates ---------- Michael's Comments - Perform length check in packet_snd() when GSO is off even when vnet_hdr is present. - Check for SKB_GSO_FCOE type and return -EINVAL - don't allow tx/rx ring when vnet_hdr is enabled. Herbert's Comments - Removed ethernet specific code. - protocol value is assumed to be passed in by the caller. Signed-off-by: Sridhar Samudrala Signed-off-by: David S. Miller --- include/linux/if_packet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 4021d47c..aa57a5f 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -46,6 +46,7 @@ struct sockaddr_ll { #define PACKET_RESERVE 12 #define PACKET_TX_RING 13 #define PACKET_LOSS 14 +#define PACKET_VNET_HDR 15 struct tpacket_stats { unsigned int tp_packets; -- cgit v1.1 From 33e5a2f776e331dc8a4379b6efb660d38f182d96 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 3 Feb 2010 10:24:30 +0100 Subject: wireless: update radiotap parser Upstream radiotap has adopted the namespace proposal David Young made and I then took care of, for which I had adapted the radiotap parser as a library outside the kernel. This brings the in-kernel parser up to speed. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 83 +++++++++++++++++++++++++++++++--------- include/net/ieee80211_radiotap.h | 4 ++ 2 files changed, 68 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a3f0a7e..5b3569b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1561,37 +1561,82 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband, * Documentation in Documentation/networking/radiotap-headers.txt */ +struct radiotap_align_size { + uint8_t align:4, size:4; +}; + +struct ieee80211_radiotap_namespace { + const struct radiotap_align_size *align_size; + int n_bits; + uint32_t oui; + uint8_t subns; +}; + +struct ieee80211_radiotap_vendor_namespaces { + const struct ieee80211_radiotap_namespace *ns; + int n_ns; +}; + /** * struct ieee80211_radiotap_iterator - tracks walk thru present radiotap args - * @rtheader: pointer to the radiotap header we are walking through - * @max_length: length of radiotap header in cpu byte ordering - * @this_arg_index: IEEE80211_RADIOTAP_... index of current arg - * @this_arg: pointer to current radiotap arg - * @arg_index: internal next argument index - * @arg: internal next argument pointer - * @next_bitmap: internal pointer to next present u32 - * @bitmap_shifter: internal shifter for curr u32 bitmap, b0 set == arg present + * @this_arg_index: index of current arg, valid after each successful call + * to ieee80211_radiotap_iterator_next() + * @this_arg: pointer to current radiotap arg; it is valid after each + * call to ieee80211_radiotap_iterator_next() but also after + * ieee80211_radiotap_iterator_init() where it will point to + * the beginning of the actual data portion + * @this_arg_size: length of the current arg, for convenience + * @current_namespace: pointer to the current namespace definition + * (or internally %NULL if the current namespace is unknown) + * @is_radiotap_ns: indicates whether the current namespace is the default + * radiotap namespace or not + * + * @overrides: override standard radiotap fields + * @n_overrides: number of overrides + * + * @_rtheader: pointer to the radiotap header we are walking through + * @_max_length: length of radiotap header in cpu byte ordering + * @_arg_index: next argument index + * @_arg: next argument pointer + * @_next_bitmap: internal pointer to next present u32 + * @_bitmap_shifter: internal shifter for curr u32 bitmap, b0 set == arg present + * @_vns: vendor namespace definitions + * @_next_ns_data: beginning of the next namespace's data + * @_reset_on_ext: internal; reset the arg index to 0 when going to the + * next bitmap word + * + * Describes the radiotap parser state. Fields prefixed with an underscore + * must not be used by users of the parser, only by the parser internally. */ struct ieee80211_radiotap_iterator { - struct ieee80211_radiotap_header *rtheader; - int max_length; + struct ieee80211_radiotap_header *_rtheader; + const struct ieee80211_radiotap_vendor_namespaces *_vns; + const struct ieee80211_radiotap_namespace *current_namespace; + + unsigned char *_arg, *_next_ns_data; + uint32_t *_next_bitmap; + + unsigned char *this_arg; int this_arg_index; - u8 *this_arg; + int this_arg_size; - int arg_index; - u8 *arg; - __le32 *next_bitmap; - u32 bitmap_shifter; + int is_radiotap_ns; + + int _max_length; + int _arg_index; + uint32_t _bitmap_shifter; + int _reset_on_ext; }; extern int ieee80211_radiotap_iterator_init( - struct ieee80211_radiotap_iterator *iterator, - struct ieee80211_radiotap_header *radiotap_header, - int max_length); + struct ieee80211_radiotap_iterator *iterator, + struct ieee80211_radiotap_header *radiotap_header, + int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns); extern int ieee80211_radiotap_iterator_next( - struct ieee80211_radiotap_iterator *iterator); + struct ieee80211_radiotap_iterator *iterator); + extern const unsigned char rfc1042_header[6]; extern const unsigned char bridge_tunnel_header[6]; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 9d3d86a..af49f8a 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -198,6 +198,10 @@ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_TX_FLAGS = 15, IEEE80211_RADIOTAP_RTS_RETRIES = 16, IEEE80211_RADIOTAP_DATA_RETRIES = 17, + + /* valid in every it_present bitmap, even vendor namespaces */ + IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, + IEEE80211_RADIOTAP_VENDOR_NAMESPACE = 30, IEEE80211_RADIOTAP_EXT = 31 }; -- cgit v1.1 From 34e895075e21be3e21e71d6317440d1ee7969ad0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 3 Feb 2010 13:59:58 +0100 Subject: mac80211: allow station add/remove to sleep Many drivers would like to sleep during station addition and removal, and currently have a high complexity there from not being able to. This introduces two new callbacks sta_add() and sta_remove() that drivers can implement instead of using sta_notify() and that can sleep, and the new sta_add() callback is also allowed to fail. The reason we didn't do this previously is that the IBSS code wants to insert stations from the RX path, which is a tasklet, so cannot sleep. This patch will keep the station allocation in that path, but moves adding the station to the driver out of line. Since the addition can now fail, we can have IBSS peer structs the driver rejected -- in that case we still talk to the station but never tell the driver about it in the control.sta pointer. If there will ever be a driver that has a low limit on the number of stations and that cannot talk to any stations that are not known to it, we need to do come up with a new strategy of handling larger IBSSs, maybe quicker expiry or rejecting peers. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 74ccf30..a19fac3 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -814,7 +814,7 @@ enum set_key_cmd { * mac80211, any ieee80211_sta pointer you get access to must * either be protected by rcu_read_lock() explicitly or implicitly, * or you must take good care to not use such a pointer after a - * call to your sta_notify callback that removed it. + * call to your sta_remove callback that removed it. * * @addr: MAC address * @aid: AID we assigned to the station if we're an AP @@ -840,8 +840,8 @@ struct ieee80211_sta { * indicates addition and removal of a station to station table, * or if a associated station made a power state transition. * - * @STA_NOTIFY_ADD: a station was added to the station table - * @STA_NOTIFY_REMOVE: a station being removed from the station table + * @STA_NOTIFY_ADD: (DEPRECATED) a station was added to the station table + * @STA_NOTIFY_REMOVE: (DEPRECATED) a station being removed from the station table * @STA_NOTIFY_SLEEP: a station is now sleeping * @STA_NOTIFY_AWAKE: a sleeping station woke up */ @@ -1534,9 +1534,14 @@ enum ieee80211_ampdu_mlme_action { * @set_rts_threshold: Configuration of RTS threshold (if device needs it) * The callback can sleep. * - * @sta_notify: Notifies low level driver about addition, removal or power - * state transition of an associated station, AP, IBSS/WDS/mesh peer etc. - * Must be atomic. + * @sta_add: Notifies low level driver about addition of an associated station, + * AP, IBSS/WDS/mesh peer etc. This callback can sleep. + * + * @sta_remove: Notifies low level driver about removal of an associated + * station, AP, IBSS/WDS/mesh peer etc. This callback can sleep. + * + * @sta_notify: Notifies low level driver about power state transition of an + * associated station, AP, IBSS/WDS/mesh peer etc. Must be atomic. * * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max), * bursting) for a hardware TX queue. @@ -1635,6 +1640,10 @@ struct ieee80211_ops { void (*get_tkip_seq)(struct ieee80211_hw *hw, u8 hw_key_idx, u32 *iv32, u16 *iv16); int (*set_rts_threshold)(struct ieee80211_hw *hw, u32 value); + int (*sta_add)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_sta *sta); + int (*sta_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_sta *sta); void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd, struct ieee80211_sta *sta); int (*conf_tx)(struct ieee80211_hw *hw, u16 queue, -- cgit v1.1 From 349e6b7289f8a3d3d5d3b859e00b41f27d1211df Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Sun, 7 Feb 2010 10:22:01 +0200 Subject: mac80211: remove get_tx_stats() driver op get_tx_stats() driver operation is not currently used anywhere in mac80211 and there are no plans to use it in the not-so-near future. So it can go without anyone missing it. Signed-off-by: Kalle Valo Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a19fac3..414d774 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -117,19 +117,6 @@ struct ieee80211_tx_queue_params { bool uapsd; }; -/** - * struct ieee80211_tx_queue_stats - transmit queue statistics - * - * @len: number of packets in queue - * @limit: queue length limit - * @count: number of frames sent - */ -struct ieee80211_tx_queue_stats { - unsigned int len; - unsigned int limit; - unsigned int count; -}; - struct ieee80211_low_level_stats { unsigned int dot11ACKFailureCount; unsigned int dot11RTSFailureCount; @@ -1548,13 +1535,6 @@ enum ieee80211_ampdu_mlme_action { * Returns a negative error code on failure. * The callback can sleep. * - * @get_tx_stats: Get statistics of the current TX queue status. This is used - * to get number of currently queued packets (queue length), maximum queue - * size (limit), and total number of packets sent using each TX queue - * (count). The 'stats' pointer points to an array that has hw->queues - * items. - * The callback must be atomic. - * * @get_tsf: Get the current TSF timer value from firmware/hardware. Currently, * this is only used for IBSS mode BSSID merging and debugging. Is not a * required function. @@ -1648,8 +1628,6 @@ struct ieee80211_ops { enum sta_notify_cmd, struct ieee80211_sta *sta); int (*conf_tx)(struct ieee80211_hw *hw, u16 queue, const struct ieee80211_tx_queue_params *params); - int (*get_tx_stats)(struct ieee80211_hw *hw, - struct ieee80211_tx_queue_stats *stats); u64 (*get_tsf)(struct ieee80211_hw *hw); void (*set_tsf)(struct ieee80211_hw *hw, u64 tsf); void (*reset_tsf)(struct ieee80211_hw *hw); -- cgit v1.1 From 375177bf35efc08e1bd37bbda4cc0c8cc4db8500 Mon Sep 17 00:00:00 2001 From: Vivek Natarajan Date: Tue, 9 Feb 2010 14:50:28 +0530 Subject: mac80211: Retry null data frame for power save. Even if the null data frame is not acked by the AP, mac80211 goes into power save. This might lead to loss of frames from the AP. Prevent this by restarting dynamic_ps_timer when ack is not received for null data frames. Cc: Johannes Berg Signed-off-by: Vivek Natarajan Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 414d774..314e981 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -945,6 +945,11 @@ enum ieee80211_tkip_key_type { * Hardware supports Unscheduled Automatic Power Save Delivery * (U-APSD) in managed mode. The mode is configured with * conf_tx() operation. + * + * @IEEE80211_HW_REPORTS_TX_ACK_STATUS: + * Hardware can provide ack status reports of Tx frames to + * the stack. + * */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -965,6 +970,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_STATIC_SMPS = 1<<15, IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS = 1<<16, IEEE80211_HW_SUPPORTS_UAPSD = 1<<17, + IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, }; /** -- cgit v1.1 From 0a02604628c49037e1de2091d75462fd856b26ed Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 10 Feb 2010 15:00:32 +0100 Subject: netfilter: xtables: consistent struct compat_xt_counters definition There is compat_u64 type which deals with different u64 type alignment on different compat-capable platforms, so use it and removed some hardcoded assumptions. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 365fabe..8b6c0e7 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -562,11 +562,7 @@ struct compat_xt_entry_target { * current task alignment */ struct compat_xt_counters { -#if defined(CONFIG_X86_64) || defined(CONFIG_IA64) - u_int32_t cnt[4]; -#else - u_int64_t cnt[2]; -#endif + compat_u64 pcnt, bcnt; /* Packet and byte counters */ }; struct compat_xt_counters_info { -- cgit v1.1 From 42107f5009da223daa800d6da6904d77297ae829 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 10 Feb 2010 15:03:27 +0100 Subject: netfilter: xtables: symmetric COMPAT_XT_ALIGN definition Rewrite COMPAT_XT_ALIGN in terms of dummy structure hack. Compat counters logically have nothing to do with it. Use ALIGN() macro while I'm at it for same types. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 8b6c0e7..9d671eb 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -93,8 +93,7 @@ struct _xt_align { __u64 u64; }; -#define XT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) \ - & ~(__alignof__(struct _xt_align)-1)) +#define XT_ALIGN(s) ALIGN((s), __alignof__(struct _xt_align)) /* Standard return verdict, or do jump. */ #define XT_STANDARD_TARGET "" @@ -571,8 +570,14 @@ struct compat_xt_counters_info { struct compat_xt_counters counters[0]; }; -#define COMPAT_XT_ALIGN(s) (((s) + (__alignof__(struct compat_xt_counters)-1)) \ - & ~(__alignof__(struct compat_xt_counters)-1)) +struct _compat_xt_align { + __u8 u8; + __u16 u16; + __u32 u32; + compat_u64 u64; +}; + +#define COMPAT_XT_ALIGN(s) ALIGN((s), __alignof__(struct _compat_xt_align)) extern void xt_compat_lock(u_int8_t af); extern void xt_compat_unlock(u_int8_t af); -- cgit v1.1 From 2b95efe7f6bb750256a702cc32d33b0cb2cd8223 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 17 Jun 2009 13:57:48 +0200 Subject: netfilter: xtables: use xt_table for hook instantiation The respective xt_table structures already have most of the metadata needed for hook setup. Add a 'priority' field to struct xt_table so that xt_hook_link() can be called with a reduced number of arguments. So should we be having more tables in the future, it comes at no static cost (only runtime, as before) - space saved: 6807373->6806555. Signed-off-by: Jan Engelhardt --- include/linux/netfilter/x_tables.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 365fabe..fdd3342 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -361,6 +361,7 @@ struct xt_table { struct module *me; u_int8_t af; /* address/protocol family */ + int priority; /* hook order */ /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; @@ -522,6 +523,9 @@ static inline unsigned long ifname_compare_aligned(const char *_a, return ret; } +extern struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *); +extern void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *); + #ifdef CONFIG_COMPAT #include -- cgit v1.1 From e3eaa9910b380530cfd2c0670fcd3f627674da8a Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 17 Jun 2009 22:14:54 +0200 Subject: netfilter: xtables: generate initial table on-demand The static initial tables are pretty large, and after the net namespace has been instantiated, they just hang around for nothing. This commit removes them and creates tables on-demand at runtime when needed. Size shrinks by 7735 bytes (x86_64). Signed-off-by: Jan Engelhardt --- include/linux/netfilter_arp/arp_tables.h | 1 + include/linux/netfilter_ipv4/ip_tables.h | 1 + include/linux/netfilter_ipv6/ip6_tables.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index f233652..0b33980 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -258,6 +258,7 @@ struct arpt_error { .target.errorname = "ERROR", \ } +extern void *arpt_alloc_initial_table(const struct xt_table *); extern struct xt_table *arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 8d1f273..364973b 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -282,6 +282,7 @@ struct ipt_error { .target.errorname = "ERROR", \ } +extern void *ipt_alloc_initial_table(const struct xt_table *); extern unsigned int ipt_do_table(struct sk_buff *skb, unsigned int hook, const struct net_device *in, diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index d2952d2..8031eb4 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -297,6 +297,7 @@ ip6t_get_target(struct ip6t_entry *e) #include extern void ip6t_init(void) __init; +extern void *ip6t_alloc_initial_table(const struct xt_table *); extern struct xt_table *ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl); -- cgit v1.1 From 66655de6d132b726be64c324bc3f9ea366d20697 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 8 Feb 2010 23:18:22 +0000 Subject: seq_file: Add helpers for iteration over a hlist Some places in kernel need to iterate over a hlist in seq_file, so provide some common helpers. Signed-off-by: Li Zefan Signed-off-by: David S. Miller --- include/linux/seq_file.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 8366d8f..c95bcdc 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -135,4 +135,15 @@ extern struct list_head *seq_list_start_head(struct list_head *head, extern struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos); +/* + * Helpers for iteration over hlist_head-s in seq_files + */ + +extern struct hlist_node *seq_hlist_start(struct hlist_head *head, + loff_t pos); +extern struct hlist_node *seq_hlist_start_head(struct hlist_head *head, + loff_t pos); +extern struct hlist_node *seq_hlist_next(void *v, struct hlist_head *head, + loff_t *ppos); + #endif -- cgit v1.1 From c4146644a56b1f213c4c5567c75771883bec33c7 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 8 Feb 2010 23:18:45 +0000 Subject: net: add a wrapper sk_entry() Signed-off-by: Li Zefan Signed-off-by: David S. Miller --- include/net/sock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 3f1a4804..c8d4000 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -317,6 +317,11 @@ struct sock { /* * Hashed lists helper routines */ +static inline struct sock *sk_entry(const struct hlist_node *node) +{ + return hlist_entry(node, struct sock, sk_node); +} + static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); -- cgit v1.1 From 15682bc488d4af8c9bb998844a94281025e0a333 Mon Sep 17 00:00:00 2001 From: Peter P Waskiewicz Jr Date: Wed, 10 Feb 2010 20:03:05 -0800 Subject: ethtool: Introduce n-tuple filter programming support This patchset enables the ethtool layer to program n-tuple filters to an underlying device. The idea is to allow capable hardware to have static rules applied that can assist steering flows into appropriate queues. Hardware that is known to support these types of filters today are ixgbe and niu. Signed-off-by: Peter P Waskiewicz Jr Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/ethtool.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netdevice.h | 3 +++ 2 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index ef4a2d8..a3cac53 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -14,6 +14,7 @@ #define _LINUX_ETHTOOL_H #include +#include /* This should work for both 32 and 64 bit userland. */ struct ethtool_cmd { @@ -242,6 +243,7 @@ enum ethtool_stringset { ETH_SS_TEST = 0, ETH_SS_STATS, ETH_SS_PRIV_FLAGS, + ETH_SS_NTUPLE_FILTERS, }; /* for passing string sets for data tagging */ @@ -290,6 +292,7 @@ struct ethtool_perm_addr { */ enum ethtool_flags { ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */ + ETH_FLAG_NTUPLE = (1 << 27), /* N-tuple filters enabled */ }; /* The following structures are for supporting RX network flow @@ -363,6 +366,35 @@ struct ethtool_rxnfc { __u32 rule_locs[0]; }; +struct ethtool_rx_ntuple_flow_spec { + __u32 flow_type; + union { + struct ethtool_tcpip4_spec tcp_ip4_spec; + struct ethtool_tcpip4_spec udp_ip4_spec; + struct ethtool_tcpip4_spec sctp_ip4_spec; + struct ethtool_ah_espip4_spec ah_ip4_spec; + struct ethtool_ah_espip4_spec esp_ip4_spec; + struct ethtool_rawip4_spec raw_ip4_spec; + struct ethtool_ether_spec ether_spec; + struct ethtool_usrip4_spec usr_ip4_spec; + __u8 hdata[64]; + } h_u, m_u; /* entry, mask */ + + __u16 vlan_tag; + __u16 vlan_tag_mask; + __u64 data; /* user-defined flow spec data */ + __u64 data_mask; /* user-defined flow spec mask */ + + /* signed to distinguish between queue and actions (DROP) */ + __s32 action; +#define ETHTOOL_RXNTUPLE_ACTION_DROP -1 +}; + +struct ethtool_rx_ntuple { + __u32 cmd; + struct ethtool_rx_ntuple_flow_spec fs; +}; + #define ETHTOOL_FLASH_MAX_FILENAME 128 enum ethtool_flash_op_type { ETHTOOL_FLASH_ALL_REGIONS = 0, @@ -377,6 +409,18 @@ struct ethtool_flash { #ifdef __KERNEL__ +struct ethtool_rx_ntuple_flow_spec_container { + struct ethtool_rx_ntuple_flow_spec fs; + struct list_head list; +}; + +struct ethtool_rx_ntuple_list { +#define ETHTOOL_MAX_NTUPLE_LIST_ENTRY 1024 +#define ETHTOOL_MAX_NTUPLE_STRING_PER_ENTRY 14 + struct list_head list; + unsigned int count; +}; + struct net_device; /* Some generic methods drivers may use in their ethtool_ops */ @@ -394,6 +438,7 @@ u32 ethtool_op_get_ufo(struct net_device *dev); int ethtool_op_set_ufo(struct net_device *dev, u32 data); u32 ethtool_op_get_flags(struct net_device *dev); int ethtool_op_set_flags(struct net_device *dev, u32 data); +void ethtool_ntuple_flush(struct net_device *dev); /** * ðtool_ops - Alter and report network device settings @@ -500,6 +545,8 @@ struct ethtool_ops { int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); int (*flash_device)(struct net_device *, struct ethtool_flash *); int (*reset)(struct net_device *, u32 *); + int (*set_rx_ntuple)(struct net_device *, struct ethtool_rx_ntuple *); + int (*get_rx_ntuple)(struct net_device *, u32 stringset, void *); }; #endif /* __KERNEL__ */ @@ -559,6 +606,9 @@ struct ethtool_ops { #define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ #define ETHTOOL_RESET 0x00000034 /* Reset hardware */ +#define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ +#define ETHTOOL_GRXNTUPLE 0x00000036 /* Get n-tuple filters from device */ + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e535700..cdf53a8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -746,6 +746,7 @@ struct net_device { #define NETIF_F_FCOE_CRC (1 << 24) /* FCoE CRC32 */ #define NETIF_F_SCTP_CSUM (1 << 25) /* SCTP checksum offload */ #define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/ +#define NETIF_F_NTUPLE (1 << 27) /* N-tuple filters supported */ /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 @@ -954,6 +955,8 @@ struct net_device { /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; #endif + /* n-tuple filter list attached to this device */ + struct ethtool_rx_ntuple_list ethtool_ntuple_list; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.1 From b87921bdf25485afd8f5a5f25e86b5acef32a9cf Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:22:48 +0100 Subject: netfilter: nf_conntrack: show helper and class in /proc/net/nf_conntrack_expect Make the output a bit more informative by showing the helper an expectation belongs to and the expectation class. Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack_expect.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 9a2b9cb..917e170 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -66,6 +66,7 @@ static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) struct nf_conntrack_expect_policy { unsigned int max_expected; unsigned int timeout; + const char *name; }; #define NF_CT_EXPECT_CLASS_DEFAULT 0 -- cgit v1.1 From 3b6b9fab42fe98358d70735cf98d43fc18dc79c9 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:23:53 +0100 Subject: netfilter: nf_conntrack_sip: pass data offset to NAT functions When using TCP multiple SIP messages might be present in a single packet. A following patch will parse them by setting the dptr to the beginning of each message. The NAT helper needs to reload the dptr value after mangling the packet however, so it needs to know the offset of the message to the beginning of the packet. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_sip.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 23aa2ec..2c6950b 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -34,10 +34,10 @@ struct sdp_media_type { struct sip_handler { const char *method; unsigned int len; - int (*request)(struct sk_buff *skb, + int (*request)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq); - int (*response)(struct sk_buff *skb, + int (*response)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code); }; @@ -100,33 +100,39 @@ enum sdp_header_types { }; extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, + unsigned int dataoff, const char **dptr, unsigned int *datalen); extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, + unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *exp, unsigned int matchoff, unsigned int matchlen); extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, - const char **dptr, unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, enum sdp_header_types type, enum sdp_header_types term, const union nf_inet_addr *addr); extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, unsigned int matchlen, u_int16_t port); extern unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, - const char **dptr, unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, const union nf_inet_addr *addr); extern unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, + unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *rtp_exp, -- cgit v1.1 From f5b321bd37fbec9188feb1f721ab46a5ac0b35da Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:26:19 +0100 Subject: netfilter: nf_conntrack_sip: add TCP support Add TCP support, which is mandated by RFC3261 for all SIP elements. SIP over TCP is similar to UDP, except that messages are delimited by Content-Length: headers and multiple messages may appear in one packet. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_sip.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 2c6950b..fa9bb89 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -84,7 +84,8 @@ enum sip_header_types { SIP_HDR_FROM, SIP_HDR_TO, SIP_HDR_CONTACT, - SIP_HDR_VIA, + SIP_HDR_VIA_UDP, + SIP_HDR_VIA_TCP, SIP_HDR_EXPIRES, SIP_HDR_CONTENT_LENGTH, }; -- cgit v1.1 From 010c0b9f34a4c567b431f8b49a58b7332ed42e47 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:27:09 +0100 Subject: netfilter: nf_nat: support mangling a single TCP packet multiple times nf_nat_mangle_tcp_packet() can currently only handle a single mangling per window because it only maintains two sequence adjustment positions: the one before the last adjustment and the one after. This patch makes sequence number adjustment tracking in nf_nat_mangle_tcp_packet() optional and allows a helper to manually update the offsets after the packet has been fully handled. Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_nat_helper.h | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 4222220..02bb6c2 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -7,13 +7,27 @@ struct sk_buff; /* These return true or false. */ -extern int nf_nat_mangle_tcp_packet(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int match_offset, - unsigned int match_len, - const char *rep_buffer, - unsigned int rep_len); +extern int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len, bool adjust); + +static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + return __nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + match_offset, match_len, + rep_buffer, rep_len, true); +} + extern int nf_nat_mangle_udp_packet(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, @@ -21,6 +35,10 @@ extern int nf_nat_mangle_udp_packet(struct sk_buff *skb, unsigned int match_len, const char *rep_buffer, unsigned int rep_len); + +extern void nf_nat_set_seq_adjust(struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + __be32 seq, s16 off); extern int nf_nat_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo); -- cgit v1.1 From 48f8ac26537c1b7b1a2422f5232f45d06c945348 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:29:38 +0100 Subject: netfilter: nf_nat_sip: add TCP support Add support for mangling TCP SIP packets. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_sip.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index fa9bb89..cd84d6f 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -104,6 +104,7 @@ extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen); +extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off); extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, -- cgit v1.1 From 9d288dffe3a276e1f06ba556845c456d696c5a4f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:30:21 +0100 Subject: netfilter: nf_conntrack_sip: add T.38 FAX support Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_sip.h | 1 + include/net/netfilter/nf_conntrack.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index cd84d6f..ff8cfbc 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -14,6 +14,7 @@ enum sip_expectation_classes { SIP_EXPECT_SIGNALLING, SIP_EXPECT_AUDIO, SIP_EXPECT_VIDEO, + SIP_EXPECT_IMAGE, __SIP_EXPECT_MAX }; #define SIP_EXPECT_MAX (__SIP_EXPECT_MAX - 1) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5043d61..5b7d883 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -70,7 +70,7 @@ union nf_conntrack_help { struct nf_conntrack_helper; /* Must be kept in sync with the classes defined by helpers */ -#define NF_CT_MAX_EXPECT_CLASSES 3 +#define NF_CT_MAX_EXPECT_CLASSES 4 /* nf_conn feature for connections that have a helper */ struct nf_conn_help { -- cgit v1.1 From 857b409a48bdc33e824dff2d730e271b964e78bd Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 12 Feb 2010 06:24:46 +0100 Subject: netfilter: nf_conntrack: elegantly simplify nf_ct_exp_net() Remove #ifdef at nf_ct_exp_net() by using nf_ct_net(). Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack_expect.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 917e170..4b47ec1 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -56,11 +56,7 @@ struct nf_conntrack_expect { static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) { -#ifdef CONFIG_NET_NS - return exp->master->ct_net; /* by definition */ -#else - return &init_net; -#endif + return nf_ct_net(exp->master); } struct nf_conntrack_expect_policy { -- cgit v1.1 From 2bec5a369ee79576a3eea2c23863325089785a2c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 8 Feb 2010 05:19:03 +0000 Subject: ipv6: fib: fix crash when changing large fib while dumping it When the fib size exceeds what can be dumped in a single skb, the dump is suspended and resumed once the last skb has been received by userspace. When the fib is changed while the dump is suspended, the walker might contain stale pointers, causing a crash when the dump is resumed. BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 IP: [] fib6_walk_continue+0xbb/0x124 [ipv6] PGD 5347a067 PUD 65c7067 PMD 0 Oops: 0000 [#1] PREEMPT SMP ... RIP: 0010:[] [] fib6_walk_continue+0xbb/0x124 [ipv6] ... Call Trace: [] ? mutex_spin_on_owner+0x59/0x71 [] inet6_dump_fib+0x11b/0x1b9 [ipv6] [] netlink_dump+0x5b/0x19e [] ? consume_skb+0x28/0x2a [] netlink_recvmsg+0x1ab/0x2c6 [] ? netlink_unicast+0xfa/0x151 [] __sock_recvmsg+0x6d/0x79 [] sock_recvmsg+0xca/0xe3 [] ? autoremove_wake_function+0x0/0x38 [] ? radix_tree_lookup_slot+0xe/0x10 [] ? find_get_page+0x90/0xa5 [] ? filemap_fault+0x201/0x34f [] ? fget_light+0x2f/0xac [] ? verify_iovec+0x4f/0x94 [] sys_recvmsg+0x14d/0x223 Store the serial number when beginning to walk the fib and reload pointers when continuing to walk after a change occured. Similar to other dumping functions, this might cause unrelated entries to be missed when entries are deleted. Tested-by: Ben Greear Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 2578081..8f279dd 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -129,6 +129,8 @@ struct fib6_walker_t { struct rt6_info *leaf; unsigned char state; unsigned char prune; + unsigned int skip; + unsigned int count; int (*func)(struct fib6_walker_t *); void *args; }; -- cgit v1.1 From 571ba42303813106d533bf6bda929d8e289f51bf Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 9 Feb 2010 11:49:47 +0000 Subject: netdevice.h: Add netdev_printk helpers like dev_printk These netdev_printk routines take a struct net_device * and emit dev_printk logging messages adding "%s: " ... netdev->dev.parent to the dev_printk format and arguments. This can create some uniformity in the output message log. These helpers should not be used until a successful alloc_netdev. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netdevice.h | 71 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cdf53a8..a51228a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2095,6 +2095,77 @@ static inline u32 dev_ethtool_get_flags(struct net_device *dev) return 0; return dev->ethtool_ops->get_flags(dev); } + +/* Logging, debugging and troubleshooting/diagnostic helpers. */ + +/* netdev_printk helpers, similar to dev_printk */ + +static inline const char *netdev_name(const struct net_device *dev) +{ + if (dev->reg_state != NETREG_REGISTERED) + return "(unregistered net_device)"; + return dev->name; +} + +#define netdev_printk(level, netdev, format, args...) \ + dev_printk(level, (netdev)->dev.parent, \ + "%s: " format, \ + netdev_name(netdev), ##args) + +#define netdev_emerg(dev, format, args...) \ + netdev_printk(KERN_EMERG, dev, format, ##args) +#define netdev_alert(dev, format, args...) \ + netdev_printk(KERN_ALERT, dev, format, ##args) +#define netdev_crit(dev, format, args...) \ + netdev_printk(KERN_CRIT, dev, format, ##args) +#define netdev_err(dev, format, args...) \ + netdev_printk(KERN_ERR, dev, format, ##args) +#define netdev_warn(dev, format, args...) \ + netdev_printk(KERN_WARNING, dev, format, ##args) +#define netdev_notice(dev, format, args...) \ + netdev_printk(KERN_NOTICE, dev, format, ##args) +#define netdev_info(dev, format, args...) \ + netdev_printk(KERN_INFO, dev, format, ##args) + +#if defined(DEBUG) +#define netdev_dbg(__dev, format, args...) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args) +#elif defined(CONFIG_DYNAMIC_DEBUG) +#define netdev_dbg(__dev, format, args...) \ +do { \ + dynamic_dev_dbg((__dev)->dev.parent, "%s: " format, \ + netdev_name(__dev), ##args); \ +} while (0) +#else +#define netdev_dbg(__dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args); \ + 0; \ +}) +#endif + +#if defined(VERBOSE_DEBUG) +#define netdev_vdbg netdev_dbg +#else + +#define netdev_vdbg(dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* + * netdev_WARN() acts like dev_printk(), but with the key difference + * of using a WARN/WARN_ON to get the message out, including the + * file/line information and a backtrace. + */ +#define netdev_WARN(dev, format, args...) \ + WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args); + + #endif /* __KERNEL__ */ #endif /* _LINUX_NETDEVICE_H */ -- cgit v1.1 From b3d95c5c93d4b57eaea0ad3f582b08a6b5fb3eb1 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 9 Feb 2010 11:49:49 +0000 Subject: include/linux/netdevice.h: Add netif_printk helpers Add macros to test a private structure for msg_enable bits and the netif_msg_##bit to test and call netdev_printk if set Simplifies logic in callers and adds message logging consistency Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netdevice.h | 53 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a51228a..1412dde 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2165,6 +2165,59 @@ do { \ #define netdev_WARN(dev, format, args...) \ WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args); +/* netif printk helpers, similar to netdev_printk */ + +#define netif_printk(priv, type, level, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_printk(level, (dev), fmt, ##args); \ +} while (0) + +#define netif_emerg(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_EMERG, dev, fmt, ##args) +#define netif_alert(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_ALERT, dev, fmt, ##args) +#define netif_crit(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_CRIT, dev, fmt, ##args) +#define netif_err(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_ERR, dev, fmt, ##args) +#define netif_warn(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_WARNING, dev, fmt, ##args) +#define netif_notice(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_NOTICE, dev, fmt, ##args) +#define netif_info(priv, type, dev, fmt, args...) \ + netif_printk(priv, type, KERN_INFO, (dev), fmt, ##args) + +#if defined(DEBUG) +#define netif_dbg(priv, type, dev, format, args...) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) +#elif defined(CONFIG_DYNAMIC_DEBUG) +#define netif_dbg(priv, type, netdev, format, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + dynamic_dev_dbg((netdev)->dev.parent, \ + "%s: " format, \ + netdev_name(netdev), ##args); \ +} while (0) +#else +#define netif_dbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +#if defined(VERBOSE_DEBUG) +#define netif_vdbg netdev_dbg +#else +#define netif_vdbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif #endif /* __KERNEL__ */ -- cgit v1.1 From a63374631e7192a64648ecc6672619a7abf9ebcd Mon Sep 17 00:00:00 2001 From: jamal Date: Tue, 9 Feb 2010 13:21:17 +0000 Subject: xfrm: use proper kernel types kernel side should use uxx instead of __uxx types Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/xfrm.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fcee547..0beb413 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -317,8 +317,8 @@ extern void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { char *description; struct module *owner; - __u8 proto; - __u8 flags; + u8 proto; + u8 flags; #define XFRM_TYPE_NON_FRAGMENT 1 #define XFRM_TYPE_REPLAY_PROT 2 #define XFRM_TYPE_LOCAL_COADDR 4 @@ -434,24 +434,24 @@ struct xfrm_tmpl { unsigned short encap_family; - __u32 reqid; + u32 reqid; /* Mode: transport, tunnel etc. */ - __u8 mode; + u8 mode; /* Sharing mode: unique, this session only, this user only etc. */ - __u8 share; + u8 share; /* May skip this transfomration if no SA is found */ - __u8 optional; + u8 optional; /* Skip aalgos/ealgos/calgos checks. */ - __u8 allalgs; + u8 allalgs; /* Bit mask of algos allowed for acquisition */ - __u32 aalgos; - __u32 ealgos; - __u32 calgos; + u32 aalgos; + u32 ealgos; + u32 calgos; }; #define XFRM_MAX_DEPTH 6 @@ -770,7 +770,7 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen) int pdw; int pbi; - pdw = prefixlen >> 5; /* num of whole __u32 in prefix */ + pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pdw) @@ -1259,7 +1259,7 @@ struct xfrm_algo_desc { /* XFRM tunnel handlers. */ struct xfrm_tunnel { int (*handler)(struct sk_buff *skb); - int (*err_handler)(struct sk_buff *skb, __u32 info); + int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm_tunnel *next; int priority; @@ -1500,7 +1500,7 @@ static inline int xfrm_addr_cmp(xfrm_address_t *a, xfrm_address_t *b, switch (family) { default: case AF_INET: - return (__force __u32)a->a4 - (__force __u32)b->a4; + return (__force u32)a->a4 - (__force u32)b->a4; case AF_INET6: return ipv6_addr_cmp((struct in6_addr *)a, (struct in6_addr *)b); -- cgit v1.1 From fb8a0d9d1bfd1e4355f307e86a6da7209eefd5f3 Mon Sep 17 00:00:00 2001 From: "Williams, Mitch A" Date: Wed, 10 Feb 2010 01:43:04 +0000 Subject: pci: Add SR-IOV convenience functions and macros Add and export pci_num_vf to allow other subsystems to determine how many virtual function devices are associated with an SR-IOV physical function device. Add macros dev_is_pci, dev_is_ps, and dev_num_vf to make it easier for non-PCI specific code to determine SR-IOV capabilities. Signed-off-by: Mitch Williams Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/pci.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 174e539..59a98e2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -612,6 +612,9 @@ extern void pci_remove_bus_device(struct pci_dev *dev); extern void pci_stop_bus_device(struct pci_dev *dev); void pci_setup_cardbus(struct pci_bus *bus); extern void pci_sort_breadthfirst(void); +#define dev_is_pci(d) ((d)->bus == &pci_bus_type) +#define dev_is_pf(d) ((dev_is_pci(d) ? to_pci_dev(d)->is_physfn : false)) +#define dev_num_vf(d) ((dev_is_pci(d) ? pci_num_vf(to_pci_dev(d)) : 0)) /* Generic PCI functions exported to card drivers */ @@ -1129,6 +1132,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus, unsigned int devfn) { return NULL; } +#define dev_is_pci(d) (false) +#define dev_is_pf(d) (false) +#define dev_num_vf(d) (0) #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ @@ -1286,6 +1292,7 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar); extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); extern void pci_disable_sriov(struct pci_dev *dev); extern irqreturn_t pci_sriov_migration(struct pci_dev *dev); +extern int pci_num_vf(struct pci_dev *dev); #else static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { @@ -1298,6 +1305,10 @@ static inline irqreturn_t pci_sriov_migration(struct pci_dev *dev) { return IRQ_NONE; } +static inline int pci_num_vf(struct pci_dev *dev) +{ + return 0; +} #endif #if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE) -- cgit v1.1 From b280da8d54b8d82b52f368a8703b7ada6c1744d5 Mon Sep 17 00:00:00 2001 From: "Williams, Mitch A" Date: Wed, 10 Feb 2010 01:43:24 +0000 Subject: if_link: Add SR-IOV configuration methods Add SR-IOV VF management methods to IFLA_LINKINFO. This allows userspace to use rtnetlink to configure VF network devices. Signed-off-by: Mitch Williams Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/if_link.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 6674791..c9bf92c 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -78,6 +78,11 @@ enum { #define IFLA_LINKINFO IFLA_LINKINFO IFLA_NET_NS_PID, IFLA_IFALIAS, + IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, + IFLA_VF_TX_RATE, /* TX Bandwidth Allocation */ + IFLA_VFINFO, __IFLA_MAX }; @@ -196,4 +201,29 @@ enum macvlan_mode { MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ }; +/* SR-IOV virtual function managment section */ + +struct ifla_vf_mac { + __u32 vf; + __u8 mac[32]; /* MAX_ADDR_LEN */ +}; + +struct ifla_vf_vlan { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; +}; + +struct ifla_vf_tx_rate { + __u32 vf; + __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ +}; + +struct ifla_vf_info { + __u32 vf; + __u8 mac[32]; + __u32 vlan; + __u32 qos; + __u32 tx_rate; +}; #endif /* _LINUX_IF_LINK_H */ -- cgit v1.1 From 95c26df829ba4a25f40595cadb4c9433883cbe28 Mon Sep 17 00:00:00 2001 From: "Williams, Mitch A" Date: Wed, 10 Feb 2010 01:43:46 +0000 Subject: net: Add netdev ops for SR-IOV configuration Add netdev ops for configuring SR-IOV VF devices through the PF driver. Signed-off-by: Mitch Williams Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1412dde..682d025 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -28,6 +28,7 @@ #include #include #include +#include #ifdef __KERNEL__ #include @@ -621,6 +622,13 @@ struct netdev_queue { * this function is called when a VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); + * + * SR-IOV management functions. + * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); + * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); + * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate); + * int (*ndo_get_vf_config)(struct net_device *dev, + * int vf, struct ifla_vf_info *ivf); */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { @@ -660,6 +668,15 @@ struct net_device_ops { #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); #endif + int (*ndo_set_vf_mac)(struct net_device *dev, + int queue, u8 *mac); + int (*ndo_set_vf_vlan)(struct net_device *dev, + int queue, u16 vlan, u8 qos); + int (*ndo_set_vf_tx_rate)(struct net_device *dev, + int vf, int rate); + int (*ndo_get_vf_config)(struct net_device *dev, + int vf, + struct ifla_vf_info *ivf); #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); -- cgit v1.1 From 1a5778aa000ebfec7f07eed0ffa2852ffb5d16bb Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sun, 14 Feb 2010 22:35:47 -0800 Subject: net: Fix first line of kernel-doc for a few functions The function name must be followed by a space, hypen, space, and a short description. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- include/net/sock.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ae836fd..ba0f8e3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -738,7 +738,7 @@ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, } /** - * skb_peek + * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ @@ -759,7 +759,7 @@ static inline struct sk_buff *skb_peek(struct sk_buff_head *list_) } /** - * skb_peek_tail + * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ diff --git a/include/net/sock.h b/include/net/sock.h index c8d4000..580d51fa 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1049,7 +1049,7 @@ extern void sk_common_release(struct sock *sk); extern void sock_init_data(struct socket *sock, struct sock *sk); /** - * sk_filter_release: Release a socket filter + * sk_filter_release - release a socket filter * @fp: filter to remove * * Remove a filter from a socket and release its resources. -- cgit v1.1 From a1467085dcad8214bbb1d7edafbaa295cbd8c0e7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 14 Feb 2010 22:38:54 -0800 Subject: ethtool: Fix includes build break Based upon a patch by Oliver Hartkopp . Signed-off-by: David S. Miller --- include/linux/ethtool.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a3cac53..cca1c3de 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -14,7 +14,6 @@ #define _LINUX_ETHTOOL_H #include -#include /* This should work for both 32 and 64 bit userland. */ struct ethtool_cmd { @@ -409,6 +408,8 @@ struct ethtool_flash { #ifdef __KERNEL__ +#include + struct ethtool_rx_ntuple_flow_spec_container { struct ethtool_rx_ntuple_flow_spec fs; struct list_head list; -- cgit v1.1 From 23f3733d440b918ccb7746718f77256334cf6176 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 5 Jun 2009 17:31:46 +0200 Subject: netfilter: reduce NF_HOOK by one argument No changes in vmlinux filesize. Signed-off-by: Jan Engelhardt --- include/linux/netfilter.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 78f33d2..2f22816 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -163,11 +163,8 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh, - int cond) + int (*okfn)(struct sk_buff *), int thresh) { - if (!cond) - return 1; #ifndef CONFIG_NETFILTER_DEBUG if (list_empty(&nf_hooks[pf][hook])) return 1; @@ -179,7 +176,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *)) { - return nf_hook_thresh(pf, hook, skb, indev, outdev, okfn, INT_MIN, 1); + return nf_hook_thresh(pf, hook, skb, indev, outdev, okfn, INT_MIN); } /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -206,13 +203,13 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb, #define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \ ({int __ret; \ -if ((__ret=nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, thresh, 1)) == 1)\ +if ((__ret=nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, thresh)) == 1)\ __ret = (okfn)(skb); \ __ret;}) #define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) \ ({int __ret; \ -if ((__ret=nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, INT_MIN, cond)) == 1)\ +if ((cond) || (__ret = nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, INT_MIN)) == 1)\ __ret = (okfn)(skb); \ __ret;}) @@ -328,8 +325,7 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh, - int cond) + int (*okfn)(struct sk_buff *), int thresh) { return okfn(skb); } -- cgit v1.1 From 2249065f4b22b493bae2caf549b86f175f33188e Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 13 Jun 2009 04:13:26 +0200 Subject: netfilter: get rid of the grossness in netfilter.h GCC is now smart enough to follow the inline trail correctly. vmlinux size remain the same. Signed-off-by: Jan Engelhardt --- include/linux/netfilter.h | 45 ++++++++++++++++++++++++++++----------------- 1 file changed, 28 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 2f22816..7007945 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -196,25 +196,36 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb, coders :) */ -/* This is gross, but inline doesn't cut it for avoiding the function - call in fast path: gcc doesn't inline (needs value tracking?). --RR */ - -/* HX: It's slightly less gross now. */ - -#define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \ -({int __ret; \ -if ((__ret=nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, thresh)) == 1)\ - __ret = (okfn)(skb); \ -__ret;}) +static inline int +NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sk_buff *skb, + struct net_device *in, struct net_device *out, + int (*okfn)(struct sk_buff *), int thresh) +{ + int ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, thresh); + if (ret == 1) + ret = okfn(skb); + return ret; +} -#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) \ -({int __ret; \ -if ((cond) || (__ret = nf_hook_thresh(pf, hook, (skb), indev, outdev, okfn, INT_MIN)) == 1)\ - __ret = (okfn)(skb); \ -__ret;}) +static inline int +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sk_buff *skb, + struct net_device *in, struct net_device *out, + int (*okfn)(struct sk_buff *), bool cond) +{ + int ret = 1; + if (cond || + (ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, INT_MIN) == 1)) + ret = okfn(skb); + return ret; +} -#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) \ - NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, INT_MIN) +static inline int +NF_HOOK(uint8_t pf, unsigned int hook, struct sk_buff *skb, + struct net_device *in, struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return NF_HOOK_THRESH(pf, hook, skb, in, out, okfn, INT_MIN); +} /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, -- cgit v1.1 From 739674fb7febf116e7d647031fab16989a08a965 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 26 Jun 2009 08:23:19 +0200 Subject: netfilter: xtables: constify args in compat copying functions Signed-off-by: Jan Engelhardt --- include/linux/netfilter/x_tables.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index a0a144a..c61758f 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -286,8 +286,8 @@ struct xt_match { void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ - void (*compat_from_user)(void *dst, void *src); - int (*compat_to_user)(void __user *dst, void *src); + void (*compat_from_user)(void *dst, const void *src); + int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -328,8 +328,8 @@ struct xt_target { void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ - void (*compat_from_user)(void *dst, void *src); - int (*compat_to_user)(void __user *dst, void *src); + void (*compat_from_user)(void *dst, const void *src); + int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -593,13 +593,13 @@ extern short xt_compat_calc_jump(u_int8_t af, unsigned int offset); extern int xt_compat_match_offset(const struct xt_match *match); extern int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size); -extern int xt_compat_match_to_user(struct xt_entry_match *m, +extern int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size); extern int xt_compat_target_offset(const struct xt_target *target); extern void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size); -extern int xt_compat_target_to_user(struct xt_entry_target *t, +extern int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size); #endif /* CONFIG_COMPAT */ -- cgit v1.1 From 8fea97ec1772bbf553d89187340ef624d548e115 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Feb 2010 17:45:08 +0100 Subject: netfilter: nf_conntrack: pass template to l4proto ->error() handler The error handlers might need the template to get the conntrack zone introduced in the next patches to perform a conntrack lookup. Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack_l4proto.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index ca6dcf3..e3d3ee3 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -49,8 +49,8 @@ struct nf_conntrack_l4proto { /* Called when a conntrack entry is destroyed */ void (*destroy)(struct nf_conn *ct); - int (*error)(struct net *net, struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info *ctinfo, + int (*error)(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum); /* Print out the per-protocol part of the tuple. Return like seq_* */ -- cgit v1.1 From 5d0aa2ccd4699a01cfdf14886191c249d7b45a01 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Feb 2010 18:13:33 +0100 Subject: netfilter: nf_conntrack: add support for "conntrack zones" Normally, each connection needs a unique identity. Conntrack zones allow to specify a numerical zone using the CT target, connections in different zones can use the same identity. Example: iptables -t raw -A PREROUTING -i veth0 -j CT --zone 1 iptables -t raw -A OUTPUT -o veth1 -j CT --zone 1 Signed-off-by: Patrick McHardy --- include/linux/netfilter/xt_CT.h | 2 +- include/net/ip.h | 3 +++ include/net/ipv6.h | 3 +++ include/net/netfilter/nf_conntrack.h | 5 +++-- include/net/netfilter/nf_conntrack_core.h | 3 ++- include/net/netfilter/nf_conntrack_expect.h | 9 ++++++--- include/net/netfilter/nf_conntrack_extend.h | 2 ++ include/net/netfilter/nf_conntrack_zones.h | 23 +++++++++++++++++++++++ 8 files changed, 43 insertions(+), 7 deletions(-) create mode 100644 include/net/netfilter/nf_conntrack_zones.h (limited to 'include') diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h index 7fd0eff..1b56410 100644 --- a/include/linux/netfilter/xt_CT.h +++ b/include/linux/netfilter/xt_CT.h @@ -5,7 +5,7 @@ struct xt_ct_target_info { u_int16_t flags; - u_int16_t __unused; + u_int16_t zone; u_int32_t ct_events; u_int32_t exp_events; char helper[16]; diff --git a/include/net/ip.h b/include/net/ip.h index fb63371..7bc4787 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -352,8 +352,11 @@ enum ip_defrag_users { IP_DEFRAG_LOCAL_DELIVER, IP_DEFRAG_CALL_RA_CHAIN, IP_DEFRAG_CONNTRACK_IN, + __IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHORT_MAX, IP_DEFRAG_CONNTRACK_OUT, + __IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHORT_MAX, IP_DEFRAG_CONNTRACK_BRIDGE_IN, + __IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX, IP_DEFRAG_VS_IN, IP_DEFRAG_VS_OUT, IP_DEFRAG_VS_FWD diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 299bbf5..639ec53 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -355,8 +355,11 @@ struct inet_frag_queue; enum ip6_defrag_users { IP6_DEFRAG_LOCAL_DELIVER, IP6_DEFRAG_CONNTRACK_IN, + __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHORT_MAX, IP6_DEFRAG_CONNTRACK_OUT, + __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHORT_MAX, IP6_DEFRAG_CONNTRACK_BRIDGE_IN, + __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX, }; struct ip6_create_arg { diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5b7d883..bde095f 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -198,7 +198,8 @@ extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int null extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size); extern struct nf_conntrack_tuple_hash * -__nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple); +__nf_conntrack_find(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple); extern void nf_conntrack_hash_insert(struct nf_conn *ct); extern void nf_ct_delete_from_lists(struct nf_conn *ct); @@ -267,7 +268,7 @@ extern void nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data); extern void nf_conntrack_free(struct nf_conn *ct); extern struct nf_conn * -nf_conntrack_alloc(struct net *net, +nf_conntrack_alloc(struct net *net, u16 zone, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl, gfp_t gfp); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 5a449b4..dffde8e 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -49,7 +49,8 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, /* Find a connection corresponding to a tuple. */ extern struct nf_conntrack_tuple_hash * -nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple); +nf_conntrack_find_get(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple); extern int __nf_conntrack_confirm(struct sk_buff *skb); diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 4b47ec1..11e8150 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -74,13 +74,16 @@ int nf_conntrack_expect_init(struct net *net); void nf_conntrack_expect_fini(struct net *net); struct nf_conntrack_expect * -__nf_ct_expect_find(struct net *net, const struct nf_conntrack_tuple *tuple); +__nf_ct_expect_find(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple); struct nf_conntrack_expect * -nf_ct_expect_find_get(struct net *net, const struct nf_conntrack_tuple *tuple); +nf_ct_expect_find_get(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple); struct nf_conntrack_expect * -nf_ct_find_expectation(struct net *net, const struct nf_conntrack_tuple *tuple); +nf_ct_find_expectation(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple); void nf_ct_unlink_expect(struct nf_conntrack_expect *exp); void nf_ct_remove_expectations(struct nf_conn *ct); diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index e192dc1..2d2a1f9 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -8,6 +8,7 @@ enum nf_ct_ext_id { NF_CT_EXT_NAT, NF_CT_EXT_ACCT, NF_CT_EXT_ECACHE, + NF_CT_EXT_ZONE, NF_CT_EXT_NUM, }; @@ -15,6 +16,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_NAT_TYPE struct nf_conn_nat #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache +#define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h new file mode 100644 index 0000000..0bbb2bd --- /dev/null +++ b/include/net/netfilter/nf_conntrack_zones.h @@ -0,0 +1,23 @@ +#ifndef _NF_CONNTRACK_ZONES_H +#define _NF_CONNTRACK_ZONES_H + +#include + +#define NF_CT_DEFAULT_ZONE 0 + +struct nf_conntrack_zone { + u16 id; +}; + +static inline u16 nf_ct_zone(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_ZONES + struct nf_conntrack_zone *nf_ct_zone; + nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE); + if (nf_ct_zone) + return nf_ct_zone->id; +#endif + return NF_CT_DEFAULT_ZONE; +} + +#endif /* _NF_CONNTRACK_ZONES_H */ -- cgit v1.1 From ef00f89f1eb7e056aab9dfe068521e6f2320c94a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Feb 2010 18:14:57 +0100 Subject: netfilter: ctnetlink: add zone support Parse and dump the conntrack zone in ctnetlink. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_conntrack.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index ed4ef8d..9ed534c 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -40,6 +40,7 @@ enum ctattr_type { CTA_NAT_SEQ_ADJ_ORIG, CTA_NAT_SEQ_ADJ_REPLY, CTA_SECMARK, + CTA_ZONE, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -159,6 +160,7 @@ enum ctattr_expect { CTA_EXPECT_TIMEOUT, CTA_EXPECT_ID, CTA_EXPECT_HELP_NAME, + CTA_EXPECT_ZONE, __CTA_EXPECT_MAX }; #define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1) -- cgit v1.1 From 3e5e524ffb5fcf2447eb5dd9f8e54ad22dd9baa7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 15 Feb 2010 18:17:10 +0100 Subject: netfilter: CONFIG_COMPAT: allow delta to exceed 32767 with 32 bit userland and 64 bit kernels, it is unlikely but possible that insertion of new rules fails even tough there are only about 2000 iptables rules. This happens because the compat delta is using a short int. Easily reproducible via "iptables -m limit" ; after about 2050 rules inserting new ones fails with -ELOOP. Note that compat_delta included 2 bytes of padding on x86_64, so structure size remains the same. Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index c61758f..a18119f 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -588,7 +588,7 @@ extern void xt_compat_unlock(u_int8_t af); extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta); extern void xt_compat_flush_offsets(u_int8_t af); -extern short xt_compat_calc_jump(u_int8_t af, unsigned int offset); +extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset); extern int xt_compat_match_offset(const struct xt_match *match); extern int xt_compat_match_from_user(struct xt_entry_match *m, -- cgit v1.1 From 026331c4d9b526561ea96f95fac4bfc52b69e316 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Mon, 15 Feb 2010 12:53:10 +0200 Subject: cfg80211/mac80211: allow registering for and sending action frames This implements a new command to register for action frames that userspace wants to handle instead of the in-kernel rejection. It is then responsible for rejecting ones that it decided not to handle. There is no unregistration, but the socket can be closed for that. Frames that are not registered for will not be forwarded to userspace and will be rejected by the kernel, the cfg80211 API helps implementing that. Additionally, this patch adds a new command that allows doing action frame transmission from userspace. It can be used either to exchange action frames on the current operational channel (e.g., with the AP with which we are currently associated) or to exchange off-channel Public Action frames with the remain-on-channel command. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 41 ++++++++++++++++++++++++++++++++++++++++- include/net/cfg80211.h | 47 ++++++++++++++++++++++++++++++++++++++++++++++- include/net/mac80211.h | 6 +++++- 3 files changed, 91 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 127a730..8e6384f 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -3,7 +3,7 @@ /* * 802.11 netlink interface public header * - * Copyright 2006, 2007, 2008 Johannes Berg + * Copyright 2006-2010 Johannes Berg * Copyright 2008 Michael Wu * Copyright 2008 Luis Carlos Cobo * Copyright 2008 Michael Buesch @@ -299,6 +299,31 @@ * rate selection. %NL80211_ATTR_IFINDEX is used to specify the interface * and @NL80211_ATTR_TX_RATES the set of allowed rates. * + * @NL80211_CMD_REGISTER_ACTION: Register for receiving certain action frames + * (via @NL80211_CMD_ACTION) for processing in userspace. This command + * requires an interface index and a match attribute containing the first + * few bytes of the frame that should match, e.g. a single byte for only + * a category match or four bytes for vendor frames including the OUI. + * The registration cannot be dropped, but is removed automatically + * when the netlink socket is closed. Multiple registrations can be made. + * @NL80211_CMD_ACTION: Action frame TX request and RX notification. This + * command is used both as a request to transmit an Action frame and as an + * event indicating reception of an Action frame that was not processed in + * kernel code, but is for us (i.e., which may need to be processed in a + * user space application). %NL80211_ATTR_FRAME is used to specify the + * frame contents (including header). %NL80211_ATTR_WIPHY_FREQ (and + * optionally %NL80211_ATTR_WIPHY_CHANNEL_TYPE) is used to indicate on + * which channel the frame is to be transmitted or was received. This + * channel has to be the current channel (remain-on-channel or the + * operational channel). When called, this operation returns a cookie + * (%NL80211_ATTR_COOKIE) that will be included with the TX status event + * pertaining to the TX request. + * @NL80211_CMD_ACTION_TX_STATUS: Report TX status of an Action frame + * transmitted with %NL80211_CMD_ACTION. %NL80211_ATTR_COOKIE identifies + * the TX command and %NL80211_ATTR_FRAME includes the contents of the + * frame. %NL80211_ATTR_ACK flag is included if the recipient acknowledged + * the frame. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -387,6 +412,10 @@ enum nl80211_commands { NL80211_CMD_SET_TX_BITRATE_MASK, + NL80211_CMD_REGISTER_ACTION, + NL80211_CMD_ACTION, + NL80211_CMD_ACTION_TX_STATUS, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -653,6 +682,12 @@ enum nl80211_commands { * rates based on negotiated supported rates information. This attribute * is used with %NL80211_CMD_SET_TX_BITRATE_MASK. * + * @NL80211_ATTR_FRAME_MATCH: A binary attribute which typically must contain + * at least one byte, currently used with @NL80211_CMD_REGISTER_ACTION. + * + * @NL80211_ATTR_ACK: Flag attribute indicating that the frame was + * acknowledged by the recipient. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -798,6 +833,10 @@ enum nl80211_attrs { NL80211_ATTR_TX_RATES, + NL80211_ATTR_FRAME_MATCH, + + NL80211_ATTR_ACK, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5b3569b..7188934 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3,7 +3,7 @@ /* * 802.11 device and configuration interface * - * Copyright 2006-2009 Johannes Berg + * Copyright 2006-2010 Johannes Berg * * 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 @@ -998,6 +998,7 @@ struct cfg80211_pmksa { * @cancel_remain_on_channel: Cancel an on-going remain-on-channel operation. * This allows the operation to be terminated prior to timeout based on * the duration value. + * @action: Transmit an action frame * * @testmode_cmd: run a test mode command * @@ -1144,6 +1145,11 @@ struct cfg80211_ops { struct net_device *dev, u64 cookie); + int (*action)(struct wiphy *wiphy, struct net_device *dev, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type, + const u8 *buf, size_t len, u64 *cookie); + /* some temporary stuff to finish wext */ int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); @@ -1445,6 +1451,8 @@ struct cfg80211_cached_keys; * set by driver (if supported) on add_interface BEFORE registering the * netdev and may otherwise be used by driver read-only, will be update * by cfg80211 on change_interface + * @action_registrations: list of registrations for action frames + * @action_registrations_lock: lock for the list */ struct wireless_dev { struct wiphy *wiphy; @@ -1454,6 +1462,9 @@ struct wireless_dev { struct list_head list; struct net_device *netdev; + struct list_head action_registrations; + spinlock_t action_registrations_lock; + struct mutex mtx; struct work_struct cleanup_work; @@ -2291,4 +2302,38 @@ void cfg80211_remain_on_channel_expired(struct net_device *dev, void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo, gfp_t gfp); +/** + * cfg80211_rx_action - notification of received, unprocessed Action frame + * @dev: network device + * @freq: Frequency on which the frame was received in MHz + * @buf: Action frame (header + body) + * @len: length of the frame data + * @gfp: context flags + * Returns %true if a user space application is responsible for rejecting the + * unrecognized Action frame; %false if no such application is registered + * (i.e., the driver is responsible for rejecting the unrecognized Action + * frame) + * + * This function is called whenever an Action frame is received for a station + * mode interface, but is not processed in kernel. + */ +bool cfg80211_rx_action(struct net_device *dev, int freq, const u8 *buf, + size_t len, gfp_t gfp); + +/** + * cfg80211_action_tx_status - notification of TX status for Action frame + * @dev: network device + * @cookie: Cookie returned by cfg80211_ops::action() + * @buf: Action frame (header + body) + * @len: length of the frame data + * @ack: Whether frame was acknowledged + * @gfp: context flags + * + * This function is called whenever an Action frame was requested to be + * transmitted with cfg80211_ops::action() to report the TX status of the + * transmission attempt. + */ +void cfg80211_action_tx_status(struct net_device *dev, u64 cookie, + const u8 *buf, size_t len, bool ack, gfp_t gfp); + #endif /* __NET_CFG80211_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 314e981..80eb7cc 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3,7 +3,7 @@ * * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc - * Copyright 2007-2008 Johannes Berg + * Copyright 2007-2010 Johannes Berg * * 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 @@ -264,6 +264,9 @@ struct ieee80211_bss_conf { * be modified again (no seqno assignment, crypto, etc.) * @IEEE80211_TX_INTFL_HAS_RADIOTAP: This frame was injected and still * has a radiotap header at skb->data. + * @IEEE80211_TX_INTFL_NL80211_FRAME_TX: Frame was requested through nl80211 + * MLME command (internal to mac80211 to figure out whether to send TX + * status to user space) */ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), @@ -286,6 +289,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_MORE_FRAMES = BIT(18), IEEE80211_TX_INTFL_RETRANSMISSION = BIT(19), IEEE80211_TX_INTFL_HAS_RADIOTAP = BIT(20), + IEEE80211_TX_INTFL_NL80211_FRAME_TX = BIT(21), }; /** -- cgit v1.1 From 02291680ffba92e5b5865bc0c5e7d1f3056b80ec Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 14 Feb 2010 03:25:51 +0000 Subject: net ipv4: Decouple ipv4 interface parameters from binary sysctl numbers Stop using the binary sysctl enumeartion in sysctl.h as an index into a per interface array. This leads to unnecessary binary sysctl number allocation, and a fragility in data structure and implementation because of unnecessary coupling. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 42 ++++++++++++++++++++++++++++++++++++------ include/linux/sysctl.h | 4 ---- 2 files changed, 36 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index cf25780..2be1a1a 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -10,10 +10,40 @@ #include #include +enum +{ + IPV4_DEVCONF_FORWARDING=1, + IPV4_DEVCONF_MC_FORWARDING, + IPV4_DEVCONF_PROXY_ARP, + IPV4_DEVCONF_ACCEPT_REDIRECTS, + IPV4_DEVCONF_SECURE_REDIRECTS, + IPV4_DEVCONF_SEND_REDIRECTS, + IPV4_DEVCONF_SHARED_MEDIA, + IPV4_DEVCONF_RP_FILTER, + IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE, + IPV4_DEVCONF_BOOTP_RELAY, + IPV4_DEVCONF_LOG_MARTIANS, + IPV4_DEVCONF_TAG, + IPV4_DEVCONF_ARPFILTER, + IPV4_DEVCONF_MEDIUM_ID, + IPV4_DEVCONF_NOXFRM, + IPV4_DEVCONF_NOPOLICY, + IPV4_DEVCONF_FORCE_IGMP_VERSION, + IPV4_DEVCONF_ARP_ANNOUNCE, + IPV4_DEVCONF_ARP_IGNORE, + IPV4_DEVCONF_PROMOTE_SECONDARIES, + IPV4_DEVCONF_ARP_ACCEPT, + IPV4_DEVCONF_ARP_NOTIFY, + IPV4_DEVCONF_ACCEPT_LOCAL, + IPV4_DEVCONF_SRC_VMARK, + IPV4_DEVCONF_PROXY_ARP_PVLAN, + __IPV4_DEVCONF_MAX +}; + struct ipv4_devconf { void *sysctl; - int data[__NET_IPV4_CONF_MAX - 1]; - DECLARE_BITMAP(state, __NET_IPV4_CONF_MAX - 1); + int data[__IPV4_DEVCONF_MAX - 1]; + DECLARE_BITMAP(state, __IPV4_DEVCONF_MAX - 1); }; struct in_device { @@ -40,7 +70,7 @@ struct in_device { struct rcu_head rcu_head; }; -#define IPV4_DEVCONF(cnf, attr) ((cnf).data[NET_IPV4_CONF_ ## attr - 1]) +#define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) @@ -60,13 +90,13 @@ static inline void ipv4_devconf_set(struct in_device *in_dev, int index, static inline void ipv4_devconf_setall(struct in_device *in_dev) { - bitmap_fill(in_dev->cnf.state, __NET_IPV4_CONF_MAX - 1); + bitmap_fill(in_dev->cnf.state, __IPV4_DEVCONF_MAX - 1); } #define IN_DEV_CONF_GET(in_dev, attr) \ - ipv4_devconf_get((in_dev), NET_IPV4_CONF_ ## attr) + ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ - ipv4_devconf_set((in_dev), NET_IPV4_CONF_ ## attr, (val)) + ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 9f236cd..7c74e91 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -481,10 +481,6 @@ enum NET_IPV4_CONF_PROMOTE_SECONDARIES=20, NET_IPV4_CONF_ARP_ACCEPT=21, NET_IPV4_CONF_ARP_NOTIFY=22, - NET_IPV4_CONF_ACCEPT_LOCAL=23, - NET_IPV4_CONF_SRC_VMARK=24, - NET_IPV4_CONF_PROXY_ARP_PVLAN=25, - __NET_IPV4_CONF_MAX }; /* /proc/sys/net/ipv4/netfilter */ -- cgit v1.1 From 54716e3beb0ab20c49471348dfe399a71bfc8fd3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 14 Feb 2010 03:27:03 +0000 Subject: net neigh: Decouple per interface neighbour table controls from binary sysctls Stop computing the number of neighbour table settings we have by counting the number of binary sysctls. This behaviour was silly and meant that we could not add another neighbour table setting without also adding another binary sysctl. Don't pass the binary sysctl path for neighour table entries into neigh_sysctl_register. These parameters are no longer used and so are just dead code. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/linux/sysctl.h | 1 - include/net/neighbour.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 7c74e91..f66014c 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -596,7 +596,6 @@ enum { NET_NEIGH_GC_THRESH3=16, NET_NEIGH_RETRANS_TIME_MS=17, NET_NEIGH_REACHABLE_TIME_MS=18, - __NET_NEIGH_MAX }; /* /proc/sys/net/dccp */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index b017320..7834f47 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -251,7 +251,6 @@ extern void neigh_seq_stop(struct seq_file *, void *); extern int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - int p_id, int pdev_id, char *p_name, proc_handler *proc_handler); extern void neigh_sysctl_unregister(struct neigh_parms *p); -- cgit v1.1 From 522530311b35ec8fc4785062441dd2d63967ac55 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 8 Feb 2010 10:12:10 +0000 Subject: CAPI: Call a controller 'controller', not 'card' At least for our internal use, fix the misnomers that refer to a CAPI controller as 'card'. No functional changes. Signed-off-by: Jan Kiszka Signed-off-by: David S. Miller --- include/linux/isdn/capilli.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/isdn/capilli.h b/include/linux/isdn/capilli.h index d3e5e9d..856f38e 100644 --- a/include/linux/isdn/capilli.h +++ b/include/linux/isdn/capilli.h @@ -66,7 +66,7 @@ struct capi_ctr { unsigned long nsentdatapkt; int cnr; /* controller number */ - volatile unsigned short cardstate; /* controller state */ + volatile unsigned short state; /* controller state */ volatile int blocked; /* output blocked */ int traceflag; /* capi trace */ -- cgit v1.1 From ef69bb2ec6036945da1d3d3f07b75253f484f693 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 8 Feb 2010 10:12:13 +0000 Subject: CAPI: Rework controller state notifier Another step towards proper locking: Rework the callback provided to capidrv for controller state changes. This is so far attached to an application, which would require us to hold the corresponding lock across notification calls. But there is no direct relation between a controller up/down event and an application, so let's decouple them and provide a notifier call chain for those events instead. This notifier chain is first of all used internally. Here we request the highest priority to unsure that housekeeping work is done before any other notifications. The chain is exported via [un]register_capictr_notifier to our only user, capidrv, to replace the racy and unfixable capi20_set_callback. Signed-off-by: Jan Kiszka Signed-off-by: David S. Miller --- include/linux/kernelcapi.h | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/kernelcapi.h b/include/linux/kernelcapi.h index a53e932..9c26839 100644 --- a/include/linux/kernelcapi.h +++ b/include/linux/kernelcapi.h @@ -48,9 +48,7 @@ typedef struct kcapi_carddef { #include #include #include - -#define KCI_CONTRUP 0 /* arg: struct capi_profile */ -#define KCI_CONTRDOWN 1 /* arg: NULL */ +#include struct capi20_appl { u16 applid; @@ -67,11 +65,6 @@ struct capi20_appl { struct sk_buff_head recv_queue; struct work_struct recv_work; int release_in_progress; - - /* ugly hack to allow for notification of added/removed - * controllers. The Right Way (tm) is known. XXX - */ - void (*callback) (unsigned int cmd, __u32 contr, void *data); }; u16 capi20_isinstalled(void); @@ -84,11 +77,11 @@ u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN]); u16 capi20_get_profile(u32 contr, struct capi_profile *profp); int capi20_manufacturer(unsigned int cmd, void __user *data); -/* temporary hack XXX */ -void capi20_set_callback(struct capi20_appl *ap, - void (*callback) (unsigned int cmd, __u32 contr, void *data)); - +#define CAPICTR_UP 0 +#define CAPICTR_DOWN 1 +int register_capictr_notifier(struct notifier_block *nb); +int unregister_capictr_notifier(struct notifier_block *nb); #define CAPI_NOERROR 0x0000 -- cgit v1.1 From 0ca3a017a7373a4545dd7b345a8a0cecc16bc7e2 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 8 Feb 2010 10:12:14 +0000 Subject: CAPI: Rework locking of controller data structures This patch applies the mutex so far only protecting the controller list to (almost) all accesses of controller data structures. It also reworks waiting on state changes in old_capi_manufacturer so that it no longer poll and holds a module reference to the controller owner while waiting (the latter was partly done already). Modification and checking of the blocked state remains racy by design, the caller is responsible for dealing with this. Signed-off-by: Jan Kiszka Signed-off-by: David S. Miller --- include/linux/isdn/capilli.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/isdn/capilli.h b/include/linux/isdn/capilli.h index 856f38e..11b57c4 100644 --- a/include/linux/isdn/capilli.h +++ b/include/linux/isdn/capilli.h @@ -66,9 +66,10 @@ struct capi_ctr { unsigned long nsentdatapkt; int cnr; /* controller number */ - volatile unsigned short state; /* controller state */ - volatile int blocked; /* output blocked */ + unsigned short state; /* controller state */ + int blocked; /* output blocked */ int traceflag; /* capi trace */ + wait_queue_head_t state_wait_queue; struct proc_dir_entry *procent; char procfn[128]; -- cgit v1.1 From 7d720c3e4f0c4fc152a6bf17e24244a3c85412d2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 16 Feb 2010 15:20:26 +0000 Subject: percpu: add __percpu sparse annotations to net Add __percpu sparse annotations to net. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. The macro and type tricks around snmp stats make things a bit interesting. DEFINE/DECLARE_SNMP_STAT() macros mark the target field as __percpu and SNMP_UPD_PO_STATS() macro is updated accordingly. All snmp_mib_*() users which used to cast the argument to (void **) are updated to cast it to (void __percpu **). Signed-off-by: Tejun Heo Acked-by: David S. Miller Cc: Patrick McHardy Cc: Arnaldo Carvalho de Melo Cc: Vlad Yasevich Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/net/ip.h | 6 +++--- include/net/ipcomp.h | 2 +- include/net/neighbour.h | 2 +- include/net/netns/conntrack.h | 2 +- include/net/netns/core.h | 2 +- include/net/route.h | 2 +- include/net/snmp.h | 12 ++++++++---- include/net/tcp.h | 2 +- 8 files changed, 17 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 7bc4787..503994a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -174,9 +174,9 @@ extern struct ipv4_config ipv4_config; #define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd) #define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd) -extern unsigned long snmp_fold_field(void *mib[], int offt); -extern int snmp_mib_init(void *ptr[2], size_t mibsize); -extern void snmp_mib_free(void *ptr[2]); +extern unsigned long snmp_fold_field(void __percpu *mib[], int offt); +extern int snmp_mib_init(void __percpu *ptr[2], size_t mibsize); +extern void snmp_mib_free(void __percpu *ptr[2]); extern struct local_ports { seqlock_t lock; diff --git a/include/net/ipcomp.h b/include/net/ipcomp.h index 2a1092a..cc4f30c 100644 --- a/include/net/ipcomp.h +++ b/include/net/ipcomp.h @@ -9,7 +9,7 @@ struct crypto_comp; struct ipcomp_data { u16 threshold; - struct crypto_comp **tfms; + struct crypto_comp * __percpu *tfms; }; struct ip_comp_hdr; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 7834f47..da1d58b 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -164,7 +164,7 @@ struct neigh_table { rwlock_t lock; unsigned long last_rand; struct kmem_cache *kmem_cachep; - struct neigh_statistics *stats; + struct neigh_statistics __percpu *stats; struct neighbour **hash_buckets; unsigned int hash_mask; __u32 hash_rnd; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 63d4498..d4958d4 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -17,7 +17,7 @@ struct netns_ct { struct hlist_head *expect_hash; struct hlist_nulls_head unconfirmed; struct hlist_nulls_head dying; - struct ip_conntrack_stat *stat; + struct ip_conntrack_stat __percpu *stat; int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 24d4be7..78eb1ff 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -10,7 +10,7 @@ struct netns_core { int sysctl_somaxconn; - struct prot_inuse *inuse; + struct prot_inuse __percpu *inuse; }; #endif diff --git a/include/net/route.h b/include/net/route.h index bce6dd6..2c9fba7 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -101,7 +101,7 @@ struct rt_cache_stat { unsigned int out_hlist_search; }; -extern struct ip_rt_acct *ip_rt_acct; +extern struct ip_rt_acct __percpu *ip_rt_acct; struct in_device; extern int ip_rt_init(void); diff --git a/include/net/snmp.h b/include/net/snmp.h index da02ee0..692ee00 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -129,9 +129,9 @@ struct linux_xfrm_mib { * nonlocked_atomic_inc() primitives -AK */ #define DEFINE_SNMP_STAT(type, name) \ - __typeof__(type) *name[2] + __typeof__(type) __percpu *name[2] #define DECLARE_SNMP_STAT(type, name) \ - extern __typeof__(type) *name[2] + extern __typeof__(type) __percpu *name[2] #define SNMP_STAT_BHPTR(name) (name[0]) #define SNMP_STAT_USRPTR(name) (name[1]) @@ -148,9 +148,13 @@ struct linux_xfrm_mib { __this_cpu_add(mib[0]->mibs[field], addend) #define SNMP_ADD_STATS_USER(mib, field, addend) \ this_cpu_add(mib[1]->mibs[field], addend) +/* + * Use "__typeof__(*mib[0]) *ptr" instead of "__typeof__(mib[0]) ptr" + * to make @ptr a non-percpu pointer. + */ #define SNMP_UPD_PO_STATS(mib, basefield, addend) \ do { \ - __typeof__(mib[0]) ptr; \ + __typeof__(*mib[0]) *ptr; \ preempt_disable(); \ ptr = this_cpu_ptr((mib)[!in_softirq()]); \ ptr->mibs[basefield##PKTS]++; \ @@ -159,7 +163,7 @@ struct linux_xfrm_mib { } while (0) #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend) \ do { \ - __typeof__(mib[0]) ptr = \ + __typeof__(*mib[0]) *ptr = \ __this_cpu_ptr((mib)[!in_softirq()]); \ ptr->mibs[basefield##PKTS]++; \ ptr->mibs[basefield##OCTETS] += addend;\ diff --git a/include/net/tcp.h b/include/net/tcp.h index 87d164b..75a00c8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1189,7 +1189,7 @@ extern int tcp_v4_md5_do_del(struct sock *sk, #define tcp_twsk_md5_key(twsk) NULL #endif -extern struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(struct sock *); +extern struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *); extern void tcp_free_md5sig_pool(void); extern struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu); -- cgit v1.1 From 47d742752df4c1088589d4424840bc761613ab2a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 16 Feb 2010 15:21:08 +0000 Subject: percpu: add __percpu sparse annotations to net drivers Add __percpu sparse annotations to net drivers. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. Signed-off-by: Tejun Heo Acked-by: David S. Miller Cc: Eric Dumazet Cc: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 51f1512..f9cb9ba 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -30,7 +30,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; - struct macvlan_rx_stats *rx_stats; + struct macvlan_rx_stats __percpu *rx_stats; enum macvlan_mode mode; int (*receive)(struct sk_buff *skb); int (*forward)(struct net_device *dev, struct sk_buff *skb); -- cgit v1.1 From 9874c41cd5e70bfc97bcd52a8b6c98c2a6ba7299 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 16 Feb 2010 18:40:04 +0000 Subject: ipv6.h: reassembly: replace calculated magic number with multiplication On Tue, 2010-02-16 at 16:47 +0100, Patrick McHardy wrote: > Joe Perches wrote: > >> @@ -246,6 +246,8 @@ extern int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb); > >> int ip6_frag_nqueues(struct net *net); > >> int ip6_frag_mem(struct net *net); > >> > >> +#define IPV6_FRAG_HIGH_THRESH 262144 /* == 256*1024 */ > >> +#define IPV6_FRAG_LOW_THRESH 196608 /* == 192*1024 */ > >> #define IPV6_FRAG_TIMEOUT (60*HZ) /* 60 seconds */ > > > > 196608 isn't a number I want to remember. > > Is this better as: > > > > #define IPV6_FRAG_HIGH_THRESH (256 * 1024) /* 262144 */ > > #define IPV6_FRAG_LOW_THRESH (192 * 1024) /* 196608 */ > > Please send a patch, I'll apply it once these patches are in Dave's > tree. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/net/ipv6.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 639ec53..d067db1 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -246,9 +246,9 @@ extern int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb); int ip6_frag_nqueues(struct net *net); int ip6_frag_mem(struct net *net); -#define IPV6_FRAG_HIGH_THRESH 262144 /* == 256*1024 */ -#define IPV6_FRAG_LOW_THRESH 196608 /* == 192*1024 */ -#define IPV6_FRAG_TIMEOUT (60*HZ) /* 60 seconds */ +#define IPV6_FRAG_HIGH_THRESH (256 * 1024) /* 262144 */ +#define IPV6_FRAG_LOW_THRESH (192 * 1024) /* 196608 */ +#define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */ extern int __ipv6_addr_type(const struct in6_addr *addr); static inline int ipv6_addr_type(const struct in6_addr *addr) -- cgit v1.1 From 60b86755929e1a7e9038c8d860a8491cfdf8d93a Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 17 Feb 2010 10:30:23 +0000 Subject: usbnet: Convert dev(dbg|err|warn|info) macros to netdev_ These macros are too similar to the dev_ equivalents but take a usbnet * argument. Convert them to the recently introduced netdev_ macros and remove the old macros. The old macros had "\n" appended to the format string. Add the "\n" to the converted uses. Some existing uses of the dev macros in cdc_eem.c probably mistakenly had trailing "\n". No "\n" added there. Fix net1080 this/other log message inversion. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 8ce6135..df1e83d 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -214,25 +214,4 @@ extern void usbnet_set_msglevel (struct net_device *, u32); extern void usbnet_get_drvinfo (struct net_device *, struct ethtool_drvinfo *); extern int usbnet_nway_reset(struct net_device *net); -/* messaging support includes the interface name, so it must not be - * used before it has one ... notably, in minidriver bind() calls. - */ -#ifdef DEBUG -#define devdbg(usbnet, fmt, arg...) \ - printk(KERN_DEBUG "%s: " fmt "\n" , (usbnet)->net->name , ## arg) -#else -#define devdbg(usbnet, fmt, arg...) \ - ({ if (0) printk(KERN_DEBUG "%s: " fmt "\n" , (usbnet)->net->name , \ - ## arg); 0; }) -#endif - -#define deverr(usbnet, fmt, arg...) \ - printk(KERN_ERR "%s: " fmt "\n" , (usbnet)->net->name , ## arg) -#define devwarn(usbnet, fmt, arg...) \ - printk(KERN_WARNING "%s: " fmt "\n" , (usbnet)->net->name , ## arg) - -#define devinfo(usbnet, fmt, arg...) \ - printk(KERN_INFO "%s: " fmt "\n" , (usbnet)->net->name , ## arg); \ - - #endif /* __LINUX_USB_USBNET_H */ -- cgit v1.1 From 99405162598176e830d17ae6d4f3d9e070ad900c Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 14 Feb 2010 01:01:10 +0000 Subject: tun: socket filter support This patch adds Linux Socket Filter support to tun driver. Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/if_tun.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 404abe0..1350a24 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -18,6 +18,7 @@ #include #include +#include /* Read queue size */ #define TUN_READQ_SIZE 500 @@ -48,6 +49,8 @@ #define TUNGETIFF _IOR('T', 210, unsigned int) #define TUNGETSNDBUF _IOR('T', 211, int) #define TUNSETSNDBUF _IOW('T', 212, int) +#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog) +#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 -- cgit v1.1 From 6a443a0f72ad7706345412dbd2e4d4981fdfce39 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Wed, 17 Feb 2010 15:17:04 +0000 Subject: tg3: Push phylib definitions to phylib This patch pushes phylib definitions out to phylib headers. For phy IDs, this removes some code duplication. Signed-off-by: Matt Carlson Reviewed-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 2b31b91..7f437ca 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -1,3 +1,14 @@ +#define PHY_ID_BCM50610 0x0143bd60 +#define PHY_ID_BCM50610M 0x0143bd70 +#define PHY_ID_BCMAC131 0x0143bc70 +#define PHY_ID_BCM57780 0x03625d90 + +#define PHY_BCM_OUI_MASK 0xfffffc00 +#define PHY_BCM_OUI_1 0x00206000 +#define PHY_BCM_OUI_2 0x0143bc00 +#define PHY_BCM_OUI_3 0x03625c00 + + #define PHY_BCM_FLAGS_MODE_COPPER 0x00000001 #define PHY_BCM_FLAGS_MODE_1000BX 0x00000002 #define PHY_BCM_FLAGS_INTF_SGMII 0x00000010 -- cgit v1.1 From 6457d26bd40077238799e31df2b800bcf4ef9177 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 17 Feb 2010 18:48:44 -0800 Subject: IPv6: convert mc_lock to spinlock Only used for writing, so convert to spinlock Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/if_inet6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index e9d69d1..545d8b0 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -157,7 +157,7 @@ struct inet6_dev { struct ifmcaddr6 *mc_list; struct ifmcaddr6 *mc_tomb; - rwlock_t mc_lock; + spinlock_t mc_lock; unsigned char mc_qrv; unsigned char mc_gq_running; unsigned char mc_ifc_count; -- cgit v1.1 From 2906f66a5682e5670a5eefe991843689b8d8563f Mon Sep 17 00:00:00 2001 From: Venkata Mohan Reddy Date: Thu, 18 Feb 2010 12:31:05 +0100 Subject: ipvs: SCTP Trasport Loadbalancing Support Enhance IPVS to load balance SCTP transport protocol packets. This is done based on the SCTP rfc 4960. All possible control chunks have been taken care. The state machine used in this code looks some what lengthy. I tried to make the state machine easy to understand. Signed-off-by: Venkata Mohan Reddy Koppula Signed-off-by: Simon Horman Signed-off-by: Patrick McHardy --- include/net/ip_vs.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a816c37..fe82b1e1 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -225,6 +225,26 @@ enum { }; /* + * SCTP State Values + */ +enum ip_vs_sctp_states { + IP_VS_SCTP_S_NONE, + IP_VS_SCTP_S_INIT_CLI, + IP_VS_SCTP_S_INIT_SER, + IP_VS_SCTP_S_INIT_ACK_CLI, + IP_VS_SCTP_S_INIT_ACK_SER, + IP_VS_SCTP_S_ECHO_CLI, + IP_VS_SCTP_S_ECHO_SER, + IP_VS_SCTP_S_ESTABLISHED, + IP_VS_SCTP_S_SHUT_CLI, + IP_VS_SCTP_S_SHUT_SER, + IP_VS_SCTP_S_SHUT_ACK_CLI, + IP_VS_SCTP_S_SHUT_ACK_SER, + IP_VS_SCTP_S_CLOSED, + IP_VS_SCTP_S_LAST +}; + +/* * Delta sequence info structure * Each ip_vs_conn has 2 (output AND input seq. changes). * Only used in the VS/NAT. @@ -741,7 +761,7 @@ extern struct ip_vs_protocol ip_vs_protocol_udp; extern struct ip_vs_protocol ip_vs_protocol_icmp; extern struct ip_vs_protocol ip_vs_protocol_esp; extern struct ip_vs_protocol ip_vs_protocol_ah; - +extern struct ip_vs_protocol ip_vs_protocol_sctp; /* * Registering/unregistering scheduler functions -- cgit v1.1 From 37ee3d5b3e979a168536e7e2f15bd1e769cb4122 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 18 Feb 2010 19:04:44 +0100 Subject: netfilter: nf_defrag_ipv4: fix compilation error with NF_CONNTRACK=n As reported by Randy Dunlap , compilation of nf_defrag_ipv4 fails with: include/net/netfilter/nf_conntrack.h:94: error: field 'ct_general' has incomplete type include/net/netfilter/nf_conntrack.h:178: error: 'const struct sk_buff' has no member named 'nfct' include/net/netfilter/nf_conntrack.h:185: error: implicit declaration of function 'nf_conntrack_put' include/net/netfilter/nf_conntrack.h:294: error: 'const struct sk_buff' has no member named 'nfct' net/ipv4/netfilter/nf_defrag_ipv4.c:45: error: 'struct sk_buff' has no member named 'nfct' net/ipv4/netfilter/nf_defrag_ipv4.c:46: error: 'struct sk_buff' has no member named 'nfct' net/nf_conntrack.h must not be included with NF_CONNTRACK=n, add a few #ifdefs. Long term the header file should be fixed to be usable even with NF_CONNTRACK=n. Tested-by: Randy Dunlap Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack_zones.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h index 0bbb2bd..034efe8 100644 --- a/include/net/netfilter/nf_conntrack_zones.h +++ b/include/net/netfilter/nf_conntrack_zones.h @@ -1,10 +1,11 @@ #ifndef _NF_CONNTRACK_ZONES_H #define _NF_CONNTRACK_ZONES_H -#include - #define NF_CT_DEFAULT_ZONE 0 +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#include + struct nf_conntrack_zone { u16 id; }; @@ -20,4 +21,5 @@ static inline u16 nf_ct_zone(const struct nf_conn *ct) return NF_CT_DEFAULT_ZONE; } +#endif /* CONFIG_NF_CONNTRACK || CONFIG_NF_CONNTRACK_MODULE */ #endif /* _NF_CONNTRACK_ZONES_H */ -- cgit v1.1 From 501c774cb13c3ef8fb7fc5f08fa19473f7d9a0db Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Feb 2010 05:46:50 +0000 Subject: net/macvtap: add vhost support This adds support for passing a macvtap file descriptor into vhost-net, much like we already do for tun/tap. Most of the new code is taken from the respective patch in the tun driver and may get consolidated in the future. Signed-off-by: Arnd Bergmann Acked-by: Sridhar Samudrala Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index f9cb9ba..b78a712 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -7,6 +7,19 @@ #include #include +#if defined(CONFIG_MACVTAP) || defined(CONFIG_MACVTAP_MODULE) +struct socket *macvtap_get_socket(struct file *); +#else +#include +#include +struct file; +struct socket; +static inline struct socket *macvtap_get_socket(struct file *f) +{ + return ERR_PTR(-EINVAL); +} +#endif /* CONFIG_MACVTAP */ + struct macvlan_port; struct macvtap_queue; -- cgit v1.1 From bbef49daca35d4fd21bf606a10b6980f17d9df5d Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Feb 2010 08:13:30 +0000 Subject: ipv6: use standard lists for FIB walks Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 8f279dd..86f46c4 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -124,7 +124,7 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) } struct fib6_walker_t { - struct fib6_walker_t *prev, *next; + struct list_head lh; struct fib6_node *root, *node; struct rt6_info *leaf; unsigned char state; -- cgit v1.1 From 3ffe533c87281b68d469b279ff3a5056f9c75862 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Feb 2010 08:25:24 +0000 Subject: ipv6: drop unused "dev" arg of icmpv6_send() Dunno, what was the idea, it wasn't used for a long time. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index c0d8357..4c4c74e 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -174,8 +174,7 @@ struct icmp6_filter { extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, - __u32 info, - struct net_device *dev); + __u32 info); extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, -- cgit v1.1 From b54452b07a7b1b8cc1385edba3ef2ef6d4679d5a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 18 Feb 2010 08:14:31 +0000 Subject: const: struct nla_policy Make remaining netlink policies as const. Fixup coding style where needed. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index a63b219..f82e463 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -196,7 +196,7 @@ enum { * All other Exact length of attribute payload * * Example: - * static struct nla_policy my_policy[ATTR_MAX+1] __read_mostly = { + * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = { .len = sizeof(struct mystruct) }, -- cgit v1.1 From 5aa4b32fc86408705337e941ed716880c63d1590 Mon Sep 17 00:00:00 2001 From: Andreas Petlund Date: Thu, 18 Feb 2010 02:45:45 +0000 Subject: net: TCP thin-stream detection Inline function to dynamically detect thin streams based on the number of packets in flight. Used to dynamically trigger thin-stream mechanisms if enabled by ioctl or sysctl. Signed-off-by: Andreas Petlund Signed-off-by: David S. Miller --- include/net/tcp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 75a00c8..0bdc3f6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1386,6 +1386,14 @@ static inline void tcp_highest_sack_combine(struct sock *sk, tcp_sk(sk)->highest_sack = new; } +/* Determines whether this is a thin stream (which may suffer from + * increased latency). Used to trigger latency-reducing mechanisms. + */ +static inline unsigned int tcp_stream_is_thin(struct tcp_sock *tp) +{ + return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp); +} + /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, -- cgit v1.1 From 36e31b0af58728071e8023cf8e20c5166b700717 Mon Sep 17 00:00:00 2001 From: Andreas Petlund Date: Thu, 18 Feb 2010 02:47:01 +0000 Subject: net: TCP thin linear timeouts This patch will make TCP use only linear timeouts if the stream is thin. This will help to avoid the very high latencies that thin stream suffer because of exponential backoff. This mechanism is only active if enabled by iocontrol or syscontrol and the stream is identified as thin. A maximum of 6 linear timeouts is tried before exponential backoff is resumed. Signed-off-by: Andreas Petlund Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 ++++- include/net/tcp.h | 4 ++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 7fee8a4..3ba8b07 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -103,6 +103,7 @@ enum { #define TCP_CONGESTION 13 /* Congestion control algorithm */ #define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ #define TCP_COOKIE_TRANSACTIONS 15 /* TCP Cookie Transactions */ +#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ /* for TCP_INFO socket option */ #define TCPI_OPT_TIMESTAMPS 1 @@ -340,7 +341,9 @@ struct tcp_sock { u32 frto_highmark; /* snd_nxt when RTO occurred */ u16 advmss; /* Advertised MSS */ u8 frto_counter; /* Number of new acks after RTO */ - u8 nonagle; /* Disable Nagle algorithm? */ + u8 nonagle : 4,/* Disable Nagle algorithm? */ + thin_lto : 1,/* Use linear timeouts for thin streams */ + unused : 3; /* RTT measurement */ u32 srtt; /* smoothed round trip time << 3 */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 0bdc3f6..6278fc7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */ +/* TCP thin-stream limits */ +#define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ @@ -241,6 +244,7 @@ extern int sysctl_tcp_workaround_signed_windows; extern int sysctl_tcp_slow_start_after_idle; extern int sysctl_tcp_max_ssthresh; extern int sysctl_tcp_cookie_size; +extern int sysctl_tcp_thin_linear_timeouts; extern atomic_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; -- cgit v1.1 From 7e38017557bc0b87434d184f8804cadb102bb903 Mon Sep 17 00:00:00 2001 From: Andreas Petlund Date: Thu, 18 Feb 2010 04:48:19 +0000 Subject: net: TCP thin dupack This patch enables fast retransmissions after one dupACK for TCP if the stream is identified as thin. This will reduce latencies for thin streams that are not able to trigger fast retransmissions due to high packet interarrival time. This mechanism is only active if enabled by iocontrol or syscontrol and the stream is identified as thin. Signed-off-by: Andreas Petlund Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 +++- include/net/tcp.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3ba8b07..a778ee0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -104,6 +104,7 @@ enum { #define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ #define TCP_COOKIE_TRANSACTIONS 15 /* TCP Cookie Transactions */ #define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ +#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ /* for TCP_INFO socket option */ #define TCPI_OPT_TIMESTAMPS 1 @@ -343,7 +344,8 @@ struct tcp_sock { u8 frto_counter; /* Number of new acks after RTO */ u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ - unused : 3; + thin_dupack : 1,/* Fast retransmit on first dupack */ + unused : 2; /* RTT measurement */ u32 srtt; /* smoothed round trip time << 3 */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 6278fc7..56f0aec 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -245,6 +245,7 @@ extern int sysctl_tcp_slow_start_after_idle; extern int sysctl_tcp_max_ssthresh; extern int sysctl_tcp_cookie_size; extern int sysctl_tcp_thin_linear_timeouts; +extern int sysctl_tcp_thin_dupack; extern atomic_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; -- cgit v1.1 From 72032fdbcde8b333e65b3430e1bcb4358e2d6716 Mon Sep 17 00:00:00 2001 From: jamal Date: Thu, 18 Feb 2010 03:35:07 +0000 Subject: xfrm: Introduce LINUX_MIB_XFRMFWDHDRERROR XFRMINHDRERROR counter is ambigous when validating forwarding path. It makes it tricky to debug when you have both in and fwd validation. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/snmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 0f953fe..e28f5a0 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -257,6 +257,7 @@ enum LINUX_MIB_XFRMOUTPOLBLOCK, /* XfrmOutPolBlock */ LINUX_MIB_XFRMOUTPOLDEAD, /* XfrmOutPolDead */ LINUX_MIB_XFRMOUTPOLERROR, /* XfrmOutPolError */ + LINUX_MIB_XFRMFWDHDRERROR, /* XfrmFwdHdrError*/ __LINUX_MIB_XFRMMAX }; -- cgit v1.1 From 4bac6b180771f7ef5275b1a6d88e630ca3a3d6f0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Feb 2010 08:03:28 +0100 Subject: netfilter: restore POST_ROUTING hook in NF_HOOK_COND Commit 2249065 ("netfilter: get rid of the grossness in netfilter.h") inverted the logic for conditional hook invocation, breaking the POST_ROUTING hook invoked by ip_output(). Correct the logic and remove an unnecessary initialization. Reported-by: Stephen Hemminger Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 7007945..89341c3 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -212,8 +212,9 @@ NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct sk_buff *), bool cond) { - int ret = 1; - if (cond || + int ret; + + if (!cond || (ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, INT_MIN) == 1)) ret = okfn(skb); return ret; -- cgit v1.1 From fbc87d67af5ccd733f894273b215564c67e3a749 Mon Sep 17 00:00:00 2001 From: Pavel Roskin Date: Thu, 11 Feb 2010 17:56:06 -0500 Subject: Introduce PCMCIA_DEVICE_PROD_ID3 ...and use it in hostap_cs and orinoco_cs. Another PCMCIA device with Intersil Prism chipset has been reported: Socket 0: product info: "Gigabyte", "GN-WLM01_P25L_ADAPTER", "ISL37300P", "Eval-RevA" manfid: 0x02e0, 0x1011 function: 6 (network) As it's the case with some other Prism based devices, the third ID string contains a design name that should be sufficient to identify the card as having Intersil Prism chipset and thus compatible with both orinoco_cs and hostap_cs. Introduce PCMCIA_DEVICE_PROD_ID3 that matches the third ID string only. Use it in orinoco_cs and hostap_cs to match cards with the third ID string indicating Prism chipset. Remove corresponding entries that use PCMCIA_DEVICE_PROD_ID123. Reported-by: Ozzy Signed-off-by: Pavel Roskin Signed-off-by: John W. Linville --- include/pcmcia/device_id.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/pcmcia/device_id.h b/include/pcmcia/device_id.h index c33ea08..63e5b8f 100644 --- a/include/pcmcia/device_id.h +++ b/include/pcmcia/device_id.h @@ -34,6 +34,11 @@ .prod_id = { NULL, (v2), NULL, NULL }, \ .prod_id_hash = { 0, (vh2), 0, 0 }, } +#define PCMCIA_DEVICE_PROD_ID3(v3, vh3) { \ + .match_flags = PCMCIA_DEV_ID_MATCH_PROD_ID3, \ + .prod_id = { NULL, NULL, (v3), NULL }, \ + .prod_id_hash = { 0, 0, (vh3), 0 }, } + #define PCMCIA_DEVICE_PROD_ID12(v1, v2, vh1, vh2) { \ .match_flags = PCMCIA_DEV_ID_MATCH_PROD_ID1| \ PCMCIA_DEV_ID_MATCH_PROD_ID2, \ -- cgit v1.1 From ffb9eb3d8b450c22bbbc688c6b630141ac476fd9 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Wed, 17 Feb 2010 17:58:10 +0200 Subject: nl80211: add power save commands The most needed command from nl80211, which Wireless Extensions had, is support for power save mode. Add a simple command to make it possible to enable and disable power save via nl80211. I was also planning about extending the interface, for example adding the timeout value, but after thinking more about this I decided not to do it. Basically there were three reasons: Firstly, the parameters for power save are very much hardware dependent. Trying to find a unified interface which would work with all hardware, and still make sense to users, will be very difficult. Secondly, IEEE 802.11 power save implementation in Linux is still in state of flux. We have a long way to still to go and there is no way to predict what kind of implementation we will have after few years. And because we need to support nl80211 interface a long time, practically forever, adding now parameters to nl80211 might create maintenance problems later on. Third issue are the users. Power save parameters are mostly used for debugging, so debugfs is better, more flexible, interface for this. For example, wpa_supplicant currently doesn't configure anything related to power save mode. It's better to strive that kernel can automatically optimise the power save parameters, like with help of pm qos network and other traffic parameters. Later on, when we have better understanding of power save, we can extend this command with more features, if there's a need for that. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/linux/nl80211.h | 10 ++++++++++ include/net/cfg80211.h | 7 ++++--- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 8e6384f..28ba20f 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -416,6 +416,9 @@ enum nl80211_commands { NL80211_CMD_ACTION, NL80211_CMD_ACTION_TX_STATUS, + NL80211_CMD_SET_POWER_SAVE, + NL80211_CMD_GET_POWER_SAVE, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -837,6 +840,8 @@ enum nl80211_attrs { NL80211_ATTR_ACK, + NL80211_ATTR_PS_STATE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1573,4 +1578,9 @@ enum nl80211_band { NL80211_BAND_5GHZ, }; +enum nl80211_ps_state { + NL80211_PS_DISABLED, + NL80211_PS_ENABLED, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7188934..3d134a1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1150,7 +1150,6 @@ struct cfg80211_ops { enum nl80211_channel_type channel_type, const u8 *buf, size_t len, u64 *cookie); - /* some temporary stuff to finish wext */ int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); }; @@ -1489,6 +1488,9 @@ struct wireless_dev { struct cfg80211_internal_bss *auth_bsses[MAX_AUTH_BSSES]; struct cfg80211_internal_bss *current_bss; /* associated / joined */ + bool ps; + int ps_timeout; + #ifdef CONFIG_CFG80211_WEXT /* wext data */ struct { @@ -1500,8 +1502,7 @@ struct wireless_dev { u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; u8 ssid[IEEE80211_MAX_SSID_LEN]; s8 default_key, default_mgmt_key; - bool ps, prev_bssid_valid; - int ps_timeout; + bool prev_bssid_valid; } wext; #endif }; -- cgit v1.1 From 1cc523271ef0b6305c565a143e3d48f6fff826dd Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 22 Feb 2010 07:57:17 +0000 Subject: seq_file: add RCU versions of new hlist/list iterators (v3) Many usages of seq_file use RCU protected lists, so non RCU iterators will not work safely. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/rculist.h | 5 +++++ include/linux/seq_file.h | 15 +++++++++++---- 2 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 1bf0f70..701fe9c 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -406,6 +406,11 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, n->next->pprev = &n->next; } +#define __hlist_for_each_rcu(pos, head) \ + for (pos = rcu_dereference((head)->first); \ + pos && ({ prefetch(pos->next); 1; }); \ + pos = rcu_dereference(pos->next)) + /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index c95bcdc..03c0232 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -140,10 +140,17 @@ extern struct list_head *seq_list_next(void *v, struct list_head *head, */ extern struct hlist_node *seq_hlist_start(struct hlist_head *head, - loff_t pos); + loff_t pos); extern struct hlist_node *seq_hlist_start_head(struct hlist_head *head, - loff_t pos); + loff_t pos); extern struct hlist_node *seq_hlist_next(void *v, struct hlist_head *head, - loff_t *ppos); - + loff_t *ppos); + +extern struct hlist_node *seq_hlist_start_rcu(struct hlist_head *head, + loff_t pos); +extern struct hlist_node *seq_hlist_start_head_rcu(struct hlist_head *head, + loff_t pos); +extern struct hlist_node *seq_hlist_next_rcu(void *v, + struct hlist_head *head, + loff_t *ppos); #endif -- cgit v1.1 From 808f5114a9206fee855117d416440e1071ab375c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 22 Feb 2010 07:57:18 +0000 Subject: packet: convert socket list to RCU (v3) Convert AF_PACKET to use RCU, eliminating one more reader/writer lock. There is no need for a real sk_del_node_init_rcu(), because sk_del_node_init is doing the equivalent thing to hlst_del_init_rcu already; but added some comments to try and make that obvious. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/netns/packet.h | 4 ++-- include/net/sock.h | 10 ++++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netns/packet.h b/include/net/netns/packet.h index 637daf6..cb4e894 100644 --- a/include/net/netns/packet.h +++ b/include/net/netns/packet.h @@ -4,11 +4,11 @@ #ifndef __NETNS_PACKET_H__ #define __NETNS_PACKET_H__ -#include +#include #include struct netns_packet { - rwlock_t sklist_lock; + spinlock_t sklist_lock; struct hlist_head sklist; }; diff --git a/include/net/sock.h b/include/net/sock.h index 580d51fa..6cb1676 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -381,6 +381,7 @@ static __inline__ void __sk_del_node(struct sock *sk) __hlist_del(&sk->sk_node); } +/* NB: equivalent to hlist_del_init_rcu */ static __inline__ int __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { @@ -421,6 +422,7 @@ static __inline__ int sk_del_node_init(struct sock *sk) } return rc; } +#define sk_del_node_init_rcu(sk) sk_del_node_init(sk) static __inline__ int __sk_nulls_del_node_init_rcu(struct sock *sk) { @@ -454,6 +456,12 @@ static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list) __sk_add_node(sk, list); } +static __inline__ void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) +{ + sock_hold(sk); + hlist_add_head_rcu(&sk->sk_node, list); +} + static __inline__ void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); @@ -478,6 +486,8 @@ static __inline__ void sk_add_bind_node(struct sock *sk, #define sk_for_each(__sk, node, list) \ hlist_for_each_entry(__sk, node, list, sk_node) +#define sk_for_each_rcu(__sk, node, list) \ + hlist_for_each_entry_rcu(__sk, node, list, sk_node) #define sk_nulls_for_each(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define sk_nulls_for_each_rcu(__sk, node, list) \ -- cgit v1.1 From bf825f81b454fae2ffe1b675f3a549656726440e Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 22 Feb 2010 11:32:54 +0000 Subject: xfrm: introduce basic mark infrastructure Add basic structuring and accessors for xfrm mark Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/xfrm.h | 12 +++++++++--- include/net/xfrm.h | 22 ++++++++++++++++++++++ 2 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 29e04be..b971e38 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -267,8 +267,8 @@ enum xfrm_attr_type_t { XFRMA_ALG_COMP, /* struct xfrm_algo */ XFRMA_ENCAP, /* struct xfrm_algo + struct xfrm_encap_tmpl */ XFRMA_TMPL, /* 1 or more struct xfrm_user_tmpl */ - XFRMA_SA, - XFRMA_POLICY, + XFRMA_SA, /* struct xfrm_usersa_info */ + XFRMA_POLICY, /*struct xfrm_userpolicy_info */ XFRMA_SEC_CTX, /* struct xfrm_sec_ctx */ XFRMA_LTIME_VAL, XFRMA_REPLAY_VAL, @@ -276,17 +276,23 @@ enum xfrm_attr_type_t { XFRMA_ETIMER_THRESH, XFRMA_SRCADDR, /* xfrm_address_t */ XFRMA_COADDR, /* xfrm_address_t */ - XFRMA_LASTUSED, + XFRMA_LASTUSED, /* unsigned long */ XFRMA_POLICY_TYPE, /* struct xfrm_userpolicy_type */ XFRMA_MIGRATE, XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */ XFRMA_KMADDRESS, /* struct xfrm_user_kmaddress */ XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */ + XFRMA_MARK, /* struct xfrm_mark */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) }; +struct xfrm_mark { + __u32 v; /* value */ + __u32 m; /* mask */ +}; + enum xfrm_sadattr_type_t { XFRMA_SAD_UNSPEC, XFRMA_SAD_CNT, diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 0beb413..39f151c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -140,6 +140,7 @@ struct xfrm_state { struct xfrm_id id; struct xfrm_selector sel; + struct xfrm_mark mark; u32 genid; @@ -481,6 +482,7 @@ struct xfrm_policy { u32 priority; u32 index; + struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; struct xfrm_lifetime_cur curlft; @@ -1570,4 +1572,24 @@ static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) } #endif +static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) +{ + if (attrs[XFRMA_MARK]) + memcpy(m, nla_data(attrs[XFRMA_MARK]), sizeof(m)); + else + m->v = m->m = 0; + + return m->v & m->m; +} + +static inline int xfrm_mark_put(struct sk_buff *skb, struct xfrm_mark *m) +{ + if (m->m | m->v) + NLA_PUT(skb, XFRMA_MARK, sizeof(struct xfrm_mark), m); + return 0; + +nla_put_failure: + return -1; +} + #endif /* _NET_XFRM_H */ -- cgit v1.1 From bd55775c8dd656fc69b3a42a1c4ab32abb7e8af9 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 22 Feb 2010 16:20:22 -0800 Subject: xfrm: SA lookups signature with mark pass mark to all SA lookups to prepare them for when we add code to have them search. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/xfrm.h | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 39f151c..693523c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1319,7 +1319,7 @@ extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family); -extern struct xfrm_state * xfrm_stateonly_find(struct net *net, +extern struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, @@ -1328,8 +1328,14 @@ extern int xfrm_state_check_expire(struct xfrm_state *x); extern void xfrm_state_insert(struct xfrm_state *x); extern int xfrm_state_add(struct xfrm_state *x); extern int xfrm_state_update(struct xfrm_state *x); -extern struct xfrm_state *xfrm_state_lookup(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); -extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family); +extern struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, + xfrm_address_t *daddr, __be32 spi, + u8 proto, unsigned short family); +extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, + xfrm_address_t *daddr, + xfrm_address_t *saddr, + u8 proto, + unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY extern int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family); @@ -1366,7 +1372,8 @@ struct xfrmk_spdinfo { u32 spdhmcnt; }; -extern struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 seq); +extern struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, + u32 seq); extern int xfrm_state_delete(struct xfrm_state *x); extern int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info); extern void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); @@ -1451,9 +1458,11 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u8, int dir, u32 id, int d int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info); u32 xfrm_get_acqseq(void); extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); -struct xfrm_state * xfrm_find_acq(struct net *net, u8 mode, u32 reqid, u8 proto, - xfrm_address_t *daddr, xfrm_address_t *saddr, - int create, unsigned short family); +struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark, + u8 mode, u32 reqid, u8 proto, + xfrm_address_t *daddr, + xfrm_address_t *saddr, int create, + unsigned short family); extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); extern int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *xdst, struct flowi *fl, int family, int strict); -- cgit v1.1 From 8ca2e93b557f2a0b35f7769038abf600177e1122 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 22 Feb 2010 11:32:57 +0000 Subject: xfrm: SP lookups signature with mark pass mark to all SP lookups to prepare them for when we add code to have them search. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/xfrm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 693523c..a7df327 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1450,11 +1450,12 @@ extern int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *); extern void xfrm_policy_walk_done(struct xfrm_policy_walk *walk); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u8 type, int dir, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, + u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u8, int dir, u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info); u32 xfrm_get_acqseq(void); extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); -- cgit v1.1 From 72b2b1dd77e8feb0b7c0b26dee58f2a1e2c9828c Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 24 Feb 2010 18:32:59 +0100 Subject: netfilter: xtables: replace XT_ENTRY_ITERATE macro The macro is replaced by a list.h-like foreach loop. This makes the code much more inspectable. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 9 +++++++++ include/linux/netfilter_arp/arp_tables.h | 10 ++-------- include/linux/netfilter_ipv4/ip_tables.h | 11 ++--------- include/linux/netfilter_ipv6/ip6_tables.h | 10 ++-------- 4 files changed, 15 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index a18119f..9df3f5a 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -139,6 +139,7 @@ struct xt_counters_info { __ret; \ }) +#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define XT_ENTRY_ITERATE_CONTINUE(type, entries, size, n, fn, args...) \ ({ \ @@ -163,6 +164,14 @@ struct xt_counters_info { #define XT_ENTRY_ITERATE(type, entries, size, fn, args...) \ XT_ENTRY_ITERATE_CONTINUE(type, entries, size, 0, fn, args) +#endif /* !__KERNEL__ */ + +/* pos is normally a struct ipt_entry/ip6t_entry/etc. */ +#define xt_entry_foreach(pos, ehead, esize) \ + for ((pos) = (typeof(pos))(ehead); \ + (pos) < (typeof(pos))((char *)(ehead) + (esize)); \ + (pos) = (typeof(pos))((char *)(pos) + (pos)->next_offset)) + #ifdef __KERNEL__ #include diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 0b33980..e9948c0 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -211,9 +211,11 @@ static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e return (void *)e + e->target_offset; } +#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define ARPT_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct arpt_entry, entries, size, fn, ## args) +#endif /* * Main firewall chains definitions and global var's definitions. @@ -291,14 +293,6 @@ compat_arpt_get_target(struct compat_arpt_entry *e) #define COMPAT_ARPT_ALIGN(s) COMPAT_XT_ALIGN(s) -/* fn returns 0 to continue iteration */ -#define COMPAT_ARPT_ENTRY_ITERATE(entries, size, fn, args...) \ - XT_ENTRY_ITERATE(struct compat_arpt_entry, entries, size, fn, ## args) - -#define COMPAT_ARPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ - XT_ENTRY_ITERATE_CONTINUE(struct compat_arpt_entry, entries, size, n, \ - fn, ## args) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _ARPTABLES_H */ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 364973b..5b20ae7 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -227,9 +227,11 @@ ipt_get_target(struct ipt_entry *e) #define IPT_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args) +#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args) +#endif /* * Main firewall chains definitions and global var's definitions. @@ -317,15 +319,6 @@ compat_ipt_get_target(struct compat_ipt_entry *e) #define COMPAT_IPT_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct compat_ipt_entry, e, fn, ## args) -/* fn returns 0 to continue iteration */ -#define COMPAT_IPT_ENTRY_ITERATE(entries, size, fn, args...) \ - XT_ENTRY_ITERATE(struct compat_ipt_entry, entries, size, fn, ## args) - -/* fn returns 0 to continue iteration */ -#define COMPAT_IPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ - XT_ENTRY_ITERATE_CONTINUE(struct compat_ipt_entry, entries, size, n, \ - fn, ## args) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IPTABLES_H */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8031eb4..8bb3f5b 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -284,9 +284,11 @@ ip6t_get_target(struct ip6t_entry *e) #define IP6T_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args) +#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args) +#endif /* * Main firewall chains definitions and global var's definitions. @@ -345,14 +347,6 @@ compat_ip6t_get_target(struct compat_ip6t_entry *e) #define COMPAT_IP6T_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct compat_ip6t_entry, e, fn, ## args) -/* fn returns 0 to continue iteration */ -#define COMPAT_IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ - XT_ENTRY_ITERATE(struct compat_ip6t_entry, entries, size, fn, ## args) - -#define COMPAT_IP6T_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ - XT_ENTRY_ITERATE_CONTINUE(struct compat_ip6t_entry, entries, size, n, \ - fn, ## args) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IP6_TABLES_H */ -- cgit v1.1 From dcea992aca82cb08b4674c4c783e325835408d1e Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 24 Feb 2010 18:34:48 +0100 Subject: netfilter: xtables: replace XT_MATCH_ITERATE macro The macro is replaced by a list.h-like foreach loop. This makes the code more inspectable. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 10 +++++++++- include/linux/netfilter_ipv4/ip_tables.h | 6 +----- include/linux/netfilter_ipv6/ip6_tables.h | 6 +----- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 9df3f5a..84c7c92 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -120,6 +120,7 @@ struct xt_counters_info { #define XT_INV_PROTO 0x40 /* Invert the sense of PROTO. */ +#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define XT_MATCH_ITERATE(type, e, fn, args...) \ ({ \ @@ -139,7 +140,6 @@ struct xt_counters_info { __ret; \ }) -#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define XT_ENTRY_ITERATE_CONTINUE(type, entries, size, n, fn, args...) \ ({ \ @@ -172,6 +172,14 @@ struct xt_counters_info { (pos) < (typeof(pos))((char *)(ehead) + (esize)); \ (pos) = (typeof(pos))((char *)(pos) + (pos)->next_offset)) +/* can only be xt_entry_match, so no use of typeof here */ +#define xt_ematch_foreach(pos, entry) \ + for ((pos) = (struct xt_entry_match *)entry->elems; \ + (pos) < (struct xt_entry_match *)((char *)(entry) + \ + (entry)->target_offset); \ + (pos) = (struct xt_entry_match *)((char *)(pos) + \ + (pos)->u.match_size)) + #ifdef __KERNEL__ #include diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 5b20ae7..704a7b6 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -223,11 +223,11 @@ ipt_get_target(struct ipt_entry *e) return (void *)e + e->target_offset; } +#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define IPT_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args) -#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args) @@ -315,10 +315,6 @@ compat_ipt_get_target(struct compat_ipt_entry *e) #define COMPAT_IPT_ALIGN(s) COMPAT_XT_ALIGN(s) -/* fn returns 0 to continue iteration */ -#define COMPAT_IPT_MATCH_ITERATE(e, fn, args...) \ - XT_MATCH_ITERATE(struct compat_ipt_entry, e, fn, ## args) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IPTABLES_H */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8bb3f5b..e5ba03d 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -280,11 +280,11 @@ ip6t_get_target(struct ip6t_entry *e) return (void *)e + e->target_offset; } +#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define IP6T_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args) -#ifndef __KERNEL__ /* fn returns 0 to continue iteration */ #define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args) @@ -343,10 +343,6 @@ compat_ip6t_get_target(struct compat_ip6t_entry *e) #define COMPAT_IP6T_ALIGN(s) COMPAT_XT_ALIGN(s) -/* fn returns 0 to continue iteration */ -#define COMPAT_IP6T_MATCH_ITERATE(e, fn, args...) \ - XT_MATCH_ITERATE(struct compat_ip6t_entry, e, fn, ## args) - #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IP6_TABLES_H */ -- cgit v1.1 From 52c793f24054f5dc30d228e37e0e19cc8313f086 Mon Sep 17 00:00:00 2001 From: Wolfgang Grandegger Date: Mon, 22 Feb 2010 22:21:17 +0000 Subject: can: netlink support for bus-error reporting and counters This patch makes the bus-error reporting configurable and allows to retrieve the CAN TX and RX bus error counters via netlink interface. I have added support for the SJA1000. The TX and RX bus error counters are also copied to the data fields 6..7 of error messages when state changes are reported. Signed-off-by: Wolfgang Grandegger Signed-off-by: David S. Miller --- include/linux/can/dev.h | 2 ++ include/linux/can/netlink.h | 18 ++++++++++++++---- 2 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c8c660a..6e5a7f0 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -47,6 +47,8 @@ struct can_priv { int (*do_set_mode)(struct net_device *dev, enum can_mode mode); int (*do_get_state)(const struct net_device *dev, enum can_state *state); + int (*do_get_berr_counter)(const struct net_device *dev, + struct can_berr_counter *bec); unsigned int echo_skb_max; struct sk_buff **echo_skb; diff --git a/include/linux/can/netlink.h b/include/linux/can/netlink.h index c818335..3250de9 100644 --- a/include/linux/can/netlink.h +++ b/include/linux/can/netlink.h @@ -70,6 +70,14 @@ enum can_state { }; /* + * CAN bus error counters + */ +struct can_berr_counter { + __u16 txerr; + __u16 rxerr; +}; + +/* * CAN controller mode */ struct can_ctrlmode { @@ -77,10 +85,11 @@ struct can_ctrlmode { __u32 flags; }; -#define CAN_CTRLMODE_LOOPBACK 0x1 /* Loopback mode */ -#define CAN_CTRLMODE_LISTENONLY 0x2 /* Listen-only mode */ -#define CAN_CTRLMODE_3_SAMPLES 0x4 /* Triple sampling mode */ -#define CAN_CTRLMODE_ONE_SHOT 0x8 /* One-Shot mode */ +#define CAN_CTRLMODE_LOOPBACK 0x01 /* Loopback mode */ +#define CAN_CTRLMODE_LISTENONLY 0x02 /* Listen-only mode */ +#define CAN_CTRLMODE_3_SAMPLES 0x04 /* Triple sampling mode */ +#define CAN_CTRLMODE_ONE_SHOT 0x08 /* One-Shot mode */ +#define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */ /* * CAN device statistics @@ -106,6 +115,7 @@ enum { IFLA_CAN_CTRLMODE, IFLA_CAN_RESTART_MS, IFLA_CAN_RESTART, + IFLA_CAN_BERR_COUNTER, __IFLA_CAN_MAX }; -- cgit v1.1 From 45bb00609022ecf1d97e083666c68c74d237b799 Mon Sep 17 00:00:00 2001 From: Ulrich Weber Date: Thu, 25 Feb 2010 23:28:58 +0000 Subject: ipv6: Remove IPV6_ADDR_RESERVED RFC 4291 section 2.4 states that all uncategorized addresses should be considered as Global Unicast. This will remove IPV6_ADDR_RESERVED completely and return IPV6_ADDR_UNICAST in ipv6_addr_type() instead. Signed-off-by: Ulrich Weber Signed-off-by: David S. Miller --- include/net/ipv6.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d067db1..e72fb10 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -73,7 +73,6 @@ #define IPV6_ADDR_SCOPE_MASK 0x00f0U #define IPV6_ADDR_MAPPED 0x1000U -#define IPV6_ADDR_RESERVED 0x2000U /* reserved address space */ /* * Addr scopes -- cgit v1.1 From c79c5ffdce14abb4de3878c5aa8c3c6e5093c69b Mon Sep 17 00:00:00 2001 From: Peter Waskiewicz Date: Fri, 26 Feb 2010 01:54:20 +0000 Subject: ethtool: Add n-tuple string length to drvinfo and return it The drvinfo struct should include the number of strings that get_rx_ntuple will return. It will be variable if an underlying driver implements its own get_rx_ntuple routine, so userspace needs to know how much data is coming. Signed-off-by: Peter P Waskiewicz Jr Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/ethtool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index cca1c3de..f7992a2 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -63,6 +63,7 @@ struct ethtool_drvinfo { char reserved2[12]; __u32 n_priv_flags; /* number of flags valid in ETHTOOL_GPFLAGS */ __u32 n_stats; /* number of u64's from ETHTOOL_GSTATS */ + __u32 n_ntuples; /* number of n-tuple filters from GSTRINGS */ __u32 testinfo_len; __u32 eedump_len; /* Size of data from ETHTOOL_GEEPROM (bytes) */ __u32 regdump_len; /* Size of data from ETHTOOL_GREGS (bytes) */ -- cgit v1.1 From 738b0343e73604750feb107e063c28b3ca36cb84 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 26 Feb 2010 05:12:02 -0800 Subject: Revert "ethtool: Add n-tuple string length to drvinfo and return it" This reverts commit c79c5ffdce14abb4de3878c5aa8c3c6e5093c69b. As Jeff points out we can't break the user visible interface like this, we need to add this into the reserved[] thing. Signed-off-by: David S. Miller --- include/linux/ethtool.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index f7992a2..cca1c3de 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -63,7 +63,6 @@ struct ethtool_drvinfo { char reserved2[12]; __u32 n_priv_flags; /* number of flags valid in ETHTOOL_GPFLAGS */ __u32 n_stats; /* number of u64's from ETHTOOL_GSTATS */ - __u32 n_ntuples; /* number of n-tuple filters from GSTRINGS */ __u32 testinfo_len; __u32 eedump_len; /* Size of data from ETHTOOL_GEEPROM (bytes) */ __u32 regdump_len; /* Size of data from ETHTOOL_GREGS (bytes) */ -- cgit v1.1 From 773c3e75d1fc7ea5058bfeab5d82bac5b85f8cd8 Mon Sep 17 00:00:00 2001 From: Sriramakrishnan Date: Fri, 26 Feb 2010 05:22:03 -0800 Subject: can: ti hecc module : add platform specific initialization callback. CAN module on AM3517 requires programming of IO expander as part of init sequence - to enable CAN PHY. Added platform specific callback to handle phy control(switch on /off). Signed-off-by: Sriramakrishnan Signed-off-by: David S. Miller --- include/linux/can/platform/ti_hecc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/can/platform/ti_hecc.h b/include/linux/can/platform/ti_hecc.h index 4688c7b..af17cb3 100644 --- a/include/linux/can/platform/ti_hecc.h +++ b/include/linux/can/platform/ti_hecc.h @@ -1,3 +1,6 @@ +#ifndef __CAN_PLATFORM_TI_HECC_H__ +#define __CAN_PLATFORM_TI_HECC_H__ + /* * TI HECC (High End CAN Controller) driver platform header * @@ -23,6 +26,7 @@ * @mbx_offset: Mailbox RAM offset * @int_line: Interrupt line to use - 0 or 1 * @version: version for future use + * @transceiver_switch: platform specific callback fn for transceiver control * * Platform data structure to get all platform specific settings. * this structure also accounts the fact that the IP may have different @@ -35,6 +39,6 @@ struct ti_hecc_platform_data { u32 mbx_offset; u32 int_line; u32 version; + void (*transceiver_switch) (int); }; - - +#endif -- cgit v1.1 From caf66e581172dc5032bb84841a91bc7b77ad9876 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Thu, 25 Feb 2010 12:02:45 -0500 Subject: netdevice.h: check for CONFIG_WLAN instead of CONFIG_WLAN_80211 In "wireless: remove WLAN_80211 and WLAN_PRE80211 from Kconfig" I inadvertantly missed a line in include/linux/netdevice.h. I thereby effectively reverted "net: Set LL_MAX_HEADER properly for wireless." by accident. :-( Now we should check there for CONFIG_WLAN instead. Signed-off-by: John W. Linville Reported-by: Christoph Egger Cc: stable@kernel.org --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a3fccc8..99914e6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -136,7 +136,7 @@ static inline bool dev_xmit_complete(int rc) * used. */ -#if defined(CONFIG_WLAN_80211) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) +#if defined(CONFIG_WLAN) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else -- cgit v1.1 From a2835763e130c343ace5320c20d33c281e7097b7 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 26 Feb 2010 06:34:51 +0000 Subject: rtnetlink: handle rtnl_link netlink notifications manually In order to support specifying device flags during device creation, we must be able to roll back device registration in case setting the flags fails without sending any notifications related to the device to userspace. This patch changes rollback_registered_many() and register_netdevice() to manually send netlink notifications for devices not handled by rtnl_link and allows to defer notifications for devices handled by rtnl_link until setup is complete. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7a2aea5..1bfda90 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -924,7 +924,12 @@ struct net_device { NETREG_UNREGISTERED, /* completed unregister todo */ NETREG_RELEASED, /* called free_netdev */ NETREG_DUMMY, /* dummy device for NAPI poll */ - } reg_state; + } reg_state:16; + + enum { + RTNL_LINK_INITIALIZED, + RTNL_LINK_INITIALIZING, + } rtnl_link_state:16; /* Called from unregister, can be used to call free_netdev */ void (*destructor)(struct net_device *dev); -- cgit v1.1 From bd38081160bb3d036db98472e537b6a7dd4da51a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 26 Feb 2010 06:34:53 +0000 Subject: dev: support deferring device flag change notifications Split dev_change_flags() into two functions: __dev_change_flags() to perform the actual changes and __dev_notify_flags() to invoke netdevice notifiers. This will be used by rtnl_link to defer netlink notifications until the device has been fully configured. This changes ordering of some operations, in particular: - netlink notifications are sent after all changes have been performed. As a side effect this surpresses one unnecessary netlink message when the IFF_UP and other flags are changed simultaneously. - The NETDEV_UP/NETDEV_DOWN and NETDEV_CHANGE notifiers are invoked after all changes have been performed. Their relative is unchanged. - net_dmaengine_put() is invoked before the NETDEV_DOWN notifier instead of afterwards. This should not make any difference since both RX and TX are already shut down at this point. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1bfda90..c79a88b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1587,7 +1587,9 @@ extern int dev_valid_name(const char *name); extern int dev_ioctl(struct net *net, unsigned int cmd, void __user *); extern int dev_ethtool(struct net *net, struct ifreq *); extern unsigned dev_get_flags(const struct net_device *); +extern int __dev_change_flags(struct net_device *, unsigned int flags); extern int dev_change_flags(struct net_device *, unsigned); +extern void __dev_notify_flags(struct net_device *, unsigned int old_flags); extern int dev_change_name(struct net_device *, const char *); extern int dev_set_alias(struct net_device *, const char *, size_t); extern int dev_change_net_namespace(struct net_device *, -- cgit v1.1 From 3729d5021257b283f7fce33d957893162ccb2c9d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 26 Feb 2010 06:34:54 +0000 Subject: rtnetlink: support specifying device flags on device creation commit e8469ed959c373c2ff9e6f488aa5a14971aebe1f Author: Patrick McHardy Date: Tue Feb 23 20:41:30 2010 +0100 Support specifying the initial device flags when creating a device though rtnl_link. Devices allocated by rtnl_create_link() are marked as INITIALIZING in order to surpress netlink registration notifications. To complete setup, rtnl_configure_link() must be called, which performs the device flag changes and invokes the deferred notifiers if everything went well. Two examples: # add macvlan to eth0 # $ ip link add link eth0 up allmulticast on type macvlan [LINK]11: macvlan0@eth0: mtu 1500 qdisc noqueue state UNKNOWN link/ether 26:f8:84:02:f9:2a brd ff:ff:ff:ff:ff:ff [ROUTE]ff00::/8 dev macvlan0 table local metric 256 mtu 1500 advmss 1440 hoplimit 0 [ROUTE]fe80::/64 dev macvlan0 proto kernel metric 256 mtu 1500 advmss 1440 hoplimit 0 [LINK]11: macvlan0@eth0: mtu 1500 link/ether 26:f8:84:02:f9:2a [ADDR]11: macvlan0 inet6 fe80::24f8:84ff:fe02:f92a/64 scope link valid_lft forever preferred_lft forever [ROUTE]local fe80::24f8:84ff:fe02:f92a via :: dev lo table local proto none metric 0 mtu 16436 advmss 16376 hoplimit 0 [ROUTE]default via fe80::215:e9ff:fef0:10f8 dev macvlan0 proto kernel metric 1024 mtu 1500 advmss 1440 hoplimit 0 [NEIGH]fe80::215:e9ff:fef0:10f8 dev macvlan0 lladdr 00:15:e9:f0:10:f8 router STALE [ROUTE]2001:6f8:974::/64 dev macvlan0 proto kernel metric 256 expires 0sec mtu 1500 advmss 1440 hoplimit 0 [PREFIX]prefix 2001:6f8:974::/64 dev macvlan0 onlink autoconf valid 14400 preferred 131084 [ADDR]11: macvlan0 inet6 2001:6f8:974:0:24f8:84ff:fe02:f92a/64 scope global dynamic valid_lft 86399sec preferred_lft 14399sec # add VLAN to eth1, eth1 is down # $ ip link add link eth1 up type vlan id 1000 RTNETLINK answers: Network is down Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 48d3efc..af60fd0 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -87,6 +87,8 @@ extern void rtnl_link_unregister(struct rtnl_link_ops *ops); extern struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); extern struct net_device *rtnl_create_link(struct net *src_net, struct net *net, char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]); +extern int rtnl_configure_link(struct net_device *dev, + const struct ifinfomsg *ifm); extern const struct nla_policy ifla_policy[IFLA_MAX+1]; #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) -- cgit v1.1 From da3f5cf1f8ebb0fab5c5fd09adb189166594ad6c Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 23 Feb 2010 11:45:51 +0000 Subject: skbuff: align sk_buff::cb to 64 bit and close some potential holes The alignment requirement for 64-bit load/store instructions on ARM is implementation defined. Some CPUs (such as Marvell Feroceon) do not generate an exception, if such an instruction is executed with an address that is not 64 bit aligned. In such a case, the Feroceon corrupts adjacent memory, which showed up in my tests as a crash in the rx path of ath9k that only occured with CONFIG_XFRM set. This crash happened, because the first field of the mac80211 rx status info in the cb is an u64, and changing it corrupted the skb->sp field. This patch also closes some potential pre-existing holes in the sk_buff struct surrounding the cb[] area. Signed-off-by: Felix Fietkau Cc: stable@kernel.org Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ba0f8e3..d266eee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -315,22 +315,23 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - struct sock *sk; ktime_t tstamp; + + struct sock *sk; struct net_device *dev; - unsigned long _skb_dst; -#ifdef CONFIG_XFRM - struct sec_path *sp; -#endif /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ - char cb[48]; + char cb[48] __aligned(8); + unsigned long _skb_dst; +#ifdef CONFIG_XFRM + struct sec_path *sp; +#endif unsigned int len, data_len; __u16 mac_len, -- cgit v1.1 From c13854cef4751000b968d4e8ac95796562d5b96f Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 8 Feb 2010 15:27:07 +0100 Subject: Bluetooth: Convert controller hdev->type to hdev->bus The hdev->type is misnamed and should be actually hdev->bus instead. So convert it now. Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 2 +- include/net/bluetooth/hci_core.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index ed3aea1..3350a66 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -43,7 +43,7 @@ #define HCI_NOTIFY_CONN_DEL 2 #define HCI_NOTIFY_VOICE_SETTING 3 -/* HCI device types */ +/* HCI bus types */ #define HCI_VIRTUAL 0 #define HCI_USB 1 #define HCI_PCCARD 2 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7b86094a..7e65885 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -70,7 +70,7 @@ struct hci_dev { char name[8]; unsigned long flags; __u16 id; - __u8 type; + __u8 bus; bdaddr_t bdaddr; __u8 dev_name[248]; __u8 dev_class[3]; -- cgit v1.1 From ca325f698996c1a0770a67f41e7dc97a007d8bc2 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 8 Feb 2010 16:22:31 +0100 Subject: Bluetooth: Convert inquiry cache to use debugfs instead of sysfs The output of the inquiry cache is only useful for debugging purposes and so move it into debugfs. Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7e65885..4c94c1e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -134,6 +134,8 @@ struct hci_dev { atomic_t promisc; + struct dentry *debugfs; + struct device *parent; struct device dev; -- cgit v1.1 From 943da25d95c7e8fd8c39dbf09e030f5da46f5d85 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 13 Feb 2010 02:28:41 +0100 Subject: Bluetooth: Add controller types for BR/EDR and 802.11 AMP With the Bluetooth 3.0 specification and the introduction of alternate MAC/PHY (AMP) support, it is required to differentiate between primary BR/EDR controllers and 802.11 AMP controllers. So introduce a special type inside HCI device for differentiation. For now all AMP controllers will be treated as raw devices until an AMP manager has been implemented. Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 4 ++++ include/net/bluetooth/hci_core.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 3350a66..fc0c502 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -52,6 +52,10 @@ #define HCI_PCI 5 #define HCI_SDIO 6 +/* HCI controller types */ +#define HCI_BREDR 0x00 +#define HCI_80211 0x01 + /* HCI device quirks */ enum { HCI_QUIRK_NO_RESET, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4c94c1e..ce3c99e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -71,6 +71,7 @@ struct hci_dev { unsigned long flags; __u16 id; __u8 bus; + __u8 dev_type; bdaddr_t bdaddr; __u8 dev_name[248]; __u8 dev_class[3]; -- cgit v1.1 From a2ce766238f72ff7337606c0bc96803c30c9e05c Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Fri, 26 Feb 2010 14:04:39 +0000 Subject: pci: Add PCI LRDT tag size and section size This patch adds a preprocessor constant to describe the PCI VPD large resource data type tag size and an inline function to extract the large resource section size from the large resource data type tag. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Acked-by: Jesse Barnes Signed-off-by: David S. Miller --- include/linux/pci.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index e2575f8..6f62a49 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1349,5 +1349,19 @@ static inline bool pci_is_pcie(struct pci_dev *dev) void pci_request_acs(void); + +#define PCI_VPD_LRDT_TAG_SIZE 3 + +/** + * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length + * @lrdt: Pointer to the beginning of the Large Resource Data Type tag + * + * Returns the extracted Large Resource Data Type length. + */ +static inline u16 pci_vpd_lrdt_size(const u8 *lrdt) +{ + return (u16)lrdt[1] + ((u16)lrdt[2] << 8); +} + #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.1 From 7ad506fa1adc2da3d394c562f09b8e1b3026c402 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Fri, 26 Feb 2010 14:04:40 +0000 Subject: pci: Add large and small resource data type code This patch introduces more VPD preprocessor definitions to identify some small and large resource data type item names. The patch then continues to correct how the tg3 and bnx2 drivers search for the "read-only data" large resource data type. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Acked-by: Jesse Barnes Signed-off-by: David S. Miller --- include/linux/pci.h | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 6f62a49..198d062 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1350,7 +1350,28 @@ static inline bool pci_is_pcie(struct pci_dev *dev) void pci_request_acs(void); -#define PCI_VPD_LRDT_TAG_SIZE 3 +#define PCI_VPD_LRDT 0x80 /* Large Resource Data Type */ +#define PCI_VPD_LRDT_ID(x) (x | PCI_VPD_LRDT) + +/* Large Resource Data Type Tag Item Names */ +#define PCI_VPD_LTIN_ID_STRING 0x02 /* Identifier String */ +#define PCI_VPD_LTIN_RO_DATA 0x10 /* Read-Only Data */ +#define PCI_VPD_LTIN_RW_DATA 0x11 /* Read-Write Data */ + +#define PCI_VPD_LRDT_ID_STRING PCI_VPD_LRDT_ID(PCI_VPD_LTIN_ID_STRING) +#define PCI_VPD_LRDT_RO_DATA PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RO_DATA) +#define PCI_VPD_LRDT_RW_DATA PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RW_DATA) + +/* Small Resource Data Type Tag Item Names */ +#define PCI_VPD_STIN_END 0x78 /* End */ + +#define PCI_VPD_SRDT_END PCI_VPD_STIN_END + +#define PCI_VPD_SRDT_TIN_MASK 0x78 +#define PCI_VPD_SRDT_LEN_MASK 0x07 + +#define PCI_VPD_LRDT_TAG_SIZE 3 +#define PCI_VPD_SRDT_TAG_SIZE 1 /** * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length @@ -1363,5 +1384,16 @@ static inline u16 pci_vpd_lrdt_size(const u8 *lrdt) return (u16)lrdt[1] + ((u16)lrdt[2] << 8); } +/** + * pci_vpd_srdt_size - Extracts the Small Resource Data Type length + * @lrdt: Pointer to the beginning of the Small Resource Data Type tag + * + * Returns the extracted Small Resource Data Type length. + */ +static inline u8 pci_vpd_srdt_size(const u8 *srdt) +{ + return (*srdt) & PCI_VPD_SRDT_LEN_MASK; +} + #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.1 From b55ac1b22690d2e5b02a61cf6d69c2d66969c79d Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Fri, 26 Feb 2010 14:04:41 +0000 Subject: pci: Add helper to find a VPD resource data type This patch adds the pci_vpd_find_tag() helper function to find VPD resource data types in a buffer. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Acked-by: Jesse Barnes Signed-off-by: David S. Miller --- include/linux/pci.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 198d062..e30ceea 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1395,5 +1395,17 @@ static inline u8 pci_vpd_srdt_size(const u8 *srdt) return (*srdt) & PCI_VPD_SRDT_LEN_MASK; } +/** + * pci_vpd_find_tag - Locates the Resource Data Type tag provided + * @buf: Pointer to buffered vpd data + * @off: The offset into the buffer at which to begin the search + * @len: The length of the vpd buffer + * @rdt: The Resource Data Type to search for + * + * Returns the index where the Resource Data Type was found or + * -ENOENT otherwise. + */ +int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt); + #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.1 From e1d5bdabb94da89bdb3c3f2ee105cf61fca88ec8 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Fri, 26 Feb 2010 14:04:42 +0000 Subject: pci: Add VPD information field helper functions This patch adds a preprocessor constant to describe the PCI VPD information field header size and an inline function to extract the size of the information field itself. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Acked-by: Jesse Barnes Signed-off-by: David S. Miller --- include/linux/pci.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index e30ceea..cfff32f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1373,6 +1373,8 @@ void pci_request_acs(void); #define PCI_VPD_LRDT_TAG_SIZE 3 #define PCI_VPD_SRDT_TAG_SIZE 1 +#define PCI_VPD_INFO_FLD_HDR_SIZE 3 + /** * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length * @lrdt: Pointer to the beginning of the Large Resource Data Type tag @@ -1396,6 +1398,17 @@ static inline u8 pci_vpd_srdt_size(const u8 *srdt) } /** + * pci_vpd_info_field_size - Extracts the information field length + * @lrdt: Pointer to the beginning of an information field header + * + * Returns the extracted information field length. + */ +static inline u8 pci_vpd_info_field_size(const u8 *info_field) +{ + return info_field[2]; +} + +/** * pci_vpd_find_tag - Locates the Resource Data Type tag provided * @buf: Pointer to buffered vpd data * @off: The offset into the buffer at which to begin the search -- cgit v1.1 From 4067a8541d397e9d6b443dd2ce0ecb78bfd991db Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Fri, 26 Feb 2010 14:04:43 +0000 Subject: pci: Add helper to search for VPD keywords This patch adds the pci_vpd_find_info_keyword() helper function to find information field keywords within read-only and read-write large resource data type sections. Signed-off-by: Matt Carlson Signed-off-by: Michael Chan Acked-by: Jesse Barnes Signed-off-by: David S. Miller --- include/linux/pci.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index cfff32f..1f4a521 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1375,6 +1375,10 @@ void pci_request_acs(void); #define PCI_VPD_INFO_FLD_HDR_SIZE 3 +#define PCI_VPD_RO_KEYWORD_PARTNO "PN" +#define PCI_VPD_RO_KEYWORD_MFR_ID "MN" +#define PCI_VPD_RO_KEYWORD_VENDOR0 "V0" + /** * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length * @lrdt: Pointer to the beginning of the Large Resource Data Type tag @@ -1420,5 +1424,18 @@ static inline u8 pci_vpd_info_field_size(const u8 *info_field) */ int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt); +/** + * pci_vpd_find_info_keyword - Locates an information field keyword in the VPD + * @buf: Pointer to buffered vpd data + * @off: The offset into the buffer at which to begin the search + * @len: The length of the buffer area, relative to off, in which to search + * @kw: The keyword to search for + * + * Returns the index where the information field keyword was found or + * -ENOENT otherwise. + */ +int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, + unsigned int len, const char *kw); + #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.1 From 4ab408dea0f0dba4dec0555f4f35b7ae703f5e91 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 1 Mar 2010 03:09:26 +0000 Subject: net: fix protocol sk_buff field Commit e992cd9b72a18 (kmemcheck: make bitfield annotations truly no-ops when disabled) allows us to revert a workaround we did in the past to not add holes in sk_buff structure. This patch partially reverts commit 14d18a81b5171 (net: fix kmemcheck annotations) so that sparse doesnt complain: include/linux/skbuff.h:357:41: error: invalid bitfield specifier for type restricted __be16. Reported-by: Stefan Richter Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d266eee..03f816a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -355,8 +355,8 @@ struct sk_buff { ipvs_property:1, peeked:1, nf_trace:1; - __be16 protocol:16; kmemcheck_bitfield_end(flags1); + __be16 protocol; void (*destructor)(struct sk_buff *skb); #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -- cgit v1.1